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.

DVP-MVS++		98.92 1	99.18 1	98.61 4	99.47 5	99.61 2	99.39 3	97.82 1	98.80 1	96.86 8	98.90 2	99.92 1	98.67 17	99.02 2	98.20 20	99.43 48	99.82 1

SED-MVS		98.90 2	99.07 2	98.69 3	99.38 18	99.61 2	99.33 8	97.80 4	98.25 9	97.60 2	98.87 4	99.89 3	98.67 17	99.02 2	98.26 18	99.36 61	99.61 6

APDe-MVS		98.87 3	98.96 4	98.77 1	99.58 2	99.53 7	99.44 1	97.81 2	98.22 11	97.33 4	98.70 6	99.33 10	98.86 8	98.96 6	98.40 14	99.63 5	99.57 9
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		98.86 4	98.97 3	98.75 2	99.43 12	99.63 1	99.25 12	97.81 2	98.62 2	97.69 1	97.59 21	99.90 2	98.93 5	98.99 4	98.42 12	99.37 59	99.62 4
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 5	98.91 6	98.57 5	99.21 23	99.54 6	99.42 2	97.78 6	97.49 32	96.84 9	98.94 1	99.82 5	98.59 21	98.90 10	98.22 19	99.56 17	99.48 17
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		98.73 6	98.93 5	98.50 6	99.44 11	99.57 4	99.36 4	97.65 9	98.14 13	96.51 14	98.49 8	99.65 8	98.67 17	98.60 14	98.42 12	99.40 54	99.63 2
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 7	98.89 7	98.39 9	99.60 1	99.41 13	99.00 21	97.63 12	97.78 19	95.83 18	98.33 12	99.83 4	98.85 9	98.93 8	98.56 7	99.41 51	99.40 21
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 8	98.77 9	98.23 15	98.15 50	99.26 27	98.79 27	97.59 15	98.52 3	96.25 15	97.99 16	99.75 6	99.01 3	98.27 33	97.97 32	99.59 7	99.63 2
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 9	98.78 8	98.15 19	98.14 51	99.17 33	99.34 6	97.18 29	98.44 5	95.72 19	97.84 17	99.28 12	98.87 7	99.05 1	98.05 27	99.66 2	99.60 7
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 10	98.62 12	98.32 11	99.39 17	99.33 22	99.27 10	97.42 18	98.27 8	95.25 23	98.34 11	98.83 26	99.08 1	98.26 34	98.08 26	99.48 30	99.26 35

CNVR-MVS		98.47 11	98.46 17	98.48 7	99.40 14	99.05 37	99.02 19	97.54 16	97.73 20	96.65 11	97.20 30	99.13 20	98.85 9	98.91 9	98.10 24	99.41 51	99.08 57

ACMMPR		98.40 12	98.49 14	98.28 13	99.41 13	99.40 14	99.36 4	97.35 21	98.30 7	95.02 25	97.79 18	98.39 37	99.04 2	98.26 34	98.10 24	99.50 29	99.22 41

SF-MVS		98.39 13	98.45 18	98.33 10	99.45 9	99.05 37	98.27 37	97.65 9	97.73 20	97.02 7	98.18 13	99.25 15	98.11 32	98.15 39	97.62 48	99.45 38	99.19 45

SteuartSystems-ACMMP		98.38 14	98.71 11	97.99 23	99.34 20	99.46 11	99.34 6	97.33 24	97.31 36	94.25 30	98.06 14	99.17 19	98.13 31	98.98 5	98.46 10	99.55 18	99.54 11
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		98.36 15	98.32 24	98.41 8	99.47 5	99.26 27	99.12 15	97.77 7	96.73 50	96.12 16	97.27 29	98.88 24	98.46 25	98.47 19	98.39 15	99.52 22	99.22 41
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		98.34 16	98.47 16	98.18 16	99.46 8	99.15 34	99.10 16	97.69 8	97.67 25	94.93 26	97.62 20	99.70 7	98.60 20	98.45 21	97.46 53	99.31 68	99.26 35

CP-MVS		98.32 17	98.34 23	98.29 12	99.34 20	99.30 23	99.15 14	97.35 21	97.49 32	95.58 21	97.72 19	98.62 34	98.82 11	98.29 29	97.67 47	99.51 27	99.28 30

ACMMP_NAP		98.20 18	98.49 14	97.85 25	99.50 4	99.40 14	99.26 11	97.64 11	97.47 34	92.62 47	97.59 21	99.09 22	98.71 15	98.82 12	97.86 40	99.40 54	99.19 45

MCST-MVS		98.20 18	98.36 20	98.01 22	99.40 14	99.05 37	99.00 21	97.62 13	97.59 29	93.70 34	97.42 28	99.30 11	98.77 13	98.39 27	97.48 52	99.59 7	99.31 29

DeepC-MVS_fast	96.13 1	98.13 20	98.27 26	97.97 24	99.16 26	99.03 43	99.05 18	97.24 26	98.22 11	94.17 32	95.82 41	98.07 39	98.69 16	98.83 11	98.80 2	99.52 22	99.10 54
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 21	98.05 31	98.17 18	99.38 18	99.05 37	99.00 21	97.53 17	98.04 15	95.12 24	94.80 53	99.18 18	98.58 22	98.49 18	97.78 44	99.39 56	98.98 74

MP-MVS		98.09 22	98.30 25	97.84 26	99.34 20	99.19 32	99.23 13	97.40 19	97.09 44	93.03 40	97.58 23	98.85 25	98.57 23	98.44 23	97.69 46	99.48 30	99.23 39
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MSLP-MVS++		98.04 23	97.93 33	98.18 16	99.10 27	99.09 36	98.34 36	96.99 32	97.54 30	96.60 12	94.82 52	98.45 35	98.89 6	97.46 61	98.77 4	99.17 98	99.37 22

MVS_0304		97.94 24	98.72 10	97.02 36	98.48 43	99.50 9	99.02 19	94.06 47	98.33 6	94.51 27	98.78 5	97.73 43	96.60 69	98.51 16	98.68 5	99.45 38	99.53 12

X-MVS		97.84 25	98.19 28	97.42 30	99.40 14	99.35 18	99.06 17	97.25 25	97.38 35	90.85 63	96.06 38	98.72 30	98.53 24	98.41 25	98.15 23	99.46 34	99.28 30

PGM-MVS		97.81 26	98.11 29	97.46 29	99.55 3	99.34 21	99.32 9	94.51 45	96.21 64	93.07 37	98.05 15	97.95 42	98.82 11	98.22 37	97.89 39	99.48 30	99.09 56

CPTT-MVS		97.78 27	97.54 36	98.05 21	98.91 35	99.05 37	99.00 21	96.96 33	97.14 42	95.92 17	95.50 45	98.78 28	98.99 4	97.20 67	96.07 94	98.54 167	99.04 66

PHI-MVS		97.78 27	98.44 19	97.02 36	98.73 38	99.25 29	98.11 40	95.54 39	96.66 53	92.79 44	98.52 7	99.38 9	97.50 45	97.84 49	98.39 15	99.45 38	99.03 67

TSAR-MVS + ACMM		97.71 29	98.60 13	96.66 40	98.64 41	99.05 37	98.85 26	97.23 27	98.45 4	89.40 94	97.51 25	99.27 14	96.88 61	98.53 15	97.81 43	98.96 129	99.59 8

train_agg		97.65 30	98.06 30	97.18 33	98.94 32	98.91 56	98.98 25	97.07 31	96.71 51	90.66 70	97.43 27	99.08 23	98.20 27	97.96 46	97.14 64	99.22 87	99.19 45

