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.

ETV-MVS		93.80 54	94.57 47	92.91 69	93.98 93	97.50 70	93.62 117	88.70 113	91.95 70	87.57 66	90.21 51	90.79 65	94.56 46	97.20 23	96.35 35	99.02 1	97.98 56

CS-MVS		94.53 48	94.73 46	94.31 45	96.30 62	98.53 29	94.98 67	89.24 100	93.37 55	90.24 43	88.96 58	89.76 74	96.09 30	97.48 16	96.42 29	98.99 2	98.59 26

DPE-MVS		97.83 6	98.13 6	97.48 7	98.83 24	99.19 4	98.99 1	96.70 1	96.05 20	94.39 12	98.30 3	99.47 4	97.02 8	97.75 7	97.02 16	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
EC-MVSNet		94.19 51	95.05 42	93.18 61	93.56 107	97.65 67	95.34 63	86.37 149	92.05 69	88.71 54	89.91 52	93.32 50	96.14 29	97.29 20	96.42 29	98.98 3	98.70 18

APDe-MVS		97.79 7	97.96 8	97.60 4	99.20 2	99.10 7	98.88 2	96.68 2	96.81 9	94.64 9	97.84 5	98.02 13	97.24 3	97.74 8	97.02 16	98.97 5	99.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TSAR-MVS + MP.		97.31 11	97.64 11	96.92 15	97.28 49	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 13	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
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

MED-MVS		98.10 1	98.34 3	97.82 1	99.06 5	99.12 6	98.70 6	96.61 6	98.03 1	96.47 1	98.77 1	99.31 5	97.16 5	97.50 15	96.87 21	98.89 8	98.79 14

test2506		90.93 107	89.20 131	92.95 67	94.97 77	98.30 41	94.53 74	90.25 68	89.91 107	88.39 57	83.23 97	64.17 237	90.69 122	96.75 35	96.10 49	98.87 9	95.97 154

test1111		90.47 121	89.10 133	92.07 91	94.92 79	98.30 41	94.17 89	90.30 67	89.56 115	83.92 131	73.25 189	73.66 180	90.26 128	96.77 33	96.14 47	98.87 9	96.04 151

ECVR-MVS		90.77 114	89.27 129	92.52 76	94.97 77	98.30 41	94.53 74	90.25 68	89.91 107	85.80 102	73.64 182	74.31 179	90.69 122	96.75 35	96.10 49	98.87 9	95.91 158

DVP-MVS++		98.07 2	98.46 1	97.62 3	99.08 3	99.29 2	98.84 3	96.63 4	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

baseline1		90.81 110	90.29 111	91.42 113	93.67 105	95.86 134	93.94 104	89.69 81	89.29 118	82.85 137	82.91 101	80.30 138	89.60 134	95.05 71	94.79 78	98.80 13	93.82 193

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
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

DVP-MVS		97.93 5	98.23 4	97.58 5	99.05 8	99.31 1	98.64 7	96.62 5	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
SPE-MVS-test		94.63 46	95.28 40	93.88 52	96.56 59	98.67 16	93.41 126	89.31 97	94.27 45	89.64 46	90.84 47	91.64 59	95.58 36	97.04 27	96.17 44	98.77 16	98.32 41

SED-MVS		97.98 3	98.36 2	97.54 6	98.94 18	99.29 2	98.81 4	96.64 3	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

MGCNet		96.54 24	97.36 16	95.60 35	98.03 36	99.07 9	98.02 24	92.24 48	95.87 22	92.54 28	96.41 17	96.08 34	94.03 55	97.69 9	97.47 3	98.73 19	98.90 13

TSAR-MVS + GP.		95.86 31	96.95 24	94.60 44	94.07 90	98.11 49	96.30 47	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

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 6	97.16 12	98.68 20	98.97 11
Skip Steuart: Steuart Systems R&D Blog.
TestfortrainingZip							98.60 9	96.48 8		96.36 3						98.66 22

ME-MVS		97.97 4	98.17 5	97.75 2	99.06 5	99.08 8	98.60 9	96.48 8	97.14 4	96.47 1	98.77 1	99.29 6	97.22 4	97.29 20	96.80 23	98.66 22	98.79 14

PHI-MVS		95.86 31	96.93 25	94.61 43	97.60 45	98.65 21	96.49 44	93.13 43	94.07 47	87.91 63	97.12 9	97.17 26	93.90 59	96.46 43	96.93 19	98.64 24	98.10 53

3Dnovator	90.28 7	94.70 45	94.34 51	95.11 38	98.06 35	98.21 45	96.89 41	91.03 60	94.72 41	91.45 33	82.87 102	93.10 52	94.61 45	96.24 51	97.08 15	98.63 25	98.16 47

EIA-MVS		92.72 64	92.96 63	92.44 82	93.86 100	97.76 62	93.13 132	88.65 116	89.78 112	86.68 79	86.69 69	87.57 76	93.74 61	96.07 54	95.32 62	98.58 26	97.53 75

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

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 38	97.55 22	96.68 21	97.32 17	96.65 26	98.55 28	98.26 43

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
casdiffmvs_mvg		91.94 75	91.25 91	92.75 72	93.41 109	97.19 89	95.48 60	89.77 75	89.86 109	86.41 83	81.02 126	82.23 111	92.93 75	95.44 66	95.61 57	98.51 29	97.40 80
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		89.36 139	91.49 86	86.88 168	92.10 154	97.60 69	92.16 150	85.89 152	84.21 176	75.20 169	82.58 106	87.13 78	77.40 234	95.90 58	95.63 56	98.51 29	97.36 81
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
casdiffmvs		91.72 83	91.16 93	92.38 84	93.16 123	97.15 92	93.95 101	89.49 94	91.58 78	86.03 92	80.75 128	80.95 130	93.16 70	95.25 68	95.22 66	98.50 32	97.23 88
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMMP		95.54 34	95.49 37	95.61 34	98.27 33	98.53 29	97.16 37	94.86 35	94.88 38	89.34 47	95.36 30	91.74 57	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
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 43	95.42 43	96.46 24	97.65 12	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
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 35	95.85 31	96.65 37	96.35 35	98.47 35	98.48 35

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.
XVS					95.68 66	98.66 17	94.96 68			88.03 59		96.06 35				98.46 37

X-MVStestdata					95.68 66	98.66 17	94.96 68			88.03 59		96.06 35				98.46 37

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 39	97.07 7	96.60 40	96.34 38	98.46 37	98.42 38

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
MVSMamba_PlusPlus		94.63 46	95.45 39	93.67 54	94.05 92	98.25 44	95.98 53	90.70 62	95.11 33	87.05 75	91.10 44	90.84 63	95.77 33	97.52 14	97.32 7	98.44 41	98.00 55

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 31	97.27 2	96.64 38	96.33 39	98.44 41	98.56 27

DeepC-MVS	92.10 3	95.22 37	94.77 45	95.75 32	97.77 41	98.54 28	97.63 32	95.96 20	95.07 35	88.85 52	85.35 79	91.85 56	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
CDPH-MVS		94.80 44	95.50 36	93.98 49	98.34 30	98.06 50	97.41 34	93.23 42	92.81 60	82.98 136	92.51 37	94.82 45	93.53 65	96.08 53	96.30 41	98.42 44	97.94 59

DELS-MVS		93.71 55	93.47 55	94.00 47	96.82 56	98.39 38	96.80 42	91.07 59	89.51 116	89.94 45	83.80 91	89.29 75	90.95 116	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
QAPM		94.13 52	94.33 52	93.90 50	97.82 40	98.37 39	96.47 45	90.89 61	92.73 64	85.63 106	85.35 79	93.87 48	94.17 52	95.71 61	95.90 53	98.40 46	98.42 38

MVS_111021_HR		94.84 42	95.91 33	93.60 55	97.35 47	98.46 35	95.08 66	91.19 57	94.18 46	85.97 93	95.38 29	92.56 54	93.61 64	96.61 39	96.25 42	98.40 46	97.92 61

SD-MVS		97.35 10	97.73 10	96.90 16	97.35 47	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
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 54	90.49 41	96.30 19	95.31 44	96.71 20	96.46 43	96.02 51	98.38 49	98.19 46

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 33	96.79 17	96.44 45	95.77 54	98.35 50	98.56 27

