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.

DELS-MVS		98.19 48	98.77 56	97.52 50	98.29 60	99.71 8	99.12 40	94.58 62	98.80 99	95.38 47	96.24 114	98.24 70	97.92 93	99.06 37	99.52 1	99.82 10	99.79 38
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
DeepC-MVS	97.63 4	98.33 45	98.57 59	98.04 41	98.62 56	99.65 16	99.45 24	98.15 23	99.51 16	92.80 93	95.74 124	96.44 88	99.46 21	99.37 18	99.50 2	99.78 28	99.81 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	96.92 7	98.67 36	99.05 41	98.23 37	99.57 26	99.45 60	99.11 41	94.66 58	99.69 3	96.80 32	96.55 109	99.61 51	99.40 25	98.87 51	99.49 3	99.85 3	99.66 100

MSLP-MVS++		99.15 17	99.24 30	99.04 14	99.52 31	99.49 55	99.09 43	98.07 29	99.37 24	98.47 8	97.79 76	99.89 33	99.50 17	98.93 44	99.45 4	99.61 115	99.76 55

IS_MVSNet		97.86 57	98.86 52	96.68 73	96.02 98	99.72 5	98.35 74	93.37 84	98.75 108	94.01 71	96.88 98	98.40 67	98.48 78	99.09 34	99.42 5	99.83 8	99.80 30

Vis-MVSNet (Re-imp)		97.40 73	98.89 51	95.66 99	95.99 101	99.62 28	97.82 92	93.22 87	98.82 96	91.40 107	96.94 95	98.56 65	95.70 150	99.14 32	99.41 6	99.79 25	99.75 62

PHI-MVS		99.08 21	99.43 17	98.67 28	99.15 45	99.59 40	99.11 41	97.35 39	99.14 54	97.30 26	99.44 10	99.96 11	99.32 30	98.89 49	99.39 7	99.79 25	99.58 114

APD-MVS		99.25 11	99.38 19	99.09 10	99.69 8	99.58 43	99.56 16	98.32 6	98.85 89	97.87 19	98.91 38	99.92 27	99.30 33	99.45 14	99.38 8	99.79 25	99.58 114
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepPCF-MVS	97.74 3	98.34 44	99.46 11	97.04 62	98.82 51	99.33 81	96.28 137	97.47 38	99.58 8	94.70 58	98.99 32	99.85 39	97.24 111	99.55 9	99.34 9	97.73 194	99.56 120

DeepC-MVS_fast	98.34 1	99.17 16	99.45 12	98.85 24	99.55 28	99.37 72	99.64 8	98.05 31	99.53 13	96.58 34	98.93 36	99.92 27	99.49 19	99.46 13	99.32 10	99.80 24	99.64 107
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SMA-MVS		99.38 4	99.60 2	99.12 8	99.76 2	99.62 28	99.39 28	98.23 18	99.52 15	98.03 16	99.45 9	99.98 1	99.64 5	99.58 7	99.30 11	99.68 87	99.76 55

3Dnovator+	96.92 7	98.71 35	99.05 41	98.32 33	99.53 29	99.34 78	99.06 45	94.61 59	99.65 4	97.49 23	96.75 99	99.86 36	99.44 23	98.78 56	99.30 11	99.81 16	99.67 96

QAPM		98.62 39	99.04 44	98.13 38	99.57 26	99.48 56	99.17 37	94.78 55	99.57 9	96.16 37	96.73 100	99.80 42	99.33 29	98.79 55	99.29 13	99.75 39	99.64 107

APDe-MVS		99.49 1	99.64 1	99.32 2	99.74 4	99.74 4	99.75 1	98.34 3	99.56 10	98.72 6	99.57 5	99.97 6	99.53 16	99.65 2	99.25 14	99.84 5	99.77 51

ACMMPR		99.30 8	99.54 5	99.03 15	99.66 15	99.64 21	99.68 4	98.25 13	99.56 10	97.12 29	99.19 18	99.95 16	99.72 1	99.43 15	99.25 14	99.72 57	99.77 51

HFP-MVS		99.32 6	99.53 7	99.07 12	99.69 8	99.59 40	99.63 11	98.31 7	99.56 10	97.37 25	99.27 15	99.97 6	99.70 3	99.35 20	99.24 16	99.71 67	99.76 55

UA-Net		97.13 79	99.14 34	94.78 107	97.21 78	99.38 70	97.56 100	92.04 97	98.48 121	88.03 122	98.39 61	99.91 30	94.03 180	99.33 22	99.23 17	99.81 16	99.25 151

LS3D		97.79 58	98.25 69	97.26 56	98.40 58	99.63 24	99.53 17	98.63 1	99.25 41	88.13 121	96.93 96	94.14 118	99.19 37	99.14 32	99.23 17	99.69 78	99.42 139

X-MVS		98.93 28	99.37 20	98.42 31	99.67 12	99.62 28	99.60 14	98.15 23	99.08 64	93.81 77	98.46 58	99.95 16	99.59 10	99.49 12	99.21 19	99.68 87	99.75 62

PGM-MVS		98.86 30	99.35 24	98.29 34	99.77 1	99.63 24	99.67 5	95.63 45	98.66 111	95.27 48	99.11 24	99.82 41	99.67 4	99.33 22	99.19 20	99.73 51	99.74 66

SteuartSystems-ACMMP		99.20 14	99.51 9	98.83 26	99.66 15	99.66 14	99.71 3	98.12 27	99.14 54	96.62 33	99.16 20	99.98 1	99.12 44	99.63 3	99.19 20	99.78 28	99.83 22
Skip Steuart: Steuart Systems R&D Blog.
TSAR-MVS + MP.		99.27 9	99.57 3	98.92 22	98.78 53	99.53 49	99.72 2	98.11 28	99.73 2	97.43 24	99.15 21	99.96 11	99.59 10	99.73 1	99.07 22	99.88 1	99.82 23
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		99.25 11	99.50 10	98.96 20	98.79 52	99.55 47	99.33 31	98.29 10	99.75 1	97.96 18	99.15 21	99.95 16	99.61 6	99.17 30	99.06 23	99.81 16	99.84 18
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
MSP-MVS		99.45 2	99.54 5	99.35 1	99.72 7	99.76 1	99.63 11	98.37 2	99.63 6	99.03 2	98.95 35	99.98 1	99.60 7	99.60 5	99.05 24	99.74 44	99.79 38

DVP-MVS		99.34 5	99.52 8	99.14 7	99.68 11	99.75 3	99.64 8	98.31 7	99.44 19	98.10 13	99.28 14	99.98 1	99.30 33	99.34 21	99.05 24	99.81 16	99.79 38

canonicalmvs		97.31 74	97.81 90	96.72 72	96.20 97	99.45 60	98.21 80	91.60 106	99.22 43	95.39 46	98.48 56	90.95 135	99.16 42	97.66 126	99.05 24	99.76 35	99.90 3

OpenMVS	96.23 11	97.95 56	98.45 64	97.35 51	99.52 31	99.42 65	98.91 52	94.61 59	98.87 86	92.24 102	94.61 135	99.05 60	99.10 46	98.64 66	99.05 24	99.74 44	99.51 131

