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.

DELS-MVS		96.06 55	96.04 62	96.07 51	97.77 57	99.25 30	98.10 43	93.26 57	94.42 122	92.79 46	88.52 114	93.48 74	95.06 116	98.51 17	98.83 1	99.45 38	99.28 31
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DeepC-MVS_fast	96.13 1	98.13 21	98.27 27	97.97 25	99.16 27	99.03 44	99.05 20	97.24 28	98.22 12	94.17 34	95.82 42	98.07 40	98.69 17	98.83 11	98.80 2	99.52 22	99.10 55
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	93.79 8	97.08 39	97.20 43	96.95 39	99.09 29	99.03 44	98.20 41	93.33 55	97.99 17	93.82 35	90.61 96	96.80 51	97.82 38	97.90 49	98.78 3	99.47 33	99.26 36

MSLP-MVS++		98.04 24	97.93 34	98.18 17	99.10 28	99.09 37	98.34 38	96.99 34	97.54 31	96.60 14	94.82 53	98.45 36	98.89 6	97.46 62	98.77 4	99.17 110	99.37 22

MGCNet		97.94 25	98.72 11	97.02 37	98.48 44	99.50 9	99.02 21	94.06 49	98.33 7	94.51 29	98.78 6	97.73 44	96.60 74	98.51 17	98.68 5	99.45 38	99.53 12

DeepPCF-MVS	95.28 2	97.00 41	98.35 23	95.42 61	97.30 65	98.94 52	94.82 142	96.03 40	98.24 11	92.11 54	95.80 43	98.64 34	95.51 108	98.95 7	98.66 6	96.78 217	99.20 45

SMA-MVS		98.66 8	98.89 8	98.39 10	99.60 1	99.41 14	99.00 23	97.63 14	97.78 20	95.83 20	98.33 13	99.83 4	98.85 10	98.93 8	98.56 7	99.41 53	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
IS_MVSNet		95.28 64	96.43 57	93.94 109	95.30 94	99.01 48	95.90 117	91.12 113	94.13 128	87.50 133	91.23 87	94.45 68	94.17 133	98.45 22	98.50 8	99.65 3	99.23 40

DeepC-MVS	94.87 4	96.76 50	96.50 55	97.05 36	98.21 50	99.28 26	98.67 30	97.38 22	97.31 37	90.36 86	89.19 106	93.58 73	98.19 29	98.31 29	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
SteuartSystems-ACMMP		98.38 15	98.71 12	97.99 24	99.34 21	99.46 12	99.34 8	97.33 26	97.31 37	94.25 32	98.06 15	99.17 20	98.13 32	98.98 5	98.46 10	99.55 18	99.54 11
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	93.91 7	97.23 37	97.22 42	97.24 33	98.89 37	98.85 62	98.26 40	93.25 59	97.99 17	95.56 24	90.01 102	98.03 42	98.05 35	97.91 48	98.43 11	99.44 45	99.35 24

DVP-MVS		98.86 5	98.97 4	98.75 3	99.43 13	99.63 1	99.25 14	97.81 2	98.62 2	97.69 3	97.59 22	99.90 2	98.93 5	98.99 4	98.42 12	99.37 61	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
MSP-MVS		98.73 7	98.93 6	98.50 7	99.44 12	99.57 4	99.36 4	97.65 11	98.14 14	96.51 16	98.49 9	99.65 9	98.67 18	98.60 14	98.42 12	99.40 56	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
APDe-MVS		98.87 4	98.96 5	98.77 2	99.58 2	99.53 7	99.44 1	97.81 2	98.22 12	97.33 6	98.70 7	99.33 11	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
APD-MVS		98.36 16	98.32 25	98.41 9	99.47 6	99.26 28	99.12 17	97.77 7	96.73 51	96.12 18	97.27 30	98.88 25	98.46 26	98.47 20	98.39 15	99.52 22	99.22 42
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PHI-MVS		97.78 28	98.44 20	97.02 37	98.73 39	99.25 30	98.11 42	95.54 41	96.66 54	92.79 46	98.52 8	99.38 10	97.50 46	97.84 50	98.39 15	99.45 38	99.03 68

Vis-MVSNet (Re-imp)		94.46 86	96.24 59	92.40 130	95.23 99	98.64 78	95.56 127	90.99 114	94.42 122	85.02 144	90.88 94	94.65 67	88.01 212	98.17 39	98.37 17	99.57 14	98.53 121

ME-MVS		98.97 1	99.00 3	98.94 1	99.53 4	99.47 11	99.35 6	97.66 9	98.36 6	98.80 1	99.17 1	99.76 6	98.86 8	98.57 15	98.32 18	99.42 50	99.33 26

SED-MVS		98.90 3	99.07 2	98.69 4	99.38 19	99.61 2	99.33 10	97.80 4	98.25 10	97.60 4	98.87 5	99.89 3	98.67 18	99.02 2	98.26 19	99.36 63	99.61 6

DPE-MVS		98.75 6	98.91 7	98.57 6	99.21 24	99.54 6	99.42 2	97.78 6	97.49 33	96.84 11	98.94 2	99.82 5	98.59 22	98.90 10	98.22 20	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
DVP-MVS++		98.92 2	99.18 1	98.61 5	99.47 6	99.61 2	99.39 3	97.82 1	98.80 1	96.86 10	98.90 3	99.92 1	98.67 18	99.02 2	98.20 21	99.43 48	99.82 1

UA-Net		93.96 104	95.95 63	91.64 139	96.06 81	98.59 82	95.29 130	90.00 124	91.06 180	82.87 152	90.64 95	98.06 41	86.06 223	98.14 41	98.20 21	99.58 11	96.96 185

QAPM		96.78 49	97.14 46	96.36 44	99.05 30	99.14 36	98.02 45	93.26 57	97.27 39	90.84 75	91.16 88	97.31 46	97.64 44	97.70 55	98.20 21	99.33 65	99.18 49

X-MVS		97.84 26	98.19 29	97.42 31	99.40 15	99.35 19	99.06 19	97.25 27	97.38 36	90.85 72	96.06 39	98.72 31	98.53 25	98.41 26	98.15 24	99.46 34	99.28 31

ACMMPR		98.40 13	98.49 15	98.28 14	99.41 14	99.40 15	99.36 4	97.35 23	98.30 8	95.02 27	97.79 19	98.39 38	99.04 2	98.26 35	98.10 25	99.50 29	99.22 42

CNVR-MVS		98.47 12	98.46 18	98.48 8	99.40 15	99.05 38	99.02 21	97.54 18	97.73 21	96.65 13	97.20 31	99.13 21	98.85 10	98.91 9	98.10 25	99.41 53	99.08 58

HFP-MVS		98.48 11	98.62 13	98.32 12	99.39 18	99.33 23	99.27 12	97.42 20	98.27 9	95.25 25	98.34 12	98.83 27	99.08 1	98.26 35	98.08 27	99.48 30	99.26 36

CANet		96.84 47	97.20 43	96.42 42	97.92 55	99.24 32	98.60 32	93.51 54	97.11 44	93.07 39	91.16 88	97.24 47	96.21 89	98.24 37	98.05 28	99.22 92	99.35 24

TSAR-MVS + MP.		98.49 10	98.78 9	98.15 20	98.14 52	99.17 34	99.34 8	97.18 31	98.44 5	95.72 21	97.84 18	99.28 13	98.87 7	99.05 1	98.05 28	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
test1111		93.94 107	92.78 136	95.29 64	96.14 80	99.42 13	96.79 75	92.85 65	95.08 109	91.39 60	80.69 188	79.86 176	95.00 117	98.28 33	98.00 30	99.58 11	98.11 148

test2506		94.32 94	93.00 134	95.87 53	96.16 78	99.39 17	96.96 64	92.80 66	95.22 103	94.47 30	91.55 85	70.45 229	95.25 113	98.29 30	97.98 31	99.59 7	98.10 149

ECVR-MVS		94.14 98	92.96 135	95.52 59	96.16 78	99.39 17	96.96 64	92.80 66	95.22 103	92.38 51	81.48 183	80.31 172	95.25 113	98.29 30	97.98 31	99.59 7	98.05 150

SD-MVS		98.52 9	98.77 10	98.23 16	98.15 51	99.26 28	98.79 29	97.59 17	98.52 3	96.25 17	97.99 17	99.75 7	99.01 3	98.27 34	97.97 33	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
EC-MVSNet		96.49 51	97.63 36	95.16 65	94.75 114	98.69 72	97.39 57	88.97 143	96.34 61	92.02 55	96.04 40	96.46 53	98.21 27	98.41 26	97.96 34	99.61 6	99.55 10

