High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_0728_SECOND				87.71 35	95.34 1	71.43 60	93.49 10	94.23 7					97.49 4	89.08 22	96.41 12	94.21 68

SED-MVS		90.08 2	90.85 2	87.77 28	95.30 2	70.98 71	93.57 8	94.06 15	77.24 61	93.10 1	95.72 8	82.99 1	97.44 7	89.07 25	96.63 4	94.88 16

IU-MVS					95.30 2	71.25 64		92.95 60	66.81 322	92.39 6				88.94 28	96.63 4	94.85 21

test_241102_ONE					95.30 2	70.98 71		94.06 15	77.17 64	93.10 1	95.39 16	82.99 1	97.27 15

DVP-MVS		89.60 3	90.35 3	87.33 45	95.27 5	71.25 64	93.49 10	92.73 69	77.33 58	92.12 12	95.78 4	80.98 11	97.40 9	89.08 22	96.41 12	93.33 121
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					95.27 5	71.25 64	93.60 7	94.11 11	77.33 58	92.81 3	95.79 3	80.98 11

test_one_0601					95.07 7	71.46 59		94.14 10	78.27 41	92.05 14	95.74 6	80.83 13

test_part2					95.06 8	72.65 32				91.80 16

HPM-MVS++		89.02 11	89.15 12	88.63 5	95.01 9	76.03 1	92.38 32	92.85 64	80.26 11	87.78 48	94.27 47	75.89 22	96.81 27	87.45 47	96.44 9	93.05 140

FOURS1					95.00 10	72.39 41	95.06 1	93.84 20	74.49 151	91.30 18

DPE-MVS		89.48 6	89.98 5	88.01 16	94.80 11	72.69 31	91.59 51	94.10 13	75.90 105	92.29 7	95.66 10	81.67 6	97.38 14	87.44 48	96.34 15	93.95 83
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CNVR-MVS		88.93 13	89.13 13	88.33 8	94.77 12	73.82 8	90.51 70	93.00 51	80.90 7	88.06 43	94.06 59	76.43 19	96.84 25	88.48 36	95.99 18	94.34 62

ACMMPR		87.44 29	87.23 36	88.08 15	94.64 13	73.59 12	93.04 17	93.20 39	76.78 77	84.66 89	94.52 32	68.81 109	96.65 34	84.53 72	94.90 45	94.00 80

region2R		87.42 31	87.20 37	88.09 14	94.63 14	73.55 13	93.03 19	93.12 45	76.73 80	84.45 94	94.52 32	69.09 103	96.70 31	84.37 74	94.83 49	94.03 78

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 61	82.45 3	96.87 24	83.77 82	96.48 8	94.88 16

HFP-MVS		87.58 26	87.47 31	87.94 19	94.58 16	73.54 15	93.04 17	93.24 38	76.78 77	84.91 82	94.44 39	70.78 75	96.61 36	84.53 72	94.89 46	93.66 100

MED-MVS test				87.86 26	94.57 17	71.43 60	93.28 12	94.36 3	75.24 124	92.25 9	95.03 20		97.39 11	88.15 39	95.96 19	94.75 30

MED-MVS		89.59 4	90.16 4	87.86 26	94.57 17	71.43 60	93.28 12	94.36 3	76.30 96	92.25 9	95.03 20	81.59 7	97.39 11	88.15 39	95.96 19	94.75 30

TestfortrainingZip a		89.27 7	89.82 7	87.60 39	94.57 17	70.90 77	93.28 12	94.36 3	75.24 124	92.25 9	95.03 20	81.59 7	97.39 11	86.12 57	95.96 19	94.52 52

ME-MVS		88.98 12	89.39 9	87.75 30	94.54 20	71.43 60	91.61 49	94.25 6	76.30 96	90.62 21	95.03 20	78.06 16	97.07 20	88.15 39	95.96 19	94.75 30

MCST-MVS		87.37 34	87.25 35	87.73 31	94.53 21	72.46 40	89.82 88	93.82 21	73.07 194	84.86 85	92.89 95	76.22 20	96.33 45	84.89 66	95.13 40	94.40 58

APDe-MVS		89.15 9	89.63 8	87.73 31	94.49 22	71.69 54	93.83 4	93.96 18	75.70 112	91.06 19	96.03 1	76.84 17	97.03 21	89.09 21	95.65 31	94.47 55
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS Recon		83.11 130	82.09 141	86.15 70	94.44 23	70.92 76	88.79 135	92.20 101	70.53 249	79.17 193	91.03 159	64.12 166	96.03 55	68.39 267	90.14 125	91.50 204

XVS		87.18 37	86.91 44	88.00 17	94.42 24	73.33 19	92.78 23	92.99 54	79.14 26	83.67 113	94.17 53	67.45 127	96.60 37	83.06 87	94.50 57	94.07 76

X-MVStestdata		80.37 197	77.83 237	88.00 17	94.42 24	73.33 19	92.78 23	92.99 54	79.14 26	83.67 113	12.47 484	67.45 127	96.60 37	83.06 87	94.50 57	94.07 76

mPP-MVS		86.67 46	86.32 53	87.72 33	94.41 26	73.55 13	92.74 25	92.22 98	76.87 74	82.81 134	94.25 49	66.44 140	96.24 49	82.88 92	94.28 64	93.38 117

NCCC		88.06 18	88.01 22	88.24 11	94.41 26	73.62 11	91.22 62	92.83 65	81.50 5	85.79 72	93.47 80	73.02 45	97.00 22	84.90 64	94.94 44	94.10 74

ZNCC-MVS		87.94 22	87.85 24	88.20 12	94.39 28	73.33 19	93.03 19	93.81 22	76.81 75	85.24 77	94.32 44	71.76 60	96.93 23	85.53 61	95.79 26	94.32 64

ZD-MVS					94.38 29	72.22 46		92.67 72	70.98 237	87.75 50	94.07 58	74.01 36	96.70 31	84.66 70	94.84 48

MP-MVS		87.71 23	87.64 26	87.93 21	94.36 30	73.88 6	92.71 27	92.65 75	77.57 49	83.84 109	94.40 41	72.24 54	96.28 47	85.65 59	95.30 39	93.62 107
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 31	71.25 64	95.06 1	94.23 7	78.38 38	92.78 4	95.74 6	82.45 3	97.49 4	89.42 19	96.68 2	94.95 12

MSC_two_6792asdad				89.16 1	94.34 31	75.53 2		92.99 54					97.53 2	89.67 15	96.44 9	94.41 56

No_MVS				89.16 1	94.34 31	75.53 2		92.99 54					97.53 2	89.67 15	96.44 9	94.41 56

MSP-MVS		89.51 5	89.91 6	88.30 10	94.28 34	73.46 17	92.90 21	94.11 11	80.27 10	91.35 17	94.16 54	78.35 15	96.77 28	89.59 17	94.22 66	94.67 36
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
SMA-MVS		89.08 10	89.23 10	88.61 6	94.25 35	73.73 9	92.40 29	93.63 26	74.77 145	92.29 7	95.97 2	74.28 33	97.24 16	88.58 33	96.91 1	94.87 18
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
APD-MVS		87.44 29	87.52 30	87.19 47	94.24 36	72.39 41	91.86 45	92.83 65	73.01 196	88.58 34	94.52 32	73.36 38	96.49 42	84.26 75	95.01 41	92.70 154
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PGM-MVS		86.68 45	86.27 55	87.90 22	94.22 37	73.38 18	90.22 81	93.04 46	75.53 115	83.86 108	94.42 40	67.87 124	96.64 35	82.70 98	94.57 56	93.66 100

CP-MVS		87.11 38	86.92 43	87.68 37	94.20 38	73.86 7	93.98 3	92.82 68	76.62 83	83.68 112	94.46 36	67.93 122	95.95 62	84.20 78	94.39 61	93.23 124

MTAPA		87.23 36	87.00 39	87.90 22	94.18 39	74.25 5	86.58 226	92.02 109	79.45 22	85.88 70	94.80 27	68.07 120	96.21 50	86.69 52	95.34 36	93.23 124

GST-MVS		87.42 31	87.26 34	87.89 24	94.12 40	72.97 24	92.39 31	93.43 33	76.89 73	84.68 86	93.99 65	70.67 77	96.82 26	84.18 79	95.01 41	93.90 86

SR-MVS		86.73 43	86.67 48	86.91 55	94.11 41	72.11 49	92.37 33	92.56 80	74.50 150	86.84 64	94.65 31	67.31 129	95.77 64	84.80 68	92.85 78	92.84 152

114514_t		80.68 184	79.51 195	84.20 150	94.09 42	67.27 176	89.64 96	91.11 150	58.75 420	74.08 315	90.72 166	58.10 249	95.04 99	69.70 252	89.42 140	90.30 252

HPM-MVS		87.11 38	86.98 41	87.50 43	93.88 43	72.16 47	92.19 38	93.33 36	76.07 102	83.81 110	93.95 68	69.77 92	96.01 58	85.15 62	94.66 51	94.32 64
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
save fliter					93.80 44	72.35 44	90.47 74	91.17 147	74.31 156

ACMMP_NAP		88.05 20	88.08 21	87.94 19	93.70 45	73.05 22	90.86 65	93.59 28	76.27 98	88.14 41	95.09 19	71.06 72	96.67 33	87.67 44	96.37 14	94.09 75

HPM-MVS_fast		85.35 79	84.95 85	86.57 63	93.69 46	70.58 84	92.15 40	91.62 132	73.89 168	82.67 136	94.09 57	62.60 186	95.54 70	80.93 111	92.93 77	93.57 110

TSAR-MVS + MP.		88.02 21	88.11 20	87.72 33	93.68 47	72.13 48	91.41 58	92.35 87	74.62 149	88.90 32	93.85 71	75.75 23	96.00 59	87.80 43	94.63 54	95.04 10
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MP-MVS-pluss		87.67 25	87.72 25	87.54 40	93.64 48	72.04 50	89.80 90	93.50 30	75.17 132	86.34 68	95.29 17	70.86 74	96.00 59	88.78 31	96.04 16	94.58 45
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP		85.89 65	85.39 76	87.38 44	93.59 49	72.63 33	92.74 25	93.18 44	76.78 77	80.73 170	93.82 72	64.33 164	96.29 46	82.67 99	90.69 116	93.23 124
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
DeepC-MVS_fast	79.65 3	86.91 41	86.62 50	87.76 29	93.52 50	72.37 43	91.26 59	93.04 46	76.62 83	84.22 100	93.36 84	71.44 66	96.76 29	80.82 113	95.33 37	94.16 70
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CDPH-MVS		85.76 68	85.29 81	87.17 48	93.49 51	71.08 69	88.58 147	92.42 85	68.32 309	84.61 91	93.48 78	72.32 52	96.15 53	79.00 138	95.43 34	94.28 66

DP-MVS		76.78 285	74.57 304	83.42 190	93.29 52	69.46 104	88.55 149	83.70 345	63.98 368	70.20 360	88.89 224	54.01 290	94.80 111	46.66 434	81.88 279	86.01 383

CPTT-MVS		83.73 108	83.33 116	84.92 111	93.28 53	70.86 78	92.09 41	90.38 172	68.75 301	79.57 185	92.83 97	60.60 230	93.04 211	80.92 112	91.56 102	90.86 226

reproduce-ours		87.47 27	87.61 27	87.07 50	93.27 54	71.60 55	91.56 54	93.19 40	74.98 136	88.96 30	95.54 12	71.20 70	96.54 40	86.28 54	93.49 71	93.06 138

our_new_method		87.47 27	87.61 27	87.07 50	93.27 54	71.60 55	91.56 54	93.19 40	74.98 136	88.96 30	95.54 12	71.20 70	96.54 40	86.28 54	93.49 71	93.06 138

NormalMVS		86.29 54	85.88 65	87.52 41	93.26 56	72.47 38	91.65 47	92.19 103	79.31 24	84.39 96	92.18 111	64.64 162	95.53 71	80.70 116	94.65 52	94.56 49

lecture		88.09 17	88.59 16	86.58 62	93.26 56	69.77 96	93.70 6	94.16 9	77.13 66	89.76 26	95.52 14	72.26 53	96.27 48	86.87 50	94.65 52	93.70 99

TEST9					93.26 56	72.96 25	88.75 138	91.89 117	68.44 307	85.00 80	93.10 88	74.36 32	95.41 80

train_agg		86.43 49	86.20 56	87.13 49	93.26 56	72.96 25	88.75 138	91.89 117	68.69 302	85.00 80	93.10 88	74.43 30	95.41 80	84.97 63	95.71 29	93.02 142

test_8					93.13 60	72.57 35	88.68 143	91.84 121	68.69 302	84.87 84	93.10 88	74.43 30	95.16 90

新几何1				83.42 190	93.13 60	70.71 80		85.48 322	57.43 431	81.80 148	91.98 118	63.28 172	92.27 244	64.60 298	92.99 76	87.27 353

reproduce_model		87.28 35	87.39 33	86.95 54	93.10 62	71.24 68	91.60 50	93.19 40	74.69 146	88.80 33	95.61 11	70.29 81	96.44 43	86.20 56	93.08 75	93.16 131

AdaColmap		80.58 191	79.42 197	84.06 162	93.09 63	68.91 115	89.36 110	88.97 238	69.27 284	75.70 274	89.69 196	57.20 261	95.77 64	63.06 310	88.41 160	87.50 346

SR-MVS-dyc-post		85.77 67	85.61 72	86.23 66	93.06 64	70.63 82	91.88 43	92.27 91	73.53 179	85.69 73	94.45 37	65.00 160	95.56 68	82.75 94	91.87 95	92.50 164

RE-MVS-def			85.48 75		93.06 64	70.63 82	91.88 43	92.27 91	73.53 179	85.69 73	94.45 37	63.87 168		82.75 94	91.87 95	92.50 164

原ACMM1				84.35 137	93.01 66	68.79 117		92.44 82	63.96 369	81.09 161	91.57 137	66.06 148	95.45 75	67.19 277	94.82 50	88.81 312

CSCG		86.41 51	86.19 58	87.07 50	92.91 67	72.48 37	90.81 66	93.56 29	73.95 165	83.16 125	91.07 156	75.94 21	95.19 89	79.94 124	94.38 62	93.55 112

agg_prior					92.85 68	71.94 52		91.78 125		84.41 95			94.93 101

9.14			88.26 19		92.84 69		91.52 56	94.75 1	73.93 167	88.57 35	94.67 30	75.57 25	95.79 63	86.77 51	95.76 27

SF-MVS		88.46 15	88.74 15	87.64 38	92.78 70	71.95 51	92.40 29	94.74 2	75.71 110	89.16 29	95.10 18	75.65 24	96.19 51	87.07 49	96.01 17	94.79 23

