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 56	99.43 58	97.48 84	98.88 121	99.30 14	98.47 14	99.85 8	99.43 39	96.71 17	99.96 4	99.86 1	99.80 24	99.89 5

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 20	99.24 5	99.02 80	98.87 78	97.65 34	99.73 18	99.48 29	97.53 7	99.94 12	98.43 63	99.81 15	99.70 60

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 102	99.23 7	99.69 1	98.88 71	97.32 58	99.53 33	99.47 31	97.81 3	99.94 12	98.47 59	99.72 60	99.74 43

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 52	99.41 60	97.54 82	98.89 114	99.31 13	98.49 13	99.86 5	99.42 40	96.45 24	99.96 4	99.86 1	99.74 52	99.90 4

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 13	99.25 2	98.97 91	98.58 168	97.62 36	99.45 35	99.46 36	97.42 9	99.94 12	98.47 59	99.81 15	99.69 63
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 34	98.96 16	99.39 11	98.93 59	97.38 55	99.41 38	99.54 17	96.66 18	99.84 80	98.86 35	99.85 6	99.87 8
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
lecture		98.95 7	98.78 11	99.45 15	99.75 3	98.63 26	99.43 10	99.38 8	97.60 39	99.58 29	99.47 31	95.36 61	99.93 31	98.87 34	99.57 92	99.78 26

reproduce_model		98.94 8	98.81 10	99.34 27	99.52 40	98.26 50	98.94 100	98.84 88	98.06 21	99.35 42	99.61 4	96.39 27	99.94 12	98.77 38	99.82 14	99.83 14

reproduce-ours		98.93 9	98.78 11	99.38 19	99.49 47	98.38 36	98.86 128	98.83 90	98.06 21	99.29 46	99.58 13	96.40 25	99.94 12	98.68 41	99.81 15	99.81 20

our_new_method		98.93 9	98.78 11	99.38 19	99.49 47	98.38 36	98.86 128	98.83 90	98.06 21	99.29 46	99.58 13	96.40 25	99.94 12	98.68 41	99.81 15	99.81 20

test_fmvsmconf_n		98.92 11	98.87 6	99.04 62	98.88 138	97.25 106	98.82 140	99.34 11	98.75 7	99.80 10	99.61 4	95.16 74	99.95 9	99.70 13	99.80 24	99.93 1

DPE-MVS		98.92 11	98.67 17	99.65 2	99.58 33	99.20 9	98.42 234	98.91 65	97.58 40	99.54 32	99.46 36	97.10 12	99.94 12	97.64 110	99.84 11	99.83 14
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 13	98.74 15	99.37 23	99.36 61	98.25 51	98.89 114	99.24 19	98.77 6	99.89 1	99.59 11	93.39 108	99.96 4	99.78 6	99.76 42	99.89 5

SteuartSystems-ACMMP		98.90 13	98.75 14	99.36 25	99.22 97	98.43 34	99.10 64	98.87 78	97.38 55	99.35 42	99.40 43	97.78 5	99.87 71	97.77 98	99.85 6	99.78 26
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 15	99.01 3	98.45 114	99.42 59	96.43 147	98.96 96	99.36 10	98.63 9	99.86 5	99.51 23	95.91 43	99.97 1	99.72 10	99.75 48	98.94 196

TSAR-MVS + MP.		98.78 16	98.62 18	99.24 41	99.69 25	98.28 49	99.14 55	98.66 146	96.84 89	99.56 30	99.31 63	96.34 28	99.70 133	98.32 69	99.73 55	99.73 48
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 16	98.56 22	99.45 15	99.32 68	98.87 19	98.47 224	98.81 99	97.72 29	98.76 86	99.16 91	97.05 13	99.78 115	98.06 80	99.66 71	99.69 63

MSP-MVS		98.74 18	98.55 23	99.29 34	99.75 3	98.23 52	99.26 28	98.88 71	97.52 43	99.41 38	98.78 153	96.00 39	99.79 112	97.79 97	99.59 88	99.85 11
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
fmvsm_s_conf0.5_n_8		98.73 19	98.62 18	99.05 61	99.35 62	97.27 100	98.80 149	99.23 24	98.93 2	99.79 11	99.59 11	92.34 124	99.95 9	99.82 4	99.71 62	99.92 2

