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	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 58	95.39 11	99.29 1	98.28 27	94.78 31	98.93 6	98.87 6	96.04 2	99.86 8	97.45 12	99.58 21	99.59 19

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 30	95.13 16	99.19 1	98.89 4	95.54 5	99.85 16	97.52 8	99.66 10	99.56 25

DVP-MVS		97.91 3	97.81 3	98.22 12	99.45 3	95.36 13	98.21 43	97.85 105	94.92 22	98.73 10	98.87 6	95.08 8	99.84 21	97.52 8	99.67 6	99.48 39
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
DPE-MVS		97.86 4	97.65 5	98.47 5	99.17 32	95.78 7	97.21 143	98.35 20	95.16 15	98.71 12	98.80 11	95.05 10	99.89 3	96.70 26	99.73 1	99.73 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		97.82 5	97.73 4	98.08 17	99.15 33	94.82 26	98.81 7	98.30 24	94.76 33	98.30 17	98.90 3	93.77 17	99.68 45	97.93 1	99.69 3	99.75 5

CNVR-MVS		97.68 6	97.44 9	98.37 7	98.90 50	95.86 6	97.27 135	98.08 63	95.81 4	97.87 26	98.31 45	94.26 13	99.68 45	97.02 19	99.49 36	99.57 22

SteuartSystems-ACMMP		97.62 7	97.53 7	97.87 22	98.39 76	94.25 36	98.43 24	98.27 30	95.34 10	98.11 19	98.56 18	94.53 12	99.71 37	96.57 30	99.62 15	99.65 12
Skip Steuart: Steuart Systems R&D Blog.
MSP-MVS		97.59 8	97.54 6	97.73 34	99.40 11	93.77 52	98.53 15	98.29 25	95.55 6	98.56 14	97.81 84	93.90 15	99.65 49	96.62 27	99.21 64	99.77 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
TSAR-MVS + MP.		97.42 9	97.33 11	97.69 38	99.25 27	94.24 37	98.07 52	97.85 105	93.72 61	98.57 13	98.35 36	93.69 18	99.40 97	97.06 18	99.46 39	99.44 43
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		97.41 10	97.53 7	97.06 60	98.57 69	94.46 30	97.92 65	98.14 53	94.82 28	99.01 3	98.55 20	94.18 14	97.41 302	96.94 20	99.64 13	99.32 55
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
SF-MVS		97.39 11	97.13 12	98.17 14	99.02 42	95.28 19	98.23 40	98.27 30	92.37 112	98.27 18	98.65 16	93.33 21	99.72 36	96.49 32	99.52 28	99.51 33

SMA-MVS		97.35 12	97.03 18	98.30 8	99.06 38	95.42 10	97.94 63	98.18 46	90.57 172	98.85 9	98.94 1	93.33 21	99.83 24	96.72 25	99.68 4	99.63 14
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
HPM-MVS++		97.34 13	96.97 20	98.47 5	99.08 36	96.16 4	97.55 107	97.97 90	95.59 5	96.61 59	97.89 75	92.57 32	99.84 21	95.95 51	99.51 31	99.40 48

NCCC		97.30 14	97.03 18	98.11 16	98.77 53	95.06 24	97.34 128	98.04 78	95.96 2	97.09 42	97.88 77	93.18 23	99.71 37	95.84 56	99.17 67	99.56 25

ACMMP_NAP		97.20 15	96.86 23	98.23 11	99.09 34	95.16 22	97.60 100	98.19 44	92.82 101	97.93 24	98.74 13	91.60 48	99.86 8	96.26 35	99.52 28	99.67 11

XVS		97.18 16	96.96 21	97.81 26	99.38 14	94.03 46	98.59 12	98.20 42	94.85 24	96.59 61	98.29 48	91.70 45	99.80 28	95.66 60	99.40 46	99.62 15

MCST-MVS		97.18 16	96.84 25	98.20 13	99.30 24	95.35 15	97.12 150	98.07 68	93.54 69	96.08 79	97.69 91	93.86 16	99.71 37	96.50 31	99.39 48	99.55 28

HFP-MVS		97.14 18	96.92 22	97.83 24	99.42 7	94.12 42	98.52 16	98.32 22	93.21 81	97.18 37	98.29 48	92.08 39	99.83 24	95.63 65	99.59 17	99.54 29

MTAPA		97.08 19	96.78 30	97.97 21	99.37 16	94.42 32	97.24 137	98.08 63	95.07 20	96.11 78	98.59 17	90.88 64	99.90 2	96.18 44	99.50 33	99.58 21

region2R		97.07 20	96.84 25	97.77 31	99.46 2	93.79 50	98.52 16	98.24 37	93.19 84	97.14 39	98.34 39	91.59 49	99.87 7	95.46 72	99.59 17	99.64 13

ACMMPR		97.07 20	96.84 25	97.79 28	99.44 6	93.88 48	98.52 16	98.31 23	93.21 81	97.15 38	98.33 42	91.35 53	99.86 8	95.63 65	99.59 17	99.62 15

CP-MVS		97.02 22	96.81 28	97.64 41	99.33 21	93.54 55	98.80 8	98.28 27	92.99 90	96.45 69	98.30 47	91.90 42	99.85 16	95.61 67	99.68 4	99.54 29

SR-MVS		97.01 23	96.86 23	97.47 44	99.09 34	93.27 64	97.98 57	98.07 68	93.75 60	97.45 29	98.48 27	91.43 51	99.59 61	96.22 38	99.27 57	99.54 29

ZNCC-MVS		96.96 24	96.67 34	97.85 23	99.37 16	94.12 42	98.49 20	98.18 46	92.64 107	96.39 71	98.18 55	91.61 47	99.88 4	95.59 70	99.55 24	99.57 22

APD-MVS		96.95 25	96.60 36	98.01 18	99.03 41	94.93 25	97.72 84	98.10 61	91.50 134	98.01 21	98.32 44	92.33 35	99.58 64	94.85 85	99.51 31	99.53 32
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MSLP-MVS++		96.94 26	97.06 14	96.59 70	98.72 55	91.86 99	97.67 89	98.49 13	94.66 37	97.24 36	98.41 33	92.31 37	98.94 144	96.61 28	99.46 39	98.96 87

DeepC-MVS_fast	93.89 2	96.93 27	96.64 35	97.78 29	98.64 64	94.30 33	97.41 119	98.04 78	94.81 29	96.59 61	98.37 35	91.24 55	99.64 56	95.16 78	99.52 28	99.42 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CS-MVS-test		96.89 28	97.04 17	96.45 82	98.29 81	91.66 104	99.03 4	97.85 105	95.84 3	96.90 46	97.97 71	91.24 55	98.75 160	96.92 21	99.33 53	98.94 90

SR-MVS-dyc-post		96.88 29	96.80 29	97.11 59	99.02 42	92.34 84	97.98 57	98.03 80	93.52 71	97.43 32	98.51 23	91.40 52	99.56 72	96.05 46	99.26 59	99.43 45

CS-MVS		96.86 30	97.06 14	96.26 97	98.16 95	91.16 130	99.09 3	97.87 100	95.30 11	97.06 43	98.03 65	91.72 43	98.71 166	97.10 17	99.17 67	98.90 95

mPP-MVS		96.86 30	96.60 36	97.64 41	99.40 11	93.44 57	98.50 19	98.09 62	93.27 80	95.95 85	98.33 42	91.04 60	99.88 4	95.20 77	99.57 23	99.60 18

GST-MVS		96.85 32	96.52 40	97.82 25	99.36 18	94.14 41	98.29 31	98.13 54	92.72 104	96.70 53	98.06 62	91.35 53	99.86 8	94.83 86	99.28 56	99.47 40

patch_mono-2		96.83 33	97.44 9	95.01 157	99.05 39	85.39 282	96.98 159	98.77 5	94.70 35	97.99 22	98.66 14	93.61 19	99.91 1	97.67 4	99.50 33	99.72 10

APD-MVS_3200maxsize		96.81 34	96.71 33	97.12 58	99.01 45	92.31 86	97.98 57	98.06 71	93.11 87	97.44 30	98.55 20	90.93 62	99.55 74	96.06 45	99.25 61	99.51 33

PGM-MVS		96.81 34	96.53 39	97.65 39	99.35 20	93.53 56	97.65 92	98.98 1	92.22 114	97.14 39	98.44 30	91.17 58	99.85 16	94.35 97	99.46 39	99.57 22

MP-MVS		96.77 36	96.45 45	97.72 35	99.39 13	93.80 49	98.41 25	98.06 71	93.37 77	95.54 100	98.34 39	90.59 68	99.88 4	94.83 86	99.54 26	99.49 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PHI-MVS		96.77 36	96.46 44	97.71 37	98.40 74	94.07 44	98.21 43	98.45 16	89.86 184	97.11 41	98.01 68	92.52 33	99.69 43	96.03 49	99.53 27	99.36 53

MP-MVS-pluss		96.70 38	96.27 49	97.98 20	99.23 30	94.71 27	96.96 161	98.06 71	90.67 163	95.55 98	98.78 12	91.07 59	99.86 8	96.58 29	99.55 24	99.38 51
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + GP.		96.69 39	96.49 41	97.27 52	98.31 80	93.39 58	96.79 172	96.72 220	94.17 49	97.44 30	97.66 95	92.76 26	99.33 102	96.86 23	97.76 116	99.08 76

HPM-MVS		96.69 39	96.45 45	97.40 46	99.36 18	93.11 67	98.87 6	98.06 71	91.17 149	96.40 70	97.99 69	90.99 61	99.58 64	95.61 67	99.61 16	99.49 37
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MVS_111021_HR		96.68 41	96.58 38	96.99 61	98.46 70	92.31 86	96.20 227	98.90 2	94.30 47	95.86 87	97.74 89	92.33 35	99.38 100	96.04 48	99.42 44	99.28 58

DELS-MVS		96.61 42	96.38 47	97.30 49	97.79 113	93.19 65	95.96 238	98.18 46	95.23 12	95.87 86	97.65 96	91.45 50	99.70 42	95.87 52	99.44 43	99.00 85
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
DeepPCF-MVS	93.97 1	96.61 42	97.09 13	95.15 149	98.09 98	86.63 262	96.00 236	98.15 51	95.43 7	97.95 23	98.56 18	93.40 20	99.36 101	96.77 24	99.48 37	99.45 41

EI-MVSNet-Vis-set		96.51 44	96.47 42	96.63 67	98.24 85	91.20 125	96.89 165	97.73 113	94.74 34	96.49 65	98.49 25	90.88 64	99.58 64	96.44 33	98.32 99	99.13 70

HPM-MVS_fast		96.51 44	96.27 49	97.22 54	99.32 22	92.74 74	98.74 9	98.06 71	90.57 172	96.77 50	98.35 36	90.21 71	99.53 78	94.80 89	99.63 14	99.38 51

DROMVSNet		96.42 46	96.47 42	96.26 97	97.01 151	91.52 110	98.89 5	97.75 110	94.42 42	96.64 58	97.68 92	89.32 77	98.60 175	97.45 12	99.11 73	98.67 114

CANet		96.39 47	96.02 52	97.50 43	97.62 123	93.38 59	97.02 154	97.96 91	95.42 8	94.86 110	97.81 84	87.38 107	99.82 26	96.88 22	99.20 65	99.29 56

dcpmvs_2		96.37 48	97.05 16	94.31 196	98.96 46	84.11 299	97.56 104	97.51 138	93.92 55	97.43 32	98.52 22	92.75 27	99.32 104	97.32 16	99.50 33	99.51 33