AdaColmap		97.53 31	96.93 48	98.24 14	99.21 23	98.77 65	98.47 34	97.34 23	96.68 52	96.52 13	95.11 50	96.12 58	98.72 14	97.19 69	96.24 90	99.17 98	98.39 123

TSAR-MVS + GP.		97.45 32	98.36 20	96.39 42	95.56 87	98.93 53	97.74 49	93.31 54	97.61 28	94.24 31	98.44 10	99.19 17	98.03 35	97.60 56	97.41 55	99.44 45	99.33 26

CSCG		97.44 33	97.18 44	97.75 27	99.47 5	99.52 8	98.55 32	95.41 40	97.69 24	95.72 19	94.29 56	95.53 63	98.10 33	96.20 110	97.38 57	99.24 80	99.62 4

ACMMP		97.37 34	97.48 38	97.25 31	98.88 37	99.28 25	98.47 34	96.86 34	97.04 46	92.15 51	97.57 24	96.05 60	97.67 40	97.27 65	95.99 99	99.46 34	99.14 53
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 34	96.77 51	98.07 20	98.97 31	98.21 97	97.94 46	96.85 35	97.66 26	97.58 3	93.33 62	96.84 49	98.01 36	97.13 71	96.20 92	99.09 111	98.01 139
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator+	93.91 7	97.23 36	97.22 41	97.24 32	98.89 36	98.85 61	98.26 38	93.25 57	97.99 16	95.56 22	90.01 100	98.03 41	98.05 34	97.91 47	98.43 11	99.44 45	99.35 24

MVS_111021_LR		97.16 37	98.01 32	96.16 47	98.47 44	98.98 48	96.94 64	93.89 49	97.64 27	91.44 56	98.89 3	96.41 53	97.20 51	98.02 45	97.29 62	99.04 123	98.85 89

3Dnovator	93.79 8	97.08 38	97.20 42	96.95 38	99.09 28	99.03 43	98.20 39	93.33 53	97.99 16	93.82 33	90.61 95	96.80 50	97.82 37	97.90 48	98.78 3	99.47 33	99.26 35

MVS_111021_HR		97.04 39	98.20 27	95.69 55	98.44 46	99.29 24	96.59 80	93.20 58	97.70 23	89.94 84	98.46 9	96.89 48	96.71 65	98.11 42	97.95 34	99.27 75	99.01 70

SPE-MVS-test		97.00 40	97.85 34	96.00 51	97.77 56	99.56 5	96.35 89	91.95 76	97.54 30	92.20 50	96.14 37	96.00 61	98.19 28	98.46 20	97.78 44	99.57 14	99.45 19

DeepPCF-MVS	95.28 2	97.00 40	98.35 22	95.42 60	97.30 64	98.94 51	94.82 129	96.03 38	98.24 10	92.11 52	95.80 42	98.64 33	95.51 96	98.95 7	98.66 6	96.78 202	99.20 44

OMC-MVS		97.00 40	96.92 49	97.09 34	98.69 39	98.66 74	97.85 47	95.02 42	98.09 14	94.47 28	93.15 63	96.90 47	97.38 47	97.16 70	96.82 77	99.13 105	97.65 152

CNLPA		96.90 43	96.28 57	97.64 28	98.56 42	98.63 79	96.85 68	96.60 36	97.73 20	97.08 6	89.78 102	96.28 56	97.80 39	96.73 85	96.63 80	98.94 131	98.14 135

CS-MVS		96.87 44	97.41 40	96.24 46	97.42 61	99.48 10	97.30 56	91.83 82	97.17 40	93.02 41	94.80 53	94.45 67	98.16 30	98.61 13	97.85 41	99.69 1	99.50 13

DPM-MVS		96.86 45	96.82 50	96.91 39	98.08 52	98.20 98	98.52 33	97.20 28	97.24 39	91.42 57	91.84 79	98.45 35	97.25 50	97.07 72	97.40 56	98.95 130	97.55 155

CANet		96.84 46	97.20 42	96.42 41	97.92 54	99.24 31	98.60 30	93.51 52	97.11 43	93.07 37	91.16 87	97.24 46	96.21 78	98.24 36	98.05 27	99.22 87	99.35 24

CDPH-MVS		96.84 46	97.49 37	96.09 48	98.92 34	98.85 61	98.61 29	95.09 41	96.00 72	87.29 115	95.45 47	97.42 44	97.16 52	97.83 50	97.94 35	99.44 45	98.92 80

QAPM		96.78 48	97.14 45	96.36 43	99.05 29	99.14 35	98.02 43	93.26 55	97.27 38	90.84 66	91.16 87	97.31 45	97.64 43	97.70 54	98.20 20	99.33 63	99.18 48

DeepC-MVS	94.87 4	96.76 49	96.50 54	97.05 35	98.21 49	99.28 25	98.67 28	97.38 20	97.31 36	90.36 77	89.19 104	93.58 72	98.19 28	98.31 28	98.50 8	99.51 27	99.36 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EC-MVSNet		96.49 50	97.63 35	95.16 64	94.75 113	98.69 71	97.39 55	88.97 129	96.34 60	92.02 53	96.04 39	96.46 52	98.21 26	98.41 25	97.96 33	99.61 6	99.55 10

TAPA-MVS	94.18 5	96.38 51	96.49 55	96.25 44	98.26 48	98.66 74	98.00 44	94.96 43	97.17 40	89.48 91	92.91 67	96.35 54	97.53 44	96.59 91	95.90 102	99.28 72	97.82 143
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ETV-MVS		96.31 52	97.47 39	94.96 71	94.79 110	98.78 64	96.08 98	91.41 97	96.16 65	90.50 72	95.76 43	96.20 57	97.39 46	98.42 24	97.82 42	99.57 14	99.18 48

EPNet		96.27 53	96.97 47	95.46 59	98.47 44	98.28 94	97.41 53	93.67 50	95.86 77	92.86 43	97.51 25	93.79 71	91.76 151	97.03 74	97.03 67	98.61 163	99.28 30
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DELS-MVS		96.06 54	96.04 61	96.07 50	97.77 56	99.25 29	98.10 41	93.26 55	94.42 116	92.79 44	88.52 112	93.48 73	95.06 104	98.51 16	98.83 1	99.45 38	99.28 30
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 55	95.14 77	96.25 44	97.73 59	98.73 67	97.59 51	97.13 30	92.50 147	89.09 101	89.85 101	96.65 51	96.90 60	94.97 146	94.89 132	99.08 113	98.38 124
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EIA-MVS		95.50 56	96.19 59	94.69 82	94.83 109	98.88 60	95.93 104	91.50 93	94.47 115	89.43 92	93.14 64	92.72 77	97.05 57	97.82 52	97.13 65	99.43 48	99.15 51

MAR-MVS		95.50 56	95.60 65	95.39 61	98.67 40	98.18 100	95.89 107	89.81 117	94.55 114	91.97 54	92.99 65	90.21 91	97.30 49	96.79 82	97.49 51	98.72 153	98.99 72
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 56	95.22 75	95.82 54	98.98 30	98.97 49	97.67 50	93.04 62	94.64 112	89.18 99	84.44 150	94.79 65	96.79 62	97.23 66	97.61 49	99.24 80	98.88 85

CHOSEN 280x420		95.46 59	97.01 46	93.66 105	97.28 65	97.98 106	96.40 87	85.39 169	96.10 69	91.07 60	96.53 33	96.34 55	95.61 91	97.65 55	96.95 71	96.21 203	97.49 157

LS3D		95.46 59	95.14 77	95.84 53	97.91 55	98.90 58	98.58 31	97.79 5	97.07 45	83.65 131	88.71 108	88.64 104	97.82 37	97.49 59	97.42 54	99.26 78	97.72 151

