High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

DVP-MVS		97.93 5	98.23 4	97.58 5	99.05 8	99.31 1	98.64 7	96.62 6	97.56 3	95.08 8	96.61 15	99.64 1	97.32 1	97.91 4	97.31 8	98.77 16	99.26 2
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
HFP-MVS		97.11 16	97.19 19	97.00 14	98.97 15	98.73 15	98.37 14	95.69 24	96.60 11	93.28 23	96.87 10	96.64 32	97.27 2	96.64 38	96.33 39	98.44 41	98.56 27

APDe-MVS		97.79 7	97.96 8	97.60 4	99.20 2	99.10 7	98.88 2	96.68 3	96.81 9	94.64 9	97.84 5	98.02 13	97.24 3	97.74 9	97.02 17	98.97 5	99.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
aaEdge-Enhanced		97.97 4	98.17 5	97.75 2	99.06 6	99.08 8	98.60 9	96.48 8	97.14 4	96.47 2	98.77 1	99.29 6	97.22 4	97.29 20	96.80 23	98.66 22	98.79 14

MED-MVS		98.16 1	98.41 2	97.87 1	99.09 3	99.15 6	98.72 6	96.75 1	98.03 1	96.62 1	98.77 1	99.31 5	97.16 5	97.77 6	97.07 16	98.89 8	98.79 14

TSAR-MVS + MP.		97.31 11	97.64 11	96.92 15	97.28 50	98.56 26	98.61 8	95.48 31	96.72 10	94.03 16	96.73 14	98.29 11	97.15 6	97.61 14	96.42 29	98.96 6	99.13 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
ACMMPR		96.92 19	96.96 22	96.87 17	98.99 14	98.78 14	98.38 13	95.52 27	96.57 12	92.81 27	96.06 23	95.90 40	97.07 7	96.60 40	96.34 38	98.46 37	98.42 38

DPE-MVS		97.83 6	98.13 6	97.48 7	98.83 24	99.19 4	98.99 1	96.70 2	96.05 20	94.39 12	98.30 3	99.47 4	97.02 8	97.75 8	97.02 17	98.98 3	99.10 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SD-MVS		97.35 10	97.73 10	96.90 16	97.35 48	98.66 17	97.85 29	96.25 14	96.86 8	94.54 11	96.75 13	99.13 8	96.99 9	96.94 30	96.58 27	98.39 48	99.20 5
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
CNVR-MVS		97.30 12	97.41 13	97.18 10	99.02 12	98.60 24	98.15 19	96.24 16	96.12 19	94.10 14	95.54 28	97.99 14	96.99 9	97.97 3	97.17 11	98.57 27	98.50 34

DVP-MVS++		98.07 2	98.46 1	97.62 3	99.08 4	99.29 2	98.84 3	96.63 5	97.89 2	95.35 6	97.83 6	99.48 3	96.98 11	97.99 2	97.14 13	98.82 12	99.60 1

CPTT-MVS		95.54 34	95.07 41	96.10 27	97.88 40	97.98 53	97.92 28	94.86 35	94.56 43	92.16 30	91.01 46	95.71 41	96.97 12	94.56 90	93.50 114	96.81 188	98.14 49

MSP-MVS		97.70 8	98.09 7	97.24 8	99.00 13	99.17 5	98.76 5	96.41 12	96.91 7	93.88 17	97.72 7	99.04 9	96.93 13	97.29 20	97.31 8	98.45 40	99.23 4
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
SED-MVS		97.98 3	98.36 3	97.54 6	98.94 18	99.29 2	98.81 4	96.64 4	97.14 4	95.16 7	97.96 4	99.61 2	96.92 14	98.00 1	97.24 10	98.75 18	99.25 3

MSLP-MVS++		96.05 30	95.63 34	96.55 23	98.33 31	98.17 47	96.94 41	94.61 37	94.70 42	94.37 13	89.20 57	95.96 39	96.81 15	95.57 62	97.33 6	98.24 68	98.47 36

APD-MVS		97.12 15	97.05 21	97.19 9	99.04 9	98.63 22	98.45 11	96.54 7	94.81 40	93.50 19	96.10 22	97.40 24	96.81 15	97.05 26	96.82 22	98.80 13	98.56 27
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		96.68 22	96.59 29	96.77 19	98.85 23	98.58 25	98.18 18	95.51 29	95.34 28	92.94 26	95.21 31	96.25 34	96.79 17	96.44 45	95.77 54	98.35 50	98.56 27

SMA-MVS		97.53 9	97.93 9	97.07 12	99.21 1	99.02 11	98.08 22	96.25 14	96.36 14	93.57 18	96.56 16	99.27 7	96.78 18	97.91 4	97.43 4	98.51 29	98.94 12
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
HPM-MVS++		97.22 13	97.40 14	97.01 13	99.08 4	98.55 27	98.19 17	96.48 8	96.02 21	93.28 23	96.26 20	98.71 10	96.76 19	97.30 19	96.25 42	98.30 59	98.68 20

PGM-MVS		96.16 27	96.33 31	95.95 28	99.04 9	98.63 22	98.32 15	92.76 45	93.42 55	90.49 41	96.30 19	95.31 45	96.71 20	96.46 43	96.02 51	98.38 49	98.19 46

NCCC		96.75 21	96.67 27	96.85 18	99.03 11	98.44 36	98.15 19	96.28 13	96.32 15	92.39 29	92.16 39	97.55 22	96.68 21	97.32 17	96.65 26	98.55 28	98.26 43

ACMMP_NAP		96.93 18	97.27 18	96.53 25	99.06 6	98.95 12	98.24 16	96.06 18	95.66 24	90.96 36	95.63 27	97.71 18	96.53 22	97.66 12	96.68 24	98.30 59	98.61 25

AdaColmap		95.02 40	93.71 53	96.54 24	98.51 28	97.76 63	96.69 44	95.94 22	93.72 53	93.50 19	89.01 58	90.53 70	96.49 23	94.51 93	93.76 106	98.07 87	96.69 124

MCST-MVS		96.83 20	97.06 20	96.57 21	98.88 22	98.47 34	98.02 24	96.16 17	95.58 26	90.96 36	95.78 26	97.84 16	96.46 24	97.00 29	96.17 44	98.94 7	98.55 32

DeepC-MVS_fast	93.32 1	96.48 25	96.42 30	96.56 22	98.70 27	98.31 40	97.97 26	95.76 23	96.31 16	92.01 31	91.43 44	95.42 44	96.46 24	97.65 13	97.69 1	98.49 34	98.12 51
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SteuartSystems-ACMMP		97.10 17	97.49 12	96.65 20	98.97 15	98.95 12	98.43 12	95.96 20	95.12 31	91.46 32	96.85 11	97.60 20	96.37 26	97.76 7	97.16 12	98.68 20	98.97 11
Skip Steuart: Steuart Systems R&D Blog.
MP-MVS		96.56 23	96.72 26	96.37 26	98.93 20	98.48 33	98.04 23	95.55 26	94.32 44	90.95 38	95.88 25	97.02 28	96.29 27	96.77 33	96.01 52	98.47 35	98.56 27
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SF-MVS		97.20 14	97.29 17	97.10 11	98.95 17	98.51 32	97.51 33	96.48 8	96.17 18	94.64 9	97.32 8	97.57 21	96.23 28	96.78 32	96.15 46	98.79 15	98.55 32

EC-MVSNet		94.19 51	95.05 42	93.18 61	93.56 108	97.65 68	95.34 64	86.37 149	92.05 70	88.71 54	89.91 53	93.32 51	96.14 29	97.29 20	96.42 29	98.98 3	98.70 18

CS-MVS		94.53 48	94.73 46	94.31 45	96.30 63	98.53 29	94.98 68	89.24 100	93.37 56	90.24 43	88.96 59	89.76 75	96.09 30	97.48 16	96.42 29	98.99 2	98.59 26

X-MVS		96.07 29	96.33 31	95.77 31	98.94 18	98.66 17	97.94 27	95.41 33	95.12 31	88.03 59	93.00 36	96.06 36	95.85 31	96.65 37	96.35 35	98.47 35	98.48 35

DeepC-MVS	92.10 3	95.22 37	94.77 45	95.75 32	97.77 42	98.54 28	97.63 32	95.96 20	95.07 35	88.85 52	85.35 80	91.85 57	95.82 32	96.88 31	97.10 14	98.44 41	98.63 22
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVSMamba_PlusPlus		94.63 46	95.45 39	93.67 54	94.05 93	98.25 44	95.98 54	90.70 62	95.11 33	87.05 76	91.10 45	90.84 64	95.77 33	97.52 15	97.32 7	98.44 41	98.00 55

train_agg		96.15 28	96.64 28	95.58 36	98.44 29	98.03 51	98.14 21	95.40 34	93.90 51	87.72 65	96.26 20	98.10 12	95.75 34	96.25 50	95.45 60	98.01 102	98.47 36

TSAR-MVS + GP.		95.86 31	96.95 24	94.60 44	94.07 91	98.11 49	96.30 48	91.76 53	95.67 23	91.07 34	96.82 12	97.69 19	95.71 35	95.96 56	95.75 55	98.68 20	98.63 22

