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.

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 55	99.43 57	97.48 83	98.88 116	99.30 13	98.47 13	99.85 8	99.43 36	96.71 17	99.96 4	99.86 1	99.80 24	99.89 4

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 19	99.24 5	99.02 79	98.87 75	97.65 31	99.73 17	99.48 27	97.53 7	99.94 11	98.43 57	99.81 15	99.70 58

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 100	99.23 7	99.69 1	98.88 68	97.32 53	99.53 30	99.47 29	97.81 3	99.94 11	98.47 53	99.72 59	99.74 41

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 51	99.41 59	97.54 81	98.89 110	99.31 12	98.49 12	99.86 5	99.42 37	96.45 24	99.96 4	99.86 1	99.74 52	99.90 3

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 89	98.58 162	97.62 33	99.45 32	99.46 33	97.42 9	99.94 11	98.47 53	99.81 15	99.69 61
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
APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 33	98.96 16	99.39 10	98.93 56	97.38 50	99.41 35	99.54 15	96.66 18	99.84 77	98.86 32	99.85 6	99.87 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
reproduce_model		98.94 7	98.81 10	99.34 26	99.52 39	98.26 49	98.94 98	98.84 85	98.06 19	99.35 39	99.61 4	96.39 27	99.94 11	98.77 35	99.82 14	99.83 13

reproduce-ours		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 123	98.83 87	98.06 19	99.29 43	99.58 11	96.40 25	99.94 11	98.68 37	99.81 15	99.81 19

our_new_method		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 123	98.83 87	98.06 19	99.29 43	99.58 11	96.40 25	99.94 11	98.68 37	99.81 15	99.81 19

test_fmvsmconf_n		98.92 10	98.87 6	99.04 60	98.88 135	97.25 101	98.82 135	99.34 10	98.75 6	99.80 10	99.61 4	95.16 73	99.95 9	99.70 12	99.80 24	99.93 1

DPE-MVS		98.92 10	98.67 16	99.65 2	99.58 32	99.20 9	98.42 222	98.91 62	97.58 36	99.54 29	99.46 33	97.10 12	99.94 11	97.64 104	99.84 11	99.83 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_l_conf0.5_n_3		98.90 12	98.74 14	99.37 22	99.36 60	98.25 50	98.89 110	99.24 18	98.77 5	99.89 1	99.59 10	93.39 107	99.96 4	99.78 5	99.76 42	99.89 4

SteuartSystems-ACMMP		98.90 12	98.75 13	99.36 24	99.22 95	98.43 33	99.10 63	98.87 75	97.38 50	99.35 39	99.40 40	97.78 5	99.87 68	97.77 92	99.85 6	99.78 25
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 14	99.01 3	98.45 108	99.42 58	96.43 140	98.96 94	99.36 9	98.63 8	99.86 5	99.51 21	95.91 43	99.97 1	99.72 9	99.75 48	98.94 190

TSAR-MVS + MP.		98.78 15	98.62 17	99.24 40	99.69 24	98.28 48	99.14 54	98.66 142	96.84 82	99.56 27	99.31 60	96.34 28	99.70 129	98.32 63	99.73 55	99.73 46
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		98.78 15	98.56 20	99.45 15	99.32 66	98.87 19	98.47 214	98.81 96	97.72 26	98.76 82	99.16 87	97.05 13	99.78 111	98.06 74	99.66 69	99.69 61

MSP-MVS		98.74 17	98.55 21	99.29 33	99.75 3	98.23 51	99.26 27	98.88 68	97.52 39	99.41 35	98.78 144	96.00 39	99.79 108	97.79 91	99.59 86	99.85 10
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
XVS		98.70 18	98.49 27	99.34 26	99.70 22	98.35 44	99.29 22	98.88 68	97.40 47	98.46 100	99.20 77	95.90 45	99.89 57	97.85 87	99.74 52	99.78 25

fmvsm_s_conf0.5_n_6		98.65 19	98.55 21	98.95 69	98.50 174	97.30 95	98.79 151	99.16 32	98.14 17	99.86 5	99.41 39	93.71 104	99.91 46	99.71 10	99.64 77	99.65 74

MCST-MVS		98.65 19	98.37 36	99.48 13	99.60 31	98.87 19	98.41 223	98.68 134	97.04 74	98.52 98	98.80 142	96.78 16	99.83 79	97.93 81	99.61 82	99.74 41

SD-MVS		98.64 21	98.68 15	98.53 99	99.33 63	98.36 43	98.90 106	98.85 84	97.28 56	99.72 19	99.39 41	96.63 20	97.60 374	98.17 69	99.85 6	99.64 77
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
HFP-MVS		98.63 22	98.40 33	99.32 32	99.72 12	98.29 47	99.23 32	98.96 51	96.10 120	98.94 65	99.17 84	96.06 36	99.92 37	97.62 105	99.78 34	99.75 39

ACMMP_NAP		98.61 23	98.30 50	99.55 9	99.62 30	98.95 17	98.82 135	98.81 96	95.80 131	99.16 55	99.47 29	95.37 60	99.92 37	97.89 85	99.75 48	99.79 23

region2R		98.61 23	98.38 35	99.29 33	99.74 7	98.16 57	99.23 32	98.93 56	96.15 116	98.94 65	99.17 84	95.91 43	99.94 11	97.55 113	99.79 30	99.78 25

NCCC		98.61 23	98.35 39	99.38 18	99.28 81	98.61 26	98.45 215	98.76 114	97.82 25	98.45 103	98.93 126	96.65 19	99.83 79	97.38 122	99.41 117	99.71 54

SF-MVS		98.59 26	98.32 49	99.41 17	99.54 35	98.71 22	99.04 73	98.81 96	95.12 168	99.32 42	99.39 41	96.22 30	99.84 77	97.72 95	99.73 55	99.67 70

ACMMPR		98.59 26	98.36 37	99.29 33	99.74 7	98.15 58	99.23 32	98.95 52	96.10 120	98.93 69	99.19 82	95.70 49	99.94 11	97.62 105	99.79 30	99.78 25

test_fmvsmconf0.1_n		98.58 28	98.44 31	98.99 62	97.73 254	97.15 106	98.84 131	98.97 48	98.75 6	99.43 34	99.54 15	93.29 109	99.93 30	99.64 15	99.79 30	99.89 4

SMA-MVS		98.58 28	98.25 53	99.56 8	99.51 40	99.04 15	98.95 95	98.80 103	93.67 253	99.37 38	99.52 18	96.52 22	99.89 57	98.06 74	99.81 15	99.76 38
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
MTAPA		98.58 28	98.29 51	99.46 14	99.76 2	98.64 25	98.90 106	98.74 118	97.27 60	98.02 127	99.39 41	94.81 83	99.96 4	97.91 83	99.79 30	99.77 31

HPM-MVS++		98.58 28	98.25 53	99.55 9	99.50 42	99.08 11	98.72 167	98.66 142	97.51 40	98.15 114	98.83 139	95.70 49	99.92 37	97.53 115	99.67 66	99.66 73

SR-MVS		98.57 32	98.35 39	99.24 40	99.53 36	98.18 55	99.09 64	98.82 90	96.58 98	99.10 57	99.32 58	95.39 58	99.82 86	97.70 100	99.63 79	99.72 50

CP-MVS		98.57 32	98.36 37	99.19 44	99.66 26	97.86 69	99.34 16	98.87 75	95.96 123	98.60 95	99.13 92	96.05 37	99.94 11	97.77 92	99.86 2	99.77 31

MSLP-MVS++		98.56 34	98.57 19	98.55 95	99.26 84	96.80 120	98.71 168	99.05 42	97.28 56	98.84 75	99.28 63	96.47 23	99.40 189	98.52 51	99.70 62	99.47 106

DeepC-MVS_fast	96.70 1	98.55 35	98.34 44	99.18 46	99.25 85	98.04 63	98.50 211	98.78 110	97.72 26	98.92 71	99.28 63	95.27 66	99.82 86	97.55 113	99.77 36	99.69 61
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		98.54 36	98.35 39	99.13 52	99.49 46	97.86 69	99.11 60	98.80 103	96.49 101	99.17 52	99.35 53	95.34 62	99.82 86	97.72 95	99.65 72	99.71 54

fmvsm_s_conf0.5_n_5		98.53 37	98.35 39	99.08 57	99.07 115	97.46 87	98.68 176	99.20 27	97.50 41	99.87 2	99.50 23	91.96 141	99.96 4	99.76 6	99.65 72	99.82 17

fmvsm_s_conf0.5_n_3		98.53 37	98.45 30	98.79 77	99.23 93	97.32 92	98.80 144	99.26 15	98.82 2	99.87 2	99.60 8	90.95 168	99.93 30	99.76 6	99.73 55	99.12 165

APD-MVS_3200maxsize		98.53 37	98.33 48	99.15 50	99.50 42	97.92 68	99.15 51	98.81 96	96.24 112	99.20 49	99.37 47	95.30 64	99.80 98	97.73 94	99.67 66	99.72 50

MM		98.51 40	98.24 55	99.33 30	99.12 109	98.14 60	98.93 101	97.02 360	98.96 1	99.17 52	99.47 29	91.97 140	99.94 11	99.85 3	99.69 63	99.91 2

mPP-MVS		98.51 40	98.26 52	99.25 39	99.75 3	98.04 63	99.28 24	98.81 96	96.24 112	98.35 110	99.23 72	95.46 55	99.94 11	97.42 120	99.81 15	99.77 31

ZNCC-MVS		98.49 42	98.20 61	99.35 25	99.73 11	98.39 34	99.19 44	98.86 81	95.77 133	98.31 113	99.10 96	95.46 55	99.93 30	97.57 112	99.81 15	99.74 41

SPE-MVS-test		98.49 42	98.50 25	98.46 107	99.20 98	97.05 110	99.64 4	98.50 184	97.45 46	98.88 72	99.14 91	95.25 68	99.15 217	98.83 33	99.56 96	99.20 150

PGM-MVS		98.49 42	98.23 57	99.27 38	99.72 12	98.08 62	98.99 86	99.49 5	95.43 149	99.03 58	99.32 58	95.56 52	99.94 11	96.80 151	99.77 36	99.78 25

EI-MVSNet-Vis-set		98.47 45	98.39 34	98.69 84	99.46 52	96.49 137	98.30 234	98.69 131	97.21 63	98.84 75	99.36 51	95.41 57	99.78 111	98.62 40	99.65 72	99.80 22

MVS_111021_HR		98.47 45	98.34 44	98.88 74	99.22 95	97.32 92	97.91 286	99.58 3	97.20 64	98.33 111	99.00 115	95.99 40	99.64 142	98.05 76	99.76 42	99.69 61

balanced_conf03		98.45 47	98.35 39	98.74 80	98.65 163	97.55 79	99.19 44	98.60 153	96.72 92	99.35 39	98.77 146	95.06 78	99.55 165	98.95 29	99.87 1	99.12 165

test_fmvsmvis_n_1920		98.44 48	98.51 23	98.23 128	98.33 194	96.15 154	98.97 89	99.15 34	98.55 11	98.45 103	99.55 13	94.26 96	99.97 1	99.65 13	99.66 69	98.57 230

CS-MVS		98.44 48	98.49 27	98.31 120	99.08 114	96.73 124	99.67 3	98.47 191	97.17 66	98.94 65	99.10 96	95.73 48	99.13 220	98.71 36	99.49 107	99.09 170

GST-MVS		98.43 50	98.12 65	99.34 26	99.72 12	98.38 35	99.09 64	98.82 90	95.71 137	98.73 85	99.06 107	95.27 66	99.93 30	97.07 130	99.63 79	99.72 50

fmvsm_s_conf0.5_n		98.42 51	98.51 23	98.13 137	99.30 72	95.25 200	98.85 127	99.39 7	97.94 23	99.74 16	99.62 3	92.59 118	99.91 46	99.65 13	99.52 102	99.25 143

EI-MVSNet-UG-set		98.41 52	98.34 44	98.61 90	99.45 55	96.32 147	98.28 237	98.68 134	97.17 66	98.74 83	99.37 47	95.25 68	99.79 108	98.57 42	99.54 99	99.73 46

DELS-MVS		98.40 53	98.20 61	98.99 62	99.00 122	97.66 74	97.75 307	98.89 65	97.71 28	98.33 111	98.97 117	94.97 80	99.88 66	98.42 59	99.76 42	99.42 117
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
fmvsm_s_conf0.5_n_a		98.38 54	98.42 32	98.27 122	99.09 113	95.41 190	98.86 123	99.37 8	97.69 30	99.78 12	99.61 4	92.38 121	99.91 46	99.58 17	99.43 115	99.49 102

TSAR-MVS + GP.		98.38 54	98.24 55	98.81 76	99.22 95	97.25 101	98.11 261	98.29 230	97.19 65	98.99 63	99.02 110	96.22 30	99.67 136	98.52 51	98.56 165	99.51 95