3Dnovator+	90.56 5	95.06 39	94.56 48	95.65 33	98.11 34	98.15 48	97.19 36	91.59 55	95.11 33	93.23 25	81.99 116	94.71 46	95.43 39	96.48 42	96.88 20	98.35 50	98.63 22

CANet		94.85 41	94.92 43	94.78 40	97.25 50	98.52 31	97.20 35	91.81 52	93.25 56	91.06 35	86.29 72	94.46 47	92.99 73	97.02 28	96.68 24	98.34 52	98.20 45

PVSNet_BlendedMVS		92.80 61	92.44 70	93.23 58	96.02 64	97.83 59	93.74 112	90.58 63	91.86 72	90.69 39	85.87 77	82.04 115	90.01 129	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 64	97.83 59	93.74 112	90.58 63	91.86 72	90.69 39	85.87 77	82.04 115	90.01 129	96.39 46	95.26 64	98.34 52	97.81 66

hybridcas		91.91 77	91.29 89	92.65 74	93.18 120	97.22 86	94.63 71	89.68 82	91.78 75	87.11 73	80.73 131	81.57 121	92.96 74	95.56 63	95.14 68	98.32 55	97.01 100

GBi-Net		90.21 124	90.11 115	90.32 125	88.66 192	93.65 169	94.25 85	85.78 154	90.03 101	85.56 108	77.38 151	86.13 83	89.38 139	93.97 110	94.16 95	98.31 56	95.47 167

test1		90.21 124	90.11 115	90.32 125	88.66 192	93.65 169	94.25 85	85.78 154	90.03 101	85.56 108	77.38 151	86.13 83	89.38 139	93.97 110	94.16 95	98.31 56	95.47 167

FMVSNet2		89.61 135	89.14 132	90.16 131	88.66 192	93.65 169	94.25 85	85.44 158	88.57 130	84.96 128	73.53 184	83.82 95	89.38 139	94.23 102	94.68 85	98.31 56	95.47 167

ACMMP_NAP		96.93 18	97.27 18	96.53 25	99.06 5	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 11	96.68 24	98.30 59	98.61 25

HPM-MVS++		97.22 13	97.40 14	97.01 13	99.08 3	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

TAPA-MVS	90.35 6	93.69 56	93.52 54	93.90 50	96.89 55	97.62 68	96.15 48	91.67 54	94.94 36	85.97 93	87.72 64	91.96 55	94.40 48	93.76 120	93.06 134	98.30 59	95.58 165
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tfpn200view9		89.55 136	87.86 151	91.53 110	93.90 98	97.26 78	94.31 82	89.74 78	85.87 160	81.15 144	76.46 161	70.38 199	91.76 104	94.92 75	93.51 111	98.28 62	96.61 126

sasdasda		93.08 58	93.09 58	93.07 65	94.24 84	97.86 55	95.45 61	87.86 133	94.00 49	87.47 68	88.32 60	82.37 108	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 84	97.86 55	95.45 61	87.86 133	94.00 49	87.47 68	88.32 60	82.37 108	95.13 41	93.96 113	96.41 32	98.27 63	98.73 16

thres600view7		89.28 142	87.47 161	91.39 114	94.12 88	97.25 81	93.94 104	89.74 78	85.62 165	80.63 150	75.24 175	69.33 209	91.66 106	94.92 75	93.23 124	98.27 63	96.72 122

thres200		89.49 137	87.72 153	91.55 109	93.95 95	97.25 81	94.34 80	89.74 78	85.66 163	81.18 143	76.12 167	70.19 205	91.80 102	94.92 75	93.51 111	98.27 63	96.40 137

OpenMVS	88.18 11	92.51 66	91.61 84	93.55 56	97.74 42	98.02 52	95.66 57	90.46 65	89.14 121	86.50 82	75.80 168	90.38 72	92.69 83	94.99 72	95.30 63	98.27 63	97.63 70

MSLP-MVS++		96.05 30	95.63 34	96.55 23	98.33 31	98.17 47	96.94 40	94.61 37	94.70 42	94.37 13	89.20 56	95.96 38	96.81 15	95.57 62	97.33 6	98.24 68	98.47 36

UA-Net		90.81 110	92.58 67	88.74 144	94.87 81	97.44 72	92.61 139	88.22 123	82.35 193	78.93 157	85.20 81	95.61 41	79.56 229	96.52 41	96.57 28	98.23 69	94.37 185

CLD-MVS		92.50 67	91.96 78	93.13 62	93.93 97	96.24 125	95.69 56	88.77 110	92.92 58	89.01 50	88.19 62	81.74 119	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
Vis-MVSNet (Re-imp)		90.54 119	92.76 65	87.94 155	93.73 104	96.94 105	92.17 149	87.91 128	88.77 127	76.12 167	83.68 92	90.80 64	79.49 230	96.34 48	96.35 35	98.21 71	96.46 134

MGCFI-Net		92.75 63	92.98 62	92.48 79	94.18 86	97.77 61	95.28 65	87.77 135	93.88 52	85.28 123	88.19 62	82.17 113	94.14 53	93.86 116	96.32 40	98.20 72	98.69 19

thres400		89.40 138	87.58 158	91.53 110	94.06 91	97.21 88	94.19 88	89.83 74	85.69 162	81.08 146	75.50 173	69.76 206	91.80 102	94.79 83	93.51 111	98.20 72	96.60 127

FMVSNet3		90.19 126	90.06 117	90.34 124	88.69 191	93.85 161	94.58 72	85.78 154	90.03 101	85.56 108	77.38 151	86.13 83	89.22 145	93.29 134	94.36 91	98.20 72	95.40 171

Casviewmamba		92.36 70	91.93 79	92.87 70	93.39 110	97.42 73	94.57 73	89.86 72	93.10 57	87.57 66	82.10 114	82.17 113	93.67 63	95.97 55	95.43 61	98.18 75	97.30 85

EPP-MVSNet		92.13 71	93.06 60	91.05 119	93.66 106	97.30 76	92.18 147	87.90 129	90.24 96	83.63 133	86.14 74	90.52 71	90.76 120	94.82 81	94.38 90	98.18 75	97.98 56

ET-MVSNet_ETH3D		89.93 128	90.84 103	88.87 142	79.60 251	96.19 126	94.43 76	86.56 146	90.63 85	80.75 149	90.71 48	77.78 164	93.73 62	91.36 169	93.45 116	98.15 77	95.77 160

FC-MVSNet-train		90.55 118	90.19 113	90.97 120	93.78 102	95.16 140	92.11 152	88.85 106	87.64 140	83.38 135	84.36 86	78.41 157	89.53 135	94.69 85	93.15 130	98.15 77	97.92 61

thres100view900		89.36 139	87.61 156	91.39 114	93.90 98	96.86 107	94.35 79	89.66 83	85.87 160	81.15 144	76.46 161	70.38 199	91.17 110	94.09 105	93.43 117	98.13 79	96.16 146

UniMVSNet_NR-MVSNet		86.80 159	85.86 178	87.89 157	88.17 198	94.07 157	90.15 179	88.51 118	84.20 177	73.45 179	72.38 194	70.30 204	88.95 149	90.25 189	92.21 150	98.12 80	97.62 72

MVSTER		91.73 82	91.61 84	91.86 97	93.18 120	94.56 144	94.37 78	87.90 129	90.16 100	88.69 55	89.23 55	81.28 124	88.92 151	95.75 60	93.95 102	98.12 80	96.37 138

LGP-MVS_train		91.83 79	92.04 77	91.58 108	95.46 72	96.18 127	95.97 54	89.85 73	90.45 91	77.76 159	91.92 41	80.07 144	92.34 94	94.27 99	93.47 115	98.11 82	97.90 64

viewmacassd2359aftdt		90.80 112	89.95 121	91.78 98	93.17 122	97.14 95	93.99 98	89.56 91	87.66 139	83.65 132	78.82 145	80.23 140	92.23 95	93.74 121	95.11 69	98.10 83	96.97 111

NR-MVSNet		85.46 179	84.54 189	86.52 174	88.33 197	93.78 163	90.45 172	87.87 131	84.40 171	71.61 191	70.59 200	62.09 244	82.79 213	91.75 162	91.75 162	98.10 83	97.44 78

viewmanbaseed2359cas		91.57 86	91.09 95	92.12 89	93.36 111	97.26 78	94.02 97	89.62 89	90.50 90	84.95 129	82.00 115	81.36 122	92.69 83	94.47 96	95.04 70	98.09 85	97.00 103