EI-MVSNet-UG-set		96.34 49	96.30 48	96.47 79	98.20 90	90.93 137	96.86 166	97.72 115	94.67 36	96.16 77	98.46 28	90.43 69	99.58 64	96.23 37	97.96 110	98.90 95

train_agg		96.30 50	95.83 56	97.72 35	98.70 56	94.19 38	96.41 205	98.02 83	88.58 225	96.03 80	97.56 106	92.73 29	99.59 61	95.04 80	99.37 52	99.39 49

ACMMP		96.27 51	95.93 53	97.28 51	99.24 28	92.62 77	98.25 36	98.81 3	92.99 90	94.56 116	98.39 34	88.96 82	99.85 16	94.57 96	97.63 117	99.36 53
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
MVS_111021_LR		96.24 52	96.19 51	96.39 87	98.23 89	91.35 117	96.24 225	98.79 4	93.99 53	95.80 89	97.65 96	89.92 75	99.24 110	95.87 52	99.20 65	98.58 116

DeepC-MVS	93.07 3	96.06 53	95.66 57	97.29 50	97.96 102	93.17 66	97.30 133	98.06 71	93.92 55	93.38 143	98.66 14	86.83 113	99.73 33	95.60 69	99.22 63	98.96 87
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CSCG		96.05 54	95.91 54	96.46 81	99.24 28	90.47 152	98.30 30	98.57 12	89.01 208	93.97 130	97.57 104	92.62 31	99.76 31	94.66 92	99.27 57	99.15 68

ETV-MVS		96.02 55	95.89 55	96.40 85	97.16 137	92.44 82	97.47 116	97.77 109	94.55 39	96.48 66	94.51 256	91.23 57	98.92 145	95.65 63	98.19 103	97.82 165

canonicalmvs		96.02 55	95.45 62	97.75 33	97.59 126	95.15 23	98.28 32	97.60 127	94.52 40	96.27 74	96.12 183	87.65 100	99.18 116	96.20 43	94.82 178	98.91 94

CDPH-MVS		95.97 57	95.38 65	97.77 31	98.93 47	94.44 31	96.35 214	97.88 98	86.98 267	96.65 57	97.89 75	91.99 41	99.47 89	92.26 133	99.46 39	99.39 49

UA-Net		95.95 58	95.53 59	97.20 56	97.67 118	92.98 70	97.65 92	98.13 54	94.81 29	96.61 59	98.35 36	88.87 83	99.51 83	90.36 173	97.35 127	99.11 74

VNet		95.89 59	95.45 62	97.21 55	98.07 100	92.94 71	97.50 110	98.15 51	93.87 57	97.52 28	97.61 102	85.29 133	99.53 78	95.81 57	95.27 170	99.16 66

alignmvs		95.87 60	95.23 69	97.78 29	97.56 129	95.19 21	97.86 68	97.17 178	94.39 44	96.47 67	96.40 170	85.89 126	99.20 113	96.21 42	95.11 174	98.95 89

casdiffmvs_mvg		95.81 61	95.57 58	96.51 75	96.87 156	91.49 111	97.50 110	97.56 134	93.99 53	95.13 107	97.92 74	87.89 96	98.78 155	95.97 50	97.33 128	99.26 60
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DPM-MVS		95.69 62	94.92 75	98.01 18	98.08 99	95.71 9	95.27 267	97.62 126	90.43 175	95.55 98	97.07 127	91.72 43	99.50 86	89.62 188	98.94 79	98.82 104

DP-MVS Recon		95.68 63	95.12 73	97.37 47	99.19 31	94.19 38	97.03 152	98.08 63	88.35 232	95.09 108	97.65 96	89.97 74	99.48 88	92.08 142	98.59 89	98.44 133

casdiffmvs		95.64 64	95.49 60	96.08 104	96.76 167	90.45 153	97.29 134	97.44 155	94.00 52	95.46 102	97.98 70	87.52 104	98.73 162	95.64 64	97.33 128	99.08 76
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MG-MVS		95.61 65	95.38 65	96.31 92	98.42 73	90.53 150	96.04 233	97.48 141	93.47 73	95.67 95	98.10 58	89.17 79	99.25 109	91.27 160	98.77 83	99.13 70

baseline		95.58 66	95.42 64	96.08 104	96.78 163	90.41 155	97.16 147	97.45 151	93.69 64	95.65 96	97.85 81	87.29 108	98.68 168	95.66 60	97.25 132	99.13 70

CPTT-MVS		95.57 67	95.19 70	96.70 64	99.27 26	91.48 112	98.33 28	98.11 59	87.79 248	95.17 106	98.03 65	87.09 111	99.61 57	93.51 113	99.42 44	99.02 79

EIA-MVS		95.53 68	95.47 61	95.71 124	97.06 146	89.63 172	97.82 73	97.87 100	93.57 65	93.92 131	95.04 233	90.61 67	98.95 143	94.62 94	98.68 86	98.54 118

3Dnovator+	91.43 4	95.40 69	94.48 89	98.16 15	96.90 155	95.34 16	98.48 21	97.87 100	94.65 38	88.53 262	98.02 67	83.69 154	99.71 37	93.18 120	98.96 78	99.44 43

PS-MVSNAJ		95.37 70	95.33 67	95.49 137	97.35 131	90.66 148	95.31 264	97.48 141	93.85 58	96.51 64	95.70 207	88.65 87	99.65 49	94.80 89	98.27 100	96.17 213

MVSFormer		95.37 70	95.16 71	95.99 111	96.34 190	91.21 123	98.22 41	97.57 131	91.42 138	96.22 75	97.32 114	86.20 123	97.92 256	94.07 101	99.05 74	98.85 101

xiu_mvs_v2_base		95.32 72	95.29 68	95.40 142	97.22 133	90.50 151	95.44 258	97.44 155	93.70 63	96.46 68	96.18 179	88.59 90	99.53 78	94.79 91	97.81 113	96.17 213

PVSNet_Blended_VisFu		95.27 73	94.91 76	96.38 88	98.20 90	90.86 139	97.27 135	98.25 35	90.21 177	94.18 124	97.27 116	87.48 105	99.73 33	93.53 112	97.77 115	98.55 117

diffmvs		95.25 74	95.13 72	95.63 127	96.43 186	89.34 188	95.99 237	97.35 167	92.83 100	96.31 72	97.37 113	86.44 118	98.67 169	96.26 35	97.19 134	98.87 100
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		95.23 75	94.81 77	96.51 75	97.18 136	91.58 108	98.26 35	98.12 56	94.38 45	94.90 109	98.15 57	82.28 188	98.92 145	91.45 157	98.58 90	99.01 82
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPP-MVSNet		95.22 76	95.04 74	95.76 117	97.49 130	89.56 176	98.67 10	97.00 198	90.69 161	94.24 122	97.62 101	89.79 76	98.81 153	93.39 118	96.49 149	98.92 93

EPNet		95.20 77	94.56 84	97.14 57	92.80 328	92.68 76	97.85 71	94.87 314	96.64 1	92.46 159	97.80 86	86.23 120	99.65 49	93.72 111	98.62 88	99.10 75
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator	91.36 5	95.19 78	94.44 91	97.44 45	96.56 176	93.36 61	98.65 11	98.36 17	94.12 50	89.25 247	98.06 62	82.20 190	99.77 30	93.41 117	99.32 54	99.18 65

OMC-MVS		95.09 79	94.70 81	96.25 100	98.46 70	91.28 119	96.43 203	97.57 131	92.04 123	94.77 112	97.96 72	87.01 112	99.09 128	91.31 159	96.77 141	98.36 140

xiu_mvs_v1_base_debu		95.01 80	94.76 78	95.75 119	96.58 173	91.71 100	96.25 222	97.35 167	92.99 90	96.70 53	96.63 157	82.67 178	99.44 93	96.22 38	97.46 120	96.11 218

xiu_mvs_v1_base		95.01 80	94.76 78	95.75 119	96.58 173	91.71 100	96.25 222	97.35 167	92.99 90	96.70 53	96.63 157	82.67 178	99.44 93	96.22 38	97.46 120	96.11 218

xiu_mvs_v1_base_debi		95.01 80	94.76 78	95.75 119	96.58 173	91.71 100	96.25 222	97.35 167	92.99 90	96.70 53	96.63 157	82.67 178	99.44 93	96.22 38	97.46 120	96.11 218

PAPM_NR		95.01 80	94.59 83	96.26 97	98.89 51	90.68 147	97.24 137	97.73 113	91.80 128	92.93 156	96.62 160	89.13 80	99.14 121	89.21 200	97.78 114	98.97 86

lupinMVS		94.99 84	94.56 84	96.29 95	96.34 190	91.21 123	95.83 243	96.27 247	88.93 213	96.22 75	96.88 138	86.20 123	98.85 150	95.27 76	99.05 74	98.82 104

Effi-MVS+		94.93 85	94.45 90	96.36 90	96.61 170	91.47 113	96.41 205	97.41 160	91.02 154	94.50 117	95.92 191	87.53 103	98.78 155	93.89 107	96.81 140	98.84 103

IS-MVSNet		94.90 86	94.52 87	96.05 107	97.67 118	90.56 149	98.44 23	96.22 250	93.21 81	93.99 128	97.74 89	85.55 131	98.45 187	89.98 177	97.86 111	99.14 69

MVS_Test		94.89 87	94.62 82	95.68 125	96.83 160	89.55 177	96.70 181	97.17 178	91.17 149	95.60 97	96.11 186	87.87 97	98.76 159	93.01 128	97.17 135	98.72 109

PVSNet_Blended		94.87 88	94.56 84	95.81 116	98.27 82	89.46 183	95.47 257	98.36 17	88.84 216	94.36 119	96.09 187	88.02 93	99.58 64	93.44 115	98.18 104	98.40 136

jason		94.84 89	94.39 92	96.18 102	95.52 223	90.93 137	96.09 231	96.52 236	89.28 201	96.01 83	97.32 114	84.70 140	98.77 158	95.15 79	98.91 81	98.85 101
jason: jason.
API-MVS		94.84 89	94.49 88	95.90 113	97.90 108	92.00 96	97.80 75	97.48 141	89.19 204	94.81 111	96.71 143	88.84 84	99.17 117	88.91 206	98.76 84	96.53 203

test_yl		94.78 91	94.23 93	96.43 83	97.74 115	91.22 121	96.85 167	97.10 184	91.23 146	95.71 92	96.93 133	84.30 146	99.31 105	93.10 121	95.12 172	98.75 106

DCV-MVSNet		94.78 91	94.23 93	96.43 83	97.74 115	91.22 121	96.85 167	97.10 184	91.23 146	95.71 92	96.93 133	84.30 146	99.31 105	93.10 121	95.12 172	98.75 106

WTY-MVS		94.71 93	94.02 95	96.79 63	97.71 117	92.05 94	96.59 196	97.35 167	90.61 169	94.64 114	96.93 133	86.41 119	99.39 98	91.20 162	94.71 182	98.94 90

sss		94.51 94	93.80 99	96.64 65	97.07 143	91.97 97	96.32 217	98.06 71	88.94 212	94.50 117	96.78 140	84.60 141	99.27 108	91.90 143	96.02 154	98.68 113

CANet_DTU		94.37 95	93.65 103	96.55 71	96.46 184	92.13 92	96.21 226	96.67 227	94.38 45	93.53 139	97.03 130	79.34 237	99.71 37	90.76 167	98.45 96	97.82 165

