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.

MED-MVS		99.49 1	99.57 5	99.39 1	99.71 7	99.65 23	99.63 12	98.29 12	99.50 19	99.40 1	99.69 5	99.94 25	99.50 16	99.50 13	99.06 29	99.83 15	99.64 125

APDe-MVS		99.49 1	99.64 1	99.32 3	99.74 4	99.74 12	99.75 1	98.34 4	99.56 11	98.72 7	99.57 9	99.97 8	99.53 15	99.65 2	99.25 16	99.84 12	99.77 58
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		99.45 3	99.54 8	99.35 2	99.72 6	99.76 6	99.63 12	98.37 2	99.63 8	99.03 4	98.95 41	99.98 2	99.60 7	99.60 7	99.05 31	99.74 54	99.79 45
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
SED-MVS		99.44 4	99.58 4	99.28 4	99.69 8	99.76 6	99.62 15	98.35 3	99.51 17	99.05 3	99.60 8	99.98 2	99.28 38	99.61 6	98.83 52	99.70 90	99.77 58

DVP-MVS++		99.41 5	99.64 1	99.14 8	99.69 8	99.75 9	99.64 8	98.33 6	99.67 5	98.10 14	99.66 6	99.99 1	99.33 31	99.62 5	98.86 47	99.74 54	99.90 7

DPE-MVS		99.39 6	99.55 7	99.20 5	99.63 21	99.71 16	99.66 6	98.33 6	99.29 41	98.40 12	99.64 7	99.98 2	99.31 34	99.56 9	98.96 40	99.85 10	99.70 102
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SMA-MVS		99.38 7	99.60 3	99.12 10	99.76 2	99.62 34	99.39 31	98.23 19	99.52 16	98.03 18	99.45 13	99.98 2	99.64 5	99.58 8	99.30 12	99.68 102	99.76 64
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
MSP-MVS		99.34 8	99.52 11	99.14 8	99.68 13	99.75 9	99.64 8	98.31 9	99.44 22	98.10 14	99.28 20	99.98 2	99.30 36	99.34 24	99.05 31	99.81 24	99.79 45
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
HFP-MVS		99.32 9	99.53 10	99.07 14	99.69 8	99.59 46	99.63 12	98.31 9	99.56 11	97.37 27	99.27 21	99.97 8	99.70 3	99.35 23	99.24 18	99.71 82	99.76 64

ACMMPR		99.30 10	99.54 8	99.03 17	99.66 17	99.64 28	99.68 4	98.25 15	99.56 11	97.12 31	99.19 23	99.95 17	99.72 1	99.43 17	99.25 16	99.72 71	99.77 58

TSAR-MVS + MP.		99.27 11	99.57 5	98.92 23	98.78 55	99.53 56	99.72 2	98.11 29	99.73 3	97.43 26	99.15 26	99.96 12	99.59 9	99.73 1	99.07 27	99.88 4	99.82 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CP-MVS		99.27 11	99.44 18	99.08 13	99.62 23	99.58 49	99.53 20	98.16 22	99.21 54	97.79 21	99.15 26	99.96 12	99.59 9	99.54 11	98.86 47	99.78 35	99.74 77

SD-MVS		99.25 13	99.50 13	98.96 21	98.79 54	99.55 54	99.33 34	98.29 12	99.75 2	97.96 19	99.15 26	99.95 17	99.61 6	99.17 33	99.06 29	99.81 24	99.84 25
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
APD-MVS		99.25 13	99.38 24	99.09 12	99.69 8	99.58 49	99.56 19	98.32 8	98.85 106	97.87 20	98.91 44	99.92 29	99.30 36	99.45 16	99.38 8	99.79 32	99.58 135
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		99.23 15	99.28 33	99.17 6	99.65 19	99.34 97	99.46 26	98.21 20	99.28 42	98.47 9	98.89 46	99.94 25	99.50 16	99.42 18	98.61 62	99.73 62	99.52 147

SteuartSystems-ACMMP		99.20 16	99.51 12	98.83 27	99.66 17	99.66 22	99.71 3	98.12 28	99.14 69	96.62 34	99.16 25	99.98 2	99.12 50	99.63 3	99.19 22	99.78 35	99.83 29
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		99.18 17	99.32 30	99.03 17	99.65 19	99.41 83	98.87 55	98.24 18	99.14 69	98.73 6	99.11 30	99.92 29	98.92 63	99.22 29	98.84 51	99.76 42	99.56 141

DeepC-MVS_fast	98.34 1	99.17 18	99.45 15	98.85 25	99.55 30	99.37 90	99.64 8	98.05 32	99.53 14	96.58 35	98.93 42	99.92 29	99.49 19	99.46 15	99.32 11	99.80 31	99.64 125
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSLP-MVS++		99.15 19	99.24 36	99.04 16	99.52 33	99.49 64	99.09 45	98.07 30	99.37 28	98.47 9	97.79 84	99.89 36	99.50 16	98.93 51	99.45 4	99.61 134	99.76 64

CPTT-MVS		99.14 20	99.20 38	99.06 15	99.58 26	99.53 56	99.45 27	97.80 37	99.19 57	98.32 13	98.58 59	99.95 17	99.60 7	99.28 27	98.20 94	99.64 126	99.69 106

MCST-MVS		99.11 21	99.27 34	98.93 22	99.67 14	99.33 100	99.51 22	98.31 9	99.28 42	96.57 36	99.10 32	99.90 34	99.71 2	99.19 32	98.35 79	99.82 17	99.71 99

HPM-MVS++		99.10 22	99.30 32	98.86 24	99.69 8	99.48 65	99.59 17	98.34 4	99.26 46	96.55 37	99.10 32	99.96 12	99.36 29	99.25 28	98.37 78	99.64 126	99.66 118

PHI-MVS		99.08 23	99.43 21	98.67 29	99.15 46	99.59 46	99.11 43	97.35 40	99.14 69	97.30 28	99.44 14	99.96 12	99.32 33	98.89 56	99.39 7	99.79 32	99.58 135

MP-MVS		99.07 24	99.36 26	98.74 28	99.63 21	99.57 51	99.66 6	98.25 15	99.00 91	95.62 47	98.97 39	99.94 25	99.54 14	99.51 12	98.79 56	99.71 82	99.73 83
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
AdaColmap		99.06 25	98.98 52	99.15 7	99.60 25	99.30 103	99.38 32	98.16 22	99.02 89	98.55 8	98.71 55	99.57 57	99.58 12	99.09 38	97.84 115	99.64 126	99.36 165

ACMMP_NAP		99.05 26	99.45 15	98.58 31	99.73 5	99.60 44	99.64 8	98.28 14	99.23 49	94.57 68	99.35 18	99.97 8	99.55 13	99.63 3	98.66 59	99.70 90	99.74 77

NCCC		99.05 26	99.08 43	99.02 19	99.62 23	99.38 86	99.43 30	98.21 20	99.36 32	97.66 24	97.79 84	99.90 34	99.45 23	99.17 33	98.43 73	99.77 40	99.51 152

CNLPA		99.03 28	99.05 46	99.01 20	99.27 44	99.22 113	99.03 49	97.98 33	99.34 36	99.00 5	98.25 73	99.71 50	99.31 34	98.80 61	98.82 54	99.48 171	99.17 176

PLC	97.93 2	99.02 29	98.94 53	99.11 11	99.46 35	99.24 109	99.06 47	97.96 34	99.31 38	99.16 2	97.90 82	99.79 46	99.36 29	98.71 71	98.12 98	99.65 121	99.52 147
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
X-MVS		98.93 30	99.37 25	98.42 32	99.67 14	99.62 34	99.60 16	98.15 24	99.08 80	93.81 86	98.46 66	99.95 17	99.59 9	99.49 14	99.21 21	99.68 102	99.75 72

CSCG		98.90 31	98.93 54	98.85 25	99.75 3	99.72 13	99.49 23	96.58 43	99.38 26	98.05 17	98.97 39	97.87 78	99.49 19	97.78 135	98.92 43	99.78 35	99.90 7