MG-MVS		83.41 119	83.45 112	83.28 195	92.74 71	62.28 306	88.17 164	89.50 206	75.22 126	81.49 154	92.74 103	66.75 134	95.11 94	72.85 214	91.58 101	92.45 168

APD-MVS_3200maxsize		85.97 61	85.88 65	86.22 67	92.69 72	69.53 99	91.93 42	92.99 54	73.54 178	85.94 69	94.51 35	65.80 152	95.61 67	83.04 89	92.51 83	93.53 114

test12				86.80 58	92.63 73	70.70 81		91.79 124		82.71 135		71.67 63	96.16 52		94.50 57	93.54 113

test_prior				86.33 64	92.61 74	69.59 98		92.97 59					95.48 74			93.91 84

SD-MVS		88.06 18	88.50 18	86.71 60	92.60 75	72.71 29	91.81 46	93.19 40	77.87 42	90.32 23	94.00 63	74.83 26	93.78 158	87.63 45	94.27 65	93.65 104
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
PAPM_NR		83.02 131	82.41 132	84.82 115	92.47 76	66.37 192	87.93 174	91.80 123	73.82 169	77.32 235	90.66 169	67.90 123	94.90 104	70.37 242	89.48 139	93.19 130

DeepPCF-MVS	80.84 1	88.10 16	88.56 17	86.73 59	92.24 77	69.03 110	89.57 99	93.39 35	77.53 53	89.79 25	94.12 56	78.98 14	96.58 39	85.66 58	95.72 28	94.58 45

SteuartSystems-ACMMP		88.72 14	88.86 14	88.32 9	92.14 78	72.96 25	93.73 5	93.67 25	80.19 12	88.10 42	94.80 27	73.76 37	97.11 18	87.51 46	95.82 25	94.90 15
Skip Steuart: Steuart Systems R&D Blog.
UA-Net		85.08 84	84.96 84	85.45 89	92.07 79	68.07 145	89.78 91	90.86 158	82.48 2	84.60 92	93.20 87	69.35 97	95.22 88	71.39 232	90.88 114	93.07 137

旧先验1					91.96 80	65.79 208		86.37 309			93.08 92	69.31 99			92.74 80	88.74 317

MSLP-MVS++		85.43 75	85.76 69	84.45 130	91.93 81	70.24 85	90.71 67	92.86 63	77.46 55	84.22 100	92.81 99	67.16 131	92.94 213	80.36 119	94.35 63	90.16 256

LFMVS		81.82 152	81.23 152	83.57 186	91.89 82	63.43 281	89.84 87	81.85 376	77.04 70	83.21 121	93.10 88	52.26 305	93.43 184	71.98 227	89.95 130	93.85 88

PLC	70.83 11	78.05 256	76.37 278	83.08 207	91.88 83	67.80 156	88.19 163	89.46 207	64.33 361	69.87 369	88.38 239	53.66 292	93.58 166	58.86 354	82.73 268	87.86 337
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
dcpmvs_2		85.63 70	86.15 60	84.06 162	91.71 84	64.94 236	86.47 230	91.87 119	73.63 174	86.60 67	93.02 93	76.57 18	91.87 261	83.36 84	92.15 90	95.35 3

MVS_111021_HR		85.14 82	84.75 87	86.32 65	91.65 85	72.70 30	85.98 248	90.33 176	76.11 101	82.08 143	91.61 136	71.36 68	94.17 139	81.02 110	92.58 82	92.08 187

test222					91.50 86	68.26 137	84.16 305	83.20 357	54.63 442	79.74 182	91.63 133	58.97 242			91.42 103	86.77 368

SymmetryMVS		85.38 78	84.81 86	87.07 50	91.47 87	72.47 38	91.65 47	88.06 265	79.31 24	84.39 96	92.18 111	64.64 162	95.53 71	80.70 116	90.91 113	93.21 127

TSAR-MVS + GP.		85.71 69	85.33 78	86.84 56	91.34 88	72.50 36	89.07 124	87.28 286	76.41 88	85.80 71	90.22 184	74.15 35	95.37 85	81.82 103	91.88 94	92.65 158

MAR-MVS		81.84 151	80.70 161	85.27 94	91.32 89	71.53 58	89.82 88	90.92 154	69.77 273	78.50 206	86.21 304	62.36 192	94.52 123	65.36 291	92.05 93	89.77 280
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
balanced_conf03		86.78 42	86.99 40	86.15 70	91.24 90	67.61 162	90.51 70	92.90 61	77.26 60	87.44 56	91.63 133	71.27 69	96.06 54	85.62 60	95.01 41	94.78 24

DeepC-MVS	79.81 2	87.08 40	86.88 45	87.69 36	91.16 91	72.32 45	90.31 79	93.94 19	77.12 67	82.82 133	94.23 50	72.13 56	97.09 19	84.83 67	95.37 35	93.65 104
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVSMamba_PlusPlus		85.99 59	85.96 64	86.05 73	91.09 92	67.64 161	89.63 97	92.65 75	72.89 199	84.64 90	91.71 128	71.85 58	96.03 55	84.77 69	94.45 60	94.49 54

3Dnovator+	77.84 4	85.48 73	84.47 92	88.51 7	91.08 93	73.49 16	93.18 16	93.78 23	80.79 8	76.66 252	93.37 83	60.40 234	96.75 30	77.20 160	93.73 70	95.29 6

Anonymous202405211		78.25 248	77.01 259	81.99 247	91.03 94	60.67 330	84.77 282	83.90 343	70.65 248	80.00 180	91.20 151	41.08 417	91.43 284	65.21 292	85.26 223	93.85 88

SPE-MVS-test		86.29 54	86.48 51	85.71 80	91.02 95	67.21 180	92.36 34	93.78 23	78.97 33	83.51 118	91.20 151	70.65 78	95.15 91	81.96 102	94.89 46	94.77 25

VDD-MVS		83.01 132	82.36 134	84.96 107	91.02 95	66.40 191	88.91 128	88.11 261	77.57 49	84.39 96	93.29 85	52.19 306	93.91 152	77.05 163	88.70 154	94.57 47

API-MVS		81.99 148	81.23 152	84.26 148	90.94 97	70.18 91	91.10 63	89.32 216	71.51 222	78.66 202	88.28 242	65.26 155	95.10 97	64.74 297	91.23 107	87.51 345

testdata				79.97 298	90.90 98	64.21 256		84.71 330	59.27 413	85.40 75	92.91 94	62.02 199	89.08 339	68.95 260	91.37 105	86.63 373

PHI-MVS		86.43 49	86.17 59	87.24 46	90.88 99	70.96 73	92.27 37	94.07 14	72.45 202	85.22 78	91.90 120	69.47 95	96.42 44	83.28 86	95.94 23	94.35 61

VNet		82.21 143	82.41 132	81.62 253	90.82 100	60.93 324	84.47 291	89.78 193	76.36 94	84.07 104	91.88 121	64.71 161	90.26 315	70.68 239	88.89 148	93.66 100

PVSNet_Blended_VisFu		82.62 137	81.83 147	84.96 107	90.80 101	69.76 97	88.74 140	91.70 128	69.39 280	78.96 195	88.46 237	65.47 154	94.87 107	74.42 197	88.57 155	90.24 254

MM		89.16 8	89.23 10	88.97 4	90.79 102	73.65 10	92.66 28	91.17 147	86.57 1	87.39 57	94.97 25	71.70 62	97.68 1	92.19 1	95.63 32	95.57 1

CS-MVS		86.69 44	86.95 42	85.90 78	90.76 103	67.57 164	92.83 22	93.30 37	79.67 19	84.57 93	92.27 107	71.47 65	95.02 100	84.24 77	93.46 73	95.13 9

Anonymous20240529		80.19 203	78.89 212	84.10 153	90.60 104	64.75 243	88.95 127	90.90 155	65.97 339	80.59 172	91.17 153	49.97 340	93.73 164	69.16 258	82.70 270	93.81 92

h-mvs33		83.15 127	82.19 138	86.02 76	90.56 105	70.85 79	88.15 166	89.16 227	76.02 103	84.67 87	91.39 144	61.54 207	95.50 73	82.71 96	75.48 364	91.72 198

Anonymous20231211		78.97 232	77.69 245	82.81 222	90.54 106	64.29 255	90.11 83	91.51 137	65.01 352	76.16 269	88.13 251	50.56 332	93.03 212	69.68 253	77.56 333	91.11 215

LS3D		76.95 282	74.82 301	83.37 193	90.45 107	67.36 172	89.15 120	86.94 296	61.87 393	69.52 372	90.61 172	51.71 319	94.53 122	46.38 437	86.71 195	88.21 331

VDDNet		81.52 162	80.67 162	84.05 165	90.44 108	64.13 258	89.73 93	85.91 316	71.11 231	83.18 124	93.48 78	50.54 333	93.49 178	73.40 208	88.25 163	94.54 51

testing3-2		75.12 315	75.19 297	74.91 380	90.40 109	45.09 463	80.29 371	78.42 415	78.37 40	76.54 257	87.75 256	44.36 394	87.28 367	57.04 373	83.49 256	92.37 170

CNLPA		78.08 254	76.79 266	81.97 248	90.40 109	71.07 70	87.59 184	84.55 333	66.03 338	72.38 339	89.64 199	57.56 255	86.04 379	59.61 345	83.35 259	88.79 313

PAPR		81.66 157	80.89 159	83.99 172	90.27 111	64.00 259	86.76 220	91.77 126	68.84 300	77.13 245	89.50 203	67.63 125	94.88 106	67.55 272	88.52 157	93.09 136

Vis-MVSNet		83.46 118	82.80 125	85.43 90	90.25 112	68.74 121	90.30 80	90.13 184	76.33 95	80.87 167	92.89 95	61.00 221	94.20 136	72.45 224	90.97 111	93.35 120
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DPM-MVS		84.93 86	84.29 93	86.84 56	90.20 113	73.04 23	87.12 202	93.04 46	69.80 271	82.85 132	91.22 150	73.06 44	96.02 57	76.72 172	94.63 54	91.46 208

EPP-MVSNet		83.40 120	83.02 120	84.57 123	90.13 114	64.47 251	92.32 35	90.73 162	74.45 153	79.35 191	91.10 154	69.05 106	95.12 92	72.78 215	87.22 184	94.13 72

CANet		86.45 48	86.10 61	87.51 42	90.09 115	70.94 75	89.70 94	92.59 79	81.78 4	81.32 156	91.43 143	70.34 79	97.23 17	84.26 75	93.36 74	94.37 60

test2506		77.30 276	76.49 273	79.74 304	90.08 116	52.02 427	87.86 178	63.10 470	74.88 141	80.16 179	92.79 100	38.29 433	92.35 241	68.74 263	92.50 84	94.86 19

ECVR-MVS		79.61 210	79.26 203	80.67 281	90.08 116	54.69 409	87.89 176	77.44 423	74.88 141	80.27 176	92.79 100	48.96 356	92.45 235	68.55 264	92.50 84	94.86 19

HQP_MVS		83.64 112	83.14 117	85.14 98	90.08 116	68.71 123	91.25 60	92.44 82	79.12 28	78.92 197	91.00 161	60.42 232	95.38 82	78.71 142	86.32 200	91.33 209

plane_prior7					90.08 116	68.51 131

patch_mono-2		83.65 111	84.54 89	80.99 273	90.06 120	65.83 205	84.21 302	88.74 250	71.60 220	85.01 79	92.44 105	74.51 29	83.50 404	82.15 101	92.15 90	93.64 106

test1111		79.43 217	79.18 206	80.15 295	89.99 121	53.31 422	87.33 197	77.05 427	75.04 134	80.23 178	92.77 102	48.97 355	92.33 243	68.87 261	92.40 86	94.81 22

CHOSEN 1792x2688		77.63 270	75.69 283	83.44 189	89.98 122	68.58 129	78.70 394	87.50 281	56.38 436	75.80 273	86.84 281	58.67 245	91.40 285	61.58 329	85.75 216	90.34 249

IS-MVSNet		83.15 127	82.81 124	84.18 151	89.94 123	63.30 283	91.59 51	88.46 258	79.04 30	79.49 186	92.16 113	65.10 157	94.28 130	67.71 270	91.86 97	94.95 12

plane_prior1					89.90 124

sasdasda		85.91 63	85.87 67	86.04 74	89.84 125	69.44 105	90.45 76	93.00 51	76.70 81	88.01 45	91.23 147	73.28 40	93.91 152	81.50 105	88.80 150	94.77 25

canonicalmvs		85.91 63	85.87 67	86.04 74	89.84 125	69.44 105	90.45 76	93.00 51	76.70 81	88.01 45	91.23 147	73.28 40	93.91 152	81.50 105	88.80 150	94.77 25

plane_prior6					89.84 125	68.70 125						60.42 232

mvsmamba		80.60 188	79.38 198	84.27 146	89.74 128	67.24 178	87.47 187	86.95 295	70.02 264	75.38 284	88.93 222	51.24 324	92.56 229	75.47 188	89.22 143	93.00 144

NP-MVS					89.62 129	68.32 135					90.24 182

EIA-MVS		83.31 125	82.80 125	84.82 115	89.59 130	65.59 213	88.21 162	92.68 71	74.66 148	78.96 195	86.42 300	69.06 105	95.26 87	75.54 186	90.09 126	93.62 107

HyFIR lowres test		77.53 271	75.40 291	83.94 175	89.59 130	66.62 188	80.36 369	88.64 255	56.29 437	76.45 258	85.17 330	57.64 254	93.28 188	61.34 332	83.10 264	91.91 190

TAPA-MVS	73.13 9	79.15 226	77.94 232	82.79 226	89.59 130	62.99 293	88.16 165	91.51 137	65.77 340	77.14 244	91.09 155	60.91 222	93.21 195	50.26 415	87.05 188	92.17 184
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thres100view900		76.50 289	75.55 288	79.33 313	89.52 133	56.99 377	85.83 255	83.23 354	73.94 166	76.32 262	87.12 277	51.89 315	91.95 256	48.33 425	83.75 248	89.07 295

GeoE		81.71 154	81.01 157	83.80 180	89.51 134	64.45 252	88.97 126	88.73 251	71.27 228	78.63 203	89.76 195	66.32 142	93.20 198	69.89 250	86.02 208	93.74 97

alignmvs		85.48 73	85.32 79	85.96 77	89.51 134	69.47 102	89.74 92	92.47 81	76.17 100	87.73 52	91.46 142	70.32 80	93.78 158	81.51 104	88.95 147	94.63 42

PS-MVSNAJ		81.69 155	81.02 156	83.70 181	89.51 134	68.21 142	84.28 301	90.09 185	70.79 241	81.26 160	85.62 318	63.15 178	94.29 129	75.62 184	88.87 149	88.59 321

fmvsm_s_conf0.5_n_9		87.39 33	87.95 23	85.70 81	89.48 137	67.88 153	88.59 146	89.05 232	80.19 12	90.70 20	95.40 15	74.56 28	93.92 151	91.54 2	92.07 92	95.31 5