SPE-MVS-test		94.63 46	95.28 40	93.88 52	96.56 60	98.67 16	93.41 127	89.31 97	94.27 45	89.64 46	90.84 48	91.64 60	95.58 36	97.04 27	96.17 44	98.77 16	98.32 41

PLC	90.69 4	94.32 50	92.99 61	95.87 30	97.91 38	96.49 118	95.95 56	94.12 38	94.94 36	94.09 15	85.90 76	90.77 67	95.58 36	94.52 92	93.32 122	97.55 139	95.00 178
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ACMMP		95.54 34	95.49 37	95.61 34	98.27 33	98.53 29	97.16 38	94.86 35	94.88 38	89.34 47	95.36 30	91.74 58	95.50 38	95.51 64	94.16 95	98.50 32	98.22 44
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+	90.56 5	95.06 39	94.56 48	95.65 33	98.11 35	98.15 48	97.19 37	91.59 55	95.11 33	93.23 25	81.99 117	94.71 47	95.43 39	96.48 42	96.88 21	98.35 50	98.63 22

CSCG		95.68 33	95.46 38	95.93 29	98.71 26	99.07 9	97.13 39	93.55 40	95.48 27	93.35 22	90.61 50	93.82 50	95.16 40	94.60 89	95.57 58	97.70 128	99.08 10

sasdasda		93.08 58	93.09 58	93.07 65	94.24 85	97.86 56	95.45 62	87.86 133	94.00 49	87.47 68	88.32 61	82.37 109	95.13 41	93.96 113	96.41 32	98.27 63	98.73 16

canonicalmvs		93.08 58	93.09 58	93.07 65	94.24 85	97.86 56	95.45 62	87.86 133	94.00 49	87.47 68	88.32 61	82.37 109	95.13 41	93.96 113	96.41 32	98.27 63	98.73 16

CNLPA		93.69 56	92.50 68	95.06 39	97.11 53	97.36 75	93.88 107	93.30 41	95.64 25	93.44 21	80.32 134	90.73 68	94.99 43	93.58 123	93.33 120	97.67 132	96.57 130

OMC-MVS		94.49 49	94.36 50	94.64 42	97.17 52	97.73 65	95.49 60	92.25 47	96.18 17	90.34 42	88.51 60	92.88 54	94.90 44	94.92 75	94.17 94	97.69 130	96.15 148

3Dnovator	90.28 7	94.70 45	94.34 51	95.11 38	98.06 36	98.21 45	96.89 42	91.03 60	94.72 41	91.45 33	82.87 103	93.10 53	94.61 45	96.24 51	97.08 15	98.63 25	98.16 47

ETV-MVS		93.80 54	94.57 47	92.91 69	93.98 94	97.50 71	93.62 118	88.70 113	91.95 71	87.57 66	90.21 52	90.79 66	94.56 46	97.20 23	96.35 35	99.02 1	97.98 56

DPM-MVS		95.07 38	94.84 44	95.34 37	97.44 47	97.49 72	97.76 30	95.52 27	94.88 38	88.92 51	87.25 66	96.44 33	94.41 47	95.78 59	96.11 48	97.99 106	95.95 156

TAPA-MVS	90.35 6	93.69 56	93.52 54	93.90 50	96.89 56	97.62 69	96.15 49	91.67 54	94.94 36	85.97 94	87.72 65	91.96 56	94.40 48	93.76 120	93.06 134	98.30 59	95.58 166
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LS3D		91.97 74	90.98 98	93.12 63	97.03 55	97.09 100	95.33 65	95.59 25	92.47 66	79.26 157	81.60 120	82.77 104	94.39 49	94.28 98	94.23 93	97.14 160	94.45 184

MAR-MVS		92.71 65	92.63 66	92.79 71	97.70 44	97.15 93	93.75 112	87.98 127	90.71 84	85.76 104	86.28 74	86.38 83	94.35 50	94.95 73	95.49 59	97.22 154	97.44 79
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
MVS_111021_LR		94.84 42	95.57 35	94.00 47	97.11 53	97.72 67	94.88 71	91.16 58	95.24 30	88.74 53	96.03 24	91.52 62	94.33 51	95.96 56	95.01 71	97.79 118	97.49 78

QAPM		94.13 52	94.33 52	93.90 50	97.82 41	98.37 39	96.47 46	90.89 61	92.73 65	85.63 107	85.35 80	93.87 49	94.17 52	95.71 61	95.90 53	98.40 46	98.42 38

MGCFI-Net		92.75 63	92.98 62	92.48 79	94.18 87	97.77 62	95.28 66	87.77 135	93.88 52	85.28 124	88.19 63	82.17 114	94.14 53	93.86 116	96.32 40	98.20 72	98.69 19

TSAR-MVS + COLMAP		92.39 68	92.31 73	92.47 81	95.35 77	96.46 120	96.13 50	92.04 51	95.33 29	80.11 153	94.95 32	77.35 169	94.05 54	94.49 95	93.08 132	97.15 158	94.53 182

MGCNet		96.54 24	97.36 16	95.60 35	98.03 37	99.07 9	98.02 24	92.24 48	95.87 22	92.54 28	96.41 17	96.08 35	94.03 55	97.69 10	97.47 3	98.73 19	98.90 13

TSAR-MVS + ACMM		96.19 26	97.39 15	94.78 40	97.70 44	98.41 37	97.72 31	95.49 30	96.47 13	86.66 82	96.35 18	97.85 15	93.99 56	97.19 24	96.37 34	97.12 161	99.13 7

ACMM	88.76 10	91.70 84	90.43 109	93.19 60	95.56 70	95.14 142	93.35 131	91.48 56	92.26 68	87.12 73	84.02 89	79.34 150	93.99 56	94.07 106	92.68 142	97.62 137	95.50 167
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OPM-MVS		91.08 101	89.34 128	93.11 64	96.18 64	96.13 129	96.39 47	92.39 46	82.97 189	81.74 140	82.55 109	80.20 142	93.97 58	94.62 87	93.23 124	98.00 104	95.73 162
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PHI-MVS		95.86 31	96.93 25	94.61 43	97.60 46	98.65 21	96.49 45	93.13 43	94.07 47	87.91 63	97.12 9	97.17 26	93.90 59	96.46 43	96.93 20	98.64 24	98.10 53

DeepPCF-MVS	92.65 2	95.50 36	96.96 22	93.79 53	96.44 61	98.21 45	93.51 124	94.08 39	96.94 6	89.29 48	93.08 35	96.77 30	93.82 60	97.68 11	97.40 5	95.59 211	98.65 21

EIA-MVS		92.72 64	92.96 63	92.44 82	93.86 101	97.76 63	93.13 133	88.65 116	89.78 113	86.68 80	86.69 70	87.57 77	93.74 61	96.07 54	95.32 62	98.58 26	97.53 76

ET-MVSNet_ETH3D		89.93 128	90.84 103	88.87 142	79.60 253	96.19 127	94.43 77	86.56 146	90.63 86	80.75 150	90.71 49	77.78 165	93.73 62	91.36 169	93.45 116	98.15 77	95.77 161

Casviewmamba		92.36 70	91.93 79	92.87 70	93.39 111	97.42 74	94.57 74	89.86 72	93.10 58	87.57 66	82.10 115	82.17 114	93.67 63	95.97 55	95.43 61	98.18 75	97.30 86

MVS_111021_HR		94.84 42	95.91 33	93.60 55	97.35 48	98.46 35	95.08 67	91.19 57	94.18 46	85.97 94	95.38 29	92.56 55	93.61 64	96.61 39	96.25 42	98.40 46	97.92 61

CDPH-MVS		94.80 44	95.50 36	93.98 49	98.34 30	98.06 50	97.41 35	93.23 42	92.81 61	82.98 137	92.51 38	94.82 46	93.53 65	96.08 53	96.30 41	98.42 44	97.94 59

Effi-MVS+		89.79 131	89.83 124	89.74 134	92.98 132	96.45 121	93.48 126	84.24 169	87.62 142	76.45 166	81.76 118	77.56 168	93.48 66	94.61 88	93.59 109	97.82 117	97.22 91

PCF-MVS	90.19 8	92.98 60	92.07 76	94.04 46	96.39 62	97.87 55	96.03 52	95.47 32	87.16 147	85.09 127	84.81 84	93.21 52	93.46 67	91.98 160	91.98 158	97.78 120	97.51 77
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
viewdifsd2359ckpt09		91.65 85	90.91 102	92.51 77	93.35 113	97.36 75	93.95 102	89.64 86	89.83 111	86.67 81	82.25 113	80.77 135	93.37 68	94.71 84	94.48 88	98.07 87	96.99 106

