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 10	98.67 66	95.39 12	99.29 1	98.28 51	94.78 60	98.93 19	98.87 30	96.04 2	99.86 9	97.45 45	99.58 23	99.59 31

SED-MVS		98.05 2	97.99 1	98.24 11	99.42 9	95.30 18	98.25 39	98.27 54	95.13 39	99.19 12	98.89 27	95.54 5	99.85 20	97.52 41	99.66 10	99.56 39

TestfortrainingZip a		97.92 3	97.70 9	98.58 3	99.56 1	96.08 5	98.69 11	98.70 16	93.45 116	98.73 29	98.53 50	95.46 7	99.86 9	96.63 67	99.58 23	99.80 1

DVP-MVS		97.91 4	97.81 4	98.22 14	99.45 5	95.36 14	98.21 46	97.85 135	94.92 49	98.73 29	98.87 30	95.08 9	99.84 25	97.52 41	99.67 6	99.48 55
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 5	97.65 10	98.47 6	99.17 37	95.78 8	97.21 191	98.35 41	95.16 37	98.71 33	98.80 37	95.05 11	99.89 3	96.70 66	99.73 1	99.73 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		97.82 6	97.73 8	98.08 19	99.15 38	94.82 29	98.81 8	98.30 47	94.76 63	98.30 41	98.90 24	93.77 18	99.68 73	97.93 28	99.69 3	99.75 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CNVR-MVS		97.68 7	97.44 22	98.37 8	98.90 58	95.86 7	97.27 182	98.08 92	95.81 19	97.87 56	98.31 79	94.26 14	99.68 73	97.02 55	99.49 42	99.57 35

fmvsm_l_conf0.5_n		97.65 8	97.75 7	97.34 60	98.21 104	92.75 91	97.83 96	98.73 10	95.04 44	99.30 6	98.84 35	93.34 23	99.78 47	99.32 7	99.13 96	99.50 51

fmvsm_l_conf0.5_n_3		97.64 9	97.60 12	97.79 33	98.14 111	93.94 55	97.93 81	98.65 23	96.70 7	99.38 4	99.07 10	89.92 90	99.81 34	99.16 13	99.43 52	99.61 29

fmvsm_l_conf0.5_n_a		97.63 10	97.76 6	97.26 67	98.25 97	92.59 99	97.81 101	98.68 18	94.93 47	99.24 9	98.87 30	93.52 21	99.79 44	99.32 7	99.21 81	99.40 65

SteuartSystems-ACMMP		97.62 11	97.53 16	97.87 27	98.39 86	94.25 43	98.43 26	98.27 54	95.34 31	98.11 45	98.56 46	94.53 13	99.71 65	96.57 71	99.62 17	99.65 20
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_l_conf0.5_n_9		97.59 12	97.79 5	96.97 85	98.28 92	91.49 143	97.61 136	98.71 13	97.10 4	99.70 1	98.93 21	90.95 75	99.77 50	99.35 6	99.53 32	99.65 20

MSP-MVS		97.59 12	97.54 15	97.73 41	99.40 13	93.77 60	98.53 18	98.29 49	95.55 26	98.56 36	97.81 127	93.90 16	99.65 77	96.62 68	99.21 81	99.77 3
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
lecture		97.58 14	97.63 11	97.43 57	99.37 18	92.93 85	98.86 7	98.85 5	95.27 33	98.65 34	98.90 24	91.97 51	99.80 39	97.63 37	99.21 81	99.57 35

test_fmvsm_n_1920		97.55 15	97.89 3	96.53 104	98.41 83	91.73 129	98.01 64	99.02 1	96.37 12	99.30 6	98.92 22	92.39 43	99.79 44	99.16 13	99.46 45	98.08 218

ME-MVS		97.54 16	97.39 25	98.00 23	99.21 35	94.50 35	97.75 108	98.34 43	94.23 86	98.15 44	98.53 50	93.32 26	99.84 25	97.40 49	99.58 23	99.65 20

reproduce-ours		97.53 17	97.51 18	97.60 50	98.97 52	93.31 72	97.71 118	98.20 68	95.80 20	97.88 53	98.98 17	92.91 29	99.81 34	97.68 32	99.43 52	99.67 15

our_new_method		97.53 17	97.51 18	97.60 50	98.97 52	93.31 72	97.71 118	98.20 68	95.80 20	97.88 53	98.98 17	92.91 29	99.81 34	97.68 32	99.43 52	99.67 15

reproduce_model		97.51 19	97.51 18	97.50 53	98.99 51	93.01 81	97.79 104	98.21 66	95.73 23	97.99 49	99.03 14	92.63 38	99.82 32	97.80 30	99.42 55	99.67 15

test_fmvsmconf_n		97.49 20	97.56 14	97.29 63	97.44 163	92.37 106	97.91 83	98.88 4	95.83 18	98.92 22	99.05 13	91.45 60	99.80 39	99.12 15	99.46 45	99.69 14

TSAR-MVS + MP.		97.42 21	97.33 27	97.69 45	99.25 31	94.24 44	98.07 59	97.85 135	93.72 101	98.57 35	98.35 70	93.69 19	99.40 131	97.06 54	99.46 45	99.44 60
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 22	97.53 16	97.06 81	98.57 77	94.46 37	97.92 82	98.14 82	94.82 56	99.01 16	98.55 48	94.18 15	97.41 381	96.94 56	99.64 14	99.32 73
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 23	97.13 29	98.17 16	99.02 47	95.28 20	98.23 43	98.27 54	92.37 164	98.27 42	98.65 44	93.33 24	99.72 63	96.49 73	99.52 34	99.51 48

SMA-MVS		97.35 24	97.03 38	98.30 9	99.06 43	95.42 11	97.94 79	98.18 75	90.57 246	98.85 26	98.94 20	93.33 24	99.83 30	96.72 64	99.68 4	99.63 25
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 25	96.97 41	98.47 6	99.08 41	96.16 4	97.55 147	97.97 119	95.59 24	96.61 95	97.89 114	92.57 40	99.84 25	95.95 97	99.51 37	99.40 65

fmvsm_s_conf0.5_n_9		97.33 26	97.57 13	96.62 100	98.43 81	90.32 199	97.80 102	98.53 29	97.24 3	99.62 2	99.14 1	88.65 107	99.80 39	99.54 1	99.15 93	99.74 9

fmvsm_s_conf0.5_n_8		97.32 27	97.48 21	96.85 87	98.28 92	91.07 167	97.76 106	98.62 25	97.53 2	99.20 11	99.12 4	88.24 115	99.81 34	99.41 3	99.17 89	99.67 15

NCCC		97.30 28	97.03 38	98.11 18	98.77 61	95.06 26	97.34 175	98.04 107	95.96 14	97.09 77	97.88 117	93.18 27	99.71 65	95.84 102	99.17 89	99.56 39

fmvsm_s_conf0.5_n_10		97.29 29	97.40 24	96.97 85	98.24 98	91.96 125	97.89 86	98.72 12	96.77 6	99.46 3	99.06 11	87.78 125	99.84 25	99.40 4	99.27 73	99.12 91

MM		97.29 29	96.98 40	98.23 12	98.01 121	95.03 27	98.07 59	95.76 337	97.78 1	97.52 60	98.80 37	88.09 117	99.86 9	99.44 2	99.37 66	99.80 1

ACMMP_NAP		97.20 31	96.86 47	98.23 12	99.09 39	95.16 23	97.60 137	98.19 73	92.82 152	97.93 52	98.74 41	91.60 58	99.86 9	96.26 78	99.52 34	99.67 15

XVS		97.18 32	96.96 43	97.81 31	99.38 16	94.03 53	98.59 16	98.20 68	94.85 52	96.59 97	98.29 82	91.70 55	99.80 39	95.66 106	99.40 60	99.62 26

MCST-MVS		97.18 32	96.84 49	98.20 15	99.30 28	95.35 16	97.12 198	98.07 97	93.54 110	96.08 123	97.69 139	93.86 17	99.71 65	96.50 72	99.39 62	99.55 42

fmvsm_s_conf0.5_n_3		97.15 34	97.36 26	96.52 106	97.98 124	91.19 159	97.84 93	98.65 23	97.08 5	99.25 8	99.10 5	87.88 123	99.79 44	99.32 7	99.18 88	98.59 162

HFP-MVS		97.14 35	96.92 45	97.83 29	99.42 9	94.12 49	98.52 19	98.32 45	93.21 125	97.18 71	98.29 82	92.08 48	99.83 30	95.63 111	99.59 19	99.54 44

test_fmvsmconf0.1_n		97.09 36	97.06 33	97.19 72	95.67 297	92.21 113	97.95 78	98.27 54	95.78 22	98.40 40	99.00 15	89.99 88	99.78 47	99.06 17	99.41 58	99.59 31

fmvsm_s_conf0.5_n_6		97.08 37	97.17 28	96.81 88	97.28 168	91.73 129	97.75 108	98.50 30	94.86 51	99.22 10	98.78 39	89.75 93	99.76 52	99.10 16	99.29 71	98.94 117

MTAPA		97.08 37	96.78 57	97.97 26	99.37 18	94.42 39	97.24 184	98.08 92	95.07 43	96.11 121	98.59 45	90.88 78	99.90 2	96.18 90	99.50 39	99.58 34

region2R		97.07 39	96.84 49	97.77 37	99.46 4	93.79 58	98.52 19	98.24 62	93.19 128	97.14 74	98.34 73	91.59 59	99.87 7	95.46 117	99.59 19	99.64 24

ACMMPR		97.07 39	96.84 49	97.79 33	99.44 8	93.88 56	98.52 19	98.31 46	93.21 125	97.15 73	98.33 76	91.35 64	99.86 9	95.63 111	99.59 19	99.62 26

CP-MVS		97.02 41	96.81 54	97.64 48	99.33 25	93.54 63	98.80 9	98.28 51	92.99 138	96.45 109	98.30 81	91.90 52	99.85 20	95.61 113	99.68 4	99.54 44

SR-MVS		97.01 42	96.86 47	97.47 55	99.09 39	93.27 74	97.98 69	98.07 97	93.75 100	97.45 62	98.48 59	91.43 62	99.59 93	96.22 81	99.27 73	99.54 44

fmvsm_s_conf0.5_n_5		97.00 43	96.97 41	97.09 78	97.58 159	92.56 100	97.68 122	98.47 34	94.02 91	98.90 24	98.89 27	88.94 101	99.78 47	99.18 11	99.03 105	98.93 121

ZNCC-MVS		96.96 44	96.67 62	97.85 28	99.37 18	94.12 49	98.49 23	98.18 75	92.64 159	96.39 111	98.18 89	91.61 57	99.88 4	95.59 116	99.55 29	99.57 35

APD-MVS		96.95 45	96.60 64	98.01 21	99.03 46	94.93 28	97.72 116	98.10 90	91.50 196	98.01 48	98.32 78	92.33 44	99.58 96	94.85 131	99.51 37	99.53 47
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MSLP-MVS++		96.94 46	97.06 33	96.59 101	98.72 63	91.86 127	97.67 123	98.49 31	94.66 68	97.24 70	98.41 65	92.31 46	98.94 193	96.61 69	99.46 45	98.96 113

DeepC-MVS_fast	93.89 2	96.93 47	96.64 63	97.78 35	98.64 72	94.30 40	97.41 165	98.04 107	94.81 58	96.59 97	98.37 68	91.24 67	99.64 85	95.16 122	99.52 34	99.42 64
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SPE-MVS-test		96.89 48	97.04 37	96.45 117	98.29 91	91.66 136	99.03 4	97.85 135	95.84 17	96.90 81	97.97 107	91.24 67	98.75 221	96.92 57	99.33 68	98.94 117

SR-MVS-dyc-post		96.88 49	96.80 55	97.11 77	99.02 47	92.34 107	97.98 69	98.03 109	93.52 113	97.43 65	98.51 54	91.40 63	99.56 104	96.05 92	99.26 76	99.43 62

CS-MVS		96.86 50	97.06 33	96.26 133	98.16 110	91.16 164	99.09 3	97.87 130	95.30 32	97.06 78	98.03 99	91.72 53	98.71 231	97.10 53	99.17 89	98.90 126

mPP-MVS		96.86 50	96.60 64	97.64 48	99.40 13	93.44 65	98.50 22	98.09 91	93.27 124	95.95 129	98.33 76	91.04 72	99.88 4	95.20 120	99.57 28	99.60 30

fmvsm_s_conf0.5_n		96.85 52	97.13 29	96.04 147	98.07 118	90.28 200	97.97 75	98.76 9	94.93 47	98.84 27	99.06 11	88.80 104	99.65 77	99.06 17	98.63 121	98.18 204

GST-MVS		96.85 52	96.52 68	97.82 30	99.36 22	94.14 48	98.29 33	98.13 83	92.72 155	96.70 89	98.06 96	91.35 64	99.86 9	94.83 133	99.28 72	99.47 57

balanced_conf03		96.84 54	96.89 46	96.68 92	97.63 151	92.22 112	98.17 52	97.82 141	94.44 78	98.23 43	97.36 169	90.97 74	99.22 149	97.74 31	99.66 10	98.61 159

patch_mono-2		96.83 55	97.44 22	95.01 215	99.05 44	85.39 354	96.98 211	98.77 8	94.70 65	97.99 49	98.66 42	93.61 20	99.91 1	97.67 36	99.50 39	99.72 13

APD-MVS_3200maxsize		96.81 56	96.71 61	97.12 75	99.01 50	92.31 109	97.98 69	98.06 100	93.11 134	97.44 63	98.55 48	90.93 76	99.55 106	96.06 91	99.25 78	99.51 48

PGM-MVS		96.81 56	96.53 67	97.65 46	99.35 24	93.53 64	97.65 127	98.98 2	92.22 168	97.14 74	98.44 62	91.17 70	99.85 20	94.35 153	99.46 45	99.57 35

MP-MVS		96.77 58	96.45 75	97.72 42	99.39 15	93.80 57	98.41 27	98.06 100	93.37 120	95.54 147	98.34 73	90.59 82	99.88 4	94.83 133	99.54 31	99.49 53
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PHI-MVS		96.77 58	96.46 74	97.71 44	98.40 84	94.07 51	98.21 46	98.45 36	89.86 264	97.11 76	98.01 102	92.52 41	99.69 71	96.03 95	99.53 32	99.36 71

fmvsm_s_conf0.5_n_4		96.75 60	97.07 32	95.79 170	97.76 140	89.57 226	97.66 126	98.66 21	95.36 29	99.03 15	98.90 24	88.39 112	99.73 59	99.17 12	98.66 119	98.08 218

fmvsm_s_conf0.5_n_a		96.75 60	96.93 44	96.20 138	97.64 149	90.72 182	98.00 65	98.73 10	94.55 72	98.91 23	99.08 7	88.22 116	99.63 86	98.91 20	98.37 134	98.25 199