MGCNet		87.69 24	87.55 29	88.12 13	89.45 138	71.76 53	91.47 57	89.54 204	82.14 3	86.65 66	94.28 46	68.28 118	97.46 6	90.81 6	95.31 38	95.15 8

MGCFI-Net		85.06 85	85.51 74	83.70 181	89.42 139	63.01 289	89.43 104	92.62 78	76.43 87	87.53 53	91.34 145	72.82 49	93.42 185	81.28 108	88.74 153	94.66 39

ACMP	74.13 6	81.51 164	80.57 164	84.36 136	89.42 139	68.69 126	89.97 85	91.50 140	74.46 152	75.04 300	90.41 176	53.82 291	94.54 121	77.56 156	82.91 265	89.86 276
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
thres600view7		76.50 289	75.44 289	79.68 306	89.40 141	57.16 374	85.53 264	83.23 354	73.79 170	76.26 263	87.09 278	51.89 315	91.89 259	48.05 430	83.72 251	90.00 268

ETV-MVS		84.90 88	84.67 88	85.59 86	89.39 142	68.66 127	88.74 140	92.64 77	79.97 16	84.10 103	85.71 313	69.32 98	95.38 82	80.82 113	91.37 105	92.72 153

BH-RMVSNet		79.61 210	78.44 220	83.14 203	89.38 143	65.93 202	84.95 279	87.15 292	73.56 177	78.19 215	89.79 194	56.67 266	93.36 186	59.53 346	86.74 194	90.13 258

HQP-NCC					89.33 144		89.17 116		76.41 88	77.23 238

ACMP_Plane					89.33 144		89.17 116		76.41 88	77.23 238

HQP-MVS		82.61 138	82.02 143	84.37 135	89.33 144	66.98 183	89.17 116	92.19 103	76.41 88	77.23 238	90.23 183	60.17 235	95.11 94	77.47 157	85.99 209	91.03 219

EC-MVSNet		86.01 58	86.38 52	84.91 112	89.31 147	66.27 194	92.32 35	93.63 26	79.37 23	84.17 102	91.88 121	69.04 107	95.43 77	83.93 81	93.77 69	93.01 143

ACMM	73.20 8	80.78 183	79.84 185	83.58 185	89.31 147	68.37 134	89.99 84	91.60 134	70.28 259	77.25 236	89.66 198	53.37 296	93.53 174	74.24 200	82.85 266	88.85 310
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Test_1112_low_res		76.40 295	75.44 289	79.27 314	89.28 149	58.09 356	81.69 347	87.07 293	59.53 411	72.48 337	86.67 290	61.30 214	89.33 332	60.81 336	80.15 300	90.41 246

F-COLMAP		76.38 296	74.33 310	82.50 236	89.28 149	66.95 186	88.41 153	89.03 233	64.05 366	66.83 402	88.61 232	46.78 369	92.89 215	57.48 367	78.55 316	87.67 340

SSM_0404		81.91 149	80.84 160	85.13 101	89.24 151	68.26 137	87.84 179	89.25 222	71.06 234	80.62 171	90.39 177	59.57 237	94.65 119	72.45 224	87.19 185	92.47 167

LPG-MVS_test		82.08 145	81.27 151	84.50 127	89.23 152	68.76 119	90.22 81	91.94 115	75.37 121	76.64 253	91.51 139	54.29 285	94.91 102	78.44 144	83.78 245	89.83 277

LGP-MVS_train				84.50 127	89.23 152	68.76 119		91.94 115	75.37 121	76.64 253	91.51 139	54.29 285	94.91 102	78.44 144	83.78 245	89.83 277

BH-untuned		79.47 215	78.60 216	82.05 245	89.19 154	65.91 203	86.07 247	88.52 257	72.18 208	75.42 282	87.69 259	61.15 218	93.54 173	60.38 338	86.83 193	86.70 370

xiu_mvs_v2_base		81.69 155	81.05 155	83.60 183	89.15 155	68.03 147	84.46 293	90.02 186	70.67 244	81.30 159	86.53 298	63.17 177	94.19 138	75.60 185	88.54 156	88.57 322

test_yl		81.17 167	80.47 168	83.24 198	89.13 156	63.62 268	86.21 243	89.95 189	72.43 205	81.78 149	89.61 200	57.50 256	93.58 166	70.75 237	86.90 190	92.52 162

DCV-MVSNet		81.17 167	80.47 168	83.24 198	89.13 156	63.62 268	86.21 243	89.95 189	72.43 205	81.78 149	89.61 200	57.50 256	93.58 166	70.75 237	86.90 190	92.52 162

tfpn200view9		76.42 294	75.37 293	79.55 311	89.13 156	57.65 368	85.17 270	83.60 346	73.41 183	76.45 258	86.39 301	52.12 307	91.95 256	48.33 425	83.75 248	89.07 295

thres400		76.50 289	75.37 293	79.86 300	89.13 156	57.65 368	85.17 270	83.60 346	73.41 183	76.45 258	86.39 301	52.12 307	91.95 256	48.33 425	83.75 248	90.00 268

1112_ss		77.40 274	76.43 275	80.32 289	89.11 160	60.41 335	83.65 315	87.72 277	62.13 390	73.05 328	86.72 285	62.58 188	89.97 321	62.11 324	80.80 291	90.59 239

SDMVSNet		80.38 195	80.18 174	80.99 273	89.03 161	64.94 236	80.45 368	89.40 209	75.19 130	76.61 255	89.98 186	60.61 229	87.69 362	76.83 168	83.55 254	90.33 250

sd_testset		77.70 267	77.40 252	78.60 326	89.03 161	60.02 339	79.00 389	85.83 318	75.19 130	76.61 255	89.98 186	54.81 277	85.46 387	62.63 316	83.55 254	90.33 250

Fast-Effi-MVS+		80.81 176	79.92 181	83.47 187	88.85 163	64.51 248	85.53 264	89.39 210	70.79 241	78.49 207	85.06 333	67.54 126	93.58 166	67.03 280	86.58 196	92.32 173

PVSNet_BlendedMVS		80.60 188	80.02 179	82.36 239	88.85 163	65.40 216	86.16 245	92.00 111	69.34 282	78.11 217	86.09 308	66.02 149	94.27 131	71.52 229	82.06 276	87.39 347

PVSNet_Blended		80.98 171	80.34 170	82.90 217	88.85 163	65.40 216	84.43 296	92.00 111	67.62 315	78.11 217	85.05 334	66.02 149	94.27 131	71.52 229	89.50 138	89.01 302

MVS_111021_LR		82.61 138	82.11 139	84.11 152	88.82 166	71.58 57	85.15 272	86.16 313	74.69 146	80.47 175	91.04 157	62.29 193	90.55 312	80.33 120	90.08 127	90.20 255

mamba_0408		79.37 222	77.52 249	84.93 110	88.81 167	67.96 149	65.03 468	88.66 252	70.96 238	79.48 187	89.80 192	58.69 243	94.65 119	70.35 243	85.93 211	92.18 181

SSM_04072		77.67 269	77.52 249	78.12 338	88.81 167	67.96 149	65.03 468	88.66 252	70.96 238	79.48 187	89.80 192	58.69 243	74.23 460	70.35 243	85.93 211	92.18 181

SSM_0407		81.58 159	80.48 167	84.87 113	88.81 167	67.96 149	87.37 194	89.25 222	71.06 234	79.48 187	90.39 177	59.57 237	94.48 126	72.45 224	85.93 211	92.18 181

BH-w/o		78.21 250	77.33 255	80.84 277	88.81 167	65.13 226	84.87 280	87.85 273	69.75 274	74.52 310	84.74 340	61.34 213	93.11 205	58.24 362	85.84 214	84.27 409

FIs		82.07 146	82.42 131	81.04 272	88.80 171	58.34 354	88.26 161	93.49 31	76.93 72	78.47 209	91.04 157	69.92 89	92.34 242	69.87 251	84.97 225	92.44 169

OPM-MVS		83.50 117	82.95 122	85.14 98	88.79 172	70.95 74	89.13 121	91.52 136	77.55 52	80.96 164	91.75 127	60.71 224	94.50 124	79.67 130	86.51 198	89.97 272
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
WR-MVS		79.49 214	79.22 205	80.27 290	88.79 172	58.35 353	85.06 276	88.61 256	78.56 35	77.65 228	88.34 240	63.81 170	90.66 311	64.98 295	77.22 335	91.80 193

OMC-MVS		82.69 136	81.97 145	84.85 114	88.75 174	67.42 168	87.98 170	90.87 157	74.92 139	79.72 183	91.65 131	62.19 196	93.96 144	75.26 190	86.42 199	93.16 131

hse-mvs2		81.72 153	80.94 158	84.07 159	88.72 175	67.68 160	85.87 252	87.26 289	76.02 103	84.67 87	88.22 245	61.54 207	93.48 180	82.71 96	73.44 392	91.06 217

AUN-MVS		79.21 225	77.60 247	84.05 165	88.71 176	67.61 162	85.84 254	87.26 289	69.08 292	77.23 238	88.14 250	53.20 298	93.47 181	75.50 187	73.45 391	91.06 217

ACMH	67.68 16	75.89 302	73.93 314	81.77 251	88.71 176	66.61 189	88.62 145	89.01 235	69.81 270	66.78 403	86.70 289	41.95 412	91.51 280	55.64 383	78.14 325	87.17 356
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Vis-MVSNet (Re-imp)		78.36 247	78.45 219	78.07 340	88.64 178	51.78 433	86.70 221	79.63 405	74.14 162	75.11 297	90.83 165	61.29 215	89.75 325	58.10 363	91.60 99	92.69 156

PatchMatch-RL		72.38 349	70.90 353	76.80 361	88.60 179	67.38 171	79.53 380	76.17 433	62.75 383	69.36 374	82.00 396	45.51 386	84.89 393	53.62 394	80.58 294	78.12 451

ACMH+	68.96 14	76.01 301	74.01 312	82.03 246	88.60 179	65.31 222	88.86 130	87.55 279	70.25 261	67.75 389	87.47 267	41.27 415	93.19 200	58.37 360	75.94 357	87.60 342

LTVRE_ROB	69.57 13	76.25 297	74.54 306	81.41 259	88.60 179	64.38 254	79.24 384	89.12 231	70.76 243	69.79 371	87.86 255	49.09 353	93.20 198	56.21 382	80.16 299	86.65 372
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
DELS-MVS		85.41 76	85.30 80	85.77 79	88.49 182	67.93 152	85.52 266	93.44 32	78.70 34	83.63 115	89.03 217	74.57 27	95.71 66	80.26 121	94.04 67	93.66 100
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
CLD-MVS		82.31 142	81.65 148	84.29 143	88.47 183	67.73 158	85.81 256	92.35 87	75.78 108	78.33 212	86.58 295	64.01 167	94.35 128	76.05 178	87.48 180	90.79 228
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_NR-MVSNet		81.88 150	81.54 149	82.92 216	88.46 184	63.46 279	87.13 201	92.37 86	80.19 12	78.38 210	89.14 213	71.66 64	93.05 209	70.05 247	76.46 347	92.25 176

ab-mvs		79.51 213	78.97 210	81.14 269	88.46 184	60.91 325	83.84 310	89.24 224	70.36 255	79.03 194	88.87 225	63.23 176	90.21 317	65.12 293	82.57 271	92.28 175

testing91		76.54 287	75.66 286	79.18 317	88.43 186	55.89 395	81.08 355	83.00 361	73.76 171	75.34 286	84.29 348	46.20 378	90.07 319	64.33 299	84.50 232	91.58 201

FC-MVSNet-test		81.52 162	82.02 143	80.03 297	88.42 187	55.97 394	87.95 172	93.42 34	77.10 68	77.38 233	90.98 163	69.96 88	91.79 262	68.46 266	84.50 232	92.33 172

Effi-MVS+		83.62 114	83.08 118	85.24 95	88.38 188	67.45 167	88.89 129	89.15 228	75.50 116	82.27 139	88.28 242	69.61 94	94.45 127	77.81 152	87.84 172	93.84 90

UniMVSNet (Re)		81.60 158	81.11 154	83.09 205	88.38 188	64.41 253	87.60 183	93.02 50	78.42 37	78.56 205	88.16 246	69.78 91	93.26 191	69.58 254	76.49 346	91.60 199

VPNet		78.69 239	78.66 215	78.76 323	88.31 190	55.72 398	84.45 294	86.63 304	76.79 76	78.26 213	90.55 174	59.30 240	89.70 327	66.63 281	77.05 337	90.88 225

FA-MVS(test-final)		80.96 172	79.91 182	84.10 153	88.30 191	65.01 230	84.55 290	90.01 187	73.25 189	79.61 184	87.57 262	58.35 248	94.72 115	71.29 233	86.25 203	92.56 160

TR-MVS		77.44 272	76.18 279	81.20 267	88.24 192	63.24 284	84.61 288	86.40 308	67.55 316	77.81 225	86.48 299	54.10 287	93.15 202	57.75 366	82.72 269	87.20 355

myMVS_eth3d28		73.62 330	73.53 320	73.90 393	88.20 193	47.41 453	78.06 404	79.37 407	74.29 158	73.98 316	84.29 348	44.67 390	83.54 403	51.47 405	87.39 181	90.74 232

EI-MVSNet-Vis-set		84.19 94	83.81 103	85.31 93	88.18 194	67.85 154	87.66 182	89.73 198	80.05 15	82.95 128	89.59 202	70.74 76	94.82 108	80.66 118	84.72 229	93.28 123

testing11		75.14 314	74.01 312	78.53 330	88.16 195	56.38 388	80.74 362	80.42 395	70.67 244	72.69 335	83.72 364	43.61 400	89.86 322	62.29 320	83.76 247	89.36 291

testing99		76.09 300	75.12 299	79.00 318	88.16 195	55.50 401	80.79 359	81.40 381	73.30 187	75.17 294	84.27 351	44.48 393	90.02 320	64.28 300	84.22 241	91.48 206

GDP-MVS		83.52 116	82.64 128	86.16 69	88.14 197	68.45 132	89.13 121	92.69 70	72.82 200	83.71 111	91.86 123	55.69 272	95.35 86	80.03 122	89.74 134	94.69 33

baseline1		76.98 281	76.75 269	77.66 348	88.13 198	55.66 399	85.12 273	81.89 374	73.04 195	76.79 248	88.90 223	62.43 191	87.78 361	63.30 307	71.18 408	89.55 286

test_0402		72.79 347	70.44 358	79.84 301	88.13 198	65.99 201	85.93 250	84.29 337	65.57 343	67.40 396	85.49 321	46.92 366	92.61 225	35.88 463	74.38 382	80.94 442

tttt0517		79.40 219	77.91 233	83.90 176	88.10 200	63.84 264	88.37 157	84.05 341	71.45 223	76.78 249	89.12 214	49.93 343	94.89 105	70.18 246	83.18 263	92.96 146