AdaColmap		94.34 96	93.68 102	96.31 92	98.59 66	91.68 103	96.59 196	97.81 108	89.87 183	92.15 168	97.06 128	83.62 157	99.54 76	89.34 194	98.07 107	97.70 169

CNLPA		94.28 97	93.53 107	96.52 72	98.38 77	92.55 79	96.59 196	96.88 211	90.13 180	91.91 174	97.24 118	85.21 134	99.09 128	87.64 230	97.83 112	97.92 157

MAR-MVS		94.22 98	93.46 112	96.51 75	98.00 101	92.19 91	97.67 89	97.47 144	88.13 239	93.00 151	95.84 195	84.86 139	99.51 83	87.99 217	98.17 105	97.83 164
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
PAPR		94.18 99	93.42 117	96.48 78	97.64 122	91.42 116	95.55 253	97.71 119	88.99 209	92.34 165	95.82 197	89.19 78	99.11 124	86.14 256	97.38 125	98.90 95

h-mvs33		94.15 100	93.52 109	96.04 108	97.81 112	90.22 157	97.62 99	97.58 130	95.19 13	96.74 51	97.45 109	83.67 155	99.61 57	95.85 54	79.73 337	98.29 143

CHOSEN 1792x2688		94.15 100	93.51 110	96.06 106	98.27 82	89.38 186	95.18 271	98.48 15	85.60 290	93.76 134	97.11 125	83.15 165	99.61 57	91.33 158	98.72 85	99.19 64

Vis-MVSNet (Re-imp)		94.15 100	93.88 98	94.95 163	97.61 124	87.92 232	98.10 49	95.80 266	92.22 114	93.02 150	97.45 109	84.53 143	97.91 259	88.24 214	97.97 109	99.02 79

CDS-MVSNet		94.14 103	93.54 106	95.93 112	96.18 197	91.46 114	96.33 216	97.04 194	88.97 211	93.56 136	96.51 164	87.55 102	97.89 260	89.80 182	95.95 156	98.44 133
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PLC	91.00 6	94.11 104	93.43 115	96.13 103	98.58 68	91.15 131	96.69 183	97.39 161	87.29 262	91.37 185	96.71 143	88.39 91	99.52 82	87.33 237	97.13 136	97.73 167
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
FIs		94.09 105	93.70 101	95.27 145	95.70 216	92.03 95	98.10 49	98.68 8	93.36 79	90.39 205	96.70 145	87.63 101	97.94 252	92.25 135	90.50 246	95.84 226

PVSNet_BlendedMVS		94.06 106	93.92 97	94.47 187	98.27 82	89.46 183	96.73 177	98.36 17	90.17 178	94.36 119	95.24 227	88.02 93	99.58 64	93.44 115	90.72 242	94.36 309

nrg030		94.05 107	93.31 119	96.27 96	95.22 245	94.59 28	98.34 27	97.46 146	92.93 98	91.21 195	96.64 151	87.23 110	98.22 206	94.99 83	85.80 287	95.98 222

UGNet		94.04 108	93.28 120	96.31 92	96.85 157	91.19 126	97.88 67	97.68 120	94.40 43	93.00 151	96.18 179	73.39 297	99.61 57	91.72 149	98.46 95	98.13 148
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
TAMVS		94.01 109	93.46 112	95.64 126	96.16 199	90.45 153	96.71 180	96.89 210	89.27 202	93.46 141	96.92 136	87.29 108	97.94 252	88.70 210	95.74 161	98.53 119

114514_t		93.95 110	93.06 125	96.63 67	99.07 37	91.61 105	97.46 118	97.96 91	77.99 350	93.00 151	97.57 104	86.14 125	99.33 102	89.22 199	99.15 69	98.94 90

FC-MVSNet-test		93.94 111	93.57 104	95.04 154	95.48 225	91.45 115	98.12 48	98.71 6	93.37 77	90.23 208	96.70 145	87.66 99	97.85 262	91.49 155	90.39 247	95.83 227

mvsany_test1		93.93 112	93.98 96	93.78 225	94.94 259	86.80 255	94.62 279	92.55 344	88.77 222	96.85 47	98.49 25	88.98 81	98.08 226	95.03 81	95.62 165	96.46 208

GeoE		93.89 113	93.28 120	95.72 123	96.96 154	89.75 170	98.24 39	96.92 207	89.47 196	92.12 170	97.21 120	84.42 144	98.39 194	87.71 224	96.50 148	99.01 82

HY-MVS	89.66 9	93.87 114	92.95 128	96.63 67	97.10 142	92.49 81	95.64 251	96.64 228	89.05 207	93.00 151	95.79 201	85.77 129	99.45 92	89.16 203	94.35 184	97.96 155

XVG-OURS-SEG-HR		93.86 115	93.55 105	94.81 171	97.06 146	88.53 213	95.28 265	97.45 151	91.68 131	94.08 127	97.68 92	82.41 186	98.90 148	93.84 109	92.47 207	96.98 191

mvsmamba		93.83 116	93.46 112	94.93 166	94.88 264	90.85 140	98.55 14	95.49 282	94.24 48	91.29 192	96.97 132	83.04 169	98.14 214	95.56 71	91.17 232	95.78 232

VDD-MVS		93.82 117	93.08 124	96.02 109	97.88 109	89.96 166	97.72 84	95.85 264	92.43 110	95.86 87	98.44 30	68.42 323	99.39 98	96.31 34	94.85 176	98.71 111

mvs_anonymous		93.82 117	93.74 100	94.06 205	96.44 185	85.41 280	95.81 244	97.05 192	89.85 186	90.09 218	96.36 172	87.44 106	97.75 272	93.97 103	96.69 145	99.02 79

HQP_MVS		93.78 119	93.43 115	94.82 169	96.21 194	89.99 162	97.74 79	97.51 138	94.85 24	91.34 186	96.64 151	81.32 204	98.60 175	93.02 126	92.23 210	95.86 223

PS-MVSNAJss		93.74 120	93.51 110	94.44 188	93.91 300	89.28 193	97.75 78	97.56 134	92.50 109	89.94 222	96.54 163	88.65 87	98.18 211	93.83 110	90.90 239	95.86 223

XVG-OURS		93.72 121	93.35 118	94.80 174	97.07 143	88.61 208	94.79 276	97.46 146	91.97 126	93.99 128	97.86 80	81.74 199	98.88 149	92.64 132	92.67 205	96.92 195

HyFIR lowres test		93.66 122	92.92 129	95.87 114	98.24 85	89.88 167	94.58 281	98.49 13	85.06 300	93.78 133	95.78 202	82.86 174	98.67 169	91.77 148	95.71 163	99.07 78

iter_conf_final		93.60 123	93.11 123	95.04 154	97.13 140	91.30 118	97.92 65	95.65 275	92.98 95	91.60 178	96.64 151	79.28 239	98.13 215	95.34 75	91.49 224	95.70 240

LFMVS		93.60 123	92.63 143	96.52 72	98.13 97	91.27 120	97.94 63	93.39 337	90.57 172	96.29 73	98.31 45	69.00 319	99.16 118	94.18 100	95.87 158	99.12 73

F-COLMAP		93.58 125	92.98 127	95.37 143	98.40 74	88.98 201	97.18 145	97.29 172	87.75 251	90.49 202	97.10 126	85.21 134	99.50 86	86.70 247	96.72 144	97.63 171

ab-mvs		93.57 126	92.55 148	96.64 65	97.28 132	91.96 98	95.40 259	97.45 151	89.81 188	93.22 149	96.28 175	79.62 234	99.46 90	90.74 168	93.11 199	98.50 123

LS3D		93.57 126	92.61 146	96.47 79	97.59 126	91.61 105	97.67 89	97.72 115	85.17 298	90.29 207	98.34 39	84.60 141	99.73 33	83.85 290	98.27 100	98.06 154

FA-MVS(test-final)		93.52 128	92.92 129	95.31 144	96.77 164	88.54 212	94.82 275	96.21 252	89.61 191	94.20 123	95.25 226	83.24 162	99.14 121	90.01 176	96.16 153	98.25 144

Fast-Effi-MVS+		93.46 129	92.75 138	95.59 130	96.77 164	90.03 159	96.81 171	97.13 181	88.19 235	91.30 189	94.27 272	86.21 122	98.63 172	87.66 229	96.46 151	98.12 149

hse-mvs2		93.45 130	92.99 126	94.81 171	97.02 150	88.59 209	96.69 183	96.47 239	95.19 13	96.74 51	96.16 182	83.67 155	98.48 186	95.85 54	79.13 341	97.35 184

QAPM		93.45 130	92.27 157	96.98 62	96.77 164	92.62 77	98.39 26	98.12 56	84.50 308	88.27 268	97.77 87	82.39 187	99.81 27	85.40 269	98.81 82	98.51 122

UniMVSNet_NR-MVSNet		93.37 132	92.67 142	95.47 140	95.34 234	92.83 72	97.17 146	98.58 11	92.98 95	90.13 213	95.80 198	88.37 92	97.85 262	91.71 150	83.93 315	95.73 239

1112_ss		93.37 132	92.42 154	96.21 101	97.05 148	90.99 133	96.31 218	96.72 220	86.87 270	89.83 226	96.69 147	86.51 117	99.14 121	88.12 215	93.67 193	98.50 123

UniMVSNet (Re)		93.31 134	92.55 148	95.61 129	95.39 228	93.34 62	97.39 124	98.71 6	93.14 86	90.10 217	94.83 243	87.71 98	98.03 237	91.67 153	83.99 314	95.46 250

OPM-MVS		93.28 135	92.76 136	94.82 169	94.63 278	90.77 144	96.65 187	97.18 176	93.72 61	91.68 177	97.26 117	79.33 238	98.63 172	92.13 139	92.28 209	95.07 272
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		93.24 136	92.48 153	95.51 135	95.70 216	92.39 83	97.86 68	98.66 10	92.30 113	92.09 172	95.37 221	80.49 217	98.40 190	93.95 104	85.86 286	95.75 237

test_fmvs1		93.21 137	93.53 107	92.25 277	96.55 178	81.20 325	97.40 123	96.96 200	90.68 162	96.80 48	98.04 64	69.25 318	98.40 190	97.58 7	98.50 91	97.16 188

MVSTER		93.20 138	92.81 135	94.37 192	96.56 176	89.59 175	97.06 151	97.12 182	91.24 145	91.30 189	95.96 189	82.02 193	98.05 233	93.48 114	90.55 244	95.47 249

test1111		93.19 139	92.82 134	94.30 197	97.58 128	84.56 294	98.21 43	89.02 361	93.53 70	94.58 115	98.21 52	72.69 298	99.05 136	93.06 124	98.48 94	99.28 58

ECVR-MVS		93.19 139	92.73 140	94.57 185	97.66 120	85.41 280	98.21 43	88.23 362	93.43 75	94.70 113	98.21 52	72.57 299	99.07 133	93.05 125	98.49 92	99.25 61

HQP-MVS		93.19 139	92.74 139	94.54 186	95.86 209	89.33 189	96.65 187	97.39 161	93.55 66	90.14 209	95.87 193	80.95 207	98.50 183	92.13 139	92.10 215	95.78 232

iter_conf05		93.18 142	92.63 143	94.83 168	96.64 169	90.69 146	97.60 100	95.53 281	92.52 108	91.58 179	96.64 151	76.35 277	98.13 215	95.43 73	91.42 227	95.68 242

