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		99.25 1	99.41 1	99.05 1	99.61 1	99.72 1	99.11 19	97.84 2	99.08 1	99.16 1	99.22 1	99.94 1	99.08 1	99.08 1	99.10 1	99.52 22	99.74 2

MED-MVS		99.04 2	99.09 3	98.97 2	99.54 5	99.50 10	99.29 12	97.86 1	98.88 2	98.85 2	99.17 2	99.73 9	98.82 13	98.80 14	98.22 22	99.50 30	99.33 27

aaEdge-Enhanced		98.97 3	99.00 5	98.94 3	99.53 6	99.47 13	99.35 6	97.66 11	98.36 8	98.80 3	99.17 2	99.76 7	98.86 9	98.57 18	98.32 20	99.42 54	99.33 27

DVP-MVS++		98.92 4	99.18 2	98.61 7	99.47 8	99.61 3	99.39 3	97.82 3	98.80 3	96.86 12	98.90 5	99.92 2	98.67 20	99.02 3	98.20 24	99.43 51	99.82 1

SED-MVS		98.90 5	99.07 4	98.69 6	99.38 21	99.61 3	99.33 10	97.80 6	98.25 12	97.60 6	98.87 7	99.89 4	98.67 20	99.02 3	98.26 21	99.36 68	99.61 7

APDe-MVS		98.87 6	98.96 7	98.77 4	99.58 3	99.53 8	99.44 1	97.81 4	98.22 14	97.33 8	98.70 9	99.33 13	98.86 9	98.96 7	98.40 16	99.63 5	99.57 10
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		98.86 7	98.97 6	98.75 5	99.43 15	99.63 2	99.25 15	97.81 4	98.62 4	97.69 5	97.59 24	99.90 3	98.93 6	98.99 5	98.42 14	99.37 66	99.62 5
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
DPE-MVS		98.75 8	98.91 9	98.57 8	99.21 26	99.54 7	99.42 2	97.78 8	97.49 36	96.84 13	98.94 4	99.82 6	98.59 24	98.90 11	98.22 22	99.56 17	99.48 18
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		98.73 9	98.93 8	98.50 9	99.44 14	99.57 5	99.36 4	97.65 13	98.14 16	96.51 18	98.49 11	99.65 11	98.67 20	98.60 16	98.42 14	99.40 60	99.63 3
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
SMA-MVS		98.66 10	98.89 10	98.39 12	99.60 2	99.41 16	99.00 25	97.63 16	97.78 22	95.83 22	98.33 15	99.83 5	98.85 11	98.93 9	98.56 8	99.41 57	99.40 22
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
SD-MVS		98.52 11	98.77 12	98.23 18	98.15 54	99.26 30	98.79 31	97.59 19	98.52 5	96.25 19	97.99 19	99.75 8	99.01 4	98.27 37	97.97 36	99.59 7	99.63 3
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
TSAR-MVS + MP.		98.49 12	98.78 11	98.15 22	98.14 55	99.17 36	99.34 8	97.18 33	98.44 7	95.72 23	97.84 20	99.28 15	98.87 8	99.05 2	98.05 31	99.66 2	99.60 8
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HFP-MVS		98.48 13	98.62 15	98.32 14	99.39 20	99.33 25	99.27 13	97.42 22	98.27 11	95.25 27	98.34 14	98.83 29	99.08 1	98.26 38	98.08 30	99.48 32	99.26 38

CNVR-MVS		98.47 14	98.46 20	98.48 10	99.40 17	99.05 40	99.02 23	97.54 20	97.73 23	96.65 15	97.20 33	99.13 23	98.85 11	98.91 10	98.10 28	99.41 57	99.08 61

ACMMPR		98.40 15	98.49 17	98.28 16	99.41 16	99.40 17	99.36 4	97.35 25	98.30 10	95.02 29	97.79 21	98.39 41	99.04 3	98.26 38	98.10 28	99.50 30	99.22 44

SF-MVS		98.39 16	98.45 21	98.33 13	99.45 12	99.05 40	98.27 42	97.65 13	97.73 23	97.02 11	98.18 16	99.25 18	98.11 36	98.15 43	97.62 52	99.45 41	99.19 48

SteuartSystems-ACMMP		98.38 17	98.71 14	97.99 26	99.34 23	99.46 14	99.34 8	97.33 28	97.31 41	94.25 34	98.06 17	99.17 22	98.13 35	98.98 6	98.46 12	99.55 18	99.54 12
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		98.36 18	98.32 27	98.41 11	99.47 8	99.26 30	99.12 18	97.77 9	96.73 58	96.12 20	97.27 32	98.88 27	98.46 28	98.47 23	98.39 17	99.52 22	99.22 44
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		98.34 19	98.47 19	98.18 19	99.46 11	99.15 37	99.10 20	97.69 10	97.67 29	94.93 30	97.62 23	99.70 10	98.60 23	98.45 25	97.46 57	99.31 76	99.26 38

CP-MVS		98.32 20	98.34 26	98.29 15	99.34 23	99.30 26	99.15 17	97.35 25	97.49 36	95.58 25	97.72 22	98.62 37	98.82 13	98.29 33	97.67 51	99.51 28	99.28 33

ACMMP_NAP		98.20 21	98.49 17	97.85 28	99.50 7	99.40 17	99.26 14	97.64 15	97.47 38	92.62 51	97.59 24	99.09 25	98.71 18	98.82 13	97.86 44	99.40 60	99.19 48

MCST-MVS		98.20 21	98.36 23	98.01 25	99.40 17	99.05 40	99.00 25	97.62 17	97.59 33	93.70 38	97.42 31	99.30 14	98.77 16	98.39 31	97.48 56	99.59 7	99.31 32

DeepC-MVS_fast	96.13 1	98.13 23	98.27 29	97.97 27	99.16 29	99.03 46	99.05 22	97.24 30	98.22 14	94.17 36	95.82 45	98.07 43	98.69 19	98.83 12	98.80 3	99.52 22	99.10 58
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		98.10 24	98.05 34	98.17 21	99.38 21	99.05 40	99.00 25	97.53 21	98.04 18	95.12 28	94.80 58	99.18 21	98.58 25	98.49 22	97.78 48	99.39 63	98.98 78

MP-MVS		98.09 25	98.30 28	97.84 29	99.34 23	99.19 35	99.23 16	97.40 23	97.09 49	93.03 44	97.58 26	98.85 28	98.57 26	98.44 27	97.69 50	99.48 32	99.23 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MSLP-MVS++		98.04 26	97.93 36	98.18 19	99.10 30	99.09 39	98.34 41	96.99 36	97.54 34	96.60 16	94.82 57	98.45 39	98.89 7	97.46 67	98.77 5	99.17 115	99.37 23

MGCNet		97.94 27	98.72 13	97.02 39	98.48 47	99.50 10	99.02 23	94.06 51	98.33 9	94.51 31	98.78 8	97.73 47	96.60 78	98.51 20	98.68 6	99.45 41	99.53 13

X-MVS		97.84 28	98.19 31	97.42 33	99.40 17	99.35 21	99.06 21	97.25 29	97.38 40	90.85 74	96.06 42	98.72 33	98.53 27	98.41 29	98.15 27	99.46 37	99.28 33

PGM-MVS		97.81 29	98.11 32	97.46 32	99.55 4	99.34 24	99.32 11	94.51 49	96.21 74	93.07 41	98.05 18	97.95 46	98.82 13	98.22 41	97.89 43	99.48 32	99.09 60

CPTT-MVS		97.78 30	97.54 40	98.05 24	98.91 38	99.05 40	99.00 25	96.96 37	97.14 47	95.92 21	95.50 50	98.78 31	98.99 5	97.20 74	96.07 115	98.54 192	99.04 70

PHI-MVS		97.78 30	98.44 22	97.02 39	98.73 42	99.25 32	98.11 45	95.54 43	96.66 61	92.79 48	98.52 10	99.38 12	97.50 49	97.84 53	98.39 17	99.45 41	99.03 71

TSAR-MVS + ACMM		97.71 32	98.60 16	96.66 43	98.64 45	99.05 40	98.85 30	97.23 31	98.45 6	89.40 112	97.51 28	99.27 17	96.88 65	98.53 19	97.81 47	98.96 150	99.59 9

train_agg		97.65 33	98.06 33	97.18 36	98.94 35	98.91 60	98.98 29	97.07 35	96.71 59	90.66 81	97.43 30	99.08 26	98.20 31	97.96 50	97.14 69	99.22 97	99.19 48

AdaColmap		97.53 34	96.93 52	98.24 17	99.21 26	98.77 69	98.47 38	97.34 27	96.68 60	96.52 17	95.11 55	96.12 62	98.72 17	97.19 76	96.24 109	99.17 115	98.39 146

TSAR-MVS + GP.		97.45 35	98.36 23	96.39 45	95.56 91	98.93 57	97.74 55	93.31 58	97.61 32	94.24 35	98.44 13	99.19 20	98.03 39	97.60 61	97.41 59	99.44 48	99.33 27

