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.

LCM-MVSNet		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 1

LCM-MVSNet-Re		94.20 121	94.58 106	93.04 174	95.91 213	83.13 206	93.79 135	99.19 2	92.00 91	98.84 5	98.04 35	93.64 72	99.02 110	81.28 273	98.54 154	96.96 219

DROMVSNet		95.44 69	95.62 69	94.89 105	96.93 143	87.69 129	96.48 33	99.14 3	93.93 55	92.77 221	94.52 227	93.95 70	99.49 22	93.62 43	99.22 80	97.51 194

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 26	98.81 24	93.86 31	99.07 2	98.98 4	97.01 13	98.92 4	98.78 14	95.22 37	98.61 176	96.85 2	99.77 10	99.31 27
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
CS-MVS-test		93.33 138	93.53 141	92.71 188	95.74 222	83.08 207	94.55 112	98.85 5	91.02 127	89.30 291	91.91 295	91.79 118	99.23 80	90.23 144	98.41 164	95.82 264

FOURS1					99.21 3	94.68 12	98.45 4	98.81 6	97.73 6	98.27 20

TDRefinement		97.68 3	97.60 4	97.93 2	99.02 12	95.95 5	98.61 3	98.81 6	97.41 10	97.28 48	98.46 25	94.62 58	98.84 137	94.64 17	99.53 35	98.99 53

ANet_high		94.83 95	96.28 37	90.47 260	96.65 154	73.16 328	94.33 118	98.74 8	96.39 23	98.09 25	98.93 8	93.37 79	98.70 166	90.38 134	99.68 18	99.53 14

ACMH+	88.43 11	96.48 30	96.82 16	95.47 83	98.54 42	89.06 99	95.65 68	98.61 9	96.10 26	98.16 23	97.52 59	96.90 7	98.62 175	90.30 140	99.60 25	98.72 90

CS-MVS		92.12 180	92.62 162	90.60 257	94.57 266	78.12 278	92.00 195	98.58 10	87.75 196	90.08 274	91.88 297	89.79 166	99.10 97	90.35 136	98.60 149	94.58 296

SF-MVS		95.88 56	95.88 58	95.87 66	98.12 74	89.65 88	95.58 70	98.56 11	91.84 101	96.36 83	96.68 117	94.37 64	99.32 68	92.41 91	99.05 97	98.64 98

HPM-MVS		96.81 12	96.62 23	97.36 24	98.89 19	93.53 38	97.51 9	98.44 12	92.35 82	95.95 107	96.41 132	96.71 8	99.42 29	93.99 33	99.36 56	99.13 39
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
AllTest		94.88 91	94.51 110	96.00 55	98.02 84	92.17 51	95.26 81	98.43 13	90.48 140	95.04 150	96.74 112	92.54 104	97.86 242	85.11 236	98.98 105	97.98 153

TestCases				96.00 55	98.02 84	92.17 51		98.43 13	90.48 140	95.04 150	96.74 112	92.54 104	97.86 242	85.11 236	98.98 105	97.98 153

xxxxxxxxxxxxxcwj		95.03 83	94.93 90	95.33 88	97.46 119	88.05 122	92.04 192	98.42 15	87.63 200	96.36 83	96.68 117	94.37 64	99.32 68	92.41 91	99.05 97	98.64 98

APDe-MVS		96.46 32	96.64 22	95.93 60	97.68 105	89.38 96	96.90 19	98.41 16	92.52 77	97.43 43	97.92 41	95.11 42	99.50 19	94.45 19	99.30 64	98.92 67

9.14			94.81 94		97.49 116		94.11 125	98.37 17	87.56 203	95.38 131	96.03 157	94.66 56	99.08 99	90.70 128	98.97 109

ETH3D-3000-0.1		94.86 92	94.55 107	95.81 67	97.61 109	89.72 86	94.05 127	98.37 17	88.09 188	95.06 149	95.85 163	92.58 102	99.10 97	90.33 139	98.99 104	98.62 102

abl_6		97.31 5	97.12 13	97.86 3	98.54 42	95.32 7	96.61 26	98.35 19	95.81 31	97.55 36	97.44 64	96.51 9	99.40 43	94.06 30	99.23 78	98.85 75

MP-MVS-pluss		96.08 49	95.92 57	96.57 45	99.06 10	91.21 65	93.25 147	98.32 20	87.89 192	96.86 65	97.38 67	95.55 24	99.39 48	95.47 10	99.47 39	99.11 41
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FC-MVSNet-test		95.32 75	95.88 58	93.62 157	98.49 54	81.77 219	95.90 60	98.32 20	93.93 55	97.53 39	97.56 56	88.48 176	99.40 43	92.91 79	99.83 6	99.68 4

COLMAP_ROB	91.06 5	96.75 16	96.62 23	97.13 28	98.38 58	94.31 16	96.79 22	98.32 20	96.69 17	96.86 65	97.56 56	95.48 25	98.77 154	90.11 149	99.44 45	98.31 124
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
DPE-MVS		95.89 54	95.88 58	95.92 62	97.93 91	89.83 85	93.46 143	98.30 23	92.37 80	97.75 29	96.95 95	95.14 39	99.51 18	91.74 107	99.28 72	98.41 119
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PGM-MVS		96.32 41	95.94 55	97.43 19	98.59 36	93.84 32	95.33 78	98.30 23	91.40 118	95.76 115	96.87 102	95.26 35	99.45 23	92.77 80	99.21 81	99.00 51

ACMH	88.36 12	96.59 27	97.43 5	94.07 141	98.56 37	85.33 178	96.33 42	98.30 23	94.66 40	98.72 8	98.30 30	97.51 5	98.00 230	94.87 14	99.59 27	98.86 72
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
nrg030		96.32 41	96.55 26	95.62 77	97.83 94	88.55 112	95.77 64	98.29 26	92.68 73	98.03 26	97.91 42	95.13 40	98.95 122	93.85 36	99.49 38	99.36 24

APD-MVS_3200maxsize		96.82 10	96.65 21	97.32 25	97.95 90	93.82 33	96.31 44	98.25 27	95.51 35	96.99 60	97.05 91	95.63 21	99.39 48	93.31 62	98.88 116	98.75 84

LPG-MVS_test		96.38 40	96.23 39	96.84 40	98.36 61	92.13 53	95.33 78	98.25 27	91.78 105	97.07 53	97.22 82	96.38 13	99.28 73	92.07 97	99.59 27	99.11 41

LGP-MVS_train				96.84 40	98.36 61	92.13 53		98.25 27	91.78 105	97.07 53	97.22 82	96.38 13	99.28 73	92.07 97	99.59 27	99.11 41

Anonymous20231211		96.60 25	97.13 12	95.00 102	97.46 119	86.35 162	97.11 16	98.24 30	97.58 8	98.72 8	98.97 7	93.15 86	99.15 87	93.18 68	99.74 13	99.50 16

canonicalmvs		94.59 103	94.69 100	94.30 135	95.60 232	87.03 142	95.59 69	98.24 30	91.56 115	95.21 143	92.04 294	94.95 50	98.66 172	91.45 116	97.57 234	97.20 212

DVP-MVS++.		95.93 53	96.34 34	94.70 114	96.54 163	86.66 152	98.45 4	98.22 32	93.26 68	97.54 37	97.36 71	93.12 87	99.38 54	93.88 34	98.68 142	98.04 144

test_0728_SECOND				94.88 106	98.55 40	86.72 149	95.20 84	98.22 32					99.38 54	93.44 55	99.31 62	98.53 109

Vis-MVSNet		95.50 67	95.48 72	95.56 81	98.11 75	89.40 95	95.35 76	98.22 32	92.36 81	94.11 175	98.07 33	92.02 112	99.44 24	93.38 60	97.67 230	97.85 169
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UA-Net		97.35 4	97.24 11	97.69 5	98.22 69	93.87 30	98.42 6	98.19 35	96.95 14	95.46 129	99.23 4	93.45 75	99.57 13	95.34 12	99.89 2	99.63 9

test_one_0601					98.26 66	87.14 138		98.18 36	94.25 48	96.99 60	97.36 71	95.13 40

test0726					98.51 46	86.69 150	95.34 77	98.18 36	91.85 98	97.63 32	97.37 68	95.58 22

MSP-MVS		95.34 74	94.63 105	97.48 14	98.67 28	94.05 22	96.41 38	98.18 36	91.26 121	95.12 144	95.15 199	86.60 212	99.50 19	93.43 57	96.81 257	98.89 69
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
ACMMP		96.61 24	96.34 34	97.43 19	98.61 33	93.88 29	96.95 18	98.18 36	92.26 85	96.33 85	96.84 106	95.10 43	99.40 43	93.47 52	99.33 60	99.02 50
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
EIA-MVS		92.35 174	92.03 173	93.30 170	95.81 218	83.97 195	92.80 158	98.17 40	87.71 197	89.79 284	87.56 342	91.17 140	99.18 85	87.97 195	97.27 242	96.77 227

HPM-MVS_fast		97.01 7	96.89 15	97.39 22	99.12 8	93.92 28	97.16 12	98.17 40	93.11 70	96.48 79	97.36 71	96.92 6	99.34 62	94.31 23	99.38 55	98.92 67

XVG-OURS		94.72 99	94.12 122	96.50 48	98.00 86	94.23 17	91.48 218	98.17 40	90.72 134	95.30 135	96.47 127	87.94 187	96.98 285	91.41 117	97.61 233	98.30 125

ZNCC-MVS		96.42 36	96.20 41	97.07 30	98.80 26	92.79 47	96.08 52	98.16 43	91.74 109	95.34 133	96.36 140	95.68 19	99.44 24	94.41 21	99.28 72	98.97 59

FIs		94.90 89	95.35 76	93.55 160	98.28 64	81.76 220	95.33 78	98.14 44	93.05 71	97.07 53	97.18 84	87.65 190	99.29 71	91.72 108	99.69 15	99.61 11

XVG-OURS-SEG-HR		95.38 72	95.00 89	96.51 47	98.10 76	94.07 19	92.46 171	98.13 45	90.69 135	93.75 189	96.25 148	98.03 2	97.02 284	92.08 96	95.55 283	98.45 116

SR-MVS-dyc-post		96.84 8	96.60 25	97.56 10	98.07 78	95.27 8	96.37 39	98.12 46	95.66 33	97.00 58	97.03 92	94.85 52	99.42 29	93.49 48	98.84 121	98.00 149

RE-MVS-def			96.66 20		98.07 78	95.27 8	96.37 39	98.12 46	95.66 33	97.00 58	97.03 92	95.40 27		93.49 48	98.84 121	98.00 149

RPMNet		90.31 221	90.14 220	90.81 252	91.01 327	78.93 266	92.52 166	98.12 46	91.91 95	89.10 292	96.89 101	68.84 314	99.41 36	90.17 147	92.70 331	94.08 305

SED-MVS		96.00 52	96.41 32	94.76 111	98.51 46	86.97 143	95.21 82	98.10 49	91.95 92	97.63 32	97.25 79	96.48 11	99.35 59	93.29 63	99.29 67	97.95 157

test_241102_TWO								98.10 49	91.95 92	97.54 37	97.25 79	95.37 28	99.35 59	93.29 63	99.25 75	98.49 112

test_241102_ONE					98.51 46	86.97 143		98.10 49	91.85 98	97.63 32	97.03 92	96.48 11	98.95 122

test_part1		94.39 110	94.55 107	93.92 148	96.14 195	82.86 210	95.54 72	98.09 52	95.36 36	98.27 20	98.36 28	75.91 295	99.44 24	93.41 58	99.84 3	99.47 17