Vis-MVSNet		96.16 108	98.22 73	93.75 122	95.33 127	99.70 10	97.27 109	90.85 120	98.30 128	85.51 139	95.72 126	96.45 86	93.69 186	98.70 63	99.00 28	99.84 5	99.69 90
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CANet		98.46 41	99.16 33	97.64 48	98.48 57	99.64 21	99.35 30	94.71 57	99.53 13	95.17 50	97.63 82	99.59 52	98.38 80	98.88 50	98.99 29	99.74 44	99.86 15

CDPH-MVS		98.41 42	99.10 37	97.61 49	99.32 42	99.36 73	99.49 20	96.15 44	98.82 96	91.82 104	98.41 59	99.66 50	99.10 46	98.93 44	98.97 30	99.75 39	99.58 114

DPE-MVS		99.39 3	99.55 4	99.20 3	99.63 20	99.71 8	99.66 6	98.33 5	99.29 33	98.40 11	99.64 4	99.98 1	99.31 31	99.56 8	98.96 31	99.85 3	99.70 86

TSAR-MVS + ACMM		98.77 32	99.45 12	97.98 43	99.37 36	99.46 58	99.44 26	98.13 26	99.65 4	92.30 100	98.91 38	99.95 16	99.05 49	99.42 16	98.95 32	99.58 133	99.82 23

EPP-MVSNet		97.75 61	98.71 57	96.63 77	95.68 113	99.56 46	97.51 101	93.10 91	99.22 43	94.99 54	97.18 91	97.30 80	98.65 70	98.83 52	98.93 33	99.84 5	99.92 1

CHOSEN 280x420		97.99 55	99.24 30	96.53 79	98.34 59	99.61 33	98.36 73	89.80 137	99.27 36	95.08 52	99.81 1	98.58 64	98.64 71	99.02 39	98.92 34	98.93 180	99.48 135

CSCG		98.90 29	98.93 50	98.85 24	99.75 3	99.72 5	99.49 20	96.58 42	99.38 22	98.05 15	98.97 33	97.87 73	99.49 19	97.78 119	98.92 34	99.78 28	99.90 3

CHOSEN 1792x2688		96.41 101	96.99 118	95.74 97	98.01 65	99.72 5	97.70 98	90.78 123	99.13 59	90.03 114	87.35 187	95.36 102	98.33 81	98.59 73	98.91 36	99.59 129	99.87 12

MVS_111021_LR		98.67 36	99.41 18	97.81 46	99.37 36	99.53 49	98.51 65	95.52 47	99.27 36	94.85 55	99.56 6	99.69 49	99.04 50	99.36 19	98.88 37	99.60 123	99.58 114

MVS_0304		98.14 50	99.03 45	97.10 59	98.05 64	99.63 24	99.27 33	94.33 64	99.63 6	93.06 89	97.32 85	99.05 60	98.09 87	98.82 53	98.87 38	99.81 16	99.89 6

CP-MVS		99.27 9	99.44 15	99.08 11	99.62 22	99.58 43	99.53 17	98.16 21	99.21 45	97.79 20	99.15 21	99.96 11	99.59 10	99.54 10	98.86 39	99.78 28	99.74 66

MAR-MVS		97.71 62	98.04 81	97.32 52	99.35 40	98.91 106	97.65 99	91.68 104	98.00 140	97.01 30	97.72 80	94.83 108	98.85 64	98.44 82	98.86 39	99.41 162	99.52 127
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
xxxxxxxxxxxxxcwj		98.14 50	97.38 104	99.03 15	99.65 17	99.41 67	98.87 53	98.24 16	99.14 54	98.73 4	99.11 24	86.38 159	98.92 57	99.22 26	98.84 41	99.76 35	99.56 120

SF-MVS		99.18 15	99.32 25	99.03 15	99.65 17	99.41 67	98.87 53	98.24 16	99.14 54	98.73 4	99.11 24	99.92 27	98.92 57	99.22 26	98.84 41	99.76 35	99.56 120

MVS_111021_HR		98.59 40	99.36 21	97.68 47	99.42 34	99.61 33	98.14 83	94.81 54	99.31 30	95.00 53	99.51 7	99.79 44	99.00 53	98.94 43	98.83 43	99.69 78	99.57 119

CNLPA		99.03 26	99.05 41	99.01 19	99.27 43	99.22 91	99.03 47	97.98 32	99.34 28	99.00 3	98.25 65	99.71 48	99.31 31	98.80 54	98.82 44	99.48 152	99.17 155

FMVSNet2		96.64 97	97.50 96	95.63 100	93.81 146	97.98 155	98.09 85	90.87 119	98.99 76	93.48 83	93.17 151	95.25 103	97.89 94	98.63 67	98.80 45	99.68 87	99.67 96

MP-MVS		99.07 22	99.36 21	98.74 27	99.63 20	99.57 45	99.66 6	98.25 13	99.00 75	95.62 42	98.97 33	99.94 24	99.54 15	99.51 11	98.79 46	99.71 67	99.73 70
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CS-MVS		98.06 52	99.12 35	96.82 71	95.83 106	99.66 14	98.93 51	93.12 90	98.95 78	94.29 68	98.55 53	99.05 60	98.94 55	99.05 38	98.78 47	99.83 8	99.80 30

ETV-MVS		98.05 53	99.25 29	96.65 75	95.61 115	99.61 33	98.26 79	93.52 80	98.90 85	93.74 80	99.32 13	99.20 57	98.90 60	99.21 28	98.72 48	99.87 2	99.79 38

TSAR-MVS + GP.		98.66 38	99.36 21	97.85 45	97.16 80	99.46 58	99.03 47	94.59 61	99.09 62	97.19 28	99.73 3	99.95 16	99.39 26	98.95 42	98.69 49	99.75 39	99.65 103

ACMMP_NAP		99.05 24	99.45 12	98.58 30	99.73 5	99.60 38	99.64 8	98.28 11	99.23 42	94.57 59	99.35 12	99.97 6	99.55 14	99.63 3	98.66 50	99.70 76	99.74 66

OMC-MVS		98.84 31	99.01 47	98.65 29	99.39 35	99.23 90	99.22 34	96.70 41	99.40 21	97.77 21	97.89 75	99.80 42	99.21 35	99.02 39	98.65 51	99.57 137	99.07 162

FMVSNet3		97.02 82	98.12 78	95.73 98	93.59 152	97.98 155	98.34 75	91.32 113	98.80 99	93.92 73	97.21 88	95.94 98	97.63 103	98.61 69	98.62 52	99.61 115	99.65 103

CNVR-MVS		99.23 13	99.28 27	99.17 4	99.65 17	99.34 78	99.46 23	98.21 19	99.28 34	98.47 8	98.89 40	99.94 24	99.50 17	99.42 16	98.61 53	99.73 51	99.52 127

baseline		97.45 71	98.70 58	95.99 93	95.89 103	99.36 73	98.29 76	91.37 112	99.21 45	92.99 91	98.40 60	96.87 85	97.96 92	98.60 71	98.60 54	99.42 161	99.86 15

zzz-MVS		99.31 7	99.44 15	99.16 5	99.73 5	99.65 16	99.63 11	98.26 12	99.27 36	98.01 17	99.27 15	99.97 6	99.60 7	99.59 6	98.58 55	99.71 67	99.73 70

