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.

APDe-MVS		99.49 1	99.64 1	99.32 2	99.74 4	99.74 12	99.75 1	98.34 4	99.56 11	98.72 6	99.57 8	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 2	99.54 7	99.35 1	99.72 6	99.76 6	99.63 12	98.37 2	99.63 8	99.03 3	98.95 40	99.98 2	99.60 7	99.60 7	99.05 30	99.74 53	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 3	99.58 4	99.28 3	99.69 7	99.76 6	99.62 14	98.35 3	99.51 17	99.05 2	99.60 7	99.98 2	99.28 37	99.61 6	98.83 51	99.70 89	99.77 58

DVP-MVS++		99.41 4	99.64 1	99.14 7	99.69 7	99.75 9	99.64 8	98.33 6	99.67 5	98.10 13	99.66 5	99.99 1	99.33 30	99.62 5	98.86 46	99.74 53	99.90 7

DPE-MVS		99.39 5	99.55 6	99.20 4	99.63 20	99.71 16	99.66 6	98.33 6	99.29 40	98.40 11	99.64 6	99.98 2	99.31 33	99.56 9	98.96 39	99.85 10	99.70 100
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SMA-MVS		99.38 6	99.60 3	99.12 9	99.76 2	99.62 33	99.39 30	98.23 18	99.52 16	98.03 17	99.45 12	99.98 2	99.64 5	99.58 8	99.30 12	99.68 101	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 7	99.52 10	99.14 7	99.68 12	99.75 9	99.64 8	98.31 9	99.44 21	98.10 13	99.28 19	99.98 2	99.30 35	99.34 23	99.05 30	99.81 23	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 8	99.53 9	99.07 13	99.69 7	99.59 45	99.63 12	98.31 9	99.56 11	97.37 26	99.27 20	99.97 8	99.70 3	99.35 22	99.24 18	99.71 81	99.76 64

ACMMPR		99.30 9	99.54 7	99.03 16	99.66 16	99.64 27	99.68 4	98.25 14	99.56 11	97.12 30	99.19 22	99.95 17	99.72 1	99.43 16	99.25 16	99.72 70	99.77 58

TSAR-MVS + MP.		99.27 10	99.57 5	98.92 22	98.78 54	99.53 55	99.72 2	98.11 28	99.73 3	97.43 25	99.15 25	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 10	99.44 17	99.08 12	99.62 22	99.58 48	99.53 19	98.16 21	99.21 53	97.79 20	99.15 25	99.96 12	99.59 9	99.54 11	98.86 46	99.78 34	99.74 77

SD-MVS		99.25 12	99.50 12	98.96 20	98.79 53	99.55 53	99.33 33	98.29 12	99.75 2	97.96 18	99.15 25	99.95 17	99.61 6	99.17 32	99.06 29	99.81 23	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 12	99.38 23	99.09 11	99.69 7	99.58 48	99.56 18	98.32 8	98.85 103	97.87 19	98.91 43	99.92 28	99.30 35	99.45 15	99.38 8	99.79 31	99.58 132
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		99.23 14	99.28 32	99.17 5	99.65 18	99.34 94	99.46 25	98.21 19	99.28 41	98.47 8	98.89 45	99.94 25	99.50 16	99.42 17	98.61 61	99.73 61	99.52 144

SteuartSystems-ACMMP		99.20 15	99.51 11	98.83 26	99.66 16	99.66 22	99.71 3	98.12 27	99.14 67	96.62 33	99.16 24	99.98 2	99.12 49	99.63 3	99.19 22	99.78 34	99.83 29
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		99.18 16	99.32 29	99.03 16	99.65 18	99.41 81	98.87 54	98.24 17	99.14 67	98.73 5	99.11 29	99.92 28	98.92 62	99.22 28	98.84 50	99.76 41	99.56 138

DeepC-MVS_fast	98.34 1	99.17 17	99.45 14	98.85 24	99.55 29	99.37 87	99.64 8	98.05 31	99.53 14	96.58 34	98.93 41	99.92 28	99.49 18	99.46 14	99.32 11	99.80 30	99.64 123
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 18	99.24 35	99.04 15	99.52 32	99.49 63	99.09 44	98.07 29	99.37 27	98.47 8	97.79 83	99.89 35	99.50 16	98.93 50	99.45 4	99.61 131	99.76 64

CPTT-MVS		99.14 19	99.20 37	99.06 14	99.58 25	99.53 55	99.45 26	97.80 36	99.19 56	98.32 12	98.58 58	99.95 17	99.60 7	99.28 26	98.20 92	99.64 123	99.69 104

MCST-MVS		99.11 20	99.27 33	98.93 21	99.67 13	99.33 97	99.51 21	98.31 9	99.28 41	96.57 35	99.10 31	99.90 33	99.71 2	99.19 31	98.35 77	99.82 16	99.71 98

HPM-MVS++		99.10 21	99.30 31	98.86 23	99.69 7	99.48 64	99.59 16	98.34 4	99.26 45	96.55 36	99.10 31	99.96 12	99.36 28	99.25 27	98.37 76	99.64 123	99.66 116

PHI-MVS		99.08 22	99.43 20	98.67 28	99.15 45	99.59 45	99.11 42	97.35 39	99.14 67	97.30 27	99.44 13	99.96 12	99.32 32	98.89 55	99.39 7	99.79 31	99.58 132

MP-MVS		99.07 23	99.36 25	98.74 27	99.63 20	99.57 50	99.66 6	98.25 14	99.00 88	95.62 46	98.97 38	99.94 25	99.54 14	99.51 12	98.79 55	99.71 81	99.73 83
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
AdaColmap		99.06 24	98.98 51	99.15 6	99.60 24	99.30 100	99.38 31	98.16 21	99.02 86	98.55 7	98.71 54	99.57 56	99.58 12	99.09 37	97.84 112	99.64 123	99.36 162

ACMMP_NAP		99.05 25	99.45 14	98.58 30	99.73 5	99.60 43	99.64 8	98.28 13	99.23 48	94.57 67	99.35 17	99.97 8	99.55 13	99.63 3	98.66 58	99.70 89	99.74 77

NCCC		99.05 25	99.08 42	99.02 18	99.62 22	99.38 83	99.43 29	98.21 19	99.36 31	97.66 23	97.79 83	99.90 33	99.45 22	99.17 32	98.43 71	99.77 39	99.51 149

CNLPA		99.03 27	99.05 45	99.01 19	99.27 43	99.22 110	99.03 48	97.98 32	99.34 35	99.00 4	98.25 72	99.71 49	99.31 33	98.80 60	98.82 53	99.48 168	99.17 173

PLC	97.93 2	99.02 28	98.94 52	99.11 10	99.46 34	99.24 106	99.06 46	97.96 33	99.31 37	99.16 1	97.90 81	99.79 45	99.36 28	98.71 69	98.12 96	99.65 119	99.52 144
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
X-MVS		98.93 29	99.37 24	98.42 31	99.67 13	99.62 33	99.60 15	98.15 23	99.08 77	93.81 85	98.46 65	99.95 17	99.59 9	99.49 13	99.21 21	99.68 101	99.75 72

CSCG		98.90 30	98.93 53	98.85 24	99.75 3	99.72 13	99.49 22	96.58 42	99.38 25	98.05 16	98.97 38	97.87 77	99.49 18	97.78 132	98.92 42	99.78 34	99.90 7

PGM-MVS		98.86 31	99.35 28	98.29 34	99.77 1	99.63 30	99.67 5	95.63 45	98.66 127	95.27 54	99.11 29	99.82 42	99.67 4	99.33 24	99.19 22	99.73 61	99.74 77