CSCG		97.44 36	97.18 48	97.75 30	99.47 8	99.52 9	98.55 36	95.41 44	97.69 28	95.72 23	94.29 61	95.53 67	98.10 37	96.20 124	97.38 61	99.24 88	99.62 5

ACMMP		97.37 37	97.48 42	97.25 34	98.88 41	99.28 28	98.47 38	96.86 38	97.04 51	92.15 55	97.57 27	96.05 64	97.67 44	97.27 72	95.99 120	99.46 37	99.14 57
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
PLC	94.95 3	97.37 37	96.77 55	98.07 23	98.97 34	98.21 118	97.94 51	96.85 39	97.66 30	97.58 7	93.33 67	96.84 53	98.01 40	97.13 78	96.20 111	99.09 129	98.01 162
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator+	93.91 7	97.23 39	97.22 45	97.24 35	98.89 40	98.85 65	98.26 43	93.25 61	97.99 19	95.56 26	90.01 106	98.03 45	98.05 38	97.91 51	98.43 13	99.44 48	99.35 25

MVS_111021_LR		97.16 40	98.01 35	96.16 50	98.47 48	98.98 52	96.94 70	93.89 53	97.64 31	91.44 60	98.89 6	96.41 57	97.20 55	98.02 49	97.29 67	99.04 144	98.85 93

3Dnovator	93.79 8	97.08 41	97.20 46	96.95 41	99.09 31	99.03 46	98.20 44	93.33 57	97.99 19	93.82 37	90.61 100	96.80 54	97.82 41	97.90 52	98.78 4	99.47 36	99.26 38

MVS_111021_HR		97.04 42	98.20 30	95.69 58	98.44 50	99.29 27	96.59 88	93.20 62	97.70 27	89.94 101	98.46 12	96.89 52	96.71 70	98.11 46	97.95 38	99.27 83	99.01 74

SPE-MVS-test		97.00 43	97.85 37	96.00 54	97.77 60	99.56 6	96.35 97	91.95 81	97.54 34	92.20 54	96.14 41	96.00 65	98.19 32	98.46 24	97.78 48	99.57 14	99.45 20

DeepPCF-MVS	95.28 2	97.00 43	98.35 25	95.42 64	97.30 68	98.94 55	94.82 153	96.03 42	98.24 13	92.11 56	95.80 46	98.64 36	95.51 119	98.95 8	98.66 7	96.78 228	99.20 47

OMC-MVS		97.00 43	96.92 53	97.09 37	98.69 43	98.66 78	97.85 52	95.02 46	98.09 17	94.47 32	93.15 68	96.90 51	97.38 51	97.16 77	96.82 92	99.13 122	97.65 175

CNLPA		96.90 46	96.28 61	97.64 31	98.56 46	98.63 83	96.85 74	96.60 40	97.73 23	97.08 10	89.78 108	96.28 60	97.80 43	96.73 93	96.63 95	98.94 153	98.14 158

CS-MVS		96.87 47	97.41 44	96.24 49	97.42 65	99.48 12	97.30 62	91.83 89	97.17 45	93.02 45	94.80 58	94.45 72	98.16 34	98.61 15	97.85 45	99.69 1	99.50 14

DPM-MVS		96.86 48	96.82 54	96.91 42	98.08 56	98.20 119	98.52 37	97.20 32	97.24 44	91.42 61	91.84 84	98.45 39	97.25 54	97.07 79	97.40 60	98.95 151	97.55 178

CANet		96.84 49	97.20 46	96.42 44	97.92 58	99.24 34	98.60 34	93.51 56	97.11 48	93.07 41	91.16 92	97.24 50	96.21 96	98.24 40	98.05 31	99.22 97	99.35 25

CDPH-MVS		96.84 49	97.49 41	96.09 51	98.92 37	98.85 65	98.61 33	95.09 45	96.00 82	87.29 145	95.45 52	97.42 48	97.16 56	97.83 54	97.94 39	99.44 48	98.92 84

QAPM		96.78 51	97.14 49	96.36 46	99.05 32	99.14 38	98.02 48	93.26 59	97.27 43	90.84 77	91.16 92	97.31 49	97.64 47	97.70 59	98.20 24	99.33 70	99.18 51

DeepC-MVS	94.87 4	96.76 52	96.50 58	97.05 38	98.21 53	99.28 28	98.67 32	97.38 24	97.31 41	90.36 90	89.19 112	93.58 77	98.19 32	98.31 32	98.50 10	99.51 28	99.36 24
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVSMamba_PlusPlus		96.66 53	97.63 38	95.52 61	94.94 110	99.02 48	97.77 54	92.59 71	97.73 23	89.99 98	95.56 49	94.81 69	98.43 29	98.58 17	98.53 9	99.40 60	99.16 53

EC-MVSNet		96.49 54	97.63 38	95.16 68	94.75 119	98.69 75	97.39 61	88.97 153	96.34 70	92.02 57	96.04 43	96.46 56	98.21 30	98.41 29	97.96 37	99.61 6	99.55 11

TAPA-MVS	94.18 5	96.38 55	96.49 59	96.25 47	98.26 52	98.66 78	98.00 49	94.96 47	97.17 45	89.48 109	92.91 72	96.35 58	97.53 48	96.59 102	95.90 123	99.28 80	97.82 166
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ETV-MVS		96.31 56	97.47 43	94.96 76	94.79 115	98.78 68	96.08 111	91.41 117	96.16 75	90.50 84	95.76 47	96.20 61	97.39 50	98.42 28	97.82 46	99.57 14	99.18 51

EPNet		96.27 57	96.97 51	95.46 63	98.47 48	98.28 111	97.41 59	93.67 54	95.86 89	92.86 47	97.51 28	93.79 76	91.76 178	97.03 81	97.03 73	98.61 188	99.28 33
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DELS-MVS		96.06 58	96.04 65	96.07 53	97.77 60	99.25 32	98.10 46	93.26 59	94.42 132	92.79 48	88.52 121	93.48 78	95.06 127	98.51 20	98.83 2	99.45 41	99.28 33
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	93.95 6	95.65 59	95.14 81	96.25 47	97.73 63	98.73 71	97.59 57	97.13 34	92.50 171	89.09 125	89.85 107	96.65 55	96.90 64	94.97 167	94.89 154	99.08 131	98.38 147
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EIA-MVS		95.50 60	96.19 63	94.69 91	94.83 114	98.88 64	95.93 121	91.50 109	94.47 131	89.43 110	93.14 69	92.72 82	97.05 61	97.82 56	97.13 70	99.43 51	99.15 55

MAR-MVS		95.50 60	95.60 69	95.39 65	98.67 44	98.18 122	95.89 126	89.81 140	94.55 128	91.97 58	92.99 70	90.21 96	97.30 53	96.79 90	97.49 55	98.72 177	98.99 76
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
OpenMVS	92.33 11	95.50 60	95.22 79	95.82 57	98.98 33	98.97 53	97.67 56	93.04 66	94.64 126	89.18 119	84.44 178	94.79 70	96.79 67	97.23 73	97.61 53	99.24 88	98.88 89

CHOSEN 280x420		95.46 63	97.01 50	93.66 127	97.28 69	97.98 129	96.40 95	85.39 204	96.10 79	91.07 70	96.53 36	96.34 59	95.61 112	97.65 60	96.95 79	96.21 238	97.49 180

LS3D		95.46 63	95.14 81	95.84 56	97.91 59	98.90 62	98.58 35	97.79 7	97.07 50	83.65 161	88.71 117	88.64 109	97.82 41	97.49 65	97.42 58	99.26 86	97.72 174

PVSNet_BlendedMVS		95.41 65	95.28 77	95.57 59	97.42 65	99.02 48	95.89 126	93.10 64	96.16 75	93.12 39	91.99 80	85.27 142	94.66 133	98.09 47	97.34 62	99.24 88	99.08 61

PVSNet_Blended		95.41 65	95.28 77	95.57 59	97.42 65	99.02 48	95.89 126	93.10 64	96.16 75	93.12 39	91.99 80	85.27 142	94.66 133	98.09 47	97.34 62	99.24 88	99.08 61

IS_MVSNet		95.28 67	96.43 60	93.94 119	95.30 97	99.01 51	95.90 124	91.12 123	94.13 139	87.50 144	91.23 91	94.45 72	94.17 144	98.45 25	98.50 10	99.65 3	99.23 42

EPP-MVSNet		95.27 68	96.18 64	94.20 116	94.88 112	98.64 81	94.97 147	90.70 127	95.34 104	89.67 105	91.66 87	93.84 75	95.42 122	97.32 71	97.00 75	99.58 11	99.47 19

sasdasda		95.25 69	95.45 73	95.00 72	95.27 99	98.72 72	96.89 71	89.82 138	96.51 64	90.84 77	93.72 64	86.01 129	97.66 45	95.78 141	97.94 39	99.54 19	99.50 14

canonicalmvs		95.25 69	95.45 73	95.00 72	95.27 99	98.72 72	96.89 71	89.82 138	96.51 64	90.84 77	93.72 64	86.01 129	97.66 45	95.78 141	97.94 39	99.54 19	99.50 14

