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.

RA-MVS		99.64 1	99.87 1	99.37 2	99.62 11	99.95 15	99.95 1	96.99 4	99.97 11	99.76 4	99.63 23	100.00 1	99.90 8	99.87 14	99.67 13	99.96 15	100.00 1

aaEdge-Enhanced		99.62 2	99.80 4	99.41 1	99.64 8	99.95 15	99.91 2	97.15 2	99.93 37	99.83 3	99.61 25	100.00 1	99.94 1	99.86 15	99.29 28	100.00 1	100.00 1

MED-MVS		99.54 3	99.73 18	99.32 3	99.64 8	99.96 7	99.75 21	96.98 6	99.98 4	99.84 2	99.61 25	100.00 1	99.91 5	99.72 23	98.84 47	99.79 73	100.00 1

SED-MVS		99.44 4	99.69 24	99.15 4	99.61 17	99.95 15	99.81 9	96.94 11	99.97 11	98.73 6	99.53 34	100.00 1	99.91 5	99.90 8	98.52 63	99.87 34	100.00 1

SF-MVS		99.41 5	99.68 26	99.09 6	99.65 7	99.94 23	99.76 14	96.95 8	99.88 48	98.39 9	99.60 27	100.00 1	99.82 18	99.43 31	98.93 41	99.99 7	100.00 1

APDe-MVS		99.40 6	99.81 3	98.92 11	99.62 11	99.96 7	99.76 14	96.87 19	99.95 29	97.66 11	99.57 32	100.00 1	99.63 33	99.88 11	99.28 29	100.00 1	100.00 1
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MSLP-MVS++		99.39 7	99.76 11	98.95 9	99.60 21	99.99 1	99.83 7	96.82 21	99.92 42	97.58 14	99.58 31	100.00 1	99.93 2	98.98 38	99.86 8	99.96 15	100.00 1

CNVR-MVS		99.39 7	99.75 14	98.98 7	99.69 1	99.95 15	99.76 14	96.91 14	99.98 4	97.59 13	99.64 21	100.00 1	99.93 2	99.94 2	98.75 56	99.97 14	99.97 104

DVP-MVS		99.38 9	99.57 40	99.15 4	99.62 11	99.94 23	99.72 28	96.99 4	99.98 4	98.85 5	98.21 88	100.00 1	99.88 12	99.88 11	98.96 39	99.85 38	100.00 1
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
MSP-MVS		99.38 9	99.78 7	98.91 14	99.61 17	99.96 7	99.85 5	96.94 11	99.96 23	97.38 17	99.60 27	100.00 1	99.70 25	99.96 1	98.96 39	100.00 1	100.00 1
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
DPE-MVS		99.37 11	99.74 17	98.94 10	99.60 21	99.94 23	99.87 4	96.95 8	99.94 34	97.42 15	99.62 24	100.00 1	99.80 21	99.91 5	98.78 54	99.98 12	100.00 1
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		99.36 12	99.70 23	98.96 8	99.62 11	99.94 23	99.85 5	96.90 18	99.97 11	97.64 12	99.50 38	100.00 1	99.88 12	99.90 8	98.60 58	99.87 34	100.00 1

SMA-MVS		99.34 13	99.79 6	98.81 16	99.69 1	99.94 23	99.75 21	96.91 14	99.98 4	96.76 19	99.37 45	100.00 1	99.90 8	99.88 11	99.46 18	99.84 41	99.92 151
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
APD-MVS		99.33 14	99.85 2	98.73 17	99.61 17	99.92 45	99.77 13	96.91 14	99.93 37	96.31 23	99.59 30	99.95 46	99.84 16	99.73 20	99.84 9	99.95 18	100.00 1
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		99.24 15	99.75 14	98.65 18	99.63 10	99.96 7	99.76 14	96.91 14	99.97 11	95.86 27	99.67 12	100.00 1	99.75 22	99.85 16	98.80 52	99.98 12	99.97 104

CNLPA		99.24 15	99.58 37	98.85 15	99.34 37	99.95 15	99.32 42	96.65 31	99.96 23	98.44 8	98.97 60	100.00 1	99.57 36	98.66 47	99.56 16	99.76 93	99.97 104

AdaColmap		99.21 17	99.45 43	98.92 11	99.67 5	99.95 15	99.65 33	96.77 26	99.97 11	97.67 10	100.00 1	99.69 60	99.93 2	99.26 34	97.25 126	99.85 38	100.00 1

HFP-MVS		99.19 18	99.77 10	98.51 21	99.55 25	99.94 23	99.76 14	96.84 20	99.88 48	95.27 31	99.67 12	100.00 1	99.85 15	99.56 26	99.36 23	99.79 73	99.97 104

PLC	98.06 1	99.17 19	99.38 45	98.92 11	99.47 27	99.90 54	99.48 38	96.47 36	99.96 23	98.73 6	99.52 37	100.00 1	99.55 38	98.54 61	97.73 94	99.84 41	99.99 68
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SD-MVS		99.16 20	99.73 18	98.49 22	97.93 57	99.95 15	99.74 25	96.94 11	99.96 23	96.60 21	99.47 41	100.00 1	99.88 12	99.15 36	99.59 14	99.84 41	100.00 1
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
CP-MVS		99.14 21	99.67 27	98.53 20	99.45 29	99.94 23	99.63 35	96.62 33	99.82 61	95.92 26	99.65 17	100.00 1	99.71 24	99.76 19	98.56 60	99.83 47	100.00 1

ACMMPR		99.12 22	99.76 11	98.36 23	99.45 29	99.94 23	99.75 21	96.70 30	99.93 37	94.65 35	99.65 17	99.96 44	99.84 16	99.51 29	99.35 24	99.79 73	99.96 125

MCST-MVS		99.08 23	99.72 21	98.33 24	99.59 24	99.97 3	99.78 12	96.96 7	99.95 29	93.72 40	99.67 12	100.00 1	99.90 8	99.91 5	98.55 61	100.00 1	100.00 1

CPTT-MVS		99.08 23	99.53 42	98.57 19	99.44 31	99.93 39	99.60 36	95.92 41	99.77 69	97.01 18	99.67 12	100.00 1	99.72 23	99.56 26	97.76 89	99.70 142	99.98 88

DeepC-MVS_fast	98.03 2	99.05 25	99.78 7	98.21 27	99.47 27	99.97 3	99.75 21	96.80 22	99.97 11	93.58 42	98.68 71	99.94 47	99.69 26	99.93 4	99.95 3	99.96 15	99.98 88
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + MP.		98.99 26	99.61 34	98.27 25	97.88 58	99.92 45	99.71 30	96.80 22	99.96 23	95.58 29	98.71 70	100.00 1	99.68 28	99.91 5	98.78 54	99.99 7	100.00 1
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		98.98 27	99.62 33	98.22 26	99.62 11	99.94 23	99.74 25	96.95 8	99.87 52	93.76 39	99.49 40	100.00 1	99.39 44	99.73 20	98.35 66	99.89 30	99.96 125

SteuartSystems-ACMMP		98.95 28	99.80 4	97.95 30	99.43 32	99.96 7	99.76 14	96.45 37	99.82 61	93.63 41	99.64 21	100.00 1	98.56 89	99.90 8	99.31 26	99.84 41	100.00 1
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		98.85 29	99.67 27	97.89 31	98.63 52	99.93 39	98.95 53	95.20 43	99.84 59	94.94 32	99.74 11	100.00 1	99.69 26	98.40 68	99.75 11	99.93 23	99.99 68

MP-MVS		98.82 30	99.63 31	97.88 32	99.41 33	99.91 53	99.74 25	96.76 27	99.88 48	91.89 53	99.50 38	99.94 47	99.65 31	99.71 24	98.49 64	99.82 51	99.97 104
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMP_NAP		98.68 31	99.58 37	97.62 33	99.62 11	99.92 45	99.72 28	96.78 25	99.71 74	90.13 82	99.66 16	99.99 37	99.63 33	99.78 18	98.14 74	99.82 51	99.89 165

train_agg		98.62 32	99.76 11	97.28 35	99.03 45	99.93 39	99.65 33	96.37 38	99.98 4	89.24 94	99.53 34	99.83 52	99.59 35	99.85 16	99.19 33	99.80 66	100.00 1

X-MVS		98.62 32	99.75 14	97.29 34	99.50 26	99.94 23	99.71 30	96.55 34	99.85 56	88.58 100	99.65 17	99.98 39	99.67 29	99.60 25	99.26 30	99.77 85	99.97 104

OMC-MVS		98.59 34	99.07 51	98.03 29	99.41 33	99.90 54	99.26 45	94.33 45	99.94 34	96.03 24	96.68 105	99.72 59	99.42 41	98.86 41	98.84 47	99.72 133	99.58 217

DPM-MVS		98.58 35	99.78 7	97.17 37	98.02 56	99.64 88	99.80 11	96.72 29	99.96 23	90.05 84	99.57 32	100.00 1	98.66 85	99.56 26	99.96 2	99.80 66	99.80 194