OMC-MVS		98.84 32	99.01 50	98.65 29	99.39 36	99.23 109	99.22 35	96.70 41	99.40 24	97.77 21	97.89 82	99.80 43	99.21 38	99.02 43	98.65 59	99.57 153	99.07 180

MVS_0304		98.81 33	99.44 17	98.08 39	98.83 51	99.75 9	99.58 17	95.53 46	99.76 1	96.48 38	99.70 4	98.64 66	98.21 99	99.00 46	99.33 10	99.82 16	99.90 7

TSAR-MVS + ACMM		98.77 34	99.45 14	97.98 43	99.37 37	99.46 66	99.44 28	98.13 26	99.65 6	92.30 113	98.91 43	99.95 17	99.05 55	99.42 17	98.95 40	99.58 149	99.82 30

ACMMP		98.74 35	99.03 49	98.40 32	99.36 39	99.64 27	99.20 36	97.75 37	98.82 110	95.24 55	98.85 46	99.87 37	99.17 45	98.74 67	97.50 127	99.71 81	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 36	99.11 40	98.28 35	99.36 39	99.35 92	99.48 24	97.96 33	98.83 108	93.86 84	98.70 55	99.86 38	99.44 23	99.08 39	98.38 74	99.61 131	99.58 132

3Dnovator+	96.92 7	98.71 37	99.05 45	98.32 33	99.53 30	99.34 94	99.06 46	94.61 59	99.65 6	97.49 24	96.75 107	99.86 38	99.44 23	98.78 62	99.30 12	99.81 23	99.67 112

MVS_111021_LR		98.67 38	99.41 22	97.81 46	99.37 37	99.53 55	98.51 67	95.52 48	99.27 43	94.85 62	99.56 9	99.69 50	99.04 56	99.36 20	98.88 45	99.60 139	99.58 132

3Dnovator	96.92 7	98.67 38	99.05 45	98.23 37	99.57 26	99.45 68	99.11 42	94.66 58	99.69 4	96.80 32	96.55 117	99.61 53	99.40 25	98.87 58	99.49 3	99.85 10	99.66 116

TSAR-MVS + GP.		98.66 40	99.36 25	97.85 45	97.16 82	99.46 66	99.03 48	94.59 62	99.09 74	97.19 29	99.73 3	99.95 17	99.39 26	98.95 48	98.69 57	99.75 47	99.65 119

QAPM		98.62 41	99.04 48	98.13 38	99.57 26	99.48 64	99.17 38	94.78 55	99.57 10	96.16 40	96.73 108	99.80 43	99.33 30	98.79 61	99.29 14	99.75 47	99.64 123

MVS_111021_HR		98.59 42	99.36 25	97.68 48	99.42 35	99.61 38	98.14 91	94.81 54	99.31 37	95.00 60	99.51 10	99.79 45	99.00 59	98.94 49	98.83 51	99.69 93	99.57 137

SPE-MVS-test		98.58 43	99.42 21	97.60 52	98.52 58	99.91 1	98.60 64	94.60 61	99.37 27	94.62 66	99.40 15	99.16 61	99.39 26	99.36 20	98.85 49	99.90 3	99.92 3

CS-MVS		98.56 44	99.32 29	97.68 48	98.28 63	99.89 2	98.71 61	94.53 64	99.41 23	95.43 50	99.05 36	98.66 65	99.19 40	99.21 29	99.07 27	99.93 1	99.94 1

CANet		98.46 45	99.16 38	97.64 50	98.48 59	99.64 27	99.35 32	94.71 57	99.53 14	95.17 56	97.63 89	99.59 54	98.38 96	98.88 57	98.99 37	99.74 53	99.86 21

CDPH-MVS		98.41 46	99.10 41	97.61 51	99.32 42	99.36 89	99.49 22	96.15 44	98.82 110	91.82 118	98.41 66	99.66 51	99.10 51	98.93 50	98.97 38	99.75 47	99.58 132

TAPA-MVS	97.53 5	98.41 46	98.84 57	97.91 44	99.08 47	99.33 97	99.15 39	97.13 40	99.34 35	93.20 96	97.75 85	99.19 60	99.20 39	98.66 71	98.13 95	99.66 115	99.48 153
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DeepPCF-MVS	97.74 3	98.34 48	99.46 13	97.04 66	98.82 52	99.33 97	96.28 156	97.47 38	99.58 9	94.70 65	98.99 37	99.85 40	97.24 130	99.55 10	99.34 9	97.73 215	99.56 138

DeepC-MVS	97.63 4	98.33 49	98.57 62	98.04 41	98.62 57	99.65 23	99.45 26	98.15 23	99.51 17	92.80 105	95.74 137	96.44 92	99.46 21	99.37 19	99.50 2	99.78 34	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 50	98.53 64	98.05 40	98.76 55	98.77 132	99.13 40	98.07 29	99.10 73	94.27 78	96.70 109	99.84 41	98.70 78	97.90 126	98.11 97	99.40 181	99.28 165

MSDG		98.27 51	98.29 71	98.24 36	99.20 44	99.22 110	99.20 36	97.82 35	99.37 27	94.43 73	95.90 130	97.31 83	99.12 49	98.76 64	98.35 77	99.67 110	99.14 177

EC-MVSNet		98.22 52	99.44 17	96.79 75	95.62 129	99.56 51	99.01 50	92.22 108	99.17 58	94.51 70	99.41 14	99.62 52	99.49 18	99.16 34	99.26 15	99.91 2	99.94 1

DELS-MVS		98.19 53	98.77 59	97.52 53	98.29 62	99.71 16	99.12 41	94.58 63	98.80 113	95.38 53	96.24 122	98.24 74	97.92 111	99.06 40	99.52 1	99.82 16	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 54	98.35 70	97.99 42	98.65 56	99.36 89	98.94 52	98.14 25	98.59 129	93.62 90	96.61 113	99.76 48	99.03 57	97.77 133	97.45 132	99.57 153	98.89 188
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ETV-MVS		98.05 55	99.25 34	96.65 80	95.61 130	99.61 38	98.26 85	93.52 85	98.90 99	93.74 89	99.32 18	99.20 59	98.90 65	99.21 29	98.72 56	99.87 8	99.79 45

EPNet		98.05 55	98.86 55	97.10 64	99.02 48	99.43 75	98.47 70	94.73 56	99.05 83	95.62 46	98.93 41	97.62 81	95.48 177	98.59 81	98.55 63	99.29 188	99.84 25
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CHOSEN 280x420		97.99 57	99.24 35	96.53 85	98.34 61	99.61 38	98.36 79	89.80 154	99.27 43	95.08 59	99.81 1	98.58 68	98.64 86	99.02 43	98.92 42	98.93 200	99.48 153

OpenMVS	96.23 11	97.95 58	98.45 67	97.35 56	99.52 32	99.42 79	98.91 53	94.61 59	98.87 100	92.24 115	94.61 150	99.05 64	99.10 51	98.64 73	99.05 30	99.74 53	99.51 149

IS_MVSNet		97.86 59	98.86 55	96.68 78	96.02 105	99.72 13	98.35 80	93.37 90	98.75 124	94.01 79	96.88 106	98.40 71	98.48 94	99.09 37	99.42 5	99.83 15	99.80 37

LS3D		97.79 60	98.25 73	97.26 61	98.40 60	99.63 30	99.53 19	98.63 1	99.25 47	88.13 139	96.93 104	94.14 123	99.19 40	99.14 35	99.23 19	99.69 93	99.42 157

