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.

TDRefinement		97.59 2	98.32 3	96.73 4	95.90 67	98.10 2	99.08 2	93.92 32	98.24 4	96.44 13	98.12 20	97.86 53	96.06 2	99.24 1	98.93 1	99.00 2	97.77 5

LTVRE_ROB	95.06 1	97.73 1	98.39 2	96.95 1	96.33 52	96.94 36	98.30 22	94.90 15	98.61 2	97.73 3	97.97 25	98.57 24	95.74 4	99.24 1	98.70 4	98.72 8	98.70 2
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
WR-MVS		97.53 3	98.20 4	96.76 3	96.93 30	98.17 1	98.60 10	96.67 7	96.39 15	94.46 32	99.14 1	98.92 12	94.57 15	99.06 3	98.80 2	99.32 1	96.92 27

PS-CasMVS		97.22 5	97.84 8	96.50 5	97.08 26	97.92 6	98.17 32	97.02 2	94.71 27	95.32 21	98.52 13	98.97 10	92.91 43	99.04 4	98.47 6	98.49 21	97.24 14

SixPastTwentyTwo		97.36 4	97.73 11	96.92 2	97.36 14	96.15 57	98.29 23	94.43 24	96.50 13	96.96 7	98.74 6	98.74 19	96.04 3	99.03 5	97.74 18	98.44 25	97.22 15

PEN-MVS		97.16 6	97.87 7	96.33 12	97.20 22	97.97 4	98.25 27	96.86 6	95.09 25	94.93 26	98.66 8	99.16 6	92.27 53	98.98 6	98.39 8	98.49 21	96.83 31

DTE-MVSNet		97.16 6	97.75 10	96.47 6	97.40 13	97.95 5	98.20 30	96.89 5	95.30 20	95.15 24	98.66 8	98.80 17	92.77 47	98.97 7	98.27 10	98.44 25	96.28 42

CP-MVSNet		96.97 10	97.42 15	96.44 7	97.06 27	97.82 8	98.12 34	96.98 3	93.50 48	95.21 23	97.98 24	98.44 26	92.83 46	98.93 8	98.37 9	98.46 24	96.91 28

WR-MVS_H		97.06 9	97.78 9	96.23 14	96.74 38	98.04 3	98.25 27	97.32 1	94.40 34	93.71 52	98.55 11	98.89 13	92.97 40	98.91 9	98.45 7	98.38 30	97.19 16

PMVS	87.16 16	95.88 37	96.47 32	95.19 38	97.00 29	96.02 61	96.70 66	91.57 90	94.43 33	95.33 20	97.16 51	95.37 118	92.39 49	98.89 10	98.72 3	98.17 37	94.71 74
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_part1		96.91 11	98.63 1	94.90 47	94.62 104	97.75 11	98.33 21	93.88 34	98.92 1	93.11 67	99.06 2	99.66 1	90.49 93	98.84 11	98.61 5	98.97 3	97.60 8

COLMAP_ROB	93.74 2	97.09 8	97.98 5	96.05 18	95.97 64	97.78 9	98.56 11	91.72 88	97.53 8	96.01 15	98.14 19	98.76 18	95.28 5	98.76 12	98.23 11	98.77 6	96.67 36
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	89.90 10	96.27 19	97.52 14	94.81 48	95.19 87	97.18 33	97.97 37	92.52 59	96.72 10	90.50 123	97.31 45	99.11 7	94.10 20	98.67 13	97.90 15	98.56 16	95.79 52

UniMVSNet_ETH3D		96.15 24	97.71 12	94.33 56	97.31 18	96.71 41	95.06 110	96.91 4	97.86 6	90.42 124	98.55 11	99.60 2	88.01 120	98.51 14	97.81 17	98.26 31	94.95 68

LS3D		95.83 40	96.35 35	95.22 37	96.47 48	97.49 17	97.99 35	92.35 64	94.92 26	94.58 31	94.88 100	95.11 128	91.52 64	98.48 15	98.05 13	98.42 27	95.49 57

UA-Net		96.56 14	96.73 25	96.36 10	98.99 1	97.90 7	97.79 45	95.64 10	92.78 62	92.54 75	96.23 71	95.02 130	94.31 18	98.43 16	98.12 12	98.89 4	98.58 3

ACMH	90.17 8	96.61 13	97.69 13	95.35 31	95.29 83	96.94 36	98.43 15	92.05 76	98.04 5	95.38 19	98.07 22	99.25 5	93.23 34	98.35 17	97.16 43	97.72 53	96.00 48
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RPSCF		95.46 45	96.95 22	93.73 81	95.72 74	95.94 64	95.58 101	88.08 145	95.31 19	91.34 107	96.26 68	98.04 43	93.63 29	98.28 18	97.67 19	98.01 44	97.13 19

LGP-MVS_train		96.10 27	96.29 37	95.87 20	96.72 39	97.35 27	98.43 15	93.83 36	90.81 110	92.67 74	95.05 94	98.86 15	95.01 7	98.11 19	97.37 39	98.52 18	96.50 38

TSAR-MVS + MP.		95.99 31	96.57 29	95.31 33	96.87 31	96.50 48	98.71 5	91.58 89	93.25 53	92.71 71	96.86 57	96.57 90	93.92 21	98.09 20	97.91 14	98.08 40	96.81 32
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
zzz-MVS		96.18 22	96.01 47	96.38 8	98.30 2	96.18 56	98.51 13	94.48 23	94.56 29	94.81 30	91.73 140	96.96 76	94.30 19	98.09 20	97.83 16	97.91 48	96.73 33

ACMM	90.06 9	96.31 18	96.42 33	96.19 15	97.21 21	97.16 34	98.71 5	93.79 39	94.35 35	93.81 46	92.80 130	98.23 34	95.11 6	98.07 22	97.45 30	98.51 19	96.86 30
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	89.62 11	95.96 33	96.28 38	95.59 24	96.58 44	97.23 31	98.26 26	93.22 51	92.33 74	92.31 84	94.29 110	98.73 20	94.68 12	98.04 23	97.14 44	98.47 23	96.17 45
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Gipuma		95.86 38	96.17 42	95.50 28	95.92 66	94.59 108	94.77 118	92.50 60	97.82 7	97.90 2	95.56 83	97.88 51	94.71 11	98.02 24	94.81 97	97.23 75	94.48 82
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SteuartSystems-ACMMP		95.96 33	96.13 46	95.76 22	97.06 27	97.36 25	98.40 19	94.24 27	91.49 90	91.91 95	94.50 105	96.89 80	94.99 8	98.01 25	97.44 31	97.97 46	97.25 12
Skip Steuart: Steuart Systems R&D Blog.
CP-MVS		96.21 21	96.16 44	96.27 13	97.56 9	97.13 35	98.43 15	94.70 18	92.62 65	94.13 40	92.71 131	98.03 44	94.54 16	98.00 26	97.60 22	98.23 33	97.05 23

ACMMP		96.12 26	96.27 40	95.93 19	97.20 22	97.60 13	98.64 7	93.74 40	92.47 69	93.13 66	93.23 123	98.06 41	94.51 17	97.99 27	97.57 24	98.39 29	96.99 24
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
pmmvs6		94.58 63	97.30 16	91.40 124	94.84 96	94.61 107	93.40 149	92.43 63	98.51 3	85.61 164	98.73 7	99.53 3	84.40 145	97.88 28	97.03 45	97.72 53	94.79 71

