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.

SD-MVS		99.41 44	99.52 6	99.05 170	99.74 72	99.68 54	99.46 157	99.52 91	99.11 10	99.88 5	99.91 8	99.43 1	97.70 356	98.72 109	99.93 10	99.77 70
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
TSAR-MVS + MP.		99.58 5	99.50 8	99.81 41	99.91 1	99.66 59	99.63 64	99.39 216	98.91 44	99.78 34	99.85 32	99.36 2	99.94 57	98.84 91	99.88 36	99.82 38
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PC_three_1452									98.18 110	99.84 14	99.70 138	99.31 3	98.52 341	98.30 165	99.80 87	99.81 44

SteuartSystems-ACMMP		99.54 10	99.42 14	99.87 12	99.82 38	99.81 27	99.59 84	99.51 104	98.62 65	99.79 29	99.83 45	99.28 4	99.97 11	98.48 145	99.90 23	99.84 20
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		99.59 3	99.50 8	99.88 6	99.51 157	99.88 8	99.87 5	99.51 104	98.99 29	99.88 5	99.81 65	99.27 5	99.96 19	98.85 88	99.80 87	99.81 44

OPU-MVS				99.64 80	99.56 149	99.72 47	99.60 77				99.70 138	99.27 5	99.42 254	98.24 167	99.80 87	99.79 60

SED-MVS		99.61 2	99.52 6	99.88 6	99.84 33	99.90 2	99.60 77	99.48 145	99.08 15	99.91 1	99.81 65	99.20 7	99.96 19	98.91 74	99.85 58	99.79 60

test_241102_ONE					99.84 33	99.90 2		99.48 145	99.07 17	99.91 1	99.74 122	99.20 7	99.76 181

MSLP-MVS++		99.46 25	99.47 10	99.44 125	99.60 139	99.16 128	99.41 177	99.71 13	98.98 32	99.45 120	99.78 100	99.19 9	99.54 238	99.28 37	99.84 65	99.63 131

SMA-MVS		99.44 31	99.30 43	99.85 28	99.73 80	99.83 17	99.56 105	99.47 163	97.45 192	99.78 34	99.82 52	99.18 10	99.91 94	98.79 100	99.89 33	99.81 44
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
APDe-MVS		99.66 1	99.57 1	99.92 1	99.77 51	99.89 4	99.75 31	99.56 57	99.02 19	99.88 5	99.85 32	99.18 10	99.96 19	99.22 42	99.92 11	99.90 1

HPM-MVS_fast		99.51 15	99.40 17	99.85 28	99.91 1	99.79 33	99.76 30	99.56 57	97.72 163	99.76 41	99.75 116	99.13 12	99.92 83	99.07 58	99.92 11	99.85 16

PGM-MVS		99.45 27	99.31 39	99.86 21	99.87 16	99.78 40	99.58 92	99.65 32	97.84 148	99.71 51	99.80 81	99.12 13	99.97 11	98.33 161	99.87 40	99.83 31

test_one_0601					99.81 41	99.88 8		99.49 132	98.97 35	99.65 75	99.81 65	99.09 14

test_0728_THIRD									98.99 29	99.81 24	99.80 81	99.09 14	99.96 19	98.85 88	99.90 23	99.88 7

HFP-MVS		99.49 16	99.37 21	99.86 21	99.87 16	99.80 29	99.66 52	99.67 22	98.15 112	99.68 58	99.69 146	99.06 16	99.96 19	98.69 114	99.87 40	99.84 20

#test#		99.43 35	99.29 47	99.86 21	99.87 16	99.80 29	99.55 114	99.67 22	97.83 149	99.68 58	99.69 146	99.06 16	99.96 19	98.39 153	99.87 40	99.84 20

TSAR-MVS + GP.		99.36 51	99.36 23	99.36 132	99.67 106	98.61 194	99.07 270	99.33 248	99.00 26	99.82 22	99.81 65	99.06 16	99.84 140	99.09 56	99.42 140	99.65 120

pcd_1.5k_mvsjas		8.27 344	11.03 347	0.00 358	0.00 381	0.00 382	0.00 369	0.00 382	0.00 376	0.00 377	0.27 377	99.01 19	0.00 377	0.00 375	0.00 375	0.00 373

PS-MVSNAJss		98.92 117	98.92 100	98.90 195	98.78 310	98.53 199	99.78 25	99.54 74	98.07 126	99.00 224	99.76 111	99.01 19	99.37 261	99.13 52	97.23 259	98.81 231

PS-MVSNAJ		99.32 56	99.32 32	99.30 143	99.57 145	98.94 162	98.97 298	99.46 173	98.92 43	99.71 51	99.24 296	99.01 19	99.98 6	99.35 27	99.66 123	98.97 221

EI-MVSNet-Vis-set		99.58 5	99.56 3	99.64 80	99.78 46	99.15 132	99.61 76	99.45 185	99.01 22	99.89 4	99.82 52	99.01 19	99.92 83	99.56 5	99.95 6	99.85 16

Regformer-1		99.53 12	99.47 10	99.72 64	99.71 91	99.44 99	99.49 143	99.46 173	98.95 38	99.83 19	99.76 111	99.01 19	99.93 72	99.17 48	99.87 40	99.80 54

Regformer-2		99.54 10	99.47 10	99.75 54	99.71 91	99.52 88	99.49 143	99.49 132	98.94 39	99.83 19	99.76 111	99.01 19	99.94 57	99.15 51	99.87 40	99.80 54

Regformer-4		99.59 3	99.54 4	99.73 61	99.76 54	99.41 102	99.58 92	99.49 132	99.02 19	99.88 5	99.80 81	99.00 25	99.94 57	99.45 19	99.92 11	99.84 20

EI-MVSNet-UG-set		99.58 5	99.57 1	99.64 80	99.78 46	99.14 133	99.60 77	99.45 185	99.01 22	99.90 3	99.83 45	98.98 26	99.93 72	99.59 2	99.95 6	99.86 13

Regformer-3		99.57 8	99.53 5	99.68 68	99.76 54	99.29 113	99.58 92	99.44 194	99.01 22	99.87 11	99.80 81	98.97 27	99.91 94	99.44 21	99.92 11	99.83 31

region2R		99.48 20	99.35 26	99.87 12	99.88 12	99.80 29	99.65 59	99.66 27	98.13 114	99.66 69	99.68 153	98.96 28	99.96 19	98.62 123	99.87 40	99.84 20

segment_acmp												98.96 28

CNVR-MVS		99.42 40	99.30 43	99.78 48	99.62 131	99.71 49	99.26 236	99.52 91	98.82 50	99.39 139	99.71 134	98.96 28	99.85 134	98.59 131	99.80 87	99.77 70

xxxxxxxxxxxxxcwj		99.43 35	99.32 32	99.75 54	99.76 54	99.59 73	99.14 258	99.53 85	99.00 26	99.71 51	99.80 81	98.95 31	99.93 72	98.19 170	99.84 65	99.74 81

SF-MVS		99.38 49	99.24 59	99.79 46	99.79 44	99.68 54	99.57 98	99.54 74	97.82 154	99.71 51	99.80 81	98.95 31	99.93 72	98.19 170	99.84 65	99.74 81

ACMMPR		99.49 16	99.36 23	99.86 21	99.87 16	99.79 33	99.66 52	99.67 22	98.15 112	99.67 64	99.69 146	98.95 31	99.96 19	98.69 114	99.87 40	99.84 20

test_241102_TWO								99.48 145	99.08 15	99.88 5	99.81 65	98.94 34	99.96 19	98.91 74	99.84 65	99.88 7

DVP-MVS		99.57 8	99.47 10	99.88 6	99.85 26	99.89 4	99.57 98	99.37 231	99.10 11	99.81 24	99.80 81	98.94 34	99.96 19	98.93 71	99.86 51	99.81 44
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					99.85 26	99.89 4	99.62 70	99.50 124	99.10 11	99.86 12	99.82 52	98.94 34

xiu_mvs_v2_base		99.26 66	99.25 57	99.29 146	99.53 153	98.91 166	99.02 284	99.45 185	98.80 54	99.71 51	99.26 294	98.94 34	99.98 6	99.34 31	99.23 155	98.98 220

CP-MVS		99.45 27	99.32 32	99.85 28	99.83 37	99.75 43	99.69 40	99.52 91	98.07 126	99.53 106	99.63 179	98.93 38	99.97 11	98.74 105	99.91 16	99.83 31

ZNCC-MVS		99.47 23	99.33 30	99.87 12	99.87 16	99.81 27	99.64 62	99.67 22	98.08 125	99.55 103	99.64 173	98.91 39	99.96 19	98.72 109	99.90 23	99.82 38

MCST-MVS		99.43 35	99.30 43	99.82 38	99.79 44	99.74 46	99.29 220	99.40 212	98.79 55	99.52 109	99.62 185	98.91 39	99.90 109	98.64 121	99.75 102	99.82 38

HPM-MVS		99.42 40	99.28 51	99.83 36	99.90 4	99.72 47	99.81 15	99.54 74	97.59 175	99.68 58	99.63 179	98.91 39	99.94 57	98.58 132	99.91 16	99.84 20
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testdata				99.54 96	99.75 64	98.95 159		99.51 104	97.07 230	99.43 125	99.70 138	98.87 42	99.94 57	97.76 207	99.64 126	99.72 94

APD-MVS_3200maxsize		99.48 20	99.35 26	99.85 28	99.76 54	99.83 17	99.63 64	99.54 74	98.36 88	99.79 29	99.82 52	98.86 43	99.95 46	98.62 123	99.81 83	99.78 68

DeepC-MVS_fast	98.69 1	99.49 16	99.39 18	99.77 50	99.63 125	99.59 73	99.36 201	99.46 173	99.07 17	99.79 29	99.82 52	98.85 44	99.92 83	98.68 116	99.87 40	99.82 38
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
9.14			99.10 72		99.72 85		99.40 185	99.51 104	97.53 185	99.64 79	99.78 100	98.84 45	99.91 94	97.63 220	99.82 80

CDPH-MVS		99.13 82	98.91 102	99.80 43	99.75 64	99.71 49	99.15 256	99.41 206	96.60 266	99.60 91	99.55 208	98.83 46	99.90 109	97.48 236	99.83 74	99.78 68

ACMMP_NAP		99.47 23	99.34 28	99.88 6	99.87 16	99.86 13	99.47 154	99.48 145	98.05 131	99.76 41	99.86 26	98.82 47	99.93 72	98.82 98	99.91 16	99.84 20

XVS		99.53 12	99.42 14	99.87 12	99.85 26	99.83 17	99.69 40	99.68 19	98.98 32	99.37 144	99.74 122	98.81 48	99.94 57	98.79 100	99.86 51	99.84 20

X-MVStestdata		96.55 296	95.45 311	99.87 12	99.85 26	99.83 17	99.69 40	99.68 19	98.98 32	99.37 144	64.01 374	98.81 48	99.94 57	98.79 100	99.86 51	99.84 20

MP-MVS-pluss		99.37 50	99.20 63	99.88 6	99.90 4	99.87 12	99.30 216	99.52 91	97.18 218	99.60 91	99.79 93	98.79 50	99.95 46	98.83 94	99.91 16	99.83 31
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mPP-MVS		99.44 31	99.30 43	99.86 21	99.88 12	99.79 33	99.69 40	99.48 145	98.12 116	99.50 112	99.75 116	98.78 51	99.97 11	98.57 134	99.89 33	99.83 31

