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.

ME-MVS		99.07 1	99.22 2	98.90 1	99.39 6	99.81 9	99.36 15	96.46 1	99.30 11	99.11 2	98.75 10	99.99 1	99.23 5	98.67 17	98.11 18	99.83 4	99.93 19

SED-MVS		98.87 2	99.20 3	98.48 2	99.32 13	99.85 2	99.55 8	96.20 8	99.48 3	96.78 5	98.51 17	99.99 1	99.36 2	98.98 8	97.59 30	99.67 22	99.99 3

DVP-MVS++		98.75 3	99.11 8	98.33 4	99.41 5	99.85 2	99.61 4	96.22 7	99.32 9	95.80 7	98.27 20	99.97 5	99.22 6	98.95 9	97.48 34	99.71 21	99.98 5

MSP-MVS		98.75 3	99.27 1	98.15 9	99.21 19	99.82 7	99.58 6	96.09 15	99.32 9	95.16 11	98.79 7	99.55 10	99.05 8	99.54 1	97.88 22	99.84 3	99.99 3
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
CNVR-MVS		98.73 5	99.17 6	98.22 6	99.47 4	99.85 2	99.57 7	96.23 5	99.30 11	94.90 13	98.65 12	98.93 21	99.36 2	99.46 3	98.21 12	99.81 8	99.80 34

DPE-MVS		98.69 6	99.14 7	98.16 8	99.37 9	99.82 7	99.66 3	96.26 3	99.18 18	95.02 12	98.62 14	99.98 4	98.88 13	98.90 12	97.51 33	99.75 13	99.97 8
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		98.65 7	98.87 15	98.38 3	99.30 15	99.85 2	99.14 25	96.23 5	99.51 2	97.16 3	96.01 36	99.99 1	98.90 12	98.89 13	97.88 22	99.56 55	99.98 5
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
APDe-MVS		98.60 8	98.97 12	98.18 7	99.38 8	99.78 13	99.35 17	96.14 11	99.24 15	95.66 9	98.19 22	99.01 18	98.66 19	98.77 15	97.80 25	99.86 2	99.97 8
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		98.55 9	98.75 17	98.32 5	99.48 2	99.68 23	99.51 10	96.24 4	99.08 22	95.94 6	98.64 13	99.30 14	99.02 10	97.94 30	96.86 54	99.75 13	99.76 37

SMA-MVS		98.47 10	99.06 9	97.77 12	99.48 2	99.78 13	99.37 12	96.14 11	99.29 13	93.03 21	97.59 31	99.97 5	99.03 9	98.94 10	98.30 10	99.60 35	99.58 67
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
NCCC		98.41 11	99.18 4	97.52 16	99.36 10	99.84 6	99.55 8	96.08 17	99.33 8	91.77 26	98.79 7	99.46 12	98.59 21	99.15 7	98.07 20	99.73 16	99.64 56

SD-MVS		98.33 12	99.01 10	97.54 15	97.17 52	99.77 16	99.14 25	96.09 15	99.34 7	94.06 17	97.91 27	99.89 7	99.18 7	97.99 29	98.21 12	99.63 29	99.95 13
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
APD-MVS		98.28 13	98.69 18	97.80 11	99.31 14	99.62 30	99.31 20	96.15 10	99.19 17	93.60 18	97.28 32	98.35 29	98.72 18	98.27 22	98.22 11	99.73 16	99.89 27
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MCST-MVS		98.20 14	99.18 4	97.06 22	99.27 17	99.87 1	99.37 12	96.11 13	99.37 5	89.29 35	98.76 9	99.50 11	98.37 26	99.23 5	97.64 28	99.95 1	99.87 31

HPM-MVS++		98.16 15	98.87 15	97.32 18	99.39 6	99.70 21	99.18 23	96.10 14	99.09 21	91.14 28	98.02 25	99.89 7	98.44 24	98.75 16	97.03 48	99.67 22	99.63 59

MSLP-MVS++		98.12 16	98.23 30	97.99 10	99.28 16	99.72 18	99.59 5	95.27 30	98.61 36	94.79 14	96.11 35	97.79 38	99.27 4	96.62 68	98.96 5	99.77 11	99.80 34

HFP-MVS		98.02 17	98.55 22	97.40 17	99.11 22	99.69 22	99.41 11	95.41 28	98.79 32	91.86 25	98.61 15	98.16 31	99.02 10	97.87 34	97.40 36	99.60 35	99.35 88

TSAR-MVS + MP.		97.98 18	98.62 21	97.23 20	97.08 53	99.55 36	99.17 24	95.69 23	99.40 4	93.04 20	96.68 34	98.96 20	98.58 22	98.82 14	96.95 51	99.81 8	99.96 10
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SteuartSystems-ACMMP		97.86 19	98.91 13	96.64 26	98.89 28	99.79 10	99.34 18	95.20 32	98.48 38	89.91 33	98.58 16	98.69 25	96.84 51	98.92 11	98.16 16	99.66 24	99.74 40
Skip Steuart: Steuart Systems R&D Blog.
CP-MVS		97.81 20	98.26 29	97.28 19	99.00 25	99.65 26	99.10 27	95.32 29	98.38 44	92.21 24	98.33 19	97.74 39	98.50 23	97.66 43	96.55 62	99.57 48	99.48 76

ACMMPR		97.78 21	98.28 27	97.20 21	99.03 24	99.68 23	99.37 12	95.24 31	98.86 31	91.16 27	97.86 29	97.26 41	98.79 16	97.64 45	97.40 36	99.60 35	99.25 96

DeepC-MVS_fast	95.01 1	97.67 22	98.22 31	97.02 23	99.00 25	99.79 10	99.10 27	95.82 20	99.05 24	89.53 34	93.54 51	96.77 44	98.83 14	99.34 4	99.44 2	99.82 6	99.63 59
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		97.54 23	97.35 40	97.77 12	99.17 20	99.55 36	98.57 34	95.76 22	99.04 25	94.66 15	97.94 26	94.39 58	98.82 15	96.21 80	94.78 105	99.62 31	99.52 72

ACMMP_NAP		97.51 24	98.27 28	96.63 27	99.34 11	99.72 18	99.25 21	95.94 19	98.11 49	87.10 50	96.98 33	98.50 27	98.61 20	98.58 19	96.83 55	99.56 55	99.14 110

MP-MVS		97.46 25	98.30 26	96.48 28	98.93 27	99.43 44	99.20 22	95.42 27	98.43 40	87.60 46	98.19 22	98.01 37	98.09 28	98.05 27	96.67 59	99.64 27	99.35 88
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
train_agg		97.42 26	98.88 14	95.71 33	98.46 35	99.60 33	99.05 29	95.16 33	99.10 20	84.38 76	98.47 18	98.85 22	97.61 32	98.54 20	97.66 27	99.62 31	99.93 19

MGCNet		97.38 27	99.01 10	95.47 36	97.24 51	99.68 23	98.62 33	89.40 51	98.88 30	90.96 29	99.09 4	98.85 22	96.90 49	98.13 24	98.54 8	99.72 19	99.91 24

CPTT-MVS		97.32 28	97.60 39	96.99 24	98.29 38	99.31 56	99.04 30	94.67 37	97.99 55	93.12 19	98.03 24	98.26 30	98.77 17	96.08 85	94.26 114	98.07 204	99.27 95

X-MVS		97.20 29	98.42 25	95.77 31	99.04 23	99.64 27	98.95 32	95.10 35	98.16 47	83.97 84	98.27 20	98.08 34	97.95 29	97.89 31	97.46 35	99.58 44	99.47 77

PHI-MVS		97.09 30	98.69 18	95.22 38	97.99 43	99.59 35	97.56 46	92.16 41	98.41 42	87.11 49	98.70 11	99.42 13	96.95 46	96.88 61	98.16 16	99.56 55	99.70 47

DPM-MVS		97.07 31	97.99 34	96.00 30	97.25 50	99.16 66	99.67 2	95.99 18	99.08 22	85.97 59	93.00 56	98.44 28	97.47 34	99.22 6	99.62 1	99.66 24	97.44 180

PGM-MVS		97.03 32	98.14 33	95.73 32	99.34 11	99.61 32	99.34 18	89.99 47	97.70 58	87.67 45	99.44 2	96.45 47	98.44 24	97.65 44	97.09 44	99.58 44	99.06 121

