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 64	95.39 11	99.29 1	98.28 49	94.78 60	98.93 19	98.87 30	96.04 2	99.86 9	97.45 45	99.58 23	99.59 29

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 52	95.13 39	99.19 12	98.89 27	95.54 5	99.85 18	97.52 41	99.66 10	99.56 37

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 133	94.92 49	98.73 29	98.87 30	95.08 8	99.84 23	97.52 41	99.67 6	99.48 53
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 9	98.47 5	99.17 35	95.78 7	97.21 188	98.35 39	95.16 37	98.71 31	98.80 37	95.05 10	99.89 3	96.70 65	99.73 1	99.73 11
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 8	98.08 18	99.15 36	94.82 28	98.81 8	98.30 45	94.76 63	98.30 39	98.90 24	93.77 17	99.68 71	97.93 28	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CNVR-MVS		97.68 6	97.44 21	98.37 7	98.90 56	95.86 6	97.27 179	98.08 90	95.81 19	97.87 54	98.31 77	94.26 13	99.68 71	97.02 54	99.49 40	99.57 33

fmvsm_l_conf0.5_n		97.65 7	97.75 7	97.34 58	98.21 102	92.75 89	97.83 93	98.73 10	95.04 44	99.30 6	98.84 35	93.34 22	99.78 45	99.32 7	99.13 94	99.50 49

fmvsm_l_conf0.5_n_3		97.64 8	97.60 11	97.79 31	98.14 109	93.94 53	97.93 78	98.65 21	96.70 7	99.38 4	99.07 10	89.92 89	99.81 32	99.16 13	99.43 50	99.61 27

fmvsm_l_conf0.5_n_a		97.63 9	97.76 6	97.26 65	98.25 95	92.59 97	97.81 98	98.68 16	94.93 47	99.24 9	98.87 30	93.52 20	99.79 42	99.32 7	99.21 79	99.40 63

SteuartSystems-ACMMP		97.62 10	97.53 15	97.87 25	98.39 84	94.25 41	98.43 23	98.27 52	95.34 31	98.11 43	98.56 46	94.53 12	99.71 63	96.57 69	99.62 17	99.65 19
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_l_conf0.5_n_9		97.59 11	97.79 5	96.97 83	98.28 90	91.49 141	97.61 133	98.71 13	97.10 4	99.70 1	98.93 21	90.95 74	99.77 48	99.35 6	99.53 30	99.65 19

MSP-MVS		97.59 11	97.54 14	97.73 39	99.40 11	93.77 58	98.53 15	98.29 47	95.55 26	98.56 34	97.81 125	93.90 15	99.65 75	96.62 66	99.21 79	99.77 2
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 13	97.63 10	97.43 55	99.37 16	92.93 83	98.86 7	98.85 5	95.27 33	98.65 32	98.90 24	91.97 50	99.80 37	97.63 37	99.21 79	99.57 33

test_fmvsm_n_1920		97.55 14	97.89 3	96.53 102	98.41 81	91.73 127	98.01 61	99.02 1	96.37 12	99.30 6	98.92 22	92.39 42	99.79 42	99.16 13	99.46 43	98.08 216

ME-MVS		97.54 15	97.39 24	98.00 22	99.21 33	94.50 34	97.75 105	98.34 41	94.23 86	98.15 42	98.53 50	93.32 25	99.84 23	97.40 49	99.58 23	99.65 19

reproduce-ours		97.53 16	97.51 17	97.60 48	98.97 50	93.31 70	97.71 115	98.20 66	95.80 20	97.88 51	98.98 17	92.91 28	99.81 32	97.68 32	99.43 50	99.67 14

our_new_method		97.53 16	97.51 17	97.60 48	98.97 50	93.31 70	97.71 115	98.20 66	95.80 20	97.88 51	98.98 17	92.91 28	99.81 32	97.68 32	99.43 50	99.67 14

reproduce_model		97.51 18	97.51 17	97.50 51	98.99 49	93.01 79	97.79 101	98.21 64	95.73 23	97.99 47	99.03 14	92.63 37	99.82 30	97.80 30	99.42 53	99.67 14

test_fmvsmconf_n		97.49 19	97.56 13	97.29 61	97.44 161	92.37 104	97.91 80	98.88 4	95.83 18	98.92 22	99.05 13	91.45 59	99.80 37	99.12 15	99.46 43	99.69 13

TSAR-MVS + MP.		97.42 20	97.33 26	97.69 43	99.25 29	94.24 42	98.07 56	97.85 133	93.72 101	98.57 33	98.35 68	93.69 18	99.40 129	97.06 53	99.46 43	99.44 58
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 21	97.53 15	97.06 79	98.57 75	94.46 35	97.92 79	98.14 80	94.82 56	99.01 16	98.55 48	94.18 14	97.41 379	96.94 55	99.64 14	99.32 71
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 22	97.13 28	98.17 15	99.02 45	95.28 19	98.23 40	98.27 52	92.37 162	98.27 40	98.65 44	93.33 23	99.72 61	96.49 71	99.52 32	99.51 46

SMA-MVS		97.35 23	97.03 37	98.30 8	99.06 41	95.42 10	97.94 76	98.18 73	90.57 244	98.85 26	98.94 20	93.33 23	99.83 28	96.72 63	99.68 4	99.63 23
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 24	96.97 40	98.47 5	99.08 39	96.16 4	97.55 144	97.97 117	95.59 24	96.61 93	97.89 112	92.57 39	99.84 23	95.95 95	99.51 35	99.40 63

fmvsm_s_conf0.5_n_9		97.33 25	97.57 12	96.62 98	98.43 79	90.32 197	97.80 99	98.53 27	97.24 3	99.62 2	99.14 1	88.65 106	99.80 37	99.54 1	99.15 91	99.74 8

fmvsm_s_conf0.5_n_8		97.32 26	97.48 20	96.85 85	98.28 90	91.07 165	97.76 103	98.62 23	97.53 2	99.20 11	99.12 4	88.24 114	99.81 32	99.41 3	99.17 87	99.67 14

NCCC		97.30 27	97.03 37	98.11 17	98.77 59	95.06 25	97.34 172	98.04 105	95.96 14	97.09 75	97.88 115	93.18 26	99.71 63	95.84 100	99.17 87	99.56 37

fmvsm_s_conf0.5_n_10		97.29 28	97.40 23	96.97 83	98.24 96	91.96 123	97.89 83	98.72 12	96.77 6	99.46 3	99.06 11	87.78 124	99.84 23	99.40 4	99.27 71	99.12 89

MM		97.29 28	96.98 39	98.23 11	98.01 119	95.03 26	98.07 56	95.76 335	97.78 1	97.52 58	98.80 37	88.09 116	99.86 9	99.44 2	99.37 64	99.80 1

ACMMP_NAP		97.20 30	96.86 46	98.23 11	99.09 37	95.16 22	97.60 134	98.19 71	92.82 150	97.93 50	98.74 41	91.60 57	99.86 9	96.26 76	99.52 32	99.67 14

XVS		97.18 31	96.96 42	97.81 29	99.38 14	94.03 51	98.59 13	98.20 66	94.85 52	96.59 95	98.29 80	91.70 54	99.80 37	95.66 104	99.40 58	99.62 24

MCST-MVS		97.18 31	96.84 48	98.20 14	99.30 26	95.35 15	97.12 195	98.07 95	93.54 110	96.08 121	97.69 137	93.86 16	99.71 63	96.50 70	99.39 60	99.55 40

fmvsm_s_conf0.5_n_3		97.15 33	97.36 25	96.52 104	97.98 122	91.19 157	97.84 90	98.65 21	97.08 5	99.25 8	99.10 5	87.88 122	99.79 42	99.32 7	99.18 86	98.59 160

HFP-MVS		97.14 34	96.92 44	97.83 27	99.42 7	94.12 47	98.52 16	98.32 43	93.21 123	97.18 69	98.29 80	92.08 47	99.83 28	95.63 109	99.59 19	99.54 42

test_fmvsmconf0.1_n		97.09 35	97.06 32	97.19 70	95.67 295	92.21 111	97.95 75	98.27 52	95.78 22	98.40 38	99.00 15	89.99 87	99.78 45	99.06 17	99.41 56	99.59 29

fmvsm_s_conf0.5_n_6		97.08 36	97.17 27	96.81 86	97.28 166	91.73 127	97.75 105	98.50 28	94.86 51	99.22 10	98.78 39	89.75 92	99.76 50	99.10 16	99.29 69	98.94 115

MTAPA		97.08 36	96.78 56	97.97 24	99.37 16	94.42 37	97.24 181	98.08 90	95.07 43	96.11 119	98.59 45	90.88 77	99.90 2	96.18 88	99.50 37	99.58 32

region2R		97.07 38	96.84 48	97.77 35	99.46 2	93.79 56	98.52 16	98.24 60	93.19 126	97.14 72	98.34 71	91.59 58	99.87 7	95.46 115	99.59 19	99.64 22

ACMMPR		97.07 38	96.84 48	97.79 31	99.44 6	93.88 54	98.52 16	98.31 44	93.21 123	97.15 71	98.33 74	91.35 63	99.86 9	95.63 109	99.59 19	99.62 24

CP-MVS		97.02 40	96.81 53	97.64 46	99.33 23	93.54 61	98.80 9	98.28 49	92.99 136	96.45 107	98.30 79	91.90 51	99.85 18	95.61 111	99.68 4	99.54 42

SR-MVS		97.01 41	96.86 46	97.47 53	99.09 37	93.27 72	97.98 66	98.07 95	93.75 100	97.45 60	98.48 57	91.43 61	99.59 91	96.22 79	99.27 71	99.54 42

fmvsm_s_conf0.5_n_5		97.00 42	96.97 40	97.09 76	97.58 157	92.56 98	97.68 119	98.47 32	94.02 91	98.90 24	98.89 27	88.94 100	99.78 45	99.18 11	99.03 103	98.93 119

ZNCC-MVS		96.96 43	96.67 61	97.85 26	99.37 16	94.12 47	98.49 20	98.18 73	92.64 157	96.39 109	98.18 87	91.61 56	99.88 4	95.59 114	99.55 27	99.57 33

APD-MVS		96.95 44	96.60 63	98.01 20	99.03 44	94.93 27	97.72 113	98.10 88	91.50 194	98.01 46	98.32 76	92.33 43	99.58 94	94.85 129	99.51 35	99.53 45
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MSLP-MVS++		96.94 45	97.06 32	96.59 99	98.72 61	91.86 125	97.67 120	98.49 29	94.66 68	97.24 68	98.41 63	92.31 45	98.94 191	96.61 67	99.46 43	98.96 111

DeepC-MVS_fast	93.89 2	96.93 46	96.64 62	97.78 33	98.64 70	94.30 38	97.41 162	98.04 105	94.81 58	96.59 95	98.37 66	91.24 66	99.64 83	95.16 120	99.52 32	99.42 62
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 47	97.04 36	96.45 115	98.29 89	91.66 134	99.03 4	97.85 133	95.84 17	96.90 79	97.97 105	91.24 66	98.75 219	96.92 56	99.33 66	98.94 115

SR-MVS-dyc-post		96.88 48	96.80 54	97.11 75	99.02 45	92.34 105	97.98 66	98.03 107	93.52 113	97.43 63	98.51 52	91.40 62	99.56 102	96.05 90	99.26 74	99.43 60

CS-MVS		96.86 49	97.06 32	96.26 131	98.16 108	91.16 162	99.09 3	97.87 128	95.30 32	97.06 76	98.03 97	91.72 52	98.71 229	97.10 52	99.17 87	98.90 124

mPP-MVS		96.86 49	96.60 63	97.64 46	99.40 11	93.44 63	98.50 19	98.09 89	93.27 122	95.95 127	98.33 74	91.04 71	99.88 4	95.20 118	99.57 26	99.60 28

fmvsm_s_conf0.5_n		96.85 51	97.13 28	96.04 145	98.07 116	90.28 198	97.97 72	98.76 9	94.93 47	98.84 27	99.06 11	88.80 103	99.65 75	99.06 17	98.63 119	98.18 202

GST-MVS		96.85 51	96.52 67	97.82 28	99.36 20	94.14 46	98.29 30	98.13 81	92.72 153	96.70 87	98.06 94	91.35 63	99.86 9	94.83 131	99.28 70	99.47 55

balanced_conf03		96.84 53	96.89 45	96.68 90	97.63 149	92.22 110	98.17 49	97.82 139	94.44 78	98.23 41	97.36 167	90.97 73	99.22 147	97.74 31	99.66 10	98.61 157

patch_mono-2		96.83 54	97.44 21	95.01 213	99.05 42	85.39 352	96.98 208	98.77 8	94.70 65	97.99 47	98.66 42	93.61 19	99.91 1	97.67 36	99.50 37	99.72 12

APD-MVS_3200maxsize		96.81 55	96.71 60	97.12 73	99.01 48	92.31 107	97.98 66	98.06 98	93.11 132	97.44 61	98.55 48	90.93 75	99.55 104	96.06 89	99.25 76	99.51 46

PGM-MVS		96.81 55	96.53 66	97.65 44	99.35 22	93.53 62	97.65 124	98.98 2	92.22 166	97.14 72	98.44 60	91.17 69	99.85 18	94.35 151	99.46 43	99.57 33

MP-MVS		96.77 57	96.45 74	97.72 40	99.39 13	93.80 55	98.41 24	98.06 98	93.37 118	95.54 145	98.34 71	90.59 81	99.88 4	94.83 131	99.54 29	99.49 51
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PHI-MVS		96.77 57	96.46 73	97.71 42	98.40 82	94.07 49	98.21 43	98.45 34	89.86 262	97.11 74	98.01 100	92.52 40	99.69 69	96.03 93	99.53 30	99.36 69

fmvsm_s_conf0.5_n_4		96.75 59	97.07 31	95.79 168	97.76 138	89.57 224	97.66 123	98.66 19	95.36 29	99.03 15	98.90 24	88.39 111	99.73 57	99.17 12	98.66 117	98.08 216

fmvsm_s_conf0.5_n_a		96.75 59	96.93 43	96.20 136	97.64 147	90.72 180	98.00 62	98.73 10	94.55 72	98.91 23	99.08 7	88.22 115	99.63 84	98.91 20	98.37 132	98.25 197