ACMMP_NAP		95.86 38	96.18 41	95.47 29	97.11 25	97.26 29	98.37 20	93.48 47	93.49 49	93.99 44	95.61 80	94.11 140	92.49 48	97.87 29	97.44 31	97.40 65	97.52 9

X-MVS		95.33 50	95.13 67	95.57 26	97.35 15	97.48 19	98.43 15	94.28 25	92.30 75	93.28 59	86.89 187	96.82 83	91.87 58	97.85 30	97.59 23	98.19 35	96.95 26

ACMMPR		96.54 15	96.71 26	96.35 11	97.55 10	97.63 12	98.62 9	94.54 19	94.45 31	94.19 38	95.04 96	97.35 66	94.92 10	97.85 30	97.50 27	98.26 31	97.17 17

v7n		96.49 16	97.20 19	95.65 23	95.57 77	96.04 60	97.93 39	92.49 61	96.40 14	97.13 6	98.99 3	99.41 4	93.79 26	97.84 32	96.15 68	97.00 83	95.60 56

DVP-MVS++		96.63 12	97.92 6	95.12 41	97.77 7	97.52 16	98.29 23	93.83 36	96.72 10	92.52 76	98.10 21	99.07 9	90.87 80	97.83 33	97.44 31	97.44 62	98.76 1

FC-MVSNet-test		91.49 133	94.43 81	88.07 169	94.97 92	90.53 169	95.42 104	91.18 95	93.24 54	72.94 211	98.37 16	93.86 143	78.78 175	97.82 34	96.13 70	95.13 137	91.05 140

APDe-MVS		96.23 20	97.22 18	95.08 42	96.66 42	97.56 15	98.63 8	93.69 43	94.62 28	89.80 132	97.73 33	98.13 38	93.84 25	97.79 35	97.63 20	97.87 49	97.08 22

CS-MVS-test		94.55 65	94.02 92	95.16 39	94.82 97	95.30 84	97.14 52	93.35 49	83.18 174	94.01 43	93.00 127	96.93 78	93.13 36	97.78 36	97.42 35	98.50 20	94.55 79

anonymousdsp		95.45 47	96.70 27	93.99 69	88.43 202	92.05 151	99.18 1	85.42 179	94.29 36	96.10 14	98.63 10	99.08 8	96.11 1	97.77 37	97.41 36	98.70 9	97.69 6

MP-MVS		96.13 25	95.93 50	96.37 9	98.19 4	97.31 28	98.49 14	94.53 22	91.39 96	94.38 35	94.32 109	96.43 92	94.59 14	97.75 38	97.44 31	98.04 43	96.88 29
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SED-MVS		95.73 42	96.98 21	94.28 57	96.08 60	97.39 24	98.18 31	93.80 38	94.20 37	89.61 138	97.29 46	97.49 63	90.69 84	97.74 39	97.41 36	97.32 70	97.34 10

DVP-MVS		96.10 27	97.23 17	94.79 50	96.28 55	97.49 17	97.90 41	93.60 45	95.47 18	89.57 139	97.32 44	97.72 56	93.89 23	97.74 39	97.53 25	97.51 58	97.34 10
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
DROMVSNet		94.23 71	93.81 101	94.71 51	94.85 95	96.23 54	97.14 52	93.40 48	81.79 181	91.58 104	93.29 122	95.21 127	93.13 36	97.73 41	96.95 46	98.20 34	95.45 58

PGM-MVS		95.90 36	95.72 54	96.10 16	97.53 11	97.45 23	98.55 12	94.12 29	90.25 113	93.71 52	93.20 124	97.18 70	94.63 13	97.68 42	97.34 40	98.08 40	96.97 25

DCV-MVSNet		93.49 92	95.15 66	91.55 119	94.05 118	95.92 67	95.15 108	91.21 93	92.76 64	87.01 158	89.71 159	97.16 71	83.90 149	97.65 43	96.87 48	97.99 45	95.95 50

test2506		89.51 152	87.77 174	91.55 119	94.76 98	95.23 86	94.26 134	92.80 55	92.49 67	83.31 181	89.97 157	50.93 227	86.84 128	97.62 44	96.72 51	97.32 70	91.42 138

ECVR-MVS		93.05 105	94.25 90	91.65 117	94.76 98	95.23 86	94.26 134	92.80 55	92.49 67	83.90 177	96.75 60	89.99 166	86.84 128	97.62 44	96.72 51	97.32 70	90.92 143

EPP-MVSNet		93.63 87	93.95 94	93.26 92	95.15 88	96.54 46	96.18 87	91.97 78	91.74 83	85.76 162	94.95 98	84.27 188	91.60 63	97.61 46	97.38 38	98.87 5	95.18 65

test1111		93.25 97	94.43 81	91.88 113	95.09 90	94.97 97	94.58 123	92.81 54	93.60 47	83.79 179	97.17 50	89.25 173	87.59 122	97.54 47	96.57 55	97.42 64	91.89 130

SMA-MVS		95.99 31	96.48 31	95.41 30	97.43 12	97.36 25	97.55 50	93.70 42	94.05 42	93.79 47	97.02 55	94.53 135	92.28 52	97.53 48	97.19 41	97.73 52	97.67 7
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
DPE-MVS		96.00 30	96.80 23	95.06 43	95.87 70	97.47 22	98.25 27	93.73 41	92.38 71	91.57 105	97.55 39	97.97 46	92.98 39	97.49 49	97.61 21	97.96 47	97.16 18
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CS-MVS		94.36 68	94.66 76	94.01 66	95.22 85	96.08 59	97.91 40	89.00 133	86.12 154	89.62 137	93.09 126	97.68 59	93.78 27	97.44 50	97.50 27	98.55 17	94.74 72

IS_MVSNet		92.76 111	93.25 117	92.19 109	94.91 94	95.56 76	95.86 91	92.12 72	88.10 136	82.71 184	93.15 125	88.30 176	88.86 108	97.29 51	96.95 46	98.66 11	93.38 101

HFP-MVS		96.18 22	96.53 30	95.77 21	97.34 17	97.26 29	98.16 33	94.54 19	94.45 31	92.52 76	95.05 94	96.95 77	93.89 23	97.28 52	97.46 29	98.19 35	97.25 12

TranMVSNet+NR-MVSNet		95.72 43	96.42 33	94.91 46	96.21 56	96.77 40	96.90 63	94.99 13	92.62 65	91.92 94	98.51 14	98.63 22	90.82 81	97.27 53	96.83 49	98.63 13	94.31 83

Anonymous20231211		93.19 98	95.50 60	90.49 137	93.77 129	95.29 85	94.36 131	90.04 114	91.44 94	84.59 171	96.72 61	97.65 60	82.45 159	97.25 54	96.32 64	97.74 51	93.79 93

APD-MVS		95.38 48	95.68 55	95.03 44	97.30 19	96.90 38	97.83 44	93.92 32	89.40 125	90.35 125	95.41 87	97.69 58	92.97 40	97.24 55	97.17 42	97.83 50	95.96 49
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CSCG		96.07 29	97.15 20	94.81 48	96.06 62	97.58 14	96.52 75	90.98 99	96.51 12	93.60 54	97.13 52	98.55 25	93.01 38	97.17 56	95.36 83	98.68 10	97.78 4

