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		99.21 1	99.41 1	98.97 1	99.38 10	99.87 1	99.72 1	96.34 4	99.62 2	99.05 4	98.83 7	99.99 1	99.58 1	98.89 13	98.68 7	99.76 12	99.99 3

aaEdge-Enhanced		99.07 2	99.22 3	98.90 2	99.39 7	99.81 11	99.36 18	96.46 1	99.30 14	99.11 3	98.75 11	99.99 1	99.23 8	98.67 19	98.11 20	99.83 4	99.93 20

MED-MVS		99.06 3	99.20 4	98.90 2	99.39 7	99.83 8	99.57 9	96.39 3	99.46 5	99.17 2	98.75 11	99.98 5	99.26 7	98.77 16	97.68 28	99.61 36	99.93 20

SED-MVS		98.87 4	99.20 4	98.48 4	99.32 16	99.85 3	99.55 11	96.20 10	99.48 4	96.78 7	98.51 19	99.99 1	99.36 4	98.98 8	97.59 33	99.67 24	99.99 3

DVP-MVS++		98.75 5	99.11 10	98.33 6	99.41 6	99.85 3	99.61 6	96.22 9	99.32 12	95.80 9	98.27 22	99.97 7	99.22 9	98.95 9	97.48 37	99.71 22	99.98 6

MSP-MVS		98.75 5	99.27 2	98.15 11	99.21 22	99.82 9	99.58 8	96.09 17	99.32 12	95.16 13	98.79 8	99.55 12	99.05 11	99.54 1	97.88 24	99.84 3	99.99 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
CNVR-MVS		98.73 7	99.17 8	98.22 8	99.47 5	99.85 3	99.57 9	96.23 7	99.30 14	94.90 15	98.65 14	98.93 23	99.36 4	99.46 3	98.21 14	99.81 8	99.80 36

DPE-MVS		98.69 8	99.14 9	98.16 10	99.37 12	99.82 9	99.66 5	96.26 5	99.18 21	95.02 14	98.62 16	99.98 5	98.88 16	98.90 12	97.51 36	99.75 14	99.97 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		98.65 9	98.87 17	98.38 5	99.30 17	99.85 3	99.14 28	96.23 7	99.51 3	97.16 5	96.01 39	99.99 1	98.90 15	98.89 13	97.88 24	99.56 59	99.98 6
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
APDe-MVS		98.60 10	98.97 14	98.18 9	99.38 10	99.78 15	99.35 20	96.14 13	99.24 18	95.66 11	98.19 24	99.01 20	98.66 22	98.77 16	97.80 27	99.86 2	99.97 9
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		98.55 11	98.75 19	98.32 7	99.48 3	99.68 26	99.51 13	96.24 6	99.08 25	95.94 8	98.64 15	99.30 16	99.02 13	97.94 33	96.86 57	99.75 14	99.76 40

SMA-MVS		98.47 12	99.06 11	97.77 14	99.48 3	99.78 15	99.37 15	96.14 13	99.29 16	93.03 23	97.59 33	99.97 7	99.03 12	98.94 10	98.30 11	99.60 39	99.58 71
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
NCCC		98.41 13	99.18 6	97.52 18	99.36 13	99.84 7	99.55 11	96.08 19	99.33 11	91.77 28	98.79 8	99.46 14	98.59 24	99.15 7	98.07 22	99.73 17	99.64 59

SD-MVS		98.33 14	99.01 12	97.54 17	97.17 55	99.77 18	99.14 28	96.09 17	99.34 10	94.06 19	97.91 29	99.89 9	99.18 10	97.99 32	98.21 14	99.63 31	99.95 14
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
APD-MVS		98.28 15	98.69 20	97.80 13	99.30 17	99.62 33	99.31 23	96.15 12	99.19 20	93.60 20	97.28 34	98.35 32	98.72 21	98.27 25	98.22 13	99.73 17	99.89 29
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MCST-MVS		98.20 16	99.18 6	97.06 24	99.27 20	99.87 1	99.37 15	96.11 15	99.37 8	89.29 37	98.76 10	99.50 13	98.37 30	99.23 5	97.64 31	99.95 1	99.87 33

HPM-MVS++		98.16 17	98.87 17	97.32 20	99.39 7	99.70 24	99.18 26	96.10 16	99.09 24	91.14 30	98.02 27	99.89 9	98.44 28	98.75 18	97.03 51	99.67 24	99.63 62

MSLP-MVS++		98.12 18	98.23 32	97.99 12	99.28 19	99.72 21	99.59 7	95.27 32	98.61 40	94.79 16	96.11 38	97.79 41	99.27 6	96.62 72	98.96 5	99.77 11	99.80 36

HFP-MVS		98.02 19	98.55 24	97.40 19	99.11 25	99.69 25	99.41 14	95.41 30	98.79 36	91.86 27	98.61 17	98.16 34	99.02 13	97.87 37	97.40 39	99.60 39	99.35 95

TSAR-MVS + MP.		97.98 20	98.62 23	97.23 22	97.08 56	99.55 39	99.17 27	95.69 25	99.40 6	93.04 22	96.68 36	98.96 22	98.58 25	98.82 15	96.95 54	99.81 8	99.96 11
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SteuartSystems-ACMMP		97.86 21	98.91 15	96.64 28	98.89 31	99.79 12	99.34 21	95.20 34	98.48 42	89.91 35	98.58 18	98.69 27	96.84 55	98.92 11	98.16 18	99.66 26	99.74 43
Skip Steuart: Steuart Systems R&D Blog.
CP-MVS		97.81 22	98.26 31	97.28 21	99.00 28	99.65 29	99.10 30	95.32 31	98.38 48	92.21 26	98.33 21	97.74 42	98.50 26	97.66 46	96.55 65	99.57 52	99.48 81

ACMMPR		97.78 23	98.28 29	97.20 23	99.03 27	99.68 26	99.37 15	95.24 33	98.86 35	91.16 29	97.86 31	97.26 44	98.79 19	97.64 48	97.40 39	99.60 39	99.25 103

DeepC-MVS_fast	95.01 1	97.67 24	98.22 33	97.02 25	99.00 28	99.79 12	99.10 30	95.82 22	99.05 27	89.53 36	93.54 54	96.77 47	98.83 17	99.34 4	99.44 2	99.82 6	99.63 62
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		97.54 25	97.35 42	97.77 14	99.17 23	99.55 39	98.57 37	95.76 24	99.04 28	94.66 17	97.94 28	94.39 61	98.82 18	96.21 85	94.78 115	99.62 34	99.52 76

ACMMP_NAP		97.51 26	98.27 30	96.63 29	99.34 14	99.72 21	99.25 24	95.94 21	98.11 53	87.10 52	96.98 35	98.50 29	98.61 23	98.58 21	96.83 58	99.56 59	99.14 117

MP-MVS		97.46 27	98.30 28	96.48 30	98.93 30	99.43 47	99.20 25	95.42 29	98.43 44	87.60 48	98.19 24	98.01 40	98.09 32	98.05 30	96.67 62	99.64 29	99.35 95
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
train_agg		97.42 28	98.88 16	95.71 35	98.46 38	99.60 36	99.05 32	95.16 35	99.10 23	84.38 79	98.47 20	98.85 24	97.61 36	98.54 22	97.66 30	99.62 34	99.93 20

MGCNet		97.38 29	99.01 12	95.47 38	97.24 54	99.68 26	98.62 36	89.40 53	98.88 34	90.96 31	99.09 4	98.85 24	96.90 53	98.13 27	98.54 9	99.72 20	99.91 26

CPTT-MVS		97.32 30	97.60 41	96.99 26	98.29 41	99.31 59	99.04 33	94.67 39	97.99 59	93.12 21	98.03 26	98.26 33	98.77 20	96.08 90	94.26 124	98.07 216	99.27 102

X-MVS		97.20 31	98.42 27	95.77 33	99.04 26	99.64 30	98.95 35	95.10 37	98.16 51	83.97 88	98.27 22	98.08 37	97.95 33	97.89 34	97.46 38	99.58 48	99.47 82

PHI-MVS		97.09 32	98.69 20	95.22 40	97.99 46	99.59 38	97.56 49	92.16 43	98.41 46	87.11 51	98.70 13	99.42 15	96.95 50	96.88 64	98.16 18	99.56 59	99.70 50

DPM-MVS		97.07 33	97.99 36	96.00 32	97.25 53	99.16 69	99.67 3	95.99 20	99.08 25	85.97 61	93.00 59	98.44 30	97.47 38	99.22 6	99.62 1	99.66 26	97.44 192

PGM-MVS		97.03 34	98.14 35	95.73 34	99.34 14	99.61 35	99.34 21	89.99 49	97.70 62	87.67 47	99.44 2	96.45 50	98.44 28	97.65 47	97.09 47	99.58 48	99.06 129

PLC	94.37 2	97.03 34	96.54 49	97.60 16	98.84 32	98.63 79	98.17 41	94.99 38	99.01 30	96.80 6	93.21 58	95.64 52	97.36 39	96.37 79	94.79 114	99.41 103	98.12 175
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + ACMM		96.90 36	98.64 22	94.88 42	98.12 44	99.47 44	99.01 34	95.43 28	99.23 19	81.98 118	95.95 40	99.16 19	95.13 77	98.61 20	98.11 20	99.58 48	99.93 20

