High-res multi-view results

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

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

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

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

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

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

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

DELS-MVS		96.06 53	96.04 60	96.07 50	97.77 56	99.25 23	98.10 42	93.26 56	94.42 104	92.79 43	88.52 108	93.48 71	95.06 91	98.51 15	98.83 1	99.45 31	99.28 26
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DeepC-MVS_fast	96.13 1	98.13 20	98.27 25	97.97 25	99.16 27	99.03 39	99.05 18	97.24 27	98.22 9	94.17 32	95.82 39	98.07 39	98.69 17	98.83 10	98.80 2	99.52 14	99.10 52
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	93.79 8	97.08 37	97.20 40	96.95 38	99.09 29	99.03 39	98.20 40	93.33 54	97.99 14	93.82 33	90.61 91	96.80 49	97.82 37	97.90 45	98.78 3	99.47 26	99.26 31

MSLP-MVS++		98.04 23	97.93 32	98.18 17	99.10 28	99.09 31	98.34 36	96.99 33	97.54 30	96.60 13	94.82 50	98.45 35	98.89 6	97.46 56	98.77 4	99.17 88	99.37 17

DeepPCF-MVS	95.28 2	97.00 40	98.35 20	95.42 58	97.30 62	98.94 47	94.82 115	96.03 39	98.24 8	92.11 48	95.80 40	98.64 32	95.51 86	98.95 6	98.66 5	96.78 187	99.20 40

SMA-MVS		98.66 6	98.89 6	98.39 9	99.60 1	99.41 8	99.00 20	97.63 12	97.78 17	95.83 19	98.33 10	99.83 3	98.85 10	98.93 7	98.56 6	99.41 44	99.40 15
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
IS_MVSNet		95.28 63	96.43 55	93.94 86	95.30 89	99.01 43	95.90 94	91.12 87	94.13 109	87.50 101	91.23 82	94.45 67	94.17 105	98.45 18	98.50 7	99.65 2	99.23 35

DeepC-MVS	94.87 4	96.76 47	96.50 53	97.05 36	98.21 49	99.28 19	98.67 27	97.38 21	97.31 35	90.36 69	89.19 101	93.58 70	98.19 27	98.31 24	98.50 7	99.51 19	99.36 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SteuartSystems-ACMMP		98.38 14	98.71 9	97.99 24	99.34 21	99.46 7	99.34 5	97.33 25	97.31 35	94.25 30	98.06 13	99.17 18	98.13 28	98.98 4	98.46 9	99.55 12	99.54 9
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	93.91 7	97.23 35	97.22 39	97.24 33	98.89 36	98.85 57	98.26 39	93.25 58	97.99 14	95.56 23	90.01 97	98.03 41	98.05 32	97.91 44	98.43 10	99.44 39	99.35 19

DVP-MVS		98.86 3	98.97 2	98.75 2	99.43 13	99.63 1	99.25 12	97.81 1	98.62 1	97.69 1	97.59 20	99.90 1	98.93 5	98.99 3	98.42 11	99.37 53	99.62 3
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
MSP-MVS		98.73 5	98.93 4	98.50 6	99.44 12	99.57 3	99.36 3	97.65 8	98.14 11	96.51 15	98.49 6	99.65 7	98.67 18	98.60 13	98.42 11	99.40 47	99.63 1
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
APDe-MVS		98.87 2	98.96 3	98.77 1	99.58 2	99.53 5	99.44 1	97.81 1	98.22 9	97.33 4	98.70 4	99.33 9	98.86 8	98.96 5	98.40 13	99.63 3	99.57 8

APD-MVS		98.36 15	98.32 22	98.41 8	99.47 6	99.26 21	99.12 15	97.77 6	96.73 50	96.12 17	97.27 28	98.88 24	98.46 25	98.47 17	98.39 14	99.52 14	99.22 37
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PHI-MVS		97.78 26	98.44 17	97.02 37	98.73 38	99.25 23	98.11 41	95.54 40	96.66 53	92.79 43	98.52 5	99.38 8	97.50 44	97.84 46	98.39 14	99.45 31	99.03 66

Vis-MVSNet (Re-imp)		94.46 80	96.24 57	92.40 105	95.23 92	98.64 71	95.56 102	90.99 88	94.42 104	85.02 111	90.88 89	94.65 66	88.01 174	98.17 32	98.37 16	99.57 8	98.53 103

SED-MVS		98.90 1	99.07 1	98.69 3	99.38 19	99.61 2	99.33 7	97.80 3	98.25 7	97.60 2	98.87 3	99.89 2	98.67 18	99.02 2	98.26 17	99.36 55	99.61 5

DPE-MVS		98.75 4	98.91 5	98.57 4	99.21 24	99.54 4	99.42 2	97.78 5	97.49 31	96.84 9	98.94 1	99.82 4	98.59 21	98.90 9	98.22 18	99.56 10	99.48 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		93.96 89	95.95 62	91.64 113	96.06 76	98.59 76	95.29 104	90.00 99	91.06 154	82.87 119	90.64 90	98.06 40	86.06 185	98.14 35	98.20 19	99.58 6	96.96 159

QAPM		96.78 46	97.14 43	96.36 44	99.05 30	99.14 30	98.02 43	93.26 56	97.27 37	90.84 60	91.16 83	97.31 44	97.64 42	97.70 50	98.20 19	99.33 57	99.18 45

X-MVS		97.84 24	98.19 27	97.42 31	99.40 15	99.35 12	99.06 17	97.25 26	97.38 34	90.85 57	96.06 36	98.72 29	98.53 24	98.41 22	98.15 21	99.46 27	99.28 26

ACMMPR		98.40 12	98.49 12	98.28 14	99.41 14	99.40 9	99.36 3	97.35 22	98.30 5	95.02 26	97.79 17	98.39 37	99.04 2	98.26 28	98.10 22	99.50 22	99.22 37

CNVR-MVS		98.47 10	98.46 15	98.48 7	99.40 15	99.05 32	99.02 19	97.54 17	97.73 18	96.65 12	97.20 29	99.13 19	98.85 10	98.91 8	98.10 22	99.41 44	99.08 55

HFP-MVS		98.48 9	98.62 10	98.32 12	99.39 18	99.33 16	99.27 10	97.42 19	98.27 6	95.25 24	98.34 9	98.83 26	99.08 1	98.26 28	98.08 24	99.48 23	99.26 31

CANet		96.84 44	97.20 40	96.42 42	97.92 54	99.24 25	98.60 29	93.51 53	97.11 41	93.07 37	91.16 83	97.24 45	96.21 73	98.24 30	98.05 25	99.22 79	99.35 19

TSAR-MVS + MP.		98.49 8	98.78 7	98.15 20	98.14 51	99.17 28	99.34 5	97.18 30	98.44 4	95.72 20	97.84 16	99.28 11	98.87 7	99.05 1	98.05 25	99.66 1	99.60 6
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CS-MVS		96.45 48	97.46 37	95.28 61	94.58 110	98.63 73	97.19 57	90.59 93	95.87 74	91.74 51	95.84 38	96.55 51	98.05 32	98.04 41	97.99 27	99.51 19	99.29 25