Fast-Effi-MVS+		88.56 146	87.99 149	89.22 139	91.56 162	95.21 140	92.29 146	82.69 188	86.82 151	77.73 161	76.24 166	73.39 182	93.36 69	94.22 103	93.64 107	97.65 134	96.43 137

casdiffmvs		91.72 83	91.16 93	92.38 84	93.16 124	97.15 93	93.95 102	89.49 94	91.58 79	86.03 93	80.75 129	80.95 131	93.16 70	95.25 68	95.22 66	98.50 32	97.23 89
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CLD-MVS		92.50 67	91.96 78	93.13 62	93.93 98	96.24 126	95.69 57	88.77 110	92.92 59	89.01 50	88.19 63	81.74 120	93.13 71	93.63 122	93.08 132	98.23 69	97.91 63
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TPM-MVS					98.33 31	97.85 58	97.06 40			89.97 44	93.26 34	97.16 27	93.12 72			97.79 118	95.95 156
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
ACM-MVS					98.26 34	97.95 54	97.46 34		93.48 54	87.20 72	92.59 37	96.71 31	93.07 73			97.52 141	97.79 69

CANet		94.85 41	94.92 43	94.78 40	97.25 51	98.52 31	97.20 36	91.81 52	93.25 57	91.06 35	86.29 73	94.46 48	92.99 74	97.02 28	96.68 24	98.34 52	98.20 45

hybridcas		91.91 77	91.29 89	92.65 74	93.18 121	97.22 87	94.63 72	89.68 82	91.78 76	87.11 74	80.73 132	81.57 122	92.96 75	95.56 63	95.14 68	98.32 55	97.01 101

MVS_Test		91.81 80	92.19 74	91.37 116	93.24 116	96.95 104	94.43 77	86.25 150	91.45 80	83.45 135	86.31 72	85.15 91	92.93 76	93.99 109	94.71 83	97.92 112	96.77 119

casdiffmvs_mvg		91.94 75	91.25 91	92.75 72	93.41 110	97.19 90	95.48 61	89.77 75	89.86 110	86.41 84	81.02 127	82.23 112	92.93 76	95.44 66	95.61 57	98.51 29	97.40 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
HQP-MVS		92.39 68	92.49 69	92.29 87	95.65 69	95.94 134	95.64 59	92.12 50	92.46 67	79.65 155	91.97 41	82.68 105	92.92 78	93.47 128	92.77 141	97.74 124	98.12 51

E2		92.03 72	91.47 87	92.69 73	93.29 114	97.27 78	94.14 94	89.63 88	91.02 82	88.25 58	83.68 93	82.18 113	92.84 79	94.51 93	94.62 86	98.00 104	97.00 104

viewdifsd2359ckpt13		91.32 92	90.71 105	92.04 92	93.21 120	97.23 84	93.57 122	89.54 92	89.94 106	85.21 125	81.31 123	80.56 137	92.78 80	94.56 90	94.57 87	97.95 111	96.80 117

viewcassd2359sk11		91.81 80	91.13 94	92.61 75	93.28 115	97.26 79	94.16 91	89.64 86	90.27 95	87.79 64	82.51 110	81.72 121	92.78 80	94.43 97	94.69 84	98.01 102	96.99 106

E3new		91.52 87	90.67 106	92.51 77	93.24 116	97.23 84	94.16 91	89.65 84	89.19 120	87.26 71	81.25 124	81.00 129	92.71 82	94.26 100	94.75 79	98.03 93	96.99 106

E3		91.50 89	90.67 106	92.48 79	93.24 116	97.23 84	94.16 91	89.65 84	89.18 121	87.08 75	81.24 125	81.04 128	92.71 82	94.26 100	94.75 79	98.03 93	96.99 106

viewmanbaseed2359cas		91.57 86	91.09 95	92.12 89	93.36 112	97.26 79	94.02 98	89.62 89	90.50 91	84.95 130	82.00 116	81.36 123	92.69 84	94.47 96	95.04 70	98.09 85	97.00 104

OpenMVS	88.18 11	92.51 66	91.61 84	93.55 56	97.74 43	98.02 52	95.66 58	90.46 65	89.14 122	86.50 83	75.80 169	90.38 73	92.69 84	94.99 72	95.30 63	98.27 63	97.63 71

E5new		91.10 99	90.03 118	92.35 85	93.15 126	97.13 98	94.28 84	89.76 76	87.71 138	86.24 86	79.61 138	80.18 143	92.62 86	93.77 118	94.80 76	98.02 99	97.01 101

E5		91.10 99	90.03 118	92.35 85	93.15 126	97.13 98	94.28 84	89.76 76	87.71 138	86.24 86	79.61 138	80.18 143	92.62 86	93.77 118	94.80 76	98.02 99	97.01 101

casdiffseed414692147		89.97 127	88.31 142	91.90 95	93.03 131	96.77 110	93.66 117	88.85 106	86.52 156	85.39 121	74.87 177	75.76 177	92.53 88	93.35 132	94.26 92	97.97 110	96.67 125

E4		91.04 103	90.00 120	92.25 88	93.15 126	97.14 96	94.09 95	89.62 89	87.54 143	86.08 91	79.38 140	80.24 140	92.53 88	93.89 115	94.82 75	98.04 92	96.99 106

E6new		90.91 108	89.94 122	92.04 92	93.14 129	97.16 91	93.76 110	88.98 102	87.44 144	85.85 101	79.15 143	79.96 147	92.48 90	94.04 107	94.75 79	98.03 93	97.06 99

E6		90.91 108	89.94 122	92.04 92	93.14 129	97.16 91	93.76 110	88.98 102	87.44 144	85.85 101	79.15 143	79.96 147	92.48 90	94.04 107	94.75 79	98.03 93	97.06 99

PatchMatch-RL		90.30 123	88.93 135	91.89 96	95.41 76	95.68 136	90.94 166	88.67 115	89.80 112	86.95 78	85.90 76	72.51 189	92.46 92	93.56 125	92.18 151	96.93 179	92.89 204

ACMP	89.13 9	92.03 72	91.70 83	92.41 83	94.92 80	96.44 122	93.95 102	89.96 71	91.81 75	85.48 113	90.97 47	79.12 152	92.42 93	93.28 135	92.55 145	97.76 122	97.74 70
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20231211		89.82 130	88.18 146	91.74 99	92.52 150	96.09 131	93.38 129	89.30 98	88.95 124	85.90 98	64.55 239	84.39 94	92.41 94	92.24 154	93.06 134	96.93 179	97.95 58

LGP-MVS_train		91.83 79	92.04 77	91.58 108	95.46 73	96.18 128	95.97 55	89.85 73	90.45 92	77.76 160	91.92 42	80.07 145	92.34 95	94.27 99	93.47 115	98.11 82	97.90 64

viewmacassd2359aftdt		90.80 112	89.95 121	91.78 98	93.17 123	97.14 96	93.99 99	89.56 91	87.66 140	83.65 133	78.82 146	80.23 141	92.23 96	93.74 121	95.11 69	98.10 83	96.97 112

Anonymous202405211			88.00 148		93.16 124	96.38 124	93.58 119	89.34 96	87.92 137		65.04 234	83.03 101	92.07 97	92.67 140	93.33 120	96.96 174	97.63 71

dtuplus		90.51 120	89.50 126	91.69 104	92.61 149	96.04 132	93.70 116	88.72 112	88.47 133	86.07 92	79.85 136	80.92 133	92.04 98	91.20 171	92.89 138	96.99 171	97.14 96

viewmamba		91.38 90	91.07 97	91.74 99	92.86 137	96.52 117	93.58 119	88.83 108	94.05 48	85.68 106	83.53 96	81.22 126	92.03 99	92.17 157	93.24 123	97.46 145	96.75 122

viewmambaseed2359dif		90.70 117	89.81 125	91.73 101	92.66 147	96.10 130	93.97 100	88.69 114	89.92 107	86.12 89	80.79 128	80.73 136	91.92 100	91.13 176	92.81 140	97.06 165	97.20 93

DI_MVS_pp		91.05 102	90.15 114	92.11 90	92.67 146	96.61 111	96.03 52	88.44 119	90.25 96	85.92 97	73.73 182	84.89 93	91.92 100	94.17 104	94.07 99	97.68 131	97.31 85

diffmvs_AUTHOR		91.22 96	90.82 104	91.68 105	92.69 145	96.56 113	94.05 96	88.87 105	91.87 72	85.08 128	82.26 112	80.04 146	91.84 102	93.80 117	93.93 103	97.56 138	97.26 87

thres400		89.40 138	87.58 158	91.53 110	94.06 92	97.21 89	94.19 89	89.83 74	85.69 163	81.08 147	75.50 174	69.76 207	91.80 103	94.79 83	93.51 111	98.20 72	96.60 128

thres200		89.49 137	87.72 153	91.55 109	93.95 96	97.25 82	94.34 81	89.74 78	85.66 164	81.18 144	76.12 168	70.19 206	91.80 103	94.92 75	93.51 111	98.27 63	96.40 138

tfpn200view9		89.55 136	87.86 151	91.53 110	93.90 99	97.26 79	94.31 83	89.74 78	85.87 161	81.15 145	76.46 162	70.38 200	91.76 105	94.92 75	93.51 111	98.28 62	96.61 127

diffmvs		91.37 91	91.09 95	91.70 103	92.71 143	96.47 119	94.03 97	88.78 109	92.74 63	85.43 116	83.63 95	80.37 138	91.76 105	93.39 130	93.78 105	97.50 143	97.23 89
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
thres600view7		89.28 142	87.47 161	91.39 114	94.12 89	97.25 82	93.94 105	89.74 78	85.62 166	80.63 151	75.24 176	69.33 210	91.66 107	94.92 75	93.23 124	98.27 63	96.72 123

