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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

WR-MVS		99.22 3	99.15 6	99.30 2	99.54 11	99.62 1	99.63 4	99.45 1	97.75 15	98.47 22	99.71 6	99.05 42	98.88 4	99.54 6	99.49 3	99.81 1	98.87 10

WR-MVS_H		98.97 10	98.82 15	99.14 8	99.56 9	99.56 5	99.54 11	99.42 2	96.07 41	98.37 24	99.34 32	99.09 35	98.43 18	99.45 11	99.41 6	99.53 11	98.86 11

PS-CasMVS		99.08 5	98.90 12	99.28 3	99.65 3	99.56 5	99.59 6	99.39 3	96.36 36	98.83 14	99.46 22	99.09 35	98.62 10	99.51 8	99.36 9	99.63 4	98.97 8

UniMVSNet_ETH3D		98.93 11	99.20 4	98.63 22	99.54 11	99.33 8	98.73 65	99.37 4	98.87 6	97.86 38	99.27 36	99.78 2	96.59 87	99.52 7	99.40 7	99.67 3	98.21 43

CP-MVSNet		98.91 12	98.61 20	99.25 4	99.63 5	99.50 7	99.55 10	99.36 5	95.53 67	98.77 16	99.11 43	98.64 79	98.57 13	99.42 12	99.28 12	99.61 5	98.78 13

PEN-MVS		99.08 5	98.95 9	99.23 5	99.65 3	99.59 3	99.64 2	99.34 6	96.68 28	98.65 17	99.43 24	99.33 17	98.47 17	99.50 9	99.32 10	99.60 6	98.79 12

DTE-MVSNet		99.03 7	98.88 13	99.21 6	99.66 2	99.59 3	99.62 5	99.34 6	96.92 24	98.52 19	99.36 30	98.98 47	98.57 13	99.49 10	99.23 13	99.56 10	98.55 26

UA-Net		98.66 17	98.60 23	98.73 15	99.83 1	99.28 10	98.56 74	99.24 8	96.04 42	97.12 71	98.44 78	98.95 52	98.17 29	99.15 25	99.00 23	99.48 18	99.33 4

gg-mvs-nofinetune		94.13 169	93.93 162	94.37 183	97.99 130	95.86 177	95.45 198	99.22 9	97.61 16	95.10 153	99.50 20	84.50 196	81.73 216	95.31 156	94.12 168	96.71 170	90.59 188

SixPastTwentyTwo		99.25 2	99.20 4	99.32 1	99.53 15	99.32 9	99.64 2	99.19 10	98.05 11	99.19 6	99.74 4	98.96 51	99.03 2	99.69 3	99.58 2	99.32 27	99.06 7

LTVRE_ROB	97.71 1	99.33 1	99.47 2	99.16 7	99.16 42	99.11 14	99.39 13	99.16 11	99.26 3	99.22 5	99.51 19	99.75 4	98.54 15	99.71 2	99.47 4	99.52 13	99.46 1
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		97.94 52	97.27 73	98.71 18	98.66 87	99.07 17	99.33 16	99.05 12	91.33 155	97.64 46	96.30 131	98.52 87	98.19 26	98.83 36	98.96 24	99.40 21	97.90 57

pmmvs6		98.77 14	99.35 3	98.09 45	98.32 104	98.92 26	98.57 72	99.03 13	99.36 2	96.86 84	99.77 3	99.86 1	96.20 102	99.56 5	99.39 8	99.59 7	98.61 23

test_part1		99.20 4	99.62 1	98.72 16	98.92 66	99.62 1	99.52 12	99.01 14	99.39 1	97.87 37	99.74 4	99.75 4	97.29 64	99.73 1	99.71 1	99.69 2	99.41 2

Fast-Effi-MVS+-dtu		94.34 164	93.26 171	95.62 160	97.82 145	95.97 176	95.86 186	99.01 14	86.88 200	93.39 189	90.83 203	95.46 159	90.61 178	94.46 169	94.68 162	97.01 159	94.51 159

TranMVSNet+NR-MVSNet		98.45 19	98.22 32	98.72 16	99.32 32	99.06 18	98.99 37	98.89 16	95.52 68	97.53 50	99.42 26	98.83 63	98.01 35	98.55 56	98.34 59	99.57 9	97.80 60

DU-MVS		98.23 27	97.74 56	98.81 12	99.23 34	98.77 42	98.76 59	98.88 17	94.10 116	98.50 20	98.87 57	98.32 98	97.99 36	98.40 64	98.08 75	99.49 17	97.64 70

NR-MVSNet		98.00 44	97.88 46	98.13 43	98.33 102	98.77 42	98.83 55	98.88 17	94.10 116	97.46 55	98.87 57	98.58 84	95.78 111	99.13 26	98.16 70	99.52 13	97.53 78

UniMVSNet (Re)		98.23 27	97.85 48	98.67 20	99.15 43	98.87 29	98.74 62	98.84 19	94.27 114	97.94 36	99.01 45	98.39 94	97.82 43	98.35 69	98.29 64	99.51 16	97.78 61

DROMVSNet		97.63 64	96.88 97	98.50 27	98.74 79	99.16 12	99.33 16	98.83 20	88.77 183	96.62 93	96.48 125	97.75 117	98.19 26	99.00 29	98.76 35	99.29 29	98.27 42

v7n		99.03 7	99.03 8	99.02 9	99.09 53	99.11 14	99.57 9	98.82 21	98.21 10	99.25 3	99.84 2	99.59 7	98.76 6	99.23 20	98.83 33	98.63 72	98.40 35

UniMVSNet_NR-MVSNet		98.12 37	97.56 63	98.78 13	99.13 48	98.89 28	98.76 59	98.78 22	93.81 124	98.50 20	98.81 61	97.64 124	97.99 36	98.18 75	97.92 80	99.53 11	97.64 70

GeoE		97.48 78	96.84 101	98.22 40	99.01 59	98.39 72	98.85 54	98.76 23	92.37 144	97.53 50	97.58 98	98.23 103	97.11 68	97.57 95	96.98 105	98.10 111	96.78 111

Effi-MVS+		96.46 120	95.28 136	97.85 68	98.64 91	97.16 141	97.15 151	98.75 24	90.27 170	98.03 33	93.93 175	96.21 151	96.55 91	96.34 133	96.69 115	97.97 118	96.33 125

Baseline_NR-MVSNet		98.17 31	97.90 45	98.48 30	99.23 34	98.59 58	98.83 55	98.73 25	93.97 121	96.95 78	99.66 8	98.23 103	97.90 40	98.40 64	99.06 18	99.25 31	97.42 85

DCV-MVSNet		97.56 67	97.63 59	97.47 92	98.41 99	99.12 13	98.63 69	98.57 26	95.71 58	95.60 141	93.79 177	98.01 112	94.25 142	99.16 24	98.88 30	99.35 23	98.74 15

FC-MVSNet-test		97.54 69	98.26 30	96.70 128	98.87 68	97.79 116	98.49 78	98.56 27	96.04 42	90.39 204	99.65 9	98.67 76	95.15 126	99.23 20	99.07 16	98.73 70	97.39 86

MIMVSNet1		98.22 30	98.51 24	97.87 66	99.40 26	98.82 38	99.31 18	98.53 28	97.39 19	96.59 95	99.31 34	99.23 30	94.76 134	98.93 33	98.67 40	98.63 72	97.25 93