MGCFI-Net		95.12 71	95.39 76	94.79 86	95.24 101	98.68 76	96.80 78	89.72 142	96.48 66	90.11 94	93.64 66	85.86 134	97.36 52	95.69 147	97.92 42	99.53 21	99.49 17

Casviewmamba		94.92 72	94.85 88	95.00 72	94.72 123	98.62 85	96.69 85	91.81 91	96.94 53	90.43 85	88.11 125	86.57 120	96.84 66	97.72 58	97.32 64	99.48 32	98.69 109

UGNet		94.92 72	96.63 56	92.93 136	96.03 85	98.63 83	94.53 162	91.52 107	96.23 73	90.03 97	92.87 73	96.10 63	86.28 234	96.68 96	96.60 96	99.16 118	99.32 31
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
MVSTER		94.89 74	95.07 84	94.68 92	94.71 125	96.68 162	97.00 66	90.57 129	95.18 115	93.05 43	95.21 53	86.41 124	93.72 156	97.59 62	95.88 124	99.00 145	98.50 134

E2		94.88 75	94.85 88	94.91 78	94.58 134	98.59 86	96.16 104	91.80 92	95.88 87	91.04 71	90.11 105	86.91 117	96.68 72	96.91 84	96.85 87	99.19 112	98.70 108

baseline		94.83 76	95.82 67	93.68 126	94.75 119	97.80 131	96.51 91	88.53 158	97.02 52	89.34 115	92.93 71	92.18 84	94.69 132	95.78 141	96.08 114	98.27 204	98.97 82

MVS_Test		94.82 77	95.66 68	93.84 124	94.79 115	98.35 109	96.49 92	89.10 152	96.12 78	87.09 147	92.58 75	90.61 93	96.48 85	96.51 109	96.89 84	99.11 126	98.54 130

MSDG		94.82 77	93.73 124	96.09 51	98.34 51	97.43 140	97.06 65	96.05 41	95.84 90	90.56 83	86.30 157	89.10 106	95.55 117	96.13 130	95.61 133	99.00 145	95.73 223

TSAR-MVS + COLMAP		94.79 79	94.51 92	95.11 69	96.50 75	97.54 135	97.99 50	94.54 48	97.81 21	85.88 152	96.73 35	81.28 183	96.99 62	96.29 118	95.21 145	98.76 176	96.73 203

CLD-MVS		94.79 79	94.36 98	95.30 66	95.21 103	97.46 138	97.23 63	92.24 77	96.43 67	91.77 59	92.69 74	84.31 160	96.06 100	95.52 150	95.03 150	99.31 76	99.06 66
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PVSNet_Blended_VisFu		94.77 81	95.54 71	93.87 123	96.48 76	98.97 53	94.33 167	91.84 84	94.93 122	90.37 89	85.04 172	94.99 68	90.87 197	98.12 45	97.30 65	99.30 78	99.45 20

DCV-MVSNet		94.76 82	95.12 83	94.35 109	95.10 107	95.81 191	96.46 93	89.49 146	96.33 71	90.16 92	92.55 76	90.26 95	95.83 106	95.52 150	96.03 118	99.06 138	99.33 27

PatchMatch-RL		94.69 83	94.41 96	95.02 71	97.63 64	98.15 123	94.50 165	91.99 79	95.32 105	91.31 63	95.47 51	83.44 170	96.02 102	96.56 103	95.23 144	98.69 180	96.67 204

hybridcas		94.67 84	94.44 95	94.94 77	94.66 130	98.57 90	96.76 81	91.72 100	96.60 62	90.57 82	86.88 138	85.79 135	96.53 81	97.55 64	97.07 71	99.43 51	98.62 121

viewcassd2359sk11		94.63 85	94.45 94	94.84 83	94.58 134	98.57 90	96.13 107	91.79 93	95.32 105	90.67 80	88.73 116	86.13 127	96.65 73	96.82 85	96.87 86	99.21 103	98.68 111

PMMVS		94.61 86	95.56 70	93.50 129	94.30 155	96.74 160	94.91 149	89.56 145	95.58 100	87.72 142	96.15 40	92.86 80	96.06 100	95.47 152	95.02 151	98.43 201	97.09 191

baseline1		94.59 87	94.47 93	94.72 90	95.16 104	97.97 130	96.07 113	91.94 82	94.86 123	89.98 99	91.60 88	85.87 133	95.64 109	97.07 79	96.90 80	99.52 22	97.06 195

casdiffmvs_mvg		94.55 88	94.26 100	94.88 80	94.96 109	98.51 98	97.11 64	91.82 90	94.28 135	89.20 118	86.60 146	86.85 118	96.56 80	97.47 66	97.25 68	99.64 4	98.83 96
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
thisisatest0530		94.54 89	95.47 72	93.46 130	94.51 141	98.65 80	94.66 157	90.72 125	95.69 96	86.90 148	93.80 62	89.44 100	94.74 130	96.98 83	94.86 155	99.19 112	98.85 93

tttt0517		94.52 90	95.44 75	93.44 131	94.51 141	98.68 76	94.61 160	90.72 125	95.61 99	86.84 149	93.78 63	89.26 103	94.74 130	97.02 82	94.86 155	99.20 110	98.87 91

Vis-MVSNet (Re-imp)		94.46 91	96.24 62	92.40 140	95.23 102	98.64 81	95.56 138	90.99 124	94.42 132	85.02 155	90.88 98	94.65 71	88.01 224	98.17 42	98.37 19	99.57 14	98.53 131

HQP-MVS		94.43 92	94.57 91	94.27 112	96.41 78	97.23 147	96.89 71	93.98 52	95.94 85	83.68 160	95.01 56	84.46 155	95.58 116	95.47 152	94.85 158	99.07 133	99.00 75

ACMP	92.88 9	94.43 92	94.38 97	94.50 98	96.01 86	97.69 133	95.85 131	92.09 78	95.74 92	89.12 122	95.14 54	82.62 178	94.77 129	95.73 144	94.67 159	99.14 121	99.06 66
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	92.75 10	94.41 94	93.84 122	95.09 70	96.41 78	96.80 156	94.88 152	93.54 55	96.41 68	90.16 92	92.31 78	83.11 173	96.32 93	96.22 121	94.65 160	99.22 97	97.35 185
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
viewdifsd2359ckpt09		94.40 95	94.26 100	94.57 94	94.51 141	98.50 104	95.96 120	91.72 100	95.31 109	89.37 113	88.33 122	85.88 132	96.64 74	96.61 98	96.57 98	99.20 110	98.60 124

casdiffmvs		94.38 96	94.15 112	94.64 93	94.70 127	98.51 98	96.03 118	91.66 103	95.70 94	89.36 114	86.48 150	85.03 151	96.60 78	97.40 68	97.30 65	99.52 22	98.67 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3new		94.34 97	93.98 117	94.75 88	94.56 136	98.56 93	96.13 107	91.78 95	94.54 130	90.22 91	87.24 133	85.36 141	96.62 75	96.61 98	96.90 80	99.22 97	98.68 111

E3		94.33 98	93.99 116	94.73 89	94.56 136	98.56 93	96.14 105	91.78 95	94.55 128	90.05 96	87.23 134	85.39 139	96.61 77	96.61 98	96.90 80	99.21 103	98.68 111

test2506		94.32 99	93.00 144	95.87 55	96.16 81	99.39 19	96.96 68	92.80 68	95.22 113	94.47 32	91.55 89	70.45 243	95.25 124	98.29 33	97.98 34	99.59 7	98.10 160

viewmanbaseed2359cas		94.31 100	94.25 102	94.38 107	94.72 123	98.59 86	96.09 110	91.84 84	95.35 103	87.92 140	87.86 127	85.54 137	96.45 89	96.71 94	97.04 72	99.26 86	98.67 114

diffmvs		94.31 100	94.21 104	94.42 103	94.64 131	98.28 111	96.36 96	91.56 105	96.77 57	88.89 127	88.97 113	84.23 162	96.01 103	96.05 131	96.41 102	99.05 142	98.79 100
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
onestephybrid01		94.30 102	94.16 111	94.46 100	94.74 122	98.25 115	95.77 133	91.59 104	96.57 63	90.06 95	88.08 126	85.68 136	95.53 118	95.37 156	96.41 102	99.07 133	98.74 107

viewmamba		94.27 103	94.15 112	94.42 103	94.77 118	98.24 116	95.87 129	91.46 112	97.44 39	88.99 126	88.77 115	85.11 148	96.34 92	94.77 169	96.19 113	99.07 133	98.53 131

hybridnocas07		94.25 104	94.18 106	94.33 110	94.75 119	98.23 117	95.86 130	91.49 110	96.88 55	89.13 120	89.37 111	84.73 153	95.73 107	95.14 162	96.27 107	99.05 142	98.62 121

hybrid		94.23 105	94.23 103	94.24 115	94.70 127	98.20 119	95.66 135	91.43 114	96.94 53	89.13 120	89.47 110	84.64 154	95.59 115	95.56 148	96.20 111	98.95 151	98.57 126

viewdifsd2359ckpt07		94.23 105	94.19 105	94.27 112	94.69 129	98.45 106	96.06 115	91.72 100	95.09 118	88.79 131	86.81 139	86.35 126	95.64 109	97.38 69	96.88 85	98.68 181	98.40 144

viewdifsd2359ckpt13		94.14 107	94.00 114	94.30 111	94.55 138	98.55 95	95.71 134	91.76 97	95.03 120	88.12 139	87.34 130	85.15 146	96.39 90	96.81 89	96.60 96	99.24 88	98.50 134

