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.

DVP-MVS++		99.41 4	99.64 1	99.14 8	99.69 8	99.75 9	99.64 8	98.33 6	99.67 4	98.10 14	99.66 4	99.99 1	99.33 31	99.62 5	98.86 44	99.74 49	99.90 6

SED-MVS		99.44 3	99.58 4	99.28 3	99.69 8	99.76 6	99.62 15	98.35 3	99.51 17	99.05 2	99.60 6	99.98 2	99.28 38	99.61 6	98.83 50	99.70 83	99.77 56

DVP-MVS		99.45 2	99.54 7	99.35 1	99.72 7	99.76 6	99.63 12	98.37 2	99.63 7	99.03 3	98.95 41	99.98 2	99.60 7	99.60 7	99.05 29	99.74 49	99.79 42
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
SMA-MVS		99.38 6	99.60 3	99.12 10	99.76 2	99.62 34	99.39 30	98.23 20	99.52 16	98.03 18	99.45 11	99.98 2	99.64 5	99.58 9	99.30 11	99.68 95	99.76 61
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
DPE-MVS		99.39 5	99.55 6	99.20 4	99.63 22	99.71 15	99.66 6	98.33 6	99.29 37	98.40 12	99.64 5	99.98 2	99.31 34	99.56 10	98.96 36	99.85 9	99.70 92
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		99.34 7	99.52 10	99.14 8	99.68 13	99.75 9	99.64 8	98.31 9	99.44 21	98.10 14	99.28 18	99.98 2	99.30 36	99.34 24	99.05 29	99.81 21	99.79 42
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
SteuartSystems-ACMMP		99.20 16	99.51 11	98.83 28	99.66 17	99.66 21	99.71 3	98.12 29	99.14 62	96.62 36	99.16 24	99.98 2	99.12 49	99.63 3	99.19 21	99.78 33	99.83 27
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		99.05 26	99.45 14	98.58 32	99.73 5	99.60 44	99.64 8	98.28 13	99.23 46	94.57 66	99.35 16	99.97 8	99.55 14	99.63 3	98.66 57	99.70 83	99.74 72

zzz-MVS		99.31 9	99.44 17	99.16 6	99.73 5	99.65 22	99.63 12	98.26 14	99.27 40	98.01 19	99.27 19	99.97 8	99.60 7	99.59 8	98.58 62	99.71 74	99.73 76

MTAPA										98.09 16		99.97 8

HFP-MVS		99.32 8	99.53 9	99.07 14	99.69 8	99.59 46	99.63 12	98.31 9	99.56 11	97.37 28	99.27 19	99.97 8	99.70 3	99.35 23	99.24 17	99.71 74	99.76 61

APDe-MVS		99.49 1	99.64 1	99.32 2	99.74 4	99.74 11	99.75 1	98.34 4	99.56 11	98.72 7	99.57 7	99.97 8	99.53 16	99.65 2	99.25 15	99.84 11	99.77 56

TSAR-MVS + MP.		99.27 11	99.57 5	98.92 24	98.78 55	99.53 56	99.72 2	98.11 30	99.73 2	97.43 27	99.15 25	99.96 13	99.59 10	99.73 1	99.07 26	99.88 4	99.82 28
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MTMP										98.46 11		99.96 13

HPM-MVS++		99.10 22	99.30 31	98.86 25	99.69 8	99.48 64	99.59 17	98.34 4	99.26 43	96.55 39	99.10 32	99.96 13	99.36 29	99.25 28	98.37 75	99.64 116	99.66 106

CP-MVS		99.27 11	99.44 17	99.08 13	99.62 24	99.58 49	99.53 19	98.16 23	99.21 49	97.79 22	99.15 25	99.96 13	99.59 10	99.54 12	98.86 44	99.78 33	99.74 72

PHI-MVS		99.08 23	99.43 20	98.67 30	99.15 47	99.59 46	99.11 43	97.35 41	99.14 62	97.30 29	99.44 12	99.96 13	99.32 33	98.89 56	99.39 7	99.79 30	99.58 122

XVS					97.42 76	99.62 34	98.59 67			93.81 84		99.95 18				99.69 86

X-MVStestdata					97.42 76	99.62 34	98.59 67			93.81 84		99.95 18				99.69 86

X-MVS		98.93 30	99.37 24	98.42 33	99.67 14	99.62 34	99.60 16	98.15 25	99.08 72	93.81 84	98.46 63	99.95 18	99.59 10	99.49 14	99.21 20	99.68 95	99.75 68

SD-MVS		99.25 13	99.50 12	98.96 22	98.79 54	99.55 54	99.33 33	98.29 12	99.75 1	97.96 20	99.15 25	99.95 18	99.61 6	99.17 34	99.06 28	99.81 21	99.84 23
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
TSAR-MVS + ACMM		98.77 34	99.45 14	97.98 45	99.37 38	99.46 66	99.44 28	98.13 28	99.65 5	92.30 109	98.91 44	99.95 18	99.05 54	99.42 18	98.95 37	99.58 142	99.82 28

ACMMPR		99.30 10	99.54 7	99.03 17	99.66 17	99.64 27	99.68 4	98.25 15	99.56 11	97.12 32	99.19 22	99.95 18	99.72 1	99.43 17	99.25 15	99.72 64	99.77 56

TSAR-MVS + GP.		98.66 40	99.36 25	97.85 47	97.16 84	99.46 66	99.03 49	94.59 64	99.09 70	97.19 31	99.73 3	99.95 18	99.39 27	98.95 49	98.69 56	99.75 44	99.65 109

CPTT-MVS		99.14 20	99.20 37	99.06 15	99.58 27	99.53 56	99.45 26	97.80 38	99.19 52	98.32 13	98.58 58	99.95 18	99.60 7	99.28 27	98.20 87	99.64 116	99.69 96

SR-MVS					99.67 14			98.25 15				99.94 26

MP-MVS		99.07 24	99.36 25	98.74 29	99.63 22	99.57 51	99.66 6	98.25 15	99.00 83	95.62 47	98.97 39	99.94 26	99.54 15	99.51 13	98.79 54	99.71 74	99.73 76
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CNVR-MVS		99.23 15	99.28 32	99.17 5	99.65 19	99.34 87	99.46 25	98.21 21	99.28 38	98.47 9	98.89 46	99.94 26	99.50 17	99.42 18	98.61 60	99.73 57	99.52 135

SF-MVS		99.18 17	99.32 29	99.03 17	99.65 19	99.41 75	98.87 55	98.24 18	99.14 62	98.73 5	99.11 29	99.92 29	98.92 61	99.22 29	98.84 48	99.76 40	99.56 128

APD-MVS		99.25 13	99.38 23	99.09 12	99.69 8	99.58 49	99.56 18	98.32 8	98.85 97	97.87 21	98.91 44	99.92 29	99.30 36	99.45 16	99.38 8	99.79 30	99.58 122
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepC-MVS_fast	98.34 1	99.17 18	99.45 14	98.85 26	99.55 30	99.37 81	99.64 8	98.05 33	99.53 14	96.58 37	98.93 42	99.92 29	99.49 19	99.46 15	99.32 10	99.80 29	99.64 113
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
UA-Net		97.13 85	99.14 39	94.78 115	97.21 82	99.38 78	97.56 110	92.04 104	98.48 130	88.03 131	98.39 66	99.91 32	94.03 191	99.33 25	99.23 18	99.81 21	99.25 160