FMVSNet1		97.40 84	98.09 37	96.60 132	97.80 148	98.76 45	98.26 89	98.50 29	96.79 26	93.13 192	99.28 35	98.64 79	92.90 162	97.67 89	97.86 83	99.02 43	97.64 70

zzz-MVS		98.14 34	97.78 53	98.55 25	99.58 6	98.58 60	98.98 39	98.48 30	95.98 47	97.39 57	94.73 159	99.27 24	97.98 38	98.81 37	98.64 45	98.90 58	98.46 31

ACMMPR		98.31 24	98.07 39	98.60 23	99.58 6	98.83 34	99.09 28	98.48 30	96.25 38	97.03 75	96.81 116	99.09 35	98.39 20	98.55 56	98.45 51	99.01 45	98.53 29

CR-MVSNet		91.94 188	88.50 198	95.94 151	96.14 194	92.08 201	95.23 201	98.47 32	84.30 213	96.44 100	94.58 163	75.57 215	92.92 160	90.22 204	92.22 185	96.43 175	90.56 189

Patchmtry						92.70 196	95.23 201	98.47 32		96.44 100

HFP-MVS		98.17 31	98.02 40	98.35 37	99.36 28	98.62 57	98.79 58	98.46 34	96.24 39	96.53 97	97.13 113	98.98 47	98.02 34	98.20 72	98.42 53	98.95 54	98.54 27

MIMVSNet		93.68 177	93.96 160	93.35 192	97.82 145	96.08 174	96.34 174	98.46 34	91.28 158	86.67 218	94.95 154	94.87 164	84.39 214	94.53 165	94.65 163	96.45 174	91.34 185

SteuartSystems-ACMMP		98.06 40	97.78 53	98.39 35	99.54 11	98.79 40	98.94 44	98.42 36	93.98 120	95.85 125	96.66 122	99.25 28	98.61 11	98.71 46	98.38 56	98.97 50	98.67 20
Skip Steuart: Steuart Systems R&D Blog.
test2506		94.29 167	91.43 189	97.64 80	98.66 87	98.83 34	98.50 76	98.40 37	96.04 42	94.45 167	94.88 156	55.05 228	96.70 81	99.28 15	99.04 21	99.14 35	96.87 107

test1111		97.48 78	97.20 78	97.81 73	98.78 77	98.85 31	98.68 66	98.40 37	96.68 28	94.84 159	99.13 42	90.32 189	97.01 73	99.27 18	99.05 19	99.19 33	97.10 98

ECVR-MVS		97.40 84	97.11 87	97.73 78	98.66 87	98.83 34	98.50 76	98.40 37	96.04 42	95.00 157	98.95 49	91.07 186	96.70 81	99.28 15	99.04 21	99.14 35	96.58 116

SR-MVS					99.33 31			98.40 37				98.90 55

MP-MVS		97.98 48	97.53 65	98.50 27	99.56 9	98.58 60	98.97 40	98.39 41	93.49 127	97.14 68	96.08 135	99.23 30	98.06 32	98.50 61	98.38 56	98.90 58	98.44 33
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		98.00 44	97.57 62	98.50 27	99.47 21	98.56 63	98.91 46	98.38 42	94.71 95	97.01 76	95.20 148	99.06 39	98.20 24	98.61 53	98.46 48	99.02 43	98.40 35

X-MVS		97.60 65	97.00 92	98.29 38	99.50 18	98.76 45	98.90 47	98.37 43	94.67 98	96.40 104	91.47 198	98.78 69	97.60 53	98.55 56	98.50 46	98.96 52	98.29 38

EPP-MVSNet		97.29 88	96.88 97	97.76 76	98.70 82	99.10 16	98.92 45	98.36 44	95.12 80	93.36 190	97.39 104	91.00 187	97.65 50	98.72 44	98.91 27	99.58 8	97.92 55

PGM-MVS		97.82 57	97.25 75	98.48 30	99.54 11	98.75 49	99.02 32	98.35 45	92.41 143	96.84 85	95.39 145	98.99 46	98.24 23	98.43 63	98.34 59	98.90 58	98.41 34

3Dnovator+	96.20 4	97.58 66	97.14 83	98.10 44	98.98 64	97.85 108	98.60 71	98.33 46	96.41 34	97.23 66	94.66 162	97.26 133	96.91 76	97.91 77	97.87 82	98.53 82	98.03 48

APDe-MVS		98.29 25	98.42 27	98.14 42	99.45 22	98.90 27	99.18 25	98.30 47	95.96 49	95.13 151	98.79 62	99.25 28	97.92 39	98.80 38	98.71 37	98.85 65	98.54 27

ACMMP		97.99 46	97.60 61	98.45 32	99.53 15	98.83 34	99.13 27	98.30 47	94.57 101	96.39 108	95.32 146	98.95 52	98.37 21	98.61 53	98.47 47	99.00 46	98.45 32
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
TDRefinement		99.00 9	99.13 7	98.86 10	98.99 63	99.05 20	99.58 7	98.29 49	98.96 5	97.96 35	99.40 27	98.67 76	98.87 5	99.60 4	99.46 5	99.46 19	98.74 15

LGP-MVS_train		97.96 51	97.53 65	98.45 32	99.45 22	98.64 56	99.09 28	98.27 50	92.99 139	96.04 120	96.57 123	99.29 20	98.66 8	98.73 42	98.42 53	99.19 33	98.09 46

DVP-MVS++		98.44 21	98.92 11	97.88 65	99.17 40	99.00 23	98.89 48	98.26 51	97.54 18	96.05 119	99.35 31	99.76 3	96.34 97	98.79 39	98.65 42	98.56 79	99.35 3

ACMM	94.29 11	98.12 37	97.71 57	98.59 24	99.51 17	98.58 60	99.24 21	98.25 52	96.22 40	96.90 79	95.01 152	98.89 57	98.52 16	98.66 49	98.32 62	99.13 38	98.28 41
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SED-MVS		98.05 41	98.46 26	97.57 84	99.01 59	98.99 24	98.82 57	98.24 53	95.76 57	94.70 162	98.96 47	99.49 10	96.19 103	98.74 40	98.65 42	98.46 87	98.63 21

Fast-Effi-MVS+		96.80 108	95.92 128	97.84 69	98.57 92	97.46 131	98.06 98	98.24 53	89.64 178	97.57 49	96.45 126	97.35 131	96.73 80	97.22 106	96.64 117	97.86 121	96.65 114

IS_MVSNet		96.62 117	96.48 113	96.78 126	98.46 96	98.68 55	98.61 70	98.24 53	92.23 146	89.63 208	95.90 140	94.40 168	96.23 99	98.65 50	98.77 34	99.52 13	96.76 112

CS-MVS		97.89 54	97.44 67	98.42 34	98.71 81	99.22 11	99.34 14	98.21 56	91.60 152	96.62 93	96.73 119	98.69 75	98.20 24	98.65 50	99.18 15	99.44 20	97.99 51

APD-MVS		97.47 80	97.16 81	97.84 69	99.32 32	98.39 72	98.47 81	98.21 56	92.08 148	95.23 148	96.68 121	98.90 55	96.99 74	98.20 72	98.21 66	98.80 67	97.67 68
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		97.56 67	97.11 87	98.09 45	99.18 39	97.95 103	98.57 72	98.20 58	94.08 118	97.25 65	95.96 139	98.81 66	97.13 67	97.51 97	97.30 99	98.21 103	98.15 45