MVS_111021_HR		97.04 40	98.20 28	95.69 56	98.44 47	99.29 25	96.59 82	93.20 60	97.70 24	89.94 95	98.46 10	96.89 49	96.71 66	98.11 43	97.95 35	99.27 78	99.01 71

sasdasda		95.25 66	95.45 70	95.00 69	95.27 96	98.72 69	96.89 67	89.82 128	96.51 55	90.84 75	93.72 60	86.01 123	97.66 42	95.78 136	97.94 36	99.54 19	99.50 13

canonicalmvs		95.25 66	95.45 70	95.00 69	95.27 96	98.72 69	96.89 67	89.82 128	96.51 55	90.84 75	93.72 60	86.01 123	97.66 42	95.78 136	97.94 36	99.54 19	99.50 13

CDPH-MVS		96.84 47	97.49 38	96.09 49	98.92 35	98.85 62	98.61 31	95.09 43	96.00 73	87.29 134	95.45 48	97.42 45	97.16 53	97.83 51	97.94 36	99.44 45	98.92 81

MGCFI-Net		95.12 68	95.39 73	94.79 81	95.24 98	98.68 73	96.80 74	89.72 132	96.48 57	90.11 90	93.64 62	85.86 128	97.36 49	95.69 142	97.92 39	99.53 21	99.49 16

PGM-MVS		97.81 27	98.11 30	97.46 30	99.55 3	99.34 22	99.32 11	94.51 47	96.21 65	93.07 39	98.05 16	97.95 43	98.82 12	98.22 38	97.89 40	99.48 30	99.09 57

ACMMP_NAP		98.20 19	98.49 15	97.85 26	99.50 5	99.40 15	99.26 13	97.64 13	97.47 35	92.62 49	97.59 22	99.09 23	98.71 16	98.82 12	97.86 41	99.40 56	99.19 46

CS-MVS		96.87 45	97.41 41	96.24 47	97.42 62	99.48 10	97.30 58	91.83 86	97.17 41	93.02 43	94.80 54	94.45 68	98.16 31	98.61 13	97.85 42	99.69 1	99.50 13

ETV-MVS		96.31 53	97.47 40	94.96 72	94.79 111	98.78 65	96.08 105	91.41 107	96.16 66	90.50 81	95.76 44	96.20 58	97.39 47	98.42 25	97.82 43	99.57 14	99.18 49

TSAR-MVS + ACMM		97.71 30	98.60 14	96.66 41	98.64 42	99.05 38	98.85 28	97.23 29	98.45 4	89.40 105	97.51 26	99.27 15	96.88 62	98.53 16	97.81 44	98.96 141	99.59 8

SPE-MVS-test		97.00 41	97.85 35	96.00 52	97.77 57	99.56 5	96.35 91	91.95 78	97.54 31	92.20 52	96.14 38	96.00 62	98.19 29	98.46 21	97.78 45	99.57 14	99.45 19

NCCC		98.10 22	98.05 32	98.17 19	99.38 19	99.05 38	99.00 23	97.53 19	98.04 16	95.12 26	94.80 54	99.18 19	98.58 23	98.49 19	97.78 45	99.39 58	98.98 75

MP-MVS		98.09 23	98.30 26	97.84 27	99.34 21	99.19 33	99.23 15	97.40 21	97.09 45	93.03 42	97.58 24	98.85 26	98.57 24	98.44 24	97.69 47	99.48 30	99.23 40
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		98.32 18	98.34 24	98.29 13	99.34 21	99.30 24	99.15 16	97.35 23	97.49 33	95.58 23	97.72 20	98.62 35	98.82 12	98.29 30	97.67 48	99.51 27	99.28 31

SF-MVS		98.39 14	98.45 19	98.33 11	99.45 10	99.05 38	98.27 39	97.65 11	97.73 21	97.02 9	98.18 14	99.25 16	98.11 33	98.15 40	97.62 49	99.45 38	99.19 46

OpenMVS	92.33 11	95.50 57	95.22 76	95.82 55	98.98 31	98.97 50	97.67 52	93.04 64	94.64 116	89.18 111	84.44 167	94.79 66	96.79 63	97.23 68	97.61 50	99.24 83	98.88 86

Vis-MVSNet		92.77 134	95.00 83	90.16 162	94.10 147	98.79 64	94.76 145	88.26 150	92.37 165	79.95 167	88.19 117	91.58 82	84.38 233	97.59 58	97.58 51	99.52 22	98.91 84
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MAR-MVS		95.50 57	95.60 66	95.39 62	98.67 41	98.18 112	95.89 119	89.81 130	94.55 118	91.97 56	92.99 66	90.21 92	97.30 50	96.79 85	97.49 52	98.72 166	98.99 73
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
MCST-MVS		98.20 19	98.36 21	98.01 23	99.40 15	99.05 38	99.00 23	97.62 15	97.59 30	93.70 36	97.42 29	99.30 12	98.77 14	98.39 28	97.48 53	99.59 7	99.31 30

HPM-MVS++		98.34 17	98.47 17	98.18 17	99.46 9	99.15 35	99.10 18	97.69 8	97.67 26	94.93 28	97.62 21	99.70 8	98.60 21	98.45 22	97.46 54	99.31 71	99.26 36

LS3D		95.46 60	95.14 78	95.84 54	97.91 56	98.90 59	98.58 33	97.79 5	97.07 46	83.65 150	88.71 110	88.64 105	97.82 38	97.49 60	97.42 55	99.26 81	97.72 163

TSAR-MVS + GP.		97.45 33	98.36 21	96.39 43	95.56 88	98.93 54	97.74 51	93.31 56	97.61 29	94.24 33	98.44 11	99.19 18	98.03 36	97.60 57	97.41 56	99.44 45	99.33 26

DPM-MVS		96.86 46	96.82 51	96.91 40	98.08 53	98.20 110	98.52 35	97.20 30	97.24 40	91.42 59	91.84 80	98.45 36	97.25 51	97.07 74	97.40 57	98.95 142	97.55 167

CSCG		97.44 34	97.18 45	97.75 28	99.47 6	99.52 8	98.55 34	95.41 42	97.69 25	95.72 21	94.29 57	95.53 64	98.10 34	96.20 119	97.38 58	99.24 83	99.62 4

PVSNet_BlendedMVS		95.41 62	95.28 74	95.57 57	97.42 62	99.02 46	95.89 119	93.10 62	96.16 66	93.12 37	91.99 76	85.27 134	94.66 122	98.09 44	97.34 59	99.24 83	99.08 58

PVSNet_Blended		95.41 62	95.28 74	95.57 57	97.42 62	99.02 46	95.89 119	93.10 62	96.16 66	93.12 37	91.99 76	85.27 134	94.66 122	98.09 44	97.34 59	99.24 83	99.08 58

casdiffmvs		94.38 91	94.15 104	94.64 88	94.70 119	98.51 92	96.03 111	91.66 98	95.70 84	89.36 107	86.48 140	85.03 141	96.60 74	97.40 63	97.30 61	99.52 22	98.67 107
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		94.77 77	95.54 68	93.87 113	96.48 73	98.97 50	94.33 155	91.84 81	94.93 112	90.37 85	85.04 161	94.99 65	90.87 185	98.12 42	97.30 61	99.30 73	99.45 19

MVS_111021_LR		97.16 38	98.01 33	96.16 48	98.47 45	98.98 49	96.94 66	93.89 51	97.64 28	91.44 58	98.89 4	96.41 54	97.20 52	98.02 46	97.29 63	99.04 135	98.85 90

casdiffmvs_mvg		94.55 83	94.26 95	94.88 75	94.96 106	98.51 92	97.11 60	91.82 87	94.28 125	89.20 110	86.60 136	86.85 114	96.56 76	97.47 61	97.25 64	99.64 4	98.83 93
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
train_agg		97.65 31	98.06 31	97.18 34	98.94 33	98.91 57	98.98 27	97.07 33	96.71 52	90.66 79	97.43 28	99.08 24	98.20 28	97.96 47	97.14 65	99.22 92	99.19 46

EIA-MVS		95.50 57	96.19 60	94.69 86	94.83 110	98.88 61	95.93 114	91.50 103	94.47 121	89.43 103	93.14 65	92.72 78	97.05 58	97.82 53	97.13 66	99.43 48	99.15 52

viewmanbaseed2359cas		94.31 95	94.25 97	94.38 99	94.72 116	98.59 82	96.09 104	91.84 81	95.35 93	87.92 129	87.86 118	85.54 129	96.45 84	96.71 89	97.04 67	99.26 81	98.67 107

viewmacassd2359aftdt		93.65 118	93.29 130	94.07 108	94.61 122	98.51 92	96.04 110	91.75 94	93.61 136	86.56 139	84.89 162	84.41 144	96.17 90	95.97 128	97.03 68	99.28 75	98.63 112