PLC	94.37 2	97.03 32	96.54 46	97.60 14	98.84 29	98.64 75	98.17 38	94.99 36	99.01 26	96.80 4	93.21 55	95.64 49	97.36 35	96.37 74	94.79 104	99.41 97	98.12 164
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + ACMM		96.90 34	98.64 20	94.88 40	98.12 41	99.47 41	99.01 31	95.43 26	99.23 16	81.98 108	95.95 37	99.16 17	95.13 73	98.61 18	98.11 18	99.58 44	99.93 19

TSAR-MVS + GP.		96.47 35	98.45 24	94.17 45	92.12 88	99.29 57	97.76 42	88.05 58	99.36 6	90.26 32	97.82 30	99.21 15	97.21 38	96.78 66	96.74 57	99.63 29	99.94 16

EPNet		96.23 36	97.89 36	94.29 43	97.62 46	99.44 43	97.14 53	88.63 54	98.16 47	88.14 41	99.46 1	94.15 61	94.61 88	97.20 53	97.23 40	99.57 48	99.59 64
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNLPA		96.14 37	95.43 55	96.98 25	98.55 32	99.41 48	95.91 59	95.15 34	99.00 27	95.71 8	84.21 114	94.55 56	97.25 36	95.50 109	96.23 68	99.28 128	99.09 120

MVS_111021_LR		96.07 38	97.94 35	93.88 48	97.86 44	99.43 44	95.70 62	89.65 50	98.73 33	84.86 71	99.38 3	94.08 62	95.78 70	97.81 37	96.73 58	99.43 91	99.42 81

ACMMP		96.05 39	96.70 45	95.29 37	98.01 42	99.43 44	97.60 45	94.33 39	97.62 61	86.17 54	98.92 5	92.81 69	96.10 63	95.67 98	93.33 134	99.55 60	99.12 114
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
3Dnovator+	90.72 7	95.99 40	96.42 48	95.50 35	98.18 40	99.33 55	97.44 48	87.73 62	97.93 56	92.36 23	84.67 105	97.33 40	97.55 33	97.32 49	98.47 9	99.72 19	99.88 28

DeepPCF-MVS	94.02 3	95.92 41	98.47 23	92.95 58	97.57 47	99.79 10	91.45 144	94.42 38	99.76 1	86.48 53	92.88 57	98.12 33	92.62 124	99.49 2	99.32 3	95.15 243	99.95 13

CDPH-MVS		95.90 42	97.77 38	93.72 51	98.28 39	99.43 44	98.40 35	91.30 45	98.34 45	78.62 136	94.80 43	95.74 48	96.11 62	97.86 35	98.67 7	99.59 39	99.56 69

CSCG		95.77 43	95.35 57	96.26 29	99.13 21	99.60 33	98.14 39	91.89 44	96.57 76	92.61 22	89.65 68	91.74 77	96.96 43	93.69 143	96.58 61	98.86 158	99.63 59

OMC-MVS		95.75 44	95.84 53	95.64 34	98.52 34	99.34 54	97.15 52	92.02 43	98.94 29	90.45 31	88.31 74	94.64 54	96.35 58	96.02 88	95.99 79	99.34 112	97.65 176

MVS_111021_HR		95.70 45	98.16 32	92.83 59	97.57 47	99.77 16	94.78 78	88.05 58	98.61 36	82.29 103	98.85 6	94.66 53	94.63 84	97.80 38	97.63 29	99.64 27	99.79 36

3Dnovator	90.31 8	95.67 46	96.16 51	95.11 39	98.59 31	99.37 53	97.50 47	87.98 60	98.02 54	89.09 36	85.36 104	94.62 55	97.66 30	97.10 57	98.90 6	99.82 6	99.73 43

CANet		95.40 47	96.27 49	94.40 42	96.25 58	99.62 30	98.37 36	88.59 55	98.09 50	87.58 47	84.57 108	95.54 51	95.87 67	98.12 25	98.03 21	99.73 16	99.90 26

QAPM		95.17 48	96.05 52	94.14 46	98.55 32	99.49 39	97.41 49	87.88 61	97.72 57	84.21 80	84.59 107	95.60 50	97.21 38	97.10 57	98.19 15	99.57 48	99.65 54

SPE-MVS-test		95.06 49	96.98 43	92.82 60	95.83 61	99.40 49	93.23 117	85.29 97	99.27 14	85.89 63	93.86 50	92.70 71	97.19 40	97.70 41	96.18 71	99.49 70	99.76 37

CS-MVS		94.82 50	96.19 50	93.22 54	95.19 66	99.24 59	95.10 73	85.07 103	98.72 34	87.33 48	91.35 59	89.98 86	97.06 42	98.01 28	96.28 66	99.60 35	99.72 44

MVSTER		94.75 51	96.50 47	92.70 62	90.91 106	94.51 168	97.37 50	83.37 121	98.40 43	89.04 37	93.23 54	97.04 43	95.91 66	97.73 39	95.59 98	99.61 33	99.01 125

TAPA-MVS	92.04 6	94.72 52	95.13 60	94.24 44	97.72 45	99.17 64	97.61 44	92.16 41	97.66 60	81.99 107	87.84 79	93.94 64	96.50 55	95.74 95	94.27 113	99.46 81	97.31 184
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DeepC-MVS	92.23 5	94.53 53	94.26 73	94.86 41	96.73 55	99.50 38	97.85 41	95.45 25	96.22 83	82.73 96	80.68 124	88.02 91	96.92 47	97.49 48	98.20 14	99.47 75	99.69 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CHOSEN 280x420		94.51 54	97.78 37	90.70 92	95.54 65	99.49 39	94.14 89	74.91 195	98.43 40	85.32 68	94.78 44	99.19 16	94.95 79	97.02 59	96.18 71	99.35 108	99.36 87

ETV-MVS		94.49 55	97.23 42	91.29 80	90.43 116	98.55 78	93.41 108	84.53 112	99.16 19	83.13 90	94.72 45	94.08 62	96.61 54	97.72 40	96.60 60	99.61 33	99.81 33

EC-MVSNet		94.33 56	96.88 44	91.36 78	90.12 125	97.70 114	95.20 72	80.27 148	98.63 35	85.97 59	93.92 49	93.85 67	97.09 41	97.54 47	96.81 56	99.49 70	99.70 47

MAR-MVS		94.18 57	95.12 61	93.09 57	98.40 37	99.17 64	94.20 88	81.92 130	98.47 39	86.52 52	90.92 61	84.21 111	98.12 27	95.88 92	97.59 30	99.40 99	99.58 67
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
PCF-MVS	92.56 4	93.95 58	93.82 76	94.10 47	96.07 60	99.25 58	96.82 55	95.51 24	92.00 144	81.51 112	82.97 118	93.88 66	95.63 71	94.24 127	94.71 107	99.09 140	99.70 47
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DELS-MVS		93.82 59	93.82 76	93.81 50	96.34 57	99.47 41	97.26 51	88.53 56	92.13 141	87.80 44	79.67 129	88.01 92	93.14 113	98.28 21	99.22 4	99.80 10	99.98 5
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
OpenMVS	88.43 11	93.49 60	93.62 79	93.34 52	98.46 35	99.39 50	97.00 54	87.66 64	95.37 92	81.21 116	75.96 155	91.58 79	96.21 61	96.37 74	97.10 43	99.52 65	99.54 71

EIA-MVS		93.32 61	95.32 58	90.99 86	90.45 115	98.53 81	93.46 106	84.68 108	97.56 64	81.38 113	91.04 60	87.37 95	96.39 57	97.27 50	95.73 90	99.59 39	99.76 37

PVSNet_BlendedMVS		93.30 62	93.46 83	93.10 55	95.60 63	99.38 51	93.59 101	88.70 52	98.09 50	88.10 42	86.96 87	75.02 147	93.08 114	97.89 31	96.90 52	99.56 55	100.00 1

PVSNet_Blended		93.30 62	93.46 83	93.10 55	95.60 63	99.38 51	93.59 101	88.70 52	98.09 50	88.10 42	86.96 87	75.02 147	93.08 114	97.89 31	96.90 52	99.56 55	100.00 1

test2506		93.08 64	93.40 85	92.70 62	92.76 81	99.20 61	94.67 81	86.82 69	92.58 134	90.81 30	86.28 92	85.24 106	91.69 133	96.85 62	96.33 64	99.45 86	97.34 183

PMMVS		93.05 65	95.40 56	90.31 103	91.41 97	97.54 121	92.62 133	83.25 123	98.08 53	79.44 134	95.18 41	88.52 90	96.43 56	95.70 96	93.88 117	98.68 174	98.91 128