MGCNet		96.74 62	96.31 79	98.02 20	96.87 200	94.65 31	97.58 138	94.39 403	96.47 11	97.16 72	98.39 66	87.53 134	99.87 7	98.97 19	99.41 58	99.55 42

test_fmvsmvis_n_1920		96.70 63	96.84 49	96.31 127	96.62 225	91.73 129	97.98 69	98.30 47	96.19 13	96.10 122	98.95 19	89.42 94	99.76 52	98.90 21	99.08 100	97.43 258

MP-MVS-pluss		96.70 63	96.27 81	97.98 25	99.23 34	94.71 30	96.96 213	98.06 100	90.67 236	95.55 145	98.78 39	91.07 71	99.86 9	96.58 70	99.55 29	99.38 69
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + GP.		96.69 65	96.49 69	97.27 66	98.31 90	93.39 66	96.79 233	96.72 286	94.17 87	97.44 63	97.66 143	92.76 33	99.33 137	96.86 60	97.76 160	99.08 97

HPM-MVS		96.69 65	96.45 75	97.40 58	99.36 22	93.11 79	98.87 6	98.06 100	91.17 215	96.40 110	97.99 105	90.99 73	99.58 96	95.61 113	99.61 18	99.49 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MVS_111021_HR		96.68 67	96.58 66	96.99 83	98.46 78	92.31 109	96.20 294	98.90 3	94.30 85	95.86 132	97.74 134	92.33 44	99.38 134	96.04 94	99.42 55	99.28 76

fmvsm_s_conf0.5_n_2		96.62 68	96.82 53	96.02 149	97.98 124	90.43 192	97.50 151	98.59 26	96.59 9	99.31 5	99.08 7	84.47 194	99.75 56	99.37 5	98.45 131	97.88 231

DELS-MVS		96.61 69	96.38 78	97.30 62	97.79 138	93.19 77	95.96 308	98.18 75	95.23 34	95.87 131	97.65 144	91.45 60	99.70 70	95.87 98	99.44 51	99.00 108
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 69	97.09 31	95.15 206	98.09 114	86.63 321	96.00 306	98.15 80	95.43 27	97.95 51	98.56 46	93.40 22	99.36 135	96.77 61	99.48 43	99.45 58

fmvsm_s_conf0.1_n		96.58 71	96.77 58	96.01 152	96.67 223	90.25 201	97.91 83	98.38 37	94.48 76	98.84 27	99.14 1	88.06 118	99.62 87	98.82 22	98.60 123	98.15 208

MVSMamba_PlusPlus		96.51 72	96.48 70	96.59 101	98.07 118	91.97 123	98.14 53	97.79 143	90.43 251	97.34 68	97.52 159	91.29 66	99.19 152	98.12 27	99.64 14	98.60 160

EI-MVSNet-Vis-set		96.51 72	96.47 71	96.63 97	98.24 98	91.20 158	96.89 221	97.73 150	94.74 64	96.49 104	98.49 56	90.88 78	99.58 96	96.44 74	98.32 136	99.13 88

HPM-MVS_fast		96.51 72	96.27 81	97.22 69	99.32 26	92.74 92	98.74 10	98.06 100	90.57 246	96.77 86	98.35 70	90.21 85	99.53 110	94.80 137	99.63 16	99.38 69

fmvsm_s_conf0.5_n_7		96.45 75	96.80 55	95.37 198	97.29 167	88.38 270	97.23 188	98.47 34	95.14 38	98.43 39	99.09 6	87.58 131	99.72 63	98.80 24	99.21 81	98.02 222

EC-MVSNet		96.42 76	96.47 71	96.26 133	97.01 189	91.52 142	98.89 5	97.75 147	94.42 79	96.64 94	97.68 140	89.32 95	98.60 247	97.45 45	99.11 99	98.67 157

fmvsm_s_conf0.1_n_a		96.40 77	96.47 71	96.16 140	95.48 306	90.69 183	97.91 83	98.33 44	94.07 89	98.93 19	99.14 1	87.44 138	99.61 88	98.63 25	98.32 136	98.18 204

CANet		96.39 78	96.02 86	97.50 53	97.62 152	93.38 67	97.02 204	97.96 120	95.42 28	94.86 162	97.81 127	87.38 140	99.82 32	96.88 58	99.20 86	99.29 74

dcpmvs_2		96.37 79	97.05 36	94.31 261	98.96 54	84.11 375	97.56 142	97.51 183	93.92 95	97.43 65	98.52 53	92.75 34	99.32 139	97.32 52	99.50 39	99.51 48

NormalMVS		96.36 80	96.11 84	97.12 75	99.37 18	92.90 86	97.99 66	97.63 164	95.92 15	96.57 100	97.93 109	85.34 176	99.50 118	94.99 127	99.21 81	98.97 110

EI-MVSNet-UG-set		96.34 81	96.30 80	96.47 114	98.20 105	90.93 172	96.86 224	97.72 152	94.67 67	96.16 120	98.46 60	90.43 83	99.58 96	96.23 80	97.96 153	98.90 126

fmvsm_s_conf0.1_n_2		96.33 82	96.44 77	96.00 153	97.30 166	90.37 198	97.53 148	97.92 125	96.52 10	99.14 14	99.08 7	83.21 216	99.74 57	99.22 10	98.06 148	97.88 231

train_agg		96.30 83	95.83 91	97.72 42	98.70 64	94.19 45	96.41 270	98.02 112	88.58 310	96.03 124	97.56 156	92.73 36	99.59 93	95.04 124	99.37 66	99.39 67

ACMMP		96.27 84	95.93 87	97.28 65	99.24 32	92.62 97	98.25 39	98.81 6	92.99 138	94.56 172	98.39 66	88.96 100	99.85 20	94.57 147	97.63 161	99.36 71
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 85	96.19 83	96.39 122	98.23 103	91.35 151	96.24 292	98.79 7	93.99 93	95.80 134	97.65 144	89.92 90	99.24 147	95.87 98	99.20 86	98.58 163

test_fmvsmconf0.01_n		96.15 86	95.85 90	97.03 82	92.66 420	91.83 128	97.97 75	97.84 139	95.57 25	97.53 59	99.00 15	84.20 200	99.76 52	98.82 22	99.08 100	99.48 55

DeepC-MVS	93.07 3	96.06 87	95.66 92	97.29 63	97.96 126	93.17 78	97.30 180	98.06 100	93.92 95	93.38 212	98.66 42	86.83 147	99.73 59	95.60 115	99.22 80	98.96 113
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 88	95.91 88	96.46 116	99.24 32	90.47 189	98.30 32	98.57 28	89.01 292	93.97 193	97.57 154	92.62 39	99.76 52	94.66 141	99.27 73	99.15 86

sasdasda		96.02 89	95.45 99	97.75 39	97.59 155	95.15 24	98.28 34	97.60 169	94.52 74	96.27 115	96.12 249	87.65 128	99.18 155	96.20 86	94.82 246	98.91 123

ETV-MVS		96.02 89	95.89 89	96.40 120	97.16 174	92.44 104	97.47 160	97.77 146	94.55 72	96.48 105	94.51 331	91.23 69	98.92 196	95.65 109	98.19 142	97.82 239

canonicalmvs		96.02 89	95.45 99	97.75 39	97.59 155	95.15 24	98.28 34	97.60 169	94.52 74	96.27 115	96.12 249	87.65 128	99.18 155	96.20 86	94.82 246	98.91 123

CDPH-MVS		95.97 92	95.38 104	97.77 37	98.93 55	94.44 38	96.35 279	97.88 128	86.98 356	96.65 93	97.89 114	91.99 50	99.47 123	92.26 193	99.46 45	99.39 67

UA-Net		95.95 93	95.53 95	97.20 71	97.67 145	92.98 83	97.65 127	98.13 83	94.81 58	96.61 95	98.35 70	88.87 102	99.51 115	90.36 245	97.35 172	99.11 93

SymmetryMVS		95.94 94	95.54 94	97.15 73	97.85 134	92.90 86	97.99 66	96.91 273	95.92 15	96.57 100	97.93 109	85.34 176	99.50 118	94.99 127	96.39 211	99.05 101

MGCFI-Net		95.94 94	95.40 103	97.56 52	97.59 155	94.62 32	98.21 46	97.57 174	94.41 80	96.17 119	96.16 247	87.54 133	99.17 157	96.19 88	94.73 251	98.91 123

BP-MVS1		95.89 96	95.49 96	97.08 80	96.67 223	93.20 76	98.08 57	96.32 311	94.56 71	96.32 112	97.84 123	84.07 203	99.15 161	96.75 62	98.78 114	98.90 126

VNet		95.89 96	95.45 99	97.21 70	98.07 118	92.94 84	97.50 151	98.15 80	93.87 97	97.52 60	97.61 150	85.29 178	99.53 110	95.81 103	95.27 237	99.16 84

alignmvs		95.87 98	95.23 109	97.78 35	97.56 161	95.19 22	97.86 89	97.17 238	94.39 82	96.47 106	96.40 234	85.89 163	99.20 151	96.21 85	95.11 242	98.95 116

casdiffmvs_mvg		95.81 99	95.57 93	96.51 110	96.87 200	91.49 143	97.50 151	97.56 178	93.99 93	95.13 157	97.92 112	87.89 122	98.78 213	95.97 96	97.33 173	99.26 78
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		95.69 100	94.92 119	98.01 21	98.08 117	95.71 10	95.27 349	97.62 168	90.43 251	95.55 145	97.07 189	91.72 53	99.50 118	89.62 261	98.94 109	98.82 141

DP-MVS Recon		95.68 101	95.12 114	97.37 59	99.19 36	94.19 45	97.03 202	98.08 92	88.35 319	95.09 158	97.65 144	89.97 89	99.48 122	92.08 204	98.59 124	98.44 181

casdiffmvs		95.64 102	95.49 96	96.08 143	96.76 220	90.45 190	97.29 181	97.44 203	94.00 92	95.46 150	97.98 106	87.52 136	98.73 225	95.64 110	97.33 173	99.08 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GDP-MVS		95.62 103	95.13 112	97.09 78	96.79 211	93.26 75	97.89 86	97.83 140	93.58 105	96.80 83	97.82 125	83.06 223	99.16 159	94.40 150	97.95 154	98.87 135

MG-MVS		95.61 104	95.38 104	96.31 127	98.42 82	90.53 187	96.04 303	97.48 188	93.47 115	95.67 142	98.10 92	89.17 97	99.25 146	91.27 222	98.77 115	99.13 88

baseline		95.58 105	95.42 102	96.08 143	96.78 215	90.41 193	97.16 195	97.45 199	93.69 104	95.65 143	97.85 121	87.29 141	98.68 235	95.66 106	97.25 179	99.13 88

CPTT-MVS		95.57 106	95.19 110	96.70 91	99.27 30	91.48 145	98.33 30	98.11 88	87.79 337	95.17 156	98.03 99	87.09 145	99.61 88	93.51 171	99.42 55	99.02 102

EIA-MVS		95.53 107	95.47 98	95.71 178	97.06 182	89.63 222	97.82 98	97.87 130	93.57 106	93.92 194	95.04 303	90.61 81	98.95 191	94.62 143	98.68 118	98.54 166

3Dnovator+	91.43 4	95.40 108	94.48 140	98.16 17	96.90 198	95.34 17	98.48 24	97.87 130	94.65 69	88.53 342	98.02 101	83.69 207	99.71 65	93.18 179	98.96 108	99.44 60

PS-MVSNAJ		95.37 109	95.33 106	95.49 192	97.35 165	90.66 185	95.31 346	97.48 188	93.85 98	96.51 103	95.70 274	88.65 107	99.65 77	94.80 137	98.27 139	96.17 297

MVSFormer		95.37 109	95.16 111	95.99 154	96.34 257	91.21 156	98.22 44	97.57 174	91.42 200	96.22 117	97.32 170	86.20 159	97.92 331	94.07 156	99.05 102	98.85 137

diffmvs_AUTHOR		95.33 111	95.27 108	95.50 191	96.37 255	89.08 252	96.08 301	97.38 214	93.09 136	96.53 102	97.74 134	86.45 153	98.68 235	96.32 76	97.48 164	98.75 148

xiu_mvs_v2_base		95.32 112	95.29 107	95.40 197	97.22 170	90.50 188	95.44 339	97.44 203	93.70 103	96.46 107	96.18 244	88.59 111	99.53 110	94.79 140	97.81 157	96.17 297

PVSNet_Blended_VisFu		95.27 113	94.91 120	96.38 123	98.20 105	90.86 175	97.27 182	98.25 60	90.21 255	94.18 186	97.27 176	87.48 137	99.73 59	93.53 170	97.77 159	98.55 165

viewcassd2359sk11		95.26 114	95.09 115	95.80 168	96.95 195	89.72 220	96.80 232	97.56 178	92.21 170	95.37 151	97.80 129	87.17 144	98.77 216	94.82 135	97.10 185	98.90 126

KinetiMVS		95.26 114	94.75 126	96.79 89	96.99 191	92.05 119	97.82 98	97.78 144	94.77 62	96.46 107	97.70 137	80.62 277	99.34 136	92.37 192	98.28 138	98.97 110

diffmvs		95.25 116	95.13 112	95.63 181	96.43 250	89.34 239	95.99 307	97.35 219	92.83 151	96.31 113	97.37 168	86.44 154	98.67 238	96.26 78	97.19 182	98.87 135
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmanbaseed2359cas		95.24 117	95.02 117	95.91 157	96.87 200	89.98 210	96.82 229	97.49 186	92.26 166	95.47 149	97.82 125	86.47 152	98.69 233	94.80 137	97.20 181	99.06 100

Vis-MVSNet		95.23 118	94.81 121	96.51 110	97.18 173	91.58 140	98.26 38	98.12 85	94.38 83	94.90 161	98.15 91	82.28 244	98.92 196	91.45 219	98.58 125	99.01 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPP-MVSNet		95.22 119	95.04 116	95.76 171	97.49 162	89.56 227	98.67 14	97.00 263	90.69 234	94.24 182	97.62 149	89.79 92	98.81 209	93.39 176	96.49 208	98.92 122