MGCNet		96.74 61	96.31 78	98.02 19	96.87 198	94.65 30	97.58 135	94.39 401	96.47 11	97.16 70	98.39 64	87.53 133	99.87 7	98.97 19	99.41 56	99.55 40

test_fmvsmvis_n_1920		96.70 62	96.84 48	96.31 125	96.62 223	91.73 127	97.98 66	98.30 45	96.19 13	96.10 120	98.95 19	89.42 93	99.76 50	98.90 21	99.08 98	97.43 256

MP-MVS-pluss		96.70 62	96.27 80	97.98 23	99.23 32	94.71 29	96.96 210	98.06 98	90.67 234	95.55 143	98.78 39	91.07 70	99.86 9	96.58 68	99.55 27	99.38 67
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + GP.		96.69 64	96.49 68	97.27 64	98.31 88	93.39 64	96.79 230	96.72 284	94.17 87	97.44 61	97.66 141	92.76 32	99.33 135	96.86 59	97.76 158	99.08 95

HPM-MVS		96.69 64	96.45 74	97.40 56	99.36 20	93.11 77	98.87 6	98.06 98	91.17 213	96.40 108	97.99 103	90.99 72	99.58 94	95.61 111	99.61 18	99.49 51
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MVS_111021_HR		96.68 66	96.58 65	96.99 81	98.46 76	92.31 107	96.20 291	98.90 3	94.30 85	95.86 130	97.74 132	92.33 43	99.38 132	96.04 92	99.42 53	99.28 74

fmvsm_s_conf0.5_n_2		96.62 67	96.82 52	96.02 147	97.98 122	90.43 190	97.50 148	98.59 24	96.59 9	99.31 5	99.08 7	84.47 193	99.75 54	99.37 5	98.45 129	97.88 229

DELS-MVS		96.61 68	96.38 77	97.30 60	97.79 136	93.19 75	95.96 305	98.18 73	95.23 34	95.87 129	97.65 142	91.45 59	99.70 68	95.87 96	99.44 49	99.00 106
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 68	97.09 30	95.15 204	98.09 112	86.63 319	96.00 303	98.15 78	95.43 27	97.95 49	98.56 46	93.40 21	99.36 133	96.77 60	99.48 41	99.45 56

fmvsm_s_conf0.1_n		96.58 70	96.77 57	96.01 150	96.67 221	90.25 199	97.91 80	98.38 35	94.48 76	98.84 27	99.14 1	88.06 117	99.62 85	98.82 22	98.60 121	98.15 206

MVSMamba_PlusPlus		96.51 71	96.48 69	96.59 99	98.07 116	91.97 121	98.14 50	97.79 141	90.43 249	97.34 66	97.52 157	91.29 65	99.19 150	98.12 27	99.64 14	98.60 158

EI-MVSNet-Vis-set		96.51 71	96.47 70	96.63 95	98.24 96	91.20 156	96.89 218	97.73 148	94.74 64	96.49 102	98.49 54	90.88 77	99.58 94	96.44 72	98.32 134	99.13 86

HPM-MVS_fast		96.51 71	96.27 80	97.22 67	99.32 24	92.74 90	98.74 10	98.06 98	90.57 244	96.77 84	98.35 68	90.21 84	99.53 108	94.80 135	99.63 16	99.38 67

fmvsm_s_conf0.5_n_7		96.45 74	96.80 54	95.37 196	97.29 165	88.38 268	97.23 185	98.47 32	95.14 38	98.43 37	99.09 6	87.58 130	99.72 61	98.80 24	99.21 79	98.02 220

EC-MVSNet		96.42 75	96.47 70	96.26 131	97.01 187	91.52 140	98.89 5	97.75 145	94.42 79	96.64 92	97.68 138	89.32 94	98.60 245	97.45 45	99.11 97	98.67 155

fmvsm_s_conf0.1_n_a		96.40 76	96.47 70	96.16 138	95.48 304	90.69 181	97.91 80	98.33 42	94.07 89	98.93 19	99.14 1	87.44 137	99.61 86	98.63 25	98.32 134	98.18 202

CANet		96.39 77	96.02 85	97.50 51	97.62 150	93.38 65	97.02 201	97.96 118	95.42 28	94.86 160	97.81 125	87.38 139	99.82 30	96.88 57	99.20 84	99.29 72

dcpmvs_2		96.37 78	97.05 35	94.31 259	98.96 52	84.11 373	97.56 139	97.51 181	93.92 95	97.43 63	98.52 51	92.75 33	99.32 137	97.32 51	99.50 37	99.51 46

NormalMVS		96.36 79	96.11 83	97.12 73	99.37 16	92.90 84	97.99 63	97.63 162	95.92 15	96.57 98	97.93 107	85.34 175	99.50 116	94.99 125	99.21 79	98.97 108

EI-MVSNet-UG-set		96.34 80	96.30 79	96.47 112	98.20 103	90.93 170	96.86 221	97.72 150	94.67 67	96.16 118	98.46 58	90.43 82	99.58 94	96.23 78	97.96 151	98.90 124

fmvsm_s_conf0.1_n_2		96.33 81	96.44 76	96.00 151	97.30 164	90.37 196	97.53 145	97.92 123	96.52 10	99.14 14	99.08 7	83.21 215	99.74 55	99.22 10	98.06 146	97.88 229

train_agg		96.30 82	95.83 90	97.72 40	98.70 62	94.19 43	96.41 267	98.02 110	88.58 308	96.03 122	97.56 154	92.73 35	99.59 91	95.04 122	99.37 64	99.39 65

ACMMP		96.27 83	95.93 86	97.28 63	99.24 30	92.62 95	98.25 36	98.81 6	92.99 136	94.56 170	98.39 64	88.96 99	99.85 18	94.57 145	97.63 159	99.36 69
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 84	96.19 82	96.39 120	98.23 101	91.35 149	96.24 289	98.79 7	93.99 93	95.80 132	97.65 142	89.92 89	99.24 145	95.87 96	99.20 84	98.58 161

test_fmvsmconf0.01_n		96.15 85	95.85 89	97.03 80	92.66 418	91.83 126	97.97 72	97.84 137	95.57 25	97.53 57	99.00 15	84.20 199	99.76 50	98.82 22	99.08 98	99.48 53

DeepC-MVS	93.07 3	96.06 86	95.66 91	97.29 61	97.96 124	93.17 76	97.30 177	98.06 98	93.92 95	93.38 210	98.66 42	86.83 146	99.73 57	95.60 113	99.22 78	98.96 111
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 87	95.91 87	96.46 114	99.24 30	90.47 187	98.30 29	98.57 26	89.01 290	93.97 191	97.57 152	92.62 38	99.76 50	94.66 139	99.27 71	99.15 84

sasdasda		96.02 88	95.45 98	97.75 37	97.59 153	95.15 23	98.28 31	97.60 167	94.52 74	96.27 113	96.12 247	87.65 127	99.18 153	96.20 84	94.82 244	98.91 121

ETV-MVS		96.02 88	95.89 88	96.40 118	97.16 172	92.44 102	97.47 157	97.77 144	94.55 72	96.48 103	94.51 329	91.23 68	98.92 194	95.65 107	98.19 140	97.82 237

canonicalmvs		96.02 88	95.45 98	97.75 37	97.59 153	95.15 23	98.28 31	97.60 167	94.52 74	96.27 113	96.12 247	87.65 127	99.18 153	96.20 84	94.82 244	98.91 121

CDPH-MVS		95.97 91	95.38 103	97.77 35	98.93 53	94.44 36	96.35 276	97.88 126	86.98 354	96.65 91	97.89 112	91.99 49	99.47 121	92.26 191	99.46 43	99.39 65

UA-Net		95.95 92	95.53 94	97.20 69	97.67 143	92.98 81	97.65 124	98.13 81	94.81 58	96.61 93	98.35 68	88.87 101	99.51 113	90.36 243	97.35 170	99.11 91

SymmetryMVS		95.94 93	95.54 93	97.15 71	97.85 132	92.90 84	97.99 63	96.91 271	95.92 15	96.57 98	97.93 107	85.34 175	99.50 116	94.99 125	96.39 209	99.05 99

MGCFI-Net		95.94 93	95.40 102	97.56 50	97.59 153	94.62 31	98.21 43	97.57 172	94.41 80	96.17 117	96.16 245	87.54 132	99.17 155	96.19 86	94.73 249	98.91 121

BP-MVS1		95.89 95	95.49 95	97.08 78	96.67 221	93.20 74	98.08 54	96.32 309	94.56 71	96.32 110	97.84 121	84.07 202	99.15 159	96.75 61	98.78 112	98.90 124

VNet		95.89 95	95.45 98	97.21 68	98.07 116	92.94 82	97.50 148	98.15 78	93.87 97	97.52 58	97.61 148	85.29 177	99.53 108	95.81 101	95.27 235	99.16 82

alignmvs		95.87 97	95.23 108	97.78 33	97.56 159	95.19 21	97.86 86	97.17 236	94.39 82	96.47 104	96.40 232	85.89 162	99.20 149	96.21 83	95.11 240	98.95 114

casdiffmvs_mvg		95.81 98	95.57 92	96.51 108	96.87 198	91.49 141	97.50 148	97.56 176	93.99 93	95.13 155	97.92 110	87.89 121	98.78 211	95.97 94	97.33 171	99.26 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
DPM-MVS		95.69 99	94.92 118	98.01 20	98.08 115	95.71 9	95.27 346	97.62 166	90.43 249	95.55 143	97.07 187	91.72 52	99.50 116	89.62 259	98.94 107	98.82 139

DP-MVS Recon		95.68 100	95.12 113	97.37 57	99.19 34	94.19 43	97.03 199	98.08 90	88.35 317	95.09 156	97.65 142	89.97 88	99.48 120	92.08 202	98.59 122	98.44 179

casdiffmvs		95.64 101	95.49 95	96.08 141	96.76 218	90.45 188	97.29 178	97.44 201	94.00 92	95.46 148	97.98 104	87.52 135	98.73 223	95.64 108	97.33 171	99.08 95
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		95.62 102	95.13 111	97.09 76	96.79 209	93.26 73	97.89 83	97.83 138	93.58 105	96.80 81	97.82 123	83.06 222	99.16 157	94.40 148	97.95 152	98.87 133

MG-MVS		95.61 103	95.38 103	96.31 125	98.42 80	90.53 185	96.04 300	97.48 186	93.47 115	95.67 140	98.10 90	89.17 96	99.25 144	91.27 220	98.77 113	99.13 86

baseline		95.58 104	95.42 101	96.08 141	96.78 213	90.41 191	97.16 192	97.45 197	93.69 104	95.65 141	97.85 119	87.29 140	98.68 233	95.66 104	97.25 177	99.13 86

CPTT-MVS		95.57 105	95.19 109	96.70 89	99.27 28	91.48 143	98.33 27	98.11 86	87.79 335	95.17 154	98.03 97	87.09 144	99.61 86	93.51 169	99.42 53	99.02 100

EIA-MVS		95.53 106	95.47 97	95.71 176	97.06 180	89.63 220	97.82 95	97.87 128	93.57 106	93.92 192	95.04 301	90.61 80	98.95 189	94.62 141	98.68 116	98.54 164

3Dnovator+	91.43 4	95.40 107	94.48 139	98.16 16	96.90 196	95.34 16	98.48 21	97.87 128	94.65 69	88.53 340	98.02 99	83.69 206	99.71 63	93.18 177	98.96 106	99.44 58

PS-MVSNAJ		95.37 108	95.33 105	95.49 190	97.35 163	90.66 183	95.31 343	97.48 186	93.85 98	96.51 101	95.70 272	88.65 106	99.65 75	94.80 135	98.27 137	96.17 295

MVSFormer		95.37 108	95.16 110	95.99 152	96.34 255	91.21 154	98.22 41	97.57 172	91.42 198	96.22 115	97.32 168	86.20 158	97.92 329	94.07 154	99.05 100	98.85 135

diffmvs_AUTHOR		95.33 110	95.27 107	95.50 189	96.37 253	89.08 250	96.08 298	97.38 212	93.09 134	96.53 100	97.74 132	86.45 152	98.68 233	96.32 74	97.48 162	98.75 146

xiu_mvs_v2_base		95.32 111	95.29 106	95.40 195	97.22 168	90.50 186	95.44 336	97.44 201	93.70 103	96.46 105	96.18 242	88.59 110	99.53 108	94.79 138	97.81 155	96.17 295

PVSNet_Blended_VisFu		95.27 112	94.91 119	96.38 121	98.20 103	90.86 173	97.27 179	98.25 58	90.21 253	94.18 184	97.27 174	87.48 136	99.73 57	93.53 168	97.77 157	98.55 163

viewcassd2359sk11		95.26 113	95.09 114	95.80 166	96.95 193	89.72 218	96.80 229	97.56 176	92.21 168	95.37 149	97.80 127	87.17 143	98.77 214	94.82 133	97.10 183	98.90 124

KinetiMVS		95.26 113	94.75 125	96.79 87	96.99 189	92.05 117	97.82 95	97.78 142	94.77 62	96.46 105	97.70 135	80.62 276	99.34 134	92.37 190	98.28 136	98.97 108

diffmvs		95.25 115	95.13 111	95.63 179	96.43 248	89.34 237	95.99 304	97.35 217	92.83 149	96.31 111	97.37 166	86.44 153	98.67 236	96.26 76	97.19 180	98.87 133
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		95.24 116	95.02 116	95.91 155	96.87 198	89.98 208	96.82 226	97.49 184	92.26 164	95.47 147	97.82 123	86.47 151	98.69 231	94.80 135	97.20 179	99.06 98

Vis-MVSNet		95.23 117	94.81 120	96.51 108	97.18 171	91.58 138	98.26 35	98.12 83	94.38 83	94.90 159	98.15 89	82.28 243	98.92 194	91.45 217	98.58 123	99.01 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPP-MVSNet		95.22 118	95.04 115	95.76 169	97.49 160	89.56 225	98.67 11	97.00 261	90.69 232	94.24 180	97.62 147	89.79 91	98.81 207	93.39 174	96.49 206	98.92 120