LS3D		92.70 66	92.23 97	93.26 53	96.24 59	98.72 70	97.93 40	96.17 9	96.41 77	72.46 152	81.39 123	80.76 124	97.66 30	95.69 97	95.62 95	99.07 142	97.02 192

baseline1		92.67 67	93.62 79	91.55 72	91.16 101	97.15 125	93.92 95	85.97 77	94.76 100	84.07 82	87.17 83	86.89 98	94.62 87	96.72 67	95.90 82	99.57 48	96.79 196

IS_MVSNet		92.67 67	94.99 63	89.96 110	91.17 100	98.54 79	92.77 126	84.00 115	92.72 132	81.90 110	85.67 101	92.47 72	90.39 147	97.82 36	97.81 24	99.51 66	99.91 24

TSAR-MVS + COLMAP		92.56 69	92.44 95	92.71 61	94.61 69	97.69 115	97.69 43	91.09 46	98.96 28	76.71 142	94.68 46	69.41 189	96.91 48	95.80 94	94.18 115	99.26 131	96.33 200

baseline		92.56 69	94.38 69	90.43 100	90.71 110	98.23 89	95.07 74	80.73 147	97.52 65	82.45 100	87.34 82	85.91 102	94.07 102	96.29 79	95.94 81	99.58 44	99.47 77

sasdasda		92.54 71	93.28 86	91.68 68	91.44 95	98.24 87	95.45 67	81.84 134	95.98 87	84.85 72	90.69 62	78.53 129	96.96 43	92.97 150	97.06 45	99.57 48	99.47 77

canonicalmvs		92.54 71	93.28 86	91.68 68	91.44 95	98.24 87	95.45 67	81.84 134	95.98 87	84.85 72	90.69 62	78.53 129	96.96 43	92.97 150	97.06 45	99.57 48	99.47 77

PatchMatch-RL		92.54 71	92.82 94	92.21 64	96.57 56	98.74 69	91.85 141	86.30 72	96.23 82	85.18 69	95.21 40	73.58 158	94.22 100	95.40 112	93.08 138	99.14 137	97.49 179

MVS_Test		92.42 74	94.43 65	90.08 109	90.69 111	98.26 86	94.78 78	80.81 146	97.27 67	78.76 135	87.06 85	84.25 110	95.84 68	97.67 42	97.56 32	99.59 39	98.93 127

MGCFI-Net		92.39 75	93.14 89	91.51 75	91.38 98	98.16 90	95.28 71	81.66 137	95.82 89	84.36 78	90.51 65	78.30 131	96.80 52	92.82 154	96.97 50	99.55 60	99.42 81

thisisatest0530		92.31 76	95.14 59	89.02 126	90.02 127	98.45 83	91.30 145	83.58 118	96.90 72	77.90 138	90.45 66	94.33 59	91.98 130	95.57 102	91.43 165	99.31 119	98.81 131

tttt0517		92.29 77	95.12 61	88.99 127	90.02 127	98.44 85	91.19 148	83.58 118	96.88 73	77.86 139	90.45 66	94.32 60	91.98 130	95.54 105	91.43 165	99.31 119	98.78 133

EPP-MVSNet		92.29 77	94.35 71	89.88 112	90.36 118	97.69 115	90.89 152	83.31 122	93.39 118	83.47 88	85.56 102	93.92 65	91.93 132	95.49 110	94.77 106	99.34 112	99.62 62

HQP-MVS		91.94 79	93.03 90	90.66 94	93.69 71	96.48 139	95.92 58	89.73 48	97.33 66	72.65 150	95.37 38	73.56 159	92.75 123	94.85 120	94.12 116	99.23 134	99.51 73

MSDG		91.93 80	90.28 131	93.85 49	97.36 49	97.12 126	95.88 60	94.07 40	94.52 104	84.13 81	76.74 148	80.89 123	92.54 125	93.97 137	93.61 128	99.14 137	95.10 216

UGNet		91.71 81	94.43 65	88.53 129	92.72 83	98.00 96	90.22 159	84.81 106	94.45 106	83.05 91	87.65 81	92.74 70	81.04 209	94.51 125	94.45 110	99.32 118	99.21 102
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
thres100view900		91.69 82	91.52 104	91.88 67	91.61 90	98.89 67	95.49 65	86.96 66	93.24 119	80.82 121	87.90 76	71.15 178	96.88 50	96.00 89	93.51 130	99.51 66	99.95 13

E2		91.67 83	91.90 101	91.41 77	90.00 130	98.06 92	93.59 101	85.55 81	93.75 112	84.70 74	82.50 120	77.16 132	95.17 72	96.33 77	96.16 73	99.46 81	99.35 88

CLD-MVS		91.67 83	91.30 109	92.10 65	91.25 99	96.59 136	95.93 57	87.25 65	96.86 74	85.55 67	87.08 84	73.01 165	93.26 112	93.07 148	92.84 144	99.34 112	99.68 51
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ET-MVSNet_ETH3D		91.59 85	94.96 64	87.65 132	72.75 241	97.24 124	95.29 69	82.73 126	96.81 75	78.49 137	95.30 39	90.48 85	97.23 37	91.60 167	94.31 111	99.43 91	99.01 125

tfpn200view9		91.47 86	91.31 107	91.65 70	91.61 90	98.69 72	95.03 75	86.17 73	93.24 119	80.82 121	87.90 76	71.15 178	96.80 52	95.53 106	92.82 146	99.47 75	99.88 28

CANet_DTU		91.36 87	95.75 54	86.23 145	92.31 87	98.71 71	95.60 64	78.41 162	98.20 46	56.48 217	94.38 47	87.96 93	95.11 74	96.89 60	96.07 74	99.48 73	98.01 168

thres200		91.36 87	91.19 111	91.55 72	91.60 92	98.69 72	94.98 76	86.17 73	92.16 140	80.76 125	87.66 80	71.15 178	96.35 58	95.53 106	93.23 136	99.47 75	99.92 23

FMVSNet3		91.25 89	92.13 99	90.21 104	85.64 174	93.14 181	95.29 69	80.09 149	96.40 78	85.74 64	77.13 141	86.81 99	94.98 78	97.19 54	97.11 42	99.55 60	97.13 189

thres400		91.24 90	91.01 119	91.50 76	91.56 93	98.77 68	94.66 83	86.41 71	91.87 146	80.56 126	87.05 86	71.01 181	96.35 58	95.67 98	92.82 146	99.48 73	99.88 28

PVSNet_Blended_VisFu		91.20 91	92.89 93	89.23 124	93.41 74	98.61 77	89.80 161	85.39 92	92.84 129	82.80 95	74.21 164	91.38 81	84.64 183	97.22 52	96.04 77	99.34 112	99.93 19

viewcassd2359sk11		91.16 92	91.10 117	91.23 81	89.96 133	97.99 97	93.45 107	85.49 83	92.46 137	84.03 83	80.13 127	75.86 142	94.99 77	95.98 90	96.00 78	99.44 89	99.29 93

DCV-MVSNet		91.15 93	92.00 100	90.17 108	90.78 108	92.23 198	93.70 98	81.17 143	95.16 95	82.98 92	89.46 70	83.31 113	93.98 107	91.79 166	92.87 141	98.41 192	99.18 106

DI_MVS_pp		91.11 94	91.47 105	90.68 93	90.01 129	97.77 106	95.87 61	83.56 120	94.72 101	82.12 105	68.46 186	87.46 94	93.07 116	96.46 73	95.73 90	99.47 75	99.71 46

diffmvs		91.05 95	91.15 112	90.93 89	90.15 122	97.79 103	94.05 90	85.45 87	95.63 90	81.95 109	80.45 126	73.01 165	94.47 91	95.56 103	95.89 83	99.49 70	99.72 44
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet (Re-imp)		91.05 95	94.43 65	87.11 134	91.05 103	97.99 97	92.53 135	83.82 117	92.71 133	76.28 143	84.50 109	92.43 73	79.52 214	97.24 51	97.68 26	99.43 91	98.45 149

thres600view7		90.97 97	90.70 122	91.30 79	91.53 94	98.69 72	94.33 84	86.17 73	91.75 148	80.19 128	86.06 96	70.90 182	96.10 63	95.53 106	92.08 157	99.47 75	99.86 32

viewdifsd2359ckpt09		90.94 98	91.04 118	90.82 91	89.85 139	97.92 101	93.33 115	85.35 93	92.89 126	81.87 111	79.68 128	75.67 145	95.08 75	96.17 81	95.76 88	99.42 94	99.20 104

baseline2		90.91 99	94.40 68	86.84 137	87.54 165	96.83 132	89.95 160	79.22 157	96.00 86	77.04 141	88.68 71	89.73 87	88.01 168	96.35 76	93.51 130	99.29 122	99.68 51