EPNet		95.20 120	94.56 133	97.14 74	92.80 417	92.68 96	97.85 92	94.87 387	96.64 8	92.46 229	97.80 129	86.23 156	99.65 77	93.72 166	98.62 122	99.10 94
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator	91.36 5	95.19 121	94.44 142	97.44 56	96.56 233	93.36 69	98.65 15	98.36 38	94.12 88	89.25 325	98.06 96	82.20 246	99.77 50	93.41 175	99.32 69	99.18 83

guyue		95.17 122	94.96 118	95.82 166	96.97 193	89.65 221	97.56 142	95.58 349	94.82 56	95.72 137	97.42 165	82.90 228	98.84 205	96.71 65	96.93 189	98.96 113

OMC-MVS		95.09 123	94.70 127	96.25 136	98.46 78	91.28 152	96.43 266	97.57 174	92.04 178	94.77 167	97.96 108	87.01 146	99.09 172	91.31 221	96.77 193	98.36 188

viewmacassd2359aftdt		95.07 124	94.80 122	95.87 160	96.53 238	89.84 216	96.90 220	97.48 188	92.44 161	95.36 152	97.89 114	85.23 179	98.68 235	94.40 150	97.00 188	99.09 95

xiu_mvs_v1_base_debu		95.01 125	94.76 123	95.75 173	96.58 229	91.71 132	96.25 289	97.35 219	92.99 138	96.70 89	96.63 221	82.67 234	99.44 127	96.22 81	97.46 165	96.11 303

xiu_mvs_v1_base		95.01 125	94.76 123	95.75 173	96.58 229	91.71 132	96.25 289	97.35 219	92.99 138	96.70 89	96.63 221	82.67 234	99.44 127	96.22 81	97.46 165	96.11 303

xiu_mvs_v1_base_debi		95.01 125	94.76 123	95.75 173	96.58 229	91.71 132	96.25 289	97.35 219	92.99 138	96.70 89	96.63 221	82.67 234	99.44 127	96.22 81	97.46 165	96.11 303

PAPM_NR		95.01 125	94.59 131	96.26 133	98.89 59	90.68 184	97.24 184	97.73 150	91.80 183	92.93 226	96.62 224	89.13 98	99.14 164	89.21 274	97.78 158	98.97 110

lupinMVS		94.99 129	94.56 133	96.29 131	96.34 257	91.21 156	95.83 316	96.27 315	88.93 298	96.22 117	96.88 203	86.20 159	98.85 203	95.27 119	99.05 102	98.82 141

Effi-MVS+		94.93 130	94.45 141	96.36 125	96.61 226	91.47 146	96.41 270	97.41 209	91.02 223	94.50 175	95.92 258	87.53 134	98.78 213	93.89 162	96.81 192	98.84 140

IS-MVSNet		94.90 131	94.52 137	96.05 146	97.67 145	90.56 186	98.44 25	96.22 318	93.21 125	93.99 191	97.74 134	85.55 173	98.45 261	89.98 250	97.86 155	99.14 87

LuminaMVS		94.89 132	94.35 145	96.53 104	95.48 306	92.80 90	96.88 223	96.18 322	92.85 150	95.92 130	96.87 205	81.44 261	98.83 206	96.43 75	97.10 185	97.94 227

MVS_Test		94.89 132	94.62 130	95.68 179	96.83 206	89.55 228	96.70 244	97.17 238	91.17 215	95.60 144	96.11 253	87.87 124	98.76 218	93.01 187	97.17 183	98.72 152

viewdifsd2359ckpt13		94.87 134	94.52 137	95.90 158	96.88 199	90.19 203	96.92 217	97.36 217	91.26 208	94.65 169	97.46 160	85.79 167	98.64 242	93.64 168	96.76 194	98.88 134

PVSNet_Blended		94.87 134	94.56 133	95.81 167	98.27 94	89.46 234	95.47 338	98.36 38	88.84 301	94.36 178	96.09 254	88.02 119	99.58 96	93.44 173	98.18 143	98.40 184

jason		94.84 136	94.39 143	96.18 139	95.52 304	90.93 172	96.09 300	96.52 301	89.28 283	96.01 127	97.32 170	84.70 190	98.77 216	95.15 123	98.91 111	98.85 137
jason: jason.
API-MVS		94.84 136	94.49 139	95.90 158	97.90 132	92.00 122	97.80 102	97.48 188	89.19 286	94.81 165	96.71 210	88.84 103	99.17 157	88.91 281	98.76 116	96.53 286

AstraMVS		94.82 138	94.64 129	95.34 200	96.36 256	88.09 282	97.58 138	94.56 396	94.98 45	95.70 140	97.92 112	81.93 254	98.93 194	96.87 59	95.88 218	98.99 109

viewdifsd2359ckpt09		94.81 139	94.37 144	96.12 142	96.91 196	90.75 181	96.94 214	97.31 224	90.51 249	94.31 180	97.38 167	85.70 169	98.71 231	93.54 169	96.75 195	98.90 126

test_yl		94.78 140	94.23 148	96.43 118	97.74 141	91.22 154	96.85 225	97.10 244	91.23 212	95.71 138	96.93 198	84.30 197	99.31 141	93.10 180	95.12 240	98.75 148

DCV-MVSNet		94.78 140	94.23 148	96.43 118	97.74 141	91.22 154	96.85 225	97.10 244	91.23 212	95.71 138	96.93 198	84.30 197	99.31 141	93.10 180	95.12 240	98.75 148

viewdifsd2359ckpt07		94.76 142	94.68 128	95.01 215	96.76 220	87.41 297	96.38 276	97.43 206	92.65 157	94.52 173	97.75 132	85.55 173	98.81 209	94.36 152	96.69 199	98.82 141

SSM_0404		94.73 143	94.31 147	95.98 155	97.05 184	90.90 174	97.01 207	97.29 225	91.24 209	94.17 187	97.60 151	85.03 183	98.76 218	92.14 198	97.30 176	98.29 197

WTY-MVS		94.71 144	94.02 153	96.79 89	97.71 143	92.05 119	96.59 259	97.35 219	90.61 242	94.64 170	96.93 198	86.41 155	99.39 132	91.20 224	94.71 252	98.94 117

mamv4		94.66 145	96.10 85	90.37 401	98.01 121	73.41 452	96.82 229	97.78 144	89.95 262	94.52 173	97.43 164	92.91 29	99.09 172	98.28 26	99.16 92	98.60 160

mvsmamba		94.57 146	94.14 150	95.87 160	97.03 187	89.93 214	97.84 93	95.85 333	91.34 203	94.79 166	96.80 206	80.67 275	98.81 209	94.85 131	98.12 146	98.85 137

SSM_0407		94.54 147	94.12 152	95.80 168	96.79 211	90.38 195	96.79 233	97.29 225	91.24 209	93.68 198	97.60 151	85.03 183	98.67 238	92.14 198	96.51 204	98.35 190

RRT-MVS		94.51 148	94.35 145	94.98 219	96.40 251	86.55 324	97.56 142	97.41 209	93.19 128	94.93 160	97.04 191	79.12 305	99.30 143	96.19 88	97.32 175	99.09 95

sss		94.51 148	93.80 157	96.64 93	97.07 179	91.97 123	96.32 284	98.06 100	88.94 297	94.50 175	96.78 207	84.60 191	99.27 145	91.90 205	96.02 214	98.68 156

test_cas_vis1_n_1920		94.48 150	94.55 136	94.28 263	96.78 215	86.45 326	97.63 133	97.64 162	93.32 123	97.68 58	98.36 69	73.75 368	99.08 175	96.73 63	99.05 102	97.31 265

CANet_DTU		94.37 151	93.65 163	96.55 103	96.46 248	92.13 117	96.21 293	96.67 293	94.38 83	93.53 206	97.03 196	79.34 301	99.71 65	90.76 234	98.45 131	97.82 239

AdaColmap		94.34 152	93.68 162	96.31 127	98.59 74	91.68 135	96.59 259	97.81 142	89.87 263	92.15 240	97.06 190	83.62 210	99.54 108	89.34 268	98.07 147	97.70 244

viewmambaseed2359dif		94.28 153	94.14 150	94.71 237	96.21 261	86.97 311	95.93 310	97.11 243	89.00 293	95.00 159	97.70 137	86.02 162	98.59 251	93.71 167	96.59 203	98.57 164

CNLPA		94.28 153	93.53 168	96.52 106	98.38 87	92.55 101	96.59 259	96.88 277	90.13 259	91.91 248	97.24 178	85.21 180	99.09 172	87.64 307	97.83 156	97.92 228

MAR-MVS		94.22 155	93.46 173	96.51 110	98.00 123	92.19 116	97.67 123	97.47 192	88.13 327	93.00 221	95.84 262	84.86 189	99.51 115	87.99 294	98.17 144	97.83 238
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		94.18 156	93.42 178	96.48 113	97.64 149	91.42 149	95.55 333	97.71 156	88.99 294	92.34 236	95.82 264	89.19 96	99.11 167	86.14 333	97.38 170	98.90 126

SDMVSNet		94.17 157	93.61 164	95.86 163	98.09 114	91.37 150	97.35 174	98.20 68	93.18 130	91.79 252	97.28 174	79.13 304	98.93 194	94.61 144	92.84 284	97.28 266

test_vis1_n_1920		94.17 157	94.58 132	92.91 332	97.42 164	82.02 402	97.83 96	97.85 135	94.68 66	98.10 46	98.49 56	70.15 392	99.32 139	97.91 29	98.82 112	97.40 260

h-mvs33		94.15 159	93.52 170	96.04 147	97.81 137	90.22 202	97.62 135	97.58 173	95.19 35	96.74 87	97.45 161	83.67 208	99.61 88	95.85 100	79.73 424	98.29 197

CHOSEN 1792x2688		94.15 159	93.51 171	96.06 145	98.27 94	89.38 237	95.18 356	98.48 33	85.60 379	93.76 197	97.11 187	83.15 219	99.61 88	91.33 220	98.72 117	99.19 82

Vis-MVSNet (Re-imp)		94.15 159	93.88 156	94.95 223	97.61 153	87.92 286	98.10 55	95.80 336	92.22 168	93.02 220	97.45 161	84.53 193	97.91 334	88.24 290	97.97 152	99.02 102

CDS-MVSNet		94.14 162	93.54 167	95.93 156	96.18 269	91.46 147	96.33 283	97.04 258	88.97 296	93.56 203	96.51 228	87.55 132	97.89 335	89.80 255	95.95 216	98.44 181
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PLC	91.00 6	94.11 163	93.43 176	96.13 141	98.58 76	91.15 165	96.69 246	97.39 211	87.29 351	91.37 262	96.71 210	88.39 112	99.52 114	87.33 314	97.13 184	97.73 242
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
FIs		94.09 164	93.70 161	95.27 202	95.70 295	92.03 121	98.10 55	98.68 18	93.36 122	90.39 283	96.70 212	87.63 130	97.94 328	92.25 195	90.50 325	95.84 311

PVSNet_BlendedMVS		94.06 165	93.92 155	94.47 250	98.27 94	89.46 234	96.73 240	98.36 38	90.17 256	94.36 178	95.24 297	88.02 119	99.58 96	93.44 173	90.72 321	94.36 396

nrg030		94.05 166	93.31 180	96.27 132	95.22 329	94.59 33	98.34 29	97.46 194	92.93 145	91.21 272	96.64 217	87.23 143	98.22 281	94.99 127	85.80 372	95.98 307

UGNet		94.04 167	93.28 181	96.31 127	96.85 203	91.19 159	97.88 88	97.68 157	94.40 81	93.00 221	96.18 244	73.39 370	99.61 88	91.72 211	98.46 130	98.13 209
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		94.01 168	93.46 173	95.64 180	96.16 271	90.45 190	96.71 243	96.89 276	89.27 284	93.46 210	96.92 201	87.29 141	97.94 328	88.70 286	95.74 222	98.53 167

Elysia		94.00 169	93.12 186	96.64 93	96.08 281	92.72 94	97.50 151	97.63 164	91.15 217	94.82 163	97.12 185	74.98 355	99.06 181	90.78 232	98.02 149	98.12 211

StellarMVS		94.00 169	93.12 186	96.64 93	96.08 281	92.72 94	97.50 151	97.63 164	91.15 217	94.82 163	97.12 185	74.98 355	99.06 181	90.78 232	98.02 149	98.12 211

IMVS_0403		93.98 171	93.79 158	94.55 246	96.19 265	86.16 335	96.35 279	97.24 232	91.54 191	93.59 202	97.04 191	85.86 164	98.73 225	90.68 237	95.59 228	98.76 144

114514_t		93.95 172	93.06 189	96.63 97	99.07 42	91.61 137	97.46 162	97.96 120	77.99 443	93.00 221	97.57 154	86.14 161	99.33 137	89.22 273	99.15 93	98.94 117

IMVS_0407		93.94 173	93.75 159	94.49 249	96.19 265	86.16 335	96.35 279	97.24 232	91.54 191	93.50 207	97.04 191	85.64 171	98.54 254	90.68 237	95.59 228	98.76 144

FC-MVSNet-test		93.94 173	93.57 165	95.04 213	95.48 306	91.45 148	98.12 54	98.71 13	93.37 120	90.23 286	96.70 212	87.66 127	97.85 337	91.49 217	90.39 326	95.83 312

mvsany_test1		93.93 175	93.98 154	93.78 295	94.94 346	86.80 314	94.62 368	92.55 436	88.77 307	96.85 82	98.49 56	88.98 99	98.08 299	95.03 125	95.62 227	96.46 291

GeoE		93.89 176	93.28 181	95.72 177	96.96 194	89.75 219	98.24 42	96.92 272	89.47 277	92.12 242	97.21 180	84.42 195	98.39 269	87.71 301	96.50 207	99.01 105

HY-MVS	89.66 9	93.87 177	92.95 194	96.63 97	97.10 178	92.49 103	95.64 330	96.64 294	89.05 291	93.00 221	95.79 268	85.77 168	99.45 126	89.16 277	94.35 254	97.96 225

XVG-OURS-SEG-HR		93.86 178	93.55 166	94.81 229	97.06 182	88.53 266	95.28 347	97.45 199	91.68 188	94.08 190	97.68 140	82.41 242	98.90 199	93.84 164	92.47 290	96.98 274