DCV-MVSNet		91.24 95	91.26 90	91.22 118	92.84 138	93.44 174	93.82 108	86.75 145	91.33 81	85.61 108	84.00 90	85.46 90	91.27 108	92.91 137	93.62 108	97.02 168	98.05 54

viewdifsd2359ckpt07		90.96 106	90.40 110	91.62 106	93.22 119	96.95 104	93.49 125	89.26 99	88.94 125	85.56 109	80.56 133	80.99 130	91.25 109	94.88 79	94.01 100	96.92 181	96.49 134

GeoE		89.29 141	88.68 137	89.99 133	92.75 142	96.03 133	93.07 136	83.79 176	86.98 149	81.34 143	74.72 178	78.92 153	91.22 110	93.31 133	93.21 127	97.78 120	97.60 75

thres100view900		89.36 139	87.61 156	91.39 114	93.90 99	96.86 108	94.35 80	89.66 83	85.87 161	81.15 145	76.46 162	70.38 200	91.17 111	94.09 105	93.43 117	98.13 79	96.16 147

PMMVS		89.88 129	91.19 92	88.35 148	89.73 182	91.97 219	90.62 171	81.92 210	90.57 90	80.58 152	92.16 39	86.85 82	91.17 111	92.31 151	91.35 169	96.11 199	93.11 203

onestephybrid01		91.32 92	90.98 98	91.72 102	92.81 139	96.53 116	93.37 130	88.92 104	92.09 69	86.86 79	83.06 99	81.79 119	91.09 113	92.66 141	93.52 110	97.26 152	97.22 91

HyFIR lowres test		87.87 150	86.42 167	89.57 135	95.56 70	96.99 103	92.37 143	84.15 171	86.64 153	77.17 164	57.65 254	83.97 95	91.08 114	92.09 158	92.44 146	97.09 163	95.16 175

hybridnocas07		91.26 94	90.98 98	91.59 107	92.70 144	96.41 123	93.58 119	88.76 111	92.74 63	85.96 96	84.20 88	80.95 131	91.05 115	92.38 149	93.38 119	97.52 141	96.77 119

FA-MVS(training)		90.79 113	91.33 88	90.17 130	93.76 104	97.22 87	92.74 138	77.79 237	90.60 89	88.03 59	78.80 147	87.41 78	91.00 116	95.40 67	93.43 117	97.70 128	96.46 135

viewdifsd2359ckpt11		89.68 132	88.67 138	90.86 121	92.35 151	95.23 138	91.72 162	88.40 121	88.84 126	86.14 88	80.75 129	78.17 161	90.95 117	90.02 196	91.15 173	95.59 211	96.50 132

DELS-MVS		93.71 55	93.47 55	94.00 47	96.82 57	98.39 38	96.80 43	91.07 59	89.51 117	89.94 45	83.80 92	89.29 76	90.95 117	97.32 17	97.65 2	98.42 44	98.32 41
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
viewmsd2359difaftdt		89.67 134	88.66 139	90.85 122	92.35 151	95.23 138	91.72 162	88.40 121	88.80 127	86.12 89	80.75 129	78.20 160	90.94 119	90.02 196	91.15 173	95.59 211	96.50 132

ACMH+	85.75 12	87.19 157	86.02 174	88.56 146	93.42 109	94.41 151	89.91 188	87.66 139	83.45 186	72.25 191	76.42 164	71.99 193	90.78 120	89.86 199	90.94 175	97.32 149	95.11 177

hybrid		91.19 97	90.98 98	91.43 112	92.63 148	96.34 125	93.39 128	88.61 117	92.81 61	85.87 99	83.98 91	81.17 127	90.76 121	92.64 144	93.14 131	97.33 148	96.76 121

EPP-MVSNet		92.13 71	93.06 60	91.05 119	93.66 107	97.30 77	92.18 148	87.90 129	90.24 97	83.63 134	86.14 75	90.52 72	90.76 121	94.82 81	94.38 90	98.18 75	97.98 56

test2506		90.93 107	89.20 131	92.95 67	94.97 78	98.30 41	94.53 75	90.25 68	89.91 108	88.39 57	83.23 98	64.17 238	90.69 123	96.75 35	96.10 49	98.87 9	95.97 155

ECVR-MVS		90.77 114	89.27 129	92.52 76	94.97 78	98.30 41	94.53 75	90.25 68	89.91 108	85.80 103	73.64 183	74.31 180	90.69 123	96.75 35	96.10 49	98.87 9	95.91 159

RPSCF		89.68 132	89.24 130	90.20 128	92.97 134	92.93 192	92.30 145	87.69 137	90.44 93	85.12 126	91.68 43	85.84 89	90.69 123	87.34 222	86.07 225	92.46 247	90.37 233

ACMH	85.51 13	87.31 155	86.59 165	88.14 151	93.96 95	94.51 147	89.00 204	87.99 126	81.58 199	70.15 205	78.41 150	71.78 194	90.60 126	91.30 170	91.99 157	97.17 157	96.58 129
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 280x420		90.77 114	92.14 75	89.17 140	93.86 101	92.81 196	93.16 132	80.22 225	90.21 98	84.67 131	89.89 54	91.38 63	90.57 127	94.94 74	92.11 153	92.52 246	93.65 196

MSDG		90.42 122	88.25 145	92.94 68	96.67 59	94.41 151	93.96 101	92.91 44	89.59 115	86.26 85	76.74 159	80.92 133	90.43 128	92.60 145	92.08 155	97.44 147	91.41 222

test1111		90.47 121	89.10 133	92.07 91	94.92 80	98.30 41	94.17 90	90.30 67	89.56 116	83.92 132	73.25 190	73.66 181	90.26 129	96.77 33	96.14 47	98.87 9	96.04 152

PVSNet_BlendedMVS		92.80 61	92.44 70	93.23 58	96.02 65	97.83 60	93.74 113	90.58 63	91.86 73	90.69 39	85.87 78	82.04 116	90.01 130	96.39 46	95.26 64	98.34 52	97.81 66

PVSNet_Blended		92.80 61	92.44 70	93.23 58	96.02 65	97.83 60	93.74 113	90.58 63	91.86 73	90.69 39	85.87 78	82.04 116	90.01 130	96.39 46	95.26 64	98.34 52	97.81 66

CANet_DTU		90.74 116	92.93 64	88.19 150	94.36 84	96.61 111	94.34 81	84.66 164	90.66 85	68.75 215	90.41 51	86.89 81	89.78 132	95.46 65	94.87 73	97.25 153	95.62 164

0.4-1-1-0.1		85.56 177	83.44 198	88.04 152	83.51 241	92.54 203	92.35 144	82.48 193	82.48 192	85.45 114	76.70 160	73.34 183	89.71 133	81.68 252	84.56 234	94.73 235	92.79 210

0.3-1-1-0.015		85.24 184	82.99 208	87.87 158	83.27 243	92.15 211	92.14 152	82.29 198	81.93 197	85.41 117	76.15 167	73.18 185	89.63 134	81.11 255	84.26 237	94.50 236	92.12 217

baseline1		90.81 110	90.29 111	91.42 113	93.67 106	95.86 135	93.94 105	89.69 81	89.29 119	82.85 138	82.91 102	80.30 139	89.60 135	95.05 71	94.79 78	98.80 13	93.82 194

FC-MVSNet-train		90.55 118	90.19 113	90.97 120	93.78 103	95.16 141	92.11 153	88.85 106	87.64 141	83.38 136	84.36 87	78.41 158	89.53 136	94.69 85	93.15 130	98.15 77	97.92 61

0.4-1-1-0.2		85.17 185	82.95 209	87.75 159	83.20 244	92.00 218	91.99 157	82.20 200	81.62 198	85.34 122	76.38 165	73.33 184	89.43 137	81.21 254	84.14 238	94.36 237	92.00 218

USDC		86.73 161	85.96 176	87.63 162	91.64 159	93.97 159	92.76 137	84.58 166	88.19 134	70.67 201	80.10 135	67.86 217	89.43 137	91.81 161	89.77 206	96.69 190	90.05 237

Effi-MVS+-dtu		87.51 153	88.13 147	86.77 171	91.10 168	94.90 144	90.91 168	82.67 189	83.47 185	71.55 193	81.11 126	77.04 170	89.41 139	92.65 143	91.68 165	95.00 233	96.09 150

GBi-Net		90.21 124	90.11 115	90.32 125	88.66 193	93.65 170	94.25 86	85.78 154	90.03 102	85.56 109	77.38 152	86.13 84	89.38 140	93.97 110	94.16 95	98.31 56	95.47 168

test1		90.21 124	90.11 115	90.32 125	88.66 193	93.65 170	94.25 86	85.78 154	90.03 102	85.56 109	77.38 152	86.13 84	89.38 140	93.97 110	94.16 95	98.31 56	95.47 168