MCST-MVS		99.11 21	99.27 33	98.93 23	99.67 14	99.33 90	99.51 21	98.31 9	99.28 38	96.57 38	99.10 32	99.90 33	99.71 2	99.19 33	98.35 76	99.82 15	99.71 90

NCCC		99.05 26	99.08 42	99.02 20	99.62 24	99.38 78	99.43 29	98.21 21	99.36 30	97.66 25	97.79 81	99.90 33	99.45 23	99.17 34	98.43 70	99.77 38	99.51 140

MSLP-MVS++		99.15 19	99.24 35	99.04 16	99.52 33	99.49 63	99.09 45	98.07 31	99.37 27	98.47 9	97.79 81	99.89 35	99.50 17	98.93 51	99.45 4	99.61 124	99.76 61

mPP-MVS					99.53 31							99.89 35

ACMMP		98.74 35	99.03 49	98.40 34	99.36 40	99.64 27	99.20 37	97.75 39	98.82 104	95.24 55	98.85 47	99.87 37	99.17 46	98.74 69	97.50 118	99.71 74	99.76 61
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
train_agg		98.73 36	99.11 40	98.28 37	99.36 40	99.35 85	99.48 24	97.96 35	98.83 102	93.86 83	98.70 56	99.86 38	99.44 24	99.08 41	98.38 73	99.61 124	99.58 122

abl_6				98.09 41	99.33 43	99.22 100	98.79 60	94.96 55	98.52 129	97.00 34	97.30 91	99.86 38	98.76 72			99.69 86	99.41 149

3Dnovator+	96.92 7	98.71 37	99.05 45	98.32 35	99.53 31	99.34 87	99.06 47	94.61 61	99.65 5	97.49 26	96.75 104	99.86 38	99.44 24	98.78 64	99.30 11	99.81 21	99.67 102

DeepPCF-MVS	97.74 3	98.34 48	99.46 13	97.04 69	98.82 53	99.33 90	96.28 147	97.47 40	99.58 9	94.70 64	98.99 38	99.85 41	97.24 121	99.55 11	99.34 9	97.73 205	99.56 128

DPM-MVS		98.31 50	98.53 65	98.05 42	98.76 56	98.77 122	99.13 41	98.07 31	99.10 69	94.27 77	96.70 106	99.84 42	98.70 74	97.90 122	98.11 92	99.40 173	99.28 157

PGM-MVS		98.86 32	99.35 28	98.29 36	99.77 1	99.63 30	99.67 5	95.63 47	98.66 120	95.27 54	99.11 29	99.82 43	99.67 4	99.33 25	99.19 21	99.73 57	99.74 72

QAPM		98.62 41	99.04 48	98.13 40	99.57 28	99.48 64	99.17 39	94.78 57	99.57 10	96.16 41	96.73 105	99.80 44	99.33 31	98.79 63	99.29 13	99.75 44	99.64 113

OMC-MVS		98.84 33	99.01 51	98.65 31	99.39 37	99.23 99	99.22 36	96.70 43	99.40 24	97.77 23	97.89 80	99.80 44	99.21 39	99.02 45	98.65 58	99.57 146	99.07 171

9.14												99.79 46

MVS_111021_HR		98.59 42	99.36 25	97.68 50	99.42 36	99.61 39	98.14 90	94.81 56	99.31 34	95.00 59	99.51 9	99.79 46	99.00 58	98.94 50	98.83 50	99.69 86	99.57 127

PLC	97.93 2	99.02 29	98.94 53	99.11 11	99.46 35	99.24 98	99.06 47	97.96 35	99.31 34	99.16 1	97.90 79	99.79 46	99.36 29	98.71 70	98.12 91	99.65 112	99.52 135
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.50 6	98.18 54	98.35 71	97.99 44	98.65 57	99.36 82	98.94 53	98.14 27	98.59 122	93.62 89	96.61 110	99.76 49	99.03 56	97.77 129	97.45 123	99.57 146	98.89 179
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CNLPA		99.03 28	99.05 45	99.01 21	99.27 45	99.22 100	99.03 49	97.98 34	99.34 32	99.00 4	98.25 70	99.71 50	99.31 34	98.80 62	98.82 52	99.48 161	99.17 164

MVS_111021_LR		98.67 38	99.41 22	97.81 48	99.37 38	99.53 56	98.51 69	95.52 49	99.27 40	94.85 61	99.56 8	99.69 51	99.04 55	99.36 21	98.88 42	99.60 132	99.58 122

CDPH-MVS		98.41 46	99.10 41	97.61 53	99.32 44	99.36 82	99.49 22	96.15 46	98.82 104	91.82 113	98.41 64	99.66 52	99.10 51	98.93 51	98.97 35	99.75 44	99.58 122

DROMVSNet		98.22 52	99.44 17	96.79 78	95.62 123	99.56 52	99.01 51	92.22 101	99.17 54	94.51 69	99.41 13	99.62 53	99.49 19	99.16 36	99.26 14	99.91 2	99.94 1

3Dnovator	96.92 7	98.67 38	99.05 45	98.23 39	99.57 28	99.45 68	99.11 43	94.66 60	99.69 3	96.80 35	96.55 114	99.61 54	99.40 26	98.87 59	99.49 3	99.85 9	99.66 106

CANet		98.46 45	99.16 38	97.64 52	98.48 60	99.64 27	99.35 32	94.71 59	99.53 14	95.17 56	97.63 87	99.59 55	98.38 88	98.88 58	98.99 34	99.74 49	99.86 19

UGNet		97.66 68	99.07 44	96.01 99	97.19 83	99.65 22	97.09 129	93.39 89	99.35 31	94.40 74	98.79 49	99.59 55	94.24 188	98.04 114	98.29 83	99.73 57	99.80 35
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
AdaColmap		99.06 25	98.98 52	99.15 7	99.60 26	99.30 93	99.38 31	98.16 23	99.02 81	98.55 8	98.71 55	99.57 57	99.58 13	99.09 39	97.84 105	99.64 116	99.36 154

PVSNet_Blended_VisFu		97.41 76	98.49 67	96.15 94	97.49 74	99.76 6	96.02 151	93.75 83	99.26 43	93.38 93	93.73 149	99.35 58	96.47 143	98.96 48	98.46 67	99.77 38	99.90 6

RPSCF		97.61 69	98.16 81	96.96 77	98.10 65	99.00 108	98.84 58	93.76 81	99.45 20	94.78 63	99.39 15	99.31 59	98.53 85	96.61 164	95.43 174	97.74 203	97.93 197

ETV-MVS		98.05 57	99.25 34	96.65 82	95.61 124	99.61 39	98.26 86	93.52 87	98.90 93	93.74 88	99.32 17	99.20 60	98.90 64	99.21 31	98.72 55	99.87 8	99.79 42

TAPA-MVS	97.53 5	98.41 46	98.84 58	97.91 46	99.08 49	99.33 90	99.15 40	97.13 42	99.34 32	93.20 94	97.75 83	99.19 61	99.20 40	98.66 72	98.13 90	99.66 108	99.48 144
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CS-MVS-test		98.58 43	99.42 21	97.60 54	98.52 59	99.91 1	98.60 66	94.60 63	99.37 27	94.62 65	99.40 14	99.16 62	99.39 27	99.36 21	98.85 47	99.90 3	99.92 3