APD-MVS		99.27 64	99.08 75	99.84 35	99.75 64	99.79 33	99.50 133	99.50 124	97.16 220	99.77 36	99.82 52	98.78 51	99.94 57	97.56 229	99.86 51	99.80 54
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TAPA-MVS	97.07 15	97.74 248	97.34 268	98.94 185	99.70 98	97.53 251	99.25 238	99.51 104	91.90 349	99.30 158	99.63 179	98.78 51	99.64 224	88.09 360	99.87 40	99.65 120
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TEST9					99.67 106	99.65 62	99.05 275	99.41 206	96.22 294	98.95 230	99.49 230	98.77 54	99.91 94

agg_prior1		99.01 110	98.76 123	99.76 53	99.67 106	99.62 66	98.99 291	99.40 212	96.26 290	98.87 243	99.49 230	98.77 54	99.91 94	97.69 217	99.72 109	99.75 76

train_agg		99.02 107	98.77 121	99.77 50	99.67 106	99.65 62	99.05 275	99.41 206	96.28 287	98.95 230	99.49 230	98.76 56	99.91 94	97.63 220	99.72 109	99.75 76

test_8					99.67 106	99.61 68	99.03 281	99.41 206	96.28 287	98.93 234	99.48 236	98.76 56	99.91 94

API-MVS		99.04 104	99.03 82	99.06 168	99.40 195	99.31 111	99.55 114	99.56 57	98.54 69	99.33 154	99.39 263	98.76 56	99.78 175	96.98 268	99.78 94	98.07 339

RE-MVS-def			99.34 28		99.76 54	99.82 23	99.63 64	99.52 91	98.38 84	99.76 41	99.82 52	98.75 59		98.61 126	99.81 83	99.77 70

DP-MVS Recon		99.12 88	98.95 98	99.65 75	99.74 72	99.70 51	99.27 227	99.57 51	96.40 283	99.42 128	99.68 153	98.75 59	99.80 167	97.98 189	99.72 109	99.44 177

Test By Simon												98.75 59

ACMMP		99.45 27	99.32 32	99.82 38	99.89 9	99.67 57	99.62 70	99.69 18	98.12 116	99.63 80	99.84 41	98.73 62	99.96 19	98.55 140	99.83 74	99.81 44
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
DPE-MVS		99.46 25	99.32 32	99.91 2	99.78 46	99.88 8	99.36 201	99.51 104	98.73 59	99.88 5	99.84 41	98.72 63	99.96 19	98.16 175	99.87 40	99.88 7
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
NCCC		99.34 53	99.19 64	99.79 46	99.61 135	99.65 62	99.30 216	99.48 145	98.86 46	99.21 182	99.63 179	98.72 63	99.90 109	98.25 166	99.63 128	99.80 54

DeepPCF-MVS	98.18 3	98.81 134	99.37 21	97.12 323	99.60 139	91.75 360	98.61 334	99.44 194	99.35 1	99.83 19	99.85 32	98.70 65	99.81 162	99.02 62	99.91 16	99.81 44

SR-MVS		99.43 35	99.29 47	99.86 21	99.75 64	99.83 17	99.59 84	99.62 33	98.21 106	99.73 47	99.79 93	98.68 66	99.96 19	98.44 151	99.77 97	99.79 60

test_prior3		99.21 70	99.05 77	99.68 68	99.67 106	99.48 93	98.96 299	99.56 57	98.34 90	99.01 219	99.52 220	98.68 66	99.83 151	97.96 190	99.74 105	99.74 81

test_prior2							98.96 299		98.34 90	99.01 219	99.52 220	98.68 66		97.96 190	99.74 105

DPM-MVS		98.95 115	98.71 127	99.66 71	99.63 125	99.55 80	98.64 333	99.10 294	97.93 140	99.42 128	99.55 208	98.67 69	99.80 167	95.80 303	99.68 120	99.61 135

原ACMM1				99.65 75	99.73 80	99.33 107		99.47 163	97.46 189	99.12 198	99.66 165	98.67 69	99.91 94	97.70 216	99.69 115	99.71 101

HPM-MVS++		99.39 48	99.23 61	99.87 12	99.75 64	99.84 16	99.43 168	99.51 104	98.68 63	99.27 166	99.53 217	98.64 71	99.96 19	98.44 151	99.80 87	99.79 60

abl_6		99.44 31	99.31 39	99.83 36	99.85 26	99.75 43	99.66 52	99.59 43	98.13 114	99.82 22	99.81 65	98.60 72	99.96 19	98.46 149	99.88 36	99.79 60

ZD-MVS					99.71 91	99.79 33		99.61 35	96.84 248	99.56 99	99.54 213	98.58 73	99.96 19	96.93 273	99.75 102

PHI-MVS		99.30 58	99.17 66	99.70 67	99.56 149	99.52 88	99.58 92	99.80 8	97.12 224	99.62 84	99.73 129	98.58 73	99.90 109	98.61 126	99.91 16	99.68 110

test1172		99.43 35	99.29 47	99.85 28	99.75 64	99.82 23	99.60 77	99.56 57	98.28 96	99.74 45	99.79 93	98.53 75	99.95 46	98.55 140	99.78 94	99.79 60

SR-MVS-dyc-post		99.45 27	99.31 39	99.85 28	99.76 54	99.82 23	99.63 64	99.52 91	98.38 84	99.76 41	99.82 52	98.53 75	99.95 46	98.61 126	99.81 83	99.77 70

GST-MVS		99.40 47	99.24 59	99.85 28	99.86 22	99.79 33	99.60 77	99.67 22	97.97 137	99.63 80	99.68 153	98.52 77	99.95 46	98.38 155	99.86 51	99.81 44

ETH3D-3000-0.1		99.21 70	99.02 85	99.77 50	99.73 80	99.69 52	99.38 194	99.51 104	97.45 192	99.61 87	99.75 116	98.51 78	99.91 94	97.45 241	99.83 74	99.71 101

MVS_111021_LR		99.41 44	99.33 30	99.65 75	99.77 51	99.51 90	98.94 305	99.85 6	98.82 50	99.65 75	99.74 122	98.51 78	99.80 167	98.83 94	99.89 33	99.64 127

MVS_111021_HR		99.41 44	99.32 32	99.66 71	99.72 85	99.47 95	98.95 303	99.85 6	98.82 50	99.54 104	99.73 129	98.51 78	99.74 185	98.91 74	99.88 36	99.77 70

旧先验1					99.74 72	99.59 73		99.54 74			99.69 146	98.47 81			99.68 120	99.73 88

DELS-MVS		99.48 20	99.42 14	99.65 75	99.72 85	99.40 104	99.05 275	99.66 27	99.14 6	99.57 98	99.80 81	98.46 82	99.94 57	99.57 4	99.84 65	99.60 137
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
PAPR		98.63 151	98.34 160	99.51 110	99.40 195	99.03 145	98.80 318	99.36 232	96.33 284	99.00 224	99.12 311	98.46 82	99.84 140	95.23 316	99.37 149	99.66 116

zzz-MVS		99.49 16	99.36 23	99.89 4	99.90 4	99.86 13	99.36 201	99.47 163	98.79 55	99.68 58	99.81 65	98.43 84	99.97 11	98.88 77	99.90 23	99.83 31

MTAPA		99.52 14	99.39 18	99.89 4	99.90 4	99.86 13	99.66 52	99.47 163	98.79 55	99.68 58	99.81 65	98.43 84	99.97 11	98.88 77	99.90 23	99.83 31

新几何1				99.75 54	99.75 64	99.59 73		99.54 74	96.76 252	99.29 161	99.64 173	98.43 84	99.94 57	96.92 275	99.66 123	99.72 94

F-COLMAP		99.19 72	99.04 80	99.64 80	99.78 46	99.27 116	99.42 175	99.54 74	97.29 208	99.41 132	99.59 195	98.42 87	99.93 72	98.19 170	99.69 115	99.73 88

ETV-MVS		99.26 66	99.21 62	99.40 128	99.46 178	99.30 112	99.56 105	99.52 91	98.52 71	99.44 124	99.27 293	98.41 88	99.86 128	99.10 55	99.59 132	99.04 213

1121		99.09 97	98.87 107	99.75 54	99.74 72	99.60 70	99.27 227	99.48 145	96.82 251	99.25 173	99.65 166	98.38 89	99.93 72	97.53 232	99.67 122	99.73 88

test12				99.75 54	99.64 122	99.61 68		99.29 270		99.21 182		98.38 89	99.89 117		99.74 105	99.74 81

CSCG		99.32 56	99.32 32	99.32 138	99.85 26	98.29 217	99.71 37	99.66 27	98.11 118	99.41 132	99.80 81	98.37 91	99.96 19	98.99 64	99.96 5	99.72 94

CS-MVS		99.34 53	99.31 39	99.43 126	99.44 185	99.47 95	99.68 45	99.56 57	98.41 81	99.62 84	99.41 255	98.35 92	99.76 181	99.52 7	99.76 100	99.05 212

PAPM_NR		99.04 104	98.84 113	99.66 71	99.74 72	99.44 99	99.39 189	99.38 222	97.70 165	99.28 163	99.28 290	98.34 93	99.85 134	96.96 270	99.45 138	99.69 106

TAMVS		99.12 88	99.08 75	99.24 154	99.46 178	98.55 197	99.51 127	99.46 173	98.09 121	99.45 120	99.82 52	98.34 93	99.51 239	98.70 111	98.93 180	99.67 113

ETH3D cwj APD-0.16		99.06 101	98.84 113	99.72 64	99.51 157	99.60 70	99.23 241	99.44 194	97.04 233	99.39 139	99.67 159	98.30 95	99.92 83	97.27 248	99.69 115	99.64 127

MP-MVS		99.33 55	99.15 67	99.87 12	99.88 12	99.82 23	99.66 52	99.46 173	98.09 121	99.48 116	99.74 122	98.29 96	99.96 19	97.93 193	99.87 40	99.82 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test222					99.75 64	99.49 91	98.91 308	99.49 132	96.42 281	99.34 153	99.65 166	98.28 97			99.69 115	99.72 94

PLC	97.94 4	99.02 107	98.85 112	99.53 102	99.66 115	99.01 148	99.24 240	99.52 91	96.85 247	99.27 166	99.48 236	98.25 98	99.91 94	97.76 207	99.62 129	99.65 120
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSP-MVS		99.42 40	99.27 53	99.88 6	99.89 9	99.80 29	99.67 48	99.50 124	98.70 61	99.77 36	99.49 230	98.21 99	99.95 46	98.46 149	99.77 97	99.88 7
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
DROMVSNet		99.44 31	99.39 18	99.58 90	99.56 149	99.49 91	99.88 1	99.58 49	98.38 84	99.73 47	99.69 146	98.20 100	99.70 208	99.64 1	99.82 80	99.54 150

xiu_mvs_v1_base_debu		99.29 61	99.27 53	99.34 133	99.63 125	98.97 153	99.12 260	99.51 104	98.86 46	99.84 14	99.47 239	98.18 101	99.99 1	99.50 10	99.31 150	99.08 205

xiu_mvs_v1_base		99.29 61	99.27 53	99.34 133	99.63 125	98.97 153	99.12 260	99.51 104	98.86 46	99.84 14	99.47 239	98.18 101	99.99 1	99.50 10	99.31 150	99.08 205

xiu_mvs_v1_base_debi		99.29 61	99.27 53	99.34 133	99.63 125	98.97 153	99.12 260	99.51 104	98.86 46	99.84 14	99.47 239	98.18 101	99.99 1	99.50 10	99.31 150	99.08 205