PVSNet_BlendedMVS		95.41 61	95.28 73	95.57 56	97.42 61	99.02 45	95.89 107	93.10 60	96.16 65	93.12 35	91.99 75	85.27 128	94.66 110	98.09 43	97.34 58	99.24 80	99.08 57

PVSNet_Blended		95.41 61	95.28 73	95.57 56	97.42 61	99.02 45	95.89 107	93.10 60	96.16 65	93.12 35	91.99 75	85.27 128	94.66 110	98.09 43	97.34 58	99.24 80	99.08 57

IS_MVSNet		95.28 63	96.43 56	93.94 97	95.30 93	99.01 47	95.90 105	91.12 100	94.13 122	87.50 114	91.23 86	94.45 67	94.17 119	98.45 21	98.50 8	99.65 3	99.23 39

EPP-MVSNet		95.27 64	96.18 60	94.20 94	94.88 107	98.64 77	94.97 123	90.70 104	95.34 92	89.67 87	91.66 82	93.84 70	95.42 99	97.32 64	97.00 69	99.58 11	99.47 18

sasdasda		95.25 65	95.45 69	95.00 68	95.27 95	98.72 68	96.89 65	89.82 115	96.51 54	90.84 66	93.72 59	86.01 120	97.66 41	95.78 124	97.94 35	99.54 19	99.50 13

canonicalmvs		95.25 65	95.45 69	95.00 68	95.27 95	98.72 68	96.89 65	89.82 115	96.51 54	90.84 66	93.72 59	86.01 120	97.66 41	95.78 124	97.94 35	99.54 19	99.50 13

MGCFI-Net		95.12 67	95.39 72	94.79 79	95.24 97	98.68 72	96.80 72	89.72 119	96.48 56	90.11 80	93.64 61	85.86 124	97.36 48	95.69 130	97.92 38	99.53 21	99.49 16

UGNet		94.92 68	96.63 52	92.93 114	96.03 81	98.63 79	94.53 135	91.52 91	96.23 63	90.03 81	92.87 68	96.10 59	86.28 198	96.68 88	96.60 81	99.16 101	99.32 28
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 69	95.07 80	94.68 83	94.71 116	96.68 139	97.00 60	90.57 106	95.18 102	93.05 39	95.21 48	86.41 116	93.72 129	97.59 57	95.88 103	99.00 124	98.50 112

baseline		94.83 70	95.82 63	93.68 104	94.75 113	97.80 108	96.51 83	88.53 134	97.02 47	89.34 96	92.93 66	92.18 79	94.69 109	95.78 124	96.08 93	98.27 178	98.97 78

MVS_Test		94.82 71	95.66 64	93.84 102	94.79 110	98.35 92	96.49 84	89.10 128	96.12 68	87.09 117	92.58 70	90.61 88	96.48 72	96.51 98	96.89 73	99.11 108	98.54 109

MSDG		94.82 71	93.73 109	96.09 48	98.34 47	97.43 117	97.06 59	96.05 37	95.84 78	90.56 71	86.30 138	89.10 101	95.55 95	96.13 114	95.61 111	99.00 124	95.73 188

TSAR-MVS + COLMAP		94.79 73	94.51 86	95.11 65	96.50 71	97.54 112	97.99 45	94.54 44	97.81 18	85.88 122	96.73 32	81.28 159	96.99 58	96.29 105	95.21 123	98.76 152	96.73 179

CLD-MVS		94.79 73	94.36 91	95.30 62	95.21 99	97.46 115	97.23 57	92.24 72	96.43 57	91.77 55	92.69 69	84.31 139	96.06 82	95.52 132	95.03 128	99.31 68	99.06 62
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 75	95.54 67	93.87 101	96.48 72	98.97 49	94.33 138	91.84 79	94.93 108	90.37 76	85.04 144	94.99 64	90.87 166	98.12 41	97.30 60	99.30 70	99.45 19

DCV-MVSNet		94.76 76	95.12 79	94.35 91	95.10 103	95.81 167	96.46 85	89.49 123	96.33 61	90.16 78	92.55 71	90.26 90	95.83 87	95.52 132	96.03 97	99.06 118	99.33 26

PatchMatch-RL		94.69 77	94.41 89	95.02 67	97.63 60	98.15 101	94.50 136	91.99 74	95.32 93	91.31 59	95.47 46	83.44 146	96.02 84	96.56 92	95.23 122	98.69 156	96.67 180

viewcassd2359sk11		94.63 78	94.45 88	94.84 76	94.58 122	98.57 83	96.13 95	91.79 84	95.32 93	90.67 69	88.73 107	86.13 118	96.65 67	96.82 77	96.87 74	99.21 91	98.68 99

PMMVS		94.61 79	95.56 66	93.50 107	94.30 132	96.74 137	94.91 125	89.56 122	95.58 88	87.72 112	96.15 36	92.86 75	96.06 82	95.47 134	95.02 129	98.43 175	97.09 168

baseline1		94.59 80	94.47 87	94.72 81	95.16 100	97.97 107	96.07 99	91.94 77	94.86 109	89.98 82	91.60 83	85.87 123	95.64 89	97.07 72	96.90 72	99.52 22	97.06 172

casdiffmvs_mvg		94.55 81	94.26 93	94.88 73	94.96 105	98.51 86	97.11 58	91.82 83	94.28 119	89.20 98	86.60 129	86.85 112	96.56 71	97.47 60	97.25 63	99.64 4	98.83 92
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 82	95.47 68	93.46 108	94.51 126	98.65 76	94.66 132	90.72 102	95.69 84	86.90 118	93.80 57	89.44 95	94.74 107	96.98 76	94.86 133	99.19 96	98.85 89

tttt0517		94.52 83	95.44 71	93.44 109	94.51 126	98.68 72	94.61 134	90.72 102	95.61 87	86.84 119	93.78 58	89.26 98	94.74 107	97.02 75	94.86 133	99.20 95	98.87 87

Vis-MVSNet (Re-imp)		94.46 84	96.24 58	92.40 118	95.23 98	98.64 77	95.56 114	90.99 101	94.42 116	85.02 125	90.88 93	94.65 66	88.01 188	98.17 38	98.37 17	99.57 14	98.53 110

HQP-MVS		94.43 85	94.57 85	94.27 93	96.41 74	97.23 124	96.89 65	93.98 48	95.94 74	83.68 130	95.01 51	84.46 137	95.58 94	95.47 134	94.85 136	99.07 115	99.00 71

ACMP	92.88 9	94.43 85	94.38 90	94.50 86	96.01 82	97.69 110	95.85 110	92.09 73	95.74 80	89.12 100	95.14 49	82.62 154	94.77 106	95.73 127	94.67 137	99.14 104	99.06 62
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	92.75 10	94.41 87	93.84 107	95.09 66	96.41 74	96.80 133	94.88 128	93.54 51	96.41 58	90.16 78	92.31 73	83.11 149	96.32 76	96.22 108	94.65 138	99.22 87	97.35 162
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
casdiffmvs		94.38 88	94.15 100	94.64 84	94.70 118	98.51 86	96.03 102	91.66 88	95.70 82	89.36 95	86.48 133	85.03 135	96.60 69	97.40 62	97.30 60	99.52 22	98.67 100
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test2506		94.32 89	93.00 123	95.87 52	96.16 77	99.39 16	96.96 62	92.80 64	95.22 100	94.47 28	91.55 84	70.45 205	95.25 101	98.29 29	97.98 30	99.59 7	98.10 137

viewmanbaseed2359cas		94.31 90	94.25 94	94.38 89	94.72 115	98.59 81	96.09 97	91.84 79	95.35 91	87.92 110	87.86 115	85.54 125	96.45 74	96.71 86	97.04 66	99.26 78	98.67 100

diffmvs		94.31 90	94.21 95	94.42 88	94.64 119	98.28 94	96.36 88	91.56 89	96.77 49	88.89 102	88.97 105	84.23 140	96.01 85	96.05 115	96.41 85	99.05 122	98.79 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
viewdifsd2359ckpt13		94.14 92	94.00 101	94.30 92	94.55 123	98.55 85	95.71 112	91.76 86	95.03 106	88.12 109	87.34 118	85.15 131	96.39 75	96.81 81	96.60 81	99.24 80	98.50 112