CHOSEN 280x420		93.12 143	92.72 141	94.34 194	96.71 168	87.27 243	90.29 349	97.72 115	86.61 274	91.34 186	95.29 223	84.29 148	98.41 189	93.25 119	98.94 79	97.35 184

RRT_MVS		93.10 144	92.83 133	93.93 218	94.76 269	88.04 228	98.47 22	96.55 235	93.44 74	90.01 221	97.04 129	80.64 214	97.93 255	94.33 98	90.21 249	95.83 227

Effi-MVS+-dtu		93.08 145	93.21 122	92.68 268	96.02 207	83.25 309	97.14 149	96.72 220	93.85 58	91.20 196	93.44 303	83.08 167	98.30 201	91.69 152	95.73 162	96.50 205

test_djsdf		93.07 146	92.76 136	94.00 209	93.49 314	88.70 207	98.22 41	97.57 131	91.42 138	90.08 219	95.55 215	82.85 175	97.92 256	94.07 101	91.58 222	95.40 255

VDDNet		93.05 147	92.07 161	96.02 109	96.84 158	90.39 156	98.08 51	95.85 264	86.22 282	95.79 90	98.46 28	67.59 326	99.19 114	94.92 84	94.85 176	98.47 128

thisisatest0530		93.03 148	92.21 159	95.49 137	97.07 143	89.11 199	97.49 115	92.19 346	90.16 179	94.09 126	96.41 169	76.43 276	99.05 136	90.38 172	95.68 164	98.31 142

EI-MVSNet		93.03 148	92.88 131	93.48 239	95.77 214	86.98 252	96.44 201	97.12 182	90.66 165	91.30 189	97.64 99	86.56 115	98.05 233	89.91 179	90.55 244	95.41 252

CLD-MVS		92.98 150	92.53 150	94.32 195	96.12 203	89.20 195	95.28 265	97.47 144	92.66 105	89.90 223	95.62 211	80.58 215	98.40 190	92.73 131	92.40 208	95.38 257
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tttt0517		92.96 151	92.33 156	94.87 167	97.11 141	87.16 249	97.97 62	92.09 347	90.63 167	93.88 132	97.01 131	76.50 273	99.06 135	90.29 175	95.45 167	98.38 138

ACMM	89.79 8	92.96 151	92.50 152	94.35 193	96.30 192	88.71 206	97.58 102	97.36 166	91.40 140	90.53 201	96.65 150	79.77 231	98.75 160	91.24 161	91.64 220	95.59 244
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LPG-MVS_test		92.94 153	92.56 147	94.10 203	96.16 199	88.26 220	97.65 92	97.46 146	91.29 141	90.12 215	97.16 122	79.05 242	98.73 162	92.25 135	91.89 218	95.31 261

BH-untuned		92.94 153	92.62 145	93.92 219	97.22 133	86.16 271	96.40 209	96.25 249	90.06 181	89.79 227	96.17 181	83.19 163	98.35 197	87.19 240	97.27 131	97.24 186

DU-MVS		92.90 155	92.04 162	95.49 137	94.95 257	92.83 72	97.16 147	98.24 37	93.02 89	90.13 213	95.71 205	83.47 158	97.85 262	91.71 150	83.93 315	95.78 232

PatchMatch-RL		92.90 155	92.02 164	95.56 131	98.19 92	90.80 142	95.27 267	97.18 176	87.96 241	91.86 176	95.68 208	80.44 218	98.99 141	84.01 286	97.54 119	96.89 196

PMMVS		92.86 157	92.34 155	94.42 190	94.92 260	86.73 258	94.53 283	96.38 243	84.78 305	94.27 121	95.12 232	83.13 166	98.40 190	91.47 156	96.49 149	98.12 149

OpenMVS	89.19 12	92.86 157	91.68 176	96.40 85	95.34 234	92.73 75	98.27 33	98.12 56	84.86 303	85.78 305	97.75 88	78.89 249	99.74 32	87.50 234	98.65 87	96.73 200

Test_1112_low_res		92.84 159	91.84 170	95.85 115	97.04 149	89.97 165	95.53 255	96.64 228	85.38 293	89.65 232	95.18 228	85.86 127	99.10 125	87.70 225	93.58 198	98.49 125

baseline1		92.82 160	91.90 168	95.55 133	97.20 135	90.77 144	97.19 144	94.58 319	92.20 116	92.36 163	96.34 173	84.16 149	98.21 207	89.20 201	83.90 318	97.68 170

1314		92.81 161	92.03 163	95.14 150	95.33 237	89.52 180	96.04 233	97.44 155	87.72 252	86.25 302	95.33 222	83.84 152	98.79 154	89.26 197	97.05 137	97.11 189

DP-MVS		92.76 162	91.51 184	96.52 72	98.77 53	90.99 133	97.38 126	96.08 256	82.38 327	89.29 244	97.87 78	83.77 153	99.69 43	81.37 310	96.69 145	98.89 98

test_fmvs1_n		92.73 163	92.88 131	92.29 275	96.08 206	81.05 326	97.98 57	97.08 187	90.72 160	96.79 49	98.18 55	63.07 345	98.45 187	97.62 6	98.42 97	97.36 182

BH-RMVSNet		92.72 164	91.97 166	94.97 161	97.16 137	87.99 230	96.15 229	95.60 276	90.62 168	91.87 175	97.15 124	78.41 255	98.57 179	83.16 292	97.60 118	98.36 140

ACMP	89.59 10	92.62 165	92.14 160	94.05 206	96.40 187	88.20 223	97.36 127	97.25 175	91.52 133	88.30 266	96.64 151	78.46 254	98.72 165	91.86 146	91.48 225	95.23 268
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LCM-MVSNet-Re		92.50 166	92.52 151	92.44 271	96.82 162	81.89 319	96.92 163	93.71 333	92.41 111	84.30 318	94.60 254	85.08 136	97.03 315	91.51 154	97.36 126	98.40 136

TranMVSNet+NR-MVSNet		92.50 166	91.63 177	95.14 150	94.76 269	92.07 93	97.53 108	98.11 59	92.90 99	89.56 235	96.12 183	83.16 164	97.60 285	89.30 195	83.20 324	95.75 237

thres600view7		92.49 168	91.60 178	95.18 148	97.91 107	89.47 181	97.65 92	94.66 316	92.18 120	93.33 144	94.91 238	78.06 262	99.10 125	81.61 304	94.06 190	96.98 191

thres100view900		92.43 169	91.58 179	94.98 160	97.92 106	89.37 187	97.71 86	94.66 316	92.20 116	93.31 145	94.90 239	78.06 262	99.08 130	81.40 307	94.08 187	96.48 206

jajsoiax		92.42 170	91.89 169	94.03 208	93.33 320	88.50 214	97.73 81	97.53 136	92.00 125	88.85 254	96.50 165	75.62 284	98.11 221	93.88 108	91.56 223	95.48 246

thres400		92.42 170	91.52 182	95.12 152	97.85 110	89.29 191	97.41 119	94.88 311	92.19 118	93.27 147	94.46 261	78.17 258	99.08 130	81.40 307	94.08 187	96.98 191

tfpn200view9		92.38 172	91.52 182	94.95 163	97.85 110	89.29 191	97.41 119	94.88 311	92.19 118	93.27 147	94.46 261	78.17 258	99.08 130	81.40 307	94.08 187	96.48 206

test_vis1_n		92.37 173	92.26 158	92.72 265	94.75 271	82.64 311	98.02 55	96.80 217	91.18 148	97.77 27	97.93 73	58.02 352	98.29 202	97.63 5	98.21 102	97.23 187

bld_raw_dy_0_64		92.37 173	91.69 175	94.39 191	94.28 292	89.73 171	97.71 86	93.65 334	92.78 103	90.46 203	96.67 149	75.88 279	97.97 244	92.92 130	90.89 240	95.48 246

WR-MVS		92.34 175	91.53 181	94.77 176	95.13 250	90.83 141	96.40 209	97.98 89	91.88 127	89.29 244	95.54 216	82.50 183	97.80 267	89.79 183	85.27 295	95.69 241

NR-MVSNet		92.34 175	91.27 192	95.53 134	94.95 257	93.05 68	97.39 124	98.07 68	92.65 106	84.46 316	95.71 205	85.00 137	97.77 271	89.71 184	83.52 321	95.78 232

mvs_tets		92.31 177	91.76 171	93.94 216	93.41 317	88.29 218	97.63 98	97.53 136	92.04 123	88.76 257	96.45 167	74.62 288	98.09 225	93.91 106	91.48 225	95.45 251

TAPA-MVS	90.10 7	92.30 178	91.22 195	95.56 131	98.33 79	89.60 174	96.79 172	97.65 123	81.83 331	91.52 181	97.23 119	87.94 95	98.91 147	71.31 354	98.37 98	98.17 147
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thisisatest0515		92.29 179	91.30 190	95.25 146	96.60 171	88.90 203	94.36 290	92.32 345	87.92 242	93.43 142	94.57 255	77.28 269	99.00 140	89.42 192	95.86 159	97.86 161

Fast-Effi-MVS+-dtu		92.29 179	91.99 165	93.21 250	95.27 241	85.52 278	97.03 152	96.63 231	92.09 121	89.11 250	95.14 230	80.33 221	98.08 226	87.54 233	94.74 181	96.03 221

IterMVS-LS		92.29 179	91.94 167	93.34 244	96.25 193	86.97 253	96.57 199	97.05 192	90.67 163	89.50 238	94.80 245	86.59 114	97.64 280	89.91 179	86.11 285	95.40 255
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PVSNet	86.66 18	92.24 182	91.74 174	93.73 226	97.77 114	83.69 306	92.88 330	96.72 220	87.91 243	93.00 151	94.86 241	78.51 253	99.05 136	86.53 248	97.45 124	98.47 128

VPNet		92.23 183	91.31 189	94.99 158	95.56 221	90.96 135	97.22 142	97.86 104	92.96 97	90.96 197	96.62 160	75.06 286	98.20 208	91.90 143	83.65 320	95.80 230

thres200		92.23 183	91.39 185	94.75 178	97.61 124	89.03 200	96.60 195	95.09 301	92.08 122	93.28 146	94.00 284	78.39 256	99.04 139	81.26 311	94.18 186	96.19 212

anonymousdsp		92.16 185	91.55 180	93.97 212	92.58 332	89.55 177	97.51 109	97.42 159	89.42 198	88.40 263	94.84 242	80.66 213	97.88 261	91.87 145	91.28 230	94.48 304

XXY-MVS		92.16 185	91.23 194	94.95 163	94.75 271	90.94 136	97.47 116	97.43 158	89.14 205	88.90 251	96.43 168	79.71 232	98.24 204	89.56 189	87.68 270	95.67 243

BH-w/o		92.14 187	91.75 172	93.31 245	96.99 153	85.73 275	95.67 248	95.69 271	88.73 223	89.26 246	94.82 244	82.97 172	98.07 230	85.26 271	96.32 152	96.13 217

Anonymous202405211		92.07 188	90.83 208	95.76 117	98.19 92	88.75 205	97.58 102	95.00 304	86.00 285	93.64 135	97.45 109	66.24 337	99.53 78	90.68 170	92.71 203	99.01 82

FE-MVS		92.05 189	91.05 199	95.08 153	96.83 160	87.93 231	93.91 307	95.70 269	86.30 279	94.15 125	94.97 234	76.59 272	99.21 112	84.10 284	96.86 138	98.09 153