MVS_Test		97.30 75	98.54 60	95.87 94	95.74 109	99.28 85	98.19 81	91.40 111	99.18 49	91.59 106	98.17 67	96.18 93	98.63 72	98.61 69	98.55 56	99.66 100	99.78 44

EPNet		98.05 53	98.86 52	97.10 59	99.02 48	99.43 64	98.47 66	94.73 56	99.05 70	95.62 42	98.93 36	97.62 77	95.48 158	98.59 73	98.55 56	99.29 171	99.84 18
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CVMVSNet		95.33 124	97.09 114	93.27 137	95.23 128	98.39 144	95.49 150	92.58 94	97.71 155	83.00 154	94.44 138	93.28 125	93.92 183	97.79 118	98.54 58	99.41 162	99.45 137

casdiffmvs		96.93 85	97.43 102	96.34 84	95.70 111	99.50 54	97.75 96	93.22 87	98.98 77	92.64 94	94.97 131	91.71 133	98.93 56	98.62 68	98.52 59	99.82 10	99.72 81

PVSNet_Blended_VisFu		97.41 72	98.49 63	96.15 87	97.49 70	99.76 1	96.02 141	93.75 76	99.26 39	93.38 85	93.73 143	99.35 55	96.47 133	98.96 41	98.46 60	99.77 33	99.90 3

DCV-MVSNet		97.56 67	98.36 66	96.62 78	96.44 88	98.36 146	98.37 71	91.73 103	99.11 60	94.80 56	98.36 62	96.28 91	98.60 74	98.12 94	98.44 61	99.76 35	99.87 12

baseline1		97.58 66	98.05 80	97.02 65	96.21 96	99.45 60	97.71 97	93.71 78	98.47 122	95.75 41	98.78 44	93.20 127	98.91 59	98.52 77	98.44 61	99.81 16	99.53 124

NCCC		99.05 24	99.08 38	99.02 18	99.62 22	99.38 70	99.43 27	98.21 19	99.36 26	97.66 22	97.79 76	99.90 31	99.45 22	99.17 30	98.43 63	99.77 33	99.51 131

PVSNet_BlendedMVS		97.51 69	97.71 91	97.28 54	98.06 62	99.61 33	97.31 107	95.02 51	99.08 64	95.51 44	98.05 69	90.11 138	98.07 88	98.91 47	98.40 64	99.72 57	99.78 44

PVSNet_Blended		97.51 69	97.71 91	97.28 54	98.06 62	99.61 33	97.31 107	95.02 51	99.08 64	95.51 44	98.05 69	90.11 138	98.07 88	98.91 47	98.40 64	99.72 57	99.78 44

train_agg		98.73 34	99.11 36	98.28 35	99.36 38	99.35 76	99.48 22	97.96 33	98.83 94	93.86 76	98.70 50	99.86 36	99.44 23	99.08 36	98.38 66	99.61 115	99.58 114

CDS-MVSNet		96.59 100	98.02 83	94.92 106	94.45 139	98.96 104	97.46 103	91.75 102	97.86 149	90.07 113	96.02 117	97.25 81	96.21 137	98.04 105	98.38 66	99.60 123	99.65 103
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HPM-MVS++		99.10 20	99.30 26	98.86 23	99.69 8	99.48 56	99.59 15	98.34 3	99.26 39	96.55 36	99.10 27	99.96 11	99.36 27	99.25 25	98.37 68	99.64 108	99.66 100

MCST-MVS		99.11 19	99.27 28	98.93 21	99.67 12	99.33 81	99.51 19	98.31 7	99.28 34	96.57 35	99.10 27	99.90 31	99.71 2	99.19 29	98.35 69	99.82 10	99.71 84

MSDG		98.27 47	98.29 68	98.24 36	99.20 44	99.22 91	99.20 35	97.82 35	99.37 24	94.43 64	95.90 120	97.31 79	99.12 44	98.76 58	98.35 69	99.67 95	99.14 159

test0.0.03 1		96.69 94	98.12 78	95.01 105	95.49 122	98.99 101	95.86 143	90.82 121	98.38 125	92.54 98	96.66 103	97.33 78	95.75 148	97.75 122	98.34 71	99.60 123	99.40 143

GBi-Net		96.98 83	98.00 84	95.78 95	93.81 146	97.98 155	98.09 85	91.32 113	98.80 99	93.92 73	97.21 88	95.94 98	97.89 94	98.07 100	98.34 71	99.68 87	99.67 96

test1		96.98 83	98.00 84	95.78 95	93.81 146	97.98 155	98.09 85	91.32 113	98.80 99	93.92 73	97.21 88	95.94 98	97.89 94	98.07 100	98.34 71	99.68 87	99.67 96

FMVSNet1		95.77 114	96.41 138	95.03 104	93.42 153	97.86 162	97.11 118	89.89 134	98.53 118	92.00 103	89.17 172	93.23 126	98.15 85	98.07 100	98.34 71	99.61 115	99.69 90

EIA-MVS		97.70 63	98.78 55	96.44 83	95.72 110	99.65 16	98.14 83	93.72 77	98.30 128	92.31 99	98.63 51	97.90 72	98.97 54	98.92 46	98.30 75	99.78 28	99.80 30

UGNet		97.66 64	99.07 40	96.01 92	97.19 79	99.65 16	97.09 119	93.39 82	99.35 27	94.40 66	98.79 43	99.59 52	94.24 177	98.04 105	98.29 76	99.73 51	99.80 30
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
IterMVS-LS		96.12 109	97.48 98	94.53 110	95.19 129	97.56 179	97.15 115	89.19 144	99.08 64	88.23 120	94.97 131	94.73 110	97.84 99	97.86 116	98.26 77	99.60 123	99.88 10
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous202405211			97.40 103		96.45 87	99.54 48	98.08 88	93.79 73	98.24 132		93.55 144	94.41 114	98.88 63	98.04 105	98.24 78	99.75 39	99.76 55

EPNet_dtu		96.30 104	98.53 61	93.70 125	98.97 49	98.24 150	97.36 105	94.23 66	98.85 89	79.18 176	99.19 18	98.47 66	94.09 179	97.89 114	98.21 79	98.39 186	98.85 171
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CPTT-MVS		99.14 18	99.20 32	99.06 13	99.58 25	99.53 49	99.45 24	97.80 36	99.19 48	98.32 12	98.58 52	99.95 16	99.60 7	99.28 24	98.20 80	99.64 108	99.69 90

HyFIR lowres test		95.99 111	96.56 126	95.32 102	97.99 66	99.65 16	96.54 130	88.86 146	98.44 123	89.77 117	84.14 196	97.05 83	99.03 51	98.55 75	98.19 81	99.73 51	99.86 15

diffmvs		96.83 87	97.33 107	96.25 85	95.76 108	99.34 78	98.06 89	93.22 87	99.43 20	92.30 100	96.90 97	89.83 142	98.55 75	98.00 108	98.14 82	99.64 108	99.70 86