ECVR-MVS		94.14 92	92.96 124	95.52 58	96.16 77	99.39 16	96.96 62	92.80 64	95.22 100	92.38 49	81.48 164	80.31 160	95.25 101	98.29 29	97.98 30	99.59 7	98.05 138

LGP-MVS_train		94.12 94	94.62 84	93.53 106	96.44 73	97.54 112	97.40 54	91.84 79	94.66 111	81.09 144	95.70 44	83.36 147	95.10 103	96.36 103	95.71 109	99.32 65	99.03 67

diffmvs_AUTHOR		94.09 95	93.86 105	94.36 90	94.60 121	98.31 93	96.29 90	91.51 92	96.39 59	88.49 103	87.35 117	83.32 148	96.16 81	96.17 113	96.64 79	99.10 109	98.82 94

RPSCF		94.05 96	94.00 101	94.12 95	96.20 76	96.41 147	96.61 79	91.54 90	95.83 79	89.73 86	96.94 31	92.80 76	95.35 100	91.63 200	90.44 203	95.27 215	93.94 205

DI_MVS_pp		94.01 97	93.63 111	94.44 87	94.54 125	98.26 96	97.51 52	90.63 105	95.88 76	89.34 96	80.54 171	89.36 96	95.48 97	96.33 104	96.27 89	99.17 98	98.78 97

UA-Net		93.96 98	95.95 62	91.64 127	96.06 80	98.59 81	95.29 117	90.00 111	91.06 167	82.87 133	90.64 94	98.06 40	86.06 199	98.14 40	98.20 20	99.58 11	96.96 173

FA-MVS(training)		93.94 99	95.16 76	92.53 117	94.87 108	98.57 83	95.42 116	79.49 204	95.37 90	90.98 61	86.54 131	94.26 69	95.44 98	97.80 53	95.19 124	98.97 127	98.38 124

test1111		93.94 99	92.78 125	95.29 63	96.14 79	99.42 12	96.79 73	92.85 63	95.08 105	91.39 58	80.69 169	79.86 163	95.00 105	98.28 32	98.00 29	99.58 11	98.11 136

viewmambaseed2359dif		93.92 101	93.38 117	94.54 85	94.55 123	98.15 101	96.41 86	91.47 94	95.10 104	89.58 89	86.64 127	85.10 133	96.17 79	94.08 163	95.77 108	99.09 111	98.84 91

CANet_DTU		93.92 101	96.57 53	90.83 137	95.63 85	98.39 91	96.99 61	87.38 145	96.26 62	71.97 191	96.31 35	93.02 74	94.53 113	97.38 63	96.83 76	98.49 170	97.79 144

FC-MVSNet-train		93.85 103	93.91 103	93.78 103	94.94 106	96.79 136	94.29 139	91.13 99	93.84 127	88.26 107	90.40 96	85.23 130	94.65 112	96.54 94	95.31 119	99.38 57	99.28 30

GBi-Net		93.81 104	94.18 96	93.38 110	91.34 167	95.86 163	96.22 91	88.68 131	95.23 97	90.40 73	86.39 134	91.16 82	94.40 116	96.52 95	96.30 86	99.21 91	97.79 144

test1		93.81 104	94.18 96	93.38 110	91.34 167	95.86 163	96.22 91	88.68 131	95.23 97	90.40 73	86.39 134	91.16 82	94.40 116	96.52 95	96.30 86	99.21 91	97.79 144

FMVSNet3		93.79 106	94.17 98	93.35 112	91.21 170	95.99 156	96.62 78	88.68 131	95.23 97	90.40 73	86.39 134	91.16 82	94.11 120	95.96 117	96.67 78	99.07 115	97.79 144

viewmacassd2359aftdt		93.65 107	93.29 119	94.07 96	94.61 120	98.51 86	96.04 101	91.75 87	93.61 130	86.56 120	84.89 145	84.41 138	96.17 79	95.97 116	97.03 67	99.28 72	98.63 103

tfpn200view9		93.64 108	92.57 130	94.89 72	95.33 91	98.94 51	96.82 69	92.31 68	92.63 143	88.29 104	87.21 121	78.01 171	97.12 55	96.82 77	95.85 104	99.45 38	98.56 107

thres200		93.62 109	92.54 131	94.88 73	95.36 90	98.93 53	96.75 75	92.31 68	92.84 140	88.28 106	86.99 123	77.81 174	97.13 53	96.82 77	95.92 100	99.45 38	98.49 114

OPM-MVS		93.61 110	92.43 138	95.00 68	96.94 68	97.34 120	97.78 48	94.23 46	89.64 180	85.53 123	88.70 109	82.81 152	96.28 77	96.28 106	95.00 131	99.24 80	97.22 165
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres400		93.56 111	92.43 138	94.87 75	95.40 89	98.91 56	96.70 77	92.38 67	92.93 139	88.19 108	86.69 126	77.35 175	97.13 53	96.75 84	95.85 104	99.42 50	98.56 107

thres100view900		93.55 112	92.47 137	94.81 78	95.33 91	98.74 66	96.78 74	92.30 71	92.63 143	88.29 104	87.21 121	78.01 171	96.78 63	96.38 100	95.92 100	99.38 57	98.40 122

Anonymous20231211		93.49 113	92.33 142	94.84 76	94.78 112	98.00 105	96.11 96	91.85 78	94.86 109	90.91 62	74.69 190	89.18 99	96.73 64	94.82 147	95.51 114	98.67 157	99.24 38

thres600view7		93.49 113	92.37 141	94.79 79	95.42 88	98.93 53	96.58 81	92.31 68	93.04 137	87.88 111	86.62 128	76.94 178	97.09 56	96.82 77	95.63 110	99.45 38	98.63 103

ET-MVSNet_ETH3D		93.34 115	94.33 92	92.18 121	83.26 225	97.66 111	96.72 76	89.89 114	95.62 86	87.17 116	96.00 40	83.69 145	96.99 58	93.78 164	95.34 118	99.06 118	98.18 134

FMVSNet2		93.30 116	93.36 118	93.22 113	91.34 167	95.86 163	96.22 91	88.24 137	95.15 103	89.92 85	81.64 162	89.36 96	94.40 116	96.77 83	96.98 70	99.21 91	97.79 144

viewdifsd2359ckpt11		93.27 117	92.72 126	93.91 99	94.46 128	97.42 118	94.91 125	91.42 95	95.74 80	89.57 90	87.34 118	82.87 151	95.61 91	92.62 183	94.62 140	97.49 195	98.44 115

viewmsd2359difaftdt		93.27 117	92.72 126	93.91 99	94.46 128	97.42 118	94.91 125	91.42 95	95.69 84	89.59 88	87.34 118	82.90 150	95.60 93	92.62 183	94.62 140	97.49 195	98.44 115

COLMAP_ROB	90.49 14	93.27 117	92.71 128	93.93 98	97.75 58	97.44 116	96.07 99	93.17 59	95.40 89	83.86 129	83.76 154	88.72 103	93.87 124	94.25 159	94.11 156	98.87 138	95.28 194
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
baseline2		93.01 120	94.17 98	91.64 127	92.83 154	97.49 114	93.40 150	87.53 143	93.67 129	86.07 121	91.83 80	86.58 113	91.36 155	96.38 100	95.06 127	98.67 157	98.20 133