HPM-MVS_fast		98.38 54	98.13 64	99.12 54	99.75 3	97.86 69	99.44 9	98.82 90	94.46 208	98.94 65	99.20 77	95.16 73	99.74 121	97.58 108	99.85 6	99.77 31

patch_mono-2		98.36 57	98.87 6	96.82 232	99.53 36	90.68 340	98.64 186	99.29 14	97.88 24	99.19 51	99.52 18	96.80 15	99.97 1	99.11 25	99.86 2	99.82 17

HPM-MVS		98.36 57	98.10 68	99.13 52	99.74 7	97.82 73	99.53 6	98.80 103	94.63 197	98.61 94	98.97 117	95.13 75	99.77 116	97.65 103	99.83 13	99.79 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_4		98.35 59	98.50 25	97.90 154	99.16 104	95.08 209	98.75 155	99.24 18	98.39 14	99.81 9	99.52 18	92.35 122	99.90 54	99.74 8	99.51 104	98.71 211

APD-MVS		98.35 59	98.00 74	99.42 16	99.51 40	98.72 21	98.80 144	98.82 90	94.52 205	99.23 48	99.25 71	95.54 54	99.80 98	96.52 158	99.77 36	99.74 41
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 61	98.23 57	98.67 86	99.27 82	96.90 116	97.95 279	99.58 3	97.14 69	98.44 105	99.01 114	95.03 79	99.62 149	97.91 83	99.75 48	99.50 97

PHI-MVS		98.34 61	98.06 69	99.18 46	99.15 107	98.12 61	99.04 73	99.09 37	93.32 268	98.83 77	99.10 96	96.54 21	99.83 79	97.70 100	99.76 42	99.59 85

MP-MVS		98.33 63	98.01 73	99.28 36	99.75 3	98.18 55	99.22 36	98.79 108	96.13 117	97.92 138	99.23 72	94.54 86	99.94 11	96.74 154	99.78 34	99.73 46
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 64	98.19 63	98.67 86	98.96 129	97.36 90	99.24 30	98.57 164	94.81 189	98.99 63	98.90 130	95.22 71	99.59 152	99.15 24	99.84 11	99.07 178

MP-MVS-pluss		98.31 64	97.92 76	99.49 12	99.72 12	98.88 18	98.43 220	98.78 110	94.10 218	97.69 153	99.42 37	95.25 68	99.92 37	98.09 73	99.80 24	99.67 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 66	98.21 59	98.57 92	99.25 85	97.11 107	98.66 182	99.20 27	98.82 2	99.79 11	99.60 8	89.38 199	99.92 37	99.80 4	99.38 122	98.69 213

MVS_0304		98.23 67	97.91 77	99.21 43	98.06 224	97.96 67	98.58 195	95.51 397	98.58 9	98.87 73	99.26 66	92.99 113	99.95 9	99.62 16	99.67 66	99.73 46

ACMMP		98.23 67	97.95 75	99.09 56	99.74 7	97.62 77	99.03 76	99.41 6	95.98 122	97.60 162	99.36 51	94.45 91	99.93 30	97.14 127	98.85 151	99.70 58
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
EC-MVSNet		98.21 69	98.11 66	98.49 104	98.34 191	97.26 100	99.61 5	98.43 200	96.78 85	98.87 73	98.84 137	93.72 103	99.01 242	98.91 31	99.50 105	99.19 154

fmvsm_s_conf0.1_n		98.18 70	98.21 59	98.11 141	98.54 172	95.24 201	98.87 119	99.24 18	97.50 41	99.70 20	99.67 1	91.33 157	99.89 57	99.47 19	99.54 99	99.21 149

fmvsm_s_conf0.1_n_2		98.14 71	98.02 72	98.53 99	98.88 135	97.07 109	98.69 174	98.82 90	98.78 4	99.77 13	99.61 4	88.83 218	99.91 46	99.71 10	99.07 135	98.61 223

fmvsm_s_conf0.1_n_a		98.08 72	98.04 71	98.21 129	97.66 260	95.39 191	98.89 110	99.17 31	97.24 61	99.76 15	99.67 1	91.13 162	99.88 66	99.39 20	99.41 117	99.35 122

dcpmvs_2		98.08 72	98.59 18	96.56 257	99.57 33	90.34 349	99.15 51	98.38 210	96.82 84	99.29 43	99.49 26	95.78 47	99.57 155	98.94 30	99.86 2	99.77 31

CANet		98.05 74	97.76 80	98.90 73	98.73 148	97.27 96	98.35 225	98.78 110	97.37 52	97.72 150	98.96 122	91.53 153	99.92 37	98.79 34	99.65 72	99.51 95

train_agg		97.97 75	97.52 92	99.33 30	99.31 68	98.50 29	97.92 284	98.73 121	92.98 284	97.74 147	98.68 157	96.20 32	99.80 98	96.59 155	99.57 90	99.68 66

ETV-MVS		97.96 76	97.81 78	98.40 115	98.42 179	97.27 96	98.73 163	98.55 169	96.84 82	98.38 107	97.44 276	95.39 58	99.35 194	97.62 105	98.89 146	98.58 229

UA-Net		97.96 76	97.62 84	98.98 64	98.86 139	97.47 85	98.89 110	99.08 38	96.67 95	98.72 86	99.54 15	93.15 111	99.81 91	94.87 213	98.83 152	99.65 74

CDPH-MVS		97.94 78	97.49 94	99.28 36	99.47 50	98.44 31	97.91 286	98.67 139	92.57 300	98.77 81	98.85 136	95.93 42	99.72 123	95.56 192	99.69 63	99.68 66

DeepPCF-MVS	96.37 2	97.93 79	98.48 29	96.30 282	99.00 122	89.54 364	97.43 329	98.87 75	98.16 16	99.26 47	99.38 46	96.12 35	99.64 142	98.30 64	99.77 36	99.72 50

DeepC-MVS	95.98 3	97.88 80	97.58 86	98.77 78	99.25 85	96.93 114	98.83 133	98.75 116	96.96 78	96.89 188	99.50 23	90.46 176	99.87 68	97.84 89	99.76 42	99.52 92
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf0.01_n		97.86 81	97.54 91	98.83 75	95.48 379	96.83 119	98.95 95	98.60 153	98.58 9	98.93 69	99.55 13	88.57 223	99.91 46	99.54 18	99.61 82	99.77 31

DP-MVS Recon		97.86 81	97.46 97	99.06 59	99.53 36	98.35 44	98.33 227	98.89 65	92.62 297	98.05 122	98.94 125	95.34 62	99.65 139	96.04 174	99.42 116	99.19 154

CSCG		97.85 83	97.74 81	98.20 131	99.67 25	95.16 204	99.22 36	99.32 11	93.04 282	97.02 181	98.92 128	95.36 61	99.91 46	97.43 119	99.64 77	99.52 92

BP-MVS1		97.82 84	97.51 93	98.76 79	98.25 201	97.39 89	99.15 51	97.68 297	96.69 93	98.47 99	99.10 96	90.29 180	99.51 172	98.60 41	99.35 125	99.37 120

MG-MVS		97.81 85	97.60 85	98.44 110	99.12 109	95.97 163	97.75 307	98.78 110	96.89 81	98.46 100	99.22 74	93.90 102	99.68 135	94.81 217	99.52 102	99.67 70

VNet		97.79 86	97.40 101	98.96 67	98.88 135	97.55 79	98.63 189	98.93 56	96.74 89	99.02 59	98.84 137	90.33 179	99.83 79	98.53 45	96.66 229	99.50 97

EIA-MVS		97.75 87	97.58 86	98.27 122	98.38 183	96.44 139	99.01 81	98.60 153	95.88 127	97.26 169	97.53 270	94.97 80	99.33 197	97.38 122	99.20 131	99.05 179

PS-MVSNAJ		97.73 88	97.77 79	97.62 182	98.68 158	95.58 181	97.34 338	98.51 179	97.29 55	98.66 91	97.88 235	94.51 87	99.90 54	97.87 86	99.17 133	97.39 272

casdiffmvs_mvg		97.72 89	97.48 96	98.44 110	98.42 179	96.59 132	98.92 103	98.44 196	96.20 114	97.76 144	99.20 77	91.66 147	99.23 207	98.27 68	98.41 175	99.49 102
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CPTT-MVS		97.72 89	97.32 105	98.92 70	99.64 28	97.10 108	99.12 58	98.81 96	92.34 308	98.09 119	99.08 105	93.01 112	99.92 37	96.06 173	99.77 36	99.75 39

PVSNet_Blended_VisFu		97.70 91	97.46 97	98.44 110	99.27 82	95.91 171	98.63 189	99.16 32	94.48 207	97.67 154	98.88 133	92.80 115	99.91 46	97.11 128	99.12 134	99.50 97

mvsany_test1		97.69 92	97.70 82	97.66 180	98.24 202	94.18 255	97.53 323	97.53 315	95.52 145	99.66 22	99.51 21	94.30 94	99.56 158	98.38 60	98.62 161	99.23 145

sasdasda		97.67 93	97.23 109	98.98 64	98.70 153	98.38 35	99.34 16	98.39 206	96.76 87	97.67 154	97.40 280	92.26 126	99.49 176	98.28 65	96.28 247	99.08 174

canonicalmvs		97.67 93	97.23 109	98.98 64	98.70 153	98.38 35	99.34 16	98.39 206	96.76 87	97.67 154	97.40 280	92.26 126	99.49 176	98.28 65	96.28 247	99.08 174

xiu_mvs_v2_base		97.66 95	97.70 82	97.56 186	98.61 167	95.46 188	97.44 327	98.46 192	97.15 68	98.65 92	98.15 211	94.33 93	99.80 98	97.84 89	98.66 160	97.41 270

GDP-MVS		97.64 96	97.28 106	98.71 83	98.30 199	97.33 91	99.05 69	98.52 176	96.34 109	98.80 78	99.05 108	89.74 189	99.51 172	96.86 148	98.86 150	99.28 137

baseline		97.64 96	97.44 99	98.25 126	98.35 186	96.20 151	99.00 83	98.32 220	96.33 111	98.03 125	99.17 84	91.35 156	99.16 214	98.10 72	98.29 182	99.39 118

casdiffmvs		97.63 98	97.41 100	98.28 121	98.33 194	96.14 155	98.82 135	98.32 220	96.38 108	97.95 133	99.21 75	91.23 161	99.23 207	98.12 71	98.37 176	99.48 104
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MGCFI-Net		97.62 99	97.19 112	98.92 70	98.66 160	98.20 53	99.32 21	98.38 210	96.69 93	97.58 163	97.42 279	92.10 134	99.50 175	98.28 65	96.25 250	99.08 174

xiu_mvs_v1_base_debu		97.60 100	97.56 88	97.72 170	98.35 186	95.98 158	97.86 296	98.51 179	97.13 70	99.01 60	98.40 184	91.56 149	99.80 98	98.53 45	98.68 156	97.37 274

xiu_mvs_v1_base		97.60 100	97.56 88	97.72 170	98.35 186	95.98 158	97.86 296	98.51 179	97.13 70	99.01 60	98.40 184	91.56 149	99.80 98	98.53 45	98.68 156	97.37 274

xiu_mvs_v1_base_debi		97.60 100	97.56 88	97.72 170	98.35 186	95.98 158	97.86 296	98.51 179	97.13 70	99.01 60	98.40 184	91.56 149	99.80 98	98.53 45	98.68 156	97.37 274

diffmvs		97.58 103	97.40 101	98.13 137	98.32 197	95.81 176	98.06 267	98.37 212	96.20 114	98.74 83	98.89 132	91.31 159	99.25 204	98.16 70	98.52 167	99.34 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSFormer		97.57 104	97.49 94	97.84 157	98.07 221	95.76 177	99.47 7	98.40 204	94.98 178	98.79 79	98.83 139	92.34 123	98.41 315	96.91 136	99.59 86	99.34 124

alignmvs		97.56 105	97.07 118	99.01 61	98.66 160	98.37 42	98.83 133	98.06 277	96.74 89	98.00 131	97.65 258	90.80 170	99.48 181	98.37 61	96.56 233	99.19 154

DPM-MVS		97.55 106	96.99 121	99.23 42	99.04 117	98.55 27	97.17 353	98.35 215	94.85 188	97.93 137	98.58 167	95.07 77	99.71 128	92.60 285	99.34 126	99.43 115

OMC-MVS		97.55 106	97.34 104	98.20 131	99.33 63	95.92 170	98.28 237	98.59 157	95.52 145	97.97 132	99.10 96	93.28 110	99.49 176	95.09 208	98.88 147	99.19 154

PAPM_NR		97.46 108	97.11 115	98.50 102	99.50 42	96.41 142	98.63 189	98.60 153	95.18 165	97.06 179	98.06 217	94.26 96	99.57 155	93.80 253	98.87 149	99.52 92

EPP-MVSNet		97.46 108	97.28 106	97.99 149	98.64 164	95.38 192	99.33 20	98.31 222	93.61 257	97.19 172	99.07 106	94.05 99	99.23 207	96.89 140	98.43 174	99.37 120

3Dnovator	94.51 5	97.46 108	96.93 124	99.07 58	97.78 248	97.64 75	99.35 15	99.06 40	97.02 75	93.75 300	99.16 87	89.25 203	99.92 37	97.22 126	99.75 48	99.64 77