FE-MVS		77.78 263	75.68 284	84.08 158	88.09 201	66.00 200	83.13 329	87.79 274	68.42 308	78.01 220	85.23 328	45.50 387	95.12 92	59.11 351	85.83 215	91.11 215

VPA-MVSNet		80.60 188	80.55 165	80.76 279	88.07 202	60.80 327	86.86 214	91.58 135	75.67 113	80.24 177	89.45 209	63.34 171	90.25 316	70.51 241	79.22 313	91.23 212

UGNet		80.83 175	79.59 194	84.54 124	88.04 203	68.09 144	89.42 106	88.16 260	76.95 71	76.22 264	89.46 207	49.30 350	93.94 147	68.48 265	90.31 121	91.60 199
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
UBG		73.08 342	72.27 336	75.51 372	88.02 204	51.29 438	78.35 401	77.38 424	65.52 344	73.87 318	82.36 388	45.55 385	86.48 374	55.02 386	84.39 238	88.75 315

WR-MVS_H		78.51 244	78.49 218	78.56 328	88.02 204	56.38 388	88.43 151	92.67 72	77.14 65	73.89 317	87.55 264	66.25 143	89.24 335	58.92 353	73.55 390	90.06 266

QAPM		80.88 173	79.50 196	85.03 104	88.01 206	68.97 114	91.59 51	92.00 111	66.63 331	75.15 296	92.16 113	57.70 253	95.45 75	63.52 303	88.76 152	90.66 235

RRT-MVS		82.60 140	82.10 140	84.10 153	87.98 207	62.94 294	87.45 190	91.27 143	77.42 56	79.85 181	90.28 180	56.62 267	94.70 117	79.87 127	88.15 165	94.67 36

3Dnovator	76.31 5	83.38 121	82.31 135	86.59 61	87.94 208	72.94 28	90.64 68	92.14 108	77.21 63	75.47 278	92.83 97	58.56 246	94.72 115	73.24 211	92.71 81	92.13 186

WBMVS		73.43 333	72.81 329	75.28 376	87.91 209	50.99 440	78.59 397	81.31 383	65.51 346	74.47 311	84.83 337	46.39 372	86.68 371	58.41 359	77.86 327	88.17 332

testing222		74.04 325	72.66 331	78.19 336	87.89 210	55.36 402	81.06 356	79.20 410	71.30 227	74.65 308	83.57 369	39.11 428	88.67 348	51.43 407	85.75 216	90.53 241

EI-MVSNet-UG-set		83.81 103	83.38 114	85.09 103	87.87 211	67.53 166	87.44 193	89.66 199	79.74 18	82.23 140	89.41 211	70.24 82	94.74 114	79.95 123	83.92 244	92.99 145

TranMVSNet+NR-MVSNet		80.84 174	80.31 171	82.42 237	87.85 212	62.33 304	87.74 181	91.33 142	80.55 9	77.99 221	89.86 188	65.23 156	92.62 224	67.05 279	75.24 374	92.30 174

BP-MVS1		84.32 91	83.71 106	86.17 68	87.84 213	67.85 154	89.38 109	89.64 201	77.73 45	83.98 106	92.12 116	56.89 264	95.43 77	84.03 80	91.75 98	95.24 7

CP-MVSNet		78.22 249	78.34 223	77.84 344	87.83 214	54.54 411	87.94 173	91.17 147	77.65 46	73.48 323	88.49 236	62.24 195	88.43 352	62.19 321	74.07 383	90.55 240

DU-MVS		81.12 170	80.52 166	82.90 217	87.80 215	63.46 279	87.02 206	91.87 119	79.01 31	78.38 210	89.07 215	65.02 158	93.05 209	70.05 247	76.46 347	92.20 179

NR-MVSNet		80.23 201	79.38 198	82.78 227	87.80 215	63.34 282	86.31 238	91.09 151	79.01 31	72.17 342	89.07 215	67.20 130	92.81 221	66.08 286	75.65 360	92.20 179

TAMVS		78.89 235	77.51 251	83.03 210	87.80 215	67.79 157	84.72 283	85.05 328	67.63 314	76.75 250	87.70 258	62.25 194	90.82 305	58.53 358	87.13 187	90.49 243

fmvsm_s_conf0.5_n_11		86.06 56	86.75 47	84.00 170	87.78 218	66.09 196	89.96 86	90.80 160	77.37 57	86.72 65	94.20 52	72.51 51	92.78 222	89.08 22	92.33 87	93.13 135

thres200		75.55 306	74.47 307	78.82 322	87.78 218	57.85 363	83.07 332	83.51 349	72.44 204	75.84 272	84.42 343	52.08 310	91.75 264	47.41 432	83.64 253	86.86 366

ETVMVS		72.25 353	71.05 350	75.84 366	87.77 220	51.91 430	79.39 382	74.98 436	69.26 285	73.71 319	82.95 379	40.82 419	86.14 377	46.17 438	84.43 237	89.47 287

E3new		83.78 106	83.60 109	84.31 140	87.76 221	64.89 240	86.24 242	92.20 101	75.15 133	82.87 130	91.23 147	70.11 84	93.52 176	79.05 134	87.79 173	94.51 53

viewcassd2359sk11		83.89 101	83.74 105	84.34 138	87.76 221	64.91 239	86.30 239	92.22 98	75.47 117	83.04 127	91.52 138	70.15 83	93.53 174	79.26 133	87.96 170	94.57 47

fmvsm_s_conf0.5_n_8		86.56 47	87.17 38	84.73 120	87.76 221	65.62 212	89.20 114	92.21 100	79.94 17	89.74 27	94.86 26	68.63 112	94.20 136	90.83 5	91.39 104	94.38 59

PS-CasMVS		78.01 258	78.09 229	77.77 346	87.71 224	54.39 413	88.02 169	91.22 144	77.50 54	73.26 325	88.64 231	60.73 223	88.41 353	61.88 325	73.88 387	90.53 241

PCF-MVS	73.52 7	80.38 195	78.84 213	85.01 105	87.71 224	68.99 113	83.65 315	91.46 141	63.00 377	77.77 227	90.28 180	66.10 146	95.09 98	61.40 330	88.22 164	90.94 224
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
E2		84.00 99	83.87 100	84.39 133	87.70 226	64.95 233	86.40 235	92.23 95	75.85 106	83.21 121	91.78 125	70.09 85	93.55 171	79.52 131	88.05 167	94.66 39

E3		84.00 99	83.87 100	84.39 133	87.70 226	64.95 233	86.40 235	92.23 95	75.85 106	83.21 121	91.78 125	70.09 85	93.55 171	79.52 131	88.05 167	94.66 39

thisisatest0530		79.40 219	77.76 242	84.31 140	87.69 228	65.10 229	87.36 195	84.26 339	70.04 263	77.42 232	88.26 244	49.94 341	94.79 112	70.20 245	84.70 230	93.03 141

casdiffmvs_mvg		85.99 59	86.09 62	85.70 81	87.65 229	67.22 179	88.69 142	93.04 46	79.64 21	85.33 76	92.54 104	73.30 39	94.50 124	83.49 83	91.14 108	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt09		83.34 122	82.55 130	85.70 81	87.64 230	67.72 159	88.43 151	91.68 129	71.91 214	81.65 152	90.68 168	67.10 132	94.75 113	76.17 175	87.70 176	94.62 44

E6		84.22 92	84.12 95	84.52 125	87.60 231	65.36 220	87.45 190	92.30 90	76.51 85	83.53 116	92.26 108	69.26 100	93.49 178	79.88 125	88.26 161	94.69 33

E5		84.22 92	84.12 95	84.51 126	87.60 231	65.36 220	87.45 190	92.31 89	76.51 85	83.53 116	92.26 108	69.25 101	93.50 177	79.88 125	88.26 161	94.69 33

GBi-Net		78.40 245	77.40 252	81.40 260	87.60 231	63.01 289	88.39 154	89.28 218	71.63 217	75.34 286	87.28 269	54.80 278	91.11 295	62.72 312	79.57 305	90.09 262

test1		78.40 245	77.40 252	81.40 260	87.60 231	63.01 289	88.39 154	89.28 218	71.63 217	75.34 286	87.28 269	54.80 278	91.11 295	62.72 312	79.57 305	90.09 262

FMVSNet2		78.20 251	77.21 256	81.20 267	87.60 231	62.89 295	87.47 187	89.02 234	71.63 217	75.29 292	87.28 269	54.80 278	91.10 298	62.38 318	79.38 310	89.61 284

CDS-MVSNet		79.07 229	77.70 244	83.17 202	87.60 231	68.23 141	84.40 299	86.20 312	67.49 317	76.36 261	86.54 297	61.54 207	90.79 306	61.86 326	87.33 182	90.49 243
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
E4		84.10 96	83.99 99	84.45 130	87.58 237	64.99 232	86.54 228	92.25 94	76.38 92	83.37 119	92.09 117	69.88 90	93.58 166	79.78 128	88.03 169	94.77 25

HY-MVS	69.67 12	77.95 259	77.15 257	80.36 287	87.57 238	60.21 338	83.37 324	87.78 275	66.11 335	75.37 285	87.06 280	63.27 173	90.48 313	61.38 331	82.43 272	90.40 247

xiu_mvs_v1_base_debu		80.80 179	79.72 190	84.03 167	87.35 239	70.19 88	85.56 259	88.77 245	69.06 293	81.83 145	88.16 246	50.91 327	92.85 217	78.29 148	87.56 177	89.06 297

xiu_mvs_v1_base		80.80 179	79.72 190	84.03 167	87.35 239	70.19 88	85.56 259	88.77 245	69.06 293	81.83 145	88.16 246	50.91 327	92.85 217	78.29 148	87.56 177	89.06 297

xiu_mvs_v1_base_debi		80.80 179	79.72 190	84.03 167	87.35 239	70.19 88	85.56 259	88.77 245	69.06 293	81.83 145	88.16 246	50.91 327	92.85 217	78.29 148	87.56 177	89.06 297

MVSFormer		82.85 134	82.05 142	85.24 95	87.35 239	70.21 86	90.50 72	90.38 172	68.55 304	81.32 156	89.47 205	61.68 204	93.46 182	78.98 139	90.26 123	92.05 188

lupinMVS		81.39 165	80.27 173	84.76 119	87.35 239	70.21 86	85.55 262	86.41 307	62.85 380	81.32 156	88.61 232	61.68 204	92.24 246	78.41 146	90.26 123	91.83 191

fmvsm_s_conf0.5_n_10		86.38 52	86.76 46	85.24 95	87.33 244	67.30 174	89.50 101	90.98 152	76.25 99	90.56 22	94.75 29	68.38 115	94.24 135	90.80 7	92.32 89	94.19 69

testing3		68.56 389	67.67 388	71.22 418	87.33 244	42.87 468	83.06 333	71.54 448	70.36 255	69.08 377	84.38 345	30.33 455	85.69 383	37.50 461	75.45 367	85.09 401

fmvsm_s_conf0.5_n_6		85.55 72	86.20 56	83.60 183	87.32 246	65.13 226	88.86 130	91.63 131	75.41 119	88.23 40	93.45 81	68.56 113	92.47 234	89.52 18	92.78 79	93.20 129

baseline		84.93 86	84.98 83	84.80 117	87.30 247	65.39 218	87.30 198	92.88 62	77.62 47	84.04 105	92.26 108	71.81 59	93.96 144	81.31 107	90.30 122	95.03 11

PAPM		77.68 268	76.40 277	81.51 256	87.29 248	61.85 313	83.78 311	89.59 203	64.74 354	71.23 352	88.70 228	62.59 187	93.66 165	52.66 399	87.03 189	89.01 302

fmvsm_l_conf0.5_n_3		86.02 57	86.32 53	85.14 98	87.20 249	68.54 130	89.57 99	90.44 170	75.31 123	87.49 54	94.39 42	72.86 47	92.72 223	89.04 27	90.56 118	94.16 70

LCM-MVSNet-Re		77.05 279	76.94 262	77.36 354	87.20 249	51.60 434	80.06 374	80.46 393	75.20 129	67.69 390	86.72 285	62.48 189	88.98 341	63.44 305	89.25 141	91.51 203

casdiffmvs		85.11 83	85.14 82	85.01 105	87.20 249	65.77 209	87.75 180	92.83 65	77.84 43	84.36 99	92.38 106	72.15 55	93.93 150	81.27 109	90.48 119	95.33 4
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
icg_test_0407_2		78.92 234	78.93 211	78.90 321	87.13 252	63.59 272	76.58 415	89.33 212	70.51 250	77.82 223	89.03 217	61.84 200	81.38 419	72.56 220	85.56 218	91.74 194

IMVS_0407		80.61 186	79.90 183	82.75 230	87.13 252	63.59 272	85.33 268	89.33 212	70.51 250	77.82 223	89.03 217	61.84 200	92.91 214	72.56 220	85.56 218	91.74 194

IMVS_0404		77.16 278	76.42 276	79.37 312	87.13 252	63.59 272	77.12 413	89.33 212	70.51 250	66.22 413	89.03 217	50.36 335	82.78 409	72.56 220	85.56 218	91.74 194

IMVS_0403		80.80 179	80.12 178	82.87 219	87.13 252	63.59 272	85.19 269	89.33 212	70.51 250	78.49 207	89.03 217	63.26 174	93.27 190	72.56 220	85.56 218	91.74 194

COLMAP_ROB	66.92 17	73.01 343	70.41 359	80.81 278	87.13 252	65.63 211	88.30 160	84.19 340	62.96 378	63.80 431	87.69 259	38.04 434	92.56 229	46.66 434	74.91 377	84.24 410
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_l_conf0.5_n_9		85.84 66	86.63 49	83.46 188	87.12 257	66.01 199	88.56 148	89.43 208	75.59 114	89.32 28	94.32 44	72.89 46	91.21 294	90.11 11	92.33 87	93.16 131

KinetiMVS		83.31 125	82.61 129	85.39 91	87.08 258	67.56 165	88.06 168	91.65 130	77.80 44	82.21 141	91.79 124	57.27 259	94.07 142	77.77 153	89.89 132	94.56 49

fmvsm_s_conf0.5_n_3		86.36 53	87.46 32	83.09 205	87.08 258	65.21 223	89.09 123	90.21 181	79.67 19	89.98 24	95.02 24	73.17 42	91.71 267	91.30 3	91.60 99	92.34 171

PEN-MVS		77.73 264	77.69 245	77.84 344	87.07 260	53.91 416	87.91 175	91.18 146	77.56 51	73.14 327	88.82 226	61.23 216	89.17 337	59.95 341	72.37 398	90.43 245

viewdifsd2359ckpt13		82.91 133	82.29 136	84.77 118	86.96 261	66.90 187	87.47 187	91.62 132	72.19 207	81.68 151	90.71 167	66.92 133	93.28 188	75.90 180	87.15 186	94.12 73