COLMAP_ROB	96.15 12	97.78 61	98.17 79	97.32 57	98.84 50	99.45 68	99.28 34	95.43 49	99.48 19	91.80 119	94.83 149	98.36 72	98.90 65	98.09 108	97.85 111	99.68 101	99.15 174
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 62	98.25 73	97.21 62	99.11 46	99.25 104	97.06 140	94.09 71	98.72 125	95.14 58	98.47 64	96.29 94	98.43 95	98.65 72	97.44 133	99.45 172	98.94 183

EPP-MVSNet		97.75 63	98.71 60	96.63 83	95.68 125	99.56 51	97.51 116	93.10 104	99.22 50	94.99 61	97.18 98	97.30 84	98.65 85	98.83 59	98.93 41	99.84 12	99.92 3

MAR-MVS		97.71 64	98.04 85	97.32 57	99.35 41	98.91 124	97.65 113	91.68 118	98.00 158	97.01 31	97.72 87	94.83 113	98.85 71	98.44 90	98.86 46	99.41 179	99.52 144
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 65	98.78 58	96.44 90	95.72 118	99.65 23	98.14 91	93.72 82	98.30 146	92.31 112	98.63 56	97.90 76	98.97 60	98.92 52	98.30 83	99.78 34	99.80 37

UGNet		97.66 66	99.07 44	96.01 106	97.19 81	99.65 23	97.09 138	93.39 87	99.35 33	94.40 75	98.79 48	99.59 54	94.24 197	98.04 116	98.29 86	99.73 61	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 67	98.16 80	96.96 74	98.10 64	99.00 117	98.84 56	93.76 79	99.45 20	94.78 64	99.39 16	99.31 58	98.53 93	96.61 172	95.43 183	97.74 213	97.93 206

baseline1		97.58 68	98.05 84	97.02 69	96.21 101	99.45 68	97.71 109	93.71 83	98.47 137	95.75 45	98.78 49	93.20 133	98.91 63	98.52 85	98.44 69	99.81 23	99.53 141

DCV-MVSNet		97.56 69	98.36 69	96.62 84	96.44 93	98.36 165	98.37 77	91.73 117	99.11 72	94.80 63	98.36 69	96.28 95	98.60 89	98.12 105	98.44 69	99.76 41	99.87 18

PMMVS		97.52 70	98.39 68	96.51 87	95.82 115	98.73 139	97.80 105	93.05 105	98.76 121	94.39 76	99.07 34	97.03 88	98.55 91	98.31 96	97.61 122	99.43 176	99.21 172

PVSNet_BlendedMVS		97.51 71	97.71 99	97.28 59	98.06 65	99.61 38	97.31 123	95.02 52	99.08 77	95.51 48	98.05 76	90.11 151	98.07 106	98.91 53	98.40 72	99.72 70	99.78 51

PVSNet_Blended		97.51 71	97.71 99	97.28 59	98.06 65	99.61 38	97.31 123	95.02 52	99.08 77	95.51 48	98.05 76	90.11 151	98.07 106	98.91 53	98.40 72	99.72 70	99.78 51

baseline		97.45 73	98.70 61	95.99 107	95.89 110	99.36 89	98.29 82	91.37 128	99.21 53	92.99 100	98.40 67	96.87 89	97.96 110	98.60 79	98.60 62	99.42 178	99.86 21

PVSNet_Blended_VisFu		97.41 74	98.49 66	96.15 97	97.49 72	99.76 6	96.02 160	93.75 81	99.26 45	93.38 95	93.73 159	99.35 57	96.47 152	98.96 47	98.46 67	99.77 39	99.90 7

Vis-MVSNet (Re-imp)		97.40 75	98.89 54	95.66 114	95.99 108	99.62 33	97.82 103	93.22 98	98.82 110	91.40 122	96.94 103	98.56 69	95.70 169	99.14 35	99.41 6	99.79 31	99.75 72

sasdasda		97.31 76	97.81 96	96.72 76	96.20 102	99.45 68	98.21 86	91.60 120	99.22 50	95.39 51	98.48 61	90.95 145	99.16 46	97.66 139	99.05 30	99.76 41	99.90 7

canonicalmvs		97.31 76	97.81 96	96.72 76	96.20 102	99.45 68	98.21 86	91.60 120	99.22 50	95.39 51	98.48 61	90.95 145	99.16 46	97.66 139	99.05 30	99.76 41	99.90 7

MVS_Test		97.30 78	98.54 63	95.87 109	95.74 117	99.28 101	98.19 88	91.40 127	99.18 57	91.59 120	98.17 74	96.18 97	98.63 87	98.61 76	98.55 63	99.66 115	99.78 51

ECVR-MVS		97.27 79	97.09 126	97.48 54	96.95 86	99.79 4	98.48 68	94.42 66	99.17 58	96.28 39	93.54 161	89.39 157	98.89 68	99.03 41	99.09 25	99.88 4	99.61 130

casdiffmvs_mvg		97.27 79	97.97 90	96.46 89	95.83 114	99.51 61	98.42 73	93.32 92	98.34 144	92.38 111	95.64 140	95.35 107	98.91 63	98.73 68	98.45 68	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 81	97.79 98	96.64 82	96.17 104	99.43 75	98.14 91	91.52 125	99.23 48	95.16 57	98.48 61	90.87 147	99.07 54	97.59 145	99.02 35	99.76 41	99.91 6

thisisatest0530		97.23 82	98.25 73	96.05 102	95.60 132	99.59 45	96.96 142	93.23 96	99.17 58	92.60 108	98.75 52	96.19 96	98.17 100	98.19 103	96.10 169	99.72 70	99.77 58

tttt0517		97.23 82	98.24 76	96.04 103	95.60 132	99.60 43	96.94 143	93.23 96	99.15 63	92.56 109	98.74 53	96.12 99	98.17 100	98.21 101	96.10 169	99.73 61	99.78 51

viewcassd2359sk11		97.19 84	97.82 94	96.44 90	95.59 134	99.43 75	97.70 110	93.35 91	99.15 63	93.50 92	97.20 97	92.68 134	98.77 74	98.38 93	98.21 90	99.73 61	99.73 83

test2506		97.16 85	96.68 142	97.73 47	96.95 86	99.79 4	98.48 68	94.42 66	99.17 58	97.74 22	99.15 25	80.93 212	98.89 68	99.03 41	99.09 25	99.88 4	99.62 127

MVSTER		97.16 85	97.71 99	96.52 86	95.97 109	98.48 154	98.63 63	92.10 110	98.68 126	95.96 43	99.23 21	91.79 141	96.87 138	98.76 64	97.37 136	99.57 153	99.68 109

UA-Net		97.13 87	99.14 39	94.78 123	97.21 80	99.38 83	97.56 115	92.04 111	98.48 136	88.03 140	98.39 68	99.91 31	94.03 200	99.33 24	99.23 19	99.81 23	99.25 169

Anonymous20231211		97.10 88	97.06 129	97.14 63	96.32 95	99.52 58	98.16 89	93.76 79	98.84 107	95.98 42	90.92 181	94.58 118	98.90 65	97.72 137	98.10 98	99.71 81	99.75 72

test1111		97.09 89	96.83 137	97.39 55	96.92 88	99.81 3	98.44 72	94.45 65	99.17 58	95.85 44	92.10 175	88.97 161	98.78 73	99.02 43	99.11 24	99.88 4	99.63 125

FC-MVSNet-train		97.04 90	97.91 92	96.03 104	96.00 107	98.41 161	96.53 151	93.42 86	99.04 85	93.02 99	98.03 78	94.32 121	97.47 126	97.93 123	97.77 116	99.75 47	99.88 16

FMVSNet3		97.02 91	98.12 82	95.73 113	93.59 170	97.98 174	98.34 81	91.32 129	98.80 113	93.92 81	97.21 94	95.94 102	97.63 121	98.61 76	98.62 60	99.61 131	99.65 119