Effi-MVS+		92.93 121	93.86 105	91.86 123	94.07 136	98.09 104	95.59 113	85.98 161	94.27 120	79.54 152	91.12 90	81.81 156	96.71 65	96.67 89	96.06 95	99.27 75	98.98 74

CDS-MVSNet		92.77 122	93.60 112	91.80 125	92.63 156	96.80 133	95.24 118	89.14 127	90.30 177	84.58 126	86.76 124	90.65 87	90.42 174	95.89 119	96.49 83	98.79 149	98.32 129
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Vis-MVSNet		92.77 122	95.00 82	90.16 146	94.10 135	98.79 63	94.76 131	88.26 136	92.37 152	79.95 148	88.19 114	91.58 81	84.38 209	97.59 57	97.58 50	99.52 22	98.91 83
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		92.66 124	92.49 134	92.85 115	97.13 66	98.89 59	95.90 105	88.50 135	95.32 93	83.31 132	71.99 208	88.96 102	94.10 121	96.69 87	96.49 83	98.15 180	99.10 54

IterMVS-LS		92.56 125	93.18 120	91.84 124	93.90 138	94.97 192	94.99 122	86.20 158	94.18 121	82.68 134	85.81 140	87.36 111	94.43 114	95.31 138	96.02 98	98.87 138	98.60 106
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GeoE		92.52 126	92.64 129	92.39 119	93.96 137	97.76 109	96.01 103	85.60 166	93.23 135	83.94 128	81.56 163	84.80 136	95.63 90	96.22 108	95.83 106	99.19 96	99.07 61

EPNet_dtu		92.45 127	95.02 81	89.46 155	98.02 53	95.47 178	94.79 130	92.62 66	94.97 107	70.11 202	94.76 55	92.61 78	84.07 212	95.94 118	95.56 112	97.15 199	95.82 187
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		92.03 128	91.55 153	92.58 116	97.13 66	98.72 68	94.65 133	86.54 154	93.58 132	82.56 135	67.75 219	90.47 89	95.67 88	95.87 120	95.54 113	98.91 135	98.93 79

test0.0.03 1		91.97 129	93.91 103	89.72 151	93.31 148	96.40 148	91.34 188	87.06 149	93.86 125	81.67 140	91.15 89	89.16 100	86.02 200	95.08 143	95.09 125	98.91 135	96.64 182

Fast-Effi-MVS+		91.87 130	92.08 145	91.62 129	92.91 152	97.21 125	94.93 124	84.60 181	93.61 130	81.49 142	83.50 155	78.95 166	96.62 68	96.55 93	96.22 91	99.16 101	98.51 111

dmvs_re		91.84 131	91.60 152	92.12 122	91.60 163	97.26 122	95.14 120	91.96 75	91.02 168	80.98 145	86.56 130	77.96 173	93.84 126	94.71 148	95.08 126	99.22 87	98.62 105

MS-PatchMatch		91.82 132	92.51 132	91.02 133	95.83 84	96.88 129	95.05 121	84.55 183	93.85 126	82.01 137	82.51 160	91.71 80	90.52 173	95.07 144	93.03 178	98.13 181	94.52 196

Effi-MVS+-dtu		91.78 133	93.59 113	89.68 154	92.44 158	97.11 126	94.40 137	84.94 177	92.43 148	75.48 173	91.09 91	83.75 144	93.55 132	96.61 90	95.47 115	97.24 198	98.67 100

IB-MVS	89.56 15	91.71 134	92.50 133	90.79 139	95.94 83	98.44 90	87.05 210	91.38 98	93.15 136	92.98 42	84.78 146	85.14 132	78.27 217	92.47 188	94.44 151	99.10 109	99.08 57
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		91.63 135	93.82 108	89.08 159	92.02 161	96.40 148	93.26 153	87.26 146	93.72 128	77.26 160	88.61 111	89.86 93	85.50 202	95.72 129	95.02 129	99.16 101	97.44 159

test-LLR		91.62 136	93.56 114	89.35 158	93.31 148	96.57 142	92.02 179	87.06 149	92.34 153	75.05 180	90.20 97	88.64 104	90.93 162	96.19 111	94.07 157	97.75 190	96.90 176

MDTV_nov1_ep13		91.57 137	93.18 120	89.70 152	93.39 146	96.97 127	93.53 147	80.91 201	95.70 82	81.86 138	92.40 72	89.93 92	93.25 137	91.97 197	90.80 200	95.25 216	94.46 198

FMVSNet1		91.54 138	90.93 159	92.26 120	90.35 177	95.27 185	95.22 119	87.16 148	91.37 164	87.62 113	75.45 185	83.84 143	94.43 114	96.52 95	96.30 86	98.82 142	97.74 150

ACMH	90.77 13	91.51 139	91.63 151	91.38 130	95.62 86	96.87 131	91.76 183	89.66 120	91.58 162	78.67 154	86.73 125	78.12 169	93.77 128	94.59 150	94.54 147	98.78 150	98.98 74
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	90.88 12	91.41 140	91.13 156	91.74 126	95.11 102	96.95 128	93.13 155	89.48 124	92.42 149	79.93 149	85.13 143	78.02 170	93.82 127	93.49 171	93.88 162	98.94 131	97.99 140

Fast-Effi-MVS+-dtu		91.19 141	93.64 110	88.33 167	92.19 160	96.46 145	93.99 142	81.52 199	92.59 145	71.82 192	92.17 74	85.54 125	91.68 152	95.73 127	94.64 139	98.80 147	98.34 126

TESTMET0.1,1		91.07 142	93.56 114	88.17 169	90.43 174	96.57 142	92.02 179	82.83 192	92.34 153	75.05 180	90.20 97	88.64 104	90.93 162	96.19 111	94.07 157	97.75 190	96.90 176

test-mter		90.95 143	93.54 116	87.93 179	90.28 178	96.80 133	91.44 185	82.68 193	92.15 157	74.37 184	89.57 103	88.23 109	90.88 165	96.37 102	94.31 153	97.93 187	97.37 161

SCA		90.92 144	93.04 122	88.45 165	93.72 143	97.33 121	92.77 159	76.08 216	96.02 71	78.26 156	91.96 77	90.86 85	93.99 123	90.98 205	90.04 206	95.88 207	94.06 204

EPMVS		90.88 145	92.12 144	89.44 156	94.71 116	97.24 123	93.55 146	76.81 211	95.89 75	81.77 139	91.49 85	86.47 115	93.87 124	90.21 208	90.07 205	95.92 206	93.49 211

CostFormer		90.69 146	90.48 164	90.93 135	94.18 133	96.08 155	94.03 141	78.20 207	93.47 133	89.96 83	90.97 92	80.30 161	93.72 129	87.66 218	88.75 210	95.51 212	96.12 184

USDC		90.69 146	90.52 163	90.88 136	94.17 134	96.43 146	95.82 111	86.76 151	93.92 124	76.27 169	86.49 132	74.30 188	93.67 131	95.04 145	93.36 171	98.61 163	94.13 201

PatchmatchNet		90.56 148	92.49 134	88.31 168	93.83 141	96.86 132	92.42 167	76.50 213	95.96 73	78.31 155	91.96 77	89.66 94	93.48 133	90.04 210	89.20 209	95.32 213	93.73 209
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pmmvs4		90.55 149	89.91 166	91.30 132	90.26 179	94.95 193	92.73 161	87.94 140	93.44 134	85.35 124	82.28 161	76.09 180	93.02 140	93.56 169	92.26 194	98.51 169	96.77 178