EPNet		95.20 119	94.56 132	97.14 72	92.80 415	92.68 94	97.85 89	94.87 385	96.64 8	92.46 227	97.80 127	86.23 155	99.65 75	93.72 164	98.62 120	99.10 92
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator	91.36 5	95.19 120	94.44 141	97.44 54	96.56 231	93.36 67	98.65 12	98.36 36	94.12 88	89.25 323	98.06 94	82.20 245	99.77 48	93.41 173	99.32 67	99.18 81

guyue		95.17 121	94.96 117	95.82 164	96.97 191	89.65 219	97.56 139	95.58 347	94.82 56	95.72 135	97.42 163	82.90 227	98.84 203	96.71 64	96.93 187	98.96 111

OMC-MVS		95.09 122	94.70 126	96.25 134	98.46 76	91.28 150	96.43 263	97.57 172	92.04 176	94.77 165	97.96 106	87.01 145	99.09 170	91.31 219	96.77 191	98.36 186

viewmacassd2359aftdt		95.07 123	94.80 121	95.87 158	96.53 236	89.84 214	96.90 217	97.48 186	92.44 159	95.36 150	97.89 112	85.23 178	98.68 233	94.40 148	97.00 186	99.09 93

xiu_mvs_v1_base_debu		95.01 124	94.76 122	95.75 171	96.58 227	91.71 130	96.25 286	97.35 217	92.99 136	96.70 87	96.63 219	82.67 233	99.44 125	96.22 79	97.46 163	96.11 301

xiu_mvs_v1_base		95.01 124	94.76 122	95.75 171	96.58 227	91.71 130	96.25 286	97.35 217	92.99 136	96.70 87	96.63 219	82.67 233	99.44 125	96.22 79	97.46 163	96.11 301

xiu_mvs_v1_base_debi		95.01 124	94.76 122	95.75 171	96.58 227	91.71 130	96.25 286	97.35 217	92.99 136	96.70 87	96.63 219	82.67 233	99.44 125	96.22 79	97.46 163	96.11 301

PAPM_NR		95.01 124	94.59 130	96.26 131	98.89 57	90.68 182	97.24 181	97.73 148	91.80 181	92.93 224	96.62 222	89.13 97	99.14 162	89.21 272	97.78 156	98.97 108

lupinMVS		94.99 128	94.56 132	96.29 129	96.34 255	91.21 154	95.83 313	96.27 313	88.93 296	96.22 115	96.88 201	86.20 158	98.85 201	95.27 117	99.05 100	98.82 139

Effi-MVS+		94.93 129	94.45 140	96.36 123	96.61 224	91.47 144	96.41 267	97.41 207	91.02 221	94.50 173	95.92 256	87.53 133	98.78 211	93.89 160	96.81 190	98.84 138

IS-MVSNet		94.90 130	94.52 136	96.05 144	97.67 143	90.56 184	98.44 22	96.22 316	93.21 123	93.99 189	97.74 132	85.55 172	98.45 259	89.98 248	97.86 153	99.14 85

LuminaMVS		94.89 131	94.35 144	96.53 102	95.48 304	92.80 88	96.88 220	96.18 320	92.85 148	95.92 128	96.87 203	81.44 260	98.83 204	96.43 73	97.10 183	97.94 225

MVS_Test		94.89 131	94.62 129	95.68 177	96.83 204	89.55 226	96.70 241	97.17 236	91.17 213	95.60 142	96.11 251	87.87 123	98.76 216	93.01 185	97.17 181	98.72 150

viewdifsd2359ckpt13		94.87 133	94.52 136	95.90 156	96.88 197	90.19 201	96.92 214	97.36 215	91.26 206	94.65 167	97.46 158	85.79 166	98.64 240	93.64 166	96.76 192	98.88 132

PVSNet_Blended		94.87 133	94.56 132	95.81 165	98.27 92	89.46 232	95.47 335	98.36 36	88.84 299	94.36 176	96.09 252	88.02 118	99.58 94	93.44 171	98.18 141	98.40 182

jason		94.84 135	94.39 142	96.18 137	95.52 302	90.93 170	96.09 297	96.52 299	89.28 281	96.01 125	97.32 168	84.70 189	98.77 214	95.15 121	98.91 109	98.85 135
jason: jason.
API-MVS		94.84 135	94.49 138	95.90 156	97.90 130	92.00 120	97.80 99	97.48 186	89.19 284	94.81 163	96.71 208	88.84 102	99.17 155	88.91 279	98.76 114	96.53 284

AstraMVS		94.82 137	94.64 128	95.34 198	96.36 254	88.09 280	97.58 135	94.56 394	94.98 45	95.70 138	97.92 110	81.93 253	98.93 192	96.87 58	95.88 216	98.99 107

viewdifsd2359ckpt09		94.81 138	94.37 143	96.12 140	96.91 194	90.75 179	96.94 211	97.31 222	90.51 247	94.31 178	97.38 165	85.70 168	98.71 229	93.54 167	96.75 193	98.90 124

test_yl		94.78 139	94.23 147	96.43 116	97.74 139	91.22 152	96.85 222	97.10 242	91.23 210	95.71 136	96.93 196	84.30 196	99.31 139	93.10 178	95.12 238	98.75 146

DCV-MVSNet		94.78 139	94.23 147	96.43 116	97.74 139	91.22 152	96.85 222	97.10 242	91.23 210	95.71 136	96.93 196	84.30 196	99.31 139	93.10 178	95.12 238	98.75 146

viewdifsd2359ckpt07		94.76 141	94.68 127	95.01 213	96.76 218	87.41 295	96.38 273	97.43 204	92.65 155	94.52 171	97.75 130	85.55 172	98.81 207	94.36 150	96.69 197	98.82 139

SSM_0404		94.73 142	94.31 146	95.98 153	97.05 182	90.90 172	97.01 204	97.29 223	91.24 207	94.17 185	97.60 149	85.03 182	98.76 216	92.14 196	97.30 174	98.29 195

WTY-MVS		94.71 143	94.02 152	96.79 87	97.71 141	92.05 117	96.59 256	97.35 217	90.61 240	94.64 168	96.93 196	86.41 154	99.39 130	91.20 222	94.71 250	98.94 115

mamv4		94.66 144	96.10 84	90.37 399	98.01 119	73.41 450	96.82 226	97.78 142	89.95 260	94.52 171	97.43 162	92.91 28	99.09 170	98.28 26	99.16 90	98.60 158

mvsmamba		94.57 145	94.14 149	95.87 158	97.03 185	89.93 212	97.84 90	95.85 331	91.34 201	94.79 164	96.80 204	80.67 274	98.81 207	94.85 129	98.12 144	98.85 135

SSM_0407		94.54 146	94.12 151	95.80 166	96.79 209	90.38 193	96.79 230	97.29 223	91.24 207	93.68 196	97.60 149	85.03 182	98.67 236	92.14 196	96.51 202	98.35 188

RRT-MVS		94.51 147	94.35 144	94.98 217	96.40 249	86.55 322	97.56 139	97.41 207	93.19 126	94.93 158	97.04 189	79.12 304	99.30 141	96.19 86	97.32 173	99.09 93

sss		94.51 147	93.80 156	96.64 91	97.07 177	91.97 121	96.32 281	98.06 98	88.94 295	94.50 173	96.78 205	84.60 190	99.27 143	91.90 203	96.02 212	98.68 154

test_cas_vis1_n_1920		94.48 149	94.55 135	94.28 261	96.78 213	86.45 324	97.63 130	97.64 160	93.32 121	97.68 56	98.36 67	73.75 367	99.08 173	96.73 62	99.05 100	97.31 263

CANet_DTU		94.37 150	93.65 162	96.55 101	96.46 246	92.13 115	96.21 290	96.67 291	94.38 83	93.53 204	97.03 194	79.34 300	99.71 63	90.76 232	98.45 129	97.82 237

AdaColmap		94.34 151	93.68 161	96.31 125	98.59 72	91.68 133	96.59 256	97.81 140	89.87 261	92.15 238	97.06 188	83.62 209	99.54 106	89.34 266	98.07 145	97.70 242

viewmambaseed2359dif		94.28 152	94.14 149	94.71 235	96.21 259	86.97 309	95.93 307	97.11 241	89.00 291	95.00 157	97.70 135	86.02 161	98.59 249	93.71 165	96.59 201	98.57 162

CNLPA		94.28 152	93.53 167	96.52 104	98.38 85	92.55 99	96.59 256	96.88 275	90.13 257	91.91 246	97.24 176	85.21 179	99.09 170	87.64 305	97.83 154	97.92 226

MAR-MVS		94.22 154	93.46 172	96.51 108	98.00 121	92.19 114	97.67 120	97.47 190	88.13 325	93.00 219	95.84 260	84.86 188	99.51 113	87.99 292	98.17 142	97.83 236
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		94.18 155	93.42 177	96.48 111	97.64 147	91.42 147	95.55 330	97.71 154	88.99 292	92.34 234	95.82 262	89.19 95	99.11 165	86.14 331	97.38 168	98.90 124

SDMVSNet		94.17 156	93.61 163	95.86 161	98.09 112	91.37 148	97.35 171	98.20 66	93.18 128	91.79 250	97.28 172	79.13 303	98.93 192	94.61 142	92.84 282	97.28 264

test_vis1_n_1920		94.17 156	94.58 131	92.91 330	97.42 162	82.02 400	97.83 93	97.85 133	94.68 66	98.10 44	98.49 54	70.15 391	99.32 137	97.91 29	98.82 110	97.40 258

h-mvs33		94.15 158	93.52 169	96.04 145	97.81 135	90.22 200	97.62 132	97.58 171	95.19 35	96.74 85	97.45 159	83.67 207	99.61 86	95.85 98	79.73 422	98.29 195

CHOSEN 1792x2688		94.15 158	93.51 170	96.06 143	98.27 92	89.38 235	95.18 353	98.48 31	85.60 377	93.76 195	97.11 185	83.15 218	99.61 86	91.33 218	98.72 115	99.19 80

Vis-MVSNet (Re-imp)		94.15 158	93.88 155	94.95 221	97.61 151	87.92 284	98.10 52	95.80 334	92.22 166	93.02 218	97.45 159	84.53 192	97.91 332	88.24 288	97.97 150	99.02 100

CDS-MVSNet		94.14 161	93.54 166	95.93 154	96.18 267	91.46 145	96.33 280	97.04 256	88.97 294	93.56 201	96.51 226	87.55 131	97.89 333	89.80 253	95.95 214	98.44 179
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PLC	91.00 6	94.11 162	93.43 175	96.13 139	98.58 74	91.15 163	96.69 243	97.39 209	87.29 349	91.37 260	96.71 208	88.39 111	99.52 112	87.33 312	97.13 182	97.73 240
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
FIs		94.09 163	93.70 160	95.27 200	95.70 293	92.03 119	98.10 52	98.68 16	93.36 120	90.39 281	96.70 210	87.63 129	97.94 326	92.25 193	90.50 323	95.84 309

PVSNet_BlendedMVS		94.06 164	93.92 154	94.47 248	98.27 92	89.46 232	96.73 237	98.36 36	90.17 254	94.36 176	95.24 295	88.02 118	99.58 94	93.44 171	90.72 319	94.36 394

nrg030		94.05 165	93.31 179	96.27 130	95.22 327	94.59 32	98.34 26	97.46 192	92.93 143	91.21 270	96.64 215	87.23 142	98.22 279	94.99 125	85.80 370	95.98 305

UGNet		94.04 166	93.28 180	96.31 125	96.85 201	91.19 157	97.88 85	97.68 155	94.40 81	93.00 219	96.18 242	73.39 369	99.61 86	91.72 209	98.46 128	98.13 207
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		94.01 167	93.46 172	95.64 178	96.16 269	90.45 188	96.71 240	96.89 274	89.27 282	93.46 208	96.92 199	87.29 140	97.94 326	88.70 284	95.74 220	98.53 165

Elysia		94.00 168	93.12 185	96.64 91	96.08 279	92.72 92	97.50 148	97.63 162	91.15 215	94.82 161	97.12 183	74.98 354	99.06 179	90.78 230	98.02 147	98.12 209

StellarMVS		94.00 168	93.12 185	96.64 91	96.08 279	92.72 92	97.50 148	97.63 162	91.15 215	94.82 161	97.12 183	74.98 354	99.06 179	90.78 230	98.02 147	98.12 209

IMVS_0403		93.98 170	93.79 157	94.55 244	96.19 263	86.16 333	96.35 276	97.24 230	91.54 189	93.59 200	97.04 189	85.86 163	98.73 223	90.68 235	95.59 226	98.76 142

114514_t		93.95 171	93.06 188	96.63 95	99.07 40	91.61 135	97.46 159	97.96 118	77.99 441	93.00 219	97.57 152	86.14 160	99.33 135	89.22 271	99.15 91	98.94 115

IMVS_0407		93.94 172	93.75 158	94.49 247	96.19 263	86.16 333	96.35 276	97.24 230	91.54 189	93.50 205	97.04 189	85.64 170	98.54 252	90.68 235	95.59 226	98.76 142

FC-MVSNet-test		93.94 172	93.57 164	95.04 211	95.48 304	91.45 146	98.12 51	98.71 13	93.37 118	90.23 284	96.70 210	87.66 126	97.85 335	91.49 215	90.39 324	95.83 310

mvsany_test1		93.93 174	93.98 153	93.78 293	94.94 344	86.80 312	94.62 365	92.55 434	88.77 305	96.85 80	98.49 54	88.98 98	98.08 297	95.03 123	95.62 225	96.46 289

GeoE		93.89 175	93.28 180	95.72 175	96.96 192	89.75 217	98.24 39	96.92 270	89.47 275	92.12 240	97.21 178	84.42 194	98.39 267	87.71 299	96.50 205	99.01 103

HY-MVS	89.66 9	93.87 176	92.95 193	96.63 95	97.10 176	92.49 101	95.64 327	96.64 292	89.05 289	93.00 219	95.79 266	85.77 167	99.45 124	89.16 275	94.35 252	97.96 223

XVG-OURS-SEG-HR		93.86 177	93.55 165	94.81 227	97.06 180	88.53 264	95.28 344	97.45 197	91.68 186	94.08 188	97.68 138	82.41 241	98.90 197	93.84 162	92.47 288	96.98 272

VDD-MVS		93.82 178	93.08 187	96.02 147	97.88 131	89.96 211	97.72 113	95.85 331	92.43 160	95.86 130	98.44 60	68.42 408	99.39 130	96.31 75	94.85 242	98.71 152

mvs_anonymous		93.82 178	93.74 159	94.06 271	96.44 247	85.41 350	95.81 314	97.05 254	89.85 264	90.09 294	96.36 234	87.44 137	97.75 349	93.97 156	96.69 197	99.02 100