GBi-Net		96.98 92	98.00 88	95.78 110	93.81 164	97.98 174	98.09 94	91.32 129	98.80 113	93.92 81	97.21 94	95.94 102	97.89 112	98.07 111	98.34 79	99.68 101	99.67 112

test1		96.98 92	98.00 88	95.78 110	93.81 164	97.98 174	98.09 94	91.32 129	98.80 113	93.92 81	97.21 94	95.94 102	97.89 112	98.07 111	98.34 79	99.68 101	99.67 112

viewdifsd2359ckpt13		96.93 94	97.71 99	96.03 104	95.58 135	99.43 75	97.42 119	93.30 94	99.09 74	91.43 121	96.95 102	92.45 135	98.70 78	98.30 97	97.98 102	99.72 70	99.73 83

casdiffmvs		96.93 94	97.43 112	96.34 93	95.70 121	99.50 62	97.75 108	93.22 98	98.98 90	92.64 106	94.97 146	91.71 142	98.93 61	98.62 75	98.52 66	99.82 16	99.72 95
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 96	97.60 104	96.14 98	95.71 119	99.44 74	97.82 103	93.39 87	98.93 95	91.34 123	96.10 124	92.27 138	98.82 72	98.40 92	98.30 83	99.75 47	99.75 72

DI_MVS_pp		96.90 97	97.49 107	96.21 95	95.61 130	99.40 82	98.72 60	92.11 109	99.14 67	92.98 101	93.08 171	95.14 109	98.13 104	98.05 115	97.91 107	99.74 53	99.73 83

diffmvs		96.83 98	97.33 116	96.25 94	95.76 116	99.34 94	98.06 98	93.22 98	99.43 22	92.30 113	96.90 105	89.83 156	98.55 91	98.00 120	98.14 94	99.64 123	99.70 100
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 99	97.19 123	96.39 92	95.64 128	99.38 83	98.15 90	93.24 95	98.78 119	92.85 104	95.93 129	91.24 144	98.75 77	97.41 151	97.86 110	99.70 89	99.74 77

TSAR-MVS + COLMAP		96.79 100	96.55 145	97.06 65	97.70 71	98.46 156	99.07 45	96.23 43	99.38 25	91.32 124	98.80 47	85.61 184	98.69 81	97.64 143	96.92 143	99.37 183	99.06 181

thres200		96.76 101	96.53 146	97.03 67	96.31 96	99.67 19	98.37 77	93.99 74	97.68 174	94.49 71	95.83 136	86.77 173	99.18 43	98.26 98	97.82 113	99.82 16	99.66 116

tfpn200view9		96.75 102	96.51 148	97.03 67	96.31 96	99.67 19	98.41 74	93.99 74	97.35 179	94.52 68	95.90 130	86.93 171	99.14 48	98.26 98	97.80 114	99.82 16	99.70 100

CLD-MVS		96.74 103	96.51 148	97.01 71	96.71 90	98.62 145	98.73 59	94.38 68	98.94 93	94.46 72	97.33 92	87.03 169	98.07 106	97.20 161	96.87 144	99.72 70	99.54 140
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thres100view900		96.72 104	96.47 152	97.00 72	96.31 96	99.52 58	98.28 83	94.01 72	97.35 179	94.52 68	95.90 130	86.93 171	99.09 53	98.07 111	97.87 109	99.81 23	99.63 125

thres400		96.71 105	96.45 154	97.02 69	96.28 99	99.63 30	98.41 74	94.00 73	97.82 169	94.42 74	95.74 137	86.26 179	99.18 43	98.20 102	97.79 115	99.81 23	99.70 100

thres600view7		96.69 106	96.43 156	97.00 72	96.28 99	99.67 19	98.41 74	93.99 74	97.85 168	94.29 77	95.96 127	85.91 182	99.19 40	98.26 98	97.63 121	99.82 16	99.73 83

test0.0.03 1		96.69 106	98.12 82	95.01 121	95.49 139	98.99 119	95.86 162	90.82 137	98.38 140	92.54 110	96.66 111	97.33 82	95.75 167	97.75 135	98.34 79	99.60 139	99.40 160

diffmvs_AUTHOR		96.68 108	97.10 125	96.19 96	95.71 119	99.37 87	97.91 100	93.19 101	99.36 31	91.97 117	95.90 130	89.02 160	98.67 84	98.01 119	98.30 83	99.68 101	99.74 77

ACMM	96.26 9	96.67 109	96.69 141	96.66 79	97.29 79	98.46 156	96.48 152	95.09 51	99.21 53	93.19 97	98.78 49	86.73 174	98.17 100	97.84 130	96.32 161	99.74 53	99.49 152
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CANet_DTU		96.64 110	99.08 42	93.81 139	97.10 83	99.42 79	98.85 55	90.01 148	99.31 37	79.98 191	99.78 2	99.10 63	97.42 127	98.35 94	98.05 100	99.47 170	99.53 141

FMVSNet2		96.64 110	97.50 106	95.63 115	93.81 164	97.98 174	98.09 94	90.87 135	98.99 89	93.48 93	93.17 168	95.25 108	97.89 112	98.63 74	98.80 54	99.68 101	99.67 112

ACMP	96.25 10	96.62 112	96.72 140	96.50 88	96.96 85	98.75 136	97.80 105	94.30 69	98.85 103	93.12 98	98.78 49	86.61 176	97.23 131	97.73 136	96.61 151	99.62 129	99.71 98
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CDS-MVSNet		96.59 113	98.02 87	94.92 122	94.45 157	98.96 122	97.46 118	91.75 116	97.86 167	90.07 131	96.02 126	97.25 85	96.21 156	98.04 116	98.38 74	99.60 139	99.65 119
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
FA-MVS(training)		96.52 114	98.29 71	94.45 129	95.88 112	99.52 58	97.66 112	81.47 207	98.94 93	93.79 88	95.54 144	99.11 62	98.29 98	98.89 55	96.49 156	99.63 128	99.52 144

viewmacassd2359aftdt		96.50 115	97.01 131	95.91 108	95.65 127	99.45 68	97.65 113	93.31 93	98.36 142	90.30 129	94.48 153	90.82 148	98.77 74	97.91 124	98.26 87	99.76 41	99.77 58

viewdifsd2359ckpt11		96.47 116	96.78 138	96.10 101	95.69 122	99.24 106	97.16 132	93.19 101	99.37 27	92.90 103	95.88 134	89.35 158	98.69 81	96.32 184	97.65 119	98.99 198	99.68 109

viewmsd2359difaftdt		96.47 116	96.78 138	96.11 100	95.69 122	99.24 106	97.16 132	93.19 101	99.35 33	92.93 102	95.88 134	89.34 159	98.69 81	96.31 185	97.65 119	98.99 198	99.68 109

CHOSEN 1792x2688		96.41 118	96.99 132	95.74 112	98.01 67	99.72 13	97.70 110	90.78 139	99.13 71	90.03 132	87.35 208	95.36 106	98.33 97	98.59 81	98.91 44	99.59 145	99.87 18

HQP-MVS		96.37 119	96.58 143	96.13 99	97.31 78	98.44 158	98.45 71	95.22 50	98.86 101	88.58 137	98.33 70	87.00 170	97.67 120	97.23 159	96.56 154	99.56 156	99.62 127

baseline2		96.36 120	97.82 94	94.65 125	94.60 156	99.09 115	96.45 153	89.63 156	98.36 142	91.29 125	97.60 90	94.13 124	96.37 153	98.45 88	97.70 117	99.54 162	99.41 158