XVS		98.70 20	98.49 29	99.34 27	99.70 23	98.35 45	99.29 23	98.88 71	97.40 52	98.46 108	99.20 81	95.90 45	99.89 60	97.85 93	99.74 52	99.78 26

fmvsm_s_conf0.5_n_6		98.65 21	98.55 23	98.95 71	98.50 178	97.30 96	98.79 157	99.16 34	98.14 19	99.86 5	99.41 42	93.71 105	99.91 49	99.71 11	99.64 79	99.65 76

MCST-MVS		98.65 21	98.37 38	99.48 13	99.60 32	98.87 19	98.41 235	98.68 138	97.04 81	98.52 106	98.80 151	96.78 16	99.83 82	97.93 87	99.61 84	99.74 43

SD-MVS		98.64 23	98.68 16	98.53 103	99.33 65	98.36 44	98.90 110	98.85 87	97.28 62	99.72 21	99.39 44	96.63 20	97.60 388	98.17 75	99.85 6	99.64 79
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 24	98.40 35	99.32 33	99.72 13	98.29 48	99.23 33	98.96 54	96.10 128	98.94 69	99.17 88	96.06 36	99.92 39	97.62 111	99.78 34	99.75 41

ACMMP_NAP		98.61 25	98.30 53	99.55 9	99.62 31	98.95 17	98.82 140	98.81 99	95.80 140	99.16 58	99.47 31	95.37 60	99.92 39	97.89 91	99.75 48	99.79 24

region2R		98.61 25	98.38 37	99.29 34	99.74 8	98.16 58	99.23 33	98.93 59	96.15 124	98.94 69	99.17 88	95.91 43	99.94 12	97.55 119	99.79 30	99.78 26

NCCC		98.61 25	98.35 41	99.38 19	99.28 83	98.61 27	98.45 225	98.76 117	97.82 28	98.45 111	98.93 132	96.65 19	99.83 82	97.38 130	99.41 120	99.71 56

SF-MVS		98.59 28	98.32 52	99.41 18	99.54 36	98.71 22	99.04 74	98.81 99	95.12 177	99.32 45	99.39 44	96.22 30	99.84 80	97.72 101	99.73 55	99.67 72

ACMMPR		98.59 28	98.36 39	99.29 34	99.74 8	98.15 59	99.23 33	98.95 55	96.10 128	98.93 73	99.19 86	95.70 49	99.94 12	97.62 111	99.79 30	99.78 26

test_fmvsmconf0.1_n		98.58 30	98.44 33	98.99 64	97.73 264	97.15 111	98.84 136	98.97 51	98.75 7	99.43 37	99.54 17	93.29 110	99.93 31	99.64 16	99.79 30	99.89 5

SMA-MVS		98.58 30	98.25 56	99.56 8	99.51 41	99.04 15	98.95 97	98.80 106	93.67 264	99.37 41	99.52 20	96.52 22	99.89 60	98.06 80	99.81 15	99.76 40
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 30	98.29 54	99.46 14	99.76 2	98.64 25	98.90 110	98.74 121	97.27 66	98.02 135	99.39 44	94.81 84	99.96 4	97.91 89	99.79 30	99.77 33

HPM-MVS++		98.58 30	98.25 56	99.55 9	99.50 43	99.08 11	98.72 175	98.66 146	97.51 44	98.15 122	98.83 148	95.70 49	99.92 39	97.53 121	99.67 68	99.66 75

SR-MVS		98.57 34	98.35 41	99.24 41	99.53 37	98.18 56	99.09 65	98.82 93	96.58 105	99.10 60	99.32 61	95.39 58	99.82 89	97.70 106	99.63 81	99.72 52

CP-MVS		98.57 34	98.36 39	99.19 45	99.66 27	97.86 70	99.34 17	98.87 78	95.96 132	98.60 102	99.13 96	96.05 37	99.94 12	97.77 98	99.86 2	99.77 33

MSLP-MVS++		98.56 36	98.57 21	98.55 99	99.26 86	96.80 126	98.71 176	99.05 44	97.28 62	98.84 79	99.28 66	96.47 23	99.40 197	98.52 57	99.70 64	99.47 108