OPM-MVS		95.96 33	96.59 28	95.23 36	96.67 41	96.52 47	97.86 43	93.28 50	95.27 23	93.46 56	96.26 68	98.85 16	92.89 44	97.09 57	96.37 63	97.22 76	95.78 53
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ETV-MVS		92.12 127	90.44 144	94.08 63	96.36 51	93.63 128	96.27 85	92.00 77	78.90 201	92.13 87	85.29 197	89.85 168	90.26 98	97.07 58	96.29 66	97.46 59	92.04 126

DU-MVS		95.51 44	95.68 55	95.33 32	96.45 49	96.44 50	96.61 72	95.32 11	89.97 118	93.78 48	97.46 41	98.07 40	91.19 71	97.03 59	96.53 56	98.61 14	94.22 84

Baseline_NR-MVSNet		94.85 58	95.35 63	94.26 58	96.45 49	93.86 123	96.70 66	94.54 19	90.07 116	90.17 129	98.77 5	97.89 48	90.64 87	97.03 59	96.16 67	97.04 82	93.67 96

PHI-MVS		94.65 62	94.84 72	94.44 52	94.95 93	96.55 43	96.46 78	91.10 97	88.96 128	96.00 16	94.55 104	95.32 121	90.67 85	96.97 61	96.69 54	97.44 62	94.84 69

CPTT-MVS		95.00 56	94.52 79	95.57 26	96.84 35	96.78 39	97.88 42	93.67 44	92.20 76	92.35 83	85.87 195	97.56 62	94.98 9	96.96 62	96.07 71	97.70 55	96.18 44

Vis-MVSNet		94.39 67	95.85 53	92.68 102	90.91 185	95.88 68	97.62 49	91.41 91	91.95 81	89.20 141	97.29 46	96.26 95	90.60 92	96.95 63	95.91 72	96.32 102	96.71 34
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet (Re)		95.46 45	95.86 52	95.00 45	96.09 58	96.60 42	96.68 70	94.99 13	90.36 112	92.13 87	97.64 37	98.13 38	91.38 65	96.90 64	96.74 50	98.73 7	94.63 77

FC-MVSNet-train		92.75 112	95.40 62	89.66 151	95.21 86	94.82 100	97.00 59	89.40 128	91.13 101	81.71 190	97.72 34	96.43 92	77.57 187	96.89 65	96.72 51	97.05 80	94.09 87

EG-PatchMatch MVS		94.81 59	95.53 58	93.97 70	95.89 69	94.62 106	95.55 103	88.18 143	92.77 63	94.88 28	97.04 54	98.61 23	93.31 31	96.89 65	95.19 87	95.99 115	93.56 99

MDA-MVSNet-bldmvs		89.75 147	91.67 134	87.50 174	74.25 221	90.88 163	94.68 121	85.89 173	91.64 85	91.03 113	95.86 74	94.35 138	89.10 107	96.87 67	86.37 185	90.04 182	85.72 177

NR-MVSNet		94.55 65	95.66 57	93.25 94	94.26 113	96.44 50	96.69 68	95.32 11	89.97 118	91.79 100	97.46 41	98.39 28	82.85 154	96.87 67	96.48 59	98.57 15	93.98 90

DeepC-MVS	92.47 4	96.44 17	96.75 24	96.08 17	97.57 8	97.19 32	97.96 38	94.28 25	95.29 21	94.92 27	98.31 18	96.92 79	93.69 28	96.81 69	96.50 58	98.06 42	96.27 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SD-MVS		95.77 41	96.17 42	95.30 34	96.72 39	96.19 55	97.01 58	93.04 52	94.03 43	92.71 71	96.45 66	96.78 87	93.91 22	96.79 70	95.89 74	98.42 27	97.09 21
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
TransMVSNet (Re)		93.55 91	96.32 36	90.32 140	94.38 110	94.05 116	93.30 152	89.53 124	97.15 9	85.12 167	98.83 4	97.89 48	82.21 160	96.75 71	96.14 69	97.35 68	93.46 100

UniMVSNet_NR-MVSNet		95.34 49	95.51 59	95.14 40	95.80 72	96.55 43	96.61 72	94.79 16	90.04 117	93.78 48	97.51 40	97.25 67	91.19 71	96.68 72	96.31 65	98.65 12	94.22 84

3Dnovator+	92.82 3	95.22 52	95.16 65	95.29 35	96.17 57	96.55 43	97.64 47	94.02 31	94.16 40	94.29 37	92.09 137	93.71 145	91.90 56	96.68 72	96.51 57	97.70 55	96.40 39

xxxxxxxxxxxxxcwj		95.03 55	96.14 45	93.73 81	95.30 80	95.93 65	94.80 116	91.76 85	93.11 57	91.93 92	95.83 76	98.96 11	91.11 74	96.62 74	96.44 60	97.46 59	96.13 46

SF-MVS		94.88 57	95.87 51	93.73 81	95.30 80	95.93 65	94.80 116	91.76 85	93.11 57	91.93 92	95.83 76	97.07 73	91.11 74	96.62 74	96.44 60	97.46 59	96.13 46

TSAR-MVS + ACMM		95.17 54	95.95 48	94.26 58	96.07 61	96.46 49	95.67 98	94.21 28	93.84 45	90.99 115	97.18 49	95.24 126	93.55 30	96.60 76	95.61 81	95.06 141	96.69 35

MSLP-MVS++		93.91 76	94.30 87	93.45 86	95.51 78	95.83 70	93.12 155	91.93 81	91.45 93	91.40 106	87.42 182	96.12 102	93.27 32	96.57 77	96.40 62	95.49 126	96.29 41

Anonymous202405211			94.63 77		94.51 109	94.96 98	93.94 139	91.35 92	90.82 108		95.60 82	95.85 108	81.74 167	96.47 78	95.84 76	97.39 66	92.85 110

pm-mvs1		93.27 96	95.94 49	90.16 141	94.13 116	93.66 126	92.61 165	89.91 117	95.73 17	84.28 176	98.51 14	98.29 31	82.80 155	96.44 79	95.76 77	97.25 74	93.21 104

FPMVS		90.81 135	91.60 136	89.88 146	92.52 158	88.18 179	93.31 151	83.62 190	91.59 87	88.45 150	88.96 167	89.73 170	86.96 125	96.42 80	95.69 79	94.43 153	90.65 145

TSAR-MVS + GP.		94.25 69	94.81 73	93.60 84	96.52 47	95.80 71	94.37 127	92.47 62	90.89 106	88.92 143	95.34 89	94.38 137	92.85 45	96.36 81	95.62 80	96.47 94	95.28 63

CNVR-MVS		94.24 70	94.47 80	93.96 71	96.56 45	95.67 74	96.43 79	91.95 79	92.08 79	91.28 109	90.51 148	95.35 119	91.20 70	96.34 82	95.50 82	96.34 100	95.88 51

OMC-MVS		94.74 60	95.46 61	93.91 73	94.62 104	96.26 53	96.64 71	89.36 130	94.20 37	94.15 39	94.02 115	97.73 55	91.34 67	96.15 83	95.04 91	97.37 67	94.80 70

MIMVSNet1		92.52 116	94.88 71	89.77 147	96.09 58	91.99 152	96.92 61	89.68 122	95.92 16	84.55 172	96.64 63	98.21 36	78.44 181	96.08 84	95.10 88	92.91 174	90.22 150