VDD-MVS		93.82 179	93.08 188	96.02 149	97.88 133	89.96 213	97.72 116	95.85 333	92.43 162	95.86 132	98.44 62	68.42 409	99.39 132	96.31 77	94.85 244	98.71 154

mvs_anonymous		93.82 179	93.74 160	94.06 273	96.44 249	85.41 352	95.81 317	97.05 256	89.85 266	90.09 296	96.36 236	87.44 138	97.75 351	93.97 158	96.69 199	99.02 102

HQP_MVS		93.78 181	93.43 176	94.82 227	96.21 261	89.99 208	97.74 111	97.51 183	94.85 52	91.34 263	96.64 217	81.32 263	98.60 247	93.02 185	92.23 293	95.86 308

PS-MVSNAJss		93.74 182	93.51 171	94.44 252	93.91 384	89.28 244	97.75 108	97.56 178	92.50 160	89.94 299	96.54 227	88.65 107	98.18 286	93.83 165	90.90 319	95.86 308

XVG-OURS		93.72 183	93.35 179	94.80 232	97.07 179	88.61 261	94.79 365	97.46 194	91.97 181	93.99 191	97.86 120	81.74 257	98.88 200	92.64 191	92.67 289	96.92 278

mamba_0408		93.70 184	92.99 190	95.83 165	96.79 211	90.38 195	88.69 455	97.07 250	90.96 225	93.68 198	97.31 172	84.97 186	98.76 218	90.95 228	96.51 204	98.35 190

HyFIR lowres test		93.66 185	92.92 195	95.87 160	98.24 98	89.88 215	94.58 370	98.49 31	85.06 389	93.78 196	95.78 269	82.86 229	98.67 238	91.77 210	95.71 224	99.07 99

LFMVS		93.60 186	92.63 209	96.52 106	98.13 113	91.27 153	97.94 79	93.39 424	90.57 246	96.29 114	98.31 79	69.00 402	99.16 159	94.18 155	95.87 219	99.12 91

icg_test_0407_2		93.58 187	93.46 173	93.94 285	96.19 265	86.16 335	93.73 405	97.24 232	91.54 191	93.50 207	97.04 191	85.64 171	96.91 401	90.68 237	95.59 228	98.76 144

F-COLMAP		93.58 187	92.98 193	95.37 198	98.40 84	88.98 254	97.18 193	97.29 225	87.75 340	90.49 281	97.10 188	85.21 180	99.50 118	86.70 324	96.72 198	97.63 246

ab-mvs		93.57 189	92.55 213	96.64 93	97.28 168	91.96 125	95.40 340	97.45 199	89.81 268	93.22 218	96.28 240	79.62 298	99.46 124	90.74 235	93.11 281	98.50 171

LS3D		93.57 189	92.61 211	96.47 114	97.59 155	91.61 137	97.67 123	97.72 152	85.17 387	90.29 285	98.34 73	84.60 191	99.73 59	83.85 369	98.27 139	98.06 220

FA-MVS(test-final)		93.52 191	92.92 195	95.31 201	96.77 217	88.54 265	94.82 364	96.21 320	89.61 272	94.20 184	95.25 296	83.24 215	99.14 164	90.01 249	96.16 213	98.25 199

SSM_04072		93.51 192	92.99 190	95.05 211	96.79 211	90.38 195	88.69 455	97.07 250	90.96 225	93.68 198	97.31 172	84.97 186	96.42 412	90.95 228	96.51 204	98.35 190

viewdifsd2359ckpt11		93.46 193	93.22 184	94.17 266	96.11 278	85.42 350	96.43 266	97.07 250	92.91 146	94.20 184	98.00 103	80.82 273	98.73 225	94.42 148	89.04 339	98.34 194

viewmsd2359difaftdt		93.46 193	93.23 183	94.17 266	96.12 276	85.42 350	96.43 266	97.08 247	92.91 146	94.21 183	98.00 103	80.82 273	98.74 223	94.41 149	89.05 337	98.34 194

Fast-Effi-MVS+		93.46 193	92.75 203	95.59 184	96.77 217	90.03 205	96.81 231	97.13 240	88.19 322	91.30 266	94.27 349	86.21 158	98.63 244	87.66 306	96.46 210	98.12 211

hse-mvs2		93.45 196	92.99 190	94.81 229	97.02 188	88.59 262	96.69 246	96.47 304	95.19 35	96.74 87	96.16 247	83.67 208	98.48 260	95.85 100	79.13 428	97.35 263

QAPM		93.45 196	92.27 223	96.98 84	96.77 217	92.62 97	98.39 28	98.12 85	84.50 397	88.27 350	97.77 131	82.39 243	99.81 34	85.40 346	98.81 113	98.51 170

UniMVSNet_NR-MVSNet		93.37 198	92.67 207	95.47 195	95.34 318	92.83 88	97.17 194	98.58 27	92.98 143	90.13 291	95.80 265	88.37 114	97.85 337	91.71 212	83.93 401	95.73 322

1112_ss		93.37 198	92.42 220	96.21 137	97.05 184	90.99 168	96.31 285	96.72 286	86.87 359	89.83 303	96.69 214	86.51 151	99.14 164	88.12 291	93.67 275	98.50 171

UniMVSNet (Re)		93.31 200	92.55 213	95.61 183	95.39 312	93.34 70	97.39 170	98.71 13	93.14 133	90.10 295	94.83 314	87.71 126	98.03 310	91.67 215	83.99 400	95.46 331

OPM-MVS		93.28 201	92.76 201	94.82 227	94.63 362	90.77 179	96.65 250	97.18 236	93.72 101	91.68 256	97.26 177	79.33 302	98.63 244	92.13 201	92.28 292	95.07 359
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		93.24 202	92.48 218	95.51 189	95.70 295	92.39 105	97.86 89	98.66 21	92.30 165	92.09 244	95.37 289	80.49 280	98.40 264	93.95 159	85.86 371	95.75 320

test_fmvs1		93.21 203	93.53 168	92.25 355	96.55 235	81.20 409	97.40 169	96.96 265	90.68 235	96.80 83	98.04 98	69.25 400	98.40 264	97.58 40	98.50 126	97.16 271

MVSTER		93.20 204	92.81 200	94.37 255	96.56 233	89.59 225	97.06 201	97.12 241	91.24 209	91.30 266	95.96 256	82.02 250	98.05 306	93.48 172	90.55 323	95.47 330

test1111		93.19 205	92.82 199	94.30 262	97.58 159	84.56 369	98.21 46	89.02 455	93.53 111	94.58 171	98.21 86	72.69 371	99.05 184	93.06 183	98.48 129	99.28 76

ECVR-MVS		93.19 205	92.73 205	94.57 245	97.66 147	85.41 352	98.21 46	88.23 457	93.43 118	94.70 168	98.21 86	72.57 372	99.07 179	93.05 184	98.49 127	99.25 79

HQP-MVS		93.19 205	92.74 204	94.54 247	95.86 287	89.33 240	96.65 250	97.39 211	93.55 107	90.14 287	95.87 260	80.95 267	98.50 257	92.13 201	92.10 298	95.78 316

CHOSEN 280x420		93.12 208	92.72 206	94.34 258	96.71 222	87.27 301	90.29 445	97.72 152	86.61 363	91.34 263	95.29 291	84.29 199	98.41 263	93.25 177	98.94 109	97.35 263

sd_testset		93.10 209	92.45 219	95.05 211	98.09 114	89.21 246	96.89 221	97.64 162	93.18 130	91.79 252	97.28 174	75.35 352	98.65 241	88.99 279	92.84 284	97.28 266

Effi-MVS+-dtu		93.08 210	93.21 185	92.68 343	96.02 284	83.25 385	97.14 197	96.72 286	93.85 98	91.20 273	93.44 387	83.08 221	98.30 276	91.69 214	95.73 223	96.50 288

test_djsdf		93.07 211	92.76 201	94.00 277	93.49 399	88.70 260	98.22 44	97.57 174	91.42 200	90.08 297	95.55 282	82.85 230	97.92 331	94.07 156	91.58 305	95.40 338

VDDNet		93.05 212	92.07 227	96.02 149	96.84 204	90.39 194	98.08 57	95.85 333	86.22 371	95.79 135	98.46 60	67.59 412	99.19 152	94.92 130	94.85 244	98.47 176

thisisatest0530		93.03 213	92.21 225	95.49 192	97.07 179	89.11 251	97.49 159	92.19 438	90.16 257	94.09 189	96.41 233	76.43 343	99.05 184	90.38 244	95.68 225	98.31 196

EI-MVSNet		93.03 213	92.88 197	93.48 311	95.77 293	86.98 310	96.44 264	97.12 241	90.66 238	91.30 266	97.64 147	86.56 149	98.05 306	89.91 252	90.55 323	95.41 335

CLD-MVS		92.98 215	92.53 215	94.32 259	96.12 276	89.20 247	95.28 347	97.47 192	92.66 156	89.90 300	95.62 278	80.58 278	98.40 264	92.73 190	92.40 291	95.38 340
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tttt0517		92.96 216	92.33 222	94.87 226	97.11 177	87.16 307	97.97 75	92.09 439	90.63 240	93.88 195	97.01 197	76.50 340	99.06 181	90.29 247	95.45 234	98.38 186

ACMM	89.79 8	92.96 216	92.50 217	94.35 256	96.30 259	88.71 259	97.58 138	97.36 217	91.40 202	90.53 280	96.65 216	79.77 294	98.75 221	91.24 223	91.64 303	95.59 326
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LPG-MVS_test		92.94 218	92.56 212	94.10 271	96.16 271	88.26 274	97.65 127	97.46 194	91.29 204	90.12 293	97.16 182	79.05 307	98.73 225	92.25 195	91.89 301	95.31 345

BH-untuned		92.94 218	92.62 210	93.92 289	97.22 170	86.16 335	96.40 274	96.25 317	90.06 260	89.79 304	96.17 246	83.19 217	98.35 272	87.19 317	97.27 178	97.24 268

DU-MVS		92.90 220	92.04 229	95.49 192	94.95 344	92.83 88	97.16 195	98.24 62	93.02 137	90.13 291	95.71 272	83.47 211	97.85 337	91.71 212	83.93 401	95.78 316

PatchMatch-RL		92.90 220	92.02 231	95.56 185	98.19 107	90.80 177	95.27 349	97.18 236	87.96 329	91.86 251	95.68 275	80.44 281	98.99 189	84.01 364	97.54 163	96.89 279

VortexMVS		92.88 222	92.64 208	93.58 306	96.58 229	87.53 296	96.93 216	97.28 228	92.78 154	89.75 305	94.99 304	82.73 233	97.76 349	94.60 145	88.16 348	95.46 331

PMMVS		92.86 223	92.34 221	94.42 254	94.92 347	86.73 317	94.53 372	96.38 309	84.78 394	94.27 181	95.12 302	83.13 220	98.40 264	91.47 218	96.49 208	98.12 211

OpenMVS	89.19 12	92.86 223	91.68 244	96.40 120	95.34 318	92.73 93	98.27 36	98.12 85	84.86 392	85.78 394	97.75 132	78.89 314	99.74 57	87.50 311	98.65 120	96.73 283

Test_1112_low_res		92.84 225	91.84 238	95.85 164	97.04 186	89.97 212	95.53 335	96.64 294	85.38 382	89.65 310	95.18 298	85.86 164	99.10 169	87.70 302	93.58 280	98.49 173

baseline1		92.82 226	91.90 236	95.55 187	97.20 172	90.77 179	97.19 192	94.58 395	92.20 171	92.36 233	96.34 237	84.16 201	98.21 282	89.20 275	83.90 404	97.68 245

1314		92.81 227	92.03 230	95.14 207	95.33 321	89.52 231	96.04 303	97.44 203	87.72 341	86.25 391	95.33 290	83.84 205	98.79 212	89.26 271	97.05 187	97.11 272

DP-MVS		92.76 228	91.51 252	96.52 106	98.77 61	90.99 168	97.38 172	96.08 325	82.38 419	89.29 322	97.87 118	83.77 206	99.69 71	81.37 392	96.69 199	98.89 132

test_fmvs1_n		92.73 229	92.88 197	92.29 352	96.08 281	81.05 410	97.98 69	97.08 247	90.72 233	96.79 85	98.18 89	63.07 435	98.45 261	97.62 39	98.42 133	97.36 261

BH-RMVSNet		92.72 230	91.97 233	94.97 221	97.16 174	87.99 284	96.15 298	95.60 347	90.62 241	91.87 250	97.15 184	78.41 320	98.57 252	83.16 371	97.60 162	98.36 188

ACMP	89.59 10	92.62 231	92.14 226	94.05 274	96.40 251	88.20 277	97.36 173	97.25 231	91.52 195	88.30 348	96.64 217	78.46 319	98.72 230	91.86 208	91.48 307	95.23 352
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LCM-MVSNet-Re		92.50 232	92.52 216	92.44 345	96.82 208	81.89 403	96.92 217	93.71 421	92.41 163	84.30 407	94.60 326	85.08 182	97.03 395	91.51 216	97.36 171	98.40 184

TranMVSNet+NR-MVSNet		92.50 232	91.63 245	95.14 207	94.76 355	92.07 118	97.53 148	98.11 88	92.90 149	89.56 313	96.12 249	83.16 218	97.60 364	89.30 269	83.20 410	95.75 320

thres600view7		92.49 234	91.60 246	95.18 205	97.91 131	89.47 232	97.65 127	94.66 392	92.18 175	93.33 213	94.91 309	78.06 327	99.10 169	81.61 385	94.06 269	96.98 274

IMVS_0404		92.44 235	91.92 235	94.00 277	96.19 265	86.16 335	93.84 402	97.24 232	91.54 191	88.17 354	97.04 191	76.96 337	97.09 392	90.68 237	95.59 228	98.76 144

thres100view900		92.43 236	91.58 247	94.98 219	97.92 130	89.37 238	97.71 118	94.66 392	92.20 171	93.31 214	94.90 310	78.06 327	99.08 175	81.40 389	94.08 265	96.48 289

jajsoiax		92.42 237	91.89 237	94.03 276	93.33 407	88.50 267	97.73 113	97.53 181	92.00 180	88.85 334	96.50 229	75.62 350	98.11 293	93.88 163	91.56 306	95.48 328

thres400		92.42 237	91.52 250	95.12 209	97.85 134	89.29 242	97.41 165	94.88 384	92.19 173	93.27 216	94.46 336	78.17 323	99.08 175	81.40 389	94.08 265	96.98 274

tfpn200view9		92.38 239	91.52 250	94.95 223	97.85 134	89.29 242	97.41 165	94.88 384	92.19 173	93.27 216	94.46 336	78.17 323	99.08 175	81.40 389	94.08 265	96.48 289

test_vis1_n		92.37 240	92.26 224	92.72 340	94.75 356	82.64 392	98.02 63	96.80 283	91.18 214	97.77 57	97.93 109	58.02 445	98.29 277	97.63 37	98.21 141	97.23 269