FMVSNet2		89.61 135	89.14 132	90.16 131	88.66 193	93.65 170	94.25 86	85.44 158	88.57 131	84.96 129	73.53 185	83.82 96	89.38 140	94.23 102	94.68 85	98.31 56	95.47 168

baseline		91.19 97	91.89 80	90.38 123	92.76 140	95.04 143	93.55 123	84.54 167	92.92 59	85.71 105	86.68 71	86.96 80	89.28 143	92.00 159	92.62 144	96.46 193	96.99 106

thisisatest0530		91.04 103	91.74 81	90.21 127	92.93 136	97.00 102	92.06 154	87.63 140	90.74 83	81.51 141	86.81 68	82.48 106	89.23 144	94.81 82	93.03 136	97.90 113	97.33 84

tttt0517		91.01 105	91.71 82	90.19 129	92.98 132	97.07 101	91.96 159	87.63 140	90.61 88	81.42 142	86.76 69	82.26 111	89.23 144	94.86 80	93.03 136	97.90 113	97.36 82

FMVSNet3		90.19 126	90.06 117	90.34 124	88.69 192	93.85 162	94.58 73	85.78 154	90.03 102	85.56 109	77.38 152	86.13 84	89.22 146	93.29 134	94.36 91	98.20 72	95.40 172

IterMVS-LS		88.60 144	88.45 140	88.78 143	92.02 156	92.44 207	92.00 156	83.57 180	86.52 156	78.90 159	78.61 149	81.34 124	89.12 147	90.68 184	93.18 128	97.10 162	96.35 140
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TinyColmap		84.04 202	82.01 219	86.42 175	90.87 171	91.84 220	88.89 206	84.07 173	82.11 196	69.89 207	71.08 199	60.81 252	89.04 148	90.52 186	89.19 212	95.76 203	88.50 247

FMVSNet1		87.33 154	86.00 175	88.89 141	87.13 219	92.83 195	93.08 135	84.46 168	81.35 201	82.20 139	66.33 225	77.96 163	88.96 149	93.97 110	94.16 95	97.54 140	95.38 173

UniMVSNet_NR-MVSNet		86.80 159	85.86 178	87.89 157	88.17 199	94.07 158	90.15 180	88.51 118	84.20 178	73.45 180	72.38 195	70.30 205	88.95 150	90.25 189	92.21 150	98.12 80	97.62 73

DU-MVS		86.12 167	84.81 187	87.66 160	87.77 206	93.78 164	90.15 180	87.87 131	84.40 172	73.45 180	70.59 201	64.82 235	88.95 150	90.14 190	92.33 147	97.76 122	97.62 73

MVSTER		91.73 82	91.61 84	91.86 97	93.18 121	94.56 145	94.37 79	87.90 129	90.16 101	88.69 55	89.23 56	81.28 125	88.92 152	95.75 60	93.95 102	98.12 80	96.37 139

LTVRE_ROB	81.71 16	82.44 225	81.84 221	83.13 215	89.01 188	92.99 189	88.90 205	82.32 197	66.26 261	54.02 264	74.68 180	59.62 258	88.87 153	90.71 183	92.02 156	95.68 208	96.62 126
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
CHOSEN 1792x2688		88.57 145	87.82 152	89.44 137	95.46 73	96.89 107	93.74 113	85.87 153	89.63 114	77.42 163	61.38 247	83.31 99	88.80 154	93.44 129	93.16 129	95.37 219	96.95 114

UniMVSNet_ETH3D		84.57 191	81.40 228	88.28 149	89.34 186	94.38 153	90.33 174	86.50 148	74.74 246	77.52 162	59.90 252	62.04 246	88.78 155	88.82 215	92.65 143	97.22 154	97.24 88

SCA		86.25 163	87.52 159	84.77 194	91.59 160	93.90 160	89.11 201	73.25 254	90.38 94	72.84 187	83.26 97	83.79 97	88.49 156	86.07 229	85.56 228	93.33 239	89.67 239

pmmvs4		86.00 171	84.28 191	88.00 153	87.80 204	92.01 217	89.94 187	84.91 162	86.79 152	80.98 148	73.41 188	66.34 226	88.12 157	89.31 207	88.90 216	96.24 198	93.20 202

CostFormer		86.78 160	86.05 172	87.62 163	92.15 154	93.20 183	91.55 164	75.83 242	88.11 136	85.29 123	81.76 118	76.22 174	87.80 158	84.45 235	85.21 231	93.12 241	93.42 199

dmvs_re		87.31 155	86.10 171	88.74 144	89.84 179	94.28 154	92.66 139	89.41 95	82.61 191	74.69 171	74.69 179	69.47 208	87.78 159	92.38 149	93.23 124	98.03 93	96.02 154

EPNet		93.92 53	94.40 49	93.36 57	97.89 39	96.55 114	96.08 51	92.14 49	91.65 77	89.16 49	94.07 33	90.17 74	87.78 159	95.24 69	94.97 72	97.09 163	98.15 48
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PatchmatchNet		85.70 173	86.65 164	84.60 197	91.79 157	93.40 175	89.27 197	73.62 249	90.19 99	72.63 189	82.74 106	81.93 118	87.64 161	84.99 233	84.29 236	92.64 245	89.00 242
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v2v482		84.51 193	83.05 207	86.20 176	87.25 215	93.28 180	90.22 178	85.40 159	79.94 212	69.78 208	67.74 217	65.15 232	87.57 162	89.12 211	90.55 186	96.97 172	95.60 165

EPMVS		85.77 172	86.24 169	85.23 189	92.76 140	93.78 164	89.91 188	73.60 250	90.19 99	74.22 173	82.18 114	78.06 162	87.55 163	85.61 232	85.38 230	93.32 240	88.48 248

IS_MVSNet		91.87 78	93.35 57	90.14 132	94.09 90	97.73 65	93.09 134	88.12 125	88.71 129	79.98 154	84.49 85	90.63 69	87.49 164	97.07 25	96.96 19	98.07 87	97.88 65

Baseline_NR-MVSNet		85.28 182	83.42 200	87.46 164	87.77 206	90.80 235	89.90 190	87.69 137	83.93 182	74.16 174	64.72 237	66.43 225	87.48 165	90.14 190	90.83 176	97.73 125	97.11 97

COLMAP_ROB	84.39 15	87.61 152	86.03 173	89.46 136	95.54 72	94.48 148	91.77 161	90.14 70	87.16 147	75.50 169	73.41 188	76.86 172	87.33 166	90.05 195	89.76 207	96.48 192	90.46 232
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
dps		85.00 187	83.21 205	87.08 166	90.73 173	92.55 202	89.34 196	75.29 244	84.94 167	87.01 77	79.27 142	67.69 218	87.27 167	84.22 236	83.56 239	92.83 244	90.25 235

dtuonly		85.32 181	85.19 184	85.48 184	89.06 187	91.16 229	91.15 165	82.82 186	83.63 183	70.67 201	72.83 193	79.27 151	87.08 168	89.96 198	88.41 217	92.11 252	91.06 227

v10		84.18 199	83.17 206	85.37 185	87.34 213	92.68 198	90.32 175	81.33 217	79.93 213	69.23 213	66.33 225	65.74 228	87.03 169	90.84 179	90.38 188	96.97 172	96.29 144

TranMVSNet+NR-MVSNet		85.57 176	84.41 190	86.92 167	87.67 209	93.34 177	90.31 176	88.43 120	83.07 188	70.11 206	69.99 207	65.28 230	86.96 170	89.73 201	92.27 148	98.06 90	97.17 95

v1192		83.56 210	82.35 213	84.98 191	86.84 224	92.84 193	90.01 185	82.70 187	78.54 223	66.48 229	64.88 235	62.91 240	86.91 171	90.72 182	90.25 192	96.94 176	96.32 142

v1144		84.03 203	82.88 210	85.37 185	87.17 217	93.15 187	90.18 179	83.31 183	78.83 222	67.85 221	65.99 227	64.99 233	86.79 172	90.75 181	90.33 190	96.90 182	96.15 148

v1921920		83.30 214	82.09 217	84.70 195	86.59 228	92.67 199	89.82 191	82.23 199	78.32 224	65.76 234	64.64 238	62.35 243	86.78 173	90.34 188	90.02 200	97.02 168	96.31 143

v144192		83.48 211	82.23 214	84.94 192	86.65 225	92.84 193	89.63 195	82.48 193	77.87 227	67.36 225	65.33 232	63.50 239	86.51 174	89.72 202	89.99 202	97.03 167	96.35 140

v1240		82.88 220	81.66 224	84.29 201	86.46 229	92.52 206	89.06 202	81.82 212	77.16 232	65.09 238	64.17 240	61.50 249	86.36 175	90.12 192	90.13 194	96.95 175	96.04 152

tpmrst		83.72 207	83.45 197	84.03 206	92.21 153	91.66 223	88.74 207	73.58 251	88.14 135	72.67 188	77.37 155	72.11 192	86.34 176	82.94 240	82.05 242	90.63 259	89.86 238