CS-MVS-test		99.30 58	99.25 57	99.45 120	99.46 178	99.23 120	99.80 19	99.57 51	98.28 96	99.53 106	99.44 245	98.16 104	99.79 170	99.38 24	99.61 131	99.34 187

testtj		99.12 88	98.87 107	99.86 21	99.72 85	99.79 33	99.44 162	99.51 104	97.29 208	99.59 94	99.74 122	98.15 105	99.96 19	96.74 281	99.69 115	99.81 44

EIA-MVS		99.18 74	99.09 74	99.45 120	99.49 169	99.18 125	99.67 48	99.53 85	97.66 171	99.40 137	99.44 245	98.10 106	99.81 162	98.94 69	99.62 129	99.35 185

CNLPA		99.14 80	98.99 90	99.59 87	99.58 143	99.41 102	99.16 252	99.44 194	98.45 77	99.19 188	99.49 230	98.08 107	99.89 117	97.73 211	99.75 102	99.48 167

114514_t		98.93 116	98.67 131	99.72 64	99.85 26	99.53 85	99.62 70	99.59 43	92.65 347	99.71 51	99.78 100	98.06 108	99.90 109	98.84 91	99.91 16	99.74 81

CDS-MVSNet		99.09 97	99.03 82	99.25 152	99.42 187	98.73 183	99.45 158	99.46 173	98.11 118	99.46 119	99.77 107	98.01 109	99.37 261	98.70 111	98.92 182	99.66 116
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MG-MVS		99.13 82	99.02 85	99.45 120	99.57 145	98.63 191	99.07 270	99.34 241	98.99 29	99.61 87	99.82 52	97.98 110	99.87 125	97.00 266	99.80 87	99.85 16

EI-MVSNet		98.67 147	98.67 131	98.68 228	99.35 204	97.97 232	99.50 133	99.38 222	96.93 244	99.20 185	99.83 45	97.87 111	99.36 265	98.38 155	97.56 239	98.71 250

IterMVS-LS		98.46 156	98.42 155	98.58 235	99.59 141	98.00 230	99.37 197	99.43 202	96.94 243	99.07 210	99.59 195	97.87 111	99.03 316	98.32 163	95.62 297	98.71 250
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		98.98 112	98.80 118	99.53 102	99.76 54	99.19 123	98.75 323	99.55 67	97.25 212	99.47 117	99.77 107	97.82 113	99.87 125	96.93 273	99.90 23	99.54 150

OMC-MVS		99.08 99	99.04 80	99.20 157	99.67 106	98.22 221	99.28 222	99.52 91	98.07 126	99.66 69	99.81 65	97.79 114	99.78 175	97.79 204	99.81 83	99.60 137

LS3D		99.27 64	99.12 70	99.74 59	99.18 248	99.75 43	99.56 105	99.57 51	98.45 77	99.49 115	99.85 32	97.77 115	99.94 57	98.33 161	99.84 65	99.52 156

PVSNet_Blended_VisFu		99.36 51	99.28 51	99.61 85	99.86 22	99.07 142	99.47 154	99.93 2	97.66 171	99.71 51	99.86 26	97.73 116	99.96 19	99.47 17	99.82 80	99.79 60

1314		98.68 146	98.54 150	99.11 165	98.89 294	98.65 189	99.27 227	99.49 132	96.89 245	97.99 316	99.56 205	97.72 117	99.83 151	97.74 210	99.27 153	98.84 230

MVS_Test		99.10 96	98.97 94	99.48 114	99.49 169	99.14 133	99.67 48	99.34 241	97.31 206	99.58 96	99.76 111	97.65 118	99.82 158	98.87 81	99.07 170	99.46 174

PVSNet_BlendedMVS		98.86 122	98.80 118	99.03 173	99.76 54	98.79 180	99.28 222	99.91 3	97.42 198	99.67 64	99.37 267	97.53 119	99.88 122	98.98 65	97.29 258	98.42 322

PVSNet_Blended		99.08 99	98.97 94	99.42 127	99.76 54	98.79 180	98.78 320	99.91 3	96.74 253	99.67 64	99.49 230	97.53 119	99.88 122	98.98 65	99.85 58	99.60 137

UA-Net		99.42 40	99.29 47	99.80 43	99.62 131	99.55 80	99.50 133	99.70 15	98.79 55	99.77 36	99.96 1	97.45 121	99.96 19	98.92 73	99.90 23	99.89 2

ETH3 D test6400		98.70 143	98.35 159	99.73 61	99.69 101	99.60 70	99.16 252	99.45 185	95.42 316	99.27 166	99.60 192	97.39 122	99.91 94	95.36 314	99.83 74	99.70 103

MVSFormer		99.17 76	99.12 70	99.29 146	99.51 157	98.94 162	99.88 1	99.46 173	97.55 180	99.80 27	99.65 166	97.39 122	99.28 279	99.03 60	99.85 58	99.65 120

lupinMVS		99.13 82	99.01 89	99.46 119	99.51 157	98.94 162	99.05 275	99.16 288	97.86 144	99.80 27	99.56 205	97.39 122	99.86 128	98.94 69	99.85 58	99.58 145

DP-MVS		99.16 78	98.95 98	99.78 48	99.77 51	99.53 85	99.41 177	99.50 124	97.03 235	99.04 216	99.88 18	97.39 122	99.92 83	98.66 119	99.90 23	99.87 12

sss		99.17 76	99.05 77	99.53 102	99.62 131	98.97 153	99.36 201	99.62 33	97.83 149	99.67 64	99.65 166	97.37 126	99.95 46	99.19 45	99.19 158	99.68 110

mvs_anonymous		99.03 106	98.99 90	99.16 161	99.38 199	98.52 203	99.51 127	99.38 222	97.79 155	99.38 142	99.81 65	97.30 127	99.45 244	99.35 27	98.99 177	99.51 162

miper_ehance_all_eth		98.18 180	98.10 175	98.41 257	99.23 235	97.72 247	98.72 326	99.31 261	96.60 266	98.88 241	99.29 288	97.29 128	99.13 303	97.60 222	95.99 286	98.38 327

CPTT-MVS		99.11 93	98.90 103	99.74 59	99.80 43	99.46 97	99.59 84	99.49 132	97.03 235	99.63 80	99.69 146	97.27 129	99.96 19	97.82 202	99.84 65	99.81 44

PMMVS		98.80 137	98.62 141	99.34 133	99.27 227	98.70 185	98.76 322	99.31 261	97.34 203	99.21 182	99.07 313	97.20 130	99.82 158	98.56 137	98.87 185	99.52 156

EPP-MVSNet		99.13 82	98.99 90	99.53 102	99.65 120	99.06 143	99.81 15	99.33 248	97.43 196	99.60 91	99.88 18	97.14 131	99.84 140	99.13 52	98.94 179	99.69 106

c3_l		98.12 188	98.04 184	98.38 261	99.30 218	97.69 250	98.81 317	99.33 248	96.67 258	98.83 249	99.34 276	97.11 132	98.99 322	97.58 224	95.34 303	98.48 313

canonicalmvs		99.02 107	98.86 111	99.51 110	99.42 187	99.32 108	99.80 19	99.48 145	98.63 64	99.31 156	98.81 331	97.09 133	99.75 184	99.27 39	97.90 227	99.47 172

MAR-MVS		98.86 122	98.63 136	99.54 96	99.37 201	99.66 59	99.45 158	99.54 74	96.61 264	99.01 219	99.40 259	97.09 133	99.86 128	97.68 219	99.53 136	99.10 200
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
miper_enhance_ethall		98.16 182	98.08 179	98.41 257	98.96 289	97.72 247	98.45 343	99.32 258	96.95 241	98.97 228	99.17 303	97.06 135	99.22 289	97.86 198	95.99 286	98.29 330

jason		99.13 82	99.03 82	99.45 120	99.46 178	98.87 169	99.12 260	99.26 273	98.03 134	99.79 29	99.65 166	97.02 136	99.85 134	99.02 62	99.90 23	99.65 120
jason: jason.
our_test_3		97.65 264	97.68 224	97.55 312	98.62 328	94.97 333	98.84 314	99.30 265	96.83 250	98.19 307	99.34 276	97.01 137	99.02 318	95.00 320	96.01 284	98.64 282

MVS		97.28 283	96.55 292	99.48 114	98.78 310	98.95 159	99.27 227	99.39 216	83.53 362	98.08 311	99.54 213	96.97 138	99.87 125	94.23 328	99.16 159	99.63 131

Fast-Effi-MVS+-dtu		98.77 140	98.83 117	98.60 231	99.41 190	96.99 278	99.52 123	99.49 132	98.11 118	99.24 174	99.34 276	96.96 139	99.79 170	97.95 192	99.45 138	99.02 216

1112_ss		98.98 112	98.77 121	99.59 87	99.68 105	99.02 146	99.25 238	99.48 145	97.23 215	99.13 196	99.58 198	96.93 140	99.90 109	98.87 81	98.78 191	99.84 20

WTY-MVS		99.06 101	98.88 106	99.61 85	99.62 131	99.16 128	99.37 197	99.56 57	98.04 132	99.53 106	99.62 185	96.84 141	99.94 57	98.85 88	98.49 204	99.72 94

FC-MVSNet-test		98.75 141	98.62 141	99.15 163	99.08 270	99.45 98	99.86 8	99.60 40	98.23 103	98.70 268	99.82 52	96.80 142	99.22 289	99.07 58	96.38 277	98.79 233

Effi-MVS+-dtu		98.78 138	98.89 105	98.47 250	99.33 209	96.91 284	99.57 98	99.30 265	98.47 74	99.41 132	98.99 322	96.78 143	99.74 185	98.73 107	99.38 142	98.74 246

mvs-test1		98.86 122	98.84 113	98.89 198	99.33 209	97.77 244	99.44 162	99.30 265	98.47 74	99.10 203	99.43 248	96.78 143	99.95 46	98.73 107	99.02 175	98.96 223

Test_1112_low_res		98.89 118	98.66 134	99.57 92	99.69 101	98.95 159	99.03 281	99.47 163	96.98 237	99.15 194	99.23 297	96.77 145	99.89 117	98.83 94	98.78 191	99.86 13

FIs		98.78 138	98.63 136	99.23 156	99.18 248	99.54 82	99.83 12	99.59 43	98.28 96	98.79 255	99.81 65	96.75 146	99.37 261	99.08 57	96.38 277	98.78 234

PVSNet	96.02 17	98.85 130	98.84 113	98.89 198	99.73 80	97.28 257	98.32 350	99.60 40	97.86 144	99.50 112	99.57 202	96.75 146	99.86 128	98.56 137	99.70 114	99.54 150

nrg030		98.64 150	98.42 155	99.28 149	99.05 276	99.69 52	99.81 15	99.46 173	98.04 132	99.01 219	99.82 52	96.69 148	99.38 258	99.34 31	94.59 317	98.78 234

CHOSEN 280x420		99.12 88	99.13 69	99.08 166	99.66 115	97.89 238	98.43 344	99.71 13	98.88 45	99.62 84	99.76 111	96.63 149	99.70 208	99.46 18	99.99 1	99.66 116

eth_miper_zixun_eth		98.05 198	97.96 193	98.33 264	99.26 229	97.38 255	98.56 339	99.31 261	96.65 260	98.88 241	99.52 220	96.58 150	99.12 307	97.39 245	95.53 300	98.47 315

cdsmvs_eth3d_5k		24.64 342	32.85 345	0.00 358	0.00 381	0.00 382	0.00 369	99.51 104	0.00 376	0.00 377	99.56 205	96.58 150	0.00 377	0.00 375	0.00 375	0.00 373