EPNet		94.33 166	93.52 167	95.27 168	98.81 74	94.71 187	96.77 162	98.20 58	88.12 192	96.53 97	92.53 188	91.19 183	85.25 213	95.22 158	95.26 153	96.09 180	97.63 74
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ETV-MVS		96.54 119	95.27 137	98.02 58	99.07 56	97.48 130	98.16 94	98.19 60	87.33 198	97.58 48	92.67 186	95.93 156	96.22 100	98.49 62	98.46 48	98.91 57	96.50 122

pm-mvs1		98.14 34	98.66 19	97.53 88	97.93 134	98.49 68	98.14 95	98.19 60	97.95 12	96.17 115	99.63 11	98.85 60	95.41 122	98.91 34	98.89 29	99.34 24	97.86 58

SCA		91.15 195	87.65 202	95.23 171	96.15 193	95.68 179	96.68 166	98.18 62	90.46 167	97.21 67	92.44 190	80.17 207	93.51 155	86.04 213	83.58 209	89.68 209	85.21 208

v10		97.64 63	97.26 74	98.08 49	98.07 124	98.56 63	98.86 52	98.18 62	94.48 107	98.24 28	99.56 16	98.98 47	97.72 47	96.05 142	96.26 129	97.42 140	96.93 102

DVP-MVS		98.27 26	98.61 20	97.87 66	99.17 40	99.03 21	99.07 30	98.17 64	96.75 27	94.35 170	98.92 51	99.58 8	97.86 42	98.67 48	98.70 38	98.63 72	98.63 21
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
v8		97.51 73	97.16 81	97.91 62	97.99 130	98.48 69	98.76 59	98.17 64	94.54 105	97.69 44	99.48 21	98.76 72	97.63 52	96.10 141	96.14 131	97.20 150	96.64 115

DeepC-MVS	96.08 5	98.58 18	98.49 25	98.68 19	99.37 27	98.52 66	99.01 36	98.17 64	97.17 22	98.25 27	99.56 16	99.62 6	98.29 22	98.40 64	98.09 72	98.97 50	98.08 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSP-MVS		97.67 60	97.88 46	97.43 94	99.34 29	98.99 24	98.87 51	98.12 67	95.63 59	94.16 176	97.45 102	99.50 9	96.44 95	96.35 132	98.70 38	97.65 131	98.57 25
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
RPMNet		90.52 197	86.27 211	95.48 163	95.95 199	92.08 201	95.55 194	98.12 67	84.30 213	95.60 141	87.49 211	72.78 220	91.24 170	87.93 208	89.34 197	96.41 176	89.98 192

ACMH	95.26 7	98.75 15	98.93 10	98.54 26	98.86 69	99.01 22	99.58 7	98.10 69	98.67 7	97.30 62	99.18 40	99.42 12	98.40 19	99.19 22	98.86 31	98.99 48	98.19 44
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FC-MVSNet-train		97.65 62	98.16 34	97.05 111	98.85 70	98.85 31	99.34 14	98.08 70	94.50 106	94.41 168	99.21 38	98.80 67	92.66 164	98.98 31	98.85 32	98.96 52	97.94 53

thisisatest0515		97.82 57	97.67 58	97.99 61	98.49 94	98.07 92	98.48 79	98.06 71	95.35 73	97.74 42	98.83 60	97.61 125	96.74 79	97.53 96	98.30 63	98.43 92	98.01 50

ACMP	94.03 12	97.97 50	97.61 60	98.39 35	99.43 25	98.51 67	98.97 40	98.06 71	94.63 99	96.10 117	96.12 134	99.20 32	98.63 9	98.68 47	98.20 69	99.14 35	97.93 54
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Gipuma		98.43 22	98.15 35	98.76 14	99.00 62	98.29 76	97.91 108	98.06 71	99.02 4	99.50 1	96.33 128	98.67 76	99.22 1	99.02 28	98.02 77	98.88 63	97.66 69
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DPE-MVS		97.99 46	98.12 36	97.84 69	98.65 90	98.86 30	98.86 52	98.05 74	94.18 115	95.49 144	98.90 53	99.33 17	97.11 68	98.53 59	98.65 42	98.86 64	98.39 37
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MAR-MVS		95.51 140	94.49 156	96.71 127	97.92 135	96.40 165	96.72 164	98.04 75	86.74 202	96.72 87	92.52 189	95.14 162	94.02 147	96.81 120	96.54 120	96.85 162	97.25 93
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
EIA-MVS		96.23 126	94.85 149	97.84 69	99.08 54	98.21 78	97.69 118	98.03 76	85.68 208	98.09 31	91.75 196	97.07 138	95.66 119	97.58 94	97.72 87	98.47 86	95.91 136

TransMVSNet (Re)		98.23 27	98.72 17	97.66 79	98.22 113	98.73 51	98.66 68	98.03 76	98.60 8	96.40 104	99.60 13	98.24 101	95.26 124	99.19 22	99.05 19	99.36 22	97.64 70

ACMMP_NAP		98.12 37	98.08 38	98.18 41	99.34 29	98.74 50	98.97 40	98.00 78	95.13 79	96.90 79	97.54 101	99.27 24	97.18 66	98.72 44	98.45 51	98.68 71	98.69 17

CPTT-MVS		97.08 97	96.25 115	98.05 54	99.21 36	98.30 75	98.54 75	97.98 79	94.28 112	95.89 124	89.57 207	98.54 86	98.18 28	97.82 82	97.32 97	98.54 80	97.91 56

IterMVS-LS		96.35 121	95.85 129	96.93 119	97.53 160	98.00 99	97.37 137	97.97 80	95.49 70	96.71 90	98.94 50	93.23 174	94.82 133	93.15 186	95.05 155	97.17 152	97.12 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
canonicalmvs		97.11 95	96.88 97	97.38 95	98.34 101	98.72 53	97.52 129	97.94 81	95.60 60	95.01 156	94.58 163	94.50 167	96.59 87	97.84 81	98.03 76	98.90 58	98.91 9

Anonymous202405211			97.39 69		98.85 70	98.59 58	97.89 111	97.93 82	94.41 109		97.37 105	96.99 140	93.09 158	98.61 53	98.46 48	99.11 40	97.27 91

LS3D		97.93 53	97.80 50	98.08 49	99.20 37	98.77 42	98.89 48	97.92 83	96.59 31	96.99 77	96.71 120	97.14 137	96.39 96	99.04 27	98.96 24	99.10 42	97.39 86

FMVSNet2		95.77 136	96.20 119	95.27 168	96.77 184	98.18 81	97.28 142	97.90 84	93.12 134	91.37 201	98.25 84	96.05 154	90.04 184	94.96 162	95.94 138	98.28 96	96.90 103

Effi-MVS+-dtu		95.94 133	95.08 143	96.94 118	98.54 93	97.38 132	96.66 167	97.89 85	88.68 184	95.92 122	92.90 185	97.28 132	94.18 145	96.68 126	96.13 133	98.45 88	96.51 121

TSAR-MVS + ACMM		97.54 69	97.79 51	97.26 100	98.23 111	98.10 91	97.71 117	97.88 86	95.97 48	95.57 143	98.71 69	98.57 85	97.36 59	97.74 85	96.81 111	96.83 165	98.59 24