TAPA-MVS	97.53 5	98.41 42	98.84 54	97.91 44	99.08 47	99.33 81	99.15 38	97.13 40	99.34 28	93.20 86	97.75 78	99.19 58	99.20 36	98.66 64	98.13 83	99.66 100	99.48 135
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	97.93 2	99.02 27	98.94 49	99.11 9	99.46 33	99.24 89	99.06 45	97.96 33	99.31 30	99.16 1	97.90 74	99.79 44	99.36 27	98.71 62	98.12 84	99.65 104	99.52 127
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
DPM-MVS		98.31 46	98.53 61	98.05 40	98.76 54	98.77 113	99.13 39	98.07 29	99.10 61	94.27 70	96.70 101	99.84 40	98.70 67	97.90 113	98.11 85	99.40 164	99.28 148

Anonymous20231211		97.10 80	97.06 116	97.14 58	96.32 90	99.52 52	98.16 82	93.76 74	98.84 93	95.98 39	90.92 160	94.58 113	98.90 60	97.72 124	98.10 86	99.71 67	99.75 62

gg-mvs-nofinetune		90.85 187	94.14 166	87.02 193	94.89 134	99.25 87	98.64 61	76.29 207	88.24 207	57.50 210	79.93 202	95.45 101	95.18 167	98.77 57	98.07 87	99.62 113	99.24 152

CANet_DTU		96.64 97	99.08 38	93.81 121	97.10 81	99.42 65	98.85 55	90.01 131	99.31 30	79.98 172	99.78 2	99.10 59	97.42 108	98.35 84	98.05 88	99.47 154	99.53 124

Fast-Effi-MVS+		95.38 122	96.52 129	94.05 118	94.15 141	99.14 96	97.24 111	86.79 165	98.53 118	87.62 126	94.51 136	87.06 148	98.76 65	98.60 71	98.04 89	99.72 57	99.77 51

GG-mvs-BLEND		69.11 203	98.13 77	35.26 208	3.49 217	98.20 152	94.89 161	2.38 214	98.42 124	5.82 217	96.37 112	98.60 63	5.97 213	98.75 60	97.98 90	99.01 179	98.61 173

Effi-MVS+		95.81 113	97.31 111	94.06 117	95.09 130	99.35 76	97.24 111	88.22 155	98.54 117	85.38 140	98.52 54	88.68 143	98.70 67	98.32 85	97.93 91	99.74 44	99.84 18

MIMVSNet		94.49 142	97.59 95	90.87 176	91.74 176	98.70 122	94.68 170	78.73 201	97.98 141	83.71 148	97.71 81	94.81 109	96.96 117	97.97 109	97.92 92	99.40 164	98.04 184

DI_MVS_plusplus_trai		96.90 86	97.49 97	96.21 86	95.61 115	99.40 69	98.72 60	92.11 95	99.14 54	92.98 92	93.08 154	95.14 104	98.13 86	98.05 104	97.91 93	99.74 44	99.73 70

testgi		95.67 116	97.48 98	93.56 128	95.07 131	99.00 99	95.33 154	88.47 152	98.80 99	86.90 130	97.30 86	92.33 129	95.97 145	97.66 126	97.91 93	99.60 123	99.38 144

thres100view900		96.72 92	96.47 133	97.00 68	96.31 91	99.52 52	98.28 77	94.01 68	97.35 159	94.52 60	95.90 120	86.93 151	99.09 48	98.07 100	97.87 95	99.81 16	99.63 109

COLMAP_ROB	96.15 12	97.78 59	98.17 75	97.32 52	98.84 50	99.45 60	99.28 32	95.43 48	99.48 17	91.80 105	94.83 134	98.36 68	98.90 60	98.09 97	97.85 96	99.68 87	99.15 156
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AdaColmap		99.06 23	98.98 48	99.15 6	99.60 24	99.30 84	99.38 29	98.16 21	99.02 73	98.55 7	98.71 49	99.57 54	99.58 13	99.09 34	97.84 97	99.64 108	99.36 145

thres200		96.76 89	96.53 128	97.03 63	96.31 91	99.67 11	98.37 71	93.99 70	97.68 156	94.49 62	95.83 123	86.77 153	99.18 39	98.26 87	97.82 98	99.82 10	99.66 100

tfpn200view9		96.75 90	96.51 130	97.03 63	96.31 91	99.67 11	98.41 68	93.99 70	97.35 159	94.52 60	95.90 120	86.93 151	99.14 43	98.26 87	97.80 99	99.82 10	99.70 86

thres400		96.71 93	96.45 135	97.02 65	96.28 94	99.63 24	98.41 68	94.00 69	97.82 151	94.42 65	95.74 124	86.26 160	99.18 39	98.20 91	97.79 100	99.81 16	99.70 86

FC-MVSNet-train		97.04 81	97.91 87	96.03 91	96.00 100	98.41 142	96.53 132	93.42 81	99.04 72	93.02 90	98.03 71	94.32 116	97.47 107	97.93 111	97.77 101	99.75 39	99.88 10

baseline2		96.36 103	97.82 89	94.65 109	94.60 138	99.09 97	96.45 134	89.63 139	98.36 126	91.29 109	97.60 83	94.13 119	96.37 134	98.45 80	97.70 102	99.54 146	99.41 140

IterMVS-SCA-FT		94.89 131	97.87 88	91.42 164	94.86 135	97.70 166	97.24 111	84.88 179	98.93 82	75.74 188	94.26 139	98.25 69	96.69 124	98.52 77	97.68 103	99.10 178	99.73 70

thres600view7		96.69 94	96.43 137	97.00 68	96.28 94	99.67 11	98.41 68	93.99 70	97.85 150	94.29 68	95.96 118	85.91 163	99.19 37	98.26 87	97.63 104	99.82 10	99.73 70

PMMVS		97.52 68	98.39 65	96.51 81	95.82 107	98.73 120	97.80 93	93.05 92	98.76 106	94.39 67	99.07 30	97.03 84	98.55 75	98.31 86	97.61 105	99.43 159	99.21 154

IterMVS		94.81 133	97.71 91	91.42 164	94.83 136	97.63 172	97.38 104	85.08 176	98.93 82	75.67 189	94.02 140	97.64 75	96.66 127	98.45 80	97.60 106	98.90 181	99.72 81
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Effi-MVS+-dtu		95.74 115	98.04 81	93.06 139	93.92 142	99.16 94	97.90 90	88.16 157	99.07 69	82.02 160	98.02 72	94.32 116	96.74 123	98.53 76	97.56 107	99.61 115	99.62 110

gm-plane-assit		89.44 194	92.82 191	85.49 197	91.37 189	95.34 203	79.55 210	82.12 186	91.68 206	64.79 207	87.98 183	80.26 195	95.66 151	98.51 79	97.56 107	99.45 156	98.41 178