CP-MVSNet		83.11 218	82.15 215	84.23 202	87.20 215	92.70 196	86.42 231	83.53 181	77.83 227	67.67 222	66.89 222	60.53 252	82.47 214	89.23 210	90.65 184	98.08 86	97.20 92

viewdifsd2359ckpt09		91.65 85	90.91 102	92.51 77	93.35 112	97.36 74	93.95 101	89.64 86	89.83 110	86.67 80	82.25 112	80.77 134	93.37 68	94.71 84	94.48 88	98.07 87	96.99 105

IS_MVSNet		91.87 78	93.35 57	90.14 132	94.09 89	97.73 64	93.09 133	88.12 125	88.71 128	79.98 153	84.49 84	90.63 68	87.49 163	97.07 25	96.96 18	98.07 87	97.88 65

AdaColmap		95.02 40	93.71 53	96.54 24	98.51 28	97.76 62	96.69 43	95.94 22	93.72 53	93.50 19	89.01 57	90.53 69	96.49 23	94.51 93	93.76 106	98.07 87	96.69 123

TranMVSNet+NR-MVSNet		85.57 176	84.41 190	86.92 167	87.67 208	93.34 176	90.31 175	88.43 120	83.07 187	70.11 205	69.99 206	65.28 229	86.96 169	89.73 201	92.27 148	98.06 90	97.17 94

IB-MVS	85.10 14	87.98 149	87.97 150	87.99 154	94.55 82	96.86 107	84.52 239	88.21 124	86.48 158	88.54 56	74.41 180	77.74 165	74.10 247	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
E4		91.04 103	90.00 120	92.25 88	93.15 125	97.14 95	94.09 94	89.62 89	87.54 142	86.08 90	79.38 139	80.24 139	92.53 87	93.89 115	94.82 75	98.04 92	96.99 105

E6new		90.91 108	89.94 122	92.04 92	93.14 128	97.16 90	93.76 109	88.98 102	87.44 143	85.85 100	79.15 142	79.96 146	92.48 89	94.04 107	94.75 79	98.03 93	97.06 98

E6		90.91 108	89.94 122	92.04 92	93.14 128	97.16 90	93.76 109	88.98 102	87.44 143	85.85 100	79.15 142	79.96 146	92.48 89	94.04 107	94.75 79	98.03 93	97.06 98

E3new		91.52 87	90.67 106	92.51 77	93.24 115	97.23 83	94.16 90	89.65 84	89.19 119	87.26 71	81.25 123	81.00 128	92.71 81	94.26 100	94.75 79	98.03 93	96.99 105

E3		91.50 89	90.67 106	92.48 79	93.24 115	97.23 83	94.16 90	89.65 84	89.18 120	87.08 74	81.24 124	81.04 127	92.71 81	94.26 100	94.75 79	98.03 93	96.99 105

dmvs_re		87.31 155	86.10 171	88.74 144	89.84 178	94.28 153	92.66 138	89.41 95	82.61 190	74.69 170	74.69 178	69.47 207	87.78 158	92.38 149	93.23 124	98.03 93	96.02 153

PS-CasMVS		82.53 223	81.54 226	83.68 209	87.08 220	92.54 202	86.20 233	83.46 182	76.46 236	65.73 234	65.71 229	59.41 257	81.61 222	89.06 212	90.55 186	98.03 93	97.07 97

E5new		91.10 99	90.03 118	92.35 85	93.15 125	97.13 97	94.28 83	89.76 76	87.71 137	86.24 85	79.61 137	80.18 142	92.62 85	93.77 118	94.80 76	98.02 99	97.01 100

E5		91.10 99	90.03 118	92.35 85	93.15 125	97.13 97	94.28 83	89.76 76	87.71 137	86.24 85	79.61 137	80.18 142	92.62 85	93.77 118	94.80 76	98.02 99	97.01 100

PEN-MVS		82.49 224	81.58 225	83.56 211	86.93 221	92.05 215	86.71 229	83.84 175	76.94 233	64.68 238	67.24 217	60.11 253	81.17 224	87.78 219	90.70 183	98.02 99	96.21 145

viewcassd2359sk11		91.81 80	91.13 94	92.61 75	93.28 114	97.26 78	94.16 90	89.64 86	90.27 94	87.79 64	82.51 109	81.72 120	92.78 79	94.43 97	94.69 84	98.01 102	96.99 105

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

E2		92.03 72	91.47 87	92.69 73	93.29 113	97.27 77	94.14 93	89.63 88	91.02 81	88.25 58	83.68 92	82.18 112	92.84 78	94.51 93	94.62 86	98.00 104	97.00 103

OPM-MVS		91.08 101	89.34 128	93.11 64	96.18 63	96.13 128	96.39 46	92.39 46	82.97 188	81.74 139	82.55 108	80.20 141	93.97 58	94.62 87	93.23 124	98.00 104	95.73 161
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DPM-MVS		95.07 38	94.84 44	95.34 37	97.44 46	97.49 71	97.76 30	95.52 27	94.88 38	88.92 51	87.25 65	96.44 32	94.41 47	95.78 59	96.11 48	97.99 106	95.95 155

WR-MVS_H		82.86 221	82.66 212	83.10 217	87.44 211	93.33 177	85.71 237	83.20 185	77.36 230	68.20 219	66.37 223	65.23 230	76.05 241	89.35 205	90.13 194	97.99 106	96.89 115

PVSNet_Blended_VisFu		91.92 76	92.39 72	91.36 117	95.45 74	97.85 57	92.25 146	89.54 92	88.53 131	87.47 68	79.82 136	90.53 69	85.47 189	96.31 49	95.16 67	97.99 106	98.56 27

gg-mvs-nofinetune		81.83 228	83.58 195	79.80 240	91.57 160	96.54 114	93.79 108	68.80 262	62.71 264	43.01 271	55.28 254	85.06 91	83.65 207	96.13 52	94.86 74	97.98 109	94.46 182

casdiffseed414692147		89.97 127	88.31 142	91.90 95	93.03 130	96.77 109	93.66 116	88.85 106	86.52 155	85.39 120	74.87 176	75.76 176	92.53 87	93.35 132	94.26 92	97.97 110	96.67 124

viewdifsd2359ckpt13		91.32 92	90.71 105	92.04 92	93.21 119	97.23 83	93.57 121	89.54 92	89.94 105	85.21 124	81.31 122	80.56 136	92.78 79	94.56 90	94.57 87	97.95 111	96.80 116

MVS_Test		91.81 80	92.19 74	91.37 116	93.24 115	96.95 103	94.43 76	86.25 150	91.45 79	83.45 134	86.31 71	85.15 90	92.93 75	93.99 109	94.71 83	97.92 112	96.77 118

thisisatest0530		91.04 103	91.74 81	90.21 127	92.93 135	97.00 101	92.06 153	87.63 140	90.74 82	81.51 140	86.81 67	82.48 105	89.23 143	94.81 82	93.03 136	97.90 113	97.33 83

tttt0517		91.01 105	91.71 82	90.19 129	92.98 131	97.07 100	91.96 158	87.63 140	90.61 87	81.42 141	86.76 68	82.26 110	89.23 143	94.86 80	93.03 136	97.90 113	97.36 81

DTE-MVSNet		81.76 229	81.04 231	82.60 230	86.63 225	91.48 227	85.97 235	83.70 177	76.45 237	62.44 243	67.16 218	59.98 254	78.98 231	87.15 223	89.93 203	97.88 115	95.12 175

UniMVSNet (Re)		86.22 165	85.46 183	87.11 165	88.34 196	94.42 149	89.65 193	87.10 144	84.39 173	74.61 171	70.41 203	68.10 214	85.10 192	91.17 174	91.79 161	97.84 116	97.94 59

Effi-MVS+		89.79 131	89.83 124	89.74 134	92.98 131	96.45 120	93.48 125	84.24 169	87.62 141	76.45 165	81.76 117	77.56 167	93.48 66	94.61 88	93.59 109	97.82 117	97.22 90

TPM-MVS					98.33 31	97.85 57	97.06 39			89.97 44	93.26 34	97.16 27	93.12 72			97.79 118	95.95 155
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
MVS_111021_LR		94.84 42	95.57 35	94.00 47	97.11 52	97.72 66	94.88 70	91.16 58	95.24 30	88.74 53	96.03 24	91.52 61	94.33 51	95.96 56	95.01 71	97.79 118	97.49 77