EPNet		96.27 54	96.97 48	95.46 60	98.47 45	98.28 105	97.41 55	93.67 52	95.86 79	92.86 45	97.51 26	93.79 72	91.76 166	97.03 76	97.03 68	98.61 177	99.28 31
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPP-MVSNet		95.27 65	96.18 61	94.20 106	94.88 108	98.64 78	94.97 136	90.70 117	95.34 94	89.67 98	91.66 83	93.84 71	95.42 111	97.32 66	97.00 70	99.58 11	99.47 18

E6new		93.85 112	93.39 125	94.39 97	94.50 134	98.53 90	95.93 114	91.41 107	93.47 141	88.81 118	85.51 156	84.16 151	96.46 82	96.32 111	96.99 71	99.21 98	98.78 98

E6		93.85 112	93.39 125	94.39 97	94.50 134	98.53 90	95.93 114	91.41 107	93.47 141	88.81 118	85.51 156	84.16 151	96.46 82	96.32 111	96.99 71	99.21 98	98.78 98

FMVSNet2		93.30 127	93.36 129	93.22 125	91.34 179	95.86 176	96.22 93	88.24 151	95.15 106	89.92 96	81.64 181	89.36 97	94.40 128	96.77 86	96.98 73	99.21 98	97.79 156

CHOSEN 280x420		95.46 60	97.01 47	93.66 117	97.28 66	97.98 118	96.40 89	85.39 193	96.10 70	91.07 68	96.53 34	96.34 56	95.61 103	97.65 56	96.95 74	96.21 226	97.49 169

E4		93.88 111	93.38 127	94.48 94	94.50 134	98.51 92	96.08 105	91.74 95	93.42 145	88.84 117	85.51 156	84.38 145	96.49 79	96.22 116	96.90 75	99.22 92	98.69 103

E3new		94.34 92	93.98 108	94.75 83	94.56 126	98.56 87	96.13 101	91.78 91	94.54 120	90.22 87	87.24 124	85.36 133	96.62 71	96.61 93	96.90 75	99.22 92	98.68 104

E3		94.33 93	93.99 107	94.73 84	94.56 126	98.56 87	96.14 99	91.78 91	94.55 118	90.05 91	87.23 125	85.39 131	96.61 73	96.61 93	96.90 75	99.21 98	98.68 104

baseline1		94.59 82	94.47 89	94.72 85	95.16 101	97.97 119	96.07 107	91.94 79	94.86 113	89.98 93	91.60 84	85.87 127	95.64 100	97.07 74	96.90 75	99.52 22	97.06 184

MVS_Test		94.82 73	95.66 65	93.84 114	94.79 111	98.35 103	96.49 86	89.10 142	96.12 69	87.09 136	92.58 71	90.61 89	96.48 80	96.51 104	96.89 79	99.11 120	98.54 120

viewdifsd2359ckpt07		94.23 97	94.19 99	94.27 103	94.69 120	98.45 100	96.06 109	91.72 96	95.09 108	88.79 120	86.81 129	86.35 120	95.64 100	97.38 64	96.88 80	98.68 170	98.40 133

viewcassd2359sk11		94.63 80	94.45 90	94.84 78	94.58 124	98.57 85	96.13 101	91.79 89	95.32 95	90.67 78	88.73 109	86.13 121	96.65 69	96.82 80	96.87 81	99.21 98	98.68 104

E5new		93.95 105	93.42 123	94.57 89	94.50 134	98.51 92	96.18 96	91.84 81	93.55 139	89.12 112	85.80 153	84.38 145	96.53 77	96.16 123	96.85 82	99.23 90	98.67 107

E5		93.95 105	93.42 123	94.57 89	94.50 134	98.51 92	96.18 96	91.84 81	93.55 139	89.12 112	85.80 153	84.38 145	96.53 77	96.16 123	96.85 82	99.23 90	98.67 107

E2		94.88 71	94.85 85	94.91 73	94.58 124	98.59 82	96.16 98	91.80 88	95.88 77	91.04 69	90.11 101	86.91 113	96.68 68	96.91 79	96.85 82	99.19 107	98.70 102

gg-mvs-nofinetune		86.17 222	88.57 189	83.36 233	93.44 157	98.15 113	96.58 83	72.05 252	74.12 254	49.23 260	64.81 247	90.85 87	89.90 204	97.83 51	96.84 85	98.97 139	97.41 172

CANet_DTU		93.92 109	96.57 54	90.83 152	95.63 86	98.39 102	96.99 63	87.38 159	96.26 63	71.97 216	96.31 36	93.02 75	94.53 125	97.38 64	96.83 86	98.49 184	97.79 156

OMC-MVS		97.00 41	96.92 50	97.09 35	98.69 40	98.66 75	97.85 49	95.02 44	98.09 15	94.47 30	93.15 64	96.90 48	97.38 48	97.16 72	96.82 87	99.13 117	97.65 164

FMVSNet3		93.79 117	94.17 102	93.35 124	91.21 182	95.99 169	96.62 80	88.68 145	95.23 100	90.40 82	86.39 142	91.16 83	94.11 134	95.96 129	96.67 88	99.07 127	97.79 156

diffmvs_AUTHOR		94.09 101	93.86 111	94.36 100	94.60 123	98.31 104	96.29 92	91.51 102	96.39 60	88.49 122	87.35 120	83.32 160	96.16 92	96.17 122	96.64 89	99.10 121	98.82 95

CNLPA		96.90 44	96.28 58	97.64 29	98.56 43	98.63 80	96.85 70	96.60 38	97.73 21	97.08 8	89.78 104	96.28 57	97.80 40	96.73 88	96.63 90	98.94 143	98.14 147

viewdifsd2359ckpt13		94.14 98	94.00 105	94.30 102	94.55 128	98.55 89	95.71 124	91.76 93	95.03 110	88.12 128	87.34 121	85.15 137	96.39 85	96.81 84	96.60 91	99.24 83	98.50 123

UGNet		94.92 69	96.63 53	92.93 126	96.03 82	98.63 80	94.53 151	91.52 101	96.23 64	90.03 92	92.87 69	96.10 60	86.28 222	96.68 91	96.60 91	99.16 113	99.32 29
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
viewdifsd2359ckpt09		94.40 90	94.26 95	94.57 89	94.51 131	98.50 98	95.96 113	91.72 96	95.31 99	89.37 106	88.33 115	85.88 126	96.64 70	96.61 93	96.57 93	99.20 105	98.60 115

casdiffseed414692147		93.07 131	92.06 157	94.25 105	94.46 139	98.28 105	95.61 125	91.28 111	92.74 154	88.58 121	82.11 179	80.19 174	96.25 88	96.05 126	96.49 94	99.32 67	98.57 117

CHOSEN 1792x2688		92.66 136	92.49 145	92.85 127	97.13 67	98.89 60	95.90 117	88.50 149	95.32 95	83.31 151	71.99 232	88.96 103	94.10 135	96.69 90	96.49 94	98.15 195	99.10 55

CDS-MVSNet		92.77 134	93.60 118	91.80 137	92.63 168	96.80 145	95.24 131	89.14 141	90.30 190	84.58 145	86.76 130	90.65 88	90.42 197	95.89 131	96.49 94	98.79 162	98.32 141
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
diffmvs		94.31 95	94.21 98	94.42 96	94.64 121	98.28 105	96.36 90	91.56 99	96.77 50	88.89 116	88.97 107	84.23 150	96.01 96	96.05 126	96.41 97	99.05 134	98.79 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GBi-Net		93.81 115	94.18 100	93.38 122	91.34 179	95.86 176	96.22 93	88.68 145	95.23 100	90.40 82	86.39 142	91.16 83	94.40 128	96.52 101	96.30 98	99.21 98	97.79 156

test1		93.81 115	94.18 100	93.38 122	91.34 179	95.86 176	96.22 93	88.68 145	95.23 100	90.40 82	86.39 142	91.16 83	94.40 128	96.52 101	96.30 98	99.21 98	97.79 156

FMVSNet1		91.54 150	90.93 172	92.26 132	90.35 189	95.27 198	95.22 132	87.16 162	91.37 177	87.62 132	75.45 209	83.84 155	94.43 126	96.52 101	96.30 98	98.82 155	97.74 162