LGP-MVS_train		96.23 105	96.89 120	95.46 101	97.32 74	98.77 113	98.81 57	93.60 79	98.58 114	85.52 138	99.08 29	86.67 155	97.83 100	97.87 115	97.51 109	99.69 78	99.73 70

ACMMP		98.74 33	99.03 45	98.40 32	99.36 38	99.64 21	99.20 35	97.75 37	98.82 96	95.24 49	98.85 41	99.87 35	99.17 41	98.74 61	97.50 110	99.71 67	99.76 55
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
CR-MVSNet		94.57 141	97.34 106	91.33 167	94.90 133	98.59 129	97.15 115	79.14 197	97.98 141	80.42 168	96.59 108	93.50 124	96.85 120	98.10 95	97.49 111	99.50 151	99.15 156

PatchT		93.96 150	97.36 105	90.00 183	94.76 137	98.65 124	90.11 198	78.57 202	97.96 144	80.42 168	96.07 116	94.10 120	96.85 120	98.10 95	97.49 111	99.26 172	99.15 156

FC-MVSNet-test		96.07 110	97.94 86	93.89 119	93.60 151	98.67 123	96.62 129	90.30 130	98.76 106	88.62 118	95.57 129	97.63 76	94.48 173	97.97 109	97.48 113	99.71 67	99.52 127

UniMVSNet_ETH3D		93.15 161	92.33 193	94.11 116	93.91 143	98.61 128	94.81 165	90.98 118	97.06 168	87.51 127	82.27 200	76.33 206	97.87 98	94.79 190	97.47 114	99.56 140	99.81 28

PCF-MVS	97.50 6	98.18 49	98.35 67	97.99 42	98.65 55	99.36 73	98.94 50	98.14 25	98.59 113	93.62 81	96.61 105	99.76 47	99.03 51	97.77 120	97.45 115	99.57 137	98.89 170
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PatchMatch-RL		97.77 60	98.25 69	97.21 57	99.11 46	99.25 87	97.06 121	94.09 67	98.72 109	95.14 51	98.47 57	96.29 90	98.43 79	98.65 65	97.44 116	99.45 156	98.94 165

TAMVS		95.53 118	96.50 132	94.39 113	93.86 145	99.03 98	96.67 127	89.55 141	97.33 161	90.64 111	93.02 155	91.58 134	96.21 137	97.72 124	97.43 117	99.43 159	99.36 145

LTVRE_ROB	93.20 16	92.84 166	94.92 153	90.43 180	92.83 155	98.63 125	97.08 120	87.87 159	97.91 146	68.42 203	93.54 145	79.46 200	96.62 128	97.55 132	97.40 118	99.74 44	99.92 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
MVSTER		97.16 78	97.71 91	96.52 80	95.97 102	98.48 135	98.63 62	92.10 96	98.68 110	95.96 40	99.23 17	91.79 132	96.87 119	98.76 58	97.37 119	99.57 137	99.68 95

Baseline_NR-MVSNet		93.87 152	93.98 173	93.75 122	91.66 178	97.02 192	95.53 149	91.52 110	97.16 167	87.77 125	87.93 185	83.69 175	96.35 135	95.10 186	97.23 120	99.68 87	99.73 70

FMVSNet5		95.42 120	96.47 133	94.20 114	92.26 164	95.99 200	95.66 146	87.15 163	97.87 148	93.46 84	96.68 102	93.79 122	97.52 104	97.10 148	97.21 121	99.11 177	96.62 200

pm-mvs1		94.27 143	95.57 148	92.75 142	92.58 158	98.13 153	94.87 163	90.71 125	96.70 178	83.78 145	89.94 168	89.85 141	94.96 171	97.58 131	97.07 122	99.61 115	99.72 81

Fast-Effi-MVS+-dtu		95.38 122	98.20 74	92.09 150	93.91 143	98.87 107	97.35 106	85.01 178	99.08 64	81.09 164	98.10 68	96.36 89	95.62 153	98.43 83	97.03 123	99.55 142	99.50 133

TransMVSNet (Re)		93.45 157	94.08 169	92.72 143	92.83 155	97.62 175	94.94 159	91.54 109	95.65 195	83.06 153	88.93 175	83.53 177	94.25 176	97.41 136	97.03 123	99.67 95	98.40 180

DU-MVS		93.98 149	94.44 163	93.44 132	91.66 178	97.77 163	95.03 156	91.57 107	97.17 165	86.12 132	93.13 152	81.13 191	96.60 129	95.10 186	97.01 125	99.67 95	99.80 30

TSAR-MVS + COLMAP		96.79 88	96.55 127	97.06 61	97.70 69	98.46 137	99.07 44	96.23 43	99.38 22	91.32 108	98.80 42	85.61 165	98.69 69	97.64 129	96.92 126	99.37 166	99.06 163

CLD-MVS		96.74 91	96.51 130	97.01 67	96.71 85	98.62 126	98.73 59	94.38 63	98.94 81	94.46 63	97.33 84	87.03 149	98.07 88	97.20 144	96.87 127	99.72 57	99.54 123
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TranMVSNet+NR-MVSNet		93.67 155	94.14 166	93.13 138	91.28 192	97.58 177	95.60 148	91.97 99	97.06 168	84.05 141	90.64 165	82.22 186	96.17 140	94.94 189	96.78 128	99.69 78	99.78 44

RPMNet		94.66 135	97.16 113	91.75 160	94.98 132	98.59 129	97.00 122	78.37 203	97.98 141	83.78 145	96.27 113	94.09 121	96.91 118	97.36 138	96.73 129	99.48 152	99.09 161

UniMVSNet_NR-MVSNet		94.59 139	95.47 149	93.55 129	91.85 173	97.89 161	95.03 156	92.00 98	97.33 161	86.12 132	93.19 150	87.29 147	96.60 129	96.12 170	96.70 130	99.72 57	99.80 30

ET-MVSNet_ETH3D		96.17 107	96.99 118	95.21 103	88.53 201	98.54 132	98.28 77	92.61 93	98.85 89	93.60 82	99.06 31	90.39 137	98.63 72	95.98 175	96.68 131	99.61 115	99.41 140

ACMH	95.42 14	95.27 125	95.96 142	94.45 112	96.83 84	98.78 112	94.72 168	91.67 105	98.95 78	86.82 131	96.42 111	83.67 176	97.00 115	97.48 135	96.68 131	99.69 78	99.76 55
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OPM-MVS		96.22 106	95.85 146	96.65 75	97.75 67	98.54 132	99.00 49	95.53 46	96.88 172	89.88 115	95.95 119	86.46 158	98.07 88	97.65 128	96.63 133	99.67 95	98.83 172

ACMP	96.25 10	96.62 99	96.72 123	96.50 82	96.96 83	98.75 117	97.80 93	94.30 65	98.85 89	93.12 88	98.78 44	86.61 156	97.23 112	97.73 123	96.61 134	99.62 113	99.71 84
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMH+	95.51 13	95.40 121	96.00 140	94.70 108	96.33 89	98.79 110	96.79 125	91.32 113	98.77 105	87.18 128	95.60 128	85.46 166	96.97 116	97.15 145	96.59 135	99.59 129	99.65 103

