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.

APDe-MVS		89.15 5	89.63 5	87.73 27	94.49 18	71.69 55	93.83 2	93.96 14	75.70 89	91.06 12	96.03 1	76.84 12	97.03 12	89.09 3	95.65 28	94.47 23

SMA-MVS		89.08 6	89.23 6	88.61 3	94.25 28	73.73 8	92.40 20	93.63 20	74.77 107	92.29 6	95.97 2	74.28 31	97.24 8	88.58 10	96.91 1	94.87 9
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
test0726					95.27 5	71.25 59	93.60 4	94.11 6	77.33 46	92.81 3	95.79 3	80.98 7

DVP-MVS		89.60 2	90.35 2	87.33 42	95.27 5	71.25 59	93.49 7	92.73 60	77.33 46	92.12 8	95.78 4	80.98 7	97.40 4	89.08 4	96.41 8	93.33 75
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
test_0728_THIRD									78.38 32	92.12 8	95.78 4	81.46 5	97.40 4	89.42 2	96.57 5	94.67 16

SED-MVS		90.08 1	90.85 1	87.77 23	95.30 2	70.98 65	93.57 5	94.06 10	77.24 48	93.10 1	95.72 6	82.99 1	97.44 2	89.07 6	96.63 2	94.88 7

test_241102_TWO								94.06 10	77.24 48	92.78 4	95.72 6	81.26 6	97.44 2	89.07 6	96.58 4	94.26 31

DPE-MVS		89.48 4	89.98 3	88.01 12	94.80 9	72.69 30	91.59 40	94.10 8	75.90 85	92.29 6	95.66 8	81.67 4	97.38 6	87.44 17	96.34 11	93.95 44
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_241102_ONE					95.30 2	70.98 65		94.06 10	77.17 52	93.10 1	95.39 9	82.99 1	97.27 7

MP-MVS-pluss		87.67 21	87.72 21	87.54 36	93.64 45	72.04 49	89.80 80	93.50 25	75.17 101	86.34 36	95.29 10	70.86 57	96.00 50	88.78 9	96.04 12	94.58 19
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
xxxxxxxxxxxxxcwj		87.88 18	87.92 18	87.77 23	93.80 39	72.35 42	90.47 63	89.69 163	74.31 116	89.16 15	95.10 11	75.65 18	96.19 42	87.07 18	96.01 13	94.79 11

SF-MVS		88.46 10	88.74 10	87.64 35	92.78 64	71.95 50	92.40 20	94.74 2	75.71 87	89.16 15	95.10 11	75.65 18	96.19 42	87.07 18	96.01 13	94.79 11

ACMMP_NAP		88.05 15	88.08 16	87.94 15	93.70 42	73.05 21	90.86 53	93.59 22	76.27 78	88.14 22	95.09 13	71.06 56	96.67 25	87.67 13	96.37 10	94.09 36

zzz-MVS		87.53 23	87.41 26	87.90 19	94.18 32	74.25 3	90.23 70	92.02 89	79.45 19	85.88 38	94.80 14	68.07 83	96.21 40	86.69 21	95.34 32	93.23 78

MTAPA		87.23 32	87.00 33	87.90 19	94.18 32	74.25 3	86.58 180	92.02 89	79.45 19	85.88 38	94.80 14	68.07 83	96.21 40	86.69 21	95.34 32	93.23 78

SteuartSystems-ACMMP		88.72 9	88.86 9	88.32 6	92.14 75	72.96 24	93.73 3	93.67 19	80.19 14	88.10 23	94.80 14	73.76 36	97.11 10	87.51 15	95.82 20	94.90 6
Skip Steuart: Steuart Systems R&D Blog.
9.14			88.26 14		92.84 63		91.52 43	94.75 1	73.93 126	88.57 20	94.67 17	75.57 20	95.79 55	86.77 20	95.76 24

SR-MVS		86.73 38	86.67 39	86.91 49	94.11 35	72.11 48	92.37 24	92.56 68	74.50 112	86.84 33	94.65 18	67.31 92	95.77 56	84.80 34	92.85 71	92.84 94

ETH3D-3000-0.1		88.09 12	88.29 13	87.50 38	92.76 65	71.89 53	91.43 44	94.70 3	74.47 113	88.86 18	94.61 19	75.23 21	95.84 54	86.62 23	95.92 17	94.78 13

test1172		86.20 49	86.22 45	86.12 67	93.95 37	69.89 91	91.79 38	92.28 77	75.07 102	86.40 35	94.58 20	65.00 117	95.56 61	84.34 41	92.60 74	92.90 92

region2R		87.42 27	87.20 31	88.09 10	94.63 12	73.55 11	93.03 12	93.12 39	76.73 67	84.45 64	94.52 21	69.09 78	96.70 23	84.37 40	94.83 46	94.03 39

ACMMPR		87.44 25	87.23 30	88.08 11	94.64 11	73.59 10	93.04 10	93.20 36	76.78 64	84.66 61	94.52 21	68.81 81	96.65 26	84.53 37	94.90 41	94.00 42

APD-MVS		87.44 25	87.52 23	87.19 44	94.24 29	72.39 40	91.86 36	92.83 56	73.01 144	88.58 19	94.52 21	73.36 37	96.49 34	84.26 42	95.01 38	92.70 97
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
APD-MVS_3200maxsize		85.97 50	85.88 52	86.22 64	92.69 67	69.53 98	91.93 33	92.99 46	73.54 134	85.94 37	94.51 24	65.80 109	95.61 59	83.04 58	92.51 76	93.53 70

CP-MVS		87.11 34	86.92 35	87.68 34	94.20 31	73.86 6	93.98 1	92.82 59	76.62 69	83.68 77	94.46 25	67.93 85	95.95 52	84.20 44	94.39 55	93.23 78

SR-MVS-dyc-post		85.77 53	85.61 55	86.23 63	93.06 57	70.63 77	91.88 34	92.27 78	73.53 135	85.69 42	94.45 26	65.00 117	95.56 61	82.75 61	91.87 79	92.50 104

RE-MVS-def			85.48 56		93.06 57	70.63 77	91.88 34	92.27 78	73.53 135	85.69 42	94.45 26	63.87 124		82.75 61	91.87 79	92.50 104

HFP-MVS		87.58 22	87.47 24	87.94 15	94.58 14	73.54 13	93.04 10	93.24 34	76.78 64	84.91 52	94.44 28	70.78 58	96.61 29	84.53 37	94.89 42	93.66 58

#test#		87.33 30	87.13 32	87.94 15	94.58 14	73.54 13	92.34 25	93.24 34	75.23 98	84.91 52	94.44 28	70.78 58	96.61 29	83.75 49	94.89 42	93.66 58

testtj		87.78 19	87.78 20	87.77 23	94.55 16	72.47 37	92.23 28	93.49 27	74.75 108	88.33 21	94.43 30	73.27 39	97.02 13	84.18 45	94.84 44	93.82 52

PGM-MVS		86.68 40	86.27 44	87.90 19	94.22 30	73.38 17	90.22 71	93.04 40	75.53 91	83.86 74	94.42 31	67.87 87	96.64 27	82.70 65	94.57 51	93.66 58

MP-MVS		87.71 20	87.64 22	87.93 18	94.36 26	73.88 5	92.71 19	92.65 65	77.57 39	83.84 75	94.40 32	72.24 47	96.28 38	85.65 25	95.30 36	93.62 65
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		87.94 17	87.85 19	88.20 9	94.39 24	73.33 18	93.03 12	93.81 17	76.81 62	85.24 47	94.32 33	71.76 51	96.93 15	85.53 26	95.79 21	94.32 28

ETH3D cwj APD-0.16		87.31 31	87.27 27	87.44 40	91.60 82	72.45 39	90.02 74	94.37 4	71.76 158	87.28 30	94.27 34	75.18 22	96.08 46	85.16 27	95.77 22	93.80 55

HPM-MVS++		89.02 7	89.15 7	88.63 2	95.01 8	76.03 1	92.38 23	92.85 55	80.26 13	87.78 26	94.27 34	75.89 16	96.81 19	87.45 16	96.44 7	93.05 86

mPP-MVS		86.67 41	86.32 43	87.72 29	94.41 22	73.55 11	92.74 17	92.22 82	76.87 61	82.81 91	94.25 36	66.44 99	96.24 39	82.88 60	94.28 58	93.38 72

DeepC-MVS	79.81 2	87.08 36	86.88 37	87.69 33	91.16 86	72.32 44	90.31 68	93.94 15	77.12 54	82.82 90	94.23 37	72.13 49	97.09 11	84.83 33	95.37 31	93.65 63
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVS		87.18 33	86.91 36	88.00 13	94.42 20	73.33 18	92.78 15	92.99 46	79.14 21	83.67 78	94.17 38	67.45 90	96.60 31	83.06 56	94.50 52	94.07 37

MSP-MVS		89.51 3	89.91 4	88.30 7	94.28 27	73.46 16	92.90 14	94.11 6	80.27 12	91.35 11	94.16 39	78.35 10	96.77 20	89.59 1	94.22 60	94.67 16
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
abl_6		85.23 63	84.95 68	86.07 68	92.23 74	70.48 81	90.80 55	92.08 87	73.51 137	85.26 46	94.16 39	62.75 141	95.92 53	82.46 68	91.30 88	91.81 127

DeepPCF-MVS	80.84 1	88.10 11	88.56 11	86.73 53	92.24 73	69.03 105	89.57 86	93.39 32	77.53 43	89.79 14	94.12 41	78.98 9	96.58 33	85.66 24	95.72 25	94.58 19

HPM-MVS_fast		85.35 62	84.95 68	86.57 58	93.69 43	70.58 80	92.15 31	91.62 108	73.89 127	82.67 93	94.09 42	62.60 142	95.54 64	80.93 78	92.93 69	93.57 67

ZD-MVS					94.38 25	72.22 45		92.67 62	70.98 173	87.75 27	94.07 43	74.01 35	96.70 23	84.66 36	94.84 44

CNVR-MVS		88.93 8	89.13 8	88.33 5	94.77 10	73.82 7	90.51 60	93.00 44	80.90 9	88.06 24	94.06 44	76.43 13	96.84 17	88.48 11	95.99 15	94.34 27

OPU-MVS				89.06 1	94.62 13	75.42 2	93.57 5				94.02 45	82.45 3	96.87 16	83.77 48	96.48 6	94.88 7

SD-MVS		88.06 13	88.50 12	86.71 54	92.60 71	72.71 28	91.81 37	93.19 37	77.87 34	90.32 13	94.00 46	74.83 24	93.78 141	87.63 14	94.27 59	93.65 63
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
GST-MVS		87.42 27	87.26 28	87.89 22	94.12 34	72.97 23	92.39 22	93.43 30	76.89 60	84.68 58	93.99 47	70.67 61	96.82 18	84.18 45	95.01 38	93.90 47