DI_MVS_pp		94.01 103	93.63 117	94.44 95	94.54 130	98.26 108	97.51 54	90.63 118	95.88 77	89.34 108	80.54 190	89.36 97	95.48 109	96.33 110	96.27 101	99.17 110	98.78 98

AdaColmap		97.53 32	96.93 49	98.24 15	99.21 24	98.77 66	98.47 36	97.34 25	96.68 53	96.52 15	95.11 51	96.12 59	98.72 15	97.19 71	96.24 102	99.17 110	98.39 135

Fast-Effi-MVS+		91.87 142	92.08 156	91.62 141	92.91 164	97.21 137	94.93 137	84.60 206	93.61 136	81.49 161	83.50 172	78.95 179	96.62 71	96.55 99	96.22 103	99.16 113	98.51 122

PLC	94.95 3	97.37 35	96.77 52	98.07 21	98.97 32	98.21 109	97.94 48	96.85 37	97.66 27	97.58 5	93.33 63	96.84 50	98.01 37	97.13 73	96.20 104	99.09 123	98.01 151
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
baseline		94.83 72	95.82 64	93.68 116	94.75 114	97.80 120	96.51 85	88.53 148	97.02 48	89.34 108	92.93 67	92.18 80	94.69 121	95.78 136	96.08 105	98.27 193	98.97 79

CPTT-MVS		97.78 28	97.54 37	98.05 22	98.91 36	99.05 38	99.00 23	96.96 35	97.14 43	95.92 19	95.50 46	98.78 29	98.99 4	97.20 69	96.07 106	98.54 181	99.04 67

Effi-MVS+		92.93 133	93.86 111	91.86 135	94.07 148	98.09 116	95.59 126	85.98 177	94.27 126	79.54 171	91.12 91	81.81 168	96.71 66	96.67 92	96.06 107	99.27 78	98.98 75

gm-plane-assit		83.26 236	85.29 233	80.89 237	89.52 202	89.89 248	70.26 257	78.24 232	77.11 252	58.01 257	74.16 220	66.90 243	90.63 195	97.20 69	96.05 108	98.66 174	95.68 212

DCV-MVSNet		94.76 78	95.12 80	94.35 101	95.10 104	95.81 180	96.46 87	89.49 136	96.33 62	90.16 88	92.55 72	90.26 91	95.83 98	95.52 144	96.03 109	99.06 130	99.33 26

IterMVS-LS		92.56 137	93.18 131	91.84 136	93.90 150	94.97 205	94.99 135	86.20 172	94.18 127	82.68 153	85.81 152	87.36 112	94.43 126	95.31 150	96.02 110	98.87 151	98.60 115
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMMP		97.37 35	97.48 39	97.25 32	98.88 38	99.28 26	98.47 36	96.86 36	97.04 47	92.15 53	97.57 25	96.05 61	97.67 41	97.27 67	95.99 111	99.46 34	99.14 54
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
thres100view900		93.55 123	92.47 148	94.81 80	95.33 92	98.74 67	96.78 76	92.30 73	92.63 156	88.29 123	87.21 126	78.01 186	96.78 64	96.38 106	95.92 112	99.38 59	98.40 133

thres200		93.62 120	92.54 142	94.88 75	95.36 91	98.93 54	96.75 77	92.31 70	92.84 152	88.28 125	86.99 128	77.81 193	97.13 54	96.82 80	95.92 112	99.45 38	98.49 125

TAPA-MVS	94.18 5	96.38 52	96.49 56	96.25 45	98.26 49	98.66 75	98.00 46	94.96 45	97.17 41	89.48 102	92.91 68	96.35 55	97.53 45	96.59 97	95.90 114	99.28 75	97.82 155
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVSTER		94.89 70	95.07 81	94.68 87	94.71 117	96.68 151	97.00 62	90.57 119	95.18 105	93.05 41	95.21 49	86.41 118	93.72 144	97.59 58	95.88 115	99.00 136	98.50 123

tfpn200view9		93.64 119	92.57 141	94.89 74	95.33 92	98.94 52	96.82 71	92.31 70	92.63 156	88.29 123	87.21 126	78.01 186	97.12 56	96.82 80	95.85 116	99.45 38	98.56 118

thres400		93.56 122	92.43 149	94.87 77	95.40 90	98.91 57	96.70 79	92.38 69	92.93 151	88.19 127	86.69 132	77.35 195	97.13 54	96.75 87	95.85 116	99.42 50	98.56 118

GeoE		92.52 138	92.64 140	92.39 131	93.96 149	97.76 121	96.01 112	85.60 188	93.23 146	83.94 147	81.56 182	84.80 142	95.63 102	96.22 116	95.83 118	99.19 107	99.07 62

Anonymous202405211			92.18 154		95.04 105	98.20 110	96.14 99	91.79 89	93.93 129		74.60 215	88.38 108	96.48 80	95.17 154	95.82 119	99.00 136	99.15 52

viewmambaseed2359dif		93.92 109	93.38 127	94.54 92	94.55 128	98.15 113	96.41 88	91.47 104	95.10 107	89.58 100	86.64 133	85.10 139	96.17 90	94.08 176	95.77 120	99.09 123	98.84 92

LGP-MVS_train		94.12 100	94.62 86	93.53 118	96.44 74	97.54 124	97.40 56	91.84 81	94.66 115	81.09 163	95.70 45	83.36 159	95.10 115	96.36 109	95.71 121	99.32 67	99.03 68

thres600view7		93.49 124	92.37 152	94.79 81	95.42 89	98.93 54	96.58 83	92.31 70	93.04 149	87.88 130	86.62 135	76.94 198	97.09 57	96.82 80	95.63 122	99.45 38	98.63 112

MSDG		94.82 73	93.73 115	96.09 49	98.34 48	97.43 129	97.06 61	96.05 39	95.84 80	90.56 80	86.30 147	89.10 102	95.55 107	96.13 125	95.61 123	99.00 136	95.73 211

EPNet_dtu		92.45 139	95.02 82	89.46 173	98.02 54	95.47 191	94.79 143	92.62 68	94.97 111	70.11 227	94.76 56	92.61 79	84.07 236	95.94 130	95.56 124	97.15 214	95.82 210
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		92.03 140	91.55 165	92.58 128	97.13 67	98.72 69	94.65 147	86.54 168	93.58 138	82.56 154	67.75 243	90.47 90	95.67 99	95.87 132	95.54 125	98.91 147	98.93 80

Anonymous20231211		93.49 124	92.33 153	94.84 78	94.78 113	98.00 117	96.11 103	91.85 80	94.86 113	90.91 71	74.69 214	89.18 100	96.73 65	94.82 160	95.51 126	98.67 171	99.24 39

Effi-MVS+-dtu		91.78 145	93.59 119	89.68 170	92.44 170	97.11 138	94.40 154	84.94 202	92.43 161	75.48 198	91.09 92	83.75 156	93.55 147	96.61 93	95.47 127	97.24 213	98.67 107

GG-mvs-BLEND		66.17 251	94.91 84	32.63 256	1.32 265	96.64 152	91.40 211	0.85 263	94.39 124	2.20 267	90.15 100	95.70 63	2.27 262	96.39 105	95.44 128	97.78 203	95.68 212

MIMVSNet		88.99 188	91.07 170	86.57 221	86.78 230	95.62 184	91.20 216	75.40 246	90.65 186	76.57 190	84.05 169	82.44 167	91.01 180	95.84 133	95.38 129	98.48 185	93.50 236

ET-MVSNet_ETH3D		93.34 126	94.33 94	92.18 133	83.26 242	97.66 123	96.72 78	89.89 127	95.62 88	87.17 135	96.00 41	83.69 157	96.99 59	93.78 177	95.34 130	99.06 130	98.18 146

FC-MVSNet-train		93.85 112	93.91 109	93.78 115	94.94 107	96.79 148	94.29 156	91.13 112	93.84 133	88.26 126	90.40 97	85.23 136	94.65 124	96.54 100	95.31 131	99.38 59	99.28 31

CVMVSNet		89.77 174	91.66 162	87.56 206	93.21 162	95.45 192	91.94 201	89.22 139	89.62 194	69.34 233	83.99 170	85.90 125	84.81 231	94.30 171	95.28 132	96.85 216	97.09 180

UniMVSNet_ETH3D		88.47 194	86.00 226	91.35 145	91.55 176	96.29 162	92.53 183	88.81 144	85.58 234	82.33 155	67.63 244	66.87 244	94.04 137	91.49 215	95.24 133	98.84 154	98.92 81