TSAR-MVS + GP.		96.47 37	98.45 26	94.17 47	92.12 91	99.29 60	97.76 45	88.05 60	99.36 9	90.26 34	97.82 32	99.21 17	97.21 42	96.78 69	96.74 60	99.63 31	99.94 17

EPNet		96.23 38	97.89 38	94.29 45	97.62 49	99.44 46	97.14 57	88.63 56	98.16 51	88.14 43	99.46 1	94.15 64	94.61 95	97.20 56	97.23 43	99.57 52	99.59 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNLPA		96.14 39	95.43 58	96.98 27	98.55 35	99.41 51	95.91 63	95.15 36	99.00 31	95.71 10	84.21 119	94.55 59	97.25 40	95.50 114	96.23 71	99.28 139	99.09 128

MVS_111021_LR		96.07 40	97.94 37	93.88 50	97.86 47	99.43 47	95.70 66	89.65 52	98.73 37	84.86 73	99.38 3	94.08 65	95.78 74	97.81 40	96.73 61	99.43 97	99.42 88

ACMMP		96.05 41	96.70 48	95.29 39	98.01 45	99.43 47	97.60 48	94.33 41	97.62 65	86.17 56	98.92 5	92.81 72	96.10 67	95.67 103	93.33 145	99.55 64	99.12 121
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
3Dnovator+	90.72 7	95.99 42	96.42 51	95.50 37	98.18 43	99.33 58	97.44 52	87.73 64	97.93 60	92.36 25	84.67 110	97.33 43	97.55 37	97.32 52	98.47 10	99.72 20	99.88 30

DeepPCF-MVS	94.02 3	95.92 43	98.47 25	92.95 60	97.57 50	99.79 12	91.45 155	94.42 40	99.76 1	86.48 55	92.88 60	98.12 36	92.62 135	99.49 2	99.32 3	95.15 257	99.95 14

CDPH-MVS		95.90 44	97.77 40	93.72 53	98.28 42	99.43 47	98.40 38	91.30 47	98.34 49	78.62 147	94.80 46	95.74 51	96.11 66	97.86 38	98.67 8	99.59 43	99.56 73

CSCG		95.77 45	95.35 60	96.26 31	99.13 24	99.60 36	98.14 42	91.89 46	96.57 80	92.61 24	89.65 72	91.74 80	96.96 47	93.69 149	96.58 64	98.86 169	99.63 62

OMC-MVS		95.75 46	95.84 56	95.64 36	98.52 37	99.34 57	97.15 56	92.02 45	98.94 33	90.45 33	88.31 78	94.64 57	96.35 62	96.02 93	95.99 82	99.34 122	97.65 188

MVS_111021_HR		95.70 47	98.16 34	92.83 62	97.57 50	99.77 18	94.78 82	88.05 60	98.61 40	82.29 113	98.85 6	94.66 56	94.63 91	97.80 41	97.63 32	99.64 29	99.79 38

3Dnovator	90.31 8	95.67 48	96.16 54	95.11 41	98.59 34	99.37 56	97.50 50	87.98 62	98.02 58	89.09 38	85.36 109	94.62 58	97.66 34	97.10 60	98.90 6	99.82 6	99.73 46

CANet		95.40 49	96.27 52	94.40 44	96.25 61	99.62 33	98.37 39	88.59 57	98.09 54	87.58 49	84.57 113	95.54 54	95.87 71	98.12 28	98.03 23	99.73 17	99.90 28

QAPM		95.17 50	96.05 55	94.14 48	98.55 35	99.49 42	97.41 53	87.88 63	97.72 61	84.21 83	84.59 112	95.60 53	97.21 42	97.10 60	98.19 17	99.57 52	99.65 57

SPE-MVS-test		95.06 51	96.98 45	92.82 63	95.83 64	99.40 52	93.23 124	85.29 103	99.27 17	85.89 65	93.86 53	92.70 74	97.19 44	97.70 44	96.18 74	99.49 74	99.76 40

MVSMamba_PlusPlus		94.95 52	96.76 47	92.84 61	90.79 111	98.88 71	97.50 50	87.29 67	99.03 29	83.39 94	92.88 60	90.90 87	98.45 27	98.32 23	98.30 11	99.63 31	98.98 135

CS-MVS		94.82 53	96.19 53	93.22 56	95.19 69	99.24 62	95.10 77	85.07 113	98.72 38	87.33 50	91.35 63	89.98 90	97.06 46	98.01 31	96.28 69	99.60 39	99.72 47

MVSTER		94.75 54	96.50 50	92.70 65	90.91 109	94.51 179	97.37 54	83.37 131	98.40 47	89.04 39	93.23 57	97.04 46	95.91 70	97.73 42	95.59 105	99.61 36	99.01 133

TAPA-MVS	92.04 6	94.72 55	95.13 63	94.24 46	97.72 48	99.17 67	97.61 47	92.16 43	97.66 64	81.99 117	87.84 83	93.94 67	96.50 59	95.74 100	94.27 123	99.46 85	97.31 196
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DeepC-MVS	92.23 5	94.53 56	94.26 76	94.86 43	96.73 58	99.50 41	97.85 44	95.45 27	96.22 89	82.73 103	80.68 131	88.02 95	96.92 51	97.49 51	98.20 16	99.47 79	99.69 53
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CHOSEN 280x420		94.51 57	97.78 39	90.70 101	95.54 68	99.49 42	94.14 95	74.91 206	98.43 44	85.32 70	94.78 47	99.19 18	94.95 84	97.02 62	96.18 74	99.35 118	99.36 94

ETV-MVS		94.49 58	97.23 44	91.29 85	90.43 120	98.55 82	93.41 114	84.53 122	99.16 22	83.13 97	94.72 48	94.08 65	96.61 58	97.72 43	96.60 63	99.61 36	99.81 35

EC-MVSNet		94.33 59	96.88 46	91.36 82	90.12 134	97.70 122	95.20 76	80.27 158	98.63 39	85.97 61	93.92 52	93.85 70	97.09 45	97.54 50	96.81 59	99.49 74	99.70 50

MAR-MVS		94.18 60	95.12 64	93.09 59	98.40 40	99.17 67	94.20 94	81.92 140	98.47 43	86.52 54	90.92 65	84.21 115	98.12 31	95.88 96	97.59 33	99.40 105	99.58 71
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
PCF-MVS	92.56 4	93.95 61	93.82 79	94.10 49	96.07 63	99.25 61	96.82 59	95.51 26	92.00 154	81.51 123	82.97 123	93.88 69	95.63 75	94.24 132	94.71 117	99.09 151	99.70 50
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DELS-MVS		93.82 62	93.82 79	93.81 52	96.34 60	99.47 44	97.26 55	88.53 58	92.13 151	87.80 46	79.67 138	88.01 96	93.14 124	98.28 24	99.22 4	99.80 10	99.98 6
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
OpenMVS	88.43 11	93.49 63	93.62 82	93.34 54	98.46 38	99.39 53	97.00 58	87.66 66	95.37 100	81.21 127	75.96 167	91.58 82	96.21 65	96.37 79	97.10 46	99.52 69	99.54 75

EIA-MVS		93.32 64	95.32 61	90.99 91	90.45 119	98.53 85	93.46 112	84.68 118	97.56 68	81.38 124	91.04 64	87.37 99	96.39 61	97.27 53	95.73 94	99.59 43	99.76 40

PVSNet_BlendedMVS		93.30 65	93.46 86	93.10 57	95.60 66	99.38 54	93.59 107	88.70 54	98.09 54	88.10 44	86.96 91	75.02 155	93.08 125	97.89 34	96.90 55	99.56 59	100.00 1

PVSNet_Blended		93.30 65	93.46 86	93.10 57	95.60 66	99.38 54	93.59 107	88.70 54	98.09 54	88.10 44	86.96 91	75.02 155	93.08 125	97.89 34	96.90 55	99.56 59	100.00 1

test2506		93.08 67	93.40 88	92.70 65	92.76 84	99.20 64	94.67 85	86.82 72	92.58 144	90.81 32	86.28 97	85.24 110	91.69 145	96.85 65	96.33 67	99.45 91	97.34 195

PMMVS		93.05 68	95.40 59	90.31 113	91.41 100	97.54 132	92.62 144	83.25 133	98.08 57	79.44 145	95.18 44	88.52 94	96.43 60	95.70 101	93.88 128	98.68 185	98.91 137

LS3D		92.70 69	92.23 100	93.26 55	96.24 62	98.72 74	97.93 43	96.17 11	96.41 82	72.46 163	81.39 128	80.76 128	97.66 34	95.69 102	95.62 102	99.07 153	97.02 204

baseline1		92.67 70	93.62 82	91.55 75	91.16 104	97.15 136	93.92 101	85.97 80	94.76 109	84.07 85	87.17 87	86.89 102	94.62 94	96.72 70	95.90 86	99.57 52	96.79 208