GeoE		89.29 141	88.68 137	89.99 133	92.75 141	96.03 132	93.07 135	83.79 176	86.98 148	81.34 142	74.72 177	78.92 152	91.22 109	93.31 133	93.21 127	97.78 120	97.60 74

PCF-MVS	90.19 8	92.98 60	92.07 76	94.04 46	96.39 61	97.87 54	96.03 51	95.47 32	87.16 146	85.09 126	84.81 83	93.21 51	93.46 67	91.98 160	91.98 158	97.78 120	97.51 76
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DU-MVS		86.12 167	84.81 187	87.66 160	87.77 205	93.78 163	90.15 179	87.87 131	84.40 171	73.45 179	70.59 200	64.82 234	88.95 149	90.14 190	92.33 147	97.76 122	97.62 72

ACMP	89.13 9	92.03 72	91.70 83	92.41 83	94.92 79	96.44 121	93.95 101	89.96 71	91.81 74	85.48 112	90.97 46	79.12 151	92.42 92	93.28 135	92.55 145	97.76 122	97.74 69
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HQP-MVS		92.39 68	92.49 69	92.29 87	95.65 68	95.94 133	95.64 58	92.12 50	92.46 66	79.65 154	91.97 40	82.68 104	92.92 77	93.47 128	92.77 141	97.74 124	98.12 51

Baseline_NR-MVSNet		85.28 182	83.42 200	87.46 164	87.77 205	90.80 234	89.90 189	87.69 137	83.93 181	74.16 173	64.72 236	66.43 224	87.48 164	90.14 190	90.83 176	97.73 125	97.11 96

tfpnnormal		83.80 206	81.26 230	86.77 171	89.60 182	93.26 181	89.72 192	87.60 142	72.78 247	70.44 202	60.53 248	61.15 249	85.55 187	92.72 139	91.44 167	97.71 126	96.92 114

UGNet		91.52 87	93.41 56	89.32 138	94.13 87	97.15 92	91.83 159	89.01 101	90.62 86	85.86 99	86.83 66	91.73 58	77.40 234	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
FA-MVS(training)		90.79 113	91.33 88	90.17 130	93.76 103	97.22 86	92.74 137	77.79 237	90.60 88	88.03 59	78.80 146	87.41 77	91.00 115	95.40 67	93.43 117	97.70 128	96.46 134

CSCG		95.68 33	95.46 38	95.93 29	98.71 26	99.07 9	97.13 38	93.55 40	95.48 27	93.35 22	90.61 49	93.82 49	95.16 40	94.60 89	95.57 58	97.70 128	99.08 10

OMC-MVS		94.49 49	94.36 50	94.64 42	97.17 51	97.73 64	95.49 59	92.25 47	96.18 17	90.34 42	88.51 59	92.88 53	94.90 44	94.92 75	94.17 94	97.69 130	96.15 147

DI_MVS_pp		91.05 102	90.15 114	92.11 90	92.67 145	96.61 110	96.03 51	88.44 119	90.25 95	85.92 96	73.73 181	84.89 92	91.92 99	94.17 104	94.07 99	97.68 131	97.31 84

CNLPA		93.69 56	92.50 68	95.06 39	97.11 52	97.36 74	93.88 106	93.30 41	95.64 25	93.44 21	80.32 133	90.73 67	94.99 43	93.58 123	93.33 120	97.67 132	96.57 129

usedtu_dtu_shiyan1		86.08 170	86.20 170	85.93 177	81.88 248	93.87 160	90.68 168	86.54 147	86.84 149	72.93 184	71.70 195	75.39 177	85.90 182	91.74 163	91.33 170	97.66 133	92.56 213

Fast-Effi-MVS+		88.56 146	87.99 149	89.22 139	91.56 161	95.21 139	92.29 145	82.69 188	86.82 150	77.73 160	76.24 165	73.39 181	93.36 69	94.22 103	93.64 107	97.65 134	96.43 136

pm-mvs1		84.55 192	83.46 196	85.82 178	88.16 199	93.39 175	89.05 202	85.36 160	74.03 246	72.43 189	65.08 232	71.11 195	82.30 216	93.48 127	91.70 163	97.64 135	95.43 170

TransMVSNet (Re)		82.67 222	80.93 233	84.69 196	88.71 190	91.50 225	87.90 218	87.15 143	71.54 252	68.24 218	63.69 240	64.67 236	78.51 233	91.65 165	90.73 182	97.64 135	92.73 212

ACMM	88.76 10	91.70 84	90.43 109	93.19 60	95.56 69	95.14 141	93.35 130	91.48 56	92.26 67	87.12 72	84.02 88	79.34 149	93.99 56	94.07 106	92.68 142	97.62 137	95.50 166
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
diffmvs_AUTHOR		91.22 96	90.82 104	91.68 105	92.69 144	96.56 112	94.05 95	88.87 105	91.87 71	85.08 127	82.26 111	80.04 145	91.84 101	93.80 117	93.93 103	97.56 138	97.26 86

PLC	90.69 4	94.32 50	92.99 61	95.87 30	97.91 37	96.49 117	95.95 55	94.12 38	94.94 36	94.09 15	85.90 75	90.77 66	95.58 36	94.52 92	93.32 122	97.55 139	95.00 177
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
FMVSNet1		87.33 154	86.00 175	88.89 141	87.13 218	92.83 194	93.08 134	84.46 168	81.35 200	82.20 138	66.33 224	77.96 162	88.96 148	93.97 110	94.16 95	97.54 140	95.38 172

hybridnocas07		91.26 94	90.98 98	91.59 107	92.70 143	96.41 122	93.58 118	88.76 111	92.74 62	85.96 95	84.20 87	80.95 130	91.05 114	92.38 149	93.38 119	97.52 141	96.77 118

FC-MVSNet-test		86.15 166	89.10 133	82.71 228	89.83 179	93.18 183	87.88 219	84.69 163	86.54 154	62.18 245	82.39 110	83.31 98	74.18 246	92.52 147	91.86 160	97.50 142	93.88 192

diffmvs		91.37 91	91.09 95	91.70 103	92.71 142	96.47 118	94.03 96	88.78 109	92.74 62	85.43 115	83.63 94	80.37 137	91.76 104	93.39 130	93.78 105	97.50 142	97.23 88
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmamba		91.38 90	91.07 97	91.74 99	92.86 136	96.52 116	93.58 118	88.83 108	94.05 48	85.68 105	83.53 95	81.22 125	92.03 98	92.17 157	93.24 123	97.46 144	96.75 121

gm-plane-assit		77.65 245	78.50 243	76.66 247	87.96 201	85.43 258	64.70 267	74.50 245	64.15 262	51.26 265	61.32 246	58.17 258	84.11 205	95.16 70	93.83 104	97.45 145	91.41 221

MSDG		90.42 122	88.25 145	92.94 68	96.67 58	94.41 150	93.96 100	92.91 44	89.59 114	86.26 84	76.74 158	80.92 132	90.43 127	92.60 145	92.08 155	97.44 146	91.41 221

hybrid		91.19 97	90.98 98	91.43 112	92.63 147	96.34 124	93.39 127	88.61 117	92.81 60	85.87 98	83.98 90	81.17 126	90.76 120	92.64 144	93.14 131	97.33 147	96.76 120

ACMH+	85.75 12	87.19 157	86.02 174	88.56 146	93.42 108	94.41 150	89.91 187	87.66 139	83.45 185	72.25 190	76.42 163	71.99 192	90.78 119	89.86 199	90.94 175	97.32 148	95.11 176

baseline2		88.97 143	89.50 126	88.36 147	91.14 166	95.30 136	90.13 181	85.17 161	87.24 145	80.80 148	84.46 85	78.44 156	85.60 186	93.54 126	91.87 159	97.31 149	95.66 162

EG-PatchMatch MVS		81.70 230	81.31 229	82.15 233	88.75 189	93.81 162	87.14 225	78.89 231	71.57 250	64.12 241	61.20 247	68.46 212	76.73 239	91.48 166	90.77 179	97.28 150	91.90 218

onestephybrid01		91.32 92	90.98 98	91.72 102	92.81 138	96.53 115	93.37 129	88.92 104	92.09 68	86.86 78	83.06 98	81.79 118	91.09 112	92.66 141	93.52 110	97.26 151	97.22 90