WR-MVS_H		96.60 25	97.05 14	95.24 94	99.02 12	86.44 158	96.78 23	98.08 53	97.42 9	98.48 16	97.86 45	91.76 120	99.63 6	94.23 26	99.84 3	99.66 6

CP-MVS		96.44 35	96.08 49	97.54 11	98.29 63	94.62 14	96.80 21	98.08 53	92.67 75	95.08 148	96.39 137	94.77 54	99.42 29	93.17 69	99.44 45	98.58 107

ACMP	88.15 13	95.71 61	95.43 75	96.54 46	98.17 72	91.73 61	94.24 120	98.08 53	89.46 159	96.61 76	96.47 127	95.85 17	99.12 93	90.45 131	99.56 33	98.77 83
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SR-MVS		96.70 19	96.42 29	97.54 11	98.05 80	94.69 11	96.13 50	98.07 56	95.17 37	96.82 67	96.73 114	95.09 44	99.43 28	92.99 77	98.71 138	98.50 111

v7n		96.82 10	97.31 10	95.33 88	98.54 42	86.81 147	96.83 20	98.07 56	96.59 20	98.46 17	98.43 27	92.91 94	99.52 17	96.25 6	99.76 11	99.65 8

UniMVSNet (Re)		95.32 75	95.15 85	95.80 69	97.79 95	88.91 102	92.91 155	98.07 56	93.46 65	96.31 87	95.97 160	90.14 158	99.34 62	92.11 94	99.64 23	99.16 36

test1172		96.79 15	96.52 27	97.60 9	98.03 83	94.87 10	96.07 53	98.06 59	95.76 32	96.89 63	96.85 103	94.85 52	99.42 29	93.35 61	98.81 129	98.53 109

SD-MVS		95.19 81	95.73 66	93.55 160	96.62 157	88.88 105	94.67 103	98.05 60	91.26 121	97.25 50	96.40 133	95.42 26	94.36 340	92.72 84	99.19 83	97.40 202
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
casdiffmvs		94.32 115	94.80 95	92.85 184	96.05 202	81.44 225	92.35 179	98.05 60	91.53 116	95.75 116	96.80 107	93.35 80	98.49 190	91.01 123	98.32 179	98.64 98

PEN-MVS		96.69 20	97.39 8	94.61 117	99.16 4	84.50 185	96.54 29	98.05 60	98.06 4	98.64 13	98.25 31	95.01 48	99.65 3	92.95 78	99.83 6	99.68 4

XVG-ACMP-BASELINE		95.68 62	95.34 77	96.69 43	98.40 56	93.04 42	94.54 114	98.05 60	90.45 142	96.31 87	96.76 110	92.91 94	98.72 160	91.19 119	99.42 47	98.32 122

baseline		94.26 118	94.80 95	92.64 191	96.08 200	80.99 231	93.69 138	98.04 64	90.80 133	94.89 156	96.32 142	93.19 84	98.48 194	91.68 110	98.51 158	98.43 117

ACMMP_NAP		96.21 45	96.12 47	96.49 49	98.90 18	91.42 63	94.57 109	98.03 65	90.42 143	96.37 82	97.35 74	95.68 19	99.25 77	94.44 20	99.34 58	98.80 79

ACMM	88.83 9	96.30 43	96.07 50	96.97 35	98.39 57	92.95 45	94.74 101	98.03 65	90.82 132	97.15 51	96.85 103	96.25 15	99.00 114	93.10 72	99.33 60	98.95 61
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETH3D cwj APD-0.16		93.99 126	93.38 144	95.80 69	96.82 148	89.92 82	92.72 159	98.02 67	84.73 248	93.65 193	95.54 185	91.68 122	99.22 81	88.78 180	98.49 161	98.26 128

DeepC-MVS	91.39 4	95.43 70	95.33 78	95.71 75	97.67 106	90.17 79	93.86 134	98.02 67	87.35 204	96.22 95	97.99 38	94.48 62	99.05 104	92.73 83	99.68 18	97.93 159
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
GST-MVS		96.24 44	95.99 54	97.00 34	98.65 29	92.71 48	95.69 67	98.01 69	92.08 90	95.74 117	96.28 145	95.22 37	99.42 29	93.17 69	99.06 94	98.88 71

OurMVSNet-221017-0		96.80 13	96.75 18	96.96 36	99.03 11	91.85 58	97.98 7	98.01 69	94.15 50	98.93 3	99.07 5	88.07 183	99.57 13	95.86 9	99.69 15	99.46 18

SteuartSystems-ACMMP		96.40 38	96.30 36	96.71 42	98.63 30	91.96 56	95.70 65	98.01 69	93.34 67	96.64 74	96.57 124	94.99 49	99.36 58	93.48 51	99.34 58	98.82 77
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		96.39 39	96.17 44	97.04 31	98.51 46	93.37 39	96.30 46	97.98 72	92.35 82	95.63 121	96.47 127	95.37 28	99.27 75	93.78 38	99.14 88	98.48 113

#test#		95.89 54	95.51 71	97.04 31	98.51 46	93.37 39	95.14 87	97.98 72	89.34 162	95.63 121	96.47 127	95.37 28	99.27 75	91.99 99	99.14 88	98.48 113

LS3D		96.11 48	95.83 62	96.95 37	94.75 255	94.20 18	97.34 11	97.98 72	97.31 11	95.32 134	96.77 108	93.08 89	99.20 83	91.79 105	98.16 198	97.44 198

PS-CasMVS		96.69 20	97.43 5	94.49 128	99.13 6	84.09 194	96.61 26	97.97 75	97.91 5	98.64 13	98.13 32	95.24 36	99.65 3	93.39 59	99.84 3	99.72 2

region2R		96.41 37	96.09 48	97.38 23	98.62 31	93.81 35	96.32 43	97.96 76	92.26 85	95.28 137	96.57 124	95.02 47	99.41 36	93.63 42	99.11 92	98.94 62

ACMMPR		96.46 32	96.14 45	97.41 21	98.60 34	93.82 33	96.30 46	97.96 76	92.35 82	95.57 124	96.61 122	94.93 51	99.41 36	93.78 38	99.15 87	99.00 51

XVS		96.49 29	96.18 42	97.44 17	98.56 37	93.99 26	96.50 31	97.95 78	94.58 41	94.38 171	96.49 126	94.56 59	99.39 48	93.57 44	99.05 97	98.93 63

X-MVStestdata		90.70 207	88.45 247	97.44 17	98.56 37	93.99 26	96.50 31	97.95 78	94.58 41	94.38 171	26.89 368	94.56 59	99.39 48	93.57 44	99.05 97	98.93 63

Gipuma		95.31 77	95.80 64	93.81 154	97.99 89	90.91 70	96.42 37	97.95 78	96.69 17	91.78 248	98.85 12	91.77 119	95.49 323	91.72 108	99.08 93	95.02 286
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DTE-MVSNet		96.74 17	97.43 5	94.67 115	99.13 6	84.68 184	96.51 30	97.94 81	98.14 3	98.67 12	98.32 29	95.04 45	99.69 2	93.27 65	99.82 8	99.62 10

PS-MVSNAJss		96.01 51	96.04 52	95.89 65	98.82 23	88.51 114	95.57 71	97.88 82	88.72 175	98.81 6	98.86 10	90.77 144	99.60 8	95.43 11	99.53 35	99.57 13

pmmvs6		96.80 13	97.36 9	95.15 98	99.12 8	87.82 128	96.68 24	97.86 83	96.10 26	98.14 24	99.28 3	97.94 3	98.21 213	91.38 118	99.69 15	99.42 19

TranMVSNet+NR-MVSNet		96.07 50	96.26 38	95.50 82	98.26 66	87.69 129	93.75 136	97.86 83	95.96 30	97.48 41	97.14 86	95.33 32	99.44 24	90.79 126	99.76 11	99.38 22

PHI-MVS		94.34 114	93.80 127	95.95 57	95.65 228	91.67 62	94.82 98	97.86 83	87.86 193	93.04 214	94.16 239	91.58 124	98.78 150	90.27 142	98.96 111	97.41 199

testtj		94.81 96	94.42 111	96.01 54	97.23 127	90.51 77	94.77 100	97.85 86	91.29 120	94.92 155	95.66 176	91.71 121	99.40 43	88.07 193	98.25 188	98.11 140

ETV-MVS		92.99 153	92.74 158	93.72 155	95.86 215	86.30 163	92.33 180	97.84 87	91.70 112	92.81 219	86.17 352	92.22 108	99.19 84	88.03 194	97.73 224	95.66 272

UniMVSNet_NR-MVSNet		95.35 73	95.21 83	95.76 72	97.69 104	88.59 110	92.26 184	97.84 87	94.91 38	96.80 68	95.78 171	90.42 153	99.41 36	91.60 112	99.58 31	99.29 28

3Dnovator+	92.74 2	95.86 57	95.77 65	96.13 52	96.81 150	90.79 73	96.30 46	97.82 89	96.13 25	94.74 162	97.23 81	91.33 130	99.16 86	93.25 66	98.30 182	98.46 115

HQP_MVS		94.26 118	93.93 124	95.23 95	97.71 101	88.12 120	94.56 110	97.81 90	91.74 109	93.31 200	95.59 178	86.93 204	98.95 122	89.26 169	98.51 158	98.60 105

plane_prior5								97.81 90					98.95 122	89.26 169	98.51 158	98.60 105

DU-MVS		95.28 78	95.12 87	95.75 73	97.75 97	88.59 110	92.58 164	97.81 90	93.99 52	96.80 68	95.90 161	90.10 162	99.41 36	91.60 112	99.58 31	99.26 29

APD-MVS		95.00 85	94.69 100	95.93 60	97.38 122	90.88 71	94.59 106	97.81 90	89.22 167	95.46 129	96.17 153	93.42 78	99.34 62	89.30 165	98.87 119	97.56 191
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SMA-MVS		95.77 59	95.54 70	96.47 50	98.27 65	91.19 66	95.09 88	97.79 94	86.48 215	97.42 45	97.51 61	94.47 63	99.29 71	93.55 46	99.29 67	98.93 63
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
MP-MVS		96.14 47	95.68 67	97.51 13	98.81 24	94.06 20	96.10 51	97.78 95	92.73 72	93.48 196	96.72 115	94.23 66	99.42 29	91.99 99	99.29 67	99.05 48
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MSLP-MVS++		93.25 145	93.88 125	91.37 230	96.34 178	82.81 211	93.11 149	97.74 96	89.37 161	94.08 177	95.29 197	90.40 156	96.35 307	90.35 136	98.25 188	94.96 287

mPP-MVS		96.46 32	96.05 51	97.69 5	98.62 31	94.65 13	96.45 34	97.74 96	92.59 76	95.47 127	96.68 117	94.50 61	99.42 29	93.10 72	99.26 74	98.99 53

ETH3 D test6400		91.91 184	91.25 195	93.89 150	96.59 158	84.41 186	92.10 189	97.72 98	78.52 300	91.82 247	93.78 254	88.70 174	99.13 91	83.61 250	98.39 168	98.14 136