EPNet_dtu		96.30 121	98.53 64	93.70 143	98.97 49	98.24 169	97.36 121	94.23 70	98.85 103	79.18 195	99.19 22	98.47 70	94.09 199	97.89 127	98.21 90	98.39 206	98.85 189
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LGP-MVS_train		96.23 122	96.89 134	95.46 117	97.32 76	98.77 132	98.81 57	93.60 84	98.58 130	85.52 157	99.08 33	86.67 175	97.83 118	97.87 128	97.51 126	99.69 93	99.73 83

OPM-MVS		96.22 123	95.85 165	96.65 80	97.75 69	98.54 151	99.00 51	95.53 46	96.88 192	89.88 133	95.95 128	86.46 178	98.07 106	97.65 142	96.63 150	99.67 110	98.83 190
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ET-MVSNet_ETH3D		96.17 124	96.99 132	95.21 119	88.53 222	98.54 151	98.28 83	92.61 106	98.85 103	93.60 91	99.06 35	90.39 150	98.63 87	95.98 195	96.68 148	99.61 131	99.41 158

Vis-MVSNet		96.16 125	98.22 77	93.75 140	95.33 144	99.70 18	97.27 125	90.85 136	98.30 146	85.51 158	95.72 139	96.45 90	93.69 206	98.70 70	99.00 36	99.84 12	99.69 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
IterMVS-LS		96.12 126	97.48 108	94.53 126	95.19 146	97.56 199	97.15 134	89.19 161	99.08 77	88.23 138	94.97 146	94.73 115	97.84 117	97.86 129	98.26 87	99.60 139	99.88 16
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		96.07 127	97.94 91	93.89 137	93.60 169	98.67 142	96.62 148	90.30 147	98.76 121	88.62 136	95.57 143	97.63 80	94.48 193	97.97 121	97.48 130	99.71 81	99.52 144

dmvs_re		96.02 128	96.49 151	95.47 116	93.49 171	99.26 103	97.25 127	93.82 77	97.51 176	90.43 128	97.52 91	87.93 164	98.12 105	96.86 169	96.59 152	99.73 61	99.76 64

MS-PatchMatch		95.99 129	97.26 121	94.51 127	97.46 73	98.76 135	97.27 125	86.97 183	99.09 74	89.83 134	93.51 163	97.78 78	96.18 158	97.53 148	95.71 180	99.35 184	98.41 196

HyFIR lowres test		95.99 129	96.56 144	95.32 118	97.99 68	99.65 23	96.54 149	88.86 163	98.44 138	89.77 135	84.14 218	97.05 87	99.03 57	98.55 83	98.19 93	99.73 61	99.86 21

GeoE		95.98 131	97.24 122	94.51 127	95.02 149	99.38 83	98.02 99	87.86 178	98.37 141	87.86 143	92.99 173	93.54 128	98.56 90	98.61 76	97.92 105	99.73 61	99.85 24

Effi-MVS+		95.81 132	97.31 120	94.06 135	95.09 147	99.35 92	97.24 128	88.22 172	98.54 133	85.38 159	98.52 59	88.68 162	98.70 78	98.32 95	97.93 104	99.74 53	99.84 25

FMVSNet1		95.77 133	96.41 157	95.03 120	93.42 172	97.86 181	97.11 137	89.89 151	98.53 134	92.00 116	89.17 193	93.23 132	98.15 103	98.07 111	98.34 79	99.61 131	99.69 104

Effi-MVS+-dtu		95.74 134	98.04 85	93.06 157	93.92 160	99.16 112	97.90 101	88.16 174	99.07 82	82.02 179	98.02 79	94.32 121	96.74 142	98.53 84	97.56 124	99.61 131	99.62 127

testgi		95.67 135	97.48 108	93.56 146	95.07 148	99.00 117	95.33 173	88.47 169	98.80 113	86.90 149	97.30 93	92.33 137	95.97 164	97.66 139	97.91 107	99.60 139	99.38 161

MDTV_nov1_ep13		95.57 136	97.48 108	93.35 154	95.43 141	98.97 121	97.19 131	83.72 205	98.92 98	87.91 142	97.75 85	96.12 99	97.88 115	96.84 171	95.64 181	97.96 211	98.10 202

TAMVS		95.53 137	96.50 150	94.39 131	93.86 163	99.03 116	96.67 146	89.55 158	97.33 181	90.64 127	93.02 172	91.58 143	96.21 156	97.72 137	97.43 134	99.43 176	99.36 162

test-LLR		95.50 138	97.32 117	93.37 152	95.49 139	98.74 137	96.44 154	90.82 137	98.18 151	82.75 174	96.60 114	94.67 116	95.54 175	98.09 108	96.00 171	99.20 192	98.93 184

FMVSNet5		95.42 139	96.47 152	94.20 132	92.26 184	95.99 220	95.66 165	87.15 182	97.87 166	93.46 94	96.68 110	93.79 127	97.52 123	97.10 165	97.21 138	99.11 195	96.62 221

ACMH+	95.51 13	95.40 140	96.00 159	94.70 124	96.33 94	98.79 129	96.79 144	91.32 129	98.77 120	87.18 147	95.60 142	85.46 185	96.97 135	97.15 162	96.59 152	99.59 145	99.65 119

Fast-Effi-MVS+-dtu		95.38 141	98.20 78	92.09 168	93.91 161	98.87 126	97.35 122	85.01 198	99.08 77	81.09 183	98.10 75	96.36 93	95.62 172	98.43 91	97.03 140	99.55 158	99.50 151

Fast-Effi-MVS+		95.38 141	96.52 147	94.05 136	94.15 159	99.14 114	97.24 128	86.79 184	98.53 134	87.62 145	94.51 151	87.06 168	98.76 76	98.60 79	98.04 101	99.72 70	99.77 58

CVMVSNet		95.33 143	97.09 126	93.27 155	95.23 145	98.39 163	95.49 169	92.58 107	97.71 173	83.00 173	94.44 154	93.28 131	93.92 203	97.79 131	98.54 65	99.41 179	99.45 155

ACMH	95.42 14	95.27 144	95.96 161	94.45 129	96.83 89	98.78 131	94.72 187	91.67 119	98.95 91	86.82 150	96.42 119	83.67 195	97.00 134	97.48 150	96.68 148	99.69 93	99.76 64
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs4		95.09 145	95.90 162	94.14 133	92.29 183	97.70 185	95.45 170	90.31 145	98.60 128	90.70 126	93.25 166	89.90 154	96.67 145	97.13 163	95.42 184	99.44 174	99.28 165

EPMVS		95.05 146	96.86 136	92.94 159	95.84 113	98.96 122	96.68 145	79.87 213	99.05 83	90.15 130	97.12 99	95.99 101	97.49 125	95.17 205	94.75 202	97.59 217	96.96 217

IB-MVS	93.96 15	95.02 147	96.44 155	93.36 153	97.05 84	99.28 101	90.43 214	93.39 87	98.02 157	96.02 41	94.92 148	92.07 140	83.52 224	95.38 201	95.82 177	99.72 70	99.59 131
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		94.95 148	97.44 111	92.04 169	95.55 136	99.16 112	96.26 157	79.30 217	99.02 86	85.73 156	98.18 73	97.13 86	97.69 119	96.03 193	94.91 197	97.69 216	97.65 208

TESTMET0.1,1		94.95 148	97.32 117	92.20 166	92.62 176	98.74 137	96.44 154	86.67 186	98.18 151	82.75 174	96.60 114	94.67 116	95.54 175	98.09 108	96.00 171	99.20 192	98.93 184