SMA-MVS		98.13 36	98.22 32	98.02 58	99.44 24	98.73 51	98.24 90	97.87 87	95.22 75	96.76 86	98.66 71	99.35 16	97.03 72	98.53 59	98.39 55	98.80 67	98.69 17
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
Vis-MVSNet (Re-imp)		96.29 123	96.50 111	96.05 147	97.96 133	97.83 109	97.30 141	97.86 88	93.14 133	88.90 211	96.80 117	95.28 160	95.15 126	98.37 68	98.25 65	99.12 39	95.84 137

ACMH+	94.90 8	98.40 23	98.71 18	98.04 55	98.93 65	98.84 33	99.30 19	97.86 88	97.78 14	94.19 175	98.77 65	99.39 14	98.61 11	99.33 14	99.07 16	99.33 25	97.81 59

Anonymous20231211		97.49 76	97.91 44	97.00 115	98.31 107	98.72 53	98.27 88	97.84 90	94.76 94	94.77 161	98.14 87	98.38 96	93.60 152	98.96 32	98.66 41	99.22 32	97.77 64

UGNet		96.79 109	97.82 49	95.58 161	97.57 159	98.39 72	98.48 79	97.84 90	95.85 52	94.68 163	97.91 91	99.07 38	87.12 203	97.71 86	97.51 89	97.80 122	98.29 38
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_0304		97.18 94	96.84 101	97.58 83	99.15 43	98.19 80	98.11 96	97.81 92	92.36 145	98.06 32	97.43 103	99.06 39	94.24 143	96.80 121	96.54 120	98.12 109	97.52 79

SD-MVS		97.84 55	97.78 53	97.90 63	98.33 102	98.06 93	97.95 105	97.80 93	96.03 46	96.72 87	97.57 99	99.18 33	97.50 54	97.88 78	97.08 102	99.11 40	98.68 19
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
OPM-MVS		98.01 42	98.01 41	98.00 60	99.11 50	98.12 88	98.68 66	97.72 94	96.65 30	96.68 91	98.40 80	99.28 23	97.44 56	98.20 72	97.82 86	98.40 93	97.58 75
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		97.66 61	97.79 51	97.52 90	98.32 104	98.53 65	98.45 82	97.69 95	97.59 17	96.12 116	97.79 94	96.70 143	95.69 116	98.35 69	98.34 59	98.85 65	97.22 96

COLMAP_ROB	96.84 2	98.75 15	98.82 15	98.66 21	99.14 46	98.79 40	99.30 19	97.67 96	98.33 9	97.82 40	99.20 39	99.18 33	98.76 6	99.27 18	98.96 24	99.29 29	98.03 48
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TSAR-MVS + GP.		97.26 90	97.33 71	97.18 105	98.21 114	98.06 93	96.38 173	97.66 97	93.92 123	95.23 148	98.48 76	98.33 97	97.41 57	97.63 93	97.35 93	98.18 105	97.57 76

PVSNet_Blended_VisFu		97.44 81	97.14 83	97.79 74	99.15 43	98.44 70	98.32 86	97.66 97	93.74 126	97.73 43	98.79 62	96.93 142	95.64 121	97.69 87	96.91 108	98.25 101	97.50 81

Vis-MVSNet		98.01 42	98.42 27	97.54 87	96.89 181	98.82 38	99.14 26	97.59 99	96.30 37	97.04 74	99.26 37	98.83 63	96.01 108	98.73 42	98.21 66	98.58 78	98.75 14
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GBi-Net		95.21 147	95.35 134	95.04 173	96.77 184	98.18 81	97.28 142	97.58 100	88.43 189	90.28 205	96.01 136	92.43 177	90.04 184	97.67 89	97.86 83	98.28 96	96.90 103

test1		95.21 147	95.35 134	95.04 173	96.77 184	98.18 81	97.28 142	97.58 100	88.43 189	90.28 205	96.01 136	92.43 177	90.04 184	97.67 89	97.86 83	98.28 96	96.90 103

FMVSNet3		94.06 171	93.85 164	94.31 186	95.46 209	97.80 115	96.34 174	97.58 100	88.43 189	90.28 205	96.01 136	92.43 177	88.67 196	91.82 195	93.96 171	97.53 133	96.50 122

test20.03		96.08 128	96.80 104	95.25 170	99.19 38	97.58 122	97.24 146	97.56 103	94.95 88	91.91 199	98.58 73	98.03 110	87.88 199	97.43 99	96.94 107	97.69 128	94.05 167

NCCC		96.56 118	95.68 130	97.59 82	99.04 58	97.54 127	97.67 119	97.56 103	94.84 91	96.10 117	87.91 210	98.09 107	96.98 75	97.20 107	96.80 112	98.21 103	97.38 89

CANet		96.81 107	96.50 111	97.17 106	99.10 52	97.96 102	97.86 113	97.51 105	91.30 156	97.75 41	97.64 96	97.89 115	93.39 156	96.98 117	96.73 113	97.40 141	96.99 100

PatchT		91.40 192	88.54 197	94.74 177	91.48 221	92.18 200	97.42 135	97.51 105	84.96 210	96.44 100	94.16 170	75.47 216	92.92 160	90.22 204	92.22 185	92.66 200	90.56 189

EPNet_dtu		93.45 179	92.51 179	94.55 182	98.39 100	91.67 206	95.46 196	97.50 107	86.56 203	97.38 58	93.52 178	94.20 171	85.82 208	93.31 183	92.53 184	92.72 197	95.76 142
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PHI-MVS		97.44 81	97.17 80	97.74 77	98.14 120	98.41 71	98.03 101	97.50 107	92.07 149	98.01 34	97.33 107	98.62 82	96.02 107	98.34 71	98.21 66	98.76 69	97.24 95

CSCG		98.45 19	98.61 20	98.26 39	99.11 50	99.06 18	98.17 93	97.49 109	97.93 13	97.37 59	98.88 55	99.29 20	98.10 30	98.40 64	97.51 89	99.32 27	99.16 5

tfpn200view9		93.80 176	91.75 186	96.20 145	97.52 161	98.15 86	97.48 132	97.47 110	87.65 194	93.56 186	83.03 216	84.12 197	92.62 165	97.04 112	98.09 72	98.52 83	94.17 164

CDPH-MVS		96.68 113	95.99 124	97.48 91	99.13 48	97.64 119	98.08 97	97.46 111	90.56 166	95.13 151	94.87 157	98.27 100	96.56 90	97.09 111	96.45 123	98.54 80	97.08 99

HyFIR lowres test		95.05 150	93.54 166	96.81 125	97.81 147	96.88 152	98.18 91	97.46 111	94.28 112	94.98 158	96.57 123	92.89 176	96.15 105	90.90 203	91.87 188	96.28 177	91.35 184

thres600view7		94.34 164	92.31 181	96.70 128	98.19 116	98.12 88	97.85 114	97.45 113	91.49 153	93.98 179	84.27 213	82.02 203	94.24 143	97.04 112	98.76 35	98.49 84	94.47 161

thres200		93.98 174	91.90 185	96.40 142	97.66 152	98.12 88	97.20 147	97.45 113	90.16 172	93.82 180	83.08 215	83.74 199	93.80 149	97.04 112	97.48 91	98.49 84	93.70 171

xxxxxxxxxxxxxcwj		97.32 87	97.55 64	97.05 111	98.80 75	97.83 109	96.02 182	97.44 115	94.98 84	95.74 131	97.16 110	99.30 19	95.72 113	97.85 79	97.97 78	98.60 75	97.78 61