TAPA-MVS	88.58 10	92.49 171	91.75 183	94.73 112	96.50 167	89.69 87	92.91 155	97.68 99	78.02 304	92.79 220	94.10 240	90.85 143	97.96 234	84.76 242	98.16 198	96.54 231
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CPTT-MVS		94.74 98	94.12 122	96.60 44	98.15 73	93.01 43	95.84 62	97.66 100	89.21 168	93.28 203	95.46 188	88.89 173	98.98 115	89.80 156	98.82 127	97.80 174

DP-MVS		95.62 63	95.84 61	94.97 103	97.16 132	88.62 109	94.54 114	97.64 101	96.94 15	96.58 77	97.32 77	93.07 90	98.72 160	90.45 131	98.84 121	97.57 189

zzz-MVS		96.47 31	96.14 45	97.47 15	98.95 16	94.05 22	93.69 138	97.62 102	94.46 45	96.29 89	96.94 96	93.56 73	99.37 56	94.29 24	99.42 47	98.99 53

MTGPA								97.62 102

MTAPA		96.65 22	96.38 33	97.47 15	98.95 16	94.05 22	95.88 61	97.62 102	94.46 45	96.29 89	96.94 96	93.56 73	99.37 56	94.29 24	99.42 47	98.99 53

anonymousdsp		96.74 17	96.42 29	97.68 7	98.00 86	94.03 25	96.97 17	97.61 105	87.68 199	98.45 18	98.77 15	94.20 67	99.50 19	96.70 3	99.40 53	99.53 14

mvs_tets		96.83 9	96.71 19	97.17 27	98.83 22	92.51 49	96.58 28	97.61 105	87.57 202	98.80 7	98.90 9	96.50 10	99.59 12	96.15 7	99.47 39	99.40 21

VPA-MVSNet		95.14 82	95.67 68	93.58 159	97.76 96	83.15 205	94.58 108	97.58 107	93.39 66	97.05 56	98.04 35	93.25 82	98.51 189	89.75 159	99.59 27	99.08 45

v10		94.68 101	95.27 82	92.90 182	96.57 160	80.15 238	94.65 105	97.57 108	90.68 136	97.43 43	98.00 37	88.18 180	99.15 87	94.84 15	99.55 34	99.41 20

CSCG		94.69 100	94.75 97	94.52 125	97.55 113	87.87 126	95.01 93	97.57 108	92.68 73	96.20 97	93.44 261	91.92 116	98.78 150	89.11 173	99.24 77	96.92 220

ZD-MVS					97.23 127	90.32 78		97.54 110	84.40 250	94.78 160	95.79 168	92.76 99	99.39 48	88.72 183	98.40 165

UniMVSNet_ETH3D		97.13 6	97.72 3	95.35 86	99.51 2	87.38 133	97.70 8	97.54 110	98.16 2	98.94 2	99.33 2	97.84 4	99.08 99	90.73 127	99.73 14	99.59 12

Effi-MVS+		92.79 160	92.74 158	92.94 180	95.10 245	83.30 202	94.00 129	97.53 112	91.36 119	89.35 290	90.65 318	94.01 69	98.66 172	87.40 205	95.30 291	96.88 223

CP-MVSNet		96.19 46	96.80 17	94.38 134	98.99 14	83.82 197	96.31 44	97.53 112	97.60 7	98.34 19	97.52 59	91.98 115	99.63 6	93.08 74	99.81 9	99.70 3

RPSCF		95.58 65	94.89 92	97.62 8	97.58 111	96.30 4	95.97 57	97.53 112	92.42 78	93.41 197	97.78 46	91.21 136	97.77 251	91.06 120	97.06 247	98.80 79

diffmvs		91.74 186	91.93 177	91.15 240	93.06 294	78.17 277	88.77 289	97.51 115	86.28 219	92.42 231	93.96 247	88.04 184	97.46 267	90.69 129	96.67 262	97.82 172

PVSNet_Blended_VisFu		91.63 189	91.20 196	92.94 180	97.73 100	83.95 196	92.14 188	97.46 116	78.85 299	92.35 235	94.98 209	84.16 230	99.08 99	86.36 222	96.77 259	95.79 266

DeepPCF-MVS	90.46 6	94.20 121	93.56 138	96.14 51	95.96 209	92.96 44	89.48 272	97.46 116	85.14 238	96.23 94	95.42 191	93.19 84	98.08 223	90.37 135	98.76 135	97.38 205

jajsoiax		96.59 27	96.42 29	97.12 29	98.76 27	92.49 50	96.44 36	97.42 118	86.96 211	98.71 10	98.72 17	95.36 31	99.56 16	95.92 8	99.45 43	99.32 26

OMC-MVS		94.22 120	93.69 132	95.81 67	97.25 126	91.27 64	92.27 183	97.40 119	87.10 210	94.56 166	95.42 191	93.74 71	98.11 222	86.62 216	98.85 120	98.06 141

v1240		93.29 140	93.71 131	92.06 213	96.01 207	77.89 282	91.81 211	97.37 120	85.12 240	96.69 72	96.40 133	86.67 210	99.07 103	94.51 18	98.76 135	99.22 32

NR-MVSNet		95.28 78	95.28 81	95.26 93	97.75 97	87.21 137	95.08 89	97.37 120	93.92 57	97.65 31	95.90 161	90.10 162	99.33 67	90.11 149	99.66 21	99.26 29

MVSFormer		92.18 179	92.23 169	92.04 214	94.74 257	80.06 242	97.15 13	97.37 120	88.98 169	88.83 295	92.79 276	77.02 287	99.60 8	96.41 4	96.75 260	96.46 238

test_djsdf		96.62 23	96.49 28	97.01 33	98.55 40	91.77 60	97.15 13	97.37 120	88.98 169	98.26 22	98.86 10	93.35 80	99.60 8	96.41 4	99.45 43	99.66 6

DP-MVS Recon		92.31 175	91.88 178	93.60 158	97.18 131	86.87 146	91.10 227	97.37 120	84.92 245	92.08 243	94.08 241	88.59 175	98.20 214	83.50 251	98.14 200	95.73 268

test_prior3		93.29 140	92.85 154	94.61 117	95.95 210	87.23 135	90.21 250	97.36 125	89.33 163	90.77 261	94.81 216	90.41 154	98.68 170	88.21 187	98.55 151	97.93 159

test_prior				94.61 117	95.95 210	87.23 135		97.36 125					98.68 170			97.93 159

QAPM		92.88 157	92.77 156	93.22 172	95.82 216	83.31 201	96.45 34	97.35 127	83.91 253	93.75 189	96.77 108	89.25 171	98.88 129	84.56 244	97.02 249	97.49 195

GeoE		94.55 105	94.68 102	94.15 138	97.23 127	85.11 180	94.14 124	97.34 128	88.71 176	95.26 138	95.50 186	94.65 57	99.12 93	90.94 124	98.40 165	98.23 129

OPM-MVS		95.61 64	95.45 73	96.08 53	98.49 54	91.00 68	92.65 163	97.33 129	90.05 148	96.77 70	96.85 103	95.04 45	98.56 184	92.77 80	99.06 94	98.70 93
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP3-MVS								97.31 130							97.73 224

HQP-MVS		92.09 181	91.49 189	93.88 151	96.36 174	84.89 182	91.37 219	97.31 130	87.16 207	88.81 297	93.40 262	84.76 226	98.60 178	86.55 218	97.73 224	98.14 136

PCF-MVS	84.52 17	89.12 244	87.71 263	93.34 167	96.06 201	85.84 172	86.58 326	97.31 130	68.46 349	93.61 194	93.89 250	87.51 193	98.52 188	67.85 353	98.11 204	95.66 272
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
114514_t		90.51 211	89.80 225	92.63 193	98.00 86	82.24 215	93.40 145	97.29 133	65.84 356	89.40 289	94.80 219	86.99 202	98.75 155	83.88 249	98.61 147	96.89 222

CLD-MVS		91.82 185	91.41 191	93.04 174	96.37 172	83.65 199	86.82 318	97.29 133	84.65 249	92.27 239	89.67 328	92.20 109	97.85 244	83.95 248	99.47 39	97.62 187
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
3Dnovator	92.54 3	94.80 97	94.90 91	94.47 129	95.47 235	87.06 140	96.63 25	97.28 135	91.82 104	94.34 173	97.41 65	90.60 151	98.65 174	92.47 89	98.11 204	97.70 181

DELS-MVS		92.05 182	92.16 170	91.72 221	94.44 268	80.13 240	87.62 299	97.25 136	87.34 205	92.22 240	93.18 268	89.54 169	98.73 159	89.67 160	98.20 196	96.30 244
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
v1921920		93.26 143	93.61 135	92.19 206	96.04 206	78.31 275	91.88 204	97.24 137	85.17 237	96.19 99	96.19 150	86.76 209	99.05 104	94.18 28	98.84 121	99.22 32

test_0402		95.73 60	96.22 40	94.26 136	98.19 71	85.77 173	93.24 148	97.24 137	96.88 16	97.69 30	97.77 48	94.12 68	99.13 91	91.54 115	99.29 67	97.88 165

v1192		93.49 134	93.78 128	92.62 194	96.16 193	79.62 254	91.83 210	97.22 139	86.07 223	96.10 103	96.38 138	87.22 197	99.02 110	94.14 29	98.88 116	99.22 32

F-COLMAP		92.28 176	91.06 200	95.95 57	97.52 114	91.90 57	93.53 141	97.18 140	83.98 252	88.70 303	94.04 242	88.41 178	98.55 186	80.17 284	95.99 274	97.39 203

v8		94.65 102	95.29 80	92.74 187	96.65 154	79.77 252	94.59 106	97.17 141	91.86 97	97.47 42	97.93 40	88.16 181	99.08 99	94.32 22	99.47 39	99.38 22

v144192		93.20 148	93.54 139	92.16 210	96.05 202	78.26 276	91.95 197	97.14 142	84.98 244	95.96 106	96.11 154	87.08 201	99.04 107	93.79 37	98.84 121	99.17 35

DeepC-MVS_fast	89.96 7	93.73 130	93.44 142	94.60 121	96.14 195	87.90 125	93.36 146	97.14 142	85.53 232	93.90 186	95.45 189	91.30 132	98.59 180	89.51 162	98.62 146	97.31 208
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MCST-MVS		92.91 155	92.51 165	94.10 140	97.52 114	85.72 174	91.36 222	97.13 144	80.33 281	92.91 218	94.24 235	91.23 135	98.72 160	89.99 153	97.93 217	97.86 167

KD-MVS_self_test		94.10 123	94.73 99	92.19 206	97.66 107	79.49 257	94.86 97	97.12 145	89.59 158	96.87 64	97.65 52	90.40 156	98.34 203	89.08 174	99.35 57	98.75 84

pm-mvs1		95.43 70	95.94 55	93.93 147	98.38 58	85.08 181	95.46 75	97.12 145	91.84 101	97.28 48	98.46 25	95.30 34	97.71 256	90.17 147	99.42 47	98.99 53

save fliter					97.46 119	88.05 122	92.04 192	97.08 147	87.63 200

CDPH-MVS		92.67 165	91.83 179	95.18 97	96.94 141	88.46 115	90.70 236	97.07 148	77.38 306	92.34 237	95.08 204	92.67 101	98.88 129	85.74 227	98.57 150	98.20 133