PGM-MVS		98.47 36	99.73 18	97.00 39	99.68 3	99.94 23	99.76 14	91.74 51	99.84 59	91.17 69	100.00 1	99.69 60	99.81 19	99.38 32	99.30 27	99.82 51	99.95 138

MGCNet		98.44 37	99.67 27	97.00 39	97.82 60	99.92 45	99.46 39	91.78 50	99.95 29	94.10 37	100.00 1	100.00 1	98.91 71	98.59 55	99.22 31	99.95 18	99.99 68

TSAR-MVS + ACMM		98.30 38	99.64 30	96.74 43	99.08 44	99.94 23	99.67 32	96.73 28	99.97 11	86.30 133	98.30 79	99.99 37	98.78 79	99.73 20	99.57 15	99.88 33	99.98 88

CSCG		98.22 39	98.37 72	98.04 28	99.60 21	99.82 64	99.45 40	93.59 46	99.16 114	96.46 22	98.22 87	95.86 110	99.41 43	96.33 161	99.22 31	99.75 104	99.94 145

3Dnovator+	95.21 7	98.17 40	99.08 50	97.12 38	99.28 40	99.78 75	98.61 60	89.93 65	99.93 37	95.36 30	95.50 116	100.00 1	99.56 37	98.58 56	99.80 10	99.95 18	99.97 104

ACMMP		98.16 41	99.01 52	97.18 36	98.86 47	99.92 45	98.77 58	95.73 42	99.31 109	91.15 70	100.00 1	99.81 54	98.82 77	98.11 91	95.91 169	99.77 85	99.97 104
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
MVS_111021_LR		98.15 42	99.69 24	96.36 48	99.23 42	99.93 39	97.79 72	91.84 49	99.87 52	90.53 78	100.00 1	99.57 65	98.93 70	99.44 30	99.08 36	99.85 38	99.95 138

EPNet		98.11 43	99.63 31	96.34 49	98.44 54	99.88 59	98.55 61	90.25 61	99.93 37	92.60 49	100.00 1	99.73 57	98.41 96	98.87 40	99.02 37	99.82 51	99.97 104
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TSAR-MVS + GP.		98.06 44	99.55 41	96.32 50	94.72 85	99.92 45	99.22 46	89.98 63	99.97 11	94.77 34	99.94 10	100.00 1	99.43 40	98.52 65	98.53 62	99.79 73	100.00 1

3Dnovator	95.01 8	97.98 45	98.89 57	96.92 42	99.36 35	99.76 78	98.72 59	89.98 63	99.98 4	93.99 38	94.60 130	99.43 70	99.50 39	98.55 58	99.91 5	99.99 7	99.98 88

MVS_111021_HR		97.94 46	99.59 35	96.02 52	99.27 41	99.97 3	97.03 100	90.44 58	99.89 46	90.75 73	100.00 1	99.73 57	98.68 84	98.67 46	98.89 44	99.95 18	99.97 104

QAPM		97.90 47	98.89 57	96.74 43	99.35 36	99.80 70	98.84 55	90.20 62	99.94 34	92.85 44	94.17 134	99.78 55	99.42 41	98.71 44	99.87 7	99.79 73	99.98 88

CDPH-MVS		97.88 48	99.59 35	95.89 53	98.90 46	99.95 15	99.40 41	92.86 48	99.86 55	85.33 146	98.62 73	99.45 69	99.06 65	99.29 33	99.94 4	99.81 61	100.00 1

CANet		97.62 49	98.94 55	96.08 51	97.19 63	99.93 39	99.29 44	90.38 59	99.87 52	91.00 71	95.79 115	99.51 66	98.72 83	98.53 62	99.00 38	99.90 28	99.99 68

TAPA-MVS	96.62 5	97.60 50	98.46 71	96.60 46	98.73 50	99.90 54	99.30 43	94.96 44	99.46 92	87.57 113	96.05 112	98.53 82	99.26 55	98.04 96	97.33 122	99.77 85	99.88 171
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DeepPCF-MVS	97.16 4	97.58 51	99.72 21	95.07 68	98.45 53	99.96 7	93.83 185	95.93 40	100.00 1	90.79 72	98.38 78	99.85 51	95.28 173	99.94 2	99.97 1	96.15 263	99.97 104

SPE-MVS-test		97.51 52	99.18 48	95.56 58	97.16 64	99.96 7	97.39 86	89.82 68	100.00 1	89.88 85	99.16 52	98.38 88	99.23 57	98.85 42	97.93 81	99.87 34	100.00 1

PCF-MVS	97.20 3	97.49 53	98.20 77	96.66 45	97.62 61	99.92 45	98.93 54	96.64 32	98.53 155	88.31 107	94.04 137	99.58 64	98.94 67	97.53 117	97.79 87	99.54 179	99.97 104
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CS-MVS		97.46 54	98.98 53	95.68 57	96.74 68	99.93 39	97.62 78	89.69 69	99.98 4	91.33 66	98.53 76	97.50 97	98.77 80	98.60 54	98.35 66	99.92 25	100.00 1

MSDG		97.29 55	97.55 93	97.00 39	98.66 51	99.71 83	99.03 51	96.15 39	99.59 81	89.67 91	92.77 154	94.86 113	98.75 81	98.22 80	97.94 79	99.72 133	99.76 199

CHOSEN 280x420		97.16 56	99.58 37	94.35 84	96.95 67	99.97 3	97.19 93	81.55 192	99.92 42	91.75 60	100.00 1	100.00 1	98.84 76	98.55 58	98.65 57	99.79 73	99.97 104

MVSMamba_PlusPlus		97.06 57	99.09 49	94.69 77	92.17 119	99.75 79	99.05 50	89.87 67	99.95 29	87.59 112	97.96 92	97.97 92	99.64 32	98.62 52	99.46 18	99.82 51	99.96 125

DELS-MVS		97.05 58	98.05 82	95.88 55	97.09 65	99.99 1	98.82 56	90.30 60	98.44 161	91.40 64	92.91 151	96.57 103	97.68 143	98.56 57	99.88 6	100.00 1	100.00 1
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DeepC-MVS	96.33 6	97.05 58	97.59 92	96.42 47	97.37 62	99.92 45	99.10 48	96.54 35	99.34 106	86.64 127	91.93 164	93.15 124	99.11 63	99.11 37	99.68 12	99.73 123	99.97 104
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test2506		97.04 60	98.09 81	95.81 56	94.12 90	99.80 70	97.33 89	89.48 73	98.90 134	95.99 25	99.11 55	92.84 126	98.14 116	98.14 87	98.32 70	99.82 51	99.51 222

MAR-MVS		97.03 61	98.00 84	95.89 53	99.32 38	99.74 82	96.76 110	84.89 144	99.97 11	94.86 33	98.29 80	90.58 134	99.67 29	98.02 98	99.50 17	99.82 51	99.92 151
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
MVSTER		97.00 62	98.85 59	94.83 75	92.71 109	97.43 189	99.03 51	85.52 137	99.82 61	92.74 47	99.15 53	99.94 47	99.19 60	98.66 47	96.99 141	99.79 73	99.98 88

EC-MVSNet		96.90 63	99.32 46	94.07 86	91.64 157	99.30 131	98.18 68	85.61 136	99.97 11	89.79 86	99.33 46	99.31 73	99.28 53	98.48 67	98.86 45	99.91 26	100.00 1

baseline1		96.87 64	98.55 65	94.91 70	92.89 108	99.45 103	96.34 118	88.54 86	98.88 137	92.82 45	98.93 62	96.58 102	99.07 64	98.19 82	98.04 76	99.80 66	99.78 196

OpenMVS	94.03 11	96.87 64	98.10 80	95.44 62	99.29 39	99.78 75	98.46 66	89.92 66	99.47 91	85.78 142	91.05 174	98.50 83	99.30 51	98.49 66	99.41 20	99.89 30	99.98 88

PatchMatch-RL		96.84 66	98.03 83	95.47 59	98.84 48	99.81 68	95.61 151	89.20 77	99.65 78	91.28 67	99.39 42	93.46 122	98.18 113	98.05 94	96.28 153	99.69 147	99.55 219

ETV-MVS		96.79 67	99.19 47	94.00 88	91.78 142	99.63 90	97.15 95	88.00 92	99.95 29	88.34 106	99.32 47	98.71 79	98.82 77	98.69 45	98.01 77	99.90 28	100.00 1

IS_MVSNet		96.66 68	98.62 64	94.38 80	92.41 115	99.70 84	97.19 93	87.67 107	99.05 123	91.27 68	95.09 121	98.46 87	97.95 128	98.64 49	99.37 21	99.79 73	100.00 1

PMMVS		96.45 69	98.24 76	94.36 83	92.58 110	99.01 149	97.08 99	87.42 127	99.88 48	90.06 83	99.39 42	94.63 114	99.33 48	97.85 104	96.99 141	99.70 142	99.96 125

LS3D		96.44 70	97.31 100	95.41 63	97.06 66	99.87 60	99.51 37	97.48 1	99.57 82	79.00 170	95.39 117	89.19 141	99.81 19	98.55 58	98.84 47	99.62 168	99.78 196