CNLPA		97.45 111	97.03 119	98.73 81	99.05 116	97.44 88	98.07 266	98.53 173	95.32 158	96.80 193	98.53 172	93.32 108	99.72 123	94.31 236	99.31 128	99.02 181

lupinMVS		97.44 112	97.22 111	98.12 140	98.07 221	95.76 177	97.68 312	97.76 294	94.50 206	98.79 79	98.61 162	92.34 123	99.30 200	97.58 108	99.59 86	99.31 130

3Dnovator+	94.38 6	97.43 113	96.78 132	99.38 18	97.83 245	98.52 28	99.37 12	98.71 126	97.09 73	92.99 329	99.13 92	89.36 200	99.89 57	96.97 133	99.57 90	99.71 54

Vis-MVSNet		97.42 114	97.11 115	98.34 118	98.66 160	96.23 150	99.22 36	99.00 45	96.63 97	98.04 124	99.21 75	88.05 239	99.35 194	96.01 176	99.21 130	99.45 112
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 115	97.25 108	97.91 153	98.70 153	96.80 120	98.82 135	98.69 131	94.53 203	98.11 117	98.28 199	94.50 90	99.57 155	94.12 242	99.49 107	97.37 274

sss		97.39 116	96.98 123	98.61 90	98.60 168	96.61 129	98.22 243	98.93 56	93.97 228	98.01 130	98.48 177	91.98 138	99.85 73	96.45 160	98.15 184	99.39 118

test_cas_vis1_n_1920		97.38 117	97.36 103	97.45 189	98.95 130	93.25 291	99.00 83	98.53 173	97.70 29	99.77 13	99.35 53	84.71 304	99.85 73	98.57 42	99.66 69	99.26 141

PVSNet_Blended		97.38 117	97.12 114	98.14 134	99.25 85	95.35 195	97.28 343	99.26 15	93.13 278	97.94 135	98.21 207	92.74 116	99.81 91	96.88 142	99.40 120	99.27 138

WTY-MVS		97.37 119	96.92 125	98.72 82	98.86 139	96.89 118	98.31 232	98.71 126	95.26 161	97.67 154	98.56 171	92.21 130	99.78 111	95.89 178	96.85 223	99.48 104

jason		97.32 120	97.08 117	98.06 145	97.45 280	95.59 180	97.87 294	97.91 288	94.79 190	98.55 97	98.83 139	91.12 163	99.23 207	97.58 108	99.60 84	99.34 124
jason: jason.
MVS_Test		97.28 121	97.00 120	98.13 137	98.33 194	95.97 163	98.74 159	98.07 272	94.27 213	98.44 105	98.07 216	92.48 119	99.26 203	96.43 161	98.19 183	99.16 160

EPNet		97.28 121	96.87 127	98.51 101	94.98 388	96.14 155	98.90 106	97.02 360	98.28 15	95.99 225	99.11 94	91.36 155	99.89 57	96.98 132	99.19 132	99.50 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsmamba		97.25 123	96.99 121	98.02 147	98.34 191	95.54 185	99.18 48	97.47 321	95.04 174	98.15 114	98.57 170	89.46 196	99.31 199	97.68 102	99.01 140	99.22 147

test_yl		97.22 124	96.78 132	98.54 97	98.73 148	96.60 130	98.45 215	98.31 222	94.70 191	98.02 127	98.42 182	90.80 170	99.70 129	96.81 149	96.79 225	99.34 124

DCV-MVSNet		97.22 124	96.78 132	98.54 97	98.73 148	96.60 130	98.45 215	98.31 222	94.70 191	98.02 127	98.42 182	90.80 170	99.70 129	96.81 149	96.79 225	99.34 124

IS-MVSNet		97.22 124	96.88 126	98.25 126	98.85 141	96.36 145	99.19 44	97.97 282	95.39 152	97.23 170	98.99 116	91.11 164	98.93 254	94.60 224	98.59 163	99.47 106

PLC	95.07 4	97.20 127	96.78 132	98.44 110	99.29 77	96.31 149	98.14 256	98.76 114	92.41 306	96.39 213	98.31 197	94.92 82	99.78 111	94.06 245	98.77 155	99.23 145
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 128	97.18 113	97.20 202	98.81 144	93.27 288	95.78 398	99.15 34	95.25 162	96.79 194	98.11 214	92.29 125	99.07 232	98.56 44	99.85 6	99.25 143

LS3D		97.16 129	96.66 141	98.68 85	98.53 173	97.19 104	98.93 101	98.90 63	92.83 291	95.99 225	99.37 47	92.12 133	99.87 68	93.67 257	99.57 90	98.97 186

AdaColmap		97.15 130	96.70 137	98.48 105	99.16 104	96.69 126	98.01 273	98.89 65	94.44 209	96.83 189	98.68 157	90.69 173	99.76 117	94.36 232	99.29 129	98.98 185

mamv4		97.13 131	98.11 66	94.17 363	98.97 128	83.70 406	98.66 182	98.71 126	94.63 197	97.83 141	98.90 130	96.25 29	99.55 165	99.27 22	99.76 42	99.27 138

Effi-MVS+		97.12 132	96.69 138	98.39 116	98.19 210	96.72 125	97.37 334	98.43 200	93.71 246	97.65 158	98.02 220	92.20 131	99.25 204	96.87 145	97.79 196	99.19 154

CHOSEN 1792x2688		97.12 132	96.80 129	98.08 143	99.30 72	94.56 239	98.05 268	99.71 1	93.57 258	97.09 175	98.91 129	88.17 233	99.89 57	96.87 145	99.56 96	99.81 19

F-COLMAP		97.09 134	96.80 129	97.97 150	99.45 55	94.95 218	98.55 203	98.62 152	93.02 283	96.17 220	98.58 167	94.01 100	99.81 91	93.95 247	98.90 145	99.14 163

RRT-MVS		97.03 135	96.78 132	97.77 166	97.90 241	94.34 248	99.12 58	98.35 215	95.87 128	98.06 121	98.70 155	86.45 270	99.63 145	98.04 77	98.54 166	99.35 122

TAMVS		97.02 136	96.79 131	97.70 173	98.06 224	95.31 198	98.52 205	98.31 222	93.95 229	97.05 180	98.61 162	93.49 106	98.52 297	95.33 199	97.81 195	99.29 135

CDS-MVSNet		96.99 137	96.69 138	97.90 154	98.05 226	95.98 158	98.20 246	98.33 219	93.67 253	96.95 182	98.49 176	93.54 105	98.42 308	95.24 205	97.74 199	99.31 130
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 138	96.55 144	98.21 129	98.17 215	96.07 157	97.98 277	98.21 239	97.24 61	97.13 174	98.93 126	86.88 262	99.91 46	95.00 211	99.37 124	98.66 219

114514_t		96.93 139	96.27 154	98.92 70	99.50 42	97.63 76	98.85 127	98.90 63	84.80 405	97.77 143	99.11 94	92.84 114	99.66 138	94.85 214	99.77 36	99.47 106

MAR-MVS		96.91 140	96.40 150	98.45 108	98.69 156	96.90 116	98.66 182	98.68 134	92.40 307	97.07 178	97.96 227	91.54 152	99.75 119	93.68 255	98.92 144	98.69 213
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
HyFIR lowres test		96.90 141	96.49 147	98.14 134	99.33 63	95.56 182	97.38 332	99.65 2	92.34 308	97.61 161	98.20 208	89.29 202	99.10 229	96.97 133	97.60 204	99.77 31

Vis-MVSNet (Re-imp)		96.87 142	96.55 144	97.83 158	98.73 148	95.46 188	99.20 42	98.30 228	94.96 180	96.60 201	98.87 134	90.05 183	98.59 292	93.67 257	98.60 162	99.46 110

SDMVSNet		96.85 143	96.42 148	98.14 134	99.30 72	96.38 143	99.21 39	99.23 23	95.92 124	95.96 227	98.76 151	85.88 280	99.44 186	97.93 81	95.59 262	98.60 224

PAPR		96.84 144	96.24 156	98.65 88	98.72 152	96.92 115	97.36 336	98.57 164	93.33 267	96.67 196	97.57 267	94.30 94	99.56 158	91.05 327	98.59 163	99.47 106

HY-MVS	93.96 8	96.82 145	96.23 157	98.57 92	98.46 178	97.00 111	98.14 256	98.21 239	93.95 229	96.72 195	97.99 224	91.58 148	99.76 117	94.51 228	96.54 234	98.95 189

UGNet		96.78 146	96.30 153	98.19 133	98.24 202	95.89 173	98.88 116	98.93 56	97.39 49	96.81 192	97.84 239	82.60 331	99.90 54	96.53 157	99.49 107	98.79 201
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
PVSNet_BlendedMVS		96.73 147	96.60 142	97.12 211	99.25 85	95.35 195	98.26 240	99.26 15	94.28 212	97.94 135	97.46 273	92.74 116	99.81 91	96.88 142	93.32 298	96.20 365

test_vis1_n_1920		96.71 148	96.84 128	96.31 281	99.11 111	89.74 357	99.05 69	98.58 162	98.08 18	99.87 2	99.37 47	78.48 363	99.93 30	99.29 21	99.69 63	99.27 138

mvs_anonymous		96.70 149	96.53 146	97.18 205	98.19 210	93.78 264	98.31 232	98.19 243	94.01 225	94.47 259	98.27 202	92.08 136	98.46 303	97.39 121	97.91 191	99.31 130

1112_ss		96.63 150	96.00 164	98.50 102	98.56 169	96.37 144	98.18 254	98.10 265	92.92 287	94.84 247	98.43 180	92.14 132	99.58 154	94.35 233	96.51 235	99.56 91

PMMVS		96.60 151	96.33 152	97.41 193	97.90 241	93.93 260	97.35 337	98.41 202	92.84 290	97.76 144	97.45 275	91.10 165	99.20 211	96.26 166	97.91 191	99.11 168

DP-MVS		96.59 152	95.93 167	98.57 92	99.34 61	96.19 153	98.70 172	98.39 206	89.45 377	94.52 257	99.35 53	91.85 142	99.85 73	92.89 281	98.88 147	99.68 66

PatchMatch-RL		96.59 152	96.03 163	98.27 122	99.31 68	96.51 136	97.91 286	99.06 40	93.72 245	96.92 186	98.06 217	88.50 228	99.65 139	91.77 310	99.00 142	98.66 219

GeoE		96.58 154	96.07 160	98.10 142	98.35 186	95.89 173	99.34 16	98.12 259	93.12 279	96.09 221	98.87 134	89.71 190	98.97 244	92.95 277	98.08 187	99.43 115

XVG-OURS		96.55 155	96.41 149	96.99 218	98.75 147	93.76 265	97.50 326	98.52 176	95.67 139	96.83 189	99.30 61	88.95 216	99.53 168	95.88 179	96.26 249	97.69 263

FIs		96.51 156	96.12 159	97.67 177	97.13 304	97.54 81	99.36 13	99.22 26	95.89 126	94.03 286	98.35 190	91.98 138	98.44 306	96.40 162	92.76 306	97.01 282

XVG-OURS-SEG-HR		96.51 156	96.34 151	97.02 217	98.77 146	93.76 265	97.79 305	98.50 184	95.45 148	96.94 183	99.09 103	87.87 244	99.55 165	96.76 153	95.83 261	97.74 260

PS-MVSNAJss		96.43 158	96.26 155	96.92 227	95.84 368	95.08 209	99.16 50	98.50 184	95.87 128	93.84 295	98.34 194	94.51 87	98.61 289	96.88 142	93.45 295	97.06 280

test_fmvs1		96.42 159	96.67 140	95.66 310	98.82 143	88.53 384	98.80 144	98.20 241	96.39 107	99.64 24	99.20 77	80.35 351	99.67 136	99.04 27	99.57 90	98.78 204

FC-MVSNet-test		96.42 159	96.05 161	97.53 187	96.95 313	97.27 96	99.36 13	99.23 23	95.83 130	93.93 289	98.37 188	92.00 137	98.32 326	96.02 175	92.72 307	97.00 283

ab-mvs		96.42 159	95.71 177	98.55 95	98.63 165	96.75 123	97.88 293	98.74 118	93.84 235	96.54 206	98.18 210	85.34 290	99.75 119	95.93 177	96.35 239	99.15 161

FA-MVS(test-final)		96.41 162	95.94 166	97.82 160	98.21 206	95.20 203	97.80 303	97.58 305	93.21 273	97.36 167	97.70 251	89.47 195	99.56 158	94.12 242	97.99 188	98.71 211

PVSNet	91.96 18	96.35 163	96.15 158	96.96 222	99.17 100	92.05 313	96.08 391	98.68 134	93.69 249	97.75 146	97.80 245	88.86 217	99.69 134	94.26 238	99.01 140	99.15 161

Test_1112_low_res		96.34 164	95.66 182	98.36 117	98.56 169	95.94 166	97.71 310	98.07 272	92.10 317	94.79 251	97.29 288	91.75 144	99.56 158	94.17 240	96.50 236	99.58 89