IS_MVSNet		92.67 70	94.99 66	89.96 120	91.17 103	98.54 83	92.77 135	84.00 125	92.72 142	81.90 120	85.67 106	92.47 75	90.39 159	97.82 39	97.81 26	99.51 70	99.91 26

TSAR-MVS + COLMAP		92.56 72	92.44 98	92.71 64	94.61 72	97.69 123	97.69 46	91.09 48	98.96 32	76.71 153	94.68 49	69.41 201	96.91 52	95.80 99	94.18 125	99.26 142	96.33 212

baseline		92.56 72	94.38 72	90.43 110	90.71 114	98.23 93	95.07 78	80.73 157	97.52 69	82.45 108	87.34 86	85.91 106	94.07 111	96.29 84	95.94 84	99.58 48	99.47 82

sasdasda		92.54 74	93.28 89	91.68 71	91.44 98	98.24 91	95.45 71	81.84 144	95.98 94	84.85 74	90.69 66	78.53 133	96.96 47	92.97 158	97.06 48	99.57 52	99.47 82

canonicalmvs		92.54 74	93.28 89	91.68 71	91.44 98	98.24 91	95.45 71	81.84 144	95.98 94	84.85 74	90.69 66	78.53 133	96.96 47	92.97 158	97.06 48	99.57 52	99.47 82

PatchMatch-RL		92.54 74	92.82 97	92.21 67	96.57 59	98.74 73	91.85 152	86.30 75	96.23 88	85.18 71	95.21 43	73.58 170	94.22 108	95.40 117	93.08 149	99.14 148	97.49 191

MVS_Test		92.42 77	94.43 68	90.08 119	90.69 115	98.26 90	94.78 82	80.81 156	97.27 71	78.76 146	87.06 89	84.25 114	95.84 72	97.67 45	97.56 35	99.59 43	98.93 136

MGCFI-Net		92.39 78	93.14 92	91.51 78	91.38 101	98.16 94	95.28 75	81.66 147	95.82 97	84.36 81	90.51 69	78.30 135	96.80 56	92.82 162	96.97 53	99.55 64	99.42 88

thisisatest0530		92.31 79	95.14 62	89.02 136	90.02 137	98.45 87	91.30 156	83.58 128	96.90 76	77.90 149	90.45 70	94.33 62	91.98 141	95.57 107	91.43 176	99.31 129	98.81 141

tttt0517		92.29 80	95.12 64	88.99 137	90.02 137	98.44 89	91.19 160	83.58 128	96.88 77	77.86 150	90.45 70	94.32 63	91.98 141	95.54 110	91.43 176	99.31 129	98.78 144

EPP-MVSNet		92.29 80	94.35 74	89.88 122	90.36 122	97.69 123	90.89 164	83.31 132	93.39 128	83.47 93	85.56 107	93.92 68	91.93 143	95.49 115	94.77 116	99.34 122	99.62 65

HQP-MVS		91.94 82	93.03 93	90.66 103	93.69 74	96.48 150	95.92 62	89.73 50	97.33 70	72.65 161	95.37 41	73.56 171	92.75 134	94.85 125	94.12 126	99.23 145	99.51 77

MSDG		91.93 83	90.28 140	93.85 51	97.36 52	97.12 137	95.88 64	94.07 42	94.52 114	84.13 84	76.74 160	80.89 127	92.54 136	93.97 142	93.61 139	99.14 148	95.10 228

UGNet		91.71 84	94.43 68	88.53 139	92.72 86	98.00 100	90.22 171	84.81 116	94.45 116	83.05 98	87.65 85	92.74 73	81.04 221	94.51 130	94.45 120	99.32 128	99.21 109
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
thres100view900		91.69 85	91.52 107	91.88 70	91.61 93	98.89 70	95.49 69	86.96 69	93.24 129	80.82 132	87.90 80	71.15 190	96.88 54	96.00 94	93.51 141	99.51 70	99.95 14

E2		91.67 86	91.90 104	91.41 80	90.00 140	98.06 96	93.59 107	85.55 84	93.75 122	84.70 76	82.50 125	77.16 136	95.17 76	96.33 82	96.16 76	99.46 85	99.35 95

CLD-MVS		91.67 86	91.30 113	92.10 68	91.25 102	96.59 147	95.93 61	87.25 68	96.86 78	85.55 69	87.08 88	73.01 177	93.26 123	93.07 156	92.84 155	99.34 122	99.68 54
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ET-MVSNet_ETH3D		91.59 88	94.96 67	87.65 142	72.75 255	97.24 135	95.29 73	82.73 136	96.81 79	78.49 148	95.30 42	90.48 89	97.23 41	91.60 177	94.31 121	99.43 97	99.01 133

tfpn200view9		91.47 89	91.31 111	91.65 73	91.61 93	98.69 76	95.03 79	86.17 76	93.24 129	80.82 132	87.90 80	71.15 190	96.80 56	95.53 111	92.82 157	99.47 79	99.88 30

Casviewmamba		91.42 90	91.45 110	91.38 81	90.16 130	97.86 106	94.22 93	85.43 94	95.30 101	84.02 87	79.08 142	76.50 140	95.02 81	96.70 71	95.91 85	99.45 91	98.80 142

CANet_DTU		91.36 91	95.75 57	86.23 155	92.31 90	98.71 75	95.60 68	78.41 173	98.20 50	56.48 229	94.38 50	87.96 97	95.11 78	96.89 63	96.07 77	99.48 77	98.01 180

thres200		91.36 91	91.19 115	91.55 75	91.60 95	98.69 76	94.98 80	86.17 76	92.16 150	80.76 136	87.66 84	71.15 190	96.35 62	95.53 111	93.23 147	99.47 79	99.92 25

FMVSNet3		91.25 93	92.13 102	90.21 114	85.64 185	93.14 193	95.29 73	80.09 159	96.40 83	85.74 66	77.13 153	86.81 103	94.98 83	97.19 57	97.11 45	99.55 64	97.13 201

thres400		91.24 94	91.01 124	91.50 79	91.56 96	98.77 72	94.66 87	86.41 74	91.87 156	80.56 137	87.05 90	71.01 193	96.35 62	95.67 103	92.82 157	99.48 77	99.88 30

PVSNet_Blended_VisFu		91.20 95	92.89 96	89.23 134	93.41 77	98.61 81	89.80 173	85.39 97	92.84 139	82.80 102	74.21 177	91.38 84	84.64 195	97.22 55	96.04 80	99.34 122	99.93 20

viewcassd2359sk11		91.16 96	91.10 122	91.23 86	89.96 143	97.99 101	93.45 113	85.49 86	92.46 147	84.03 86	80.13 134	75.86 148	94.99 82	95.98 95	96.00 81	99.44 95	99.29 100

DCV-MVSNet		91.15 97	92.00 103	90.17 118	90.78 112	92.23 210	93.70 104	81.17 153	95.16 104	82.98 99	89.46 74	83.31 117	93.98 116	91.79 176	92.87 152	98.41 203	99.18 113

DI_MVS_pp		91.11 98	91.47 108	90.68 102	90.01 139	97.77 112	95.87 65	83.56 130	94.72 110	82.12 115	68.46 200	87.46 98	93.07 127	96.46 78	95.73 94	99.47 79	99.71 49

hybridcas		91.06 99	90.80 127	91.36 82	90.05 135	97.82 107	94.34 88	85.32 99	94.61 112	84.46 78	77.14 152	75.28 153	94.53 97	96.52 75	95.42 107	99.46 85	98.84 140

diffmvs		91.05 100	91.15 116	90.93 94	90.15 131	97.79 109	94.05 96	85.45 91	95.63 98	81.95 119	80.45 133	73.01 177	94.47 99	95.56 108	95.89 87	99.49 74	99.72 47
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet (Re-imp)		91.05 100	94.43 68	87.11 144	91.05 106	97.99 101	92.53 146	83.82 127	92.71 143	76.28 154	84.50 114	92.43 76	79.52 226	97.24 54	97.68 28	99.43 97	98.45 160

thres600view7		90.97 102	90.70 131	91.30 84	91.53 97	98.69 76	94.33 89	86.17 76	91.75 158	80.19 139	86.06 101	70.90 194	96.10 67	95.53 111	92.08 168	99.47 79	99.86 34

viewdifsd2359ckpt09		90.94 103	91.04 123	90.82 97	89.85 149	97.92 105	93.33 121	85.35 98	92.89 136	81.87 121	79.68 137	75.67 151	95.08 79	96.17 86	95.76 92	99.42 100	99.20 111

baseline2		90.91 104	94.40 71	86.84 147	87.54 176	96.83 143	89.95 172	79.22 167	96.00 93	77.04 152	88.68 75	89.73 91	88.01 180	96.35 81	93.51 141	99.29 132	99.68 54

hybrid		90.90 105	91.12 119	90.63 107	90.26 127	97.66 127	92.76 136	85.22 108	96.34 86	82.32 112	81.25 129	73.73 169	93.86 117	93.70 148	95.69 98	99.38 108	99.50 79

onestephybrid01		90.88 106	90.91 126	90.85 95	90.31 125	97.71 120	92.72 140	85.46 90	95.97 96	83.61 92	78.95 143	75.19 154	93.62 120	93.08 155	95.68 99	99.37 110	99.79 38

hybridnocas07		90.86 107	90.94 125	90.76 100	90.34 123	97.71 120	93.08 129	85.27 104	96.19 90	82.38 111	81.06 130	73.79 168	94.13 110	92.73 164	95.63 101	99.38 108	99.43 87

casdiffmvs_mvg		90.83 108	90.52 135	91.20 88	90.56 116	97.67 126	94.96 81	85.45 91	90.72 168	82.03 116	76.70 161	77.08 137	94.61 95	96.57 74	95.62 102	99.57 52	99.28 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmamba		90.78 109	90.80 127	90.77 99	90.34 123	97.68 125	93.09 128	85.20 109	96.57 80	81.81 122	80.08 135	74.29 165	94.77 89	92.01 172	95.53 106	99.39 107	99.44 86