casdiffmvs_mvg		90.83 100	90.52 126	91.20 83	90.56 112	97.67 117	94.96 77	85.45 87	90.72 157	82.03 106	76.70 149	77.08 133	94.61 88	96.57 70	95.62 95	99.57 48	99.28 94
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMP	89.80 9	90.72 101	91.15 112	90.21 104	92.55 85	96.52 138	92.63 132	85.71 79	94.65 102	81.06 118	93.32 52	70.56 186	90.52 146	92.68 156	91.05 172	98.76 166	99.31 92
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
casdiffmvs		90.69 102	90.56 125	90.85 90	90.14 123	97.81 102	92.94 123	85.30 94	93.47 116	82.50 99	76.34 153	74.12 156	94.67 83	96.51 71	96.26 67	99.55 60	99.42 81
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
FA-MVS(training)		90.67 103	93.03 90	87.92 131	90.95 105	98.45 83	92.61 134	66.04 232	94.90 97	84.47 75	77.52 140	91.74 77	94.07 102	97.11 56	92.46 154	99.40 99	99.03 122

viewmanbaseed2359cas		90.60 104	90.74 121	90.44 99	90.21 121	98.01 95	93.39 110	85.57 80	92.53 136	79.63 132	78.77 133	74.90 150	94.37 98	95.55 104	96.19 70	99.45 86	99.20 104

E3new		90.58 105	90.21 134	91.01 85	89.89 138	97.93 99	93.35 114	85.40 91	90.82 156	83.22 89	77.64 138	74.60 152	94.80 81	95.38 114	95.85 84	99.37 101	99.23 97

ACMM	89.40 10	90.58 105	90.02 137	91.23 81	93.30 76	94.75 164	90.69 155	88.22 57	95.20 93	82.70 97	88.54 72	71.40 176	93.48 111	93.64 144	90.94 173	98.99 148	95.72 211
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E3		90.56 107	90.22 133	90.96 88	89.90 137	97.93 99	93.37 111	85.41 90	90.85 155	82.94 94	77.63 139	74.66 151	94.78 82	95.39 113	95.84 86	99.37 101	99.23 97

GBi-Net		90.49 108	91.12 115	89.75 115	84.99 177	92.73 186	93.94 92	80.09 149	96.40 78	85.74 64	77.13 141	86.81 99	94.42 92	94.12 131	93.73 119	99.35 108	96.90 193

test1		90.49 108	91.12 115	89.75 115	84.99 177	92.73 186	93.94 92	80.09 149	96.40 78	85.74 64	77.13 141	86.81 99	94.42 92	94.12 131	93.73 119	99.35 108	96.90 193

viewdifsd2359ckpt13		90.44 110	90.52 126	90.35 102	89.94 135	98.06 92	92.84 124	85.47 84	92.33 139	79.93 130	77.99 134	74.39 154	94.49 90	96.09 84	95.76 88	99.44 89	99.03 122

diffmvs_AUTHOR		90.43 111	90.26 132	90.64 95	90.00 130	97.72 112	93.72 97	85.18 101	94.49 105	81.20 117	77.72 135	71.57 173	94.30 99	94.78 121	95.85 84	99.42 94	99.66 53

viewdifsd2359ckpt07		90.42 112	90.45 129	90.39 101	90.14 123	97.76 108	93.31 116	85.51 82	91.60 150	80.95 119	77.01 145	76.13 141	93.04 117	96.50 72	95.66 94	99.41 97	98.48 147

ECVR-MVS		90.37 113	88.96 153	92.01 66	92.76 81	99.20 61	94.67 81	86.82 69	92.58 134	86.71 51	68.95 185	71.46 175	91.69 133	96.85 62	96.33 64	99.45 86	97.38 182

LGP-MVS_train		90.34 114	91.63 103	88.83 128	93.31 75	96.14 145	95.49 65	85.24 99	93.91 110	68.71 164	93.96 48	71.63 172	91.12 142	93.82 140	92.79 148	99.07 142	99.16 109

viewmambaseed2359dif		90.29 115	89.69 139	90.98 87	90.03 126	97.61 119	93.96 91	85.18 101	93.22 121	82.97 93	76.79 147	74.32 155	94.41 95	91.14 173	95.02 102	99.33 117	99.74 40

test1111		90.01 116	88.67 158	91.57 71	92.68 84	99.20 61	94.25 87	86.90 68	92.03 143	85.04 70	67.79 190	71.21 177	91.12 142	96.83 64	96.34 63	99.42 94	97.28 185

E5new		89.87 117	89.21 147	90.64 95	89.76 141	97.78 104	93.37 111	85.47 84	88.83 169	81.32 114	75.36 157	73.09 162	94.63 84	94.54 123	95.71 92	99.29 122	99.17 107

E5		89.87 117	89.21 147	90.64 95	89.76 141	97.78 104	93.37 111	85.47 84	88.83 169	81.32 114	75.36 157	73.09 162	94.63 84	94.54 123	95.71 92	99.29 122	99.17 107

EPNet_dtu		89.82 119	94.18 74	84.74 155	96.87 54	95.54 157	92.65 131	86.91 67	96.99 69	54.17 228	92.41 58	88.54 89	78.35 217	96.15 83	96.05 76	99.47 75	93.60 225
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
RPSCF		89.81 120	89.75 138	89.88 112	93.22 78	93.99 174	94.78 78	85.23 100	94.01 109	82.52 98	95.00 42	87.23 96	92.01 129	85.16 228	83.48 233	91.54 248	89.38 241

E4		89.71 121	89.07 150	90.45 98	89.76 141	97.77 106	93.15 119	85.26 98	88.58 174	80.86 120	74.87 160	73.08 164	94.38 97	94.44 126	95.61 97	99.29 122	99.14 110

MDTV_nov1_ep13		89.63 122	94.38 69	84.09 162	88.76 157	97.53 122	89.37 169	68.46 230	96.95 70	70.27 159	87.88 78	93.67 68	91.04 144	93.12 146	93.83 118	96.62 226	97.68 175

UA-Net		89.56 123	93.03 90	85.52 151	92.46 86	97.55 120	91.92 139	81.91 131	85.24 192	71.39 154	83.57 115	96.56 46	76.01 228	96.81 65	97.04 47	99.46 81	94.41 220

E6new		89.53 124	88.95 154	90.21 104	89.75 144	97.74 110	92.76 127	84.66 109	88.63 172	80.77 123	74.83 161	72.74 168	94.07 102	94.20 128	95.39 99	99.27 129	99.10 117

E6		89.53 124	88.95 154	90.21 104	89.75 144	97.74 110	92.76 127	84.66 109	88.63 172	80.77 123	74.83 161	72.74 168	94.07 102	94.20 128	95.39 99	99.27 129	99.10 117

FMVSNet2		89.51 126	89.63 140	89.38 121	84.99 177	92.73 186	93.94 92	79.28 156	93.73 113	84.28 79	69.36 184	82.32 116	94.42 92	96.16 82	96.22 69	99.35 108	96.90 193

0.3-1-1-0.015		89.49 127	89.45 143	89.53 117	81.16 206	94.36 171	93.56 104	84.71 107	93.21 122	86.01 55	85.38 103	76.34 135	94.39 96	85.97 221	92.53 153	97.35 220	98.35 153

CostFormer		89.42 128	91.67 102	86.80 139	89.99 132	96.33 141	90.75 153	64.79 234	95.17 94	83.62 87	86.20 94	82.15 118	92.96 118	89.22 191	92.94 139	98.68 174	99.65 54

0.4-1-1-0.2		89.40 129	89.35 145	89.46 120	81.13 207	94.37 170	93.62 100	84.58 111	93.20 123	85.95 61	84.67 105	76.32 139	94.14 101	85.99 220	92.56 152	97.36 219	98.35 153

FC-MVSNet-train		89.37 130	89.62 141	89.08 125	90.48 114	94.16 173	89.45 165	83.99 116	91.09 153	80.09 129	82.84 119	74.52 153	91.44 139	93.79 141	91.57 163	99.01 146	99.35 88

OPM-MVS		89.33 131	87.45 170	91.53 74	94.49 70	96.20 143	96.47 56	89.72 49	82.77 199	75.43 144	80.53 125	70.86 184	93.80 108	94.00 135	91.85 161	99.29 122	95.91 205
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
viewmacassd2359aftdt		89.31 132	88.92 156	89.76 114	89.95 134	97.76 108	93.06 121	85.30 94	88.99 168	77.33 140	73.96 166	73.12 161	93.55 110	93.79 141	95.80 87	99.36 106	99.02 124

test-LLR		89.31 132	93.60 81	84.30 159	88.08 161	96.98 128	88.10 175	78.00 163	94.83 98	62.43 191	84.29 112	90.96 82	89.70 153	95.63 100	92.86 142	99.51 66	99.64 56