FA-MVS(training)		96.52 108	98.29 72	94.45 121	95.88 113	99.52 59	97.66 107	81.47 197	98.94 88	93.79 87	95.54 135	99.11 63	98.29 90	98.89 56	96.49 147	99.63 121	99.52 135

CANet_DTU		96.64 104	99.08 42	93.81 131	97.10 85	99.42 73	98.85 57	90.01 140	99.31 34	79.98 182	99.78 2	99.10 64	97.42 118	98.35 93	98.05 95	99.47 163	99.53 132

MVS_0304		98.14 55	99.03 49	97.10 66	98.05 68	99.63 30	99.27 35	94.33 71	99.63 7	93.06 97	97.32 90	99.05 65	98.09 96	98.82 61	98.87 43	99.81 21	99.89 10

OpenMVS	96.23 11	97.95 60	98.45 68	97.35 58	99.52 33	99.42 73	98.91 54	94.61 61	98.87 94	92.24 111	94.61 141	99.05 65	99.10 51	98.64 74	99.05 29	99.74 49	99.51 140

CS-MVS		98.56 44	99.32 29	97.68 50	98.28 64	99.89 2	98.71 63	94.53 66	99.41 23	95.43 51	99.05 37	98.66 67	99.19 41	99.21 31	99.07 26	99.93 1	99.94 1

GG-mvs-BLEND		69.11 215	98.13 82	35.26 220	3.49 229	98.20 161	94.89 171	2.38 226	98.42 133	5.82 230	96.37 117	98.60 68	5.97 225	98.75 68	97.98 97	99.01 189	98.61 182

CHOSEN 280x420		97.99 59	99.24 35	96.53 86	98.34 62	99.61 39	98.36 80	89.80 146	99.27 40	95.08 58	99.81 1	98.58 69	98.64 78	99.02 45	98.92 39	98.93 190	99.48 144

Vis-MVSNet (Re-imp)		97.40 77	98.89 55	95.66 107	95.99 109	99.62 34	97.82 100	93.22 94	98.82 104	91.40 116	96.94 100	98.56 70	95.70 160	99.14 37	99.41 6	99.79 30	99.75 68

EPNet_dtu		96.30 112	98.53 65	93.70 135	98.97 51	98.24 159	97.36 115	94.23 73	98.85 97	79.18 186	99.19 22	98.47 71	94.09 190	97.89 123	98.21 86	98.39 196	98.85 180
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IS_MVSNet		97.86 61	98.86 56	96.68 80	96.02 106	99.72 12	98.35 81	93.37 91	98.75 117	94.01 78	96.88 103	98.40 72	98.48 86	99.09 39	99.42 5	99.83 14	99.80 35

COLMAP_ROB	96.15 12	97.78 63	98.17 80	97.32 59	98.84 52	99.45 68	99.28 34	95.43 50	99.48 19	91.80 114	94.83 140	98.36 73	98.90 64	98.09 106	97.85 104	99.68 95	99.15 165
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
IterMVS-SCA-FT		94.89 141	97.87 93	91.42 174	94.86 145	97.70 176	97.24 121	84.88 189	98.93 90	75.74 198	94.26 145	98.25 74	96.69 134	98.52 86	97.68 111	99.10 188	99.73 76

DELS-MVS		98.19 53	98.77 60	97.52 55	98.29 63	99.71 15	99.12 42	94.58 65	98.80 107	95.38 53	96.24 119	98.24 75	97.92 103	99.06 42	99.52 1	99.82 15	99.79 42
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
ADS-MVSNet		94.65 146	97.04 124	91.88 169	95.68 121	98.99 110	95.89 152	79.03 210	99.15 59	85.81 146	96.96 99	98.21 76	97.10 123	94.48 203	94.24 197	97.74 203	97.21 203

EIA-MVS		97.70 67	98.78 59	96.44 90	95.72 118	99.65 22	98.14 90	93.72 84	98.30 138	92.31 108	98.63 57	97.90 77	98.97 59	98.92 53	98.30 82	99.78 33	99.80 35

CSCG		98.90 31	98.93 54	98.85 26	99.75 3	99.72 12	99.49 22	96.58 44	99.38 25	98.05 17	98.97 39	97.87 78	99.49 19	97.78 128	98.92 39	99.78 33	99.90 6

MS-PatchMatch		95.99 119	97.26 117	94.51 119	97.46 75	98.76 125	97.27 119	86.97 174	99.09 70	89.83 125	93.51 153	97.78 79	96.18 149	97.53 142	95.71 171	99.35 176	98.41 187

IterMVS		94.81 143	97.71 96	91.42 174	94.83 146	97.63 183	97.38 114	85.08 186	98.93 90	75.67 199	94.02 146	97.64 80	96.66 137	98.45 89	97.60 114	98.90 191	99.72 87
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		96.07 118	97.94 91	93.89 129	93.60 161	98.67 132	96.62 139	90.30 139	98.76 114	88.62 127	95.57 134	97.63 81	94.48 184	97.97 118	97.48 121	99.71 74	99.52 135

EPNet		98.05 57	98.86 56	97.10 66	99.02 50	99.43 72	98.47 72	94.73 58	99.05 78	95.62 47	98.93 42	97.62 82	95.48 168	98.59 82	98.55 63	99.29 180	99.84 23
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test0.0.03 1		96.69 101	98.12 83	95.01 113	95.49 131	98.99 110	95.86 153	90.82 128	98.38 134	92.54 107	96.66 108	97.33 83	95.75 158	97.75 131	98.34 78	99.60 132	99.40 152

MSDG		98.27 51	98.29 72	98.24 38	99.20 46	99.22 100	99.20 37	97.82 37	99.37 27	94.43 72	95.90 125	97.31 84	99.12 49	98.76 66	98.35 76	99.67 103	99.14 168

EPP-MVSNet		97.75 65	98.71 61	96.63 84	95.68 121	99.56 52	97.51 111	93.10 97	99.22 47	94.99 60	97.18 96	97.30 85	98.65 77	98.83 60	98.93 38	99.84 11	99.92 3

CDS-MVSNet		96.59 107	98.02 88	94.92 114	94.45 149	98.96 113	97.46 113	91.75 109	97.86 159	90.07 122	96.02 122	97.25 86	96.21 147	98.04 114	98.38 73	99.60 132	99.65 109
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SCA		94.95 139	97.44 106	92.04 161	95.55 128	99.16 103	96.26 148	79.30 207	99.02 81	85.73 147	98.18 71	97.13 87	97.69 111	96.03 184	94.91 188	97.69 206	97.65 199

HyFIR lowres test		95.99 119	96.56 135	95.32 110	97.99 70	99.65 22	96.54 140	88.86 155	98.44 132	89.77 126	84.14 208	97.05 88	99.03 56	98.55 84	98.19 88	99.73 57	99.86 19

PMMVS		97.52 72	98.39 69	96.51 88	95.82 115	98.73 129	97.80 101	93.05 98	98.76 114	94.39 75	99.07 35	97.03 89	98.55 83	98.31 95	97.61 113	99.43 168	99.21 163

baseline		97.45 75	98.70 62	95.99 100	95.89 111	99.36 82	98.29 83	91.37 119	99.21 49	92.99 100	98.40 65	96.87 90	97.96 101	98.60 80	98.60 61	99.42 170	99.86 19