OpenMVS	89.45 8	92.27 177	92.13 172	92.68 190	94.53 267	84.10 193	95.70 65	97.03 149	82.44 269	91.14 258	96.42 131	88.47 177	98.38 199	85.95 226	97.47 237	95.55 276

原ACMM1				92.87 183	96.91 144	84.22 190		97.01 150	76.84 311	89.64 287	94.46 228	88.00 185	98.70 166	81.53 271	98.01 213	95.70 270

DVP-MVS		95.82 58	96.18 42	94.72 113	98.51 46	86.69 150	95.20 84	97.00 151	91.85 98	97.40 46	97.35 74	95.58 22	99.34 62	93.44 55	99.31 62	98.13 138
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
CANet		92.38 173	91.99 175	93.52 164	93.82 284	83.46 200	91.14 225	97.00 151	89.81 153	86.47 324	94.04 242	87.90 188	99.21 82	89.50 163	98.27 184	97.90 163

HPM-MVS++		95.02 84	94.39 112	96.91 38	97.88 92	93.58 37	94.09 126	96.99 153	91.05 126	92.40 232	95.22 198	91.03 142	99.25 77	92.11 94	98.69 141	97.90 163

v1144		93.50 133	93.81 126	92.57 196	96.28 183	79.61 255	91.86 209	96.96 154	86.95 212	95.91 110	96.32 142	87.65 190	98.96 120	93.51 47	98.88 116	99.13 39

MVS_Test		92.57 170	93.29 145	90.40 263	93.53 286	75.85 308	92.52 166	96.96 154	88.73 174	92.35 235	96.70 116	90.77 144	98.37 202	92.53 88	95.49 285	96.99 218

PVSNet_BlendedMVS		90.35 218	89.96 222	91.54 227	94.81 252	78.80 271	90.14 254	96.93 156	79.43 289	88.68 304	95.06 205	86.27 215	98.15 220	80.27 281	98.04 210	97.68 183

PVSNet_Blended		88.74 254	88.16 258	90.46 262	94.81 252	78.80 271	86.64 322	96.93 156	74.67 319	88.68 304	89.18 334	86.27 215	98.15 220	80.27 281	96.00 273	94.44 300

TEST9					96.45 170	89.46 91	90.60 238	96.92 158	79.09 295	90.49 266	94.39 231	91.31 131	98.88 129

train_agg		92.71 164	91.83 179	95.35 86	96.45 170	89.46 91	90.60 238	96.92 158	79.37 290	90.49 266	94.39 231	91.20 137	98.88 129	88.66 184	98.43 163	97.72 180

NCCC		94.08 124	93.54 139	95.70 76	96.49 168	89.90 84	92.39 176	96.91 160	90.64 137	92.33 238	94.60 224	90.58 152	98.96 120	90.21 146	97.70 228	98.23 129

test_8					96.37 172	89.14 98	90.51 241	96.89 161	79.37 290	90.42 268	94.36 233	91.20 137	98.82 139

agg_prior1		92.60 167	91.76 182	95.10 100	96.20 189	88.89 103	90.37 245	96.88 162	79.67 287	90.21 271	94.41 229	91.30 132	98.78 150	88.46 186	98.37 175	97.64 186

agg_prior					96.20 189	88.89 103		96.88 162		90.21 271			98.78 150

MSC_two_6792asdad				95.90 63	96.54 163	89.57 89		96.87 164					99.41 36	94.06 30	99.30 64	98.72 90

No_MVS				95.90 63	96.54 163	89.57 89		96.87 164					99.41 36	94.06 30	99.30 64	98.72 90

MIMVSNet1		95.52 66	95.45 73	95.72 74	99.14 5	89.02 100	96.23 49	96.87 164	93.73 59	97.87 27	98.49 24	90.73 148	99.05 104	86.43 221	99.60 25	99.10 44

IU-MVS					98.51 46	86.66 152		96.83 167	72.74 331	95.83 113				93.00 76	99.29 67	98.64 98

TSAR-MVS + MP.		94.96 87	94.75 97	95.57 80	98.86 21	88.69 106	96.37 39	96.81 168	85.23 235	94.75 161	97.12 87	91.85 117	99.40 43	93.45 53	98.33 177	98.62 102
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		94.58 104	94.29 116	95.46 84	96.94 141	89.35 97	91.81 211	96.80 169	89.66 155	93.90 186	95.44 190	92.80 98	98.72 160	92.74 82	98.52 156	98.32 122

cascas		87.02 288	86.28 289	89.25 286	91.56 322	76.45 302	84.33 341	96.78 170	71.01 339	86.89 323	85.91 353	81.35 255	96.94 286	83.09 255	95.60 282	94.35 302

IterMVS-LS		93.78 129	94.28 117	92.27 203	96.27 184	79.21 264	91.87 205	96.78 170	91.77 107	96.57 78	97.07 89	87.15 199	98.74 158	91.99 99	99.03 103	98.86 72
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous20240529		95.50 67	95.83 62	94.50 126	97.33 125	85.93 170	95.19 86	96.77 172	96.64 19	97.61 35	98.05 34	93.23 83	98.79 146	88.60 185	99.04 102	98.78 81

TransMVSNet (Re)		95.27 80	96.04 52	92.97 177	98.37 60	81.92 218	95.07 90	96.76 173	93.97 54	97.77 28	98.57 19	95.72 18	97.90 236	88.89 178	99.23 78	99.08 45

EG-PatchMatch MVS		94.54 107	94.67 103	94.14 139	97.87 93	86.50 154	92.00 195	96.74 174	88.16 187	96.93 62	97.61 54	93.04 91	97.90 236	91.60 112	98.12 203	98.03 147

1112_ss		88.42 258	87.41 267	91.45 228	96.69 153	80.99 231	89.72 267	96.72 175	73.37 327	87.00 322	90.69 316	77.38 283	98.20 214	81.38 272	93.72 318	95.15 282

Baseline_NR-MVSNet		94.47 109	95.09 88	92.60 195	98.50 53	80.82 234	92.08 190	96.68 176	93.82 58	96.29 89	98.56 20	90.10 162	97.75 254	90.10 151	99.66 21	99.24 31

eth_miper_zixun_eth		90.72 206	90.61 210	91.05 241	92.04 313	76.84 298	86.91 314	96.67 177	85.21 236	94.41 169	93.92 248	79.53 267	98.26 210	89.76 158	97.02 249	98.06 141

Fast-Effi-MVS+-dtu		92.77 162	92.16 170	94.58 124	94.66 263	88.25 117	92.05 191	96.65 178	89.62 156	90.08 274	91.23 306	92.56 103	98.60 178	86.30 223	96.27 269	96.90 221

test11								96.65 178

RRT_test8_iter05		88.21 261	88.17 256	88.33 301	91.62 320	66.82 356	91.73 214	96.60 180	86.34 218	94.14 174	95.38 196	47.72 369	99.11 95	91.78 106	98.26 185	99.06 47

LF4IMVS		92.72 163	92.02 174	94.84 108	95.65 228	91.99 55	92.92 154	96.60 180	85.08 242	92.44 230	93.62 256	86.80 208	96.35 307	86.81 211	98.25 188	96.18 249

GBi-Net		93.21 146	92.96 151	93.97 144	95.40 237	84.29 187	95.99 54	96.56 182	88.63 177	95.10 145	98.53 21	81.31 256	98.98 115	86.74 212	98.38 170	98.65 94

test1		93.21 146	92.96 151	93.97 144	95.40 237	84.29 187	95.99 54	96.56 182	88.63 177	95.10 145	98.53 21	81.31 256	98.98 115	86.74 212	98.38 170	98.65 94

FMVSNet1		94.84 94	95.13 86	93.97 144	97.60 110	84.29 187	95.99 54	96.56 182	92.38 79	97.03 57	98.53 21	90.12 159	98.98 115	88.78 180	99.16 86	98.65 94

ITE_SJBPF				95.95 57	97.34 124	93.36 41		96.55 185	91.93 94	94.82 158	95.39 194	91.99 114	97.08 282	85.53 229	97.96 215	97.41 199

Fast-Effi-MVS+		91.28 199	90.86 203	92.53 198	95.45 236	82.53 213	89.25 281	96.52 186	85.00 243	89.91 279	88.55 338	92.94 92	98.84 137	84.72 243	95.44 287	96.22 247

V42		93.43 136	93.58 136	92.97 177	95.34 241	81.22 228	92.67 162	96.49 187	87.25 206	96.20 97	96.37 139	87.32 196	98.85 136	92.39 93	98.21 194	98.85 75

PLC	85.34 15	90.40 215	88.92 239	94.85 107	96.53 166	90.02 80	91.58 216	96.48 188	80.16 282	86.14 326	92.18 290	85.73 220	98.25 211	76.87 313	94.61 306	96.30 244
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
c3_l		91.32 198	91.42 190	91.00 245	92.29 306	76.79 299	87.52 305	96.42 189	85.76 229	94.72 164	93.89 250	82.73 241	98.16 219	90.93 125	98.55 151	98.04 144

Regformer-2		94.86 92	94.55 107	95.77 71	92.83 299	89.98 81	91.87 205	96.40 190	94.38 47	96.19 99	95.04 206	92.47 107	99.04 107	93.49 48	98.31 180	98.28 126

USDC		89.02 245	89.08 235	88.84 291	95.07 246	74.50 319	88.97 284	96.39 191	73.21 328	93.27 204	96.28 145	82.16 248	96.39 304	77.55 307	98.80 131	95.62 275

ambc				92.98 176	96.88 145	83.01 209	95.92 59	96.38 192		96.41 80	97.48 62	88.26 179	97.80 247	89.96 154	98.93 113	98.12 139

PAPM_NR		91.03 201	90.81 205	91.68 223	96.73 152	81.10 230	93.72 137	96.35 193	88.19 186	88.77 301	92.12 293	85.09 225	97.25 277	82.40 263	93.90 315	96.68 230

v2v482		93.29 140	93.63 134	92.29 202	96.35 177	78.82 269	91.77 213	96.28 194	88.45 181	95.70 120	96.26 147	86.02 218	98.90 126	93.02 75	98.81 129	99.14 38

AdaColmap		91.63 189	91.36 192	92.47 201	95.56 233	86.36 161	92.24 186	96.27 195	88.88 173	89.90 280	92.69 279	91.65 123	98.32 204	77.38 310	97.64 231	92.72 334

Test_1112_low_res		87.50 276	86.58 282	90.25 267	96.80 151	77.75 284	87.53 304	96.25 196	69.73 345	86.47 324	93.61 257	75.67 296	97.88 238	79.95 286	93.20 323	95.11 284

test12				94.43 132	95.95 210	86.75 148		96.24 197		89.76 285		89.79 166	98.79 146		97.95 216	97.75 179

PAPR		87.65 272	86.77 280	90.27 266	92.85 298	77.38 289	88.56 294	96.23 198	76.82 312	84.98 332	89.75 327	86.08 217	97.16 280	72.33 337	93.35 321	96.26 246

MVS_111021_HR		93.63 132	93.42 143	94.26 136	96.65 154	86.96 145	89.30 278	96.23 198	88.36 184	93.57 195	94.60 224	93.45 75	97.77 251	90.23 144	98.38 170	98.03 147