ECVR-MVS		94.14 107	92.96 145	95.52 61	96.16 81	99.39 19	96.96 68	92.80 68	95.22 113	92.38 53	81.48 194	80.31 184	95.25 124	98.29 33	97.98 34	99.59 7	98.05 161

LGP-MVS_train		94.12 109	94.62 90	93.53 128	96.44 77	97.54 135	97.40 60	91.84 84	94.66 125	81.09 174	95.70 48	83.36 171	95.10 126	96.36 114	95.71 131	99.32 72	99.03 71

diffmvs_AUTHOR		94.09 110	93.86 120	94.36 108	94.60 133	98.31 110	96.29 98	91.51 108	96.39 69	88.49 133	87.35 129	83.32 172	96.16 99	96.17 127	96.64 94	99.10 127	98.82 98

RPSCF		94.05 111	94.00 114	94.12 117	96.20 80	96.41 170	96.61 87	91.54 106	95.83 91	89.73 104	96.94 34	92.80 81	95.35 123	91.63 225	90.44 228	95.27 255	93.94 243

DI_MVS_pp		94.01 112	93.63 126	94.44 102	94.54 140	98.26 114	97.51 58	90.63 128	95.88 87	89.34 115	80.54 202	89.36 101	95.48 120	96.33 115	96.27 107	99.17 115	98.78 101

UA-Net		93.96 113	95.95 66	91.64 149	96.06 84	98.59 86	95.29 141	90.00 134	91.06 191	82.87 163	90.64 99	98.06 44	86.06 235	98.14 44	98.20 24	99.58 11	96.96 196

E5new		93.95 114	93.42 132	94.57 94	94.50 144	98.51 98	96.18 102	91.84 84	93.55 150	89.12 122	85.80 164	84.38 157	96.53 81	96.16 128	96.85 87	99.23 95	98.67 114

E5		93.95 114	93.42 132	94.57 94	94.50 144	98.51 98	96.18 102	91.84 84	93.55 150	89.12 122	85.80 164	84.38 157	96.53 81	96.16 128	96.85 87	99.23 95	98.67 114

FA-MVS(training)		93.94 116	95.16 80	92.53 139	94.87 113	98.57 90	95.42 140	79.49 242	95.37 102	90.98 72	86.54 148	94.26 74	95.44 121	97.80 57	95.19 146	98.97 148	98.38 147

test1111		93.94 116	92.78 146	95.29 67	96.14 83	99.42 15	96.79 79	92.85 67	95.08 119	91.39 62	80.69 200	79.86 188	95.00 128	98.28 36	98.00 33	99.58 11	98.11 159

viewmambaseed2359dif		93.92 118	93.38 136	94.54 97	94.55 138	98.15 123	96.41 94	91.47 111	95.10 117	89.58 107	86.64 143	85.10 149	96.17 97	94.08 186	95.77 130	99.09 129	98.84 95

CANet_DTU		93.92 118	96.57 57	90.83 162	95.63 89	98.39 108	96.99 67	87.38 169	96.26 72	71.97 228	96.31 38	93.02 79	94.53 136	97.38 69	96.83 91	98.49 195	97.79 167

E4		93.88 120	93.38 136	94.48 99	94.50 144	98.51 98	96.08 111	91.74 99	93.42 156	88.84 128	85.51 167	84.38 157	96.49 84	96.22 121	96.90 80	99.22 97	98.69 109

E6new		93.85 121	93.39 134	94.39 105	94.50 144	98.53 96	95.93 121	91.41 117	93.47 152	88.81 129	85.51 167	84.16 163	96.46 87	96.32 116	96.99 76	99.21 103	98.78 101

E6		93.85 121	93.39 134	94.39 105	94.50 144	98.53 96	95.93 121	91.41 117	93.47 152	88.81 129	85.51 167	84.16 163	96.46 87	96.32 116	96.99 76	99.21 103	98.78 101

FC-MVSNet-train		93.85 121	93.91 118	93.78 125	94.94 110	96.79 159	94.29 168	91.13 122	93.84 144	88.26 137	90.40 101	85.23 145	94.65 135	96.54 105	95.31 141	99.38 64	99.28 33

GBi-Net		93.81 124	94.18 106	93.38 132	91.34 191	95.86 187	96.22 99	88.68 155	95.23 110	90.40 86	86.39 152	91.16 87	94.40 139	96.52 106	96.30 104	99.21 103	97.79 167

test1		93.81 124	94.18 106	93.38 132	91.34 191	95.86 187	96.22 99	88.68 155	95.23 110	90.40 86	86.39 152	91.16 87	94.40 139	96.52 106	96.30 104	99.21 103	97.79 167

FMVSNet3		93.79 126	94.17 109	93.35 134	91.21 194	95.99 180	96.62 86	88.68 155	95.23 110	90.40 86	86.39 152	91.16 87	94.11 145	95.96 134	96.67 93	99.07 133	97.79 167

dtuplus		93.75 127	93.15 142	94.46 100	94.41 153	98.12 126	96.06 115	91.45 113	94.25 137	89.32 117	85.82 162	85.24 144	96.38 91	93.99 187	95.83 127	99.12 124	98.78 101

viewmacassd2359aftdt		93.65 128	93.29 139	94.07 118	94.61 132	98.51 98	96.04 117	91.75 98	93.61 147	86.56 150	84.89 173	84.41 156	96.17 97	95.97 133	97.03 73	99.28 80	98.63 119

tfpn200view9		93.64 129	92.57 151	94.89 79	95.33 95	98.94 55	96.82 75	92.31 73	92.63 167	88.29 134	87.21 135	78.01 199	97.12 59	96.82 85	95.85 125	99.45 41	98.56 128

thres200		93.62 130	92.54 152	94.88 80	95.36 94	98.93 57	96.75 82	92.31 73	92.84 163	88.28 136	86.99 137	77.81 206	97.13 57	96.82 85	95.92 121	99.45 41	98.49 136

OPM-MVS		93.61 131	92.43 159	95.00 72	96.94 72	97.34 143	97.78 53	94.23 50	89.64 205	85.53 153	88.70 118	82.81 176	96.28 94	96.28 119	95.00 153	99.24 88	97.22 188
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres400		93.56 132	92.43 159	94.87 82	95.40 93	98.91 60	96.70 84	92.38 72	92.93 162	88.19 138	86.69 142	77.35 208	97.13 57	96.75 92	95.85 125	99.42 54	98.56 128

thres100view900		93.55 133	92.47 158	94.81 85	95.33 95	98.74 70	96.78 80	92.30 76	92.63 167	88.29 134	87.21 135	78.01 199	96.78 68	96.38 111	95.92 121	99.38 64	98.40 144

Anonymous20231211		93.49 134	92.33 163	94.84 83	94.78 117	98.00 128	96.11 109	91.85 83	94.86 123	90.91 73	74.69 228	89.18 104	96.73 69	94.82 168	95.51 136	98.67 182	99.24 41

thres600view7		93.49 134	92.37 162	94.79 86	95.42 92	98.93 57	96.58 89	92.31 73	93.04 160	87.88 141	86.62 145	76.94 211	97.09 60	96.82 85	95.63 132	99.45 41	98.63 119

ET-MVSNet_ETH3D		93.34 136	94.33 99	92.18 143	83.26 256	97.66 134	96.72 83	89.89 137	95.62 98	87.17 146	96.00 44	83.69 169	96.99 62	93.78 188	95.34 140	99.06 138	98.18 157

FMVSNet2		93.30 137	93.36 138	93.22 135	91.34 191	95.86 187	96.22 99	88.24 161	95.15 116	89.92 102	81.64 192	89.36 101	94.40 139	96.77 91	96.98 78	99.21 103	97.79 167

viewdifsd2359ckpt11		93.27 138	92.72 147	93.91 121	94.46 149	97.42 141	94.91 149	91.42 115	95.74 92	89.57 108	87.34 130	82.87 175	95.61 112	92.62 208	94.62 162	97.49 221	98.44 137

viewmsd2359difaftdt		93.27 138	92.72 147	93.91 121	94.46 149	97.42 141	94.91 149	91.42 115	95.69 96	89.59 106	87.34 130	82.90 174	95.60 114	92.62 208	94.62 162	97.49 221	98.44 137

COLMAP_ROB	90.49 14	93.27 138	92.71 149	93.93 120	97.75 62	97.44 139	96.07 113	93.17 63	95.40 101	83.86 159	83.76 182	88.72 108	93.87 151	94.25 182	94.11 178	98.87 161	95.28 230
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
casdiffseed414692147		93.07 141	92.06 167	94.25 114	94.46 149	98.28 111	95.61 136	91.28 121	92.74 165	88.58 132	82.11 190	80.19 186	96.25 95	96.05 131	96.49 99	99.32 72	98.57 126

baseline2		93.01 142	94.17 109	91.64 149	92.83 177	97.49 137	93.40 181	87.53 167	93.67 146	86.07 151	91.83 85	86.58 119	91.36 183	96.38 111	95.06 149	98.67 182	98.20 156