TAMVS		90.54 150	90.87 161	90.16 146	91.48 165	96.61 141	93.26 153	86.08 159	87.71 196	81.66 141	83.11 158	84.04 141	90.42 174	94.54 151	94.60 142	98.04 185	95.48 192

FMVSNet5		90.36 151	90.93 159	89.70 152	87.99 212	92.25 217	92.03 178	83.51 187	92.20 156	84.13 127	85.59 141	86.48 114	92.43 143	94.61 149	94.52 148	98.13 181	90.85 219

UniMVSNet_NR-MVSNet		90.35 152	89.96 165	90.80 138	89.66 186	95.83 166	92.48 165	90.53 107	90.96 170	79.57 150	79.33 175	77.14 176	93.21 138	92.91 180	94.50 150	99.37 59	99.05 64

IterMVS-SCA-FT		90.24 153	92.48 136	87.63 184	92.85 153	94.30 208	93.79 144	81.47 200	92.66 142	69.95 203	84.66 148	88.38 107	89.99 179	95.39 137	94.34 152	97.74 192	97.63 153

IterMVS		90.20 154	92.43 138	87.61 185	92.82 155	94.31 207	94.11 140	81.54 198	92.97 138	69.90 204	84.71 147	88.16 110	89.96 180	95.25 139	94.17 155	97.31 197	97.46 158
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPMNet		90.19 155	92.03 147	88.05 174	93.46 144	95.95 160	93.41 149	74.59 222	92.40 150	75.91 171	84.22 151	86.41 116	92.49 142	94.42 155	93.85 164	98.44 173	96.96 173

CR-MVSNet		90.16 156	91.96 148	88.06 173	93.32 147	95.95 160	93.36 151	75.99 217	92.40 150	75.19 177	83.18 156	85.37 127	92.05 146	95.21 140	94.56 145	98.47 172	97.08 170

thisisatest0515		90.12 157	92.06 146	87.85 180	90.03 181	96.17 153	87.83 207	87.45 144	91.71 161	77.15 161	85.40 142	84.01 142	85.74 201	95.41 136	93.30 174	98.88 137	98.43 118

dps		90.11 158	89.37 171	90.98 134	93.89 139	96.21 152	93.49 148	77.61 209	91.95 158	92.74 46	88.85 106	78.77 168	92.37 144	87.71 217	87.71 214	95.80 208	94.38 199

UniMVSNet (Re)		90.03 159	89.61 168	90.51 142	89.97 183	96.12 154	92.32 169	89.26 125	90.99 169	80.95 146	78.25 178	75.08 185	91.14 158	93.78 164	93.87 163	99.41 51	99.21 43

ADS-MVSNet		89.80 160	91.33 155	88.00 177	94.43 130	96.71 138	92.29 171	74.95 221	96.07 70	77.39 159	88.67 110	86.09 119	93.26 136	88.44 214	89.57 208	95.68 209	93.81 208

CVMVSNet		89.77 161	91.66 150	87.56 187	93.21 150	95.45 179	91.94 182	89.22 126	89.62 181	69.34 208	83.99 153	85.90 122	84.81 207	94.30 158	95.28 120	96.85 201	97.09 168

DU-MVS		89.67 162	88.84 173	90.63 141	89.26 196	95.61 172	92.48 165	89.91 112	91.22 165	79.57 150	77.72 179	71.18 202	93.21 138	92.53 186	94.57 144	99.35 62	99.05 64

testgi		89.42 163	91.50 154	87.00 194	92.40 159	95.59 174	89.15 204	85.27 173	92.78 141	72.42 189	91.75 81	76.00 181	84.09 211	94.38 156	93.82 166	98.65 161	96.15 183

TinyColmap		89.42 163	88.58 175	90.40 143	93.80 142	95.45 179	93.96 143	86.54 154	92.24 155	76.49 166	80.83 167	70.44 206	93.37 134	94.45 154	93.30 174	98.26 179	93.37 212

NR-MVSNet		89.34 165	88.66 174	90.13 149	90.40 175	95.61 172	93.04 157	89.91 112	91.22 165	78.96 153	77.72 179	68.90 214	89.16 184	94.24 160	93.95 160	99.32 65	98.99 72

GA-MVS		89.28 166	90.75 162	87.57 186	91.77 162	96.48 144	92.29 171	87.58 142	90.61 174	65.77 213	84.48 149	76.84 179	89.46 182	95.84 121	93.68 167	98.52 168	97.34 163

Baseline_NR-MVSNet		89.27 167	88.01 183	90.73 140	89.26 196	93.71 212	92.71 162	89.78 118	90.73 171	81.28 143	73.53 200	72.85 194	92.30 145	92.53 186	93.84 165	99.07 115	98.88 85

TranMVSNet+NR-MVSNet		89.23 168	88.48 177	90.11 150	89.07 202	95.25 186	92.91 158	90.43 108	90.31 176	77.10 162	76.62 183	71.57 200	91.83 150	92.12 192	94.59 143	99.32 65	98.92 80

pm-mvs1		89.19 169	89.02 172	89.38 157	90.40 175	95.74 170	92.05 177	88.10 139	86.13 206	77.70 157	73.72 199	79.44 165	88.97 185	95.81 123	94.51 149	99.08 113	97.78 149

PatchT		89.13 170	91.71 149	86.11 201	92.92 151	95.59 174	83.64 218	75.09 220	91.87 159	75.19 177	82.63 159	85.06 134	92.05 146	95.21 140	94.56 145	97.76 189	97.08 170

TDRefinement		89.07 171	88.15 180	90.14 148	95.16 100	96.88 129	95.55 115	90.20 109	89.68 179	76.42 167	76.67 182	74.30 188	84.85 206	93.11 176	91.91 196	98.64 162	94.47 197

MIMVSNet		88.99 172	91.07 157	86.57 197	86.78 218	95.62 171	91.20 191	75.40 219	90.65 173	76.57 165	84.05 152	82.44 155	91.01 161	95.84 121	95.38 117	98.48 171	93.50 210

anonymousdsp		88.90 173	91.00 158	86.44 198	88.74 209	95.97 158	90.40 198	82.86 191	88.77 187	67.33 211	81.18 166	81.44 158	90.22 177	96.23 107	94.27 154	99.12 107	99.16 50

tpm cat1		88.90 173	87.78 189	90.22 145	93.88 140	95.39 181	93.79 144	78.11 208	92.55 146	89.43 92	81.31 165	79.84 164	91.40 154	84.95 221	86.34 219	94.68 222	94.09 202

tpmrst		88.86 175	89.62 167	87.97 178	94.33 131	95.98 157	92.62 163	76.36 214	94.62 113	76.94 163	85.98 139	82.80 153	92.80 141	86.90 220	87.15 216	94.77 220	93.93 206

tfpnnormal		88.50 176	87.01 198	90.23 144	91.36 166	95.78 169	92.74 160	90.09 110	83.65 215	76.33 168	71.46 211	69.58 211	91.84 149	95.54 131	94.02 159	99.06 118	99.03 67

UniMVSNet_ETH3D		88.47 177	86.00 207	91.35 131	91.55 164	96.29 150	92.53 164	88.81 130	85.58 210	82.33 136	67.63 220	66.87 220	94.04 122	91.49 201	95.24 121	98.84 141	98.92 80

SixPastTwentyTwo		88.37 178	89.47 169	87.08 192	90.01 182	95.93 162	87.41 208	85.32 170	90.26 178	70.26 200	86.34 137	71.95 198	90.93 162	92.89 181	91.72 197	98.55 166	97.22 165