SD-MVS		98.52 7	98.77 8	98.23 16	98.15 50	99.26 21	98.79 26	97.59 16	98.52 2	96.25 16	97.99 15	99.75 5	99.01 3	98.27 27	97.97 28	99.59 4	99.63 1
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
MVS_111021_HR		97.04 39	98.20 26	95.69 53	98.44 46	99.29 18	96.59 75	93.20 59	97.70 22	89.94 76	98.46 7	96.89 47	96.71 64	98.11 38	97.95 29	99.27 68	99.01 69

canonicalmvs		95.25 65	95.45 69	95.00 65	95.27 91	98.72 65	96.89 62	89.82 103	96.51 54	90.84 60	93.72 58	86.01 116	97.66 41	95.78 115	97.94 30	99.54 13	99.50 11

CDPH-MVS		96.84 44	97.49 34	96.09 48	98.92 34	98.85 57	98.61 28	95.09 42	96.00 69	87.29 102	95.45 45	97.42 43	97.16 51	97.83 47	97.94 30	99.44 39	98.92 79

MVS_0304		96.31 50	96.91 48	95.62 54	97.21 64	99.20 26	98.55 31	93.10 61	97.04 45	89.73 78	90.30 93	96.35 53	95.71 79	98.14 35	97.93 32	99.38 50	99.40 15

PGM-MVS		97.81 25	98.11 28	97.46 30	99.55 3	99.34 15	99.32 8	94.51 46	96.21 61	93.07 37	98.05 14	97.95 42	98.82 12	98.22 31	97.89 33	99.48 23	99.09 54

ACMMP_NAP		98.20 18	98.49 12	97.85 26	99.50 4	99.40 9	99.26 11	97.64 11	97.47 33	92.62 46	97.59 20	99.09 21	98.71 16	98.82 11	97.86 34	99.40 47	99.19 41

ETV-MVS		96.31 50	97.47 36	94.96 67	94.79 102	98.78 60	96.08 88	91.41 84	96.16 62	90.50 64	95.76 41	96.20 57	97.39 45	98.42 21	97.82 35	99.57 8	99.18 45

TSAR-MVS + ACMM		97.71 28	98.60 11	96.66 41	98.64 41	99.05 32	98.85 25	97.23 28	98.45 3	89.40 84	97.51 24	99.27 13	96.88 60	98.53 14	97.81 36	98.96 117	99.59 7

NCCC		98.10 21	98.05 30	98.17 19	99.38 19	99.05 32	99.00 20	97.53 18	98.04 13	95.12 25	94.80 51	99.18 17	98.58 22	98.49 16	97.78 37	99.39 49	98.98 73

MP-MVS		98.09 22	98.30 24	97.84 27	99.34 21	99.19 27	99.23 13	97.40 20	97.09 42	93.03 40	97.58 22	98.85 25	98.57 23	98.44 20	97.69 38	99.48 23	99.23 35
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		98.32 17	98.34 21	98.29 13	99.34 21	99.30 17	99.15 14	97.35 22	97.49 31	95.58 22	97.72 18	98.62 33	98.82 12	98.29 25	97.67 39	99.51 19	99.28 26

xxxxxxxxxxxxxcwj		97.07 38	95.99 61	98.33 10	99.45 9	99.05 32	98.27 37	97.65 8	97.73 18	97.02 7	98.18 11	81.99 144	98.11 29	98.15 33	97.62 40	99.45 31	99.19 41

SF-MVS		98.39 13	98.45 16	98.33 10	99.45 9	99.05 32	98.27 37	97.65 8	97.73 18	97.02 7	98.18 11	99.25 14	98.11 29	98.15 33	97.62 40	99.45 31	99.19 41

OpenMVS	92.33 11	95.50 56	95.22 73	95.82 52	98.98 31	98.97 45	97.67 51	93.04 64	94.64 100	89.18 88	84.44 136	94.79 65	96.79 61	97.23 61	97.61 42	99.24 73	98.88 84

Vis-MVSNet		92.77 107	95.00 79	90.16 133	94.10 121	98.79 59	94.76 117	88.26 123	92.37 139	79.95 134	88.19 110	91.58 79	84.38 195	97.59 53	97.58 43	99.52 14	98.91 82
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
zzz-MVS		98.43 11	98.31 23	98.57 4	99.48 5	99.40 9	99.32 8	97.62 13	97.70 22	96.67 11	96.59 32	99.09 21	98.86 8	98.65 12	97.56 44	99.45 31	99.17 47

CS-MVS-test		95.94 54	97.30 38	94.36 81	94.44 114	98.51 77	96.65 72	88.71 116	97.06 44	88.76 92	94.68 53	95.44 63	98.01 35	98.29 25	97.55 45	99.56 10	99.54 9

MAR-MVS		95.50 56	95.60 65	95.39 59	98.67 40	98.18 88	95.89 96	89.81 104	94.55 102	91.97 49	92.99 62	90.21 89	97.30 47	96.79 75	97.49 46	98.72 140	98.99 71
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
MCST-MVS		98.20 18	98.36 18	98.01 23	99.40 15	99.05 32	99.00 20	97.62 13	97.59 29	93.70 34	97.42 27	99.30 10	98.77 14	98.39 23	97.48 47	99.59 4	99.31 24

HPM-MVS++		98.34 16	98.47 14	98.18 17	99.46 8	99.15 29	99.10 16	97.69 7	97.67 25	94.93 27	97.62 19	99.70 6	98.60 20	98.45 18	97.46 48	99.31 62	99.26 31

LS3D		95.46 59	95.14 74	95.84 51	97.91 55	98.90 54	98.58 30	97.79 4	97.07 43	83.65 117	88.71 104	88.64 102	97.82 37	97.49 55	97.42 49	99.26 72	97.72 138

TSAR-MVS + GP.		97.45 31	98.36 18	96.39 43	95.56 83	98.93 49	97.74 49	93.31 55	97.61 28	94.24 31	98.44 8	99.19 16	98.03 34	97.60 52	97.41 50	99.44 39	99.33 21

DPM-MVS		96.86 43	96.82 49	96.91 39	98.08 52	98.20 86	98.52 33	97.20 29	97.24 38	91.42 53	91.84 76	98.45 35	97.25 48	97.07 67	97.40 51	98.95 118	97.55 142

CSCG		97.44 32	97.18 42	97.75 28	99.47 6	99.52 6	98.55 31	95.41 41	97.69 24	95.72 20	94.29 55	95.53 62	98.10 31	96.20 103	97.38 52	99.24 73	99.62 3

PVSNet_BlendedMVS		95.41 61	95.28 71	95.57 55	97.42 60	99.02 41	95.89 96	93.10 61	96.16 62	93.12 35	91.99 72	85.27 121	94.66 96	98.09 39	97.34 53	99.24 73	99.08 55

PVSNet_Blended		95.41 61	95.28 71	95.57 55	97.42 60	99.02 41	95.89 96	93.10 61	96.16 62	93.12 35	91.99 72	85.27 121	94.66 96	98.09 39	97.34 53	99.24 73	99.08 55

casdiffmvs		94.38 84	94.15 94	94.64 77	94.70 108	98.51 77	96.03 91	91.66 79	95.70 79	89.36 85	86.48 120	85.03 126	96.60 68	97.40 57	97.30 55	99.52 14	98.67 95

PVSNet_Blended_VisFu		94.77 73	95.54 67	93.87 88	96.48 71	98.97 45	94.33 124	91.84 76	94.93 96	90.37 68	85.04 131	94.99 64	90.87 152	98.12 37	97.30 55	99.30 64	99.45 14