HQP_MVS		93.78 180	93.43 175	94.82 225	96.21 259	89.99 206	97.74 108	97.51 181	94.85 52	91.34 261	96.64 215	81.32 262	98.60 245	93.02 183	92.23 291	95.86 306

PS-MVSNAJss		93.74 181	93.51 170	94.44 250	93.91 382	89.28 242	97.75 105	97.56 176	92.50 158	89.94 297	96.54 225	88.65 106	98.18 284	93.83 163	90.90 317	95.86 306

XVG-OURS		93.72 182	93.35 178	94.80 230	97.07 177	88.61 259	94.79 362	97.46 192	91.97 179	93.99 189	97.86 118	81.74 256	98.88 198	92.64 189	92.67 287	96.92 276

mamba_0408		93.70 183	92.99 189	95.83 163	96.79 209	90.38 193	88.69 452	97.07 248	90.96 223	93.68 196	97.31 170	84.97 185	98.76 216	90.95 226	96.51 202	98.35 188

HyFIR lowres test		93.66 184	92.92 194	95.87 158	98.24 96	89.88 213	94.58 367	98.49 29	85.06 387	93.78 194	95.78 267	82.86 228	98.67 236	91.77 208	95.71 222	99.07 97

LFMVS		93.60 185	92.63 208	96.52 104	98.13 111	91.27 151	97.94 76	93.39 422	90.57 244	96.29 112	98.31 77	69.00 401	99.16 157	94.18 153	95.87 217	99.12 89

icg_test_0407_2		93.58 186	93.46 172	93.94 283	96.19 263	86.16 333	93.73 402	97.24 230	91.54 189	93.50 205	97.04 189	85.64 170	96.91 399	90.68 235	95.59 226	98.76 142

F-COLMAP		93.58 186	92.98 192	95.37 196	98.40 82	88.98 252	97.18 190	97.29 223	87.75 338	90.49 279	97.10 186	85.21 179	99.50 116	86.70 322	96.72 196	97.63 244

ab-mvs		93.57 188	92.55 212	96.64 91	97.28 166	91.96 123	95.40 337	97.45 197	89.81 266	93.22 216	96.28 238	79.62 297	99.46 122	90.74 233	93.11 279	98.50 169

LS3D		93.57 188	92.61 210	96.47 112	97.59 153	91.61 135	97.67 120	97.72 150	85.17 385	90.29 283	98.34 71	84.60 190	99.73 57	83.85 367	98.27 137	98.06 218

FA-MVS(test-final)		93.52 190	92.92 194	95.31 199	96.77 215	88.54 263	94.82 361	96.21 318	89.61 270	94.20 182	95.25 294	83.24 214	99.14 162	90.01 247	96.16 211	98.25 197

SSM_04072		93.51 191	92.99 189	95.05 209	96.79 209	90.38 193	88.69 452	97.07 248	90.96 223	93.68 196	97.31 170	84.97 185	96.42 410	90.95 226	96.51 202	98.35 188

viewdifsd2359ckpt11		93.46 192	93.22 183	94.17 264	96.11 276	85.42 348	96.43 263	97.07 248	92.91 144	94.20 182	98.00 101	80.82 272	98.73 223	94.42 146	89.04 337	98.34 192

viewmsd2359difaftdt		93.46 192	93.23 182	94.17 264	96.12 274	85.42 348	96.43 263	97.08 245	92.91 144	94.21 181	98.00 101	80.82 272	98.74 221	94.41 147	89.05 335	98.34 192

Fast-Effi-MVS+		93.46 192	92.75 202	95.59 182	96.77 215	90.03 203	96.81 228	97.13 238	88.19 320	91.30 264	94.27 347	86.21 157	98.63 242	87.66 304	96.46 208	98.12 209

hse-mvs2		93.45 195	92.99 189	94.81 227	97.02 186	88.59 260	96.69 243	96.47 302	95.19 35	96.74 85	96.16 245	83.67 207	98.48 258	95.85 98	79.13 426	97.35 261

QAPM		93.45 195	92.27 222	96.98 82	96.77 215	92.62 95	98.39 25	98.12 83	84.50 395	88.27 348	97.77 129	82.39 242	99.81 32	85.40 344	98.81 111	98.51 168

UniMVSNet_NR-MVSNet		93.37 197	92.67 206	95.47 193	95.34 316	92.83 86	97.17 191	98.58 25	92.98 141	90.13 289	95.80 263	88.37 113	97.85 335	91.71 210	83.93 399	95.73 320

1112_ss		93.37 197	92.42 219	96.21 135	97.05 182	90.99 166	96.31 282	96.72 284	86.87 357	89.83 301	96.69 212	86.51 150	99.14 162	88.12 289	93.67 273	98.50 169

UniMVSNet (Re)		93.31 199	92.55 212	95.61 181	95.39 310	93.34 68	97.39 167	98.71 13	93.14 131	90.10 293	94.83 312	87.71 125	98.03 308	91.67 213	83.99 398	95.46 329

OPM-MVS		93.28 200	92.76 200	94.82 225	94.63 360	90.77 177	96.65 247	97.18 234	93.72 101	91.68 254	97.26 175	79.33 301	98.63 242	92.13 199	92.28 290	95.07 357
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		93.24 201	92.48 217	95.51 187	95.70 293	92.39 103	97.86 86	98.66 19	92.30 163	92.09 242	95.37 287	80.49 279	98.40 262	93.95 157	85.86 369	95.75 318

test_fmvs1		93.21 202	93.53 167	92.25 353	96.55 233	81.20 407	97.40 166	96.96 263	90.68 233	96.80 81	98.04 96	69.25 399	98.40 262	97.58 40	98.50 124	97.16 269

MVSTER		93.20 203	92.81 199	94.37 253	96.56 231	89.59 223	97.06 198	97.12 239	91.24 207	91.30 264	95.96 254	82.02 249	98.05 304	93.48 170	90.55 321	95.47 328

test1111		93.19 204	92.82 198	94.30 260	97.58 157	84.56 367	98.21 43	89.02 453	93.53 111	94.58 169	98.21 84	72.69 370	99.05 182	93.06 181	98.48 127	99.28 74

ECVR-MVS		93.19 204	92.73 204	94.57 243	97.66 145	85.41 350	98.21 43	88.23 455	93.43 116	94.70 166	98.21 84	72.57 371	99.07 177	93.05 182	98.49 125	99.25 77

HQP-MVS		93.19 204	92.74 203	94.54 245	95.86 285	89.33 238	96.65 247	97.39 209	93.55 107	90.14 285	95.87 258	80.95 266	98.50 255	92.13 199	92.10 296	95.78 314

CHOSEN 280x420		93.12 207	92.72 205	94.34 256	96.71 220	87.27 299	90.29 442	97.72 150	86.61 361	91.34 261	95.29 289	84.29 198	98.41 261	93.25 175	98.94 107	97.35 261

sd_testset		93.10 208	92.45 218	95.05 209	98.09 112	89.21 244	96.89 218	97.64 160	93.18 128	91.79 250	97.28 172	75.35 351	98.65 239	88.99 277	92.84 282	97.28 264

Effi-MVS+-dtu		93.08 209	93.21 184	92.68 341	96.02 282	83.25 383	97.14 194	96.72 284	93.85 98	91.20 271	93.44 385	83.08 220	98.30 274	91.69 212	95.73 221	96.50 286

test_djsdf		93.07 210	92.76 200	94.00 275	93.49 397	88.70 258	98.22 41	97.57 172	91.42 198	90.08 295	95.55 280	82.85 229	97.92 329	94.07 154	91.58 303	95.40 336

VDDNet		93.05 211	92.07 226	96.02 147	96.84 202	90.39 192	98.08 54	95.85 331	86.22 369	95.79 133	98.46 58	67.59 411	99.19 150	94.92 128	94.85 242	98.47 174

thisisatest0530		93.03 212	92.21 224	95.49 190	97.07 177	89.11 249	97.49 156	92.19 436	90.16 255	94.09 187	96.41 231	76.43 342	99.05 182	90.38 242	95.68 223	98.31 194

EI-MVSNet		93.03 212	92.88 196	93.48 309	95.77 291	86.98 308	96.44 261	97.12 239	90.66 236	91.30 264	97.64 145	86.56 148	98.05 304	89.91 250	90.55 321	95.41 333

CLD-MVS		92.98 214	92.53 214	94.32 257	96.12 274	89.20 245	95.28 344	97.47 190	92.66 154	89.90 298	95.62 276	80.58 277	98.40 262	92.73 188	92.40 289	95.38 338
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tttt0517		92.96 215	92.33 221	94.87 224	97.11 175	87.16 305	97.97 72	92.09 437	90.63 238	93.88 193	97.01 195	76.50 339	99.06 179	90.29 245	95.45 232	98.38 184

ACMM	89.79 8	92.96 215	92.50 216	94.35 254	96.30 257	88.71 257	97.58 135	97.36 215	91.40 200	90.53 278	96.65 214	79.77 293	98.75 219	91.24 221	91.64 301	95.59 324
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LPG-MVS_test		92.94 217	92.56 211	94.10 269	96.16 269	88.26 272	97.65 124	97.46 192	91.29 202	90.12 291	97.16 180	79.05 306	98.73 223	92.25 193	91.89 299	95.31 343

BH-untuned		92.94 217	92.62 209	93.92 287	97.22 168	86.16 333	96.40 271	96.25 315	90.06 258	89.79 302	96.17 244	83.19 216	98.35 270	87.19 315	97.27 176	97.24 266

DU-MVS		92.90 219	92.04 228	95.49 190	94.95 342	92.83 86	97.16 192	98.24 60	93.02 135	90.13 289	95.71 270	83.47 210	97.85 335	91.71 210	83.93 399	95.78 314

PatchMatch-RL		92.90 219	92.02 230	95.56 183	98.19 105	90.80 175	95.27 346	97.18 234	87.96 327	91.86 249	95.68 273	80.44 280	98.99 187	84.01 362	97.54 161	96.89 277

VortexMVS		92.88 221	92.64 207	93.58 304	96.58 227	87.53 294	96.93 213	97.28 226	92.78 152	89.75 303	94.99 302	82.73 232	97.76 347	94.60 143	88.16 346	95.46 329

PMMVS		92.86 222	92.34 220	94.42 252	94.92 345	86.73 315	94.53 369	96.38 307	84.78 392	94.27 179	95.12 300	83.13 219	98.40 262	91.47 216	96.49 206	98.12 209

OpenMVS	89.19 12	92.86 222	91.68 243	96.40 118	95.34 316	92.73 91	98.27 33	98.12 83	84.86 390	85.78 392	97.75 130	78.89 313	99.74 55	87.50 309	98.65 118	96.73 281

Test_1112_low_res		92.84 224	91.84 237	95.85 162	97.04 184	89.97 210	95.53 332	96.64 292	85.38 380	89.65 308	95.18 296	85.86 163	99.10 167	87.70 300	93.58 278	98.49 171

baseline1		92.82 225	91.90 235	95.55 185	97.20 170	90.77 177	97.19 189	94.58 393	92.20 169	92.36 231	96.34 235	84.16 200	98.21 280	89.20 273	83.90 402	97.68 243

1314		92.81 226	92.03 229	95.14 205	95.33 319	89.52 229	96.04 300	97.44 201	87.72 339	86.25 389	95.33 288	83.84 204	98.79 210	89.26 269	97.05 185	97.11 270

DP-MVS		92.76 227	91.51 251	96.52 104	98.77 59	90.99 166	97.38 169	96.08 323	82.38 417	89.29 320	97.87 116	83.77 205	99.69 69	81.37 390	96.69 197	98.89 130

test_fmvs1_n		92.73 228	92.88 196	92.29 350	96.08 279	81.05 408	97.98 66	97.08 245	90.72 231	96.79 83	98.18 87	63.07 434	98.45 259	97.62 39	98.42 131	97.36 259

BH-RMVSNet		92.72 229	91.97 232	94.97 219	97.16 172	87.99 282	96.15 295	95.60 345	90.62 239	91.87 248	97.15 182	78.41 319	98.57 250	83.16 369	97.60 160	98.36 186

ACMP	89.59 10	92.62 230	92.14 225	94.05 272	96.40 249	88.20 275	97.36 170	97.25 229	91.52 193	88.30 346	96.64 215	78.46 318	98.72 228	91.86 206	91.48 305	95.23 350
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LCM-MVSNet-Re		92.50 231	92.52 215	92.44 343	96.82 206	81.89 401	96.92 214	93.71 419	92.41 161	84.30 405	94.60 324	85.08 181	97.03 393	91.51 214	97.36 169	98.40 182

TranMVSNet+NR-MVSNet		92.50 231	91.63 244	95.14 205	94.76 353	92.07 116	97.53 145	98.11 86	92.90 147	89.56 311	96.12 247	83.16 217	97.60 362	89.30 267	83.20 408	95.75 318

thres600view7		92.49 233	91.60 245	95.18 203	97.91 129	89.47 230	97.65 124	94.66 390	92.18 173	93.33 211	94.91 307	78.06 326	99.10 167	81.61 383	94.06 267	96.98 272

IMVS_0404		92.44 234	91.92 234	94.00 275	96.19 263	86.16 333	93.84 399	97.24 230	91.54 189	88.17 352	97.04 189	76.96 336	97.09 390	90.68 235	95.59 226	98.76 142

thres100view900		92.43 235	91.58 246	94.98 217	97.92 128	89.37 236	97.71 115	94.66 390	92.20 169	93.31 212	94.90 308	78.06 326	99.08 173	81.40 387	94.08 263	96.48 287

jajsoiax		92.42 236	91.89 236	94.03 274	93.33 405	88.50 265	97.73 110	97.53 179	92.00 178	88.85 332	96.50 227	75.62 349	98.11 291	93.88 161	91.56 304	95.48 326

thres400		92.42 236	91.52 249	95.12 207	97.85 132	89.29 240	97.41 162	94.88 382	92.19 171	93.27 214	94.46 334	78.17 322	99.08 173	81.40 387	94.08 263	96.98 272

tfpn200view9		92.38 238	91.52 249	94.95 221	97.85 132	89.29 240	97.41 162	94.88 382	92.19 171	93.27 214	94.46 334	78.17 322	99.08 173	81.40 387	94.08 263	96.48 287

test_vis1_n		92.37 239	92.26 223	92.72 338	94.75 354	82.64 390	98.02 60	96.80 281	91.18 212	97.77 55	97.93 107	58.02 444	98.29 275	97.63 37	98.21 139	97.23 267