ADS-MVSNet		84.08 201	84.95 185	83.05 220	91.53 164	91.75 222	88.16 217	70.70 259	89.96 105	69.51 210	78.83 145	76.97 171	86.29 177	84.08 237	84.60 233	92.13 251	88.48 248

CR-MVSNet		85.48 178	86.29 168	84.53 199	91.08 170	92.10 212	89.18 199	73.30 252	84.75 168	71.08 198	73.12 192	77.91 164	86.27 178	91.48 166	90.75 180	96.27 197	93.94 191

PatchT		83.86 204	85.51 182	81.94 234	88.41 196	91.56 225	78.79 257	71.57 257	84.08 180	71.08 198	70.62 200	76.13 175	86.27 178	91.48 166	90.75 180	95.52 217	93.94 191

v8		84.45 197	83.30 204	85.80 179	87.53 211	92.95 190	90.31 176	82.46 195	80.46 205	71.43 194	66.99 220	67.16 220	86.14 180	89.26 209	90.22 193	96.94 176	96.06 151

MDTV_nov1_ep13		86.64 162	87.50 160	85.65 182	90.73 173	93.69 168	89.96 186	78.03 236	89.48 118	76.85 165	84.92 83	82.42 108	86.14 180	86.85 226	86.15 224	92.17 249	88.97 243

Fast-Effi-MVS+-dtu		86.25 163	87.70 154	84.56 198	90.37 178	93.70 167	90.54 172	78.14 234	83.50 184	65.37 237	81.59 121	75.83 176	86.09 182	91.70 164	91.70 163	96.88 184	95.84 160

usedtu_dtu_shiyan1		86.08 170	86.20 170	85.93 177	81.88 250	93.87 161	90.68 169	86.54 147	86.84 150	72.93 185	71.70 196	75.39 178	85.90 183	91.74 163	91.33 170	97.66 133	92.56 214

usedtu_blend_shiyan5		83.61 208	81.81 223	85.71 181	74.05 258	89.88 240	91.99 157	82.09 202	78.96 218	85.41 117	75.60 171	73.18 185	85.67 184	82.18 245	80.05 253	95.03 228	92.85 207

blend_shiyan4		84.25 198	82.04 218	86.82 169	82.33 245	89.89 239	90.94 166	81.51 216	81.22 202	85.41 117	75.60 171	73.18 185	85.67 184	81.60 253	79.96 257	95.08 224	92.85 207

FE-MVSNET3		83.34 213	81.82 222	85.12 190	74.05 258	89.88 240	88.48 210	82.09 202	78.96 218	85.41 117	75.60 171	73.18 185	85.67 184	82.18 245	80.05 253	95.03 228	92.87 205

baseline2		88.97 143	89.50 126	88.36 147	91.14 167	95.30 137	90.13 182	85.17 161	87.24 146	80.80 149	84.46 86	78.44 157	85.60 187	93.54 126	91.87 159	97.31 150	95.66 163

tfpnnormal		83.80 206	81.26 230	86.77 171	89.60 183	93.26 182	89.72 193	87.60 142	72.78 248	70.44 203	60.53 251	61.15 251	85.55 188	92.72 139	91.44 167	97.71 126	96.92 115

V42		84.48 195	83.36 203	85.79 180	87.14 218	93.28 180	90.03 183	83.98 174	80.30 207	71.20 197	66.90 222	67.17 219	85.55 188	89.35 205	90.27 191	96.82 187	96.27 145

PVSNet_Blended_VisFu		91.92 76	92.39 72	91.36 117	95.45 75	97.85 58	92.25 147	89.54 92	88.53 132	87.47 68	79.82 137	90.53 70	85.47 190	96.31 49	95.16 67	97.99 106	98.56 27

RPMNet		84.82 190	85.90 177	83.56 211	91.10 168	92.10 212	88.73 208	71.11 258	84.75 168	68.79 214	73.56 184	77.62 167	85.33 191	90.08 194	89.43 210	96.32 196	93.77 195

tpm cat1		84.13 200	81.99 220	86.63 173	91.74 158	91.50 226	90.68 169	75.69 243	86.12 160	85.44 115	72.39 194	70.72 197	85.16 192	80.89 256	81.56 243	91.07 256	90.71 230

UniMVSNet (Re)		86.22 165	85.46 183	87.11 165	88.34 197	94.42 150	89.65 194	87.10 144	84.39 174	74.61 172	70.41 204	68.10 215	85.10 193	91.17 174	91.79 161	97.84 116	97.94 59

blended_shiyan8		81.65 231	80.43 236	83.06 219	74.09 256	89.98 237	88.48 210	81.99 208	79.15 215	73.52 179	67.98 215	70.34 204	85.09 194	82.39 243	80.39 249	95.19 222	92.81 209

wanda-best-256-512		81.56 234	80.31 237	83.02 221	74.05 258	89.88 240	88.48 210	82.09 202	78.96 218	73.38 182	68.19 211	70.37 202	85.08 195	82.18 245	80.05 253	95.03 228	92.52 215

FE-blended-shiyan7		81.56 234	80.31 237	83.02 221	74.05 258	89.88 240	88.48 210	82.09 202	78.97 217	73.38 182	68.19 211	70.35 203	85.08 195	82.18 245	80.05 253	95.03 228	92.52 215

blended_shiyan6		81.63 232	80.44 235	83.02 221	74.06 257	89.96 238	88.46 214	81.98 209	79.01 216	73.38 182	68.03 214	70.41 199	85.03 197	82.38 244	80.40 248	95.18 223	92.87 205

MS-PatchMatch		87.63 151	87.61 156	87.65 161	93.95 96	94.09 157	92.60 141	81.52 215	86.64 153	76.41 167	73.46 187	85.94 87	85.01 198	92.23 155	90.00 201	96.43 195	90.93 229

pmmvs5		83.37 212	82.68 211	84.18 204	87.13 219	93.18 184	86.74 229	82.08 206	76.48 236	67.28 226	71.26 198	62.70 242	84.71 199	90.77 180	90.12 197	97.15 158	94.24 187

anonymousdsp		84.51 193	85.85 179	82.95 224	86.30 230	93.51 173	85.77 237	80.38 224	78.25 226	63.42 243	73.51 186	72.20 191	84.64 200	93.21 136	92.16 152	97.19 156	98.14 49

test-mter		86.09 169	88.38 141	83.43 213	87.89 203	92.61 200	86.89 228	77.11 240	84.30 175	68.62 217	82.57 108	82.45 107	84.34 201	92.40 148	90.11 198	95.74 204	94.21 189

test-LLR		86.88 158	88.28 143	85.24 188	91.22 165	92.07 214	87.41 223	83.62 178	84.58 170	69.33 211	83.00 100	82.79 102	84.24 202	92.26 152	89.81 204	95.64 209	93.44 197

TESTMET0.1,1		86.11 168	88.28 143	83.59 210	87.80 204	92.07 214	87.41 223	77.12 239	84.58 170	69.33 211	83.00 100	82.79 102	84.24 202	92.26 152	89.81 204	95.64 209	93.44 197

tpm		83.16 215	83.64 194	82.60 230	90.75 172	91.05 230	88.49 209	73.99 247	82.36 193	67.08 228	78.10 151	68.79 211	84.17 204	85.95 231	85.96 226	91.09 255	93.23 201

GA-MVS		85.08 186	85.65 180	84.42 200	89.77 181	94.25 155	89.26 198	84.62 165	81.19 203	62.25 245	75.72 170	68.44 214	84.14 205	93.57 124	91.68 165	96.49 191	94.71 181

gm-plane-assit		77.65 245	78.50 243	76.66 247	87.96 202	85.43 260	64.70 269	74.50 245	64.15 263	51.26 267	61.32 248	58.17 260	84.11 206	95.16 70	93.83 104	97.45 146	91.41 222

SixPastTwentyTwo		83.12 217	83.44 198	82.74 226	87.71 208	93.11 188	82.30 247	82.33 196	79.24 214	64.33 240	78.77 148	62.75 241	84.11 206	88.11 217	87.89 219	95.70 207	94.21 189

gg-mvs-nofinetune		81.83 228	83.58 195	79.80 240	91.57 161	96.54 115	93.79 109	68.80 262	62.71 265	43.01 273	55.28 258	85.06 92	83.65 208	96.13 52	94.86 74	97.98 109	94.46 183

FMVSNet5		84.47 196	84.72 188	84.18 204	83.30 242	88.43 251	88.09 218	79.42 229	84.25 176	74.14 175	73.15 191	78.74 154	83.65 208	91.19 173	91.19 172	96.46 193	86.07 254

gbinet_0.2-2-1-0.02		81.58 233	80.59 234	82.73 227	73.97 262	89.77 244	88.25 216	82.49 192	77.59 229	73.56 178	67.87 216	71.56 195	83.06 210	82.77 241	80.22 250	95.04 226	94.38 185

IterMVS-SCA-FT		85.44 180	86.71 163	83.97 207	90.59 176	90.84 233	89.73 192	78.34 233	84.07 181	66.40 231	77.27 157	78.66 155	83.06 210	91.20 171	90.10 199	95.72 206	94.78 179