V42		88.31 179	87.95 185	88.73 162	89.44 191	95.34 182	92.23 173	87.21 147	88.83 185	74.49 183	74.89 189	73.43 193	90.41 176	92.08 195	92.77 185	98.60 165	98.33 127

v2v482		88.25 180	87.71 190	88.88 160	89.23 200	95.28 183	92.10 175	87.89 141	88.69 188	73.31 187	75.32 186	71.64 199	91.89 148	92.10 194	92.92 180	98.86 140	97.99 140

v8		88.21 181	87.94 186	88.51 164	89.62 187	95.01 191	92.31 170	84.99 175	88.94 183	74.70 182	75.03 187	73.51 192	90.67 170	92.11 193	92.74 186	98.80 147	98.24 131

v10		88.00 182	87.96 184	88.05 174	89.44 191	94.68 199	92.36 168	83.35 188	89.37 182	72.96 188	73.98 197	72.79 195	91.35 156	93.59 166	92.88 181	98.81 145	98.42 120

tpm		87.95 183	89.44 170	86.21 200	92.53 157	94.62 202	91.40 186	76.36 214	91.46 163	69.80 206	87.43 116	75.14 183	91.55 153	89.85 212	90.60 202	95.61 210	96.96 173

WR-MVS_H		87.93 184	87.85 187	88.03 176	89.62 187	95.58 176	90.47 197	85.55 167	87.20 201	76.83 164	74.42 194	72.67 196	86.37 197	93.22 175	93.04 177	99.33 63	98.83 92

WR-MVS		87.93 184	88.09 181	87.75 181	89.26 196	95.28 183	90.81 194	86.69 152	88.90 184	75.29 176	74.31 195	73.72 191	85.19 205	92.26 189	93.32 173	99.27 75	98.81 95

v1144		87.92 186	87.79 188	88.07 171	89.27 195	95.15 188	92.17 174	85.62 165	88.52 189	71.52 193	73.80 198	72.40 197	91.06 160	93.54 170	92.80 183	98.81 145	98.33 127

CP-MVSNet		87.89 187	87.27 193	88.62 163	89.30 194	95.06 189	90.60 196	85.78 163	87.43 200	75.98 170	74.60 191	68.14 217	90.76 167	93.07 178	93.60 168	99.30 70	98.98 74

pmmvs5		87.83 188	88.09 181	87.51 189	89.59 189	95.48 177	89.75 202	84.73 179	86.07 208	71.44 194	80.57 170	70.09 209	90.74 169	94.47 153	92.87 182	98.82 142	97.10 167

TransMVSNet (Re)		87.73 189	86.79 200	88.83 161	90.76 171	94.40 205	91.33 189	89.62 121	84.73 212	75.41 175	72.73 204	71.41 201	86.80 194	94.53 152	93.93 161	99.06 118	95.83 186

LTVRE_ROB	87.32 16	87.55 190	88.25 179	86.73 195	90.66 172	95.80 168	93.05 156	84.77 178	83.35 216	60.32 225	83.12 157	67.39 218	93.32 135	94.36 157	94.86 133	98.28 177	98.87 87
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		87.51 191	87.31 192	87.74 182	89.04 203	94.87 197	92.07 176	85.03 174	88.49 190	70.32 199	72.65 205	70.35 207	91.21 157	93.59 166	92.80 183	98.78 150	98.42 120

v148		87.51 191	86.79 200	88.36 166	89.39 193	95.21 187	89.84 201	88.20 138	87.61 198	77.56 158	73.38 202	70.32 208	86.80 194	90.70 206	92.31 192	98.37 176	97.98 142

v144192		87.40 193	87.20 195	87.64 183	88.89 204	94.88 196	91.65 184	84.70 180	87.80 195	71.17 197	73.20 203	70.91 203	90.75 168	92.69 182	92.49 189	98.71 154	98.43 118

PS-CasMVS		87.33 194	86.68 203	88.10 170	89.22 201	94.93 194	90.35 199	85.70 164	86.44 205	74.01 185	73.43 201	66.59 223	90.04 178	92.92 179	93.52 169	99.28 72	98.91 83

v1921920		87.31 195	87.13 196	87.52 188	88.87 206	94.72 198	91.96 181	84.59 182	88.28 191	69.86 205	72.50 206	70.03 210	91.10 159	93.33 173	92.61 188	98.71 154	98.44 115

PEN-MVS		87.22 196	86.50 205	88.07 171	88.88 205	94.44 204	90.99 193	86.21 156	86.53 204	73.66 186	74.97 188	66.56 224	89.42 183	91.20 203	93.48 170	99.24 80	98.31 130

v1240		86.89 197	86.75 202	87.06 193	88.75 208	94.65 201	91.30 190	84.05 184	87.49 199	68.94 209	71.96 209	68.86 215	90.65 171	93.33 173	92.72 187	98.67 157	98.24 131

EG-PatchMatch MVS		86.68 198	87.24 194	86.02 202	90.58 173	96.26 151	91.08 192	81.59 197	84.96 211	69.80 206	71.35 212	75.08 185	84.23 210	94.24 160	93.35 172	98.82 142	95.46 193

DTE-MVSNet		86.67 199	86.09 206	87.35 190	88.45 211	94.08 210	90.65 195	86.05 160	86.13 206	72.19 190	74.58 193	66.77 222	87.61 191	90.31 207	93.12 176	99.13 105	97.62 154

v7n		86.43 200	86.52 204	86.33 199	87.91 213	94.93 194	90.15 200	83.05 189	86.57 203	70.21 201	71.48 210	66.78 221	87.72 189	94.19 162	92.96 179	98.92 133	98.76 98

MDTV_nov1_ep13_2view		86.30 201	88.27 178	84.01 207	87.71 215	94.67 200	88.08 206	76.78 212	90.59 175	68.66 210	80.46 172	80.12 162	87.58 192	89.95 211	88.20 212	95.25 216	93.90 207

gg-mvs-nofinetune		86.17 202	88.57 176	83.36 209	93.44 145	98.15 101	96.58 81	72.05 225	74.12 229	49.23 233	64.81 223	90.85 86	89.90 181	97.83 50	96.84 75	98.97 127	97.41 160

pmnet_mix02		86.12 203	87.12 197	84.96 205	89.82 184	94.12 209	84.88 216	86.63 153	91.78 160	65.60 214	80.76 168	76.98 177	86.61 196	87.29 219	84.80 222	96.21 203	94.09 202

pmmvs6		85.98 204	84.89 212	87.25 191	88.83 207	94.35 206	89.36 203	85.30 172	78.51 226	75.44 174	62.71 225	75.41 182	87.65 190	93.58 168	92.40 191	96.89 200	97.29 164

EU-MVSNet		85.62 205	87.65 191	83.24 210	88.54 210	92.77 216	87.12 209	85.32 170	86.71 202	64.54 216	78.52 177	75.11 184	78.35 216	92.25 190	92.28 193	95.58 211	95.93 185

MVS-HIRNet		85.36 206	86.89 199	83.57 208	90.13 180	94.51 203	83.57 219	72.61 224	88.27 192	71.22 196	68.97 215	81.81 156	88.91 186	93.08 177	91.94 195	94.97 219	89.64 222

N_pmnet		84.80 207	85.10 211	84.45 206	89.25 199	92.86 215	84.04 217	86.21 156	88.78 186	66.73 212	72.41 207	74.87 187	85.21 204	88.32 215	86.45 217	95.30 214	92.04 216