PatchMatch-RL		94.69 79	94.41 91	95.02 68	97.63 61	98.15 113	94.50 153	91.99 76	95.32 95	91.31 61	95.47 47	83.44 158	96.02 95	96.56 98	95.23 134	98.69 169	96.67 193

TSAR-MVS + COLMAP		94.79 75	94.51 88	95.11 66	96.50 72	97.54 124	97.99 47	94.54 46	97.81 19	85.88 141	96.73 33	81.28 171	96.99 59	96.29 113	95.21 135	98.76 165	96.73 192

FA-MVS(training)		93.94 107	95.16 77	92.53 129	94.87 109	98.57 85	95.42 129	79.49 230	95.37 92	90.98 70	86.54 138	94.26 70	95.44 110	97.80 54	95.19 136	98.97 139	98.38 136

test0.0.03 1		91.97 141	93.91 109	89.72 167	93.31 160	96.40 160	91.34 213	87.06 163	93.86 131	81.67 159	91.15 90	89.16 101	86.02 224	95.08 155	95.09 137	98.91 147	96.64 195

dmvs_re		91.84 143	91.60 164	92.12 134	91.60 175	97.26 134	95.14 133	91.96 77	91.02 181	80.98 164	86.56 137	77.96 188	93.84 141	94.71 161	95.08 138	99.22 92	98.62 114

baseline2		93.01 132	94.17 102	91.64 139	92.83 166	97.49 126	93.40 169	87.53 157	93.67 135	86.07 140	91.83 81	86.58 115	91.36 171	96.38 106	95.06 139	98.67 171	98.20 145

CLD-MVS		94.79 75	94.36 93	95.30 63	95.21 100	97.46 127	97.23 59	92.24 74	96.43 58	91.77 57	92.69 70	84.31 148	96.06 93	95.52 144	95.03 140	99.31 71	99.06 63
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
FC-MVSNet-test		91.63 147	93.82 114	89.08 177	92.02 173	96.40 160	93.26 172	87.26 160	93.72 134	77.26 185	88.61 113	89.86 94	85.50 226	95.72 141	95.02 141	99.16 113	97.44 171

PMMVS		94.61 81	95.56 67	93.50 119	94.30 144	96.74 149	94.91 138	89.56 135	95.58 90	87.72 131	96.15 37	92.86 76	96.06 93	95.47 146	95.02 141	98.43 190	97.09 180

OPM-MVS		93.61 121	92.43 149	95.00 69	96.94 69	97.34 132	97.78 50	94.23 48	89.64 193	85.53 142	88.70 111	82.81 164	96.28 87	96.28 114	95.00 143	99.24 83	97.22 177
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PCF-MVS	93.95 6	95.65 56	95.14 78	96.25 45	97.73 60	98.73 68	97.59 53	97.13 32	92.50 160	89.09 115	89.85 103	96.65 52	96.90 61	94.97 159	94.89 144	99.08 125	98.38 136
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thisisatest0530		94.54 84	95.47 69	93.46 120	94.51 131	98.65 77	94.66 146	90.72 115	95.69 86	86.90 137	93.80 58	89.44 96	94.74 119	96.98 78	94.86 145	99.19 107	98.85 90

tttt0517		94.52 85	95.44 72	93.44 121	94.51 131	98.68 73	94.61 149	90.72 115	95.61 89	86.84 138	93.78 59	89.26 99	94.74 119	97.02 77	94.86 145	99.20 105	98.87 88

LTVRE_ROB	87.32 16	87.55 209	88.25 192	86.73 219	90.66 184	95.80 181	93.05 175	84.77 203	83.35 240	60.32 252	83.12 174	67.39 242	93.32 150	94.36 170	94.86 145	98.28 192	98.87 88
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
HQP-MVS		94.43 87	94.57 87	94.27 103	96.41 75	97.23 136	96.89 67	93.98 50	95.94 75	83.68 149	95.01 52	84.46 143	95.58 106	95.47 146	94.85 148	99.07 127	99.00 72

ACMP	92.88 9	94.43 87	94.38 92	94.50 93	96.01 83	97.69 122	95.85 122	92.09 75	95.74 82	89.12 112	95.14 50	82.62 166	94.77 118	95.73 139	94.67 149	99.14 116	99.06 63
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	92.75 10	94.41 89	93.84 113	95.09 67	96.41 75	96.80 145	94.88 141	93.54 53	96.41 59	90.16 88	92.31 74	83.11 161	96.32 86	96.22 116	94.65 150	99.22 92	97.35 174
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Fast-Effi-MVS+-dtu		91.19 153	93.64 116	88.33 186	92.19 172	96.46 157	93.99 159	81.52 225	92.59 158	71.82 217	92.17 75	85.54 129	91.68 167	95.73 139	94.64 151	98.80 160	98.34 138

viewdifsd2359ckpt11		93.27 128	92.72 137	93.91 111	94.46 139	97.42 130	94.91 138	91.42 105	95.74 82	89.57 101	87.34 121	82.87 163	95.61 103	92.62 197	94.62 152	97.49 210	98.44 126

viewmsd2359difaftdt		93.27 128	92.72 137	93.91 111	94.46 139	97.42 130	94.91 138	91.42 105	95.69 86	89.59 99	87.34 121	82.90 162	95.60 105	92.62 197	94.62 152	97.49 210	98.44 126

TAMVS		90.54 163	90.87 174	90.16 162	91.48 177	96.61 153	93.26 172	86.08 175	87.71 212	81.66 160	83.11 175	84.04 153	90.42 197	94.54 164	94.60 154	98.04 200	95.48 216

TranMVSNet+NR-MVSNet		89.23 184	88.48 190	90.11 166	89.07 214	95.25 199	92.91 177	90.43 121	90.31 189	77.10 187	76.62 207	71.57 224	91.83 165	92.12 206	94.59 155	99.32 67	98.92 81

DU-MVS		89.67 175	88.84 186	90.63 156	89.26 208	95.61 185	92.48 184	89.91 125	91.22 178	79.57 169	77.72 203	71.18 226	93.21 153	92.53 200	94.57 156	99.35 64	99.05 65

CR-MVSNet		90.16 169	91.96 160	88.06 192	93.32 159	95.95 173	93.36 170	75.99 244	92.40 163	75.19 202	83.18 173	85.37 132	92.05 161	95.21 152	94.56 157	98.47 186	97.08 182

PatchT		89.13 186	91.71 161	86.11 225	92.92 163	95.59 187	83.64 244	75.09 247	91.87 172	75.19 202	82.63 176	85.06 140	92.05 161	95.21 152	94.56 157	97.76 204	97.08 182

ACMH	90.77 13	91.51 151	91.63 163	91.38 143	95.62 87	96.87 143	91.76 202	89.66 133	91.58 175	78.67 176	86.73 131	78.12 182	93.77 143	94.59 163	94.54 159	98.78 163	98.98 75
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet5		90.36 164	90.93 172	89.70 168	87.99 224	92.25 234	92.03 197	83.51 213	92.20 169	84.13 146	85.59 155	86.48 116	92.43 158	94.61 162	94.52 160	98.13 196	90.85 245

pm-mvs1		89.19 185	89.02 185	89.38 175	90.40 187	95.74 183	92.05 196	88.10 153	86.13 230	77.70 182	73.72 223	79.44 178	88.97 209	95.81 135	94.51 161	99.08 125	97.78 161

UniMVSNet_NR-MVSNet		90.35 165	89.96 178	90.80 153	89.66 198	95.83 179	92.48 184	90.53 120	90.96 183	79.57 169	79.33 194	77.14 196	93.21 153	92.91 194	94.50 162	99.37 61	99.05 65

IB-MVS	89.56 15	91.71 146	92.50 144	90.79 154	95.94 84	98.44 101	87.05 235	91.38 110	93.15 147	92.98 44	84.78 163	85.14 138	78.27 242	92.47 202	94.44 163	99.10 121	99.08 58
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
IterMVS-SCA-FT		90.24 166	92.48 147	87.63 203	92.85 165	94.30 222	93.79 161	81.47 226	92.66 155	69.95 228	84.66 165	88.38 108	89.99 202	95.39 149	94.34 164	97.74 207	97.63 165

test-mter		90.95 155	93.54 122	87.93 198	90.28 190	96.80 145	91.44 210	82.68 219	92.15 170	74.37 209	89.57 105	88.23 110	90.88 184	96.37 108	94.31 165	97.93 202	97.37 173

anonymousdsp		88.90 189	91.00 171	86.44 222	88.74 221	95.97 171	90.40 223	82.86 217	88.77 200	67.33 237	81.18 185	81.44 170	90.22 200	96.23 115	94.27 166	99.12 119	99.16 51