WR-MVS		92.34 240	91.53 248	94.77 232	95.13 335	90.83 174	96.40 271	97.98 116	91.88 180	89.29 320	95.54 281	82.50 238	97.80 342	89.79 254	85.27 378	95.69 321

NR-MVSNet		92.34 240	91.27 259	95.53 186	94.95 342	93.05 78	97.39 167	98.07 95	92.65 155	84.46 403	95.71 270	85.00 184	97.77 346	89.71 255	83.52 405	95.78 314

mvs_tets		92.31 242	91.76 239	93.94 283	93.41 402	88.29 270	97.63 130	97.53 179	92.04 176	88.76 335	96.45 229	74.62 359	98.09 296	93.91 159	91.48 305	95.45 331

TAPA-MVS	90.10 7	92.30 243	91.22 262	95.56 183	98.33 87	89.60 222	96.79 230	97.65 158	81.83 421	91.52 256	97.23 177	87.94 120	98.91 196	71.31 444	98.37 132	98.17 205
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thisisatest0515		92.29 244	91.30 257	95.25 201	96.60 225	88.90 254	94.36 378	92.32 435	87.92 328	93.43 209	94.57 325	77.28 333	99.00 186	89.42 264	95.86 218	97.86 233

Fast-Effi-MVS+-dtu		92.29 244	91.99 231	93.21 320	95.27 323	85.52 346	97.03 199	96.63 295	92.09 174	89.11 326	95.14 298	80.33 283	98.08 297	87.54 308	94.74 248	96.03 304

IterMVS-LS		92.29 244	91.94 233	93.34 314	96.25 258	86.97 309	96.57 259	97.05 254	90.67 234	89.50 314	94.80 314	86.59 147	97.64 357	89.91 250	86.11 368	95.40 336
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PVSNet	86.66 18	92.24 247	91.74 242	93.73 294	97.77 137	83.69 380	92.88 422	96.72 284	87.91 329	93.00 219	94.86 310	78.51 317	99.05 182	86.53 323	97.45 167	98.47 174

VPNet		92.23 248	91.31 256	94.99 215	95.56 300	90.96 168	97.22 187	97.86 132	92.96 142	90.96 272	96.62 222	75.06 352	98.20 281	91.90 203	83.65 404	95.80 312

thres200		92.23 248	91.39 252	94.75 234	97.61 151	89.03 251	96.60 255	95.09 371	92.08 175	93.28 213	94.00 362	78.39 320	99.04 185	81.26 393	94.18 259	96.19 294

anonymousdsp		92.16 250	91.55 247	93.97 279	92.58 420	89.55 226	97.51 147	97.42 206	89.42 278	88.40 342	94.84 311	80.66 275	97.88 334	91.87 205	91.28 309	94.48 389

XXY-MVS		92.16 250	91.23 261	94.95 221	94.75 354	90.94 169	97.47 157	97.43 204	89.14 285	88.90 328	96.43 230	79.71 294	98.24 277	89.56 260	87.68 351	95.67 322

BH-w/o		92.14 252	91.75 240	93.31 315	96.99 189	85.73 343	95.67 322	95.69 340	88.73 306	89.26 322	94.82 313	82.97 225	98.07 301	85.26 347	96.32 210	96.13 300

testing3-2		92.10 253	92.05 227	92.27 351	97.71 141	79.56 427	97.42 161	94.41 400	93.53 111	93.22 216	95.49 283	69.16 400	99.11 165	93.25 175	94.22 257	98.13 207

Anonymous202405211		92.07 254	90.83 278	95.76 169	98.19 105	88.75 256	97.58 135	95.00 374	86.00 372	93.64 199	97.45 159	66.24 423	99.53 108	90.68 235	92.71 285	99.01 103

FE-MVS		92.05 255	91.05 267	95.08 208	96.83 204	87.93 283	93.91 396	95.70 338	86.30 366	94.15 186	94.97 303	76.59 338	99.21 148	84.10 360	96.86 188	98.09 215

WR-MVS_H		92.00 256	91.35 253	93.95 281	95.09 337	89.47 230	98.04 59	98.68 16	91.46 196	88.34 344	94.68 319	85.86 163	97.56 364	85.77 339	84.24 396	94.82 374

Anonymous20240529		91.98 257	90.73 284	95.73 174	98.14 109	89.40 234	97.99 63	97.72 150	79.63 435	93.54 203	97.41 164	69.94 393	99.56 102	91.04 225	91.11 312	98.22 199

MonoMVSNet		91.92 258	91.77 238	92.37 345	92.94 411	83.11 386	97.09 197	95.55 349	92.91 144	90.85 274	94.55 326	81.27 264	96.52 408	93.01 185	87.76 350	97.47 255

PatchmatchNet		91.91 259	91.35 253	93.59 303	95.38 311	84.11 373	93.15 417	95.39 354	89.54 272	92.10 241	93.68 375	82.82 230	98.13 287	84.81 351	95.32 234	98.52 166
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing91		91.90 260	91.02 268	94.53 246	96.54 234	86.55 322	95.86 311	95.64 344	91.77 183	91.89 247	93.47 384	69.94 393	98.86 199	90.23 246	93.86 270	98.18 202

CP-MVSNet		91.89 261	91.24 260	93.82 290	95.05 338	88.57 261	97.82 95	98.19 71	91.70 185	88.21 350	95.76 268	81.96 250	97.52 370	87.86 294	84.65 387	95.37 339

SCA		91.84 262	91.18 264	93.83 289	95.59 298	84.95 363	94.72 363	95.58 347	90.82 226	92.25 236	93.69 373	75.80 346	98.10 292	86.20 329	95.98 213	98.45 176

FMVSNet3		91.78 263	90.69 287	95.03 212	96.53 236	92.27 109	97.02 201	96.93 266	89.79 267	89.35 317	94.65 322	77.01 334	97.47 373	86.12 332	88.82 338	95.35 340

AUN-MVS		91.76 264	90.75 282	94.81 227	97.00 188	88.57 261	96.65 247	96.49 301	89.63 269	92.15 238	96.12 247	78.66 315	98.50 255	90.83 228	79.18 425	97.36 259

X-MVStestdata		91.71 265	89.67 331	97.81 29	99.38 14	94.03 51	98.59 13	98.20 66	94.85 52	96.59 95	32.69 470	91.70 54	99.80 37	95.66 104	99.40 58	99.62 24

MVS		91.71 265	90.44 294	95.51 187	95.20 329	91.59 137	96.04 300	97.45 197	73.44 451	87.36 368	95.60 277	85.42 174	99.10 167	85.97 336	97.46 163	95.83 310

EPNet_dtu		91.71 265	91.28 258	92.99 327	93.76 387	83.71 379	96.69 243	95.28 361	93.15 130	87.02 377	95.95 255	83.37 213	97.38 381	79.46 406	96.84 189	97.88 229
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing11		91.68 268	90.75 282	94.47 248	96.53 236	86.56 321	95.76 318	94.51 397	91.10 219	91.24 269	93.59 379	68.59 405	98.86 199	91.10 223	94.29 255	98.00 222

baseline2		91.63 269	90.86 274	93.94 283	94.33 371	86.32 326	95.92 308	91.64 441	89.37 279	86.94 380	94.69 318	81.62 258	98.69 231	88.64 285	94.57 251	96.81 279

testing99		91.62 270	90.72 285	94.32 257	96.48 243	86.11 338	95.81 314	94.76 387	91.55 188	91.75 252	93.44 385	68.55 406	98.82 205	90.43 240	93.69 272	98.04 219

test2506		91.60 271	90.78 279	94.04 273	97.66 145	83.81 376	98.27 33	75.53 471	93.43 116	95.23 152	98.21 84	67.21 414	99.07 177	93.01 185	98.49 125	99.25 77

miper_ehance_all_eth		91.59 272	91.13 265	92.97 328	95.55 301	86.57 320	94.47 372	96.88 275	87.77 336	88.88 330	94.01 361	86.22 156	97.54 366	89.49 261	86.93 359	94.79 379

v2v482		91.59 272	90.85 276	93.80 291	93.87 384	88.17 277	96.94 211	96.88 275	89.54 272	89.53 312	94.90 308	81.70 257	98.02 309	89.25 270	85.04 384	95.20 351

V42		91.58 274	90.87 273	93.73 294	94.05 379	88.50 265	97.32 175	96.97 262	88.80 304	89.71 304	94.33 342	82.54 237	98.05 304	89.01 276	85.07 382	94.64 387

PCF-MVS	89.48 11	91.56 275	89.95 319	96.36 123	96.60 225	92.52 100	92.51 427	97.26 227	79.41 436	88.90 328	96.56 224	84.04 203	99.55 104	77.01 420	97.30 174	97.01 271
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UBG		91.55 276	90.76 280	93.94 283	96.52 239	85.06 359	95.22 349	94.54 395	90.47 248	91.98 244	92.71 396	72.02 374	98.74 221	88.10 290	95.26 236	98.01 221

PS-CasMVS		91.55 276	90.84 277	93.69 298	94.96 341	88.28 271	97.84 90	98.24 60	91.46 196	88.04 355	95.80 263	79.67 295	97.48 372	87.02 319	84.54 393	95.31 343

miper_enhance_ethall		91.54 278	91.01 269	93.15 322	95.35 315	87.07 307	93.97 391	96.90 272	86.79 358	89.17 324	93.43 388	86.55 149	97.64 357	89.97 249	86.93 359	94.74 383

myMVS_eth3d28		91.52 279	90.97 270	93.17 321	96.91 194	83.24 384	95.61 328	94.96 378	92.24 165	91.98 244	93.28 389	69.31 398	98.40 262	88.71 283	95.68 223	97.88 229

PAPM		91.52 279	90.30 300	95.20 202	95.30 322	89.83 215	93.38 413	96.85 278	86.26 368	88.59 338	95.80 263	84.88 187	98.15 286	75.67 425	95.93 215	97.63 244

ET-MVSNet_ETH3D		91.49 281	90.11 310	95.63 179	96.40 249	91.57 139	95.34 340	93.48 421	90.60 242	75.58 446	95.49 283	80.08 287	96.79 404	94.25 152	89.76 329	98.52 166

TR-MVS		91.48 282	90.59 290	94.16 267	96.40 249	87.33 296	95.67 322	95.34 360	87.68 340	91.46 258	95.52 282	76.77 337	98.35 270	82.85 374	93.61 276	96.79 280

tpmrst		91.44 283	91.32 255	91.79 368	95.15 333	79.20 433	93.42 412	95.37 356	88.55 311	93.49 207	93.67 376	82.49 239	98.27 276	90.41 241	89.34 333	97.90 227

test-LLR		91.42 284	91.19 263	92.12 356	94.59 361	80.66 411	94.29 383	92.98 427	91.11 217	90.76 276	92.37 404	79.02 308	98.07 301	88.81 280	96.74 194	97.63 244

MSDG		91.42 284	90.24 304	94.96 220	97.15 174	88.91 253	93.69 405	96.32 309	85.72 376	86.93 381	96.47 228	80.24 284	98.98 188	80.57 397	95.05 241	96.98 272

c3_l		91.38 286	90.89 272	92.88 332	95.58 299	86.30 327	94.68 364	96.84 279	88.17 321	88.83 334	94.23 350	85.65 169	97.47 373	89.36 265	84.63 388	94.89 369

GA-MVS		91.38 286	90.31 299	94.59 238	94.65 359	87.62 292	94.34 379	96.19 319	90.73 230	90.35 282	93.83 366	71.84 376	97.96 320	87.22 314	93.61 276	98.21 200

v1144		91.37 288	90.60 289	93.68 299	93.89 383	88.23 274	96.84 224	97.03 258	88.37 316	89.69 306	94.39 336	82.04 248	97.98 313	87.80 296	85.37 375	94.84 371

GBi-Net		91.35 289	90.27 302	94.59 238	96.51 240	91.18 159	97.50 148	96.93 266	88.82 301	89.35 317	94.51 329	73.87 363	97.29 385	86.12 332	88.82 338	95.31 343

test1		91.35 289	90.27 302	94.59 238	96.51 240	91.18 159	97.50 148	96.93 266	88.82 301	89.35 317	94.51 329	73.87 363	97.29 385	86.12 332	88.82 338	95.31 343

UniMVSNet_ETH3D		91.34 291	90.22 307	94.68 236	94.86 349	87.86 287	97.23 185	97.46 192	87.99 326	89.90 298	96.92 199	66.35 421	98.23 278	90.30 244	90.99 315	97.96 223

FMVSNet2		91.31 292	90.08 311	94.99 215	96.51 240	92.21 111	97.41 162	96.95 264	88.82 301	88.62 337	94.75 316	73.87 363	97.42 378	85.20 348	88.55 343	95.35 340

reproduce_monomvs		91.30 293	91.10 266	91.92 360	96.82 206	82.48 394	97.01 204	97.49 184	94.64 70	88.35 343	95.27 292	70.53 386	98.10 292	95.20 118	84.60 390	95.19 354

D2MVS		91.30 293	90.95 271	92.35 346	94.71 357	85.52 346	96.18 293	98.21 64	88.89 297	86.60 384	93.82 368	79.92 291	97.95 324	89.29 268	90.95 316	93.56 409

v8		91.29 295	90.53 293	93.57 306	94.15 375	88.12 279	97.34 172	97.06 253	88.99 292	88.32 345	94.26 349	83.08 220	98.01 310	87.62 306	83.92 401	94.57 388

CVMVSNet		91.23 296	91.75 240	89.67 408	95.77 291	74.69 445	96.44 261	94.88 382	85.81 374	92.18 237	97.64 145	79.07 305	95.58 426	88.06 291	95.86 218	98.74 149

cl22		91.21 297	90.56 292	93.14 323	96.09 278	86.80 312	94.41 376	96.58 298	87.80 334	88.58 339	93.99 363	80.85 271	97.62 360	89.87 252	86.93 359	94.99 360