Effi-MVS+		92.93 143	93.86 120	91.86 145	94.07 159	98.09 127	95.59 137	85.98 188	94.27 136	79.54 182	91.12 95	81.81 180	96.71 70	96.67 97	96.06 116	99.27 83	98.98 78

CDS-MVSNet		92.77 144	93.60 127	91.80 147	92.63 179	96.80 156	95.24 142	89.14 151	90.30 202	84.58 156	86.76 140	90.65 92	90.42 209	95.89 136	96.49 99	98.79 173	98.32 152
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Vis-MVSNet		92.77 144	95.00 86	90.16 172	94.10 158	98.79 67	94.76 156	88.26 160	92.37 176	79.95 178	88.19 124	91.58 86	84.38 246	97.59 62	97.58 54	99.52 22	98.91 87
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		92.66 146	92.49 155	92.85 137	97.13 70	98.89 63	95.90 124	88.50 159	95.32 105	83.31 162	71.99 247	88.96 107	94.10 146	96.69 95	96.49 99	98.15 206	99.10 58

IterMVS-LS		92.56 147	93.18 140	91.84 146	93.90 161	94.97 217	94.99 146	86.20 183	94.18 138	82.68 164	85.81 163	87.36 116	94.43 137	95.31 157	96.02 119	98.87 161	98.60 124
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GeoE		92.52 148	92.64 150	92.39 141	93.96 160	97.76 132	96.01 119	85.60 199	93.23 157	83.94 158	81.56 193	84.80 152	95.63 111	96.22 121	95.83 127	99.19 112	99.07 65

EPNet_dtu		92.45 149	95.02 85	89.46 184	98.02 57	95.47 203	94.79 154	92.62 70	94.97 121	70.11 239	94.76 60	92.61 83	84.07 250	95.94 135	95.56 134	97.15 225	95.82 222
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		92.03 150	91.55 175	92.58 138	97.13 70	98.72 72	94.65 158	86.54 179	93.58 149	82.56 165	67.75 259	90.47 94	95.67 108	95.87 137	95.54 135	98.91 157	98.93 83

test0.0.03 1		91.97 151	93.91 118	89.72 177	93.31 171	96.40 171	91.34 225	87.06 174	93.86 142	81.67 170	91.15 94	89.16 105	86.02 236	95.08 163	95.09 147	98.91 157	96.64 206

Fast-Effi-MVS+		91.87 152	92.08 166	91.62 151	92.91 175	97.21 148	94.93 148	84.60 217	93.61 147	81.49 172	83.50 183	78.95 191	96.62 75	96.55 104	96.22 110	99.16 118	98.51 133

dmvs_re		91.84 153	91.60 174	92.12 144	91.60 187	97.26 145	95.14 144	91.96 80	91.02 192	80.98 175	86.56 147	77.96 201	93.84 153	94.71 170	95.08 148	99.22 97	98.62 121

MS-PatchMatch		91.82 154	92.51 153	91.02 158	95.83 88	96.88 152	95.05 145	84.55 219	93.85 143	82.01 167	82.51 188	91.71 85	90.52 208	95.07 164	93.03 202	98.13 207	94.52 232

Effi-MVS+-dtu		91.78 155	93.59 128	89.68 180	92.44 181	97.11 149	94.40 166	84.94 213	92.43 172	75.48 209	91.09 96	83.75 168	93.55 159	96.61 98	95.47 137	97.24 224	98.67 114

IB-MVS	89.56 15	91.71 156	92.50 154	90.79 164	95.94 87	98.44 107	87.05 247	91.38 120	93.15 158	92.98 46	84.78 174	85.14 147	78.27 256	92.47 213	94.44 173	99.10 127	99.08 61
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
FC-MVSNet-test		91.63 157	93.82 123	89.08 188	92.02 184	96.40 171	93.26 184	87.26 170	93.72 145	77.26 196	88.61 120	89.86 98	85.50 238	95.72 146	95.02 151	99.16 118	97.44 182

test-LLR		91.62 158	93.56 129	89.35 187	93.31 171	96.57 165	92.02 210	87.06 174	92.34 177	75.05 216	90.20 102	88.64 109	90.93 193	96.19 125	94.07 179	97.75 216	96.90 199

MDTV_nov1_ep13		91.57 159	93.18 140	89.70 178	93.39 169	96.97 150	93.53 177	80.91 239	95.70 94	81.86 168	92.40 77	89.93 97	93.25 164	91.97 222	90.80 225	95.25 256	94.46 234

FMVSNet1		91.54 160	90.93 183	92.26 142	90.35 201	95.27 210	95.22 143	87.16 173	91.37 188	87.62 143	75.45 223	83.84 167	94.43 137	96.52 106	96.30 104	98.82 166	97.74 173

ACMH	90.77 13	91.51 161	91.63 173	91.38 153	95.62 90	96.87 154	91.76 214	89.66 143	91.58 186	78.67 187	86.73 141	78.12 195	93.77 155	94.59 172	94.54 169	98.78 174	98.98 78
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	90.88 12	91.41 162	91.13 180	91.74 148	95.11 106	96.95 151	93.13 186	89.48 147	92.42 173	79.93 179	85.13 171	78.02 197	93.82 154	93.49 195	93.88 185	98.94 153	97.99 163

Fast-Effi-MVS+-dtu		91.19 163	93.64 125	88.33 197	92.19 183	96.46 168	93.99 171	81.52 237	92.59 169	71.82 229	92.17 79	85.54 137	91.68 179	95.73 144	94.64 161	98.80 171	98.34 149

TESTMET0.1,1		91.07 164	93.56 129	88.17 199	90.43 198	96.57 165	92.02 210	82.83 229	92.34 177	75.05 216	90.20 102	88.64 109	90.93 193	96.19 125	94.07 179	97.75 216	96.90 199

test-mter		90.95 165	93.54 131	87.93 209	90.28 202	96.80 156	91.44 222	82.68 230	92.15 181	74.37 220	89.57 109	88.23 114	90.88 196	96.37 113	94.31 175	97.93 213	97.37 184

SCA		90.92 166	93.04 143	88.45 195	93.72 166	97.33 144	92.77 190	76.08 255	96.02 81	78.26 192	91.96 82	90.86 90	93.99 150	90.98 230	90.04 231	95.88 243	94.06 242

EPMVS		90.88 167	92.12 165	89.44 185	94.71 125	97.24 146	93.55 176	76.81 249	95.89 86	81.77 169	91.49 90	86.47 122	93.87 151	90.21 233	90.07 230	95.92 242	93.49 250

CostFormer		90.69 168	90.48 188	90.93 160	94.18 156	96.08 178	94.03 170	78.20 245	93.47 152	89.96 100	90.97 97	80.30 185	93.72 156	87.66 244	88.75 235	95.51 251	96.12 214

USDC		90.69 168	90.52 187	90.88 161	94.17 157	96.43 169	95.82 132	86.76 176	93.92 141	76.27 205	86.49 149	74.30 226	93.67 158	95.04 166	93.36 195	98.61 188	94.13 239

usedtu_dtu_shiyan1		90.61 170	91.45 177	89.62 182	85.03 251	96.03 179	93.51 178	89.17 150	93.13 159	79.51 183	81.79 191	84.24 161	91.63 180	95.06 165	93.79 190	98.88 159	96.12 214

PatchmatchNet		90.56 171	92.49 155	88.31 198	93.83 164	96.86 155	92.42 198	76.50 252	95.96 83	78.31 191	91.96 82	89.66 99	93.48 160	90.04 235	89.20 234	95.32 252	93.73 248
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pmmvs4		90.55 172	89.91 190	91.30 156	90.26 203	94.95 218	92.73 192	87.94 164	93.44 155	85.35 154	82.28 189	76.09 217	93.02 167	93.56 193	92.26 218	98.51 194	96.77 202

TAMVS		90.54 173	90.87 185	90.16 172	91.48 189	96.61 164	93.26 184	86.08 186	87.71 224	81.66 171	83.11 186	84.04 165	90.42 209	94.54 173	94.60 164	98.04 211	95.48 228

dtuonly		90.46 174	91.17 179	89.63 181	91.72 186	95.69 195	94.51 164	87.20 172	90.71 197	73.98 222	81.33 195	86.42 123	94.02 149	94.30 180	93.91 184	96.36 237	95.83 220

FMVSNet5		90.36 175	90.93 183	89.70 178	87.99 237	92.25 248	92.03 209	83.51 224	92.20 180	84.13 157	85.59 166	86.48 121	92.43 170	94.61 171	94.52 170	98.13 207	90.85 259

UniMVSNet_NR-MVSNet		90.35 176	89.96 189	90.80 163	89.66 210	95.83 190	92.48 196	90.53 130	90.96 194	79.57 180	79.33 206	77.14 209	93.21 165	92.91 205	94.50 172	99.37 66	99.05 68