SF-MVS		97.26 90	97.43 68	97.05 111	98.80 75	97.83 109	96.02 182	97.44 115	94.98 84	95.74 131	97.16 110	98.45 93	95.72 113	97.85 79	97.97 78	98.60 75	97.78 61

v2v482		97.33 86	96.84 101	97.90 63	98.19 116	97.83 109	98.74 62	97.44 115	95.42 71	98.23 29	99.46 22	98.84 62	97.46 55	95.51 153	96.10 134	97.36 144	94.72 156

v1144		97.51 73	97.05 90	98.04 55	98.26 109	97.98 100	98.88 50	97.42 118	95.38 72	98.56 18	99.59 15	99.01 45	97.65 50	95.77 146	96.06 136	97.47 136	95.56 147

tpm		89.84 201	86.81 208	93.36 191	96.60 188	91.92 204	95.02 203	97.39 119	86.79 201	96.54 96	95.03 150	69.70 224	87.66 200	88.79 207	86.19 203	86.95 217	89.27 196

gm-plane-assit		91.85 189	87.91 200	96.44 141	99.14 46	98.25 77	99.02 32	97.38 120	95.57 63	98.31 25	99.34 32	51.00 229	88.93 193	93.16 185	91.57 189	95.85 181	86.50 206

train_agg		96.68 113	95.93 127	97.56 85	99.08 54	97.16 141	98.44 84	97.37 121	91.12 160	95.18 150	95.43 144	98.48 91	97.36 59	96.48 129	95.52 148	97.95 119	97.34 90

thisisatest0530		94.81 156	93.06 172	96.85 124	98.01 127	97.18 140	96.93 158	97.36 122	89.73 177	95.80 128	94.98 153	77.88 212	94.89 130	96.73 123	97.35 93	98.13 108	97.54 77

tttt0517		94.81 156	93.04 173	96.88 123	98.15 119	97.37 133	96.99 155	97.36 122	89.51 179	95.74 131	94.89 155	77.53 214	94.89 130	96.94 118	97.35 93	98.17 106	97.70 67

anonymousdsp		98.85 13	98.88 13	98.83 11	98.69 85	98.20 79	99.68 1	97.35 124	97.09 23	98.98 10	99.86 1	99.43 11	98.94 3	99.28 15	99.19 14	99.33 25	99.08 6

MCST-MVS		96.79 109	96.08 121	97.62 81	98.78 77	97.52 128	98.01 103	97.32 125	93.20 131	95.84 126	93.97 174	98.12 106	97.34 61	96.34 133	95.88 141	98.45 88	97.51 80

AdaColmap		95.85 135	94.65 152	97.26 100	98.70 82	97.20 138	97.33 140	97.30 126	91.28 158	95.90 123	88.16 209	96.17 152	96.60 86	97.34 102	96.82 110	97.71 125	95.60 146

v1192		97.52 72	97.03 91	98.09 45	98.31 107	98.01 98	98.96 43	97.25 127	95.22 75	98.89 12	99.64 10	98.83 63	97.68 49	95.63 149	95.91 139	97.47 136	95.97 135

v144192		97.49 76	96.99 94	98.07 51	98.11 123	97.95 103	99.02 32	97.21 128	94.90 90	98.88 13	99.53 18	98.89 57	97.75 45	95.59 150	95.90 140	97.43 139	96.16 129

CNVR-MVS		97.03 100	96.77 106	97.34 96	98.89 67	97.67 118	97.64 122	97.17 129	94.40 110	95.70 137	94.02 172	98.76 72	96.49 94	97.78 84	97.29 100	98.12 109	97.47 82

DeepC-MVS_fast	95.38 6	97.53 71	97.30 72	97.79 74	98.83 73	97.64 119	98.18 91	97.14 130	95.57 63	97.83 39	97.10 114	98.80 67	96.53 92	97.41 100	97.32 97	98.24 102	97.26 92
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVS_Test		95.34 146	94.88 148	95.89 152	96.93 180	96.84 156	96.66 167	97.08 131	90.06 174	94.02 177	97.61 97	96.64 144	93.59 153	92.73 190	94.02 170	97.03 158	96.24 126

v1921920		97.50 75	97.00 92	98.07 51	98.20 115	97.94 106	99.03 31	97.06 132	95.29 74	99.01 9	99.62 12	98.73 74	97.74 46	95.52 152	95.78 144	97.39 142	96.12 131

v1240		97.43 83	96.87 100	98.09 45	98.25 110	97.92 107	99.02 32	97.06 132	94.77 93	99.09 8	99.68 7	98.51 89	97.78 44	95.25 157	95.81 142	97.32 146	96.13 130

PMVS	90.51 17	97.77 59	97.98 42	97.53 88	98.68 86	98.14 87	97.67 119	97.03 134	96.43 32	98.38 23	98.72 68	97.03 139	94.44 139	99.37 13	99.30 11	98.98 49	96.86 108
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
v148		96.99 102	96.70 108	97.34 96	97.89 137	97.23 137	98.33 85	96.96 135	95.57 63	97.12 71	98.99 46	99.40 13	97.23 65	96.22 138	95.45 149	96.50 172	94.02 168

MSLP-MVS++		96.66 115	96.46 114	96.89 122	98.02 126	97.71 117	95.57 190	96.96 135	94.36 111	96.19 114	91.37 199	98.24 101	97.07 70	97.69 87	97.89 81	97.52 134	97.95 52

thres400		94.04 172	91.94 184	96.50 138	97.98 132	97.82 113	97.66 121	96.96 135	90.96 161	94.20 173	83.24 214	82.82 201	93.80 149	96.50 128	98.09 72	98.38 94	94.15 165

pmmvs-eth3d		96.84 106	96.22 117	97.56 85	97.63 156	96.38 168	98.74 62	96.91 138	94.63 99	98.26 26	99.43 24	98.28 99	96.58 89	94.52 167	95.54 147	97.24 148	94.75 155

TSAR-MVS + MP.		98.15 33	98.23 31	98.06 53	98.47 95	98.16 85	99.23 22	96.87 139	95.58 62	96.72 87	98.41 79	99.06 39	98.05 33	98.99 30	98.90 28	99.00 46	98.51 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MVS_111021_HR		97.27 89	97.11 87	97.46 93	98.46 96	97.82 113	97.50 130	96.86 140	94.97 86	97.13 70	96.99 115	98.39 94	96.82 78	97.65 92	97.38 92	98.02 114	96.56 119

MDTV_nov1_ep13_2view		94.39 163	93.34 169	95.63 159	97.23 175	95.33 182	97.76 115	96.84 141	94.55 102	97.47 53	98.96 47	97.70 120	93.88 148	92.27 192	86.81 202	90.56 205	87.73 203

EG-PatchMatch MVS		97.98 48	97.92 43	98.04 55	98.84 72	98.04 96	97.90 109	96.83 142	95.07 81	98.79 15	99.07 44	99.37 15	97.88 41	98.74 40	98.16 70	98.01 115	96.96 101

casdiffmvs		97.00 101	97.36 70	96.59 133	97.65 153	97.98 100	98.06 98	96.81 143	95.78 55	92.77 198	99.40 27	99.26 27	95.65 120	96.70 124	96.39 125	98.59 77	95.99 134