MVS_Test		83.15 127	83.06 119	83.41 192	86.86 262	63.21 285	86.11 246	92.00 111	74.31 156	82.87 130	89.44 210	70.03 87	93.21 195	77.39 159	88.50 158	93.81 92

UniMVSNet_ETH3D		79.10 228	78.24 226	81.70 252	86.85 263	60.24 337	87.28 199	88.79 244	74.25 159	76.84 246	90.53 175	49.48 346	91.56 273	67.98 268	82.15 274	93.29 122

FMVSNet3		77.88 261	76.85 264	80.97 275	86.84 264	62.36 303	86.52 229	88.77 245	71.13 230	75.34 286	86.66 291	54.07 288	91.10 298	62.72 312	79.57 305	89.45 288

viewmanbaseed2359cas		83.66 110	83.55 110	84.00 170	86.81 265	64.53 246	86.65 223	91.75 127	74.89 140	83.15 126	91.68 129	68.74 111	92.83 220	79.02 136	89.24 142	94.63 42

FMVSNet1		77.44 272	76.12 280	81.40 260	86.81 265	63.01 289	88.39 154	89.28 218	70.49 254	74.39 312	87.28 269	49.06 354	91.11 295	60.91 334	78.52 317	90.09 262

nrg030		83.88 102	83.53 111	84.96 107	86.77 267	69.28 109	90.46 75	92.67 72	74.79 144	82.95 128	91.33 146	72.70 50	93.09 206	80.79 115	79.28 312	92.50 164

ET-MVSNet_ETH3D		78.63 240	76.63 272	84.64 122	86.73 268	69.47 102	85.01 277	84.61 332	69.54 278	66.51 410	86.59 293	50.16 337	91.75 264	76.26 174	84.24 240	92.69 156

fmvsm_s_conf0.5_n_4		85.39 77	85.75 70	84.30 142	86.70 269	65.83 205	88.77 136	89.78 193	75.46 118	88.35 36	93.73 74	69.19 102	93.06 208	91.30 3	88.44 159	94.02 79

fmvsm_s_conf0.5_n		83.80 104	83.71 106	84.07 159	86.69 270	67.31 173	89.46 103	83.07 359	71.09 232	86.96 63	93.70 75	69.02 108	91.47 282	88.79 30	84.62 231	93.44 116

UWE-MVS		72.13 355	71.49 342	74.03 391	86.66 271	47.70 450	81.40 353	76.89 429	63.60 372	75.59 275	84.22 352	39.94 422	85.62 384	48.98 422	86.13 206	88.77 314

jason		81.39 165	80.29 172	84.70 121	86.63 272	69.90 94	85.95 249	86.77 300	63.24 373	81.07 162	89.47 205	61.08 220	92.15 248	78.33 147	90.07 128	92.05 188
jason: jason.
viewmacassd2359aftdt		83.76 107	83.66 108	84.07 159	86.59 273	64.56 245	86.88 213	91.82 122	75.72 109	83.34 120	92.15 115	68.24 119	92.88 216	79.05 134	89.15 145	94.77 25

guyue		81.13 169	80.64 163	82.60 234	86.52 274	63.92 263	86.69 222	87.73 276	73.97 164	80.83 169	89.69 196	56.70 265	91.33 288	78.26 151	85.40 222	92.54 161

viewdifsd2359ckpt07		82.83 135	82.78 127	82.99 212	86.51 275	62.58 297	85.09 275	90.83 159	75.22 126	82.28 138	91.63 133	69.43 96	92.03 251	77.71 154	86.32 200	94.34 62

PS-MVSNAJss		82.07 146	81.31 150	84.34 138	86.51 275	67.27 176	89.27 112	91.51 137	71.75 215	79.37 190	90.22 184	63.15 178	94.27 131	77.69 155	82.36 273	91.49 205

WTY-MVS		75.65 305	75.68 284	75.57 370	86.40 277	56.82 379	77.92 407	82.40 369	65.10 349	76.18 266	87.72 257	63.13 181	80.90 422	60.31 339	81.96 277	89.00 304

fmvsm_s_conf0.5_n_5		85.22 81	85.55 73	84.25 149	86.26 278	67.40 170	89.18 115	89.31 217	72.50 201	88.31 37	93.86 70	69.66 93	91.96 255	89.81 13	91.05 109	93.38 117

DTE-MVSNet		76.99 280	76.80 265	77.54 353	86.24 279	53.06 425	87.52 185	90.66 163	77.08 69	72.50 336	88.67 230	60.48 231	89.52 329	57.33 370	70.74 410	90.05 267

PVSNet	64.34 18	72.08 356	70.87 354	75.69 368	86.21 280	56.44 386	74.37 433	80.73 387	62.06 391	70.17 362	82.23 392	42.86 404	83.31 406	54.77 388	84.45 236	87.32 351

SD_0403		74.65 318	74.77 302	74.29 388	86.20 281	47.42 452	83.71 313	85.12 325	69.30 283	68.50 383	87.95 254	59.40 239	86.05 378	49.38 419	83.35 259	89.40 289

fmvsm_s_conf0.5_n_2		84.04 97	84.11 97	83.81 179	86.17 282	65.00 231	86.96 208	87.28 286	74.35 154	88.25 39	94.23 50	61.82 202	92.60 226	89.85 12	88.09 166	93.84 90

fmvsm_s_conf0.5_n_a		83.63 113	83.41 113	84.28 144	86.14 283	68.12 143	89.43 104	82.87 364	70.27 260	87.27 59	93.80 73	69.09 103	91.58 270	88.21 38	83.65 252	93.14 134

test_fmvsm_n_1920		85.29 80	85.34 77	85.13 101	86.12 284	69.93 92	88.65 144	90.78 161	69.97 267	88.27 38	93.98 66	71.39 67	91.54 277	88.49 35	90.45 120	93.91 84

mamv4		76.81 284	78.23 228	72.54 407	86.12 284	65.75 210	78.76 393	82.07 373	64.12 363	72.97 330	91.02 160	67.97 121	68.08 472	83.04 89	78.02 326	83.80 417

tfpnnormal		74.39 319	73.16 325	78.08 339	86.10 286	58.05 357	84.65 287	87.53 280	70.32 258	71.22 353	85.63 317	54.97 276	89.86 322	43.03 449	75.02 376	86.32 375

AstraMVS		80.81 176	80.14 177	82.80 223	86.05 287	63.96 260	86.46 231	85.90 317	73.71 172	80.85 168	90.56 173	54.06 289	91.57 272	79.72 129	83.97 243	92.86 150

VortexMVS		78.57 243	77.89 235	80.59 282	85.89 288	62.76 296	85.61 257	89.62 202	72.06 211	74.99 301	85.38 324	55.94 271	90.77 309	74.99 191	76.58 344	88.23 329

IterMVS-LS		80.06 204	79.38 198	82.11 244	85.89 288	63.20 286	86.79 217	89.34 211	74.19 160	75.45 281	86.72 285	66.62 136	92.39 238	72.58 217	76.86 340	90.75 231
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Baseline_NR-MVSNet		78.15 253	78.33 224	77.61 350	85.79 290	56.21 392	86.78 218	85.76 319	73.60 176	77.93 222	87.57 262	65.02 158	88.99 340	67.14 278	75.33 371	87.63 341

cascas		76.72 286	74.64 303	82.99 212	85.78 291	65.88 204	82.33 338	89.21 225	60.85 399	72.74 332	81.02 402	47.28 363	93.75 162	67.48 273	85.02 224	89.34 292

fmvsm_s_conf0.5_n_7		83.34 122	84.03 98	81.28 264	85.73 292	65.13 226	85.40 267	89.90 191	74.96 138	82.13 142	93.89 69	66.65 135	87.92 358	86.56 53	91.05 109	90.80 227

MVS		78.19 252	76.99 261	81.78 250	85.66 293	66.99 182	84.66 285	90.47 169	55.08 441	72.02 344	85.27 326	63.83 169	94.11 141	66.10 285	89.80 133	84.24 410

XVG-OURS		80.41 193	79.23 204	83.97 173	85.64 294	69.02 112	83.03 334	90.39 171	71.09 232	77.63 229	91.49 141	54.62 284	91.35 286	75.71 182	83.47 257	91.54 202

fmvsm_s_conf0.1_n_2		83.80 104	83.79 104	83.83 177	85.62 295	64.94 236	87.03 205	86.62 305	74.32 155	87.97 47	94.33 43	60.67 226	92.60 226	89.72 14	87.79 173	93.96 81

CANet_DTU		80.61 186	79.87 184	82.83 220	85.60 296	63.17 288	87.36 195	88.65 254	76.37 93	75.88 271	88.44 238	53.51 294	93.07 207	73.30 209	89.74 134	92.25 176

XVG-OURS-SEG-HR		80.81 176	79.76 187	83.96 174	85.60 296	68.78 118	83.54 321	90.50 168	70.66 247	76.71 251	91.66 130	60.69 225	91.26 289	76.94 164	81.58 281	91.83 191

Elysia		81.53 160	80.16 175	85.62 84	85.51 298	68.25 139	88.84 133	92.19 103	71.31 225	80.50 173	89.83 190	46.89 367	94.82 108	76.85 165	89.57 136	93.80 94

StellarMVS		81.53 160	80.16 175	85.62 84	85.51 298	68.25 139	88.84 133	92.19 103	71.31 225	80.50 173	89.83 190	46.89 367	94.82 108	76.85 165	89.57 136	93.80 94

TransMVSNet (Re)		75.39 312	74.56 305	77.86 343	85.50 300	57.10 376	86.78 218	86.09 315	72.17 209	71.53 349	87.34 268	63.01 182	89.31 333	56.84 376	61.83 443	87.17 356

fmvsm_l_conf0.5_n		84.47 90	84.54 89	84.27 146	85.42 301	68.81 116	88.49 150	87.26 289	68.08 311	88.03 44	93.49 77	72.04 57	91.77 263	88.90 29	89.14 146	92.24 178

fmvsm_l_conf0.5_n_a		84.13 95	84.16 94	84.06 162	85.38 302	68.40 133	88.34 158	86.85 299	67.48 318	87.48 55	93.40 82	70.89 73	91.61 268	88.38 37	89.22 143	92.16 185

MVP-Stereo		76.12 298	74.46 308	81.13 270	85.37 303	69.79 95	84.42 298	87.95 269	65.03 351	67.46 393	85.33 325	53.28 297	91.73 266	58.01 364	83.27 261	81.85 437
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tt0320-xc		70.11 375	67.45 392	78.07 340	85.33 304	59.51 346	83.28 325	78.96 412	58.77 418	67.10 399	80.28 412	36.73 438	87.42 365	56.83 377	59.77 450	87.29 352

SSC-MVS3.2		73.35 337	73.39 321	73.23 397	85.30 305	49.01 448	74.58 432	81.57 378	75.21 128	73.68 320	85.58 319	52.53 299	82.05 414	54.33 391	77.69 331	88.63 320

thisisatest0515		77.33 275	75.38 292	83.18 201	85.27 306	63.80 265	82.11 342	83.27 353	65.06 350	75.91 270	83.84 359	49.54 345	94.27 131	67.24 276	86.19 204	91.48 206

tt0805		78.73 237	77.83 237	81.43 258	85.17 307	60.30 336	89.41 107	90.90 155	71.21 229	77.17 243	88.73 227	46.38 373	93.21 195	72.57 218	78.96 314	90.79 228

OpenMVS	72.83 10	79.77 208	78.33 224	84.09 157	85.17 307	69.91 93	90.57 69	90.97 153	66.70 325	72.17 342	91.91 119	54.70 282	93.96 144	61.81 327	90.95 112	88.41 326

AllTest		70.96 363	68.09 378	79.58 309	85.15 309	63.62 268	84.58 289	79.83 402	62.31 387	60.32 444	86.73 283	32.02 449	88.96 343	50.28 413	71.57 406	86.15 379

TestCases				79.58 309	85.15 309	63.62 268		79.83 402	62.31 387	60.32 444	86.73 283	32.02 449	88.96 343	50.28 413	71.57 406	86.15 379

Effi-MVS+-dtu		80.03 205	78.57 217	84.42 132	85.13 311	68.74 121	88.77 136	88.10 262	74.99 135	74.97 302	83.49 370	57.27 259	93.36 186	73.53 205	80.88 289	91.18 213

SixPastTwentyTwo		73.37 334	71.26 349	79.70 305	85.08 312	57.89 362	85.57 258	83.56 348	71.03 236	65.66 415	85.88 310	42.10 410	92.57 228	59.11 351	63.34 438	88.65 319

LuminaMVS		80.68 184	79.62 193	83.83 177	85.07 313	68.01 148	86.99 207	88.83 242	70.36 255	81.38 155	87.99 253	50.11 338	92.51 233	79.02 136	86.89 192	90.97 222

test_fmvsmconf_n		85.92 62	86.04 63	85.57 87	85.03 314	69.51 100	89.62 98	90.58 165	73.42 182	87.75 50	94.02 61	72.85 48	93.24 192	90.37 8	90.75 115	93.96 81

EG-PatchMatch MVS		74.04 325	71.82 339	80.71 280	84.92 315	67.42 168	85.86 253	88.08 263	66.04 337	64.22 426	83.85 358	35.10 444	92.56 229	57.44 368	80.83 290	82.16 435

fmvsm_s_conf0.1_n		83.56 115	83.38 114	84.10 153	84.86 316	67.28 175	89.40 108	83.01 360	70.67 244	87.08 60	93.96 67	68.38 115	91.45 283	88.56 34	84.50 232	93.56 111

sc_t1		72.19 354	69.51 365	80.23 292	84.81 317	61.09 322	84.68 284	80.22 399	60.70 400	71.27 351	83.58 368	36.59 439	89.24 335	60.41 337	63.31 439	90.37 248

tt0320		70.49 371	68.03 379	77.89 342	84.78 318	59.12 348	83.55 319	80.44 394	58.13 424	67.43 395	80.41 410	39.26 426	87.54 364	55.12 385	63.18 440	86.99 363

IB-MVS	68.01 15	75.85 303	73.36 323	83.31 194	84.76 319	66.03 197	83.38 323	85.06 327	70.21 262	69.40 373	81.05 401	45.76 383	94.66 118	65.10 294	75.49 363	89.25 294
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
mvs_tets		79.13 227	77.77 241	83.22 200	84.70 320	66.37 192	89.17 116	90.19 182	69.38 281	75.40 283	89.46 207	44.17 396	93.15 202	76.78 171	80.70 293	90.14 257