IterMVS-SCA-FT		90.24 177	92.48 157	87.63 214	92.85 176	94.30 234	93.79 173	81.47 238	92.66 166	69.95 240	84.66 176	88.38 112	89.99 214	95.39 155	94.34 174	97.74 218	97.63 176

IterMVS		90.20 178	92.43 159	87.61 215	92.82 178	94.31 233	94.11 169	81.54 236	92.97 161	69.90 241	84.71 175	88.16 115	89.96 215	95.25 158	94.17 177	97.31 223	97.46 181
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPMNet		90.19 179	92.03 169	88.05 204	93.46 167	95.95 184	93.41 180	74.59 261	92.40 174	75.91 207	84.22 179	86.41 124	92.49 169	94.42 177	93.85 187	98.44 199	96.96 196

CR-MVSNet		90.16 180	91.96 170	88.06 203	93.32 170	95.95 184	93.36 182	75.99 256	92.40 174	75.19 213	83.18 184	85.37 140	92.05 173	95.21 159	94.56 167	98.47 197	97.08 193

thisisatest0515		90.12 181	92.06 167	87.85 210	90.03 205	96.17 176	87.83 244	87.45 168	91.71 185	77.15 197	85.40 170	84.01 166	85.74 237	95.41 154	93.30 198	98.88 159	98.43 140

dps		90.11 182	89.37 195	90.98 159	93.89 162	96.21 175	93.49 179	77.61 247	91.95 182	92.74 50	88.85 114	78.77 193	92.37 171	87.71 243	87.71 242	95.80 246	94.38 235

UniMVSNet (Re)		90.03 183	89.61 192	90.51 168	89.97 207	96.12 177	92.32 200	89.26 148	90.99 193	80.95 176	78.25 213	75.08 222	91.14 189	93.78 188	93.87 186	99.41 57	99.21 46

ADS-MVSNet		89.80 184	91.33 178	88.00 207	94.43 152	96.71 161	92.29 202	74.95 260	96.07 80	77.39 195	88.67 119	86.09 128	93.26 163	88.44 239	89.57 233	95.68 248	93.81 246

CVMVSNet		89.77 185	91.66 172	87.56 217	93.21 173	95.45 204	91.94 213	89.22 149	89.62 206	69.34 245	83.99 181	85.90 131	84.81 244	94.30 180	95.28 142	96.85 227	97.09 191

DU-MVS		89.67 186	88.84 197	90.63 166	89.26 221	95.61 197	92.48 196	89.91 135	91.22 189	79.57 180	77.72 216	71.18 240	93.21 165	92.53 211	94.57 166	99.35 69	99.05 68

0.4-1-1-0.1		89.64 187	88.08 207	91.46 152	86.21 244	94.41 230	94.79 154	86.20 183	88.54 214	91.15 68	86.64 143	78.03 196	94.36 142	84.47 257	88.05 238	96.08 241	96.40 207

testgi		89.42 188	91.50 176	87.00 224	92.40 182	95.59 199	89.15 241	85.27 208	92.78 164	72.42 226	91.75 86	76.00 218	84.09 249	94.38 178	93.82 189	98.65 186	96.15 212

TinyColmap		89.42 188	88.58 199	90.40 169	93.80 165	95.45 204	93.96 172	86.54 179	92.24 179	76.49 202	80.83 198	70.44 244	93.37 161	94.45 176	93.30 198	98.26 205	93.37 251

0.3-1-1-0.015		89.40 190	87.72 215	91.36 154	86.10 246	94.08 236	94.62 159	86.10 185	88.02 219	91.16 64	86.39 152	77.89 202	94.30 143	83.93 260	87.88 239	95.88 243	95.86 219

NR-MVSNet		89.34 191	88.66 198	90.13 175	90.40 199	95.61 197	93.04 188	89.91 135	91.22 189	78.96 185	77.72 216	68.90 252	89.16 220	94.24 183	93.95 182	99.32 72	98.99 76

0.4-1-1-0.2		89.32 192	87.66 217	91.26 157	86.11 245	93.97 238	94.54 161	85.98 188	87.83 222	91.12 69	86.40 151	78.02 197	94.06 147	84.03 258	87.73 241	95.75 247	95.62 227

GA-MVS		89.28 193	90.75 186	87.57 216	91.77 185	96.48 167	92.29 202	87.58 166	90.61 199	65.77 254	84.48 177	76.84 212	89.46 218	95.84 138	93.68 191	98.52 193	97.34 186

Baseline_NR-MVSNet		89.27 194	88.01 208	90.73 165	89.26 221	93.71 240	92.71 193	89.78 141	90.73 195	81.28 173	73.53 238	72.85 232	92.30 172	92.53 211	93.84 188	99.07 133	98.88 89

TranMVSNet+NR-MVSNet		89.23 195	88.48 201	90.11 176	89.07 227	95.25 211	92.91 189	90.43 131	90.31 201	77.10 198	76.62 221	71.57 238	91.83 177	92.12 217	94.59 165	99.32 72	98.92 84

pm-mvs1		89.19 196	89.02 196	89.38 186	90.40 199	95.74 194	92.05 208	88.10 163	86.13 243	77.70 193	73.72 237	79.44 190	88.97 221	95.81 140	94.51 171	99.08 131	97.78 172

PatchT		89.13 197	91.71 171	86.11 236	92.92 174	95.59 199	83.64 258	75.09 259	91.87 183	75.19 213	82.63 187	85.06 150	92.05 173	95.21 159	94.56 167	97.76 215	97.08 193

TDRefinement		89.07 198	88.15 204	90.14 174	95.16 104	96.88 152	95.55 139	90.20 132	89.68 204	76.42 203	76.67 220	74.30 226	84.85 243	93.11 201	91.91 220	98.64 187	94.47 233

MIMVSNet		88.99 199	91.07 181	86.57 232	86.78 243	95.62 196	91.20 228	75.40 258	90.65 198	76.57 201	84.05 180	82.44 179	91.01 192	95.84 138	95.38 139	98.48 196	93.50 249

anonymousdsp		88.90 200	91.00 182	86.44 233	88.74 234	95.97 182	90.40 235	82.86 228	88.77 212	67.33 249	81.18 197	81.44 182	90.22 212	96.23 120	94.27 176	99.12 124	99.16 53

tpm cat1		88.90 200	87.78 214	90.22 171	93.88 163	95.39 206	93.79 173	78.11 246	92.55 170	89.43 110	81.31 196	79.84 189	91.40 182	84.95 254	86.34 248	94.68 262	94.09 240

tpmrst		88.86 202	89.62 191	87.97 208	94.33 154	95.98 181	92.62 194	76.36 253	94.62 127	76.94 199	85.98 161	82.80 177	92.80 168	86.90 246	87.15 244	94.77 260	93.93 244

blend_shiyan4		88.50 203	86.74 230	90.54 167	85.31 250	92.15 252	93.79 173	85.10 209	87.64 226	91.16 64	86.06 158	77.89 202	91.22 185	84.59 255	82.60 261	96.67 231	96.25 208

tfpnnormal		88.50 203	87.01 225	90.23 170	91.36 190	95.78 193	92.74 191	90.09 133	83.65 252	76.33 204	71.46 250	69.58 249	91.84 176	95.54 149	94.02 181	99.06 138	99.03 71

UniMVSNet_ETH3D		88.47 205	86.00 237	91.35 155	91.55 188	96.29 173	92.53 195	88.81 154	85.58 247	82.33 166	67.63 260	66.87 258	94.04 148	91.49 226	95.24 143	98.84 165	98.92 84

SixPastTwentyTwo		88.37 206	89.47 193	87.08 222	90.01 206	95.93 186	87.41 245	85.32 205	90.26 203	70.26 237	86.34 156	71.95 236	90.93 193	92.89 206	91.72 221	98.55 191	97.22 188

V42		88.31 207	87.95 210	88.73 192	89.44 215	95.34 207	92.23 204	87.21 171	88.83 210	74.49 219	74.89 227	73.43 231	90.41 211	92.08 220	92.77 209	98.60 190	98.33 150

v2v482		88.25 208	87.71 216	88.88 190	89.23 225	95.28 208	92.10 206	87.89 165	88.69 213	73.31 224	75.32 224	71.64 237	91.89 175	92.10 219	92.92 204	98.86 163	97.99 163

v8		88.21 209	87.94 211	88.51 194	89.62 211	95.01 216	92.31 201	84.99 211	88.94 208	74.70 218	75.03 225	73.51 230	90.67 205	92.11 218	92.74 210	98.80 171	98.24 154

v10		88.00 210	87.96 209	88.05 204	89.44 215	94.68 224	92.36 199	83.35 225	89.37 207	72.96 225	73.98 235	72.79 233	91.35 184	93.59 190	92.88 205	98.81 169	98.42 142

usedtu_blend_shiyan5		87.98 211	86.70 231	89.47 183	77.63 261	92.14 253	94.53 162	85.67 194	86.74 235	91.16 64	86.06 158	77.89 202	91.22 185	85.19 250	82.63 257	96.58 232	96.25 208

tpm		87.95 212	89.44 194	86.21 235	92.53 180	94.62 227	91.40 223	76.36 253	91.46 187	69.80 243	87.43 128	75.14 220	91.55 181	89.85 237	90.60 227	95.61 249	96.96 196