PGM-MVS		98.86 32	99.35 29	98.29 35	99.77 1	99.63 31	99.67 5	95.63 46	98.66 130	95.27 55	99.11 30	99.82 43	99.67 4	99.33 25	99.19 22	99.73 62	99.74 77

OMC-MVS		98.84 33	99.01 51	98.65 30	99.39 37	99.23 112	99.22 36	96.70 42	99.40 25	97.77 22	97.89 83	99.80 44	99.21 39	99.02 44	98.65 60	99.57 156	99.07 183

MGCNet		98.81 34	99.44 18	98.08 40	98.83 52	99.75 9	99.58 18	95.53 47	99.76 1	96.48 39	99.70 4	98.64 67	98.21 102	99.00 47	99.33 10	99.82 17	99.90 7

TSAR-MVS + ACMM		98.77 35	99.45 15	97.98 44	99.37 38	99.46 67	99.44 29	98.13 27	99.65 6	92.30 114	98.91 44	99.95 17	99.05 56	99.42 18	98.95 41	99.58 152	99.82 30

ACMMP		98.74 36	99.03 50	98.40 33	99.36 40	99.64 28	99.20 37	97.75 38	98.82 113	95.24 56	98.85 47	99.87 38	99.17 46	98.74 69	97.50 130	99.71 82	99.76 64
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 37	99.11 41	98.28 36	99.36 40	99.35 95	99.48 25	97.96 34	98.83 111	93.86 85	98.70 56	99.86 39	99.44 24	99.08 40	98.38 76	99.61 134	99.58 135

3Dnovator+	96.92 7	98.71 38	99.05 46	98.32 34	99.53 31	99.34 97	99.06 47	94.61 60	99.65 6	97.49 25	96.75 108	99.86 39	99.44 24	98.78 63	99.30 12	99.81 24	99.67 114

MVS_111021_LR		98.67 39	99.41 23	97.81 47	99.37 38	99.53 56	98.51 68	95.52 49	99.27 44	94.85 63	99.56 10	99.69 51	99.04 57	99.36 21	98.88 46	99.60 142	99.58 135

3Dnovator	96.92 7	98.67 39	99.05 46	98.23 38	99.57 27	99.45 69	99.11 43	94.66 59	99.69 4	96.80 33	96.55 119	99.61 54	99.40 26	98.87 59	99.49 3	99.85 10	99.66 118

TSAR-MVS + GP.		98.66 41	99.36 26	97.85 46	97.16 83	99.46 67	99.03 49	94.59 63	99.09 77	97.19 30	99.73 3	99.95 17	99.39 27	98.95 49	98.69 58	99.75 48	99.65 121

QAPM		98.62 42	99.04 49	98.13 39	99.57 27	99.48 65	99.17 39	94.78 56	99.57 10	96.16 41	96.73 109	99.80 44	99.33 31	98.79 62	99.29 14	99.75 48	99.64 125

MVS_111021_HR		98.59 43	99.36 26	97.68 49	99.42 36	99.61 39	98.14 93	94.81 55	99.31 38	95.00 61	99.51 11	99.79 46	99.00 60	98.94 50	98.83 52	99.69 94	99.57 140

SPE-MVS-test		98.58 44	99.42 22	97.60 53	98.52 59	99.91 1	98.60 65	94.60 62	99.37 28	94.62 67	99.40 16	99.16 62	99.39 27	99.36 21	98.85 50	99.90 3	99.92 3

CS-MVS		98.56 45	99.32 30	97.68 49	98.28 64	99.89 2	98.71 62	94.53 65	99.41 24	95.43 51	99.05 37	98.66 66	99.19 41	99.21 30	99.07 27	99.93 1	99.94 1

CANet		98.46 46	99.16 39	97.64 51	98.48 60	99.64 28	99.35 33	94.71 58	99.53 14	95.17 57	97.63 90	99.59 55	98.38 99	98.88 58	98.99 38	99.74 54	99.86 21

CDPH-MVS		98.41 47	99.10 42	97.61 52	99.32 43	99.36 92	99.49 23	96.15 45	98.82 113	91.82 121	98.41 67	99.66 52	99.10 52	98.93 51	98.97 39	99.75 48	99.58 135

TAPA-MVS	97.53 5	98.41 47	98.84 58	97.91 45	99.08 48	99.33 100	99.15 40	97.13 41	99.34 36	93.20 97	97.75 86	99.19 61	99.20 40	98.66 73	98.13 97	99.66 116	99.48 156
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DeepPCF-MVS	97.74 3	98.34 49	99.46 14	97.04 67	98.82 53	99.33 100	96.28 159	97.47 39	99.58 9	94.70 66	98.99 38	99.85 41	97.24 133	99.55 10	99.34 9	97.73 218	99.56 141

DeepC-MVS	97.63 4	98.33 50	98.57 63	98.04 42	98.62 58	99.65 23	99.45 27	98.15 24	99.51 17	92.80 106	95.74 139	96.44 93	99.46 22	99.37 20	99.50 2	99.78 35	99.81 35
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DPM-MVS		98.31 51	98.53 65	98.05 41	98.76 56	98.77 135	99.13 41	98.07 30	99.10 76	94.27 79	96.70 110	99.84 42	98.70 80	97.90 129	98.11 99	99.40 184	99.28 168

MSDG		98.27 52	98.29 72	98.24 37	99.20 45	99.22 113	99.20 37	97.82 36	99.37 28	94.43 74	95.90 132	97.31 84	99.12 50	98.76 65	98.35 79	99.67 111	99.14 180

EC-MVSNet		98.22 53	99.44 18	96.79 76	95.62 131	99.56 52	99.01 51	92.22 111	99.17 59	94.51 71	99.41 15	99.62 53	99.49 19	99.16 35	99.26 15	99.91 2	99.94 1

DELS-MVS		98.19 54	98.77 60	97.52 54	98.29 63	99.71 16	99.12 42	94.58 64	98.80 116	95.38 54	96.24 124	98.24 75	97.92 114	99.06 41	99.52 1	99.82 17	99.79 45
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
PCF-MVS	97.50 6	98.18 55	98.35 71	97.99 43	98.65 57	99.36 92	98.94 53	98.14 26	98.59 132	93.62 91	96.61 115	99.76 49	99.03 58	97.77 136	97.45 135	99.57 156	98.89 191
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ETV-MVS		98.05 56	99.25 35	96.65 81	95.61 132	99.61 39	98.26 86	93.52 86	98.90 102	93.74 90	99.32 19	99.20 60	98.90 66	99.21 30	98.72 57	99.87 8	99.79 45

EPNet		98.05 56	98.86 56	97.10 65	99.02 49	99.43 76	98.47 71	94.73 57	99.05 86	95.62 47	98.93 42	97.62 82	95.48 180	98.59 83	98.55 64	99.29 191	99.84 25
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CHOSEN 280x420		97.99 58	99.24 36	96.53 86	98.34 62	99.61 39	98.36 80	89.80 157	99.27 44	95.08 60	99.81 1	98.58 69	98.64 88	99.02 44	98.92 43	98.93 203	99.48 156

OpenMVS	96.23 11	97.95 59	98.45 68	97.35 57	99.52 33	99.42 80	98.91 54	94.61 60	98.87 103	92.24 116	94.61 153	99.05 65	99.10 52	98.64 75	99.05 31	99.74 54	99.51 152

IS_MVSNet		97.86 60	98.86 56	96.68 79	96.02 106	99.72 13	98.35 81	93.37 91	98.75 127	94.01 80	96.88 107	98.40 72	98.48 97	99.09 38	99.42 5	99.83 15	99.80 37

LS3D		97.79 61	98.25 74	97.26 62	98.40 61	99.63 31	99.53 20	98.63 1	99.25 48	88.13 142	96.93 105	94.14 124	99.19 41	99.14 36	99.23 19	99.69 94	99.42 160