IterMVS		90.20 167	92.43 149	87.61 204	92.82 167	94.31 221	94.11 157	81.54 224	92.97 150	69.90 229	84.71 164	88.16 111	89.96 203	95.25 151	94.17 167	97.31 212	97.46 170
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
COLMAP_ROB	90.49 14	93.27 128	92.71 139	93.93 110	97.75 59	97.44 128	96.07 107	93.17 61	95.40 91	83.86 148	83.76 171	88.72 104	93.87 139	94.25 172	94.11 168	98.87 151	95.28 218
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test-LLR		91.62 148	93.56 120	89.35 176	93.31 160	96.57 154	92.02 198	87.06 163	92.34 166	75.05 205	90.20 98	88.64 105	90.93 181	96.19 120	94.07 169	97.75 205	96.90 188

TESTMET0.1,1		91.07 154	93.56 120	88.17 188	90.43 186	96.57 154	92.02 198	82.83 218	92.34 166	75.05 205	90.20 98	88.64 105	90.93 181	96.19 120	94.07 169	97.75 205	96.90 188

tfpnnormal		88.50 192	87.01 214	90.23 160	91.36 178	95.78 182	92.74 179	90.09 123	83.65 239	76.33 193	71.46 235	69.58 235	91.84 164	95.54 143	94.02 171	99.06 130	99.03 68

NR-MVSNet		89.34 180	88.66 187	90.13 165	90.40 187	95.61 185	93.04 176	89.91 125	91.22 178	78.96 174	77.72 203	68.90 238	89.16 208	94.24 173	93.95 172	99.32 67	98.99 73

TransMVSNet (Re)		87.73 208	86.79 216	88.83 180	90.76 183	94.40 219	91.33 214	89.62 134	84.73 236	75.41 200	72.73 228	71.41 225	86.80 218	94.53 165	93.93 173	99.06 130	95.83 209

ACMH+	90.88 12	91.41 152	91.13 169	91.74 138	95.11 103	96.95 140	93.13 174	89.48 137	92.42 162	79.93 168	85.13 160	78.02 184	93.82 142	93.49 184	93.88 174	98.94 143	97.99 152

UniMVSNet (Re)		90.03 172	89.61 181	90.51 158	89.97 195	96.12 166	92.32 188	89.26 138	90.99 182	80.95 165	78.25 200	75.08 209	91.14 177	93.78 177	93.87 175	99.41 53	99.21 44

RPMNet		90.19 168	92.03 159	88.05 193	93.46 156	95.95 173	93.41 168	74.59 249	92.40 163	75.91 196	84.22 168	86.41 118	92.49 157	94.42 168	93.85 176	98.44 188	96.96 185

Baseline_NR-MVSNet		89.27 183	88.01 197	90.73 155	89.26 208	93.71 228	92.71 181	89.78 131	90.73 184	81.28 162	73.53 224	72.85 218	92.30 160	92.53 200	93.84 177	99.07 127	98.88 86

testgi		89.42 177	91.50 166	87.00 213	92.40 171	95.59 187	89.15 229	85.27 197	92.78 153	72.42 214	91.75 82	76.00 205	84.09 235	94.38 169	93.82 178	98.65 175	96.15 201

usedtu_dtu_shiyan1		90.61 160	91.45 167	89.62 171	85.03 237	96.03 168	93.51 166	89.17 140	93.13 148	79.51 172	81.79 180	84.24 149	91.63 168	95.06 157	93.79 179	98.88 149	96.12 203

GA-MVS		89.28 182	90.75 175	87.57 205	91.77 174	96.48 156	92.29 190	87.58 156	90.61 187	65.77 240	84.48 166	76.84 199	89.46 206	95.84 133	93.68 180	98.52 182	97.34 175

CP-MVSNet		87.89 205	87.27 209	88.62 182	89.30 206	95.06 202	90.60 221	85.78 181	87.43 217	75.98 195	74.60 215	68.14 241	90.76 190	93.07 192	93.60 181	99.30 73	98.98 75

PS-CasMVS		87.33 213	86.68 222	88.10 189	89.22 213	94.93 207	90.35 224	85.70 182	86.44 229	74.01 210	73.43 225	66.59 247	90.04 201	92.92 193	93.52 182	99.28 75	98.91 84

PEN-MVS		87.22 215	86.50 224	88.07 190	88.88 217	94.44 217	90.99 218	86.21 170	86.53 227	73.66 211	74.97 212	66.56 248	89.42 207	91.20 217	93.48 183	99.24 83	98.31 142

USDC		90.69 158	90.52 176	90.88 151	94.17 146	96.43 158	95.82 123	86.76 165	93.92 130	76.27 194	86.49 139	74.30 212	93.67 146	95.04 158	93.36 184	98.61 177	94.13 227

EG-PatchMatch MVS		86.68 217	87.24 210	86.02 226	90.58 185	96.26 163	91.08 217	81.59 223	84.96 235	69.80 231	71.35 236	75.08 209	84.23 234	94.24 173	93.35 185	98.82 155	95.46 217

WR-MVS		87.93 202	88.09 194	87.75 200	89.26 208	95.28 196	90.81 219	86.69 166	88.90 197	75.29 201	74.31 219	73.72 215	85.19 229	92.26 203	93.32 186	99.27 78	98.81 96

thisisatest0515		90.12 170	92.06 157	87.85 199	90.03 193	96.17 165	87.83 232	87.45 158	91.71 174	77.15 186	85.40 159	84.01 154	85.74 225	95.41 148	93.30 187	98.88 149	98.43 129

TinyColmap		89.42 177	88.58 188	90.40 159	93.80 154	95.45 192	93.96 160	86.54 168	92.24 168	76.49 191	80.83 186	70.44 230	93.37 149	94.45 167	93.30 187	98.26 194	93.37 238

DTE-MVSNet		86.67 218	86.09 225	87.35 209	88.45 223	94.08 224	90.65 220	86.05 176	86.13 230	72.19 215	74.58 217	66.77 246	87.61 215	90.31 221	93.12 189	99.13 117	97.62 166

WR-MVS_H		87.93 202	87.85 201	88.03 195	89.62 199	95.58 189	90.47 222	85.55 189	87.20 218	76.83 189	74.42 218	72.67 220	86.37 221	93.22 189	93.04 190	99.33 65	98.83 93

MS-PatchMatch		91.82 144	92.51 143	91.02 148	95.83 85	96.88 141	95.05 134	84.55 208	93.85 132	82.01 156	82.51 177	91.71 81	90.52 196	95.07 156	93.03 191	98.13 196	94.52 220

v7n		86.43 219	86.52 223	86.33 223	87.91 225	94.93 207	90.15 225	83.05 215	86.57 226	70.21 226	71.48 234	66.78 245	87.72 213	94.19 175	92.96 192	98.92 145	98.76 101

v2v482		88.25 197	87.71 205	88.88 179	89.23 212	95.28 196	92.10 194	87.89 155	88.69 201	73.31 212	75.32 210	71.64 223	91.89 163	92.10 208	92.92 193	98.86 153	97.99 152

v10		88.00 199	87.96 198	88.05 193	89.44 203	94.68 212	92.36 187	83.35 214	89.37 195	72.96 213	73.98 221	72.79 219	91.35 172	93.59 179	92.88 194	98.81 158	98.42 131

pmmvs5		87.83 206	88.09 194	87.51 208	89.59 201	95.48 190	89.75 227	84.73 204	86.07 232	71.44 219	80.57 189	70.09 233	90.74 192	94.47 166	92.87 195	98.82 155	97.10 179

v1192		87.51 210	87.31 208	87.74 201	89.04 215	94.87 210	92.07 195	85.03 199	88.49 204	70.32 224	72.65 229	70.35 231	91.21 176	93.59 179	92.80 196	98.78 163	98.42 131

v1144		87.92 204	87.79 202	88.07 190	89.27 207	95.15 201	92.17 193	85.62 187	88.52 203	71.52 218	73.80 222	72.40 221	91.06 179	93.54 183	92.80 196	98.81 158	98.33 139