CP-MVSNet		93.25 160	94.00 172	92.38 145	91.65 180	97.56 179	94.38 177	89.20 143	96.05 189	83.16 152	89.51 170	81.97 187	96.16 141	96.43 160	96.56 136	99.71 67	99.89 6

HQP-MVS		96.37 102	96.58 125	96.13 88	97.31 76	98.44 139	98.45 67	95.22 49	98.86 87	88.58 119	98.33 63	87.00 150	97.67 102	97.23 142	96.56 136	99.56 140	99.62 110

PS-CasMVS		92.72 171	93.36 184	91.98 154	91.62 182	97.52 181	94.13 181	88.98 145	95.94 192	81.51 163	87.35 187	79.95 197	95.91 146	96.37 162	96.49 138	99.70 76	99.89 6

Anonymous20231206		90.70 189	93.93 174	86.92 194	90.21 199	96.79 195	90.30 197	86.61 169	96.05 189	69.25 202	88.46 179	84.86 172	85.86 200	97.11 147	96.47 139	99.30 170	97.80 187

MVS-HIRNet		92.51 174	95.97 141	88.48 190	93.73 149	98.37 145	90.33 196	75.36 209	98.32 127	77.78 182	89.15 173	94.87 107	95.14 168	97.62 130	96.39 140	98.51 183	97.11 193

DTE-MVSNet		92.42 178	92.85 189	91.91 157	90.87 195	96.97 193	94.53 176	89.81 135	95.86 194	81.59 162	88.83 176	77.88 204	95.01 170	94.34 192	96.35 141	99.64 108	99.73 70

ACMM	96.26 9	96.67 96	96.69 124	96.66 74	97.29 77	98.46 137	96.48 133	95.09 50	99.21 45	93.19 87	98.78 44	86.73 154	98.17 82	97.84 117	96.32 142	99.74 44	99.49 134
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EU-MVSNet		92.80 168	94.76 158	90.51 178	91.88 171	96.74 197	92.48 188	88.69 149	96.21 184	79.00 177	91.51 156	87.82 145	91.83 195	95.87 177	96.27 143	99.21 173	98.92 169

PEN-MVS		92.72 171	93.20 186	92.15 149	91.29 190	97.31 189	94.67 171	89.81 135	96.19 185	81.83 161	88.58 178	79.06 201	95.61 154	95.21 183	96.27 143	99.72 57	99.82 23

TinyColmap		94.00 148	94.35 164	93.60 126	95.89 103	98.26 148	97.49 102	88.82 147	98.56 116	83.21 151	91.28 159	80.48 194	96.68 125	97.34 139	96.26 145	99.53 148	98.24 181

test-mter		94.86 132	97.32 108	92.00 153	92.41 161	98.82 109	96.18 140	86.35 171	98.05 138	82.28 158	96.48 110	94.39 115	95.46 160	98.17 93	96.20 146	99.32 169	99.13 160

NR-MVSNet		94.01 147	94.51 161	93.44 132	92.56 159	97.77 163	95.67 145	91.57 107	97.17 165	85.84 135	93.13 152	80.53 193	95.29 164	97.01 149	96.17 147	99.69 78	99.75 62

tfpnnormal		93.85 154	94.12 168	93.54 130	93.22 154	98.24 150	95.45 151	91.96 100	94.61 198	83.91 143	90.74 162	81.75 189	97.04 114	97.49 134	96.16 148	99.68 87	99.84 18

USDC		94.26 144	94.83 156	93.59 127	96.02 98	98.44 139	97.84 91	88.65 150	98.86 87	82.73 157	94.02 140	80.56 192	96.76 122	97.28 141	96.15 149	99.55 142	98.50 176

thisisatest0530		97.23 76	98.25 69	96.05 89	95.60 117	99.59 40	96.96 123	93.23 85	99.17 50	92.60 96	98.75 47	96.19 92	98.17 82	98.19 92	96.10 150	99.72 57	99.77 51

tttt0517		97.23 76	98.24 72	96.04 90	95.60 117	99.60 38	96.94 124	93.23 85	99.15 51	92.56 97	98.74 48	96.12 95	98.17 82	98.21 90	96.10 150	99.73 51	99.78 44

test-LLR		95.50 119	97.32 108	93.37 134	95.49 122	98.74 118	96.44 135	90.82 121	98.18 133	82.75 155	96.60 106	94.67 111	95.54 156	98.09 97	96.00 152	99.20 174	98.93 166

TESTMET0.1,1		94.95 129	97.32 108	92.20 148	92.62 157	98.74 118	96.44 135	86.67 167	98.18 133	82.75 155	96.60 106	94.67 111	95.54 156	98.09 97	96.00 152	99.20 174	98.93 166

EG-PatchMatch MVS		92.45 175	93.92 175	90.72 177	92.56 159	98.43 141	94.88 162	84.54 181	97.18 164	79.55 174	86.12 194	83.23 180	93.15 190	97.22 143	96.00 152	99.67 95	99.27 150

UniMVSNet (Re)		94.58 140	95.34 150	93.71 124	92.25 165	98.08 154	94.97 158	91.29 117	97.03 170	87.94 123	93.97 142	86.25 161	96.07 142	96.27 167	95.97 155	99.72 57	99.79 38

anonymousdsp		93.12 162	95.86 145	89.93 185	91.09 193	98.25 149	95.12 155	85.08 176	97.44 158	73.30 196	90.89 161	90.78 136	95.25 166	97.91 112	95.96 156	99.71 67	99.82 23

WR-MVS_H		93.54 156	94.67 159	92.22 146	91.95 169	97.91 160	94.58 174	88.75 148	96.64 179	83.88 144	90.66 164	85.13 169	94.40 174	96.54 158	95.91 157	99.73 51	99.89 6

WR-MVS		93.43 159	94.48 162	92.21 147	91.52 185	97.69 168	94.66 172	89.98 132	96.86 173	83.43 149	90.12 166	85.03 170	93.94 182	96.02 174	95.82 158	99.71 67	99.82 23

IB-MVS	93.96 15	95.02 128	96.44 136	93.36 135	97.05 82	99.28 85	90.43 195	93.39 82	98.02 139	96.02 38	94.92 133	92.07 131	83.52 202	95.38 180	95.82 158	99.72 57	99.59 113
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
pmmvs6		91.90 185	92.53 192	91.17 170	91.81 174	97.63 172	93.23 183	88.37 154	93.43 203	80.61 166	77.32 204	87.47 146	94.12 178	96.58 156	95.72 160	98.88 182	99.53 124

MS-PatchMatch		95.99 111	97.26 112	94.51 111	97.46 71	98.76 116	97.27 109	86.97 164	99.09 62	89.83 116	93.51 146	97.78 74	96.18 139	97.53 133	95.71 161	99.35 167	98.41 178

MDTV_nov1_ep13		95.57 117	97.48 98	93.35 136	95.43 124	98.97 103	97.19 114	83.72 185	98.92 84	87.91 124	97.75 78	96.12 95	97.88 97	96.84 153	95.64 162	97.96 190	98.10 183