XXY-MVS		92.58 168	93.16 150	90.84 251	97.75 97	79.84 248	91.87 205	96.22 200	85.94 225	95.53 126	97.68 50	92.69 100	94.48 336	83.21 254	97.51 235	98.21 132

MSDG		90.82 203	90.67 209	91.26 234	94.16 273	83.08 207	86.63 323	96.19 201	90.60 139	91.94 245	91.89 296	89.16 172	95.75 318	80.96 279	94.51 307	94.95 288

miper_ehance_all_eth		90.48 212	90.42 214	90.69 254	91.62 320	76.57 301	86.83 317	96.18 202	83.38 255	94.06 179	92.66 281	82.20 247	98.04 225	89.79 157	97.02 249	97.45 197

TinyColmap		92.00 183	92.76 157	89.71 277	95.62 231	77.02 293	90.72 235	96.17 203	87.70 198	95.26 138	96.29 144	92.54 104	96.45 302	81.77 268	98.77 134	95.66 272

DPM-MVS		89.35 240	88.40 248	92.18 209	96.13 198	84.20 191	86.96 313	96.15 204	75.40 317	87.36 319	91.55 304	83.30 234	98.01 229	82.17 266	96.62 263	94.32 303

HyFIR lowres test		87.19 284	85.51 294	92.24 204	97.12 136	80.51 235	85.03 333	96.06 205	66.11 355	91.66 249	92.98 272	70.12 312	99.14 89	75.29 322	95.23 293	97.07 213

xiu_mvs_v1_base_debu		91.47 193	91.52 186	91.33 231	95.69 225	81.56 222	89.92 261	96.05 206	83.22 257	91.26 254	90.74 313	91.55 125	98.82 139	89.29 166	95.91 275	93.62 320

xiu_mvs_v1_base		91.47 193	91.52 186	91.33 231	95.69 225	81.56 222	89.92 261	96.05 206	83.22 257	91.26 254	90.74 313	91.55 125	98.82 139	89.29 166	95.91 275	93.62 320

xiu_mvs_v1_base_debi		91.47 193	91.52 186	91.33 231	95.69 225	81.56 222	89.92 261	96.05 206	83.22 257	91.26 254	90.74 313	91.55 125	98.82 139	89.29 166	95.91 275	93.62 320

Regformer-4		94.90 89	94.67 103	95.59 78	92.78 301	89.02 100	92.39 176	95.91 209	94.50 43	96.41 80	95.56 183	92.10 111	99.01 112	94.23 26	98.14 200	98.74 87

UnsupCasMVSNet_eth		90.33 219	90.34 215	90.28 265	94.64 264	80.24 236	89.69 268	95.88 210	85.77 228	93.94 185	95.69 174	81.99 250	92.98 351	84.21 247	91.30 342	97.62 187

CANet_DTU		89.85 234	89.17 233	91.87 216	92.20 309	80.02 245	90.79 233	95.87 211	86.02 224	82.53 348	91.77 299	80.01 264	98.57 183	85.66 228	97.70 228	97.01 217

PMVS	87.21 14	94.97 86	95.33 78	93.91 149	98.97 15	97.16 2	95.54 72	95.85 212	96.47 21	93.40 199	97.46 63	95.31 33	95.47 324	86.18 225	98.78 133	89.11 351
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Regformer-1		94.55 105	94.33 115	95.19 96	92.83 299	88.54 113	91.87 205	95.84 213	93.99 52	95.95 107	95.04 206	92.00 113	98.79 146	93.14 71	98.31 180	98.23 129

alignmvs		93.26 143	92.85 154	94.50 126	95.70 224	87.45 131	93.45 144	95.76 214	91.58 114	95.25 140	92.42 288	81.96 251	98.72 160	91.61 111	97.87 220	97.33 207

无先验							89.94 260	95.75 215	70.81 341				98.59 180	81.17 276		94.81 289

WR-MVS		93.49 134	93.72 130	92.80 186	97.57 112	80.03 244	90.14 254	95.68 216	93.70 60	96.62 75	95.39 194	87.21 198	99.04 107	87.50 202	99.64 23	99.33 25

VPNet		93.08 149	93.76 129	91.03 242	98.60 34	75.83 310	91.51 217	95.62 217	91.84 101	95.74 117	97.10 88	89.31 170	98.32 204	85.07 238	99.06 94	98.93 63

Anonymous20240521		92.86 159	93.57 137	90.74 253	96.57 160	75.50 312	94.15 123	95.60 218	89.38 160	95.90 111	97.90 44	80.39 263	97.96 234	92.60 87	99.68 18	98.75 84

xiu_mvs_v2_base		89.00 247	89.19 232	88.46 299	94.86 250	74.63 316	86.97 312	95.60 218	80.88 277	87.83 314	88.62 337	91.04 141	98.81 144	82.51 262	94.38 308	91.93 340

PS-MVSNAJ		88.86 251	88.99 238	88.48 298	94.88 248	74.71 314	86.69 321	95.60 218	80.88 277	87.83 314	87.37 345	90.77 144	98.82 139	82.52 261	94.37 309	91.93 340

CHOSEN 1792x2688		87.19 284	85.92 292	91.00 245	97.13 135	79.41 258	84.51 339	95.60 218	64.14 359	90.07 276	94.81 216	78.26 277	97.14 281	73.34 331	95.38 290	96.46 238

miper_enhance_ethall		88.42 258	87.87 261	90.07 272	88.67 353	75.52 311	85.10 332	95.59 222	75.68 313	92.49 228	89.45 331	78.96 269	97.88 238	87.86 198	97.02 249	96.81 225

MVP-Stereo		90.07 228	88.92 239	93.54 162	96.31 181	86.49 155	90.93 230	95.59 222	79.80 283	91.48 250	95.59 178	80.79 260	97.39 273	78.57 301	91.19 343	96.76 228
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
cdsmvs_eth3d_5k		23.35 337	31.13 340	0.00 355	0.00 378	0.00 379	0.00 366	95.58 224	0.00 373	0.00 374	91.15 307	93.43 77	0.00 374	0.00 372	0.00 372	0.00 370

CNLPA		91.72 187	91.20 196	93.26 171	96.17 192	91.02 67	91.14 225	95.55 225	90.16 147	90.87 260	93.56 259	86.31 214	94.40 339	79.92 290	97.12 246	94.37 301

FMVSNet2		92.78 161	92.73 160	92.95 179	95.40 237	81.98 217	94.18 122	95.53 226	88.63 177	96.05 104	97.37 68	81.31 256	98.81 144	87.38 206	98.67 144	98.06 141

ab-mvs		92.40 172	92.62 162	91.74 220	97.02 137	81.65 221	95.84 62	95.50 227	86.95 212	92.95 217	97.56 56	90.70 149	97.50 264	79.63 291	97.43 238	96.06 253

MVS_111021_LR		93.66 131	93.28 147	94.80 109	96.25 187	90.95 69	90.21 250	95.43 228	87.91 190	93.74 191	94.40 230	92.88 96	96.38 305	90.39 133	98.28 183	97.07 213

tfpnnormal		94.27 117	94.87 93	92.48 200	97.71 101	80.88 233	94.55 112	95.41 229	93.70 60	96.67 73	97.72 49	91.40 128	98.18 217	87.45 203	99.18 85	98.36 120

Effi-MVS+-dtu		93.90 128	92.60 164	97.77 4	94.74 257	96.67 3	94.00 129	95.41 229	89.94 149	91.93 246	92.13 292	90.12 159	98.97 119	87.68 200	97.48 236	97.67 184

mvs-test1		93.07 151	91.80 181	96.89 39	94.74 257	95.83 6	92.17 187	95.41 229	89.94 149	89.85 281	90.59 319	90.12 159	98.88 129	87.68 200	95.66 281	95.97 256

cl____		90.65 209	90.56 211	90.91 249	91.85 315	76.98 296	86.75 319	95.36 232	85.53 232	94.06 179	94.89 213	77.36 285	97.98 233	90.27 142	98.98 105	97.76 177

DIV-MVS_self_test		90.65 209	90.56 211	90.91 249	91.85 315	76.99 295	86.75 319	95.36 232	85.52 234	94.06 179	94.89 213	77.37 284	97.99 232	90.28 141	98.97 109	97.76 177

testgi		90.38 216	91.34 193	87.50 310	97.49 116	71.54 337	89.43 273	95.16 234	88.38 183	94.54 167	94.68 223	92.88 96	93.09 350	71.60 342	97.85 221	97.88 165

v148		92.87 158	93.29 145	91.62 224	96.25 187	77.72 285	91.28 223	95.05 235	89.69 154	95.93 109	96.04 156	87.34 195	98.38 199	90.05 152	97.99 214	98.78 81

miper_lstm_enhance		89.90 233	89.80 225	90.19 271	91.37 324	77.50 287	83.82 346	95.00 236	84.84 246	93.05 213	94.96 210	76.53 294	95.20 332	89.96 154	98.67 144	97.86 167

VNet		92.67 165	92.96 151	91.79 218	96.27 184	80.15 238	91.95 197	94.98 237	92.19 88	94.52 168	96.07 155	87.43 194	97.39 273	84.83 240	98.38 170	97.83 170

FMVSNet3		90.78 205	90.32 216	92.16 210	93.03 296	79.92 247	92.54 165	94.95 238	86.17 222	95.10 145	96.01 158	69.97 313	98.75 155	86.74 212	98.38 170	97.82 172

BH-untuned		90.68 208	90.90 201	90.05 274	95.98 208	79.57 256	90.04 257	94.94 239	87.91 190	94.07 178	93.00 270	87.76 189	97.78 250	79.19 297	95.17 294	92.80 332

RRT_MVS		91.36 196	90.05 221	95.29 92	89.21 348	88.15 119	92.51 170	94.89 240	86.73 214	95.54 125	95.68 175	61.82 348	99.30 70	94.91 13	99.13 91	98.43 117

D2MVS		89.93 232	89.60 230	90.92 247	94.03 278	78.40 274	88.69 291	94.85 241	78.96 297	93.08 211	95.09 203	74.57 298	96.94 286	88.19 189	98.96 111	97.41 199

SixPastTwentyTwo		94.91 88	95.21 83	93.98 143	98.52 45	83.19 204	95.93 58	94.84 242	94.86 39	98.49 15	98.74 16	81.45 254	99.60 8	94.69 16	99.39 54	99.15 37

旧先验1					96.20 189	84.17 192		94.82 243			95.57 182	89.57 168			97.89 219	96.32 243

API-MVS		91.52 192	91.61 184	91.26 234	94.16 273	86.26 165	94.66 104	94.82 243	91.17 124	92.13 242	91.08 309	90.03 165	97.06 283	79.09 298	97.35 241	90.45 349

FMVSNet5		87.82 268	86.56 283	91.62 224	92.31 305	79.81 251	93.49 142	94.81 245	83.26 256	91.36 252	96.93 98	52.77 365	97.49 266	76.07 318	98.03 211	97.55 192

MAR-MVS		90.32 220	88.87 242	94.66 116	94.82 251	91.85 58	94.22 121	94.75 246	80.91 276	87.52 318	88.07 341	86.63 211	97.87 241	76.67 314	96.21 270	94.25 304
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
mvs_anonymous		90.37 217	91.30 194	87.58 309	92.17 310	68.00 350	89.84 265	94.73 247	83.82 254	93.22 208	97.40 66	87.54 192	97.40 272	87.94 196	95.05 296	97.34 206