Vis-MVSNet		96.16 116	98.22 78	93.75 132	95.33 136	99.70 17	97.27 119	90.85 127	98.30 138	85.51 149	95.72 131	96.45 91	93.69 197	98.70 71	99.00 33	99.84 11	99.69 96
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PatchmatchNet		94.70 144	97.08 122	91.92 166	95.53 129	98.85 117	95.77 154	79.54 205	98.95 86	85.98 144	98.52 59	96.45 91	97.39 119	95.32 192	94.09 198	97.32 209	97.38 202
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DeepC-MVS	97.63 4	98.33 49	98.57 63	98.04 43	98.62 58	99.65 22	99.45 26	98.15 25	99.51 17	92.80 102	95.74 129	96.44 93	99.46 22	99.37 20	99.50 2	99.78 33	99.81 33
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
Fast-Effi-MVS+-dtu		95.38 132	98.20 79	92.09 160	93.91 153	98.87 116	97.35 116	85.01 188	99.08 72	81.09 174	98.10 73	96.36 94	95.62 163	98.43 92	97.03 132	99.55 151	99.50 142

PatchMatch-RL		97.77 64	98.25 74	97.21 64	99.11 48	99.25 96	97.06 131	94.09 74	98.72 118	95.14 57	98.47 62	96.29 95	98.43 87	98.65 73	97.44 124	99.45 165	98.94 174

DCV-MVSNet		97.56 71	98.36 70	96.62 85	96.44 95	98.36 155	98.37 78	91.73 110	99.11 68	94.80 62	98.36 67	96.28 96	98.60 81	98.12 103	98.44 68	99.76 40	99.87 16

thisisatest0530		97.23 81	98.25 74	96.05 96	95.60 126	99.59 46	96.96 133	93.23 92	99.17 54	92.60 105	98.75 53	96.19 97	98.17 91	98.19 101	96.10 160	99.72 64	99.77 56

MVS_Test		97.30 79	98.54 64	95.87 101	95.74 117	99.28 94	98.19 88	91.40 118	99.18 53	91.59 115	98.17 72	96.18 98	98.63 79	98.61 77	98.55 63	99.66 108	99.78 48

tpmrst		93.86 163	95.88 153	91.50 173	95.69 120	98.62 135	95.64 157	79.41 206	98.80 107	83.76 157	95.63 132	96.13 99	97.25 120	92.92 207	92.31 206	97.27 210	96.74 208

tttt0517		97.23 81	98.24 77	96.04 97	95.60 126	99.60 44	96.94 134	93.23 92	99.15 59	92.56 106	98.74 54	96.12 100	98.17 91	98.21 99	96.10 160	99.73 57	99.78 48

MDTV_nov1_ep13		95.57 126	97.48 103	93.35 146	95.43 133	98.97 112	97.19 124	83.72 195	98.92 92	87.91 133	97.75 83	96.12 100	97.88 107	96.84 163	95.64 172	97.96 201	98.10 193

EPMVS		95.05 137	96.86 129	92.94 151	95.84 114	98.96 113	96.68 136	79.87 203	99.05 78	90.15 121	97.12 97	95.99 102	97.49 116	95.17 195	94.75 193	97.59 207	96.96 207

GBi-Net		96.98 90	98.00 89	95.78 102	93.81 156	97.98 165	98.09 92	91.32 120	98.80 107	93.92 80	97.21 93	95.94 103	97.89 104	98.07 109	98.34 78	99.68 95	99.67 102

test1		96.98 90	98.00 89	95.78 102	93.81 156	97.98 165	98.09 92	91.32 120	98.80 107	93.92 80	97.21 93	95.94 103	97.89 104	98.07 109	98.34 78	99.68 95	99.67 102

FMVSNet3		97.02 89	98.12 83	95.73 106	93.59 162	97.98 165	98.34 82	91.32 120	98.80 107	93.92 80	97.21 93	95.94 103	97.63 113	98.61 77	98.62 59	99.61 124	99.65 109

gg-mvs-nofinetune		90.85 198	94.14 177	87.02 204	94.89 144	99.25 96	98.64 64	76.29 218	88.24 219	57.50 223	79.93 214	95.45 106	95.18 177	98.77 65	98.07 94	99.62 122	99.24 161

CHOSEN 1792x2688		96.41 109	96.99 125	95.74 105	98.01 69	99.72 12	97.70 106	90.78 130	99.13 67	90.03 123	87.35 198	95.36 107	98.33 89	98.59 82	98.91 41	99.59 138	99.87 16

FMVSNet2		96.64 104	97.50 101	95.63 108	93.81 156	97.98 165	98.09 92	90.87 126	98.99 84	93.48 91	93.17 158	95.25 108	97.89 104	98.63 75	98.80 53	99.68 95	99.67 102

DI_MVS_plusplus_trai		96.90 93	97.49 102	96.21 93	95.61 124	99.40 77	98.72 62	92.11 102	99.14 62	92.98 101	93.08 161	95.14 109	98.13 95	98.05 113	97.91 101	99.74 49	99.73 76

thisisatest0515		94.61 148	96.89 127	91.95 165	92.00 179	98.47 145	92.01 200	90.73 132	98.18 143	83.96 152	94.51 142	95.13 110	93.38 198	97.38 146	94.74 194	99.61 124	99.79 42

tpm cat1		94.06 156	94.90 164	93.06 149	95.42 135	98.52 143	96.64 138	80.67 199	97.82 161	92.63 104	93.39 155	95.00 111	96.06 153	91.36 213	91.58 212	96.98 213	96.66 210

MVS-HIRNet		92.51 184	95.97 150	88.48 201	93.73 159	98.37 154	90.33 206	75.36 220	98.32 137	77.78 192	89.15 183	94.87 112	95.14 178	97.62 139	96.39 150	98.51 193	97.11 204

MAR-MVS		97.71 66	98.04 86	97.32 59	99.35 42	98.91 115	97.65 108	91.68 111	98.00 150	97.01 33	97.72 85	94.83 113	98.85 70	98.44 91	98.86 44	99.41 171	99.52 135
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
MIMVSNet		94.49 152	97.59 100	90.87 186	91.74 187	98.70 131	94.68 180	78.73 212	97.98 151	83.71 158	97.71 86	94.81 114	96.96 127	97.97 118	97.92 99	99.40 173	98.04 194

IterMVS-LS		96.12 117	97.48 103	94.53 118	95.19 138	97.56 190	97.15 125	89.19 153	99.08 72	88.23 129	94.97 137	94.73 115	97.84 109	97.86 125	98.26 84	99.60 132	99.88 14
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-LLR		95.50 129	97.32 113	93.37 144	95.49 131	98.74 127	96.44 145	90.82 128	98.18 143	82.75 165	96.60 111	94.67 116	95.54 166	98.09 106	96.00 162	99.20 184	98.93 175

TESTMET0.1,1		94.95 139	97.32 113	92.20 158	92.62 167	98.74 127	96.44 145	86.67 177	98.18 143	82.75 165	96.60 111	94.67 116	95.54 166	98.09 106	96.00 162	99.20 184	98.93 175

Anonymous20231211		97.10 86	97.06 123	97.14 65	96.32 97	99.52 59	98.16 89	93.76 81	98.84 101	95.98 43	90.92 170	94.58 118	98.90 64	97.72 133	98.10 93	99.71 74	99.75 68