WR-MVS		92.34 241	91.53 249	94.77 234	95.13 337	90.83 176	96.40 274	97.98 118	91.88 182	89.29 322	95.54 283	82.50 239	97.80 344	89.79 256	85.27 380	95.69 323

NR-MVSNet		92.34 241	91.27 260	95.53 188	94.95 344	93.05 80	97.39 170	98.07 97	92.65 157	84.46 405	95.71 272	85.00 185	97.77 348	89.71 257	83.52 407	95.78 316

mvs_tets		92.31 243	91.76 240	93.94 285	93.41 404	88.29 272	97.63 133	97.53 181	92.04 178	88.76 337	96.45 231	74.62 360	98.09 298	93.91 161	91.48 307	95.45 333

TAPA-MVS	90.10 7	92.30 244	91.22 263	95.56 185	98.33 89	89.60 224	96.79 233	97.65 160	81.83 423	91.52 258	97.23 179	87.94 121	98.91 198	71.31 446	98.37 134	98.17 207
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thisisatest0515		92.29 245	91.30 258	95.25 203	96.60 227	88.90 256	94.36 381	92.32 437	87.92 330	93.43 211	94.57 327	77.28 334	99.00 188	89.42 266	95.86 220	97.86 235

Fast-Effi-MVS+-dtu		92.29 245	91.99 232	93.21 322	95.27 325	85.52 348	97.03 202	96.63 297	92.09 176	89.11 328	95.14 300	80.33 284	98.08 299	87.54 310	94.74 250	96.03 306

IterMVS-LS		92.29 245	91.94 234	93.34 316	96.25 260	86.97 311	96.57 262	97.05 256	90.67 236	89.50 316	94.80 316	86.59 148	97.64 359	89.91 252	86.11 370	95.40 338
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PVSNet	86.66 18	92.24 248	91.74 243	93.73 296	97.77 139	83.69 382	92.88 425	96.72 286	87.91 331	93.00 221	94.86 312	78.51 318	99.05 184	86.53 325	97.45 169	98.47 176

VPNet		92.23 249	91.31 257	94.99 217	95.56 302	90.96 170	97.22 190	97.86 134	92.96 144	90.96 274	96.62 224	75.06 353	98.20 283	91.90 205	83.65 406	95.80 314

thres200		92.23 249	91.39 253	94.75 236	97.61 153	89.03 253	96.60 258	95.09 373	92.08 177	93.28 215	94.00 364	78.39 321	99.04 187	81.26 395	94.18 261	96.19 296

anonymousdsp		92.16 251	91.55 248	93.97 281	92.58 422	89.55 228	97.51 150	97.42 208	89.42 280	88.40 344	94.84 313	80.66 276	97.88 336	91.87 207	91.28 311	94.48 391

XXY-MVS		92.16 251	91.23 262	94.95 223	94.75 356	90.94 171	97.47 160	97.43 206	89.14 287	88.90 330	96.43 232	79.71 295	98.24 279	89.56 262	87.68 353	95.67 324

BH-w/o		92.14 253	91.75 241	93.31 317	96.99 191	85.73 345	95.67 325	95.69 342	88.73 308	89.26 324	94.82 315	82.97 226	98.07 303	85.26 349	96.32 212	96.13 302

testing3-2		92.10 254	92.05 228	92.27 353	97.71 143	79.56 429	97.42 164	94.41 402	93.53 111	93.22 218	95.49 285	69.16 401	99.11 167	93.25 177	94.22 259	98.13 209

Anonymous202405211		92.07 255	90.83 279	95.76 171	98.19 107	88.75 258	97.58 138	95.00 376	86.00 374	93.64 201	97.45 161	66.24 424	99.53 110	90.68 237	92.71 287	99.01 105

FE-MVS		92.05 256	91.05 268	95.08 210	96.83 206	87.93 285	93.91 399	95.70 340	86.30 368	94.15 188	94.97 305	76.59 339	99.21 150	84.10 362	96.86 190	98.09 217

WR-MVS_H		92.00 257	91.35 254	93.95 283	95.09 339	89.47 232	98.04 62	98.68 18	91.46 198	88.34 346	94.68 321	85.86 164	97.56 366	85.77 341	84.24 398	94.82 376

Anonymous20240529		91.98 258	90.73 285	95.73 176	98.14 111	89.40 236	97.99 66	97.72 152	79.63 437	93.54 205	97.41 166	69.94 394	99.56 104	91.04 227	91.11 314	98.22 201

MonoMVSNet		91.92 259	91.77 239	92.37 347	92.94 413	83.11 388	97.09 200	95.55 351	92.91 146	90.85 276	94.55 328	81.27 265	96.52 410	93.01 187	87.76 352	97.47 257

PatchmatchNet		91.91 260	91.35 254	93.59 305	95.38 313	84.11 375	93.15 420	95.39 356	89.54 274	92.10 243	93.68 377	82.82 231	98.13 289	84.81 353	95.32 236	98.52 168
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing91		91.90 261	91.02 269	94.53 248	96.54 236	86.55 324	95.86 314	95.64 346	91.77 185	91.89 249	93.47 386	69.94 394	98.86 201	90.23 248	93.86 272	98.18 204

CP-MVSNet		91.89 262	91.24 261	93.82 292	95.05 340	88.57 263	97.82 98	98.19 73	91.70 187	88.21 352	95.76 270	81.96 251	97.52 372	87.86 296	84.65 389	95.37 341

SCA		91.84 263	91.18 265	93.83 291	95.59 300	84.95 365	94.72 366	95.58 349	90.82 228	92.25 238	93.69 375	75.80 347	98.10 294	86.20 331	95.98 215	98.45 178

FMVSNet3		91.78 264	90.69 288	95.03 214	96.53 238	92.27 111	97.02 204	96.93 268	89.79 269	89.35 319	94.65 324	77.01 335	97.47 375	86.12 334	88.82 340	95.35 342

AUN-MVS		91.76 265	90.75 283	94.81 229	97.00 190	88.57 263	96.65 250	96.49 303	89.63 271	92.15 240	96.12 249	78.66 316	98.50 257	90.83 230	79.18 427	97.36 261

X-MVStestdata		91.71 266	89.67 332	97.81 31	99.38 16	94.03 53	98.59 16	98.20 68	94.85 52	96.59 97	32.69 472	91.70 55	99.80 39	95.66 106	99.40 60	99.62 26

MVS		91.71 266	90.44 295	95.51 189	95.20 331	91.59 139	96.04 303	97.45 199	73.44 453	87.36 370	95.60 279	85.42 175	99.10 169	85.97 338	97.46 165	95.83 312

EPNet_dtu		91.71 266	91.28 259	92.99 329	93.76 389	83.71 381	96.69 246	95.28 363	93.15 132	87.02 379	95.95 257	83.37 214	97.38 383	79.46 408	96.84 191	97.88 231
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing11		91.68 269	90.75 283	94.47 250	96.53 238	86.56 323	95.76 321	94.51 399	91.10 221	91.24 271	93.59 381	68.59 406	98.86 201	91.10 225	94.29 257	98.00 224

baseline2		91.63 270	90.86 275	93.94 285	94.33 373	86.32 328	95.92 311	91.64 443	89.37 281	86.94 382	94.69 320	81.62 259	98.69 233	88.64 287	94.57 253	96.81 281

testing99		91.62 271	90.72 286	94.32 259	96.48 245	86.11 340	95.81 317	94.76 389	91.55 190	91.75 254	93.44 387	68.55 407	98.82 207	90.43 242	93.69 274	98.04 221

test2506		91.60 272	90.78 280	94.04 275	97.66 147	83.81 378	98.27 36	75.53 473	93.43 118	95.23 154	98.21 86	67.21 415	99.07 179	93.01 187	98.49 127	99.25 79

miper_ehance_all_eth		91.59 273	91.13 266	92.97 330	95.55 303	86.57 322	94.47 375	96.88 277	87.77 338	88.88 332	94.01 363	86.22 157	97.54 368	89.49 263	86.93 361	94.79 381

v2v482		91.59 273	90.85 277	93.80 293	93.87 386	88.17 279	96.94 214	96.88 277	89.54 274	89.53 314	94.90 310	81.70 258	98.02 311	89.25 272	85.04 386	95.20 353

V42		91.58 275	90.87 274	93.73 296	94.05 381	88.50 267	97.32 178	96.97 264	88.80 306	89.71 306	94.33 344	82.54 238	98.05 306	89.01 278	85.07 384	94.64 389

PCF-MVS	89.48 11	91.56 276	89.95 320	96.36 125	96.60 227	92.52 102	92.51 430	97.26 229	79.41 438	88.90 330	96.56 226	84.04 204	99.55 106	77.01 422	97.30 176	97.01 273
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UBG		91.55 277	90.76 281	93.94 285	96.52 241	85.06 361	95.22 352	94.54 397	90.47 250	91.98 246	92.71 398	72.02 375	98.74 223	88.10 292	95.26 238	98.01 223

PS-CasMVS		91.55 277	90.84 278	93.69 300	94.96 343	88.28 273	97.84 93	98.24 62	91.46 198	88.04 357	95.80 265	79.67 296	97.48 374	87.02 321	84.54 395	95.31 345

miper_enhance_ethall		91.54 279	91.01 270	93.15 324	95.35 317	87.07 309	93.97 394	96.90 274	86.79 360	89.17 326	93.43 390	86.55 150	97.64 359	89.97 251	86.93 361	94.74 385

myMVS_eth3d28		91.52 280	90.97 271	93.17 323	96.91 196	83.24 386	95.61 331	94.96 380	92.24 167	91.98 246	93.28 391	69.31 399	98.40 264	88.71 285	95.68 225	97.88 231

PAPM		91.52 280	90.30 301	95.20 204	95.30 324	89.83 217	93.38 416	96.85 280	86.26 370	88.59 340	95.80 265	84.88 188	98.15 288	75.67 427	95.93 217	97.63 246

ET-MVSNet_ETH3D		91.49 282	90.11 311	95.63 181	96.40 251	91.57 141	95.34 343	93.48 423	90.60 244	75.58 448	95.49 285	80.08 288	96.79 406	94.25 154	89.76 331	98.52 168

TR-MVS		91.48 283	90.59 291	94.16 269	96.40 251	87.33 298	95.67 325	95.34 362	87.68 342	91.46 260	95.52 284	76.77 338	98.35 272	82.85 376	93.61 278	96.79 282

tpmrst		91.44 284	91.32 256	91.79 370	95.15 335	79.20 435	93.42 415	95.37 358	88.55 313	93.49 209	93.67 378	82.49 240	98.27 278	90.41 243	89.34 335	97.90 229

test-LLR		91.42 285	91.19 264	92.12 358	94.59 363	80.66 413	94.29 386	92.98 429	91.11 219	90.76 278	92.37 406	79.02 309	98.07 303	88.81 282	96.74 196	97.63 246

MSDG		91.42 285	90.24 305	94.96 222	97.15 176	88.91 255	93.69 408	96.32 311	85.72 378	86.93 383	96.47 230	80.24 285	98.98 190	80.57 399	95.05 243	96.98 274

c3_l		91.38 287	90.89 273	92.88 334	95.58 301	86.30 329	94.68 367	96.84 281	88.17 323	88.83 336	94.23 352	85.65 170	97.47 375	89.36 267	84.63 390	94.89 371

GA-MVS		91.38 287	90.31 300	94.59 240	94.65 361	87.62 294	94.34 382	96.19 321	90.73 232	90.35 284	93.83 368	71.84 377	97.96 322	87.22 316	93.61 278	98.21 202

v1144		91.37 289	90.60 290	93.68 301	93.89 385	88.23 276	96.84 227	97.03 260	88.37 318	89.69 308	94.39 338	82.04 249	97.98 315	87.80 298	85.37 377	94.84 373

GBi-Net		91.35 290	90.27 303	94.59 240	96.51 242	91.18 161	97.50 151	96.93 268	88.82 303	89.35 319	94.51 331	73.87 364	97.29 387	86.12 334	88.82 340	95.31 345

test1		91.35 290	90.27 303	94.59 240	96.51 242	91.18 161	97.50 151	96.93 268	88.82 303	89.35 319	94.51 331	73.87 364	97.29 387	86.12 334	88.82 340	95.31 345

UniMVSNet_ETH3D		91.34 292	90.22 308	94.68 238	94.86 351	87.86 289	97.23 188	97.46 194	87.99 328	89.90 300	96.92 201	66.35 422	98.23 280	90.30 246	90.99 317	97.96 225

FMVSNet2		91.31 293	90.08 312	94.99 217	96.51 242	92.21 113	97.41 165	96.95 266	88.82 303	88.62 339	94.75 318	73.87 364	97.42 380	85.20 350	88.55 345	95.35 342

reproduce_monomvs		91.30 294	91.10 267	91.92 362	96.82 208	82.48 396	97.01 207	97.49 186	94.64 70	88.35 345	95.27 294	70.53 387	98.10 294	95.20 120	84.60 392	95.19 356

D2MVS		91.30 294	90.95 272	92.35 348	94.71 359	85.52 348	96.18 296	98.21 66	88.89 299	86.60 386	93.82 370	79.92 292	97.95 326	89.29 270	90.95 318	93.56 411

v8		91.29 296	90.53 294	93.57 308	94.15 377	88.12 281	97.34 175	97.06 255	88.99 294	88.32 347	94.26 351	83.08 221	98.01 312	87.62 308	83.92 403	94.57 390

CVMVSNet		91.23 297	91.75 241	89.67 410	95.77 293	74.69 447	96.44 264	94.88 384	85.81 376	92.18 239	97.64 147	79.07 306	95.58 428	88.06 293	95.86 220	98.74 151

cl22		91.21 298	90.56 293	93.14 325	96.09 280	86.80 314	94.41 379	96.58 300	87.80 336	88.58 341	93.99 365	80.85 272	97.62 362	89.87 254	86.93 361	94.99 362