EIA-MVS		96.34 71	98.55 65	93.76 95	91.93 132	99.66 86	97.14 96	88.33 90	99.51 86	85.98 138	98.82 66	96.08 108	99.33 48	98.38 71	97.40 116	99.81 61	100.00 1

EPP-MVSNet		96.29 72	98.34 73	93.90 90	91.77 144	99.38 111	95.45 157	87.25 132	99.38 101	91.36 65	94.86 128	98.49 85	97.83 136	98.01 99	98.23 72	99.75 104	99.99 68

UGNet		96.05 73	98.55 65	93.13 118	94.64 86	99.65 87	94.70 173	87.78 96	99.40 100	89.69 90	98.25 83	99.25 75	92.12 214	96.50 152	97.08 136	99.84 41	99.72 207
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
COLMAP_ROB	93.56 12	96.03 74	96.83 114	95.11 67	97.87 59	99.52 94	98.81 57	91.40 54	99.42 96	84.97 149	90.46 179	96.82 101	98.05 121	96.46 156	96.19 156	99.54 179	98.92 237
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PVSNet_BlendedMVS		96.01 75	96.48 123	95.46 60	96.47 70	99.89 57	95.64 147	91.23 55	99.75 71	91.59 62	96.80 102	82.44 184	98.05 121	98.53 62	97.92 82	99.80 66	100.00 1

PVSNet_Blended		96.01 75	96.48 123	95.46 60	96.47 70	99.89 57	95.64 147	91.23 55	99.75 71	91.59 62	96.80 102	82.44 184	98.05 121	98.53 62	97.92 82	99.80 66	100.00 1

thisisatest0530		95.89 77	98.32 74	93.06 125	91.76 145	99.75 79	94.94 165	87.60 113	99.91 44	86.66 126	98.28 81	99.98 39	97.72 139	97.10 133	93.24 205	99.65 160	99.95 138

tttt0517		95.88 78	98.31 75	93.04 126	91.75 147	99.75 79	94.90 166	87.60 113	99.91 44	86.63 128	98.28 81	99.98 39	97.72 139	97.10 133	93.24 205	99.65 160	99.95 138

thres100view900		95.86 79	96.62 117	94.97 69	93.10 98	99.83 62	97.76 73	89.15 78	98.62 151	90.69 74	99.00 57	84.86 168	99.30 51	97.57 115	96.48 148	99.81 61	100.00 1

RPSCF		95.86 79	96.94 112	94.61 78	96.52 69	98.67 165	98.54 62	88.43 88	99.56 83	90.51 80	99.39 42	98.70 80	97.72 139	93.77 213	92.00 222	95.93 264	96.50 258

DCV-MVSNet		95.85 81	97.53 94	93.89 91	93.20 97	97.01 195	97.14 96	84.77 145	99.16 114	90.38 81	98.96 61	93.73 119	98.23 112	96.57 151	97.37 117	99.64 164	99.93 147

baseline		95.85 81	98.13 79	93.20 116	92.29 118	99.58 92	97.49 80	84.33 154	99.44 93	87.28 119	97.00 100	94.04 118	97.93 129	98.36 73	98.47 65	99.87 34	99.99 68

sasdasda		95.80 83	97.02 105	94.37 81	92.96 104	99.47 99	97.49 80	84.58 147	99.44 93	92.05 51	98.54 74	86.65 151	99.37 45	96.18 165	98.93 41	99.77 85	99.92 151

canonicalmvs		95.80 83	97.02 105	94.37 81	92.96 104	99.47 99	97.49 80	84.58 147	99.44 93	92.05 51	98.54 74	86.65 151	99.37 45	96.18 165	98.93 41	99.77 85	99.92 151

tfpn200view9		95.78 85	96.54 120	94.89 72	93.10 98	99.82 64	97.67 74	88.85 81	98.62 151	90.69 74	99.00 57	84.86 168	99.28 53	97.41 125	96.10 159	99.76 93	99.99 68

thres200		95.77 86	96.55 119	94.86 73	93.09 100	99.82 64	97.63 77	88.85 81	98.49 156	90.66 76	98.99 59	84.86 168	99.20 58	97.41 125	96.28 153	99.76 93	100.00 1

MVS_Test		95.74 87	98.18 78	92.90 130	92.16 120	99.49 98	97.36 87	84.30 155	99.79 66	84.94 150	96.65 106	93.63 121	98.85 75	98.61 53	99.10 35	99.81 61	100.00 1

thres400		95.72 88	96.48 123	94.84 74	93.00 103	99.83 62	97.55 79	88.93 79	98.49 156	90.61 77	98.86 63	84.63 172	99.20 58	97.45 119	96.10 159	99.77 85	99.99 68

MGCFI-Net		95.71 89	96.97 111	94.25 85	92.90 107	99.44 106	97.35 88	84.44 152	99.42 96	91.70 61	98.51 77	86.56 154	99.33 48	96.09 170	98.83 50	99.77 85	99.92 151

thres600view7		95.64 90	96.38 127	94.79 76	92.96 104	99.82 64	97.48 85	88.85 81	98.38 162	90.52 79	98.84 65	84.61 173	99.15 61	97.41 125	95.60 174	99.76 93	99.99 68

Vis-MVSNet (Re-imp)		95.60 91	98.52 70	92.19 140	92.37 116	99.56 93	96.37 116	87.41 128	98.95 129	84.77 153	94.88 127	98.48 86	92.44 211	98.63 51	99.37 21	99.76 93	99.77 198

FMVSNet3		95.59 92	97.51 96	93.34 106	89.48 182	96.57 203	97.67 74	84.17 157	99.48 88	89.76 87	95.09 121	94.35 115	99.14 62	98.37 72	98.86 45	99.82 51	99.89 165

ECVR-MVS		95.46 93	95.58 152	95.31 65	94.12 90	99.80 70	97.33 89	89.48 73	98.90 134	92.99 43	87.97 194	86.41 157	98.14 116	98.14 87	98.32 70	99.82 51	99.52 221

E2		95.42 94	96.83 114	93.78 93	91.73 149	99.38 111	96.39 115	87.87 93	98.79 141	88.36 105	95.90 114	88.17 143	98.59 87	97.72 107	97.85 84	99.75 104	99.98 88

PVSNet_Blended_VisFu		95.37 95	97.44 98	92.95 127	95.20 78	99.80 70	92.68 194	88.41 89	99.12 117	87.64 111	88.31 193	99.10 76	94.07 189	98.27 76	97.51 106	99.73 123	100.00 1

DI_MVS_pp		95.29 96	97.02 105	93.28 110	91.76 145	99.52 94	97.84 71	85.67 135	99.08 121	87.29 118	87.76 198	97.46 98	97.31 147	97.83 105	97.48 108	99.83 47	100.00 1

ET-MVSNet_ETH3D		95.20 97	97.82 89	92.15 141	80.77 251	98.13 177	97.65 76	86.93 133	99.72 73	88.56 103	99.29 50	97.01 100	99.24 56	94.58 199	95.98 166	99.75 104	99.99 68

TSAR-MVS + COLMAP		95.20 97	95.03 164	95.41 63	96.17 72	98.69 164	99.11 47	93.40 47	99.97 11	84.89 151	98.23 85	75.01 221	99.34 47	97.27 130	96.37 152	99.58 172	99.64 215

GBi-Net		95.19 99	96.99 109	93.09 120	89.11 183	96.47 205	96.90 102	84.17 157	99.48 88	89.76 87	95.09 121	94.35 115	98.87 72	96.50 152	97.21 127	99.74 110	99.81 190

test1		95.19 99	96.99 109	93.09 120	89.11 183	96.47 205	96.90 102	84.17 157	99.48 88	89.76 87	95.09 121	94.35 115	98.87 72	96.50 152	97.21 127	99.74 110	99.81 190

Casviewmamba		95.18 101	96.38 127	93.78 93	91.93 132	99.35 120	96.87 105	87.70 101	98.75 143	87.91 109	93.22 149	87.56 149	98.54 90	98.23 79	97.74 92	99.75 104	99.84 184

test1111		95.15 102	95.18 160	95.12 66	94.07 92	99.80 70	97.20 92	89.53 72	98.80 140	92.22 50	85.44 210	86.24 159	97.89 131	98.12 89	98.34 69	99.80 66	99.51 222

test0.0.03 1		95.15 102	97.87 88	91.99 142	91.69 151	98.82 160	93.04 191	83.60 162	99.65 78	88.80 98	94.15 135	97.67 95	94.97 175	96.62 149	98.16 73	99.83 47	100.00 1

baseline2		95.13 104	98.55 65	91.15 148	90.29 178	99.00 150	94.49 177	82.00 186	99.68 76	84.82 152	96.47 107	99.30 74	95.71 167	98.24 78	97.14 134	99.57 174	100.00 1

viewcassd2359sk11		95.10 105	96.36 129	93.63 96	91.68 154	99.37 115	96.09 127	87.78 96	98.72 144	88.01 108	94.74 129	86.41 157	98.47 93	97.69 109	97.61 101	99.73 123	99.98 88

casdiffmvs_mvg		95.10 105	96.45 126	93.53 98	92.05 127	99.42 108	97.25 91	87.66 108	97.17 193	86.09 134	91.79 166	91.27 128	98.31 106	98.06 93	97.42 115	99.81 61	100.00 1
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPNet_dtu		95.10 105	98.81 61	90.78 150	98.38 55	98.47 167	96.54 112	89.36 75	99.78 68	65.65 230	99.31 48	98.24 90	94.79 178	98.28 75	99.35 24	99.93 23	98.27 241
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
hybridcas		95.05 108	95.96 138	93.99 89	91.86 136	99.37 115	97.00 101	87.63 111	98.85 138	89.09 96	91.13 172	86.81 150	98.59 87	98.19 82	97.47 109	99.76 93	99.86 180