EPMVS		89.31 132	93.70 78	84.18 161	91.10 102	98.10 91	89.17 171	62.71 238	96.24 81	70.21 161	86.46 91	92.37 74	92.79 121	91.95 164	93.59 129	99.10 139	97.19 186

0.4-1-1-0.1		89.28 135	89.22 146	89.36 122	81.12 208	94.34 172	93.49 105	84.24 114	93.17 124	85.92 62	84.41 110	76.32 139	94.04 106	85.88 223	92.10 156	97.33 221	98.32 155

Anonymous20231211		89.22 136	87.56 168	91.16 84	90.23 120	96.62 135	93.22 118	85.44 89	92.89 126	84.37 77	60.13 212	81.25 121	96.02 65	90.61 176	92.01 158	97.70 212	99.41 84

Effi-MVS+		88.96 137	91.13 114	86.43 143	89.12 153	97.62 118	93.15 119	75.52 189	93.90 111	66.40 170	86.23 93	70.51 187	95.03 76	95.89 91	94.28 112	99.37 101	99.51 73

SCA		88.76 138	94.29 72	82.30 181	89.33 151	96.81 133	87.68 177	61.52 244	96.95 70	64.68 181	88.35 73	94.80 52	91.58 136	92.23 158	93.21 137	98.99 148	97.70 174

test0.0.03 1		88.71 139	92.22 98	84.63 157	88.08 161	94.71 166	85.91 200	78.00 163	95.54 91	72.96 148	86.10 95	85.88 104	83.59 195	92.95 153	93.24 135	99.25 133	97.09 190

PatchmatchNet		88.67 140	94.10 75	82.34 180	89.38 150	97.72 112	87.24 183	62.18 242	97.00 68	64.79 180	87.97 75	94.43 57	91.55 137	91.21 172	92.77 149	98.90 153	97.60 178
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
dps		88.66 141	90.19 135	86.88 136	89.94 135	96.48 139	89.56 163	64.08 236	94.12 108	89.00 38	83.39 116	82.56 115	90.16 150	86.81 216	89.26 192	98.53 187	98.71 135

TESTMET0.1,1		88.63 142	93.60 81	82.84 175	84.07 185	96.98 128	88.10 175	73.22 210	94.83 98	62.43 191	84.29 112	90.96 82	89.70 153	95.63 100	92.86 142	99.51 66	99.64 56

CHOSEN 1792x2688		88.63 142	89.01 151	88.19 130	94.83 67	99.21 60	92.66 130	79.85 153	92.40 138	72.18 153	56.38 232	80.22 126	90.24 148	97.64 45	97.28 39	99.37 101	99.94 16

CDS-MVSNet		88.59 144	90.13 136	86.79 140	86.98 170	95.43 158	92.03 137	81.33 141	85.54 189	74.51 147	77.07 144	85.14 107	87.03 173	93.90 138	95.18 101	98.88 156	98.67 138
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewdifsd2359ckpt11		88.57 145	87.77 166	89.51 118	89.74 146	95.73 153	91.01 150	85.05 104	92.88 128	82.40 102	77.72 135	70.86 184	92.86 119	87.17 207	91.36 169	95.98 240	98.64 139

viewmsd2359difaftdt		88.57 145	87.76 167	89.51 118	89.74 146	95.73 153	91.01 150	85.05 104	92.79 130	82.43 101	77.72 135	70.90 182	92.85 120	87.16 208	91.37 168	95.98 240	98.64 139

casdiffseed414692147		88.35 147	86.99 172	89.95 111	89.67 148	97.32 123	92.02 138	84.43 113	87.86 176	80.50 127	69.80 182	67.01 194	93.79 109	93.52 145	94.70 109	99.30 121	98.70 136

IB-MVS	84.67 14	88.34 148	90.61 124	85.70 148	92.99 80	98.62 76	78.85 232	86.07 76	94.35 107	88.64 39	85.99 97	75.69 144	68.09 242	88.21 195	91.43 165	99.55 60	99.96 10
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
test-mter		88.25 149	93.27 88	82.38 179	83.89 186	96.86 131	87.10 187	72.80 212	94.58 103	61.85 196	83.21 117	90.65 84	89.18 157	95.43 111	92.58 151	99.46 81	99.61 63

COLMAP_ROB	84.42 15	88.24 150	87.32 171	89.32 123	95.83 61	95.82 149	92.81 125	87.68 63	92.09 142	72.64 151	72.34 173	79.96 127	88.79 159	89.54 186	89.46 188	98.16 201	92.00 231
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
IterMVS-LS		87.95 151	89.40 144	86.26 144	88.79 156	90.93 213	91.23 147	76.05 186	90.87 154	71.07 156	75.51 156	81.18 122	91.21 141	94.11 134	95.01 103	99.20 136	98.23 159
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		87.86 152	88.25 161	87.40 133	94.67 68	98.54 79	90.33 158	76.51 185	89.60 166	70.89 157	51.43 243	85.69 105	92.79 121	96.59 69	95.96 80	99.22 135	99.94 16

Vis-MVSNet		87.60 153	91.31 107	83.27 170	89.14 152	98.04 94	90.35 157	79.42 154	87.23 178	66.92 168	79.10 132	84.63 109	74.34 235	95.81 93	96.06 75	99.46 81	98.32 155
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GeoE		87.55 154	88.17 162	86.82 138	88.74 158	96.32 142	92.75 129	74.93 194	90.13 162	72.73 149	69.47 183	74.03 157	92.51 126	93.99 136	93.62 127	99.29 122	99.59 64

dmvs_re		87.43 155	87.99 163	86.77 141	84.94 181	96.19 144	91.87 140	85.95 78	91.25 152	68.58 165	81.45 122	66.04 197	89.95 152	90.91 174	91.57 163	99.37 101	98.54 144

RPMNet		87.35 156	92.41 96	81.45 185	88.85 155	96.06 146	89.42 168	59.59 251	93.57 114	61.81 197	76.48 152	91.48 80	90.18 149	96.32 78	93.37 133	98.87 157	99.59 64

tpm cat1		87.34 157	88.52 160	85.95 146	89.83 140	95.80 150	90.73 154	64.91 233	92.99 125	82.21 104	71.19 179	82.68 114	90.13 151	86.38 217	90.87 175	97.90 209	99.74 40

MS-PatchMatch		87.19 158	88.59 159	85.55 150	93.15 79	96.58 137	92.35 136	74.19 202	91.97 145	70.33 158	71.42 177	85.89 103	84.28 185	93.12 146	89.16 194	99.00 147	91.99 232

Effi-MVS+-dtu		87.18 159	90.48 128	83.32 169	86.51 171	95.76 152	91.16 149	74.28 201	90.44 161	61.31 200	86.72 90	72.68 170	91.25 140	95.01 118	93.64 122	95.45 242	99.12 114

FMVSNet5		87.06 160	89.52 142	84.20 160	79.92 227	86.57 241	87.11 186	72.37 214	96.06 84	75.41 145	84.33 111	91.76 76	91.60 135	91.51 168	91.22 170	98.77 163	85.16 247

Fast-Effi-MVS+-dtu		86.94 161	91.27 110	81.89 182	86.27 172	95.06 159	90.68 156	68.93 227	91.76 147	57.18 215	89.56 69	75.85 143	89.19 156	94.56 122	92.84 144	99.07 142	99.23 97

Fast-Effi-MVS+		86.94 161	87.88 165	85.84 147	86.99 169	95.80 150	91.24 146	73.48 209	92.75 131	69.22 162	72.70 171	65.71 198	94.84 80	94.98 119	94.71 107	99.26 131	98.48 147

tpmrst		86.78 163	90.29 130	82.69 176	90.55 113	96.95 130	88.49 173	62.58 239	95.09 96	63.52 187	76.67 151	84.00 112	92.05 128	87.93 198	91.89 160	98.98 150	99.50 75

CR-MVSNet		86.73 164	91.47 105	81.20 188	88.56 159	96.06 146	89.43 166	61.37 245	93.57 114	60.81 202	72.89 170	88.85 88	88.13 166	96.03 86	93.64 122	98.89 155	99.22 100