ACMP	89.80 9	90.72 110	91.15 116	90.21 114	92.55 88	96.52 149	92.63 143	85.71 82	94.65 111	81.06 129	93.32 55	70.56 198	90.52 158	92.68 165	91.05 183	98.76 177	99.31 99
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
casdiffmvs		90.69 111	90.56 134	90.85 95	90.14 132	97.81 108	92.94 132	85.30 100	93.47 126	82.50 107	76.34 165	74.12 166	94.67 90	96.51 76	96.26 70	99.55 64	99.42 88
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
FA-MVS(training)		90.67 112	93.03 93	87.92 141	90.95 108	98.45 87	92.61 145	66.04 244	94.90 106	84.47 77	77.52 151	91.74 80	94.07 111	97.11 59	92.46 165	99.40 105	99.03 130

viewmanbaseed2359cas		90.60 113	90.74 130	90.44 109	90.21 129	98.01 99	93.39 116	85.57 83	92.53 146	79.63 143	78.77 144	74.90 158	94.37 106	95.55 109	96.19 73	99.45 91	99.20 111

E3new		90.58 114	90.21 143	91.01 90	89.89 148	97.93 103	93.35 120	85.40 96	90.82 167	83.22 96	77.64 149	74.60 160	94.80 87	95.38 119	95.85 88	99.37 110	99.23 104

ACMM	89.40 10	90.58 114	90.02 146	91.23 86	93.30 79	94.75 175	90.69 167	88.22 59	95.20 102	82.70 104	88.54 76	71.40 188	93.48 122	93.64 150	90.94 184	98.99 159	95.72 223
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E3		90.56 116	90.22 142	90.96 93	89.90 147	97.93 103	93.37 117	85.41 95	90.85 166	82.94 101	77.63 150	74.66 159	94.78 88	95.39 118	95.84 90	99.37 110	99.23 104

GBi-Net		90.49 117	91.12 119	89.75 125	84.99 189	92.73 198	93.94 98	80.09 159	96.40 83	85.74 66	77.13 153	86.81 103	94.42 100	94.12 136	93.73 130	99.35 118	96.90 205

test1		90.49 117	91.12 119	89.75 125	84.99 189	92.73 198	93.94 98	80.09 159	96.40 83	85.74 66	77.13 153	86.81 103	94.42 100	94.12 136	93.73 130	99.35 118	96.90 205

viewdifsd2359ckpt13		90.44 119	90.52 135	90.35 112	89.94 145	98.06 96	92.84 133	85.47 87	92.33 149	79.93 141	77.99 145	74.39 163	94.49 98	96.09 89	95.76 92	99.44 95	99.03 130

diffmvs_AUTHOR		90.43 120	90.26 141	90.64 104	90.00 140	97.72 118	93.72 103	85.18 110	94.49 115	81.20 128	77.72 146	71.57 185	94.30 107	94.78 126	95.85 88	99.42 100	99.66 56

viewdifsd2359ckpt07		90.42 121	90.45 138	90.39 111	90.14 132	97.76 114	93.31 122	85.51 85	91.60 160	80.95 130	77.01 157	76.13 147	93.04 128	96.50 77	95.66 100	99.41 103	98.48 158

ECVR-MVS		90.37 122	88.96 163	92.01 69	92.76 84	99.20 64	94.67 85	86.82 72	92.58 144	86.71 53	68.95 199	71.46 187	91.69 145	96.85 65	96.33 67	99.45 91	97.38 194

LGP-MVS_train		90.34 123	91.63 106	88.83 138	93.31 78	96.14 156	95.49 69	85.24 106	93.91 120	68.71 175	93.96 51	71.63 184	91.12 154	93.82 145	92.79 159	99.07 153	99.16 116

viewmambaseed2359dif		90.29 124	89.69 148	90.98 92	90.03 136	97.61 129	93.96 97	85.18 110	93.22 131	82.97 100	76.79 159	74.32 164	94.41 103	91.14 183	95.02 111	99.33 127	99.74 43

test1111		90.01 125	88.67 168	91.57 74	92.68 87	99.20 64	94.25 92	86.90 71	92.03 153	85.04 72	67.79 204	71.21 189	91.12 154	96.83 67	96.34 66	99.42 100	97.28 197

dtuplus		89.91 126	89.13 158	90.82 97	89.75 154	97.55 130	93.24 123	85.10 112	91.04 164	82.64 105	75.46 169	74.51 162	94.91 85	90.75 186	94.99 113	99.29 132	99.60 67

E5new		89.87 127	89.21 156	90.64 104	89.76 151	97.78 110	93.37 117	85.47 87	88.83 180	81.32 125	75.36 170	73.09 174	94.63 91	94.54 128	95.71 96	99.29 132	99.17 114

E5		89.87 127	89.21 156	90.64 104	89.76 151	97.78 110	93.37 117	85.47 87	88.83 180	81.32 125	75.36 170	73.09 174	94.63 91	94.54 128	95.71 96	99.29 132	99.17 114

EPNet_dtu		89.82 129	94.18 77	84.74 165	96.87 57	95.54 168	92.65 142	86.91 70	96.99 73	54.17 240	92.41 62	88.54 93	78.35 229	96.15 88	96.05 79	99.47 79	93.60 237
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
RPSCF		89.81 130	89.75 147	89.88 122	93.22 81	93.99 186	94.78 82	85.23 107	94.01 119	82.52 106	95.00 45	87.23 100	92.01 140	85.16 239	83.48 245	91.54 262	89.38 255

E4		89.71 131	89.07 160	90.45 108	89.76 151	97.77 112	93.15 126	85.26 105	88.58 185	80.86 131	74.87 173	73.08 176	94.38 105	94.44 131	95.61 104	99.29 132	99.14 117

MDTV_nov1_ep13		89.63 132	94.38 72	84.09 173	88.76 168	97.53 133	89.37 181	68.46 242	96.95 74	70.27 170	87.88 82	93.67 71	91.04 156	93.12 153	93.83 129	96.62 238	97.68 187

UA-Net		89.56 133	93.03 93	85.52 161	92.46 89	97.55 130	91.92 150	81.91 141	85.24 204	71.39 165	83.57 120	96.56 49	76.01 240	96.81 68	97.04 50	99.46 85	94.41 232

E6new		89.53 134	88.95 164	90.21 114	89.75 154	97.74 116	92.76 136	84.66 119	88.63 183	80.77 134	74.83 174	72.74 180	94.07 111	94.20 133	95.39 108	99.27 140	99.10 124

E6		89.53 134	88.95 164	90.21 114	89.75 154	97.74 116	92.76 136	84.66 119	88.63 183	80.77 134	74.83 174	72.74 180	94.07 111	94.20 133	95.39 108	99.27 140	99.10 124

FMVSNet2		89.51 136	89.63 149	89.38 131	84.99 189	92.73 198	93.94 98	79.28 166	93.73 123	84.28 82	69.36 197	82.32 120	94.42 100	96.16 87	96.22 72	99.35 118	96.90 205

0.3-1-1-0.015		89.49 137	89.45 152	89.53 127	81.16 219	94.36 183	93.56 110	84.71 117	93.21 132	86.01 57	85.38 108	76.34 141	94.39 104	85.97 232	92.53 164	97.35 232	98.35 164

CostFormer		89.42 138	91.67 105	86.80 149	89.99 142	96.33 152	90.75 165	64.79 246	95.17 103	83.62 91	86.20 99	82.15 122	92.96 129	89.22 202	92.94 150	98.68 185	99.65 57

0.4-1-1-0.2		89.40 139	89.35 154	89.46 130	81.13 220	94.37 182	93.62 106	84.58 121	93.20 133	85.95 63	84.67 110	76.32 145	94.14 109	85.99 231	92.56 163	97.36 231	98.35 164

FC-MVSNet-train		89.37 140	89.62 150	89.08 135	90.48 118	94.16 185	89.45 177	83.99 126	91.09 163	80.09 140	82.84 124	74.52 161	91.44 151	93.79 146	91.57 174	99.01 157	99.35 95