DeepC-MVS_fast	96.70 1	98.55 37	98.34 47	99.18 47	99.25 87	98.04 64	98.50 221	98.78 113	97.72 29	98.92 75	99.28 66	95.27 67	99.82 89	97.55 119	99.77 36	99.69 63
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 38	98.35 41	99.13 53	99.49 47	97.86 70	99.11 61	98.80 106	96.49 109	99.17 55	99.35 56	95.34 63	99.82 89	97.72 101	99.65 74	99.71 56

fmvsm_s_conf0.5_n_5		98.53 39	98.35 41	99.08 58	99.07 117	97.46 88	98.68 184	99.20 29	97.50 45	99.87 2	99.50 25	91.96 143	99.96 4	99.76 7	99.65 74	99.82 18

fmvsm_s_conf0.5_n_3		98.53 39	98.45 32	98.79 79	99.23 95	97.32 93	98.80 149	99.26 16	98.82 3	99.87 2	99.60 8	90.95 172	99.93 31	99.76 7	99.73 55	99.12 171

APD-MVS_3200maxsize		98.53 39	98.33 51	99.15 51	99.50 43	97.92 69	99.15 52	98.81 99	96.24 120	99.20 52	99.37 50	95.30 65	99.80 101	97.73 100	99.67 68	99.72 52

MM		98.51 42	98.24 58	99.33 31	99.12 111	98.14 61	98.93 105	97.02 373	98.96 1	99.17 55	99.47 31	91.97 142	99.94 12	99.85 3	99.69 65	99.91 3

mPP-MVS		98.51 42	98.26 55	99.25 40	99.75 3	98.04 64	99.28 25	98.81 99	96.24 120	98.35 118	99.23 76	95.46 55	99.94 12	97.42 127	99.81 15	99.77 33

ZNCC-MVS		98.49 44	98.20 64	99.35 26	99.73 12	98.39 35	99.19 45	98.86 84	95.77 142	98.31 121	99.10 100	95.46 55	99.93 31	97.57 118	99.81 15	99.74 43

SPE-MVS-test		98.49 44	98.50 27	98.46 113	99.20 100	97.05 116	99.64 4	98.50 190	97.45 51	98.88 76	99.14 95	95.25 69	99.15 227	98.83 36	99.56 99	99.20 156

PGM-MVS		98.49 44	98.23 60	99.27 39	99.72 13	98.08 63	98.99 87	99.49 5	95.43 158	99.03 61	99.32 61	95.56 52	99.94 12	96.80 159	99.77 36	99.78 26

EI-MVSNet-Vis-set		98.47 47	98.39 36	98.69 87	99.46 53	96.49 144	98.30 246	98.69 135	97.21 69	98.84 79	99.36 54	95.41 57	99.78 115	98.62 45	99.65 74	99.80 23

MVS_111021_HR		98.47 47	98.34 47	98.88 76	99.22 97	97.32 93	97.91 300	99.58 3	97.20 70	98.33 119	99.00 121	95.99 40	99.64 147	98.05 82	99.76 42	99.69 63

balanced_conf03		98.45 49	98.35 41	98.74 83	98.65 167	97.55 80	99.19 45	98.60 157	96.72 99	99.35 42	98.77 156	95.06 79	99.55 170	98.95 31	99.87 1	99.12 171

test_fmvsmvis_n_1920		98.44 50	98.51 25	98.23 135	98.33 200	96.15 161	98.97 91	99.15 36	98.55 12	98.45 111	99.55 15	94.26 97	99.97 1	99.65 14	99.66 71	98.57 240

CS-MVS		98.44 50	98.49 29	98.31 127	99.08 116	96.73 130	99.67 3	98.47 197	97.17 73	98.94 69	99.10 100	95.73 48	99.13 230	98.71 40	99.49 110	99.09 176

GST-MVS		98.43 52	98.12 68	99.34 27	99.72 13	98.38 36	99.09 65	98.82 93	95.71 146	98.73 89	99.06 112	95.27 67	99.93 31	97.07 138	99.63 81	99.72 52

fmvsm_s_conf0.5_n		98.42 53	98.51 25	98.13 145	99.30 74	95.25 208	98.85 132	99.39 7	97.94 25	99.74 17	99.62 3	92.59 119	99.91 49	99.65 14	99.52 105	99.25 149

EI-MVSNet-UG-set		98.41 54	98.34 47	98.61 94	99.45 56	96.32 154	98.28 249	98.68 138	97.17 73	98.74 87	99.37 50	95.25 69	99.79 112	98.57 48	99.54 102	99.73 48