COLMAP_ROB	96.15 12	97.78 62	98.17 80	97.32 58	98.84 51	99.45 69	99.28 35	95.43 50	99.48 20	91.80 122	94.83 152	98.36 73	98.90 66	98.09 111	97.85 114	99.68 102	99.15 177
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PatchMatch-RL		97.77 63	98.25 74	97.21 63	99.11 47	99.25 107	97.06 143	94.09 72	98.72 128	95.14 59	98.47 65	96.29 95	98.43 98	98.65 74	97.44 136	99.45 175	98.94 186

EPP-MVSNet		97.75 64	98.71 61	96.63 84	95.68 127	99.56 52	97.51 119	93.10 107	99.22 51	94.99 62	97.18 99	97.30 85	98.65 87	98.83 60	98.93 42	99.84 12	99.92 3

MAR-MVS		97.71 65	98.04 86	97.32 58	99.35 42	98.91 127	97.65 116	91.68 121	98.00 161	97.01 32	97.72 88	94.83 114	98.85 72	98.44 92	98.86 47	99.41 182	99.52 147
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		97.70 66	98.78 59	96.44 91	95.72 120	99.65 23	98.14 93	93.72 83	98.30 149	92.31 113	98.63 57	97.90 77	98.97 61	98.92 53	98.30 85	99.78 35	99.80 37

UGNet		97.66 67	99.07 45	96.01 109	97.19 82	99.65 23	97.09 141	93.39 88	99.35 34	94.40 76	98.79 49	99.59 55	94.24 200	98.04 119	98.29 88	99.73 62	99.80 37
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
RPSCF		97.61 68	98.16 81	96.96 75	98.10 65	99.00 120	98.84 57	93.76 80	99.45 21	94.78 65	99.39 17	99.31 59	98.53 95	96.61 175	95.43 186	97.74 216	97.93 209

baseline1		97.58 69	98.05 85	97.02 70	96.21 102	99.45 69	97.71 112	93.71 84	98.47 140	95.75 46	98.78 50	93.20 135	98.91 64	98.52 87	98.44 71	99.81 24	99.53 144

DCV-MVSNet		97.56 70	98.36 70	96.62 85	96.44 94	98.36 168	98.37 78	91.73 120	99.11 75	94.80 64	98.36 70	96.28 96	98.60 91	98.12 108	98.44 71	99.76 42	99.87 18

PMMVS		97.52 71	98.39 69	96.51 88	95.82 116	98.73 142	97.80 107	93.05 108	98.76 124	94.39 77	99.07 35	97.03 89	98.55 93	98.31 98	97.61 125	99.43 179	99.21 175

PVSNet_BlendedMVS		97.51 72	97.71 101	97.28 60	98.06 66	99.61 39	97.31 126	95.02 53	99.08 80	95.51 49	98.05 77	90.11 154	98.07 109	98.91 54	98.40 74	99.72 71	99.78 51

PVSNet_Blended		97.51 72	97.71 101	97.28 60	98.06 66	99.61 39	97.31 126	95.02 53	99.08 80	95.51 49	98.05 77	90.11 154	98.07 109	98.91 54	98.40 74	99.72 71	99.78 51

baseline		97.45 74	98.70 62	95.99 110	95.89 111	99.36 92	98.29 83	91.37 131	99.21 54	92.99 101	98.40 68	96.87 90	97.96 113	98.60 81	98.60 63	99.42 181	99.86 21

PVSNet_Blended_VisFu		97.41 75	98.49 67	96.15 100	97.49 73	99.76 6	96.02 163	93.75 82	99.26 46	93.38 96	93.73 162	99.35 58	96.47 155	98.96 48	98.46 69	99.77 40	99.90 7

Vis-MVSNet (Re-imp)		97.40 76	98.89 55	95.66 117	95.99 109	99.62 34	97.82 105	93.22 101	98.82 113	91.40 125	96.94 104	98.56 70	95.70 172	99.14 36	99.41 6	99.79 32	99.75 72

sasdasda		97.31 77	97.81 97	96.72 77	96.20 103	99.45 69	98.21 87	91.60 123	99.22 51	95.39 52	98.48 62	90.95 148	99.16 47	97.66 142	99.05 31	99.76 42	99.90 7

canonicalmvs		97.31 77	97.81 97	96.72 77	96.20 103	99.45 69	98.21 87	91.60 123	99.22 51	95.39 52	98.48 62	90.95 148	99.16 47	97.66 142	99.05 31	99.76 42	99.90 7

MVS_Test		97.30 79	98.54 64	95.87 112	95.74 119	99.28 104	98.19 89	91.40 130	99.18 58	91.59 123	98.17 75	96.18 98	98.63 89	98.61 78	98.55 64	99.66 116	99.78 51

ECVR-MVS		97.27 80	97.09 129	97.48 55	96.95 87	99.79 4	98.48 69	94.42 67	99.17 59	96.28 40	93.54 164	89.39 160	98.89 69	99.03 42	99.09 25	99.88 4	99.61 133

casdiffmvs_mvg		97.27 80	97.97 91	96.46 90	95.83 115	99.51 62	98.42 74	93.32 93	98.34 147	92.38 112	95.64 142	95.35 108	98.91 64	98.73 70	98.45 70	99.86 9	99.80 37
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MGCFI-Net		97.26 82	97.79 100	96.64 83	96.17 105	99.43 76	98.14 93	91.52 128	99.23 49	95.16 58	98.48 62	90.87 150	99.07 55	97.59 148	99.02 36	99.76 42	99.91 6

thisisatest0530		97.23 83	98.25 74	96.05 105	95.60 134	99.59 46	96.96 145	93.23 99	99.17 59	92.60 109	98.75 53	96.19 97	98.17 103	98.19 105	96.10 172	99.72 71	99.77 58

tttt0517		97.23 83	98.24 77	96.04 106	95.60 134	99.60 44	96.94 146	93.23 99	99.15 65	92.56 110	98.74 54	96.12 100	98.17 103	98.21 103	96.10 172	99.73 62	99.78 51

viewcassd2359sk11		97.19 85	97.82 95	96.44 91	95.59 136	99.43 76	97.70 113	93.35 92	99.15 65	93.50 93	97.20 98	92.68 137	98.77 75	98.38 95	98.21 92	99.73 62	99.73 83

test2506		97.16 86	96.68 145	97.73 48	96.95 87	99.79 4	98.48 69	94.42 67	99.17 59	97.74 23	99.15 26	80.93 215	98.89 69	99.03 42	99.09 25	99.88 4	99.62 130

MVSTER		97.16 86	97.71 101	96.52 87	95.97 110	98.48 157	98.63 64	92.10 113	98.68 129	95.96 44	99.23 22	91.79 144	96.87 141	98.76 65	97.37 139	99.57 156	99.68 111

UA-Net		97.13 88	99.14 40	94.78 126	97.21 81	99.38 86	97.56 118	92.04 114	98.48 139	88.03 143	98.39 69	99.91 32	94.03 203	99.33 25	99.23 19	99.81 24	99.25 172

Anonymous20231211		97.10 89	97.06 132	97.14 64	96.32 96	99.52 59	98.16 91	93.76 80	98.84 110	95.98 43	90.92 184	94.58 119	98.90 66	97.72 140	98.10 100	99.71 82	99.75 72

test1111		97.09 90	96.83 140	97.39 56	96.92 89	99.81 3	98.44 73	94.45 66	99.17 59	95.85 45	92.10 178	88.97 164	98.78 74	99.02 44	99.11 24	99.88 4	99.63 128

viewdifsd2359ckpt07		97.07 91	97.81 97	96.22 96	95.75 118	99.42 80	98.19 89	93.27 97	99.14 69	91.92 120	95.46 147	93.66 129	98.53 95	98.75 67	98.48 68	99.65 121	99.73 83