HPM-MVS++		95.21 53	94.89 70	95.59 24	97.79 6	95.39 82	97.68 46	94.05 30	91.91 82	94.35 36	93.38 121	95.07 129	92.94 42	96.01 85	95.88 75	96.73 86	96.61 37

MVS_111021_HR		93.82 83	94.26 89	93.31 89	95.01 91	93.97 121	95.73 95	89.75 120	92.06 80	92.49 78	94.01 116	96.05 104	90.61 91	95.95 86	94.78 100	96.28 103	93.04 107

NCCC		93.87 81	93.42 113	94.40 54	96.84 35	95.42 79	96.47 77	92.62 58	92.36 73	92.05 89	83.83 202	95.55 112	91.84 59	95.89 87	95.23 86	96.56 91	95.63 55

Vis-MVSNet (Re-imp)		90.68 136	92.18 129	88.92 158	94.63 103	92.75 140	92.91 159	91.20 94	89.21 127	75.01 208	93.96 117	89.07 174	82.72 157	95.88 88	95.30 84	97.08 79	89.08 158

AdaColmap		92.41 120	91.49 137	93.48 85	95.96 65	95.02 94	95.37 106	91.73 87	87.97 139	91.28 109	82.82 206	91.04 161	90.62 89	95.82 89	95.07 89	95.95 116	92.67 115

canonicalmvs		93.38 94	94.36 84	92.24 108	93.94 124	96.41 52	94.18 136	90.47 106	93.07 59	88.47 149	88.66 169	93.78 144	88.80 109	95.74 90	95.75 78	97.57 57	97.13 19

DeepC-MVS_fast	91.38 6	94.73 61	94.98 68	94.44 52	96.83 37	96.12 58	96.69 68	92.17 70	92.98 60	93.72 50	94.14 111	95.45 116	90.49 93	95.73 91	95.30 84	96.71 87	95.13 66
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EIA-MVS		91.95 130	90.36 146	93.81 78	96.54 46	94.65 104	95.38 105	90.40 107	78.01 206	93.72 50	86.70 190	91.95 156	89.93 101	95.67 92	94.72 104	96.89 85	90.79 144

CDPH-MVS		93.96 73	93.86 97	94.08 63	96.31 53	95.84 69	96.92 61	91.85 82	87.21 144	91.25 111	92.83 128	96.06 103	91.05 77	95.57 93	94.81 97	97.12 77	94.72 73

tfpnnormal		92.45 117	94.77 74	89.74 148	93.95 123	93.44 135	93.25 153	88.49 142	95.27 23	83.20 182	96.51 64	96.23 97	83.17 153	95.47 94	94.52 106	96.38 97	91.97 128

CNLPA		93.14 101	93.67 104	92.53 104	94.62 104	94.73 102	95.00 112	86.57 169	92.85 61	92.43 80	90.94 143	94.67 132	90.35 97	95.41 95	93.70 118	96.23 106	93.37 102

CLD-MVS		92.81 110	94.32 85	91.05 128	95.39 79	95.31 83	95.82 92	81.44 202	89.40 125	91.94 91	95.86 74	97.36 65	85.83 136	95.35 96	94.59 105	95.85 119	92.34 122
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GBi-Net		89.35 153	90.58 141	87.91 170	91.22 180	94.05 116	92.88 160	90.05 111	79.40 192	78.60 199	90.58 145	87.05 180	78.54 178	95.32 97	94.98 92	96.17 109	92.67 115

test1		89.35 153	90.58 141	87.91 170	91.22 180	94.05 116	92.88 160	90.05 111	79.40 192	78.60 199	90.58 145	87.05 180	78.54 178	95.32 97	94.98 92	96.17 109	92.67 115

FMVSNet1		92.86 109	95.26 64	90.06 143	92.40 162	95.16 88	94.37 127	92.22 66	93.18 56	82.16 189	96.76 59	97.48 64	81.85 164	95.32 97	94.98 92	97.34 69	93.93 91

TinyColmap		93.17 99	93.33 116	93.00 100	93.84 127	92.76 139	94.75 120	88.90 136	93.97 44	97.48 4	95.28 93	95.29 122	88.37 114	95.31 100	91.58 145	94.65 149	89.10 157

3Dnovator	91.81 5	93.36 95	94.27 88	92.29 107	92.99 148	95.03 92	95.76 93	87.79 148	93.82 46	92.38 82	92.19 136	93.37 149	88.14 118	95.26 101	94.85 96	96.69 88	95.40 59

UGNet		92.31 125	94.70 75	89.53 153	90.99 184	95.53 77	96.19 86	92.10 74	91.35 97	85.76 162	95.31 90	95.48 115	76.84 192	95.22 102	94.79 99	95.32 128	95.19 64
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
DeepPCF-MVS	90.68 7	94.56 64	94.92 69	94.15 61	94.11 117	95.71 73	97.03 57	90.65 103	93.39 52	94.08 41	95.29 91	94.15 139	93.21 35	95.22 102	94.92 95	95.82 121	95.75 54

MAR-MVS		91.86 131	91.14 140	92.71 101	94.29 111	94.24 114	94.91 113	91.82 83	81.66 183	93.32 58	84.51 200	93.42 148	86.86 127	95.16 104	94.44 107	95.05 142	94.53 81
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		93.15 100	93.65 105	92.56 103	93.89 126	92.28 146	95.09 109	86.92 164	91.26 100	92.99 69	94.46 107	96.22 98	90.64 87	95.11 105	93.45 122	95.85 119	92.74 114

GeoE		93.72 86	93.62 107	93.84 74	94.75 100	94.90 99	97.24 51	91.81 84	86.97 147	92.74 70	93.83 118	97.24 69	90.46 95	95.10 106	94.09 111	96.08 112	93.18 105

PLC	87.27 15	93.08 102	92.92 120	93.26 92	94.67 101	95.03 92	94.38 126	90.10 109	91.69 84	92.14 86	87.24 183	93.91 142	91.61 62	95.05 107	94.73 103	96.67 89	92.80 111
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSDG		92.09 129	92.84 121	91.22 127	92.55 157	92.97 136	93.42 148	85.43 178	90.24 114	91.83 97	94.70 101	94.59 133	88.48 113	94.91 108	93.31 125	95.59 125	89.15 156

Fast-Effi-MVS+		92.93 106	92.64 124	93.27 91	93.81 128	93.88 122	95.90 89	90.61 104	83.98 169	92.71 71	92.81 129	96.22 98	90.67 85	94.90 109	93.92 114	95.92 117	92.77 113

train_agg		93.89 78	93.46 112	94.40 54	97.35 15	93.78 125	97.63 48	92.19 69	88.12 135	90.52 122	93.57 120	95.78 109	92.31 51	94.78 110	93.46 121	96.36 98	94.70 76

ambc			94.61 78		98.09 5	95.14 89	91.71 178		94.18 39	96.46 12	96.26 68	96.30 94	91.26 69	94.70 111	92.00 139	93.45 164	93.67 96

PVSNet_Blended_VisFu		93.60 88	93.41 114	93.83 75	96.31 53	95.65 75	95.71 96	90.58 105	88.08 137	93.17 64	95.29 91	92.20 154	90.72 83	94.69 112	93.41 123	96.51 93	94.54 80