WR-MVS_H		92.00 190	91.35 186	93.95 214	95.09 252	89.47 181	98.04 54	98.68 8	91.46 136	88.34 264	94.68 250	85.86 127	97.56 287	85.77 264	84.24 312	94.82 289

Anonymous20240529		91.98 191	90.73 212	95.73 122	98.14 96	89.40 185	97.99 56	97.72 115	79.63 344	93.54 138	97.41 112	69.94 316	99.56 72	91.04 164	91.11 234	98.22 145

PatchmatchNet		91.91 192	91.35 186	93.59 234	95.38 229	84.11 299	93.15 326	95.39 284	89.54 193	92.10 171	93.68 296	82.82 176	98.13 215	84.81 275	95.32 169	98.52 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CP-MVSNet		91.89 193	91.24 193	93.82 222	95.05 253	88.57 210	97.82 73	98.19 44	91.70 130	88.21 270	95.76 203	81.96 194	97.52 293	87.86 219	84.65 304	95.37 258

SCA		91.84 194	91.18 197	93.83 221	95.59 219	84.95 290	94.72 277	95.58 278	90.82 155	92.25 166	93.69 294	75.80 281	98.10 222	86.20 254	95.98 155	98.45 130

FMVSNet3		91.78 195	90.69 214	95.03 156	96.53 179	92.27 88	97.02 154	96.93 203	89.79 189	89.35 241	94.65 252	77.01 270	97.47 296	86.12 257	88.82 259	95.35 259

AUN-MVS		91.76 196	90.75 211	94.81 171	97.00 152	88.57 210	96.65 187	96.49 238	89.63 190	92.15 168	96.12 183	78.66 251	98.50 183	90.83 165	79.18 340	97.36 182

X-MVStestdata		91.71 197	89.67 256	97.81 26	99.38 14	94.03 46	98.59 12	98.20 42	94.85 24	96.59 61	32.69 373	91.70 45	99.80 28	95.66 60	99.40 46	99.62 15

MVS		91.71 197	90.44 221	95.51 135	95.20 247	91.59 107	96.04 233	97.45 151	73.44 358	87.36 287	95.60 212	85.42 132	99.10 125	85.97 261	97.46 120	95.83 227

EPNet_dtu		91.71 197	91.28 191	92.99 256	93.76 305	83.71 305	96.69 183	95.28 291	93.15 85	87.02 294	95.95 190	83.37 161	97.38 304	79.46 322	96.84 139	97.88 160
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline2		91.63 200	90.86 204	93.94 216	94.33 288	86.32 265	95.92 240	91.64 351	89.37 199	86.94 295	94.69 249	81.62 201	98.69 167	88.64 211	94.57 183	96.81 198

test2506		91.60 201	90.78 209	94.04 207	97.66 120	83.81 302	98.27 33	75.53 376	93.43 75	95.23 104	98.21 52	67.21 329	99.07 133	93.01 128	98.49 92	99.25 61

miper_ehance_all_eth		91.59 202	91.13 198	92.97 257	95.55 222	86.57 263	94.47 284	96.88 211	87.77 249	88.88 253	94.01 283	86.22 121	97.54 289	89.49 190	86.93 277	94.79 294

v2v482		91.59 202	90.85 206	93.80 223	93.87 302	88.17 225	96.94 162	96.88 211	89.54 193	89.53 236	94.90 239	81.70 200	98.02 238	89.25 198	85.04 301	95.20 269

V42		91.58 204	90.87 203	93.73 226	94.05 297	88.50 214	97.32 131	96.97 199	88.80 221	89.71 228	94.33 267	82.54 182	98.05 233	89.01 204	85.07 299	94.64 302

PCF-MVS	89.48 11	91.56 205	89.95 244	96.36 90	96.60 171	92.52 80	92.51 335	97.26 173	79.41 345	88.90 251	96.56 162	84.04 151	99.55 74	77.01 336	97.30 130	97.01 190
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PS-CasMVS		91.55 206	90.84 207	93.69 230	94.96 256	88.28 219	97.84 72	98.24 37	91.46 136	88.04 274	95.80 198	79.67 233	97.48 295	87.02 244	84.54 309	95.31 261

miper_enhance_ethall		91.54 207	91.01 200	93.15 251	95.35 233	87.07 251	93.97 302	96.90 208	86.79 271	89.17 248	93.43 305	86.55 116	97.64 280	89.97 178	86.93 277	94.74 298

PAPM		91.52 208	90.30 227	95.20 147	95.30 240	89.83 168	93.38 322	96.85 214	86.26 281	88.59 260	95.80 198	84.88 138	98.15 213	75.67 340	95.93 157	97.63 171

ET-MVSNet_ETH3D		91.49 209	90.11 237	95.63 127	96.40 187	91.57 109	95.34 261	93.48 336	90.60 171	75.58 354	95.49 218	80.08 225	96.79 324	94.25 99	89.76 253	98.52 120

TR-MVS		91.48 210	90.59 217	94.16 201	96.40 187	87.33 241	95.67 248	95.34 290	87.68 253	91.46 183	95.52 217	76.77 271	98.35 197	82.85 296	93.61 196	96.79 199

tpmrst		91.44 211	91.32 188	91.79 289	95.15 248	79.20 345	93.42 321	95.37 286	88.55 228	93.49 140	93.67 297	82.49 184	98.27 203	90.41 171	89.34 256	97.90 158

test-LLR		91.42 212	91.19 196	92.12 279	94.59 279	80.66 328	94.29 294	92.98 339	91.11 151	90.76 199	92.37 317	79.02 244	98.07 230	88.81 207	96.74 142	97.63 171

MSDG		91.42 212	90.24 231	94.96 162	97.15 139	88.91 202	93.69 314	96.32 245	85.72 289	86.93 296	96.47 166	80.24 222	98.98 142	80.57 313	95.05 175	96.98 191

c3_l		91.38 214	90.89 202	92.88 260	95.58 220	86.30 266	94.68 278	96.84 215	88.17 236	88.83 256	94.23 275	85.65 130	97.47 296	89.36 193	84.63 305	94.89 284

GA-MVS		91.38 214	90.31 226	94.59 180	94.65 276	87.62 239	94.34 291	96.19 253	90.73 159	90.35 206	93.83 288	71.84 302	97.96 249	87.22 239	93.61 196	98.21 146

v1144		91.37 216	90.60 216	93.68 231	93.89 301	88.23 222	96.84 169	97.03 196	88.37 231	89.69 230	94.39 263	82.04 192	97.98 241	87.80 221	85.37 292	94.84 286

GBi-Net		91.35 217	90.27 229	94.59 180	96.51 180	91.18 127	97.50 110	96.93 203	88.82 218	89.35 241	94.51 256	73.87 292	97.29 308	86.12 257	88.82 259	95.31 261

test1		91.35 217	90.27 229	94.59 180	96.51 180	91.18 127	97.50 110	96.93 203	88.82 218	89.35 241	94.51 256	73.87 292	97.29 308	86.12 257	88.82 259	95.31 261

UniMVSNet_ETH3D		91.34 219	90.22 234	94.68 179	94.86 265	87.86 235	97.23 141	97.46 146	87.99 240	89.90 223	96.92 136	66.35 335	98.23 205	90.30 174	90.99 237	97.96 155

FMVSNet2		91.31 220	90.08 238	94.99 158	96.51 180	92.21 89	97.41 119	96.95 201	88.82 218	88.62 259	94.75 247	73.87 292	97.42 301	85.20 272	88.55 264	95.35 259

D2MVS		91.30 221	90.95 201	92.35 273	94.71 274	85.52 278	96.18 228	98.21 41	88.89 214	86.60 299	93.82 290	79.92 229	97.95 251	89.29 196	90.95 238	93.56 323

v8		91.29 222	90.53 220	93.57 236	94.15 293	88.12 227	97.34 128	97.06 191	88.99 209	88.32 265	94.26 274	83.08 167	98.01 239	87.62 231	83.92 317	94.57 303

CVMVSNet		91.23 223	91.75 172	89.67 322	95.77 214	74.69 355	96.44 201	94.88 311	85.81 287	92.18 167	97.64 99	79.07 241	95.58 342	88.06 216	95.86 159	98.74 108

cl22		91.21 224	90.56 219	93.14 252	96.09 205	86.80 255	94.41 288	96.58 234	87.80 247	88.58 261	93.99 285	80.85 212	97.62 283	89.87 181	86.93 277	94.99 275

PEN-MVS		91.20 225	90.44 221	93.48 239	94.49 282	87.91 234	97.76 77	98.18 46	91.29 141	87.78 279	95.74 204	80.35 220	97.33 306	85.46 268	82.96 325	95.19 270

Baseline_NR-MVSNet		91.20 225	90.62 215	92.95 258	93.83 303	88.03 229	97.01 157	95.12 300	88.42 230	89.70 229	95.13 231	83.47 158	97.44 299	89.66 187	83.24 323	93.37 327

cascas		91.20 225	90.08 238	94.58 184	94.97 255	89.16 198	93.65 316	97.59 129	79.90 343	89.40 239	92.92 309	75.36 285	98.36 196	92.14 138	94.75 180	96.23 210

CostFormer		91.18 228	90.70 213	92.62 269	94.84 266	81.76 320	94.09 300	94.43 321	84.15 311	92.72 158	93.77 292	79.43 236	98.20 208	90.70 169	92.18 213	97.90 158

tt0805		91.09 229	90.07 241	94.16 201	95.61 218	88.31 217	97.56 104	96.51 237	89.56 192	89.17 248	95.64 210	67.08 333	98.38 195	91.07 163	88.44 265	95.80 230

v1192		91.07 230	90.23 232	93.58 235	93.70 306	87.82 236	96.73 177	97.07 189	87.77 249	89.58 233	94.32 269	80.90 211	97.97 244	86.52 249	85.48 290	94.95 276

v144192		91.06 231	90.28 228	93.39 242	93.66 309	87.23 246	96.83 170	97.07 189	87.43 258	89.69 230	94.28 271	81.48 202	98.00 240	87.18 241	84.92 303	94.93 280

v10		91.04 232	90.23 232	93.49 238	94.12 294	88.16 226	97.32 131	97.08 187	88.26 234	88.29 267	94.22 277	82.17 191	97.97 244	86.45 251	84.12 313	94.33 310

eth_miper_zixun_eth		91.02 233	90.59 217	92.34 274	95.33 237	84.35 295	94.10 299	96.90 208	88.56 227	88.84 255	94.33 267	84.08 150	97.60 285	88.77 209	84.37 311	95.06 273

v148		90.99 234	90.38 223	92.81 263	93.83 303	85.80 274	96.78 174	96.68 225	89.45 197	88.75 258	93.93 287	82.96 173	97.82 266	87.83 220	83.25 322	94.80 292

LTVRE_ROB	88.41 13	90.99 234	89.92 246	94.19 199	96.18 197	89.55 177	96.31 218	97.09 186	87.88 244	85.67 306	95.91 192	78.79 250	98.57 179	81.50 305	89.98 250	94.44 307
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
DIV-MVS_self_test		90.97 236	90.33 224	92.88 260	95.36 232	86.19 270	94.46 286	96.63 231	87.82 245	88.18 271	94.23 275	82.99 170	97.53 291	87.72 222	85.57 289	94.93 280

cl____		90.96 237	90.32 225	92.89 259	95.37 231	86.21 269	94.46 286	96.64 228	87.82 245	88.15 272	94.18 278	82.98 171	97.54 289	87.70 225	85.59 288	94.92 282

pmmvs4		90.93 238	89.85 248	94.17 200	93.34 319	90.79 143	94.60 280	96.02 257	84.62 306	87.45 283	95.15 229	81.88 197	97.45 298	87.70 225	87.87 269	94.27 314