FC-MVSNet-train		97.04 92	97.91 93	96.03 107	96.00 108	98.41 164	96.53 154	93.42 87	99.04 88	93.02 100	98.03 79	94.32 122	97.47 129	97.93 126	97.77 119	99.75 48	99.88 16

FMVSNet3		97.02 93	98.12 83	95.73 116	93.59 173	97.98 177	98.34 82	91.32 132	98.80 116	93.92 82	97.21 95	95.94 103	97.63 124	98.61 78	98.62 61	99.61 134	99.65 121

viewdifsd2359ckpt09		97.00 94	97.68 106	96.21 97	95.54 139	99.40 84	97.73 111	93.31 94	99.17 59	92.24 116	96.62 114	92.71 136	98.76 77	98.19 105	97.95 106	99.66 116	99.71 99

GBi-Net		96.98 95	98.00 89	95.78 113	93.81 167	97.98 177	98.09 96	91.32 132	98.80 116	93.92 82	97.21 95	95.94 103	97.89 115	98.07 114	98.34 81	99.68 102	99.67 114

test1		96.98 95	98.00 89	95.78 113	93.81 167	97.98 177	98.09 96	91.32 132	98.80 116	93.92 82	97.21 95	95.94 103	97.89 115	98.07 114	98.34 81	99.68 102	99.67 114

viewdifsd2359ckpt13		96.93 97	97.71 101	96.03 107	95.58 137	99.43 76	97.42 122	93.30 96	99.09 77	91.43 124	96.95 103	92.45 138	98.70 80	98.30 99	97.98 104	99.72 71	99.73 83

casdiffmvs		96.93 97	97.43 115	96.34 94	95.70 123	99.50 63	97.75 110	93.22 101	98.98 93	92.64 107	94.97 149	91.71 145	98.93 62	98.62 77	98.52 67	99.82 17	99.72 96
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmanbaseed2359cas		96.92 99	97.60 107	96.14 101	95.71 121	99.44 75	97.82 105	93.39 88	98.93 98	91.34 126	96.10 126	92.27 141	98.82 73	98.40 94	98.30 85	99.75 48	99.75 72

DI_MVS_pp		96.90 100	97.49 110	96.21 97	95.61 132	99.40 84	98.72 61	92.11 112	99.14 69	92.98 102	93.08 174	95.14 110	98.13 107	98.05 118	97.91 110	99.74 54	99.73 83

diffmvs		96.83 101	97.33 119	96.25 95	95.76 117	99.34 97	98.06 100	93.22 101	99.43 23	92.30 114	96.90 106	89.83 159	98.55 93	98.00 123	98.14 96	99.64 126	99.70 102
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmambaseed2359dif		96.82 102	97.19 126	96.39 93	95.64 130	99.38 86	98.15 92	93.24 98	98.78 122	92.85 105	95.93 131	91.24 147	98.75 79	97.41 154	97.86 113	99.70 90	99.74 77

TSAR-MVS + COLMAP		96.79 103	96.55 148	97.06 66	97.70 72	98.46 159	99.07 46	96.23 44	99.38 26	91.32 127	98.80 48	85.61 187	98.69 83	97.64 146	96.92 146	99.37 186	99.06 184

thres200		96.76 104	96.53 149	97.03 68	96.31 97	99.67 19	98.37 78	93.99 75	97.68 177	94.49 72	95.83 138	86.77 176	99.18 44	98.26 100	97.82 116	99.82 17	99.66 118

tfpn200view9		96.75 105	96.51 151	97.03 68	96.31 97	99.67 19	98.41 75	93.99 75	97.35 182	94.52 69	95.90 132	86.93 174	99.14 49	98.26 100	97.80 117	99.82 17	99.70 102

CLD-MVS		96.74 106	96.51 151	97.01 72	96.71 91	98.62 148	98.73 60	94.38 69	98.94 96	94.46 73	97.33 93	87.03 172	98.07 109	97.20 164	96.87 147	99.72 71	99.54 143
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thres100view900		96.72 107	96.47 155	97.00 73	96.31 97	99.52 59	98.28 84	94.01 73	97.35 182	94.52 69	95.90 132	86.93 174	99.09 54	98.07 114	97.87 112	99.81 24	99.63 128

thres400		96.71 108	96.45 157	97.02 70	96.28 100	99.63 31	98.41 75	94.00 74	97.82 172	94.42 75	95.74 139	86.26 182	99.18 44	98.20 104	97.79 118	99.81 24	99.70 102

thres600view7		96.69 109	96.43 159	97.00 73	96.28 100	99.67 19	98.41 75	93.99 75	97.85 171	94.29 78	95.96 129	85.91 185	99.19 41	98.26 100	97.63 124	99.82 17	99.73 83

test0.0.03 1		96.69 109	98.12 83	95.01 124	95.49 142	98.99 122	95.86 165	90.82 140	98.38 143	92.54 111	96.66 112	97.33 83	95.75 170	97.75 138	98.34 81	99.60 142	99.40 163

diffmvs_AUTHOR		96.68 111	97.10 128	96.19 99	95.71 121	99.37 90	97.91 102	93.19 104	99.36 32	91.97 119	95.90 132	89.02 163	98.67 86	98.01 122	98.30 85	99.68 102	99.74 77

ACMM	96.26 9	96.67 112	96.69 144	96.66 80	97.29 80	98.46 159	96.48 155	95.09 52	99.21 54	93.19 98	98.78 50	86.73 177	98.17 103	97.84 133	96.32 164	99.74 54	99.49 155
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CANet_DTU		96.64 113	99.08 43	93.81 142	97.10 84	99.42 80	98.85 56	90.01 151	99.31 38	79.98 194	99.78 2	99.10 64	97.42 130	98.35 96	98.05 102	99.47 173	99.53 144

FMVSNet2		96.64 113	97.50 109	95.63 118	93.81 167	97.98 177	98.09 96	90.87 138	98.99 92	93.48 94	93.17 171	95.25 109	97.89 115	98.63 76	98.80 55	99.68 102	99.67 114

ACMP	96.25 10	96.62 115	96.72 143	96.50 89	96.96 86	98.75 139	97.80 107	94.30 70	98.85 106	93.12 99	98.78 50	86.61 179	97.23 134	97.73 139	96.61 154	99.62 132	99.71 99
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CDS-MVSNet		96.59 116	98.02 88	94.92 125	94.45 160	98.96 125	97.46 121	91.75 119	97.86 170	90.07 134	96.02 128	97.25 86	96.21 159	98.04 119	98.38 76	99.60 142	99.65 121
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
FA-MVS(training)		96.52 117	98.29 72	94.45 132	95.88 113	99.52 59	97.66 115	81.47 210	98.94 96	93.79 89	95.54 146	99.11 63	98.29 101	98.89 56	96.49 159	99.63 131	99.52 147

viewmacassd2359aftdt		96.50 118	97.01 134	95.91 111	95.65 129	99.45 69	97.65 116	93.31 94	98.36 145	90.30 132	94.48 156	90.82 151	98.77 75	97.91 127	98.26 89	99.76 42	99.77 58

viewdifsd2359ckpt11		96.47 119	96.78 141	96.10 104	95.69 124	99.24 109	97.16 135	93.19 104	99.37 28	92.90 104	95.88 136	89.35 161	98.69 83	96.32 187	97.65 122	98.99 201	99.68 111

viewmsd2359difaftdt		96.47 119	96.78 141	96.11 103	95.69 124	99.24 109	97.16 135	93.19 104	99.35 34	92.93 103	95.88 136	89.34 162	98.69 83	96.31 188	97.65 122	98.99 201	99.68 111

CHOSEN 1792x2688		96.41 121	96.99 135	95.74 115	98.01 68	99.72 13	97.70 113	90.78 142	99.13 74	90.03 135	87.35 211	95.36 107	98.33 100	98.59 83	98.91 45	99.59 148	99.87 18