V42		88.31 196	87.95 199	88.73 181	89.44 203	95.34 195	92.23 192	87.21 161	88.83 198	74.49 208	74.89 213	73.43 217	90.41 199	92.08 209	92.77 198	98.60 179	98.33 139

v8		88.21 198	87.94 200	88.51 183	89.62 199	95.01 204	92.31 189	84.99 200	88.94 196	74.70 207	75.03 211	73.51 216	90.67 193	92.11 207	92.74 199	98.80 160	98.24 143

v1240		86.89 216	86.75 218	87.06 212	88.75 220	94.65 214	91.30 215	84.05 209	87.49 216	68.94 234	71.96 233	68.86 239	90.65 194	93.33 186	92.72 200	98.67 171	98.24 143

v1921920		87.31 214	87.13 212	87.52 207	88.87 218	94.72 211	91.96 200	84.59 207	88.28 205	69.86 230	72.50 230	70.03 234	91.10 178	93.33 186	92.61 201	98.71 167	98.44 126

v144192		87.40 212	87.20 211	87.64 202	88.89 216	94.88 209	91.65 205	84.70 205	87.80 211	71.17 222	73.20 227	70.91 227	90.75 191	92.69 196	92.49 202	98.71 167	98.43 129

Anonymous20231206		83.84 235	85.19 234	82.26 236	87.38 228	92.87 230	85.49 240	83.65 211	86.07 232	63.44 247	68.42 240	69.01 237	75.45 246	93.34 185	92.44 203	98.12 198	94.20 226

pmmvs6		85.98 228	84.89 236	87.25 210	88.83 219	94.35 220	89.36 228	85.30 196	78.51 251	75.44 199	62.71 249	75.41 206	87.65 214	93.58 181	92.40 204	96.89 215	97.29 176

v148		87.51 210	86.79 216	88.36 185	89.39 205	95.21 200	89.84 226	88.20 152	87.61 215	77.56 183	73.38 226	70.32 232	86.80 218	90.70 220	92.31 205	98.37 191	97.98 154

EU-MVSNet		85.62 229	87.65 207	83.24 234	88.54 222	92.77 232	87.12 234	85.32 194	86.71 225	64.54 243	78.52 196	75.11 208	78.35 241	92.25 204	92.28 206	95.58 237	95.93 205

pmmvs4		90.55 162	89.91 179	91.30 146	90.26 191	94.95 206	92.73 180	87.94 154	93.44 144	85.35 143	82.28 178	76.09 204	93.02 155	93.56 182	92.26 207	98.51 183	96.77 191

MVS-HIRNet		85.36 230	86.89 215	83.57 232	90.13 192	94.51 216	83.57 245	72.61 251	88.27 206	71.22 221	68.97 239	81.81 168	88.91 210	93.08 191	91.94 208	94.97 245	89.64 248

TDRefinement		89.07 187	88.15 193	90.14 164	95.16 101	96.88 141	95.55 128	90.20 122	89.68 192	76.42 192	76.67 206	74.30 212	84.85 230	93.11 190	91.91 209	98.64 176	94.47 221

SixPastTwentyTwo		88.37 195	89.47 182	87.08 211	90.01 194	95.93 175	87.41 233	85.32 194	90.26 191	70.26 225	86.34 146	71.95 222	90.93 181	92.89 195	91.72 210	98.55 180	97.22 177

MIMVSNet1		80.03 241	80.93 242	78.97 241	72.46 256	90.73 246	80.81 251	82.44 220	80.39 247	63.64 245	57.57 251	64.93 249	76.37 244	91.66 213	91.55 211	98.07 199	89.70 247

FE-MVSNET2		81.81 238	81.15 241	82.57 235	75.40 254	92.39 233	86.04 238	83.61 212	81.61 245	68.16 236	55.75 252	59.22 256	83.77 237	93.31 188	91.54 212	98.45 187	94.24 225

test20.03		82.92 237	85.52 228	79.90 240	87.75 226	91.84 243	82.80 246	82.99 216	82.65 244	60.32 252	78.90 195	70.50 228	67.10 251	92.05 210	90.89 213	98.44 188	91.80 243

MDTV_nov1_ep13		91.57 149	93.18 131	89.70 168	93.39 158	96.97 139	93.53 165	80.91 227	95.70 84	81.86 157	92.40 73	89.93 93	93.25 152	91.97 211	90.80 214	95.25 242	94.46 222

FE-MVSNET		79.15 243	80.25 243	77.87 244	69.65 257	89.30 250	81.34 250	82.42 221	79.49 250	59.18 256	59.18 250	59.41 255	77.03 243	91.12 218	90.65 215	97.57 208	92.63 239

tpm		87.95 201	89.44 183	86.21 224	92.53 169	94.62 215	91.40 211	76.36 241	91.46 176	69.80 231	87.43 119	75.14 207	91.55 169	89.85 226	90.60 216	95.61 236	96.96 185

RPSCF		94.05 102	94.00 105	94.12 107	96.20 77	96.41 159	96.61 81	91.54 100	95.83 81	89.73 97	96.94 32	92.80 77	95.35 112	91.63 214	90.44 217	95.27 241	93.94 231

pmmvs-eth3d		84.33 234	82.94 239	85.96 227	84.16 239	90.94 245	86.55 236	83.79 210	84.25 237	75.85 197	70.64 237	56.43 258	87.44 217	92.20 205	90.41 218	97.97 201	95.68 212

EPMVS		90.88 157	92.12 155	89.44 174	94.71 117	97.24 135	93.55 164	76.81 237	95.89 76	81.77 158	91.49 86	86.47 117	93.87 139	90.21 222	90.07 219	95.92 230	93.49 237

SCA		90.92 156	93.04 133	88.45 184	93.72 155	97.33 133	92.77 178	76.08 243	96.02 72	78.26 181	91.96 78	90.86 86	93.99 138	90.98 219	90.04 220	95.88 231	94.06 230

PM-MVS		84.72 233	84.47 237	85.03 228	84.67 238	91.57 244	86.27 237	82.31 222	87.65 213	70.62 223	76.54 208	56.41 259	88.75 211	92.59 199	89.85 221	97.54 209	96.66 194

ADS-MVSNet		89.80 173	91.33 168	88.00 196	94.43 142	96.71 150	92.29 190	74.95 248	96.07 71	77.39 184	88.67 112	86.09 122	93.26 151	88.44 228	89.57 222	95.68 235	93.81 234

PatchmatchNet		90.56 161	92.49 145	88.31 187	93.83 153	96.86 144	92.42 186	76.50 240	95.96 74	78.31 180	91.96 78	89.66 95	93.48 148	90.04 224	89.20 223	95.32 239	93.73 235
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CostFormer		90.69 158	90.48 177	90.93 150	94.18 145	96.08 167	94.03 158	78.20 233	93.47 141	89.96 94	90.97 93	80.30 173	93.72 144	87.66 232	88.75 224	95.51 238	96.12 203

pmmvs3		79.16 242	80.12 245	78.05 243	79.36 243	86.59 253	78.13 254	73.87 250	76.42 253	57.51 258	70.59 238	57.02 257	84.66 232	90.10 223	88.32 225	94.75 247	91.77 244

MDTV_nov1_ep13_2view		86.30 220	88.27 191	84.01 231	87.71 227	94.67 213	88.08 231	76.78 238	90.59 188	68.66 235	80.46 191	80.12 175	87.58 216	89.95 225	88.20 226	95.25 242	93.90 233

0.4-1-1-0.1		89.64 176	88.08 196	91.46 142	86.21 231	94.41 218	94.79 143	86.20 172	88.54 202	91.15 66	86.64 133	78.03 183	94.36 131	84.47 245	88.05 227	96.08 229	96.40 196

0.3-1-1-0.015		89.40 179	87.72 204	91.36 144	86.10 233	94.08 224	94.62 148	86.10 174	88.02 207	91.16 62	86.39 142	77.89 189	94.30 132	83.93 248	87.88 228	95.88 231	95.86 208

CMPMVS	65.18 17	84.76 232	83.10 238	86.69 220	95.29 95	95.05 203	88.37 230	85.51 191	80.27 248	71.31 220	68.37 241	73.85 214	85.25 227	87.72 230	87.75 229	94.38 249	88.70 249
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
0.4-1-1-0.2		89.32 181	87.66 206	91.26 147	86.11 232	93.97 226	94.54 150	85.98 177	87.83 210	91.12 67	86.40 141	78.02 184	94.06 136	84.03 246	87.73 230	95.75 234	95.62 215

dps		90.11 171	89.37 184	90.98 149	93.89 151	96.21 164	93.49 167	77.61 235	91.95 171	92.74 48	88.85 108	78.77 181	92.37 159	87.71 231	87.71 231	95.80 233	94.38 223

new_pmnet		81.53 239	82.68 240	80.20 238	83.47 241	89.47 249	82.21 248	78.36 231	87.86 209	60.14 254	67.90 242	69.43 236	82.03 239	89.22 227	87.47 232	94.99 244	87.39 250

tpmrst		88.86 191	89.62 180	87.97 197	94.33 143	95.98 170	92.62 182	76.36 241	94.62 117	76.94 188	85.98 151	82.80 165	92.80 156	86.90 234	87.15 233	94.77 246	93.93 232