MVS_111021_LR		97.16 36	98.01 31	96.16 47	98.47 44	98.98 44	96.94 61	93.89 49	97.64 27	91.44 52	98.89 2	96.41 52	97.20 50	98.02 42	97.29 57	99.04 112	98.85 88

train_agg		97.65 29	98.06 29	97.18 34	98.94 33	98.91 52	98.98 24	97.07 32	96.71 51	90.66 62	97.43 26	99.08 23	98.20 26	97.96 43	97.14 58	99.22 79	99.19 41

EIA-MVS		95.50 56	96.19 58	94.69 75	94.83 101	98.88 56	95.93 93	91.50 83	94.47 103	89.43 82	93.14 61	92.72 75	97.05 56	97.82 49	97.13 59	99.43 42	99.15 49

EPNet		96.27 52	96.97 45	95.46 57	98.47 44	98.28 82	97.41 54	93.67 51	95.86 75	92.86 42	97.51 24	93.79 69	91.76 137	97.03 69	97.03 60	98.61 150	99.28 26
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPP-MVSNet		95.27 64	96.18 59	94.20 84	94.88 100	98.64 71	94.97 110	90.70 91	95.34 86	89.67 80	91.66 79	93.84 68	95.42 88	97.32 59	97.00 61	99.58 6	99.47 13

FMVSNet2		93.30 103	93.36 109	93.22 101	91.34 153	95.86 148	96.22 83	88.24 124	95.15 94	89.92 77	81.64 149	89.36 94	94.40 102	96.77 76	96.98 62	99.21 82	97.79 131

CHOSEN 280x420		95.46 59	97.01 44	93.66 92	97.28 63	97.98 93	96.40 81	85.39 156	96.10 66	91.07 55	96.53 33	96.34 55	95.61 83	97.65 51	96.95 63	96.21 188	97.49 143

baseline1		94.59 77	94.47 84	94.72 74	95.16 94	97.97 94	96.07 89	91.94 74	94.86 97	89.98 74	91.60 80	85.87 118	95.64 81	97.07 67	96.90 64	99.52 14	97.06 158

MVS_Test		94.82 69	95.66 64	93.84 89	94.79 102	98.35 81	96.49 79	89.10 114	96.12 65	87.09 104	92.58 67	90.61 86	96.48 69	96.51 91	96.89 65	99.11 99	98.54 102

gg-mvs-nofinetune		86.17 188	88.57 162	83.36 196	93.44 131	98.15 89	96.58 76	72.05 210	74.12 214	49.23 218	64.81 208	90.85 84	89.90 167	97.83 47	96.84 66	98.97 116	97.41 146

CANet_DTU		93.92 90	96.57 52	90.83 124	95.63 81	98.39 80	96.99 60	87.38 132	96.26 58	71.97 177	96.31 34	93.02 72	94.53 99	97.38 58	96.83 67	98.49 157	97.79 131

OMC-MVS		97.00 40	96.92 47	97.09 35	98.69 39	98.66 68	97.85 47	95.02 43	98.09 12	94.47 28	93.15 60	96.90 46	97.38 46	97.16 65	96.82 68	99.13 96	97.65 139

FMVSNet3		93.79 94	94.17 92	93.35 99	91.21 156	95.99 141	96.62 73	88.68 117	95.23 90	90.40 65	86.39 121	91.16 80	94.11 106	95.96 108	96.67 69	99.07 104	97.79 131

CNLPA		96.90 42	96.28 56	97.64 29	98.56 43	98.63 73	96.85 64	96.60 37	97.73 18	97.08 6	89.78 99	96.28 56	97.80 39	96.73 78	96.63 70	98.94 119	98.14 125

UGNet		94.92 66	96.63 51	92.93 102	96.03 77	98.63 73	94.53 121	91.52 82	96.23 60	90.03 73	92.87 65	96.10 59	86.28 184	96.68 80	96.60 71	99.16 91	99.32 23
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
CHOSEN 1792x2688		92.66 109	92.49 119	92.85 103	97.13 65	98.89 55	95.90 94	88.50 121	95.32 87	83.31 118	71.99 193	88.96 100	94.10 107	96.69 79	96.49 72	98.15 167	99.10 52

CDS-MVSNet		92.77 107	93.60 104	91.80 111	92.63 143	96.80 118	95.24 106	89.14 113	90.30 163	84.58 112	86.76 115	90.65 85	90.42 160	95.89 110	96.49 72	98.79 136	98.32 119
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
diffmvs		94.31 85	94.21 89	94.42 80	94.64 109	98.28 82	96.36 82	91.56 80	96.77 49	88.89 91	88.97 102	84.23 130	96.01 77	96.05 107	96.41 74	99.05 111	98.79 92

GBi-Net		93.81 92	94.18 90	93.38 97	91.34 153	95.86 148	96.22 83	88.68 117	95.23 90	90.40 65	86.39 121	91.16 80	94.40 102	96.52 88	96.30 75	99.21 82	97.79 131

test1		93.81 92	94.18 90	93.38 97	91.34 153	95.86 148	96.22 83	88.68 117	95.23 90	90.40 65	86.39 121	91.16 80	94.40 102	96.52 88	96.30 75	99.21 82	97.79 131

FMVSNet1		91.54 123	90.93 144	92.26 107	90.35 163	95.27 171	95.22 107	87.16 135	91.37 151	87.62 100	75.45 169	83.84 133	94.43 100	96.52 88	96.30 75	98.82 129	97.74 137

DI_MVS_plusplus_trai		94.01 88	93.63 103	94.44 79	94.54 111	98.26 84	97.51 53	90.63 92	95.88 73	89.34 86	80.54 156	89.36 94	95.48 87	96.33 97	96.27 78	99.17 88	98.78 93

AdaColmap		97.53 30	96.93 46	98.24 15	99.21 24	98.77 61	98.47 34	97.34 24	96.68 52	96.52 14	95.11 48	96.12 58	98.72 15	97.19 64	96.24 79	99.17 88	98.39 114

Fast-Effi-MVS+		91.87 115	92.08 130	91.62 115	92.91 138	97.21 109	94.93 111	84.60 167	93.61 117	81.49 128	83.50 141	78.95 153	96.62 66	96.55 85	96.22 80	99.16 91	98.51 104

DROMVSNet		91.87 115	92.08 130	91.62 115	92.91 138	97.21 109	94.93 111	84.60 167	93.61 117	81.49 128	83.50 141	78.95 153	96.62 66	96.55 85	96.22 80	99.16 91	98.51 104

PLC	94.95 3	97.37 33	96.77 50	98.07 21	98.97 32	98.21 85	97.94 46	96.85 36	97.66 26	97.58 3	93.33 59	96.84 48	98.01 35	97.13 66	96.20 82	99.09 101	98.01 126
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
baseline		94.83 68	95.82 63	93.68 91	94.75 105	97.80 95	96.51 78	88.53 120	97.02 47	89.34 86	92.93 63	92.18 77	94.69 95	95.78 115	96.08 83	98.27 165	98.97 77

CPTT-MVS		97.78 26	97.54 33	98.05 22	98.91 35	99.05 32	99.00 20	96.96 34	97.14 40	95.92 18	95.50 43	98.78 28	98.99 4	97.20 62	96.07 84	98.54 154	99.04 65