HPM-MVS		87.11 34	86.98 34	87.50 38	93.88 38	72.16 46	92.19 29	93.33 33	76.07 81	83.81 76	93.95 48	69.77 71	96.01 49	85.15 28	94.66 48	94.32 28
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TSAR-MVS + MP.		88.02 16	88.11 15	87.72 29	93.68 44	72.13 47	91.41 45	92.35 75	74.62 111	88.90 17	93.85 49	75.75 17	96.00 50	87.80 12	94.63 49	95.04 3
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
ACMMP		85.89 52	85.39 58	87.38 41	93.59 46	72.63 32	92.74 17	93.18 38	76.78 64	80.73 116	93.82 50	64.33 120	96.29 37	82.67 66	90.69 93	93.23 78
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
test_prior3		86.73 38	86.86 38	86.33 60	92.61 69	69.59 96	88.85 105	92.97 49	75.41 93	84.91 52	93.54 51	74.28 31	95.48 66	83.31 51	95.86 18	93.91 45

test_prior2							88.85 105		75.41 93	84.91 52	93.54 51	74.28 31		83.31 51	95.86 18

ETH3 D test6400		87.50 24	87.44 25	87.70 32	93.71 41	71.75 54	90.62 58	94.05 13	70.80 175	87.59 29	93.51 53	77.57 11	96.63 28	83.31 51	95.77 22	94.72 15

VDDNet		81.52 114	80.67 117	84.05 122	90.44 100	64.13 204	89.73 83	85.91 247	71.11 170	83.18 83	93.48 54	50.54 263	93.49 156	73.40 144	88.25 123	94.54 22

CDPH-MVS		85.76 54	85.29 62	87.17 45	93.49 48	71.08 63	88.58 119	92.42 73	68.32 227	84.61 62	93.48 54	72.32 46	96.15 45	79.00 90	95.43 30	94.28 30

NCCC		88.06 13	88.01 17	88.24 8	94.41 22	73.62 9	91.22 49	92.83 56	81.50 6	85.79 41	93.47 56	73.02 42	97.00 14	84.90 30	94.94 40	94.10 35

3Dnovator+	77.84 4	85.48 58	84.47 73	88.51 4	91.08 87	73.49 15	93.18 9	93.78 18	80.79 10	76.66 180	93.37 57	60.40 185	96.75 22	77.20 110	93.73 64	95.29 2

DeepC-MVS_fast	79.65 3	86.91 37	86.62 40	87.76 26	93.52 47	72.37 41	91.26 46	93.04 40	76.62 69	84.22 69	93.36 58	71.44 54	96.76 21	80.82 80	95.33 34	94.16 33
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VDD-MVS		83.01 91	82.36 92	84.96 88	91.02 89	66.40 159	88.91 102	88.11 207	77.57 39	84.39 67	93.29 59	52.19 240	93.91 136	77.05 112	88.70 117	94.57 21

UA-Net		85.08 67	84.96 67	85.45 75	92.07 76	68.07 132	89.78 81	90.86 132	82.48 2	84.60 63	93.20 60	69.35 75	95.22 82	71.39 160	90.88 92	93.07 85

agg_prior1		86.22 48	86.09 50	86.62 56	92.85 61	71.94 51	88.59 118	91.78 104	68.96 217	84.41 65	93.18 61	74.94 23	94.93 94	84.75 35	95.33 34	93.01 89

TEST9					93.26 51	72.96 24	88.75 110	91.89 98	68.44 226	85.00 50	93.10 62	74.36 30	95.41 72

train_agg		86.43 44	86.20 46	87.13 46	93.26 51	72.96 24	88.75 110	91.89 98	68.69 222	85.00 50	93.10 62	74.43 27	95.41 72	84.97 29	95.71 26	93.02 88

test_8					93.13 53	72.57 34	88.68 115	91.84 101	68.69 222	84.87 56	93.10 62	74.43 27	95.16 85

LFMVS		81.82 107	81.23 108	83.57 137	91.89 79	63.43 220	89.84 77	81.85 298	77.04 57	83.21 82	93.10 62	52.26 239	93.43 161	71.98 155	89.95 105	93.85 49

旧先验1					91.96 77	65.79 171		86.37 241			93.08 66	69.31 77			92.74 72	88.74 236

testdata				79.97 232	90.90 91	64.21 202		84.71 257	59.27 314	85.40 44	92.91 67	62.02 155	89.08 270	68.95 184	91.37 86	86.63 283

MCST-MVS		87.37 29	87.25 29	87.73 27	94.53 17	72.46 38	89.82 78	93.82 16	73.07 142	84.86 57	92.89 68	76.22 14	96.33 36	84.89 32	95.13 37	94.40 24

Vis-MVSNet		83.46 81	82.80 87	85.43 76	90.25 103	68.74 115	90.30 69	90.13 151	76.33 77	80.87 115	92.89 68	61.00 174	94.20 121	72.45 154	90.97 90	93.35 74
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CPTT-MVS		83.73 76	83.33 79	84.92 91	93.28 50	70.86 72	92.09 32	90.38 141	68.75 221	79.57 124	92.83 70	60.60 181	93.04 180	80.92 79	91.56 84	90.86 156

3Dnovator	76.31 5	83.38 84	82.31 93	86.59 57	87.94 179	72.94 27	90.64 57	92.14 86	77.21 50	75.47 205	92.83 70	58.56 192	94.72 106	73.24 147	92.71 73	92.13 119

MSLP-MVS++		85.43 60	85.76 54	84.45 105	91.93 78	70.24 82	90.71 56	92.86 54	77.46 45	84.22 69	92.81 72	67.16 94	92.94 182	80.36 84	94.35 57	90.16 180

MG-MVS		83.41 82	83.45 77	83.28 146	92.74 66	62.28 239	88.17 136	89.50 167	75.22 99	81.49 106	92.74 73	66.75 95	95.11 87	72.85 150	91.58 83	92.45 107

casdiffmvs		85.11 66	85.14 63	85.01 86	87.20 204	65.77 172	87.75 147	92.83 56	77.84 35	84.36 68	92.38 74	72.15 48	93.93 135	81.27 76	90.48 96	95.33 1

baseline		84.93 68	84.98 65	84.80 96	87.30 202	65.39 180	87.30 158	92.88 53	77.62 37	84.04 73	92.26 75	71.81 50	93.96 129	81.31 75	90.30 98	95.03 4

QAPM		80.88 123	79.50 139	85.03 85	88.01 178	68.97 109	91.59 40	92.00 92	66.63 242	75.15 219	92.16 76	57.70 198	95.45 68	63.52 223	88.76 116	90.66 162

IS-MVSNet		83.15 86	82.81 86	84.18 116	89.94 110	63.30 222	91.59 40	88.46 204	79.04 25	79.49 125	92.16 76	65.10 114	94.28 115	67.71 191	91.86 81	94.95 5

1121		80.84 125	79.77 132	84.05 122	93.11 55	70.78 74	84.66 225	85.42 251	57.37 328	81.76 105	92.02 78	63.41 128	94.12 125	67.28 196	92.93 69	87.26 267

新几何1				83.42 141	93.13 53	70.71 75		85.48 250	57.43 327	81.80 101	91.98 79	63.28 130	92.27 200	64.60 220	92.99 68	87.27 266

OpenMVS	72.83 10	79.77 152	78.33 165	84.09 119	85.17 232	69.91 89	90.57 59	90.97 128	66.70 238	72.17 251	91.91 80	54.70 220	93.96 129	61.81 242	90.95 91	88.41 244

PHI-MVS		86.43 44	86.17 48	87.24 43	90.88 92	70.96 67	92.27 27	94.07 9	72.45 147	85.22 48	91.90 81	69.47 74	96.42 35	83.28 54	95.94 16	94.35 26

VNet		82.21 99	82.41 90	81.62 196	90.82 93	60.93 253	84.47 231	89.78 159	76.36 76	84.07 72	91.88 82	64.71 119	90.26 250	70.68 165	88.89 113	93.66 58

OPM-MVS		83.50 80	82.95 84	85.14 82	88.79 152	70.95 68	89.13 97	91.52 111	77.55 42	80.96 114	91.75 83	60.71 177	94.50 111	79.67 89	86.51 146	89.97 196

XVG-OURS-SEG-HR		80.81 128	79.76 133	83.96 130	85.60 226	68.78 112	83.54 253	90.50 138	70.66 180	76.71 179	91.66 84	60.69 178	91.26 231	76.94 114	81.58 201	91.83 125

EPNet		83.72 77	82.92 85	86.14 66	84.22 247	69.48 99	91.05 51	85.27 252	81.30 7	76.83 175	91.65 85	66.09 104	95.56 61	76.00 122	93.85 62	93.38 72
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OMC-MVS		82.69 94	81.97 101	84.85 93	88.75 154	67.42 143	87.98 140	90.87 131	74.92 105	79.72 123	91.65 85	62.19 152	93.96 129	75.26 129	86.42 147	93.16 83

test222					91.50 83	68.26 128	84.16 240	83.20 284	54.63 339	79.74 122	91.63 87	58.97 190			91.42 85	86.77 279

MVS_111021_HR		85.14 65	84.75 70	86.32 62	91.65 81	72.70 29	85.98 195	90.33 145	76.11 80	82.08 96	91.61 88	71.36 55	94.17 124	81.02 77	92.58 75	92.08 120

原ACMM1				84.35 110	93.01 59	68.79 111		92.44 70	63.96 276	81.09 112	91.57 89	66.06 105	95.45 68	67.19 199	94.82 47	88.81 233

LPG-MVS_test		82.08 101	81.27 107	84.50 103	89.23 134	68.76 113	90.22 71	91.94 96	75.37 95	76.64 181	91.51 90	54.29 223	94.91 96	78.44 97	83.78 172	89.83 201

LGP-MVS_train				84.50 103	89.23 134	68.76 113		91.94 96	75.37 95	76.64 181	91.51 90	54.29 223	94.91 96	78.44 97	83.78 172	89.83 201

XVG-OURS		80.41 140	79.23 146	83.97 129	85.64 225	69.02 106	83.03 261	90.39 140	71.09 171	77.63 159	91.49 92	54.62 222	91.35 229	75.71 123	83.47 179	91.54 132

alignmvs		85.48 58	85.32 60	85.96 71	89.51 119	69.47 100	89.74 82	92.47 69	76.17 79	87.73 28	91.46 93	70.32 63	93.78 141	81.51 72	88.95 112	94.63 18

CANet		86.45 43	86.10 49	87.51 37	90.09 106	70.94 69	89.70 84	92.59 67	81.78 4	81.32 107	91.43 94	70.34 62	97.23 9	84.26 42	93.36 67	94.37 25

DROMVSNet		85.71 55	86.07 51	84.64 99	88.97 143	65.71 173	91.73 39	93.61 21	78.20 33	83.66 80	91.40 95	69.66 72	95.45 68	83.71 50	93.74 63	92.75 95

hse-mvs3		83.15 86	82.19 94	86.02 70	90.56 97	70.85 73	88.15 138	89.16 179	76.02 82	84.67 59	91.39 96	61.54 160	95.50 65	82.71 63	75.48 272	91.72 129

nrg030		83.88 74	83.53 76	84.96 88	86.77 212	69.28 104	90.46 65	92.67 62	74.79 106	82.95 86	91.33 97	72.70 43	93.09 176	80.79 82	79.28 229	92.50 104

canonicalmvs		85.91 51	85.87 53	86.04 69	89.84 112	69.44 103	90.45 66	93.00 44	76.70 68	88.01 25	91.23 98	73.28 38	93.91 136	81.50 73	88.80 115	94.77 14