CANet_DTU		90.74 116	92.93 64	88.19 150	94.36 83	96.61 110	94.34 80	84.66 164	90.66 84	68.75 214	90.41 50	86.89 80	89.78 131	95.46 65	94.87 73	97.25 152	95.62 163

UniMVSNet_ETH3D		84.57 191	81.40 228	88.28 149	89.34 185	94.38 152	90.33 173	86.50 148	74.74 245	77.52 161	59.90 249	62.04 245	88.78 154	88.82 215	92.65 143	97.22 153	97.24 87

MAR-MVS		92.71 65	92.63 66	92.79 71	97.70 43	97.15 92	93.75 111	87.98 127	90.71 83	85.76 103	86.28 73	86.38 82	94.35 50	94.95 73	95.49 59	97.22 153	97.44 78
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
anonymousdsp		84.51 193	85.85 179	82.95 224	86.30 229	93.51 172	85.77 236	80.38 224	78.25 225	63.42 242	73.51 185	72.20 190	84.64 199	93.21 136	92.16 152	97.19 155	98.14 49

ACMH	85.51 13	87.31 155	86.59 165	88.14 151	93.96 94	94.51 146	89.00 203	87.99 126	81.58 198	70.15 204	78.41 149	71.78 193	90.60 125	91.30 170	91.99 157	97.17 156	96.58 128
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs5		83.37 212	82.68 211	84.18 204	87.13 218	93.18 183	86.74 228	82.08 206	76.48 235	67.28 225	71.26 197	62.70 241	84.71 198	90.77 180	90.12 197	97.15 157	94.24 186

TSAR-MVS + COLMAP		92.39 68	92.31 73	92.47 81	95.35 76	96.46 119	96.13 49	92.04 51	95.33 29	80.11 152	94.95 32	77.35 168	94.05 54	94.49 95	93.08 132	97.15 157	94.53 181

LS3D		91.97 74	90.98 98	93.12 63	97.03 54	97.09 99	95.33 64	95.59 25	92.47 65	79.26 156	81.60 119	82.77 103	94.39 49	94.28 98	94.23 93	97.14 159	94.45 183

TSAR-MVS + ACMM		96.19 26	97.39 15	94.78 40	97.70 43	98.41 37	97.72 31	95.49 30	96.47 13	86.66 81	96.35 18	97.85 15	93.99 56	97.19 24	96.37 34	97.12 160	99.13 7

IterMVS-LS		88.60 144	88.45 140	88.78 143	92.02 155	92.44 206	92.00 155	83.57 180	86.52 155	78.90 158	78.61 148	81.34 123	89.12 146	90.68 184	93.18 128	97.10 161	96.35 139
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EPNet		93.92 53	94.40 49	93.36 57	97.89 38	96.55 113	96.08 50	92.14 49	91.65 76	89.16 49	94.07 33	90.17 73	87.78 158	95.24 69	94.97 72	97.09 162	98.15 48
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		87.87 150	86.42 167	89.57 135	95.56 69	96.99 102	92.37 142	84.15 171	86.64 152	77.17 163	57.65 251	83.97 94	91.08 113	92.09 158	92.44 146	97.09 162	95.16 174

viewmambaseed2359dif		90.70 117	89.81 125	91.73 101	92.66 146	96.10 129	93.97 99	88.69 114	89.92 106	86.12 88	80.79 127	80.73 135	91.92 99	91.13 176	92.81 140	97.06 164	97.20 92

WR-MVS		83.14 216	83.38 202	82.87 225	87.55 209	93.29 178	86.36 232	84.21 170	80.05 209	66.41 229	66.91 220	66.92 221	75.66 243	88.96 213	90.56 185	97.05 165	96.96 112

v144192		83.48 211	82.23 214	84.94 192	86.65 224	92.84 192	89.63 194	82.48 193	77.87 226	67.36 224	65.33 231	63.50 238	86.51 173	89.72 202	89.99 202	97.03 166	96.35 139

DCV-MVSNet		91.24 95	91.26 90	91.22 118	92.84 137	93.44 173	93.82 107	86.75 145	91.33 80	85.61 107	84.00 89	85.46 89	91.27 107	92.91 137	93.62 108	97.02 167	98.05 54

v1921920		83.30 214	82.09 217	84.70 195	86.59 227	92.67 198	89.82 190	82.23 199	78.32 223	65.76 233	64.64 237	62.35 242	86.78 172	90.34 188	90.02 200	97.02 167	96.31 142

FE-MVSNET2		76.99 248	76.02 251	78.12 245	71.26 264	89.46 246	81.92 247	80.87 222	71.48 253	61.96 246	47.82 262	54.83 261	75.73 242	89.29 208	88.91 215	97.00 169	90.36 233

dtuplus		90.51 120	89.50 126	91.69 104	92.61 148	96.04 131	93.70 115	88.72 112	88.47 132	86.07 91	79.85 135	80.92 132	92.04 97	91.20 171	92.89 138	96.99 170	97.14 95

v10		84.18 199	83.17 206	85.37 185	87.34 212	92.68 197	90.32 174	81.33 217	79.93 212	69.23 212	66.33 224	65.74 227	87.03 168	90.84 179	90.38 188	96.97 171	96.29 143

v2v482		84.51 193	83.05 207	86.20 176	87.25 214	93.28 179	90.22 177	85.40 159	79.94 211	69.78 207	67.74 216	65.15 231	87.57 161	89.12 211	90.55 186	96.97 171	95.60 164

Anonymous202405211			88.00 148		93.16 123	96.38 123	93.58 118	89.34 96	87.92 136		65.04 233	83.03 100	92.07 96	92.67 140	93.33 120	96.96 173	97.63 70

v1240		82.88 220	81.66 224	84.29 201	86.46 228	92.52 205	89.06 201	81.82 212	77.16 231	65.09 237	64.17 239	61.50 247	86.36 174	90.12 192	90.13 194	96.95 174	96.04 151

thisisatest0515		85.70 173	87.00 162	84.19 203	88.16 199	93.67 168	84.20 241	84.14 172	83.39 186	72.91 185	76.79 157	74.75 178	78.82 232	92.57 146	91.26 171	96.94 175	96.56 130

v1192		83.56 210	82.35 213	84.98 191	86.84 223	92.84 192	90.01 184	82.70 187	78.54 222	66.48 228	64.88 234	62.91 239	86.91 170	90.72 182	90.25 192	96.94 175	96.32 141

v8		84.45 197	83.30 204	85.80 179	87.53 210	92.95 189	90.31 175	82.46 195	80.46 204	71.43 193	66.99 219	67.16 219	86.14 179	89.26 209	90.22 193	96.94 175	96.06 150

Anonymous20231211		89.82 130	88.18 146	91.74 99	92.52 149	96.09 130	93.38 128	89.30 98	88.95 123	85.90 97	64.55 238	84.39 93	92.41 93	92.24 154	93.06 134	96.93 178	97.95 58

PatchMatch-RL		90.30 123	88.93 135	91.89 96	95.41 75	95.68 135	90.94 165	88.67 115	89.80 111	86.95 77	85.90 75	72.51 188	92.46 91	93.56 125	92.18 151	96.93 178	92.89 203

viewdifsd2359ckpt07		90.96 106	90.40 110	91.62 106	93.22 118	96.95 103	93.49 124	89.26 99	88.94 124	85.56 108	80.56 132	80.99 129	91.25 108	94.88 79	94.01 100	96.92 180	96.49 133

v1144		84.03 203	82.88 210	85.37 185	87.17 216	93.15 186	90.18 178	83.31 183	78.83 221	67.85 220	65.99 226	64.99 232	86.79 171	90.75 181	90.33 190	96.90 181	96.15 147

MIMVSNet		82.97 219	84.00 193	81.77 236	82.23 245	92.25 209	87.40 224	72.73 255	81.48 199	69.55 208	68.79 208	72.42 189	81.82 220	92.23 155	92.25 149	96.89 182	88.61 245

Fast-Effi-MVS+-dtu		86.25 163	87.70 154	84.56 198	90.37 177	93.70 166	90.54 171	78.14 234	83.50 183	65.37 236	81.59 120	75.83 175	86.09 181	91.70 164	91.70 163	96.88 183	95.84 159

test0.0.03 1		85.58 175	87.69 155	83.11 216	91.22 164	92.54 202	85.60 238	83.62 178	85.66 163	67.84 221	82.79 104	79.70 148	73.51 249	91.15 175	90.79 177	96.88 183	91.23 224