Regformer-3		94.28 116	94.23 121	94.46 130	92.78 301	86.28 164	92.39 176	94.70 248	93.69 63	95.97 105	95.56 183	91.34 129	98.48 194	93.45 53	98.14 200	98.62 102

EI-MVSNet-UG-set		94.35 113	94.27 119	94.59 122	92.46 304	85.87 171	92.42 174	94.69 249	93.67 64	96.13 101	95.84 166	91.20 137	98.86 134	93.78 38	98.23 191	99.03 49

EI-MVSNet-Vis-set		94.36 112	94.28 117	94.61 117	92.55 303	85.98 169	92.44 172	94.69 249	93.70 60	96.12 102	95.81 167	91.24 134	98.86 134	93.76 41	98.22 193	98.98 58

EI-MVSNet		92.99 153	93.26 149	92.19 206	92.12 311	79.21 264	92.32 181	94.67 251	91.77 107	95.24 141	95.85 163	87.14 200	98.49 190	91.99 99	98.26 185	98.86 72

MVSTER		89.32 241	88.75 243	91.03 242	90.10 338	76.62 300	90.85 231	94.67 251	82.27 270	95.24 141	95.79 168	61.09 351	98.49 190	90.49 130	98.26 185	97.97 156

新几何1				93.17 173	97.16 132	87.29 134		94.43 253	67.95 350	91.29 253	94.94 211	86.97 203	98.23 212	81.06 278	97.75 223	93.98 311

1121		90.26 222	89.23 231	93.34 167	97.15 134	87.40 132	91.94 199	94.39 254	67.88 351	91.02 259	94.91 212	86.91 206	98.59 180	81.17 276	97.71 227	94.02 310

CMPMVS	68.83 22	87.28 280	85.67 293	92.09 212	88.77 352	85.42 177	90.31 248	94.38 255	70.02 344	88.00 312	93.30 264	73.78 302	94.03 344	75.96 320	96.54 264	96.83 224
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
IS-MVSNet		94.49 108	94.35 114	94.92 104	98.25 68	86.46 157	97.13 15	94.31 256	96.24 24	96.28 92	96.36 140	82.88 238	99.35 59	88.19 189	99.52 37	98.96 60

testdata				91.03 242	96.87 146	82.01 216		94.28 257	71.55 335	92.46 229	95.42 191	85.65 222	97.38 275	82.64 259	97.27 242	93.70 318

UGNet		93.08 149	92.50 166	94.79 110	93.87 282	87.99 124	95.07 90	94.26 258	90.64 137	87.33 320	97.67 51	86.89 207	98.49 190	88.10 192	98.71 138	97.91 162
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
MVS		84.98 299	84.30 299	87.01 313	91.03 326	77.69 286	91.94 199	94.16 259	59.36 364	84.23 338	87.50 344	85.66 221	96.80 292	71.79 339	93.05 328	86.54 356

1314		86.46 291	86.33 288	86.87 315	91.65 319	74.54 317	91.94 199	94.10 260	74.28 321	84.78 334	87.33 346	83.03 237	95.00 333	78.72 299	91.16 344	91.06 346

cl22		89.02 245	88.50 246	90.59 258	89.76 340	76.45 302	86.62 324	94.03 261	82.98 263	92.65 224	92.49 282	72.05 308	97.53 262	88.93 175	97.02 249	97.78 175

EPP-MVSNet		93.91 127	93.68 133	94.59 122	98.08 77	85.55 176	97.44 10	94.03 261	94.22 49	94.94 153	96.19 150	82.07 249	99.57 13	87.28 207	98.89 114	98.65 94

UnsupCasMVSNet_bld		88.50 257	88.03 259	89.90 275	95.52 234	78.88 268	87.39 306	94.02 263	79.32 293	93.06 212	94.02 244	80.72 261	94.27 341	75.16 323	93.08 327	96.54 231

h-mvs33		92.89 156	91.99 175	95.58 79	96.97 139	90.55 75	93.94 132	94.01 264	89.23 165	93.95 183	96.19 150	76.88 290	99.14 89	91.02 121	95.71 280	97.04 216

pmmvs-eth3d		91.54 191	90.73 208	93.99 142	95.76 221	87.86 127	90.83 232	93.98 265	78.23 303	94.02 182	96.22 149	82.62 244	96.83 291	86.57 217	98.33 177	97.29 209

BH-RMVSNet		90.47 213	90.44 213	90.56 259	95.21 244	78.65 273	89.15 282	93.94 266	88.21 185	92.74 222	94.22 236	86.38 213	97.88 238	78.67 300	95.39 289	95.14 283

test222					96.95 140	85.27 179	88.83 287	93.61 267	65.09 358	90.74 263	94.85 215	84.62 228			97.36 240	93.91 312

CDS-MVSNet		89.55 237	88.22 255	93.53 163	95.37 240	86.49 155	89.26 279	93.59 268	79.76 285	91.15 257	92.31 289	77.12 286	98.38 199	77.51 308	97.92 218	95.71 269
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
new-patchmatchnet		88.97 248	90.79 206	83.50 337	94.28 272	55.83 371	85.34 331	93.56 269	86.18 221	95.47 127	95.73 173	83.10 236	96.51 300	85.40 230	98.06 208	98.16 134

IterMVS-SCA-FT		91.65 188	91.55 185	91.94 215	93.89 281	79.22 263	87.56 302	93.51 270	91.53 116	95.37 132	96.62 121	78.65 272	98.90 126	91.89 104	94.95 297	97.70 181

Anonymous20231206		88.77 253	88.29 251	90.20 270	96.31 181	78.81 270	89.56 271	93.49 271	74.26 322	92.38 233	95.58 181	82.21 246	95.43 326	72.07 338	98.75 137	96.34 242

OpenMVS_ROB	85.12 16	89.52 239	89.05 236	90.92 247	94.58 265	81.21 229	91.10 227	93.41 272	77.03 310	93.41 197	93.99 246	83.23 235	97.80 247	79.93 288	94.80 301	93.74 317

VDD-MVS		94.37 111	94.37 113	94.40 133	97.49 116	86.07 168	93.97 131	93.28 273	94.49 44	96.24 93	97.78 46	87.99 186	98.79 146	88.92 176	99.14 88	98.34 121

jason		89.17 243	88.32 249	91.70 222	95.73 223	80.07 241	88.10 296	93.22 274	71.98 334	90.09 273	92.79 276	78.53 275	98.56 184	87.43 204	97.06 247	96.46 238
jason: jason.
PAPM		81.91 318	80.11 328	87.31 312	93.87 282	72.32 335	84.02 344	93.22 274	69.47 346	76.13 365	89.84 322	72.15 307	97.23 278	53.27 366	89.02 349	92.37 337

BH-w/o		87.21 282	87.02 276	87.79 308	94.77 254	77.27 291	87.90 297	93.21 276	81.74 274	89.99 278	88.39 340	83.47 232	96.93 288	71.29 343	92.43 335	89.15 350

ppachtmachnet_test		88.61 256	88.64 244	88.50 297	91.76 317	70.99 340	84.59 338	92.98 277	79.30 294	92.38 233	93.53 260	79.57 266	97.45 268	86.50 220	97.17 245	97.07 213

IterMVS		90.18 223	90.16 217	90.21 269	93.15 292	75.98 307	87.56 302	92.97 278	86.43 217	94.09 176	96.40 133	78.32 276	97.43 269	87.87 197	94.69 304	97.23 210
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test20.03		90.80 204	90.85 204	90.63 256	95.63 230	79.24 262	89.81 266	92.87 279	89.90 151	94.39 170	96.40 133	85.77 219	95.27 331	73.86 329	99.05 97	97.39 203

CR-MVSNet		87.89 265	87.12 274	90.22 268	91.01 327	78.93 266	92.52 166	92.81 280	73.08 329	89.10 292	96.93 98	67.11 319	97.64 259	88.80 179	92.70 331	94.08 305

Patchmtry		90.11 225	89.92 223	90.66 255	90.35 336	77.00 294	92.96 153	92.81 280	90.25 146	94.74 162	96.93 98	67.11 319	97.52 263	85.17 231	98.98 105	97.46 196

GA-MVS		87.70 269	86.82 278	90.31 264	93.27 289	77.22 292	84.72 337	92.79 282	85.11 241	89.82 282	90.07 320	66.80 322	97.76 253	84.56 244	94.27 312	95.96 257

sss		87.23 281	86.82 278	88.46 299	93.96 279	77.94 279	86.84 316	92.78 283	77.59 305	87.61 317	91.83 298	78.75 271	91.92 354	77.84 304	94.20 313	95.52 277

Patchmatch-RL test		88.81 252	88.52 245	89.69 278	95.33 242	79.94 246	86.22 327	92.71 284	78.46 301	95.80 114	94.18 238	66.25 327	95.33 329	89.22 171	98.53 155	93.78 315

test_yl		90.11 225	89.73 228	91.26 234	94.09 276	79.82 249	90.44 242	92.65 285	90.90 128	93.19 209	93.30 264	73.90 300	98.03 226	82.23 264	96.87 255	95.93 258

DCV-MVSNet		90.11 225	89.73 228	91.26 234	94.09 276	79.82 249	90.44 242	92.65 285	90.90 128	93.19 209	93.30 264	73.90 300	98.03 226	82.23 264	96.87 255	95.93 258

CL-MVSNet_self_test		90.04 230	89.90 224	90.47 260	95.24 243	77.81 283	86.60 325	92.62 287	85.64 231	93.25 207	93.92 248	83.84 231	96.06 314	79.93 288	98.03 211	97.53 193

TSAR-MVS + GP.		93.07 151	92.41 168	95.06 101	95.82 216	90.87 72	90.97 229	92.61 288	88.04 189	94.61 165	93.79 253	88.08 182	97.81 246	89.41 164	98.39 168	96.50 236

TAMVS		90.16 224	89.05 236	93.49 165	96.49 168	86.37 160	90.34 247	92.55 289	80.84 279	92.99 215	94.57 226	81.94 252	98.20 214	73.51 330	98.21 194	95.90 261

MS-PatchMatch		88.05 264	87.75 262	88.95 288	93.28 288	77.93 280	87.88 298	92.49 290	75.42 316	92.57 227	93.59 258	80.44 262	94.24 343	81.28 273	92.75 330	94.69 295

MG-MVS		89.54 238	89.80 225	88.76 292	94.88 248	72.47 334	89.60 269	92.44 291	85.82 227	89.48 288	95.98 159	82.85 239	97.74 255	81.87 267	95.27 292	96.08 252

MVS_0304		90.96 202	90.15 219	93.37 166	93.17 291	87.06 140	93.62 140	92.43 292	89.60 157	82.25 349	95.50 186	82.56 245	97.83 245	84.41 246	97.83 222	95.22 280

lupinMVS		88.34 260	87.31 268	91.45 228	94.74 257	80.06 242	87.23 307	92.27 293	71.10 338	88.83 295	91.15 307	77.02 287	98.53 187	86.67 215	96.75 260	95.76 267

pmmvs5		87.87 266	87.14 273	90.07 272	93.26 290	76.97 297	88.89 286	92.18 294	73.71 326	88.36 307	93.89 250	76.86 292	96.73 294	80.32 280	96.81 257	96.51 233