Anonymous202405211			97.40 108		96.45 94	99.54 55	98.08 95	93.79 80	98.24 142		93.55 150	94.41 119	98.88 69	98.04 114	98.24 85	99.75 44	99.76 61

test-mter		94.86 142	97.32 113	92.00 163	92.41 172	98.82 118	96.18 150	86.35 181	98.05 148	82.28 168	96.48 115	94.39 120	95.46 170	98.17 102	96.20 156	99.32 178	99.13 169

Effi-MVS+-dtu		95.74 124	98.04 86	93.06 149	93.92 152	99.16 103	97.90 98	88.16 166	99.07 77	82.02 170	98.02 77	94.32 121	96.74 133	98.53 85	97.56 115	99.61 124	99.62 117

FC-MVSNet-train		97.04 88	97.91 92	96.03 98	96.00 108	98.41 151	96.53 142	93.42 88	99.04 80	93.02 99	98.03 76	94.32 121	97.47 117	97.93 120	97.77 109	99.75 44	99.88 14

LS3D		97.79 62	98.25 74	97.26 63	98.40 61	99.63 30	99.53 19	98.63 1	99.25 45	88.13 130	96.93 101	94.14 123	99.19 41	99.14 37	99.23 18	99.69 86	99.42 148

baseline2		96.36 111	97.82 94	94.65 117	94.60 148	99.09 106	96.45 144	89.63 148	98.36 136	91.29 118	97.60 88	94.13 124	96.37 144	98.45 89	97.70 110	99.54 155	99.41 149

PatchT		93.96 160	97.36 110	90.00 193	94.76 147	98.65 133	90.11 208	78.57 213	97.96 154	80.42 178	96.07 121	94.10 125	96.85 130	98.10 104	97.49 119	99.26 182	99.15 165

RPMNet		94.66 145	97.16 119	91.75 170	94.98 142	98.59 138	97.00 132	78.37 214	97.98 151	83.78 155	96.27 118	94.09 126	96.91 128	97.36 147	96.73 138	99.48 161	99.09 170

FMVSNet5		95.42 130	96.47 142	94.20 124	92.26 175	95.99 211	95.66 156	87.15 173	97.87 158	93.46 92	96.68 107	93.79 127	97.52 114	97.10 158	97.21 130	99.11 187	96.62 211

GeoE		95.98 121	97.24 118	94.51 119	95.02 141	99.38 78	98.02 97	87.86 169	98.37 135	87.86 134	92.99 163	93.54 128	98.56 82	98.61 77	97.92 99	99.73 57	99.85 22

MDTV_nov1_ep13_2view		92.44 186	95.66 156	88.68 199	91.05 205	97.92 169	92.17 199	79.64 204	98.83 102	76.20 196	91.45 167	93.51 129	95.04 179	95.68 190	93.70 201	97.96 201	98.53 184

CR-MVSNet		94.57 151	97.34 111	91.33 177	94.90 143	98.59 138	97.15 125	79.14 208	97.98 151	80.42 178	96.59 113	93.50 130	96.85 130	98.10 104	97.49 119	99.50 160	99.15 165

CVMVSNet		95.33 134	97.09 120	93.27 147	95.23 137	98.39 153	95.49 160	92.58 100	97.71 165	83.00 164	94.44 144	93.28 131	93.92 194	97.79 127	98.54 65	99.41 171	99.45 146

FMVSNet1		95.77 123	96.41 147	95.03 112	93.42 163	97.86 172	97.11 128	89.89 143	98.53 127	92.00 112	89.17 182	93.23 132	98.15 94	98.07 109	98.34 78	99.61 124	99.69 96

baseline1		97.58 70	98.05 85	97.02 72	96.21 103	99.45 68	97.71 105	93.71 85	98.47 131	95.75 46	98.78 50	93.20 133	98.91 63	98.52 86	98.44 68	99.81 21	99.53 132

dps		94.63 147	95.31 162	93.84 130	95.53 129	98.71 130	96.54 140	80.12 202	97.81 163	97.21 30	96.98 98	92.37 134	96.34 146	92.46 210	91.77 210	97.26 211	97.08 205

testgi		95.67 125	97.48 103	93.56 138	95.07 140	99.00 108	95.33 164	88.47 161	98.80 107	86.90 140	97.30 91	92.33 135	95.97 155	97.66 135	97.91 101	99.60 132	99.38 153

N_pmnet		92.21 194	94.60 171	89.42 198	91.88 182	97.38 199	89.15 212	89.74 147	97.89 157	73.75 205	87.94 195	92.23 136	93.85 195	96.10 182	93.20 203	98.15 200	97.43 201

IB-MVS	93.96 15	95.02 138	96.44 145	93.36 145	97.05 86	99.28 94	90.43 205	93.39 89	98.02 149	96.02 42	94.92 139	92.07 137	83.52 214	95.38 191	95.82 168	99.72 64	99.59 121
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
MVSTER		97.16 83	97.71 96	96.52 87	95.97 110	98.48 144	98.63 65	92.10 103	98.68 119	95.96 44	99.23 21	91.79 138	96.87 129	98.76 66	97.37 128	99.57 146	99.68 101

casdiffmvs		96.93 92	97.43 107	96.34 91	95.70 119	99.50 62	97.75 104	93.22 94	98.98 85	92.64 103	94.97 137	91.71 139	98.93 60	98.62 76	98.52 66	99.82 15	99.72 87

TAMVS		95.53 128	96.50 141	94.39 123	93.86 155	99.03 107	96.67 137	89.55 150	97.33 173	90.64 120	93.02 162	91.58 140	96.21 147	97.72 133	97.43 125	99.43 168	99.36 154

canonicalmvs		97.31 78	97.81 95	96.72 79	96.20 104	99.45 68	98.21 87	91.60 113	99.22 47	95.39 52	98.48 61	90.95 141	99.16 47	97.66 135	99.05 29	99.76 40	99.90 6

anonymousdsp		93.12 172	95.86 154	89.93 195	91.09 204	98.25 158	95.12 165	85.08 186	97.44 169	73.30 206	90.89 171	90.78 142	95.25 176	97.91 121	95.96 166	99.71 74	99.82 28

ET-MVSNet_ETH3D		96.17 115	96.99 125	95.21 111	88.53 212	98.54 141	98.28 84	92.61 99	98.85 97	93.60 90	99.06 36	90.39 143	98.63 79	95.98 186	96.68 140	99.61 124	99.41 149

PVSNet_BlendedMVS		97.51 73	97.71 96	97.28 61	98.06 66	99.61 39	97.31 117	95.02 53	99.08 72	95.51 49	98.05 74	90.11 144	98.07 97	98.91 54	98.40 71	99.72 64	99.78 48

PVSNet_Blended		97.51 73	97.71 96	97.28 61	98.06 66	99.61 39	97.31 117	95.02 53	99.08 72	95.51 49	98.05 74	90.11 144	98.07 97	98.91 54	98.40 71	99.72 64	99.78 48

pmnet_mix02		92.44 186	94.68 169	89.83 196	92.46 171	97.65 182	89.92 210	90.49 136	98.76 114	73.05 209	91.78 165	90.08 146	94.86 182	94.53 202	91.94 209	98.21 199	98.01 196

pmmvs4		95.09 136	95.90 152	94.14 125	92.29 174	97.70 176	95.45 161	90.31 137	98.60 121	90.70 119	93.25 156	89.90 147	96.67 136	97.13 156	95.42 175	99.44 167	99.28 157

pm-mvs1		94.27 153	95.57 157	92.75 152	92.58 168	98.13 163	94.87 173	90.71 133	96.70 190	83.78 155	89.94 178	89.85 148	94.96 181	97.58 140	97.07 131	99.61 124	99.72 87

diffmvs		96.83 94	97.33 112	96.25 92	95.76 116	99.34 87	98.06 96	93.22 94	99.43 22	92.30 109	96.90 102	89.83 149	98.55 83	98.00 117	98.14 89	99.64 116	99.70 92

test_part1		95.56 127	95.38 159	95.78 102	96.07 105	98.16 162	97.57 109	90.78 130	97.43 170	93.04 98	89.12 185	89.41 150	97.93 102	96.38 172	97.38 127	99.29 180	99.78 48