Anonymous20231211		94.96 109	94.99 165	94.91 70	93.01 102	99.44 106	96.85 107	88.49 87	98.78 142	92.61 48	83.94 217	90.25 136	98.94 67	95.87 176	96.77 143	99.58 172	99.89 165

UA-Net		94.95 110	98.66 63	90.63 152	94.60 88	98.94 156	96.03 129	85.28 139	98.01 175	78.92 171	97.42 98	99.96 44	89.09 238	98.95 39	98.80 52	99.82 51	98.57 239

CANet_DTU		94.90 111	98.98 53	90.13 160	94.74 84	99.81 68	98.53 63	82.23 184	99.97 11	66.76 227	100.00 1	98.50 83	98.74 82	97.52 118	97.19 132	99.76 93	99.88 171

viewdifsd2359ckpt09		94.88 112	96.22 131	93.31 107	91.61 159	99.38 111	96.37 116	87.74 98	98.82 139	85.85 139	93.69 142	86.65 151	98.61 86	97.57 115	97.44 112	99.72 133	100.00 1

viewdifsd2359ckpt07		94.83 113	96.18 136	93.25 113	91.96 131	99.31 129	97.10 98	87.65 109	98.66 149	85.26 147	91.50 169	88.11 144	97.77 138	98.16 84	97.69 96	99.74 110	99.84 184

viewdifsd2359ckpt13		94.69 114	96.20 134	92.93 129	91.67 156	99.42 108	95.73 144	87.71 100	98.67 147	84.46 154	94.31 132	86.03 161	98.27 111	97.60 112	97.35 120	99.73 123	99.99 68

E3new		94.68 115	95.67 150	93.52 100	91.63 158	99.36 118	95.96 132	87.69 105	97.81 181	87.65 110	93.38 145	84.22 178	98.48 92	97.44 120	97.52 104	99.71 137	99.96 125

E3		94.68 115	95.70 146	93.49 101	91.68 154	99.37 115	95.98 131	87.70 101	97.97 177	87.46 115	93.38 145	84.35 175	98.42 94	97.43 121	97.47 109	99.71 137	99.96 125

hybrid		94.67 117	95.86 143	93.27 112	92.11 123	99.25 139	95.62 149	87.59 115	99.37 102	86.71 124	95.07 125	82.63 183	97.88 132	97.23 131	97.50 107	99.72 133	100.00 1

onestephybrid01		94.66 118	95.70 146	93.44 102	92.13 122	99.27 136	95.49 154	87.83 95	99.33 108	87.53 114	91.54 168	85.46 166	97.92 130	96.65 147	97.63 99	99.76 93	100.00 1

viewmamba		94.61 119	95.73 145	93.30 108	92.07 125	99.30 131	95.91 137	87.51 120	99.29 111	86.31 132	93.17 150	84.33 176	98.28 110	96.42 159	97.61 101	99.73 123	99.99 68

viewmanbaseed2359cas		94.61 119	95.93 141	93.07 124	91.90 135	99.38 111	96.32 119	87.84 94	98.33 166	84.29 155	92.71 155	85.68 163	98.33 105	97.68 110	97.74 92	99.74 110	99.99 68

FC-MVSNet-train		94.61 119	96.27 130	92.68 137	92.35 117	97.14 193	93.45 189	87.73 99	98.93 130	87.31 117	96.42 108	89.35 139	95.67 168	96.06 174	96.01 165	99.56 176	99.98 88

diffmvs		94.60 122	95.63 151	93.41 104	91.98 130	99.30 131	96.86 106	87.62 112	99.30 110	86.07 137	94.12 136	81.63 194	98.16 114	97.43 121	97.60 103	99.76 93	100.00 1
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs		94.54 123	95.56 154	93.36 105	91.84 138	99.46 102	95.92 133	87.54 119	98.45 159	86.57 130	90.51 178	84.72 171	98.49 91	97.97 100	97.80 86	99.77 85	100.00 1
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CLD-MVS		94.53 124	94.45 179	94.61 78	93.85 94	98.36 170	98.12 69	89.68 70	99.35 105	89.62 92	95.19 119	77.08 211	96.66 158	95.51 182	95.67 172	99.74 110	100.00 1
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
hybridnocas07		94.51 125	95.57 153	93.28 110	92.09 124	99.29 135	95.82 138	87.55 118	99.34 106	86.52 131	93.79 141	82.79 182	97.99 126	96.33 161	97.43 114	99.71 137	100.00 1

viewmambaseed2359dif		94.51 125	95.35 157	93.53 98	91.78 142	99.34 121	96.78 109	87.58 117	98.29 167	86.97 123	92.34 157	84.00 179	98.35 102	96.15 168	97.31 125	99.74 110	100.00 1

FMVSNet2		94.48 127	95.95 139	92.77 135	89.11 183	96.47 205	96.90 102	83.38 165	99.11 118	88.64 99	87.50 203	92.26 127	98.87 72	97.91 102	98.60 58	99.74 110	99.81 190

HQP-MVS		94.48 127	95.39 156	93.42 103	95.10 79	98.35 171	98.19 67	91.41 53	99.77 69	79.79 167	99.30 49	77.08 211	96.25 161	96.93 136	96.28 153	99.76 93	99.99 68

dtuplus		94.35 129	95.26 158	93.30 108	91.49 165	99.32 128	96.08 128	87.45 124	97.99 176	86.60 129	91.07 173	85.48 165	98.42 94	95.75 179	97.18 133	99.73 123	100.00 1

FA-MVS(training)		94.33 130	97.52 95	90.60 154	92.42 114	99.77 77	96.13 126	68.75 246	99.05 123	88.49 104	91.95 162	99.48 67	98.12 119	98.39 69	94.02 197	99.68 149	99.98 88

MDTV_nov1_ep13		94.32 131	98.77 62	89.14 170	91.70 150	99.52 94	95.21 160	72.09 244	99.80 64	78.91 172	96.32 109	99.62 62	97.71 142	98.39 69	97.71 95	99.22 229	100.00 1

CDS-MVSNet		94.32 131	97.00 108	91.19 147	89.82 181	98.71 163	95.51 153	85.14 143	96.85 200	82.33 162	92.48 156	96.40 106	94.71 179	96.86 139	97.76 89	99.63 166	99.92 151
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
dps		94.29 133	97.33 99	90.75 151	92.02 128	99.21 140	94.31 179	66.97 252	99.50 87	95.61 28	96.22 111	98.64 81	96.08 163	93.71 215	94.03 196	99.52 183	99.98 88

ACMM	94.44 10	94.26 134	94.62 175	93.84 92	94.86 83	97.73 184	93.48 188	90.76 57	99.27 112	87.46 115	99.04 56	76.60 213	96.76 156	96.37 160	93.76 200	99.74 110	99.55 219
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
diffmvs_AUTHOR		94.21 135	95.08 161	93.18 117	91.86 136	99.26 138	96.42 113	87.48 121	99.02 126	85.45 145	92.20 159	80.25 204	98.14 116	97.16 132	97.69 96	99.73 123	100.00 1

ACMP	94.49 9	94.19 136	94.74 173	93.56 97	94.25 89	98.32 173	96.02 130	89.35 76	98.90 134	87.28 119	99.14 54	76.41 216	94.94 176	96.07 173	94.35 193	99.49 190	99.99 68
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
E5new		94.12 137	94.89 167	93.22 114	91.52 161	99.34 121	95.92 133	87.70 101	97.17 193	86.08 135	91.24 170	82.32 186	98.41 96	96.85 140	97.36 118	99.68 149	99.96 125

E5		94.12 137	94.89 167	93.22 114	91.52 161	99.34 121	95.92 133	87.70 101	97.17 193	86.08 135	91.24 170	82.32 186	98.41 96	96.85 140	97.36 118	99.68 149	99.96 125

EPMVS		94.08 139	98.54 69	88.87 171	92.51 112	99.47 99	94.18 181	66.53 253	99.68 76	82.40 161	95.24 118	99.40 71	97.86 133	98.12 89	97.99 78	99.75 104	99.88 171

E6new		93.99 140	94.76 170	93.09 120	91.51 163	99.33 126	95.80 140	87.45 124	97.13 196	85.80 140	90.97 175	81.86 191	98.30 107	96.74 144	97.32 123	99.67 153	99.95 138

E6		93.99 140	94.76 170	93.09 120	91.51 163	99.33 126	95.80 140	87.45 124	97.13 196	85.80 140	90.97 175	81.86 191	98.30 107	96.74 144	97.32 123	99.67 153	99.95 138