Effi-MVS+-dtu		96.29 165	96.56 143	95.51 315	97.89 243	90.22 350	98.80 144	98.10 265	96.57 100	96.45 211	96.66 344	90.81 169	98.91 257	95.72 186	97.99 188	97.40 271

QAPM		96.29 165	95.40 187	98.96 67	97.85 244	97.60 78	99.23 32	98.93 56	89.76 371	93.11 326	99.02 110	89.11 208	99.93 30	91.99 304	99.62 81	99.34 124

Fast-Effi-MVS+		96.28 167	95.70 179	98.03 146	98.29 200	95.97 163	98.58 195	98.25 236	91.74 325	95.29 240	97.23 293	91.03 167	99.15 217	92.90 279	97.96 190	98.97 186

nrg030		96.28 167	95.72 174	97.96 152	96.90 318	98.15 58	99.39 10	98.31 222	95.47 147	94.42 265	98.35 190	92.09 135	98.69 281	97.50 117	89.05 356	97.04 281

1314		96.25 169	95.73 173	97.79 162	97.13 304	95.55 184	98.19 249	98.59 157	93.47 262	92.03 354	97.82 243	91.33 157	99.49 176	94.62 223	98.44 172	98.32 243

sd_testset		96.17 170	95.76 172	97.42 192	99.30 72	94.34 248	98.82 135	99.08 38	95.92 124	95.96 227	98.76 151	82.83 330	99.32 198	95.56 192	95.59 262	98.60 224

h-mvs33		96.17 170	95.62 183	97.81 161	99.03 118	94.45 241	98.64 186	98.75 116	97.48 43	98.67 87	98.72 154	89.76 187	99.86 72	97.95 79	81.59 402	99.11 168

HQP_MVS		96.14 172	95.90 168	96.85 230	97.42 282	94.60 237	98.80 144	98.56 167	97.28 56	95.34 236	98.28 199	87.09 257	99.03 237	96.07 170	94.27 270	96.92 289

tttt0517		96.07 173	95.51 185	97.78 163	98.41 181	94.84 222	99.28 24	94.33 410	94.26 214	97.64 159	98.64 161	84.05 319	99.47 183	95.34 198	97.60 204	99.03 180

MVSTER		96.06 174	95.72 174	97.08 214	98.23 204	95.93 169	98.73 163	98.27 231	94.86 186	95.07 242	98.09 215	88.21 232	98.54 295	96.59 155	93.46 293	96.79 308

thisisatest0530		96.01 175	95.36 192	97.97 150	98.38 183	95.52 186	98.88 116	94.19 412	94.04 220	97.64 159	98.31 197	83.82 326	99.46 184	95.29 202	97.70 201	98.93 191

test_djsdf		96.00 176	95.69 180	96.93 224	95.72 370	95.49 187	99.47 7	98.40 204	94.98 178	94.58 255	97.86 236	89.16 206	98.41 315	96.91 136	94.12 278	96.88 298

EI-MVSNet		95.96 177	95.83 170	96.36 277	97.93 239	93.70 271	98.12 259	98.27 231	93.70 248	95.07 242	99.02 110	92.23 129	98.54 295	94.68 219	93.46 293	96.84 304

ECVR-MVS		95.95 178	95.71 177	96.65 242	99.02 119	90.86 335	99.03 76	91.80 423	96.96 78	98.10 118	99.26 66	81.31 337	99.51 172	96.90 139	99.04 137	99.59 85

BH-untuned		95.95 178	95.72 174	96.65 242	98.55 171	92.26 307	98.23 242	97.79 293	93.73 243	94.62 254	98.01 222	88.97 215	99.00 243	93.04 274	98.51 168	98.68 215

test1111		95.94 180	95.78 171	96.41 274	98.99 125	90.12 351	99.04 73	92.45 422	96.99 77	98.03 125	99.27 65	81.40 336	99.48 181	96.87 145	99.04 137	99.63 79

MSDG		95.93 181	95.30 199	97.83 158	98.90 133	95.36 193	96.83 378	98.37 212	91.32 340	94.43 264	98.73 153	90.27 181	99.60 151	90.05 341	98.82 153	98.52 231

BH-RMVSNet		95.92 182	95.32 197	97.69 174	98.32 197	94.64 231	98.19 249	97.45 326	94.56 201	96.03 223	98.61 162	85.02 295	99.12 223	90.68 332	99.06 136	99.30 133

test_fmvs1_n		95.90 183	95.99 165	95.63 311	98.67 159	88.32 388	99.26 27	98.22 238	96.40 106	99.67 21	99.26 66	73.91 400	99.70 129	99.02 28	99.50 105	98.87 195

Fast-Effi-MVS+-dtu		95.87 184	95.85 169	95.91 298	97.74 253	91.74 319	98.69 174	98.15 255	95.56 143	94.92 245	97.68 256	88.98 214	98.79 275	93.19 269	97.78 197	97.20 278

LFMVS		95.86 185	94.98 214	98.47 106	98.87 138	96.32 147	98.84 131	96.02 389	93.40 265	98.62 93	99.20 77	74.99 394	99.63 145	97.72 95	97.20 211	99.46 110

baseline1		95.84 186	95.12 207	98.01 148	98.49 177	95.98 158	98.73 163	97.03 358	95.37 155	96.22 216	98.19 209	89.96 185	99.16 214	94.60 224	87.48 372	98.90 194

OpenMVS	93.04 13	95.83 187	95.00 212	98.32 119	97.18 301	97.32 92	99.21 39	98.97 48	89.96 367	91.14 363	99.05 108	86.64 265	99.92 37	93.38 263	99.47 110	97.73 261

VDD-MVS		95.82 188	95.23 201	97.61 183	98.84 142	93.98 259	98.68 176	97.40 330	95.02 176	97.95 133	99.34 57	74.37 399	99.78 111	98.64 39	96.80 224	99.08 174

UniMVSNet (Re)		95.78 189	95.19 203	97.58 184	96.99 311	97.47 85	98.79 151	99.18 30	95.60 141	93.92 290	97.04 315	91.68 145	98.48 299	95.80 183	87.66 371	96.79 308

VPA-MVSNet		95.75 190	95.11 208	97.69 174	97.24 293	97.27 96	98.94 98	99.23 23	95.13 167	95.51 234	97.32 286	85.73 282	98.91 257	97.33 124	89.55 347	96.89 297

HQP-MVS		95.72 191	95.40 187	96.69 240	97.20 297	94.25 253	98.05 268	98.46 192	96.43 103	94.45 260	97.73 248	86.75 263	98.96 248	95.30 200	94.18 274	96.86 303

hse-mvs2		95.71 192	95.30 199	96.93 224	98.50 174	93.53 276	98.36 224	98.10 265	97.48 43	98.67 87	97.99 224	89.76 187	99.02 240	97.95 79	80.91 407	98.22 246

UniMVSNet_NR-MVSNet		95.71 192	95.15 204	97.40 195	96.84 321	96.97 112	98.74 159	99.24 18	95.16 166	93.88 292	97.72 250	91.68 145	98.31 328	95.81 181	87.25 377	96.92 289

PatchmatchNet		95.71 192	95.52 184	96.29 283	97.58 266	90.72 339	96.84 377	97.52 316	94.06 219	97.08 176	96.96 325	89.24 204	98.90 260	92.03 303	98.37 176	99.26 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 195	95.33 196	96.76 235	96.16 356	94.63 232	98.43 220	98.39 206	96.64 96	95.02 244	98.78 144	85.15 294	99.05 233	95.21 207	94.20 273	96.60 331
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 195	95.38 191	96.61 250	97.61 263	93.84 263	98.91 105	98.44 196	95.25 162	94.28 272	98.47 178	86.04 279	99.12 223	95.50 195	93.95 283	96.87 301
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 197	95.69 180	95.44 319	97.54 271	88.54 383	96.97 363	97.56 308	93.50 260	97.52 165	96.93 329	89.49 193	99.16 214	95.25 204	96.42 238	98.64 221

FE-MVS		95.62 198	94.90 218	97.78 163	98.37 185	94.92 219	97.17 353	97.38 332	90.95 351	97.73 149	97.70 251	85.32 292	99.63 145	91.18 319	98.33 179	98.79 201

LPG-MVS_test		95.62 198	95.34 193	96.47 268	97.46 277	93.54 274	98.99 86	98.54 171	94.67 195	94.36 268	98.77 146	85.39 287	99.11 225	95.71 187	94.15 276	96.76 311

CLD-MVS		95.62 198	95.34 193	96.46 271	97.52 274	93.75 267	97.27 344	98.46 192	95.53 144	94.42 265	98.00 223	86.21 274	98.97 244	96.25 168	94.37 268	96.66 326
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 201	94.89 219	97.76 167	98.15 217	95.15 206	96.77 379	94.41 408	92.95 286	97.18 173	97.43 277	84.78 301	99.45 185	94.63 221	97.73 200	98.68 215

MonoMVSNet		95.51 202	95.45 186	95.68 308	95.54 375	90.87 334	98.92 103	97.37 333	95.79 132	95.53 233	97.38 282	89.58 192	97.68 371	96.40 162	92.59 308	98.49 233

thres600view7		95.49 203	94.77 222	97.67 177	98.98 126	95.02 211	98.85 127	96.90 367	95.38 153	96.63 198	96.90 331	84.29 311	99.59 152	88.65 363	96.33 240	98.40 237

test_vis1_n		95.47 204	95.13 205	96.49 265	97.77 249	90.41 347	99.27 26	98.11 262	96.58 98	99.66 22	99.18 83	67.00 413	99.62 149	99.21 23	99.40 120	99.44 113

SCA		95.46 205	95.13 205	96.46 271	97.67 258	91.29 327	97.33 339	97.60 304	94.68 194	96.92 186	97.10 300	83.97 321	98.89 261	92.59 287	98.32 181	99.20 150

IterMVS-LS		95.46 205	95.21 202	96.22 285	98.12 218	93.72 270	98.32 231	98.13 258	93.71 246	94.26 273	97.31 287	92.24 128	98.10 344	94.63 221	90.12 338	96.84 304
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 207	95.34 193	95.77 306	98.69 156	88.75 379	98.87 119	97.21 345	96.13 117	97.22 171	97.68 256	77.95 371	99.65 139	97.58 108	96.77 227	98.91 193

jajsoiax		95.45 207	95.03 211	96.73 236	95.42 383	94.63 232	99.14 54	98.52 176	95.74 134	93.22 319	98.36 189	83.87 324	98.65 286	96.95 135	94.04 279	96.91 294

CVMVSNet		95.43 209	96.04 162	93.57 369	97.93 239	83.62 407	98.12 259	98.59 157	95.68 138	96.56 202	99.02 110	87.51 250	97.51 379	93.56 261	97.44 207	99.60 83

anonymousdsp		95.42 210	94.91 217	96.94 223	95.10 387	95.90 172	99.14 54	98.41 202	93.75 240	93.16 322	97.46 273	87.50 252	98.41 315	95.63 191	94.03 280	96.50 350

DU-MVS		95.42 210	94.76 223	97.40 195	96.53 338	96.97 112	98.66 182	98.99 47	95.43 149	93.88 292	97.69 253	88.57 223	98.31 328	95.81 181	87.25 377	96.92 289

mvs_tets		95.41 212	95.00 212	96.65 242	95.58 374	94.42 243	99.00 83	98.55 169	95.73 136	93.21 320	98.38 187	83.45 328	98.63 287	97.09 129	94.00 281	96.91 294

thres100view900		95.38 213	94.70 227	97.41 193	98.98 126	94.92 219	98.87 119	96.90 367	95.38 153	96.61 200	96.88 332	84.29 311	99.56 158	88.11 366	96.29 244	97.76 258

thres400		95.38 213	94.62 231	97.65 181	98.94 131	94.98 215	98.68 176	96.93 365	95.33 156	96.55 204	96.53 350	84.23 315	99.56 158	88.11 366	96.29 244	98.40 237

BH-w/o		95.38 213	95.08 209	96.26 284	98.34 191	91.79 316	97.70 311	97.43 328	92.87 289	94.24 275	97.22 294	88.66 221	98.84 267	91.55 315	97.70 201	98.16 249

VDDNet		95.36 216	94.53 236	97.86 156	98.10 220	95.13 207	98.85 127	97.75 295	90.46 358	98.36 108	99.39 41	73.27 402	99.64 142	97.98 78	96.58 232	98.81 200

TAPA-MVS	93.98 7	95.35 217	94.56 235	97.74 169	99.13 108	94.83 224	98.33 227	98.64 147	86.62 393	96.29 215	98.61 162	94.00 101	99.29 201	80.00 408	99.41 117	99.09 170
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 218	94.98 214	96.43 273	97.67 258	93.48 278	98.73 163	98.44 196	94.94 184	92.53 342	98.53 172	84.50 310	99.14 219	95.48 196	94.00 281	96.66 326
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 219	94.87 220	96.71 237	99.29 77	93.24 292	98.58 195	98.11 262	89.92 368	93.57 304	99.10 96	86.37 272	99.79 108	90.78 330	98.10 186	97.09 279
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 220	94.72 226	97.13 209	98.05 226	93.26 289	97.87 294	97.20 346	94.96 180	96.18 219	95.66 382	80.97 343	99.35 194	94.47 230	97.08 214	98.78 204

tfpn200view9		95.32 220	94.62 231	97.43 191	98.94 131	94.98 215	98.68 176	96.93 365	95.33 156	96.55 204	96.53 350	84.23 315	99.56 158	88.11 366	96.29 244	97.76 258