IterMVS-SCA-FT		94.89 150	97.87 93	91.42 182	94.86 153	97.70 185	97.24 128	84.88 199	98.93 95	75.74 207	94.26 155	98.25 73	96.69 143	98.52 85	97.68 118	99.10 196	99.73 83

test-mter		94.86 151	97.32 117	92.00 171	92.41 181	98.82 128	96.18 159	86.35 190	98.05 156	82.28 177	96.48 118	94.39 120	95.46 179	98.17 104	96.20 165	99.32 186	99.13 178

IterMVS		94.81 152	97.71 99	91.42 182	94.83 154	97.63 192	97.38 120	85.08 196	98.93 95	75.67 208	94.02 156	97.64 79	96.66 146	98.45 88	97.60 123	98.90 201	99.72 95
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchmatchNet		94.70 153	97.08 128	91.92 174	95.53 137	98.85 127	95.77 163	79.54 215	98.95 91	85.98 153	98.52 59	96.45 90	97.39 128	95.32 202	94.09 207	97.32 219	97.38 212
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
RPMNet		94.66 154	97.16 124	91.75 178	94.98 150	98.59 148	97.00 141	78.37 224	97.98 159	83.78 164	96.27 121	94.09 126	96.91 137	97.36 154	96.73 146	99.48 168	99.09 179

ADS-MVSNet		94.65 155	97.04 130	91.88 177	95.68 125	98.99 119	95.89 161	79.03 220	99.15 63	85.81 155	96.96 101	98.21 75	97.10 132	94.48 213	94.24 206	97.74 213	97.21 213

dps		94.63 156	95.31 171	93.84 138	95.53 137	98.71 140	96.54 149	80.12 212	97.81 171	97.21 28	96.98 100	92.37 136	96.34 155	92.46 220	91.77 220	97.26 221	97.08 215

thisisatest0515		94.61 157	96.89 134	91.95 173	92.00 188	98.47 155	92.01 209	90.73 140	98.18 151	83.96 161	94.51 151	95.13 110	93.38 207	97.38 153	94.74 203	99.61 131	99.79 45

UniMVSNet_NR-MVSNet		94.59 158	95.47 168	93.55 147	91.85 193	97.89 180	95.03 175	92.00 112	97.33 181	86.12 151	93.19 167	87.29 167	96.60 148	96.12 190	96.70 147	99.72 70	99.80 37

UniMVSNet (Re)		94.58 159	95.34 169	93.71 142	92.25 185	98.08 173	94.97 177	91.29 133	97.03 190	87.94 141	93.97 158	86.25 180	96.07 161	96.27 187	95.97 174	99.72 70	99.79 45

CR-MVSNet		94.57 160	97.34 115	91.33 185	94.90 151	98.59 148	97.15 134	79.14 218	97.98 159	80.42 187	96.59 116	93.50 130	96.85 139	98.10 106	97.49 128	99.50 167	99.15 174

MIMVSNet		94.49 161	97.59 105	90.87 194	91.74 196	98.70 141	94.68 189	78.73 222	97.98 159	83.71 167	97.71 88	94.81 114	96.96 136	97.97 121	97.92 105	99.40 181	98.04 203

pm-mvs1		94.27 162	95.57 167	92.75 160	92.58 177	98.13 172	94.87 182	90.71 141	96.70 198	83.78 164	89.94 189	89.85 155	94.96 190	97.58 146	97.07 139	99.61 131	99.72 95

USDC		94.26 163	94.83 175	93.59 145	96.02 105	98.44 158	97.84 102	88.65 167	98.86 101	82.73 176	94.02 156	80.56 213	96.76 141	97.28 158	96.15 168	99.55 158	98.50 194

CostFormer		94.25 164	94.88 174	93.51 149	95.43 141	98.34 166	96.21 158	80.64 210	97.94 163	94.01 79	98.30 71	86.20 181	97.52 123	92.71 218	92.69 214	97.23 222	98.02 204

tpm cat1		94.06 165	94.90 173	93.06 157	95.42 143	98.52 153	96.64 147	80.67 209	97.82 169	92.63 107	93.39 165	95.00 111	96.06 162	91.36 224	91.58 222	96.98 223	96.66 220

NR-MVSNet		94.01 166	94.51 181	93.44 150	92.56 178	97.77 182	95.67 164	91.57 122	97.17 185	85.84 154	93.13 169	80.53 214	95.29 183	97.01 166	96.17 166	99.69 93	99.75 72

TinyColmap		94.00 167	94.35 184	93.60 144	95.89 110	98.26 167	97.49 117	88.82 164	98.56 132	83.21 170	91.28 180	80.48 215	96.68 144	97.34 155	96.26 164	99.53 164	98.24 200

DU-MVS		93.98 168	94.44 183	93.44 150	91.66 198	97.77 182	95.03 175	91.57 122	97.17 185	86.12 151	93.13 169	81.13 211	96.60 148	95.10 207	97.01 142	99.67 110	99.80 37

PatchT		93.96 169	97.36 114	90.00 201	94.76 155	98.65 143	90.11 217	78.57 223	97.96 162	80.42 187	96.07 125	94.10 125	96.85 139	98.10 106	97.49 128	99.26 190	99.15 174

GA-MVS		93.93 170	96.31 158	91.16 189	93.61 168	98.79 129	95.39 172	90.69 142	98.25 149	73.28 216	96.15 123	88.42 163	94.39 195	97.76 134	95.35 185	99.58 149	99.45 155

Baseline_NR-MVSNet		93.87 171	93.98 193	93.75 140	91.66 198	97.02 212	95.53 168	91.52 125	97.16 187	87.77 144	87.93 206	83.69 194	96.35 154	95.10 207	97.23 137	99.68 101	99.73 83

tpmrst		93.86 172	95.88 163	91.50 181	95.69 122	98.62 145	95.64 166	79.41 216	98.80 113	83.76 166	95.63 141	96.13 98	97.25 129	92.92 217	92.31 216	97.27 220	96.74 218

tfpnnormal		93.85 173	94.12 188	93.54 148	93.22 173	98.24 169	95.45 170	91.96 114	94.61 219	83.91 162	90.74 183	81.75 209	97.04 133	97.49 149	96.16 167	99.68 101	99.84 25

TranMVSNet+NR-MVSNet		93.67 174	94.14 186	93.13 156	91.28 212	97.58 197	95.60 167	91.97 113	97.06 188	84.05 160	90.64 186	82.22 206	96.17 159	94.94 210	96.78 145	99.69 93	99.78 51

WR-MVS_H		93.54 175	94.67 179	92.22 164	91.95 189	97.91 179	94.58 193	88.75 165	96.64 199	83.88 163	90.66 185	85.13 188	94.40 194	96.54 176	95.91 176	99.73 61	99.89 13

TransMVSNet (Re)		93.45 176	94.08 189	92.72 161	92.83 174	97.62 195	94.94 178	91.54 124	95.65 216	83.06 172	88.93 196	83.53 196	94.25 196	97.41 151	97.03 140	99.67 110	98.40 199

SixPastTwentyTwo		93.44 177	95.32 170	91.24 187	92.11 186	98.40 162	92.77 205	88.64 168	98.09 155	77.83 200	93.51 163	85.74 183	96.52 151	96.91 168	94.89 200	99.59 145	99.73 83

WR-MVS		93.43 178	94.48 182	92.21 165	91.52 205	97.69 187	94.66 191	89.98 149	96.86 193	83.43 168	90.12 187	85.03 189	93.94 202	96.02 194	95.82 177	99.71 81	99.82 30

CP-MVSNet		93.25 179	94.00 192	92.38 163	91.65 200	97.56 199	94.38 196	89.20 160	96.05 210	83.16 171	89.51 191	81.97 207	96.16 160	96.43 178	96.56 154	99.71 81	99.89 13