DPM-MVS		84.93 68	84.29 74	86.84 50	90.20 104	73.04 22	87.12 162	93.04 40	69.80 195	82.85 89	91.22 99	73.06 41	96.02 48	76.72 117	94.63 49	91.46 137

Anonymous202405211		78.25 187	77.01 195	81.99 190	91.03 88	60.67 257	84.77 223	83.90 270	70.65 181	80.00 121	91.20 100	41.08 326	91.43 227	65.21 214	85.26 158	93.85 49

Anonymous20240529		80.19 146	78.89 152	84.10 118	90.60 96	64.75 190	88.95 101	90.90 130	65.97 250	80.59 117	91.17 101	49.97 268	93.73 147	69.16 182	82.70 191	93.81 53

EPP-MVSNet		83.40 83	83.02 83	84.57 101	90.13 105	64.47 197	92.32 26	90.73 133	74.45 115	79.35 127	91.10 102	69.05 80	95.12 86	72.78 151	87.22 135	94.13 34

TAPA-MVS	73.13 9	79.15 167	77.94 172	82.79 174	89.59 115	62.99 232	88.16 137	91.51 112	65.77 251	77.14 172	91.09 103	60.91 175	93.21 166	50.26 314	87.05 137	92.17 118
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CSCG		86.41 46	86.19 47	87.07 47	92.91 60	72.48 36	90.81 54	93.56 24	73.95 124	83.16 84	91.07 104	75.94 15	95.19 84	79.94 88	94.38 56	93.55 68

FIs		82.07 102	82.42 89	81.04 214	88.80 151	58.34 277	88.26 133	93.49 27	76.93 59	78.47 142	91.04 105	69.92 69	92.34 199	69.87 175	84.97 160	92.44 108

MVS_111021_LR		82.61 96	82.11 95	84.11 117	88.82 149	71.58 56	85.15 215	86.16 244	74.69 109	80.47 119	91.04 105	62.29 149	90.55 248	80.33 85	90.08 103	90.20 179

DP-MVS Recon		83.11 89	82.09 96	86.15 65	94.44 19	70.92 71	88.79 108	92.20 83	70.53 182	79.17 128	91.03 107	64.12 122	96.03 47	68.39 188	90.14 101	91.50 134

HQP_MVS		83.64 78	83.14 80	85.14 82	90.08 107	68.71 117	91.25 47	92.44 70	79.12 23	78.92 132	91.00 108	60.42 183	95.38 75	78.71 93	86.32 148	91.33 139

plane_prior4											91.00 108

FC-MVSNet-test		81.52 114	82.02 99	80.03 231	88.42 166	55.97 313	87.95 142	93.42 31	77.10 55	77.38 163	90.98 110	69.96 68	91.79 217	68.46 187	84.50 165	92.33 109

Vis-MVSNet (Re-imp)		78.36 186	78.45 159	78.07 263	88.64 158	51.78 335	86.70 177	79.63 319	74.14 122	75.11 220	90.83 111	61.29 168	89.75 258	58.10 274	91.60 82	92.69 99

114514_t		80.68 134	79.51 138	84.20 115	94.09 36	67.27 147	89.64 85	91.11 126	58.75 319	74.08 233	90.72 112	58.10 194	95.04 92	69.70 176	89.42 110	90.30 176

PAPM_NR		83.02 90	82.41 90	84.82 94	92.47 72	66.37 160	87.93 144	91.80 102	73.82 128	77.32 165	90.66 113	67.90 86	94.90 98	70.37 168	89.48 109	93.19 82

LS3D		76.95 217	74.82 229	83.37 144	90.45 99	67.36 146	89.15 96	86.94 233	61.87 295	69.52 280	90.61 114	51.71 251	94.53 109	46.38 334	86.71 143	88.21 246

VPNet		78.69 178	78.66 155	78.76 252	88.31 169	55.72 315	84.45 234	86.63 237	76.79 63	78.26 146	90.55 115	59.30 188	89.70 260	66.63 203	77.05 247	90.88 154

UniMVSNet_ETH3D		79.10 169	78.24 167	81.70 195	86.85 209	60.24 263	87.28 159	88.79 193	74.25 119	76.84 174	90.53 116	49.48 274	91.56 223	67.98 189	82.15 195	93.29 76

ACMP	74.13 6	81.51 116	80.57 118	84.36 109	89.42 122	68.69 120	89.97 76	91.50 115	74.46 114	75.04 223	90.41 117	53.82 228	94.54 108	77.56 106	82.91 186	89.86 200
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PCF-MVS	73.52 7	80.38 141	78.84 153	85.01 86	87.71 188	68.99 108	83.65 248	91.46 116	63.00 282	77.77 157	90.28 118	66.10 103	95.09 91	61.40 245	88.22 124	90.94 153
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
NP-MVS					89.62 114	68.32 126					90.24 119

HQP-MVS		82.61 96	82.02 99	84.37 108	89.33 126	66.98 151	89.17 92	92.19 84	76.41 71	77.23 168	90.23 120	60.17 186	95.11 87	77.47 107	85.99 154	91.03 149

PS-MVSNAJss		82.07 102	81.31 106	84.34 111	86.51 215	67.27 147	89.27 90	91.51 112	71.75 159	79.37 126	90.22 121	63.15 135	94.27 116	77.69 105	82.36 194	91.49 135

TSAR-MVS + GP.		85.71 55	85.33 59	86.84 50	91.34 84	72.50 35	89.07 98	87.28 227	76.41 71	85.80 40	90.22 121	74.15 34	95.37 78	81.82 71	91.88 78	92.65 101

Regformer-1		86.41 46	86.33 42	86.64 55	89.33 126	70.93 70	88.43 121	91.39 117	82.14 3	86.65 34	90.09 123	74.39 29	95.01 93	83.97 47	90.63 94	93.97 43

Regformer-2		86.63 42	86.53 41	86.95 48	89.33 126	71.24 62	88.43 121	92.05 88	82.50 1	86.88 32	90.09 123	74.45 26	95.61 59	84.38 39	90.63 94	94.01 41

test_part1		82.78 93	82.08 97	84.89 92	90.66 95	66.97 153	90.96 52	92.93 52	77.19 51	80.53 118	90.04 125	63.44 127	95.39 74	76.04 121	76.90 249	92.31 111

Regformer-3		85.23 63	85.07 64	85.70 73	88.95 144	69.01 107	88.29 131	89.91 157	80.95 8	85.01 49	90.01 126	72.45 45	94.19 122	82.50 67	87.57 127	93.90 47

Regformer-4		85.68 57	85.45 57	86.35 59	88.95 144	69.67 95	88.29 131	91.29 119	81.73 5	85.36 45	90.01 126	72.62 44	95.35 79	83.28 54	87.57 127	94.03 39

TranMVSNet+NR-MVSNet		80.84 125	80.31 124	82.42 182	87.85 182	62.33 237	87.74 148	91.33 118	80.55 11	77.99 153	89.86 128	65.23 113	92.62 188	67.05 201	75.24 282	92.30 112

diffmvs		82.10 100	81.88 102	82.76 177	83.00 273	63.78 210	83.68 247	89.76 160	72.94 145	82.02 97	89.85 129	65.96 108	90.79 244	82.38 69	87.30 134	93.71 57

BH-RMVSNet		79.61 154	78.44 160	83.14 155	89.38 125	65.93 167	84.95 220	87.15 230	73.56 133	78.19 148	89.79 130	56.67 209	93.36 162	59.53 259	86.74 142	90.13 182

GeoE		81.71 109	81.01 113	83.80 133	89.51 119	64.45 198	88.97 100	88.73 199	71.27 168	78.63 138	89.76 131	66.32 101	93.20 168	69.89 174	86.02 153	93.74 56

CS-MVS		84.53 71	84.97 66	83.23 151	87.54 196	63.27 223	88.82 107	93.50 25	75.98 84	83.07 85	89.73 132	70.29 64	95.23 81	82.07 70	93.70 65	91.18 143

AdaColmap		80.58 138	79.42 140	84.06 121	93.09 56	68.91 110	89.36 88	88.97 189	69.27 205	75.70 202	89.69 133	57.20 206	95.77 56	63.06 229	88.41 122	87.50 261

ACMM	73.20 8	80.78 133	79.84 131	83.58 136	89.31 131	68.37 125	89.99 75	91.60 109	70.28 186	77.25 166	89.66 134	53.37 231	93.53 155	74.24 135	82.85 187	88.85 231
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CNLPA		78.08 193	76.79 202	81.97 191	90.40 101	71.07 64	87.59 151	84.55 260	66.03 249	72.38 249	89.64 135	57.56 200	86.04 299	59.61 258	83.35 180	88.79 234

test_yl		81.17 119	80.47 121	83.24 149	89.13 138	63.62 211	86.21 190	89.95 155	72.43 150	81.78 102	89.61 136	57.50 201	93.58 150	70.75 163	86.90 139	92.52 102

DCV-MVSNet		81.17 119	80.47 121	83.24 149	89.13 138	63.62 211	86.21 190	89.95 155	72.43 150	81.78 102	89.61 136	57.50 201	93.58 150	70.75 163	86.90 139	92.52 102

EI-MVSNet-Vis-set		84.19 73	83.81 75	85.31 77	88.18 171	67.85 135	87.66 149	89.73 162	80.05 16	82.95 86	89.59 138	70.74 60	94.82 102	80.66 83	84.72 163	93.28 77

PAPR		81.66 112	80.89 115	83.99 128	90.27 102	64.00 205	86.76 176	91.77 106	68.84 220	77.13 173	89.50 139	67.63 88	94.88 100	67.55 193	88.52 120	93.09 84

jajsoiax		79.29 164	77.96 171	83.27 147	84.68 241	66.57 158	89.25 91	90.16 150	69.20 209	75.46 207	89.49 140	45.75 301	93.13 174	76.84 115	80.80 209	90.11 184

MVSFormer		82.85 92	82.05 98	85.24 80	87.35 197	70.21 83	90.50 61	90.38 141	68.55 224	81.32 107	89.47 141	61.68 157	93.46 159	78.98 91	90.26 99	92.05 121

jason		81.39 117	80.29 125	84.70 98	86.63 214	69.90 90	85.95 196	86.77 235	63.24 278	81.07 113	89.47 141	61.08 173	92.15 206	78.33 100	90.07 104	92.05 121
jason: jason.
mvs_tets		79.13 168	77.77 179	83.22 152	84.70 240	66.37 160	89.17 92	90.19 149	69.38 203	75.40 210	89.46 143	44.17 309	93.15 172	76.78 116	80.70 211	90.14 181

UGNet		80.83 127	79.59 137	84.54 102	88.04 176	68.09 131	89.42 87	88.16 206	76.95 58	76.22 190	89.46 143	49.30 277	93.94 132	68.48 186	90.31 97	91.60 130
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
VPA-MVSNet		80.60 136	80.55 119	80.76 219	88.07 175	60.80 256	86.86 170	91.58 110	75.67 90	80.24 120	89.45 145	63.34 129	90.25 251	70.51 167	79.22 230	91.23 142

MVS_Test		83.15 86	83.06 82	83.41 143	86.86 208	63.21 225	86.11 193	92.00 92	74.31 116	82.87 88	89.44 146	70.03 67	93.21 166	77.39 109	88.50 121	93.81 53