Anonymous202405211		95.28 222	94.49 238	97.67 177	99.00 122	93.75 267	98.70 172	97.04 357	90.66 354	96.49 208	98.80 142	78.13 367	99.83 79	96.21 169	95.36 266	99.44 113

thres200		95.25 223	94.57 234	97.28 199	98.81 144	94.92 219	98.20 246	97.11 350	95.24 164	96.54 206	96.22 361	84.58 308	99.53 168	87.93 371	96.50 236	97.39 272

AllTest		95.24 224	94.65 230	96.99 218	99.25 85	93.21 293	98.59 193	98.18 246	91.36 336	93.52 306	98.77 146	84.67 305	99.72 123	89.70 348	97.87 193	98.02 253

LCM-MVSNet-Re		95.22 225	95.32 197	94.91 336	98.18 212	87.85 394	98.75 155	95.66 396	95.11 169	88.96 382	96.85 335	90.26 182	97.65 372	95.65 190	98.44 172	99.22 147

EPNet_dtu		95.21 226	94.95 216	95.99 293	96.17 354	90.45 345	98.16 255	97.27 341	96.77 86	93.14 325	98.33 195	90.34 178	98.42 308	85.57 384	98.81 154	99.09 170
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 227	94.45 243	97.46 188	96.75 328	96.56 134	98.86 123	98.65 146	93.30 270	93.27 318	98.27 202	84.85 299	98.87 264	94.82 216	91.26 324	96.96 285

D2MVS		95.18 228	95.08 209	95.48 316	97.10 306	92.07 312	98.30 234	99.13 36	94.02 222	92.90 330	96.73 341	89.48 194	98.73 279	94.48 229	93.60 292	95.65 378

WR-MVS		95.15 229	94.46 241	97.22 201	96.67 333	96.45 138	98.21 244	98.81 96	94.15 216	93.16 322	97.69 253	87.51 250	98.30 330	95.29 202	88.62 362	96.90 296

TranMVSNet+NR-MVSNet		95.14 230	94.48 239	97.11 212	96.45 344	96.36 145	99.03 76	99.03 43	95.04 174	93.58 303	97.93 229	88.27 231	98.03 350	94.13 241	86.90 382	96.95 287

myMVS_eth3d28		95.12 231	94.62 231	96.64 246	98.17 215	92.17 308	98.02 272	97.32 335	95.41 151	96.22 216	96.05 367	78.01 369	99.13 220	95.22 206	97.16 212	98.60 224

baseline2		95.11 232	94.52 237	96.87 229	96.65 334	93.56 273	98.27 239	94.10 414	93.45 263	92.02 355	97.43 277	87.45 254	99.19 212	93.88 250	97.41 209	97.87 256

miper_enhance_ethall		95.10 233	94.75 224	96.12 289	97.53 273	93.73 269	96.61 385	98.08 270	92.20 316	93.89 291	96.65 346	92.44 120	98.30 330	94.21 239	91.16 325	96.34 359

Anonymous20240529		95.10 233	94.22 253	97.75 168	99.01 121	94.26 252	98.87 119	98.83 87	85.79 401	96.64 197	98.97 117	78.73 360	99.85 73	96.27 165	94.89 267	99.12 165

test-LLR		95.10 233	94.87 220	95.80 303	96.77 325	89.70 359	96.91 368	95.21 400	95.11 169	94.83 249	95.72 379	87.71 246	98.97 244	93.06 272	98.50 169	98.72 208

WR-MVS_H		95.05 236	94.46 241	96.81 233	96.86 320	95.82 175	99.24 30	99.24 18	93.87 234	92.53 342	96.84 336	90.37 177	98.24 336	93.24 267	87.93 368	96.38 358

miper_ehance_all_eth		95.01 237	94.69 228	95.97 295	97.70 256	93.31 287	97.02 361	98.07 272	92.23 313	93.51 308	96.96 325	91.85 142	98.15 340	93.68 255	91.16 325	96.44 356

testing11		95.00 238	94.28 250	97.16 207	97.96 236	93.36 286	98.09 264	97.06 356	94.94 184	95.33 239	96.15 363	76.89 384	99.40 189	95.77 185	96.30 243	98.72 208

ADS-MVSNet		95.00 238	94.45 243	96.63 247	98.00 230	91.91 315	96.04 392	97.74 296	90.15 364	96.47 209	96.64 347	87.89 242	98.96 248	90.08 339	97.06 215	99.02 181

VPNet		94.99 240	94.19 255	97.40 195	97.16 302	96.57 133	98.71 168	98.97 48	95.67 139	94.84 247	98.24 206	80.36 350	98.67 285	96.46 159	87.32 376	96.96 285

EPMVS		94.99 240	94.48 239	96.52 263	97.22 295	91.75 318	97.23 345	91.66 424	94.11 217	97.28 168	96.81 338	85.70 283	98.84 267	93.04 274	97.28 210	98.97 186

testing91		94.98 242	94.25 252	97.20 202	97.94 237	93.41 281	98.00 275	97.58 305	94.99 177	95.45 235	96.04 368	77.20 379	99.42 188	94.97 212	96.02 257	98.78 204

NR-MVSNet		94.98 242	94.16 258	97.44 190	96.53 338	97.22 103	98.74 159	98.95 52	94.96 180	89.25 381	97.69 253	89.32 201	98.18 338	94.59 226	87.40 374	96.92 289

FMVSNet3		94.97 244	94.26 251	97.11 212	98.18 212	96.62 127	98.56 202	98.26 235	93.67 253	94.09 282	97.10 300	84.25 313	98.01 351	92.08 299	92.14 311	96.70 320

CostFormer		94.95 245	94.73 225	95.60 313	97.28 291	89.06 372	97.53 323	96.89 369	89.66 373	96.82 191	96.72 342	86.05 277	98.95 253	95.53 194	96.13 255	98.79 201

PAPM		94.95 245	94.00 271	97.78 163	97.04 308	95.65 179	96.03 394	98.25 236	91.23 345	94.19 278	97.80 245	91.27 160	98.86 266	82.61 401	97.61 203	98.84 198

CP-MVSNet		94.94 247	94.30 249	96.83 231	96.72 330	95.56 182	99.11 60	98.95 52	93.89 232	92.42 347	97.90 232	87.19 256	98.12 343	94.32 235	88.21 365	96.82 307

TR-MVS		94.94 247	94.20 254	97.17 206	97.75 250	94.14 256	97.59 320	97.02 360	92.28 312	95.75 231	97.64 261	83.88 323	98.96 248	89.77 345	96.15 254	98.40 237

RPSCF		94.87 249	95.40 187	93.26 375	98.89 134	82.06 413	98.33 227	98.06 277	90.30 363	96.56 202	99.26 66	87.09 257	99.49 176	93.82 252	96.32 241	98.24 244

testing99		94.83 250	94.08 263	97.07 215	97.94 237	93.13 295	98.10 263	97.17 348	94.86 186	95.34 236	96.00 371	76.31 387	99.40 189	95.08 209	95.90 258	98.68 215

GA-MVS		94.81 251	94.03 267	97.14 208	97.15 303	93.86 262	96.76 380	97.58 305	94.00 226	94.76 253	97.04 315	80.91 344	98.48 299	91.79 309	96.25 250	99.09 170

c3_l		94.79 252	94.43 245	95.89 300	97.75 250	93.12 297	97.16 355	98.03 279	92.23 313	93.46 312	97.05 314	91.39 154	98.01 351	93.58 260	89.21 354	96.53 342

V42		94.78 253	94.14 260	96.70 239	96.33 349	95.22 202	98.97 89	98.09 269	92.32 310	94.31 271	97.06 311	88.39 229	98.55 294	92.90 279	88.87 360	96.34 359

reproduce_monomvs		94.77 254	94.67 229	95.08 331	98.40 182	89.48 365	98.80 144	98.64 147	97.57 37	93.21 320	97.65 258	80.57 349	98.83 270	97.72 95	89.47 350	96.93 288

CR-MVSNet		94.76 255	94.15 259	96.59 253	97.00 309	93.43 279	94.96 405	97.56 308	92.46 301	96.93 184	96.24 357	88.15 234	97.88 364	87.38 373	96.65 230	98.46 235

v2v482		94.69 256	94.03 267	96.65 242	96.17 354	94.79 227	98.67 180	98.08 270	92.72 293	94.00 287	97.16 297	87.69 249	98.45 304	92.91 278	88.87 360	96.72 316

pmmvs4		94.69 256	93.99 273	96.81 233	95.74 369	95.94 166	97.40 330	97.67 299	90.42 360	93.37 315	97.59 265	89.08 209	98.20 337	92.97 276	91.67 318	96.30 362

cl22		94.68 258	94.19 255	96.13 288	98.11 219	93.60 272	96.94 365	98.31 222	92.43 305	93.32 317	96.87 334	86.51 266	98.28 334	94.10 244	91.16 325	96.51 348

eth_miper_zixun_eth		94.68 258	94.41 246	95.47 317	97.64 261	91.71 320	96.73 382	98.07 272	92.71 294	93.64 301	97.21 295	90.54 175	98.17 339	93.38 263	89.76 342	96.54 340

PCF-MVS	93.45 11	94.68 258	93.43 309	98.42 114	98.62 166	96.77 122	95.48 402	98.20 241	84.63 406	93.34 316	98.32 196	88.55 226	99.81 91	84.80 393	98.96 143	98.68 215
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 261	93.54 304	98.08 143	96.88 319	96.56 134	98.19 249	98.50 184	78.05 417	92.69 337	98.02 220	91.07 166	99.63 145	90.09 338	98.36 178	98.04 252

PS-CasMVS		94.67 261	93.99 273	96.71 237	96.68 332	95.26 199	99.13 57	99.03 43	93.68 251	92.33 348	97.95 228	85.35 289	98.10 344	93.59 259	88.16 367	96.79 308

cascas		94.63 263	93.86 283	96.93 224	96.91 317	94.27 251	96.00 395	98.51 179	85.55 402	94.54 256	96.23 359	84.20 317	98.87 264	95.80 183	96.98 220	97.66 264

tpmvs		94.60 264	94.36 248	95.33 323	97.46 277	88.60 382	96.88 374	97.68 297	91.29 342	93.80 297	96.42 354	88.58 222	99.24 206	91.06 325	96.04 256	98.17 248

LTVRE_ROB	92.95 15	94.60 264	93.90 279	96.68 241	97.41 285	94.42 243	98.52 205	98.59 157	91.69 328	91.21 362	98.35 190	84.87 298	99.04 236	91.06 325	93.44 296	96.60 331
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
v1144		94.59 266	93.92 276	96.60 252	96.21 351	94.78 228	98.59 193	98.14 257	91.86 324	94.21 277	97.02 318	87.97 240	98.41 315	91.72 311	89.57 345	96.61 330

ADS-MVSNet2		94.58 267	94.40 247	95.11 329	98.00 230	88.74 380	96.04 392	97.30 337	90.15 364	96.47 209	96.64 347	87.89 242	97.56 377	90.08 339	97.06 215	99.02 181

WBMVS		94.56 268	94.04 265	96.10 290	98.03 228	93.08 299	97.82 302	98.18 246	94.02 222	93.77 299	96.82 337	81.28 338	98.34 323	95.47 197	91.00 328	96.88 298

ACMH	92.88 16	94.55 269	93.95 275	96.34 279	97.63 262	93.26 289	98.81 143	98.49 189	93.43 264	89.74 376	98.53 172	81.91 333	99.08 231	93.69 254	93.30 299	96.70 320
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 270	93.85 284	96.63 247	97.98 234	93.06 300	98.77 154	97.84 291	93.67 253	93.80 297	98.04 219	76.88 385	98.96 248	94.79 218	92.86 304	97.86 257

XVG-ACMP-BASELINE		94.54 270	94.14 260	95.75 307	96.55 337	91.65 321	98.11 261	98.44 196	94.96 180	94.22 276	97.90 232	79.18 359	99.11 225	94.05 246	93.85 285	96.48 353

AUN-MVS		94.53 272	93.73 294	96.92 227	98.50 174	93.52 277	98.34 226	98.10 265	93.83 237	95.94 229	97.98 226	85.59 285	99.03 237	94.35 233	80.94 406	98.22 246

DIV-MVS_self_test		94.52 273	94.03 267	95.99 293	97.57 270	93.38 284	97.05 359	97.94 285	91.74 325	92.81 332	97.10 300	89.12 207	98.07 348	92.60 285	90.30 335	96.53 342

cl____		94.51 274	94.01 270	96.02 292	97.58 266	93.40 283	97.05 359	97.96 284	91.73 327	92.76 334	97.08 306	89.06 210	98.13 342	92.61 284	90.29 336	96.52 345