OPM-MVS		89.33 141	87.45 180	91.53 77	94.49 73	96.20 154	96.47 60	89.72 51	82.77 211	75.43 155	80.53 132	70.86 196	93.80 118	94.00 140	91.85 172	99.29 132	95.91 217
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
viewmacassd2359aftdt		89.31 142	88.92 166	89.76 124	89.95 144	97.76 114	93.06 130	85.30 100	88.99 179	77.33 151	73.96 179	73.12 173	93.55 121	93.79 146	95.80 91	99.36 116	99.02 132

test-LLR		89.31 142	93.60 84	84.30 169	88.08 172	96.98 139	88.10 187	78.00 174	94.83 107	62.43 202	84.29 117	90.96 85	89.70 165	95.63 105	92.86 153	99.51 70	99.64 59

EPMVS		89.31 142	93.70 81	84.18 171	91.10 105	98.10 95	89.17 183	62.71 250	96.24 87	70.21 172	86.46 96	92.37 77	92.79 132	91.95 174	93.59 140	99.10 150	97.19 198

0.4-1-1-0.1		89.28 145	89.22 155	89.36 132	81.12 221	94.34 184	93.49 111	84.24 124	93.17 134	85.92 64	84.41 115	76.32 145	94.04 115	85.88 234	92.10 167	97.33 233	98.32 166

Anonymous20231211		89.22 146	87.56 178	91.16 89	90.23 128	96.62 146	93.22 125	85.44 93	92.89 136	84.37 80	60.13 228	81.25 125	96.02 69	90.61 187	92.01 169	97.70 224	99.41 91

Effi-MVS+		88.96 147	91.13 118	86.43 153	89.12 164	97.62 128	93.15 126	75.52 200	93.90 121	66.40 181	86.23 98	70.51 199	95.03 80	95.88 96	94.28 122	99.37 110	99.51 77

SCA		88.76 148	94.29 75	82.30 192	89.33 162	96.81 144	87.68 189	61.52 256	96.95 74	64.68 192	88.35 77	94.80 55	91.58 148	92.23 167	93.21 148	98.99 159	97.70 186

test0.0.03 1		88.71 149	92.22 101	84.63 167	88.08 172	94.71 177	85.91 212	78.00 174	95.54 99	72.96 159	86.10 100	85.88 108	83.59 207	92.95 161	93.24 146	99.25 144	97.09 202

PatchmatchNet		88.67 150	94.10 78	82.34 191	89.38 161	97.72 118	87.24 195	62.18 254	97.00 72	64.79 191	87.97 79	94.43 60	91.55 149	91.21 182	92.77 160	98.90 164	97.60 190
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
dps		88.66 151	90.19 144	86.88 146	89.94 145	96.48 150	89.56 175	64.08 248	94.12 118	89.00 40	83.39 121	82.56 119	90.16 162	86.81 227	89.26 203	98.53 198	98.71 146

TESTMET0.1,1		88.63 152	93.60 84	82.84 186	84.07 197	96.98 139	88.10 187	73.22 221	94.83 107	62.43 202	84.29 117	90.96 85	89.70 165	95.63 105	92.86 153	99.51 70	99.64 59

CHOSEN 1792x2688		88.63 152	89.01 161	88.19 140	94.83 70	99.21 63	92.66 141	79.85 163	92.40 148	72.18 164	56.38 249	80.22 130	90.24 160	97.64 48	97.28 42	99.37 110	99.94 17

CDS-MVSNet		88.59 154	90.13 145	86.79 150	86.98 181	95.43 169	92.03 148	81.33 151	85.54 201	74.51 158	77.07 156	85.14 111	87.03 185	93.90 143	95.18 110	98.88 167	98.67 149
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewdifsd2359ckpt11		88.57 155	87.77 176	89.51 128	89.74 157	95.73 164	91.01 162	85.05 114	92.88 138	82.40 110	77.72 146	70.86 196	92.86 130	87.17 218	91.36 180	95.98 253	98.64 150

viewmsd2359difaftdt		88.57 155	87.76 177	89.51 128	89.74 157	95.73 164	91.01 162	85.05 114	92.79 140	82.43 109	77.72 146	70.90 194	92.85 131	87.16 219	91.37 179	95.98 253	98.64 150

casdiffseed414692147		88.35 157	86.99 183	89.95 121	89.67 159	97.32 134	92.02 149	84.43 123	87.86 187	80.50 138	69.80 195	67.01 206	93.79 119	93.52 151	94.70 119	99.30 131	98.70 147

IB-MVS	84.67 14	88.34 158	90.61 133	85.70 158	92.99 83	98.62 80	78.85 244	86.07 79	94.35 117	88.64 41	85.99 102	75.69 150	68.09 256	88.21 206	91.43 176	99.55 64	99.96 11
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		88.25 159	93.27 91	82.38 190	83.89 198	96.86 142	87.10 199	72.80 223	94.58 113	61.85 207	83.21 122	90.65 88	89.18 169	95.43 116	92.58 162	99.46 85	99.61 66

COLMAP_ROB	84.42 15	88.24 160	87.32 182	89.32 133	95.83 64	95.82 160	92.81 134	87.68 65	92.09 152	72.64 162	72.34 186	79.96 131	88.79 171	89.54 197	89.46 199	98.16 213	92.00 244
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
IterMVS-LS		87.95 161	89.40 153	86.26 154	88.79 167	90.93 225	91.23 158	76.05 197	90.87 165	71.07 167	75.51 168	81.18 126	91.21 153	94.11 139	95.01 112	99.20 147	98.23 170
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		87.86 162	88.25 171	87.40 143	94.67 71	98.54 83	90.33 170	76.51 196	89.60 177	70.89 168	51.43 260	85.69 109	92.79 132	96.59 73	95.96 83	99.22 146	99.94 17

Vis-MVSNet		87.60 163	91.31 111	83.27 181	89.14 163	98.04 98	90.35 169	79.42 164	87.23 189	66.92 179	79.10 141	84.63 113	74.34 248	95.81 98	96.06 78	99.46 85	98.32 166
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GeoE		87.55 164	88.17 172	86.82 148	88.74 169	96.32 153	92.75 139	74.93 205	90.13 173	72.73 160	69.47 196	74.03 167	92.51 137	93.99 141	93.62 138	99.29 132	99.59 68

dmvs_re		87.43 165	87.99 173	86.77 151	84.94 193	96.19 155	91.87 151	85.95 81	91.25 162	68.58 176	81.45 127	66.04 209	89.95 164	90.91 184	91.57 174	99.37 110	98.54 155

RPMNet		87.35 166	92.41 99	81.45 196	88.85 166	96.06 157	89.42 180	59.59 263	93.57 124	61.81 208	76.48 164	91.48 83	90.18 161	96.32 83	93.37 144	98.87 168	99.59 68

tpm cat1		87.34 167	88.52 170	85.95 156	89.83 150	95.80 161	90.73 166	64.91 245	92.99 135	82.21 114	71.19 192	82.68 118	90.13 163	86.38 228	90.87 186	97.90 221	99.74 43

MS-PatchMatch		87.19 168	88.59 169	85.55 160	93.15 82	96.58 148	92.35 147	74.19 213	91.97 155	70.33 169	71.42 190	85.89 107	84.28 197	93.12 153	89.16 205	99.00 158	91.99 245

Effi-MVS+-dtu		87.18 169	90.48 137	83.32 180	86.51 182	95.76 163	91.16 161	74.28 212	90.44 172	61.31 211	86.72 94	72.68 182	91.25 152	95.01 123	93.64 133	95.45 255	99.12 121

FMVSNet5		87.06 170	89.52 151	84.20 170	79.92 240	86.57 255	87.11 198	72.37 225	96.06 91	75.41 156	84.33 116	91.76 79	91.60 147	91.51 178	91.22 181	98.77 174	85.16 261

Fast-Effi-MVS+-dtu		86.94 171	91.27 114	81.89 193	86.27 183	95.06 170	90.68 168	68.93 239	91.76 157	57.18 227	89.56 73	75.85 149	89.19 168	94.56 127	92.84 155	99.07 153	99.23 104

Fast-Effi-MVS+		86.94 171	87.88 175	85.84 157	86.99 180	95.80 161	91.24 157	73.48 220	92.75 141	69.22 173	72.70 184	65.71 210	94.84 86	94.98 124	94.71 117	99.26 142	98.48 158

tpmrst		86.78 173	90.29 139	82.69 187	90.55 117	96.95 141	88.49 185	62.58 251	95.09 105	63.52 198	76.67 163	84.00 116	92.05 139	87.93 209	91.89 171	98.98 161	99.50 79

CR-MVSNet		86.73 174	91.47 108	81.20 199	88.56 170	96.06 157	89.43 178	61.37 257	93.57 124	60.81 213	72.89 183	88.85 92	88.13 178	96.03 91	93.64 133	98.89 166	99.22 107