HQP-MVS		96.37 122	96.58 146	96.13 102	97.31 79	98.44 161	98.45 72	95.22 51	98.86 104	88.58 140	98.33 71	87.00 173	97.67 123	97.23 162	96.56 157	99.56 159	99.62 130

baseline2		96.36 123	97.82 95	94.65 128	94.60 159	99.09 118	96.45 156	89.63 159	98.36 145	91.29 128	97.60 91	94.13 125	96.37 156	98.45 90	97.70 120	99.54 165	99.41 161

EPNet_dtu		96.30 124	98.53 65	93.70 146	98.97 50	98.24 172	97.36 124	94.23 71	98.85 106	79.18 198	99.19 23	98.47 71	94.09 202	97.89 130	98.21 92	98.39 209	98.85 192
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LGP-MVS_train		96.23 125	96.89 137	95.46 120	97.32 77	98.77 135	98.81 58	93.60 85	98.58 133	85.52 160	99.08 34	86.67 178	97.83 121	97.87 131	97.51 129	99.69 94	99.73 83

OPM-MVS		96.22 126	95.85 168	96.65 81	97.75 70	98.54 154	99.00 52	95.53 47	96.88 195	89.88 136	95.95 130	86.46 181	98.07 109	97.65 145	96.63 153	99.67 111	98.83 193
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ET-MVSNet_ETH3D		96.17 127	96.99 135	95.21 122	88.53 225	98.54 154	98.28 84	92.61 109	98.85 106	93.60 92	99.06 36	90.39 153	98.63 89	95.98 198	96.68 151	99.61 134	99.41 161

Vis-MVSNet		96.16 128	98.22 78	93.75 143	95.33 147	99.70 18	97.27 128	90.85 139	98.30 149	85.51 161	95.72 141	96.45 91	93.69 209	98.70 72	99.00 37	99.84 12	99.69 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
IterMVS-LS		96.12 129	97.48 111	94.53 129	95.19 149	97.56 202	97.15 137	89.19 164	99.08 80	88.23 141	94.97 149	94.73 116	97.84 120	97.86 132	98.26 89	99.60 142	99.88 16
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		96.07 130	97.94 92	93.89 140	93.60 172	98.67 145	96.62 151	90.30 150	98.76 124	88.62 139	95.57 145	97.63 81	94.48 196	97.97 124	97.48 133	99.71 82	99.52 147

dmvs_re		96.02 131	96.49 154	95.47 119	93.49 174	99.26 106	97.25 130	93.82 78	97.51 179	90.43 131	97.52 92	87.93 167	98.12 108	96.86 172	96.59 155	99.73 62	99.76 64

MS-PatchMatch		95.99 132	97.26 124	94.51 130	97.46 74	98.76 138	97.27 128	86.97 186	99.09 77	89.83 137	93.51 166	97.78 79	96.18 161	97.53 151	95.71 183	99.35 187	98.41 199

HyFIR lowres test		95.99 132	96.56 147	95.32 121	97.99 69	99.65 23	96.54 152	88.86 166	98.44 141	89.77 138	84.14 221	97.05 88	99.03 58	98.55 85	98.19 95	99.73 62	99.86 21

GeoE		95.98 134	97.24 125	94.51 130	95.02 152	99.38 86	98.02 101	87.86 181	98.37 144	87.86 146	92.99 176	93.54 130	98.56 92	98.61 78	97.92 108	99.73 62	99.85 24

Effi-MVS+		95.81 135	97.31 123	94.06 138	95.09 150	99.35 95	97.24 131	88.22 175	98.54 136	85.38 162	98.52 60	88.68 165	98.70 80	98.32 97	97.93 107	99.74 54	99.84 25

FMVSNet1		95.77 136	96.41 160	95.03 123	93.42 175	97.86 184	97.11 140	89.89 154	98.53 137	92.00 118	89.17 196	93.23 134	98.15 106	98.07 114	98.34 81	99.61 134	99.69 106

Effi-MVS+-dtu		95.74 137	98.04 86	93.06 160	93.92 163	99.16 115	97.90 103	88.16 177	99.07 85	82.02 182	98.02 80	94.32 122	96.74 145	98.53 86	97.56 127	99.61 134	99.62 130

testgi		95.67 138	97.48 111	93.56 149	95.07 151	99.00 120	95.33 176	88.47 172	98.80 116	86.90 152	97.30 94	92.33 140	95.97 167	97.66 142	97.91 110	99.60 142	99.38 164

MDTV_nov1_ep13		95.57 139	97.48 111	93.35 157	95.43 144	98.97 124	97.19 134	83.72 208	98.92 101	87.91 145	97.75 86	96.12 100	97.88 118	96.84 174	95.64 184	97.96 214	98.10 205

TAMVS		95.53 140	96.50 153	94.39 134	93.86 166	99.03 119	96.67 149	89.55 161	97.33 184	90.64 130	93.02 175	91.58 146	96.21 159	97.72 140	97.43 137	99.43 179	99.36 165

test-LLR		95.50 141	97.32 120	93.37 155	95.49 142	98.74 140	96.44 157	90.82 140	98.18 154	82.75 177	96.60 116	94.67 117	95.54 178	98.09 111	96.00 174	99.20 195	98.93 187

FMVSNet5		95.42 142	96.47 155	94.20 135	92.26 187	95.99 223	95.66 168	87.15 185	97.87 169	93.46 95	96.68 111	93.79 128	97.52 126	97.10 168	97.21 141	99.11 198	96.62 224

ACMH+	95.51 13	95.40 143	96.00 162	94.70 127	96.33 95	98.79 132	96.79 147	91.32 132	98.77 123	87.18 150	95.60 144	85.46 188	96.97 138	97.15 165	96.59 155	99.59 148	99.65 121

Fast-Effi-MVS+-dtu		95.38 144	98.20 79	92.09 171	93.91 164	98.87 129	97.35 125	85.01 201	99.08 80	81.09 186	98.10 76	96.36 94	95.62 175	98.43 93	97.03 143	99.55 161	99.50 154

Fast-Effi-MVS+		95.38 144	96.52 150	94.05 139	94.15 162	99.14 117	97.24 131	86.79 187	98.53 137	87.62 148	94.51 154	87.06 171	98.76 77	98.60 81	98.04 103	99.72 71	99.77 58

CVMVSNet		95.33 146	97.09 129	93.27 158	95.23 148	98.39 166	95.49 172	92.58 110	97.71 176	83.00 176	94.44 157	93.28 133	93.92 206	97.79 134	98.54 66	99.41 182	99.45 158

ACMH	95.42 14	95.27 147	95.96 164	94.45 132	96.83 90	98.78 134	94.72 190	91.67 122	98.95 94	86.82 153	96.42 121	83.67 198	97.00 137	97.48 153	96.68 151	99.69 94	99.76 64
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs4		95.09 148	95.90 165	94.14 136	92.29 186	97.70 188	95.45 173	90.31 148	98.60 131	90.70 129	93.25 169	89.90 157	96.67 148	97.13 166	95.42 187	99.44 177	99.28 168

EPMVS		95.05 149	96.86 139	92.94 162	95.84 114	98.96 125	96.68 148	79.87 216	99.05 86	90.15 133	97.12 100	95.99 102	97.49 128	95.17 208	94.75 205	97.59 220	96.96 220

IB-MVS	93.96 15	95.02 150	96.44 158	93.36 156	97.05 85	99.28 104	90.43 217	93.39 88	98.02 160	96.02 42	94.92 151	92.07 143	83.52 227	95.38 204	95.82 180	99.72 71	99.59 134
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
SCA		94.95 151	97.44 114	92.04 172	95.55 138	99.16 115	96.26 160	79.30 220	99.02 89	85.73 159	98.18 74	97.13 87	97.69 122	96.03 196	94.91 200	97.69 219	97.65 211

TESTMET0.1,1		94.95 151	97.32 120	92.20 169	92.62 179	98.74 140	96.44 157	86.67 189	98.18 154	82.75 177	96.60 116	94.67 117	95.54 178	98.09 111	96.00 174	99.20 195	98.93 187