E4		93.99 140	94.72 174	93.13 118	91.53 160	99.34 121	95.92 133	87.59 115	97.20 191	85.67 143	90.19 180	82.18 188	98.41 96	96.83 142	97.34 121	99.68 149	99.96 125

viewmacassd2359aftdt		93.75 143	94.76 170	92.58 138	91.75 147	99.34 121	95.82 138	87.64 110	97.11 198	82.51 160	89.66 183	83.19 180	98.02 124	96.61 150	97.45 111	99.71 137	99.97 104

test-LLR		93.71 144	97.23 101	89.60 164	91.69 151	99.10 146	94.68 175	83.60 162	99.36 103	71.94 204	93.82 139	96.51 104	95.96 165	97.42 123	94.37 190	99.74 110	99.99 68

CHOSEN 1792x2688		93.69 145	94.89 167	92.28 139	96.17 72	99.84 61	95.69 146	83.17 168	98.54 154	82.04 163	77.58 249	91.15 130	96.90 151	98.36 73	98.82 51	99.73 123	99.98 88

viewdifsd2359ckpt11		93.64 146	94.30 182	92.88 132	91.82 140	98.82 160	94.88 167	87.46 122	99.08 121	86.98 122	92.20 159	80.79 195	97.85 134	93.32 223	96.13 157	98.30 246	99.75 201

viewmsd2359difaftdt		93.64 146	94.29 183	92.89 131	91.82 140	98.82 160	94.88 167	87.46 122	99.04 125	87.03 121	92.20 159	80.77 196	97.85 134	93.31 224	96.13 157	98.30 246	99.75 201

LGP-MVS_train		93.60 148	95.05 162	91.90 143	94.90 82	98.29 174	97.93 70	88.06 91	99.14 116	74.83 189	99.26 51	76.50 214	96.07 164	96.31 163	95.90 171	99.59 170	99.97 104

SCA		93.53 149	98.90 56	87.27 192	92.01 129	99.30 131	93.43 190	65.72 257	99.80 64	75.20 188	97.66 96	99.74 56	97.44 145	98.21 81	97.62 100	99.84 41	100.00 1

FMVSNet5		93.53 149	96.09 137	90.56 155	86.74 199	92.84 251	92.64 195	77.50 220	99.41 99	88.97 97	98.02 91	97.81 93	98.00 125	94.85 194	95.43 176	99.50 189	94.25 263

OPM-MVS		93.50 151	93.00 196	94.07 86	95.82 75	98.26 175	98.49 65	91.62 52	94.69 223	81.93 164	92.82 153	76.18 218	96.82 153	96.12 169	94.57 184	99.74 110	98.39 240
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CostFormer		93.50 151	96.50 122	90.00 161	91.69 151	98.65 166	93.88 184	67.64 250	98.97 127	89.16 95	97.79 94	88.92 142	97.97 127	95.14 191	96.06 161	99.63 166	100.00 1

IterMVS-LS		93.50 151	96.22 131	90.33 158	90.93 169	95.50 234	94.83 170	80.54 196	98.92 131	79.11 169	90.64 177	93.70 120	96.79 154	96.93 136	97.85 84	99.78 81	99.99 68
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchmatchNet		93.48 154	98.84 60	87.22 193	91.93 132	99.39 110	92.55 196	66.06 255	99.71 74	75.61 184	98.24 84	99.59 63	97.35 146	97.87 103	97.64 98	99.83 47	99.43 225
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MS-PatchMatch		93.46 155	95.91 142	90.61 153	95.48 76	99.31 129	95.62 149	77.23 222	99.42 96	81.88 165	88.92 190	96.06 109	93.80 191	96.45 158	93.11 210	99.65 160	98.10 247

0.3-1-1-0.015		93.45 156	93.88 186	92.95 127	85.17 216	95.96 218	96.24 124	87.68 106	97.58 184	91.83 54	98.67 72	80.39 198	98.94 67	88.61 248	96.06 161	97.85 250	99.90 160

0.4-1-1-0.2		93.35 157	93.81 187	92.80 133	85.14 218	95.96 218	96.25 122	87.39 129	97.58 184	91.79 58	98.23 85	80.39 198	98.39 100	88.57 249	96.06 161	97.85 250	99.91 158

dmvs_re		93.34 158	94.59 176	91.88 144	87.97 194	99.14 145	95.29 159	88.61 84	98.09 172	82.71 159	97.34 99	78.96 205	96.98 149	94.62 197	93.98 198	99.73 123	99.98 88

0.4-1-1-0.1		93.31 159	93.77 188	92.77 135	85.13 219	95.94 221	96.21 125	87.29 130	97.58 184	91.79 58	98.11 90	80.39 198	98.36 101	88.54 250	95.98 166	97.82 253	99.89 165

tpm cat1		93.29 160	96.53 121	89.50 166	91.84 138	99.18 143	94.70 173	67.70 249	98.38 162	86.67 125	89.16 186	99.38 72	96.66 158	94.33 201	95.30 177	99.43 207	100.00 1

casdiffseed414692147		93.14 161	93.44 191	92.79 134	91.46 166	99.20 141	95.06 163	87.27 131	96.60 204	85.16 148	87.25 204	77.77 208	98.09 120	96.80 143	96.57 146	99.67 153	99.90 160

Effi-MVS+-dtu		93.13 162	97.13 103	88.47 180	88.86 189	99.19 142	96.79 108	79.08 209	99.64 80	70.01 214	97.51 97	89.38 138	96.53 160	97.60 112	96.55 147	99.57 174	100.00 1

HyFIR lowres test		93.13 162	94.48 178	91.56 145	96.12 74	99.68 85	93.52 187	79.98 200	97.24 190	81.73 166	72.66 259	95.74 111	98.29 109	98.27 76	97.79 87	99.70 142	100.00 1

Vis-MVSNet		93.08 164	96.76 116	88.78 175	91.14 168	99.63 90	94.85 169	83.34 166	97.19 192	74.78 190	91.92 165	93.15 124	88.81 242	97.59 114	98.35 66	99.78 81	99.49 224
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Effi-MVS+		93.06 165	95.94 140	89.70 163	90.82 170	99.45 103	95.71 145	78.94 210	98.72 144	74.71 191	97.92 93	80.73 197	98.35 102	97.72 107	97.05 139	99.70 142	100.00 1

ADS-MVSNet		92.91 166	97.97 85	87.01 195	92.07 125	99.27 136	92.70 193	65.39 260	99.85 56	75.40 185	94.93 126	98.26 89	96.86 152	96.09 170	97.52 104	99.65 160	99.84 184

GeoE		92.88 167	95.20 159	90.18 159	90.59 174	99.18 143	96.31 120	78.36 215	97.52 188	78.53 174	87.11 205	88.01 145	97.63 144	97.79 106	96.76 144	99.66 158	100.00 1

TESTMET0.1,1		92.87 168	97.23 101	87.79 188	86.96 198	99.10 146	94.68 175	77.46 221	99.36 103	71.94 204	93.82 139	96.51 104	95.96 165	97.42 123	94.37 190	99.74 110	99.99 68

FC-MVSNet-test		92.78 169	96.19 135	88.80 174	88.00 193	97.54 186	93.60 186	82.36 183	98.16 168	79.71 168	91.55 167	95.41 112	89.65 233	96.09 170	95.23 178	99.49 190	99.31 228

Fast-Effi-MVS+-dtu		92.73 170	97.62 91	87.02 194	88.91 187	98.83 159	95.79 142	73.98 238	99.89 46	68.62 219	97.73 95	93.30 123	95.21 174	97.67 111	95.96 168	99.59 170	100.00 1

IB-MVS	90.59 15	92.70 171	95.70 146	89.21 169	94.62 87	99.45 103	83.77 250	88.92 80	99.53 84	92.82 45	98.86 63	86.08 160	75.24 265	92.81 231	93.17 208	99.89 30	100.00 1
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
test-mter		92.67 172	97.13 103	87.47 191	86.72 200	99.07 148	94.28 180	76.90 223	99.21 113	71.53 208	93.63 143	96.32 107	95.67 168	97.32 128	94.36 192	99.74 110	99.99 68

RPMNet		92.64 173	97.88 87	86.53 200	90.79 171	98.95 154	95.13 161	64.44 264	99.09 119	72.36 200	93.58 144	99.01 77	96.74 157	98.05 94	96.45 150	99.71 137	100.00 1

FMVSNet1		92.55 174	93.66 190	91.26 146	87.91 196	96.12 212	94.75 172	81.69 191	97.67 182	85.63 144	80.56 234	87.88 147	98.15 115	96.50 152	97.21 127	99.41 212	99.71 210

tpmrst		92.52 175	97.45 97	86.77 198	92.15 121	99.36 118	92.53 197	65.95 256	99.53 84	72.50 198	92.22 158	99.83 52	97.81 137	95.18 190	96.05 164	99.69 147	100.00 1

testgi		92.47 176	95.68 149	88.73 176	90.68 172	98.35 171	91.67 204	79.50 205	98.96 128	77.12 180	95.17 120	85.84 162	93.95 190	95.75 179	96.47 149	99.45 202	99.21 231