DELS-MVS		98.40 55	98.20 64	98.99 64	99.00 125	97.66 75	97.75 321	98.89 68	97.71 31	98.33 119	98.97 123	94.97 81	99.88 69	98.42 65	99.76 42	99.42 120
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 56	98.42 34	98.27 129	99.09 115	95.41 198	98.86 128	99.37 9	97.69 33	99.78 13	99.61 4	92.38 122	99.91 49	99.58 19	99.43 118	99.49 104

TSAR-MVS + GP.		98.38 56	98.24 58	98.81 78	99.22 97	97.25 106	98.11 275	98.29 238	97.19 71	98.99 67	99.02 115	96.22 30	99.67 140	98.52 57	98.56 173	99.51 97

HPM-MVS_fast		98.38 56	98.13 67	99.12 55	99.75 3	97.86 70	99.44 9	98.82 93	94.46 219	98.94 69	99.20 81	95.16 74	99.74 125	97.58 114	99.85 6	99.77 33

patch_mono-2		98.36 59	98.87 6	96.82 242	99.53 37	90.68 351	98.64 195	99.29 15	97.88 26	99.19 54	99.52 20	96.80 15	99.97 1	99.11 27	99.86 2	99.82 18

HPM-MVS		98.36 59	98.10 71	99.13 53	99.74 8	97.82 74	99.53 6	98.80 106	94.63 208	98.61 101	98.97 123	95.13 76	99.77 120	97.65 109	99.83 13	99.79 24
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 61	98.50 27	97.90 162	99.16 106	95.08 217	98.75 161	99.24 19	98.39 15	99.81 9	99.52 20	92.35 123	99.90 57	99.74 9	99.51 107	98.71 221

APD-MVS		98.35 61	98.00 77	99.42 17	99.51 41	98.72 21	98.80 149	98.82 93	94.52 216	99.23 51	99.25 75	95.54 54	99.80 101	96.52 166	99.77 36	99.74 43
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 63	98.23 60	98.67 89	99.27 84	96.90 122	97.95 293	99.58 3	97.14 76	98.44 113	99.01 119	95.03 80	99.62 154	97.91 89	99.75 48	99.50 99

PHI-MVS		98.34 63	98.06 72	99.18 47	99.15 109	98.12 62	99.04 74	99.09 39	93.32 279	98.83 81	99.10 100	96.54 21	99.83 82	97.70 106	99.76 42	99.59 87

MP-MVS		98.33 65	98.01 76	99.28 37	99.75 3	98.18 56	99.22 37	98.79 111	96.13 125	97.92 146	99.23 76	94.54 87	99.94 12	96.74 162	99.78 34	99.73 48
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 66	98.19 66	98.67 89	98.96 132	97.36 91	99.24 31	98.57 170	94.81 200	98.99 67	98.90 136	95.22 72	99.59 157	99.15 26	99.84 11	99.07 184

MP-MVS-pluss		98.31 66	97.92 79	99.49 12	99.72 13	98.88 18	98.43 231	98.78 113	94.10 229	97.69 163	99.42 40	95.25 69	99.92 39	98.09 79	99.80 24	99.67 72
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 68	98.21 62	98.57 96	99.25 87	97.11 113	98.66 191	99.20 29	98.82 3	99.79 11	99.60 8	89.38 207	99.92 39	99.80 5	99.38 125	98.69 223

fmvsm_s_conf0.5_n_7		98.23 69	98.35 41	97.89 164	98.86 142	94.99 223	98.58 204	99.00 47	98.29 16	99.73 18	99.60 8	91.70 147	99.92 39	99.63 17	99.73 55	98.76 215

MVS_0304		98.23 69	97.91 80	99.21 44	98.06 232	97.96 68	98.58 204	95.51 411	98.58 10	98.87 77	99.26 70	92.99 114	99.95 9	99.62 18	99.67 68	99.73 48