XVG-ACMP-BASELINE		90.93 238	90.21 235	93.09 253	94.31 290	85.89 273	95.33 262	97.26 173	91.06 153	89.38 240	95.44 220	68.61 321	98.60 175	89.46 191	91.05 235	94.79 294

v1921920		90.85 240	90.03 243	93.29 246	93.55 310	86.96 254	96.74 176	97.04 194	87.36 260	89.52 237	94.34 266	80.23 223	97.97 244	86.27 252	85.21 296	94.94 278

CR-MVSNet		90.82 241	89.77 252	93.95 214	94.45 284	87.19 247	90.23 350	95.68 273	86.89 269	92.40 160	92.36 320	80.91 209	97.05 314	81.09 312	93.95 191	97.60 176

v7n		90.76 242	89.86 247	93.45 241	93.54 311	87.60 240	97.70 88	97.37 164	88.85 215	87.65 281	94.08 282	81.08 206	98.10 222	84.68 277	83.79 319	94.66 301

RPSCF		90.75 243	90.86 204	90.42 315	96.84 158	76.29 353	95.61 252	96.34 244	83.89 314	91.38 184	97.87 78	76.45 274	98.78 155	87.16 242	92.23 210	96.20 211

MVP-Stereo		90.74 244	90.08 238	92.71 266	93.19 322	88.20 223	95.86 242	96.27 247	86.07 284	84.86 314	94.76 246	77.84 265	97.75 272	83.88 289	98.01 108	92.17 343
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pm-mvs1		90.72 245	89.65 258	93.96 213	94.29 291	89.63 172	97.79 76	96.82 216	89.07 206	86.12 304	95.48 219	78.61 252	97.78 269	86.97 245	81.67 329	94.46 305

v1240		90.70 246	89.85 248	93.23 248	93.51 313	86.80 255	96.61 193	97.02 197	87.16 265	89.58 233	94.31 270	79.55 235	97.98 241	85.52 267	85.44 291	94.90 283

EPMVS		90.70 246	89.81 250	93.37 243	94.73 273	84.21 297	93.67 315	88.02 363	89.50 195	92.38 162	93.49 301	77.82 266	97.78 269	86.03 260	92.68 204	98.11 152

Anonymous20231211		90.63 248	89.42 260	94.27 198	98.24 85	89.19 197	98.05 53	97.89 96	79.95 342	88.25 269	94.96 235	72.56 300	98.13 215	89.70 185	85.14 297	95.49 245

DTE-MVSNet		90.56 249	89.75 254	93.01 255	93.95 298	87.25 244	97.64 96	97.65 123	90.74 158	87.12 290	95.68 208	79.97 228	97.00 319	83.33 291	81.66 330	94.78 296

ACMH	87.59 16	90.53 250	89.42 260	93.87 220	96.21 194	87.92 232	97.24 137	96.94 202	88.45 229	83.91 326	96.27 176	71.92 301	98.62 174	84.43 281	89.43 255	95.05 274
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OurMVSNet-221017-0		90.51 251	90.19 236	91.44 298	93.41 317	81.25 323	96.98 159	96.28 246	91.68 131	86.55 300	96.30 174	74.20 291	97.98 241	88.96 205	87.40 275	95.09 271

miper_lstm_enhance		90.50 252	90.06 242	91.83 286	95.33 237	83.74 303	93.86 308	96.70 224	87.56 256	87.79 278	93.81 291	83.45 160	96.92 321	87.39 235	84.62 306	94.82 289

COLMAP_ROB	87.81 15	90.40 253	89.28 263	93.79 224	97.95 103	87.13 250	96.92 163	95.89 263	82.83 325	86.88 298	97.18 121	73.77 295	99.29 107	78.44 327	93.62 195	94.95 276
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
IterMVS-SCA-FT		90.31 254	89.81 250	91.82 287	95.52 223	84.20 298	94.30 293	96.15 254	90.61 169	87.39 286	94.27 272	75.80 281	96.44 327	87.34 236	86.88 281	94.82 289

MS-PatchMatch		90.27 255	89.77 252	91.78 290	94.33 288	84.72 293	95.55 253	96.73 219	86.17 283	86.36 301	95.28 225	71.28 306	97.80 267	84.09 285	98.14 106	92.81 332

tpm		90.25 256	89.74 255	91.76 292	93.92 299	79.73 341	93.98 301	93.54 335	88.28 233	91.99 173	93.25 306	77.51 268	97.44 299	87.30 238	87.94 268	98.12 149

AllTest		90.23 257	88.98 267	93.98 210	97.94 104	86.64 259	96.51 200	95.54 279	85.38 293	85.49 308	96.77 141	70.28 312	99.15 119	80.02 317	92.87 200	96.15 215

ACMH+	87.92 14	90.20 258	89.18 265	93.25 247	96.48 183	86.45 264	96.99 158	96.68 225	88.83 217	84.79 315	96.22 178	70.16 314	98.53 181	84.42 282	88.04 267	94.77 297

test-mter		90.19 259	89.54 259	92.12 279	94.59 279	80.66 328	94.29 294	92.98 339	87.68 253	90.76 199	92.37 317	67.67 325	98.07 230	88.81 207	96.74 142	97.63 171

IterMVS		90.15 260	89.67 256	91.61 294	95.48 225	83.72 304	94.33 292	96.12 255	89.99 182	87.31 289	94.15 280	75.78 283	96.27 330	86.97 245	86.89 280	94.83 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TESTMET0.1,1		90.06 261	89.42 260	91.97 282	94.41 286	80.62 330	94.29 294	91.97 349	87.28 263	90.44 204	92.47 316	68.79 320	97.67 277	88.50 213	96.60 147	97.61 175

tpm2		89.96 262	89.21 264	92.23 278	94.91 262	81.25 323	93.78 310	94.42 322	80.62 340	91.56 180	93.44 303	76.44 275	97.94 252	85.60 266	92.08 217	97.49 180

IB-MVS	87.33 17	89.91 263	88.28 276	94.79 175	95.26 244	87.70 238	95.12 273	93.95 331	89.35 200	87.03 293	92.49 315	70.74 310	99.19 114	89.18 202	81.37 331	97.49 180
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
ADS-MVSNet		89.89 264	88.68 271	93.53 237	95.86 209	84.89 291	90.93 345	95.07 302	83.23 323	91.28 193	91.81 327	79.01 246	97.85 262	79.52 319	91.39 228	97.84 162

FMVSNet1		89.88 265	88.31 275	94.59 180	95.41 227	91.18 127	97.50 110	96.93 203	86.62 273	87.41 285	94.51 256	65.94 339	97.29 308	83.04 294	87.43 273	95.31 261

pmmvs5		89.86 266	88.87 269	92.82 262	92.86 326	86.23 268	96.26 221	95.39 284	84.24 310	87.12 290	94.51 256	74.27 290	97.36 305	87.61 232	87.57 271	94.86 285

tpmvs		89.83 267	89.15 266	91.89 284	94.92 260	80.30 335	93.11 327	95.46 283	86.28 280	88.08 273	92.65 311	80.44 218	98.52 182	81.47 306	89.92 251	96.84 197

test_fmvs2		89.77 268	89.93 245	89.31 325	93.68 308	76.37 352	97.64 96	95.90 261	89.84 187	91.49 182	96.26 177	58.77 351	97.10 312	94.65 93	91.13 233	94.46 305

tfpnnormal		89.70 269	88.40 274	93.60 233	95.15 248	90.10 158	97.56 104	98.16 50	87.28 263	86.16 303	94.63 253	77.57 267	98.05 233	74.48 342	84.59 307	92.65 335

ADS-MVSNet2		89.45 270	88.59 272	92.03 281	95.86 209	82.26 317	90.93 345	94.32 326	83.23 323	91.28 193	91.81 327	79.01 246	95.99 332	79.52 319	91.39 228	97.84 162

Patchmatch-test		89.42 271	87.99 278	93.70 229	95.27 241	85.11 286	88.98 356	94.37 324	81.11 334	87.10 292	93.69 294	82.28 188	97.50 294	74.37 344	94.76 179	98.48 127

test0.0.03 1		89.37 272	88.70 270	91.41 299	92.47 334	85.63 276	95.22 270	92.70 342	91.11 151	86.91 297	93.65 298	79.02 244	93.19 359	78.00 329	89.18 257	95.41 252

SixPastTwentyTwo		89.15 273	88.54 273	90.98 305	93.49 314	80.28 336	96.70 181	94.70 315	90.78 156	84.15 321	95.57 213	71.78 303	97.71 275	84.63 278	85.07 299	94.94 278

RPMNet		88.98 274	87.05 289	94.77 176	94.45 284	87.19 247	90.23 350	98.03 80	77.87 352	92.40 160	87.55 355	80.17 224	99.51 83	68.84 359	93.95 191	97.60 176

TransMVSNet (Re)		88.94 275	87.56 282	93.08 254	94.35 287	88.45 216	97.73 81	95.23 295	87.47 257	84.26 319	95.29 223	79.86 230	97.33 306	79.44 323	74.44 352	93.45 326

USDC		88.94 275	87.83 280	92.27 276	94.66 275	84.96 289	93.86 308	95.90 261	87.34 261	83.40 328	95.56 214	67.43 327	98.19 210	82.64 300	89.67 254	93.66 322

dp		88.90 277	88.26 277	90.81 308	94.58 281	76.62 351	92.85 331	94.93 308	85.12 299	90.07 220	93.07 307	75.81 280	98.12 220	80.53 314	87.42 274	97.71 168

PatchT		88.87 278	87.42 283	93.22 249	94.08 296	85.10 287	89.51 354	94.64 318	81.92 330	92.36 163	88.15 351	80.05 226	97.01 318	72.43 350	93.65 194	97.54 179

MVS_0304		88.79 279	87.57 281	92.46 270	94.65 276	86.15 272	96.40 209	97.17 178	86.44 276	88.02 275	91.71 329	56.68 355	97.03 315	84.47 280	92.58 206	94.19 315

our_test_3		88.78 280	87.98 279	91.20 303	92.45 335	82.53 313	93.61 318	95.69 271	85.77 288	84.88 313	93.71 293	79.99 227	96.78 325	79.47 321	86.24 282	94.28 313

EU-MVSNet		88.72 281	88.90 268	88.20 329	93.15 323	74.21 356	96.63 192	94.22 327	85.18 297	87.32 288	95.97 188	76.16 278	94.98 347	85.27 270	86.17 283	95.41 252

Patchmtry		88.64 282	87.25 285	92.78 264	94.09 295	86.64 259	89.82 353	95.68 273	80.81 338	87.63 282	92.36 320	80.91 209	97.03 315	78.86 325	85.12 298	94.67 300

MIMVSNet		88.50 283	86.76 291	93.72 228	94.84 266	87.77 237	91.39 340	94.05 328	86.41 278	87.99 276	92.59 314	63.27 344	95.82 337	77.44 330	92.84 202	97.57 178

tpm cat1		88.36 284	87.21 287	91.81 288	95.13 250	80.55 331	92.58 334	95.70 269	74.97 355	87.45 283	91.96 325	78.01 264	98.17 212	80.39 315	88.74 262	96.72 201

ppachtmachnet_test		88.35 285	87.29 284	91.53 295	92.45 335	83.57 307	93.75 311	95.97 258	84.28 309	85.32 311	94.18 278	79.00 248	96.93 320	75.71 339	84.99 302	94.10 316