DI_MVS_plusplus_trai		95.48 141	94.51 154	96.61 131	97.13 176	97.30 134	98.05 100	96.79 144	93.75 125	95.08 154	96.38 127	89.76 191	94.95 129	93.97 177	94.82 161	97.64 132	95.63 145

3Dnovator	96.31 3	97.22 93	97.19 79	97.25 103	98.14 120	97.95 103	98.03 101	96.77 145	96.42 33	97.14 68	95.11 149	97.59 126	95.14 128	97.79 83	97.72 87	98.26 99	97.76 66

QAPM		97.04 99	97.14 83	96.93 119	97.78 151	98.02 97	97.36 139	96.72 146	94.68 97	96.23 110	97.21 109	97.68 122	95.70 115	97.37 101	97.24 101	97.78 124	97.77 64

PatchmatchNet		89.98 199	86.23 212	94.36 185	96.56 189	91.90 205	96.07 181	96.72 146	90.18 171	96.87 81	93.36 182	78.06 211	91.46 168	84.71 217	81.40 214	88.45 212	83.97 214
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testgi		94.81 156	96.05 123	93.35 192	99.06 57	96.87 154	97.57 127	96.70 148	95.77 56	88.60 213	93.19 183	98.87 59	81.21 217	97.03 115	96.64 117	96.97 161	93.99 169

HQP-MVS		95.97 132	95.01 146	97.08 108	98.72 80	97.19 139	97.07 152	96.69 149	91.49 153	95.77 130	92.19 192	97.93 113	96.15 105	94.66 164	94.16 166	98.10 111	97.45 83

PLC	92.55 15	96.10 127	95.36 133	96.96 116	98.13 122	96.88 152	96.49 171	96.67 150	94.07 119	95.71 136	91.14 200	96.09 153	96.84 77	96.70 124	96.58 119	97.92 120	96.03 132
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Anonymous20231206		95.69 139	95.68 130	95.70 157	98.32 104	96.95 150	97.37 137	96.65 151	93.33 129	93.61 184	98.70 70	98.03 110	91.04 173	95.07 160	94.59 164	97.20 150	93.09 178

PCF-MVS	92.69 14	95.98 131	95.05 144	97.06 110	98.43 98	97.56 125	97.76 115	96.65 151	89.95 175	95.70 137	96.18 133	98.48 91	95.74 112	93.64 178	93.35 179	98.09 113	96.18 128
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ET-MVSNet_ETH3D		93.18 181	90.80 192	95.95 150	96.05 196	96.07 175	96.92 159	96.51 153	89.34 180	95.63 139	94.08 171	72.31 223	93.13 157	94.33 171	94.83 159	97.44 138	94.65 157

CDS-MVSNet		94.91 153	95.17 140	94.60 181	97.85 139	96.21 172	96.90 161	96.39 154	90.81 163	93.40 188	97.24 108	94.54 166	85.78 209	96.25 136	96.15 130	97.26 147	95.01 153
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		93.89 175	92.82 176	95.14 172	97.62 157	96.97 149	96.12 180	96.36 155	91.30 156	91.53 200	94.68 160	80.72 205	90.80 176	95.71 147	96.29 127	98.44 91	94.09 166

MVS-HIRNet		88.72 207	86.49 209	91.33 207	91.81 219	85.66 219	87.02 222	96.25 156	81.48 220	94.82 160	96.31 130	92.14 180	90.32 181	87.60 209	83.82 207	87.74 214	78.42 218

TinyColmap		96.64 116	96.07 122	97.32 98	97.84 144	96.40 165	97.63 124	96.25 156	95.86 51	98.98 10	97.94 90	96.34 150	96.17 104	97.30 104	95.38 152	97.04 157	93.24 175

abl_6				96.45 140	97.79 150	97.28 135	97.16 150	96.16 158	89.92 176	95.72 135	91.59 197	97.16 136	94.37 141			97.51 135	95.49 148

pmmvs4		95.37 145	94.25 157	96.67 130	97.01 179	95.28 183	97.60 125	96.07 159	93.11 135	97.29 63	98.09 89	94.23 170	95.21 125	91.56 198	93.91 172	96.82 167	93.59 173

OpenMVS	94.63 9	95.75 137	95.04 145	96.58 134	97.85 139	97.55 126	96.71 165	96.07 159	90.15 173	96.47 99	90.77 205	95.95 155	94.41 140	97.01 116	96.95 106	98.00 116	96.90 103

IterMVS-SCA-FT		95.16 149	93.95 161	96.56 136	97.89 137	96.69 158	96.94 157	96.05 161	93.06 138	97.35 60	98.79 62	91.45 182	95.93 110	92.78 188	91.00 192	95.22 185	93.91 170

V42		97.10 96	96.97 95	97.26 100	97.64 154	97.60 121	98.45 82	95.99 162	94.44 108	97.35 60	99.40 27	98.63 81	97.34 61	96.33 135	96.38 126	96.82 167	96.00 133

DPM-MVS		94.86 154	93.90 163	95.99 149	98.19 116	96.52 160	96.29 178	95.95 163	93.11 135	94.61 165	88.17 208	96.44 148	93.77 151	93.33 181	93.54 177	97.11 154	96.22 127

dps		88.36 209	84.32 216	93.07 194	93.86 215	92.29 199	94.89 206	95.93 164	83.50 215	93.13 192	91.87 195	67.79 226	90.32 181	85.99 214	83.22 211	90.28 207	85.56 207

DELS-MVS		96.90 103	97.24 76	96.50 138	97.85 139	98.18 81	97.88 112	95.92 165	93.48 128	95.34 146	98.86 59	98.94 54	94.03 146	97.33 103	97.04 103	98.00 116	96.85 109
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
GA-MVS		94.18 168	92.98 174	95.58 161	97.36 168	96.42 163	96.21 179	95.86 166	90.29 169	95.08 154	96.19 132	85.37 195	92.82 163	94.01 176	94.14 167	96.16 179	94.41 163

CostFormer		89.06 206	85.65 213	93.03 196	95.88 200	92.40 198	95.30 200	95.86 166	86.49 205	93.12 194	93.40 181	74.18 218	88.25 197	82.99 218	81.46 213	89.77 208	88.66 199

EPMVS		89.28 204	86.28 210	92.79 197	96.01 197	92.00 203	95.83 187	95.85 168	90.78 164	91.00 203	94.58 163	74.65 217	88.93 193	85.00 215	82.88 212	89.09 211	84.09 213

TSAR-MVS + COLMAP		96.05 129	95.94 126	96.18 146	97.46 166	96.41 164	97.26 145	95.83 169	94.69 96	95.30 147	98.31 81	96.52 146	94.71 135	95.48 154	94.87 157	96.54 171	95.33 150

test-LLR		89.77 202	87.47 204	92.45 199	98.01 127	89.77 213	93.25 215	95.80 170	81.56 218	89.19 209	92.08 193	79.59 208	85.77 211	91.47 200	89.04 200	92.69 198	88.75 197

test0.0.03 1		91.17 194	91.50 187	90.80 209	98.01 127	95.46 181	94.22 209	95.80 170	86.55 204	81.75 221	90.83 203	87.93 192	78.48 218	94.51 168	94.11 169	96.50 172	91.08 186