Effi-MVS+		92.93 106	93.86 98	91.86 109	94.07 122	98.09 91	95.59 101	85.98 148	94.27 107	79.54 138	91.12 86	81.81 145	96.71 64	96.67 81	96.06 85	99.27 68	98.98 73

gm-plane-assit		83.26 198	85.29 195	80.89 199	89.52 176	89.89 209	70.26 215	78.24 191	77.11 212	58.01 215	74.16 180	66.90 205	90.63 158	97.20 62	96.05 86	98.66 147	95.68 175

DCV-MVSNet		94.76 74	95.12 76	94.35 82	95.10 97	95.81 152	96.46 80	89.49 109	96.33 57	90.16 70	92.55 68	90.26 88	95.83 78	95.52 121	96.03 87	99.06 107	99.33 21

IterMVS-LS		92.56 110	93.18 110	91.84 110	93.90 124	94.97 178	94.99 109	86.20 145	94.18 108	82.68 120	85.81 127	87.36 109	94.43 100	95.31 127	96.02 88	98.87 125	98.60 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMMP		97.37 33	97.48 35	97.25 32	98.88 37	99.28 19	98.47 34	96.86 35	97.04 45	92.15 47	97.57 23	96.05 60	97.67 40	97.27 60	95.99 89	99.46 27	99.14 51
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
thres100view900		93.55 99	92.47 122	94.81 72	95.33 87	98.74 62	96.78 68	92.30 70	92.63 130	88.29 93	87.21 112	78.01 159	96.78 62	96.38 93	95.92 90	99.38 50	98.40 113

thres200		93.62 96	92.54 116	94.88 69	95.36 86	98.93 49	96.75 69	92.31 67	92.84 127	88.28 95	86.99 114	77.81 161	97.13 52	96.82 72	95.92 90	99.45 31	98.49 107

TAPA-MVS	94.18 5	96.38 49	96.49 54	96.25 45	98.26 48	98.66 68	98.00 44	94.96 44	97.17 39	89.48 81	92.91 64	96.35 53	97.53 43	96.59 83	95.90 92	99.28 66	97.82 130
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVSTER		94.89 67	95.07 77	94.68 76	94.71 106	96.68 124	97.00 59	90.57 94	95.18 93	93.05 39	95.21 46	86.41 113	93.72 114	97.59 53	95.88 93	99.00 113	98.50 106

tfpn200view9		93.64 95	92.57 115	94.89 68	95.33 87	98.94 47	96.82 65	92.31 67	92.63 130	88.29 93	87.21 112	78.01 159	97.12 54	96.82 72	95.85 94	99.45 31	98.56 100

thres400		93.56 98	92.43 123	94.87 70	95.40 85	98.91 52	96.70 71	92.38 66	92.93 126	88.19 97	86.69 117	77.35 162	97.13 52	96.75 77	95.85 94	99.42 43	98.56 100

GeoE		92.52 111	92.64 114	92.39 106	93.96 123	97.76 96	96.01 92	85.60 153	93.23 122	83.94 114	81.56 150	84.80 127	95.63 82	96.22 101	95.83 96	99.19 86	99.07 59

Anonymous202405211			92.18 128		95.04 98	98.20 86	96.14 86	91.79 78	93.93 110		74.60 175	88.38 105	96.48 69	95.17 131	95.82 97	99.00 113	99.15 49

LGP-MVS_train		94.12 86	94.62 81	93.53 93	96.44 72	97.54 99	97.40 55	91.84 76	94.66 99	81.09 131	95.70 42	83.36 137	95.10 90	96.36 96	95.71 98	99.32 59	99.03 66

thres600view7		93.49 100	92.37 126	94.79 73	95.42 84	98.93 49	96.58 76	92.31 67	93.04 124	87.88 98	86.62 118	76.94 165	97.09 55	96.82 72	95.63 99	99.45 31	98.63 97

MSDG		94.82 69	93.73 101	96.09 48	98.34 47	97.43 104	97.06 58	96.05 38	95.84 76	90.56 63	86.30 125	89.10 99	95.55 85	96.13 106	95.61 100	99.00 113	95.73 174

EPNet_dtu		92.45 112	95.02 78	89.46 142	98.02 53	95.47 163	94.79 116	92.62 65	94.97 95	70.11 188	94.76 52	92.61 76	84.07 198	95.94 109	95.56 101	97.15 184	95.82 173
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		92.03 113	91.55 138	92.58 104	97.13 65	98.72 65	94.65 119	86.54 141	93.58 119	82.56 121	67.75 204	90.47 87	95.67 80	95.87 111	95.54 102	98.91 122	98.93 78

Anonymous20231211		93.49 100	92.33 127	94.84 71	94.78 104	98.00 92	96.11 87	91.85 75	94.86 97	90.91 56	74.69 174	89.18 97	96.73 63	94.82 136	95.51 103	98.67 144	99.24 34

Effi-MVS+-dtu		91.78 118	93.59 105	89.68 141	92.44 145	97.11 111	94.40 123	84.94 163	92.43 135	75.48 159	91.09 87	83.75 134	93.55 118	96.61 82	95.47 104	97.24 183	98.67 95

GG-mvs-BLEND		66.17 209	94.91 80	32.63 215	1.32 223	96.64 125	91.40 172	0.85 221	94.39 106	2.20 224	90.15 96	95.70 61	2.27 220	96.39 92	95.44 105	97.78 176	95.68 175

MIMVSNet		88.99 158	91.07 142	86.57 184	86.78 204	95.62 156	91.20 177	75.40 204	90.65 159	76.57 151	84.05 138	82.44 143	91.01 147	95.84 112	95.38 106	98.48 158	93.50 196

ET-MVSNet_ETH3D		93.34 102	94.33 88	92.18 108	83.26 210	97.66 98	96.72 70	89.89 102	95.62 82	87.17 103	96.00 37	83.69 135	96.99 57	93.78 151	95.34 107	99.06 107	98.18 124

FC-MVSNet-train		93.85 91	93.91 96	93.78 90	94.94 99	96.79 121	94.29 125	91.13 86	93.84 114	88.26 96	90.40 92	85.23 123	94.65 98	96.54 87	95.31 108	99.38 50	99.28 26

CVMVSNet		89.77 147	91.66 136	87.56 174	93.21 136	95.45 164	91.94 168	89.22 112	89.62 167	69.34 194	83.99 139	85.90 117	84.81 193	94.30 146	95.28 109	96.85 186	97.09 154

UniMVSNet_ETH3D		88.47 163	86.00 193	91.35 118	91.55 150	96.29 135	92.53 150	88.81 115	85.58 197	82.33 122	67.63 205	66.87 206	94.04 108	91.49 187	95.24 110	98.84 128	98.92 79

PatchMatch-RL		94.69 75	94.41 85	95.02 64	97.63 59	98.15 89	94.50 122	91.99 73	95.32 87	91.31 54	95.47 44	83.44 136	96.02 76	96.56 84	95.23 111	98.69 143	96.67 166