JIA-IIPM		88.26 286	87.04 290	91.91 283	93.52 312	81.42 322	89.38 355	94.38 323	80.84 337	90.93 198	80.74 362	79.22 240	97.92 256	82.76 297	91.62 221	96.38 209

testgi		87.97 287	87.21 287	90.24 317	92.86 326	80.76 327	96.67 186	94.97 306	91.74 129	85.52 307	95.83 196	62.66 347	94.47 351	76.25 337	88.36 266	95.48 246

LF4IMVS		87.94 288	87.25 285	89.98 319	92.38 337	80.05 339	94.38 289	95.25 294	87.59 255	84.34 317	94.74 248	64.31 342	97.66 279	84.83 274	87.45 272	92.23 340

gg-mvs-nofinetune		87.82 289	85.61 298	94.44 188	94.46 283	89.27 194	91.21 344	84.61 371	80.88 336	89.89 225	74.98 364	71.50 304	97.53 291	85.75 265	97.21 133	96.51 204

pmmvs6		87.81 290	86.19 294	92.69 267	91.32 341	86.30 266	97.34 128	96.41 242	80.59 341	84.05 325	94.37 265	67.37 328	97.67 277	84.75 276	79.51 339	94.09 318

K. test v3		87.64 291	86.75 292	90.32 316	93.02 325	79.48 343	96.61 193	92.08 348	90.66 165	80.25 344	94.09 281	67.21 329	96.65 326	85.96 262	80.83 333	94.83 287

Patchmatch-RL test		87.38 292	86.24 293	90.81 308	88.74 357	78.40 349	88.12 360	93.17 338	87.11 266	82.17 335	89.29 345	81.95 195	95.60 341	88.64 211	77.02 345	98.41 135

FMVSNet5		87.29 293	85.79 297	91.78 290	94.80 268	87.28 242	95.49 256	95.28 291	84.09 312	83.85 327	91.82 326	62.95 346	94.17 353	78.48 326	85.34 294	93.91 320

Anonymous20231206		87.09 294	86.14 295	89.93 320	91.22 342	80.35 333	96.11 230	95.35 287	83.57 320	84.16 320	93.02 308	73.54 296	95.61 340	72.16 351	86.14 284	93.84 321

EG-PatchMatch MVS		87.02 295	85.44 299	91.76 292	92.67 330	85.00 288	96.08 232	96.45 240	83.41 322	79.52 346	93.49 301	57.10 354	97.72 274	79.34 324	90.87 241	92.56 336

TinyColmap		86.82 296	85.35 302	91.21 302	94.91 262	82.99 310	93.94 304	94.02 330	83.58 319	81.56 336	94.68 250	62.34 348	98.13 215	75.78 338	87.35 276	92.52 337

TDRefinement		86.53 297	84.76 308	91.85 285	82.23 367	84.25 296	96.38 212	95.35 287	84.97 302	84.09 323	94.94 236	65.76 340	98.34 200	84.60 279	74.52 351	92.97 329

test_0402		86.46 298	84.79 307	91.45 297	95.02 254	85.55 277	96.29 220	94.89 310	80.90 335	82.21 334	93.97 286	68.21 324	97.29 308	62.98 363	88.68 263	91.51 347

Anonymous20240521		86.42 299	85.44 299	89.34 324	90.33 346	79.79 340	96.73 177	95.92 259	83.71 318	83.25 329	91.36 332	63.92 343	96.01 331	78.39 328	85.36 293	92.22 341

DSMNet-mixed		86.34 300	86.12 296	87.00 335	89.88 350	70.43 360	94.93 274	90.08 359	77.97 351	85.42 310	92.78 310	74.44 289	93.96 354	74.43 343	95.14 171	96.62 202

CL-MVSNet_self_test		86.31 301	85.15 303	89.80 321	88.83 356	81.74 321	93.93 305	96.22 250	86.67 272	85.03 312	90.80 334	78.09 261	94.50 349	74.92 341	71.86 357	93.15 328

pmmvs-eth3d		86.22 302	84.45 309	91.53 295	88.34 358	87.25 244	94.47 284	95.01 303	83.47 321	79.51 347	89.61 343	69.75 317	95.71 338	83.13 293	76.73 348	91.64 344

test_vis1_rt		86.16 303	85.06 304	89.46 323	93.47 316	80.46 332	96.41 205	86.61 368	85.22 296	79.15 348	88.64 346	52.41 359	97.06 313	93.08 123	90.57 243	90.87 352

test20.03		86.14 304	85.40 301	88.35 327	90.12 347	80.06 338	95.90 241	95.20 296	88.59 224	81.29 337	93.62 299	71.43 305	92.65 360	71.26 355	81.17 332	92.34 339

UnsupCasMVSNet_eth		85.99 305	84.45 309	90.62 312	89.97 349	82.40 316	93.62 317	97.37 164	89.86 184	78.59 350	92.37 317	65.25 341	95.35 346	82.27 302	70.75 358	94.10 316

KD-MVS_self_test		85.95 306	84.95 305	88.96 326	89.55 353	79.11 346	95.13 272	96.42 241	85.91 286	84.07 324	90.48 335	70.03 315	94.82 348	80.04 316	72.94 355	92.94 330

YYNet1		85.87 307	84.23 311	90.78 311	92.38 337	82.46 315	93.17 324	95.14 299	82.12 329	67.69 358	92.36 320	78.16 260	95.50 344	77.31 332	79.73 337	94.39 308

MDA-MVSNet_test_wron		85.87 307	84.23 311	90.80 310	92.38 337	82.57 312	93.17 324	95.15 298	82.15 328	67.65 359	92.33 323	78.20 257	95.51 343	77.33 331	79.74 336	94.31 312

CMPMVS	62.92 21	85.62 309	84.92 306	87.74 331	89.14 354	73.12 359	94.17 297	96.80 217	73.98 356	73.65 357	94.93 237	66.36 334	97.61 284	83.95 288	91.28 230	92.48 338
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PVSNet_0	82.17 19	85.46 310	83.64 313	90.92 306	95.27 241	79.49 342	90.55 348	95.60 276	83.76 317	83.00 332	89.95 340	71.09 307	97.97 244	82.75 298	60.79 368	95.31 261

MDA-MVSNet-bldmvs		85.00 311	82.95 316	91.17 304	93.13 324	83.33 308	94.56 282	95.00 304	84.57 307	65.13 363	92.65 311	70.45 311	95.85 335	73.57 347	77.49 344	94.33 310

MIMVSNet1		84.93 312	83.05 314	90.56 313	89.56 352	84.84 292	95.40 259	95.35 287	83.91 313	80.38 342	92.21 324	57.23 353	93.34 358	70.69 357	82.75 328	93.50 324

KD-MVS_2432*1600		84.81 313	82.64 317	91.31 300	91.07 343	85.34 284	91.22 342	95.75 267	85.56 291	83.09 330	90.21 338	67.21 329	95.89 333	77.18 334	62.48 366	92.69 333

miper_refine_blended		84.81 313	82.64 317	91.31 300	91.07 343	85.34 284	91.22 342	95.75 267	85.56 291	83.09 330	90.21 338	67.21 329	95.89 333	77.18 334	62.48 366	92.69 333

OpenMVS_ROB	81.14 20	84.42 315	82.28 320	90.83 307	90.06 348	84.05 301	95.73 247	94.04 329	73.89 357	80.17 345	91.53 331	59.15 350	97.64 280	66.92 361	89.05 258	90.80 353

mvsany_test3		83.59 316	82.44 319	87.03 334	83.80 363	73.82 357	93.70 312	90.92 357	86.42 277	82.51 333	90.26 337	46.76 362	95.71 338	90.82 166	76.76 347	91.57 346

PM-MVS		83.48 317	81.86 322	88.31 328	87.83 360	77.59 350	93.43 320	91.75 350	86.91 268	80.63 340	89.91 341	44.42 363	95.84 336	85.17 273	76.73 348	91.50 348

test_fmvs3		83.21 318	83.02 315	83.78 340	86.77 362	68.34 365	96.76 175	94.91 309	86.49 275	84.14 322	89.48 344	36.04 367	91.73 362	91.86 146	80.77 334	91.26 351

new-patchmatchnet		83.18 319	81.87 321	87.11 333	86.88 361	75.99 354	93.70 312	95.18 297	85.02 301	77.30 352	88.40 348	65.99 338	93.88 355	74.19 346	70.18 359	91.47 349

new_pmnet		82.89 320	81.12 324	88.18 330	89.63 351	80.18 337	91.77 339	92.57 343	76.79 354	75.56 355	88.23 350	61.22 349	94.48 350	71.43 353	82.92 326	89.87 356

MVS-HIRNet		82.47 321	81.21 323	86.26 337	95.38 229	69.21 363	88.96 357	89.49 360	66.28 361	80.79 339	74.08 366	68.48 322	97.39 303	71.93 352	95.47 166	92.18 342

UnsupCasMVSNet_bld		82.13 322	79.46 326	90.14 318	88.00 359	82.47 314	90.89 347	96.62 233	78.94 347	75.61 353	84.40 360	56.63 356	96.31 329	77.30 333	66.77 364	91.63 345

test_f		80.57 323	79.62 325	83.41 341	83.38 365	67.80 367	93.57 319	93.72 332	80.80 339	77.91 351	87.63 354	33.40 368	92.08 361	87.14 243	79.04 342	90.34 355

pmmvs3		79.97 324	77.50 329	87.39 332	82.80 366	79.38 344	92.70 333	90.75 358	70.69 359	78.66 349	87.47 356	51.34 360	93.40 357	73.39 348	69.65 360	89.38 357

APD_test1		79.31 325	77.70 328	84.14 339	89.11 355	69.07 364	92.36 338	91.50 352	69.07 360	73.87 356	92.63 313	39.93 365	94.32 352	70.54 358	80.25 335	89.02 358

N_pmnet		78.73 326	78.71 327	78.79 345	92.80 328	46.50 378	94.14 298	43.71 381	78.61 348	80.83 338	91.66 330	74.94 287	96.36 328	67.24 360	84.45 310	93.50 324

test_vis3_rt		72.73 327	70.55 330	79.27 344	80.02 368	68.13 366	93.92 306	74.30 378	76.90 353	58.99 367	73.58 367	20.29 376	95.37 345	84.16 283	72.80 356	74.31 366

LCM-MVSNet		72.55 328	69.39 332	82.03 342	70.81 377	65.42 370	90.12 352	94.36 325	55.02 367	65.88 361	81.72 361	24.16 375	89.96 363	74.32 345	68.10 363	90.71 354

FPMVS		71.27 329	69.85 331	75.50 349	74.64 372	59.03 374	91.30 341	91.50 352	58.80 364	57.92 368	88.28 349	29.98 371	85.53 369	53.43 368	82.84 327	81.95 362

PMMVS2		70.19 330	66.92 333	80.01 343	76.35 371	65.67 369	86.22 361	87.58 365	64.83 363	62.38 364	80.29 363	26.78 373	88.49 367	63.79 362	54.07 369	85.88 359

testf1		69.31 331	66.76 334	76.94 347	78.61 369	61.93 372	88.27 358	86.11 369	55.62 365	59.69 365	85.31 358	20.19 377	89.32 364	57.62 365	69.44 361	79.58 363