PEN-MVS		91.20 299	90.44 295	93.48 311	94.49 367	87.91 288	97.76 106	98.18 75	91.29 204	87.78 361	95.74 271	80.35 283	97.33 385	85.46 345	82.96 411	95.19 356

Baseline_NR-MVSNet		91.20 299	90.62 289	92.95 331	93.83 387	88.03 283	97.01 207	95.12 372	88.42 317	89.70 307	95.13 301	83.47 211	97.44 378	89.66 260	83.24 409	93.37 415

cascas		91.20 299	90.08 312	94.58 244	94.97 342	89.16 250	93.65 410	97.59 172	79.90 436	89.40 317	92.92 396	75.36 351	98.36 271	92.14 198	94.75 249	96.23 293

CostFormer		91.18 302	90.70 287	92.62 344	94.84 352	81.76 404	94.09 392	94.43 400	84.15 400	92.72 228	93.77 372	79.43 300	98.20 283	90.70 236	92.18 296	97.90 229

tt0805		91.09 303	90.07 315	94.16 269	95.61 299	88.31 271	97.56 142	96.51 302	89.56 273	89.17 326	95.64 277	67.08 419	98.38 270	91.07 226	88.44 346	95.80 314

v1192		91.07 304	90.23 306	93.58 306	93.70 390	87.82 291	96.73 240	97.07 250	87.77 338	89.58 311	94.32 346	80.90 271	97.97 318	86.52 326	85.48 375	94.95 363

v144192		91.06 305	90.28 302	93.39 314	93.66 393	87.23 304	96.83 228	97.07 250	87.43 347	89.69 308	94.28 348	81.48 260	98.00 313	87.18 318	84.92 388	94.93 367

v10		91.04 306	90.23 306	93.49 310	94.12 378	88.16 280	97.32 178	97.08 247	88.26 321	88.29 349	94.22 354	82.17 247	97.97 318	86.45 328	84.12 399	94.33 397

eth_miper_zixun_eth		91.02 307	90.59 291	92.34 350	95.33 321	84.35 371	94.10 391	96.90 274	88.56 312	88.84 335	94.33 344	84.08 202	97.60 364	88.77 284	84.37 397	95.06 360

v148		90.99 308	90.38 297	92.81 337	93.83 387	85.80 342	96.78 237	96.68 291	89.45 279	88.75 338	93.93 367	82.96 227	97.82 341	87.83 297	83.25 408	94.80 379

LTVRE_ROB	88.41 13	90.99 308	89.92 322	94.19 265	96.18 269	89.55 228	96.31 285	97.09 246	87.88 332	85.67 395	95.91 259	78.79 315	98.57 252	81.50 386	89.98 328	94.44 394
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		90.97 310	90.33 298	92.88 334	95.36 316	86.19 334	94.46 377	96.63 297	87.82 334	88.18 353	94.23 352	82.99 224	97.53 370	87.72 299	85.57 374	94.93 367

cl____		90.96 311	90.32 299	92.89 333	95.37 315	86.21 332	94.46 377	96.64 294	87.82 334	88.15 355	94.18 355	82.98 225	97.54 368	87.70 302	85.59 373	94.92 369

pmmvs4		90.93 312	89.85 324	94.17 266	93.34 406	90.79 178	94.60 369	96.02 326	84.62 395	87.45 366	95.15 299	81.88 255	97.45 377	87.70 302	87.87 351	94.27 401

XVG-ACMP-BASELINE		90.93 312	90.21 309	93.09 326	94.31 375	85.89 341	95.33 344	97.26 229	91.06 222	89.38 318	95.44 288	68.61 405	98.60 247	89.46 264	91.05 315	94.79 381

v1921920		90.85 314	90.03 317	93.29 318	93.55 395	86.96 313	96.74 239	97.04 258	87.36 349	89.52 315	94.34 343	80.23 286	97.97 318	86.27 329	85.21 381	94.94 365

CR-MVSNet		90.82 315	89.77 328	93.95 283	94.45 369	87.19 305	90.23 446	95.68 344	86.89 358	92.40 230	92.36 409	80.91 269	97.05 394	81.09 396	93.95 270	97.60 251

v7n		90.76 316	89.86 323	93.45 313	93.54 396	87.60 295	97.70 121	97.37 215	88.85 300	87.65 363	94.08 361	81.08 266	98.10 294	84.68 355	83.79 405	94.66 388

RPSCF		90.75 317	90.86 275	90.42 400	96.84 204	76.29 445	95.61 331	96.34 310	83.89 403	91.38 261	97.87 118	76.45 341	98.78 213	87.16 319	92.23 293	96.20 295

MVP-Stereo		90.74 318	90.08 312	92.71 341	93.19 409	88.20 277	95.86 314	96.27 315	86.07 373	84.86 403	94.76 317	77.84 330	97.75 351	83.88 368	98.01 151	92.17 436
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pm-mvs1		90.72 319	89.65 334	93.96 282	94.29 376	89.63 222	97.79 104	96.82 282	89.07 289	86.12 393	95.48 287	78.61 317	97.78 346	86.97 322	81.67 416	94.46 392

v1240		90.70 320	89.85 324	93.23 320	93.51 398	86.80 314	96.61 256	97.02 262	87.16 354	89.58 311	94.31 347	79.55 299	97.98 315	85.52 344	85.44 376	94.90 370

EPMVS		90.70 320	89.81 326	93.37 315	94.73 358	84.21 373	93.67 409	88.02 458	89.50 276	92.38 232	93.49 384	77.82 331	97.78 346	86.03 337	92.68 288	98.11 216

WBMVS		90.69 322	89.99 319	92.81 337	96.48 245	85.00 362	95.21 354	96.30 313	89.46 278	89.04 329	94.05 362	72.45 374	97.82 341	89.46 264	87.41 358	95.61 325

Anonymous20231211		90.63 323	89.42 339	94.27 264	98.24 98	89.19 249	98.05 61	97.89 126	79.95 435	88.25 351	94.96 306	72.56 373	98.13 289	89.70 258	85.14 382	95.49 327

DTE-MVSNet		90.56 324	89.75 330	93.01 328	93.95 382	87.25 302	97.64 131	97.65 160	90.74 231	87.12 374	95.68 275	79.97 291	97.00 398	83.33 370	81.66 417	94.78 383

ACMH	87.59 16	90.53 325	89.42 339	93.87 290	96.21 261	87.92 286	97.24 184	96.94 267	88.45 316	83.91 415	96.27 241	71.92 376	98.62 246	84.43 358	89.43 334	95.05 361
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		90.52 326	89.14 347	94.67 239	96.81 210	87.85 290	95.91 312	93.97 415	89.71 270	92.34 236	92.48 404	65.41 430	97.96 322	81.37 392	94.27 258	98.21 202

OurMVSNet-221017-0		90.51 327	90.19 310	91.44 379	93.41 404	81.25 407	96.98 211	96.28 314	91.68 188	86.55 388	96.30 238	74.20 363	97.98 315	88.96 280	87.40 359	95.09 358

miper_lstm_enhance		90.50 328	90.06 316	91.83 367	95.33 321	83.74 379	93.86 400	96.70 290	87.56 345	87.79 360	93.81 371	83.45 213	96.92 400	87.39 312	84.62 391	94.82 376

COLMAP_ROB	87.81 15	90.40 329	89.28 342	93.79 294	97.95 127	87.13 308	96.92 217	95.89 332	82.83 416	86.88 385	97.18 181	73.77 367	99.29 144	78.44 413	93.62 277	94.95 363
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testing222		90.31 330	88.96 349	94.35 256	96.54 236	87.29 299	95.50 336	93.84 419	90.97 224	91.75 254	92.96 395	62.18 440	98.00 313	82.86 374	94.08 265	97.76 241

IterMVS-SCA-FT		90.31 330	89.81 326	91.82 368	95.52 304	84.20 374	94.30 385	96.15 323	90.61 242	87.39 369	94.27 349	75.80 347	96.44 411	87.34 313	86.88 365	94.82 376

MS-PatchMatch		90.27 332	89.77 328	91.78 371	94.33 373	84.72 368	95.55 333	96.73 285	86.17 372	86.36 390	95.28 293	71.28 381	97.80 344	84.09 363	98.14 145	92.81 421

tpm		90.25 333	89.74 331	91.76 373	93.92 383	79.73 428	93.98 393	93.54 422	88.28 320	91.99 245	93.25 392	77.51 333	97.44 378	87.30 315	87.94 350	98.12 211

AllTest		90.23 334	88.98 348	93.98 279	97.94 128	86.64 318	96.51 263	95.54 352	85.38 382	85.49 397	96.77 208	70.28 389	99.15 161	80.02 403	92.87 282	96.15 300

dmvs_re		90.21 335	89.50 337	92.35 348	95.47 310	85.15 358	95.70 324	94.37 405	90.94 227	88.42 343	93.57 382	74.63 359	95.67 425	82.80 377	89.57 333	96.22 294

ACMH+	87.92 14	90.20 336	89.18 345	93.25 319	96.48 245	86.45 326	96.99 210	96.68 291	88.83 302	84.79 404	96.22 243	70.16 391	98.53 255	84.42 359	88.04 349	94.77 384

test-mter		90.19 337	89.54 336	92.12 358	94.59 363	80.66 413	94.29 386	92.98 429	87.68 342	90.76 278	92.37 406	67.67 411	98.07 303	88.81 282	96.74 196	97.63 246

IterMVS		90.15 338	89.67 332	91.61 375	95.48 306	83.72 380	94.33 383	96.12 324	89.99 261	87.31 372	94.15 357	75.78 349	96.27 415	86.97 322	86.89 364	94.83 374
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TESTMET0.1,1		90.06 339	89.42 339	91.97 361	94.41 371	80.62 415	94.29 386	91.97 441	87.28 352	90.44 282	92.47 405	68.79 403	97.67 356	88.50 289	96.60 202	97.61 250

SD_0403		90.01 340	90.02 318	89.96 407	95.65 298	76.76 442	95.76 321	96.46 305	90.58 245	86.59 387	96.29 239	82.12 248	94.78 436	73.00 441	93.76 273	98.35 190

tpm2		89.96 341	89.21 344	92.23 356	94.91 349	81.25 407	93.78 403	94.42 401	80.62 433	91.56 257	93.44 387	76.44 342	97.94 328	85.60 343	92.08 300	97.49 255

UWE-MVS		89.91 342	89.48 338	91.21 383	95.88 286	78.23 440	94.91 363	90.26 451	89.11 288	92.35 235	94.52 330	68.76 404	97.96 322	83.95 366	95.59 228	97.42 259

IB-MVS	87.33 17	89.91 342	88.28 359	94.79 233	95.26 328	87.70 293	95.12 358	93.95 416	89.35 282	87.03 378	92.49 403	70.74 386	99.19 152	89.18 276	81.37 418	97.49 255
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		89.89 344	88.68 354	93.53 309	95.86 287	84.89 366	90.93 441	95.07 374	83.23 414	91.28 269	91.81 419	79.01 311	97.85 337	79.52 405	91.39 309	97.84 236

WB-MVSnew		89.88 345	89.56 335	90.82 392	94.57 366	83.06 389	95.65 329	92.85 431	87.86 333	90.83 277	94.10 358	79.66 297	96.88 402	76.34 423	94.19 260	92.54 427

FMVSNet1		89.88 345	88.31 358	94.59 240	95.41 311	91.18 161	97.50 151	96.93 268	86.62 362	87.41 368	94.51 331	65.94 427	97.29 387	83.04 373	87.43 356	95.31 345

pmmvs5		89.86 347	88.87 352	92.82 336	92.86 415	86.23 331	96.26 288	95.39 356	84.24 399	87.12 374	94.51 331	74.27 362	97.36 384	87.61 309	87.57 354	94.86 372

tpmvs		89.83 348	89.15 346	91.89 365	94.92 347	80.30 420	93.11 421	95.46 355	86.28 369	88.08 356	92.65 399	80.44 281	98.52 256	81.47 388	89.92 329	96.84 280

test_fmvs2		89.77 349	89.93 321	89.31 417	93.68 392	76.37 444	97.64 131	95.90 330	89.84 267	91.49 259	96.26 242	58.77 443	97.10 391	94.65 142	91.13 313	94.46 392

SSC-MVS3.2		89.74 350	89.26 343	91.19 386	95.16 332	80.29 421	94.53 372	97.03 260	91.79 184	88.86 333	94.10 358	69.94 394	97.82 341	85.29 347	86.66 366	95.45 333

mmtdpeth		89.70 351	88.96 349	91.90 364	95.84 292	84.42 370	97.46 162	95.53 354	90.27 254	94.46 177	90.50 428	69.74 398	98.95 191	97.39 51	69.48 454	92.34 430

tfpnnormal		89.70 351	88.40 357	93.60 304	95.15 335	90.10 204	97.56 142	98.16 79	87.28 352	86.16 392	94.63 325	77.57 332	98.05 306	74.48 431	84.59 393	92.65 424

ADS-MVSNet2		89.45 353	88.59 355	92.03 360	95.86 287	82.26 400	90.93 441	94.32 408	83.23 414	91.28 269	91.81 419	79.01 311	95.99 417	79.52 405	91.39 309	97.84 236

Patchmatch-test		89.42 354	87.99 361	93.70 299	95.27 325	85.11 359	88.98 453	94.37 405	81.11 427	87.10 377	93.69 375	82.28 244	97.50 373	74.37 433	94.76 248	98.48 175

test0.0.03 1		89.37 355	88.70 353	91.41 380	92.47 424	85.63 346	95.22 352	92.70 434	91.11 219	86.91 384	93.65 379	79.02 309	93.19 453	78.00 415	89.18 336	95.41 335

SixPastTwentyTwo		89.15 356	88.54 356	90.98 388	93.49 399	80.28 422	96.70 244	94.70 391	90.78 229	84.15 410	95.57 280	71.78 378	97.71 354	84.63 356	85.07 384	94.94 365

RPMNet		88.98 357	87.05 371	94.77 234	94.45 369	87.19 305	90.23 446	98.03 109	77.87 445	92.40 230	87.55 452	80.17 287	99.51 115	68.84 452	93.95 270	97.60 251

TransMVSNet (Re)		88.94 358	87.56 364	93.08 327	94.35 372	88.45 269	97.73 113	95.23 367	87.47 346	84.26 408	95.29 291	79.86 293	97.33 385	79.44 409	74.44 445	93.45 414