EI-MVSNet-UG-set		83.81 75	83.38 78	85.09 84	87.87 181	67.53 141	87.44 155	89.66 164	79.74 18	82.23 95	89.41 147	70.24 66	94.74 105	79.95 87	83.92 171	92.99 90

RPSCF		73.23 259	71.46 260	78.54 256	82.50 285	59.85 265	82.18 267	82.84 289	58.96 316	71.15 261	89.41 147	45.48 303	84.77 309	58.82 267	71.83 310	91.02 151

RRT_MVS		79.88 151	78.38 162	84.38 107	85.42 229	70.60 79	88.71 114	88.75 198	72.30 152	78.83 134	89.14 149	44.44 307	92.18 205	78.50 96	79.33 228	90.35 174

UniMVSNet_NR-MVSNet		81.88 105	81.54 105	82.92 166	88.46 164	63.46 218	87.13 161	92.37 74	80.19 14	78.38 143	89.14 149	71.66 53	93.05 178	70.05 171	76.46 257	92.25 114

tttt0517		79.40 161	77.91 173	83.90 132	88.10 174	63.84 208	88.37 128	84.05 268	71.45 166	76.78 177	89.12 151	49.93 271	94.89 99	70.18 170	83.18 183	92.96 91

DU-MVS		81.12 121	80.52 120	82.90 167	87.80 184	63.46 218	87.02 165	91.87 100	79.01 26	78.38 143	89.07 152	65.02 115	93.05 178	70.05 171	76.46 257	92.20 116

NR-MVSNet		80.23 144	79.38 142	82.78 175	87.80 184	63.34 221	86.31 187	91.09 127	79.01 26	72.17 251	89.07 152	67.20 93	92.81 187	66.08 208	75.65 268	92.20 116

DELS-MVS		85.41 61	85.30 61	85.77 72	88.49 162	67.93 134	85.52 212	93.44 29	78.70 28	83.63 81	89.03 154	74.57 25	95.71 58	80.26 86	94.04 61	93.66 58
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
baseline1		76.98 216	76.75 205	77.66 268	88.13 172	55.66 316	85.12 216	81.89 296	73.04 143	76.79 176	88.90 155	62.43 147	87.78 288	63.30 227	71.18 314	89.55 210

DP-MVS		76.78 219	74.57 231	83.42 141	93.29 49	69.46 102	88.55 120	83.70 272	63.98 275	70.20 268	88.89 156	54.01 227	94.80 103	46.66 331	81.88 199	86.01 293

ab-mvs		79.51 156	78.97 151	81.14 211	88.46 164	60.91 254	83.84 245	89.24 176	70.36 184	79.03 129	88.87 157	63.23 133	90.21 252	65.12 215	82.57 192	92.28 113

PEN-MVS		77.73 202	77.69 183	77.84 265	87.07 207	53.91 325	87.91 145	91.18 123	77.56 41	73.14 240	88.82 158	61.23 169	89.17 268	59.95 255	72.37 305	90.43 171

test_djsdf		80.30 143	79.32 144	83.27 147	83.98 252	65.37 181	90.50 61	90.38 141	68.55 224	76.19 191	88.70 159	56.44 210	93.46 159	78.98 91	80.14 219	90.97 152

PAPM		77.68 205	76.40 211	81.51 199	87.29 203	61.85 244	83.78 246	89.59 165	64.74 263	71.23 259	88.70 159	62.59 143	93.66 149	52.66 301	87.03 138	89.01 223

DTE-MVSNet		76.99 215	76.80 201	77.54 272	86.24 217	53.06 332	87.52 152	90.66 134	77.08 56	72.50 246	88.67 161	60.48 182	89.52 262	57.33 281	70.74 316	90.05 191

PS-CasMVS		78.01 197	78.09 169	77.77 267	87.71 188	54.39 322	88.02 139	91.22 121	77.50 44	73.26 238	88.64 162	60.73 176	88.41 281	61.88 240	73.88 294	90.53 168

cdsmvs_eth3d_5k		19.96 334	26.61 336	0.00 352	0.00 373	0.00 374	0.00 364	89.26 175	0.00 369	0.00 370	88.61 163	61.62 159	0.00 370	0.00 368	0.00 368	0.00 366

lupinMVS		81.39 117	80.27 126	84.76 97	87.35 197	70.21 83	85.55 208	86.41 239	62.85 285	81.32 107	88.61 163	61.68 157	92.24 203	78.41 99	90.26 99	91.83 125

F-COLMAP		76.38 227	74.33 236	82.50 181	89.28 132	66.95 155	88.41 124	89.03 184	64.05 273	66.83 302	88.61 163	46.78 291	92.89 183	57.48 278	78.55 231	87.67 255

mvs_anonymous		79.42 160	79.11 148	80.34 226	84.45 244	57.97 283	82.59 263	87.62 220	67.40 233	76.17 194	88.56 166	68.47 82	89.59 261	70.65 166	86.05 152	93.47 71

CP-MVSNet		78.22 188	78.34 164	77.84 265	87.83 183	54.54 320	87.94 143	91.17 124	77.65 36	73.48 236	88.49 167	62.24 151	88.43 280	62.19 236	74.07 290	90.55 167

PVSNet_Blended_VisFu		82.62 95	81.83 103	84.96 88	90.80 94	69.76 93	88.74 112	91.70 107	69.39 202	78.96 130	88.46 168	65.47 111	94.87 101	74.42 132	88.57 118	90.24 178

CANet_DTU		80.61 135	79.87 130	82.83 169	85.60 226	63.17 228	87.36 156	88.65 200	76.37 75	75.88 199	88.44 169	53.51 230	93.07 177	73.30 145	89.74 107	92.25 114

PLC	70.83 11	78.05 195	76.37 212	83.08 158	91.88 80	67.80 136	88.19 135	89.46 168	64.33 269	69.87 277	88.38 170	53.66 229	93.58 150	58.86 266	82.73 189	87.86 252
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
WR-MVS		79.49 157	79.22 147	80.27 228	88.79 152	58.35 276	85.06 217	88.61 202	78.56 29	77.65 158	88.34 171	63.81 126	90.66 247	64.98 217	77.22 245	91.80 128

XXY-MVS		75.41 239	75.56 217	74.96 295	83.59 258	57.82 287	80.59 283	83.87 271	66.54 243	74.93 225	88.31 172	63.24 132	80.09 330	62.16 237	76.85 252	86.97 275

Effi-MVS+		83.62 79	83.08 81	85.24 80	88.38 167	67.45 142	88.89 103	89.15 180	75.50 92	82.27 94	88.28 173	69.61 73	94.45 112	77.81 104	87.84 125	93.84 51

API-MVS		81.99 104	81.23 108	84.26 114	90.94 90	70.18 88	91.10 50	89.32 171	71.51 165	78.66 137	88.28 173	65.26 112	95.10 90	64.74 219	91.23 89	87.51 260

thisisatest0530		79.40 161	77.76 180	84.31 112	87.69 190	65.10 186	87.36 156	84.26 266	70.04 189	77.42 162	88.26 175	49.94 269	94.79 104	70.20 169	84.70 164	93.03 87

hse-mvs2		81.72 108	80.94 114	84.07 120	88.72 155	67.68 139	85.87 199	87.26 228	76.02 82	84.67 59	88.22 176	61.54 160	93.48 157	82.71 63	73.44 299	91.06 147

CS-MVS-test		84.27 72	84.52 72	83.55 138	87.94 179	64.55 192	88.65 116	93.57 23	75.26 97	81.78 102	88.17 177	70.27 65	95.22 82	81.41 74	93.62 66	90.87 155

xiu_mvs_v1_base_debu		80.80 130	79.72 134	84.03 125	87.35 197	70.19 85	85.56 205	88.77 194	69.06 213	81.83 98	88.16 178	50.91 257	92.85 184	78.29 101	87.56 129	89.06 218

xiu_mvs_v1_base		80.80 130	79.72 134	84.03 125	87.35 197	70.19 85	85.56 205	88.77 194	69.06 213	81.83 98	88.16 178	50.91 257	92.85 184	78.29 101	87.56 129	89.06 218

xiu_mvs_v1_base_debi		80.80 130	79.72 134	84.03 125	87.35 197	70.19 85	85.56 205	88.77 194	69.06 213	81.83 98	88.16 178	50.91 257	92.85 184	78.29 101	87.56 129	89.06 218

UniMVSNet (Re)		81.60 113	81.11 110	83.09 157	88.38 167	64.41 199	87.60 150	93.02 43	78.42 31	78.56 139	88.16 178	69.78 70	93.26 165	69.58 178	76.49 256	91.60 130

AUN-MVS		79.21 166	77.60 185	84.05 122	88.71 156	67.61 140	85.84 201	87.26 228	69.08 212	77.23 168	88.14 182	53.20 233	93.47 158	75.50 128	73.45 298	91.06 147

Anonymous20231211		78.97 173	77.69 183	82.81 171	90.54 98	64.29 201	90.11 73	91.51 112	65.01 261	76.16 195	88.13 183	50.56 262	93.03 181	69.68 177	77.56 242	91.11 146

pm-mvs1		77.25 212	76.68 207	78.93 250	84.22 247	58.62 275	86.41 184	88.36 205	71.37 167	73.31 237	88.01 184	61.22 170	89.15 269	64.24 221	73.01 302	89.03 222

LTVRE_ROB	69.57 13	76.25 228	74.54 233	81.41 201	88.60 159	64.38 200	79.24 295	89.12 183	70.76 178	69.79 279	87.86 185	49.09 279	93.20 168	56.21 289	80.16 217	86.65 282
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
WTY-MVS		75.65 235	75.68 216	75.57 289	86.40 216	56.82 299	77.92 310	82.40 292	65.10 258	76.18 192	87.72 186	63.13 138	80.90 327	60.31 253	81.96 197	89.00 225

TAMVS		78.89 175	77.51 187	83.03 161	87.80 184	67.79 137	84.72 224	85.05 255	67.63 229	76.75 178	87.70 187	62.25 150	90.82 243	58.53 270	87.13 136	90.49 169

BH-untuned		79.47 158	78.60 156	82.05 188	89.19 136	65.91 168	86.07 194	88.52 203	72.18 153	75.42 209	87.69 188	61.15 171	93.54 154	60.38 252	86.83 141	86.70 281

COLMAP_ROB	66.92 17	73.01 261	70.41 272	80.81 218	87.13 206	65.63 174	88.30 130	84.19 267	62.96 283	63.80 326	87.69 188	38.04 336	92.56 191	46.66 331	74.91 284	84.24 312
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		74.26 246	72.42 253	79.80 236	83.76 256	59.59 268	85.92 198	86.64 236	66.39 244	66.96 299	87.58 190	39.46 330	91.60 221	65.76 211	69.27 320	88.22 245

Baseline_NR-MVSNet		78.15 192	78.33 165	77.61 270	85.79 222	56.21 311	86.78 174	85.76 248	73.60 132	77.93 154	87.57 191	65.02 115	88.99 271	67.14 200	75.33 278	87.63 256