CDS-MVSNet		88.34 147	88.71 136	87.90 156	90.70 174	94.54 145	92.38 141	86.02 151	80.37 205	79.42 155	79.30 140	83.43 97	82.04 217	93.39 130	94.01 100	96.86 185	95.93 157
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
V42		84.48 195	83.36 203	85.79 180	87.14 217	93.28 179	90.03 182	83.98 174	80.30 206	71.20 196	66.90 221	67.17 218	85.55 187	89.35 205	90.27 191	96.82 186	96.27 144

CPTT-MVS		95.54 34	95.07 41	96.10 27	97.88 39	97.98 53	97.92 28	94.86 35	94.56 43	92.16 30	91.01 45	95.71 40	96.97 12	94.56 90	93.50 114	96.81 187	98.14 49

v7n		82.25 226	81.54 226	83.07 218	85.55 233	92.58 200	86.68 230	81.10 221	76.54 234	65.97 232	62.91 242	60.56 251	82.36 215	91.07 177	90.35 189	96.77 188	96.80 116

USDC		86.73 161	85.96 176	87.63 162	91.64 158	93.97 158	92.76 136	84.58 166	88.19 133	70.67 200	80.10 134	67.86 216	89.43 136	91.81 161	89.77 206	96.69 189	90.05 236

GA-MVS		85.08 186	85.65 180	84.42 200	89.77 180	94.25 154	89.26 197	84.62 165	81.19 202	62.25 244	75.72 169	68.44 213	84.14 204	93.57 124	91.68 165	96.49 190	94.71 180

COLMAP_ROB	84.39 15	87.61 152	86.03 173	89.46 136	95.54 71	94.48 147	91.77 160	90.14 70	87.16 146	75.50 168	73.41 187	76.86 171	87.33 165	90.05 195	89.76 207	96.48 191	90.46 231
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
baseline		91.19 97	91.89 80	90.38 123	92.76 139	95.04 142	93.55 122	84.54 167	92.92 58	85.71 104	86.68 70	86.96 79	89.28 142	92.00 159	92.62 144	96.46 192	96.99 105

FMVSNet5		84.47 196	84.72 188	84.18 204	83.30 240	88.43 250	88.09 217	79.42 229	84.25 175	74.14 174	73.15 190	78.74 153	83.65 207	91.19 173	91.19 172	96.46 192	86.07 253

MS-PatchMatch		87.63 151	87.61 156	87.65 161	93.95 95	94.09 156	92.60 140	81.52 215	86.64 152	76.41 166	73.46 186	85.94 86	85.01 197	92.23 155	90.00 201	96.43 194	90.93 228

RPMNet		84.82 190	85.90 177	83.56 211	91.10 167	92.10 211	88.73 207	71.11 258	84.75 167	68.79 213	73.56 183	77.62 166	85.33 190	90.08 194	89.43 210	96.32 195	93.77 194

CR-MVSNet		85.48 178	86.29 168	84.53 199	91.08 169	92.10 211	89.18 198	73.30 252	84.75 167	71.08 197	73.12 191	77.91 163	86.27 177	91.48 166	90.75 180	96.27 196	93.94 190

pmmvs4		86.00 171	84.28 191	88.00 153	87.80 203	92.01 216	89.94 186	84.91 162	86.79 151	80.98 147	73.41 187	66.34 225	88.12 156	89.31 207	88.90 216	96.24 197	93.20 201

PMMVS		89.88 129	91.19 92	88.35 148	89.73 181	91.97 218	90.62 170	81.92 210	90.57 89	80.58 151	92.16 38	86.85 81	91.17 110	92.31 151	91.35 169	96.11 198	93.11 202

Anonymous20231206		78.09 244	78.11 245	78.07 246	85.19 235	89.17 247	80.99 249	81.24 220	75.46 242	58.25 256	54.78 257	59.90 255	66.73 255	88.94 214	88.26 218	96.01 199	90.25 234

v148		83.61 208	82.10 216	85.37 185	87.34 212	92.94 190	87.48 221	85.72 157	78.92 220	73.87 175	65.71 229	64.69 235	81.78 221	87.82 218	89.35 211	96.01 199	95.26 173

MIMVSNet1		73.19 252	73.70 253	72.60 253	65.42 267	86.69 257	75.56 260	79.65 227	67.87 258	55.30 258	45.24 264	56.41 259	63.79 258	86.98 224	87.66 220	95.85 201	85.04 255

TinyColmap		84.04 202	82.01 219	86.42 175	90.87 170	91.84 219	88.89 205	84.07 173	82.11 195	69.89 206	71.08 198	60.81 250	89.04 147	90.52 186	89.19 212	95.76 202	88.50 246

test-mter		86.09 169	88.38 141	83.43 213	87.89 202	92.61 199	86.89 227	77.11 240	84.30 174	68.62 216	82.57 107	82.45 106	84.34 200	92.40 148	90.11 198	95.74 203	94.21 188

GG-mvs-BLEND		62.84 258	90.21 112	30.91 267	0.57 276	94.45 148	86.99 226	0.34 274	88.71 128	0.98 277	81.55 121	91.58 60	0.86 273	92.66 141	91.43 168	95.73 204	91.11 225

IterMVS-SCA-FT		85.44 180	86.71 163	83.97 207	90.59 175	90.84 232	89.73 191	78.34 233	84.07 180	66.40 230	77.27 156	78.66 154	83.06 209	91.20 171	90.10 199	95.72 205	94.78 178

SixPastTwentyTwo		83.12 217	83.44 198	82.74 226	87.71 207	93.11 187	82.30 246	82.33 196	79.24 213	64.33 239	78.77 147	62.75 240	84.11 205	88.11 217	87.89 219	95.70 206	94.21 188

LTVRE_ROB	81.71 16	82.44 225	81.84 221	83.13 215	89.01 187	92.99 188	88.90 204	82.32 197	66.26 260	54.02 262	74.68 179	59.62 256	88.87 152	90.71 183	92.02 156	95.68 207	96.62 125
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
test-LLR		86.88 158	88.28 143	85.24 188	91.22 164	92.07 213	87.41 222	83.62 178	84.58 169	69.33 210	83.00 99	82.79 101	84.24 201	92.26 152	89.81 204	95.64 208	93.44 196

TESTMET0.1,1		86.11 168	88.28 143	83.59 210	87.80 203	92.07 213	87.41 222	77.12 239	84.58 169	69.33 210	83.00 99	82.79 101	84.24 201	92.26 152	89.81 204	95.64 208	93.44 196

viewdifsd2359ckpt11		89.68 132	88.67 138	90.86 121	92.35 150	95.23 137	91.72 161	88.40 121	88.84 125	86.14 87	80.75 128	78.17 160	90.95 116	90.02 196	91.15 173	95.59 210	96.50 131

viewmsd2359difaftdt		89.67 134	88.66 139	90.85 122	92.35 150	95.23 137	91.72 161	88.40 121	88.80 126	86.12 88	80.75 128	78.20 159	90.94 118	90.02 196	91.15 173	95.59 210	96.50 131

DeepPCF-MVS	92.65 2	95.50 36	96.96 22	93.79 53	96.44 60	98.21 45	93.51 123	94.08 39	96.94 6	89.29 48	93.08 35	96.77 30	93.82 60	97.68 10	97.40 5	95.59 210	98.65 21

test20.03		76.41 249	78.49 244	73.98 250	85.64 232	87.50 253	75.89 259	80.71 223	70.84 254	51.07 266	68.06 212	61.40 248	54.99 262	88.28 216	87.20 222	95.58 213	86.15 252

TDRefinement		84.97 188	83.39 201	86.81 170	92.97 133	94.12 155	92.18 147	87.77 135	82.78 189	71.31 195	68.43 209	68.07 215	81.10 225	89.70 203	89.03 214	95.55 214	91.62 219

FE-MVSNET		73.24 251	74.06 252	72.28 254	64.92 268	85.32 259	76.06 258	79.75 226	67.71 259	50.14 267	49.61 260	54.40 262	67.26 254	85.97 230	87.33 221	95.53 215	88.10 250