Syy-MVS		68.05 393	67.85 382	68.67 431	84.68 321	40.97 474	78.62 395	73.08 445	66.65 329	66.74 404	79.46 421	52.11 309	82.30 412	32.89 466	76.38 352	82.75 429

myMVS_eth3d		67.02 400	66.29 400	69.21 426	84.68 321	42.58 469	78.62 395	73.08 445	66.65 329	66.74 404	79.46 421	31.53 452	82.30 412	39.43 458	76.38 352	82.75 429

jajsoiax		79.29 223	77.96 231	83.27 196	84.68 321	66.57 190	89.25 113	90.16 183	69.20 289	75.46 280	89.49 204	45.75 384	93.13 204	76.84 167	80.80 291	90.11 260

WB-MVSnew		71.96 357	71.65 341	72.89 403	84.67 324	51.88 431	82.29 339	77.57 420	62.31 387	73.67 321	83.00 378	53.49 295	81.10 421	45.75 441	82.13 275	85.70 389

MIMVSNet		70.69 367	69.30 366	74.88 381	84.52 325	56.35 390	75.87 421	79.42 406	64.59 355	67.76 388	82.41 387	41.10 416	81.54 417	46.64 436	81.34 282	86.75 369

MSDG		73.36 336	70.99 351	80.49 285	84.51 326	65.80 207	80.71 363	86.13 314	65.70 341	65.46 416	83.74 362	44.60 391	90.91 304	51.13 408	76.89 339	84.74 405

mvs_anonymous		79.42 218	79.11 207	80.34 288	84.45 327	57.97 360	82.59 336	87.62 278	67.40 319	76.17 268	88.56 235	68.47 114	89.59 328	70.65 240	86.05 207	93.47 115

EI-MVSNet		80.52 192	79.98 180	82.12 242	84.28 328	63.19 287	86.41 232	88.95 239	74.18 161	78.69 200	87.54 265	66.62 136	92.43 236	72.57 218	80.57 295	90.74 232

CVMVSNet		72.99 344	72.58 332	74.25 389	84.28 328	50.85 441	86.41 232	83.45 351	44.56 461	73.23 326	87.54 265	49.38 348	85.70 382	65.90 287	78.44 319	86.19 378

pm-mvs1		77.25 277	76.68 271	78.93 320	84.22 330	58.62 351	86.41 232	88.36 259	71.37 224	73.31 324	88.01 252	61.22 217	89.15 338	64.24 301	73.01 395	89.03 301

EPNet		83.72 109	82.92 123	86.14 72	84.22 330	69.48 101	91.05 64	85.27 323	81.30 6	76.83 247	91.65 131	66.09 147	95.56 68	76.00 179	93.85 68	93.38 117
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmvis_n_1920		84.02 98	83.87 100	84.49 129	84.12 332	69.37 108	88.15 166	87.96 268	70.01 265	83.95 107	93.23 86	68.80 110	91.51 280	88.61 32	89.96 129	92.57 159

v8		79.97 207	79.02 209	82.80 223	84.09 333	64.50 250	87.96 171	90.29 179	74.13 163	75.24 293	86.81 282	62.88 185	93.89 155	74.39 198	75.40 369	90.00 268

v10		79.74 209	78.67 214	82.97 215	84.06 334	64.95 233	87.88 177	90.62 164	73.11 193	75.11 297	86.56 296	61.46 210	94.05 143	73.68 203	75.55 362	89.90 274

SCA		74.22 322	72.33 335	79.91 299	84.05 335	62.17 307	79.96 377	79.29 409	66.30 334	72.38 339	80.13 414	51.95 313	88.60 349	59.25 349	77.67 332	88.96 306

test_djsdf		80.30 200	79.32 201	83.27 196	83.98 336	65.37 219	90.50 72	90.38 172	68.55 304	76.19 265	88.70 228	56.44 268	93.46 182	78.98 139	80.14 301	90.97 222

1314		76.53 288	75.30 296	80.21 293	83.93 337	62.32 305	84.66 285	88.81 243	60.23 404	70.16 363	84.07 356	55.30 275	90.73 310	67.37 274	83.21 262	87.59 344

reproduce_monomvs		75.40 311	74.38 309	78.46 333	83.92 338	57.80 365	83.78 311	86.94 296	73.47 181	72.25 341	84.47 342	38.74 429	89.27 334	75.32 189	70.53 411	88.31 327

MS-PatchMatch		73.83 328	72.67 330	77.30 356	83.87 339	66.02 198	81.82 343	84.66 331	61.37 397	68.61 381	82.82 383	47.29 362	88.21 354	59.27 348	84.32 239	77.68 452

fmvsm_s_conf0.1_n_a		83.32 124	82.99 121	84.28 144	83.79 340	68.07 145	89.34 111	82.85 365	69.80 271	87.36 58	94.06 59	68.34 117	91.56 273	87.95 42	83.46 258	93.21 127

v1144		80.03 205	79.03 208	83.01 211	83.78 341	64.51 248	87.11 203	90.57 167	71.96 213	78.08 219	86.20 305	61.41 211	93.94 147	74.93 192	77.23 334	90.60 238

OurMVSNet-221017-0		74.26 321	72.42 334	79.80 302	83.76 342	59.59 344	85.92 251	86.64 303	66.39 333	66.96 400	87.58 261	39.46 424	91.60 269	65.76 289	69.27 416	88.22 330

mmtdpeth		74.16 323	73.01 327	77.60 352	83.72 343	61.13 320	85.10 274	85.10 326	72.06 211	77.21 242	80.33 411	43.84 398	85.75 381	77.14 162	52.61 462	85.91 386

viewdifsd2359ckpt11		80.37 197	79.73 188	82.30 240	83.70 344	62.39 301	84.20 303	86.67 301	73.22 191	80.90 165	90.62 170	63.00 183	91.56 273	76.81 169	78.44 319	92.95 147

viewmsd2359difaftdt		80.37 197	79.73 188	82.30 240	83.70 344	62.39 301	84.20 303	86.67 301	73.22 191	80.90 165	90.62 170	63.00 183	91.56 273	76.81 169	78.44 319	92.95 147

v2v482		80.23 201	79.29 202	83.05 209	83.62 346	64.14 257	87.04 204	89.97 188	73.61 175	78.18 216	87.22 273	61.10 219	93.82 156	76.11 176	76.78 343	91.18 213

XXY-MVS		75.41 310	75.56 287	74.96 379	83.59 347	57.82 364	80.59 365	83.87 344	66.54 332	74.93 303	88.31 241	63.24 175	80.09 425	62.16 322	76.85 341	86.97 364

v1192		79.59 212	78.43 221	83.07 208	83.55 348	64.52 247	86.93 211	90.58 165	70.83 240	77.78 226	85.90 309	59.15 241	93.94 147	73.96 202	77.19 336	90.76 230

EGC-MVSNET		52.07 436	47.05 440	67.14 437	83.51 349	60.71 329	80.50 367	67.75 459	0.07 487	0.43 488	75.85 449	24.26 464	81.54 417	28.82 470	62.25 442	59.16 470

v7n		78.97 232	77.58 248	83.14 203	83.45 350	65.51 214	88.32 159	91.21 145	73.69 173	72.41 338	86.32 303	57.93 250	93.81 157	69.18 257	75.65 360	90.11 260

v144192		79.47 215	78.37 222	82.78 227	83.35 351	63.96 260	86.96 208	90.36 175	69.99 266	77.50 230	85.67 316	60.66 227	93.77 160	74.27 199	76.58 344	90.62 236

tpm2		73.26 339	71.46 343	78.63 324	83.34 352	56.71 382	80.65 364	80.40 396	56.63 435	73.55 322	82.02 395	51.80 317	91.24 290	56.35 381	78.42 322	87.95 334

v1921920		79.22 224	78.03 230	82.80 223	83.30 353	63.94 262	86.80 216	90.33 176	69.91 269	77.48 231	85.53 320	58.44 247	93.75 162	73.60 204	76.85 341	90.71 234

diffmvs_AUTHOR		82.38 141	82.27 137	82.73 231	83.26 354	63.80 265	83.89 309	89.76 195	73.35 185	82.37 137	90.84 164	66.25 143	90.79 306	82.77 93	87.93 171	93.59 109

baseline2		75.70 304	73.83 317	81.30 263	83.26 354	61.79 315	82.57 337	80.65 388	66.81 322	66.88 401	83.42 371	57.86 252	92.19 247	63.47 304	79.57 305	89.91 273

v1240		78.99 231	77.78 240	82.64 232	83.21 356	63.54 276	86.62 225	90.30 178	69.74 276	77.33 234	85.68 315	57.04 262	93.76 161	73.13 212	76.92 338	90.62 236

XVG-ACMP-BASELINE		76.11 299	74.27 311	81.62 253	83.20 357	64.67 244	83.60 318	89.75 197	69.75 274	71.85 345	87.09 278	32.78 448	92.11 249	69.99 249	80.43 297	88.09 333

MDTV_nov1_ep13			69.97 363		83.18 358	53.48 419	77.10 414	80.18 401	60.45 401	69.33 375	80.44 408	48.89 357	86.90 369	51.60 404	78.51 318

PatchmatchNet		73.12 341	71.33 346	78.49 332	83.18 358	60.85 326	79.63 379	78.57 414	64.13 362	71.73 346	79.81 419	51.20 325	85.97 380	57.40 369	76.36 354	88.66 318
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Fast-Effi-MVS+-dtu		78.02 257	76.49 273	82.62 233	83.16 360	66.96 185	86.94 210	87.45 283	72.45 202	71.49 350	84.17 354	54.79 281	91.58 270	67.61 271	80.31 298	89.30 293

gg-mvs-nofinetune		69.95 377	67.96 380	75.94 365	83.07 361	54.51 412	77.23 412	70.29 451	63.11 375	70.32 359	62.33 465	43.62 399	88.69 347	53.88 393	87.76 175	84.62 407

MVSTER		79.01 230	77.88 236	82.38 238	83.07 361	64.80 242	84.08 308	88.95 239	69.01 296	78.69 200	87.17 276	54.70 282	92.43 236	74.69 193	80.57 295	89.89 275

K. test v3		71.19 360	68.51 372	79.21 316	83.04 363	57.78 366	84.35 300	76.91 428	72.90 198	62.99 434	82.86 382	39.27 425	91.09 300	61.65 328	52.66 461	88.75 315

FE-MVSNET3		76.43 293	75.32 295	79.76 303	83.00 364	60.72 328	81.74 345	88.76 249	68.99 297	72.98 329	84.19 353	56.41 269	90.27 314	62.39 317	79.40 309	88.31 327

eth_miper_zixun_eth		77.92 260	76.69 270	81.61 255	83.00 364	61.98 311	83.15 328	89.20 226	69.52 279	74.86 304	84.35 347	61.76 203	92.56 229	71.50 231	72.89 396	90.28 253

diffmvs		82.10 144	81.88 146	82.76 229	83.00 364	63.78 267	83.68 314	89.76 195	72.94 197	82.02 144	89.85 189	65.96 151	90.79 306	82.38 100	87.30 183	93.71 98
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvsmconf0.1_n		85.61 71	85.65 71	85.50 88	82.99 367	69.39 107	89.65 95	90.29 179	73.31 186	87.77 49	94.15 55	71.72 61	93.23 193	90.31 9	90.67 117	93.89 87

FMVSNet5		69.50 380	67.96 380	74.15 390	82.97 368	55.35 403	80.01 376	82.12 372	62.56 385	63.02 432	81.53 398	36.92 437	81.92 415	48.42 424	74.06 384	85.17 399

viewmambaseed2359dif		80.41 193	79.84 185	82.12 242	82.95 369	62.50 300	83.39 322	88.06 265	67.11 320	80.98 163	90.31 179	66.20 145	91.01 302	74.62 194	84.90 226	92.86 150

c3_l		78.75 236	77.91 233	81.26 265	82.89 370	61.56 317	84.09 307	89.13 230	69.97 267	75.56 276	84.29 348	66.36 141	92.09 250	73.47 207	75.48 364	90.12 259

sss		73.60 331	73.64 319	73.51 396	82.80 371	55.01 407	76.12 417	81.69 377	62.47 386	74.68 307	85.85 312	57.32 258	78.11 433	60.86 335	80.93 287	87.39 347

GA-MVS		76.87 283	75.17 298	81.97 248	82.75 372	62.58 297	81.44 352	86.35 310	72.16 210	74.74 305	82.89 381	46.20 378	92.02 253	68.85 262	81.09 286	91.30 211

v148		78.72 238	77.80 239	81.47 257	82.73 373	61.96 312	86.30 239	88.08 263	73.26 188	76.18 266	85.47 322	62.46 190	92.36 240	71.92 228	73.82 388	90.09 262

IterMVS-SCA-FT		75.43 309	73.87 316	80.11 296	82.69 374	64.85 241	81.57 349	83.47 350	69.16 290	70.49 357	84.15 355	51.95 313	88.15 355	69.23 256	72.14 402	87.34 350

miper_ehance_all_eth		78.59 242	77.76 242	81.08 271	82.66 375	61.56 317	83.65 315	89.15 228	68.87 299	75.55 277	83.79 361	66.49 139	92.03 251	73.25 210	76.39 349	89.64 283

CostFormer		75.24 313	73.90 315	79.27 314	82.65 376	58.27 355	80.80 358	82.73 367	61.57 394	75.33 290	83.13 376	55.52 273	91.07 301	64.98 295	78.34 324	88.45 324

EPNet_dtu		75.46 308	74.86 300	77.23 357	82.57 377	54.60 410	86.89 212	83.09 358	71.64 216	66.25 412	85.86 311	55.99 270	88.04 357	54.92 387	86.55 197	89.05 300
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
RPSCF		73.23 340	71.46 343	78.54 329	82.50 378	59.85 340	82.18 341	82.84 366	58.96 416	71.15 354	89.41 211	45.48 388	84.77 394	58.82 355	71.83 404	91.02 221

cl____		77.72 265	76.76 267	80.58 283	82.49 379	60.48 333	83.09 330	87.87 271	69.22 287	74.38 313	85.22 329	62.10 197	91.53 278	71.09 234	75.41 368	89.73 282

DIV-MVS_self_test		77.72 265	76.76 267	80.58 283	82.48 380	60.48 333	83.09 330	87.86 272	69.22 287	74.38 313	85.24 327	62.10 197	91.53 278	71.09 234	75.40 369	89.74 281

tpm cat1		70.57 368	68.31 374	77.35 355	82.41 381	57.95 361	78.08 403	80.22 399	52.04 448	68.54 382	77.66 437	52.00 312	87.84 360	51.77 402	72.07 403	86.25 376

cl22		78.07 255	77.01 259	81.23 266	82.37 382	61.83 314	83.55 319	87.98 267	68.96 298	75.06 299	83.87 357	61.40 212	91.88 260	73.53 205	76.39 349	89.98 271

tpm		72.37 350	71.71 340	74.35 387	82.19 383	52.00 428	79.22 385	77.29 425	64.56 356	72.95 331	83.68 366	51.35 321	83.26 407	58.33 361	75.80 358	87.81 338

tpmvs		71.09 362	69.29 367	76.49 362	82.04 384	56.04 393	78.92 391	81.37 382	64.05 366	67.18 398	78.28 432	49.74 344	89.77 324	49.67 418	72.37 398	83.67 418

dmvs_re		71.14 361	70.58 355	72.80 404	81.96 385	59.68 342	75.60 423	79.34 408	68.55 304	69.27 376	80.72 407	49.42 347	76.54 441	52.56 400	77.79 328	82.19 434

pmmvs4		74.03 327	71.91 338	80.39 286	81.96 385	68.32 135	81.45 351	82.14 371	59.32 412	69.87 369	85.13 331	52.40 303	88.13 356	60.21 340	74.74 379	84.73 406