WR-MVS_H		78.51 182	78.49 158	78.56 255	88.02 177	56.38 308	88.43 121	92.67 62	77.14 53	73.89 234	87.55 192	66.25 102	89.24 267	58.92 265	73.55 297	90.06 190

EI-MVSNet		80.52 139	79.98 128	82.12 185	84.28 245	63.19 227	86.41 184	88.95 190	74.18 121	78.69 135	87.54 193	66.62 96	92.43 194	72.57 153	80.57 213	90.74 160

CVMVSNet		72.99 262	72.58 251	74.25 302	84.28 245	50.85 341	86.41 184	83.45 279	44.56 349	73.23 239	87.54 193	49.38 275	85.70 301	65.90 209	78.44 234	86.19 288

ACMH+	68.96 14	76.01 231	74.01 238	82.03 189	88.60 159	65.31 182	88.86 104	87.55 221	70.25 187	67.75 291	87.47 195	41.27 324	93.19 170	58.37 271	75.94 265	87.60 257

RRT_test8_iter05		78.38 185	77.40 188	81.34 205	86.00 220	58.86 272	86.55 182	91.26 120	72.13 156	75.91 197	87.42 196	44.97 304	93.73 147	77.02 113	75.30 279	91.45 138

TransMVSNet (Re)		75.39 240	74.56 232	77.86 264	85.50 228	57.10 296	86.78 174	86.09 246	72.17 154	71.53 257	87.34 197	63.01 139	89.31 266	56.84 285	61.83 338	87.17 269

GBi-Net		78.40 183	77.40 188	81.40 202	87.60 191	63.01 229	88.39 125	89.28 172	71.63 161	75.34 212	87.28 198	54.80 216	91.11 234	62.72 230	79.57 222	90.09 186

test1		78.40 183	77.40 188	81.40 202	87.60 191	63.01 229	88.39 125	89.28 172	71.63 161	75.34 212	87.28 198	54.80 216	91.11 234	62.72 230	79.57 222	90.09 186

FMVSNet2		78.20 190	77.21 192	81.20 209	87.60 191	62.89 233	87.47 154	89.02 185	71.63 161	75.29 216	87.28 198	54.80 216	91.10 237	62.38 234	79.38 226	89.61 208

FMVSNet1		77.44 208	76.12 214	81.40 202	86.81 211	63.01 229	88.39 125	89.28 172	70.49 183	74.39 230	87.28 198	49.06 280	91.11 234	60.91 249	78.52 232	90.09 186

v2v482		80.23 144	79.29 145	83.05 160	83.62 257	64.14 203	87.04 164	89.97 154	73.61 131	78.18 149	87.22 202	61.10 172	93.82 139	76.11 119	76.78 254	91.18 143

ITE_SJBPF				78.22 260	81.77 295	60.57 258		83.30 280	69.25 206	67.54 293	87.20 203	36.33 341	87.28 292	54.34 294	74.62 287	86.80 278

anonymousdsp		78.60 180	77.15 193	82.98 164	80.51 314	67.08 149	87.24 160	89.53 166	65.66 253	75.16 218	87.19 204	52.52 234	92.25 202	77.17 111	79.34 227	89.61 208

MVSTER		79.01 171	77.88 175	82.38 183	83.07 270	64.80 189	84.08 244	88.95 190	69.01 216	78.69 135	87.17 205	54.70 220	92.43 194	74.69 131	80.57 213	89.89 199

thres100view900		76.50 222	75.55 218	79.33 244	89.52 118	56.99 297	85.83 202	83.23 282	73.94 125	76.32 188	87.12 206	51.89 248	91.95 212	48.33 322	83.75 174	89.07 216

thres600view7		76.50 222	75.44 220	79.68 238	89.40 123	57.16 294	85.53 210	83.23 282	73.79 129	76.26 189	87.09 207	51.89 248	91.89 215	48.05 327	83.72 177	90.00 192

XVG-ACMP-BASELINE		76.11 230	74.27 237	81.62 196	83.20 266	64.67 191	83.60 251	89.75 161	69.75 197	71.85 254	87.09 207	32.78 348	92.11 207	69.99 173	80.43 215	88.09 247

HY-MVS	69.67 12	77.95 198	77.15 193	80.36 225	87.57 195	60.21 264	83.37 255	87.78 218	66.11 246	75.37 211	87.06 209	63.27 131	90.48 249	61.38 246	82.43 193	90.40 173

CHOSEN 1792x2688		77.63 206	75.69 215	83.44 140	89.98 109	68.58 123	78.70 302	87.50 223	56.38 333	75.80 201	86.84 210	58.67 191	91.40 228	61.58 244	85.75 157	90.34 175

v8		79.97 150	79.02 150	82.80 172	84.09 249	64.50 196	87.96 141	90.29 148	74.13 123	75.24 217	86.81 211	62.88 140	93.89 138	74.39 133	75.40 276	90.00 192

AllTest		70.96 275	68.09 287	79.58 241	85.15 233	63.62 211	84.58 230	79.83 317	62.31 291	60.32 336	86.73 212	32.02 349	88.96 274	50.28 312	71.57 312	86.15 289

TestCases				79.58 241	85.15 233	63.62 211		79.83 317	62.31 291	60.32 336	86.73 212	32.02 349	88.96 274	50.28 312	71.57 312	86.15 289

mvs-test1		80.88 123	79.40 141	85.29 78	85.13 235	69.75 94	89.28 89	88.10 208	74.99 103	76.44 186	86.72 214	57.27 204	94.26 120	73.53 140	83.18 183	91.87 124

LCM-MVSNet-Re		77.05 214	76.94 198	77.36 273	87.20 204	51.60 336	80.06 287	80.46 311	75.20 100	67.69 292	86.72 214	62.48 145	88.98 272	63.44 225	89.25 111	91.51 133

1112_ss		77.40 210	76.43 210	80.32 227	89.11 142	60.41 262	83.65 248	87.72 219	62.13 293	73.05 241	86.72 214	62.58 144	89.97 255	62.11 239	80.80 209	90.59 166

ab-mvs-re		7.23 337	9.64 340	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	86.72 214	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

IterMVS-LS		80.06 147	79.38 142	82.11 186	85.89 221	63.20 226	86.79 173	89.34 170	74.19 120	75.45 208	86.72 214	66.62 96	92.39 196	72.58 152	76.86 251	90.75 159
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	67.68 16	75.89 232	73.93 239	81.77 194	88.71 156	66.61 157	88.62 117	89.01 186	69.81 194	66.78 303	86.70 219	41.95 323	91.51 226	55.64 290	78.14 237	87.17 269
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Test_1112_low_res		76.40 226	75.44 220	79.27 245	89.28 132	58.09 279	81.69 272	87.07 231	59.53 312	72.48 247	86.67 220	61.30 167	89.33 265	60.81 251	80.15 218	90.41 172

FMVSNet3		77.88 200	76.85 200	80.97 215	86.84 210	62.36 236	86.52 183	88.77 194	71.13 169	75.34 212	86.66 221	54.07 226	91.10 237	62.72 230	79.57 222	89.45 211

pmmvs6		74.69 243	73.39 244	78.61 254	81.38 302	57.48 292	86.64 178	87.95 213	64.99 262	70.18 269	86.61 222	50.43 264	89.52 262	62.12 238	70.18 318	88.83 232

ET-MVSNet_ETH3D		78.63 179	76.63 208	84.64 99	86.73 213	69.47 100	85.01 218	84.61 259	69.54 200	66.51 308	86.59 223	50.16 266	91.75 218	76.26 118	84.24 169	92.69 99

testgi		66.67 304	66.53 302	67.08 332	75.62 342	41.69 357	75.93 317	76.50 333	66.11 246	65.20 318	86.59 223	35.72 343	74.71 350	43.71 341	73.38 300	84.84 306

CLD-MVS		82.31 98	81.65 104	84.29 113	88.47 163	67.73 138	85.81 203	92.35 75	75.78 86	78.33 145	86.58 225	64.01 123	94.35 113	76.05 120	87.48 132	90.79 157
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v10		79.74 153	78.67 154	82.97 165	84.06 250	64.95 187	87.88 146	90.62 135	73.11 141	75.11 220	86.56 226	61.46 163	94.05 128	73.68 138	75.55 270	89.90 198

CDS-MVSNet		79.07 170	77.70 182	83.17 154	87.60 191	68.23 129	84.40 237	86.20 243	67.49 232	76.36 187	86.54 227	61.54 160	90.79 244	61.86 241	87.33 133	90.49 169
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
xiu_mvs_v2_base		81.69 110	81.05 111	83.60 135	89.15 137	68.03 133	84.46 233	90.02 153	70.67 179	81.30 110	86.53 228	63.17 134	94.19 122	75.60 126	88.54 119	88.57 240

TR-MVS		77.44 208	76.18 213	81.20 209	88.24 170	63.24 224	84.61 229	86.40 240	67.55 231	77.81 155	86.48 229	54.10 225	93.15 172	57.75 277	82.72 190	87.20 268

EIA-MVS		83.31 85	82.80 87	84.82 94	89.59 115	65.59 175	88.21 134	92.68 61	74.66 110	78.96 130	86.42 230	69.06 79	95.26 80	75.54 127	90.09 102	93.62 65

tfpn200view9		76.42 225	75.37 224	79.55 243	89.13 138	57.65 289	85.17 213	83.60 273	73.41 138	76.45 183	86.39 231	52.12 241	91.95 212	48.33 322	83.75 174	89.07 216

thres400		76.50 222	75.37 224	79.86 234	89.13 138	57.65 289	85.17 213	83.60 273	73.41 138	76.45 183	86.39 231	52.12 241	91.95 212	48.33 322	83.75 174	90.00 192

v7n		78.97 173	77.58 186	83.14 155	83.45 260	65.51 176	88.32 129	91.21 122	73.69 130	72.41 248	86.32 233	57.93 195	93.81 140	69.18 181	75.65 268	90.11 184

MAR-MVS		81.84 106	80.70 116	85.27 79	91.32 85	71.53 57	89.82 78	90.92 129	69.77 196	78.50 140	86.21 234	62.36 148	94.52 110	65.36 213	92.05 77	89.77 204
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
v1144		80.03 148	79.03 149	83.01 162	83.78 255	64.51 194	87.11 163	90.57 137	71.96 157	78.08 152	86.20 235	61.41 164	93.94 132	74.93 130	77.23 244	90.60 165

V42		79.38 163	78.24 167	82.83 169	81.10 308	65.50 177	85.55 208	89.82 158	71.57 164	78.21 147	86.12 236	60.66 179	93.18 171	75.64 124	75.46 274	89.81 203

PVSNet_BlendedMVS		80.60 136	80.02 127	82.36 184	88.85 146	65.40 178	86.16 192	92.00 92	69.34 204	78.11 150	86.09 237	66.02 106	94.27 116	71.52 157	82.06 196	87.39 262

v1192		79.59 155	78.43 161	83.07 159	83.55 259	64.52 193	86.93 168	90.58 136	70.83 174	77.78 156	85.90 238	59.15 189	93.94 132	73.96 137	77.19 246	90.76 158

SixPastTwentyTwo		73.37 255	71.26 265	79.70 237	85.08 237	57.89 285	85.57 204	83.56 275	71.03 172	65.66 312	85.88 239	42.10 321	92.57 190	59.11 263	63.34 337	88.65 238