APD_test2		69.31 331	66.76 334	76.94 347	78.61 369	61.93 372	88.27 358	86.11 369	55.62 365	59.69 365	85.31 358	20.19 377	89.32 364	57.62 365	69.44 361	79.58 363

EGC-MVSNET		68.77 333	63.01 338	86.07 338	92.49 333	82.24 318	93.96 303	90.96 356	0.71 378	2.62 379	90.89 333	53.66 357	93.46 356	57.25 367	84.55 308	82.51 361

Gipuma		67.86 334	65.41 336	75.18 350	92.66 331	73.45 358	66.50 369	94.52 320	53.33 368	57.80 369	66.07 369	30.81 369	89.20 366	48.15 370	78.88 343	62.90 369
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		66.11 335	64.89 337	69.79 352	72.62 375	35.23 382	65.19 370	92.83 341	20.35 373	65.20 362	88.08 352	43.14 364	82.70 370	73.12 349	63.46 365	91.45 350

ANet_high		63.94 336	59.58 339	77.02 346	61.24 379	66.06 368	85.66 363	87.93 364	78.53 349	42.94 371	71.04 368	25.42 374	80.71 371	52.60 369	30.83 372	84.28 360

PMVS	53.92 22	58.58 337	55.40 340	68.12 353	51.00 380	48.64 376	78.86 366	87.10 367	46.77 369	35.84 375	74.28 365	8.76 379	86.34 368	42.07 371	73.91 353	69.38 367
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		53.28 338	52.56 342	55.43 355	74.43 373	47.13 377	83.63 365	76.30 375	42.23 370	42.59 372	62.22 371	28.57 372	74.40 373	31.53 373	31.51 371	44.78 370

MVE	50.73 23	53.25 339	48.81 344	66.58 354	65.34 378	57.50 375	72.49 368	70.94 379	40.15 372	39.28 374	63.51 370	6.89 381	73.48 375	38.29 372	42.38 370	68.76 368
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		52.08 340	51.31 343	54.39 356	72.62 375	45.39 379	83.84 364	75.51 377	41.13 371	40.77 373	59.65 372	30.08 370	73.60 374	28.31 374	29.90 373	44.18 371

tmp_tt		51.94 341	53.82 341	46.29 357	33.73 381	45.30 380	78.32 367	67.24 380	18.02 374	50.93 370	87.05 357	52.99 358	53.11 376	70.76 356	25.29 374	40.46 372

wuyk23d		25.11 342	24.57 346	26.74 358	73.98 374	39.89 381	57.88 371	9.80 382	12.27 375	10.39 376	6.97 378	7.03 380	36.44 377	25.43 375	17.39 375	3.89 375

cdsmvs_eth3d_5k		23.24 343	30.99 345	0.00 361	0.00 384	0.00 385	0.00 372	97.63 125	0.00 379	0.00 380	96.88 138	84.38 145	0.00 380	0.00 378	0.00 378	0.00 376

testmvs		13.36 344	16.33 347	4.48 360	5.04 382	2.26 384	93.18 323	3.28 383	2.70 376	8.24 377	21.66 374	2.29 383	2.19 378	7.58 376	2.96 376	9.00 374

test123		13.04 345	15.66 348	5.18 359	4.51 383	3.45 383	92.50 336	1.81 384	2.50 377	7.58 378	20.15 375	3.67 382	2.18 379	7.13 377	1.07 377	9.90 373

ab-mvs-re		8.06 346	10.74 349	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	96.69 147	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

pcd_1.5k_mvsjas		7.39 347	9.85 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	88.65 87	0.00 380	0.00 378	0.00 378	0.00 376

test_blank		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet_test		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

DCPMVS		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

sosnet-low-res		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

sosnet		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uncertanet		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

Regformer		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

FOURS1					99.55 1	93.34 62	99.29 1	98.35 20	94.98 21	98.49 15

MSC_two_6792asdad				98.86 1	98.67 58	96.94 1		97.93 94					99.86 8	97.68 2	99.67 6	99.77 1

PC_three_1452									90.77 157	98.89 8	98.28 50	96.24 1	98.35 197	95.76 58	99.58 21	99.59 19

No_MVS				98.86 1	98.67 58	96.94 1		97.93 94					99.86 8	97.68 2	99.67 6	99.77 1

test_one_0601					99.32 22	95.20 20		98.25 35	95.13 16	98.48 16	98.87 6	95.16 7

eth-test2					0.00 384

eth-test					0.00 384

ZD-MVS					99.05 39	94.59 28		98.08 63	89.22 203	97.03 44	98.10 58	92.52 33	99.65 49	94.58 95	99.31 55

RE-MVS-def			96.72 32		99.02 42	92.34 84	97.98 57	98.03 80	93.52 71	97.43 32	98.51 23	90.71 66		96.05 46	99.26 59	99.43 45

IU-MVS					99.42 7	95.39 11		97.94 93	90.40 176	98.94 5				97.41 15	99.66 10	99.74 7

OPU-MVS				98.55 3	98.82 52	96.86 3	98.25 36				98.26 51	96.04 2	99.24 110	95.36 74	99.59 17	99.56 25

test_241102_TWO								98.27 30	95.13 16	98.93 6	98.89 4	94.99 11	99.85 16	97.52 8	99.65 12	99.74 7

test_241102_ONE					99.42 7	95.30 17		98.27 30	95.09 19	99.19 1	98.81 10	95.54 5	99.65 49

9.14			96.75 31		98.93 47		97.73 81	98.23 40	91.28 144	97.88 25	98.44 30	93.00 24	99.65 49	95.76 58	99.47 38

save fliter					98.91 49	94.28 34	97.02 154	98.02 83	95.35 9

test_0728_THIRD									94.78 31	98.73 10	98.87 6	95.87 4	99.84 21	97.45 12	99.72 2	99.77 1

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 27					99.86 8	97.52 8	99.67 6	99.75 5

test0726					99.45 3	95.36 13	98.31 29	98.29 25	94.92 22	98.99 4	98.92 2	95.08 8

GSMVS																98.45 130

test_part2					99.28 25	95.74 8				98.10 20

sam_mvs1												82.76 177				98.45 130

sam_mvs												81.94 196

ambc				86.56 336	83.60 364	70.00 362	85.69 362	94.97 306		80.60 341	88.45 347	37.42 366	96.84 323	82.69 299	75.44 350	92.86 331

MTGPA								98.08 63

test_post1							92.81 332				16.58 377	80.53 216	97.68 276	86.20 254

test_post											17.58 376	81.76 198	98.08 226

patchmatchnet-post											90.45 336	82.65 181	98.10 222

GG-mvs-BLEND				93.62 232	93.69 307	89.20 195	92.39 337	83.33 372		87.98 277	89.84 342	71.00 308	96.87 322	82.08 303	95.40 168	94.80 292

MTMP							97.86 68	82.03 373

gm-plane-assit					93.22 321	78.89 348			84.82 304		93.52 300		98.64 171	87.72 222

test9_res														94.81 88	99.38 49	99.45 41

TEST9					98.70 56	94.19 38	96.41 205	98.02 83	88.17 236	96.03 80	97.56 106	92.74 28	99.59 61

test_8					98.67 58	94.06 45	96.37 213	98.01 86	88.58 225	95.98 84	97.55 108	92.73 29	99.58 64

agg_prior2														93.94 105	99.38 49	99.50 36

agg_prior					98.67 58	93.79 50		98.00 87		95.68 94			99.57 71

TestCases				93.98 210	97.94 104	86.64 259		95.54 279	85.38 293	85.49 308	96.77 141	70.28 312	99.15 119	80.02 317	92.87 200	96.15 215

test_prior4						93.66 53	96.42 204

test_prior2							96.35 214		92.80 102	96.03 80	97.59 103	92.01 40		95.01 82	99.38 49

test_prior				97.23 53	98.67 58	92.99 69		98.00 87					99.41 96			99.29 56

旧先验2							95.94 239		81.66 332	97.34 35			98.82 152	92.26 133

新几何2							95.79 245

新几何1				97.32 48	98.60 65	93.59 54		97.75 110	81.58 333	95.75 91	97.85 81	90.04 73	99.67 47	86.50 250	99.13 71	98.69 112

旧先验1					98.38 77	93.38 59		97.75 110			98.09 60	92.30 38			99.01 76	99.16 66

无先验							95.79 245	97.87 100	83.87 316				99.65 49	87.68 228		98.89 98

原ACMM2							95.67 248

原ACMM1				96.38 88	98.59 66	91.09 132		97.89 96	87.41 259	95.22 105	97.68 92	90.25 70	99.54 76	87.95 218	99.12 72	98.49 125

test222					98.24 85	92.21 89	95.33 262	97.60 127	79.22 346	95.25 103	97.84 83	88.80 85			99.15 69	98.72 109

testdata2													99.67 47	85.96 262

segment_acmp												92.89 25

testdata				95.46 141	98.18 94	88.90 203		97.66 121	82.73 326	97.03 44	98.07 61	90.06 72	98.85 150	89.67 186	98.98 77	98.64 115

testdata1							95.26 269		93.10 88

test12				97.65 39	98.46 70	94.26 35		97.66 121		95.52 101		90.89 63	99.46 90		99.25 61	99.22 63

plane_prior7					96.21 194	89.98 164

plane_prior6					96.10 204	90.00 160						81.32 204

plane_prior5								97.51 138					98.60 175	93.02 126	92.23 210	95.86 223

plane_prior4											96.64 151

plane_prior3						90.00 160			94.46 41	91.34 186

plane_prior2							97.74 79		94.85 24

plane_prior1					96.14 202

plane_prior						89.99 162	97.24 137		94.06 51						92.16 214

n2								0.00 385

nn								0.00 385

door-mid								91.06 355

lessismore_v0				90.45 314	91.96 340	79.09 347		87.19 366		80.32 343	94.39 263	66.31 336	97.55 288	84.00 287	76.84 346	94.70 299

LGP-MVS_train				94.10 203	96.16 199	88.26 220		97.46 146	91.29 141	90.12 215	97.16 122	79.05 242	98.73 162	92.25 135	91.89 218	95.31 261

test11								97.88 98

door								91.13 354

HQP5-MVS						89.33 189

HQP-NCC					95.86 209		96.65 187		93.55 66	90.14 209

ACMP_Plane					95.86 209		96.65 187		93.55 66	90.14 209

BP-MVS														92.13 139

HQP4-MVS										90.14 209			98.50 183			95.78 232

HQP3-MVS								97.39 161							92.10 215

HQP2-MVS												80.95 207

NP-MVS					95.99 208	89.81 169					95.87 193

MDTV_nov1_ep13_2view						70.35 361	93.10 328		83.88 315	93.55 137		82.47 185		86.25 253		98.38 138

MDTV_nov1_ep13			90.76 210		95.22 245	80.33 334	93.03 329	95.28 291	88.14 238	92.84 157	93.83 288	81.34 203	98.08 226	82.86 295	94.34 185

ACMMP++_ref															90.30 248

ACMMP++															91.02 236

Test By Simon												88.73 86

ITE_SJBPF				92.43 272	95.34 234	85.37 283		95.92 259	91.47 135	87.75 280	96.39 171	71.00 308	97.96 249	82.36 301	89.86 252	93.97 319

DeepMVS_CX				74.68 351	90.84 345	64.34 371		81.61 374	65.34 362	67.47 360	88.01 353	48.60 361	80.13 372	62.33 364	73.68 354	79.58 363

High-resolution multi-view benchmark