TSAR-MVS + COLMAP		94.79 71	94.51 83	95.11 62	96.50 70	97.54 99	97.99 45	94.54 45	97.81 16	85.88 108	96.73 31	81.28 148	96.99 57	96.29 98	95.21 112	98.76 139	96.73 165

test0.0.03 1		91.97 114	93.91 96	89.72 138	93.31 134	96.40 133	91.34 174	87.06 136	93.86 112	81.67 126	91.15 85	89.16 98	86.02 186	95.08 132	95.09 113	98.91 122	96.64 168

baseline2		93.01 105	94.17 92	91.64 113	92.83 141	97.49 101	93.40 136	87.53 130	93.67 116	86.07 107	91.83 77	86.58 110	91.36 141	96.38 93	95.06 114	98.67 144	98.20 123

CLD-MVS		94.79 71	94.36 87	95.30 60	95.21 93	97.46 102	97.23 56	92.24 71	96.43 55	91.77 50	92.69 66	84.31 129	96.06 74	95.52 121	95.03 115	99.31 62	99.06 60
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
FC-MVSNet-test		91.63 120	93.82 100	89.08 146	92.02 148	96.40 133	93.26 139	87.26 133	93.72 115	77.26 146	88.61 107	89.86 91	85.50 188	95.72 119	95.02 116	99.16 91	97.44 145

PMMVS		94.61 76	95.56 66	93.50 94	94.30 117	96.74 122	94.91 113	89.56 108	95.58 84	87.72 99	96.15 35	92.86 73	96.06 74	95.47 123	95.02 116	98.43 162	97.09 154

OPM-MVS		93.61 97	92.43 123	95.00 65	96.94 67	97.34 105	97.78 48	94.23 47	89.64 166	85.53 109	88.70 105	82.81 140	96.28 72	96.28 99	95.00 118	99.24 73	97.22 151

PCF-MVS	93.95 6	95.65 55	95.14 74	96.25 45	97.73 58	98.73 64	97.59 52	97.13 31	92.50 134	89.09 90	89.85 98	96.65 50	96.90 59	94.97 135	94.89 119	99.08 102	98.38 115
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thisisatest0530		94.54 78	95.47 68	93.46 95	94.51 112	98.65 70	94.66 118	90.72 89	95.69 81	86.90 105	93.80 56	89.44 93	94.74 93	96.98 71	94.86 120	99.19 86	98.85 88

tttt0517		94.52 79	95.44 70	93.44 96	94.51 112	98.68 67	94.61 120	90.72 89	95.61 83	86.84 106	93.78 57	89.26 96	94.74 93	97.02 70	94.86 120	99.20 85	98.87 86

LTVRE_ROB	87.32 16	87.55 176	88.25 165	86.73 182	90.66 158	95.80 153	93.05 142	84.77 164	83.35 203	60.32 211	83.12 144	67.39 204	93.32 121	94.36 145	94.86 120	98.28 164	98.87 86
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
HQP-MVS		94.43 81	94.57 82	94.27 83	96.41 73	97.23 108	96.89 62	93.98 48	95.94 71	83.68 116	95.01 49	84.46 128	95.58 84	95.47 123	94.85 123	99.07 104	99.00 70

ACMP	92.88 9	94.43 81	94.38 86	94.50 78	96.01 78	97.69 97	95.85 99	92.09 72	95.74 78	89.12 89	95.14 47	82.62 142	94.77 92	95.73 117	94.67 124	99.14 95	99.06 60
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	92.75 10	94.41 83	93.84 99	95.09 63	96.41 73	96.80 118	94.88 114	93.54 52	96.41 56	90.16 70	92.31 70	83.11 138	96.32 71	96.22 101	94.65 125	99.22 79	97.35 148
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Fast-Effi-MVS+-dtu		91.19 127	93.64 102	88.33 154	92.19 147	96.46 130	93.99 128	81.52 185	92.59 132	71.82 178	92.17 71	85.54 119	91.68 138	95.73 117	94.64 126	98.80 134	98.34 116

test_part1		91.21 126	89.47 154	93.24 100	94.26 118	95.45 164	95.26 105	88.36 122	88.49 176	90.04 72	72.61 190	82.82 139	93.69 116	93.25 162	94.62 127	97.84 175	99.06 60

TAMVS		90.54 136	90.87 146	90.16 133	91.48 151	96.61 126	93.26 139	86.08 146	87.71 183	81.66 127	83.11 145	84.04 131	90.42 160	94.54 139	94.60 128	98.04 172	95.48 178

TranMVSNet+NR-MVSNet		89.23 154	88.48 163	90.11 137	89.07 188	95.25 172	92.91 144	90.43 96	90.31 162	77.10 148	76.62 167	71.57 187	91.83 136	92.12 178	94.59 129	99.32 59	98.92 79

DU-MVS		89.67 148	88.84 159	90.63 128	89.26 182	95.61 157	92.48 151	89.91 100	91.22 152	79.57 136	77.72 164	71.18 189	93.21 124	92.53 172	94.57 130	99.35 56	99.05 63

CR-MVSNet		90.16 142	91.96 134	88.06 160	93.32 133	95.95 145	93.36 137	75.99 202	92.40 137	75.19 163	83.18 143	85.37 120	92.05 132	95.21 129	94.56 131	98.47 159	97.08 156

PatchT		89.13 156	91.71 135	86.11 188	92.92 137	95.59 159	83.64 204	75.09 205	91.87 146	75.19 163	82.63 146	85.06 125	92.05 132	95.21 129	94.56 131	97.76 177	97.08 156

ACMH	90.77 13	91.51 124	91.63 137	91.38 117	95.62 82	96.87 116	91.76 169	89.66 106	91.58 149	78.67 140	86.73 116	78.12 157	93.77 113	94.59 138	94.54 133	98.78 137	98.98 73
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet5		90.36 137	90.93 144	89.70 139	87.99 198	92.25 203	92.03 164	83.51 174	92.20 143	84.13 113	85.59 128	86.48 111	92.43 129	94.61 137	94.52 134	98.13 168	90.85 204

pm-mvs1		89.19 155	89.02 158	89.38 144	90.40 161	95.74 155	92.05 163	88.10 126	86.13 193	77.70 143	73.72 183	79.44 152	88.97 171	95.81 114	94.51 135	99.08 102	97.78 136

UniMVSNet_NR-MVSNet		90.35 138	89.96 150	90.80 125	89.66 172	95.83 151	92.48 151	90.53 95	90.96 156	79.57 136	79.33 160	77.14 163	93.21 124	92.91 168	94.50 136	99.37 53	99.05 63

IB-MVS	89.56 15	91.71 119	92.50 118	90.79 126	95.94 79	98.44 79	87.05 196	91.38 85	93.15 123	92.98 41	84.78 132	85.14 124	78.27 203	92.47 174	94.44 137	99.10 100	99.08 55
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
IterMVS-SCA-FT		90.24 139	92.48 121	87.63 171	92.85 140	94.30 194	93.79 130	81.47 186	92.66 129	69.95 189	84.66 134	88.38 105	89.99 165	95.39 126	94.34 138	97.74 180	97.63 140

test-mter		90.95 129	93.54 108	87.93 166	90.28 164	96.80 118	91.44 171	82.68 180	92.15 144	74.37 170	89.57 100	88.23 107	90.88 151	96.37 95	94.31 139	97.93 174	97.37 147

anonymousdsp		88.90 159	91.00 143	86.44 185	88.74 195	95.97 143	90.40 184	82.86 178	88.77 173	67.33 197	81.18 152	81.44 147	90.22 163	96.23 100	94.27 140	99.12 98	99.16 48