ADS-MVSNet		86.68 165	90.79 120	81.88 183	90.38 117	96.81 133	86.90 188	60.50 249	96.01 85	63.93 184	81.67 121	84.72 108	90.78 145	87.03 210	91.67 162	98.77 163	97.63 177

blend_shiyan4		86.12 166	85.60 181	86.72 142	81.42 201	88.06 231	93.87 96	77.81 171	93.43 117	86.01 55	85.86 98	76.34 135	84.87 180	81.26 238	78.21 240	96.36 229	96.04 201

FMVSNet1		85.85 167	84.91 184	86.96 135	82.70 191	91.39 207	91.54 143	77.45 175	85.29 191	79.56 133	60.70 209	72.68 170	92.37 127	94.12 131	93.73 119	98.12 202	96.44 197

FC-MVSNet-test		85.51 168	89.08 149	81.35 186	85.31 176	93.35 177	87.65 178	77.55 173	90.01 164	64.07 183	79.63 130	81.83 120	74.94 232	92.08 161	90.83 177	98.55 184	95.81 206

ACMH	85.22 13	85.40 169	85.73 180	85.02 153	91.76 89	94.46 169	84.97 212	81.54 139	85.18 193	65.22 176	76.92 146	64.22 203	88.58 162	90.17 178	90.25 184	98.03 205	98.90 129
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		85.35 170	86.00 179	84.59 158	84.97 180	95.57 156	88.98 172	77.29 180	81.44 204	71.36 155	71.48 176	75.00 149	87.03 173	91.92 165	92.21 155	97.92 208	94.40 221

ACMH+	85.62 12	85.27 171	84.96 183	85.64 149	90.84 107	94.78 163	87.46 180	81.30 142	86.94 179	67.35 167	74.56 163	64.09 204	88.70 160	88.14 196	89.00 195	98.22 200	97.19 186

USDC		85.11 172	85.35 182	84.83 154	89.45 149	94.93 162	92.98 122	77.30 178	90.53 159	61.80 198	76.69 150	59.62 214	88.90 158	92.78 155	90.79 179	98.53 187	92.12 229

IterMVS		85.02 173	88.98 152	80.41 194	87.03 168	90.34 221	89.78 162	69.45 224	89.77 165	54.04 229	73.71 167	82.05 119	83.44 198	95.11 116	93.64 122	98.75 167	98.22 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		84.91 174	88.90 157	80.25 197	87.04 167	90.27 222	89.23 170	69.25 226	89.17 167	54.04 229	73.65 168	82.22 117	83.23 203	95.11 116	93.63 126	98.73 168	98.23 159

PatchT		84.89 175	90.67 123	78.13 222	87.83 164	94.99 161	72.46 245	60.22 250	91.74 149	60.81 202	72.16 174	86.95 97	88.13 166	96.03 86	93.64 122	99.36 106	99.22 100

pmmvs4		84.88 176	84.67 185	85.13 152	82.80 190	92.37 191	87.29 181	79.08 158	90.51 160	74.94 146	70.37 180	62.49 207	88.17 165	92.01 163	88.51 200	98.49 190	96.44 197

usedtu_dtu_shiyan1		84.68 177	86.53 175	82.52 177	74.54 237	93.47 176	88.46 174	81.15 144	90.11 163	66.48 169	69.83 181	73.29 160	85.61 176	93.85 139	90.47 182	98.90 153	94.73 219

CVMVSNet		84.01 178	86.91 173	80.61 192	88.39 160	93.29 178	86.06 196	82.29 128	83.13 197	54.29 225	72.68 172	79.59 128	75.11 231	91.23 171	92.91 140	97.54 217	95.58 213

tpm		83.97 179	87.97 164	79.31 207	87.35 166	93.21 180	86.00 198	61.90 243	90.69 158	54.01 231	79.42 131	75.61 146	88.65 161	87.18 206	90.48 181	97.95 207	99.21 102

GA-MVS		83.83 180	86.63 174	80.58 193	85.40 175	94.73 165	87.27 182	78.76 161	86.49 181	49.57 241	74.21 164	67.67 192	83.38 199	95.28 115	90.92 174	99.08 141	97.09 190

UniMVSNet_NR-MVSNet		83.83 180	83.70 188	83.98 163	81.41 202	92.56 190	86.54 191	82.96 124	85.98 186	66.27 171	66.16 194	63.63 205	87.78 170	87.65 201	90.81 178	98.94 151	99.13 112

usedtu_blend_shiyan5		83.68 182	83.60 189	83.79 165	64.08 246	87.81 232	93.63 99	77.82 167	79.98 216	86.01 55	85.86 98	76.34 135	84.87 180	81.05 240	78.09 241	96.30 230	96.04 201

UniMVSNet (Re)		83.28 183	83.16 191	83.42 168	81.93 196	93.12 182	86.27 194	80.83 145	85.88 187	68.23 166	64.56 202	60.58 209	84.25 186	89.13 192	89.44 190	99.04 145	99.40 85

thisisatest0515		83.17 184	86.49 176	79.30 208	82.04 194	93.12 182	78.70 233	77.92 165	86.43 182	63.05 188	74.91 159	73.01 165	75.56 230	92.10 160	88.05 213	98.50 189	97.76 172

FE-MVSNET3		83.03 185	83.56 190	82.42 178	64.08 246	87.81 232	85.44 205	77.82 167	79.99 214	86.01 55	85.86 98	76.34 135	84.87 180	81.05 240	78.09 241	96.30 230	95.79 209

TinyColmap		83.03 185	82.24 195	83.95 164	88.88 154	93.22 179	89.48 164	76.89 182	87.53 177	62.12 193	68.46 186	55.03 230	88.43 164	90.87 175	89.65 186	97.89 210	90.91 235

testgi		82.88 187	86.14 178	79.08 210	86.05 173	92.20 199	81.23 229	74.77 197	88.70 171	57.63 214	86.73 89	61.53 208	76.83 225	90.33 177	89.43 191	97.99 206	94.05 222

DU-MVS		82.87 188	82.16 196	83.70 167	80.77 214	92.24 195	86.54 191	81.91 131	86.41 183	66.27 171	63.95 203	55.66 228	87.78 170	86.83 213	90.86 176	98.94 151	99.13 112

MIMVSNet		82.87 188	86.17 177	79.02 211	77.23 235	92.88 185	84.88 213	60.62 248	86.72 180	64.16 182	73.58 169	71.48 174	88.51 163	94.14 130	93.50 132	98.72 170	90.87 237

NR-MVSNet		82.37 190	81.95 198	82.85 174	82.56 193	92.24 195	87.49 179	81.91 131	86.41 183	65.51 174	63.95 203	52.93 239	80.80 211	89.41 188	89.61 187	98.85 159	99.10 117

Baseline_NR-MVSNet		82.08 191	80.64 205	83.77 166	80.77 214	88.50 228	86.88 189	81.71 136	85.58 188	68.80 163	58.20 224	57.75 220	86.16 175	86.83 213	88.68 197	98.33 197	98.90 129

TranMVSNet+NR-MVSNet		82.07 192	81.36 201	82.90 173	80.43 220	91.39 207	87.16 185	82.75 125	84.28 195	62.98 189	62.28 208	56.01 227	85.30 179	86.06 219	90.69 180	98.80 160	98.80 132

pm-mvs1		81.68 193	81.70 199	81.65 184	82.61 192	92.26 194	85.54 204	78.95 159	76.29 233	63.81 185	58.43 223	66.33 195	80.63 212	92.30 157	89.93 185	98.37 196	96.39 199

TDRefinement		81.49 194	80.08 211	83.13 172	91.02 104	94.53 167	91.66 142	82.43 127	81.70 202	62.12 193	62.30 207	59.32 215	73.93 236	87.31 204	85.29 224	97.61 213	90.14 239

anonymousdsp		81.29 195	84.52 187	77.52 224	79.83 228	92.62 189	82.61 224	70.88 220	80.76 208	50.82 237	68.35 188	68.76 190	82.45 206	93.00 149	89.45 189	98.55 184	98.69 137

gg-mvs-nofinetune		81.27 196	84.65 186	77.32 225	87.96 163	98.48 82	95.64 63	56.36 254	59.35 254	32.80 260	47.96 247	92.11 75	91.49 138	98.12 25	97.00 49	99.65 26	99.56 69

tfpnnormal		81.11 197	79.33 219	83.19 171	84.23 183	92.29 193	86.76 190	82.27 129	72.67 239	62.02 195	56.10 234	53.86 236	85.35 178	92.06 162	89.23 193	98.49 190	99.11 116