PEN-MVS		91.20 298	90.44 294	93.48 309	94.49 365	87.91 286	97.76 103	98.18 73	91.29 202	87.78 359	95.74 269	80.35 282	97.33 383	85.46 343	82.96 409	95.19 354

Baseline_NR-MVSNet		91.20 298	90.62 288	92.95 329	93.83 385	88.03 281	97.01 204	95.12 370	88.42 315	89.70 305	95.13 299	83.47 210	97.44 376	89.66 258	83.24 407	93.37 413

cascas		91.20 298	90.08 311	94.58 242	94.97 340	89.16 248	93.65 407	97.59 170	79.90 434	89.40 315	92.92 394	75.36 350	98.36 269	92.14 196	94.75 247	96.23 291

CostFormer		91.18 301	90.70 286	92.62 342	94.84 350	81.76 402	94.09 389	94.43 398	84.15 398	92.72 226	93.77 370	79.43 299	98.20 281	90.70 234	92.18 294	97.90 227

tt0805		91.09 302	90.07 314	94.16 267	95.61 297	88.31 269	97.56 139	96.51 300	89.56 271	89.17 324	95.64 275	67.08 418	98.38 268	91.07 224	88.44 344	95.80 312

v1192		91.07 303	90.23 305	93.58 304	93.70 388	87.82 289	96.73 237	97.07 248	87.77 336	89.58 309	94.32 344	80.90 270	97.97 316	86.52 324	85.48 373	94.95 361

v144192		91.06 304	90.28 301	93.39 312	93.66 391	87.23 302	96.83 225	97.07 248	87.43 345	89.69 306	94.28 346	81.48 259	98.00 311	87.18 316	84.92 386	94.93 365

v10		91.04 305	90.23 305	93.49 308	94.12 376	88.16 278	97.32 175	97.08 245	88.26 319	88.29 347	94.22 352	82.17 246	97.97 316	86.45 326	84.12 397	94.33 395

eth_miper_zixun_eth		91.02 306	90.59 290	92.34 348	95.33 319	84.35 369	94.10 388	96.90 272	88.56 310	88.84 333	94.33 342	84.08 201	97.60 362	88.77 282	84.37 395	95.06 358

v148		90.99 307	90.38 296	92.81 335	93.83 385	85.80 340	96.78 234	96.68 289	89.45 277	88.75 336	93.93 365	82.96 226	97.82 339	87.83 295	83.25 406	94.80 377

LTVRE_ROB	88.41 13	90.99 307	89.92 321	94.19 263	96.18 267	89.55 226	96.31 282	97.09 244	87.88 330	85.67 393	95.91 257	78.79 314	98.57 250	81.50 384	89.98 326	94.44 392
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		90.97 309	90.33 297	92.88 332	95.36 314	86.19 332	94.46 374	96.63 295	87.82 332	88.18 351	94.23 350	82.99 223	97.53 368	87.72 297	85.57 372	94.93 365

cl____		90.96 310	90.32 298	92.89 331	95.37 313	86.21 330	94.46 374	96.64 292	87.82 332	88.15 353	94.18 353	82.98 224	97.54 366	87.70 300	85.59 371	94.92 367

pmmvs4		90.93 311	89.85 323	94.17 264	93.34 404	90.79 176	94.60 366	96.02 324	84.62 393	87.45 364	95.15 297	81.88 254	97.45 375	87.70 300	87.87 349	94.27 399

XVG-ACMP-BASELINE		90.93 311	90.21 308	93.09 324	94.31 373	85.89 339	95.33 341	97.26 227	91.06 220	89.38 316	95.44 286	68.61 404	98.60 245	89.46 262	91.05 313	94.79 379

v1921920		90.85 313	90.03 316	93.29 316	93.55 393	86.96 311	96.74 236	97.04 256	87.36 347	89.52 313	94.34 341	80.23 285	97.97 316	86.27 327	85.21 379	94.94 363

CR-MVSNet		90.82 314	89.77 327	93.95 281	94.45 367	87.19 303	90.23 443	95.68 342	86.89 356	92.40 228	92.36 407	80.91 268	97.05 392	81.09 394	93.95 268	97.60 249

v7n		90.76 315	89.86 322	93.45 311	93.54 394	87.60 293	97.70 118	97.37 213	88.85 298	87.65 361	94.08 359	81.08 265	98.10 292	84.68 353	83.79 403	94.66 386

RPSCF		90.75 316	90.86 274	90.42 398	96.84 202	76.29 443	95.61 328	96.34 308	83.89 401	91.38 259	97.87 116	76.45 340	98.78 211	87.16 317	92.23 291	96.20 293

MVP-Stereo		90.74 317	90.08 311	92.71 339	93.19 407	88.20 275	95.86 311	96.27 313	86.07 371	84.86 401	94.76 315	77.84 329	97.75 349	83.88 366	98.01 149	92.17 434
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pm-mvs1		90.72 318	89.65 333	93.96 280	94.29 374	89.63 220	97.79 101	96.82 280	89.07 287	86.12 391	95.48 285	78.61 316	97.78 344	86.97 320	81.67 414	94.46 390

v1240		90.70 319	89.85 323	93.23 318	93.51 396	86.80 312	96.61 253	97.02 260	87.16 352	89.58 309	94.31 345	79.55 298	97.98 313	85.52 342	85.44 374	94.90 368

EPMVS		90.70 319	89.81 325	93.37 313	94.73 356	84.21 371	93.67 406	88.02 456	89.50 274	92.38 230	93.49 382	77.82 330	97.78 344	86.03 335	92.68 286	98.11 214

WBMVS		90.69 321	89.99 318	92.81 335	96.48 243	85.00 360	95.21 351	96.30 311	89.46 276	89.04 327	94.05 360	72.45 373	97.82 339	89.46 262	87.41 356	95.61 323

Anonymous20231211		90.63 322	89.42 338	94.27 262	98.24 96	89.19 247	98.05 58	97.89 124	79.95 433	88.25 349	94.96 304	72.56 372	98.13 287	89.70 256	85.14 380	95.49 325

DTE-MVSNet		90.56 323	89.75 329	93.01 326	93.95 380	87.25 300	97.64 128	97.65 158	90.74 229	87.12 372	95.68 273	79.97 290	97.00 396	83.33 368	81.66 415	94.78 381

ACMH	87.59 16	90.53 324	89.42 338	93.87 288	96.21 259	87.92 284	97.24 181	96.94 265	88.45 314	83.91 413	96.27 239	71.92 375	98.62 244	84.43 356	89.43 332	95.05 359
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		90.52 325	89.14 346	94.67 237	96.81 208	87.85 288	95.91 309	93.97 413	89.71 268	92.34 234	92.48 402	65.41 429	97.96 320	81.37 390	94.27 256	98.21 200

OurMVSNet-221017-0		90.51 326	90.19 309	91.44 377	93.41 402	81.25 405	96.98 208	96.28 312	91.68 186	86.55 386	96.30 236	74.20 362	97.98 313	88.96 278	87.40 357	95.09 356

miper_lstm_enhance		90.50 327	90.06 315	91.83 365	95.33 319	83.74 377	93.86 397	96.70 288	87.56 343	87.79 358	93.81 369	83.45 212	96.92 398	87.39 310	84.62 389	94.82 374

COLMAP_ROB	87.81 15	90.40 328	89.28 341	93.79 292	97.95 125	87.13 306	96.92 214	95.89 330	82.83 414	86.88 383	97.18 179	73.77 366	99.29 142	78.44 411	93.62 275	94.95 361
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testing222		90.31 329	88.96 348	94.35 254	96.54 234	87.29 297	95.50 333	93.84 417	90.97 222	91.75 252	92.96 393	62.18 439	98.00 311	82.86 372	94.08 263	97.76 239

IterMVS-SCA-FT		90.31 329	89.81 325	91.82 366	95.52 302	84.20 372	94.30 382	96.15 321	90.61 240	87.39 367	94.27 347	75.80 346	96.44 409	87.34 311	86.88 363	94.82 374

MS-PatchMatch		90.27 331	89.77 327	91.78 369	94.33 371	84.72 366	95.55 330	96.73 283	86.17 370	86.36 388	95.28 291	71.28 380	97.80 342	84.09 361	98.14 143	92.81 419

tpm		90.25 332	89.74 330	91.76 371	93.92 381	79.73 426	93.98 390	93.54 420	88.28 318	91.99 243	93.25 390	77.51 332	97.44 376	87.30 313	87.94 348	98.12 209

AllTest		90.23 333	88.98 347	93.98 277	97.94 126	86.64 316	96.51 260	95.54 350	85.38 380	85.49 395	96.77 206	70.28 388	99.15 159	80.02 401	92.87 280	96.15 298

dmvs_re		90.21 334	89.50 336	92.35 346	95.47 308	85.15 356	95.70 321	94.37 403	90.94 225	88.42 341	93.57 380	74.63 358	95.67 423	82.80 375	89.57 331	96.22 292

ACMH+	87.92 14	90.20 335	89.18 344	93.25 317	96.48 243	86.45 324	96.99 207	96.68 289	88.83 300	84.79 402	96.22 241	70.16 390	98.53 253	84.42 357	88.04 347	94.77 382

test-mter		90.19 336	89.54 335	92.12 356	94.59 361	80.66 411	94.29 383	92.98 427	87.68 340	90.76 276	92.37 404	67.67 410	98.07 301	88.81 280	96.74 194	97.63 244

IterMVS		90.15 337	89.67 331	91.61 373	95.48 304	83.72 378	94.33 380	96.12 322	89.99 259	87.31 370	94.15 355	75.78 348	96.27 413	86.97 320	86.89 362	94.83 372
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TESTMET0.1,1		90.06 338	89.42 338	91.97 359	94.41 369	80.62 413	94.29 383	91.97 439	87.28 350	90.44 280	92.47 403	68.79 402	97.67 354	88.50 287	96.60 200	97.61 248

SD_0403		90.01 339	90.02 317	89.96 405	95.65 296	76.76 440	95.76 318	96.46 303	90.58 243	86.59 385	96.29 237	82.12 247	94.78 434	73.00 439	93.76 271	98.35 188

tpm2		89.96 340	89.21 343	92.23 354	94.91 347	81.25 405	93.78 400	94.42 399	80.62 431	91.56 255	93.44 385	76.44 341	97.94 326	85.60 341	92.08 298	97.49 253

UWE-MVS		89.91 341	89.48 337	91.21 381	95.88 284	78.23 438	94.91 360	90.26 449	89.11 286	92.35 233	94.52 328	68.76 403	97.96 320	83.95 364	95.59 226	97.42 257

IB-MVS	87.33 17	89.91 341	88.28 358	94.79 231	95.26 326	87.70 291	95.12 355	93.95 414	89.35 280	87.03 376	92.49 401	70.74 385	99.19 150	89.18 274	81.37 416	97.49 253
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		89.89 343	88.68 353	93.53 307	95.86 285	84.89 364	90.93 438	95.07 372	83.23 412	91.28 267	91.81 417	79.01 310	97.85 335	79.52 403	91.39 307	97.84 234

WB-MVSnew		89.88 344	89.56 334	90.82 390	94.57 364	83.06 387	95.65 326	92.85 429	87.86 331	90.83 275	94.10 356	79.66 296	96.88 400	76.34 421	94.19 258	92.54 425

FMVSNet1		89.88 344	88.31 357	94.59 238	95.41 309	91.18 159	97.50 148	96.93 266	86.62 360	87.41 366	94.51 329	65.94 426	97.29 385	83.04 371	87.43 354	95.31 343

pmmvs5		89.86 346	88.87 351	92.82 334	92.86 413	86.23 329	96.26 285	95.39 354	84.24 397	87.12 372	94.51 329	74.27 361	97.36 382	87.61 307	87.57 352	94.86 370

tpmvs		89.83 347	89.15 345	91.89 363	94.92 345	80.30 418	93.11 418	95.46 353	86.28 367	88.08 354	92.65 397	80.44 280	98.52 254	81.47 386	89.92 327	96.84 278

test_fmvs2		89.77 348	89.93 320	89.31 415	93.68 390	76.37 442	97.64 128	95.90 328	89.84 265	91.49 257	96.26 240	58.77 442	97.10 389	94.65 140	91.13 311	94.46 390

SSC-MVS3.2		89.74 349	89.26 342	91.19 384	95.16 330	80.29 419	94.53 369	97.03 258	91.79 182	88.86 331	94.10 356	69.94 393	97.82 339	85.29 345	86.66 364	95.45 331

mmtdpeth		89.70 350	88.96 348	91.90 362	95.84 290	84.42 368	97.46 159	95.53 352	90.27 252	94.46 175	90.50 426	69.74 397	98.95 189	97.39 50	69.48 452	92.34 428

tfpnnormal		89.70 350	88.40 356	93.60 302	95.15 333	90.10 202	97.56 139	98.16 77	87.28 350	86.16 390	94.63 323	77.57 331	98.05 304	74.48 429	84.59 391	92.65 422

ADS-MVSNet2		89.45 352	88.59 354	92.03 358	95.86 285	82.26 398	90.93 438	94.32 406	83.23 412	91.28 267	91.81 417	79.01 310	95.99 415	79.52 403	91.39 307	97.84 234

Patchmatch-test		89.42 353	87.99 360	93.70 297	95.27 323	85.11 357	88.98 450	94.37 403	81.11 425	87.10 375	93.69 373	82.28 243	97.50 371	74.37 431	94.76 246	98.48 173

test0.0.03 1		89.37 354	88.70 352	91.41 378	92.47 422	85.63 344	95.22 349	92.70 432	91.11 217	86.91 382	93.65 377	79.02 308	93.19 451	78.00 413	89.18 334	95.41 333

SixPastTwentyTwo		89.15 355	88.54 355	90.98 386	93.49 397	80.28 420	96.70 241	94.70 389	90.78 227	84.15 408	95.57 278	71.78 377	97.71 352	84.63 354	85.07 382	94.94 363

RPMNet		88.98 356	87.05 370	94.77 232	94.45 367	87.19 303	90.23 443	98.03 107	77.87 443	92.40 228	87.55 450	80.17 286	99.51 113	68.84 450	93.95 268	97.60 249

TransMVSNet (Re)		88.94 357	87.56 363	93.08 325	94.35 370	88.45 267	97.73 110	95.23 365	87.47 344	84.26 406	95.29 289	79.86 292	97.33 383	79.44 407	74.44 443	93.45 412