PatchT		83.86 204	85.51 182	81.94 234	88.41 195	91.56 224	78.79 255	71.57 257	84.08 179	71.08 197	70.62 199	76.13 174	86.27 177	91.48 166	90.75 180	95.52 216	93.94 190

testgi		81.94 227	84.09 192	79.43 241	89.53 184	90.83 233	82.49 245	81.75 213	80.59 203	59.46 254	82.82 103	65.75 226	67.97 251	90.10 193	89.52 209	95.39 217	89.03 240

CHOSEN 1792x2688		88.57 145	87.82 152	89.44 137	95.46 72	96.89 106	93.74 112	85.87 153	89.63 113	77.42 162	61.38 245	83.31 98	88.80 153	93.44 129	93.16 129	95.37 218	96.95 113

pmmvs-eth3d		79.78 241	77.58 246	82.34 232	81.57 249	87.46 254	82.92 243	81.28 218	75.33 243	71.34 194	61.88 243	52.41 263	81.59 223	87.56 220	86.90 223	95.36 219	91.48 220

TAMVS		84.94 189	84.95 185	84.93 193	88.82 188	93.18 183	88.44 214	81.28 218	77.16 231	73.76 176	75.43 174	76.57 172	82.04 217	90.59 185	90.79 177	95.22 220	90.94 227

blended_shiyan8		81.65 231	80.43 236	83.06 219	74.09 254	89.98 236	88.48 209	81.99 208	79.15 214	73.52 178	67.98 214	70.34 203	85.09 193	82.39 243	80.39 248	95.19 221	92.81 208

blended_shiyan6		81.63 232	80.44 235	83.02 221	74.06 255	89.96 237	88.46 213	81.98 209	79.01 215	73.38 181	68.03 213	70.41 198	85.03 196	82.38 244	80.40 247	95.18 222	92.87 204

blend_shiyan4		84.25 198	82.04 218	86.82 169	82.33 243	89.89 238	90.94 165	81.51 216	81.22 201	85.41 116	75.60 170	73.18 184	85.67 183	81.60 252	79.96 256	95.08 223	92.85 206

PM-MVS		80.29 238	79.30 241	81.45 237	81.91 246	88.23 251	82.61 244	79.01 230	79.99 210	67.15 226	69.07 207	51.39 265	82.92 212	87.55 221	85.59 227	95.08 223	93.28 199

gbinet_0.2-2-1-0.02		81.58 233	80.59 234	82.73 227	73.97 260	89.77 243	88.25 215	82.49 192	77.59 228	73.56 177	67.87 215	71.56 194	83.06 209	82.77 241	80.22 249	95.04 225	94.38 184

IterMVS		85.25 183	86.49 166	83.80 208	90.42 176	90.77 235	90.02 183	78.04 235	84.10 178	66.27 231	77.28 155	78.41 157	83.01 211	90.88 178	89.72 208	95.04 225	94.24 186
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
wanda-best-256-512		81.56 234	80.31 237	83.02 221	74.05 256	89.88 239	88.48 209	82.09 202	78.96 217	73.38 181	68.19 210	70.37 201	85.08 194	82.18 245	80.05 252	95.03 227	92.52 214

FE-blended-shiyan7		81.56 234	80.31 237	83.02 221	74.05 256	89.88 239	88.48 209	82.09 202	78.97 216	73.38 181	68.19 210	70.35 202	85.08 194	82.18 245	80.05 252	95.03 227	92.52 214

usedtu_blend_shiyan5		83.61 208	81.81 223	85.71 181	74.05 256	89.88 239	91.99 156	82.09 202	78.96 217	85.41 116	75.60 170	73.18 184	85.67 183	82.18 245	80.05 252	95.03 227	92.85 206

FE-MVSNET3		83.34 213	81.82 222	85.12 190	74.05 256	89.88 239	88.48 209	82.09 202	78.96 217	85.41 116	75.60 170	73.18 184	85.67 183	82.18 245	80.05 252	95.03 227	92.87 204

EPNet_dtu		88.32 148	90.61 108	85.64 183	96.79 57	92.27 208	92.03 154	90.31 66	89.05 122	65.44 235	89.43 54	85.90 87	74.22 245	92.76 138	92.09 154	95.02 231	92.76 210
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+-dtu		87.51 153	88.13 147	86.77 171	91.10 167	94.90 143	90.91 167	82.67 189	83.47 184	71.55 192	81.11 125	77.04 169	89.41 138	92.65 143	91.68 165	95.00 232	96.09 149

pmmvs6		80.90 236	78.77 242	83.38 214	85.84 230	91.61 223	86.01 234	82.54 191	64.17 261	70.43 203	54.14 258	67.06 220	80.73 226	90.50 187	89.17 213	94.74 233	94.75 179

0.4-1-1-0.1		85.56 177	83.44 198	88.04 152	83.51 239	92.54 202	92.35 143	82.48 193	82.48 191	85.45 113	76.70 159	73.34 182	89.71 132	81.68 251	84.56 234	94.73 234	92.79 209

0.3-1-1-0.015		85.24 184	82.99 208	87.87 158	83.27 241	92.15 210	92.14 151	82.29 198	81.93 196	85.41 116	76.15 166	73.18 184	89.63 133	81.11 254	84.26 237	94.50 235	92.12 216

0.4-1-1-0.2		85.17 185	82.95 209	87.75 159	83.20 242	92.00 217	91.99 156	82.20 200	81.62 197	85.34 121	76.38 164	73.33 183	89.43 136	81.21 253	84.14 238	94.36 236	92.00 217

CVMVSNet		83.83 205	85.53 181	81.85 235	89.60 182	90.92 230	87.81 220	83.21 184	80.11 208	60.16 251	76.47 160	78.57 155	76.79 237	89.76 200	90.13 194	93.51 237	92.75 211

SCA		86.25 163	87.52 159	84.77 194	91.59 159	93.90 159	89.11 200	73.25 254	90.38 93	72.84 186	83.26 96	83.79 96	88.49 155	86.07 229	85.56 228	93.33 238	89.67 238

EPMVS		85.77 172	86.24 169	85.23 189	92.76 139	93.78 163	89.91 187	73.60 250	90.19 98	74.22 172	82.18 113	78.06 161	87.55 162	85.61 232	85.38 230	93.32 239	88.48 247

CostFormer		86.78 160	86.05 172	87.62 163	92.15 153	93.20 182	91.55 163	75.83 242	88.11 135	85.29 122	81.76 117	76.22 173	87.80 157	84.45 235	85.21 231	93.12 240	93.42 198

pmnet_mix02		80.14 239	80.21 240	80.06 238	86.61 226	89.66 245	80.40 251	82.20 200	82.29 194	61.35 248	71.52 196	66.67 223	76.75 238	82.55 242	80.18 250	93.05 241	88.62 244

new-patchmatchnet		72.32 253	71.09 256	73.74 251	81.17 250	84.86 260	72.21 264	77.48 238	68.32 257	54.89 260	55.10 255	49.31 268	63.68 259	79.30 258	76.46 259	93.03 242	84.32 258

dps		85.00 187	83.21 205	87.08 166	90.73 172	92.55 201	89.34 195	75.29 244	84.94 166	87.01 76	79.27 141	67.69 217	87.27 166	84.22 236	83.56 239	92.83 243	90.25 234

PatchmatchNet		85.70 173	86.65 164	84.60 197	91.79 156	93.40 174	89.27 196	73.62 249	90.19 98	72.63 188	82.74 105	81.93 117	87.64 160	84.99 233	84.29 236	92.64 244	89.00 241
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CHOSEN 280x420		90.77 114	92.14 75	89.17 140	93.86 100	92.81 195	93.16 131	80.22 225	90.21 97	84.67 130	89.89 53	91.38 62	90.57 126	94.94 74	92.11 153	92.52 245	93.65 195

RPSCF		89.68 132	89.24 130	90.20 128	92.97 133	92.93 191	92.30 144	87.69 137	90.44 92	85.12 125	91.68 42	85.84 88	90.69 122	87.34 222	86.07 225	92.46 246	90.37 232

dtuonlycased		77.37 247	76.66 250	78.20 244	81.91 246	88.92 248	79.41 252	78.66 232	75.26 244	59.93 252	63.10 241	69.37 208	77.10 236	75.02 261	76.14 260	92.22 247	88.78 243