IterMVS		85.25 183	86.49 166	83.80 208	90.42 177	90.77 236	90.02 184	78.04 235	84.10 179	66.27 232	77.28 156	78.41 158	83.01 212	90.88 178	89.72 208	95.04 226	94.24 187
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PM-MVS		80.29 238	79.30 241	81.45 237	81.91 248	88.23 252	82.61 245	79.01 230	79.99 211	67.15 227	69.07 208	51.39 267	82.92 213	87.55 221	85.59 227	95.08 224	93.28 200

NR-MVSNet		85.46 179	84.54 189	86.52 174	88.33 198	93.78 164	90.45 173	87.87 131	84.40 172	71.61 192	70.59 201	62.09 245	82.79 214	91.75 162	91.75 162	98.10 83	97.44 79

CP-MVSNet		83.11 218	82.15 215	84.23 202	87.20 216	92.70 197	86.42 232	83.53 181	77.83 228	67.67 223	66.89 223	60.53 254	82.47 215	89.23 210	90.65 184	98.08 86	97.20 93

v7n		82.25 226	81.54 226	83.07 218	85.55 235	92.58 201	86.68 231	81.10 221	76.54 235	65.97 233	62.91 243	60.56 253	82.36 216	91.07 177	90.35 189	96.77 189	96.80 117

pm-mvs1		84.55 192	83.46 196	85.82 178	88.16 200	93.39 176	89.05 203	85.36 160	74.03 247	72.43 190	65.08 233	71.11 196	82.30 217	93.48 127	91.70 163	97.64 135	95.43 171

CDS-MVSNet		88.34 147	88.71 136	87.90 156	90.70 175	94.54 146	92.38 142	86.02 151	80.37 206	79.42 156	79.30 141	83.43 98	82.04 218	93.39 130	94.01 100	96.86 186	95.93 158
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		84.94 189	84.95 185	84.93 193	88.82 189	93.18 184	88.44 215	81.28 218	77.16 232	73.76 177	75.43 175	76.57 173	82.04 218	90.59 185	90.79 177	95.22 221	90.94 228

MVS-HIRNet		78.16 243	77.57 247	78.83 242	85.83 232	87.76 253	76.67 259	70.22 260	75.82 242	67.39 224	55.61 257	70.52 198	81.96 220	86.67 227	85.06 232	90.93 257	81.58 261

MIMVSNet		82.97 219	84.00 193	81.77 236	82.23 247	92.25 210	87.40 225	72.73 255	81.48 200	69.55 209	68.79 209	72.42 190	81.82 221	92.23 155	92.25 149	96.89 183	88.61 246

v148		83.61 208	82.10 216	85.37 185	87.34 213	92.94 191	87.48 222	85.72 157	78.92 221	73.87 176	65.71 230	64.69 236	81.78 222	87.82 218	89.35 211	96.01 200	95.26 174

PS-CasMVS		82.53 223	81.54 226	83.68 209	87.08 221	92.54 203	86.20 234	83.46 182	76.46 237	65.73 235	65.71 230	59.41 259	81.61 223	89.06 212	90.55 186	98.03 93	97.07 98

pmmvs-eth3d		79.78 241	77.58 246	82.34 232	81.57 251	87.46 255	82.92 244	81.28 218	75.33 244	71.34 195	61.88 245	52.41 265	81.59 224	87.56 220	86.90 223	95.36 220	91.48 221

PEN-MVS		82.49 224	81.58 225	83.56 211	86.93 222	92.05 216	86.71 230	83.84 175	76.94 234	64.68 239	67.24 218	60.11 255	81.17 225	87.78 219	90.70 183	98.02 99	96.21 146

TDRefinement		84.97 188	83.39 201	86.81 170	92.97 134	94.12 156	92.18 148	87.77 135	82.78 190	71.31 196	68.43 210	68.07 216	81.10 226	89.70 203	89.03 214	95.55 215	91.62 220

pmmvs6		80.90 236	78.77 242	83.38 214	85.84 231	91.61 224	86.01 235	82.54 191	64.17 262	70.43 204	54.14 262	67.06 221	80.73 227	90.50 187	89.17 213	94.74 234	94.75 180

MDTV_nov1_ep13_2view		80.43 237	80.94 232	79.84 239	84.82 238	90.87 232	84.23 241	73.80 248	80.28 208	64.33 240	70.05 206	68.77 212	79.67 228	84.83 234	83.50 240	92.17 249	88.25 250

CMPMVS	61.19 17	79.86 240	77.46 248	82.66 229	91.54 163	91.82 221	83.25 243	81.57 214	70.51 256	68.64 216	59.89 253	66.77 223	79.63 229	84.00 238	84.30 235	91.34 254	84.89 257
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UA-Net		90.81 110	92.58 67	88.74 144	94.87 82	97.44 73	92.61 140	88.22 123	82.35 194	78.93 158	85.20 82	95.61 42	79.56 230	96.52 41	96.57 28	98.23 69	94.37 186

Vis-MVSNet (Re-imp)		90.54 119	92.76 65	87.94 155	93.73 105	96.94 106	92.17 150	87.91 128	88.77 128	76.12 168	83.68 93	90.80 65	79.49 231	96.34 48	96.35 35	98.21 71	96.46 135

DTE-MVSNet		81.76 229	81.04 231	82.60 230	86.63 226	91.48 228	85.97 236	83.70 177	76.45 238	62.44 244	67.16 219	59.98 256	78.98 232	87.15 223	89.93 203	97.88 115	95.12 176

thisisatest0515		85.70 173	87.00 162	84.19 203	88.16 200	93.67 169	84.20 242	84.14 172	83.39 187	72.91 186	76.79 158	74.75 179	78.82 233	92.57 146	91.26 171	96.94 176	96.56 131

TransMVSNet (Re)		82.67 222	80.93 233	84.69 196	88.71 191	91.50 226	87.90 219	87.15 143	71.54 253	68.24 219	63.69 241	64.67 237	78.51 234	91.65 165	90.73 182	97.64 135	92.73 213

UGNet		91.52 87	93.41 56	89.32 138	94.13 88	97.15 93	91.83 160	89.01 101	90.62 87	85.86 100	86.83 67	91.73 59	77.40 235	94.68 86	94.43 89	97.71 126	98.40 40
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
Vis-MVSNet		89.36 139	91.49 86	86.88 168	92.10 155	97.60 70	92.16 151	85.89 152	84.21 177	75.20 170	82.58 107	87.13 79	77.40 235	95.90 58	95.63 56	98.51 29	97.36 82
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dtuonlycased		77.37 247	76.66 250	78.20 244	81.91 248	88.92 249	79.41 253	78.66 232	75.26 245	59.93 254	63.10 242	69.37 209	77.10 237	75.02 262	76.14 261	92.22 248	88.78 244

CVMVSNet		83.83 205	85.53 181	81.85 235	89.60 183	90.92 231	87.81 221	83.21 184	80.11 209	60.16 253	76.47 161	78.57 156	76.79 238	89.76 200	90.13 194	93.51 238	92.75 212

pmnet_mix02		80.14 239	80.21 240	80.06 238	86.61 227	89.66 246	80.40 252	82.20 200	82.29 195	61.35 249	71.52 197	66.67 224	76.75 239	82.55 242	80.18 251	93.05 242	88.62 245

EG-PatchMatch MVS		81.70 230	81.31 229	82.15 233	88.75 190	93.81 163	87.14 226	78.89 231	71.57 251	64.12 242	61.20 250	68.46 213	76.73 240	91.48 166	90.77 179	97.28 151	91.90 219

MDA-MVSNet-bldmvs		73.81 250	72.56 255	75.28 249	72.52 265	88.87 250	74.95 263	82.67 189	71.57 251	55.02 261	65.96 228	42.84 274	76.11 241	70.61 265	81.47 244	90.38 262	86.59 252

WR-MVS_H		82.86 221	82.66 212	83.10 217	87.44 212	93.33 178	85.71 238	83.20 185	77.36 231	68.20 220	66.37 224	65.23 231	76.05 242	89.35 205	90.13 194	97.99 106	96.89 116

FE-MVSNET2		76.99 248	76.02 251	78.12 245	71.26 266	89.46 247	81.92 248	80.87 222	71.48 254	61.96 247	47.82 266	54.83 263	75.73 243	89.29 208	88.91 215	97.00 170	90.36 234

WR-MVS		83.14 216	83.38 202	82.87 225	87.55 210	93.29 179	86.36 233	84.21 170	80.05 210	66.41 230	66.91 221	66.92 222	75.66 244	88.96 213	90.56 185	97.05 166	96.96 113

pmmvs3		71.13 255	71.06 257	71.21 255	73.54 264	80.19 265	71.69 267	64.86 264	62.04 266	52.10 265	54.92 260	48.00 272	75.03 245	83.75 239	83.24 241	90.04 263	85.27 255