ETVMVS		94.50 275	93.44 308	97.68 176	98.18 212	95.35 195	98.19 249	97.11 350	93.73 243	96.40 212	95.39 385	74.53 396	98.84 267	91.10 321	96.31 242	98.84 198

GBi-Net		94.49 276	93.80 287	96.56 257	98.21 206	95.00 212	98.82 135	98.18 246	92.46 301	94.09 282	97.07 307	81.16 339	97.95 356	92.08 299	92.14 311	96.72 316

test1		94.49 276	93.80 287	96.56 257	98.21 206	95.00 212	98.82 135	98.18 246	92.46 301	94.09 282	97.07 307	81.16 339	97.95 356	92.08 299	92.14 311	96.72 316

dmvs_re		94.48 278	94.18 257	95.37 321	97.68 257	90.11 352	98.54 204	97.08 352	94.56 201	94.42 265	97.24 292	84.25 313	97.76 369	91.02 328	92.83 305	98.24 244

v8		94.47 279	93.77 290	96.57 256	96.36 347	94.83 224	99.05 69	98.19 243	91.92 321	93.16 322	96.97 323	88.82 220	98.48 299	91.69 312	87.79 369	96.39 357

FMVSNet2		94.47 279	93.61 300	97.04 216	98.21 206	96.43 140	98.79 151	98.27 231	92.46 301	93.50 309	97.09 304	81.16 339	98.00 353	91.09 322	91.93 314	96.70 320

test2506		94.44 281	93.91 278	96.04 291	99.02 119	88.99 375	99.06 67	79.47 436	96.96 78	98.36 108	99.26 66	77.21 378	99.52 171	96.78 152	99.04 137	99.59 85

Patchmatch-test		94.42 282	93.68 298	96.63 247	97.60 264	91.76 317	94.83 409	97.49 320	89.45 377	94.14 280	97.10 300	88.99 211	98.83 270	85.37 387	98.13 185	99.29 135

PEN-MVS		94.42 282	93.73 294	96.49 265	96.28 350	94.84 222	99.17 49	99.00 45	93.51 259	92.23 350	97.83 242	86.10 276	97.90 360	92.55 290	86.92 381	96.74 313

v144192		94.39 284	93.70 296	96.48 267	96.06 359	94.35 247	98.58 195	98.16 254	91.45 333	94.33 270	97.02 318	87.50 252	98.45 304	91.08 324	89.11 355	96.63 328

Baseline_NR-MVSNet		94.35 285	93.81 286	95.96 296	96.20 352	94.05 258	98.61 192	96.67 379	91.44 334	93.85 294	97.60 264	88.57 223	98.14 341	94.39 231	86.93 380	95.68 377

miper_lstm_enhance		94.33 286	94.07 264	95.11 329	97.75 250	90.97 331	97.22 346	98.03 279	91.67 329	92.76 334	96.97 323	90.03 184	97.78 368	92.51 292	89.64 344	96.56 337

v1192		94.32 287	93.58 301	96.53 262	96.10 357	94.45 241	98.50 211	98.17 252	91.54 331	94.19 278	97.06 311	86.95 261	98.43 307	90.14 337	89.57 345	96.70 320

UWE-MVS		94.30 288	93.89 281	95.53 314	97.83 245	88.95 376	97.52 325	93.25 416	94.44 209	96.63 198	97.07 307	78.70 361	99.28 202	91.99 304	97.56 206	98.36 240

ACMH+	92.99 14	94.30 288	93.77 290	95.88 301	97.81 247	92.04 314	98.71 168	98.37 212	93.99 227	90.60 369	98.47 178	80.86 346	99.05 233	92.75 283	92.40 310	96.55 339

v148		94.29 290	93.76 292	95.91 298	96.10 357	92.93 301	98.58 195	97.97 282	92.59 299	93.47 311	96.95 327	88.53 227	98.32 326	92.56 289	87.06 379	96.49 351

v10		94.29 290	93.55 303	96.51 264	96.39 346	94.80 226	98.99 86	98.19 243	91.35 338	93.02 328	96.99 321	88.09 236	98.41 315	90.50 334	88.41 364	96.33 361

MVP-Stereo		94.28 292	93.92 276	95.35 322	94.95 389	92.60 304	97.97 278	97.65 300	91.61 330	90.68 368	97.09 304	86.32 273	98.42 308	89.70 348	99.34 126	95.02 391
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 293	93.33 311	96.97 221	97.19 300	93.38 284	98.74 159	98.57 164	91.21 347	93.81 296	98.58 167	72.85 403	98.77 277	95.05 210	93.93 284	98.77 207

OurMVSNet-221017-0		94.21 294	94.00 271	94.85 340	95.60 373	89.22 370	98.89 110	97.43 328	95.29 159	92.18 351	98.52 175	82.86 329	98.59 292	93.46 262	91.76 316	96.74 313

v1921920		94.20 295	93.47 307	96.40 276	95.98 362	94.08 257	98.52 205	98.15 255	91.33 339	94.25 274	97.20 296	86.41 271	98.42 308	90.04 342	89.39 352	96.69 325

WB-MVSnew		94.19 296	94.04 265	94.66 347	96.82 323	92.14 309	97.86 296	95.96 392	93.50 260	95.64 232	96.77 340	88.06 238	97.99 354	84.87 390	96.86 221	93.85 408

v7n		94.19 296	93.43 309	96.47 268	95.90 365	94.38 246	99.26 27	98.34 218	91.99 319	92.76 334	97.13 299	88.31 230	98.52 297	89.48 353	87.70 370	96.52 345

tpm2		94.19 296	93.76 292	95.46 318	97.23 294	89.04 373	97.31 341	96.85 373	87.08 392	96.21 218	96.79 339	83.75 327	98.74 278	92.43 295	96.23 252	98.59 227

TESTMET0.1,1		94.18 299	93.69 297	95.63 311	96.92 315	89.12 371	96.91 368	94.78 405	93.17 275	94.88 246	96.45 353	78.52 362	98.92 255	93.09 271	98.50 169	98.85 196

dp		94.15 300	93.90 279	94.90 337	97.31 290	86.82 399	96.97 363	97.19 347	91.22 346	96.02 224	96.61 349	85.51 286	99.02 240	90.00 343	94.30 269	98.85 196

ET-MVSNet_ETH3D		94.13 301	92.98 319	97.58 184	98.22 205	96.20 151	97.31 341	95.37 399	94.53 203	79.56 417	97.63 263	86.51 266	97.53 378	96.91 136	90.74 330	99.02 181

tpm		94.13 301	93.80 287	95.12 328	96.50 340	87.91 393	97.44 327	95.89 395	92.62 297	96.37 214	96.30 356	84.13 318	98.30 330	93.24 267	91.66 319	99.14 163

testing222		94.12 303	93.03 318	97.37 198	98.02 229	94.66 229	97.94 282	96.65 381	94.63 197	95.78 230	95.76 374	71.49 404	98.92 255	91.17 320	95.88 259	98.52 231

IterMVS-SCA-FT		94.11 304	93.87 282	94.85 340	97.98 234	90.56 344	97.18 351	98.11 262	93.75 240	92.58 340	97.48 272	83.97 321	97.41 381	92.48 294	91.30 322	96.58 333

Anonymous20231211		94.10 305	93.26 314	96.61 250	99.11 111	94.28 250	99.01 81	98.88 68	86.43 395	92.81 332	97.57 267	81.66 335	98.68 284	94.83 215	89.02 358	96.88 298

IterMVS		94.09 306	93.85 284	94.80 343	97.99 232	90.35 348	97.18 351	98.12 259	93.68 251	92.46 346	97.34 283	84.05 319	97.41 381	92.51 292	91.33 321	96.62 329
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 307	93.51 305	95.80 303	96.77 325	89.70 359	96.91 368	95.21 400	92.89 288	94.83 249	95.72 379	77.69 373	98.97 244	93.06 272	98.50 169	98.72 208

test0.0.03 1		94.08 307	93.51 305	95.80 303	95.53 377	92.89 302	97.38 332	95.97 391	95.11 169	92.51 344	96.66 344	87.71 246	96.94 388	87.03 375	93.67 288	97.57 268

v1240		94.06 309	93.29 313	96.34 279	96.03 361	93.90 261	98.44 218	98.17 252	91.18 348	94.13 281	97.01 320	86.05 277	98.42 308	89.13 358	89.50 349	96.70 320

X-MVStestdata		94.06 309	92.30 335	99.34 26	99.70 22	98.35 44	99.29 22	98.88 68	97.40 47	98.46 100	43.50 431	95.90 45	99.89 57	97.85 87	99.74 52	99.78 25

DTE-MVSNet		93.98 311	93.26 314	96.14 287	96.06 359	94.39 245	99.20 42	98.86 81	93.06 281	91.78 356	97.81 244	85.87 281	97.58 376	90.53 333	86.17 386	96.46 355

pm-mvs1		93.94 312	93.06 317	96.59 253	96.49 341	95.16 204	98.95 95	98.03 279	92.32 310	91.08 364	97.84 239	84.54 309	98.41 315	92.16 297	86.13 389	96.19 366

MS-PatchMatch		93.84 313	93.63 299	94.46 357	96.18 353	89.45 366	97.76 306	98.27 231	92.23 313	92.13 352	97.49 271	79.50 356	98.69 281	89.75 346	99.38 122	95.25 383

tfpnnormal		93.66 314	92.70 325	96.55 261	96.94 314	95.94 166	98.97 89	99.19 29	91.04 349	91.38 361	97.34 283	84.94 297	98.61 289	85.45 386	89.02 358	95.11 387

EU-MVSNet		93.66 314	94.14 260	92.25 385	95.96 364	83.38 409	98.52 205	98.12 259	94.69 193	92.61 339	98.13 213	87.36 255	96.39 401	91.82 308	90.00 340	96.98 284

our_test_3		93.65 316	93.30 312	94.69 345	95.45 381	89.68 361	96.91 368	97.65 300	91.97 320	91.66 359	96.88 332	89.67 191	97.93 359	88.02 369	91.49 320	96.48 353

pmmvs5		93.65 316	92.97 320	95.68 308	95.49 378	92.37 305	98.20 246	97.28 340	89.66 373	92.58 340	97.26 289	82.14 332	98.09 346	93.18 270	90.95 329	96.58 333

SSC-MVS3.2		93.59 318	93.13 316	94.97 334	96.81 324	89.71 358	97.95 279	98.49 189	94.59 200	93.50 309	96.91 330	77.74 372	98.37 322	91.69 312	90.47 333	96.83 306

test_fmvs2		93.43 319	93.58 301	92.95 379	96.97 312	83.91 405	99.19 44	97.24 343	95.74 134	95.20 241	98.27 202	69.65 406	98.72 280	96.26 166	93.73 287	96.24 363

tpm cat1		93.36 320	92.80 322	95.07 332	97.58 266	87.97 392	96.76 380	97.86 290	82.17 413	93.53 305	96.04 368	86.13 275	99.13 220	89.24 356	95.87 260	98.10 251

JIA-IIPM		93.35 321	92.49 331	95.92 297	96.48 342	90.65 341	95.01 404	96.96 363	85.93 399	96.08 222	87.33 421	87.70 248	98.78 276	91.35 317	95.58 264	98.34 241

SixPastTwentyTwo		93.34 322	92.86 321	94.75 344	95.67 371	89.41 368	98.75 155	96.67 379	93.89 232	90.15 374	98.25 205	80.87 345	98.27 335	90.90 329	90.64 331	96.57 335

USDC		93.33 323	92.71 324	95.21 325	96.83 322	90.83 337	96.91 368	97.50 318	93.84 235	90.72 367	98.14 212	77.69 373	98.82 272	89.51 352	93.21 301	95.97 371

IB-MVS	91.98 17	93.27 324	91.97 339	97.19 204	97.47 276	93.41 281	97.09 358	95.99 390	93.32 268	92.47 345	95.73 377	78.06 368	99.53 168	94.59 226	82.98 397	98.62 222
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
MIMVSNet		93.26 325	92.21 336	96.41 274	97.73 254	93.13 295	95.65 399	97.03 358	91.27 344	94.04 285	96.06 366	75.33 392	97.19 384	86.56 377	96.23 252	98.92 192

ppachtmachnet_test		93.22 326	92.63 326	94.97 334	95.45 381	90.84 336	96.88 374	97.88 289	90.60 355	92.08 353	97.26 289	88.08 237	97.86 365	85.12 389	90.33 334	96.22 364

Patchmtry		93.22 326	92.35 334	95.84 302	96.77 325	93.09 298	94.66 412	97.56 308	87.37 391	92.90 330	96.24 357	88.15 234	97.90 360	87.37 374	90.10 339	96.53 342

testing3		93.19 328	92.48 332	95.30 324	98.07 221	92.27 306	98.64 186	97.17 348	93.94 231	93.98 288	97.04 315	67.97 410	96.01 405	88.40 364	97.14 213	97.63 265