WR-MVS_H		87.93 213	87.85 212	88.03 206	89.62 211	95.58 201	90.47 234	85.55 200	87.20 230	76.83 200	74.42 232	72.67 234	86.37 233	93.22 200	93.04 201	99.33 70	98.83 96

WR-MVS		87.93 213	88.09 205	87.75 211	89.26 221	95.28 208	90.81 231	86.69 177	88.90 209	75.29 212	74.31 233	73.72 229	85.19 241	92.26 214	93.32 197	99.27 83	98.81 99

v1144		87.92 215	87.79 213	88.07 201	89.27 220	95.15 213	92.17 205	85.62 198	88.52 215	71.52 230	73.80 236	72.40 235	91.06 191	93.54 194	92.80 207	98.81 169	98.33 150

CP-MVSNet		87.89 216	87.27 220	88.62 193	89.30 219	95.06 214	90.60 233	85.78 192	87.43 229	75.98 206	74.60 229	68.14 255	90.76 202	93.07 203	93.60 192	99.30 78	98.98 78

pmmvs5		87.83 217	88.09 205	87.51 219	89.59 213	95.48 202	89.75 239	84.73 215	86.07 245	71.44 231	80.57 201	70.09 247	90.74 204	94.47 175	92.87 206	98.82 166	97.10 190

FE-MVSNET3		87.75 218	86.69 232	88.99 189	77.63 261	92.14 253	91.64 218	85.67 194	86.75 233	91.16 64	86.06 158	77.89 202	91.22 185	85.19 250	82.63 257	96.58 232	96.18 210

TransMVSNet (Re)		87.73 219	86.79 227	88.83 191	90.76 195	94.40 231	91.33 226	89.62 144	84.73 249	75.41 211	72.73 242	71.41 239	86.80 230	94.53 174	93.93 183	99.06 138	95.83 220

LTVRE_ROB	87.32 16	87.55 220	88.25 203	86.73 230	90.66 196	95.80 192	93.05 187	84.77 214	83.35 253	60.32 266	83.12 185	67.39 256	93.32 162	94.36 179	94.86 155	98.28 203	98.87 91
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
v1192		87.51 221	87.31 219	87.74 212	89.04 228	94.87 222	92.07 207	85.03 210	88.49 216	70.32 236	72.65 243	70.35 245	91.21 188	93.59 190	92.80 207	98.78 174	98.42 142

v148		87.51 221	86.79 227	88.36 196	89.39 218	95.21 212	89.84 238	88.20 162	87.61 227	77.56 194	73.38 240	70.32 246	86.80 230	90.70 231	92.31 216	98.37 202	97.98 165

v144192		87.40 223	87.20 222	87.64 213	88.89 229	94.88 221	91.65 217	84.70 216	87.80 223	71.17 234	73.20 241	70.91 241	90.75 203	92.69 207	92.49 213	98.71 178	98.43 140

PS-CasMVS		87.33 224	86.68 233	88.10 200	89.22 226	94.93 219	90.35 236	85.70 193	86.44 242	74.01 221	73.43 239	66.59 261	90.04 213	92.92 204	93.52 193	99.28 80	98.91 87

v1921920		87.31 225	87.13 223	87.52 218	88.87 231	94.72 223	91.96 212	84.59 218	88.28 217	69.86 242	72.50 244	70.03 248	91.10 190	93.33 197	92.61 212	98.71 178	98.44 137

PEN-MVS		87.22 226	86.50 235	88.07 201	88.88 230	94.44 229	90.99 230	86.21 181	86.53 240	73.66 223	74.97 226	66.56 262	89.42 219	91.20 228	93.48 194	99.24 88	98.31 153

v1240		86.89 227	86.75 229	87.06 223	88.75 233	94.65 226	91.30 227	84.05 220	87.49 228	68.94 246	71.96 248	68.86 253	90.65 206	93.33 197	92.72 211	98.67 182	98.24 154

EG-PatchMatch MVS		86.68 228	87.24 221	86.02 237	90.58 197	96.26 174	91.08 229	81.59 235	84.96 248	69.80 243	71.35 251	75.08 222	84.23 247	94.24 183	93.35 196	98.82 166	95.46 229

DTE-MVSNet		86.67 229	86.09 236	87.35 220	88.45 236	94.08 236	90.65 232	86.05 187	86.13 243	72.19 227	74.58 231	66.77 260	87.61 227	90.31 232	93.12 200	99.13 122	97.62 177

v7n		86.43 230	86.52 234	86.33 234	87.91 238	94.93 219	90.15 237	83.05 226	86.57 239	70.21 238	71.48 249	66.78 259	87.72 225	94.19 185	92.96 203	98.92 155	98.76 106

MDTV_nov1_ep13_2view		86.30 231	88.27 202	84.01 242	87.71 240	94.67 225	88.08 243	76.78 250	90.59 200	68.66 247	80.46 203	80.12 187	87.58 228	89.95 236	88.20 237	95.25 256	93.90 245

gbinet_0.2-2-1-0.02		86.23 232	85.66 238	86.89 225	78.33 258	92.17 251	91.62 221	85.96 190	86.51 241	79.33 184	78.13 214	77.66 207	89.55 217	85.60 247	82.66 256	96.56 236	96.87 201

gg-mvs-nofinetune		86.17 233	88.57 200	83.36 244	93.44 168	98.15 123	96.58 89	72.05 264	74.12 267	49.23 274	64.81 263	90.85 91	89.90 216	97.83 54	96.84 90	98.97 148	97.41 183

pmnet_mix02		86.12 234	87.12 224	84.96 240	89.82 208	94.12 235	84.88 254	86.63 178	91.78 184	65.60 255	80.76 199	76.98 210	86.61 232	87.29 245	84.80 251	96.21 238	94.09 240

blended_shiyan8		86.10 235	85.44 241	86.88 226	77.65 260	92.22 249	91.69 215	85.52 201	86.88 231	78.82 186	78.06 215	76.43 216	90.85 198	85.36 249	82.97 255	96.74 229	96.14 213

blended_shiyan6		86.10 235	85.52 239	86.79 227	77.63 261	92.20 250	91.66 216	85.46 203	86.86 232	78.43 188	78.30 212	76.71 213	90.80 201	85.37 248	82.98 254	96.74 229	96.18 210

wanda-best-256-512		86.03 237	85.37 242	86.79 227	77.63 261	92.14 253	91.64 218	85.67 194	86.75 233	78.43 188	78.36 210	76.66 214	90.81 199	85.19 250	82.63 257	96.58 232	95.88 217

FE-blended-shiyan7		86.03 237	85.37 242	86.79 227	77.63 261	92.14 253	91.64 218	85.67 194	86.74 235	78.43 188	78.36 210	76.66 214	90.81 199	85.19 250	82.63 257	96.58 232	95.88 217

pmmvs6		85.98 239	84.89 248	87.25 221	88.83 232	94.35 232	89.36 240	85.30 207	78.51 264	75.44 210	62.71 265	75.41 219	87.65 226	93.58 192	92.40 215	96.89 226	97.29 187

EU-MVSNet		85.62 240	87.65 218	83.24 245	88.54 235	92.77 246	87.12 246	85.32 205	86.71 238	64.54 257	78.52 209	75.11 221	78.35 255	92.25 215	92.28 217	95.58 250	95.93 216

MVS-HIRNet		85.36 241	86.89 226	83.57 243	90.13 204	94.51 228	83.57 259	72.61 263	88.27 218	71.22 233	68.97 255	81.81 180	88.91 222	93.08 202	91.94 219	94.97 259	89.64 262

N_pmnet		84.80 242	85.10 247	84.45 241	89.25 224	92.86 243	84.04 256	86.21 181	88.78 211	66.73 252	72.41 245	74.87 225	85.21 240	88.32 241	86.45 245	95.30 254	92.04 256

CMPMVS	65.18 17	84.76 243	83.10 250	86.69 231	95.29 98	95.05 215	88.37 242	85.51 202	80.27 261	71.31 232	68.37 257	73.85 228	85.25 239	87.72 242	87.75 240	94.38 263	88.70 263
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PM-MVS		84.72 244	84.47 249	85.03 239	84.67 252	91.57 258	86.27 249	82.31 234	87.65 225	70.62 235	76.54 222	56.41 273	88.75 223	92.59 210	89.85 232	97.54 220	96.66 205

pmmvs-eth3d		84.33 245	82.94 251	85.96 238	84.16 253	90.94 259	86.55 248	83.79 221	84.25 250	75.85 208	70.64 252	56.43 272	87.44 229	92.20 216	90.41 229	97.97 212	95.68 224

dtuonlycased		84.27 246	85.21 245	83.17 246	85.99 248	92.85 245	83.74 257	82.59 231	86.74 235	66.76 251	77.36 218	78.74 194	84.13 248	83.16 262	83.81 252	95.83 245	93.80 247