USDC		88.94 357	87.83 362	92.27 351	94.66 358	84.96 362	93.86 397	95.90 328	87.34 348	83.40 415	95.56 279	67.43 412	98.19 283	82.64 379	89.67 330	93.66 408

dp		88.90 359	88.26 359	90.81 391	94.58 363	76.62 441	92.85 423	94.93 379	85.12 386	90.07 296	93.07 391	75.81 345	98.12 290	80.53 398	87.42 355	97.71 241

PatchT		88.87 360	87.42 364	93.22 319	94.08 378	85.10 358	89.51 448	94.64 392	81.92 420	92.36 231	88.15 446	80.05 288	97.01 395	72.43 440	93.65 274	97.54 252

our_test_3		88.78 361	87.98 361	91.20 383	92.45 423	82.53 392	93.61 409	95.69 340	85.77 375	84.88 400	93.71 371	79.99 289	96.78 405	79.47 405	86.24 365	94.28 398

EU-MVSNet		88.72 362	88.90 350	88.20 419	93.15 408	74.21 447	96.63 252	94.22 408	85.18 384	87.32 369	95.97 253	76.16 343	94.98 432	85.27 346	86.17 366	95.41 333

Patchmtry		88.64 363	87.25 366	92.78 337	94.09 377	86.64 316	89.82 447	95.68 342	80.81 429	87.63 362	92.36 407	80.91 268	97.03 393	78.86 409	85.12 381	94.67 385

MIMVSNet		88.50 364	86.76 374	93.72 296	94.84 350	87.77 290	91.39 433	94.05 410	86.41 364	87.99 356	92.59 400	63.27 433	95.82 420	77.44 414	92.84 282	97.57 251

tpm cat1		88.36 365	87.21 368	91.81 367	95.13 335	80.55 414	92.58 426	95.70 338	74.97 447	87.45 364	91.96 415	78.01 328	98.17 285	80.39 399	88.74 341	96.72 282

ppachtmachnet_test		88.35 366	87.29 365	91.53 374	92.45 423	83.57 381	93.75 401	95.97 325	84.28 396	85.32 398	94.18 353	79.00 312	96.93 397	75.71 424	84.99 385	94.10 400

JIA-IIPM		88.26 367	87.04 371	91.91 361	93.52 395	81.42 404	89.38 449	94.38 402	80.84 428	90.93 273	80.74 458	79.22 302	97.92 329	82.76 376	91.62 302	96.38 290

testgi		87.97 368	87.21 368	90.24 401	92.86 413	80.76 409	96.67 246	94.97 376	91.74 184	85.52 394	95.83 261	62.66 437	94.47 437	76.25 422	88.36 345	95.48 326

LF4IMVS		87.94 369	87.25 366	89.98 404	92.38 425	80.05 424	94.38 377	95.25 364	87.59 342	84.34 404	94.74 317	64.31 431	97.66 356	84.83 350	87.45 353	92.23 431

gg-mvs-nofinetune		87.82 370	85.61 383	94.44 250	94.46 366	89.27 243	91.21 437	84.61 465	80.88 427	89.89 300	74.98 461	71.50 378	97.53 368	85.75 340	97.21 178	96.51 285

pmmvs6		87.81 371	86.19 379	92.69 340	91.32 430	86.30 327	97.34 172	96.41 306	80.59 432	84.05 412	94.37 338	67.37 413	97.67 354	84.75 352	79.51 424	94.09 402

testing3		87.67 372	86.88 373	90.05 403	96.14 272	80.71 410	97.10 196	92.85 429	90.15 256	87.54 363	94.55 326	55.70 449	94.10 440	73.77 435	94.10 262	95.35 340

K. test v3		87.64 373	86.75 375	90.32 400	93.02 410	79.48 431	96.61 253	92.08 438	90.66 236	80.25 434	94.09 358	67.21 414	96.65 407	85.96 337	80.83 418	94.83 372

Patchmatch-RL test		87.38 374	86.24 378	90.81 391	88.74 448	78.40 437	88.12 457	93.17 424	87.11 353	82.17 424	89.29 437	81.95 251	95.60 425	88.64 285	77.02 432	98.41 181

FMVSNet5		87.29 375	85.79 382	91.78 369	94.80 352	87.28 298	95.49 334	95.28 361	84.09 399	83.85 414	91.82 416	62.95 435	94.17 439	78.48 410	85.34 377	93.91 406

myMVS_eth3d		87.18 376	86.38 377	89.58 409	95.16 330	79.53 428	95.00 357	93.93 415	88.55 311	86.96 378	91.99 413	56.23 448	94.00 441	75.47 427	94.11 260	95.20 351

Syy-MVS		87.13 377	87.02 372	87.47 423	95.16 330	73.21 451	95.00 357	93.93 415	88.55 311	86.96 378	91.99 413	75.90 344	94.00 441	61.59 457	94.11 260	95.20 351

Anonymous20231206		87.09 378	86.14 380	89.93 406	91.22 431	80.35 416	96.11 296	95.35 357	83.57 408	84.16 407	93.02 392	73.54 368	95.61 424	72.16 441	86.14 367	93.84 407

EG-PatchMatch MVS		87.02 379	85.44 384	91.76 371	92.67 417	85.00 360	96.08 298	96.45 304	83.41 411	79.52 436	93.49 382	57.10 446	97.72 351	79.34 408	90.87 318	92.56 424

TinyColmap		86.82 380	85.35 387	91.21 381	94.91 347	82.99 388	93.94 393	94.02 412	83.58 407	81.56 426	94.68 319	62.34 438	98.13 287	75.78 423	87.35 358	92.52 426

UWE-MVS-28		86.81 381	86.41 376	88.02 421	92.87 412	74.60 446	95.38 339	86.70 461	88.17 321	87.28 371	94.67 321	70.83 384	93.30 449	67.45 451	94.31 254	96.17 295

mvs5depth		86.53 382	85.08 389	90.87 388	88.74 448	82.52 393	91.91 431	94.23 407	86.35 365	87.11 374	93.70 372	66.52 419	97.76 347	81.37 390	75.80 437	92.31 430

TDRefinement		86.53 382	84.76 394	91.85 364	82.23 464	84.25 370	96.38 273	95.35 357	84.97 389	84.09 410	94.94 305	65.76 427	98.34 273	84.60 355	74.52 442	92.97 416

sc_t1		86.48 384	84.10 400	93.63 300	93.45 400	85.76 342	96.79 230	94.71 388	73.06 452	86.45 387	94.35 339	55.13 450	97.95 324	84.38 358	78.55 429	97.18 268

test_0402		86.46 385	84.79 393	91.45 376	95.02 339	85.55 345	96.29 284	94.89 381	80.90 426	82.21 423	93.97 364	68.21 409	97.29 385	62.98 455	88.68 342	91.51 439

Anonymous20240521		86.42 386	85.44 384	89.34 414	90.33 435	79.79 425	96.73 237	95.92 326	83.71 406	83.25 417	91.36 422	63.92 432	96.01 414	78.39 412	85.36 376	92.22 432

DSMNet-mixed		86.34 387	86.12 381	87.00 427	89.88 439	70.43 453	94.93 359	90.08 450	77.97 442	85.42 397	92.78 395	74.44 360	93.96 443	74.43 430	95.14 237	96.62 283

CL-MVSNet_self_test		86.31 388	85.15 388	89.80 407	88.83 446	81.74 403	93.93 394	96.22 316	86.67 359	85.03 399	90.80 425	78.09 325	94.50 435	74.92 428	71.86 448	93.15 415

pmmvs-eth3d		86.22 389	84.45 396	91.53 374	88.34 450	87.25 300	94.47 372	95.01 373	83.47 409	79.51 437	89.61 435	69.75 396	95.71 421	83.13 370	76.73 435	91.64 436

test_vis1_rt		86.16 390	85.06 390	89.46 411	93.47 399	80.46 415	96.41 267	86.61 462	85.22 383	79.15 438	88.64 441	52.41 454	97.06 391	93.08 180	90.57 320	90.87 445

test20.03		86.14 391	85.40 386	88.35 417	90.12 436	80.06 423	95.90 310	95.20 366	88.59 307	81.29 427	93.62 378	71.43 379	92.65 452	71.26 445	81.17 417	92.34 428

UnsupCasMVSNet_eth		85.99 392	84.45 396	90.62 395	89.97 438	82.40 397	93.62 408	97.37 213	89.86 262	78.59 441	92.37 404	65.25 430	95.35 430	82.27 381	70.75 449	94.10 400

KD-MVS_self_test		85.95 393	84.95 391	88.96 416	89.55 442	79.11 434	95.13 354	96.42 305	85.91 373	84.07 411	90.48 427	70.03 392	94.82 433	80.04 400	72.94 446	92.94 417

ttmdpeth		85.91 394	84.76 394	89.36 413	89.14 443	80.25 421	95.66 325	93.16 426	83.77 404	83.39 416	95.26 293	66.24 423	95.26 431	80.65 396	75.57 438	92.57 423

YYNet1		85.87 395	84.23 398	90.78 394	92.38 425	82.46 396	93.17 415	95.14 369	82.12 419	67.69 454	92.36 407	78.16 324	95.50 428	77.31 416	79.73 422	94.39 393

MDA-MVSNet_test_wron		85.87 395	84.23 398	90.80 393	92.38 425	82.57 391	93.17 415	95.15 368	82.15 418	67.65 456	92.33 410	78.20 321	95.51 427	77.33 415	79.74 421	94.31 397

CMPMVS	62.92 21	85.62 397	84.92 392	87.74 422	89.14 443	73.12 452	94.17 386	96.80 281	73.98 448	73.65 450	94.93 306	66.36 420	97.61 361	83.95 364	91.28 309	92.48 427
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PVSNet_0	82.17 19	85.46 398	83.64 401	90.92 387	95.27 323	79.49 430	90.55 441	95.60 345	83.76 405	83.00 420	89.95 432	71.09 381	97.97 316	82.75 377	60.79 463	95.31 343

tt0320		85.39 399	83.12 402	92.19 355	93.44 401	85.79 341	96.19 292	94.87 385	71.19 454	82.92 421	91.76 419	58.43 443	96.81 403	81.03 395	78.26 430	93.98 404

MDA-MVSNet-bldmvs		85.00 400	82.95 405	91.17 385	93.13 409	83.33 382	94.56 368	95.00 374	84.57 394	65.13 460	92.65 397	70.45 387	95.85 418	73.57 436	77.49 431	94.33 395

MIMVSNet1		84.93 401	83.05 403	90.56 396	89.56 441	84.84 365	95.40 337	95.35 357	83.91 400	80.38 432	92.21 412	57.23 445	93.34 448	70.69 447	82.75 412	93.50 410

tt0320-xc		84.83 402	82.33 410	92.31 349	93.66 391	86.20 331	96.17 294	94.06 409	71.26 453	82.04 425	92.22 411	55.07 451	96.72 406	81.49 385	75.04 441	94.02 403

KD-MVS_2432*1600		84.81 403	82.64 406	91.31 379	91.07 432	85.34 354	91.22 435	95.75 336	85.56 378	83.09 418	90.21 430	67.21 414	95.89 416	77.18 418	62.48 461	92.69 420

miper_refine_blended		84.81 403	82.64 406	91.31 379	91.07 432	85.34 354	91.22 435	95.75 336	85.56 378	83.09 418	90.21 430	67.21 414	95.89 416	77.18 418	62.48 461	92.69 420

OpenMVS_ROB	81.14 20	84.42 405	82.28 411	90.83 389	90.06 437	84.05 375	95.73 320	94.04 411	73.89 450	80.17 435	91.53 421	59.15 441	97.64 357	66.92 453	89.05 335	90.80 446

FE-MVSNET		83.85 406	81.97 412	89.51 410	87.19 454	83.19 385	95.21 351	93.17 424	83.45 410	78.90 439	89.05 439	65.46 428	93.84 445	69.71 449	75.56 439	91.51 439

mvsany_test3		83.59 407	82.44 409	87.03 426	83.80 459	73.82 448	93.70 403	90.92 447	86.42 363	82.51 422	90.26 429	46.76 459	95.71 421	90.82 229	76.76 434	91.57 438

PM-MVS		83.48 408	81.86 414	88.31 418	87.83 452	77.59 439	93.43 411	91.75 440	86.91 355	80.63 430	89.91 433	44.42 460	95.84 419	85.17 349	76.73 435	91.50 441

test_fmvs3		83.21 409	83.02 404	83.78 432	86.77 456	68.34 458	96.76 235	94.91 380	86.49 362	84.14 409	89.48 436	36.04 464	91.73 454	91.86 206	80.77 419	91.26 444

new-patchmatchnet		83.18 410	81.87 413	87.11 425	86.88 455	75.99 444	93.70 403	95.18 367	85.02 388	77.30 444	88.40 443	65.99 425	93.88 444	74.19 433	70.18 450	91.47 442

new_pmnet		82.89 411	81.12 416	88.18 420	89.63 440	80.18 422	91.77 432	92.57 433	76.79 445	75.56 447	88.23 445	61.22 440	94.48 436	71.43 443	82.92 410	89.87 449

MVS-HIRNet		82.47 412	81.21 415	86.26 429	95.38 311	69.21 456	88.96 451	89.49 451	66.28 458	80.79 429	74.08 463	68.48 407	97.39 380	71.93 442	95.47 231	92.18 433

MVStest1		82.38 413	80.04 417	89.37 412	87.63 453	82.83 389	95.03 356	93.37 423	73.90 449	73.50 451	94.35 339	62.89 436	93.25 450	73.80 434	65.92 458	92.04 435

UnsupCasMVSNet_bld		82.13 414	79.46 419	90.14 402	88.00 451	82.47 395	90.89 440	96.62 297	78.94 438	75.61 445	84.40 456	56.63 447	96.31 412	77.30 417	66.77 457	91.63 437

dmvs_testset		81.38 415	82.60 408	77.73 438	91.74 429	51.49 473	93.03 420	84.21 466	89.07 287	78.28 442	91.25 423	76.97 335	88.53 461	56.57 461	82.24 413	93.16 414

test_f		80.57 416	79.62 418	83.41 433	83.38 462	67.80 460	93.57 410	93.72 418	80.80 430	77.91 443	87.63 449	33.40 465	92.08 453	87.14 318	79.04 427	90.34 448

pmmvs3		79.97 417	77.50 422	87.39 424	82.80 463	79.38 432	92.70 425	90.75 448	70.69 455	78.66 440	87.47 451	51.34 455	93.40 447	73.39 437	69.65 451	89.38 450