EPNet_dtu		88.32 148	90.61 108	85.64 183	96.79 58	92.27 209	92.03 155	90.31 66	89.05 123	65.44 236	89.43 55	85.90 88	74.22 246	92.76 138	92.09 154	95.02 232	92.76 211
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FC-MVSNet-test		86.15 166	89.10 133	82.71 228	89.83 180	93.18 184	87.88 220	84.69 163	86.54 155	62.18 246	82.39 111	83.31 99	74.18 247	92.52 147	91.86 160	97.50 143	93.88 193

PatchmatchNet1												61.90 247	74.10 248	82.01 250	80.80 246	90.60 260	84.59 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
IB-MVS	85.10 14	87.98 149	87.97 150	87.99 154	94.55 83	96.86 108	84.52 240	88.21 124	86.48 159	88.54 56	74.41 181	77.74 166	74.10 248	89.65 204	92.85 139	98.06 90	97.80 68
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
N_pmnet		77.55 246	76.68 249	78.56 243	85.43 236	87.30 256	78.84 256	81.88 211	78.30 225	60.61 250	61.46 246	62.15 244	74.03 250	82.04 249	80.69 247	90.59 261	84.81 258

test0.0.03 1		85.58 175	87.69 155	83.11 216	91.22 165	92.54 203	85.60 239	83.62 178	85.66 164	67.84 222	82.79 105	79.70 149	73.51 251	91.15 175	90.79 177	96.88 184	91.23 225

new_pmnet		72.29 254	73.25 254	71.16 256	75.35 255	81.38 264	73.72 265	69.27 261	75.97 240	49.84 270	56.27 255	56.12 262	69.08 252	81.73 251	80.86 245	89.72 264	80.44 263

testgi		81.94 227	84.09 192	79.43 241	89.53 185	90.83 234	82.49 246	81.75 213	80.59 204	59.46 256	82.82 104	65.75 227	67.97 253	90.10 193	89.52 209	95.39 218	89.03 241

DeepMVS_CX						71.82 269	68.37 268	48.05 269	77.38 230	46.88 271	65.77 229	47.03 273	67.48 254	64.27 268		76.89 271	76.72 264

EU-MVSNet		78.43 242	80.25 239	76.30 248	83.81 240	87.27 257	80.99 250	79.52 228	76.01 239	54.12 263	70.44 203	64.87 234	67.40 255	86.23 228	85.54 229	91.95 253	91.41 222

FE-MVSNET		73.24 251	74.06 252	72.28 254	64.92 270	85.32 261	76.06 260	79.75 226	67.71 260	50.14 269	49.61 264	54.40 264	67.26 256	85.97 230	87.33 221	95.53 216	88.10 251

Anonymous20231206		78.09 244	78.11 245	78.07 246	85.19 237	89.17 248	80.99 250	81.24 220	75.46 243	58.25 258	54.78 261	59.90 257	66.73 257	88.94 214	88.26 218	96.01 200	90.25 235

ambc			67.96 259		73.69 263	79.79 266	73.82 264		71.61 250	59.80 255	46.00 267	20.79 279	66.15 258	86.92 225	80.11 252	89.13 265	90.50 231

usedtu_dtu_shiyan2		69.49 257	68.33 258	70.84 257	57.31 274	83.43 263	77.39 258	72.63 256	54.43 267	61.92 248	40.25 270	52.40 266	65.07 259	79.46 258	79.03 259	90.69 258	89.29 240

MIMVSNet1		73.19 252	73.70 253	72.60 253	65.42 269	86.69 259	75.56 262	79.65 227	67.87 259	55.30 260	45.24 268	56.41 261	63.79 260	86.98 224	87.66 220	95.85 202	85.04 256

new-patchmatchnet		72.32 253	71.09 256	73.74 251	81.17 252	84.86 262	72.21 266	77.48 238	68.32 258	54.89 262	55.10 259	49.31 270	63.68 261	79.30 259	76.46 260	93.03 243	84.32 260

FPMVS		69.87 256	67.10 260	73.10 252	84.09 239	78.35 267	79.40 254	76.41 241	71.92 249	57.71 259	54.06 263	50.04 268	56.72 262	71.19 264	68.70 264	84.25 266	75.43 265

Gipuma		58.52 261	56.17 264	61.27 259	67.14 268	58.06 271	52.16 273	68.40 263	69.00 257	45.02 272	22.79 273	20.57 280	55.11 263	76.27 260	79.33 258	79.80 269	67.16 268
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test20.03		76.41 249	78.49 244	73.98 250	85.64 233	87.50 254	75.89 261	80.71 223	70.84 255	51.07 268	68.06 213	61.40 250	54.99 264	88.28 216	87.20 222	95.58 214	86.15 253

test_method		58.10 262	64.61 262	50.51 262	28.26 276	41.71 275	61.28 270	32.07 270	75.92 241	52.04 266	47.94 265	61.83 248	51.80 265	79.83 257	63.95 268	77.60 270	81.05 262

EMVS		39.04 266	34.32 270	44.54 265	58.25 272	39.35 276	27.61 277	62.55 266	35.99 272	16.40 277	20.04 277	14.77 281	44.80 266	33.12 273	44.10 270	57.61 275	52.89 274

E-PMN		40.00 264	35.74 269	44.98 264	57.69 273	39.15 277	28.05 276	62.70 265	35.52 273	17.78 276	20.90 274	14.36 282	44.47 267	35.89 272	47.86 269	59.15 274	56.47 273

PMVS	56.77 18	61.27 259	58.64 263	64.35 258	75.66 254	54.60 272	53.62 272	74.23 246	53.69 268	58.37 257	44.27 269	49.38 269	44.16 268	69.51 266	65.35 266	80.07 268	73.66 266
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.81 19	39.52 265	41.58 268	37.11 266	33.93 275	49.06 273	26.45 278	54.22 268	29.46 275	24.15 274	20.77 275	10.60 284	34.42 269	51.12 269	65.27 267	49.49 276	64.81 270
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		53.68 263	55.72 265	51.30 261	58.84 271	67.02 270	54.23 271	60.97 267	47.50 271	19.42 275	34.81 271	31.97 277	30.88 270	65.84 267	69.99 263	83.47 267	72.92 267

MVS_clip		28.15 268	43.14 267	10.65 269	8.94 278	19.20 279	9.65 281	1.75 272	51.68 269	2.21 281	56.15 256	38.39 275	27.36 271	38.12 271	36.05 272	14.00 278	62.41 271

tmp_tt				50.24 263	68.55 267	46.86 274	48.90 274	18.28 271	86.51 158	68.32 218	70.19 205	65.33 229	26.69 272	74.37 263	66.80 265	70.72 273

VLMVS_CLIP		29.70 267	43.84 266	13.21 268	11.25 277	21.39 278	16.21 280	1.74 273	47.67 270	3.36 280	62.42 244	35.59 276	23.65 273	41.21 270	37.55 271	23.05 277	61.07 272

WB-MVS		60.76 260	66.86 261	53.64 260	82.24 246	72.70 268	48.70 275	82.04 207	63.91 264	12.91 278	64.77 236	49.00 271	22.74 274	75.95 261	75.36 262	73.22 272	66.33 269

VLMVS		17.69 269	26.31 271	7.64 270	8.91 279	13.24 280	6.52 282	1.39 274	30.98 274	5.28 279	30.66 272	28.26 278	15.43 275	21.16 274	20.12 273	8.28 279	39.73 275

MVS_baseline		8.56 270	14.59 272	1.52 272	0.64 280	1.40 283	0.33 285	0.00 278	16.79 276	0.00 285	20.45 276	13.87 283	8.04 276	10.31 275	9.13 274	0.09 282	30.19 276

test123		3.48 272	5.31 274	1.34 273	0.20 283	1.52 282	2.17 284	0.58 276	6.13 278	0.31 284	9.85 279	0.31 286	3.90 277	2.65 277	5.28 276	0.87 281	11.46 277

testmvs		4.35 271	6.54 273	1.79 271	0.60 281	1.82 281	3.06 283	0.95 275	7.22 277	0.88 283	12.38 278	1.25 285	3.87 278	6.09 276	5.58 275	1.40 280	11.42 278

GG-mvs-BLEND		62.84 258	90.21 112	30.91 267	0.57 282	94.45 149	86.99 227	0.34 277	88.71 129	0.98 282	81.55 122	91.58 61	0.86 279	92.66 141	91.43 168	95.73 205	91.11 226

uanet_test		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

PatchmatchNet2					85.63 234	86.94 258	78.98 255
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										60.42 251	61.25 249
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							98.60 9	96.48 8		96.36 3						98.66 22

RE-MVS-def										60.19 252

9.14												97.28 25

SR-MVS					98.93 20			96.00 19				97.75 17

our_test_3					86.93 222	89.77 244	81.61 249

MTAPA										95.36 5		97.46 23

MTMP										95.70 4		96.90 29

Patchmatch-RL test							18.47 279

XVS					95.68 67	98.66 17	94.96 69			88.03 59		96.06 36				98.46 37

X-MVStestdata					95.68 67	98.66 17	94.96 69			88.03 59		96.06 36				98.46 37

mPP-MVS					98.76 25							95.49 43

NP-MVS									91.63 78

Patchmtry						92.39 208	89.18 199	73.30 252		71.08 198

High-resolution multi-view benchmark