MIMVSNet1		88.61 195	90.68 196	86.19 196	81.56 208	95.30 204	87.78 203	85.98 173	94.19 201	72.30 200	78.84 203	78.90 202	90.06 196	96.59 155	95.47 163	99.46 155	95.49 202

RPSCF		97.61 65	98.16 76	96.96 70	98.10 61	99.00 99	98.84 56	93.76 74	99.45 18	94.78 57	99.39 11	99.31 56	98.53 77	96.61 154	95.43 164	97.74 192	97.93 186

pmmvs4		95.09 126	95.90 143	94.14 115	92.29 163	97.70 166	95.45 151	90.31 128	98.60 112	90.70 110	93.25 149	89.90 140	96.67 126	97.13 146	95.42 165	99.44 158	99.28 148

GA-MVS		93.93 151	96.31 139	91.16 171	93.61 150	98.79 110	95.39 153	90.69 126	98.25 131	73.28 197	96.15 115	88.42 144	94.39 175	97.76 121	95.35 166	99.58 133	99.45 137

v10		92.79 169	94.06 170	91.31 168	91.78 175	97.29 191	94.87 163	86.10 172	96.97 171	79.82 173	88.16 181	84.56 173	95.63 152	96.33 165	95.31 167	99.65 104	99.80 30

v1192		92.43 177	93.61 179	91.05 172	91.53 184	97.43 185	94.61 173	87.99 158	96.60 180	76.72 184	87.11 189	82.74 184	95.85 147	96.35 164	95.30 168	99.60 123	99.74 66

v1144		92.81 167	94.03 171	91.40 166	91.68 177	97.60 176	94.73 167	88.40 153	96.71 177	78.48 179	88.14 182	84.46 174	95.45 161	96.31 166	95.22 169	99.65 104	99.76 55

v1240		91.99 184	93.33 185	90.44 179	91.29 190	97.30 190	94.25 179	86.79 165	96.43 183	75.49 191	86.34 193	81.85 188	95.29 164	96.42 161	95.22 169	99.52 149	99.73 70

v144192		92.38 179	93.55 182	91.00 173	91.44 186	97.47 184	94.27 178	87.41 162	96.52 182	78.03 180	87.50 186	82.65 185	95.32 163	95.82 178	95.15 171	99.55 142	99.78 44

v1921920		92.36 181	93.57 180	90.94 174	91.39 188	97.39 187	94.70 169	87.63 161	96.60 180	76.63 185	86.98 190	82.89 182	95.75 148	96.26 168	95.14 172	99.55 142	99.73 70

test20.03		90.65 190	93.71 178	87.09 192	90.44 197	96.24 198	89.74 200	85.46 175	95.59 196	72.99 198	90.68 163	85.33 167	84.41 201	95.94 176	95.10 173	99.52 149	97.06 195

pmmvs5		92.71 173	94.27 165	90.90 175	91.42 187	97.74 165	93.23 183	86.66 168	95.99 191	78.96 178	91.45 157	83.44 178	95.55 155	97.30 140	95.05 174	99.58 133	98.93 166

v7n		91.61 186	92.95 187	90.04 182	90.56 196	97.69 168	93.74 182	85.59 174	95.89 193	76.95 183	86.60 192	78.60 203	93.76 185	97.01 149	94.99 175	99.65 104	99.87 12

v2v482		92.77 170	93.52 183	91.90 158	91.59 183	97.63 172	94.57 175	90.31 128	96.80 176	79.22 175	88.74 177	81.55 190	96.04 144	95.26 182	94.97 176	99.66 100	99.69 90

SCA		94.95 129	97.44 101	92.04 151	95.55 119	99.16 94	96.26 138	79.30 196	99.02 73	85.73 137	98.18 66	97.13 82	97.69 101	96.03 173	94.91 177	97.69 195	97.65 188

v8		92.87 165	93.87 177	91.72 162	92.05 167	97.50 182	94.79 166	88.20 156	96.85 174	80.11 171	90.01 167	82.86 183	95.48 158	95.15 185	94.90 178	99.66 100	99.80 30

V42		93.05 163	93.90 176	92.04 151	91.91 170	97.66 170	94.91 160	89.91 133	96.85 174	80.58 167	89.66 169	83.43 179	95.37 162	95.03 188	94.90 178	99.59 129	99.78 44

SixPastTwentyTwo		93.44 158	95.32 151	91.24 169	92.11 166	98.40 143	92.77 186	88.64 151	98.09 137	77.83 181	93.51 146	85.74 164	96.52 132	96.91 151	94.89 180	99.59 129	99.73 70

tpm		92.38 179	94.79 157	89.56 186	94.30 140	97.50 182	94.24 180	78.97 200	97.72 154	74.93 193	97.97 73	82.91 181	96.60 129	93.65 194	94.81 181	98.33 187	98.98 164

EPMVS		95.05 127	96.86 122	92.94 141	95.84 105	98.96 104	96.68 126	79.87 192	99.05 70	90.15 112	97.12 92	95.99 97	97.49 106	95.17 184	94.75 182	97.59 196	96.96 196

thisisatest0515		94.61 138	96.89 120	91.95 155	92.00 168	98.47 136	92.01 190	90.73 124	98.18 133	83.96 142	94.51 136	95.13 105	93.38 187	97.38 137	94.74 183	99.61 115	99.79 38

v148		92.36 181	92.88 188	91.75 160	91.63 181	97.66 170	92.64 187	90.55 127	96.09 187	83.34 150	88.19 180	80.00 196	92.74 191	93.98 193	94.58 184	99.58 133	99.69 90

TDRefinement		93.04 164	93.57 180	92.41 144	96.58 86	98.77 113	97.78 95	91.96 100	98.12 136	80.84 165	89.13 174	79.87 198	87.78 198	96.44 159	94.50 185	99.54 146	98.15 182

ADS-MVSNet		94.65 136	97.04 117	91.88 159	95.68 113	98.99 101	95.89 142	79.03 199	99.15 51	85.81 136	96.96 94	98.21 71	97.10 113	94.48 191	94.24 186	97.74 192	97.21 192

PatchmatchNet		94.70 134	97.08 115	91.92 156	95.53 120	98.85 108	95.77 144	79.54 194	98.95 78	85.98 134	98.52 54	96.45 86	97.39 109	95.32 181	94.09 187	97.32 198	97.38 191
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PM-MVS		89.55 193	90.30 197	88.67 189	87.06 202	95.60 201	90.88 193	84.51 182	96.14 186	75.75 187	86.89 191	63.47 212	94.64 172	96.85 152	93.89 188	99.17 176	99.29 147

pmmvs-eth3d		89.81 192	89.65 198	90.00 183	86.94 203	95.38 202	91.08 191	86.39 170	94.57 199	82.27 159	83.03 199	64.94 209	93.96 181	96.57 157	93.82 189	99.35 167	99.24 152