APD_test1		79.31 418	77.70 421	84.14 431	89.11 445	69.07 457	92.36 430	91.50 442	69.07 456	73.87 449	92.63 399	39.93 462	94.32 438	70.54 448	80.25 420	89.02 451

N_pmnet		78.73 419	78.71 420	78.79 437	92.80 415	46.50 476	94.14 387	43.71 478	78.61 439	80.83 428	91.66 420	74.94 356	96.36 411	67.24 452	84.45 394	93.50 410

WB-MVS		76.77 420	76.63 423	77.18 439	85.32 457	56.82 471	94.53 369	89.39 452	82.66 416	71.35 452	89.18 438	75.03 353	88.88 459	35.42 468	66.79 456	85.84 453

SSC-MVS		76.05 421	75.83 424	76.72 443	84.77 458	56.22 472	94.32 381	88.96 454	81.82 422	70.52 453	88.91 440	74.79 357	88.71 460	33.69 469	64.71 459	85.23 454

test_vis3_rt		72.73 422	70.55 425	79.27 436	80.02 465	68.13 459	93.92 395	74.30 473	76.90 444	58.99 464	73.58 464	20.29 473	95.37 429	84.16 359	72.80 447	74.31 461

LCM-MVSNet		72.55 423	69.39 427	82.03 434	70.81 474	65.42 463	90.12 445	94.36 405	55.02 464	65.88 458	81.72 457	24.16 472	89.96 455	74.32 432	68.10 455	90.71 447

FPMVS		71.27 424	69.85 426	75.50 444	74.64 469	59.03 469	91.30 434	91.50 442	58.80 461	57.92 465	88.28 444	29.98 468	85.53 464	53.43 462	82.84 411	81.95 457

PMMVS2		70.19 425	66.92 429	80.01 435	76.35 468	65.67 462	86.22 458	87.58 458	64.83 460	62.38 461	80.29 460	26.78 470	88.49 462	63.79 454	54.07 465	85.88 452

dongtai		69.99 426	69.33 428	71.98 447	88.78 447	61.64 467	89.86 446	59.93 477	75.67 446	74.96 448	85.45 453	50.19 456	81.66 466	43.86 465	55.27 464	72.63 462

testf1		69.31 427	66.76 430	76.94 441	78.61 466	61.93 465	88.27 455	86.11 463	55.62 462	59.69 462	85.31 454	20.19 474	89.32 456	57.62 458	69.44 453	79.58 458

APD_test2		69.31 427	66.76 430	76.94 441	78.61 466	61.93 465	88.27 455	86.11 463	55.62 462	59.69 462	85.31 454	20.19 474	89.32 456	57.62 458	69.44 453	79.58 458

EGC-MVSNET		68.77 429	63.01 435	86.07 430	92.49 421	82.24 399	93.96 392	90.96 446	0.71 475	2.62 476	90.89 424	53.66 452	93.46 446	57.25 460	84.55 392	82.51 456

Gipuma		67.86 430	65.41 432	75.18 445	92.66 418	73.45 449	66.50 466	94.52 396	53.33 465	57.80 466	66.07 466	30.81 466	89.20 458	48.15 464	78.88 428	62.90 466
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		66.11 431	64.89 433	69.79 448	72.62 472	35.23 480	65.19 467	92.83 431	20.35 470	65.20 459	88.08 447	43.14 461	82.70 465	73.12 438	63.46 460	91.45 443

kuosan		65.27 432	64.66 434	67.11 450	83.80 459	61.32 468	88.53 454	60.77 476	68.22 457	67.67 455	80.52 459	49.12 457	70.76 472	29.67 471	53.64 466	69.26 464

ANet_high		63.94 433	59.58 436	77.02 440	61.24 476	66.06 461	85.66 460	87.93 457	78.53 440	42.94 468	71.04 465	25.42 471	80.71 467	52.60 463	30.83 469	84.28 455

PMVS	53.92 22	58.58 434	55.40 437	68.12 449	51.00 477	48.64 474	78.86 463	87.10 460	46.77 466	35.84 472	74.28 462	8.76 476	86.34 463	42.07 466	73.91 444	69.38 463
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		53.28 435	52.56 439	55.43 452	74.43 470	47.13 475	83.63 462	76.30 470	42.23 467	42.59 469	62.22 468	28.57 469	74.40 469	31.53 470	31.51 468	44.78 467

MVE	50.73 23	53.25 436	48.81 441	66.58 451	65.34 475	57.50 470	72.49 465	70.94 474	40.15 469	39.28 471	63.51 467	6.89 478	73.48 471	38.29 467	42.38 467	68.76 465
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		52.08 437	51.31 440	54.39 453	72.62 472	45.39 477	83.84 461	75.51 472	41.13 468	40.77 470	59.65 469	30.08 467	73.60 470	28.31 472	29.90 470	44.18 468

tmp_tt		51.94 438	53.82 438	46.29 454	33.73 478	45.30 478	78.32 464	67.24 475	18.02 471	50.93 467	87.05 452	52.99 453	53.11 473	70.76 446	25.29 471	40.46 469

wuyk23d		25.11 439	24.57 443	26.74 455	73.98 471	39.89 479	57.88 468	9.80 479	12.27 472	10.39 473	6.97 475	7.03 477	36.44 474	25.43 473	17.39 472	3.89 472

cdsmvs_eth3d_5k		23.24 440	30.99 442	0.00 458	0.00 481	0.00 483	0.00 469	97.63 162	0.00 476	0.00 477	96.88 201	84.38 195	0.00 477	0.00 476	0.00 475	0.00 473

testmvs		13.36 441	16.33 444	4.48 457	5.04 479	2.26 482	93.18 414	3.28 480	2.70 473	8.24 474	21.66 471	2.29 480	2.19 475	7.58 474	2.96 473	9.00 471

test123		13.04 442	15.66 445	5.18 456	4.51 480	3.45 481	92.50 428	1.81 481	2.50 474	7.58 475	20.15 472	3.67 479	2.18 476	7.13 475	1.07 474	9.90 470

ab-mvs-re		8.06 443	10.74 446	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	96.69 212	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

pcd_1.5k_mvsjas		7.39 444	9.85 447	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	88.65 106	0.00 477	0.00 476	0.00 475	0.00 473

mmdepth		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

monomultidepth		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

test_blank		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uanet_test		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

DCPMVS		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

sosnet-low-res		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

sosnet		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uncertanet		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

Regformer		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uanet		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 469	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

WAC-MVS						79.53 428								75.56 426

FOURS1					99.55 1	93.34 68	99.29 1	98.35 39	94.98 45	98.49 35

MSC_two_6792asdad				98.86 1	98.67 64	96.94 1		97.93 121					99.86 9	97.68 32	99.67 6	99.77 2

PC_three_1452									90.77 228	98.89 25	98.28 82	96.24 1	98.35 270	95.76 102	99.58 23	99.59 29

No_MVS				98.86 1	98.67 64	96.94 1		97.93 121					99.86 9	97.68 32	99.67 6	99.77 2

test_one_0601					99.32 24	95.20 20		98.25 58	95.13 39	98.48 36	98.87 30	95.16 7

eth-test2					0.00 481

eth-test					0.00 481

ZD-MVS					99.05 42	94.59 32		98.08 90	89.22 283	97.03 77	98.10 90	92.52 40	99.65 75	94.58 144	99.31 68

RE-MVS-def			96.72 59		99.02 45	92.34 105	97.98 66	98.03 107	93.52 113	97.43 63	98.51 52	90.71 79		96.05 90	99.26 74	99.43 60

IU-MVS					99.42 7	95.39 11		97.94 120	90.40 251	98.94 18				97.41 48	99.66 10	99.74 8

OPU-MVS				98.55 3	98.82 58	96.86 3	98.25 36				98.26 83	96.04 2	99.24 145	95.36 116	99.59 19	99.56 37

test_241102_TWO								98.27 52	95.13 39	98.93 19	98.89 27	94.99 11	99.85 18	97.52 41	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 52	95.09 42	99.19 12	98.81 36	95.54 5	99.65 75

9.14			96.75 58		98.93 53		97.73 110	98.23 63	91.28 205	97.88 51	98.44 60	93.00 27	99.65 75	95.76 102	99.47 42

save fliter					98.91 55	94.28 39	97.02 201	98.02 110	95.35 30

test_0728_THIRD									94.78 60	98.73 29	98.87 30	95.87 4	99.84 23	97.45 45	99.72 2	99.77 2

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 49					99.86 9	97.52 41	99.67 6	99.75 6

test0726					99.45 3	95.36 13	98.31 28	98.29 47	94.92 49	98.99 17	98.92 22	95.08 8

GSMVS																98.45 176

test_part2					99.28 27	95.74 8				98.10 44

sam_mvs1												82.76 231				98.45 176

sam_mvs												81.94 252

ambc				86.56 428	83.60 461	70.00 455	85.69 459	94.97 376		80.60 431	88.45 442	37.42 463	96.84 402	82.69 378	75.44 440	92.86 418

MTGPA								98.08 90

test_post1							92.81 424				16.58 474	80.53 278	97.68 353	86.20 329

test_post											17.58 473	81.76 255	98.08 297

patchmatchnet-post											90.45 428	82.65 236	98.10 292

GG-mvs-BLEND				93.62 301	93.69 389	89.20 245	92.39 429	83.33 467		87.98 357	89.84 434	71.00 382	96.87 401	82.08 382	95.40 233	94.80 377

MTMP							97.86 86	82.03 468

gm-plane-assit					93.22 406	78.89 436			84.82 391		93.52 381		98.64 240	87.72 297

test9_res														94.81 134	99.38 61	99.45 56

TEST9					98.70 62	94.19 43	96.41 267	98.02 110	88.17 321	96.03 122	97.56 154	92.74 34	99.59 91

test_8					98.67 64	94.06 50	96.37 275	98.01 113	88.58 308	95.98 126	97.55 156	92.73 35	99.58 94

agg_prior2														93.94 158	99.38 61	99.50 49

agg_prior					98.67 64	93.79 56		98.00 114		95.68 139			99.57 101

TestCases				93.98 277	97.94 126	86.64 316		95.54 350	85.38 380	85.49 395	96.77 206	70.28 388	99.15 159	80.02 401	92.87 280	96.15 298

test_prior4						93.66 59	96.42 266

test_prior2							96.35 276		92.80 151	96.03 122	97.59 151	92.01 48		95.01 124	99.38 61

test_prior				97.23 66	98.67 64	92.99 80		98.00 114					99.41 128			99.29 72

旧先验2							95.94 306		81.66 423	97.34 66			98.82 205	92.26 191

新几何2							95.79 316

新几何1				97.32 59	98.60 71	93.59 60		97.75 145	81.58 424	95.75 134	97.85 119	90.04 86	99.67 73	86.50 325	99.13 94	98.69 153

旧先验1					98.38 85	93.38 65		97.75 145			98.09 92	92.30 46			99.01 104	99.16 82

无先验							95.79 316	97.87 128	83.87 403				99.65 75	87.68 303		98.89 130

原ACMM2							95.67 322

原ACMM1				96.38 121	98.59 72	91.09 164		97.89 124	87.41 346	95.22 153	97.68 138	90.25 83	99.54 106	87.95 293	99.12 96	98.49 171

test222					98.24 96	92.21 111	95.33 341	97.60 167	79.22 437	95.25 151	97.84 121	88.80 103			99.15 91	98.72 150

testdata2													99.67 73	85.96 337

segment_acmp												92.89 31

testdata				95.46 194	98.18 107	88.90 254		97.66 156	82.73 415	97.03 77	98.07 93	90.06 85	98.85 201	89.67 257	98.98 105	98.64 156

testdata1							95.26 348		93.10 133

test12				97.65 44	98.46 76	94.26 40		97.66 156		95.52 146		90.89 76	99.46 122		99.25 76	99.22 79

plane_prior7					96.21 259	89.98 208

plane_prior6					96.10 277	90.00 204						81.32 262

plane_prior5								97.51 181					98.60 245	93.02 183	92.23 291	95.86 306

plane_prior4											96.64 215

plane_prior3						90.00 204			94.46 77	91.34 261

plane_prior2							97.74 108		94.85 52

plane_prior1					96.14 272

plane_prior						89.99 206	97.24 181		94.06 90						92.16 295

n2								0.00 482

nn								0.00 482

door-mid								91.06 445

lessismore_v0				90.45 397	91.96 428	79.09 435		87.19 459		80.32 433	94.39 336	66.31 422	97.55 365	84.00 363	76.84 433	94.70 384

LGP-MVS_train				94.10 269	96.16 269	88.26 272		97.46 192	91.29 202	90.12 291	97.16 180	79.05 306	98.73 223	92.25 193	91.89 299	95.31 343

test11								97.88 126

door								91.13 444

HQP5-MVS						89.33 238

HQP-NCC					95.86 285		96.65 247		93.55 107	90.14 285

ACMP_Plane					95.86 285		96.65 247		93.55 107	90.14 285

BP-MVS														92.13 199

HQP4-MVS										90.14 285			98.50 255			95.78 314

HQP3-MVS								97.39 209							92.10 296

HQP2-MVS												80.95 266

NP-MVS					95.99 283	89.81 216					95.87 258

MDTV_nov1_ep13_2view						70.35 454	93.10 419		83.88 402	93.55 202		82.47 240		86.25 328		98.38 184

MDTV_nov1_ep13			90.76 280		95.22 327	80.33 417	93.03 420	95.28 361	88.14 324	92.84 225	93.83 366	81.34 261	98.08 297	82.86 372	94.34 253

ACMMP++_ref															90.30 325

ACMMP++															91.02 314

Test By Simon												88.73 105

ITE_SJBPF				92.43 344	95.34 316	85.37 353		95.92 326	91.47 195	87.75 360	96.39 233	71.00 382	97.96 320	82.36 380	89.86 328	93.97 405

DeepMVS_CX				74.68 446	90.84 434	64.34 464		81.61 469	65.34 459	67.47 457	88.01 448	48.60 458	80.13 468	62.33 456	73.68 445	79.58 458

High-resolution multi-view benchmark