IterMVS		90.20 140	92.43 123	87.61 172	92.82 142	94.31 193	94.11 126	81.54 184	92.97 125	69.90 190	84.71 133	88.16 108	89.96 166	95.25 128	94.17 141	97.31 182	97.46 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
COLMAP_ROB	90.49 14	93.27 104	92.71 113	93.93 87	97.75 57	97.44 103	96.07 89	93.17 60	95.40 85	83.86 115	83.76 140	88.72 101	93.87 110	94.25 147	94.11 142	98.87 125	95.28 180
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test-LLR		91.62 121	93.56 106	89.35 145	93.31 134	96.57 127	92.02 165	87.06 136	92.34 140	75.05 166	90.20 94	88.64 102	90.93 148	96.19 104	94.07 143	97.75 178	96.90 162

TESTMET0.1,1		91.07 128	93.56 106	88.17 156	90.43 160	96.57 127	92.02 165	82.83 179	92.34 140	75.05 166	90.20 94	88.64 102	90.93 148	96.19 104	94.07 143	97.75 178	96.90 162

tfpnnormal		88.50 162	87.01 184	90.23 131	91.36 152	95.78 154	92.74 146	90.09 98	83.65 202	76.33 154	71.46 196	69.58 197	91.84 135	95.54 120	94.02 145	99.06 107	99.03 66

NR-MVSNet		89.34 151	88.66 160	90.13 136	90.40 161	95.61 157	93.04 143	89.91 100	91.22 152	78.96 139	77.72 164	68.90 200	89.16 170	94.24 148	93.95 146	99.32 59	98.99 71

TransMVSNet (Re)		87.73 175	86.79 186	88.83 148	90.76 157	94.40 191	91.33 175	89.62 107	84.73 199	75.41 161	72.73 188	71.41 188	86.80 180	94.53 140	93.93 147	99.06 107	95.83 172

ACMH+	90.88 12	91.41 125	91.13 141	91.74 112	95.11 96	96.95 113	93.13 141	89.48 110	92.42 136	79.93 135	85.13 130	78.02 158	93.82 112	93.49 158	93.88 148	98.94 119	97.99 127

UniMVSNet (Re)		90.03 145	89.61 153	90.51 129	89.97 169	96.12 139	92.32 155	89.26 111	90.99 155	80.95 132	78.25 163	75.08 172	91.14 144	93.78 151	93.87 149	99.41 44	99.21 39

RPMNet		90.19 141	92.03 133	88.05 161	93.46 130	95.95 145	93.41 135	74.59 207	92.40 137	75.91 157	84.22 137	86.41 113	92.49 128	94.42 143	93.85 150	98.44 160	96.96 159

Baseline_NR-MVSNet		89.27 153	88.01 169	90.73 127	89.26 182	93.71 198	92.71 148	89.78 105	90.73 157	81.28 130	73.53 184	72.85 181	92.30 131	92.53 172	93.84 151	99.07 104	98.88 84

testgi		89.42 149	91.50 139	87.00 181	92.40 146	95.59 159	89.15 190	85.27 160	92.78 128	72.42 175	91.75 78	76.00 168	84.09 197	94.38 144	93.82 152	98.65 148	96.15 169

GA-MVS		89.28 152	90.75 147	87.57 173	91.77 149	96.48 129	92.29 157	87.58 129	90.61 160	65.77 199	84.48 135	76.84 166	89.46 168	95.84 112	93.68 153	98.52 155	97.34 149

CP-MVSNet		87.89 173	87.27 179	88.62 150	89.30 180	95.06 175	90.60 182	85.78 150	87.43 187	75.98 156	74.60 175	68.14 203	90.76 153	93.07 166	93.60 154	99.30 64	98.98 73

PS-CasMVS		87.33 180	86.68 189	88.10 157	89.22 187	94.93 180	90.35 185	85.70 151	86.44 192	74.01 171	73.43 185	66.59 209	90.04 164	92.92 167	93.52 155	99.28 66	98.91 82

PEN-MVS		87.22 182	86.50 191	88.07 158	88.88 191	94.44 190	90.99 179	86.21 143	86.53 191	73.66 172	74.97 172	66.56 210	89.42 169	91.20 189	93.48 156	99.24 73	98.31 120

USDC		90.69 132	90.52 148	90.88 123	94.17 120	96.43 131	95.82 100	86.76 138	93.92 111	76.27 155	86.49 119	74.30 175	93.67 117	95.04 134	93.36 157	98.61 150	94.13 187

EG-PatchMatch MVS		86.68 184	87.24 180	86.02 189	90.58 159	96.26 136	91.08 178	81.59 183	84.96 198	69.80 192	71.35 197	75.08 172	84.23 196	94.24 148	93.35 158	98.82 129	95.46 179

WR-MVS		87.93 170	88.09 167	87.75 168	89.26 182	95.28 169	90.81 180	86.69 139	88.90 170	75.29 162	74.31 179	73.72 178	85.19 191	92.26 175	93.32 159	99.27 68	98.81 91

thisisatest0515		90.12 143	92.06 132	87.85 167	90.03 167	96.17 138	87.83 193	87.45 131	91.71 148	77.15 147	85.40 129	84.01 132	85.74 187	95.41 125	93.30 160	98.88 124	98.43 109

TinyColmap		89.42 149	88.58 161	90.40 130	93.80 128	95.45 164	93.96 129	86.54 141	92.24 142	76.49 152	80.83 153	70.44 192	93.37 120	94.45 142	93.30 160	98.26 166	93.37 198

DTE-MVSNet		86.67 185	86.09 192	87.35 177	88.45 197	94.08 196	90.65 181	86.05 147	86.13 193	72.19 176	74.58 177	66.77 208	87.61 177	90.31 192	93.12 162	99.13 96	97.62 141

WR-MVS_H		87.93 170	87.85 173	88.03 163	89.62 173	95.58 161	90.47 183	85.55 154	87.20 188	76.83 150	74.42 178	72.67 183	86.37 183	93.22 163	93.04 163	99.33 57	98.83 90

MS-PatchMatch		91.82 117	92.51 117	91.02 120	95.83 80	96.88 114	95.05 108	84.55 170	93.85 113	82.01 123	82.51 147	91.71 78	90.52 159	95.07 133	93.03 164	98.13 168	94.52 182

v7n		86.43 186	86.52 190	86.33 186	87.91 199	94.93 180	90.15 186	83.05 176	86.57 190	70.21 187	71.48 195	66.78 207	87.72 175	94.19 150	92.96 165	98.92 121	98.76 94

v2v482		88.25 166	87.71 176	88.88 147	89.23 186	95.28 169	92.10 161	87.89 128	88.69 174	73.31 173	75.32 170	71.64 186	91.89 134	92.10 180	92.92 166	98.86 127	97.99 127

v10		88.00 168	87.96 170	88.05 161	89.44 177	94.68 185	92.36 154	83.35 175	89.37 168	72.96 174	73.98 181	72.79 182	91.35 142	93.59 153	92.88 167	98.81 132	98.42 111

pmmvs5		87.83 174	88.09 167	87.51 176	89.59 175	95.48 162	89.75 188	84.73 165	86.07 195	71.44 180	80.57 155	70.09 195	90.74 155	94.47 141	92.87 168	98.82 129	97.10 153

v1192		87.51 177	87.31 178	87.74 169	89.04 189	94.87 183	92.07 162	85.03 161	88.49 176	70.32 185	72.65 189	70.35 193	91.21 143	93.59 153	92.80 169	98.78 137	98.42 111

v1144		87.92 172	87.79 174	88.07 158	89.27 181	95.15 174	92.17 160	85.62 152	88.52 175	71.52 179	73.80 182	72.40 184	91.06 146	93.54 157	92.80 169	98.81 132	98.33 117