Anonymous20231206		83.84 247	85.19 246	82.26 248	87.38 241	92.87 242	85.49 252	83.65 222	86.07 245	63.44 261	68.42 256	69.01 251	75.45 260	93.34 196	92.44 214	98.12 209	94.20 238

gm-plane-assit		83.26 248	85.29 244	80.89 249	89.52 214	89.89 262	70.26 271	78.24 244	77.11 265	58.01 271	74.16 234	66.90 257	90.63 207	97.20 74	96.05 117	98.66 185	95.68 224

test20.03		82.92 249	85.52 239	79.90 252	87.75 239	91.84 257	82.80 260	82.99 227	82.65 257	60.32 266	78.90 208	70.50 242	67.10 265	92.05 221	90.89 224	98.44 199	91.80 257

FE-MVSNET2		81.81 250	81.15 253	82.57 247	75.40 268	92.39 247	86.04 250	83.61 223	81.61 258	68.16 248	55.75 269	59.22 270	83.77 251	93.31 199	91.54 223	98.45 198	94.24 237

new_pmnet		81.53 251	82.68 252	80.20 250	83.47 255	89.47 263	82.21 262	78.36 243	87.86 221	60.14 268	67.90 258	69.43 250	82.03 253	89.22 238	87.47 243	94.99 258	87.39 264

MDA-MVSNet-bldmvs		80.11 252	80.24 256	79.94 251	77.01 266	93.21 241	78.86 267	85.94 191	82.71 256	60.86 263	79.71 205	51.77 276	83.71 252	75.60 266	86.37 247	93.28 265	92.35 253

MIMVSNet1		80.03 253	80.93 254	78.97 253	72.46 270	90.73 260	80.81 265	82.44 232	80.39 260	63.64 259	57.57 268	64.93 263	76.37 258	91.66 224	91.55 222	98.07 210	89.70 261

pmmvs3		79.16 254	80.12 257	78.05 255	79.36 257	86.59 267	78.13 268	73.87 262	76.42 266	57.51 272	70.59 253	57.02 271	84.66 245	90.10 234	88.32 236	94.75 261	91.77 258

FE-MVSNET		79.15 255	80.25 255	77.87 256	69.65 271	89.30 264	81.34 264	82.42 233	79.49 263	59.18 270	59.18 266	59.41 269	77.03 257	91.12 229	90.65 226	97.57 219	92.63 252

new-patchmatchnet		78.49 256	78.19 259	78.84 254	84.13 254	90.06 261	77.11 269	80.39 240	79.57 262	59.64 269	66.01 261	55.65 274	75.62 259	84.55 256	80.70 264	96.14 240	90.77 260

FPMVS		75.84 257	74.59 262	77.29 257	86.92 242	83.89 269	85.01 253	80.05 241	82.91 255	60.61 265	65.25 262	60.41 266	63.86 266	75.60 266	73.60 268	87.29 271	80.47 267

usedtu_dtu_shiyan2		75.82 258	75.29 261	76.44 258	65.25 273	87.28 265	82.09 263	76.55 251	68.86 269	66.94 250	48.90 272	60.22 267	74.42 261	83.98 259	83.40 253	93.39 264	94.38 235

test_method		72.96 259	78.68 258	66.28 262	50.17 276	64.90 274	75.45 270	50.90 271	87.89 220	62.54 262	62.98 264	68.34 254	70.45 263	91.90 223	82.41 262	88.19 270	92.35 253

WB-MVS		69.22 260	76.91 260	60.24 264	85.80 249	79.37 270	56.86 276	84.96 212	81.50 259	18.16 279	76.85 219	61.07 264	34.23 274	82.46 264	81.81 263	81.43 274	75.31 271

Gipuma		68.35 261	66.71 264	70.27 259	74.16 269	68.78 273	63.93 274	71.77 265	83.34 254	54.57 273	34.37 274	31.88 280	68.69 264	83.30 261	85.53 249	88.48 269	79.78 268
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	63.12 18	67.27 262	66.39 265	68.30 260	77.98 259	60.24 275	59.53 275	76.82 248	66.65 270	60.74 264	54.39 270	59.82 268	51.24 269	73.92 269	70.52 269	83.48 272	79.17 269
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GG-mvs-BLEND		66.17 263	94.91 87	32.63 268	1.32 282	96.64 163	91.40 223	0.85 278	94.39 134	2.20 284	90.15 104	95.70 66	2.27 280	96.39 110	95.44 138	97.78 214	95.68 224

PMMVS2		64.36 264	65.94 266	62.52 263	67.37 272	77.44 271	64.39 273	69.32 269	61.47 272	34.59 275	46.09 273	41.03 279	48.02 272	74.56 268	78.23 265	91.43 267	82.76 266

E-PMN		50.67 265	47.85 270	53.96 265	64.13 275	50.98 278	38.06 277	69.51 267	51.40 275	24.60 277	29.46 278	24.39 282	56.07 268	48.17 273	59.70 270	71.40 275	70.84 274

EMVS		49.98 266	46.76 271	53.74 266	64.96 274	51.29 277	37.81 278	69.35 268	51.83 274	22.69 278	29.57 277	25.06 281	57.28 267	44.81 274	56.11 271	70.32 276	68.64 275

MVE	50.86 19	49.54 267	51.43 269	47.33 267	44.14 277	59.20 276	36.45 279	60.59 270	41.47 276	31.14 276	29.58 276	17.06 285	48.52 271	62.22 270	74.63 267	63.12 277	75.87 270
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS_CLIP		39.59 268	56.46 267	19.90 269	13.25 280	27.17 280	26.54 281	2.21 277	66.02 271	6.72 282	79.09 207	45.57 278	33.38 275	53.25 271	50.75 272	37.29 278	73.40 273

MVS_clip		38.84 269	56.46 267	18.29 270	13.36 279	29.13 279	19.64 282	2.47 275	71.08 268	6.73 281	70.46 254	54.40 275	39.84 273	49.33 272	47.18 273	27.70 279	73.62 272

VLMVS		32.08 270	46.28 272	15.51 271	13.62 278	23.52 281	16.04 283	2.37 276	55.69 273	11.28 280	58.95 267	46.49 277	30.07 276	40.05 275	38.72 274	19.67 280	60.57 276

MVS_baseline		14.46 271	24.65 273	2.57 274	1.29 284	4.82 284	1.07 286	0.00 279	28.62 277	0.00 286	33.80 275	22.58 284	12.80 277	21.00 276	19.40 275	0.25 283	42.31 277

testmvs		12.09 272	16.94 274	6.42 272	3.15 281	6.08 282	9.51 284	3.84 273	21.46 278	5.31 283	27.49 279	6.76 286	10.89 278	17.06 277	15.01 276	5.84 281	24.75 278

test123		9.58 273	13.53 275	4.97 273	1.31 283	5.47 283	8.32 285	2.95 274	18.14 279	2.03 285	20.82 280	2.34 287	10.60 279	10.00 278	14.16 277	4.60 282	23.77 279

uanet_test		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	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	0.00 279	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	0.00 279	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					98.91 38	98.58 89	98.35 40		95.95 84	89.83 103	96.31 38	98.61 38	95.98 104			98.86 163	98.78 101

PatchmatchNet2					89.40 217	92.86 243	84.21 255
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												75.08 222	85.19 241	88.36 240	86.44 246	95.32 252	92.09 255
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										66.35 253	72.11 246
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							99.35 6	97.66 11		98.71 4						99.42 54

TPM-MVS					98.94 35	98.47 105	98.04 47			92.62 51	96.51 37	98.76 32	95.94 105			98.92 155	97.55 178
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										63.50 260

9.14												99.28 15

SR-MVS					99.45 12			97.61 18				99.20 19

Anonymous202405211			92.18 164		95.04 108	98.20 119	96.14 105	91.79 93	93.93 140		74.60 229	88.38 112	96.48 85	95.17 161	95.82 129	99.00 145	99.15 55

our_test_3					89.78 209	93.84 239	85.59 251

ambc			73.83 263		76.23 267	85.13 268	82.27 261		84.16 251	65.58 256	52.82 271	23.31 283	73.55 262	91.41 227	85.26 250	92.97 266	94.70 231

MTAPA										96.83 14		99.12 24

MTMP										97.18 9		98.83 29

Patchmatch-RL test							34.61 280

tmp_tt				66.88 261	86.07 247	73.86 272	68.22 272	33.38 272	96.88 55	80.67 177	88.23 123	78.82 192	49.78 270	82.68 263	77.47 266	83.19 273

XVS					96.60 73	99.35 21	96.82 75			90.85 74		98.72 33				99.46 37

X-MVStestdata					96.60 73	99.35 21	96.82 75			90.85 74		98.72 33				99.46 37

mPP-MVS					99.21 26							98.29 42

NP-MVS									95.32 105

Patchmtry						95.96 183	93.36 182	75.99 256		75.19 213

DeepMVS_CX						86.86 266	79.50 266	70.43 266	90.73 195	63.66 258	80.36 204	60.83 265	79.68 254	76.23 265		89.46 268	86.53 265

High-resolution multi-view benchmark