EPNet_dtu		75.46 237	74.86 228	77.23 277	82.57 284	54.60 319	86.89 169	83.09 286	71.64 160	66.25 310	85.86 240	55.99 211	88.04 285	54.92 292	86.55 145	89.05 221
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		73.60 253	73.64 243	73.51 306	82.80 278	55.01 318	76.12 316	81.69 299	62.47 290	74.68 228	85.85 241	57.32 203	78.11 337	60.86 250	80.93 206	87.39 262

ETV-MVS		84.90 70	84.67 71	85.59 74	89.39 124	68.66 121	88.74 112	92.64 66	79.97 17	84.10 71	85.71 242	69.32 76	95.38 75	80.82 80	91.37 86	92.72 96

v1240		78.99 172	77.78 178	82.64 178	83.21 265	63.54 215	86.62 179	90.30 147	69.74 199	77.33 164	85.68 243	57.04 207	93.76 144	73.13 148	76.92 248	90.62 163

v144192		79.47 158	78.37 163	82.78 175	83.35 261	63.96 206	86.96 166	90.36 144	69.99 190	77.50 160	85.67 244	60.66 179	93.77 143	74.27 134	76.58 255	90.62 163

tfpnnormal		74.39 244	73.16 247	78.08 262	86.10 219	58.05 280	84.65 228	87.53 222	70.32 185	71.22 260	85.63 245	54.97 215	89.86 256	43.03 343	75.02 283	86.32 285

PS-MVSNAJ		81.69 110	81.02 112	83.70 134	89.51 119	68.21 130	84.28 239	90.09 152	70.79 176	81.26 111	85.62 246	63.15 135	94.29 114	75.62 125	88.87 114	88.59 239

v1921920		79.22 165	78.03 170	82.80 172	83.30 263	63.94 207	86.80 172	90.33 145	69.91 193	77.48 161	85.53 247	58.44 193	93.75 145	73.60 139	76.85 252	90.71 161

test_0402		72.79 264	70.44 271	79.84 235	88.13 172	65.99 165	85.93 197	84.29 264	65.57 254	67.40 296	85.49 248	46.92 290	92.61 189	35.88 352	74.38 289	80.94 336

v148		78.72 177	77.80 177	81.47 200	82.73 280	61.96 243	86.30 188	88.08 210	73.26 140	76.18 192	85.47 249	62.46 146	92.36 198	71.92 156	73.82 295	90.09 186

USDC		70.33 281	68.37 282	76.21 284	80.60 312	56.23 310	79.19 297	86.49 238	60.89 300	61.29 333	85.47 249	31.78 351	89.47 264	53.37 298	76.21 263	82.94 327

MVP-Stereo		76.12 229	74.46 235	81.13 212	85.37 230	69.79 92	84.42 236	87.95 213	65.03 260	67.46 294	85.33 251	53.28 232	91.73 220	58.01 275	83.27 181	81.85 331
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVS		78.19 191	76.99 197	81.78 193	85.66 224	66.99 150	84.66 225	90.47 139	55.08 338	72.02 253	85.27 252	63.83 125	94.11 127	66.10 207	89.80 106	84.24 312

cl-mvsnet1		77.72 203	76.76 203	80.58 221	82.48 287	60.48 260	83.09 258	87.86 216	69.22 207	74.38 231	85.24 253	62.10 153	91.53 224	71.09 161	75.40 276	89.74 205

cl-mvsnet____		77.72 203	76.76 203	80.58 221	82.49 286	60.48 260	83.09 258	87.87 215	69.22 207	74.38 231	85.22 254	62.10 153	91.53 224	71.09 161	75.41 275	89.73 206

HyFIR lowres test		77.53 207	75.40 222	83.94 131	89.59 115	66.62 156	80.36 284	88.64 201	56.29 334	76.45 183	85.17 255	57.64 199	93.28 164	61.34 247	83.10 185	91.91 123

pmmvs4		74.03 250	71.91 256	80.39 224	81.96 293	68.32 126	81.45 275	82.14 294	59.32 313	69.87 277	85.13 256	52.40 237	88.13 284	60.21 254	74.74 286	84.73 308

TDRefinement		67.49 298	64.34 307	76.92 279	73.47 351	61.07 252	84.86 222	82.98 287	59.77 309	58.30 342	85.13 256	26.06 354	87.89 286	47.92 328	60.59 342	81.81 332

Fast-Effi-MVS+		80.81 128	79.92 129	83.47 139	88.85 146	64.51 194	85.53 210	89.39 169	70.79 176	78.49 141	85.06 258	67.54 89	93.58 150	67.03 202	86.58 144	92.32 110

PVSNet_Blended		80.98 122	80.34 123	82.90 167	88.85 146	65.40 178	84.43 235	92.00 92	67.62 230	78.11 150	85.05 259	66.02 106	94.27 116	71.52 157	89.50 108	89.01 223

CMPMVS	51.72 21	70.19 283	68.16 285	76.28 283	73.15 353	57.55 291	79.47 293	83.92 269	48.02 348	56.48 347	84.81 260	43.13 313	86.42 297	62.67 233	81.81 200	84.89 305
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		68.53 295	67.61 295	71.31 319	78.51 332	47.01 350	84.47 231	84.27 265	42.27 350	66.44 309	84.79 261	40.44 328	83.76 314	58.76 268	68.54 325	83.17 321

BH-w/o		78.21 189	77.33 191	80.84 217	88.81 150	65.13 185	84.87 221	87.85 217	69.75 197	74.52 229	84.74 262	61.34 166	93.11 175	58.24 273	85.84 156	84.27 311

pmmvs5		71.55 271	70.20 274	75.61 288	77.83 333	56.39 307	81.74 271	80.89 303	57.76 324	67.46 294	84.49 263	49.26 278	85.32 305	57.08 283	75.29 280	85.11 304

thres200		75.55 236	74.47 234	78.82 251	87.78 187	57.85 286	83.07 260	83.51 276	72.44 149	75.84 200	84.42 264	52.08 243	91.75 218	47.41 329	83.64 178	86.86 277

eth_miper_zixun_eth		77.92 199	76.69 206	81.61 198	83.00 273	61.98 242	83.15 257	89.20 178	69.52 201	74.86 226	84.35 265	61.76 156	92.56 191	71.50 159	72.89 303	90.28 177

cl_fuxian		78.75 176	77.91 173	81.26 207	82.89 277	61.56 248	84.09 243	89.13 182	69.97 191	75.56 203	84.29 266	66.36 100	92.09 208	73.47 143	75.48 272	90.12 183

Fast-Effi-MVS+-dtu		78.02 196	76.49 209	82.62 179	83.16 269	66.96 154	86.94 167	87.45 225	72.45 147	71.49 258	84.17 267	54.79 219	91.58 222	67.61 192	80.31 216	89.30 214

IterMVS-SCA-FT		75.43 238	73.87 241	80.11 230	82.69 281	64.85 188	81.57 274	83.47 278	69.16 210	70.49 265	84.15 268	51.95 246	88.15 283	69.23 180	72.14 308	87.34 264

1314		76.53 221	75.30 226	80.21 229	83.93 253	62.32 238	84.66 225	88.81 192	60.23 305	70.16 271	84.07 269	55.30 214	90.73 246	67.37 195	83.21 182	87.59 259

cl-mvsnet2		78.07 194	77.01 195	81.23 208	82.37 289	61.83 245	83.55 252	87.98 212	68.96 217	75.06 222	83.87 270	61.40 165	91.88 216	73.53 140	76.39 259	89.98 195

EG-PatchMatch MVS		74.04 249	71.82 258	80.71 220	84.92 238	67.42 143	85.86 200	88.08 210	66.04 248	64.22 322	83.85 271	35.10 344	92.56 191	57.44 279	80.83 208	82.16 330

thisisatest0515		77.33 211	75.38 223	83.18 153	85.27 231	63.80 209	82.11 268	83.27 281	65.06 259	75.91 197	83.84 272	49.54 273	94.27 116	67.24 198	86.19 150	91.48 136

test20.03		67.45 299	66.95 300	68.94 326	75.48 343	44.84 353	77.50 311	77.67 327	66.66 239	63.01 328	83.80 273	47.02 289	78.40 335	42.53 345	68.86 324	83.58 318

miper_ehance_all_eth		78.59 181	77.76 180	81.08 213	82.66 282	61.56 248	83.65 248	89.15 180	68.87 219	75.55 204	83.79 274	66.49 98	92.03 209	73.25 146	76.39 259	89.64 207

MSDG		73.36 257	70.99 266	80.49 223	84.51 243	65.80 170	80.71 281	86.13 245	65.70 252	65.46 313	83.74 275	44.60 305	90.91 242	51.13 307	76.89 250	84.74 307

IterMVS		74.29 245	72.94 249	78.35 259	81.53 299	63.49 217	81.58 273	82.49 291	68.06 228	69.99 274	83.69 276	51.66 252	85.54 302	65.85 210	71.64 311	86.01 293
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm		72.37 268	71.71 259	74.35 301	82.19 291	52.00 333	79.22 296	77.29 330	64.56 265	72.95 242	83.68 277	51.35 253	83.26 319	58.33 272	75.80 266	87.81 253

Effi-MVS+-dtu		80.03 148	78.57 157	84.42 106	85.13 235	68.74 115	88.77 109	88.10 208	74.99 103	74.97 224	83.49 278	57.27 204	93.36 162	73.53 140	80.88 207	91.18 143

baseline2		75.70 234	73.83 242	81.30 206	83.26 264	61.79 246	82.57 264	80.65 307	66.81 235	66.88 300	83.42 279	57.86 197	92.19 204	63.47 224	79.57 222	89.91 197

bset_n11_16_dypcd		77.12 213	75.47 219	82.06 187	81.12 307	65.99 165	81.37 277	83.20 284	69.94 192	76.09 196	83.38 280	47.75 285	92.26 201	78.51 95	77.91 238	87.95 248

TinyColmap		67.30 301	64.81 305	74.76 298	81.92 294	56.68 303	80.29 286	81.49 301	60.33 303	56.27 348	83.22 281	24.77 355	87.66 289	45.52 337	69.47 319	79.95 340

CostFormer		75.24 241	73.90 240	79.27 245	82.65 283	58.27 278	80.80 278	82.73 290	61.57 296	75.33 215	83.13 282	55.52 212	91.07 240	64.98 217	78.34 236	88.45 242

miper_lstm_enhance		74.11 248	73.11 248	77.13 278	80.11 317	59.62 267	72.23 332	86.92 234	66.76 237	70.40 266	82.92 283	56.93 208	82.92 320	69.06 183	72.63 304	88.87 230

GA-MVS		76.87 218	75.17 227	81.97 191	82.75 279	62.58 234	81.44 276	86.35 242	72.16 155	74.74 227	82.89 284	46.20 296	92.02 210	68.85 185	81.09 205	91.30 141

K. test v3		71.19 273	68.51 281	79.21 247	83.04 272	57.78 288	84.35 238	76.91 332	72.90 146	62.99 329	82.86 285	39.27 331	91.09 239	61.65 243	52.66 350	88.75 235