MVS_0304		93.92 75	93.81 101	94.05 65	96.06 62	96.00 62	96.43 79	92.76 57	85.99 156	94.43 34	94.04 114	97.08 72	88.12 119	94.65 113	94.20 110	96.47 94	94.71 74

thisisatest0515		93.79 84	94.41 83	93.06 99	94.14 114	92.50 144	95.56 102	88.55 140	91.61 86	92.45 79	96.84 58	95.71 110	90.62 89	94.58 114	95.07 89	97.05 80	94.58 78

QAPM		92.57 115	93.51 109	91.47 122	92.91 150	94.82 100	93.01 157	87.51 152	91.49 90	91.21 112	92.24 134	91.70 157	88.74 110	94.54 115	94.39 108	95.41 127	95.37 62

DELS-MVS		92.33 123	93.61 108	90.83 131	92.84 152	95.13 90	94.76 119	87.22 160	87.78 140	88.42 151	95.78 78	95.28 123	85.71 139	94.44 116	93.91 115	96.01 114	92.97 109
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
MSP-MVS		95.32 51	96.28 38	94.19 60	96.87 31	97.77 10	98.27 25	93.88 34	94.15 41	89.63 136	95.36 88	98.37 29	90.73 82	94.37 117	97.53 25	95.77 122	96.40 39
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
CANet		93.07 103	93.05 119	93.10 97	95.90 67	95.41 80	95.88 90	91.94 80	84.77 163	93.36 57	94.05 113	95.25 125	86.25 134	94.33 118	93.94 113	95.30 129	93.58 98

TAPA-MVS	88.94 13	93.78 85	94.31 86	93.18 96	94.14 114	95.99 63	95.74 94	86.98 162	93.43 51	93.88 45	90.16 155	96.88 81	91.05 77	94.33 118	93.95 112	97.28 73	95.40 59
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tfpn200view9		87.94 170	87.51 177	88.44 163	92.28 166	93.63 128	93.35 150	88.11 144	80.90 186	80.89 192	78.25 214	82.25 190	79.65 174	94.27 120	94.76 101	96.36 98	88.48 163

thres600view7		89.14 155	88.83 160	89.51 154	93.71 133	93.55 131	93.93 140	88.02 146	87.30 143	82.40 185	81.18 209	80.63 199	82.69 158	94.27 120	95.90 73	96.27 104	88.94 159

thres200		88.29 164	87.88 172	88.76 160	92.50 159	93.55 131	92.47 168	88.02 146	84.80 162	81.44 191	79.28 213	82.20 192	81.83 165	94.27 120	93.67 119	96.27 104	87.40 170

Effi-MVS+-dtu		92.32 124	91.66 135	93.09 98	95.13 89	94.73 102	94.57 124	92.14 71	81.74 182	90.33 126	88.13 175	95.91 106	89.24 105	94.23 123	93.65 120	97.12 77	93.23 103

EU-MVSNet		91.63 132	92.73 123	90.35 139	88.36 203	87.89 183	96.53 74	81.51 201	92.45 70	91.82 98	96.44 67	97.05 74	93.26 33	94.10 124	88.94 174	90.61 181	92.24 123

OpenMVS	89.22 12	91.09 134	91.42 138	90.71 133	92.79 154	93.61 130	92.74 164	85.47 177	86.10 155	90.73 116	85.71 196	93.07 152	86.69 130	94.07 125	93.34 124	95.86 118	94.02 89

MCST-MVS		93.60 88	93.40 115	93.83 75	95.30 80	95.40 81	96.49 76	90.87 100	90.08 115	91.72 101	90.28 153	95.99 105	91.69 61	93.94 126	92.99 126	96.93 84	95.13 66

Effi-MVS+		92.93 106	92.16 131	93.83 75	94.29 111	93.53 133	95.04 111	92.98 53	85.27 160	94.46 32	90.24 154	95.34 120	89.99 100	93.72 127	94.23 109	96.22 107	92.79 112

tttt0517		89.64 148	88.05 169	91.49 121	93.52 134	91.65 155	93.67 142	87.53 150	82.77 177	89.39 140	90.37 152	70.05 213	88.21 116	93.71 128	93.79 116	96.63 90	94.04 88

PM-MVS		92.65 114	93.20 118	92.00 111	92.11 170	90.16 172	95.99 88	84.81 184	91.31 98	92.41 81	95.87 73	96.64 89	92.35 50	93.65 129	92.91 127	94.34 155	91.85 131

IB-MVS	86.01 17	88.24 165	87.63 175	88.94 157	92.03 171	91.77 153	92.40 170	85.58 176	78.24 203	84.85 169	71.99 217	93.45 147	83.96 148	93.48 130	92.33 132	94.84 146	92.15 124
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
thisisatest0530		89.54 151	87.99 171	91.35 125	93.17 142	91.31 159	93.45 147	87.53 150	82.96 175	89.17 142	90.45 149	70.32 212	88.21 116	93.37 131	93.79 116	96.54 92	93.71 95

TSAR-MVS + COLMAP		93.06 104	93.65 105	92.36 105	94.62 104	94.28 113	95.36 107	89.46 127	92.18 77	91.64 102	95.55 84	95.27 124	88.60 112	93.24 132	92.50 131	94.46 152	92.55 120

PatchMatch-RL		89.59 149	88.80 162	90.51 136	92.20 168	88.00 182	91.72 177	86.64 166	84.75 164	88.25 152	87.10 185	90.66 164	89.85 103	93.23 133	92.28 133	94.41 154	85.60 178

thres400		88.54 160	88.15 168	88.98 156	93.17 142	92.84 138	93.56 145	86.93 163	86.45 151	82.37 186	79.96 211	81.46 196	81.83 165	93.21 134	94.76 101	96.04 113	88.39 164

casdiffmvs		92.42 119	93.99 93	90.60 135	93.25 140	93.82 124	94.28 133	88.73 138	91.53 88	84.53 174	97.74 32	98.64 21	86.60 131	93.21 134	91.20 150	96.21 108	91.76 136

CDS-MVSNet		88.41 161	89.79 151	86.79 179	94.55 108	90.82 164	92.50 167	89.85 118	83.26 173	80.52 194	91.05 141	89.93 167	69.11 207	93.17 136	92.71 129	94.21 157	87.63 168
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test20.03		88.20 167	91.26 139	84.63 191	96.64 43	89.39 174	90.73 186	89.97 116	91.07 103	72.02 213	94.98 97	95.45 116	69.35 206	92.70 137	91.19 151	89.06 186	84.02 180

V42		92.67 113	93.50 110	91.71 116	91.41 176	92.96 137	95.71 96	85.00 180	89.67 123	93.22 62	97.67 36	98.01 45	91.02 79	92.65 138	92.12 136	93.86 160	91.42 138

PVSNet_BlendedMVS		90.09 144	90.12 148	90.05 144	92.40 162	92.74 141	91.74 175	85.89 173	80.54 188	90.30 127	88.54 170	95.51 113	84.69 143	92.64 139	90.25 159	95.28 130	90.61 146

PVSNet_Blended		90.09 144	90.12 148	90.05 144	92.40 162	92.74 141	91.74 175	85.89 173	80.54 188	90.30 127	88.54 170	95.51 113	84.69 143	92.64 139	90.25 159	95.28 130	90.61 146