IS-MVSNet		99.05 103	98.87 107	99.57 92	99.73 80	99.32 108	99.75 31	99.20 283	98.02 135	99.56 99	99.86 26	96.54 152	99.67 214	98.09 179	99.13 163	99.73 88

diffmvs		99.14 80	99.02 85	99.51 110	99.61 135	98.96 157	99.28 222	99.49 132	98.46 76	99.72 50	99.71 134	96.50 153	99.88 122	99.31 34	99.11 164	99.67 113

CANet		99.25 68	99.14 68	99.59 87	99.41 190	99.16 128	99.35 207	99.57 51	98.82 50	99.51 111	99.61 189	96.46 154	99.95 46	99.59 2	99.98 2	99.65 120

ppachtmachnet_test		97.49 277	97.45 248	97.61 309	98.62 328	95.24 327	98.80 318	99.46 173	96.11 305	98.22 306	99.62 185	96.45 155	98.97 330	93.77 332	95.97 289	98.61 301

HY-MVS	97.30 7	98.85 130	98.64 135	99.47 117	99.42 187	99.08 140	99.62 70	99.36 232	97.39 201	99.28 163	99.68 153	96.44 156	99.92 83	98.37 157	98.22 213	99.40 182

UniMVSNet_NR-MVSNet		98.22 174	97.97 191	98.96 182	98.92 292	98.98 150	99.48 149	99.53 85	97.76 158	98.71 262	99.46 243	96.43 157	99.22 289	98.57 134	92.87 340	98.69 258

Effi-MVS+		98.81 134	98.59 147	99.48 114	99.46 178	99.12 137	98.08 356	99.50 124	97.50 188	99.38 142	99.41 255	96.37 158	99.81 162	99.11 54	98.54 201	99.51 162

AdaColmap		99.01 110	98.80 118	99.66 71	99.56 149	99.54 82	99.18 250	99.70 15	98.18 110	99.35 150	99.63 179	96.32 159	99.90 109	97.48 236	99.77 97	99.55 148

UniMVSNet (Re)		98.29 171	98.00 188	99.13 164	99.00 282	99.36 106	99.49 143	99.51 104	97.95 138	98.97 228	99.13 308	96.30 160	99.38 258	98.36 159	93.34 333	98.66 278

LCM-MVSNet-Re		97.83 231	98.15 170	96.87 329	99.30 218	92.25 358	99.59 84	98.26 345	97.43 196	96.20 345	99.13 308	96.27 161	98.73 339	98.17 174	98.99 177	99.64 127

PAPM		97.59 267	97.09 283	99.07 167	99.06 273	98.26 220	98.30 351	99.10 294	94.88 325	98.08 311	99.34 276	96.27 161	99.64 224	89.87 354	98.92 182	99.31 190

Fast-Effi-MVS+		98.70 143	98.43 154	99.51 110	99.51 157	99.28 114	99.52 123	99.47 163	96.11 305	99.01 219	99.34 276	96.20 163	99.84 140	97.88 196	98.82 188	99.39 183

EPNet_dtu		98.03 201	97.96 193	98.23 274	98.27 340	95.54 320	99.23 241	98.75 327	99.02 19	97.82 321	99.71 134	96.11 164	99.48 240	93.04 341	99.65 125	99.69 106
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline		99.15 79	99.02 85	99.53 102	99.66 115	99.14 133	99.72 35	99.48 145	98.35 89	99.42 128	99.84 41	96.07 165	99.79 170	99.51 9	99.14 162	99.67 113

D2MVS		98.41 161	98.50 151	98.15 279	99.26 229	96.62 294	99.40 185	99.61 35	97.71 164	98.98 226	99.36 270	96.04 166	99.67 214	98.70 111	97.41 254	98.15 337

miper_lstm_enhance		98.00 208	97.91 199	98.28 272	99.34 208	97.43 254	98.88 310	99.36 232	96.48 276	98.80 253	99.55 208	95.98 167	98.91 334	97.27 248	95.50 301	98.51 311

EPNet		98.86 122	98.71 127	99.30 143	97.20 356	98.18 222	99.62 70	98.91 316	99.28 2	98.63 279	99.81 65	95.96 168	99.99 1	99.24 41	99.72 109	99.73 88
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
AllTest		98.87 119	98.72 125	99.31 139	99.86 22	98.48 209	99.56 105	99.61 35	97.85 146	99.36 147	99.85 32	95.95 169	99.85 134	96.66 287	99.83 74	99.59 141

TestCases				99.31 139	99.86 22	98.48 209		99.61 35	97.85 146	99.36 147	99.85 32	95.95 169	99.85 134	96.66 287	99.83 74	99.59 141

3Dnovator	97.25 9	99.24 69	99.05 77	99.81 41	99.12 261	99.66 59	99.84 9	99.74 10	99.09 14	98.92 235	99.90 10	95.94 171	99.98 6	98.95 68	99.92 11	99.79 60

casdiffmvs		99.13 82	98.98 93	99.56 94	99.65 120	99.16 128	99.56 105	99.50 124	98.33 93	99.41 132	99.86 26	95.92 172	99.83 151	99.45 19	99.16 159	99.70 103

RPSCF		98.22 174	98.62 141	96.99 324	99.82 38	91.58 361	99.72 35	99.44 194	96.61 264	99.66 69	99.89 13	95.92 172	99.82 158	97.46 239	99.10 167	99.57 146

pmmvs4		98.13 186	97.90 200	98.81 216	98.61 330	98.87 169	98.99 291	99.21 282	96.44 279	99.06 214	99.58 198	95.90 174	99.11 308	97.18 258	96.11 283	98.46 319

HyFIR lowres test		99.11 93	98.92 100	99.65 75	99.90 4	99.37 105	99.02 284	99.91 3	97.67 170	99.59 94	99.75 116	95.90 174	99.73 192	99.53 6	99.02 175	99.86 13

COLMAP_ROB	97.56 6	98.86 122	98.75 124	99.17 160	99.88 12	98.53 199	99.34 210	99.59 43	97.55 180	98.70 268	99.89 13	95.83 176	99.90 109	98.10 178	99.90 23	99.08 205
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
DeepC-MVS	98.35 2	99.30 58	99.19 64	99.64 80	99.82 38	99.23 120	99.62 70	99.55 67	98.94 39	99.63 80	99.95 2	95.82 177	99.94 57	99.37 26	99.97 3	99.73 88
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
QAPM		98.67 147	98.30 164	99.80 43	99.20 243	99.67 57	99.77 27	99.72 11	94.74 328	98.73 260	99.90 10	95.78 178	99.98 6	96.96 270	99.88 36	99.76 75

BH-untuned		98.42 159	98.36 157	98.59 232	99.49 169	96.70 290	99.27 227	99.13 292	97.24 214	98.80 253	99.38 264	95.75 179	99.74 185	97.07 264	99.16 159	99.33 189

test_djsdf		98.67 147	98.57 148	98.98 179	98.70 321	98.91 166	99.88 1	99.46 173	97.55 180	99.22 179	99.88 18	95.73 180	99.28 279	99.03 60	97.62 234	98.75 242

DIV-MVS_self_test		98.01 206	97.85 206	98.48 246	99.24 234	97.95 236	98.71 327	99.35 237	96.50 271	98.60 284	99.54 213	95.72 181	99.03 316	97.21 252	95.77 292	98.46 319

bset_n11_16_dypcd		98.16 182	97.97 191	98.73 223	98.26 341	98.28 219	97.99 358	98.01 351	97.68 167	99.10 203	99.63 179	95.68 182	99.15 299	98.78 103	96.55 272	98.75 242

3Dnovator+	97.12 13	99.18 74	98.97 94	99.82 38	99.17 254	99.68 54	99.81 15	99.51 104	99.20 4	98.72 261	99.89 13	95.68 182	99.97 11	98.86 86	99.86 51	99.81 44

cl____		98.01 206	97.84 207	98.55 240	99.25 233	97.97 232	98.71 327	99.34 241	96.47 278	98.59 285	99.54 213	95.65 184	99.21 294	97.21 252	95.77 292	98.46 319

VNet		99.11 93	98.90 103	99.73 61	99.52 155	99.56 78	99.41 177	99.39 216	99.01 22	99.74 45	99.78 100	95.56 185	99.92 83	99.52 7	98.18 217	99.72 94

WR-MVS_H		98.13 186	97.87 205	98.90 195	99.02 280	98.84 173	99.70 38	99.59 43	97.27 210	98.40 296	99.19 302	95.53 186	99.23 286	98.34 160	93.78 329	98.61 301

CHOSEN 1792x2688		99.19 72	99.10 72	99.45 120	99.89 9	98.52 203	99.39 189	99.94 1	98.73 59	99.11 200	99.89 13	95.50 187	99.94 57	99.50 10	99.97 3	99.89 2

Vis-MVSNet (Re-imp)		98.87 119	98.72 125	99.31 139	99.71 91	98.88 168	99.80 19	99.44 194	97.91 142	99.36 147	99.78 100	95.49 188	99.43 253	97.91 194	99.11 164	99.62 133

PatchMatch-RL		98.84 133	98.62 141	99.52 108	99.71 91	99.28 114	99.06 273	99.77 9	97.74 162	99.50 112	99.53 217	95.41 189	99.84 140	97.17 259	99.64 126	99.44 177

RRT_MVS		98.60 152	98.44 153	99.05 170	98.88 295	99.14 133	99.49 143	99.38 222	97.76 158	99.29 161	99.86 26	95.38 190	99.36 265	98.81 99	97.16 263	98.64 282

test_yl		98.86 122	98.63 136	99.54 96	99.49 169	99.18 125	99.50 133	99.07 299	98.22 104	99.61 87	99.51 224	95.37 191	99.84 140	98.60 129	98.33 207	99.59 141

DCV-MVSNet		98.86 122	98.63 136	99.54 96	99.49 169	99.18 125	99.50 133	99.07 299	98.22 104	99.61 87	99.51 224	95.37 191	99.84 140	98.60 129	98.33 207	99.59 141

tpmrst		98.33 167	98.48 152	97.90 296	99.16 256	94.78 337	99.31 214	99.11 293	97.27 210	99.45 120	99.59 195	95.33 193	99.84 140	98.48 145	98.61 194	99.09 204

MVP-Stereo		97.81 236	97.75 218	97.99 290	97.53 349	96.60 295	98.96 299	98.85 322	97.22 216	97.23 332	99.36 270	95.28 194	99.46 243	95.51 309	99.78 94	97.92 351
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CANet_DTU		98.97 114	98.87 107	99.25 152	99.33 209	98.42 214	99.08 269	99.30 265	99.16 5	99.43 125	99.75 116	95.27 195	99.97 11	98.56 137	99.95 6	99.36 184

XVG-OURS		98.73 142	98.68 130	98.88 201	99.70 98	97.73 246	98.92 306	99.55 67	98.52 71	99.45 120	99.84 41	95.27 195	99.91 94	98.08 183	98.84 187	99.00 217

BH-w/o		98.00 208	97.89 204	98.32 266	99.35 204	96.20 307	99.01 289	98.90 318	96.42 281	98.38 297	99.00 321	95.26 197	99.72 196	96.06 297	98.61 194	99.03 214

EU-MVSNet		97.98 210	98.03 185	97.81 303	98.72 318	96.65 293	99.66 52	99.66 27	98.09 121	98.35 300	99.82 52	95.25 198	98.01 349	97.41 244	95.30 304	98.78 234

GeoE		98.85 130	98.62 141	99.53 102	99.61 135	99.08 140	99.80 19	99.51 104	97.10 228	99.31 156	99.78 100	95.23 199	99.77 177	98.21 168	99.03 173	99.75 76

MDTV_nov1_ep13_2view						95.18 330	99.35 207		96.84 248	99.58 96		95.19 200		97.82 202		99.46 174