PM-MVS		93.33 138	92.67 161	95.33 88	96.58 159	94.06 20	92.26 184	92.18 294	85.92 226	96.22 95	96.61 122	85.64 223	95.99 316	90.35 136	98.23 191	95.93 258

pmmvs4		88.95 249	87.70 264	92.70 189	94.30 271	85.60 175	87.22 308	92.16 296	74.62 320	89.75 286	94.19 237	77.97 279	96.41 303	82.71 258	96.36 268	96.09 251

MDA-MVSNet-bldmvs		91.04 200	90.88 202	91.55 226	94.68 262	80.16 237	85.49 330	92.14 297	90.41 144	94.93 154	95.79 168	85.10 224	96.93 288	85.15 233	94.19 314	97.57 189

door-mid								92.13 298

WTY-MVS		86.93 289	86.50 287	88.24 302	94.96 247	74.64 315	87.19 309	92.07 299	78.29 302	88.32 308	91.59 303	78.06 278	94.27 341	74.88 324	93.15 325	95.80 265

AUN-MVS		90.05 229	88.30 250	95.32 91	96.09 199	90.52 76	92.42 174	92.05 300	82.08 272	88.45 306	92.86 273	65.76 329	98.69 168	88.91 177	96.07 271	96.75 229

hse-mvs2		92.24 178	91.20 196	95.38 85	96.16 193	90.65 74	92.52 166	92.01 301	89.23 165	93.95 183	92.99 271	76.88 290	98.69 168	91.02 121	96.03 272	96.81 225

TR-MVS		87.70 269	87.17 272	89.27 285	94.11 275	79.26 261	88.69 291	91.86 302	81.94 273	90.69 264	89.79 325	82.82 240	97.42 270	72.65 336	91.98 339	91.14 345

VDDNet		94.03 125	94.27 119	93.31 169	98.87 20	82.36 214	95.51 74	91.78 303	97.19 12	96.32 86	98.60 18	84.24 229	98.75 155	87.09 209	98.83 126	98.81 78

Anonymous202405211		92.58 168	92.50 166	92.83 185	96.55 162	83.22 203	92.43 173	91.64 304	94.10 51	95.59 123	96.64 120	81.88 253	97.50 264	85.12 235	98.52 156	97.77 176

HY-MVS	82.50 18	86.81 290	85.93 291	89.47 279	93.63 285	77.93 280	94.02 128	91.58 305	75.68 313	83.64 341	93.64 255	77.40 282	97.42 270	71.70 341	92.07 338	93.05 329

door								91.26 306

PatchMatch-RL		89.18 242	88.02 260	92.64 191	95.90 214	92.87 46	88.67 293	91.06 307	80.34 280	90.03 277	91.67 301	83.34 233	94.42 338	76.35 317	94.84 300	90.64 348

ADS-MVSNet2		84.01 304	82.20 312	89.41 281	89.04 349	76.37 304	87.57 300	90.98 308	72.71 332	84.46 335	92.45 284	68.08 315	96.48 301	70.58 348	83.97 357	95.38 278

KD-MVS_2432*1600		82.17 315	80.75 322	86.42 318	82.04 371	70.09 344	81.75 352	90.80 309	82.56 265	90.37 269	89.30 332	42.90 374	96.11 312	74.47 325	92.55 333	93.06 327

miper_refine_blended		82.17 315	80.75 322	86.42 318	82.04 371	70.09 344	81.75 352	90.80 309	82.56 265	90.37 269	89.30 332	42.90 374	96.11 312	74.47 325	92.55 333	93.06 327

wuyk23d		87.83 267	90.79 206	78.96 346	90.46 335	88.63 108	92.72 159	90.67 311	91.65 113	98.68 11	97.64 53	96.06 16	77.53 367	59.84 362	99.41 52	70.73 365

our_test_3		87.55 274	87.59 265	87.44 311	91.76 317	70.48 341	83.83 345	90.55 312	79.79 284	92.06 244	92.17 291	78.63 274	95.63 319	84.77 241	94.73 302	96.22 247

test_method		50.44 335	48.94 338	54.93 350	39.68 374	12.38 376	28.59 365	90.09 313	6.82 369	41.10 371	78.41 363	54.41 361	70.69 369	50.12 367	51.26 369	81.72 363

EU-MVSNet		87.39 278	86.71 281	89.44 280	93.40 287	76.11 305	94.93 96	90.00 314	57.17 365	95.71 119	97.37 68	64.77 335	97.68 258	92.67 85	94.37 309	94.52 298

CHOSEN 280x420		80.04 329	77.97 335	86.23 321	90.13 337	74.53 318	72.87 360	89.59 315	66.38 354	76.29 364	85.32 355	56.96 357	95.36 327	69.49 351	94.72 303	88.79 353

MDA-MVSNet_test_wron		88.16 263	88.23 254	87.93 305	92.22 307	73.71 324	80.71 355	88.84 316	82.52 267	94.88 157	95.14 200	82.70 242	93.61 346	83.28 253	93.80 317	96.46 238

YYNet1		88.17 262	88.24 253	87.93 305	92.21 308	73.62 325	80.75 354	88.77 317	82.51 268	94.99 152	95.11 202	82.70 242	93.70 345	83.33 252	93.83 316	96.48 237

PVSNet	76.22 20	82.89 310	82.37 310	84.48 332	93.96 279	64.38 364	78.60 357	88.61 318	71.50 336	84.43 337	86.36 351	74.27 299	94.60 335	69.87 350	93.69 319	94.46 299

MIMVSNet		87.13 286	86.54 284	88.89 290	96.05 202	76.11 305	94.39 116	88.51 319	81.37 275	88.27 309	96.75 111	72.38 306	95.52 321	65.71 358	95.47 286	95.03 285

tpmvs		84.22 303	83.97 302	84.94 328	87.09 360	65.18 359	91.21 224	88.35 320	82.87 264	85.21 329	90.96 311	65.24 333	96.75 293	79.60 294	85.25 356	92.90 331

EPNet_dtu		85.63 295	84.37 298	89.40 282	86.30 363	74.33 321	91.64 215	88.26 321	84.84 246	72.96 367	89.85 321	71.27 311	97.69 257	76.60 315	97.62 232	96.18 249
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm cat1		80.61 327	79.46 330	84.07 335	88.78 351	65.06 362	89.26 279	88.23 322	62.27 362	81.90 354	89.66 329	62.70 346	95.29 330	71.72 340	80.60 364	91.86 342

baseline1		87.62 273	87.31 268	88.54 296	94.71 261	74.27 322	93.10 150	88.20 323	86.20 220	92.18 241	93.04 269	73.21 303	95.52 321	79.32 295	85.82 355	95.83 263

CVMVSNet		85.16 297	84.72 296	86.48 316	92.12 311	70.19 342	92.32 181	88.17 324	56.15 366	90.64 265	95.85 163	67.97 317	96.69 295	88.78 180	90.52 346	92.56 335

SCA		87.43 277	87.21 271	88.10 304	92.01 314	71.98 336	89.43 273	88.11 325	82.26 271	88.71 302	92.83 274	78.65 272	97.59 260	79.61 292	93.30 322	94.75 292

tpmrst		82.85 311	82.93 309	82.64 339	87.65 354	58.99 369	90.14 254	87.90 326	75.54 315	83.93 339	91.63 302	66.79 324	95.36 327	81.21 275	81.54 363	93.57 323

Vis-MVSNet (Re-imp)		90.42 214	90.16 217	91.20 238	97.66 107	77.32 290	94.33 118	87.66 327	91.20 123	92.99 215	95.13 201	75.40 297	98.28 206	77.86 303	99.19 83	97.99 152

bset_n11_16_dypcd		89.99 231	89.15 234	92.53 198	94.75 255	81.34 226	84.19 342	87.56 328	85.13 239	93.77 188	92.46 283	72.82 304	99.01 112	92.46 90	99.21 81	97.23 210

MDTV_nov1_ep13			83.88 303		89.42 346	61.52 367	88.74 290	87.41 329	73.99 324	84.96 333	94.01 245	65.25 332	95.53 320	78.02 302	93.16 324

PatchmatchNet		85.22 296	84.64 297	86.98 314	89.51 345	69.83 347	90.52 240	87.34 330	78.87 298	87.22 321	92.74 278	66.91 321	96.53 298	81.77 268	86.88 354	94.58 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
N_pmnet		88.90 250	87.25 270	93.83 153	94.40 270	93.81 35	84.73 335	87.09 331	79.36 292	93.26 205	92.43 287	79.29 268	91.68 355	77.50 309	97.22 244	96.00 255

EPNet		89.80 236	88.25 252	94.45 131	83.91 369	86.18 166	93.87 133	87.07 332	91.16 125	80.64 358	94.72 221	78.83 270	98.89 128	85.17 231	98.89 114	98.28 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmatch-test		86.10 293	86.01 290	86.38 320	90.63 331	74.22 323	89.57 270	86.69 333	85.73 230	89.81 283	92.83 274	65.24 333	91.04 357	77.82 306	95.78 279	93.88 314

K. test v3		93.37 137	93.27 148	93.66 156	98.05 80	82.62 212	94.35 117	86.62 334	96.05 28	97.51 40	98.85 12	76.59 293	99.65 3	93.21 67	98.20 196	98.73 89

CostFormer		83.09 308	82.21 311	85.73 322	89.27 347	67.01 351	90.35 246	86.47 335	70.42 342	83.52 343	93.23 267	61.18 350	96.85 290	77.21 311	88.26 352	93.34 325

thres200		85.85 294	85.18 295	87.88 307	94.44 268	72.52 333	89.08 283	86.21 336	88.57 180	91.44 251	88.40 339	64.22 336	98.00 230	68.35 352	95.88 278	93.12 326

ET-MVSNet_ETH3D		86.15 292	84.27 300	91.79 218	93.04 295	81.28 227	87.17 310	86.14 337	79.57 288	83.65 340	88.66 336	57.10 356	98.18 217	87.74 199	95.40 288	95.90 261

PatchT		87.51 275	88.17 256	85.55 323	90.64 330	66.91 352	92.02 194	86.09 338	92.20 87	89.05 294	97.16 85	64.15 337	96.37 306	89.21 172	92.98 329	93.37 324

DWT-MVSNet_test		80.74 325	79.18 331	85.43 325	87.51 357	66.87 353	89.87 264	86.01 339	74.20 323	80.86 357	80.62 362	48.84 367	96.68 297	81.54 270	83.14 361	92.75 333

tfpn200view9		87.05 287	86.52 285	88.67 294	95.77 219	72.94 330	91.89 202	86.00 340	90.84 130	92.61 225	89.80 323	63.93 338	98.28 206	71.27 344	96.54 264	94.79 290

thres400		87.20 283	86.52 285	89.24 287	95.77 219	72.94 330	91.89 202	86.00 340	90.84 130	92.61 225	89.80 323	63.93 338	98.28 206	71.27 344	96.54 264	96.51 233