UniMVSNet_ETH3D		93.15 180	92.33 213	94.11 134	93.91 161	98.61 147	94.81 184	90.98 134	97.06 188	87.51 146	82.27 222	76.33 228	97.87 116	94.79 211	97.47 131	99.56 156	99.81 35

anonymousdsp		93.12 181	95.86 164	89.93 203	91.09 213	98.25 168	95.12 174	85.08 196	97.44 178	73.30 215	90.89 182	90.78 149	95.25 185	97.91 124	95.96 175	99.71 81	99.82 30

V42		93.05 182	93.90 196	92.04 169	91.91 190	97.66 189	94.91 179	89.91 150	96.85 194	80.58 186	89.66 190	83.43 198	95.37 181	95.03 209	94.90 198	99.59 145	99.78 51

TDRefinement		93.04 183	93.57 200	92.41 162	96.58 91	98.77 132	97.78 107	91.96 114	98.12 154	80.84 184	89.13 195	79.87 220	87.78 220	96.44 177	94.50 205	99.54 162	98.15 201

v8		92.87 184	93.87 197	91.72 180	92.05 187	97.50 202	94.79 185	88.20 173	96.85 194	80.11 190	90.01 188	82.86 203	95.48 177	95.15 206	94.90 198	99.66 115	99.80 37

LTVRE_ROB	93.20 16	92.84 185	94.92 172	90.43 198	92.83 174	98.63 144	97.08 139	87.87 177	97.91 164	68.42 226	93.54 161	79.46 222	96.62 147	97.55 147	97.40 135	99.74 53	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		92.81 186	94.03 191	91.40 184	91.68 197	97.60 196	94.73 186	88.40 170	96.71 197	78.48 198	88.14 203	84.46 193	95.45 180	96.31 185	95.22 189	99.65 119	99.76 64

EU-MVSNet		92.80 187	94.76 177	90.51 196	91.88 191	96.74 217	92.48 207	88.69 166	96.21 205	79.00 196	91.51 177	87.82 165	91.83 215	95.87 197	96.27 162	99.21 191	98.92 187

v10		92.79 188	94.06 190	91.31 186	91.78 195	97.29 211	94.87 182	86.10 192	96.97 191	79.82 192	88.16 202	84.56 192	95.63 171	96.33 183	95.31 186	99.65 119	99.80 37

v2v482		92.77 189	93.52 203	91.90 176	91.59 203	97.63 192	94.57 194	90.31 145	96.80 196	79.22 194	88.74 198	81.55 210	96.04 163	95.26 203	94.97 196	99.66 115	99.69 104

PS-CasMVS		92.72 190	93.36 204	91.98 172	91.62 202	97.52 201	94.13 200	88.98 162	95.94 213	81.51 182	87.35 208	79.95 219	95.91 165	96.37 180	96.49 156	99.70 89	99.89 13

PEN-MVS		92.72 190	93.20 206	92.15 167	91.29 210	97.31 209	94.67 190	89.81 152	96.19 206	81.83 180	88.58 199	79.06 223	95.61 173	95.21 204	96.27 162	99.72 70	99.82 30

pmmvs5		92.71 192	94.27 185	90.90 193	91.42 207	97.74 184	93.23 202	86.66 187	95.99 212	78.96 197	91.45 178	83.44 197	95.55 174	97.30 157	95.05 194	99.58 149	98.93 184

MVS-HIRNet		92.51 193	95.97 160	88.48 209	93.73 167	98.37 164	90.33 215	75.36 230	98.32 145	77.78 201	89.15 194	94.87 112	95.14 187	97.62 144	96.39 159	98.51 203	97.11 214

EG-PatchMatch MVS		92.45 194	93.92 195	90.72 195	92.56 178	98.43 160	94.88 181	84.54 201	97.18 184	79.55 193	86.12 215	83.23 199	93.15 210	97.22 160	96.00 171	99.67 110	99.27 168

pmnet_mix02		92.44 195	94.68 178	89.83 204	92.46 180	97.65 191	89.92 219	90.49 144	98.76 121	73.05 218	91.78 176	90.08 153	94.86 191	94.53 212	91.94 219	98.21 209	98.01 205

MDTV_nov1_ep13_2view		92.44 195	95.66 166	88.68 207	91.05 214	97.92 178	92.17 208	79.64 214	98.83 108	76.20 205	91.45 178	93.51 129	95.04 188	95.68 199	93.70 211	97.96 211	98.53 193

v1192		92.43 197	93.61 199	91.05 190	91.53 204	97.43 205	94.61 192	87.99 176	96.60 200	76.72 203	87.11 210	82.74 204	95.85 166	96.35 182	95.30 187	99.60 139	99.74 77

DTE-MVSNet		92.42 198	92.85 209	91.91 175	90.87 215	96.97 213	94.53 195	89.81 152	95.86 215	81.59 181	88.83 197	77.88 226	95.01 189	94.34 214	96.35 160	99.64 123	99.73 83

v144192		92.38 199	93.55 202	91.00 191	91.44 206	97.47 204	94.27 197	87.41 181	96.52 202	78.03 199	87.50 207	82.65 205	95.32 182	95.82 198	95.15 191	99.55 158	99.78 51

tpm		92.38 199	94.79 176	89.56 205	94.30 158	97.50 202	94.24 199	78.97 221	97.72 172	74.93 212	97.97 80	82.91 201	96.60 148	93.65 216	94.81 201	98.33 207	98.98 182

v1921920		92.36 201	93.57 200	90.94 192	91.39 208	97.39 207	94.70 188	87.63 180	96.60 200	76.63 204	86.98 211	82.89 202	95.75 167	96.26 188	95.14 192	99.55 158	99.73 83

v148		92.36 201	92.88 208	91.75 178	91.63 201	97.66 189	92.64 206	90.55 143	96.09 208	83.34 169	88.19 201	80.00 217	92.74 211	93.98 215	94.58 204	99.58 149	99.69 104

N_pmnet		92.21 203	94.60 180	89.42 206	91.88 191	97.38 208	89.15 221	89.74 155	97.89 165	73.75 214	87.94 205	92.23 139	93.85 204	96.10 191	93.20 213	98.15 210	97.43 211

v1240		91.99 204	93.33 205	90.44 197	91.29 210	97.30 210	94.25 198	86.79 184	96.43 203	75.49 210	86.34 214	81.85 208	95.29 183	96.42 179	95.22 189	99.52 165	99.73 83

pmmvs6		91.90 205	92.53 212	91.17 188	91.81 194	97.63 192	93.23 202	88.37 171	93.43 224	80.61 185	77.32 227	87.47 166	94.12 198	96.58 174	95.72 179	98.88 202	99.53 141

v7n		91.61 206	92.95 207	90.04 200	90.56 216	97.69 187	93.74 201	85.59 194	95.89 214	76.95 202	86.60 213	78.60 225	93.76 205	97.01 166	94.99 195	99.65 119	99.87 18

gg-mvs-nofinetune		90.85 207	94.14 186	87.02 212	94.89 152	99.25 104	98.64 62	76.29 228	88.24 229	57.50 233	79.93 224	95.45 105	95.18 186	98.77 63	98.07 99	99.62 129	99.24 170