TinyColmap		67.30 398	64.81 405	74.76 383	81.92 387	56.68 383	80.29 371	81.49 380	60.33 402	56.27 458	83.22 373	24.77 463	87.66 363	45.52 442	69.47 415	79.95 447

ITE_SJBPF				78.22 335	81.77 388	60.57 331		83.30 352	69.25 286	67.54 391	87.20 274	36.33 441	87.28 367	54.34 390	74.62 380	86.80 367

miper_enhance_ethall		77.87 262	76.86 263	80.92 276	81.65 389	61.38 319	82.68 335	88.98 236	65.52 344	75.47 278	82.30 390	65.76 153	92.00 254	72.95 213	76.39 349	89.39 290

MVS-HIRNet		59.14 424	57.67 426	63.57 443	81.65 389	43.50 467	71.73 440	65.06 466	39.59 468	51.43 463	57.73 471	38.34 432	82.58 411	39.53 456	73.95 385	64.62 467

GG-mvs-BLEND				75.38 375	81.59 391	55.80 397	79.32 383	69.63 453		67.19 397	73.67 454	43.24 401	88.90 345	50.41 410	84.50 232	81.45 439

MonoMVSNet		76.49 292	75.80 281	78.58 327	81.55 392	58.45 352	86.36 237	86.22 311	74.87 143	74.73 306	83.73 363	51.79 318	88.73 346	70.78 236	72.15 401	88.55 323

IterMVS		74.29 320	72.94 328	78.35 334	81.53 393	63.49 278	81.58 348	82.49 368	68.06 312	69.99 366	83.69 365	51.66 320	85.54 385	65.85 288	71.64 405	86.01 383
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 280x420		66.51 404	64.71 406	71.90 410	81.45 394	63.52 277	57.98 475	68.95 457	53.57 444	62.59 436	76.70 440	46.22 377	75.29 456	55.25 384	79.68 304	76.88 454

gm-plane-assit					81.40 395	53.83 417			62.72 384		80.94 404		92.39 238	63.40 306

pmmvs6		74.69 317	73.39 321	78.61 325	81.38 396	57.48 371	86.64 224	87.95 269	64.99 353	70.18 361	86.61 292	50.43 334	89.52 329	62.12 323	70.18 413	88.83 311

test-LLR		72.94 345	72.43 333	74.48 385	81.35 397	58.04 358	78.38 398	77.46 421	66.66 326	69.95 367	79.00 426	48.06 359	79.24 427	66.13 283	84.83 227	86.15 379

test-mter		71.41 359	70.39 360	74.48 385	81.35 397	58.04 358	78.38 398	77.46 421	60.32 403	69.95 367	79.00 426	36.08 442	79.24 427	66.13 283	84.83 227	86.15 379

CR-MVSNet		73.37 334	71.27 348	79.67 307	81.32 399	65.19 224	75.92 419	80.30 397	59.92 407	72.73 333	81.19 399	52.50 301	86.69 370	59.84 342	77.71 329	87.11 360

RPMNet		73.51 332	70.49 357	82.58 235	81.32 399	65.19 224	75.92 419	92.27 91	57.60 429	72.73 333	76.45 442	52.30 304	95.43 77	48.14 429	77.71 329	87.11 360

V42		79.38 221	78.24 226	82.83 220	81.10 401	65.50 215	85.55 262	89.82 192	71.57 221	78.21 214	86.12 307	60.66 227	93.18 201	75.64 183	75.46 366	89.81 279

lessismore_v0				78.97 319	81.01 402	57.15 375		65.99 463		61.16 440	82.82 383	39.12 427	91.34 287	59.67 344	46.92 468	88.43 325

Patchmtry		70.74 366	69.16 369	75.49 373	80.72 403	54.07 415	74.94 430	80.30 397	58.34 421	70.01 364	81.19 399	52.50 301	86.54 372	53.37 396	71.09 409	85.87 388

PatchT		68.46 391	67.85 382	70.29 422	80.70 404	43.93 466	72.47 438	74.88 437	60.15 405	70.55 355	76.57 441	49.94 341	81.59 416	50.58 409	74.83 378	85.34 394

USDC		70.33 372	68.37 373	76.21 364	80.60 405	56.23 391	79.19 386	86.49 306	60.89 398	61.29 439	85.47 322	31.78 451	89.47 331	53.37 396	76.21 355	82.94 428

tpmrst		72.39 348	72.13 337	73.18 401	80.54 406	49.91 445	79.91 378	79.08 411	63.11 375	71.69 347	79.95 416	55.32 274	82.77 410	65.66 290	73.89 386	86.87 365

anonymousdsp		78.60 241	77.15 257	82.98 214	80.51 407	67.08 181	87.24 200	89.53 205	65.66 342	75.16 295	87.19 275	52.52 300	92.25 245	77.17 161	79.34 311	89.61 284

OpenMVS_ROB	64.09 19	70.56 369	68.19 375	77.65 349	80.26 408	59.41 347	85.01 277	82.96 363	58.76 419	65.43 417	82.33 389	37.63 436	91.23 291	45.34 444	76.03 356	82.32 432

test_fmvsmconf0.01_n		84.73 89	84.52 91	85.34 92	80.25 409	69.03 110	89.47 102	89.65 200	73.24 190	86.98 62	94.27 47	66.62 136	93.23 193	90.26 10	89.95 130	93.78 96

Anonymous20231206		68.60 387	67.80 385	71.02 419	80.23 410	50.75 442	78.30 402	80.47 392	56.79 434	66.11 414	82.63 386	46.35 375	78.95 429	43.62 447	75.70 359	83.36 421

miper_lstm_enhance		74.11 324	73.11 326	77.13 358	80.11 411	59.62 343	72.23 439	86.92 298	66.76 324	70.40 358	82.92 380	56.93 263	82.92 408	69.06 259	72.63 397	88.87 309

MIMVSNet1		68.58 388	66.78 398	73.98 392	80.07 412	51.82 432	80.77 360	84.37 334	64.40 359	59.75 447	82.16 393	36.47 440	83.63 402	42.73 450	70.33 412	86.48 374

ADS-MVSNet2		66.20 409	63.33 413	74.82 382	79.92 413	58.75 350	67.55 458	75.19 435	53.37 445	65.25 419	75.86 447	42.32 407	80.53 424	41.57 453	68.91 418	85.18 397

ADS-MVSNet		64.36 414	62.88 417	68.78 430	79.92 413	47.17 454	67.55 458	71.18 449	53.37 445	65.25 419	75.86 447	42.32 407	73.99 461	41.57 453	68.91 418	85.18 397

test_vis1_n_1920		75.52 307	75.78 282	74.75 384	79.84 415	57.44 372	83.26 326	85.52 321	62.83 381	79.34 192	86.17 306	45.10 389	79.71 426	78.75 141	81.21 285	87.10 362

D2MVS		74.82 316	73.21 324	79.64 308	79.81 416	62.56 299	80.34 370	87.35 285	64.37 360	68.86 378	82.66 385	46.37 374	90.10 318	67.91 269	81.24 284	86.25 376

our_test_3		69.14 383	67.00 396	75.57 370	79.80 417	58.80 349	77.96 405	77.81 418	59.55 410	62.90 435	78.25 433	47.43 361	83.97 399	51.71 403	67.58 424	83.93 415

ppachtmachnet_test		70.04 376	67.34 394	78.14 337	79.80 417	61.13 320	79.19 386	80.59 389	59.16 414	65.27 418	79.29 423	46.75 370	87.29 366	49.33 420	66.72 425	86.00 385

dp		66.80 401	65.43 402	70.90 421	79.74 419	48.82 449	75.12 428	74.77 438	59.61 409	64.08 428	77.23 438	42.89 403	80.72 423	48.86 423	66.58 427	83.16 423

EPMVS		69.02 384	68.16 376	71.59 412	79.61 420	49.80 447	77.40 410	66.93 461	62.82 382	70.01 364	79.05 424	45.79 382	77.86 435	56.58 379	75.26 373	87.13 359

PVSNet_0	57.27 20	61.67 421	59.27 424	68.85 429	79.61 420	57.44 372	68.01 456	73.44 444	55.93 438	58.54 450	70.41 461	44.58 392	77.55 436	47.01 433	35.91 473	71.55 461

CL-MVSNet_self_test		72.37 350	71.46 343	75.09 378	79.49 422	53.53 418	80.76 361	85.01 329	69.12 291	70.51 356	82.05 394	57.92 251	84.13 398	52.27 401	66.00 430	87.60 342

Patchmatch-test		64.82 413	63.24 414	69.57 424	79.42 423	49.82 446	63.49 472	69.05 456	51.98 450	59.95 446	80.13 414	50.91 327	70.98 465	40.66 455	73.57 389	87.90 336

MDA-MVSNet-bldmvs		66.68 402	63.66 412	75.75 367	79.28 424	60.56 332	73.92 435	78.35 416	64.43 357	50.13 466	79.87 418	44.02 397	83.67 401	46.10 439	56.86 452	83.03 426

TESTMET0.1,1		69.89 378	69.00 370	72.55 406	79.27 425	56.85 378	78.38 398	74.71 440	57.64 428	68.09 386	77.19 439	37.75 435	76.70 440	63.92 302	84.09 242	84.10 413

N_pmnet		52.79 434	53.26 432	51.40 459	78.99 426	7.68 493	69.52 450	3.89 492	51.63 451	57.01 455	74.98 451	40.83 418	65.96 474	37.78 460	64.67 435	80.56 446

UWE-MVS-28		65.32 410	64.93 404	66.49 439	78.70 427	38.55 476	77.86 408	64.39 468	62.00 392	64.13 427	83.60 367	41.44 413	76.00 448	31.39 468	80.89 288	84.92 402

dmvs_testset		62.63 418	64.11 409	58.19 449	78.55 428	24.76 487	75.28 424	65.94 464	67.91 313	60.34 443	76.01 446	53.56 293	73.94 462	31.79 467	67.65 423	75.88 456

EU-MVSNet		68.53 390	67.61 389	71.31 417	78.51 429	47.01 455	84.47 291	84.27 338	42.27 464	66.44 411	84.79 339	40.44 420	83.76 400	58.76 356	68.54 421	83.17 422

FE-MVSNET2		72.88 346	71.28 347	77.67 347	78.30 430	57.78 366	84.43 296	88.92 241	69.56 277	64.61 423	81.67 397	46.73 371	88.54 351	59.33 347	67.99 422	86.69 371

blend_shiyan4		72.29 352	69.65 364	80.21 293	78.24 431	62.16 308	82.29 339	87.27 288	65.41 347	68.43 385	76.42 444	39.91 423	91.23 291	63.21 308	65.66 432	87.22 354

pmmvs5		71.55 358	70.20 362	75.61 369	77.83 432	56.39 387	81.74 345	80.89 384	57.76 427	67.46 393	84.49 341	49.26 351	85.32 389	57.08 372	75.29 372	85.11 400

usedtu_blend_shiyan5		73.29 338	70.96 352	80.25 291	77.80 433	62.16 308	84.44 295	87.38 284	64.41 358	68.09 386	76.28 445	51.32 322	91.23 291	63.21 308	65.76 431	87.35 349

test0.0.03 1		68.00 394	67.69 387	68.90 428	77.55 434	47.43 451	75.70 422	72.95 447	66.66 326	66.56 406	82.29 391	48.06 359	75.87 450	44.97 445	74.51 381	83.41 420

Patchmatch-RL test		70.24 373	67.78 386	77.61 350	77.43 435	59.57 345	71.16 443	70.33 450	62.94 379	68.65 380	72.77 456	50.62 331	85.49 386	69.58 254	66.58 427	87.77 339

pmmvs-eth3d		70.50 370	67.83 384	78.52 331	77.37 436	66.18 195	81.82 343	81.51 379	58.90 417	63.90 430	80.42 409	42.69 405	86.28 376	58.56 357	65.30 434	83.11 424

JIA-IIPM		66.32 406	62.82 418	76.82 360	77.09 437	61.72 316	65.34 466	75.38 434	58.04 426	64.51 424	62.32 466	42.05 411	86.51 373	51.45 406	69.22 417	82.21 433

Gipuma		45.18 443	41.86 446	55.16 456	77.03 438	51.52 435	32.50 481	80.52 391	32.46 476	27.12 479	35.02 480	9.52 482	75.50 452	22.31 477	60.21 449	38.45 479
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDA-MVSNet_test_wron		65.03 411	62.92 415	71.37 414	75.93 439	56.73 380	69.09 455	74.73 439	57.28 432	54.03 461	77.89 434	45.88 380	74.39 459	49.89 417	61.55 444	82.99 427

test_cas_vis1_n_1920		73.76 329	73.74 318	73.81 394	75.90 440	59.77 341	80.51 366	82.40 369	58.30 422	81.62 153	85.69 314	44.35 395	76.41 444	76.29 173	78.61 315	85.23 396

FE-MVSNET		67.25 399	65.33 403	73.02 402	75.86 441	52.54 426	80.26 373	80.56 390	63.80 371	60.39 442	79.70 420	41.41 414	84.66 396	43.34 448	62.62 441	81.86 436

YYNet1		65.03 411	62.91 416	71.38 413	75.85 442	56.60 384	69.12 454	74.66 441	57.28 432	54.12 460	77.87 435	45.85 381	74.48 458	49.95 416	61.52 445	83.05 425

PMMVS		69.34 382	68.67 371	71.35 416	75.67 443	62.03 310	75.17 425	73.46 443	50.00 454	68.68 379	79.05 424	52.07 311	78.13 432	61.16 333	82.77 267	73.90 458

testgi		66.67 403	66.53 399	67.08 438	75.62 444	41.69 473	75.93 418	76.50 430	66.11 335	65.20 421	86.59 293	35.72 443	74.71 457	43.71 446	73.38 393	84.84 404

test20.03		67.45 396	66.95 397	68.94 427	75.48 445	44.84 464	77.50 409	77.67 419	66.66 326	63.01 433	83.80 360	47.02 365	78.40 431	42.53 452	68.86 420	83.58 419