RPSCF		97.83 56	98.27 29	97.31 99	98.23 111	98.06 93	97.44 134	95.79 172	96.90 25	95.81 127	98.76 66	98.61 83	97.70 48	98.90 35	98.36 58	98.90 58	98.29 38

OMC-MVS		97.23 92	97.21 77	97.25 103	97.85 139	97.52 128	97.92 107	95.77 173	95.83 53	97.09 73	97.86 92	98.52 87	96.62 85	97.51 97	96.65 116	98.26 99	96.57 117

USDC		96.30 122	95.64 132	97.07 109	97.62 157	96.35 170	97.17 149	95.71 174	95.52 68	99.17 7	98.11 88	97.46 128	95.67 117	95.44 155	93.60 175	97.09 155	92.99 179

MVSTER		91.97 187	90.31 193	93.91 187	96.81 182	96.91 151	94.22 209	95.64 175	84.98 209	92.98 196	93.42 179	72.56 221	86.64 207	95.11 159	93.89 173	97.16 153	95.31 151

CANet_DTU		94.96 152	94.62 153	95.35 165	98.03 125	96.11 173	96.92 159	95.60 176	88.59 186	97.27 64	95.27 147	96.50 147	88.77 195	95.53 151	95.59 146	95.54 183	94.78 154

CHOSEN 1792x2688		94.98 151	94.69 151	95.31 166	97.27 173	95.58 180	97.90 109	95.56 177	95.03 82	93.77 183	95.65 142	99.29 20	95.30 123	91.51 199	91.28 191	92.05 203	94.50 160

MVS_111021_LR		96.86 104	96.72 107	97.03 114	97.80 148	97.06 148	97.04 153	95.51 178	94.55 102	97.47 53	97.35 106	97.68 122	96.66 83	97.11 110	96.73 113	97.69 128	96.57 117

DeepPCF-MVS	94.55 10	97.05 98	97.13 86	96.95 117	96.06 195	97.12 145	98.01 103	95.44 179	95.18 77	97.50 52	97.86 92	98.08 108	97.31 63	97.23 105	97.00 104	97.36 144	97.45 83

MDTV_nov1_ep13		90.30 198	87.32 206	93.78 188	96.00 198	92.97 195	95.46 196	95.39 180	88.61 185	95.41 145	94.45 168	80.39 206	89.87 187	86.58 211	83.54 210	90.56 205	84.71 210

ADS-MVSNet		89.89 200	87.70 201	92.43 200	95.52 206	90.91 209	95.57 190	95.33 181	93.19 132	91.21 202	93.41 180	82.12 202	89.05 191	86.21 212	83.77 208	87.92 213	84.31 211

tpm cat1		87.19 211	82.78 218	92.33 201	95.66 203	90.61 210	94.19 211	95.27 182	86.97 199	94.38 169	90.91 202	69.40 225	87.21 202	79.57 221	77.82 217	87.25 216	84.18 212

PatchMatch-RL		94.79 159	93.75 165	96.00 148	96.80 183	95.00 185	95.47 195	95.25 183	90.68 165	95.80 128	92.97 184	93.64 172	95.67 117	96.13 140	95.81 142	96.99 160	92.01 182

diffmvs		95.86 134	96.21 118	95.44 164	97.25 174	96.85 155	96.99 155	95.23 184	94.96 87	92.82 197	98.89 54	98.85 60	93.52 154	94.21 173	94.25 165	96.84 164	95.49 148

thres100view900		92.93 182	90.89 191	95.31 166	97.52 161	96.82 157	96.41 172	95.08 185	87.65 194	93.56 186	83.03 216	84.12 197	91.12 172	94.53 165	96.91 108	98.17 106	93.21 176

baseline2		92.06 186	89.82 195	94.68 180	97.32 169	95.72 178	94.97 205	95.08 185	84.75 211	94.34 172	90.68 206	77.75 213	90.13 183	93.38 179	93.58 176	96.25 178	92.90 180

PVSNet_BlendedMVS		95.44 143	95.09 141	95.86 153	97.31 171	97.13 143	96.31 176	95.01 187	88.55 187	96.23 110	94.55 166	97.75 117	92.56 166	96.42 130	95.44 150	97.71 125	95.81 138

PVSNet_Blended		95.44 143	95.09 141	95.86 153	97.31 171	97.13 143	96.31 176	95.01 187	88.55 187	96.23 110	94.55 166	97.75 117	92.56 166	96.42 130	95.44 150	97.71 125	95.81 138

pmmvs5		95.70 138	95.22 138	96.26 144	96.55 190	97.24 136	97.50 130	94.99 189	90.95 162	96.87 81	98.47 77	97.40 129	94.45 138	92.86 187	94.98 156	97.23 149	94.64 158

CNLPA		96.24 125	95.97 125	96.57 135	97.48 165	97.10 147	96.75 163	94.95 190	94.92 89	96.20 113	94.81 158	96.61 145	96.25 98	96.94 118	95.64 145	97.79 123	95.74 143

MDA-MVSNet-bldmvs		95.45 142	95.20 139	95.74 156	94.24 213	96.38 168	97.93 106	94.80 191	95.56 66	96.87 81	98.29 82	95.24 161	96.50 93	98.65 50	90.38 194	94.09 189	91.93 183

FMVSNet5		89.65 203	87.60 203	92.04 202	95.63 205	96.61 159	94.82 207	94.75 192	80.11 222	87.72 216	77.73 221	73.81 219	83.81 215	95.64 148	96.08 135	95.49 184	93.21 176

tpmrst		87.60 210	84.13 217	91.66 205	95.65 204	89.73 215	93.77 212	94.74 193	88.85 182	93.35 191	95.60 143	72.37 222	87.40 201	81.24 219	78.19 216	85.02 220	82.90 217

IterMVS		94.48 161	93.46 168	95.66 158	97.52 161	96.43 162	97.20 147	94.73 194	92.91 141	96.44 100	98.75 67	91.10 184	94.53 137	92.10 194	90.10 196	93.51 192	92.84 181
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IB-MVS	92.44 16	93.33 180	92.15 183	94.70 178	97.42 167	96.39 167	95.57 190	94.67 195	86.40 206	93.59 185	78.28 220	95.76 158	89.59 189	95.88 145	95.98 137	97.39 142	96.34 124
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
PM-MVS		96.85 105	96.62 110	97.11 107	97.13 176	96.51 161	98.29 87	94.65 196	94.84 91	98.12 30	98.59 72	97.20 134	97.41 57	96.24 137	96.41 124	97.09 155	96.56 119

CHOSEN 280x420		91.55 191	90.27 194	93.05 195	94.61 211	88.01 218	96.56 169	94.62 197	88.04 193	94.20 173	92.66 187	86.60 193	90.82 175	95.06 161	91.89 187	87.49 215	89.61 194

TAPA-MVS	93.96 13	96.79 109	96.70 108	96.90 121	97.64 154	97.58 122	97.54 128	94.50 198	95.14 78	96.64 92	96.76 118	97.90 114	96.63 84	95.98 143	96.14 131	98.45 88	97.39 86
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MSDG		96.27 124	96.17 120	96.38 143	97.85 139	96.27 171	96.55 170	94.41 199	94.55 102	95.62 140	97.56 100	97.80 116	96.22 100	97.17 109	96.27 128	97.67 130	93.60 172

new-patchmatchnet		94.48 161	94.02 159	95.02 175	97.51 164	95.00 185	95.68 189	94.26 200	97.32 20	95.73 134	99.60 13	98.22 105	91.30 169	94.13 174	84.41 204	95.65 182	89.45 195