UniMVSNet_ETH3D		80.95 198	77.71 232	84.74 155	84.45 182	93.11 184	86.45 193	79.97 152	75.21 235	70.22 160	51.24 244	50.26 245	89.55 155	84.47 230	91.12 171	97.81 211	98.53 145

V42		80.88 199	80.74 203	81.05 189	81.21 205	92.01 201	85.96 199	77.75 172	81.62 203	59.73 209	59.93 215	58.35 219	82.98 205	86.90 212	88.06 212	98.69 173	98.32 155

v2v482		80.86 200	80.52 209	81.25 187	80.79 213	91.85 202	85.68 202	78.78 160	81.05 205	58.09 212	60.46 210	56.08 225	85.45 177	87.27 205	88.53 199	98.73 168	98.38 152

v8		80.61 201	80.61 207	80.62 191	81.51 199	91.00 212	86.06 196	74.07 205	81.78 201	59.93 208	60.10 214	58.42 218	83.35 200	86.99 211	88.11 210	98.79 161	97.83 170

pmmvs5		80.48 202	81.43 200	79.36 206	81.50 200	92.24 195	82.07 227	74.08 204	78.10 226	55.86 220	67.72 191	54.35 233	83.91 194	92.97 150	88.65 198	98.77 163	96.01 203

v10		80.38 203	80.73 204	79.96 199	81.22 204	90.40 220	86.11 195	71.63 217	82.42 200	57.65 213	58.74 221	57.47 221	84.44 184	89.75 182	88.28 203	98.71 171	98.06 167

v1144		80.36 204	80.63 206	80.05 198	80.86 212	91.56 205	85.78 201	75.22 191	80.73 209	55.83 221	58.51 222	56.99 223	83.93 193	89.79 181	88.25 204	98.68 174	98.56 143

SixPastTwentyTwo		80.28 205	82.06 197	78.21 221	81.89 198	92.35 192	77.72 234	74.48 198	83.04 198	54.22 226	76.06 154	56.40 224	83.55 196	86.83 213	84.83 227	97.38 218	94.93 217

CP-MVSNet		79.90 206	79.49 216	80.38 195	80.72 216	90.83 214	82.98 221	75.17 192	79.70 220	61.39 199	59.74 216	51.98 242	83.31 201	87.37 203	88.38 201	98.71 171	98.45 149

v1192		79.84 207	80.05 213	79.61 202	80.49 219	91.04 211	85.56 203	74.37 200	80.73 209	54.35 224	57.07 229	54.54 232	84.23 187	89.94 179	88.38 201	98.63 178	98.61 141

WR-MVS_H		79.76 208	80.07 212	79.40 205	81.25 203	91.73 204	82.77 222	74.82 196	79.02 225	62.55 190	59.41 218	57.32 222	76.27 227	87.61 202	87.30 218	98.78 162	98.09 165

WR-MVS		79.67 209	80.25 210	79.00 212	80.65 217	91.16 209	83.31 219	76.57 184	80.97 206	60.50 207	59.20 219	58.66 217	74.38 234	85.85 224	87.76 215	98.61 179	98.14 162

v148		79.66 210	79.13 222	80.27 196	81.02 210	91.76 203	81.90 228	79.32 155	79.24 223	63.79 186	58.07 226	54.34 234	77.17 223	84.42 231	87.52 217	98.40 193	98.59 142

LTVRE_ROB	79.45 16	79.66 210	80.55 208	78.61 219	83.01 189	92.19 200	87.18 184	73.69 208	71.70 242	43.22 254	71.22 178	50.85 243	87.82 169	89.47 187	90.43 183	96.75 224	98.00 169
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
v144192		79.61 212	79.77 214	79.41 204	80.28 221	91.06 210	84.87 214	73.86 206	79.65 221	55.38 222	57.76 227	55.20 229	83.46 197	88.42 194	87.89 214	98.61 179	98.42 151

v1921920		79.55 213	79.77 214	79.30 208	80.24 222	90.77 216	85.37 209	73.75 207	80.38 211	53.78 232	56.89 231	54.18 235	84.05 191	89.55 185	88.13 209	98.59 181	98.52 146

TransMVSNet (Re)		79.51 214	78.36 228	80.84 190	83.17 187	89.72 224	84.22 217	81.45 140	73.98 238	60.79 205	57.20 228	56.05 226	77.11 224	89.88 180	88.86 196	98.30 199	92.83 227

MVS-HIRNet		79.34 215	82.56 192	75.57 230	84.11 184	95.02 160	75.03 242	57.28 253	85.50 190	55.88 219	53.00 240	70.51 187	83.05 204	92.12 159	91.96 159	98.09 203	89.83 240

PS-CasMVS		79.06 216	78.58 227	79.63 201	80.59 218	90.55 218	82.54 225	75.04 193	77.76 227	58.84 210	58.16 225	50.11 247	82.09 208	87.05 209	88.18 207	98.66 177	98.27 158

gbinet_0.2-2-1-0.02		79.05 217	79.33 219	78.73 216	64.88 244	87.74 238	85.16 211	77.52 174	79.51 222	66.15 173	64.75 201	66.08 196	82.42 207	81.26 238	78.24 239	96.25 236	97.75 173

v1240		78.97 218	79.27 221	78.63 218	80.04 223	90.61 217	84.25 216	72.95 211	79.22 224	52.70 234	56.22 233	52.88 241	83.28 202	89.60 184	88.20 206	98.56 183	98.14 162

pmnet_mix02		78.91 219	81.17 202	76.28 229	81.91 197	90.82 215	74.25 243	77.87 166	86.17 185	49.04 242	67.97 189	62.93 206	77.40 221	82.75 236	82.11 235	97.18 222	95.42 214

wanda-best-256-512		78.88 220	78.96 223	78.78 213	64.08 246	87.81 232	85.44 205	77.82 167	79.99 214	64.86 177	65.31 195	64.67 199	84.16 188	81.05 240	78.09 241	96.30 230	95.81 206

FE-blended-shiyan7		78.88 220	78.96 223	78.78 213	64.08 246	87.81 232	85.44 205	77.82 167	79.98 216	64.86 177	65.31 195	64.66 200	84.16 188	81.05 240	78.09 241	96.30 230	95.81 206

MDTV_nov1_ep13_2view		78.83 222	82.35 193	74.73 233	78.65 230	91.51 206	79.18 231	62.52 240	84.51 194	52.51 235	67.49 192	67.29 193	78.90 215	85.52 226	86.34 221	96.62 226	93.76 223

PEN-MVS		78.80 223	78.13 230	79.58 203	80.03 224	89.67 225	83.61 218	75.83 187	77.71 229	58.41 211	60.11 213	50.00 248	81.02 210	84.08 232	88.14 208	98.59 181	97.18 188

blended_shiyan8		78.78 224	78.79 226	78.77 215	64.07 250	87.81 232	85.39 208	77.38 177	79.94 218	65.37 175	64.85 199	64.30 202	84.14 190	80.95 245	77.97 246	96.26 235	95.72 211

blended_shiyan6		78.78 224	78.90 225	78.64 217	64.04 251	87.78 237	85.34 210	77.30 178	79.93 219	64.84 179	65.18 198	64.66 200	84.03 192	80.99 244	78.00 245	96.27 234	95.79 209

EG-PatchMatch MVS		78.32 226	79.42 218	77.03 227	83.03 188	93.77 175	84.47 215	69.26 225	75.85 234	53.69 233	55.68 235	60.23 212	73.20 237	89.69 183	88.22 205	98.55 184	92.54 228

DTE-MVSNet		77.92 227	77.42 233	78.51 220	79.34 229	89.00 227	83.05 220	75.60 188	76.89 231	56.58 216	59.63 217	50.31 244	78.09 220	82.57 237	87.56 216	98.38 194	95.95 204

v7n		77.71 228	78.25 229	77.09 226	78.49 231	90.55 218	82.15 226	71.11 219	76.79 232	54.18 227	55.63 236	50.20 246	78.28 218	89.36 190	87.15 219	98.33 197	98.07 166

gm-plane-assit		77.20 229	82.26 194	71.30 237	81.10 209	82.00 250	54.33 258	64.41 235	63.80 253	40.93 257	59.04 220	76.57 134	87.30 172	98.26 23	97.36 38	99.74 15	98.76 134

N_pmnet		76.83 230	77.97 231	75.50 231	80.96 211	88.23 230	72.81 244	76.83 183	80.87 207	50.55 238	56.94 230	60.09 213	75.70 229	83.28 234	84.23 229	96.14 238	92.12 229

pmmvs6		76.79 231	75.69 238	78.09 223	79.95 226	89.57 226	80.92 230	74.46 199	64.79 251	60.74 206	45.71 249	60.55 210	78.37 216	88.04 197	86.00 222	94.07 245	95.15 215