TAMVS		92.43 177	94.21 184	90.35 157	88.68 190	98.85 158	94.15 182	81.53 193	95.58 212	83.61 157	87.05 206	86.45 156	94.71 179	96.27 164	95.91 169	99.42 210	99.38 227

CR-MVSNet		92.32 178	97.97 85	85.74 209	90.63 173	98.95 154	95.46 155	65.50 258	99.09 119	67.51 223	94.20 133	98.18 91	95.59 171	98.16 84	97.20 130	99.74 110	100.00 1

CVMVSNet		92.13 179	95.40 155	88.32 183	91.29 167	97.29 191	91.85 201	86.42 134	96.71 202	71.84 206	89.56 184	91.18 129	88.98 241	96.17 167	97.76 89	99.51 187	99.14 233

Fast-Effi-MVS+		92.11 180	94.33 180	89.52 165	89.06 186	99.00 150	95.13 161	76.72 225	98.59 153	78.21 176	89.99 181	77.35 210	98.34 104	97.97 100	97.44 112	99.67 153	99.96 125

ACMH+	92.61 13	91.80 181	93.03 194	90.37 156	93.03 101	98.17 176	94.00 183	84.13 160	98.12 170	77.39 178	91.95 162	74.62 225	94.36 186	94.62 197	93.82 199	99.32 221	99.87 177

IterMVS-SCA-FT		91.75 182	96.87 113	85.78 207	90.34 176	95.93 222	95.06 163	73.85 239	98.91 132	61.01 244	89.21 185	98.87 78	94.66 182	98.09 92	97.12 135	99.76 93	99.99 68

dtuonly		91.72 183	95.05 162	87.83 187	87.94 195	98.44 168	94.83 170	82.15 185	96.62 203	65.07 234	86.58 207	90.12 137	97.30 148	97.08 135	96.74 145	99.67 153	99.81 190

IterMVS		91.65 184	96.62 117	85.85 206	90.27 179	95.80 224	95.32 158	74.15 235	98.91 132	60.95 245	88.79 192	97.76 94	94.69 181	98.04 96	97.07 137	99.73 123	100.00 1
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	92.34 14	91.59 185	93.02 195	89.92 162	93.97 93	97.98 181	90.10 225	84.70 146	98.46 158	76.80 181	93.38 145	71.94 237	94.39 184	95.34 186	94.04 195	99.54 179	100.00 1
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs4		91.41 186	93.05 193	89.49 167	85.85 208	96.52 204	91.70 203	82.49 180	98.14 169	83.17 158	87.57 200	81.76 193	94.39 184	95.47 183	92.62 216	99.33 219	99.29 229

blend_shiyan4		91.06 187	91.01 209	91.13 149	85.43 210	91.84 254	96.41 114	82.84 176	97.61 183	91.83 54	98.80 67	80.39 198	92.83 202	85.75 254	82.95 255	97.42 254	99.73 203

PatchT		91.06 187	97.66 90	83.36 236	90.32 177	98.96 153	82.30 255	64.72 263	98.45 159	67.51 223	93.28 148	97.60 96	95.59 171	98.16 84	97.20 130	99.70 142	100.00 1

usedtu_dtu_shiyan1		91.03 189	93.73 189	87.88 186	80.10 253	96.73 199	93.00 192	84.24 156	97.91 179	77.39 178	84.98 211	87.83 148	93.08 198	95.84 177	93.18 207	99.46 198	99.63 216

MIMVSNet		91.01 190	96.22 131	84.93 218	85.24 214	98.09 178	90.40 220	64.96 262	97.55 187	72.65 196	96.23 110	90.81 132	96.79 154	96.69 146	97.06 138	99.52 183	97.09 255

UniMVSNet_NR-MVSNet		90.50 191	92.31 199	88.38 181	85.04 223	96.34 208	90.94 207	85.32 138	95.87 211	75.69 182	87.68 199	78.49 206	93.78 192	93.21 226	94.60 183	99.53 182	99.97 104

UniMVSNet (Re)		90.41 192	91.96 201	88.59 179	85.71 209	96.73 199	90.82 210	84.11 161	95.23 218	78.54 173	88.91 191	76.41 216	92.84 201	93.40 222	93.05 211	99.55 178	100.00 1

GA-MVS		90.38 193	94.59 176	85.46 213	88.30 192	98.44 168	92.18 198	83.30 167	97.89 180	58.05 256	92.86 152	84.25 177	91.27 224	96.65 147	92.61 217	99.66 158	99.43 225

USDC		90.36 194	91.68 202	88.82 173	92.58 110	98.02 179	96.27 121	79.83 201	98.37 164	70.61 213	89.05 187	67.50 254	94.17 187	95.77 178	94.43 188	99.46 198	98.62 238

thisisatest0515		90.28 195	94.32 181	85.57 212	85.23 215	97.23 192	85.44 246	83.09 169	96.80 201	72.41 199	89.82 182	90.87 131	87.93 247	95.27 189	90.39 240	99.33 219	99.88 171

TinyColmap		89.94 196	90.88 210	88.84 172	92.43 113	97.91 182	95.59 152	80.10 199	98.12 170	71.33 210	84.56 213	67.46 255	94.15 188	95.57 181	94.27 194	99.43 207	98.26 242

pm-mvs1		89.68 197	92.00 200	86.96 196	86.23 204	96.62 202	90.36 221	83.05 170	93.97 231	72.15 203	81.77 229	82.10 189	90.69 230	95.38 185	94.50 186	99.29 225	99.65 213

tpm		89.60 198	94.93 166	83.39 234	89.94 180	97.11 194	90.09 226	65.28 261	98.67 147	60.03 249	96.79 104	84.38 174	95.66 170	91.90 235	95.65 173	99.32 221	99.98 88

NR-MVSNet		89.52 199	90.71 211	88.14 185	86.19 205	96.20 210	92.07 199	84.58 147	95.54 213	75.27 187	87.52 201	67.96 252	91.24 225	94.33 201	93.45 203	99.49 190	99.97 104

DU-MVS		89.49 200	90.60 212	88.19 184	84.71 227	96.20 210	90.94 207	84.58 147	95.54 213	75.69 182	87.52 201	68.74 251	93.78 192	91.10 240	95.13 180	99.47 196	99.97 104

usedtu_blend_shiyan5		89.34 201	89.98 217	88.60 178	70.40 262	91.71 257	96.25 122	82.93 172	90.83 254	91.83 54	98.80 67	80.39 198	92.83 202	85.63 255	82.75 256	97.39 255	99.73 203

Baseline_NR-MVSNet		89.13 202	89.53 226	88.66 177	84.71 227	94.43 243	91.79 202	84.49 151	95.54 213	78.28 175	78.52 246	72.46 236	93.29 196	91.10 240	94.82 182	99.42 210	99.86 180

tfpnnormal		89.09 203	89.71 220	88.38 181	87.37 197	96.78 198	91.46 205	85.20 141	90.33 260	72.35 201	83.45 222	69.30 249	94.45 183	95.29 187	92.86 213	99.44 206	99.93 147

FE-MVSNET3		88.92 204	89.98 217	87.69 189	70.40 262	91.71 257	90.75 212	82.93 172	90.83 254	91.83 54	98.80 67	80.39 198	92.83 202	85.63 255	82.75 256	97.39 255	99.72 207

TranMVSNet+NR-MVSNet		88.88 205	89.90 219	87.69 189	84.06 239	95.68 225	91.88 200	85.23 140	95.16 219	72.54 197	83.06 225	70.14 246	92.93 200	90.81 243	94.53 185	99.48 194	99.89 165

WR-MVS_H		88.47 206	90.55 213	86.04 202	85.13 219	96.07 214	89.86 232	79.80 202	94.37 228	72.32 202	83.12 224	74.44 229	89.60 234	93.52 219	92.40 218	99.51 187	99.96 125

SixPastTwentyTwo		88.35 207	91.51 204	84.66 220	85.39 212	96.96 196	86.57 242	79.62 204	96.57 205	63.73 238	87.86 196	75.18 220	93.43 195	94.03 205	90.37 241	99.24 228	99.58 217

TransMVSNet (Re)		88.33 208	89.55 225	86.91 197	86.65 201	95.56 231	90.48 218	84.44 152	92.02 251	71.07 212	80.13 236	72.48 235	89.41 235	95.05 193	94.44 187	99.39 214	97.14 254

MVS-HIRNet		88.27 209	94.05 185	81.51 242	88.90 188	98.93 157	83.38 252	60.52 271	98.06 173	63.78 237	80.67 233	90.36 135	92.94 199	97.29 129	96.41 151	99.56 176	96.66 257

WR-MVS		88.23 210	90.15 215	86.00 204	84.39 234	95.64 227	89.96 229	81.80 188	94.46 226	71.60 207	82.10 227	74.36 230	88.76 243	92.48 232	92.20 220	99.46 198	99.83 188