ECVR-MVS		97.27 80	97.09 120	97.48 56	96.95 88	99.79 4	98.48 70	94.42 68	99.17 54	96.28 40	93.54 151	89.39 151	98.89 67	99.03 43	99.09 24	99.88 4	99.61 120

test1111		97.09 87	96.83 130	97.39 57	96.92 90	99.81 3	98.44 74	94.45 67	99.17 54	95.85 45	92.10 164	88.97 152	98.78 71	99.02 45	99.11 23	99.88 4	99.63 115

Effi-MVS+		95.81 122	97.31 116	94.06 127	95.09 139	99.35 85	97.24 121	88.22 164	98.54 126	85.38 150	98.52 59	88.68 153	98.70 74	98.32 94	97.93 98	99.74 49	99.84 23

GA-MVS		93.93 161	96.31 148	91.16 181	93.61 160	98.79 119	95.39 163	90.69 134	98.25 141	73.28 207	96.15 120	88.42 154	94.39 186	97.76 130	95.35 176	99.58 142	99.45 146

EU-MVSNet		92.80 178	94.76 168	90.51 188	91.88 182	96.74 208	92.48 198	88.69 158	96.21 196	79.00 187	91.51 166	87.82 155	91.83 206	95.87 188	96.27 153	99.21 183	98.92 178

pmmvs6		91.90 196	92.53 203	91.17 180	91.81 185	97.63 183	93.23 193	88.37 163	93.43 215	80.61 176	77.32 216	87.47 156	94.12 189	96.58 166	95.72 170	98.88 192	99.53 132

UniMVSNet_NR-MVSNet		94.59 149	95.47 158	93.55 139	91.85 184	97.89 171	95.03 166	92.00 105	97.33 173	86.12 142	93.19 157	87.29 157	96.60 139	96.12 181	96.70 139	99.72 64	99.80 35

Fast-Effi-MVS+		95.38 132	96.52 138	94.05 128	94.15 151	99.14 105	97.24 121	86.79 175	98.53 127	87.62 136	94.51 142	87.06 158	98.76 72	98.60 80	98.04 96	99.72 64	99.77 56

CLD-MVS		96.74 98	96.51 139	97.01 74	96.71 92	98.62 135	98.73 61	94.38 70	98.94 88	94.46 71	97.33 89	87.03 159	98.07 97	97.20 154	96.87 136	99.72 64	99.54 131
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP-MVS		96.37 110	96.58 134	96.13 95	97.31 80	98.44 148	98.45 73	95.22 51	98.86 95	88.58 128	98.33 68	87.00 160	97.67 112	97.23 152	96.56 145	99.56 149	99.62 117

thres100view900		96.72 99	96.47 142	97.00 75	96.31 98	99.52 59	98.28 84	94.01 75	97.35 171	94.52 67	95.90 125	86.93 161	99.09 53	98.07 109	97.87 103	99.81 21	99.63 115

tfpn200view9		96.75 97	96.51 139	97.03 70	96.31 98	99.67 18	98.41 75	93.99 77	97.35 171	94.52 67	95.90 125	86.93 161	99.14 48	98.26 96	97.80 107	99.82 15	99.70 92

thres200		96.76 96	96.53 137	97.03 70	96.31 98	99.67 18	98.37 78	93.99 77	97.68 166	94.49 70	95.83 128	86.77 163	99.18 44	98.26 96	97.82 106	99.82 15	99.66 106

ACMM	96.26 9	96.67 103	96.69 132	96.66 81	97.29 81	98.46 146	96.48 143	95.09 52	99.21 49	93.19 95	98.78 50	86.73 164	98.17 91	97.84 126	96.32 152	99.74 49	99.49 143
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LGP-MVS_train		96.23 113	96.89 127	95.46 109	97.32 78	98.77 122	98.81 59	93.60 86	98.58 123	85.52 148	99.08 34	86.67 165	97.83 110	97.87 124	97.51 117	99.69 86	99.73 76

ACMP	96.25 10	96.62 106	96.72 131	96.50 89	96.96 87	98.75 126	97.80 101	94.30 72	98.85 97	93.12 96	98.78 50	86.61 166	97.23 122	97.73 132	96.61 143	99.62 122	99.71 90
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
new_pmnet		90.45 202	92.84 201	87.66 202	88.96 211	96.16 210	88.71 213	84.66 190	97.56 167	71.91 213	85.60 206	86.58 167	93.28 199	96.07 183	93.54 202	98.46 194	94.39 215

OPM-MVS		96.22 114	95.85 155	96.65 82	97.75 71	98.54 141	99.00 52	95.53 48	96.88 184	89.88 124	95.95 124	86.46 168	98.07 97	97.65 137	96.63 142	99.67 103	98.83 181
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
xxxxxxxxxxxxxcwj		98.14 55	97.38 109	99.03 17	99.65 19	99.41 75	98.87 55	98.24 18	99.14 62	98.73 5	99.11 29	86.38 169	98.92 61	99.22 29	98.84 48	99.76 40	99.56 128

thres400		96.71 100	96.45 144	97.02 72	96.28 101	99.63 30	98.41 75	94.00 76	97.82 161	94.42 73	95.74 129	86.26 170	99.18 44	98.20 100	97.79 108	99.81 21	99.70 92

UniMVSNet (Re)		94.58 150	95.34 160	93.71 134	92.25 176	98.08 164	94.97 168	91.29 124	97.03 182	87.94 132	93.97 148	86.25 171	96.07 152	96.27 178	95.97 165	99.72 64	99.79 42

CostFormer		94.25 155	94.88 165	93.51 141	95.43 133	98.34 156	96.21 149	80.64 200	97.94 155	94.01 78	98.30 69	86.20 172	97.52 114	92.71 208	92.69 204	97.23 212	98.02 195

thres600view7		96.69 101	96.43 146	97.00 75	96.28 101	99.67 18	98.41 75	93.99 77	97.85 160	94.29 76	95.96 123	85.91 173	99.19 41	98.26 96	97.63 112	99.82 15	99.73 76

SixPastTwentyTwo		93.44 168	95.32 161	91.24 179	92.11 177	98.40 152	92.77 196	88.64 160	98.09 147	77.83 191	93.51 153	85.74 174	96.52 142	96.91 161	94.89 191	99.59 138	99.73 76

TSAR-MVS + COLMAP		96.79 95	96.55 136	97.06 68	97.70 73	98.46 146	99.07 46	96.23 45	99.38 25	91.32 117	98.80 48	85.61 175	98.69 76	97.64 138	96.92 135	99.37 175	99.06 172