V42		88.31 165	87.95 171	88.73 149	89.44 177	95.34 168	92.23 159	87.21 134	88.83 171	74.49 169	74.89 173	73.43 180	90.41 162	92.08 181	92.77 171	98.60 152	98.33 117

v8		88.21 167	87.94 172	88.51 151	89.62 173	95.01 177	92.31 156	84.99 162	88.94 169	74.70 168	75.03 171	73.51 179	90.67 156	92.11 179	92.74 172	98.80 134	98.24 121

v1240		86.89 183	86.75 188	87.06 180	88.75 194	94.65 187	91.30 176	84.05 171	87.49 186	68.94 195	71.96 194	68.86 201	90.65 157	93.33 160	92.72 173	98.67 144	98.24 121

v1921920		87.31 181	87.13 182	87.52 175	88.87 192	94.72 184	91.96 167	84.59 169	88.28 178	69.86 191	72.50 191	70.03 196	91.10 145	93.33 160	92.61 174	98.71 141	98.44 108

v144192		87.40 179	87.20 181	87.64 170	88.89 190	94.88 182	91.65 170	84.70 166	87.80 182	71.17 183	73.20 187	70.91 190	90.75 154	92.69 170	92.49 175	98.71 141	98.43 109

Anonymous20231206		83.84 197	85.19 196	82.26 198	87.38 202	92.87 200	85.49 200	83.65 173	86.07 195	63.44 206	68.42 201	69.01 199	75.45 206	93.34 159	92.44 176	98.12 170	94.20 186

pmmvs6		85.98 190	84.89 198	87.25 178	88.83 193	94.35 192	89.36 189	85.30 159	78.51 211	75.44 160	62.71 210	75.41 169	87.65 176	93.58 155	92.40 177	96.89 185	97.29 150

v148		87.51 177	86.79 186	88.36 153	89.39 179	95.21 173	89.84 187	88.20 125	87.61 185	77.56 144	73.38 186	70.32 194	86.80 180	90.70 191	92.31 178	98.37 163	97.98 129

EU-MVSNet		85.62 191	87.65 177	83.24 197	88.54 196	92.77 202	87.12 195	85.32 157	86.71 189	64.54 202	78.52 162	75.11 171	78.35 202	92.25 176	92.28 179	95.58 196	95.93 171

pmmvs4		90.55 135	89.91 151	91.30 119	90.26 165	94.95 179	92.73 147	87.94 127	93.44 121	85.35 110	82.28 148	76.09 167	93.02 126	93.56 156	92.26 180	98.51 156	96.77 164

MVS-HIRNet		85.36 192	86.89 185	83.57 195	90.13 166	94.51 189	83.57 205	72.61 209	88.27 179	71.22 182	68.97 200	81.81 145	88.91 172	93.08 165	91.94 181	94.97 204	89.64 207

TDRefinement		89.07 157	88.15 166	90.14 135	95.16 94	96.88 114	95.55 103	90.20 97	89.68 165	76.42 153	76.67 166	74.30 175	84.85 192	93.11 164	91.91 182	98.64 149	94.47 183

SixPastTwentyTwo		88.37 164	89.47 154	87.08 179	90.01 168	95.93 147	87.41 194	85.32 157	90.26 164	70.26 186	86.34 124	71.95 185	90.93 148	92.89 169	91.72 183	98.55 153	97.22 151

MIMVSNet1		80.03 202	80.93 203	78.97 203	72.46 216	90.73 207	80.81 209	82.44 181	80.39 208	63.64 204	57.57 211	64.93 211	76.37 204	91.66 185	91.55 184	98.07 171	89.70 206

test20.03		82.92 199	85.52 194	79.90 202	87.75 200	91.84 204	82.80 206	82.99 177	82.65 207	60.32 211	78.90 161	70.50 191	67.10 210	92.05 182	90.89 185	98.44 160	91.80 202

MDTV_nov1_ep13		91.57 122	93.18 110	89.70 139	93.39 132	96.97 112	93.53 133	80.91 187	95.70 79	81.86 124	92.40 69	89.93 90	93.25 123	91.97 183	90.80 186	95.25 201	94.46 184

tpm		87.95 169	89.44 156	86.21 187	92.53 144	94.62 188	91.40 172	76.36 199	91.46 150	69.80 192	87.43 111	75.14 170	91.55 139	89.85 197	90.60 187	95.61 195	96.96 159

RPSCF		94.05 87	94.00 95	94.12 85	96.20 75	96.41 132	96.61 74	91.54 81	95.83 77	89.73 78	96.94 30	92.80 74	95.35 89	91.63 186	90.44 188	95.27 200	93.94 191

pmmvs-eth3d		84.33 196	82.94 201	85.96 190	84.16 207	90.94 206	86.55 197	83.79 172	84.25 200	75.85 158	70.64 198	56.43 216	87.44 179	92.20 177	90.41 189	97.97 173	95.68 175

EPMVS		90.88 131	92.12 129	89.44 143	94.71 106	97.24 107	93.55 132	76.81 196	95.89 72	81.77 125	91.49 81	86.47 112	93.87 110	90.21 193	90.07 190	95.92 191	93.49 197

SCA		90.92 130	93.04 112	88.45 152	93.72 129	97.33 106	92.77 145	76.08 201	96.02 68	78.26 142	91.96 74	90.86 83	93.99 109	90.98 190	90.04 191	95.88 192	94.06 190

PM-MVS		84.72 195	84.47 199	85.03 191	84.67 206	91.57 205	86.27 198	82.31 182	87.65 184	70.62 184	76.54 168	56.41 217	88.75 173	92.59 171	89.85 192	97.54 181	96.66 167

ADS-MVSNet		89.80 146	91.33 140	88.00 164	94.43 115	96.71 123	92.29 157	74.95 206	96.07 67	77.39 145	88.67 106	86.09 115	93.26 122	88.44 199	89.57 193	95.68 194	93.81 194

PatchmatchNet		90.56 134	92.49 119	88.31 155	93.83 127	96.86 117	92.42 153	76.50 198	95.96 70	78.31 141	91.96 74	89.66 92	93.48 119	90.04 195	89.20 194	95.32 198	93.73 195
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CostFormer		90.69 132	90.48 149	90.93 122	94.18 119	96.08 140	94.03 127	78.20 192	93.47 120	89.96 75	90.97 88	80.30 149	93.72 114	87.66 203	88.75 195	95.51 197	96.12 170

pmmvs3		79.16 203	80.12 205	78.05 205	79.36 211	86.59 212	78.13 212	73.87 208	76.42 213	57.51 216	70.59 199	57.02 215	84.66 194	90.10 194	88.32 196	94.75 206	91.77 203