CP-MVSNet		88.09 211	89.57 223	86.36 201	84.63 230	95.46 236	89.48 234	80.53 197	93.42 238	71.26 211	81.25 231	69.90 247	92.78 205	93.30 225	93.69 201	99.47 196	99.96 125

pmnet_mix02		88.07 212	92.32 198	83.10 237	86.14 206	96.23 209	81.90 258	83.05 170	98.04 174	57.59 259	84.93 212	82.02 190	90.87 229	93.54 218	91.53 232	99.06 239	99.97 104

UniMVSNet_ETH3D		88.05 213	87.01 247	89.27 168	88.53 191	97.49 187	90.35 222	83.48 164	94.57 224	77.87 177	70.08 263	61.75 266	96.22 162	90.17 244	95.21 179	99.16 233	99.82 189

anonymousdsp		87.98 214	92.38 197	82.85 238	83.68 243	96.79 197	90.78 211	74.06 237	95.29 217	57.91 258	83.33 223	83.12 181	91.15 227	95.96 175	92.37 219	99.52 183	99.76 199

LTVRE_ROB	88.65 16	87.87 215	91.11 208	84.10 231	86.64 202	97.47 188	94.40 178	78.41 214	96.13 209	52.02 267	87.95 195	65.92 260	93.59 194	95.29 187	95.09 181	99.52 183	99.95 138
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
V42		87.84 216	89.42 228	85.99 205	85.16 217	96.01 216	90.52 217	81.78 190	94.43 227	67.59 221	81.32 230	71.87 238	91.48 222	91.25 239	91.16 236	99.43 207	99.92 151

TDRefinement		87.79 217	88.76 235	86.66 199	93.54 95	98.02 179	95.76 143	85.18 142	96.57 205	67.90 220	80.51 235	66.51 259	78.37 261	93.20 227	89.73 242	99.22 229	96.75 256

MDTV_nov1_ep13_2view		87.75 218	93.32 192	81.26 244	83.74 242	96.64 201	85.66 245	66.20 254	98.36 165	61.61 242	84.34 215	87.95 146	91.12 228	94.01 206	92.66 215	99.22 229	99.27 230

v8		87.54 219	89.33 229	85.45 214	85.41 211	95.50 234	90.32 223	78.94 210	94.35 229	66.93 226	81.90 228	70.99 243	91.62 220	91.49 238	91.22 235	99.48 194	99.87 177

v1144		87.49 220	89.64 221	84.97 217	84.73 226	95.84 223	90.17 224	79.30 206	93.96 232	64.65 235	78.83 243	73.38 234	91.51 221	93.77 213	91.77 227	99.45 202	99.93 147

v2v482		87.46 221	88.90 233	85.78 207	84.58 231	95.95 220	89.90 231	82.43 182	94.19 230	65.65 230	79.80 238	69.12 250	92.67 206	91.88 236	91.46 233	99.45 202	99.93 147

v10		87.40 222	89.62 222	84.80 219	84.93 224	95.07 240	90.44 219	75.63 230	94.51 225	66.52 228	78.87 242	73.47 233	91.86 218	93.69 216	91.87 225	99.45 202	99.86 180

pmmvs5		87.33 223	90.01 216	84.20 229	84.31 236	96.04 215	87.63 240	76.59 226	93.17 243	65.35 233	84.30 216	71.68 239	91.91 217	95.41 184	91.37 234	99.39 214	98.13 245

N_pmnet		87.31 224	91.51 204	82.41 241	85.13 219	95.57 230	80.59 262	81.79 189	96.20 207	58.52 255	78.62 244	85.66 164	89.36 236	94.64 196	92.14 221	99.08 237	97.72 252

PS-CasMVS		87.24 225	88.52 238	85.73 210	84.58 231	95.35 238	89.03 237	80.17 198	93.11 244	68.86 218	77.71 248	66.89 256	92.30 212	93.13 228	93.50 202	99.46 198	99.96 125

EU-MVSNet		87.20 226	90.47 214	83.38 235	85.11 222	93.85 248	86.10 244	79.76 203	93.30 242	65.39 232	84.41 214	78.43 207	85.04 256	92.20 234	93.03 212	98.86 241	98.05 249

PEN-MVS		87.20 226	88.22 239	86.01 203	84.01 241	94.93 241	90.00 228	81.52 195	93.46 237	69.29 216	79.69 239	65.51 261	91.72 219	91.01 242	93.12 209	99.49 190	99.84 184

EG-PatchMatch MVS		86.96 228	89.56 224	83.93 232	86.29 203	97.61 185	90.75 212	73.31 242	95.43 216	66.08 229	75.88 256	71.31 240	87.55 249	94.79 195	92.74 214	99.61 169	99.13 234

v1192		86.93 229	89.01 231	84.50 225	84.46 233	95.51 233	89.93 230	78.65 213	93.75 233	62.29 240	77.19 251	70.88 244	92.28 213	93.84 210	91.96 223	99.38 216	99.90 160

v1921920		86.81 230	88.93 232	84.33 228	84.23 237	95.41 237	90.09 226	78.10 216	93.74 234	62.17 241	76.98 253	71.14 241	92.05 215	93.69 216	91.69 230	99.32 221	99.88 171

v144192		86.80 231	88.90 233	84.35 226	84.33 235	95.56 231	89.34 235	77.74 218	93.60 235	64.03 236	77.82 247	70.76 245	91.28 223	92.91 230	91.74 229	99.37 217	99.90 160

DTE-MVSNet		86.70 232	87.66 243	85.58 211	83.30 245	94.29 244	89.74 233	81.53 193	92.77 247	68.93 217	80.13 236	64.00 264	90.62 231	89.45 245	93.34 204	99.32 221	99.67 211

gg-mvs-nofinetune		86.69 233	91.30 207	81.30 243	90.42 175	99.64 88	98.50 64	61.68 269	79.23 271	40.35 274	66.58 265	97.14 99	96.92 150	98.64 49	97.94 79	99.91 26	99.97 104

v148		86.63 234	87.79 241	85.28 215	84.65 229	95.97 217	86.46 243	82.84 176	92.91 246	71.52 209	78.99 241	66.74 258	86.83 252	89.28 246	90.69 238	99.41 212	99.94 145

dtuonlycased		86.51 235	91.31 206	80.92 245	83.57 244	94.69 242	81.41 260	75.18 232	97.02 199	59.42 251	87.86 196	85.42 167	86.86 251	88.71 247	87.20 249	99.08 237	98.25 244

gbinet_0.2-2-1-0.02		86.42 236	87.47 244	85.19 216	71.78 259	91.76 255	90.97 206	82.60 179	90.87 252	75.35 186	85.62 209	76.07 219	93.09 197	85.42 261	82.55 262	97.37 260	99.98 88

v1240		86.24 237	88.56 237	83.54 233	84.05 240	95.21 239	89.27 236	76.76 224	93.42 238	60.68 248	75.99 255	69.80 248	91.21 226	93.83 212	91.76 228	99.29 225	99.91 158

wanda-best-256-512		85.94 238	87.03 245	84.66 220	70.40 262	91.71 257	90.75 212	82.93 172	90.83 254	73.88 193	83.78 218	74.80 222	92.62 207	85.63 255	82.75 256	97.39 255	99.73 203

FE-blended-shiyan7		85.94 238	87.03 245	84.66 220	70.40 262	91.71 257	90.75 212	82.93 172	90.83 254	73.88 193	83.78 218	74.80 222	92.62 207	85.63 255	82.75 256	97.39 255	99.73 203

blended_shiyan8		85.87 240	86.93 250	84.64 223	70.41 261	91.71 257	90.90 209	82.61 178	90.54 259	74.01 192	83.77 220	74.58 226	92.53 210	85.57 260	82.67 261	97.37 260	99.66 212

blended_shiyan6		85.86 241	86.98 248	84.56 224	70.38 266	91.69 262	90.72 216	82.45 181	90.79 258	73.86 195	83.58 221	74.80 222	92.57 209	85.60 259	82.69 260	97.38 259	99.72 207

pmmvs6		85.75 242	86.97 249	84.34 227	84.88 225	95.59 229	87.41 241	79.19 208	87.81 266	67.56 222	63.05 269	77.76 209	89.15 237	93.45 221	91.90 224	97.83 252	99.21 231

v7n		85.39 243	87.70 242	82.70 239	82.77 247	95.64 227	88.27 239	74.83 233	92.30 249	62.58 239	76.37 254	64.80 263	88.38 245	94.29 203	90.61 239	99.34 218	99.87 177

gm-plane-assit		84.93 244	91.61 203	77.14 254	84.14 238	91.29 263	66.18 274	69.70 245	85.22 270	47.95 271	78.58 245	89.24 140	94.90 177	98.82 43	98.12 75	99.99 7	100.00 1

CMPMVS	65.66 17	84.62 245	85.02 252	84.15 230	95.40 77	97.79 183	88.35 238	79.22 207	89.66 263	60.71 247	72.20 260	73.94 231	87.32 250	86.73 252	84.55 254	93.90 266	90.31 267
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_method		84.44 246	89.04 230	79.08 248	81.15 250	92.82 252	82.06 257	61.92 267	96.17 208	59.38 252	74.47 258	67.52 253	91.96 216	96.92 138	95.53 175	97.98 249	99.85 183