ADS-MVSNet		86.68 175	90.79 129	81.88 194	90.38 121	96.81 144	86.90 200	60.50 261	96.01 92	63.93 195	81.67 126	84.72 112	90.78 157	87.03 221	91.67 173	98.77 174	97.63 189

blend_shiyan4		86.12 176	85.60 192	86.72 152	81.42 213	88.06 244	93.87 102	77.81 182	93.43 127	86.01 57	85.86 103	76.34 141	84.87 192	81.26 250	78.21 252	96.36 241	96.04 213

dtuonly		85.87 177	87.38 181	84.10 172	85.14 188	94.42 181	91.20 159	78.74 172	86.23 196	59.39 221	68.98 198	76.54 139	91.83 144	93.48 152	94.00 127	98.31 210	98.03 179

FMVSNet1		85.85 178	84.91 195	86.96 145	82.70 203	91.39 219	91.54 154	77.45 186	85.29 203	79.56 144	60.70 225	72.68 182	92.37 138	94.12 136	93.73 130	98.12 214	96.44 209

FC-MVSNet-test		85.51 179	89.08 159	81.35 197	85.31 187	93.35 189	87.65 190	77.55 184	90.01 175	64.07 194	79.63 139	81.83 124	74.94 245	92.08 170	90.83 188	98.55 195	95.81 218

ACMH	85.22 13	85.40 180	85.73 191	85.02 163	91.76 92	94.46 180	84.97 224	81.54 149	85.18 205	65.22 187	76.92 158	64.22 216	88.58 174	90.17 189	90.25 195	98.03 217	98.90 138
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		85.35 181	86.00 190	84.59 168	84.97 192	95.57 167	88.98 184	77.29 191	81.44 216	71.36 166	71.48 189	75.00 157	87.03 185	91.92 175	92.21 166	97.92 220	94.40 233

ACMH+	85.62 12	85.27 182	84.96 194	85.64 159	90.84 110	94.78 174	87.46 192	81.30 152	86.94 190	67.35 178	74.56 176	64.09 217	88.70 172	88.14 207	89.00 206	98.22 212	97.19 198

USDC		85.11 183	85.35 193	84.83 164	89.45 160	94.93 173	92.98 131	77.30 189	90.53 170	61.80 209	76.69 162	59.62 228	88.90 170	92.78 163	90.79 190	98.53 198	92.12 242

IterMVS		85.02 184	88.98 162	80.41 205	87.03 179	90.34 233	89.78 174	69.45 236	89.77 176	54.04 241	73.71 180	82.05 123	83.44 210	95.11 121	93.64 133	98.75 178	98.22 172
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		84.91 185	88.90 167	80.25 208	87.04 178	90.27 234	89.23 182	69.25 238	89.17 178	54.04 241	73.65 181	82.22 121	83.23 215	95.11 121	93.63 137	98.73 179	98.23 170

PatchT		84.89 186	90.67 132	78.13 233	87.83 175	94.99 172	72.46 259	60.22 262	91.74 159	60.81 213	72.16 187	86.95 101	88.13 178	96.03 91	93.64 133	99.36 116	99.22 107

pmmvs4		84.88 187	84.67 196	85.13 162	82.80 202	92.37 203	87.29 193	79.08 168	90.51 171	74.94 157	70.37 193	62.49 220	88.17 177	92.01 172	88.51 211	98.49 201	96.44 209

usedtu_dtu_shiyan1		84.68 188	86.53 186	82.52 188	74.54 251	93.47 188	88.46 186	81.15 154	90.11 174	66.48 180	69.83 194	73.29 172	85.61 188	93.85 144	90.47 193	98.90 164	94.73 231

CVMVSNet		84.01 189	86.91 184	80.61 203	88.39 171	93.29 190	86.06 208	82.29 138	83.13 209	54.29 237	72.68 185	79.59 132	75.11 244	91.23 181	92.91 151	97.54 229	95.58 225

tpm		83.97 190	87.97 174	79.31 218	87.35 177	93.21 192	86.00 210	61.90 255	90.69 169	54.01 243	79.42 140	75.61 152	88.65 173	87.18 217	90.48 192	97.95 219	99.21 109

GA-MVS		83.83 191	86.63 185	80.58 204	85.40 186	94.73 176	87.27 194	78.76 171	86.49 192	49.57 255	74.21 177	67.67 204	83.38 211	95.28 120	90.92 185	99.08 152	97.09 202

UniMVSNet_NR-MVSNet		83.83 191	83.70 199	83.98 174	81.41 214	92.56 202	86.54 203	82.96 134	85.98 198	66.27 182	66.16 208	63.63 218	87.78 182	87.65 212	90.81 189	98.94 162	99.13 119

usedtu_blend_shiyan5		83.68 193	83.60 200	83.79 176	64.08 260	87.81 245	93.63 105	77.82 178	79.98 229	86.01 57	85.86 103	76.34 141	84.87 192	81.05 252	78.09 253	96.30 242	96.04 213

UniMVSNet (Re)		83.28 194	83.16 202	83.42 179	81.93 208	93.12 194	86.27 206	80.83 155	85.88 199	68.23 177	64.56 216	60.58 222	84.25 198	89.13 203	89.44 201	99.04 156	99.40 92

thisisatest0515		83.17 195	86.49 187	79.30 219	82.04 206	93.12 194	78.70 245	77.92 176	86.43 193	63.05 199	74.91 172	73.01 177	75.56 243	92.10 169	88.05 224	98.50 200	97.76 184

FE-MVSNET3		83.03 196	83.56 201	82.42 189	64.08 260	87.81 245	85.44 217	77.82 178	79.99 227	86.01 57	85.86 103	76.34 141	84.87 192	81.05 252	78.09 253	96.30 242	95.79 221

TinyColmap		83.03 196	82.24 206	83.95 175	88.88 165	93.22 191	89.48 176	76.89 193	87.53 188	62.12 204	68.46 200	55.03 244	88.43 176	90.87 185	89.65 197	97.89 222	90.91 249

testgi		82.88 198	86.14 189	79.08 221	86.05 184	92.20 211	81.23 241	74.77 208	88.70 182	57.63 226	86.73 93	61.53 221	76.83 237	90.33 188	89.43 202	97.99 218	94.05 234

DU-MVS		82.87 199	82.16 207	83.70 178	80.77 227	92.24 207	86.54 203	81.91 141	86.41 194	66.27 182	63.95 217	55.66 242	87.78 182	86.83 224	90.86 187	98.94 162	99.13 119

MIMVSNet		82.87 199	86.17 188	79.02 222	77.23 248	92.88 197	84.88 225	60.62 260	86.72 191	64.16 193	73.58 182	71.48 186	88.51 175	94.14 135	93.50 143	98.72 181	90.87 251

NR-MVSNet		82.37 201	81.95 209	82.85 185	82.56 205	92.24 207	87.49 191	81.91 141	86.41 194	65.51 185	63.95 217	52.93 253	80.80 223	89.41 199	89.61 198	98.85 170	99.10 124

Baseline_NR-MVSNet		82.08 202	80.64 216	83.77 177	80.77 227	88.50 241	86.88 201	81.71 146	85.58 200	68.80 174	58.20 240	57.75 234	86.16 187	86.83 224	88.68 208	98.33 208	98.90 138

TranMVSNet+NR-MVSNet		82.07 203	81.36 212	82.90 184	80.43 233	91.39 219	87.16 197	82.75 135	84.28 207	62.98 200	62.28 223	56.01 241	85.30 191	86.06 230	90.69 191	98.80 171	98.80 142

pm-mvs1		81.68 204	81.70 210	81.65 195	82.61 204	92.26 206	85.54 216	78.95 169	76.29 247	63.81 196	58.43 239	66.33 207	80.63 224	92.30 166	89.93 196	98.37 207	96.39 211

TDRefinement		81.49 205	80.08 222	83.13 183	91.02 107	94.53 178	91.66 153	82.43 137	81.70 214	62.12 204	62.30 222	59.32 229	73.93 249	87.31 215	85.29 235	97.61 225	90.14 253

anonymousdsp		81.29 206	84.52 198	77.52 235	79.83 241	92.62 201	82.61 236	70.88 232	80.76 220	50.82 250	68.35 202	68.76 202	82.45 218	93.00 157	89.45 200	98.55 195	98.69 148

gg-mvs-nofinetune		81.27 207	84.65 197	77.32 236	87.96 174	98.48 86	95.64 67	56.36 266	59.35 270	32.80 274	47.96 264	92.11 78	91.49 150	98.12 28	97.00 52	99.65 28	99.56 73

tfpnnormal		81.11 208	79.33 230	83.19 182	84.23 195	92.29 205	86.76 202	82.27 139	72.67 253	62.02 206	56.10 251	53.86 250	85.35 190	92.06 171	89.23 204	98.49 201	99.11 123

UniMVSNet_ETH3D		80.95 209	77.71 243	84.74 165	84.45 194	93.11 196	86.45 205	79.97 162	75.21 249	70.22 171	51.24 261	50.26 259	89.55 167	84.47 241	91.12 182	97.81 223	98.53 156