MDTV_nov1_ep13_2view		86.30 187	88.27 164	84.01 194	87.71 201	94.67 186	88.08 192	76.78 197	90.59 161	68.66 196	80.46 157	80.12 150	87.58 178	89.95 196	88.20 197	95.25 201	93.90 193

CMPMVS	65.18 17	84.76 194	83.10 200	86.69 183	95.29 90	95.05 176	88.37 191	85.51 155	80.27 209	71.31 181	68.37 202	73.85 177	85.25 189	87.72 201	87.75 198	94.38 208	88.70 208
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dps		90.11 144	89.37 157	90.98 121	93.89 125	96.21 137	93.49 134	77.61 194	91.95 145	92.74 45	88.85 103	78.77 156	92.37 130	87.71 202	87.71 199	95.80 193	94.38 185

new_pmnet		81.53 200	82.68 202	80.20 200	83.47 209	89.47 210	82.21 208	78.36 190	87.86 181	60.14 213	67.90 203	69.43 198	82.03 200	89.22 198	87.47 200	94.99 203	87.39 209

tpmrst		88.86 161	89.62 152	87.97 165	94.33 116	95.98 142	92.62 149	76.36 199	94.62 101	76.94 149	85.98 126	82.80 141	92.80 127	86.90 205	87.15 201	94.77 205	93.93 192

N_pmnet		84.80 193	85.10 197	84.45 193	89.25 185	92.86 201	84.04 203	86.21 143	88.78 172	66.73 198	72.41 192	74.87 174	85.21 190	88.32 200	86.45 202	95.30 199	92.04 201

MDA-MVSNet-bldmvs		80.11 201	80.24 204	79.94 201	77.01 213	93.21 199	78.86 211	85.94 149	82.71 206	60.86 208	79.71 159	51.77 219	83.71 199	75.60 211	86.37 203	93.28 209	92.35 199

tpm cat1		88.90 159	87.78 175	90.22 132	93.88 126	95.39 167	93.79 130	78.11 193	92.55 133	89.43 82	81.31 151	79.84 151	91.40 140	84.95 206	86.34 204	94.68 207	94.09 188

Gipuma		68.35 207	66.71 210	70.27 207	74.16 215	68.78 217	63.93 218	71.77 211	83.34 204	54.57 217	34.37 215	31.88 221	68.69 209	83.30 208	85.53 205	88.48 213	79.78 213
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ambc			73.83 209		76.23 214	85.13 213	82.27 207		84.16 201	65.58 201	52.82 213	23.31 224	73.55 207	91.41 188	85.26 206	92.97 210	94.70 181

pmnet_mix02		86.12 189	87.12 183	84.96 192	89.82 170	94.12 195	84.88 202	86.63 140	91.78 147	65.60 200	80.76 154	76.98 164	86.61 182	87.29 204	84.80 207	96.21 188	94.09 188

test_method		72.96 206	78.68 206	66.28 210	50.17 220	64.90 218	75.45 214	50.90 217	87.89 180	62.54 207	62.98 209	68.34 202	70.45 208	91.90 184	82.41 208	88.19 214	92.35 199

new-patchmatchnet		78.49 204	78.19 207	78.84 204	84.13 208	90.06 208	77.11 213	80.39 188	79.57 210	59.64 214	66.01 206	55.65 218	75.62 205	84.55 207	80.70 209	96.14 190	90.77 205

PMMVS2		64.36 210	65.94 212	62.52 211	67.37 217	77.44 215	64.39 217	69.32 215	61.47 216	34.59 219	46.09 214	41.03 220	48.02 217	74.56 213	78.23 210	91.43 211	82.76 211

tmp_tt				66.88 209	86.07 205	73.86 216	68.22 216	33.38 218	96.88 48	80.67 133	88.23 109	78.82 155	49.78 215	82.68 209	77.47 211	83.19 217

MVE	50.86 19	49.54 213	51.43 213	47.33 214	44.14 221	59.20 220	36.45 222	60.59 216	41.47 219	31.14 220	29.58 216	17.06 225	48.52 216	62.22 215	74.63 212	63.12 220	75.87 215
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
FPMVS		75.84 205	74.59 208	77.29 206	86.92 203	83.89 214	85.01 201	80.05 189	82.91 205	60.61 210	65.25 207	60.41 213	63.86 211	75.60 211	73.60 213	87.29 215	80.47 212

PMVS	63.12 18	67.27 208	66.39 211	68.30 208	77.98 212	60.24 219	59.53 219	76.82 195	66.65 215	60.74 209	54.39 212	59.82 214	51.24 214	73.92 214	70.52 214	83.48 216	79.17 214
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		50.67 211	47.85 214	53.96 212	64.13 219	50.98 222	38.06 220	69.51 213	51.40 218	24.60 221	29.46 218	24.39 223	56.07 213	48.17 216	59.70 215	71.40 218	70.84 216

EMVS		49.98 212	46.76 215	53.74 213	64.96 218	51.29 221	37.81 221	69.35 214	51.83 217	22.69 222	29.57 217	25.06 222	57.28 212	44.81 217	56.11 216	70.32 219	68.64 217

testmvs		12.09 214	16.94 216	6.42 216	3.15 222	6.08 223	9.51 224	3.84 219	21.46 220	5.31 223	27.49 219	6.76 226	10.89 218	17.06 218	15.01 217	5.84 221	24.75 218

test123		9.58 215	13.53 217	4.97 217	1.31 224	5.47 224	8.32 225	2.95 220	18.14 221	2.03 225	20.82 220	2.34 227	10.60 219	10.00 219	14.16 218	4.60 222	23.77 219

uanet_test		0.00 216	0.00 218	0.00 218	0.00 225	0.00 225	0.00 226	0.00 222	0.00 222	0.00 226	0.00 221	0.00 228	0.00 221	0.00 220	0.00 219	0.00 223	0.00 220

sosnet-low-res		0.00 216	0.00 218	0.00 218	0.00 225	0.00 225	0.00 226	0.00 222	0.00 222	0.00 226	0.00 221	0.00 228	0.00 221	0.00 220	0.00 219	0.00 223	0.00 220

sosnet		0.00 216	0.00 218	0.00 218	0.00 225	0.00 225	0.00 226	0.00 222	0.00 222	0.00 226	0.00 221	0.00 228	0.00 221	0.00 220	0.00 219	0.00 223	0.00 220

RE-MVS-def										63.50 205

9.14												99.28 11

SR-MVS					99.45 9			97.61 15				99.20 15

our_test_3					89.78 171	93.84 197	85.59 199

MTAPA										96.83 10		99.12 20

MTMP										97.18 5		98.83 26

Patchmatch-RL test							34.61 223

XVS					96.60 68	99.35 12	96.82 65			90.85 57		98.72 29				99.46 27

X-MVStestdata					96.60 68	99.35 12	96.82 65			90.85 57		98.72 29				99.46 27

abl_6				96.82 40	98.60 42	98.74 62	97.74 49	93.73 50	96.25 59	94.37 29	94.55 54	98.60 34	97.25 48			99.27 68	98.61 98

mPP-MVS					99.21 24							98.29 38

NP-MVS									95.32 87

Patchmtry						95.96 144	93.36 137	75.99 202		75.19 163

DeepMVS_CX						86.86 211	79.50 210	70.43 212	90.73 157	63.66 203	80.36 158	60.83 212	79.68 201	76.23 210		89.46 212	86.53 210

High-resolution multi-view benchmark