KD-MVS_2432*1600		66.22 407	63.89 410	73.21 398	75.47 446	53.42 420	70.76 446	84.35 335	64.10 364	66.52 408	78.52 430	34.55 445	84.98 391	50.40 411	50.33 465	81.23 440

miper_refine_blended		66.22 407	63.89 410	73.21 398	75.47 446	53.42 420	70.76 446	84.35 335	64.10 364	66.52 408	78.52 430	34.55 445	84.98 391	50.40 411	50.33 465	81.23 440

Anonymous20240521		68.80 386	67.22 395	73.55 395	74.33 448	54.11 414	83.18 327	85.61 320	58.15 423	61.68 438	80.94 404	30.71 454	81.27 420	57.00 374	73.34 394	85.28 395

KD-MVS_self_test		68.81 385	67.59 390	72.46 408	74.29 449	45.45 458	77.93 406	87.00 294	63.12 374	63.99 429	78.99 428	42.32 407	84.77 394	56.55 380	64.09 437	87.16 358

mvs5depth		69.45 381	67.45 392	75.46 374	73.93 450	55.83 396	79.19 386	83.23 354	66.89 321	71.63 348	83.32 372	33.69 447	85.09 390	59.81 343	55.34 458	85.46 392

PM-MVS		66.41 405	64.14 408	73.20 400	73.92 451	56.45 385	78.97 390	64.96 467	63.88 370	64.72 422	80.24 413	19.84 471	83.44 405	66.24 282	64.52 436	79.71 448

test_fmvs1		70.93 364	70.52 356	72.16 409	73.71 452	55.05 406	80.82 357	78.77 413	51.21 453	78.58 204	84.41 344	31.20 453	76.94 439	75.88 181	80.12 302	84.47 408

UnsupCasMVSNet_bld		63.70 416	61.53 422	70.21 423	73.69 453	51.39 437	72.82 437	81.89 374	55.63 439	57.81 453	71.80 458	38.67 430	78.61 430	49.26 421	52.21 463	80.63 444

WB-MVS		54.94 428	54.72 429	55.60 455	73.50 454	20.90 489	74.27 434	61.19 472	59.16 414	50.61 464	74.15 452	47.19 364	75.78 451	17.31 480	35.07 474	70.12 462

UnsupCasMVSNet_eth		67.33 397	65.99 401	71.37 414	73.48 455	51.47 436	75.16 426	85.19 324	65.20 348	60.78 441	80.93 406	42.35 406	77.20 437	57.12 371	53.69 460	85.44 393

TDRefinement		67.49 395	64.34 407	76.92 359	73.47 456	61.07 323	84.86 281	82.98 362	59.77 408	58.30 451	85.13 331	26.06 459	87.89 359	47.92 431	60.59 448	81.81 438

dongtai		45.42 442	45.38 443	45.55 461	73.36 457	26.85 485	67.72 457	34.19 487	54.15 443	49.65 467	56.41 474	25.43 460	62.94 477	19.45 478	28.09 478	46.86 477

ambc				75.24 377	73.16 458	50.51 443	63.05 473	87.47 282		64.28 425	77.81 436	17.80 473	89.73 326	57.88 365	60.64 447	85.49 391

CMPMVS	51.72 21	70.19 374	68.16 376	76.28 363	73.15 459	57.55 370	79.47 381	83.92 342	48.02 457	56.48 457	84.81 338	43.13 402	86.42 375	62.67 315	81.81 280	84.89 403
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SSC-MVS		53.88 431	53.59 431	54.75 457	72.87 460	19.59 490	73.84 436	60.53 474	57.58 430	49.18 468	73.45 455	46.34 376	75.47 454	16.20 483	32.28 476	69.20 463

new-patchmatchnet		61.73 420	61.73 421	61.70 445	72.74 461	24.50 488	69.16 453	78.03 417	61.40 395	56.72 456	75.53 450	38.42 431	76.48 443	45.95 440	57.67 451	84.13 412

test_vis1_n		69.85 379	69.21 368	71.77 411	72.66 462	55.27 405	81.48 350	76.21 432	52.03 449	75.30 291	83.20 375	28.97 456	76.22 446	74.60 195	78.41 323	83.81 416

test_fmvs1_n		70.86 365	70.24 361	72.73 405	72.51 463	55.28 404	81.27 354	79.71 404	51.49 452	78.73 199	84.87 336	27.54 458	77.02 438	76.06 177	79.97 303	85.88 387

LF4IMVS		64.02 415	62.19 419	69.50 425	70.90 464	53.29 423	76.13 416	77.18 426	52.65 447	58.59 449	80.98 403	23.55 466	76.52 442	53.06 398	66.66 426	78.68 450

mvsany_test1		62.30 419	61.26 423	65.41 441	69.52 465	54.86 408	66.86 460	49.78 481	46.65 458	68.50 383	83.21 374	49.15 352	66.28 473	56.93 375	60.77 446	75.11 457

test_fmvs2		68.35 392	67.48 391	70.98 420	69.50 466	51.95 429	80.05 375	76.38 431	49.33 455	74.65 308	84.38 345	23.30 467	75.40 455	74.51 196	75.17 375	85.60 390

new_pmnet		50.91 437	50.29 437	52.78 458	68.58 467	34.94 480	63.71 470	56.63 478	39.73 467	44.95 469	65.47 464	21.93 468	58.48 478	34.98 464	56.62 453	64.92 466

DSMNet-mixed		57.77 426	56.90 428	60.38 447	67.70 468	35.61 478	69.18 452	53.97 479	32.30 477	57.49 454	79.88 417	40.39 421	68.57 471	38.78 459	72.37 398	76.97 453

test_vis1_rt		60.28 422	58.42 425	65.84 440	67.25 469	55.60 400	70.44 448	60.94 473	44.33 462	59.00 448	66.64 463	24.91 462	68.67 470	62.80 311	69.48 414	73.25 459

ttmdpeth		59.91 423	57.10 427	68.34 433	67.13 470	46.65 457	74.64 431	67.41 460	48.30 456	62.52 437	85.04 335	20.40 469	75.93 449	42.55 451	45.90 471	82.44 431

APD_test1		53.31 433	49.93 438	63.42 444	65.68 471	50.13 444	71.59 442	66.90 462	34.43 474	40.58 473	71.56 459	8.65 484	76.27 445	34.64 465	55.36 457	63.86 468

FPMVS		53.68 432	51.64 434	59.81 448	65.08 472	51.03 439	69.48 451	69.58 454	41.46 465	40.67 472	72.32 457	16.46 475	70.00 469	24.24 476	65.42 433	58.40 472

kuosan		39.70 446	40.40 447	37.58 464	64.52 473	26.98 483	65.62 465	33.02 488	46.12 459	42.79 471	48.99 477	24.10 465	46.56 485	12.16 486	26.30 479	39.20 478

pmmvs3		57.79 425	54.26 430	68.37 432	64.02 474	56.72 381	75.12 428	65.17 465	40.20 466	52.93 462	69.86 462	20.36 470	75.48 453	45.45 443	55.25 459	72.90 460

test_fmvs3		63.36 417	61.82 420	67.98 435	62.51 475	46.96 456	77.37 411	74.03 442	45.24 460	67.50 392	78.79 429	12.16 479	72.98 464	72.77 216	66.02 429	83.99 414

MVStest1		56.63 427	52.76 433	68.25 434	61.67 476	53.25 424	71.67 441	68.90 458	38.59 469	50.59 465	83.05 377	25.08 461	70.66 466	36.76 462	38.56 472	80.83 443

wuyk23d		16.82 453	15.94 456	19.46 468	58.74 477	31.45 481	39.22 479	3.74 493	6.84 484	6.04 487	2.70 487	1.27 491	24.29 487	10.54 487	14.40 486	2.63 484

testf1		45.72 440	41.96 444	57.00 450	56.90 478	45.32 459	66.14 463	59.26 475	26.19 478	30.89 477	60.96 469	4.14 487	70.64 467	26.39 474	46.73 469	55.04 473

APD_test2		45.72 440	41.96 444	57.00 450	56.90 478	45.32 459	66.14 463	59.26 475	26.19 478	30.89 477	60.96 469	4.14 487	70.64 467	26.39 474	46.73 469	55.04 473

mvsany_test3		53.99 430	51.45 435	61.61 446	55.51 480	44.74 465	63.52 471	45.41 485	43.69 463	58.11 452	76.45 442	17.99 472	63.76 476	54.77 388	47.59 467	76.34 455

test_vis3_rt		49.26 439	47.02 441	56.00 452	54.30 481	45.27 462	66.76 462	48.08 482	36.83 471	44.38 470	53.20 475	7.17 486	64.07 475	56.77 378	55.66 455	58.65 471

PMMVS2		40.82 445	38.86 449	46.69 460	53.84 482	16.45 491	48.61 478	49.92 480	37.49 470	31.67 475	60.97 468	8.14 485	56.42 480	28.42 471	30.72 477	67.19 465

test_f		52.09 435	50.82 436	55.90 453	53.82 483	42.31 472	59.42 474	58.31 477	36.45 472	56.12 459	70.96 460	12.18 478	57.79 479	53.51 395	56.57 454	67.60 464

LCM-MVSNet		54.25 429	49.68 439	67.97 436	53.73 484	45.28 461	66.85 461	80.78 386	35.96 473	39.45 474	62.23 467	8.70 483	78.06 434	48.24 428	51.20 464	80.57 445

E-PMN		31.77 447	30.64 450	35.15 465	52.87 485	27.67 482	57.09 476	47.86 483	24.64 480	16.40 485	33.05 481	11.23 480	54.90 481	14.46 484	18.15 482	22.87 481

EMVS		30.81 449	29.65 451	34.27 466	50.96 486	25.95 486	56.58 477	46.80 484	24.01 481	15.53 486	30.68 482	12.47 477	54.43 482	12.81 485	17.05 483	22.43 482

ANet_high		50.57 438	46.10 442	63.99 442	48.67 487	39.13 475	70.99 445	80.85 385	61.39 396	31.18 476	57.70 472	17.02 474	73.65 463	31.22 469	15.89 484	79.18 449

MVE	26.22 23	30.37 450	25.89 454	43.81 462	44.55 488	35.46 479	28.87 482	39.07 486	18.20 482	18.58 484	40.18 479	2.68 490	47.37 484	17.07 482	23.78 481	48.60 476
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	37.38 22	44.16 444	40.28 448	55.82 454	40.82 489	42.54 471	65.12 467	63.99 469	34.43 474	24.48 480	57.12 473	3.92 489	76.17 447	17.10 481	55.52 456	48.75 475
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepMVS_CX				27.40 467	40.17 490	26.90 484		24.59 491	17.44 483	23.95 481	48.61 478	9.77 481	26.48 486	18.06 479	24.47 480	28.83 480

test_method		31.52 448	29.28 452	38.23 463	27.03 491	6.50 494	20.94 483	62.21 471	4.05 485	22.35 483	52.50 476	13.33 476	47.58 483	27.04 473	34.04 475	60.62 469

tmp_tt		18.61 452	21.40 455	10.23 469	4.82 492	10.11 492	34.70 480	30.74 490	1.48 486	23.91 482	26.07 483	28.42 457	13.41 488	27.12 472	15.35 485	7.17 483

testmvs		6.04 456	8.02 459	0.10 471	0.08 493	0.03 496	69.74 449	0.04 494	0.05 488	0.31 489	1.68 488	0.02 493	0.04 489	0.24 488	0.02 487	0.25 486

test123		6.12 455	8.11 458	0.14 470	0.06 494	0.09 495	71.05 444	0.03 495	0.04 489	0.25 490	1.30 489	0.05 492	0.03 490	0.21 489	0.01 488	0.29 485

mmdepth		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

monomultidepth		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

test_blank		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

eth-test2					0.00 495

eth-test					0.00 495

uanet_test		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

DCPMVS		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

cdsmvs_eth3d_5k		19.96 451	26.61 453	0.00 472	0.00 495	0.00 497	0.00 484	89.26 221	0.00 490	0.00 491	88.61 232	61.62 206	0.00 491	0.00 490	0.00 489	0.00 487

pcd_1.5k_mvsjas		5.26 457	7.02 460	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	63.15 178	0.00 491	0.00 490	0.00 489	0.00 487

sosnet-low-res		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

sosnet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uncertanet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

Regformer		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

ab-mvs-re		7.23 454	9.64 457	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	86.72 285	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uanet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

TestfortrainingZip							93.28 12

WAC-MVS						42.58 469								39.46 457

PC_three_1452									68.21 310	92.02 15	94.00 63	82.09 5	95.98 61	84.58 71	96.68 2	94.95 12

test_241102_TWO								94.06 15	77.24 61	92.78 4	95.72 8	81.26 10	97.44 7	89.07 25	96.58 6	94.26 67

test_0728_THIRD									78.38 38	92.12 12	95.78 4	81.46 9	97.40 9	89.42 19	96.57 7	94.67 36

GSMVS																88.96 306

sam_mvs1												51.32 322				88.96 306

sam_mvs												50.01 339

MTGPA								92.02 109

test_post1							78.90 392				5.43 486	48.81 358	85.44 388	59.25 349

test_post											5.46 485	50.36 335	84.24 397

patchmatchnet-post											74.00 453	51.12 326	88.60 349

MTMP							92.18 39	32.83 489

test9_res														84.90 64	95.70 30	92.87 149

agg_prior2														82.91 91	95.45 33	92.70 154

test_prior4						72.60 34	89.01 125

test_prior2							88.85 132		75.41 119	84.91 82	93.54 76	74.28 33		83.31 85	95.86 24

旧先验2							86.56 227		58.10 425	87.04 61			88.98 341	74.07 201

新几何2							86.29 241

无先验							87.48 186	88.98 236	60.00 406				94.12 140	67.28 275		88.97 305

原ACMM2							86.86 214

testdata2													91.01 302	62.37 319

segment_acmp												73.08 43

testdata1							84.14 306		75.71 110

plane_prior5								92.44 82					95.38 82	78.71 142	86.32 200	91.33 209

plane_prior4											91.00 161

plane_prior3						68.60 128			78.44 36	78.92 197

plane_prior2							91.25 60		79.12 28

plane_prior						68.71 123	90.38 78		77.62 47						86.16 205

n2								0.00 496

nn								0.00 496

door-mid								69.98 452

test11								92.23 95

door								69.44 455

HQP5-MVS						66.98 183

BP-MVS														77.47 157

HQP4-MVS										77.24 237			95.11 94			91.03 219

HQP3-MVS								92.19 103							85.99 209

HQP2-MVS												60.17 235

MDTV_nov1_ep13_2view						37.79 477	75.16 426		55.10 440	66.53 407		49.34 349		53.98 392		87.94 335

ACMMP++_ref															81.95 278

ACMMP++															81.25 283

Test By Simon												64.33 164

High-resolution multi-view benchmark