IterMVS-SCA-FT		94.89 153	97.87 94	91.42 185	94.86 156	97.70 188	97.24 131	84.88 202	98.93 98	75.74 210	94.26 158	98.25 74	96.69 146	98.52 87	97.68 121	99.10 199	99.73 83

test-mter		94.86 154	97.32 120	92.00 174	92.41 184	98.82 131	96.18 162	86.35 193	98.05 159	82.28 180	96.48 120	94.39 121	95.46 182	98.17 107	96.20 168	99.32 189	99.13 181

IterMVS		94.81 155	97.71 101	91.42 185	94.83 157	97.63 195	97.38 123	85.08 199	98.93 98	75.67 211	94.02 159	97.64 80	96.66 149	98.45 90	97.60 126	98.90 204	99.72 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchmatchNet		94.70 156	97.08 131	91.92 177	95.53 140	98.85 130	95.77 166	79.54 218	98.95 94	85.98 156	98.52 60	96.45 91	97.39 131	95.32 205	94.09 210	97.32 222	97.38 215
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
RPMNet		94.66 157	97.16 127	91.75 181	94.98 153	98.59 151	97.00 144	78.37 227	97.98 162	83.78 167	96.27 123	94.09 127	96.91 140	97.36 157	96.73 149	99.48 171	99.09 182

ADS-MVSNet		94.65 158	97.04 133	91.88 180	95.68 127	98.99 122	95.89 164	79.03 223	99.15 65	85.81 158	96.96 102	98.21 76	97.10 135	94.48 216	94.24 209	97.74 216	97.21 216

dps		94.63 159	95.31 174	93.84 141	95.53 140	98.71 143	96.54 152	80.12 215	97.81 174	97.21 29	96.98 101	92.37 139	96.34 158	92.46 223	91.77 223	97.26 224	97.08 218

thisisatest0515		94.61 160	96.89 137	91.95 176	92.00 191	98.47 158	92.01 212	90.73 143	98.18 154	83.96 164	94.51 154	95.13 111	93.38 210	97.38 156	94.74 206	99.61 134	99.79 45

UniMVSNet_NR-MVSNet		94.59 161	95.47 171	93.55 150	91.85 196	97.89 183	95.03 178	92.00 115	97.33 184	86.12 154	93.19 170	87.29 170	96.60 151	96.12 193	96.70 150	99.72 71	99.80 37

UniMVSNet (Re)		94.58 162	95.34 172	93.71 145	92.25 188	98.08 176	94.97 180	91.29 136	97.03 193	87.94 144	93.97 161	86.25 183	96.07 164	96.27 190	95.97 177	99.72 71	99.79 45

CR-MVSNet		94.57 163	97.34 118	91.33 188	94.90 154	98.59 151	97.15 137	79.14 221	97.98 162	80.42 190	96.59 118	93.50 132	96.85 142	98.10 109	97.49 131	99.50 170	99.15 177

MIMVSNet		94.49 164	97.59 108	90.87 197	91.74 199	98.70 144	94.68 192	78.73 225	97.98 162	83.71 170	97.71 89	94.81 115	96.96 139	97.97 124	97.92 108	99.40 184	98.04 206

pm-mvs1		94.27 165	95.57 170	92.75 163	92.58 180	98.13 175	94.87 185	90.71 144	96.70 201	83.78 167	89.94 192	89.85 158	94.96 193	97.58 149	97.07 142	99.61 134	99.72 96

USDC		94.26 166	94.83 178	93.59 148	96.02 106	98.44 161	97.84 104	88.65 170	98.86 104	82.73 179	94.02 159	80.56 216	96.76 144	97.28 161	96.15 171	99.55 161	98.50 197

CostFormer		94.25 167	94.88 177	93.51 152	95.43 144	98.34 169	96.21 161	80.64 213	97.94 166	94.01 80	98.30 72	86.20 184	97.52 126	92.71 221	92.69 217	97.23 225	98.02 207

tpm cat1		94.06 168	94.90 176	93.06 160	95.42 146	98.52 156	96.64 150	80.67 212	97.82 172	92.63 108	93.39 168	95.00 112	96.06 165	91.36 227	91.58 225	96.98 226	96.66 223

NR-MVSNet		94.01 169	94.51 184	93.44 153	92.56 181	97.77 185	95.67 167	91.57 125	97.17 188	85.84 157	93.13 172	80.53 217	95.29 186	97.01 169	96.17 169	99.69 94	99.75 72

TinyColmap		94.00 170	94.35 187	93.60 147	95.89 111	98.26 170	97.49 120	88.82 167	98.56 135	83.21 173	91.28 183	80.48 218	96.68 147	97.34 158	96.26 167	99.53 167	98.24 203

DU-MVS		93.98 171	94.44 186	93.44 153	91.66 201	97.77 185	95.03 178	91.57 125	97.17 188	86.12 154	93.13 172	81.13 214	96.60 151	95.10 210	97.01 145	99.67 111	99.80 37

PatchT		93.96 172	97.36 117	90.00 204	94.76 158	98.65 146	90.11 220	78.57 226	97.96 165	80.42 190	96.07 127	94.10 126	96.85 142	98.10 109	97.49 131	99.26 193	99.15 177

GA-MVS		93.93 173	96.31 161	91.16 192	93.61 171	98.79 132	95.39 175	90.69 145	98.25 152	73.28 219	96.15 125	88.42 166	94.39 198	97.76 137	95.35 188	99.58 152	99.45 158

Baseline_NR-MVSNet		93.87 174	93.98 196	93.75 143	91.66 201	97.02 215	95.53 171	91.52 128	97.16 190	87.77 147	87.93 209	83.69 197	96.35 157	95.10 210	97.23 140	99.68 102	99.73 83

tpmrst		93.86 175	95.88 166	91.50 184	95.69 124	98.62 148	95.64 169	79.41 219	98.80 116	83.76 169	95.63 143	96.13 99	97.25 132	92.92 220	92.31 219	97.27 223	96.74 221

tfpnnormal		93.85 176	94.12 191	93.54 151	93.22 176	98.24 172	95.45 173	91.96 117	94.61 222	83.91 165	90.74 186	81.75 212	97.04 136	97.49 152	96.16 170	99.68 102	99.84 25

TranMVSNet+NR-MVSNet		93.67 177	94.14 189	93.13 159	91.28 215	97.58 200	95.60 170	91.97 116	97.06 191	84.05 163	90.64 189	82.22 209	96.17 162	94.94 213	96.78 148	99.69 94	99.78 51

WR-MVS_H		93.54 178	94.67 182	92.22 167	91.95 192	97.91 182	94.58 196	88.75 168	96.64 202	83.88 166	90.66 188	85.13 191	94.40 197	96.54 179	95.91 179	99.73 62	99.89 13

TransMVSNet (Re)		93.45 179	94.08 192	92.72 164	92.83 177	97.62 198	94.94 181	91.54 127	95.65 219	83.06 175	88.93 199	83.53 199	94.25 199	97.41 154	97.03 143	99.67 111	98.40 202

SixPastTwentyTwo		93.44 180	95.32 173	91.24 190	92.11 189	98.40 165	92.77 208	88.64 171	98.09 158	77.83 203	93.51 166	85.74 186	96.52 154	96.91 171	94.89 203	99.59 148	99.73 83

WR-MVS		93.43 181	94.48 185	92.21 168	91.52 208	97.69 190	94.66 194	89.98 152	96.86 196	83.43 171	90.12 190	85.03 192	93.94 205	96.02 197	95.82 180	99.71 82	99.82 30

CP-MVSNet		93.25 182	94.00 195	92.38 166	91.65 203	97.56 202	94.38 199	89.20 163	96.05 213	83.16 174	89.51 194	81.97 210	96.16 163	96.43 181	96.56 157	99.71 82	99.89 13