CMPMVS	66.55 18	85.55 181	87.46 178	83.32 194	84.99 211	81.97 203	79.19 218	75.93 208	79.32 195	88.82 145	85.09 198	91.07 160	82.12 161	92.56 141	89.63 165	88.84 187	92.56 119
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v10		93.96 73	94.12 91	93.77 80	93.37 137	95.45 78	96.83 65	91.13 96	89.70 122	95.02 25	97.88 29	98.23 34	91.27 68	92.39 142	92.18 135	94.99 143	93.00 108

v8		93.60 88	93.82 99	93.34 87	93.13 144	95.06 91	96.39 81	90.75 101	89.90 120	94.03 42	97.70 35	98.21 36	91.08 76	92.36 143	91.47 147	94.63 150	92.07 125

EPNet		90.17 143	89.07 158	91.45 123	97.25 20	90.62 168	94.84 114	93.54 46	80.96 185	91.85 96	86.98 186	85.88 184	77.79 184	92.30 144	92.58 130	93.41 165	94.20 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HQP-MVS		92.87 108	92.49 125	93.31 89	95.75 73	95.01 95	95.64 99	91.06 98	88.54 132	91.62 103	88.16 174	96.25 96	89.47 104	92.26 145	91.81 140	96.34 100	95.40 59

v144192		93.89 78	93.85 98	93.94 72	93.50 135	94.33 110	97.12 54	89.49 125	90.89 106	96.49 11	97.78 31	98.27 32	91.89 57	92.17 146	91.70 143	95.19 135	91.78 134

v1192		93.98 72	93.94 95	94.01 66	93.91 125	94.63 105	97.00 59	89.75 120	91.01 104	96.50 10	97.93 26	98.26 33	91.74 60	92.06 147	92.05 137	95.18 136	91.66 137

v148		92.38 121	92.78 122	91.91 112	92.86 151	92.13 149	94.84 114	87.03 161	91.47 92	93.07 68	96.92 56	98.89 13	90.10 99	92.05 148	89.69 163	93.56 163	88.27 166

USDC		92.17 126	92.17 130	92.18 110	92.93 149	92.22 147	93.66 143	87.41 155	93.49 49	97.99 1	94.10 112	96.68 88	86.46 132	92.04 149	89.18 169	94.61 151	87.47 169

v1144		93.83 82	93.87 96	93.78 79	93.72 132	94.57 109	96.85 64	89.98 115	91.31 98	95.90 17	97.89 28	98.40 27	91.13 73	92.01 150	92.01 138	95.10 139	90.94 142

v1921920		93.90 77	93.82 99	94.00 68	93.74 131	94.31 111	97.12 54	89.33 131	91.13 101	96.77 9	97.90 27	98.06 41	91.95 55	91.93 151	91.54 146	95.10 139	91.85 131

testgi		86.49 178	90.31 147	82.03 197	95.63 76	88.18 179	93.47 146	84.89 182	93.23 55	69.54 217	87.16 184	97.96 47	60.66 214	91.90 152	89.90 161	87.99 189	83.84 181

baseline1		86.96 175	87.58 176	86.24 182	93.07 146	90.44 170	89.24 197	86.85 165	85.14 161	77.26 205	90.45 149	76.09 204	75.79 197	91.80 153	91.81 140	95.20 134	87.35 171

ET-MVSNet_ETH3D		88.06 169	85.75 186	90.74 132	92.82 153	90.68 165	93.77 141	88.59 139	81.22 184	89.78 133	89.15 166	66.79 220	84.29 146	91.72 154	91.34 149	95.22 133	89.36 155

v2v482		93.42 93	93.49 111	93.32 88	93.44 136	94.05 116	96.36 84	89.76 119	91.41 95	95.24 22	97.63 38	98.34 30	90.44 96	91.65 155	91.76 142	94.69 147	89.62 153

FMVSNet2		90.28 140	92.04 132	88.23 167	91.22 180	94.05 116	92.88 160	90.69 102	86.53 150	79.89 197	94.38 108	92.73 153	78.54 178	91.64 156	92.26 134	96.17 109	92.67 115

v1240		93.89 78	93.72 103	94.09 62	93.98 122	94.31 111	97.12 54	89.37 129	90.74 111	96.92 8	98.05 23	97.89 48	92.15 54	91.53 157	91.60 144	94.99 143	91.93 129

CANet_DTU		88.95 157	89.51 155	88.29 166	93.12 145	91.22 161	93.61 144	83.47 193	80.07 191	90.71 120	89.19 165	93.68 146	76.27 196	91.44 158	91.17 152	92.59 176	89.83 152

PCF-MVS	87.46 14	92.44 118	91.80 133	93.19 95	94.66 102	95.80 71	96.37 82	90.19 108	87.57 141	92.23 85	89.26 164	93.97 141	89.24 105	91.32 159	90.82 155	96.46 96	93.86 92
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CVMVSNet		88.97 156	89.73 152	88.10 168	87.33 209	85.22 192	94.68 121	78.68 203	88.94 129	86.98 159	95.55 84	85.71 185	89.87 102	91.19 160	89.69 163	91.05 179	91.78 134

gg-mvs-nofinetune		88.32 162	88.81 161	87.75 172	93.07 146	89.37 175	89.06 198	95.94 8	95.29 21	87.15 156	97.38 43	76.38 202	68.05 210	91.04 161	89.10 171	93.24 168	83.10 186

Fast-Effi-MVS+-dtu		89.57 150	88.42 166	90.92 130	93.35 138	91.57 156	93.01 157	95.71 9	78.94 200	87.65 154	84.68 199	93.14 151	82.00 162	90.84 162	91.01 153	93.78 162	88.77 162

MVSTER		84.79 185	83.79 189	85.96 184	89.14 197	89.80 173	89.39 195	82.99 195	74.16 215	82.78 183	85.97 194	66.81 219	76.84 192	90.77 163	88.83 175	94.66 148	90.19 151

DPM-MVS		90.67 138	89.86 150	91.63 118	95.29 83	94.16 115	94.52 125	89.63 123	89.59 124	89.67 135	81.95 208	88.64 175	85.75 138	90.46 164	90.43 157	94.91 145	93.77 94

new-patchmatchnet		84.45 188	88.75 163	79.43 203	93.28 139	81.87 204	81.68 215	83.48 192	94.47 30	71.53 214	98.33 17	97.88 51	58.61 217	90.35 165	77.33 205	87.99 189	81.05 192

pmmvs-eth3d		92.34 122	92.33 126	92.34 106	92.67 155	90.67 166	96.37 82	89.06 132	90.98 105	93.60 54	97.13 52	97.02 75	88.29 115	90.20 166	91.42 148	94.07 158	88.89 161

thres100view900		86.46 179	86.00 185	86.99 177	92.28 166	91.03 162	91.09 182	84.49 186	80.90 186	80.89 192	78.25 214	82.25 190	77.57 187	90.17 167	92.84 128	95.63 123	86.57 175

FMVSNet5		79.08 206	78.83 204	79.38 205	87.52 208	86.78 186	87.64 204	78.15 205	69.54 220	70.64 215	65.97 220	65.44 222	63.87 213	90.17 167	90.46 156	88.48 188	83.45 183

E-PMN		77.81 210	77.88 211	77.73 212	88.26 204	70.48 219	80.19 217	71.20 212	86.66 149	72.89 212	88.09 176	81.74 195	78.75 176	90.02 169	68.30 217	75.10 217	59.85 219

diffmvs		90.44 139	92.23 128	88.35 165	91.36 178	91.38 158	92.45 169	84.84 183	89.88 121	85.09 168	96.69 62	97.71 57	83.33 152	90.01 170	88.96 173	93.03 172	91.00 141