CMPMVS	58.73 17	76.78 232	74.27 239	79.70 200	93.26 77	95.58 155	82.74 223	77.44 176	71.46 245	56.29 218	53.58 239	59.13 216	77.33 222	79.20 246	79.71 238	91.14 250	81.24 250
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		76.76 233	79.47 217	73.60 234	79.99 225	87.47 239	77.39 235	75.43 190	77.62 230	47.83 245	64.78 200	60.44 211	64.80 243	86.28 218	86.53 220	96.17 237	93.19 226

PM-MVS		75.81 234	76.11 237	75.46 232	73.81 238	85.48 244	76.42 237	70.57 221	80.05 213	54.75 223	62.33 206	39.56 258	80.59 213	87.71 200	82.81 234	96.61 228	94.81 218

pmmvs-eth3d		75.17 235	74.09 240	76.43 228	72.92 239	84.49 246	76.61 236	72.42 213	74.33 236	61.28 201	54.71 238	39.42 259	78.20 219	87.77 199	84.25 228	97.17 223	93.63 224

Anonymous20231206		74.59 236	77.00 234	71.78 235	77.89 234	87.45 240	75.14 241	72.29 215	77.76 227	46.65 247	52.14 241	52.93 239	61.10 247	89.37 189	88.09 211	97.59 214	91.30 234

test20.03		72.81 237	76.24 236	68.80 240	78.31 232	85.40 245	71.04 246	71.20 218	71.85 241	43.40 253	65.31 195	54.71 231	51.27 251	85.92 222	84.18 230	97.58 215	86.35 246

test_method		71.90 238	76.72 235	66.28 245	60.87 254	78.37 253	69.75 251	49.81 259	83.44 196	49.63 240	47.13 248	53.23 238	76.38 226	91.32 170	85.76 223	91.22 249	97.77 171

new_pmnet		71.86 239	73.67 241	69.75 239	72.56 242	84.20 247	70.95 248	66.81 231	80.34 212	43.62 252	51.60 242	53.81 237	71.24 240	82.91 235	80.93 236	93.35 247	81.92 249

FE-MVSNET2		71.63 240	71.59 242	71.68 236	60.60 255	86.30 242	75.64 238	72.07 216	69.87 246	51.83 236	38.70 252	42.10 256	72.39 239	88.69 193	85.13 225	97.55 216	90.33 238

MDA-MVSNet-bldmvs		69.61 241	70.36 244	68.74 241	62.88 252	88.50 228	65.40 255	77.01 181	71.60 244	43.93 249	66.71 193	35.33 261	72.47 238	61.01 254	80.63 237	90.73 251	88.75 243

pmmvs3		69.04 242	70.75 243	67.04 243	66.83 243	78.54 252	64.99 256	60.92 247	64.67 252	40.61 258	55.08 237	40.29 257	74.89 233	83.76 233	84.01 231	93.98 246	88.88 242

MIMVSNet1		68.63 243	70.24 245	66.76 244	56.86 257	83.26 248	67.93 253	70.26 223	68.05 248	46.80 246	40.44 251	48.15 249	62.01 245	84.96 229	84.86 226	96.69 225	81.93 248

FE-MVSNET		68.01 244	70.02 246	65.66 246	53.56 258	81.28 251	68.74 252	70.37 222	67.27 249	42.26 256	42.17 250	42.41 255	62.95 244	85.18 227	83.97 232	96.09 239	87.90 245

GG-mvs-BLEND		67.99 245	97.35 40	33.72 255	1.22 265	99.72 18	98.30 37	0.57 263	97.61 63	1.18 267	93.26 53	96.63 45	1.74 262	97.15 55	97.14 41	99.34 112	99.96 10

new-patchmatchnet		67.66 246	68.07 247	67.18 242	72.85 240	82.86 249	63.09 257	68.61 229	66.60 250	42.64 255	49.28 245	38.68 260	61.21 246	75.84 247	75.22 248	94.67 244	88.00 244

FPMVS		63.27 247	61.31 251	65.57 247	78.25 233	74.42 257	75.23 240	68.92 228	72.33 240	43.87 250	49.01 246	43.94 252	48.64 253	61.15 253	58.81 255	78.51 258	69.49 255

usedtu_dtu_shiyan2		63.25 248	63.29 249	63.21 248	48.45 261	77.92 254	69.85 249	62.49 241	52.94 255	50.43 239	32.38 256	43.14 253	59.67 248	73.05 248	72.69 250	88.34 252	90.90 236

WB-MVS		56.28 249	63.25 250	48.16 252	75.24 236	65.97 258	39.91 262	74.13 203	69.25 247	10.01 265	62.67 205	44.05 251	20.71 261	70.43 251	69.57 251	68.94 260	60.78 260

Gipuma		54.59 250	53.98 252	55.30 249	59.03 256	52.63 260	47.17 260	56.08 255	71.68 243	37.54 259	20.90 259	19.00 263	52.33 250	71.69 250	75.20 249	79.64 257	66.79 256
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	49.05 18	51.88 251	50.56 254	53.42 250	64.21 245	43.30 262	42.64 261	62.93 237	50.56 256	43.72 251	37.44 253	42.95 254	35.05 256	58.76 256	54.58 256	71.95 259	66.33 257
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS2		50.69 252	52.33 253	48.78 251	51.24 259	64.81 259	47.91 259	53.79 258	44.95 257	21.75 261	29.98 257	25.90 262	31.98 258	59.95 255	65.37 253	86.00 255	75.36 253

E-PMN		37.15 253	34.82 256	39.86 253	47.53 262	35.42 264	23.79 264	55.26 256	35.18 260	14.12 263	17.38 262	14.13 265	39.73 255	32.24 258	46.98 257	58.76 261	62.39 259

EMVS		36.45 254	33.63 257	39.74 254	48.47 260	35.73 263	23.59 265	55.11 257	35.61 259	12.88 264	17.49 260	14.62 264	41.04 254	29.33 259	43.00 258	57.32 262	59.62 261

MVE	42.40 19	36.00 255	38.65 255	32.92 256	29.16 263	46.17 261	22.61 266	44.21 260	26.44 262	18.88 262	17.41 261	9.36 267	32.29 257	45.75 257	61.38 254	50.35 263	64.03 258
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		21.55 256	30.91 258	10.62 257	2.78 264	11.66 265	18.51 267	4.82 261	38.21 258	4.06 266	36.35 254	4.47 268	26.81 259	23.27 260	27.11 259	6.75 264	75.30 254

test123		16.81 257	24.80 259	7.48 258	0.82 266	8.38 266	11.92 268	2.60 262	28.96 261	1.12 268	28.39 258	1.26 269	24.51 260	8.93 261	22.19 260	3.90 265	75.49 252

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							99.36 15	96.46 1		99.32 1						99.83 4

TPM-MVS					99.50 1	99.78 13	99.69 1			88.49 40	97.88 28	98.84 24	99.42 1			99.76 12	97.44 180
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										46.54 248

9.14												99.73 9

SR-MVS					99.27 17			95.82 20				99.00 19

Anonymous202405211			87.54 169		90.72 109	97.10 127	93.40 109	85.30 94	91.41 151		60.23 211	80.69 125	95.80 69	91.33 169	92.60 150	98.38 194	99.40 85

our_test_3					81.94 195	90.26 223	75.39 239

ambc			64.61 248		61.80 253	75.31 256	71.00 247		74.16 237	48.83 243	36.02 255	13.22 266	58.66 249	85.80 225	76.26 247	88.01 253	91.53 233

MTAPA										94.58 16		98.56 26

MTMP										95.24 10		98.13 32

Patchmatch-RL test							37.05 263

tmp_tt				71.24 238	90.29 119	76.39 255	65.81 254	59.43 252	97.62 61	79.65 131	90.60 64	68.71 191	49.71 252	72.71 249	65.70 252	82.54 256

XVS					93.63 72	99.64 27	94.32 85			83.97 84		98.08 34				99.59 39

X-MVStestdata					93.63 72	99.64 27	94.32 85			83.97 84		98.08 34				99.59 39

mPP-MVS					98.66 30							97.11 42

NP-MVS									97.69 59

Patchmtry						95.86 148	89.43 166	61.37 245		60.81 202

DeepMVS_CX						85.88 243	69.83 250	81.56 138	87.99 175	48.22 244	71.85 175	45.52 250	68.67 241	63.21 252		86.64 254	80.03 251

High-resolution multi-view benchmark