CMPMVS	70.31 18	90.74 208	91.06 216	90.36 199	97.32 76	97.43 205	92.97 204	87.82 179	93.50 223	75.34 211	83.27 220	84.90 190	92.19 214	92.64 219	91.21 223	96.50 226	94.46 224
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20231206		90.70 209	93.93 194	86.92 213	90.21 219	96.79 215	90.30 216	86.61 188	96.05 210	69.25 223	88.46 200	84.86 191	85.86 222	97.11 164	96.47 158	99.30 187	97.80 207

test20.03		90.65 210	93.71 198	87.09 211	90.44 217	96.24 218	89.74 220	85.46 195	95.59 217	72.99 219	90.68 184	85.33 186	84.41 223	95.94 196	95.10 193	99.52 165	97.06 216

new_pmnet		90.45 211	92.84 210	87.66 210	88.96 220	96.16 219	88.71 222	84.66 200	97.56 175	71.91 222	85.60 216	86.58 177	93.28 208	96.07 192	93.54 212	98.46 204	94.39 225

pmmvs-eth3d		89.81 212	89.65 220	90.00 201	86.94 224	95.38 222	91.08 210	86.39 189	94.57 220	82.27 178	83.03 221	64.94 232	93.96 201	96.57 175	93.82 210	99.35 184	99.24 170

PM-MVS		89.55 213	90.30 218	88.67 208	87.06 223	95.60 221	90.88 212	84.51 202	96.14 207	75.75 206	86.89 212	63.47 235	94.64 192	96.85 170	93.89 208	99.17 194	99.29 164

gm-plane-assit		89.44 214	92.82 211	85.49 216	91.37 209	95.34 223	79.55 232	82.12 206	91.68 228	64.79 230	87.98 204	80.26 216	95.66 170	98.51 87	97.56 124	99.45 172	98.41 196

MIMVSNet1		88.61 215	90.68 217	86.19 215	81.56 229	95.30 224	87.78 224	85.98 193	94.19 222	72.30 221	78.84 225	78.90 224	90.06 216	96.59 173	95.47 182	99.46 171	95.49 223

pmmvs3		88.19 216	91.27 215	84.60 218	85.60 226	93.66 227	85.68 227	81.13 208	92.36 227	63.66 232	89.51 191	77.10 227	93.22 209	96.37 180	92.40 215	98.30 208	97.46 210

MDA-MVSNet-bldmvs		87.84 217	89.22 221	86.23 214	81.74 228	96.77 216	83.74 228	89.57 157	94.50 221	72.83 220	96.64 112	64.47 234	92.71 212	81.43 229	92.28 217	96.81 224	98.47 195

test_method		87.27 218	91.58 214	82.25 221	75.65 234	87.52 233	86.81 226	72.60 231	97.51 176	73.20 217	85.07 217	79.97 218	88.69 218	97.31 156	95.24 188	96.53 225	98.41 196

FE-MVSNET		86.50 219	88.24 222	84.47 219	76.04 232	94.06 226	87.91 223	86.26 191	92.71 225	69.03 225	77.33 226	66.72 231	88.34 219	95.57 200	93.83 209	99.27 189	97.48 209

new-patchmatchnet		86.12 220	87.30 223	84.74 217	86.92 225	95.19 225	83.57 229	84.42 203	92.67 226	65.66 227	80.32 223	64.72 233	89.41 217	92.33 222	89.21 225	98.43 205	96.69 219

FPMVS		83.82 221	84.61 224	82.90 220	90.39 218	90.71 229	90.85 213	84.10 204	95.47 218	65.15 228	83.44 219	74.46 229	75.48 226	81.63 228	79.42 230	91.42 231	87.14 230

Gipuma		81.40 222	81.78 225	80.96 223	83.21 227	85.61 234	79.73 231	76.25 229	97.33 181	64.21 231	55.32 231	55.55 236	86.04 221	92.43 221	92.20 218	96.32 227	93.99 226
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
WB-MVS		81.36 223	89.93 219	71.35 226	88.65 221	87.85 232	71.46 234	88.12 175	96.23 204	32.21 238	92.61 174	83.00 200	56.27 233	91.92 223	89.43 224	91.39 232	88.49 229

PMMVS2		77.26 224	79.47 227	74.70 225	76.00 233	88.37 231	74.22 233	76.34 227	78.31 231	54.13 234	69.96 229	52.50 237	70.14 230	84.83 227	88.71 226	97.35 218	93.58 227

PMVS	72.60 17	76.39 225	77.66 228	74.92 224	81.04 230	69.37 238	68.47 235	80.54 211	85.39 230	65.07 229	73.52 228	72.91 230	65.67 232	80.35 230	76.81 231	88.71 233	85.25 233
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GG-mvs-BLEND		69.11 226	98.13 81	35.26 230	3.49 240	98.20 171	94.89 180	2.38 236	98.42 139	5.82 241	96.37 120	98.60 67	5.97 236	98.75 66	97.98 102	99.01 197	98.61 191

E-PMN		68.30 227	68.43 229	68.15 227	74.70 236	71.56 237	55.64 237	77.24 225	77.48 233	39.46 236	51.95 234	41.68 239	73.28 228	70.65 232	79.51 229	88.61 234	86.20 232

EMVS		68.12 228	68.11 230	68.14 228	75.51 235	71.76 236	55.38 238	77.20 226	77.78 232	37.79 237	53.59 232	43.61 238	74.72 227	67.05 233	76.70 232	88.27 235	86.24 231

MVE	67.97 19	65.53 229	67.43 231	63.31 229	59.33 237	74.20 235	53.09 239	70.43 232	66.27 234	43.13 235	45.98 235	30.62 240	70.65 229	79.34 231	86.30 227	83.25 236	89.33 228
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		31.24 230	40.15 232	20.86 231	12.61 238	17.99 239	25.16 240	13.30 234	48.42 235	24.82 239	53.07 233	30.13 242	28.47 234	42.73 234	37.65 233	20.79 237	51.04 234

test123		26.75 231	34.25 233	18.01 232	7.93 239	17.18 240	24.85 241	12.36 235	44.83 236	16.52 240	41.80 236	18.10 243	28.29 235	33.08 235	34.79 234	18.10 238	49.95 235

uanet_test		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 244	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

sosnet-low-res		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 244	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

sosnet		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 244	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

TPM-MVS					99.57 26	98.90 125	98.79 58			96.52 37	98.62 57	99.91 31	97.56 122			99.44 174	99.28 165
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										69.05 224

9.14												99.79 45

SR-MVS					99.67 13			98.25 14				99.94 25

Anonymous202405211			97.40 113		96.45 92	99.54 54	98.08 97	93.79 78	98.24 150		93.55 160	94.41 119	98.88 70	98.04 116	98.24 89	99.75 47	99.76 64

our_test_3					92.30 182	97.58 197	90.09 218

ambc			80.99 226		80.04 231	90.84 228	90.91 211		96.09 208	74.18 213	62.81 230	30.59 241	82.44 225	96.25 189	91.77 220	95.91 228	98.56 192

MTAPA										98.09 15		99.97 8

MTMP										98.46 10		99.96 12

Patchmatch-RL test							66.86 236

tmp_tt				82.25 221	97.73 70	88.71 230	80.18 230	68.65 233	99.15 63	86.98 148	99.47 11	85.31 187	68.35 231	87.51 226	83.81 228	91.64 230

XVS					97.42 74	99.62 33	98.59 65			93.81 85		99.95 17				99.69 93

X-MVStestdata					97.42 74	99.62 33	98.59 65			93.81 85		99.95 17				99.69 93

mPP-MVS					99.53 30							99.89 35

NP-MVS									98.57 131

Patchmtry						98.59 148	97.15 134	79.14 218		80.42 187

DeepMVS_CX						96.85 214	87.43 225	89.27 159	98.30 146	75.55 209	95.05 145	79.47 221	92.62 213	89.48 225		95.18 229	95.96 222

High-resolution multi-view benchmark