FMVSNet1		93.19 328	92.07 337	96.56 257	97.54 271	95.00 212	98.82 135	98.18 246	90.38 361	92.27 349	97.07 307	73.68 401	97.95 356	89.36 355	91.30 322	96.72 316

LF4IMVS		93.14 330	92.79 323	94.20 361	95.88 366	88.67 381	97.66 314	97.07 354	93.81 238	91.71 357	97.65 258	77.96 370	98.81 273	91.47 316	91.92 315	95.12 386

mmtdpeth		93.12 331	92.61 327	94.63 349	97.60 264	89.68 361	99.21 39	97.32 335	94.02 222	97.72 150	94.42 396	77.01 383	99.44 186	99.05 26	77.18 418	94.78 396

testgi		93.06 332	92.45 333	94.88 339	96.43 345	89.90 353	98.75 155	97.54 314	95.60 141	91.63 360	97.91 231	74.46 398	97.02 386	86.10 380	93.67 288	97.72 262

PatchT		93.06 332	91.97 339	96.35 278	96.69 331	92.67 303	94.48 415	97.08 352	86.62 393	97.08 176	92.23 415	87.94 241	97.90 360	78.89 412	96.69 228	98.49 233

RPMNet		92.81 334	91.34 345	97.24 200	97.00 309	93.43 279	94.96 405	98.80 103	82.27 412	96.93 184	92.12 416	86.98 260	99.82 86	76.32 417	96.65 230	98.46 235

UWE-MVS-28		92.79 335	92.51 330	93.62 368	96.46 343	86.28 400	97.93 283	92.71 421	94.17 215	94.78 252	97.16 297	81.05 342	96.43 400	81.45 404	96.86 221	98.14 250

myMVS_eth3d		92.73 336	92.01 338	94.89 338	97.39 286	90.94 332	97.91 286	97.46 322	93.16 276	93.42 313	95.37 386	68.09 409	96.12 403	88.34 365	96.99 217	97.60 266

TransMVSNet (Re)		92.67 337	91.51 344	96.15 286	96.58 336	94.65 230	98.90 106	96.73 375	90.86 352	89.46 380	97.86 236	85.62 284	98.09 346	86.45 378	81.12 404	95.71 376

ttmdpeth		92.61 338	91.96 341	94.55 351	94.10 399	90.60 343	98.52 205	97.29 338	92.67 295	90.18 372	97.92 230	79.75 355	97.79 367	91.09 322	86.15 388	95.26 382

Syy-MVS		92.55 339	92.61 327	92.38 382	97.39 286	83.41 408	97.91 286	97.46 322	93.16 276	93.42 313	95.37 386	84.75 302	96.12 403	77.00 416	96.99 217	97.60 266

K. test v3		92.55 339	91.91 342	94.48 355	95.64 372	89.24 369	99.07 66	94.88 404	94.04 220	86.78 396	97.59 265	77.64 376	97.64 373	92.08 299	89.43 351	96.57 335

DSMNet-mixed		92.52 341	92.58 329	92.33 383	94.15 398	82.65 411	98.30 234	94.26 411	89.08 382	92.65 338	95.73 377	85.01 296	95.76 407	86.24 379	97.76 198	98.59 227

TinyColmap		92.31 342	91.53 343	94.65 348	96.92 315	89.75 356	96.92 366	96.68 378	90.45 359	89.62 377	97.85 238	76.06 390	98.81 273	86.74 376	92.51 309	95.41 380

gg-mvs-nofinetune		92.21 343	90.58 351	97.13 209	96.75 328	95.09 208	95.85 396	89.40 429	85.43 403	94.50 258	81.98 424	80.80 347	98.40 321	92.16 297	98.33 179	97.88 255

FMVSNet5		91.81 344	90.92 347	94.49 354	97.21 296	92.09 311	98.00 275	97.55 313	89.31 380	90.86 366	95.61 383	74.48 397	95.32 411	85.57 384	89.70 343	96.07 369

pmmvs6		91.77 345	90.63 350	95.17 327	94.69 395	91.24 328	98.67 180	97.92 287	86.14 397	89.62 377	97.56 269	75.79 391	98.34 323	90.75 331	84.56 391	95.94 372

Anonymous20231206		91.66 346	91.10 346	93.33 373	94.02 403	87.35 396	98.58 195	97.26 342	90.48 357	90.16 373	96.31 355	83.83 325	96.53 398	79.36 410	89.90 341	96.12 367

Patchmatch-RL test		91.49 347	90.85 348	93.41 371	91.37 414	84.40 403	92.81 419	95.93 394	91.87 323	87.25 392	94.87 392	88.99 211	96.53 398	92.54 291	82.00 399	99.30 133

test_0402		91.32 348	90.27 354	94.48 355	96.60 335	91.12 329	98.50 211	97.22 344	86.10 398	88.30 388	96.98 322	77.65 375	97.99 354	78.13 414	92.94 303	94.34 397

test_vis1_rt		91.29 349	90.65 349	93.19 377	97.45 280	86.25 401	98.57 201	90.90 427	93.30 270	86.94 395	93.59 405	62.07 419	99.11 225	97.48 118	95.58 264	94.22 400

PVSNet_0	88.72 19	91.28 350	90.03 357	95.00 333	97.99 232	87.29 397	94.84 408	98.50 184	92.06 318	89.86 375	95.19 388	79.81 354	99.39 192	92.27 296	69.79 424	98.33 242

mvs5depth		91.23 351	90.17 355	94.41 359	92.09 411	89.79 355	95.26 403	96.50 383	90.73 353	91.69 358	97.06 311	76.12 389	98.62 288	88.02 369	84.11 394	94.82 393

Anonymous20240521		91.18 352	90.44 352	93.42 370	93.70 404	88.47 385	98.94 98	97.56 308	88.46 386	89.56 379	95.08 391	77.15 381	96.97 387	83.92 396	89.55 347	94.82 393

EG-PatchMatch MVS		91.13 353	90.12 356	94.17 363	94.73 394	89.00 374	98.13 258	97.81 292	89.22 381	85.32 406	96.46 352	67.71 411	98.42 308	87.89 372	93.82 286	95.08 388

TDRefinement		91.06 354	89.68 359	95.21 325	85.35 429	91.49 324	98.51 210	97.07 354	91.47 332	88.83 386	97.84 239	77.31 377	99.09 230	92.79 282	77.98 416	95.04 390

UnsupCasMVSNet_eth		90.99 355	89.92 358	94.19 362	94.08 400	89.83 354	97.13 357	98.67 139	93.69 249	85.83 402	96.19 362	75.15 393	96.74 392	89.14 357	79.41 411	96.00 370

test20.03		90.89 356	90.38 353	92.43 381	93.48 405	88.14 391	98.33 227	97.56 308	93.40 265	87.96 389	96.71 343	80.69 348	94.13 416	79.15 411	86.17 386	95.01 392

MDA-MVSNet_test_wron		90.71 357	89.38 362	94.68 346	94.83 391	90.78 338	97.19 350	97.46 322	87.60 389	72.41 424	95.72 379	86.51 266	96.71 395	85.92 382	86.80 383	96.56 337

YYNet1		90.70 358	89.39 361	94.62 350	94.79 393	90.65 341	97.20 348	97.46 322	87.54 390	72.54 423	95.74 375	86.51 266	96.66 396	86.00 381	86.76 384	96.54 340

KD-MVS_self_test		90.38 359	89.38 362	93.40 372	92.85 408	88.94 377	97.95 279	97.94 285	90.35 362	90.25 371	93.96 402	79.82 353	95.94 406	84.62 395	76.69 419	95.33 381

pmmvs-eth3d		90.36 360	89.05 365	94.32 360	91.10 416	92.12 310	97.63 319	96.95 364	88.86 384	84.91 407	93.13 410	78.32 364	96.74 392	88.70 361	81.81 401	94.09 403

CL-MVSNet_self_test		90.11 361	89.14 364	93.02 378	91.86 413	88.23 390	96.51 388	98.07 272	90.49 356	90.49 370	94.41 397	84.75 302	95.34 410	80.79 406	74.95 421	95.50 379

new_pmnet		90.06 362	89.00 366	93.22 376	94.18 397	88.32 388	96.42 390	96.89 369	86.19 396	85.67 403	93.62 404	77.18 380	97.10 385	81.61 403	89.29 353	94.23 399

MDA-MVSNet-bldmvs		89.97 363	88.35 369	94.83 342	95.21 385	91.34 325	97.64 316	97.51 317	88.36 387	71.17 425	96.13 364	79.22 358	96.63 397	83.65 397	86.27 385	96.52 345

CMPMVS	66.06 21	89.70 364	89.67 360	89.78 390	93.19 406	76.56 416	97.00 362	98.35 215	80.97 414	81.57 412	97.75 247	74.75 395	98.61 289	89.85 344	93.63 290	94.17 401
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 365	88.28 370	93.82 366	92.81 409	91.08 330	98.01 273	97.45 326	87.95 388	87.90 390	95.87 373	67.63 412	94.56 415	78.73 413	88.18 366	95.83 374

KD-MVS_2432*1600		89.61 366	87.96 374	94.54 352	94.06 401	91.59 322	95.59 400	97.63 302	89.87 369	88.95 383	94.38 399	78.28 365	96.82 390	84.83 391	68.05 425	95.21 384

miper_refine_blended		89.61 366	87.96 374	94.54 352	94.06 401	91.59 322	95.59 400	97.63 302	89.87 369	88.95 383	94.38 399	78.28 365	96.82 390	84.83 391	68.05 425	95.21 384

MVStest1		89.53 368	87.99 373	94.14 365	94.39 396	90.42 346	98.25 241	96.84 374	82.81 409	81.18 414	97.33 285	77.09 382	96.94 388	85.27 388	78.79 412	95.06 389

MVS-HIRNet		89.46 369	88.40 368	92.64 380	97.58 266	82.15 412	94.16 418	93.05 420	75.73 420	90.90 365	82.52 423	79.42 357	98.33 325	83.53 398	98.68 156	97.43 269

OpenMVS_ROB	86.42 20	89.00 370	87.43 378	93.69 367	93.08 407	89.42 367	97.91 286	96.89 369	78.58 416	85.86 401	94.69 393	69.48 407	98.29 333	77.13 415	93.29 300	93.36 410

mvsany_test3		88.80 371	88.04 371	91.09 389	89.78 419	81.57 414	97.83 301	95.49 398	93.81 238	87.53 391	93.95 403	56.14 422	97.43 380	94.68 219	83.13 396	94.26 398

new-patchmatchnet		88.50 372	87.45 377	91.67 387	90.31 418	85.89 402	97.16 355	97.33 334	89.47 376	83.63 409	92.77 412	76.38 386	95.06 413	82.70 400	77.29 417	94.06 405

APD_test1		88.22 373	88.01 372	88.86 392	95.98 362	74.66 424	97.21 347	96.44 385	83.96 408	86.66 398	97.90 232	60.95 420	97.84 366	82.73 399	90.23 337	94.09 403

PM-MVS		87.77 374	86.55 380	91.40 388	91.03 417	83.36 410	96.92 366	95.18 402	91.28 343	86.48 400	93.42 406	53.27 423	96.74 392	89.43 354	81.97 400	94.11 402

dmvs_testset		87.64 375	88.93 367	83.79 401	95.25 384	63.36 433	97.20 348	91.17 425	93.07 280	85.64 404	95.98 372	85.30 293	91.52 423	69.42 422	87.33 375	96.49 351

test_fmvs3		87.17 376	87.06 379	87.50 394	91.21 415	75.66 419	99.05 69	96.61 382	92.79 292	88.85 385	92.78 411	43.72 426	93.49 417	93.95 247	84.56 391	93.34 411

UnsupCasMVSNet_bld		87.17 376	85.12 383	93.31 374	91.94 412	88.77 378	94.92 407	98.30 228	84.30 407	82.30 410	90.04 418	63.96 417	97.25 383	85.85 383	74.47 423	93.93 407

N_pmnet		87.12 378	87.77 376	85.17 398	95.46 380	61.92 434	97.37 334	70.66 439	85.83 400	88.73 387	96.04 368	85.33 291	97.76 369	80.02 407	90.48 332	95.84 373

pmmvs3		86.67 379	84.86 384	92.11 386	88.16 423	87.19 398	96.63 384	94.75 406	79.88 415	87.22 393	92.75 413	66.56 414	95.20 412	81.24 405	76.56 420	93.96 406

test_f		86.07 380	85.39 381	88.10 393	89.28 421	75.57 420	97.73 309	96.33 387	89.41 379	85.35 405	91.56 417	43.31 428	95.53 408	91.32 318	84.23 393	93.21 412

WB-MVS		84.86 381	85.33 382	83.46 402	89.48 420	69.56 428	98.19 249	96.42 386	89.55 375	81.79 411	94.67 394	84.80 300	90.12 424	52.44 428	80.64 408	90.69 415