USDC		88.94 358	87.83 363	92.27 353	94.66 360	84.96 364	93.86 400	95.90 330	87.34 350	83.40 417	95.56 281	67.43 413	98.19 285	82.64 381	89.67 332	93.66 410

dp		88.90 360	88.26 360	90.81 393	94.58 365	76.62 443	92.85 426	94.93 381	85.12 388	90.07 298	93.07 393	75.81 346	98.12 292	80.53 400	87.42 357	97.71 243

PatchT		88.87 361	87.42 365	93.22 321	94.08 380	85.10 360	89.51 451	94.64 394	81.92 422	92.36 233	88.15 448	80.05 289	97.01 397	72.43 442	93.65 276	97.54 254

our_test_3		88.78 362	87.98 362	91.20 385	92.45 425	82.53 394	93.61 412	95.69 342	85.77 377	84.88 402	93.71 373	79.99 290	96.78 407	79.47 407	86.24 367	94.28 400

EU-MVSNet		88.72 363	88.90 351	88.20 421	93.15 410	74.21 449	96.63 255	94.22 410	85.18 386	87.32 371	95.97 255	76.16 344	94.98 434	85.27 348	86.17 368	95.41 335

Patchmtry		88.64 364	87.25 367	92.78 339	94.09 379	86.64 318	89.82 450	95.68 344	80.81 431	87.63 364	92.36 409	80.91 269	97.03 395	78.86 411	85.12 383	94.67 387

MIMVSNet		88.50 365	86.76 375	93.72 298	94.84 352	87.77 292	91.39 436	94.05 412	86.41 366	87.99 358	92.59 402	63.27 434	95.82 422	77.44 416	92.84 284	97.57 253

tpm cat1		88.36 366	87.21 369	91.81 369	95.13 337	80.55 416	92.58 429	95.70 340	74.97 449	87.45 366	91.96 417	78.01 329	98.17 287	80.39 401	88.74 343	96.72 284

ppachtmachnet_test		88.35 367	87.29 366	91.53 376	92.45 425	83.57 383	93.75 404	95.97 327	84.28 398	85.32 400	94.18 355	79.00 313	96.93 399	75.71 426	84.99 387	94.10 402

JIA-IIPM		88.26 368	87.04 372	91.91 363	93.52 397	81.42 406	89.38 452	94.38 404	80.84 430	90.93 275	80.74 460	79.22 303	97.92 331	82.76 378	91.62 304	96.38 292

testgi		87.97 369	87.21 369	90.24 403	92.86 415	80.76 411	96.67 249	94.97 378	91.74 186	85.52 396	95.83 263	62.66 438	94.47 439	76.25 424	88.36 347	95.48 328

LF4IMVS		87.94 370	87.25 367	89.98 406	92.38 427	80.05 426	94.38 380	95.25 366	87.59 344	84.34 406	94.74 319	64.31 432	97.66 358	84.83 352	87.45 355	92.23 433

gg-mvs-nofinetune		87.82 371	85.61 384	94.44 252	94.46 368	89.27 245	91.21 440	84.61 467	80.88 429	89.89 302	74.98 463	71.50 379	97.53 370	85.75 342	97.21 180	96.51 287

pmmvs6		87.81 372	86.19 380	92.69 342	91.32 432	86.30 329	97.34 175	96.41 308	80.59 434	84.05 414	94.37 340	67.37 414	97.67 356	84.75 354	79.51 426	94.09 404

testing3		87.67 373	86.88 374	90.05 405	96.14 274	80.71 412	97.10 199	92.85 431	90.15 258	87.54 365	94.55 328	55.70 450	94.10 442	73.77 437	94.10 264	95.35 342

K. test v3		87.64 374	86.75 376	90.32 402	93.02 412	79.48 433	96.61 256	92.08 440	90.66 238	80.25 436	94.09 360	67.21 415	96.65 409	85.96 339	80.83 420	94.83 374

Patchmatch-RL test		87.38 375	86.24 379	90.81 393	88.74 450	78.40 439	88.12 460	93.17 426	87.11 355	82.17 426	89.29 439	81.95 252	95.60 427	88.64 287	77.02 434	98.41 183

FMVSNet5		87.29 376	85.79 383	91.78 371	94.80 354	87.28 300	95.49 337	95.28 363	84.09 401	83.85 416	91.82 418	62.95 436	94.17 441	78.48 412	85.34 379	93.91 408

myMVS_eth3d		87.18 377	86.38 378	89.58 411	95.16 332	79.53 430	95.00 360	93.93 417	88.55 313	86.96 380	91.99 415	56.23 449	94.00 443	75.47 429	94.11 262	95.20 353

Syy-MVS		87.13 378	87.02 373	87.47 425	95.16 332	73.21 453	95.00 360	93.93 417	88.55 313	86.96 380	91.99 415	75.90 345	94.00 443	61.59 459	94.11 262	95.20 353

Anonymous20231206		87.09 379	86.14 381	89.93 408	91.22 433	80.35 418	96.11 299	95.35 359	83.57 410	84.16 409	93.02 394	73.54 369	95.61 426	72.16 443	86.14 369	93.84 409

EG-PatchMatch MVS		87.02 380	85.44 385	91.76 373	92.67 419	85.00 362	96.08 301	96.45 306	83.41 413	79.52 438	93.49 384	57.10 447	97.72 353	79.34 410	90.87 320	92.56 426

TinyColmap		86.82 381	85.35 388	91.21 383	94.91 349	82.99 390	93.94 396	94.02 414	83.58 409	81.56 428	94.68 321	62.34 439	98.13 289	75.78 425	87.35 360	92.52 428

UWE-MVS-28		86.81 382	86.41 377	88.02 423	92.87 414	74.60 448	95.38 342	86.70 463	88.17 323	87.28 373	94.67 323	70.83 385	93.30 451	67.45 453	94.31 256	96.17 297

mvs5depth		86.53 383	85.08 390	90.87 390	88.74 450	82.52 395	91.91 434	94.23 409	86.35 367	87.11 376	93.70 374	66.52 420	97.76 349	81.37 392	75.80 439	92.31 432

TDRefinement		86.53 383	84.76 395	91.85 366	82.23 466	84.25 372	96.38 276	95.35 359	84.97 391	84.09 412	94.94 307	65.76 428	98.34 275	84.60 357	74.52 444	92.97 418

sc_t1		86.48 385	84.10 401	93.63 302	93.45 402	85.76 344	96.79 233	94.71 390	73.06 454	86.45 389	94.35 341	55.13 451	97.95 326	84.38 360	78.55 431	97.18 270

test_0402		86.46 386	84.79 394	91.45 378	95.02 341	85.55 347	96.29 287	94.89 383	80.90 428	82.21 425	93.97 366	68.21 410	97.29 387	62.98 457	88.68 344	91.51 441

Anonymous20240521		86.42 387	85.44 385	89.34 416	90.33 437	79.79 427	96.73 240	95.92 328	83.71 408	83.25 419	91.36 424	63.92 433	96.01 416	78.39 414	85.36 378	92.22 434

DSMNet-mixed		86.34 388	86.12 382	87.00 429	89.88 441	70.43 455	94.93 362	90.08 452	77.97 444	85.42 399	92.78 397	74.44 361	93.96 445	74.43 432	95.14 239	96.62 285

CL-MVSNet_self_test		86.31 389	85.15 389	89.80 409	88.83 448	81.74 405	93.93 397	96.22 318	86.67 361	85.03 401	90.80 427	78.09 326	94.50 437	74.92 430	71.86 450	93.15 417

pmmvs-eth3d		86.22 390	84.45 397	91.53 376	88.34 452	87.25 302	94.47 375	95.01 375	83.47 411	79.51 439	89.61 437	69.75 397	95.71 423	83.13 372	76.73 437	91.64 438

test_vis1_rt		86.16 391	85.06 391	89.46 413	93.47 401	80.46 417	96.41 270	86.61 464	85.22 385	79.15 440	88.64 443	52.41 455	97.06 393	93.08 182	90.57 322	90.87 447

test20.03		86.14 392	85.40 387	88.35 419	90.12 438	80.06 425	95.90 313	95.20 368	88.59 309	81.29 429	93.62 380	71.43 380	92.65 454	71.26 447	81.17 419	92.34 430

UnsupCasMVSNet_eth		85.99 393	84.45 397	90.62 397	89.97 440	82.40 399	93.62 411	97.37 215	89.86 264	78.59 443	92.37 406	65.25 431	95.35 432	82.27 383	70.75 451	94.10 402

KD-MVS_self_test		85.95 394	84.95 392	88.96 418	89.55 444	79.11 436	95.13 357	96.42 307	85.91 375	84.07 413	90.48 429	70.03 393	94.82 435	80.04 402	72.94 448	92.94 419

ttmdpeth		85.91 395	84.76 395	89.36 415	89.14 445	80.25 423	95.66 328	93.16 428	83.77 406	83.39 418	95.26 295	66.24 424	95.26 433	80.65 398	75.57 440	92.57 425

YYNet1		85.87 396	84.23 399	90.78 396	92.38 427	82.46 398	93.17 418	95.14 371	82.12 421	67.69 456	92.36 409	78.16 325	95.50 430	77.31 418	79.73 424	94.39 395

MDA-MVSNet_test_wron		85.87 396	84.23 399	90.80 395	92.38 427	82.57 393	93.17 418	95.15 370	82.15 420	67.65 458	92.33 412	78.20 322	95.51 429	77.33 417	79.74 423	94.31 399

CMPMVS	62.92 21	85.62 398	84.92 393	87.74 424	89.14 445	73.12 454	94.17 389	96.80 283	73.98 450	73.65 452	94.93 308	66.36 421	97.61 363	83.95 366	91.28 311	92.48 429
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PVSNet_0	82.17 19	85.46 399	83.64 402	90.92 389	95.27 325	79.49 432	90.55 444	95.60 347	83.76 407	83.00 422	89.95 434	71.09 382	97.97 318	82.75 379	60.79 465	95.31 345

tt0320		85.39 400	83.12 403	92.19 357	93.44 403	85.79 343	96.19 295	94.87 387	71.19 456	82.92 423	91.76 421	58.43 444	96.81 405	81.03 397	78.26 432	93.98 406

MDA-MVSNet-bldmvs		85.00 401	82.95 406	91.17 387	93.13 411	83.33 384	94.56 371	95.00 376	84.57 396	65.13 462	92.65 399	70.45 388	95.85 420	73.57 438	77.49 433	94.33 397

MIMVSNet1		84.93 402	83.05 404	90.56 398	89.56 443	84.84 367	95.40 340	95.35 359	83.91 402	80.38 434	92.21 414	57.23 446	93.34 450	70.69 449	82.75 414	93.50 412

tt0320-xc		84.83 403	82.33 411	92.31 351	93.66 393	86.20 333	96.17 297	94.06 411	71.26 455	82.04 427	92.22 413	55.07 452	96.72 408	81.49 387	75.04 443	94.02 405

KD-MVS_2432*1600		84.81 404	82.64 407	91.31 381	91.07 434	85.34 356	91.22 438	95.75 338	85.56 380	83.09 420	90.21 432	67.21 415	95.89 418	77.18 420	62.48 463	92.69 422

miper_refine_blended		84.81 404	82.64 407	91.31 381	91.07 434	85.34 356	91.22 438	95.75 338	85.56 380	83.09 420	90.21 432	67.21 415	95.89 418	77.18 420	62.48 463	92.69 422

OpenMVS_ROB	81.14 20	84.42 406	82.28 412	90.83 391	90.06 439	84.05 377	95.73 323	94.04 413	73.89 452	80.17 437	91.53 423	59.15 442	97.64 359	66.92 455	89.05 337	90.80 448

FE-MVSNET		83.85 407	81.97 413	89.51 412	87.19 456	83.19 387	95.21 354	93.17 426	83.45 412	78.90 441	89.05 441	65.46 429	93.84 447	69.71 451	75.56 441	91.51 441

mvsany_test3		83.59 408	82.44 410	87.03 428	83.80 461	73.82 450	93.70 406	90.92 449	86.42 365	82.51 424	90.26 431	46.76 460	95.71 423	90.82 231	76.76 436	91.57 440

PM-MVS		83.48 409	81.86 415	88.31 420	87.83 454	77.59 441	93.43 414	91.75 442	86.91 357	80.63 432	89.91 435	44.42 461	95.84 421	85.17 351	76.73 437	91.50 443

test_fmvs3		83.21 410	83.02 405	83.78 434	86.77 458	68.34 460	96.76 238	94.91 382	86.49 364	84.14 411	89.48 438	36.04 465	91.73 456	91.86 208	80.77 421	91.26 446

new-patchmatchnet		83.18 411	81.87 414	87.11 427	86.88 457	75.99 446	93.70 406	95.18 369	85.02 390	77.30 446	88.40 445	65.99 426	93.88 446	74.19 435	70.18 452	91.47 444

new_pmnet		82.89 412	81.12 417	88.18 422	89.63 442	80.18 424	91.77 435	92.57 435	76.79 447	75.56 449	88.23 447	61.22 441	94.48 438	71.43 445	82.92 412	89.87 451

MVS-HIRNet		82.47 413	81.21 416	86.26 431	95.38 313	69.21 458	88.96 454	89.49 453	66.28 460	80.79 431	74.08 465	68.48 408	97.39 382	71.93 444	95.47 233	92.18 435

MVStest1		82.38 414	80.04 418	89.37 414	87.63 455	82.83 391	95.03 359	93.37 425	73.90 451	73.50 453	94.35 341	62.89 437	93.25 452	73.80 436	65.92 460	92.04 437

UnsupCasMVSNet_bld		82.13 415	79.46 420	90.14 404	88.00 453	82.47 397	90.89 443	96.62 299	78.94 440	75.61 447	84.40 458	56.63 448	96.31 414	77.30 419	66.77 459	91.63 439

dmvs_testset		81.38 416	82.60 409	77.73 440	91.74 431	51.49 475	93.03 423	84.21 468	89.07 289	78.28 444	91.25 425	76.97 336	88.53 463	56.57 463	82.24 415	93.16 416

test_f		80.57 417	79.62 419	83.41 435	83.38 464	67.80 462	93.57 413	93.72 420	80.80 432	77.91 445	87.63 451	33.40 466	92.08 455	87.14 320	79.04 429	90.34 450

pmmvs3		79.97 418	77.50 423	87.39 426	82.80 465	79.38 434	92.70 428	90.75 450	70.69 457	78.66 442	87.47 453	51.34 456	93.40 449	73.39 439	69.65 453	89.38 452