ACMH+	95.51 13	95.40 131	96.00 149	94.70 116	96.33 96	98.79 119	96.79 135	91.32 120	98.77 113	87.18 138	95.60 133	85.46 176	96.97 126	97.15 155	96.59 144	99.59 138	99.65 109

test20.03		90.65 201	93.71 189	87.09 203	90.44 208	96.24 209	89.74 211	85.46 185	95.59 208	72.99 210	90.68 173	85.33 177	84.41 213	95.94 187	95.10 184	99.52 158	97.06 206

tmp_tt				82.25 212	97.73 72	88.71 220	80.18 220	68.65 223	99.15 59	86.98 139	99.47 10	85.31 178	68.35 221	87.51 215	83.81 217	91.64 220

WR-MVS_H		93.54 166	94.67 170	92.22 156	91.95 180	97.91 170	94.58 184	88.75 157	96.64 191	83.88 154	90.66 174	85.13 179	94.40 185	96.54 168	95.91 167	99.73 57	99.89 10

WR-MVS		93.43 169	94.48 173	92.21 157	91.52 196	97.69 178	94.66 182	89.98 141	96.86 185	83.43 159	90.12 176	85.03 180	93.94 193	96.02 185	95.82 168	99.71 74	99.82 28

CMPMVS	70.31 18	90.74 199	91.06 207	90.36 191	97.32 78	97.43 196	92.97 195	87.82 170	93.50 214	75.34 202	83.27 210	84.90 181	92.19 205	92.64 209	91.21 213	96.50 216	94.46 214
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20231206		90.70 200	93.93 185	86.92 205	90.21 210	96.79 206	90.30 207	86.61 179	96.05 201	69.25 214	88.46 190	84.86 182	85.86 212	97.11 157	96.47 149	99.30 179	97.80 198

v10		92.79 179	94.06 181	91.31 178	91.78 186	97.29 202	94.87 173	86.10 182	96.97 183	79.82 183	88.16 192	84.56 183	95.63 162	96.33 176	95.31 177	99.65 112	99.80 35

v1144		92.81 177	94.03 182	91.40 176	91.68 188	97.60 187	94.73 177	88.40 162	96.71 189	78.48 189	88.14 193	84.46 184	95.45 171	96.31 177	95.22 180	99.65 112	99.76 61

Baseline_NR-MVSNet		93.87 162	93.98 184	93.75 132	91.66 189	97.02 203	95.53 159	91.52 117	97.16 179	87.77 135	87.93 196	83.69 185	96.35 145	95.10 197	97.23 129	99.68 95	99.73 76

ACMH	95.42 14	95.27 135	95.96 151	94.45 121	96.83 91	98.78 121	94.72 178	91.67 112	98.95 86	86.82 141	96.42 116	83.67 186	97.00 125	97.48 144	96.68 140	99.69 86	99.76 61
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TransMVSNet (Re)		93.45 167	94.08 180	92.72 153	92.83 165	97.62 186	94.94 169	91.54 116	95.65 207	83.06 163	88.93 186	83.53 187	94.25 187	97.41 145	97.03 132	99.67 103	98.40 190

pmmvs5		92.71 183	94.27 176	90.90 185	91.42 198	97.74 175	93.23 193	86.66 178	95.99 203	78.96 188	91.45 167	83.44 188	95.55 165	97.30 150	95.05 185	99.58 142	98.93 175

V42		93.05 173	93.90 187	92.04 161	91.91 181	97.66 180	94.91 170	89.91 142	96.85 186	80.58 177	89.66 179	83.43 189	95.37 172	95.03 199	94.90 189	99.59 138	99.78 48

EG-PatchMatch MVS		92.45 185	93.92 186	90.72 187	92.56 169	98.43 150	94.88 172	84.54 191	97.18 176	79.55 184	86.12 205	83.23 190	93.15 201	97.22 153	96.00 162	99.67 103	99.27 159

tpm		92.38 190	94.79 167	89.56 197	94.30 150	97.50 193	94.24 190	78.97 211	97.72 164	74.93 203	97.97 78	82.91 191	96.60 139	93.65 206	94.81 192	98.33 197	98.98 173

v1921920		92.36 192	93.57 191	90.94 184	91.39 199	97.39 198	94.70 179	87.63 171	96.60 192	76.63 195	86.98 201	82.89 192	95.75 158	96.26 179	95.14 183	99.55 151	99.73 76

v8		92.87 175	93.87 188	91.72 172	92.05 178	97.50 193	94.79 176	88.20 165	96.85 186	80.11 181	90.01 177	82.86 193	95.48 168	95.15 196	94.90 189	99.66 108	99.80 35

v1192		92.43 188	93.61 190	91.05 182	91.53 195	97.43 196	94.61 183	87.99 167	96.60 192	76.72 194	87.11 200	82.74 194	95.85 157	96.35 175	95.30 178	99.60 132	99.74 72

v144192		92.38 190	93.55 193	91.00 183	91.44 197	97.47 195	94.27 188	87.41 172	96.52 194	78.03 190	87.50 197	82.65 195	95.32 173	95.82 189	95.15 182	99.55 151	99.78 48

TranMVSNet+NR-MVSNet		93.67 165	94.14 177	93.13 148	91.28 203	97.58 188	95.60 158	91.97 106	97.06 180	84.05 151	90.64 175	82.22 196	96.17 150	94.94 200	96.78 137	99.69 86	99.78 48

CP-MVSNet		93.25 170	94.00 183	92.38 155	91.65 191	97.56 190	94.38 187	89.20 152	96.05 201	83.16 162	89.51 180	81.97 197	96.16 151	96.43 170	96.56 145	99.71 74	99.89 10

v1240		91.99 195	93.33 196	90.44 189	91.29 201	97.30 201	94.25 189	86.79 175	96.43 195	75.49 201	86.34 204	81.85 198	95.29 174	96.42 171	95.22 180	99.52 158	99.73 76

tfpnnormal		93.85 164	94.12 179	93.54 140	93.22 164	98.24 159	95.45 161	91.96 107	94.61 210	83.91 153	90.74 172	81.75 199	97.04 124	97.49 143	96.16 158	99.68 95	99.84 23

v2v482		92.77 180	93.52 194	91.90 168	91.59 194	97.63 183	94.57 185	90.31 137	96.80 188	79.22 185	88.74 188	81.55 200	96.04 154	95.26 193	94.97 187	99.66 108	99.69 96

DU-MVS		93.98 159	94.44 174	93.44 142	91.66 189	97.77 173	95.03 166	91.57 114	97.17 177	86.12 142	93.13 159	81.13 201	96.60 139	95.10 197	97.01 134	99.67 103	99.80 35

test2506		97.16 83	96.68 133	97.73 49	96.95 88	99.79 4	98.48 70	94.42 68	99.17 54	97.74 24	99.15 25	80.93 202	98.89 67	99.03 43	99.09 24	99.88 4	99.62 117

USDC		94.26 154	94.83 166	93.59 137	96.02 106	98.44 148	97.84 99	88.65 159	98.86 95	82.73 167	94.02 146	80.56 203	96.76 132	97.28 151	96.15 159	99.55 151	98.50 185

NR-MVSNet		94.01 157	94.51 172	93.44 142	92.56 169	97.77 173	95.67 155	91.57 114	97.17 177	85.84 145	93.13 159	80.53 204	95.29 174	97.01 159	96.17 157	99.69 86	99.75 68