DI_MVS_plusplus_trai		90.68 136	90.40 145	91.00 129	92.43 161	92.61 143	94.17 137	88.98 134	88.32 134	88.76 147	93.67 119	87.58 178	86.44 133	89.74 171	90.33 158	95.24 132	90.56 148

Anonymous20231206		87.45 173	89.66 154	84.87 188	94.00 119	87.73 185	91.36 181	86.41 171	88.89 130	75.03 207	92.59 132	96.82 83	72.48 204	89.72 172	88.06 176	89.93 183	83.81 182

IterMVS-LS		92.10 128	92.33 126	91.82 115	93.18 141	93.66 126	92.80 163	92.27 65	90.82 108	90.59 121	97.19 48	90.97 162	87.76 121	89.60 173	90.94 154	94.34 155	93.16 106
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EMVS		77.65 211	77.49 213	77.83 210	87.75 206	71.02 218	81.13 216	70.54 213	86.38 152	74.52 209	89.38 163	80.19 200	78.22 183	89.48 174	67.13 218	74.83 219	58.84 220

GA-MVS		88.76 158	88.04 170	89.59 152	92.32 165	91.46 157	92.28 171	86.62 167	83.82 171	89.84 131	92.51 133	81.94 193	83.53 151	89.41 175	89.27 168	92.95 173	87.90 167

MS-PatchMatch		87.72 172	88.62 165	86.66 180	90.81 187	88.18 179	90.92 183	82.25 196	85.86 157	80.40 195	90.14 156	89.29 172	84.93 140	89.39 176	89.12 170	90.67 180	88.34 165

EPNet_dtu		87.40 174	86.27 183	88.72 161	95.68 75	83.37 198	92.09 173	90.08 110	78.11 205	91.29 108	86.33 191	89.74 169	75.39 199	89.07 177	87.89 177	87.81 191	89.38 154
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IterMVS-SCA-FT		90.24 141	89.37 156	91.26 126	92.50 159	92.11 150	91.69 179	87.48 153	87.05 146	91.82 98	95.76 79	87.25 179	91.36 66	89.02 178	85.53 189	92.68 175	88.90 160

TAMVS		82.96 191	86.15 184	79.24 206	90.57 188	83.12 201	87.29 205	75.12 210	84.06 166	65.81 218	92.22 135	88.27 177	69.11 207	88.72 179	87.26 181	87.56 195	79.38 200

PMMVS2		69.86 215	82.14 195	55.52 216	75.19 220	63.08 222	75.52 221	60.97 216	88.50 133	25.11 226	91.77 138	96.44 91	25.43 220	88.70 180	79.34 199	70.93 220	67.17 217

MVS_Test		90.19 142	90.58 141	89.74 148	92.12 169	91.74 154	92.51 166	88.54 141	82.80 176	87.50 155	94.62 102	95.02 130	83.97 147	88.69 181	89.32 167	93.79 161	91.85 131

CHOSEN 280x420		79.24 204	78.26 208	80.38 201	79.60 217	68.80 221	89.32 196	75.38 209	77.25 207	78.02 204	75.57 216	76.17 203	81.19 168	88.61 182	81.39 196	78.79 213	80.03 197

test0.0.03 1		81.51 198	83.30 192	79.42 204	93.99 120	86.50 188	85.93 213	87.32 157	78.16 204	61.62 219	80.78 210	81.78 194	59.87 215	88.40 183	87.27 180	87.78 193	80.19 195

MIMVSNet		84.76 186	86.75 179	82.44 196	91.71 174	85.95 189	89.74 193	89.49 125	85.28 159	69.69 216	87.93 177	90.88 163	64.85 212	88.26 184	87.74 178	89.18 185	81.24 190

baseline2		84.95 183	82.68 193	87.59 173	92.64 156	88.41 178	90.09 188	84.25 187	75.88 209	85.23 166	82.49 207	71.15 210	80.14 171	88.21 185	87.21 182	93.21 171	85.39 179

FMVSNet3		87.90 171	88.63 164	87.04 176	89.78 194	93.46 134	91.62 180	90.05 111	79.40 192	78.60 199	90.58 145	87.05 180	77.07 191	88.03 186	89.86 162	95.12 138	92.04 126

gm-plane-assit		86.15 180	82.51 194	90.40 138	95.81 71	92.29 145	97.99 35	84.66 185	92.15 78	93.15 65	97.84 30	44.65 228	78.60 177	88.02 187	85.95 186	92.20 177	76.69 207

pmmvs3		81.69 196	83.83 188	79.19 207	78.33 218	78.57 209	89.53 194	58.71 218	78.88 202	84.34 175	88.36 172	91.96 155	77.69 186	87.48 188	82.42 194	86.54 198	79.18 201

IterMVS		88.32 162	88.25 167	88.41 164	90.83 186	91.24 160	93.07 156	81.69 199	86.77 148	88.55 148	95.61 80	86.91 183	87.01 124	87.38 189	83.77 191	89.29 184	86.06 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
pmmvs5		88.63 159	89.70 153	87.39 175	89.24 196	90.64 167	91.87 174	82.13 197	83.34 172	87.86 153	94.58 103	96.15 101	79.87 172	87.33 190	89.07 172	93.39 166	86.76 173

MDTV_nov1_ep13_2view		88.22 166	87.85 173	88.65 162	91.40 177	86.75 187	94.07 138	84.97 181	88.86 131	93.20 63	96.11 72	96.21 100	83.70 150	87.29 191	80.29 198	84.56 202	79.46 199

new_pmnet		76.65 213	83.52 190	68.63 214	82.60 213	72.08 217	76.76 220	64.17 214	84.41 165	49.73 222	91.77 138	91.53 158	56.16 218	86.59 192	83.26 193	82.37 209	75.02 209

PMMVS		81.93 195	83.48 191	80.12 202	72.35 222	75.05 215	88.54 200	64.01 215	77.02 208	82.22 188	87.51 181	91.12 159	79.70 173	86.59 192	86.64 183	93.88 159	80.41 193

baseline		86.71 176	88.89 159	84.16 193	87.85 205	85.23 191	89.82 191	77.69 206	84.03 168	84.75 170	94.91 99	94.59 133	77.19 190	86.57 194	86.51 184	87.66 194	90.36 149

pmmvs4		89.95 146	89.32 157	90.69 134	91.60 175	89.17 176	94.37 127	87.63 149	88.07 138	91.02 114	94.50 105	90.50 165	86.13 135	86.33 195	89.40 166	93.39 166	87.29 172

MVE	60.41 19	73.21 214	80.84 199	64.30 215	56.34 223	57.24 223	75.28 222	72.76 211	87.14 145	41.39 224	86.31 192	85.30 187	80.66 169	86.17 196	83.36 192	59.35 221	80.38 194
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CHOSEN 1792x2688		86.64 177	86.62 180	86.65 181	90.33 190	87.86 184	93.19 154	83.30 194	83.95 170	82.32 187	87.93 177	89.34 171	86.92 126	85.64 197	84.95 190	83.85 206	86.68 174