CMPMVS	65.18 17	84.76 208	83.10 214	86.69 196	95.29 94	95.05 190	88.37 205	85.51 168	80.27 223	71.31 195	68.37 217	73.85 190	85.25 203	87.72 216	87.75 213	94.38 223	88.70 223
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PM-MVS		84.72 209	84.47 213	85.03 204	84.67 221	91.57 219	86.27 212	82.31 196	87.65 197	70.62 198	76.54 184	56.41 233	88.75 187	92.59 185	89.85 207	97.54 194	96.66 181

pmmvs-eth3d		84.33 210	82.94 215	85.96 203	84.16 222	90.94 220	86.55 211	83.79 185	84.25 213	75.85 172	70.64 213	56.43 232	87.44 193	92.20 191	90.41 204	97.97 186	95.68 189

Anonymous20231206		83.84 211	85.19 210	82.26 211	87.38 216	92.87 214	85.49 214	83.65 186	86.07 208	63.44 220	68.42 216	69.01 213	75.45 221	93.34 172	92.44 190	98.12 183	94.20 200

gm-plane-assit		83.26 212	85.29 209	80.89 212	89.52 190	89.89 223	70.26 230	78.24 206	77.11 227	58.01 230	74.16 196	66.90 219	90.63 172	97.20 67	96.05 96	98.66 160	95.68 189

test20.03		82.92 213	85.52 208	79.90 215	87.75 214	91.84 218	82.80 220	82.99 190	82.65 220	60.32 225	78.90 176	70.50 204	67.10 225	92.05 196	90.89 199	98.44 173	91.80 217

new_pmnet		81.53 214	82.68 216	80.20 213	83.47 224	89.47 224	82.21 222	78.36 205	87.86 194	60.14 227	67.90 218	69.43 212	82.03 214	89.22 213	87.47 215	94.99 218	87.39 224

MDA-MVSNet-bldmvs		80.11 215	80.24 219	79.94 214	77.01 228	93.21 213	78.86 226	85.94 162	82.71 219	60.86 222	79.71 174	51.77 235	83.71 213	75.60 227	86.37 218	93.28 224	92.35 214

MIMVSNet1		80.03 216	80.93 217	78.97 216	72.46 231	90.73 221	80.81 224	82.44 194	80.39 222	63.64 218	57.57 227	64.93 225	76.37 219	91.66 199	91.55 198	98.07 184	89.70 221

pmmvs3		79.16 217	80.12 220	78.05 218	79.36 226	86.59 227	78.13 227	73.87 223	76.42 228	57.51 231	70.59 214	57.02 231	84.66 208	90.10 209	88.32 211	94.75 221	91.77 218

FE-MVSNET		79.15 218	80.25 218	77.87 219	69.65 232	89.30 225	81.34 223	82.42 195	79.49 225	59.18 229	59.18 226	59.41 230	77.03 218	91.12 204	90.65 201	97.57 193	92.63 213

new-patchmatchnet		78.49 219	78.19 222	78.84 217	84.13 223	90.06 222	77.11 228	80.39 202	79.57 224	59.64 228	66.01 221	55.65 234	75.62 220	84.55 222	80.70 225	96.14 205	90.77 220

FPMVS		75.84 220	74.59 224	77.29 220	86.92 217	83.89 229	85.01 215	80.05 203	82.91 218	60.61 224	65.25 222	60.41 228	63.86 226	75.60 227	73.60 229	87.29 230	80.47 227

test_method		72.96 221	78.68 221	66.28 224	50.17 236	64.90 234	75.45 229	50.90 232	87.89 193	62.54 221	62.98 224	68.34 216	70.45 223	91.90 198	82.41 223	88.19 229	92.35 214

WB-MVS		69.22 222	76.91 223	60.24 226	85.80 220	79.37 230	56.86 235	84.96 176	81.50 221	18.16 238	76.85 181	61.07 226	34.23 233	82.46 225	81.81 224	81.43 233	75.31 231

Gipuma		68.35 223	66.71 226	70.27 221	74.16 230	68.78 233	63.93 233	71.77 226	83.34 217	54.57 232	34.37 231	31.88 237	68.69 224	83.30 223	85.53 220	88.48 228	79.78 228
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	63.12 18	67.27 224	66.39 227	68.30 222	77.98 227	60.24 235	59.53 234	76.82 210	66.65 230	60.74 223	54.39 228	59.82 229	51.24 229	73.92 230	70.52 230	83.48 231	79.17 229
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GG-mvs-BLEND		66.17 225	94.91 83	32.63 230	1.32 239	96.64 140	91.40 186	0.85 236	94.39 118	2.20 240	90.15 99	95.70 62	2.27 236	96.39 99	95.44 116	97.78 188	95.68 189

PMMVS2		64.36 226	65.94 228	62.52 225	67.37 233	77.44 231	64.39 232	69.32 230	61.47 231	34.59 234	46.09 230	41.03 236	48.02 232	74.56 229	78.23 226	91.43 226	82.76 226

E-PMN		50.67 227	47.85 230	53.96 227	64.13 235	50.98 238	38.06 236	69.51 228	51.40 233	24.60 236	29.46 234	24.39 239	56.07 228	48.17 232	59.70 231	71.40 234	70.84 232

EMVS		49.98 228	46.76 231	53.74 228	64.96 234	51.29 237	37.81 237	69.35 229	51.83 232	22.69 237	29.57 233	25.06 238	57.28 227	44.81 233	56.11 232	70.32 235	68.64 233

MVE	50.86 19	49.54 229	51.43 229	47.33 229	44.14 237	59.20 236	36.45 238	60.59 231	41.47 234	31.14 235	29.58 232	17.06 241	48.52 231	62.22 231	74.63 228	63.12 236	75.87 230
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		12.09 230	16.94 232	6.42 231	3.15 238	6.08 239	9.51 240	3.84 234	21.46 235	5.31 239	27.49 235	6.76 242	10.89 234	17.06 234	15.01 233	5.84 237	24.75 234

test123		9.58 231	13.53 233	4.97 232	1.31 240	5.47 240	8.32 241	2.95 235	18.14 236	2.03 241	20.82 236	2.34 243	10.60 235	10.00 235	14.16 234	4.60 238	23.77 235

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

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

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

TPM-MVS					98.94 32	98.47 89	98.04 42			92.62 47	96.51 34	98.76 29	95.94 86			98.92 133	97.55 155
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										63.50 219

9.14												99.28 12

SR-MVS					99.45 9			97.61 14				99.20 16

Anonymous202405211			92.18 143		95.04 104	98.20 98	96.14 94	91.79 84	93.93 123		74.60 191	88.38 107	96.48 72	95.17 142	95.82 107	99.00 124	99.15 51

our_test_3					89.78 185	93.84 211	85.59 213

ambc			73.83 225		76.23 229	85.13 228	82.27 221		84.16 214	65.58 215	52.82 229	23.31 240	73.55 222	91.41 202	85.26 221	92.97 225	94.70 195

MTAPA										96.83 10		99.12 21

MTMP										97.18 5		98.83 26

Patchmatch-RL test							34.61 239

tmp_tt				66.88 223	86.07 219	73.86 232	68.22 231	33.38 233	96.88 48	80.67 147	88.23 113	78.82 167	49.78 230	82.68 224	77.47 227	83.19 232

XVS					96.60 69	99.35 18	96.82 69			90.85 63		98.72 30				99.46 34

X-MVStestdata					96.60 69	99.35 18	96.82 69			90.85 63		98.72 30				99.46 34

mPP-MVS					99.21 23							98.29 38

NP-MVS									95.32 93

Patchmtry						95.96 159	93.36 151	75.99 217		75.19 177

DeepMVS_CX						86.86 226	79.50 225	70.43 227	90.73 171	63.66 217	80.36 173	60.83 227	79.68 215	76.23 226		89.46 227	86.53 225

High-resolution multi-view benchmark