JIA-IIPM		97.50 274	97.02 285	98.93 187	98.73 316	97.80 243	99.30 216	98.97 307	91.73 350	98.91 236	94.86 362	95.10 201	99.71 202	97.58 224	97.98 225	99.28 192

NR-MVSNet		97.97 213	97.61 231	99.02 174	98.87 299	99.26 117	99.47 154	99.42 204	97.63 173	97.08 337	99.50 227	95.07 202	99.13 303	97.86 198	93.59 331	98.68 263

tpmvs		97.98 210	98.02 187	97.84 299	99.04 277	94.73 338	99.31 214	99.20 283	96.10 309	98.76 258	99.42 251	94.94 203	99.81 162	96.97 269	98.45 205	98.97 221

h-mvs33		97.70 256	97.28 274	98.97 181	99.70 98	97.27 258	99.36 201	99.45 185	98.94 39	99.66 69	99.64 173	94.93 204	99.99 1	99.48 15	84.36 357	99.65 120

hse-mvs2		97.50 274	97.14 281	98.59 232	99.49 169	97.05 271	99.28 222	99.22 279	98.94 39	99.66 69	99.42 251	94.93 204	99.65 221	99.48 15	83.80 359	99.08 205

v8		97.95 214	97.63 230	98.93 187	98.95 290	98.81 179	99.80 19	99.41 206	96.03 310	99.10 203	99.42 251	94.92 206	99.30 277	96.94 272	94.08 326	98.66 278

PatchmatchNet		98.31 168	98.36 157	98.19 276	99.16 256	95.32 326	99.27 227	98.92 313	97.37 202	99.37 144	99.58 198	94.90 207	99.70 208	97.43 243	99.21 156	99.54 150
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v7n		97.87 223	97.52 239	98.92 189	98.76 314	98.58 195	99.84 9	99.46 173	96.20 295	98.91 236	99.70 138	94.89 208	99.44 249	96.03 298	93.89 328	98.75 242

sam_mvs1												94.86 209				99.52 156

DU-MVS		98.08 192	97.79 209	98.96 182	98.87 299	98.98 150	99.41 177	99.45 185	97.87 143	98.71 262	99.50 227	94.82 210	99.22 289	98.57 134	92.87 340	98.68 263

Baseline_NR-MVSNet		97.76 241	97.45 248	98.68 228	99.09 268	98.29 217	99.41 177	98.85 322	95.65 314	98.63 279	99.67 159	94.82 210	99.10 310	98.07 186	92.89 339	98.64 282

patchmatchnet-post											98.70 336	94.79 212	99.74 185

Patchmatch-RL test		95.84 309	95.81 307	95.95 337	95.61 362	90.57 362	98.24 352	98.39 344	95.10 322	95.20 351	98.67 337	94.78 213	97.77 354	96.28 295	90.02 349	99.51 162

alignmvs		98.81 134	98.56 149	99.58 90	99.43 186	99.42 101	99.51 127	98.96 309	98.61 66	99.35 150	98.92 328	94.78 213	99.77 177	99.35 27	98.11 223	99.54 150

MDTV_nov1_ep13			98.32 162		99.11 263	94.44 340	99.27 227	98.74 330	97.51 187	99.40 137	99.62 185	94.78 213	99.76 181	97.59 223	98.81 190

Vis-MVSNet		99.12 88	98.97 94	99.56 94	99.78 46	99.10 138	99.68 45	99.66 27	98.49 73	99.86 12	99.87 23	94.77 216	99.84 140	99.19 45	99.41 141	99.74 81
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
anonymousdsp		98.44 157	98.28 165	98.94 185	98.50 336	98.96 157	99.77 27	99.50 124	97.07 230	98.87 243	99.77 107	94.76 217	99.28 279	98.66 119	97.60 235	98.57 307

v10		97.85 226	97.52 239	98.86 208	98.99 283	98.67 187	99.75 31	99.41 206	95.70 313	98.98 226	99.41 255	94.75 218	99.23 286	96.01 299	94.63 316	98.67 270

OpenMVS	96.50 16	98.47 155	98.12 173	99.52 108	99.04 277	99.53 85	99.82 13	99.72 11	94.56 331	98.08 311	99.88 18	94.73 219	99.98 6	97.47 238	99.76 100	99.06 211

sam_mvs												94.72 220

v148		97.79 239	97.55 235	98.50 243	98.74 315	97.72 247	99.54 117	99.33 248	96.26 290	98.90 238	99.51 224	94.68 221	99.14 300	97.83 201	93.15 337	98.63 290

v1144		97.98 210	97.69 223	98.85 211	98.87 299	98.66 188	99.54 117	99.35 237	96.27 289	99.23 178	99.35 273	94.67 222	99.23 286	96.73 282	95.16 307	98.68 263

V42		98.06 193	97.79 209	98.86 208	98.98 286	98.84 173	99.69 40	99.34 241	96.53 270	99.30 158	99.37 267	94.67 222	99.32 274	97.57 228	94.66 315	98.42 322

test_post											65.99 372	94.65 224	99.73 192

baseline1		98.31 168	97.95 195	99.38 131	99.50 167	98.74 182	99.59 84	98.93 311	98.41 81	99.14 195	99.60 192	94.59 225	99.79 170	98.48 145	93.29 334	99.61 135

DSMNet-mixed		97.25 284	97.35 265	96.95 327	97.84 346	93.61 352	99.57 98	96.63 364	96.13 304	98.87 243	98.61 340	94.59 225	97.70 356	95.08 318	98.86 186	99.55 148

Patchmatch-test		97.93 215	97.65 227	98.77 221	99.18 248	97.07 269	99.03 281	99.14 291	96.16 300	98.74 259	99.57 202	94.56 227	99.72 196	93.36 337	99.11 164	99.52 156

PCF-MVS	97.08 14	97.66 263	97.06 284	99.47 117	99.61 135	99.09 139	98.04 357	99.25 275	91.24 352	98.51 288	99.70 138	94.55 228	99.91 94	92.76 345	99.85 58	99.42 179
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PatchT		97.03 289	96.44 294	98.79 219	98.99 283	98.34 216	99.16 252	99.07 299	92.13 348	99.52 109	97.31 357	94.54 229	98.98 323	88.54 358	98.73 193	99.03 214

CVMVSNet		98.57 153	98.67 131	98.30 268	99.35 204	95.59 317	99.50 133	99.55 67	98.60 67	99.39 139	99.83 45	94.48 230	99.45 244	98.75 104	98.56 200	99.85 16

test-LLR		98.06 193	97.90 200	98.55 240	98.79 307	97.10 265	98.67 329	97.75 354	97.34 203	98.61 282	98.85 329	94.45 231	99.45 244	97.25 250	99.38 142	99.10 200

test0.0.03 1		97.71 255	97.42 257	98.56 238	98.41 339	97.82 242	98.78 320	98.63 339	97.34 203	98.05 315	98.98 325	94.45 231	98.98 323	95.04 319	97.15 264	98.89 227

v144192		97.92 218	97.60 232	98.87 205	98.83 305	98.65 189	99.55 114	99.34 241	96.20 295	99.32 155	99.40 259	94.36 233	99.26 283	96.37 294	95.03 310	98.70 254

CR-MVSNet		98.17 181	97.93 198	98.87 205	99.18 248	98.49 207	99.22 246	99.33 248	96.96 239	99.56 99	99.38 264	94.33 234	99.00 321	94.83 322	98.58 197	99.14 197

Patchmtry		97.75 245	97.40 259	98.81 216	99.10 266	98.87 169	99.11 266	99.33 248	94.83 326	98.81 251	99.38 264	94.33 234	99.02 318	96.10 296	95.57 298	98.53 309

tpm cat1		97.39 280	97.36 263	97.50 314	99.17 254	93.73 348	99.43 168	99.31 261	91.27 351	98.71 262	99.08 312	94.31 236	99.77 177	96.41 293	98.50 203	99.00 217

TranMVSNet+NR-MVSNet		97.93 215	97.66 226	98.76 222	98.78 310	98.62 192	99.65 59	99.49 132	97.76 158	98.49 290	99.60 192	94.23 237	98.97 330	98.00 188	92.90 338	98.70 254

v2v482		98.06 193	97.77 214	98.92 189	98.90 293	98.82 177	99.57 98	99.36 232	96.65 260	99.19 188	99.35 273	94.20 238	99.25 284	97.72 213	94.97 311	98.69 258

XVG-OURS-SEG-HR		98.69 145	98.62 141	98.89 198	99.71 91	97.74 245	99.12 260	99.54 74	98.44 80	99.42 128	99.71 134	94.20 238	99.92 83	98.54 142	98.90 184	99.00 217

ab-mvs		98.86 122	98.63 136	99.54 96	99.64 122	99.19 123	99.44 162	99.54 74	97.77 157	99.30 158	99.81 65	94.20 238	99.93 72	99.17 48	98.82 188	99.49 166

test_post1							99.23 241				65.14 373	94.18 241	99.71 202	97.58 224

ADS-MVSNet2		98.02 203	98.07 182	97.87 297	99.33 209	95.19 329	99.23 241	99.08 297	96.24 292	99.10 203	99.67 159	94.11 242	98.93 333	96.81 278	99.05 171	99.48 167

ADS-MVSNet		98.20 177	98.08 179	98.56 238	99.33 209	96.48 298	99.23 241	99.15 289	96.24 292	99.10 203	99.67 159	94.11 242	99.71 202	96.81 278	99.05 171	99.48 167

RPMNet		96.72 294	95.90 304	99.19 158	99.18 248	98.49 207	99.22 246	99.52 91	88.72 358	99.56 99	97.38 354	94.08 244	99.95 46	86.87 364	98.58 197	99.14 197

v1192		97.81 236	97.44 253	98.91 193	98.88 295	98.68 186	99.51 127	99.34 241	96.18 297	99.20 185	99.34 276	94.03 245	99.36 265	95.32 315	95.18 306	98.69 258

v1921920		97.80 238	97.45 248	98.84 212	98.80 306	98.53 199	99.52 123	99.34 241	96.15 302	99.24 174	99.47 239	93.98 246	99.29 278	95.40 312	95.13 308	98.69 258

Anonymous20231206		96.22 302	96.03 301	96.79 331	97.31 354	94.14 344	99.63 64	99.08 297	96.17 298	97.04 338	99.06 315	93.94 247	97.76 355	86.96 363	95.06 309	98.47 315

WR-MVS		98.06 193	97.73 220	99.06 168	98.86 302	99.25 118	99.19 249	99.35 237	97.30 207	98.66 271	99.43 248	93.94 247	99.21 294	98.58 132	94.28 322	98.71 250

N_pmnet		94.95 318	95.83 306	92.31 343	98.47 337	79.33 370	99.12 260	92.81 376	93.87 336	97.68 324	99.13 308	93.87 249	99.01 320	91.38 349	96.19 281	98.59 305

MVSTER		98.49 154	98.32 162	99.00 177	99.35 204	99.02 146	99.54 117	99.38 222	97.41 199	99.20 185	99.73 129	93.86 250	99.36 265	98.87 81	97.56 239	98.62 292

CP-MVSNet		98.09 190	97.78 212	99.01 175	98.97 288	99.24 119	99.67 48	99.46 173	97.25 212	98.48 291	99.64 173	93.79 251	99.06 312	98.63 122	94.10 325	98.74 246

cascas		97.69 257	97.43 256	98.48 246	98.60 331	97.30 256	98.18 355	99.39 216	92.96 346	98.41 295	98.78 334	93.77 252	99.27 282	98.16 175	98.61 194	98.86 228

v1240		97.69 257	97.32 271	98.79 219	98.85 303	98.43 212	99.48 149	99.36 232	96.11 305	99.27 166	99.36 270	93.76 253	99.24 285	94.46 325	95.23 305	98.70 254

test20.03		96.12 306	95.96 303	96.63 332	97.44 350	95.45 323	99.51 127	99.38 222	96.55 269	96.16 346	99.25 295	93.76 253	96.17 365	87.35 362	94.22 323	98.27 331

baseline2		97.87 223	97.55 235	98.82 214	99.18 248	98.02 229	99.41 177	96.58 365	96.97 238	96.51 342	99.17 303	93.43 255	99.57 234	97.71 214	99.03 173	98.86 228