HyFIR lowres test		88.19 168	86.56 182	90.09 142	91.24 179	92.17 148	94.30 132	88.79 137	84.06 166	85.45 165	89.52 162	85.64 186	88.64 111	85.40 198	87.28 179	92.14 178	81.87 189

pmnet_mix02		84.85 184	86.58 181	82.83 195	90.19 191	81.10 206	88.52 201	78.58 204	91.50 89	80.32 196	96.48 65	95.86 107	75.42 198	85.17 199	76.44 207	83.91 205	79.51 198

N_pmnet		79.33 202	84.22 187	73.62 213	91.72 173	73.72 216	86.11 211	76.36 207	92.38 71	53.38 220	95.54 86	95.62 111	59.14 216	84.23 200	74.84 212	75.03 218	73.25 214

CR-MVSNet		85.32 182	81.58 196	89.69 150	90.36 189	84.79 194	86.72 209	92.22 66	75.38 211	90.73 116	90.41 151	67.88 217	84.86 141	83.76 201	85.74 187	93.24 168	83.14 184

PatchT		83.44 189	81.10 197	86.18 183	77.92 219	82.58 202	89.87 190	87.39 156	75.88 209	90.73 116	89.86 158	66.71 221	84.86 141	83.76 201	85.74 187	86.33 199	83.14 184

GG-mvs-BLEND		54.28 216	77.89 210	26.72 219	0.37 228	83.31 199	70.04 223	0.39 225	74.71 213	5.36 227	68.78 218	83.06 189	0.62 224	83.73 203	78.99 202	83.55 207	72.68 216

test-mter		78.71 208	78.35 207	79.12 208	84.03 212	76.58 211	88.51 202	59.06 217	71.06 216	78.87 198	83.73 203	71.83 207	76.44 195	83.41 204	80.61 197	87.79 192	81.24 190

test-LLR		80.62 200	77.20 214	84.62 192	93.99 120	75.11 213	87.04 206	87.32 157	70.11 218	78.59 202	83.17 204	71.60 208	73.88 202	82.32 205	79.20 200	86.91 196	78.87 202

TESTMET0.1,1		77.47 212	77.20 214	77.78 211	81.94 214	75.11 213	87.04 206	58.33 219	70.11 218	78.59 202	83.17 204	71.60 208	73.88 202	82.32 205	79.20 200	86.91 196	78.87 202

RPMNet		83.42 190	78.40 206	89.28 155	89.79 193	84.79 194	90.64 187	92.11 73	75.38 211	87.10 157	79.80 212	61.99 226	82.79 156	81.88 207	82.07 195	93.23 170	82.87 187

dps		81.42 199	77.88 211	85.56 185	87.67 207	85.17 193	88.37 203	87.46 154	74.37 214	84.55 172	86.80 189	62.18 225	80.20 170	81.13 208	77.52 203	85.10 200	77.98 204

SCA		84.69 187	81.10 197	88.87 159	89.02 198	90.31 171	92.21 172	92.09 75	82.72 178	89.68 134	86.83 188	73.08 206	85.80 137	80.50 209	77.51 204	84.45 204	76.80 206

tpm		81.58 197	78.84 203	84.79 190	91.11 183	79.50 207	89.79 192	83.75 188	79.30 196	92.05 89	90.98 142	64.78 223	74.54 200	80.50 209	76.67 206	77.49 215	80.15 196

MDTV_nov1_ep13		82.33 193	79.66 200	85.45 186	88.83 200	83.88 196	90.09 188	81.98 198	79.07 199	88.82 145	88.70 168	73.77 205	78.41 182	80.29 211	76.08 208	84.56 202	75.83 208

ADS-MVSNet		79.11 205	79.38 202	78.80 209	81.90 215	75.59 212	84.36 214	83.69 189	87.31 142	76.76 206	87.58 180	76.90 201	68.55 209	78.70 212	75.56 209	77.53 214	74.07 212

PatchmatchNet		82.44 192	78.69 205	86.83 178	89.81 192	81.55 205	90.78 185	87.27 159	82.39 180	88.85 144	88.31 173	70.96 211	81.90 163	78.58 213	74.33 213	82.35 210	74.69 210
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		79.26 203	78.20 209	80.49 200	87.04 210	78.86 208	86.08 212	83.51 191	82.63 179	73.94 210	89.59 160	68.67 216	72.03 205	78.17 214	75.08 211	80.37 212	74.37 211

MVS-HIRNet		78.28 209	75.28 218	81.79 199	80.33 216	69.38 220	76.83 219	86.59 168	70.76 217	86.66 160	89.57 161	81.04 197	77.74 185	77.81 215	71.65 214	82.62 208	66.73 218

CostFormer		82.15 194	79.54 201	85.20 187	88.92 199	85.70 190	90.87 184	86.26 172	79.19 198	83.87 178	87.89 179	69.20 215	76.62 194	77.50 216	75.28 210	84.69 201	82.02 188

tpm cat1		80.03 201	75.93 217	84.81 189	89.31 195	83.26 200	88.86 199	86.55 170	79.24 197	86.10 161	84.22 201	63.62 224	77.37 189	73.43 217	70.88 216	80.67 211	76.87 205

tpmrst		78.81 207	76.18 216	81.87 198	88.56 201	77.45 210	86.74 208	81.52 200	80.08 190	83.48 180	90.84 144	66.88 218	74.54 200	73.04 218	71.02 215	76.38 216	73.95 213

DeepMVS_CX						47.68 224	53.20 224	19.21 220	63.24 221	26.96 225	66.50 219	69.82 214	66.91 211	64.27 219		54.91 223	72.72 215

tmp_tt				28.44 218	36.05 224	15.86 225	21.29 226	6.40 222	54.52 223	51.96 221	50.37 222	38.68 229	9.55 221	61.75 220	59.66 219	45.36 224

test_method		43.16 217	51.13 219	33.85 217	7.35 225	12.38 226	51.70 225	11.91 221	62.51 222	47.64 223	62.49 221	80.78 198	28.84 219	59.55 221	34.48 220	55.68 222	45.72 221

testmvs		2.38 218	3.35 220	1.26 221	0.83 226	0.96 228	1.53 228	0.83 223	3.59 224	1.63 229	6.03 223	2.93 230	1.55 223	3.49 222	2.51 222	1.21 226	3.92 223

test123		2.16 219	2.82 221	1.41 220	0.62 227	1.18 227	1.53 228	0.82 224	2.78 225	2.27 228	4.18 224	1.98 231	1.64 222	2.58 223	3.01 221	1.56 225	4.00 222

uanet_test		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet		0.00 220	0.00 222	0.00 222	0.00 229	0.00 229	0.00 230	0.00 226	0.00 226	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

RE-MVS-def										97.21 5

9.14												93.19 150

SR-MVS					97.13 24			94.77 17				97.77 54

our_test_3					91.78 172	88.87 177	94.37 127

MTAPA										94.88 28		96.88 81

MTMP										95.43 18		97.25 67

Patchmatch-RL test							8.96 227

XVS					96.86 33	97.48 19	98.73 3			93.28 59		96.82 83				98.17 37

X-MVStestdata					96.86 33	97.48 19	98.73 3			93.28 59		96.82 83				98.17 37

abl_6				91.88 113	93.76 130	94.98 96	95.64 99	88.97 135	86.20 153	90.00 130	86.31 192	94.50 136	87.31 123			95.60 124	92.48 121

mPP-MVS					98.24 3							97.65 60

NP-MVS									85.48 158

Patchmtry						83.74 197	86.72 209	92.22 66		90.73 116

High-resolution multi-view benchmark