UniMVSNet_ETH3D		93.15 183	92.33 216	94.11 137	93.91 164	98.61 150	94.81 187	90.98 137	97.06 191	87.51 149	82.27 225	76.33 231	97.87 119	94.79 214	97.47 134	99.56 159	99.81 35

anonymousdsp		93.12 184	95.86 167	89.93 206	91.09 216	98.25 171	95.12 177	85.08 199	97.44 181	73.30 218	90.89 185	90.78 152	95.25 188	97.91 127	95.96 178	99.71 82	99.82 30

V42		93.05 185	93.90 199	92.04 172	91.91 193	97.66 192	94.91 182	89.91 153	96.85 197	80.58 189	89.66 193	83.43 201	95.37 184	95.03 212	94.90 201	99.59 148	99.78 51

TDRefinement		93.04 186	93.57 203	92.41 165	96.58 92	98.77 135	97.78 109	91.96 117	98.12 157	80.84 187	89.13 198	79.87 223	87.78 223	96.44 180	94.50 208	99.54 165	98.15 204

v8		92.87 187	93.87 200	91.72 183	92.05 190	97.50 205	94.79 188	88.20 176	96.85 197	80.11 193	90.01 191	82.86 206	95.48 180	95.15 209	94.90 201	99.66 116	99.80 37

LTVRE_ROB	93.20 16	92.84 188	94.92 175	90.43 201	92.83 177	98.63 147	97.08 142	87.87 180	97.91 167	68.42 229	93.54 164	79.46 225	96.62 150	97.55 150	97.40 138	99.74 54	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
v1144		92.81 189	94.03 194	91.40 187	91.68 200	97.60 199	94.73 189	88.40 173	96.71 200	78.48 201	88.14 206	84.46 196	95.45 183	96.31 188	95.22 192	99.65 121	99.76 64

EU-MVSNet		92.80 190	94.76 180	90.51 199	91.88 194	96.74 220	92.48 210	88.69 169	96.21 208	79.00 199	91.51 180	87.82 168	91.83 218	95.87 200	96.27 165	99.21 194	98.92 190

v10		92.79 191	94.06 193	91.31 189	91.78 198	97.29 214	94.87 185	86.10 195	96.97 194	79.82 195	88.16 205	84.56 195	95.63 174	96.33 186	95.31 189	99.65 121	99.80 37

v2v482		92.77 192	93.52 206	91.90 179	91.59 206	97.63 195	94.57 197	90.31 148	96.80 199	79.22 197	88.74 201	81.55 213	96.04 166	95.26 206	94.97 199	99.66 116	99.69 106

PS-CasMVS		92.72 193	93.36 207	91.98 175	91.62 205	97.52 204	94.13 203	88.98 165	95.94 216	81.51 185	87.35 211	79.95 222	95.91 168	96.37 183	96.49 159	99.70 90	99.89 13

PEN-MVS		92.72 193	93.20 209	92.15 170	91.29 213	97.31 212	94.67 193	89.81 155	96.19 209	81.83 183	88.58 202	79.06 226	95.61 176	95.21 207	96.27 165	99.72 71	99.82 30

pmmvs5		92.71 195	94.27 188	90.90 196	91.42 210	97.74 187	93.23 205	86.66 190	95.99 215	78.96 200	91.45 181	83.44 200	95.55 177	97.30 160	95.05 197	99.58 152	98.93 187

MVS-HIRNet		92.51 196	95.97 163	88.48 212	93.73 170	98.37 167	90.33 218	75.36 233	98.32 148	77.78 204	89.15 197	94.87 113	95.14 190	97.62 147	96.39 162	98.51 206	97.11 217

EG-PatchMatch MVS		92.45 197	93.92 198	90.72 198	92.56 181	98.43 163	94.88 184	84.54 204	97.18 187	79.55 196	86.12 218	83.23 202	93.15 213	97.22 163	96.00 174	99.67 111	99.27 171

pmnet_mix02		92.44 198	94.68 181	89.83 207	92.46 183	97.65 194	89.92 222	90.49 147	98.76 124	73.05 221	91.78 179	90.08 156	94.86 194	94.53 215	91.94 222	98.21 212	98.01 208

MDTV_nov1_ep13_2view		92.44 198	95.66 169	88.68 210	91.05 217	97.92 181	92.17 211	79.64 217	98.83 111	76.20 208	91.45 181	93.51 131	95.04 191	95.68 202	93.70 214	97.96 214	98.53 196

v1192		92.43 200	93.61 202	91.05 193	91.53 207	97.43 208	94.61 195	87.99 179	96.60 203	76.72 206	87.11 213	82.74 207	95.85 169	96.35 185	95.30 190	99.60 142	99.74 77

DTE-MVSNet		92.42 201	92.85 212	91.91 178	90.87 218	96.97 216	94.53 198	89.81 155	95.86 218	81.59 184	88.83 200	77.88 229	95.01 192	94.34 217	96.35 163	99.64 126	99.73 83

v144192		92.38 202	93.55 205	91.00 194	91.44 209	97.47 207	94.27 200	87.41 184	96.52 205	78.03 202	87.50 210	82.65 208	95.32 185	95.82 201	95.15 194	99.55 161	99.78 51

tpm		92.38 202	94.79 179	89.56 208	94.30 161	97.50 205	94.24 202	78.97 224	97.72 175	74.93 215	97.97 81	82.91 204	96.60 151	93.65 219	94.81 204	98.33 210	98.98 185

v1921920		92.36 204	93.57 203	90.94 195	91.39 211	97.39 210	94.70 191	87.63 183	96.60 203	76.63 207	86.98 214	82.89 205	95.75 170	96.26 191	95.14 195	99.55 161	99.73 83

v148		92.36 204	92.88 211	91.75 181	91.63 204	97.66 192	92.64 209	90.55 146	96.09 211	83.34 172	88.19 204	80.00 220	92.74 214	93.98 218	94.58 207	99.58 152	99.69 106

N_pmnet		92.21 206	94.60 183	89.42 209	91.88 194	97.38 211	89.15 224	89.74 158	97.89 168	73.75 217	87.94 208	92.23 142	93.85 207	96.10 194	93.20 216	98.15 213	97.43 214

v1240		91.99 207	93.33 208	90.44 200	91.29 213	97.30 213	94.25 201	86.79 187	96.43 206	75.49 213	86.34 217	81.85 211	95.29 186	96.42 182	95.22 192	99.52 168	99.73 83

pmmvs6		91.90 208	92.53 215	91.17 191	91.81 197	97.63 195	93.23 205	88.37 174	93.43 227	80.61 188	77.32 230	87.47 169	94.12 201	96.58 177	95.72 182	98.88 205	99.53 144

v7n		91.61 209	92.95 210	90.04 203	90.56 219	97.69 190	93.74 204	85.59 197	95.89 217	76.95 205	86.60 216	78.60 228	93.76 208	97.01 169	94.99 198	99.65 121	99.87 18

gg-mvs-nofinetune		90.85 210	94.14 189	87.02 215	94.89 155	99.25 107	98.64 63	76.29 231	88.24 232	57.50 236	79.93 227	95.45 106	95.18 189	98.77 64	98.07 101	99.62 132	99.24 173

CMPMVS	70.31 18	90.74 211	91.06 219	90.36 202	97.32 77	97.43 208	92.97 207	87.82 182	93.50 226	75.34 214	83.27 223	84.90 193	92.19 217	92.64 222	91.21 226	96.50 229	94.46 227
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20231206		90.70 212	93.93 197	86.92 216	90.21 222	96.79 218	90.30 219	86.61 191	96.05 213	69.25 226	88.46 203	84.86 194	85.86 225	97.11 167	96.47 161	99.30 190	97.80 210

test20.03		90.65 213	93.71 201	87.09 214	90.44 220	96.24 221	89.74 223	85.46 198	95.59 220	72.99 222	90.68 187	85.33 189	84.41 226	95.94 199	95.10 196	99.52 168	97.06 219

new_pmnet		90.45 214	92.84 213	87.66 213	88.96 223	96.16 222	88.71 225	84.66 203	97.56 178	71.91 225	85.60 219	86.58 180	93.28 211	96.07 195	93.54 215	98.46 207	94.39 228

pmmvs-eth3d		89.81 215	89.65 223	90.00 204	86.94 227	95.38 225	91.08 213	86.39 192	94.57 223	82.27 181	83.03 224	64.94 235	93.96 204	96.57 178	93.82 213	99.35 187	99.24 173