TransMVSNet (Re)		97.15 286	96.58 291	98.86 208	99.12 261	98.85 172	99.49 143	98.91 316	95.48 315	97.16 335	99.80 81	93.38 256	99.11 308	94.16 330	91.73 345	98.62 292

tfpnnormal		97.84 229	97.47 245	98.98 179	99.20 243	99.22 122	99.64 62	99.61 35	96.32 285	98.27 305	99.70 138	93.35 257	99.44 249	95.69 305	95.40 302	98.27 331

Anonymous20231211		97.88 221	97.54 238	98.90 195	99.71 91	98.53 199	99.48 149	99.57 51	94.16 334	98.81 251	99.68 153	93.23 258	99.42 254	98.84 91	94.42 320	98.76 240

XXY-MVS		98.38 164	98.09 178	99.24 154	99.26 229	99.32 108	99.56 105	99.55 67	97.45 192	98.71 262	99.83 45	93.23 258	99.63 229	98.88 77	96.32 279	98.76 240

jajsoiax		98.43 158	98.28 165	98.88 201	98.60 331	98.43 212	99.82 13	99.53 85	98.19 107	98.63 279	99.80 81	93.22 260	99.44 249	99.22 42	97.50 245	98.77 238

MDA-MVSNet_test_wron		95.45 312	94.60 318	98.01 287	98.16 343	97.21 263	99.11 266	99.24 277	93.49 341	80.73 368	98.98 325	93.02 261	98.18 344	94.22 329	94.45 319	98.64 282

ACMM	97.58 5	98.37 165	98.34 160	98.48 246	99.41 190	97.10 265	99.56 105	99.45 185	98.53 70	99.04 216	99.85 32	93.00 262	99.71 202	98.74 105	97.45 250	98.64 282
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet3		98.03 201	97.76 217	98.84 212	99.39 198	98.98 150	99.40 185	99.38 222	96.67 258	99.07 210	99.28 290	92.93 263	98.98 323	97.10 261	96.65 268	98.56 308

DTE-MVSNet		97.51 273	97.19 280	98.46 251	98.63 327	98.13 226	99.84 9	99.48 145	96.68 257	97.97 317	99.67 159	92.92 264	98.56 340	96.88 277	92.60 343	98.70 254

CLD-MVS		98.16 182	98.10 175	98.33 264	99.29 222	96.82 287	98.75 323	99.44 194	97.83 149	99.13 196	99.55 208	92.92 264	99.67 214	98.32 163	97.69 231	98.48 313
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
BH-RMVSNet		98.41 161	98.08 179	99.40 128	99.41 190	98.83 176	99.30 216	98.77 326	97.70 165	98.94 232	99.65 166	92.91 266	99.74 185	96.52 289	99.55 135	99.64 127

YYNet1		95.36 314	94.51 320	97.92 294	97.89 345	97.10 265	99.10 268	99.23 278	93.26 344	80.77 367	99.04 317	92.81 267	98.02 348	94.30 326	94.18 324	98.64 282

mvs_tets		98.40 163	98.23 167	98.91 193	98.67 324	98.51 205	99.66 52	99.53 85	98.19 107	98.65 277	99.81 65	92.75 268	99.44 249	99.31 34	97.48 249	98.77 238

IterMVS		97.83 231	97.77 214	98.02 286	99.58 143	96.27 305	99.02 284	99.48 145	97.22 216	98.71 262	99.70 138	92.75 268	99.13 303	97.46 239	96.00 285	98.67 270
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UGNet		98.87 119	98.69 129	99.40 128	99.22 239	98.72 184	99.44 162	99.68 19	99.24 3	99.18 191	99.42 251	92.74 270	99.96 19	99.34 31	99.94 9	99.53 155
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
IterMVS-SCA-FT		97.82 234	97.75 218	98.06 283	99.57 145	96.36 302	99.02 284	99.49 132	97.18 218	98.71 262	99.72 133	92.72 271	99.14 300	97.44 242	95.86 291	98.67 270

SCA		98.19 178	98.16 169	98.27 273	99.30 218	95.55 318	99.07 270	98.97 307	97.57 178	99.43 125	99.57 202	92.72 271	99.74 185	97.58 224	99.20 157	99.52 156

HQP_MVS		98.27 173	98.22 168	98.44 255	99.29 222	96.97 280	99.39 189	99.47 163	98.97 35	99.11 200	99.61 189	92.71 273	99.69 212	97.78 205	97.63 232	98.67 270

plane_prior6					99.27 227	96.98 279						92.71 273

CL-MVSNet_self_test		94.49 321	93.97 324	96.08 336	96.16 360	93.67 351	98.33 349	99.38 222	95.13 318	97.33 330	98.15 349	92.69 275	96.57 363	88.67 357	79.87 363	97.99 346

dp		97.75 245	97.80 208	97.59 310	99.10 266	93.71 349	99.32 212	98.88 320	96.48 276	99.08 209	99.55 208	92.67 276	99.82 158	96.52 289	98.58 197	99.24 193

PEN-MVS		97.76 241	97.44 253	98.72 225	98.77 313	98.54 198	99.78 25	99.51 104	97.06 232	98.29 304	99.64 173	92.63 277	98.89 336	98.09 179	93.16 336	98.72 248

LPG-MVS_test		98.22 174	98.13 172	98.49 244	99.33 209	97.05 271	99.58 92	99.55 67	97.46 189	99.24 174	99.83 45	92.58 278	99.72 196	98.09 179	97.51 243	98.68 263

LGP-MVS_train				98.49 244	99.33 209	97.05 271		99.55 67	97.46 189	99.24 174	99.83 45	92.58 278	99.72 196	98.09 179	97.51 243	98.68 263

VPA-MVSNet		98.29 171	97.95 195	99.30 143	99.16 256	99.54 82	99.50 133	99.58 49	98.27 99	99.35 150	99.37 267	92.53 280	99.65 221	99.35 27	94.46 318	98.72 248

TR-MVS		97.76 241	97.41 258	98.82 214	99.06 273	97.87 239	98.87 312	98.56 341	96.63 263	98.68 270	99.22 298	92.49 281	99.65 221	95.40 312	97.79 229	98.95 226

pm-mvs1		97.68 259	97.28 274	98.88 201	99.06 273	98.62 192	99.50 133	99.45 185	96.32 285	97.87 319	99.79 93	92.47 282	99.35 269	97.54 231	93.54 332	98.67 270

HQP2-MVS												92.47 282

HQP-MVS		98.02 203	97.90 200	98.37 262	99.19 245	96.83 285	98.98 295	99.39 216	98.24 100	98.66 271	99.40 259	92.47 282	99.64 224	97.19 256	97.58 237	98.64 282

EPMVS		97.82 234	97.65 227	98.35 263	98.88 295	95.98 310	99.49 143	94.71 371	97.57 178	99.26 171	99.48 236	92.46 285	99.71 202	97.87 197	99.08 169	99.35 185

PS-CasMVS		97.93 215	97.59 234	98.95 184	98.99 283	99.06 143	99.68 45	99.52 91	97.13 222	98.31 302	99.68 153	92.44 286	99.05 313	98.51 143	94.08 326	98.75 242

cl22		97.85 226	97.64 229	98.48 246	99.09 268	97.87 239	98.60 336	99.33 248	97.11 227	98.87 243	99.22 298	92.38 287	99.17 298	98.21 168	95.99 286	98.42 322

CostFormer		97.72 251	97.73 220	97.71 307	99.15 259	94.02 345	99.54 117	99.02 303	94.67 329	99.04 216	99.35 273	92.35 288	99.77 177	98.50 144	97.94 226	99.34 187

OPM-MVS		98.19 178	98.10 175	98.45 252	98.88 295	97.07 269	99.28 222	99.38 222	98.57 68	99.22 179	99.81 65	92.12 289	99.66 217	98.08 183	97.54 241	98.61 301
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ET-MVSNet_ETH3D		96.49 298	95.64 309	99.05 170	99.53 153	98.82 177	98.84 314	97.51 358	97.63 173	84.77 363	99.21 301	92.09 290	98.91 334	98.98 65	92.21 344	99.41 181

AUN-MVS		96.88 290	96.31 296	98.59 232	99.48 176	97.04 274	99.27 227	99.22 279	97.44 195	98.51 288	99.41 255	91.97 291	99.66 217	97.71 214	83.83 358	99.07 210

ACMP	97.20 11	98.06 193	97.94 197	98.45 252	99.37 201	97.01 276	99.44 162	99.49 132	97.54 183	98.45 292	99.79 93	91.95 292	99.72 196	97.91 194	97.49 248	98.62 292
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous202405211		98.30 170	97.98 190	99.26 151	99.57 145	98.16 223	99.41 177	98.55 342	96.03 310	99.19 188	99.74 122	91.87 293	99.92 83	99.16 50	98.29 212	99.70 103

KD-MVS_self_test		95.00 316	94.34 321	96.96 326	97.07 359	95.39 325	99.56 105	99.44 194	95.11 320	97.13 336	97.32 356	91.86 294	97.27 359	90.35 353	81.23 362	98.23 335

tpm		97.67 262	97.55 235	98.03 284	99.02 280	95.01 332	99.43 168	98.54 343	96.44 279	99.12 198	99.34 276	91.83 295	99.60 232	97.75 209	96.46 275	99.48 167

thres100view900		97.76 241	97.45 248	98.69 227	99.72 85	97.86 241	99.59 84	98.74 330	97.93 140	99.26 171	98.62 338	91.75 296	99.83 151	93.22 338	98.18 217	98.37 328

thres600view7		97.86 225	97.51 241	98.92 189	99.72 85	97.95 236	99.59 84	98.74 330	97.94 139	99.27 166	98.62 338	91.75 296	99.86 128	93.73 333	98.19 216	98.96 223

LTVRE_ROB	97.16 12	98.02 203	97.90 200	98.40 259	99.23 235	96.80 288	99.70 38	99.60 40	97.12 224	98.18 308	99.70 138	91.73 298	99.72 196	98.39 153	97.45 250	98.68 263
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
OurMVSNet-221017-0		97.88 221	97.77 214	98.19 276	98.71 320	96.53 296	99.88 1	99.00 304	97.79 155	98.78 256	99.94 3	91.68 299	99.35 269	97.21 252	96.99 266	98.69 258

tfpn200view9		97.72 251	97.38 261	98.72 225	99.69 101	97.96 234	99.50 133	98.73 335	97.83 149	99.17 192	98.45 343	91.67 300	99.83 151	93.22 338	98.18 217	98.37 328

thres400		97.77 240	97.38 261	98.92 189	99.69 101	97.96 234	99.50 133	98.73 335	97.83 149	99.17 192	98.45 343	91.67 300	99.83 151	93.22 338	98.18 217	98.96 223

thisisatest0515		98.14 185	97.79 209	99.19 158	99.50 167	98.50 206	98.61 334	96.82 362	96.95 241	99.54 104	99.43 248	91.66 302	99.86 128	98.08 183	99.51 137	99.22 194

thres200		97.61 266	97.28 274	98.62 230	99.64 122	98.03 228	99.26 236	98.74 330	97.68 167	99.09 208	98.32 347	91.66 302	99.81 162	92.88 342	98.22 213	98.03 342

new_pmnet		96.38 301	96.03 301	97.41 315	98.13 344	95.16 331	99.05 275	99.20 283	93.94 335	97.39 329	98.79 332	91.61 304	99.04 314	90.43 352	95.77 292	98.05 341

pmmvs5		97.52 271	97.30 273	98.16 278	98.57 333	96.73 289	99.27 227	98.90 318	96.14 303	98.37 298	99.53 217	91.54 305	99.14 300	97.51 234	95.87 290	98.63 290

tttt0517		98.42 159	98.14 171	99.28 149	99.66 115	98.38 215	99.74 34	96.85 361	97.68 167	99.79 29	99.74 122	91.39 306	99.89 117	98.83 94	99.56 133	99.57 146

tpm2		97.44 279	97.34 268	97.74 306	99.15 259	94.36 342	99.45 158	98.94 310	93.45 343	98.90 238	99.44 245	91.35 307	99.59 233	97.31 246	98.07 224	99.29 191