V42		80.88 210	80.74 214	81.05 200	81.21 218	92.01 213	85.96 211	77.75 183	81.62 215	59.73 220	59.93 231	58.35 233	82.98 217	86.90 223	88.06 223	98.69 184	98.32 166

v2v482		80.86 211	80.52 220	81.25 198	80.79 226	91.85 214	85.68 214	78.78 170	81.05 217	58.09 224	60.46 226	56.08 239	85.45 189	87.27 216	88.53 210	98.73 179	98.38 163

v8		80.61 212	80.61 218	80.62 202	81.51 211	91.00 224	86.06 208	74.07 216	81.78 213	59.93 219	60.10 230	58.42 232	83.35 212	86.99 222	88.11 221	98.79 172	97.83 182

pmmvs5		80.48 213	81.43 211	79.36 217	81.50 212	92.24 207	82.07 239	74.08 215	78.10 240	55.86 232	67.72 205	54.35 247	83.91 206	92.97 158	88.65 209	98.77 174	96.01 215

v10		80.38 214	80.73 215	79.96 210	81.22 217	90.40 232	86.11 207	71.63 228	82.42 212	57.65 225	58.74 237	57.47 235	84.44 196	89.75 193	88.28 214	98.71 182	98.06 178

v1144		80.36 215	80.63 217	80.05 209	80.86 225	91.56 217	85.78 213	75.22 202	80.73 221	55.83 233	58.51 238	56.99 237	83.93 205	89.79 192	88.25 215	98.68 185	98.56 154

SixPastTwentyTwo		80.28 216	82.06 208	78.21 232	81.89 210	92.35 204	77.72 246	74.48 209	83.04 210	54.22 238	76.06 166	56.40 238	83.55 208	86.83 224	84.83 238	97.38 230	94.93 229

CP-MVSNet		79.90 217	79.49 227	80.38 206	80.72 229	90.83 226	82.98 233	75.17 203	79.70 233	61.39 210	59.74 232	51.98 256	83.31 213	87.37 214	88.38 212	98.71 182	98.45 160

v1192		79.84 218	80.05 224	79.61 213	80.49 232	91.04 223	85.56 215	74.37 211	80.73 221	54.35 236	57.07 245	54.54 246	84.23 199	89.94 190	88.38 212	98.63 189	98.61 152

WR-MVS_H		79.76 219	80.07 223	79.40 216	81.25 216	91.73 216	82.77 234	74.82 207	79.02 238	62.55 201	59.41 234	57.32 236	76.27 239	87.61 213	87.30 229	98.78 173	98.09 176

WR-MVS		79.67 220	80.25 221	79.00 223	80.65 230	91.16 221	83.31 231	76.57 195	80.97 218	60.50 218	59.20 235	58.66 231	74.38 247	85.85 235	87.76 226	98.61 190	98.14 173

v148		79.66 221	79.13 233	80.27 207	81.02 223	91.76 215	81.90 240	79.32 165	79.24 236	63.79 197	58.07 242	54.34 248	77.17 235	84.42 242	87.52 228	98.40 204	98.59 153

LTVRE_ROB	79.45 16	79.66 221	80.55 219	78.61 230	83.01 201	92.19 212	87.18 196	73.69 219	71.70 256	43.22 268	71.22 191	50.85 257	87.82 181	89.47 198	90.43 194	96.75 236	98.00 181
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
v144192		79.61 223	79.77 225	79.41 215	80.28 234	91.06 222	84.87 226	73.86 217	79.65 234	55.38 234	57.76 243	55.20 243	83.46 209	88.42 205	87.89 225	98.61 190	98.42 162

v1921920		79.55 224	79.77 225	79.30 219	80.24 235	90.77 228	85.37 221	73.75 218	80.38 223	53.78 244	56.89 247	54.18 249	84.05 203	89.55 196	88.13 220	98.59 192	98.52 157

TransMVSNet (Re)		79.51 225	78.36 239	80.84 201	83.17 199	89.72 236	84.22 229	81.45 150	73.98 252	60.79 216	57.20 244	56.05 240	77.11 236	89.88 191	88.86 207	98.30 211	92.83 239

MVS-HIRNet		79.34 226	82.56 203	75.57 241	84.11 196	95.02 171	75.03 254	57.28 265	85.50 202	55.88 231	53.00 257	70.51 199	83.05 216	92.12 168	91.96 170	98.09 215	89.83 254

PS-CasMVS		79.06 227	78.58 238	79.63 212	80.59 231	90.55 230	82.54 237	75.04 204	77.76 241	58.84 222	58.16 241	50.11 261	82.09 220	87.05 220	88.18 218	98.66 188	98.27 169

gbinet_0.2-2-1-0.02		79.05 228	79.33 230	78.73 227	64.88 258	87.74 251	85.16 223	77.52 185	79.51 235	66.15 184	64.75 215	66.08 208	82.42 219	81.26 250	78.24 251	96.25 248	97.75 185

v1240		78.97 229	79.27 232	78.63 229	80.04 236	90.61 229	84.25 228	72.95 222	79.22 237	52.70 246	56.22 250	52.88 255	83.28 214	89.60 195	88.20 217	98.56 194	98.14 173

pmnet_mix02		78.91 230	81.17 213	76.28 240	81.91 209	90.82 227	74.25 255	77.87 177	86.17 197	49.04 256	67.97 203	62.93 219	77.40 233	82.75 248	82.11 247	97.18 234	95.42 226

wanda-best-256-512		78.88 231	78.96 234	78.78 224	64.08 260	87.81 245	85.44 217	77.82 178	79.99 227	64.86 188	65.31 209	64.67 212	84.16 200	81.05 252	78.09 253	96.30 242	95.81 218

FE-blended-shiyan7		78.88 231	78.96 234	78.78 224	64.08 260	87.81 245	85.44 217	77.82 178	79.98 229	64.86 188	65.31 209	64.66 213	84.16 200	81.05 252	78.09 253	96.30 242	95.81 218

MDTV_nov1_ep13_2view		78.83 233	82.35 204	74.73 244	78.65 243	91.51 218	79.18 243	62.52 252	84.51 206	52.51 247	67.49 206	67.29 205	78.90 227	85.52 237	86.34 232	96.62 238	93.76 235

PEN-MVS		78.80 234	78.13 241	79.58 214	80.03 237	89.67 237	83.61 230	75.83 198	77.71 243	58.41 223	60.11 229	50.00 262	81.02 222	84.08 243	88.14 219	98.59 192	97.18 200

blended_shiyan8		78.78 235	78.79 237	78.77 226	64.07 264	87.81 245	85.39 220	77.38 188	79.94 231	65.37 186	64.85 213	64.30 215	84.14 202	80.95 257	77.97 258	96.26 247	95.72 223

blended_shiyan6		78.78 235	78.90 236	78.64 228	64.04 265	87.78 250	85.34 222	77.30 189	79.93 232	64.84 190	65.18 212	64.66 213	84.03 204	80.99 256	78.00 257	96.27 246	95.79 221

EG-PatchMatch MVS		78.32 237	79.42 229	77.03 238	83.03 200	93.77 187	84.47 227	69.26 237	75.85 248	53.69 245	55.68 252	60.23 226	73.20 251	89.69 194	88.22 216	98.55 195	92.54 240

DTE-MVSNet		77.92 238	77.42 244	78.51 231	79.34 242	89.00 239	83.05 232	75.60 199	76.89 245	56.58 228	59.63 233	50.31 258	78.09 232	82.57 249	87.56 227	98.38 205	95.95 216

v7n		77.71 239	78.25 240	77.09 237	78.49 244	90.55 230	82.15 238	71.11 231	76.79 246	54.18 239	55.63 253	50.20 260	78.28 230	89.36 201	87.15 230	98.33 208	98.07 177

gm-plane-assit		77.20 240	82.26 205	71.30 249	81.10 222	82.00 264	54.33 272	64.41 247	63.80 269	40.93 271	59.04 236	76.57 138	87.30 184	98.26 26	97.36 41	99.74 16	98.76 145

N_pmnet		76.83 241	77.97 242	75.50 242	80.96 224	88.23 243	72.81 257	76.83 194	80.87 219	50.55 251	56.94 246	60.09 227	75.70 241	83.28 246	84.23 240	96.14 251	92.12 242

pmmvs6		76.79 242	75.69 250	78.09 234	79.95 239	89.57 238	80.92 242	74.46 210	64.79 267	60.74 217	45.71 266	60.55 223	78.37 228	88.04 208	86.00 233	94.07 259	95.15 227

CMPMVS	58.73 17	76.78 243	74.27 251	79.70 211	93.26 80	95.58 166	82.74 235	77.44 187	71.46 259	56.29 230	53.58 256	59.13 230	77.33 234	79.20 258	79.71 250	91.14 264	81.24 264
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		76.76 244	79.47 228	73.60 245	79.99 238	87.47 253	77.39 247	75.43 201	77.62 244	47.83 259	64.78 214	60.44 224	64.80 257	86.28 229	86.53 231	96.17 250	93.19 238

PM-MVS		75.81 245	76.11 249	75.46 243	73.81 252	85.48 258	76.42 249	70.57 233	80.05 226	54.75 235	62.33 221	39.56 273	80.59 225	87.71 211	82.81 246	96.61 240	94.81 230

pmmvs-eth3d		75.17 246	74.09 252	76.43 239	72.92 253	84.49 260	76.61 248	72.42 224	74.33 250	61.28 212	54.71 255	39.42 274	78.20 231	87.77 210	84.25 239	97.17 235	93.63 236

dtuonlycased		75.07 247	76.40 247	73.51 246	75.65 249	87.67 252	72.62 258	71.52 229	78.23 239	52.32 248	63.34 219	65.19 211	73.66 250	73.36 260	75.24 260	95.31 256	91.75 246