APD_test1		79.31 419	77.70 422	84.14 433	89.11 447	69.07 459	92.36 433	91.50 444	69.07 458	73.87 451	92.63 401	39.93 463	94.32 440	70.54 450	80.25 422	89.02 453

N_pmnet		78.73 420	78.71 421	78.79 439	92.80 417	46.50 478	94.14 390	43.71 480	78.61 441	80.83 430	91.66 422	74.94 357	96.36 413	67.24 454	84.45 396	93.50 412

WB-MVS		76.77 421	76.63 424	77.18 441	85.32 459	56.82 473	94.53 372	89.39 454	82.66 418	71.35 454	89.18 440	75.03 354	88.88 461	35.42 470	66.79 458	85.84 455

SSC-MVS		76.05 422	75.83 425	76.72 445	84.77 460	56.22 474	94.32 384	88.96 456	81.82 424	70.52 455	88.91 442	74.79 358	88.71 462	33.69 471	64.71 461	85.23 456

test_vis3_rt		72.73 423	70.55 426	79.27 438	80.02 467	68.13 461	93.92 398	74.30 475	76.90 446	58.99 466	73.58 466	20.29 474	95.37 431	84.16 361	72.80 449	74.31 463

LCM-MVSNet		72.55 424	69.39 428	82.03 436	70.81 476	65.42 465	90.12 448	94.36 407	55.02 466	65.88 460	81.72 459	24.16 473	89.96 457	74.32 434	68.10 457	90.71 449

FPMVS		71.27 425	69.85 427	75.50 446	74.64 471	59.03 471	91.30 437	91.50 444	58.80 463	57.92 467	88.28 446	29.98 469	85.53 466	53.43 464	82.84 413	81.95 459

PMMVS2		70.19 426	66.92 430	80.01 437	76.35 470	65.67 464	86.22 461	87.58 460	64.83 462	62.38 463	80.29 462	26.78 471	88.49 464	63.79 456	54.07 467	85.88 454

dongtai		69.99 427	69.33 429	71.98 449	88.78 449	61.64 469	89.86 449	59.93 479	75.67 448	74.96 450	85.45 455	50.19 457	81.66 468	43.86 467	55.27 466	72.63 464

testf1		69.31 428	66.76 431	76.94 443	78.61 468	61.93 467	88.27 458	86.11 465	55.62 464	59.69 464	85.31 456	20.19 475	89.32 458	57.62 460	69.44 455	79.58 460

APD_test2		69.31 428	66.76 431	76.94 443	78.61 468	61.93 467	88.27 458	86.11 465	55.62 464	59.69 464	85.31 456	20.19 475	89.32 458	57.62 460	69.44 455	79.58 460

EGC-MVSNET		68.77 430	63.01 436	86.07 432	92.49 423	82.24 401	93.96 395	90.96 448	0.71 477	2.62 478	90.89 426	53.66 453	93.46 448	57.25 462	84.55 394	82.51 458

Gipuma		67.86 431	65.41 433	75.18 447	92.66 420	73.45 451	66.50 469	94.52 398	53.33 467	57.80 468	66.07 468	30.81 467	89.20 460	48.15 466	78.88 430	62.90 468
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		66.11 432	64.89 434	69.79 450	72.62 474	35.23 482	65.19 470	92.83 433	20.35 472	65.20 461	88.08 449	43.14 462	82.70 467	73.12 440	63.46 462	91.45 445

kuosan		65.27 433	64.66 435	67.11 452	83.80 461	61.32 470	88.53 457	60.77 478	68.22 459	67.67 457	80.52 461	49.12 458	70.76 474	29.67 473	53.64 468	69.26 466

ANet_high		63.94 434	59.58 437	77.02 442	61.24 478	66.06 463	85.66 463	87.93 459	78.53 442	42.94 470	71.04 467	25.42 472	80.71 469	52.60 465	30.83 471	84.28 457

PMVS	53.92 22	58.58 435	55.40 438	68.12 451	51.00 479	48.64 476	78.86 466	87.10 462	46.77 468	35.84 474	74.28 464	8.76 477	86.34 465	42.07 468	73.91 446	69.38 465
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		53.28 436	52.56 440	55.43 454	74.43 472	47.13 477	83.63 465	76.30 472	42.23 469	42.59 471	62.22 470	28.57 470	74.40 471	31.53 472	31.51 470	44.78 469

MVE	50.73 23	53.25 437	48.81 442	66.58 453	65.34 477	57.50 472	72.49 468	70.94 476	40.15 471	39.28 473	63.51 469	6.89 479	73.48 473	38.29 469	42.38 469	68.76 467
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		52.08 438	51.31 441	54.39 455	72.62 474	45.39 479	83.84 464	75.51 474	41.13 470	40.77 472	59.65 471	30.08 468	73.60 472	28.31 474	29.90 472	44.18 470

tmp_tt		51.94 439	53.82 439	46.29 456	33.73 480	45.30 480	78.32 467	67.24 477	18.02 473	50.93 469	87.05 454	52.99 454	53.11 475	70.76 448	25.29 473	40.46 471

wuyk23d		25.11 440	24.57 444	26.74 457	73.98 473	39.89 481	57.88 471	9.80 481	12.27 474	10.39 475	6.97 477	7.03 478	36.44 476	25.43 475	17.39 474	3.89 474

cdsmvs_eth3d_5k		23.24 441	30.99 443	0.00 460	0.00 483	0.00 485	0.00 472	97.63 164	0.00 478	0.00 479	96.88 203	84.38 196	0.00 479	0.00 478	0.00 477	0.00 475

testmvs		13.36 442	16.33 445	4.48 459	5.04 481	2.26 484	93.18 417	3.28 482	2.70 475	8.24 476	21.66 473	2.29 481	2.19 477	7.58 476	2.96 475	9.00 473

test123		13.04 443	15.66 446	5.18 458	4.51 482	3.45 483	92.50 431	1.81 483	2.50 476	7.58 477	20.15 474	3.67 480	2.18 478	7.13 477	1.07 476	9.90 472

ab-mvs-re		8.06 444	10.74 447	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	96.69 214	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

pcd_1.5k_mvsjas		7.39 445	9.85 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	88.65 107	0.00 479	0.00 478	0.00 477	0.00 475

mmdepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

monomultidepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

test_blank		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet_test		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

DCPMVS		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

sosnet-low-res		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

sosnet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uncertanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

Regformer		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

MED-MVS test				98.00 23	99.56 1	94.50 35	98.69 11	98.70 16	93.45 116	98.73 29	98.53 50		99.86 9	97.40 49	99.58 23	99.65 20

TestfortrainingZip							98.69 11

WAC-MVS						79.53 430								75.56 428

FOURS1					99.55 3	93.34 70	99.29 1	98.35 41	94.98 45	98.49 37

MSC_two_6792asdad				98.86 1	98.67 66	96.94 1		97.93 123					99.86 9	97.68 32	99.67 6	99.77 3

PC_three_1452									90.77 230	98.89 25	98.28 84	96.24 1	98.35 272	95.76 104	99.58 23	99.59 31

No_MVS				98.86 1	98.67 66	96.94 1		97.93 123					99.86 9	97.68 32	99.67 6	99.77 3

test_one_0601					99.32 26	95.20 21		98.25 60	95.13 39	98.48 38	98.87 30	95.16 8

eth-test2					0.00 483

eth-test					0.00 483

ZD-MVS					99.05 44	94.59 33		98.08 92	89.22 285	97.03 79	98.10 92	92.52 41	99.65 77	94.58 146	99.31 70

RE-MVS-def			96.72 60		99.02 47	92.34 107	97.98 69	98.03 109	93.52 113	97.43 65	98.51 54	90.71 80		96.05 92	99.26 76	99.43 62

IU-MVS					99.42 9	95.39 12		97.94 122	90.40 253	98.94 18				97.41 48	99.66 10	99.74 9

OPU-MVS				98.55 4	98.82 60	96.86 3	98.25 39				98.26 85	96.04 2	99.24 147	95.36 118	99.59 19	99.56 39

test_241102_TWO								98.27 54	95.13 39	98.93 19	98.89 27	94.99 12	99.85 20	97.52 41	99.65 13	99.74 9

test_241102_ONE					99.42 9	95.30 18		98.27 54	95.09 42	99.19 12	98.81 36	95.54 5	99.65 77

9.14			96.75 59		98.93 55		97.73 113	98.23 65	91.28 207	97.88 53	98.44 62	93.00 28	99.65 77	95.76 104	99.47 44

save fliter					98.91 57	94.28 41	97.02 204	98.02 112	95.35 30

test_0728_THIRD									94.78 60	98.73 29	98.87 30	95.87 4	99.84 25	97.45 45	99.72 2	99.77 3

test_0728_SECOND				98.51 5	99.45 5	95.93 6	98.21 46	98.28 51					99.86 9	97.52 41	99.67 6	99.75 7

test0726					99.45 5	95.36 14	98.31 31	98.29 49	94.92 49	98.99 17	98.92 22	95.08 9

GSMVS																98.45 178

test_part2					99.28 29	95.74 9				98.10 46

sam_mvs1												82.76 232				98.45 178

sam_mvs												81.94 253

ambc				86.56 430	83.60 463	70.00 457	85.69 462	94.97 378		80.60 433	88.45 444	37.42 464	96.84 404	82.69 380	75.44 442	92.86 420

MTGPA								98.08 92

test_post1							92.81 427				16.58 476	80.53 279	97.68 355	86.20 331

test_post											17.58 475	81.76 256	98.08 299

patchmatchnet-post											90.45 430	82.65 237	98.10 294

GG-mvs-BLEND				93.62 303	93.69 391	89.20 247	92.39 432	83.33 469		87.98 359	89.84 436	71.00 383	96.87 403	82.08 384	95.40 235	94.80 379

MTMP							97.86 89	82.03 470

gm-plane-assit					93.22 408	78.89 438			84.82 393		93.52 383		98.64 242	87.72 299

test9_res														94.81 136	99.38 63	99.45 58

TEST9					98.70 64	94.19 45	96.41 270	98.02 112	88.17 323	96.03 124	97.56 156	92.74 35	99.59 93

test_8					98.67 66	94.06 52	96.37 278	98.01 115	88.58 310	95.98 128	97.55 158	92.73 36	99.58 96

agg_prior2														93.94 160	99.38 63	99.50 51

agg_prior					98.67 66	93.79 58		98.00 116		95.68 141			99.57 103

TestCases				93.98 279	97.94 128	86.64 318		95.54 352	85.38 382	85.49 397	96.77 208	70.28 389	99.15 161	80.02 403	92.87 282	96.15 300

test_prior4						93.66 61	96.42 269

test_prior2							96.35 279		92.80 153	96.03 124	97.59 153	92.01 49		95.01 126	99.38 63

test_prior				97.23 68	98.67 66	92.99 82		98.00 116					99.41 130			99.29 74

旧先验2							95.94 309		81.66 425	97.34 68			98.82 207	92.26 193

新几何2							95.79 319

新几何1				97.32 61	98.60 73	93.59 62		97.75 147	81.58 426	95.75 136	97.85 121	90.04 87	99.67 75	86.50 327	99.13 96	98.69 155

旧先验1					98.38 87	93.38 67		97.75 147			98.09 94	92.30 47			99.01 106	99.16 84

无先验							95.79 319	97.87 130	83.87 405				99.65 77	87.68 305		98.89 132

原ACMM2							95.67 325

原ACMM1				96.38 123	98.59 74	91.09 166		97.89 126	87.41 348	95.22 155	97.68 140	90.25 84	99.54 108	87.95 295	99.12 98	98.49 173

test222					98.24 98	92.21 113	95.33 344	97.60 169	79.22 439	95.25 153	97.84 123	88.80 104			99.15 93	98.72 152

testdata2													99.67 75	85.96 339

segment_acmp												92.89 32

testdata				95.46 196	98.18 109	88.90 256		97.66 158	82.73 417	97.03 79	98.07 95	90.06 86	98.85 203	89.67 259	98.98 107	98.64 158

testdata1							95.26 351		93.10 135

test12				97.65 46	98.46 78	94.26 42		97.66 158		95.52 148		90.89 77	99.46 124		99.25 78	99.22 81

plane_prior7					96.21 261	89.98 210

plane_prior6					96.10 279	90.00 206						81.32 263

plane_prior5								97.51 183					98.60 247	93.02 185	92.23 293	95.86 308

plane_prior4											96.64 217

plane_prior3						90.00 206			94.46 77	91.34 263

plane_prior2							97.74 111		94.85 52

plane_prior1					96.14 274

plane_prior						89.99 208	97.24 184		94.06 90						92.16 297

n2								0.00 484

nn								0.00 484

door-mid								91.06 447

lessismore_v0				90.45 399	91.96 430	79.09 437		87.19 461		80.32 435	94.39 338	66.31 423	97.55 367	84.00 365	76.84 435	94.70 386

LGP-MVS_train				94.10 271	96.16 271	88.26 274		97.46 194	91.29 204	90.12 293	97.16 182	79.05 307	98.73 225	92.25 195	91.89 301	95.31 345

test11								97.88 128

door								91.13 446

HQP5-MVS						89.33 240

HQP-NCC					95.86 287		96.65 250		93.55 107	90.14 287

ACMP_Plane					95.86 287		96.65 250		93.55 107	90.14 287

BP-MVS														92.13 201

HQP4-MVS										90.14 287			98.50 257			95.78 316

HQP3-MVS								97.39 211							92.10 298

HQP2-MVS												80.95 267

NP-MVS					95.99 285	89.81 218					95.87 260

MDTV_nov1_ep13_2view						70.35 456	93.10 422		83.88 404	93.55 204		82.47 241		86.25 330		98.38 186

MDTV_nov1_ep13			90.76 281		95.22 329	80.33 419	93.03 423	95.28 363	88.14 326	92.84 227	93.83 368	81.34 262	98.08 299	82.86 374	94.34 255

ACMMP++_ref															90.30 327

ACMMP++															91.02 316

Test By Simon												88.73 106

ITE_SJBPF				92.43 346	95.34 318	85.37 355		95.92 328	91.47 197	87.75 362	96.39 235	71.00 383	97.96 322	82.36 382	89.86 330	93.97 407

DeepMVS_CX				74.68 448	90.84 436	64.34 466		81.61 471	65.34 461	67.47 459	88.01 450	48.60 459	80.13 470	62.33 458	73.68 447	79.58 460

High-resolution multi-view benchmark