TinyColmap		94.00 158	94.35 175	93.60 136	95.89 111	98.26 157	97.49 112	88.82 156	98.56 125	83.21 161	91.28 169	80.48 205	96.68 135	97.34 148	96.26 155	99.53 157	98.24 191

gm-plane-assit		89.44 205	92.82 202	85.49 208	91.37 200	95.34 214	79.55 222	82.12 196	91.68 218	64.79 220	87.98 194	80.26 206	95.66 161	98.51 88	97.56 115	99.45 165	98.41 187

v148		92.36 192	92.88 199	91.75 170	91.63 192	97.66 180	92.64 197	90.55 135	96.09 199	83.34 160	88.19 191	80.00 207	92.74 202	93.98 205	94.58 195	99.58 142	99.69 96

test_method		87.27 209	91.58 205	82.25 212	75.65 223	87.52 222	86.81 216	72.60 221	97.51 168	73.20 208	85.07 207	79.97 208	88.69 209	97.31 149	95.24 179	96.53 215	98.41 187

PS-CasMVS		92.72 181	93.36 195	91.98 164	91.62 193	97.52 192	94.13 191	88.98 154	95.94 204	81.51 173	87.35 198	79.95 209	95.91 156	96.37 173	96.49 147	99.70 83	99.89 10

TDRefinement		93.04 174	93.57 191	92.41 154	96.58 93	98.77 122	97.78 103	91.96 107	98.12 146	80.84 175	89.13 184	79.87 210	87.78 210	96.44 169	94.50 196	99.54 155	98.15 192

DeepMVS_CX						96.85 205	87.43 215	89.27 151	98.30 138	75.55 200	95.05 136	79.47 211	92.62 204	89.48 214		95.18 219	95.96 212

LTVRE_ROB	93.20 16	92.84 176	94.92 163	90.43 190	92.83 165	98.63 134	97.08 130	87.87 168	97.91 156	68.42 216	93.54 151	79.46 212	96.62 138	97.55 141	97.40 126	99.74 49	99.92 3
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
PEN-MVS		92.72 181	93.20 197	92.15 159	91.29 201	97.31 200	94.67 181	89.81 144	96.19 197	81.83 171	88.58 189	79.06 213	95.61 164	95.21 194	96.27 153	99.72 64	99.82 28

MIMVSNet1		88.61 206	90.68 208	86.19 207	81.56 219	95.30 215	87.78 214	85.98 183	94.19 213	72.30 212	78.84 215	78.90 214	90.06 207	96.59 165	95.47 173	99.46 164	95.49 213

v7n		91.61 197	92.95 198	90.04 192	90.56 207	97.69 178	93.74 192	85.59 184	95.89 205	76.95 193	86.60 203	78.60 215	93.76 196	97.01 159	94.99 186	99.65 112	99.87 16

DTE-MVSNet		92.42 189	92.85 200	91.91 167	90.87 206	96.97 204	94.53 186	89.81 144	95.86 206	81.59 172	88.83 187	77.88 216	95.01 180	94.34 204	96.35 151	99.64 116	99.73 76

pmmvs3		88.19 207	91.27 206	84.60 210	85.60 216	93.66 217	85.68 217	81.13 198	92.36 217	63.66 222	89.51 180	77.10 217	93.22 200	96.37 173	92.40 205	98.30 198	97.46 200

UniMVSNet_ETH3D		93.15 171	92.33 204	94.11 126	93.91 153	98.61 137	94.81 175	90.98 125	97.06 180	87.51 137	82.27 212	76.33 218	97.87 108	94.79 201	97.47 122	99.56 149	99.81 33

FPMVS		83.82 211	84.61 213	82.90 211	90.39 209	90.71 219	90.85 204	84.10 194	95.47 209	65.15 218	83.44 209	74.46 219	75.48 216	81.63 217	79.42 219	91.42 221	87.14 219

PMVS	72.60 17	76.39 214	77.66 217	74.92 215	81.04 220	69.37 227	68.47 224	80.54 201	85.39 220	65.07 219	73.52 217	72.91 220	65.67 222	80.35 219	76.81 220	88.71 222	85.25 222
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmmvs-eth3d		89.81 203	89.65 210	90.00 193	86.94 214	95.38 213	91.08 201	86.39 180	94.57 211	82.27 169	83.03 211	64.94 221	93.96 192	96.57 167	93.82 200	99.35 176	99.24 161

new-patchmatchnet		86.12 210	87.30 212	84.74 209	86.92 215	95.19 216	83.57 219	84.42 193	92.67 216	65.66 217	80.32 213	64.72 222	89.41 208	92.33 212	89.21 214	98.43 195	96.69 209

MDA-MVSNet-bldmvs		87.84 208	89.22 211	86.23 206	81.74 218	96.77 207	83.74 218	89.57 149	94.50 212	72.83 211	96.64 109	64.47 223	92.71 203	81.43 218	92.28 207	96.81 214	98.47 186

PM-MVS		89.55 204	90.30 209	88.67 200	87.06 213	95.60 212	90.88 203	84.51 192	96.14 198	75.75 197	86.89 202	63.47 224	94.64 183	96.85 162	93.89 199	99.17 186	99.29 156

Gipuma		81.40 212	81.78 214	80.96 214	83.21 217	85.61 223	79.73 221	76.25 219	97.33 173	64.21 221	55.32 220	55.55 225	86.04 211	92.43 211	92.20 208	96.32 217	93.99 216
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.26 213	79.47 216	74.70 216	76.00 222	88.37 221	74.22 223	76.34 217	78.31 221	54.13 224	69.96 218	52.50 226	70.14 220	84.83 216	88.71 215	97.35 208	93.58 217

EMVS		68.12 217	68.11 219	68.14 218	75.51 224	71.76 225	55.38 227	77.20 216	77.78 222	37.79 227	53.59 221	43.61 227	74.72 217	67.05 222	76.70 221	88.27 224	86.24 220

E-PMN		68.30 216	68.43 218	68.15 217	74.70 225	71.56 226	55.64 226	77.24 215	77.48 223	39.46 226	51.95 223	41.68 228	73.28 218	70.65 221	79.51 218	88.61 223	86.20 221

MVE	67.97 19	65.53 218	67.43 220	63.31 219	59.33 226	74.20 224	53.09 228	70.43 222	66.27 224	43.13 225	45.98 224	30.62 229	70.65 219	79.34 220	86.30 216	83.25 225	89.33 218
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ambc			80.99 215		80.04 221	90.84 218	90.91 202		96.09 199	74.18 204	62.81 219	30.59 230	82.44 215	96.25 180	91.77 210	95.91 218	98.56 183

testmvs		31.24 219	40.15 221	20.86 221	12.61 227	17.99 228	25.16 229	13.30 224	48.42 225	24.82 228	53.07 222	30.13 231	28.47 223	42.73 223	37.65 222	20.79 226	51.04 223

test123		26.75 220	34.25 222	18.01 222	7.93 228	17.18 229	24.85 230	12.36 225	44.83 226	16.52 229	41.80 225	18.10 232	28.29 224	33.08 224	34.79 223	18.10 227	49.95 224

uanet_test		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet-low-res		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

RE-MVS-def										69.05 215

our_test_3					92.30 173	97.58 188	90.09 209

Patchmatch-RL test							66.86 225

NP-MVS									98.57 124

Patchmtry						98.59 138	97.15 125	79.14 208		80.42 178

High-resolution multi-view benchmark