MDTV_nov1_ep13_2view		92.44 176	95.66 147	88.68 188	91.05 194	97.92 159	92.17 189	79.64 193	98.83 94	76.20 186	91.45 157	93.51 123	95.04 169	95.68 179	93.70 190	97.96 190	98.53 175

new_pmnet		90.45 191	92.84 190	87.66 191	88.96 200	96.16 199	88.71 202	84.66 180	97.56 157	71.91 201	85.60 195	86.58 157	93.28 188	96.07 172	93.54 191	98.46 184	94.39 204

N_pmnet		92.21 183	94.60 160	89.42 187	91.88 171	97.38 188	89.15 201	89.74 138	97.89 147	73.75 195	87.94 184	92.23 130	93.85 184	96.10 171	93.20 192	98.15 189	97.43 190

CostFormer		94.25 145	94.88 155	93.51 131	95.43 124	98.34 147	96.21 139	80.64 189	97.94 145	94.01 71	98.30 64	86.20 162	97.52 104	92.71 196	92.69 193	97.23 201	98.02 185

pmmvs3		88.19 196	91.27 194	84.60 199	85.60 205	93.66 206	85.68 205	81.13 187	92.36 205	63.66 209	89.51 170	77.10 205	93.22 189	96.37 162	92.40 194	98.30 188	97.46 189

tpmrst		93.86 153	95.88 144	91.50 163	95.69 112	98.62 126	95.64 147	79.41 195	98.80 99	83.76 147	95.63 127	96.13 94	97.25 110	92.92 195	92.31 195	97.27 199	96.74 197

MDA-MVSNet-bldmvs		87.84 197	89.22 199	86.23 195	81.74 207	96.77 196	83.74 206	89.57 140	94.50 200	72.83 199	96.64 104	64.47 211	92.71 192	81.43 206	92.28 196	96.81 203	98.47 177

Gipuma		81.40 200	81.78 202	80.96 202	83.21 206	85.61 211	79.73 209	76.25 208	97.33 161	64.21 208	55.32 208	55.55 213	86.04 199	92.43 199	92.20 197	96.32 205	93.99 205
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ambc			80.99 203		80.04 210	90.84 207	90.91 192		96.09 187	74.18 194	62.81 207	30.59 218	82.44 203	96.25 169	91.77 198	95.91 206	98.56 174

dps		94.63 137	95.31 152	93.84 120	95.53 120	98.71 121	96.54 130	80.12 191	97.81 153	97.21 27	96.98 93	92.37 128	96.34 136	92.46 198	91.77 198	97.26 200	97.08 194

tpm cat1		94.06 146	94.90 154	93.06 139	95.42 126	98.52 134	96.64 128	80.67 188	97.82 151	92.63 95	93.39 148	95.00 106	96.06 143	91.36 201	91.58 200	96.98 202	96.66 199

CMPMVS	70.31 18	90.74 188	91.06 195	90.36 181	97.32 74	97.43 185	92.97 185	87.82 160	93.50 202	75.34 192	83.27 198	84.90 171	92.19 194	92.64 197	91.21 201	96.50 204	94.46 203
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new-patchmatchnet		86.12 198	87.30 200	84.74 198	86.92 204	95.19 205	83.57 207	84.42 183	92.67 204	65.66 204	80.32 201	64.72 210	89.41 197	92.33 200	89.21 202	98.43 185	96.69 198

PMMVS2		77.26 201	79.47 204	74.70 204	76.00 211	88.37 210	74.22 211	76.34 206	78.31 209	54.13 211	69.96 206	52.50 214	70.14 208	84.83 204	88.71 203	97.35 197	93.58 206

MVE	67.97 19	65.53 206	67.43 208	63.31 207	59.33 214	74.20 212	53.09 216	70.43 210	66.27 212	43.13 212	45.98 212	30.62 217	70.65 207	79.34 208	86.30 204	83.25 213	89.33 207
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				82.25 201	97.73 68	88.71 209	80.18 208	68.65 211	99.15 51	86.98 129	99.47 8	85.31 168	68.35 209	87.51 203	83.81 205	91.64 208

E-PMN		68.30 204	68.43 206	68.15 205	74.70 213	71.56 214	55.64 214	77.24 204	77.48 211	39.46 213	51.95 211	41.68 216	73.28 206	70.65 209	79.51 206	88.61 211	86.20 210

FPMVS		83.82 199	84.61 201	82.90 200	90.39 198	90.71 208	90.85 194	84.10 184	95.47 197	65.15 205	83.44 197	74.46 207	75.48 204	81.63 205	79.42 207	91.42 209	87.14 208

PMVS	72.60 17	76.39 202	77.66 205	74.92 203	81.04 209	69.37 215	68.47 212	80.54 190	85.39 208	65.07 206	73.52 205	72.91 208	65.67 210	80.35 207	76.81 208	88.71 210	85.25 211
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		68.12 205	68.11 207	68.14 206	75.51 212	71.76 213	55.38 215	77.20 205	77.78 210	37.79 214	53.59 209	43.61 215	74.72 205	67.05 210	76.70 209	88.27 212	86.24 209

testmvs		31.24 207	40.15 209	20.86 209	12.61 215	17.99 216	25.16 217	13.30 212	48.42 213	24.82 215	53.07 210	30.13 219	28.47 211	42.73 211	37.65 210	20.79 214	51.04 212

test123		26.75 208	34.25 210	18.01 210	7.93 216	17.18 217	24.85 218	12.36 213	44.83 214	16.52 216	41.80 213	18.10 220	28.29 212	33.08 212	34.79 211	18.10 215	49.95 213

uanet_test		0.00 209	0.00 211	0.00 211	0.00 218	0.00 218	0.00 219	0.00 215	0.00 215	0.00 218	0.00 214	0.00 221	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

sosnet-low-res		0.00 209	0.00 211	0.00 211	0.00 218	0.00 218	0.00 219	0.00 215	0.00 215	0.00 218	0.00 214	0.00 221	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

sosnet		0.00 209	0.00 211	0.00 211	0.00 218	0.00 218	0.00 219	0.00 215	0.00 215	0.00 218	0.00 214	0.00 221	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

9.14												99.79 44

SR-MVS					99.67 12			98.25 13				99.94 24

our_test_3					92.30 162	97.58 177	90.09 199

test_part1																	99.62 110

MTAPA										98.09 14		99.97 6

MTMP										98.46 10		99.96 11

Patchmatch-RL test							66.86 213

XVS					97.42 72	99.62 28	98.59 63			93.81 77		99.95 16				99.69 78

X-MVStestdata					97.42 72	99.62 28	98.59 63			93.81 77		99.95 16				99.69 78

abl_6				98.09 39	99.33 41	99.22 91	98.79 58	94.96 53	98.52 120	97.00 31	97.30 86	99.86 36	98.76 65			99.69 78	99.41 140

mPP-MVS					99.53 29							99.89 33

NP-MVS									98.57 115

Patchmtry						98.59 129	97.15 115	79.14 197		80.42 168

DeepMVS_CX						96.85 194	87.43 204	89.27 142	98.30 128	75.55 190	95.05 130	79.47 199	92.62 193	89.48 202		95.18 207	95.96 201

High-resolution multi-view benchmark