MVS-HIRNet		95.75 310	95.16 314	97.51 313	99.30 218	93.69 350	98.88 310	95.78 366	85.09 361	98.78 256	92.65 364	91.29 308	99.37 261	94.85 321	99.85 58	99.46 174

thisisatest0530		98.35 166	98.03 185	99.31 139	99.63 125	98.56 196	99.54 117	96.75 363	97.53 185	99.73 47	99.65 166	91.25 309	99.89 117	98.62 123	99.56 133	99.48 167

testgi		97.65 264	97.50 242	98.13 280	99.36 203	96.45 299	99.42 175	99.48 145	97.76 158	97.87 319	99.45 244	91.09 310	98.81 337	94.53 324	98.52 202	99.13 199

ITE_SJBPF				98.08 281	99.29 222	96.37 301		98.92 313	98.34 90	98.83 249	99.75 116	91.09 310	99.62 230	95.82 301	97.40 255	98.25 333

DeepMVS_CX				93.34 341	99.29 222	82.27 367		99.22 279	85.15 360	96.33 344	99.05 316	90.97 312	99.73 192	93.57 335	97.77 230	98.01 343

ACMH	97.28 8	98.10 189	97.99 189	98.44 255	99.41 190	96.96 282	99.60 77	99.56 57	98.09 121	98.15 309	99.91 8	90.87 313	99.70 208	98.88 77	97.45 250	98.67 270
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test1111		98.04 199	98.11 174	97.83 300	99.74 72	93.82 346	99.58 92	95.40 368	99.12 9	99.65 75	99.93 4	90.73 314	99.84 140	99.43 22	99.38 142	99.82 38

ECVR-MVS		98.04 199	98.05 183	98.00 289	99.74 72	94.37 341	99.59 84	94.98 369	99.13 7	99.66 69	99.93 4	90.67 315	99.84 140	99.40 23	99.38 142	99.80 54

SixPastTwentyTwo		97.50 274	97.33 270	98.03 284	98.65 325	96.23 306	99.77 27	98.68 338	97.14 221	97.90 318	99.93 4	90.45 316	99.18 297	97.00 266	96.43 276	98.67 270

MIMVSNet		97.73 249	97.45 248	98.57 236	99.45 184	97.50 252	99.02 284	98.98 306	96.11 305	99.41 132	99.14 307	90.28 317	98.74 338	95.74 304	98.93 180	99.47 172

GBi-Net		97.68 259	97.48 243	98.29 269	99.51 157	97.26 260	99.43 168	99.48 145	96.49 272	99.07 210	99.32 283	90.26 318	98.98 323	97.10 261	96.65 268	98.62 292

test1		97.68 259	97.48 243	98.29 269	99.51 157	97.26 260	99.43 168	99.48 145	96.49 272	99.07 210	99.32 283	90.26 318	98.98 323	97.10 261	96.65 268	98.62 292

FMVSNet2		97.72 251	97.36 263	98.80 218	99.51 157	98.84 173	99.45 158	99.42 204	96.49 272	98.86 248	99.29 288	90.26 318	98.98 323	96.44 291	96.56 271	98.58 306

Anonymous20240529		98.09 190	97.68 224	99.34 133	99.66 115	98.44 211	99.40 185	99.43 202	93.67 338	99.22 179	99.89 13	90.23 321	99.93 72	99.26 40	98.33 207	99.66 116

ACMH+	97.24 10	97.92 218	97.78 212	98.32 266	99.46 178	96.68 292	99.56 105	99.54 74	98.41 81	97.79 323	99.87 23	90.18 322	99.66 217	98.05 187	97.18 262	98.62 292

LF4IMVS		97.52 271	97.46 247	97.70 308	98.98 286	95.55 318	99.29 220	98.82 325	98.07 126	98.66 271	99.64 173	89.97 323	99.61 231	97.01 265	96.68 267	97.94 349

GA-MVS		97.85 226	97.47 245	99.00 177	99.38 199	97.99 231	98.57 337	99.15 289	97.04 233	98.90 238	99.30 286	89.83 324	99.38 258	96.70 284	98.33 207	99.62 133

test_part1		97.75 245	97.24 278	99.29 146	99.59 141	99.63 65	99.65 59	99.49 132	96.17 298	98.44 293	99.69 146	89.80 325	99.47 241	98.68 116	93.66 330	98.78 234

PVSNet_0	94.43 19	96.09 307	95.47 310	97.94 292	99.31 217	94.34 343	97.81 359	99.70 15	97.12 224	97.46 327	98.75 335	89.71 326	99.79 170	97.69 217	81.69 361	99.68 110

Anonymous20240521		96.20 304	95.89 305	97.13 322	97.72 348	94.96 334	99.79 24	99.29 270	93.01 345	97.20 334	99.03 318	89.69 327	98.36 343	91.16 350	96.13 282	98.07 339

XVG-ACMP-BASELINE		97.83 231	97.71 222	98.20 275	99.11 263	96.33 303	99.41 177	99.52 91	98.06 130	99.05 215	99.50 227	89.64 328	99.73 192	97.73 211	97.38 256	98.53 309

gg-mvs-nofinetune		96.17 305	95.32 313	98.73 223	98.79 307	98.14 225	99.38 194	94.09 372	91.07 354	98.07 314	91.04 367	89.62 329	99.35 269	96.75 280	99.09 168	98.68 263

DWT-MVSNet_test		97.53 270	97.40 259	97.93 293	99.03 279	94.86 336	99.57 98	98.63 339	96.59 268	98.36 299	98.79 332	89.32 330	99.74 185	98.14 177	98.16 221	99.20 196

GG-mvs-BLEND				98.45 252	98.55 334	98.16 223	99.43 168	93.68 373		97.23 332	98.46 342	89.30 331	99.22 289	95.43 311	98.22 213	97.98 347

USDC		97.34 281	97.20 279	97.75 305	99.07 271	95.20 328	98.51 341	99.04 302	97.99 136	98.31 302	99.86 26	89.02 332	99.55 237	95.67 307	97.36 257	98.49 312

MS-PatchMatch		97.24 285	97.32 271	96.99 324	98.45 338	93.51 353	98.82 316	99.32 258	97.41 199	98.13 310	99.30 286	88.99 333	99.56 235	95.68 306	99.80 87	97.90 352

VPNet		97.84 229	97.44 253	99.01 175	99.21 241	98.94 162	99.48 149	99.57 51	98.38 84	99.28 163	99.73 129	88.89 334	99.39 256	99.19 45	93.27 335	98.71 250

K. test v3		97.10 288	96.79 289	98.01 287	98.72 318	96.33 303	99.87 5	97.05 360	97.59 175	96.16 346	99.80 81	88.71 335	99.04 314	96.69 285	96.55 272	98.65 280

lessismore_v0				97.79 304	98.69 322	95.44 324		94.75 370		95.71 350	99.87 23	88.69 336	99.32 274	95.89 300	94.93 313	98.62 292

TDRefinement		95.42 313	94.57 319	97.97 291	89.83 371	96.11 308	99.48 149	98.75 327	96.74 253	96.68 341	99.88 18	88.65 337	99.71 202	98.37 157	82.74 360	98.09 338

TESTMET0.1,1		97.55 268	97.27 277	98.40 259	98.93 291	96.53 296	98.67 329	97.61 357	96.96 239	98.64 278	99.28 290	88.63 338	99.45 244	97.30 247	99.38 142	99.21 195

test_0402		96.64 295	96.24 297	97.85 298	98.85 303	96.43 300	99.44 162	99.26 273	93.52 340	96.98 339	99.52 220	88.52 339	99.20 296	92.58 347	97.50 245	97.93 350

UnsupCasMVSNet_eth		96.44 299	96.12 299	97.40 316	98.65 325	95.65 315	99.36 201	99.51 104	97.13 222	96.04 348	98.99 322	88.40 340	98.17 345	96.71 283	90.27 348	98.40 325

MDA-MVSNet-bldmvs		94.96 317	93.98 323	97.92 294	98.24 342	97.27 258	99.15 256	99.33 248	93.80 337	80.09 369	99.03 318	88.31 341	97.86 353	93.49 336	94.36 321	98.62 292

test-mter		97.49 277	97.13 282	98.55 240	98.79 307	97.10 265	98.67 329	97.75 354	96.65 260	98.61 282	98.85 329	88.23 342	99.45 244	97.25 250	99.38 142	99.10 200

TinyColmap		97.12 287	96.89 287	97.83 300	99.07 271	95.52 321	98.57 337	98.74 330	97.58 177	97.81 322	99.79 93	88.16 343	99.56 235	95.10 317	97.21 260	98.39 326

pmmvs-eth3d		95.34 315	94.73 317	97.15 320	95.53 364	95.94 311	99.35 207	99.10 294	95.13 318	93.55 356	97.54 352	88.15 344	97.91 351	94.58 323	89.69 351	97.61 354

RRT_test8_iter05		97.72 251	97.60 232	98.08 281	99.23 235	96.08 309	99.63 64	99.49 132	97.54 183	98.94 232	99.81 65	87.99 345	99.35 269	99.21 44	96.51 274	98.81 231

KD-MVS_2432*1600		94.62 319	93.72 325	97.31 317	97.19 357	95.82 313	98.34 347	99.20 283	95.00 323	97.57 325	98.35 345	87.95 346	98.10 346	92.87 343	77.00 365	98.01 343

miper_refine_blended		94.62 319	93.72 325	97.31 317	97.19 357	95.82 313	98.34 347	99.20 283	95.00 323	97.57 325	98.35 345	87.95 346	98.10 346	92.87 343	77.00 365	98.01 343

new-patchmatchnet		94.48 322	94.08 322	95.67 338	95.08 365	92.41 357	99.18 250	99.28 272	94.55 332	93.49 357	97.37 355	87.86 348	97.01 361	91.57 348	88.36 352	97.61 354

test2506		96.81 292	96.65 290	97.29 319	99.74 72	92.21 359	99.60 77	85.06 378	99.13 7	99.77 36	99.93 4	87.82 349	99.85 134	99.38 24	99.38 142	99.80 54

FMVSNet5		96.43 300	96.19 298	97.15 320	99.11 263	95.89 312	99.32 212	99.52 91	94.47 333	98.34 301	99.07 313	87.54 350	97.07 360	92.61 346	95.72 295	98.47 315

pmmvs6		96.53 297	96.09 300	97.82 302	98.69 322	95.47 322	99.37 197	99.47 163	93.46 342	97.41 328	99.78 100	87.06 351	99.33 273	96.92 275	92.70 342	98.65 280

pmmvs3		94.09 325	93.25 328	96.60 333	94.76 366	94.49 339	98.92 306	98.18 349	89.66 355	96.48 343	98.06 350	86.28 352	97.33 358	89.68 355	87.20 354	97.97 348