PM-MVS		89.55 216	90.30 221	88.67 211	87.06 226	95.60 224	90.88 215	84.51 205	96.14 210	75.75 209	86.89 215	63.47 238	94.64 195	96.85 173	93.89 211	99.17 197	99.29 167

gm-plane-assit		89.44 217	92.82 214	85.49 219	91.37 212	95.34 226	79.55 235	82.12 209	91.68 231	64.79 233	87.98 207	80.26 219	95.66 173	98.51 89	97.56 127	99.45 175	98.41 199

MIMVSNet1		88.61 218	90.68 220	86.19 218	81.56 232	95.30 227	87.78 227	85.98 196	94.19 225	72.30 224	78.84 228	78.90 227	90.06 219	96.59 176	95.47 185	99.46 174	95.49 226

pmmvs3		88.19 219	91.27 218	84.60 221	85.60 229	93.66 230	85.68 230	81.13 211	92.36 230	63.66 235	89.51 194	77.10 230	93.22 212	96.37 183	92.40 218	98.30 211	97.46 213

MDA-MVSNet-bldmvs		87.84 220	89.22 224	86.23 217	81.74 231	96.77 219	83.74 231	89.57 160	94.50 224	72.83 223	96.64 113	64.47 237	92.71 215	81.43 232	92.28 220	96.81 227	98.47 198

test_method		87.27 221	91.58 217	82.25 224	75.65 237	87.52 236	86.81 229	72.60 234	97.51 179	73.20 220	85.07 220	79.97 221	88.69 221	97.31 159	95.24 191	96.53 228	98.41 199

FE-MVSNET		86.50 222	88.24 225	84.47 222	76.04 235	94.06 229	87.91 226	86.26 194	92.71 228	69.03 228	77.33 229	66.72 234	88.34 222	95.57 203	93.83 212	99.27 192	97.48 212

new-patchmatchnet		86.12 223	87.30 226	84.74 220	86.92 228	95.19 228	83.57 232	84.42 206	92.67 229	65.66 230	80.32 226	64.72 236	89.41 220	92.33 225	89.21 228	98.43 208	96.69 222

FPMVS		83.82 224	84.61 227	82.90 223	90.39 221	90.71 232	90.85 216	84.10 207	95.47 221	65.15 231	83.44 222	74.46 232	75.48 229	81.63 231	79.42 233	91.42 234	87.14 233

Gipuma		81.40 225	81.78 228	80.96 226	83.21 230	85.61 237	79.73 234	76.25 232	97.33 184	64.21 234	55.32 234	55.55 239	86.04 224	92.43 224	92.20 221	96.32 230	93.99 229
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
WB-MVS		81.36 226	89.93 222	71.35 229	88.65 224	87.85 235	71.46 237	88.12 178	96.23 207	32.21 241	92.61 177	83.00 203	56.27 236	91.92 226	89.43 227	91.39 235	88.49 232

PMMVS2		77.26 227	79.47 230	74.70 228	76.00 236	88.37 234	74.22 236	76.34 230	78.31 234	54.13 237	69.96 232	52.50 240	70.14 233	84.83 230	88.71 229	97.35 221	93.58 230

PMVS	72.60 17	76.39 228	77.66 231	74.92 227	81.04 233	69.37 241	68.47 238	80.54 214	85.39 233	65.07 232	73.52 231	72.91 233	65.67 235	80.35 233	76.81 234	88.71 236	85.25 236
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GG-mvs-BLEND		69.11 229	98.13 82	35.26 233	3.49 243	98.20 174	94.89 183	2.38 239	98.42 142	5.82 244	96.37 122	98.60 68	5.97 239	98.75 67	97.98 104	99.01 200	98.61 194

E-PMN		68.30 230	68.43 232	68.15 230	74.70 239	71.56 240	55.64 240	77.24 228	77.48 236	39.46 239	51.95 237	41.68 242	73.28 231	70.65 235	79.51 232	88.61 237	86.20 235

EMVS		68.12 231	68.11 233	68.14 231	75.51 238	71.76 239	55.38 241	77.20 229	77.78 235	37.79 240	53.59 235	43.61 241	74.72 230	67.05 236	76.70 235	88.27 238	86.24 234

MVE	67.97 19	65.53 232	67.43 234	63.31 232	59.33 240	74.20 238	53.09 242	70.43 235	66.27 237	43.13 238	45.98 238	30.62 243	70.65 232	79.34 234	86.30 230	83.25 239	89.33 231
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		31.24 233	40.15 235	20.86 234	12.61 241	17.99 242	25.16 243	13.30 237	48.42 238	24.82 242	53.07 236	30.13 245	28.47 237	42.73 237	37.65 236	20.79 240	51.04 237

test123		26.75 234	34.25 236	18.01 235	7.93 242	17.18 243	24.85 244	12.36 238	44.83 239	16.52 243	41.80 239	18.10 246	28.29 238	33.08 238	34.79 237	18.10 241	49.95 238

uanet_test		0.00 235	0.00 237	0.00 236	0.00 244	0.00 244	0.00 245	0.00 240	0.00 240	0.00 245	0.00 240	0.00 247	0.00 240	0.00 239	0.00 238	0.00 242	0.00 239

sosnet-low-res		0.00 235	0.00 237	0.00 236	0.00 244	0.00 244	0.00 245	0.00 240	0.00 240	0.00 245	0.00 240	0.00 247	0.00 240	0.00 239	0.00 238	0.00 242	0.00 239

sosnet		0.00 235	0.00 237	0.00 236	0.00 244	0.00 244	0.00 245	0.00 240	0.00 240	0.00 245	0.00 240	0.00 247	0.00 240	0.00 239	0.00 238	0.00 242	0.00 239

TPM-MVS					99.57 27	98.90 128	98.79 59			96.52 38	98.62 58	99.91 32	97.56 125			99.44 177	99.28 168
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										69.05 227

9.14												99.79 46

SR-MVS					99.67 14			98.25 15				99.94 25

Anonymous202405211			97.40 116		96.45 93	99.54 55	98.08 99	93.79 79	98.24 153		93.55 163	94.41 120	98.88 71	98.04 119	98.24 91	99.75 48	99.76 64

our_test_3					92.30 185	97.58 200	90.09 221

ambc			80.99 229		80.04 234	90.84 231	90.91 214		96.09 211	74.18 216	62.81 233	30.59 244	82.44 228	96.25 192	91.77 223	95.91 231	98.56 195

MTAPA										98.09 16		99.97 8

MTMP										98.46 11		99.96 12

Patchmatch-RL test							66.86 239

tmp_tt				82.25 224	97.73 71	88.71 233	80.18 233	68.65 236	99.15 65	86.98 151	99.47 12	85.31 190	68.35 234	87.51 229	83.81 231	91.64 233

XVS					97.42 75	99.62 34	98.59 66			93.81 86		99.95 17				99.69 94

X-MVStestdata					97.42 75	99.62 34	98.59 66			93.81 86		99.95 17				99.69 94

mPP-MVS					99.53 31							99.89 36

NP-MVS									98.57 134

Patchmtry						98.59 151	97.15 137	79.14 221		80.42 190

DeepMVS_CX						96.85 217	87.43 228	89.27 162	98.30 149	75.55 212	95.05 148	79.47 224	92.62 216	89.48 228		95.18 232	95.96 225

High-resolution multi-view benchmark