N_pmnet		84.80 231	85.10 235	84.45 230	89.25 211	92.86 231	84.04 243	86.21 170	88.78 199	66.73 239	72.41 231	74.87 211	85.21 228	88.32 229	86.45 234	95.30 240	92.04 242

MDA-MVSNet-bldmvs		80.11 240	80.24 244	79.94 239	77.01 252	93.21 229	78.86 253	85.94 180	82.71 243	60.86 249	79.71 193	51.77 261	83.71 238	75.60 253	86.37 235	93.28 251	92.35 240

tpm cat1		88.90 189	87.78 203	90.22 161	93.88 152	95.39 194	93.79 161	78.11 234	92.55 159	89.43 103	81.31 184	79.84 177	91.40 170	84.95 242	86.34 236	94.68 248	94.09 228

Gipuma		68.35 249	66.71 252	70.27 247	74.16 255	68.78 259	63.93 260	71.77 253	83.34 241	54.57 259	34.37 257	31.88 263	68.69 250	83.30 249	85.53 237	88.48 255	79.78 254
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ambc			73.83 251		76.23 253	85.13 254	82.27 247		84.16 238	65.58 242	52.82 254	23.31 266	73.55 248	91.41 216	85.26 238	92.97 252	94.70 219

pmnet_mix02		86.12 223	87.12 213	84.96 229	89.82 196	94.12 223	84.88 242	86.63 167	91.78 173	65.60 241	80.76 187	76.98 197	86.61 220	87.29 233	84.80 239	96.21 226	94.09 228

usedtu_dtu_shiyan2		75.82 246	75.29 249	76.44 246	65.25 259	87.28 251	82.09 249	76.55 239	68.86 255	66.94 238	48.90 255	60.22 253	74.42 247	83.98 247	83.40 240	93.39 250	94.38 223

blended_shiyan6		86.10 224	85.52 228	86.79 216	77.63 247	92.20 236	91.66 204	85.46 192	86.86 220	78.43 177	78.30 199	76.71 200	90.80 189	85.37 236	82.98 241	96.74 218	96.18 199

blended_shiyan8		86.10 224	85.44 230	86.88 215	77.65 246	92.22 235	91.69 203	85.52 190	86.88 219	78.82 175	78.06 202	76.43 203	90.85 186	85.36 237	82.97 242	96.74 218	96.14 202

gbinet_0.2-2-1-0.02		86.23 221	85.66 227	86.89 214	78.33 244	92.17 237	91.62 209	85.96 179	86.51 228	79.33 173	78.13 201	77.66 194	89.55 205	85.60 235	82.66 243	96.56 225	96.87 190

wanda-best-256-512		86.03 226	85.37 231	86.79 216	77.63 247	92.14 239	91.64 206	85.67 183	86.75 221	78.43 177	78.36 197	76.66 201	90.81 187	85.19 238	82.63 244	96.58 221	95.88 206

FE-blended-shiyan7		86.03 226	85.37 231	86.79 216	77.63 247	92.14 239	91.64 206	85.67 183	86.74 223	78.43 177	78.36 197	76.66 201	90.81 187	85.19 238	82.63 244	96.58 221	95.88 206

usedtu_blend_shiyan5		87.98 200	86.70 220	89.47 172	77.63 247	92.14 239	94.53 151	85.67 183	86.74 223	91.16 62	86.06 148	77.89 189	91.22 173	85.19 238	82.63 244	96.58 221	96.25 197

FE-MVSNET3		87.75 207	86.69 221	88.99 178	77.63 247	92.14 239	91.64 206	85.67 183	86.75 221	91.16 62	86.06 148	77.89 189	91.22 173	85.19 238	82.63 244	96.58 221	96.18 199

blend_shiyan4		88.50 192	86.74 219	90.54 157	85.31 236	92.15 238	93.79 161	85.10 198	87.64 214	91.16 62	86.06 148	77.89 189	91.22 173	84.59 243	82.60 248	96.67 220	96.25 197

test_method		72.96 247	78.68 246	66.28 250	50.17 262	64.90 260	75.45 256	50.90 259	87.89 208	62.54 248	62.98 248	68.34 240	70.45 249	91.90 212	82.41 249	88.19 256	92.35 240

WB-MVS		69.22 248	76.91 248	60.24 252	85.80 235	79.37 256	56.86 262	84.96 201	81.50 246	18.16 265	76.85 205	61.07 250	34.23 259	82.46 251	81.81 250	81.43 260	75.31 257

new-patchmatchnet		78.49 244	78.19 247	78.84 242	84.13 240	90.06 247	77.11 255	80.39 228	79.57 249	59.64 255	66.01 245	55.65 260	75.62 245	84.55 244	80.70 251	96.14 228	90.77 246

PMMVS2		64.36 252	65.94 254	62.52 251	67.37 258	77.44 257	64.39 259	69.32 257	61.47 257	34.59 261	46.09 256	41.03 262	48.02 258	74.56 255	78.23 252	91.43 253	82.76 252

tmp_tt				66.88 249	86.07 234	73.86 258	68.22 258	33.38 260	96.88 49	80.67 166	88.23 116	78.82 180	49.78 256	82.68 250	77.47 253	83.19 259

MVE	50.86 19	49.54 255	51.43 255	47.33 255	44.14 263	59.20 262	36.45 265	60.59 258	41.47 260	31.14 262	29.58 258	17.06 267	48.52 257	62.22 257	74.63 254	63.12 263	75.87 256
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
FPMVS		75.84 245	74.59 250	77.29 245	86.92 229	83.89 255	85.01 241	80.05 229	82.91 242	60.61 251	65.25 246	60.41 252	63.86 252	75.60 253	73.60 255	87.29 257	80.47 253

PMVS	63.12 18	67.27 250	66.39 253	68.30 248	77.98 245	60.24 261	59.53 261	76.82 236	66.65 256	60.74 250	54.39 253	59.82 254	51.24 255	73.92 256	70.52 256	83.48 258	79.17 255
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		50.67 253	47.85 256	53.96 253	64.13 261	50.98 264	38.06 263	69.51 255	51.40 259	24.60 263	29.46 260	24.39 265	56.07 254	48.17 258	59.70 257	71.40 261	70.84 258

EMVS		49.98 254	46.76 257	53.74 254	64.96 260	51.29 263	37.81 264	69.35 256	51.83 258	22.69 264	29.57 259	25.06 264	57.28 253	44.81 259	56.11 258	70.32 262	68.64 259

testmvs		12.09 256	16.94 258	6.42 257	3.15 264	6.08 265	9.51 267	3.84 261	21.46 261	5.31 266	27.49 261	6.76 268	10.89 260	17.06 260	15.01 259	5.84 264	24.75 260

test123		9.58 257	13.53 259	4.97 258	1.31 266	5.47 266	8.32 268	2.95 262	18.14 262	2.03 268	20.82 262	2.34 269	10.60 261	10.00 261	14.16 260	4.60 265	23.77 261

uanet_test		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet-low-res		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

TestfortrainingZip							99.35 6	97.66 9		98.71 2						99.42 50

TPM-MVS					98.94 33	98.47 99	98.04 44			92.62 49	96.51 35	98.76 30	95.94 97			98.92 145	97.55 167
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										63.50 246

9.14												99.28 13

SR-MVS					99.45 10			97.61 16				99.20 17

our_test_3					89.78 197	93.84 227	85.59 239

MTAPA										96.83 12		99.12 22

MTMP										97.18 7		98.83 27

Patchmatch-RL test							34.61 266

XVS					96.60 70	99.35 19	96.82 71			90.85 72		98.72 31				99.46 34

X-MVStestdata					96.60 70	99.35 19	96.82 71			90.85 72		98.72 31				99.46 34

mPP-MVS					99.21 24							98.29 39

NP-MVS									95.32 95

Patchmtry						95.96 172	93.36 170	75.99 244		75.19 202

DeepMVS_CX						86.86 252	79.50 252	70.43 254	90.73 184	63.66 244	80.36 192	60.83 251	79.68 240	76.23 252		89.46 254	86.53 251

High-resolution multi-view benchmark