MS-PatchMatch		94.84 155	94.76 150	94.94 176	96.38 191	94.69 188	95.90 185	94.03 201	92.49 142	93.81 181	95.79 141	96.38 149	94.54 136	94.70 163	94.85 158	94.97 187	94.43 162

N_pmnet		92.46 183	92.38 180	92.55 198	97.91 136	93.47 192	97.42 135	94.01 202	96.40 35	88.48 214	98.50 75	98.07 109	88.14 198	91.04 202	84.30 205	89.35 210	84.85 209

pmnet_mix02		93.59 178	92.65 177	94.69 179	96.76 187	94.16 190	97.03 154	93.00 203	95.79 54	96.03 121	98.91 52	97.69 121	92.99 159	90.03 206	84.10 206	92.35 201	87.89 202

baseline		94.07 170	94.50 155	93.57 190	96.34 192	93.40 193	95.56 193	92.39 204	92.07 149	94.00 178	98.24 85	97.51 127	89.19 190	91.75 196	92.72 183	93.96 191	95.79 140

CLD-MVS		96.73 112	96.92 96	96.51 137	98.70 82	97.57 124	97.64 122	92.07 205	93.10 137	96.31 109	98.29 82	99.02 44	95.99 109	97.20 107	96.47 122	98.37 95	96.81 110
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
FPMVS		94.70 160	94.99 147	94.37 183	95.84 201	93.20 194	96.00 184	91.93 206	95.03 82	94.64 164	94.68 160	93.29 173	90.95 174	98.07 76	97.34 96	96.85 162	93.29 174

EU-MVSNet		96.03 130	96.23 116	95.80 155	95.48 208	94.18 189	98.99 37	91.51 207	97.22 21	97.66 45	99.15 41	98.51 89	98.08 31	95.92 144	92.88 182	93.09 195	95.72 144

TAMVS		92.46 183	93.34 169	91.44 206	97.03 178	93.84 191	94.68 208	90.60 208	90.44 168	85.31 219	97.14 112	93.03 175	85.78 209	94.34 170	93.67 174	95.22 185	90.93 187

MVE	72.99 18	85.37 215	89.43 196	80.63 215	74.43 223	71.94 224	88.25 221	89.81 209	93.27 130	67.32 224	96.32 129	91.83 181	90.40 180	93.36 180	90.79 193	73.55 223	88.49 200
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CVMVSNet		94.01 173	94.25 157	93.73 189	94.36 212	92.44 197	97.45 133	88.56 210	95.59 61	93.06 195	98.88 55	90.03 190	94.84 132	94.08 175	93.45 178	94.09 189	95.31 151

CMPMVS	71.81 19	92.34 185	92.85 175	91.75 204	92.70 217	90.43 211	88.84 220	88.56 210	85.87 207	94.35 170	90.98 201	95.89 157	91.14 171	96.14 139	94.83 159	94.93 188	95.78 141
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
E-PMN		86.94 212	85.10 214	89.09 214	95.77 202	83.54 222	89.89 219	86.55 212	92.18 147	87.34 217	94.02 172	83.42 200	89.63 188	93.32 182	77.11 218	85.33 218	72.09 219

PMMVS2		86.47 214	92.62 178	79.29 216	92.01 218	85.63 220	93.74 213	86.37 213	93.95 122	54.18 226	98.19 86	97.39 130	58.46 219	96.57 127	93.07 180	90.99 204	83.55 216

EMVS		86.63 213	84.48 215	89.15 213	95.51 207	83.66 221	90.19 218	86.14 214	91.78 151	88.68 212	93.83 176	81.97 204	89.05 191	92.76 189	76.09 219	85.31 219	71.28 220

PMMVS		91.67 190	91.47 188	91.91 203	89.43 222	88.61 217	94.99 204	85.67 215	87.50 196	93.80 182	94.42 169	94.88 163	90.71 177	92.26 193	92.96 181	96.83 165	89.65 193

test-mter		89.16 205	88.14 199	90.37 210	94.79 210	91.05 208	93.60 214	85.26 216	81.65 217	88.32 215	92.22 191	79.35 210	87.03 204	92.28 191	90.12 195	93.19 194	90.29 191

TESTMET0.1,1		88.60 208	87.47 204	89.93 211	94.23 214	89.77 213	93.25 215	84.47 217	81.56 218	89.19 209	92.08 193	79.59 208	85.77 211	91.47 200	89.04 200	92.69 198	88.75 197

new_pmnet		90.85 196	92.26 182	89.21 212	93.68 216	89.05 216	93.20 217	84.16 218	92.99 139	84.25 220	97.72 95	94.60 165	86.80 206	93.20 184	91.30 190	93.21 193	86.94 205

pmmvs3		91.20 193	91.40 190	90.96 208	91.71 220	91.08 207	95.41 199	81.34 219	87.36 197	94.57 166	95.02 151	94.30 169	90.42 179	94.28 172	89.26 198	92.30 202	88.49 200

DeepMVS_CX						72.99 223	80.14 223	37.34 220	83.46 216	60.13 225	84.40 212	85.48 194	86.93 205	87.22 210		79.61 221	87.32 204

test_method		61.30 216	70.45 219	50.62 217	22.69 225	30.92 226	68.31 225	25.76 221	80.56 221	68.71 222	82.80 218	91.08 185	44.64 220	80.50 220	56.70 220	73.64 222	70.58 221

tmp_tt				45.72 218	60.00 224	38.74 225	45.50 226	12.18 222	79.58 223	68.42 223	67.62 222	65.04 227	22.12 221	84.83 216	78.72 215	66.08 224

testmvs		4.99 218	6.88 220	2.78 221	1.73 226	2.04 228	3.10 228	1.71 223	7.27 224	3.92 229	12.18 223	6.71 230	3.31 223	6.94 222	5.51 222	2.94 225	7.51 222

test123		4.41 219	5.71 221	2.88 220	1.28 227	2.21 227	3.09 229	1.65 224	6.35 225	4.98 228	8.53 224	3.88 231	3.46 222	5.79 223	5.71 221	2.85 226	7.50 223

GG-mvs-BLEND		61.03 217	87.02 207	30.71 219	0.74 228	90.01 212	78.90 224	0.74 225	84.56 212	9.46 227	79.17 219	90.69 188	1.37 224	91.74 197	89.13 199	93.04 196	83.83 215

uanet_test		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

RE-MVS-def										99.38 2

9.14												96.98 141

our_test_3					97.32 169	95.13 184	97.59 126

ambc			96.78 105		99.01 59	97.11 146	95.73 188		95.91 50	99.25 3	98.56 74	97.17 135	97.04 71	96.76 122	95.22 154	96.72 169	96.73 113

MTAPA										97.43 56		99.27 24

MTMP										97.63 47		99.03 43

Patchmatch-RL test							17.42 227

XVS					99.48 19	98.76 45	99.22 23			96.40 104		98.78 69				98.94 55

X-MVStestdata					99.48 19	98.76 45	99.22 23			96.40 104		98.78 69				98.94 55

mPP-MVS					99.58 6							98.98 47

NP-MVS									89.27 181

High-resolution multi-view benchmark