IB-MVS	77.21 19	83.11 307	81.05 318	89.29 284	91.15 325	75.85 308	85.66 329	86.00 340	79.70 286	82.02 353	86.61 348	48.26 368	98.39 197	77.84 304	92.22 336	93.63 319
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
PMMVS		83.00 309	81.11 317	88.66 295	83.81 370	86.44 158	82.24 351	85.65 343	61.75 363	82.07 351	85.64 354	79.75 265	91.59 356	75.99 319	93.09 326	87.94 355

tpm		84.38 302	84.08 301	85.30 327	90.47 334	63.43 366	89.34 276	85.63 344	77.24 309	87.62 316	95.03 208	61.00 352	97.30 276	79.26 296	91.09 345	95.16 281

LFMVS		91.33 197	91.16 199	91.82 217	96.27 184	79.36 259	95.01 93	85.61 345	96.04 29	94.82 158	97.06 90	72.03 309	98.46 196	84.96 239	98.70 140	97.65 185

FPMVS		84.50 301	83.28 305	88.16 303	96.32 180	94.49 15	85.76 328	85.47 346	83.09 260	85.20 330	94.26 234	63.79 340	86.58 364	63.72 360	91.88 341	83.40 359

tpm2		81.46 319	80.35 326	84.80 329	89.90 339	65.14 360	90.44 242	85.36 347	65.82 357	82.05 352	92.44 286	57.94 355	96.69 295	70.71 347	88.49 351	92.56 335

thres100view900		87.35 279	86.89 277	88.72 293	96.14 195	73.09 329	93.00 152	85.31 348	92.13 89	93.26 205	90.96 311	63.42 341	98.28 206	71.27 344	96.54 264	94.79 290

thres600view7		87.66 271	87.10 275	89.36 283	96.05 202	73.17 327	92.72 159	85.31 348	91.89 96	93.29 202	90.97 310	63.42 341	98.39 197	73.23 332	96.99 254	96.51 233

dp		79.28 330	78.62 333	81.24 342	85.97 364	56.45 370	86.91 314	85.26 350	72.97 330	81.45 356	89.17 335	56.01 360	95.45 325	73.19 333	76.68 365	91.82 343

PMMVS2		81.31 320	83.44 304	74.92 348	90.52 333	46.49 373	69.19 362	85.23 351	84.30 251	87.95 313	94.71 222	76.95 289	84.36 366	64.07 359	98.09 206	93.89 313

ADS-MVSNet		82.25 313	81.55 314	84.34 333	89.04 349	65.30 358	87.57 300	85.13 352	72.71 332	84.46 335	92.45 284	68.08 315	92.33 353	70.58 348	83.97 357	95.38 278

test-LLR		83.58 305	83.17 306	84.79 330	89.68 342	66.86 354	83.08 347	84.52 353	83.07 261	82.85 346	84.78 356	62.86 344	93.49 347	82.85 256	94.86 298	94.03 308

test-mter		81.21 322	80.01 329	84.79 330	89.68 342	66.86 354	83.08 347	84.52 353	73.85 325	82.85 346	84.78 356	43.66 373	93.49 347	82.85 256	94.86 298	94.03 308

JIA-IIPM		85.08 298	83.04 307	91.19 239	87.56 355	86.14 167	89.40 275	84.44 355	88.98 169	82.20 350	97.95 39	56.82 358	96.15 310	76.55 316	83.45 359	91.30 344

thisisatest0530		88.69 255	87.52 266	92.20 205	96.33 179	79.36 259	92.81 157	84.01 356	86.44 216	93.67 192	92.68 280	53.62 364	99.25 77	89.65 161	98.45 162	98.00 149

tttt0517		89.81 235	88.90 241	92.55 197	97.00 138	79.73 253	95.03 92	83.65 357	89.88 152	95.30 135	94.79 220	53.64 363	99.39 48	91.99 99	98.79 132	98.54 108

thisisatest0515		84.72 300	82.99 308	89.90 275	92.96 297	75.33 313	84.36 340	83.42 358	77.37 307	88.27 309	86.65 347	53.94 362	98.72 160	82.56 260	97.40 239	95.67 271

PVSNet_0	70.34 21	74.58 333	72.96 336	79.47 345	90.63 331	66.24 357	73.26 358	83.40 359	63.67 361	78.02 362	78.35 364	72.53 305	89.59 361	56.68 364	60.05 368	82.57 362

pmmvs3		80.83 324	78.96 332	86.45 317	87.23 359	77.48 288	84.87 334	82.31 360	63.83 360	85.03 331	89.50 330	49.66 366	93.10 349	73.12 334	95.10 295	88.78 354

E-PMN		80.72 326	80.86 321	80.29 344	85.11 366	68.77 349	72.96 359	81.97 361	87.76 195	83.25 345	83.01 360	62.22 347	89.17 362	77.15 312	94.31 311	82.93 360

test0.0.03 1		82.48 312	81.47 316	85.48 324	89.70 341	73.57 326	84.73 335	81.64 362	83.07 261	88.13 311	86.61 348	62.86 344	89.10 363	66.24 357	90.29 347	93.77 316

baseline2		83.38 306	81.54 315	88.90 289	91.38 323	72.84 332	88.78 288	81.22 363	78.97 296	79.82 360	87.56 342	61.73 349	97.80 247	74.30 327	90.05 348	96.05 254

EMVS		80.35 328	80.28 327	80.54 343	84.73 368	69.07 348	72.54 361	80.73 364	87.80 194	81.66 355	81.73 361	62.89 343	89.84 360	75.79 321	94.65 305	82.71 361

TESTMET0.1,1		79.09 331	78.04 334	82.25 340	87.52 356	64.03 365	83.08 347	80.62 365	70.28 343	80.16 359	83.22 359	44.13 372	90.56 358	79.95 286	93.36 320	92.15 338

lessismore_v0				93.87 152	98.05 80	83.77 198		80.32 366		97.13 52	97.91 42	77.49 281	99.11 95	92.62 86	98.08 207	98.74 87

new_pmnet		81.22 321	81.01 320	81.86 341	90.92 329	70.15 343	84.03 343	80.25 367	70.83 340	85.97 327	89.78 326	67.93 318	84.65 365	67.44 354	91.90 340	90.78 347

MVS-HIRNet		78.83 332	80.60 324	73.51 349	93.07 293	47.37 372	87.10 311	78.00 368	68.94 347	77.53 363	97.26 78	71.45 310	94.62 334	63.28 361	88.74 350	78.55 364

DSMNet-mixed		82.21 314	81.56 313	84.16 334	89.57 344	70.00 346	90.65 237	77.66 369	54.99 367	83.30 344	97.57 55	77.89 280	90.50 359	66.86 356	95.54 284	91.97 339

EPMVS		81.17 323	80.37 325	83.58 336	85.58 365	65.08 361	90.31 248	71.34 370	77.31 308	85.80 328	91.30 305	59.38 353	92.70 352	79.99 285	82.34 362	92.96 330

gg-mvs-nofinetune		82.10 317	81.02 319	85.34 326	87.46 358	71.04 338	94.74 101	67.56 371	96.44 22	79.43 361	98.99 6	45.24 370	96.15 310	67.18 355	92.17 337	88.85 352

GG-mvs-BLEND				83.24 338	85.06 367	71.03 339	94.99 95	65.55 372		74.09 366	75.51 365	44.57 371	94.46 337	59.57 363	87.54 353	84.24 358

MVE	59.87 23	73.86 334	72.65 337	77.47 347	87.00 362	74.35 320	61.37 364	60.93 373	67.27 352	69.69 368	86.49 350	81.24 259	72.33 368	56.45 365	83.45 359	85.74 357
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MTMP							94.82 98	54.62 374

DeepMVS_CX				53.83 351	70.38 373	64.56 363		48.52 375	33.01 368	65.50 369	74.21 366	56.19 359	46.64 370	38.45 369	70.07 366	50.30 366

tmp_tt		37.97 336	44.33 339	18.88 352	11.80 375	21.54 375	63.51 363	45.66 376	4.23 370	51.34 370	50.48 367	59.08 354	22.11 371	44.50 368	68.35 367	13.00 367

testmvs		9.02 339	11.42 342	1.81 354	2.77 377	1.13 378	79.44 356	1.90 377	1.18 372	2.65 373	6.80 369	1.95 377	0.87 373	2.62 371	3.45 371	3.44 369

test123		9.49 338	12.01 341	1.91 353	2.87 376	1.30 377	82.38 350	1.34 378	1.36 371	2.84 372	6.56 370	2.45 376	0.97 372	2.73 370	5.56 370	3.47 368

test_blank		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uanet_test		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

pcd_1.5k_mvsjas		7.56 340	10.09 343	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	90.77 144	0.00 374	0.00 372	0.00 372	0.00 370

sosnet-low-res		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

sosnet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uncertanet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

Regformer		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

n2								0.00 379

nn								0.00 379

ab-mvs-re		7.56 340	10.08 344	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	90.69 316	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uanet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

PC_three_1452									75.31 318	95.87 112	95.75 172	92.93 93	96.34 309	87.18 208	98.68 142	98.04 144

eth-test2					0.00 378

eth-test					0.00 378

OPU-MVS				95.15 98	96.84 147	89.43 93	95.21 82				95.66 176	93.12 87	98.06 224	86.28 224	98.61 147	97.95 157

test_0728_THIRD									93.26 68	97.40 46	97.35 74	94.69 55	99.34 62	93.88 34	99.42 47	98.89 69

GSMVS																94.75 292

test_part2					98.21 70	89.41 94				96.72 71

sam_mvs1												66.64 325				94.75 292

sam_mvs												66.41 326

test_post1							90.21 250				5.85 372	65.36 331	96.00 315	79.61 292

test_post											6.07 371	65.74 330	95.84 317

patchmatchnet-post											91.71 300	66.22 328	97.59 260

gm-plane-assit					87.08 361	59.33 368			71.22 337		83.58 358		97.20 279	73.95 328

test9_res														88.16 191	98.40 165	97.83 170

agg_prior2														87.06 210	98.36 176	97.98 153

test_prior4						89.91 83	90.74 234

test_prior2							90.21 250		89.33 163	90.77 261	94.81 216	90.41 154		88.21 187	98.55 151

旧先验2							90.00 259		68.65 348	92.71 223			96.52 299	85.15 233

新几何2							90.02 258

原ACMM2							89.34 276

testdata2													98.03 226	80.24 283

segment_acmp												92.14 110

testdata1							88.96 285		88.44 182

plane_prior7					97.71 101	88.68 107

plane_prior6					97.21 130	88.23 118						86.93 204

plane_prior4											95.59 178

plane_prior3						88.43 116			90.35 145	93.31 200

plane_prior2							94.56 110		91.74 109

plane_prior1					97.38 122

plane_prior						88.12 120	93.01 151		88.98 169						98.06 208

HQP5-MVS						84.89 182

HQP-NCC					96.36 174		91.37 219		87.16 207	88.81 297

ACMP_Plane					96.36 174		91.37 219		87.16 207	88.81 297

BP-MVS														86.55 218

HQP4-MVS										88.81 297			98.61 176			98.15 135

HQP2-MVS												84.76 226

NP-MVS					96.82 148	87.10 139					93.40 262

MDTV_nov1_ep13_2view						42.48 374	88.45 295		67.22 353	83.56 342		66.80 322		72.86 335		94.06 307

ACMMP++_ref															98.82 127

ACMMP++															99.25 75

Test By Simon												90.61 150

High-resolution multi-view benchmark