Anonymous20231206		84.28 247	89.53 226	78.17 251	82.31 249	94.16 246	82.57 254	76.51 227	93.38 241	52.98 264	79.47 240	73.74 232	75.45 264	95.07 192	94.41 189	99.18 232	96.46 259

new_pmnet		84.12 248	87.89 240	79.72 247	80.43 252	94.14 247	80.26 263	74.14 236	96.01 210	56.30 263	74.94 257	76.45 215	88.59 244	93.11 229	89.31 244	98.59 245	91.27 266

test20.03		83.86 249	88.73 236	78.16 252	82.60 248	93.00 249	81.61 259	74.68 234	92.36 248	57.50 260	83.01 226	74.48 228	73.30 266	92.40 233	91.14 237	99.29 225	94.75 262

pmmvs-eth3d		82.92 250	83.31 255	82.47 240	76.97 256	91.76 255	83.79 249	76.10 228	90.33 260	69.95 215	71.04 262	48.09 274	89.02 240	93.85 209	89.14 245	99.02 240	98.96 236

PM-MVS		82.79 251	84.51 253	80.77 246	77.22 255	92.13 253	83.61 251	73.31 242	93.50 236	61.06 243	77.15 252	46.52 277	90.55 232	94.14 204	89.05 248	98.85 242	99.12 235

pmmvs3		80.91 252	85.62 251	75.42 256	75.01 258	89.09 267	75.31 268	68.70 247	86.99 268	46.74 273	81.18 232	62.91 265	87.95 246	93.84 210	89.06 247	98.80 244	96.23 260

MIMVSNet1		80.64 253	83.97 254	76.76 255	68.91 268	91.15 265	78.32 267	75.47 231	89.58 264	56.64 262	65.10 266	65.17 262	82.14 257	93.51 220	91.64 231	99.10 235	91.66 265

MDA-MVSNet-bldmvs		80.30 254	82.83 256	77.34 253	69.16 267	94.29 244	72.16 269	81.97 187	90.14 262	57.32 261	94.01 138	47.97 275	86.81 253	68.74 269	86.82 251	96.63 262	97.86 250

FE-MVSNET2		79.98 255	80.91 258	78.89 249	67.11 270	92.85 250	83.34 253	77.59 219	88.33 265	59.81 250	55.71 272	48.82 273	86.33 254	93.94 207	89.34 243	99.14 234	97.39 253

new-patchmatchnet		78.17 256	80.82 260	75.07 257	76.93 257	91.20 264	71.90 270	73.32 241	86.59 269	48.91 268	67.11 264	47.85 276	81.19 258	88.18 251	87.02 250	98.19 248	97.79 251

FE-MVSNET		77.93 257	80.91 258	74.45 258	61.41 272	89.15 266	78.53 266	75.91 229	87.12 267	52.74 265	63.25 268	50.07 272	79.29 260	91.87 237	89.12 246	98.81 243	95.76 261

usedtu_dtu_shiyan2		74.26 258	75.54 261	72.77 260	60.18 275	86.34 268	79.24 265	68.68 248	77.80 272	57.94 257	47.93 275	58.22 269	76.77 262	80.13 264	80.11 265	93.82 267	98.26 242

FPMVS		73.80 259	74.62 262	72.84 259	83.09 246	84.44 270	83.89 248	73.64 240	92.20 250	48.50 269	72.19 261	59.51 268	63.16 268	69.13 268	66.26 272	84.74 272	78.59 275

WB-MVS		71.64 260	82.10 257	59.45 264	79.66 254	78.44 273	55.66 278	78.80 212	93.01 245	19.20 282	86.36 208	71.05 242	39.18 277	85.26 262	81.08 263	84.19 273	79.49 274

Gipuma		71.02 261	72.60 265	69.19 261	71.31 260	75.11 274	66.36 273	61.65 270	94.93 220	47.29 272	38.74 277	38.52 279	75.52 263	86.09 253	85.92 253	93.01 268	88.87 269
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
GG-mvs-BLEND		69.85 262	99.39 44	35.39 270	3.67 283	99.94 23	99.10 48	1.69 278	99.85 56	3.19 285	98.13 89	99.46 68	4.92 280	99.23 35	99.14 34	99.80 66	100.00 1

PMMVS2		65.18 263	68.25 266	61.59 262	61.37 273	79.72 272	59.18 277	61.80 268	64.72 275	37.33 275	53.82 273	35.59 280	54.46 273	73.94 267	80.52 264	95.40 265	89.43 268

PMVS	60.14 18	62.67 264	64.05 267	61.06 263	68.32 269	53.27 280	52.23 279	67.63 251	75.07 274	48.30 270	58.27 270	57.43 270	49.99 274	67.20 270	62.42 273	79.87 276	74.68 278
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		61.76 265	72.90 264	48.76 267	21.21 278	68.61 275	66.11 275	37.38 273	94.83 222	33.06 276	64.31 267	29.72 281	86.08 255	74.44 266	78.71 266	48.74 280	99.65 213

E-PMN		55.33 266	55.79 272	54.81 266	59.81 276	57.23 278	38.83 280	63.59 265	64.06 277	24.66 279	35.33 279	26.40 284	58.69 270	55.41 272	70.54 269	83.26 274	81.56 272

EMVS		55.14 267	55.29 273	54.97 265	60.87 274	57.52 277	38.58 281	63.57 266	64.54 276	23.36 280	36.96 278	27.99 283	60.69 269	51.17 273	66.61 271	82.73 275	82.25 271

MVE	58.81 19	52.07 268	55.15 274	48.48 268	42.45 277	62.35 276	36.41 283	54.70 272	49.88 279	27.65 278	29.98 280	18.08 285	54.87 272	65.93 271	77.26 267	74.79 277	82.59 270
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test123		48.14 269	58.11 271	36.51 269	8.71 282	56.81 279	59.55 276	24.08 274	77.50 273	14.41 283	49.20 274	11.94 287	80.98 259	41.62 277	69.81 270	31.32 282	99.90 160

VLMVS		47.88 270	62.86 269	30.41 271	13.00 279	26.27 282	37.28 282	2.54 276	97.44 189	30.01 277	97.00 100	52.97 271	40.80 276	44.70 276	45.14 275	58.85 278	76.49 276

MVS_clip		46.11 271	63.35 268	26.00 272	12.01 280	33.73 281	26.34 285	2.75 275	94.91 221	23.05 281	88.94 189	60.62 267	46.82 275	46.33 275	44.06 276	45.05 281	74.88 277

VLMVS_CLIP		44.39 272	62.37 270	23.41 273	9.53 281	24.68 283	30.42 284	1.84 277	90.84 253	10.54 284	96.05 112	45.46 278	36.81 278	49.96 274	49.68 274	51.36 279	79.92 273

MVS_baseline		21.04 273	35.16 275	4.58 274	2.24 284	9.17 284	4.92 286	0.06 279	50.56 278	0.00 286	56.43 271	29.28 282	15.61 279	25.42 278	24.35 277	4.64 283	50.89 279

uanet_test		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 280	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet-low-res		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 280	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 280	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

ACM-MVS					99.68 3	99.94 23	99.81 9		99.99 3	89.28 93	99.60 27	100.00 1	99.91 5			99.94 22	99.88 171

PatchmatchNet2					85.38 213	95.67 226	80.93 261
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												86.46 155	89.06 239	94.58 199	91.87 225	99.09 236	98.09 248
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										58.61 254	77.46 250
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							99.91 2	97.15 2		99.89 1						100.00 1

TPM-MVS					99.67 5	99.96 7	99.82 8			94.63 36	99.65 17	100.00 1	99.90 8			99.99 7	99.80 194
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										52.74 265

9.14												100.00 1

SR-MVS					99.61 17			96.80 22				100.00 1

Anonymous202405211			95.78 144		93.26 96	99.52 94	96.70 111	88.55 85	97.93 178		88.99 188	90.68 133	98.99 66	96.46 156	97.02 140	99.64 164	99.89 165

our_test_3					85.89 207	96.09 213	82.15 256

ambc			74.33 263		66.84 271	84.26 271	84.17 247		93.39 240	58.99 253	45.93 276	18.06 286	70.61 267	93.94 207	86.62 252	92.61 270	98.13 245

MTAPA										96.61 20		100.00 1

MTMP										97.42 15		100.00 1

Patchmatch-RL test							68.01 272

tmp_tt				78.81 250	98.80 49	85.73 269	70.08 271	77.87 217	98.68 146	83.71 156	99.53 34	74.55 227	54.97 271	78.28 265	72.43 268	87.45 271

XVS					95.09 80	99.94 23	97.49 80			88.58 100		99.98 39				99.78 81

X-MVStestdata					95.09 80	99.94 23	97.49 80			88.58 100		99.98 39				99.78 81

mPP-MVS					99.23 42							99.87 50

NP-MVS									99.79 66

Patchmtry						99.00 150	95.46 155	65.50 258		67.51 223

DeepMVS_CX						97.31 190	79.48 264	89.65 71	98.66 149	60.89 246	94.40 131	66.89 256	87.65 248	81.69 263		92.76 269	94.24 264

High-resolution multi-view benchmark