Anonymous20231206		74.59 248	77.00 245	71.78 247	77.89 247	87.45 254	75.14 253	72.29 226	77.76 241	46.65 261	52.14 258	52.93 253	61.10 261	89.37 200	88.09 222	97.59 226	91.30 248

test20.03		72.81 249	76.24 248	68.80 252	78.31 245	85.40 259	71.04 260	71.20 230	71.85 255	43.40 267	65.31 209	54.71 245	51.27 265	85.92 233	84.18 242	97.58 227	86.35 260

test_method		71.90 250	76.72 246	66.28 257	60.87 268	78.37 267	69.75 265	49.81 271	83.44 208	49.63 254	47.13 265	53.23 252	76.38 238	91.32 180	85.76 234	91.22 263	97.77 183

new_pmnet		71.86 251	73.67 253	69.75 251	72.56 256	84.20 261	70.95 262	66.81 243	80.34 224	43.62 266	51.60 259	53.81 251	71.24 254	82.91 247	80.93 248	93.35 261	81.92 263

FE-MVSNET2		71.63 252	71.59 254	71.68 248	60.60 269	86.30 256	75.64 250	72.07 227	69.87 260	51.83 249	38.70 269	42.10 270	72.39 253	88.69 204	85.13 236	97.55 228	90.33 252

MDA-MVSNet-bldmvs		69.61 253	70.36 256	68.74 253	62.88 266	88.50 241	65.40 269	77.01 192	71.60 258	43.93 263	66.71 207	35.33 277	72.47 252	61.01 267	80.63 249	90.73 265	88.75 257

pmmvs3		69.04 254	70.75 255	67.04 255	66.83 257	78.54 266	64.99 270	60.92 259	64.67 268	40.61 272	55.08 254	40.29 271	74.89 246	83.76 244	84.01 243	93.98 260	88.88 256

MIMVSNet1		68.63 255	70.24 257	66.76 256	56.86 271	83.26 262	67.93 267	70.26 235	68.05 263	46.80 260	40.44 268	48.15 263	62.01 259	84.96 240	84.86 237	96.69 237	81.93 262

FE-MVSNET		68.01 256	70.02 258	65.66 258	53.56 272	81.28 265	68.74 266	70.37 234	67.27 264	42.26 270	42.17 267	42.41 269	62.95 258	85.18 238	83.97 244	96.09 252	87.90 259

GG-mvs-BLEND		67.99 257	97.35 42	33.72 267	1.22 282	99.72 21	98.30 40	0.57 278	97.61 67	1.18 284	93.26 56	96.63 48	1.74 280	97.15 58	97.14 44	99.34 122	99.96 11

new-patchmatchnet		67.66 258	68.07 259	67.18 254	72.85 254	82.86 263	63.09 271	68.61 241	66.60 265	42.64 269	49.28 262	38.68 276	61.21 260	75.84 259	75.22 261	94.67 258	88.00 258

FPMVS		63.27 259	61.31 263	65.57 259	78.25 246	74.42 271	75.23 252	68.92 240	72.33 254	43.87 264	49.01 263	43.94 266	48.64 267	61.15 266	58.81 268	78.51 272	69.49 270

usedtu_dtu_shiyan2		63.25 260	63.29 261	63.21 260	48.45 275	77.92 268	69.85 263	62.49 253	52.94 271	50.43 252	32.38 273	43.14 267	59.67 262	73.05 261	72.69 263	88.34 266	90.90 250

WB-MVS		56.28 261	63.25 262	48.16 264	75.24 250	65.97 272	39.91 276	74.13 214	69.25 261	10.01 280	62.67 220	44.05 265	20.71 278	70.43 264	69.57 264	68.94 274	60.78 277

Gipuma		54.59 262	53.98 264	55.30 261	59.03 270	52.63 274	47.17 274	56.08 267	71.68 257	37.54 273	20.90 277	19.00 280	52.33 264	71.69 263	75.20 262	79.64 271	66.79 272
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	49.05 18	51.88 263	50.56 267	53.42 262	64.21 259	43.30 276	42.64 275	62.93 249	50.56 272	43.72 265	37.44 270	42.95 268	35.05 270	58.76 269	54.58 269	71.95 273	66.33 273
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS2		50.69 264	52.33 265	48.78 263	51.24 273	64.81 273	47.91 273	53.79 270	44.95 273	21.75 275	29.98 274	25.90 279	31.98 272	59.95 268	65.37 266	86.00 269	75.36 267

E-PMN		37.15 265	34.82 271	39.86 265	47.53 276	35.42 278	23.79 278	55.26 268	35.18 276	14.12 277	17.38 280	14.13 283	39.73 269	32.24 274	46.98 270	58.76 275	62.39 276

VLMVS		36.50 266	51.93 266	18.49 269	8.29 278	18.63 280	21.97 281	1.28 276	80.28 225	13.73 278	86.62 95	39.25 275	26.38 275	37.23 272	34.66 273	39.31 278	66.86 271

EMVS		36.45 267	33.63 272	39.74 266	48.47 274	35.73 277	23.59 279	55.11 269	35.61 275	12.88 279	17.49 278	14.62 282	41.04 268	29.33 275	43.00 271	57.32 276	59.62 278

MVE	42.40 19	36.00 268	38.65 270	32.92 268	29.16 277	46.17 275	22.61 280	44.21 272	26.44 278	18.88 276	17.41 279	9.36 285	32.29 271	45.75 270	61.38 267	50.35 277	64.03 275
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS_CLIP		33.23 269	49.27 268	14.51 270	7.24 280	16.76 281	18.95 282	1.13 277	64.81 266	3.75 283	79.75 136	30.93 278	24.03 277	40.41 271	39.43 272	31.94 279	72.82 269

MVS_clip		31.49 270	46.47 269	14.02 271	7.61 279	20.07 279	14.19 284	1.32 275	69.07 262	5.31 281	61.95 224	39.87 272	30.11 273	35.49 273	33.84 274	25.57 280	64.99 274

testmvs		21.55 271	30.91 273	10.62 272	2.78 281	11.66 282	18.51 283	4.82 273	38.21 274	4.06 282	36.35 271	4.47 286	26.81 274	23.27 276	27.11 275	6.75 281	75.30 268

test123		16.81 272	24.80 274	7.48 273	0.82 283	8.38 283	11.92 285	2.60 274	28.96 277	1.12 285	28.39 276	1.26 287	24.51 276	8.93 278	22.19 276	3.90 282	75.49 266

MVS_baseline		11.06 273	19.10 275	1.69 274	0.69 284	3.26 284	0.76 286	0.00 279	23.46 279	0.00 286	29.43 275	15.04 281	8.33 279	16.25 277	14.60 277	0.37 283	31.63 279

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					99.49 2	99.75 20	99.67 3		99.40 6	83.23 95	96.42 37	98.41 31	99.44 2			99.69 23	99.10 124

PatchmatchNet2					81.28 215	88.61 240	73.12 256
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												60.37 225	75.66 242	83.46 245	84.21 241	96.20 249	92.20 241
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										50.13 253	56.56 248
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							99.36 18	96.46 1		99.32 1						99.83 4

TPM-MVS					99.50 1	99.78 15	99.69 2			88.49 42	97.88 30	98.84 26	99.42 3			99.76 12	97.44 192
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										46.54 262

9.14												99.73 11

SR-MVS					99.27 20			95.82 22				99.00 21

Anonymous202405211			87.54 179		90.72 113	97.10 138	93.40 115	85.30 100	91.41 161		60.23 227	80.69 129	95.80 73	91.33 179	92.60 161	98.38 205	99.40 92

our_test_3					81.94 207	90.26 235	75.39 251

ambc			64.61 260		61.80 267	75.31 270	71.00 261		74.16 251	48.83 257	36.02 272	13.22 284	58.66 263	85.80 236	76.26 259	88.01 267	91.53 247

MTAPA										94.58 18		98.56 28

MTMP										95.24 12		98.13 35

Patchmatch-RL test							37.05 277

tmp_tt				71.24 250	90.29 126	76.39 269	65.81 268	59.43 264	97.62 65	79.65 142	90.60 68	68.71 203	49.71 266	72.71 262	65.70 265	82.54 270

XVS					93.63 75	99.64 30	94.32 90			83.97 88		98.08 37				99.59 43

X-MVStestdata					93.63 75	99.64 30	94.32 90			83.97 88		98.08 37				99.59 43

mPP-MVS					98.66 33							97.11 45

NP-MVS									97.69 63

Patchmtry						95.86 159	89.43 178	61.37 257		60.81 213

DeepMVS_CX						85.88 257	69.83 264	81.56 148	87.99 186	48.22 258	71.85 188	45.52 264	68.67 255	63.21 265		86.64 268	80.03 265

High-resolution multi-view benchmark