MS-PatchMatch		73.83 251	72.67 250	77.30 275	83.87 254	66.02 164	81.82 269	84.66 258	61.37 299	68.61 287	82.82 286	47.29 287	88.21 282	59.27 260	84.32 168	77.68 345

lessismore_v0				78.97 249	81.01 309	57.15 295		65.99 355		61.16 334	82.82 286	39.12 332	91.34 230	59.67 257	46.92 355	88.43 243

D2MVS		74.82 242	73.21 246	79.64 240	79.81 321	62.56 235	80.34 285	87.35 226	64.37 268	68.86 284	82.66 288	46.37 293	90.10 254	67.91 190	81.24 204	86.25 286

Anonymous20231206		68.60 293	67.80 292	71.02 320	80.23 316	50.75 342	78.30 306	80.47 310	56.79 331	66.11 311	82.63 289	46.35 294	78.95 333	43.62 342	75.70 267	83.36 320

MIMVSNet		70.69 277	69.30 276	74.88 296	84.52 242	56.35 309	75.87 320	79.42 320	64.59 264	67.76 290	82.41 290	41.10 325	81.54 325	46.64 333	81.34 202	86.75 280

OpenMVS_ROB	64.09 19	70.56 279	68.19 284	77.65 269	80.26 315	59.41 270	85.01 218	82.96 288	58.76 318	65.43 314	82.33 291	37.63 338	91.23 233	45.34 339	76.03 264	82.32 328

miper_enhance_ethall		77.87 201	76.86 199	80.92 216	81.65 296	61.38 250	82.68 262	88.98 187	65.52 255	75.47 205	82.30 292	65.76 110	92.00 211	72.95 149	76.39 259	89.39 212

test0.0.03 1		68.00 297	67.69 294	68.90 327	77.55 334	47.43 348	75.70 321	72.95 344	66.66 239	66.56 304	82.29 293	48.06 283	75.87 346	44.97 340	74.51 288	83.41 319

PVSNet	64.34 18	72.08 270	70.87 269	75.69 287	86.21 218	56.44 306	74.37 328	80.73 306	62.06 294	70.17 270	82.23 294	42.86 315	83.31 318	54.77 293	84.45 167	87.32 265

MIMVSNet1		68.58 294	66.78 301	73.98 304	80.07 318	51.82 334	80.77 279	84.37 261	64.40 267	59.75 339	82.16 295	36.47 340	83.63 316	42.73 344	70.33 317	86.48 284

CL-MVSNet_2432*1600		72.37 268	71.46 260	75.09 294	79.49 327	53.53 327	80.76 280	85.01 256	69.12 211	70.51 264	82.05 296	57.92 196	84.13 312	52.27 302	66.00 331	87.60 257

tpm2		73.26 258	71.46 260	78.63 253	83.34 262	56.71 302	80.65 282	80.40 312	56.63 332	73.55 235	82.02 297	51.80 250	91.24 232	56.35 288	78.42 235	87.95 248

PatchMatch-RL		72.38 267	70.90 267	76.80 281	88.60 159	67.38 145	79.53 292	76.17 334	62.75 287	69.36 282	82.00 298	45.51 302	84.89 308	53.62 297	80.58 212	78.12 344

FMVSNet5		69.50 287	67.96 288	74.15 303	82.97 275	55.35 317	80.01 288	82.12 295	62.56 289	63.02 327	81.53 299	36.92 339	81.92 323	48.42 321	74.06 291	85.17 303

CR-MVSNet		73.37 255	71.27 264	79.67 239	81.32 305	65.19 183	75.92 318	80.30 313	59.92 308	72.73 244	81.19 300	52.50 235	86.69 294	59.84 256	77.71 239	87.11 273

Patchmtry		70.74 276	69.16 278	75.49 291	80.72 310	54.07 324	74.94 327	80.30 313	58.34 320	70.01 272	81.19 300	52.50 235	86.54 295	53.37 298	71.09 315	85.87 296

IB-MVS	68.01 15	75.85 233	73.36 245	83.31 145	84.76 239	66.03 163	83.38 254	85.06 254	70.21 188	69.40 281	81.05 302	45.76 300	94.66 107	65.10 216	75.49 271	89.25 215
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
cascas		76.72 220	74.64 230	82.99 163	85.78 223	65.88 169	82.33 266	89.21 177	60.85 301	72.74 243	81.02 303	47.28 288	93.75 145	67.48 194	85.02 159	89.34 213

LF4IMVS		64.02 315	62.19 318	69.50 325	70.90 355	53.29 331	76.13 315	77.18 331	52.65 343	58.59 340	80.98 304	23.55 356	76.52 343	53.06 300	66.66 328	78.68 343

Anonymous20240521		68.80 292	67.22 298	73.55 305	74.33 346	54.11 323	83.18 256	85.61 249	58.15 321	61.68 332	80.94 305	30.71 352	81.27 326	57.00 284	73.34 301	85.28 300

gm-plane-assit					81.40 301	53.83 326			62.72 288		80.94 305		92.39 196	63.40 226

UnsupCasMVSNet_eth		67.33 300	65.99 303	71.37 316	73.48 350	51.47 338	75.16 323	85.19 253	65.20 257	60.78 335	80.93 307	42.35 317	77.20 341	57.12 282	53.69 349	85.44 298

MVS_0304		72.48 265	70.89 268	77.24 276	82.20 290	59.68 266	84.11 242	83.49 277	67.10 234	66.87 301	80.59 308	35.00 345	87.40 290	59.07 264	79.58 221	84.63 309

MDTV_nov1_ep13			69.97 275		83.18 267	53.48 328	77.10 314	80.18 316	60.45 302	69.33 283	80.44 309	48.89 281	86.90 293	51.60 305	78.51 233

pmmvs-eth3d		70.50 280	67.83 291	78.52 257	77.37 336	66.18 162	81.82 269	81.51 300	58.90 317	63.90 325	80.42 310	42.69 316	86.28 298	58.56 269	65.30 333	83.11 323

PM-MVS		66.41 306	64.14 308	73.20 309	73.92 348	56.45 305	78.97 299	64.96 358	63.88 277	64.72 319	80.24 311	19.84 359	83.44 317	66.24 204	64.52 335	79.71 341

SCA		74.22 247	72.33 254	79.91 233	84.05 251	62.17 240	79.96 289	79.29 321	66.30 245	72.38 249	80.13 312	51.95 246	88.60 278	59.25 261	77.67 241	88.96 227

Patchmatch-test		64.82 313	63.24 313	69.57 324	79.42 328	49.82 345	63.49 353	69.05 352	51.98 345	59.95 338	80.13 312	50.91 257	70.98 355	40.66 348	73.57 296	87.90 251

tpmrst		72.39 266	72.13 255	73.18 310	80.54 313	49.91 344	79.91 290	79.08 322	63.11 280	71.69 256	79.95 314	55.32 213	82.77 321	65.66 212	73.89 293	86.87 276

DSMNet-mixed		57.77 321	56.90 323	60.38 336	67.70 357	35.61 360	69.18 342	53.97 362	32.30 359	57.49 344	79.88 315	40.39 329	68.57 357	38.78 350	72.37 305	76.97 346

MDA-MVSNet-bldmvs		66.68 303	63.66 311	75.75 286	79.28 329	60.56 259	73.92 329	78.35 324	64.43 266	50.13 353	79.87 316	44.02 310	83.67 315	46.10 335	56.86 345	83.03 325

PatchmatchNet		73.12 260	71.33 263	78.49 258	83.18 267	60.85 255	79.63 291	78.57 323	64.13 270	71.73 255	79.81 317	51.20 255	85.97 300	57.40 280	76.36 262	88.66 237
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ppachtmachnet_test		70.04 284	67.34 297	78.14 261	79.80 322	61.13 251	79.19 297	80.59 308	59.16 315	65.27 315	79.29 318	46.75 292	87.29 291	49.33 318	66.72 327	86.00 295

EPMVS		69.02 290	68.16 285	71.59 314	79.61 325	49.80 346	77.40 312	66.93 354	62.82 286	70.01 272	79.05 319	45.79 299	77.86 339	56.58 286	75.26 281	87.13 272

PMMVS		69.34 288	68.67 280	71.35 318	75.67 341	62.03 241	75.17 322	73.46 342	50.00 347	68.68 285	79.05 319	52.07 244	78.13 336	61.16 248	82.77 188	73.90 348

test-LLR		72.94 263	72.43 252	74.48 299	81.35 303	58.04 281	78.38 303	77.46 328	66.66 239	69.95 275	79.00 321	48.06 283	79.24 331	66.13 205	84.83 161	86.15 289

test-mter		71.41 272	70.39 273	74.48 299	81.35 303	58.04 281	78.38 303	77.46 328	60.32 304	69.95 275	79.00 321	36.08 342	79.24 331	66.13 205	84.83 161	86.15 289

DIV-MVS_2432*1600		68.81 291	67.59 296	72.46 312	74.29 347	45.45 351	77.93 309	87.00 232	63.12 279	63.99 324	78.99 323	42.32 318	84.77 309	56.55 287	64.09 336	87.16 271

KD-MVS_2432*1600		66.22 308	63.89 309	73.21 307	75.47 344	53.42 329	70.76 337	84.35 262	64.10 271	66.52 306	78.52 324	34.55 346	84.98 306	50.40 310	50.33 353	81.23 334

miper_refine_blended		66.22 308	63.89 309	73.21 307	75.47 344	53.42 329	70.76 337	84.35 262	64.10 271	66.52 306	78.52 324	34.55 346	84.98 306	50.40 310	50.33 353	81.23 334

DWT-MVSNet_test		73.70 252	71.86 257	79.21 247	82.91 276	58.94 271	82.34 265	82.17 293	65.21 256	71.05 262	78.31 326	44.21 308	90.17 253	63.29 228	77.28 243	88.53 241

tpmvs		71.09 274	69.29 277	76.49 282	82.04 292	56.04 312	78.92 300	81.37 302	64.05 273	67.18 298	78.28 327	49.74 272	89.77 257	49.67 317	72.37 305	83.67 317

our_test_3		69.14 289	67.00 299	75.57 289	79.80 322	58.80 273	77.96 308	77.81 326	59.55 311	62.90 330	78.25 328	47.43 286	83.97 313	51.71 304	67.58 326	83.93 316

MDA-MVSNet_test_wron		65.03 311	62.92 314	71.37 316	75.93 339	56.73 300	69.09 345	74.73 339	57.28 329	54.03 350	77.89 329	45.88 297	74.39 352	49.89 316	61.55 339	82.99 326

YYNet1		65.03 311	62.91 315	71.38 315	75.85 340	56.60 304	69.12 344	74.66 341	57.28 329	54.12 349	77.87 330	45.85 298	74.48 351	49.95 315	61.52 340	83.05 324

ambc				75.24 293	73.16 352	50.51 343	63.05 354	87.47 224		64.28 321	77.81 331	17.80 360	89.73 259	57.88 276	60.64 341	85.49 297

tpm cat1		70.57 278	68.31 283	77.35 274	82.41 288	57.95 284	78.08 307	80.22 315	52.04 344	68.54 288	77.66 332	52.00 245	87.84 287	51.77 303	72.07 309	86.25 286

dp		66.80 302	65.43 304	70.90 321	79.74 324	48.82 347	75.12 325	74.77 338	59.61 310	64.08 323	77.23 333	42.89 314	80.72 328	48.86 320	66.58 329	83.16 322