SSC-MVS		84.27 382	84.71 385	82.96 406	89.19 422	68.83 429	98.08 265	96.30 388	89.04 383	81.37 413	94.47 395	84.60 307	89.89 425	49.80 430	79.52 410	90.15 416

dongtai		82.47 383	81.88 386	84.22 400	95.19 386	76.03 417	94.59 414	74.14 438	82.63 410	87.19 394	96.09 365	64.10 416	87.85 428	58.91 426	84.11 394	88.78 420

test_vis3_rt		79.22 384	77.40 391	84.67 399	86.44 427	74.85 423	97.66 314	81.43 434	84.98 404	67.12 427	81.91 425	28.09 436	97.60 374	88.96 359	80.04 409	81.55 425

test_method		79.03 385	78.17 387	81.63 407	86.06 428	54.40 439	82.75 427	96.89 369	39.54 431	80.98 415	95.57 384	58.37 421	94.73 414	84.74 394	78.61 413	95.75 375

testf1		79.02 386	77.70 388	82.99 404	88.10 424	66.90 430	94.67 410	93.11 417	71.08 422	74.02 420	93.41 407	34.15 432	93.25 418	72.25 420	78.50 414	88.82 418

APD_test2		79.02 386	77.70 388	82.99 404	88.10 424	66.90 430	94.67 410	93.11 417	71.08 422	74.02 420	93.41 407	34.15 432	93.25 418	72.25 420	78.50 414	88.82 418

LCM-MVSNet		78.70 388	76.24 394	86.08 396	77.26 435	71.99 426	94.34 416	96.72 376	61.62 426	76.53 418	89.33 419	33.91 434	92.78 421	81.85 402	74.60 422	93.46 409

kuosan		78.45 389	77.69 390	80.72 408	92.73 410	75.32 421	94.63 413	74.51 437	75.96 418	80.87 416	93.19 409	63.23 418	79.99 432	42.56 432	81.56 403	86.85 424

Gipuma		78.40 390	76.75 393	83.38 403	95.54 375	80.43 415	79.42 428	97.40 330	64.67 425	73.46 422	80.82 426	45.65 425	93.14 420	66.32 424	87.43 373	76.56 428
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 391	75.44 395	85.46 397	82.54 430	74.95 422	94.23 417	93.08 419	72.80 421	74.68 419	87.38 420	36.36 431	91.56 422	73.95 418	63.94 427	89.87 417

FPMVS		77.62 392	77.14 392	79.05 410	79.25 433	60.97 435	95.79 397	95.94 393	65.96 424	67.93 426	94.40 398	37.73 430	88.88 427	68.83 423	88.46 363	87.29 421

EGC-MVSNET		75.22 393	69.54 396	92.28 384	94.81 392	89.58 363	97.64 316	96.50 383	1.82 436	5.57 437	95.74 375	68.21 408	96.26 402	73.80 419	91.71 317	90.99 414

ANet_high		69.08 394	65.37 398	80.22 409	65.99 437	71.96 427	90.91 423	90.09 428	82.62 411	49.93 432	78.39 427	29.36 435	81.75 429	62.49 425	38.52 431	86.95 423

tmp_tt		68.90 395	66.97 397	74.68 412	50.78 439	59.95 436	87.13 424	83.47 433	38.80 432	62.21 428	96.23 359	64.70 415	76.91 434	88.91 360	30.49 432	87.19 422

PMVS	61.03 23	65.95 396	63.57 400	73.09 413	57.90 438	51.22 440	85.05 426	93.93 415	54.45 427	44.32 433	83.57 422	13.22 437	89.15 426	58.68 427	81.00 405	78.91 427
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 397	64.25 399	67.02 414	82.28 431	59.36 437	91.83 422	85.63 431	52.69 428	60.22 429	77.28 428	41.06 429	80.12 431	46.15 431	41.14 429	61.57 430

EMVS		64.07 398	63.26 401	66.53 415	81.73 432	58.81 438	91.85 421	84.75 432	51.93 430	59.09 430	75.13 429	43.32 427	79.09 433	42.03 433	39.47 430	61.69 429

MVE	62.14 22	63.28 399	59.38 402	74.99 411	74.33 436	65.47 432	85.55 425	80.50 435	52.02 429	51.10 431	75.00 430	10.91 440	80.50 430	51.60 429	53.40 428	78.99 426
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 400	30.18 404	30.16 416	78.61 434	43.29 441	66.79 429	14.21 440	17.31 433	14.82 436	11.93 436	11.55 439	41.43 435	37.08 434	19.30 433	5.76 433

cdsmvs_eth3d_5k		23.98 401	31.98 403	0.00 419	0.00 442	0.00 444	0.00 430	98.59 157	0.00 437	0.00 438	98.61 162	90.60 174	0.00 438	0.00 437	0.00 436	0.00 434

testmvs		21.48 402	24.95 405	11.09 418	14.89 440	6.47 443	96.56 386	9.87 441	7.55 434	17.93 434	39.02 432	9.43 441	5.90 437	16.56 436	12.72 434	20.91 432

test123		20.95 403	23.72 406	12.64 417	13.54 441	8.19 442	96.55 387	6.13 442	7.48 435	16.74 435	37.98 433	12.97 438	6.05 436	16.69 435	5.43 435	23.68 431

ab-mvs-re		8.20 404	10.94 407	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	98.43 180	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

pcd_1.5k_mvsjas		7.88 405	10.50 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	94.51 87	0.00 438	0.00 437	0.00 436	0.00 434

mmdepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

monomultidepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

test_blank		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet_test		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

DCPMVS		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

sosnet-low-res		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

sosnet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uncertanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

Regformer		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

WAC-MVS						90.94 332								88.66 362

FOURS1					99.82 1	98.66 24	99.69 1	98.95 52	97.46 45	99.39 37

MSC_two_6792asdad				99.62 6	99.17 100	99.08 11		98.63 150					99.94 11	98.53 45	99.80 24	99.86 8

PC_three_1452									95.08 173	99.60 26	99.16 87	97.86 2	98.47 302	97.52 116	99.72 59	99.74 41

No_MVS				99.62 6	99.17 100	99.08 11		98.63 150					99.94 11	98.53 45	99.80 24	99.86 8

test_one_0601					99.66 26	99.25 2		98.86 81	97.55 38	99.20 49	99.47 29	97.57 6

eth-test2					0.00 442

eth-test					0.00 442

ZD-MVS					99.46 52	98.70 23		98.79 108	93.21 273	98.67 87	98.97 117	95.70 49	99.83 79	96.07 170	99.58 89

RE-MVS-def			98.34 44		99.49 46	97.86 69	99.11 60	98.80 103	96.49 101	99.17 52	99.35 53	95.29 65		97.72 95	99.65 72	99.71 54

IU-MVS					99.71 19	99.23 7		98.64 147	95.28 160	99.63 25				98.35 62	99.81 15	99.83 13

OPU-MVS				99.37 22	99.24 92	99.05 14	99.02 79				99.16 87	97.81 3	99.37 193	97.24 125	99.73 55	99.70 58

test_241102_TWO								98.87 75	97.65 31	99.53 30	99.48 27	97.34 11	99.94 11	98.43 57	99.80 24	99.83 13

test_241102_ONE					99.71 19	99.24 5		98.87 75	97.62 33	99.73 17	99.39 41	97.53 7	99.74 121

9.14			98.06 69		99.47 50		98.71 168	98.82 90	94.36 211	99.16 55	99.29 62	96.05 37	99.81 91	97.00 131	99.71 61

save fliter					99.46 52	98.38 35	98.21 244	98.71 126	97.95 22

test_0728_THIRD									97.32 53	99.45 32	99.46 33	97.88 1	99.94 11	98.47 53	99.86 2	99.85 10

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 89	98.88 68					99.94 11	98.47 53	99.81 15	99.84 12

test0726					99.72 12	99.25 2	99.06 67	98.88 68	97.62 33	99.56 27	99.50 23	97.42 9

GSMVS																99.20 150

test_part2					99.63 29	99.18 10				99.27 46

sam_mvs1												89.45 197				99.20 150

sam_mvs												88.99 211

ambc				89.49 391	86.66 426	75.78 418	92.66 420	96.72 376		86.55 399	92.50 414	46.01 424	97.90 360	90.32 335	82.09 398	94.80 395

MTGPA								98.74 118

test_post1							96.68 383				30.43 435	87.85 245	98.69 281	92.59 287

test_post											31.83 434	88.83 218	98.91 257

patchmatchnet-post											95.10 390	89.42 198	98.89 261

GG-mvs-BLEND				96.59 253	96.34 348	94.98 215	96.51 388	88.58 430		93.10 327	94.34 401	80.34 352	98.05 349	89.53 351	96.99 217	96.74 313

MTMP							98.89 110	94.14 413

gm-plane-assit					95.88 366	87.47 395			89.74 372		96.94 328		99.19 212	93.32 266

test9_res														96.39 164	99.57 90	99.69 61

TEST9					99.31 68	98.50 29	97.92 284	98.73 121	92.63 296	97.74 147	98.68 157	96.20 32	99.80 98

test_8					99.29 77	98.44 31	97.89 292	98.72 123	92.98 284	97.70 152	98.66 160	96.20 32	99.80 98

agg_prior2														95.87 180	99.57 90	99.68 66

agg_prior					99.30 72	98.38 35		98.72 123		97.57 164			99.81 91

TestCases				96.99 218	99.25 85	93.21 293		98.18 246	91.36 336	93.52 306	98.77 146	84.67 305	99.72 123	89.70 348	97.87 193	98.02 253

test_prior4						98.01 65	97.86 296

test_prior2							97.80 303		96.12 119	97.89 140	98.69 156	95.96 41		96.89 140	99.60 84

test_prior				99.19 44	99.31 68	98.22 52		98.84 85					99.70 129			99.65 74

旧先验2							97.57 322		91.30 341	98.67 87			99.80 98	95.70 189

新几何2							97.64 316

新几何1				99.16 49	99.34 61	98.01 65		98.69 131	90.06 366	98.13 116	98.95 124	94.60 85	99.89 57	91.97 306	99.47 110	99.59 85

旧先验1					99.29 77	97.48 83		98.70 130			99.09 103	95.56 52			99.47 110	99.61 81

无先验							97.58 321	98.72 123	91.38 335				99.87 68	93.36 265		99.60 83

原ACMM2							97.67 313

原ACMM1				98.65 88	99.32 66	96.62 127		98.67 139	93.27 272	97.81 142	98.97 117	95.18 72	99.83 79	93.84 251	99.46 113	99.50 97

test222					99.23 93	97.17 105	97.40 330	98.66 142	88.68 385	98.05 122	98.96 122	94.14 98			99.53 101	99.61 81

testdata2													99.89 57	91.65 314

segment_acmp												96.85 14

testdata				98.26 125	99.20 98	95.36 193		98.68 134	91.89 322	98.60 95	99.10 96	94.44 92	99.82 86	94.27 237	99.44 114	99.58 89

testdata1							97.32 340		96.34 109

test12				99.18 46	99.16 104	98.19 54		98.53 173		98.07 120		95.13 75	99.72 123		99.56 96	99.63 79

plane_prior7					97.42 282	94.63 232

plane_prior6					97.35 289	94.61 235						87.09 257

plane_prior5								98.56 167					99.03 237	96.07 170	94.27 270	96.92 289

plane_prior4											98.28 199

plane_prior3						94.61 235			97.02 75	95.34 236

plane_prior2							98.80 144		97.28 56

plane_prior1					97.37 288

plane_prior						94.60 237	98.44 218		96.74 89						94.22 272

n2								0.00 443

nn								0.00 443

door-mid								94.37 409

lessismore_v0				94.45 358	94.93 390	88.44 386		91.03 426		86.77 397	97.64 261	76.23 388	98.42 308	90.31 336	85.64 390	96.51 348

LGP-MVS_train				96.47 268	97.46 277	93.54 274		98.54 171	94.67 195	94.36 268	98.77 146	85.39 287	99.11 225	95.71 187	94.15 276	96.76 311

test11								98.66 142

door								94.64 407

HQP5-MVS						94.25 253

HQP-NCC					97.20 297		98.05 268		96.43 103	94.45 260

ACMP_Plane					97.20 297		98.05 268		96.43 103	94.45 260

BP-MVS														95.30 200

HQP4-MVS										94.45 260			98.96 248			96.87 301

HQP3-MVS								98.46 192							94.18 274

HQP2-MVS												86.75 263

NP-MVS					97.28 291	94.51 240					97.73 248

MDTV_nov1_ep13_2view						84.26 404	96.89 373		90.97 350	97.90 139		89.89 186		93.91 249		99.18 159

MDTV_nov1_ep13			95.40 187		97.48 275	88.34 387	96.85 376	97.29 338	93.74 242	97.48 166	97.26 289	89.18 205	99.05 233	91.92 307	97.43 208

ACMMP++_ref															92.97 302

ACMMP++															93.61 291

Test By Simon												94.64 84

ITE_SJBPF				95.44 319	97.42 282	91.32 326		97.50 318	95.09 172	93.59 302	98.35 190	81.70 334	98.88 263	89.71 347	93.39 297	96.12 367

DeepMVS_CX				86.78 395	97.09 307	72.30 425		95.17 403	75.92 419	84.34 408	95.19 388	70.58 405	95.35 409	79.98 409	89.04 357	92.68 413

High-resolution multi-view benchmark