IB-MVS	95.67 18	96.22 302	95.44 312	98.57 236	99.21 241	96.70 290	98.65 332	97.74 356	96.71 255	97.27 331	98.54 341	86.03 353	99.92 83	98.47 148	86.30 355	99.10 200
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
tmp_tt		82.80 333	81.52 336	86.66 348	66.61 378	68.44 376	92.79 367	97.92 352	68.96 367	80.04 370	99.85 32	85.77 354	96.15 366	97.86 198	43.89 371	95.39 362

CMPMVS	69.68 23	94.13 324	94.90 316	91.84 344	97.24 355	80.01 369	98.52 340	99.48 145	89.01 356	91.99 360	99.67 159	85.67 355	99.13 303	95.44 310	97.03 265	96.39 360
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		95.51 311	95.04 315	96.92 328	97.38 351	95.60 316	99.52 123	99.50 124	93.65 339	96.97 340	99.17 303	85.28 356	96.56 364	88.36 359	95.55 299	98.60 304

LFMVS		97.90 220	97.35 265	99.54 96	99.52 155	99.01 148	99.39 189	98.24 346	97.10 228	99.65 75	99.79 93	84.79 357	99.91 94	99.28 37	98.38 206	99.69 106

FMVSNet1		96.84 291	96.36 295	98.29 269	99.32 216	97.26 260	99.43 168	99.48 145	95.11 320	98.55 286	99.32 283	83.95 358	98.98 323	95.81 302	96.26 280	98.62 292

VDD-MVS		97.73 249	97.35 265	98.88 201	99.47 177	97.12 264	99.34 210	98.85 322	98.19 107	99.67 64	99.85 32	82.98 359	99.92 83	99.49 14	98.32 211	99.60 137

EG-PatchMatch MVS		95.97 308	95.69 308	96.81 330	97.78 347	92.79 356	99.16 252	98.93 311	96.16 300	94.08 355	99.22 298	82.72 360	99.47 241	95.67 307	97.50 245	98.17 336

VDDNet		97.55 268	97.02 285	99.16 161	99.49 169	98.12 227	99.38 194	99.30 265	95.35 317	99.68 58	99.90 10	82.62 361	99.93 72	99.31 34	98.13 222	99.42 179

UniMVSNet_ETH3D		97.32 282	96.81 288	98.87 205	99.40 195	97.46 253	99.51 127	99.53 85	95.86 312	98.54 287	99.77 107	82.44 362	99.66 217	98.68 116	97.52 242	99.50 165

OpenMVS_ROB	92.34 20	94.38 323	93.70 327	96.41 335	97.38 351	93.17 354	99.06 273	98.75 327	86.58 359	94.84 354	98.26 348	81.53 363	99.32 274	89.01 356	97.87 228	96.76 358

test_method		91.10 328	91.36 331	90.31 347	95.85 361	73.72 375	94.89 364	99.25 275	68.39 368	95.82 349	99.02 320	80.50 364	98.95 332	93.64 334	94.89 314	98.25 333

MVS_0304		96.79 293	96.52 293	97.59 310	99.22 239	94.92 335	99.04 280	99.59 43	96.49 272	98.43 294	98.99 322	80.48 365	99.39 256	97.15 260	99.27 153	98.47 315

UnsupCasMVSNet_bld		93.53 326	92.51 329	96.58 334	97.38 351	93.82 346	98.24 352	99.48 145	91.10 353	93.10 358	96.66 358	74.89 366	98.37 342	94.03 331	87.71 353	97.56 356

Gipuma		90.99 329	90.15 332	93.51 340	98.73 316	90.12 363	93.98 365	99.45 185	79.32 364	92.28 359	94.91 361	69.61 367	97.98 350	87.42 361	95.67 296	92.45 364
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PM-MVS		92.96 327	92.23 330	95.14 339	95.61 362	89.98 364	99.37 197	98.21 347	94.80 327	95.04 353	97.69 351	65.06 368	97.90 352	94.30 326	89.98 350	97.54 357

EMVS		80.02 335	79.22 338	82.43 353	91.19 368	76.40 372	97.55 362	92.49 377	66.36 371	83.01 366	91.27 366	64.63 369	85.79 372	65.82 371	60.65 369	85.08 368

E-PMN		80.61 334	79.88 337	82.81 351	90.75 369	76.38 373	97.69 360	95.76 367	66.44 370	83.52 364	92.25 365	62.54 370	87.16 371	68.53 370	61.40 368	84.89 369

ambc				93.06 342	92.68 367	82.36 366	98.47 342	98.73 335		95.09 352	97.41 353	55.55 371	99.10 310	96.42 292	91.32 346	97.71 353

FPMVS		84.93 332	85.65 333	82.75 352	86.77 373	63.39 377	98.35 346	98.92 313	74.11 365	83.39 365	98.98 325	50.85 372	92.40 369	84.54 366	94.97 311	92.46 363

PMMVS2		86.87 330	85.37 334	91.35 346	90.21 370	83.80 365	98.89 309	97.45 359	83.13 363	91.67 361	95.03 360	48.49 373	94.70 367	85.86 365	77.62 364	95.54 361

LCM-MVSNet		86.80 331	85.22 335	91.53 345	87.81 372	80.96 368	98.23 354	98.99 305	71.05 366	90.13 362	96.51 359	48.45 374	96.88 362	90.51 351	85.30 356	96.76 358

ANet_high		77.30 336	74.86 340	84.62 350	75.88 376	77.61 371	97.63 361	93.15 375	88.81 357	64.27 372	89.29 368	36.51 375	83.93 373	75.89 368	52.31 370	92.33 365

test123		39.01 341	42.50 343	28.53 356	39.17 379	20.91 380	98.75 323	19.17 381	19.83 375	38.57 374	66.67 371	33.16 376	15.42 375	37.50 374	29.66 373	49.26 370

testmvs		39.17 340	43.78 342	25.37 357	36.04 380	16.84 381	98.36 345	26.56 379	20.06 374	38.51 375	67.32 370	29.64 377	15.30 376	37.59 373	39.90 372	43.98 371

wuyk23d		40.18 339	41.29 344	36.84 355	86.18 374	49.12 379	79.73 368	22.81 380	27.64 373	25.46 376	28.45 375	21.98 378	48.89 374	55.80 372	23.56 374	12.51 372

PMVS	70.75 22	75.98 338	74.97 339	79.01 354	70.98 377	55.18 378	93.37 366	98.21 347	65.08 372	61.78 373	93.83 363	21.74 379	92.53 368	78.59 367	91.12 347	89.34 367
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	76.82 21	76.91 337	74.31 341	84.70 349	85.38 375	76.05 374	96.88 363	93.17 374	67.39 369	71.28 371	89.01 369	21.66 380	87.69 370	71.74 369	72.29 367	90.35 366
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_blank		0.13 345	0.17 348	0.00 358	0.00 381	0.00 382	0.00 369	0.00 382	0.00 376	0.00 377	1.57 376	0.00 381	0.00 377	0.00 375	0.00 375	0.00 373

uanet_test		0.02 346	0.03 349	0.00 358	0.00 381	0.00 382	0.00 369	0.00 382	0.00 376	0.00 377	0.27 377	0.00 381	0.00 377	0.00 375	0.00 375	0.00 373

sosnet-low-res		0.02 346	0.03 349	0.00 358	0.00 381	0.00 382	0.00 369	0.00 382	0.00 376	0.00 377	0.27 377	0.00 381	0.00 377	0.00 375	0.00 375	0.00 373

sosnet		0.02 346	0.03 349	0.00 358	0.00 381	0.00 382	0.00 369	0.00 382	0.00 376	0.00 377	0.27 377	0.00 381	0.00 377	0.00 375	0.00 375	0.00 373

uncertanet		0.02 346	0.03 349	0.00 358	0.00 381	0.00 382	0.00 369	0.00 382	0.00 376	0.00 377	0.27 377	0.00 381	0.00 377	0.00 375	0.00 375	0.00 373

Regformer		0.02 346	0.03 349	0.00 358	0.00 381	0.00 382	0.00 369	0.00 382	0.00 376	0.00 377	0.27 377	0.00 381	0.00 377	0.00 375	0.00 375	0.00 373

ab-mvs-re		8.30 343	11.06 346	0.00 358	0.00 381	0.00 382	0.00 369	0.00 382	0.00 376	0.00 377	99.58 198	0.00 381	0.00 377	0.00 375	0.00 375	0.00 373

uanet		0.02 346	0.03 349	0.00 358	0.00 381	0.00 382	0.00 369	0.00 382	0.00 376	0.00 377	0.27 377	0.00 381	0.00 377	0.00 375	0.00 375	0.00 373

FOURS1					99.91 1	99.93 1	99.87 5	99.56 57	99.10 11	99.81 24

MSC_two_6792asdad				99.87 12	99.51 157	99.76 41		99.33 248					99.96 19	98.87 81	99.84 65	99.89 2

No_MVS				99.87 12	99.51 157	99.76 41		99.33 248					99.96 19	98.87 81	99.84 65	99.89 2

eth-test2					0.00 381

eth-test					0.00 381

IU-MVS					99.84 33	99.88 8		99.32 258	98.30 95	99.84 14				98.86 86	99.85 58	99.89 2

save fliter					99.76 54	99.59 73	99.14 258	99.40 212	99.00 26

test_0728_SECOND				99.91 2	99.84 33	99.89 4	99.57 98	99.51 104					99.96 19	98.93 71	99.86 51	99.88 7

GSMVS																99.52 156

test_part2					99.81 41	99.83 17				99.77 36

MTGPA								99.47 163

MTMP							99.54 117	98.88 320

gm-plane-assit					98.54 335	92.96 355			94.65 330		99.15 306		99.64 224	97.56 229

test9_res														97.49 235	99.72 109	99.75 76

agg_prior2														97.21 252	99.73 108	99.75 76

agg_prior					99.67 106	99.62 66		99.40 212		98.87 243			99.91 94

test_prior4						99.56 78	98.99 291

test_prior				99.68 68	99.67 106	99.48 93		99.56 57					99.83 151			99.74 81

旧先验2							98.96 299		96.70 256	99.47 117			99.94 57	98.19 170

新几何2							99.01 289

无先验							98.99 291	99.51 104	96.89 245				99.93 72	97.53 232		99.72 94

原ACMM2							98.95 303

testdata2													99.95 46	96.67 286

testdata1							98.85 313		98.32 94

plane_prior7					99.29 222	97.03 275

plane_prior5								99.47 163					99.69 212	97.78 205	97.63 232	98.67 270

plane_prior4											99.61 189

plane_prior3						97.00 277			98.69 62	99.11 200

plane_prior2							99.39 189		98.97 35

plane_prior1					99.26 229

plane_prior						96.97 280	99.21 248		98.45 77						97.60 235

n2								0.00 382

nn								0.00 382

door-mid								98.05 350

test11								99.35 237

door								97.92 352

HQP5-MVS						96.83 285

HQP-NCC					99.19 245		98.98 295		98.24 100	98.66 271

ACMP_Plane					99.19 245		98.98 295		98.24 100	98.66 271

BP-MVS														97.19 256

HQP4-MVS										98.66 271			99.64 224			98.64 282

HQP3-MVS								99.39 216							97.58 237

NP-MVS					99.23 235	96.92 283					99.40 259

ACMMP++_ref															97.19 261

ACMMP++															97.43 253

High-resolution multi-view benchmark