MDTV_nov1_ep13_2view		80.43 237	80.94 232	79.84 239	84.82 236	90.87 231	84.23 240	73.80 248	80.28 207	64.33 239	70.05 205	68.77 211	79.67 227	84.83 234	83.50 240	92.17 248	88.25 249

MDTV_nov1_ep13		86.64 162	87.50 160	85.65 182	90.73 172	93.69 167	89.96 185	78.03 236	89.48 117	76.85 164	84.92 82	82.42 107	86.14 179	86.85 226	86.15 224	92.17 248	88.97 242

ADS-MVSNet		84.08 201	84.95 185	83.05 220	91.53 163	91.75 221	88.16 216	70.70 259	89.96 104	69.51 209	78.83 144	76.97 170	86.29 176	84.08 237	84.60 233	92.13 250	88.48 247

dtuonly		85.32 181	85.19 184	85.48 184	89.06 186	91.16 228	91.15 164	82.82 186	83.63 182	70.67 200	72.83 192	79.27 150	87.08 167	89.96 198	88.41 217	92.11 251	91.06 226

EU-MVSNet		78.43 242	80.25 239	76.30 248	83.81 238	87.27 256	80.99 249	79.52 228	76.01 238	54.12 261	70.44 202	64.87 233	67.40 253	86.23 228	85.54 229	91.95 252	91.41 221

CMPMVS	61.19 17	79.86 240	77.46 248	82.66 229	91.54 162	91.82 220	83.25 242	81.57 214	70.51 255	68.64 215	59.89 250	66.77 222	79.63 228	84.00 238	84.30 235	91.34 253	84.89 256
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
tpm		83.16 215	83.64 194	82.60 230	90.75 171	91.05 229	88.49 208	73.99 247	82.36 192	67.08 227	78.10 150	68.79 210	84.17 203	85.95 231	85.96 226	91.09 254	93.23 200

tpm cat1		84.13 200	81.99 220	86.63 173	91.74 157	91.50 225	90.68 168	75.69 243	86.12 159	85.44 114	72.39 193	70.72 196	85.16 191	80.89 255	81.56 243	91.07 255	90.71 229

MVS-HIRNet		78.16 243	77.57 247	78.83 242	85.83 231	87.76 252	76.67 257	70.22 260	75.82 241	67.39 223	55.61 253	70.52 197	81.96 219	86.67 227	85.06 232	90.93 256	81.58 259

usedtu_dtu_shiyan2		69.49 257	68.33 258	70.84 257	57.31 272	83.43 261	77.39 256	72.63 256	54.43 266	61.92 247	40.25 266	52.40 264	65.07 257	79.46 257	79.03 258	90.69 257	89.29 239

tpmrst		83.72 207	83.45 197	84.03 206	92.21 152	91.66 222	88.74 206	73.58 251	88.14 134	72.67 187	77.37 154	72.11 191	86.34 175	82.94 240	82.05 242	90.63 258	89.86 237

N_pmnet		77.55 246	76.68 249	78.56 243	85.43 234	87.30 255	78.84 254	81.88 211	78.30 224	60.61 249	61.46 244	62.15 243	74.03 248	82.04 249	80.69 246	90.59 259	84.81 257

MDA-MVSNet-bldmvs		73.81 250	72.56 255	75.28 249	72.52 263	88.87 249	74.95 261	82.67 189	71.57 250	55.02 259	65.96 227	42.84 272	76.11 240	70.61 264	81.47 244	90.38 260	86.59 251

pmmvs3		71.13 255	71.06 257	71.21 255	73.54 262	80.19 263	71.69 265	64.86 264	62.04 265	52.10 263	54.92 256	48.00 270	75.03 244	83.75 239	83.24 241	90.04 261	85.27 254

new_pmnet		72.29 254	73.25 254	71.16 256	75.35 253	81.38 262	73.72 263	69.27 261	75.97 239	49.84 268	56.27 252	56.12 260	69.08 250	81.73 250	80.86 245	89.72 262	80.44 261

ambc			67.96 259		73.69 261	79.79 264	73.82 262		71.61 249	59.80 253	46.00 263	20.79 274	66.15 256	86.92 225	80.11 251	89.13 263	90.50 230

FPMVS		69.87 256	67.10 260	73.10 252	84.09 237	78.35 265	79.40 253	76.41 241	71.92 248	57.71 257	54.06 259	50.04 266	56.72 260	71.19 263	68.70 263	84.25 264	75.43 263

PMMVS2		53.68 263	55.72 265	51.30 261	58.84 269	67.02 268	54.23 269	60.97 267	47.50 268	19.42 273	34.81 267	31.97 273	30.88 268	65.84 266	69.99 262	83.47 265	72.92 265

PMVS	56.77 18	61.27 259	58.64 263	64.35 258	75.66 252	54.60 270	53.62 270	74.23 246	53.69 267	58.37 255	44.27 265	49.38 267	44.16 266	69.51 265	65.35 265	80.07 266	73.66 264
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		58.52 261	56.17 264	61.27 259	67.14 266	58.06 269	52.16 271	68.40 263	69.00 256	45.02 270	22.79 268	20.57 275	55.11 261	76.27 259	79.33 257	79.80 267	67.16 266
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		58.10 262	64.61 262	50.51 262	28.26 274	41.71 273	61.28 268	32.07 270	75.92 240	52.04 264	47.94 261	61.83 246	51.80 263	79.83 256	63.95 267	77.60 268	81.05 260

DeepMVS_CX						71.82 267	68.37 266	48.05 269	77.38 229	46.88 269	65.77 228	47.03 271	67.48 252	64.27 267		76.89 269	76.72 262

WB-MVS		60.76 260	66.86 261	53.64 260	82.24 244	72.70 266	48.70 273	82.04 207	63.91 263	12.91 276	64.77 235	49.00 269	22.74 270	75.95 260	75.36 261	73.22 270	66.33 267

tmp_tt				50.24 263	68.55 265	46.86 272	48.90 272	18.28 271	86.51 157	68.32 217	70.19 204	65.33 228	26.69 269	74.37 262	66.80 264	70.72 271

E-PMN		40.00 264	35.74 267	44.98 264	57.69 271	39.15 275	28.05 274	62.70 265	35.52 270	17.78 274	20.90 269	14.36 277	44.47 265	35.89 269	47.86 268	59.15 272	56.47 269

EMVS		39.04 266	34.32 268	44.54 265	58.25 270	39.35 274	27.61 275	62.55 266	35.99 269	16.40 275	20.04 271	14.77 276	44.80 264	33.12 270	44.10 269	57.61 273	52.89 270

MVE	39.81 19	39.52 265	41.58 266	37.11 266	33.93 273	49.06 271	26.45 276	54.22 268	29.46 271	24.15 272	20.77 270	10.60 278	34.42 267	51.12 268	65.27 266	49.49 274	64.81 268
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		4.35 267	6.54 269	1.79 268	0.60 275	1.82 276	3.06 278	0.95 272	7.22 272	0.88 278	12.38 272	1.25 279	3.87 272	6.09 271	5.58 270	1.40 275	11.42 272

test123		3.48 268	5.31 270	1.34 269	0.20 277	1.52 277	2.17 279	0.58 273	6.13 273	0.31 279	9.85 273	0.31 280	3.90 271	2.65 272	5.28 271	0.87 276	11.46 271

uanet_test		0.00 269	0.00 271	0.00 270	0.00 278	0.00 278	0.00 280	0.00 275	0.00 274	0.00 280	0.00 274	0.00 281	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

sosnet-low-res		0.00 269	0.00 271	0.00 270	0.00 278	0.00 278	0.00 280	0.00 275	0.00 274	0.00 280	0.00 274	0.00 281	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

sosnet		0.00 269	0.00 271	0.00 270	0.00 278	0.00 278	0.00 280	0.00 275	0.00 274	0.00 280	0.00 274	0.00 281	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

RE-MVS-def										60.19 250

9.14												97.28 25

SR-MVS					98.93 20			96.00 19				97.75 17

our_test_3					86.93 221	89.77 243	81.61 248

MTAPA										95.36 5		97.46 23

MTMP										95.70 4		96.90 29

Patchmatch-RL test							18.47 277

mPP-MVS					98.76 25							95.49 42

NP-MVS									91.63 77

Patchmtry						92.39 207	89.18 198	73.30 252		71.08 197

High-resolution multi-view benchmark