TESTMET0.1,1		69.89 286	69.00 279	72.55 311	79.27 330	56.85 298	78.38 303	74.71 340	57.64 325	68.09 289	77.19 334	37.75 337	76.70 342	63.92 222	84.09 170	84.10 315

CHOSEN 280x420		66.51 305	64.71 306	71.90 313	81.45 300	63.52 216	57.98 355	68.95 353	53.57 340	62.59 331	76.70 335	46.22 295	75.29 349	55.25 291	79.68 220	76.88 347

PatchT		68.46 296	67.85 290	70.29 322	80.70 311	43.93 354	72.47 331	74.88 337	60.15 306	70.55 263	76.57 336	49.94 269	81.59 324	50.58 308	74.83 285	85.34 299

RPMNet		73.51 254	70.49 270	82.58 180	81.32 305	65.19 183	75.92 318	92.27 78	57.60 326	72.73 244	76.45 337	52.30 238	95.43 71	48.14 326	77.71 239	87.11 273

ADS-MVSNet2		66.20 310	63.33 312	74.82 297	79.92 319	58.75 274	67.55 347	75.19 336	53.37 341	65.25 316	75.86 338	42.32 318	80.53 329	41.57 346	68.91 322	85.18 301

ADS-MVSNet		64.36 314	62.88 316	68.78 329	79.92 319	47.17 349	67.55 347	71.18 345	53.37 341	65.25 316	75.86 338	42.32 318	73.99 353	41.57 346	68.91 322	85.18 301

new-patchmatchnet		61.73 317	61.73 319	61.70 335	72.74 354	24.50 367	69.16 343	78.03 325	61.40 297	56.72 346	75.53 340	38.42 334	76.48 344	45.95 336	57.67 344	84.13 314

N_pmnet		52.79 324	53.26 325	51.40 341	78.99 331	7.68 370	69.52 340	3.89 370	51.63 346	57.01 345	74.98 341	40.83 327	65.96 358	37.78 351	64.67 334	80.56 339

patchmatchnet-post											74.00 342	51.12 256	88.60 278

GG-mvs-BLEND				75.38 292	81.59 298	55.80 314	79.32 294	69.63 349		67.19 297	73.67 343	43.24 312	88.90 276	50.41 309	84.50 165	81.45 333

Patchmatch-RL test		70.24 282	67.78 293	77.61 270	77.43 335	59.57 269	71.16 334	70.33 346	62.94 284	68.65 286	72.77 344	50.62 261	85.49 303	69.58 178	66.58 329	87.77 254

FPMVS		53.68 323	51.64 326	59.81 337	65.08 358	51.03 340	69.48 341	69.58 350	41.46 351	40.67 355	72.32 345	16.46 362	70.00 356	24.24 358	65.42 332	58.40 355

UnsupCasMVSNet_bld		63.70 316	61.53 320	70.21 323	73.69 349	51.39 339	72.82 330	81.89 296	55.63 336	57.81 343	71.80 346	38.67 333	78.61 334	49.26 319	52.21 351	80.63 337

PVSNet_0	57.27 20	61.67 318	59.27 321	68.85 328	79.61 325	57.44 293	68.01 346	73.44 343	55.93 335	58.54 341	70.41 347	44.58 306	77.55 340	47.01 330	35.91 356	71.55 350

pmmvs3		57.79 320	54.26 324	68.37 330	64.02 359	56.72 301	75.12 325	65.17 356	40.20 352	52.93 351	69.86 348	20.36 358	75.48 348	45.45 338	55.25 348	72.90 349

new_pmnet		50.91 325	50.29 327	52.78 340	68.58 356	34.94 362	63.71 352	56.63 361	39.73 353	44.95 354	65.47 349	21.93 357	58.48 359	34.98 353	56.62 346	64.92 352

gg-mvs-nofinetune		69.95 285	67.96 288	75.94 285	83.07 270	54.51 321	77.23 313	70.29 347	63.11 280	70.32 267	62.33 350	43.62 311	88.69 277	53.88 296	87.76 126	84.62 310

JIA-IIPM		66.32 307	62.82 317	76.82 280	77.09 337	61.72 247	65.34 350	75.38 335	58.04 323	64.51 320	62.32 351	42.05 322	86.51 296	51.45 306	69.22 321	82.21 329

LCM-MVSNet		54.25 322	49.68 328	67.97 331	53.73 362	45.28 352	66.85 349	80.78 305	35.96 356	39.45 356	62.23 352	8.70 368	78.06 338	48.24 325	51.20 352	80.57 338

PMMVS2		40.82 329	38.86 332	46.69 342	53.84 361	16.45 368	48.61 358	49.92 363	37.49 355	31.67 357	60.97 353	8.14 369	56.42 360	28.42 355	30.72 358	67.19 351

MVS-HIRNet		59.14 319	57.67 322	63.57 334	81.65 296	43.50 355	71.73 333	65.06 357	39.59 354	51.43 352	57.73 354	38.34 335	82.58 322	39.53 349	73.95 292	64.62 353

ANet_high		50.57 326	46.10 329	63.99 333	48.67 365	39.13 358	70.99 336	80.85 304	61.39 298	31.18 358	57.70 355	17.02 361	73.65 354	31.22 354	15.89 363	79.18 342

PMVS	37.38 22	44.16 328	40.28 331	55.82 338	40.82 367	42.54 356	65.12 351	63.99 359	34.43 357	24.48 360	57.12 356	3.92 370	76.17 345	17.10 361	55.52 347	48.75 356
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		31.52 331	29.28 335	38.23 344	27.03 369	6.50 371	20.94 363	62.21 360	4.05 365	22.35 363	52.50 357	13.33 363	47.58 363	27.04 357	34.04 357	60.62 354

DeepMVS_CX				27.40 347	40.17 368	26.90 365		24.59 369	17.44 363	23.95 361	48.61 358	9.77 366	26.48 365	18.06 360	24.47 359	28.83 359

MVE	26.22 23	30.37 333	25.89 337	43.81 343	44.55 366	35.46 361	28.87 362	39.07 366	18.20 362	18.58 364	40.18 359	2.68 371	47.37 364	17.07 362	23.78 360	48.60 357
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		45.18 327	41.86 330	55.16 339	77.03 338	51.52 337	32.50 361	80.52 309	32.46 358	27.12 359	35.02 360	9.52 367	75.50 347	22.31 359	60.21 343	38.45 358
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		31.77 330	30.64 333	35.15 345	52.87 363	27.67 364	57.09 356	47.86 364	24.64 360	16.40 365	33.05 361	11.23 365	54.90 361	14.46 363	18.15 361	22.87 360

EMVS		30.81 332	29.65 334	34.27 346	50.96 364	25.95 366	56.58 357	46.80 365	24.01 361	15.53 366	30.68 362	12.47 364	54.43 362	12.81 364	17.05 362	22.43 361

tmp_tt		18.61 335	21.40 338	10.23 349	4.82 370	10.11 369	34.70 360	30.74 368	1.48 366	23.91 362	26.07 363	28.42 353	13.41 367	27.12 356	15.35 364	7.17 362

X-MVStestdata		80.37 142	77.83 176	88.00 13	94.42 20	73.33 18	92.78 15	92.99 46	79.14 21	83.67 78	12.47 364	67.45 90	96.60 31	83.06 56	94.50 52	94.07 37

test_post											5.46 365	50.36 265	84.24 311

test_post1							78.90 301				5.43 366	48.81 282	85.44 304	59.25 261

wuyk23d		16.82 336	15.94 339	19.46 348	58.74 360	31.45 363	39.22 359	3.74 371	6.84 364	6.04 367	2.70 367	1.27 372	24.29 366	10.54 365	14.40 365	2.63 363

testmvs		6.04 339	8.02 342	0.10 351	0.08 371	0.03 373	69.74 339	0.04 372	0.05 367	0.31 368	1.68 368	0.02 374	0.04 368	0.24 366	0.02 366	0.25 365

test123		6.12 338	8.11 341	0.14 350	0.06 372	0.09 372	71.05 335	0.03 373	0.04 368	0.25 369	1.30 369	0.05 373	0.03 369	0.21 367	0.01 367	0.29 364

uanet_test		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

pcd_1.5k_mvsjas		5.26 340	7.02 343	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	63.15 135	0.00 370	0.00 368	0.00 368	0.00 366

sosnet-low-res		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

sosnet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uncertanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

Regformer		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

eth-test2					0.00 373

eth-test					0.00 373

IU-MVS					95.30 2	71.25 59		92.95 51	66.81 235	92.39 5				88.94 8	96.63 2	94.85 10

save fliter					93.80 39	72.35 42	90.47 63	91.17 124	74.31 116

test_0728_SECOND				87.71 31	95.34 1	71.43 58	93.49 7	94.23 5					97.49 1	89.08 4	96.41 8	94.21 32

GSMVS																88.96 227

test_part2					95.06 7	72.65 31				91.80 10

sam_mvs1												51.32 254				88.96 227

sam_mvs												50.01 267

MTGPA								92.02 89

MTMP							92.18 30	32.83 367

test9_res														84.90 30	95.70 27	92.87 93

agg_prior2														82.91 59	95.45 29	92.70 97

agg_prior					92.85 61	71.94 51		91.78 104		84.41 65			94.93 94

test_prior4						72.60 33	89.01 99

test_prior				86.33 60	92.61 69	69.59 96		92.97 49					95.48 66			93.91 45

旧先验2							86.56 181		58.10 322	87.04 31			88.98 272	74.07 136

新几何2							86.29 189

无先验							87.48 153	88.98 187	60.00 307				94.12 125	67.28 196		88.97 226

原ACMM2							86.86 170

testdata2													91.01 241	62.37 235

segment_acmp												73.08 40

testdata1							84.14 241		75.71 87

test12				86.80 52	92.63 68	70.70 76		91.79 103		82.71 92		71.67 52	96.16 44		94.50 52	93.54 69

plane_prior7					90.08 107	68.51 124

plane_prior6					89.84 112	68.70 119						60.42 183

plane_prior5								92.44 70					95.38 75	78.71 93	86.32 148	91.33 139

plane_prior3						68.60 122			78.44 30	78.92 132

plane_prior2							91.25 47		79.12 23

plane_prior1					89.90 111

plane_prior						68.71 117	90.38 67		77.62 37						86.16 151

n2								0.00 374

nn								0.00 374

door-mid								69.98 348

test11								92.23 81

door								69.44 351

HQP5-MVS						66.98 151

HQP-NCC					89.33 126		89.17 92		76.41 71	77.23 168

ACMP_Plane					89.33 126		89.17 92		76.41 71	77.23 168

BP-MVS														77.47 107

HQP4-MVS										77.24 167			95.11 87			91.03 149

HQP3-MVS								92.19 84							85.99 154

HQP2-MVS												60.17 186

MDTV_nov1_ep13_2view						37.79 359	75.16 323		55.10 337	66.53 305		49.34 276		53.98 295		87.94 250

ACMMP++_ref															81.95 198

ACMMP++															81.25 203

Test By Simon												64.33 120

High-resolution multi-view benchmark