ACMMP		98.23 69	97.95 78	99.09 57	99.74 8	97.62 78	99.03 77	99.41 6	95.98 131	97.60 172	99.36 54	94.45 92	99.93 31	97.14 135	98.85 158	99.70 60
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 72	98.11 69	98.49 110	98.34 197	97.26 105	99.61 5	98.43 207	96.78 92	98.87 77	98.84 144	93.72 104	99.01 252	98.91 33	99.50 108	99.19 160

fmvsm_s_conf0.1_n		98.18 73	98.21 62	98.11 149	98.54 176	95.24 209	98.87 124	99.24 19	97.50 45	99.70 22	99.67 1	91.33 160	99.89 60	99.47 21	99.54 102	99.21 155

fmvsm_s_conf0.1_n_2		98.14 74	98.02 75	98.53 103	98.88 138	97.07 115	98.69 182	98.82 93	98.78 5	99.77 14	99.61 4	88.83 226	99.91 49	99.71 11	99.07 141	98.61 233

fmvsm_s_conf0.1_n_a		98.08 75	98.04 74	98.21 136	97.66 270	95.39 199	98.89 114	99.17 33	97.24 67	99.76 16	99.67 1	91.13 166	99.88 69	99.39 22	99.41 120	99.35 128

dcpmvs_2		98.08 75	98.59 20	96.56 267	99.57 34	90.34 363	99.15 52	98.38 217	96.82 91	99.29 46	99.49 28	95.78 47	99.57 160	98.94 32	99.86 2	99.77 33

CANet		98.05 77	97.76 83	98.90 75	98.73 152	97.27 100	98.35 237	98.78 113	97.37 57	97.72 160	98.96 128	91.53 156	99.92 39	98.79 37	99.65 74	99.51 97

train_agg		97.97 78	97.52 96	99.33 31	99.31 70	98.50 30	97.92 298	98.73 124	92.98 295	97.74 157	98.68 167	96.20 32	99.80 101	96.59 163	99.57 92	99.68 68

ETV-MVS		97.96 79	97.81 81	98.40 122	98.42 184	97.27 100	98.73 171	98.55 175	96.84 89	98.38 115	97.44 288	95.39 58	99.35 202	97.62 111	98.89 152	98.58 239

UA-Net		97.96 79	97.62 87	98.98 66	98.86 142	97.47 86	98.89 114	99.08 40	96.67 102	98.72 91	99.54 17	93.15 112	99.81 94	94.87 222	98.83 159	99.65 76

CDPH-MVS		97.94 81	97.49 98	99.28 37	99.47 51	98.44 32	97.91 300	98.67 143	92.57 311	98.77 85	98.85 143	95.93 42	99.72 127	95.56 200	99.69 65	99.68 68

DeepPCF-MVS	96.37 2	97.93 82	98.48 31	96.30 293	99.00 125	89.54 378	97.43 343	98.87 78	98.16 18	99.26 50	99.38 49	96.12 35	99.64 147	98.30 70	99.77 36	99.72 52

DeepC-MVS	95.98 3	97.88 83	97.58 89	98.77 81	99.25 87	96.93 120	98.83 138	98.75 119	96.96 85	96.89 198	99.50 25	90.46 180	99.87 71	97.84 95	99.76 42	99.52 94
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 84	97.54 95	98.83 77	95.48 393	96.83 125	98.95 97	98.60 157	98.58 10	98.93 73	99.55 15	88.57 231	99.91 49	99.54 20	99.61 84	99.77 33

DP-MVS Recon		97.86 84	97.46 101	99.06 60	99.53 37	98.35 45	98.33 239	98.89 68	92.62 308	98.05 130	98.94 131	95.34 63	99.65 144	96.04 182	99.42 119	99.19 160

CSCG		97.85 86	97.74 84	98.20 138	99.67 26	95.16 212	99.22 37	99.32 12	93.04 293	97.02 191	98.92 134	95.36 61	99.91 49	97.43 126	99.64 79	99.52 94

SymmetryMVS		97.84 87	97.58 89	98.62 93	99.01 123	96.60 136	98.94 100	98.44 202	97.86 27	98.71 92	99.08 109	91.22 165	99.80 101	97.40 128	97.53 216	99.47 108

BP-MVS1		97.82 88	97.51 97	98.76 82	98.25 208	97.39 90	99.15 52	97.68 305	96.69 100	98.47 107	99.10 100	90.29 184	99.51 177	98.60 46	99.35 128	99.37 125

MG-MVS		97.81 89	97.60 88	98.44 116	99.12 111	95.97 170	97.75 321	98.78 113	96.89 88	98.46 108	99.22 78	93.90 103	99.68 139	94.81 226	99.52 105	99.67 72

VNet		97.79 90	97.40 105	98.96 69	98.88 138	97.55 80	98.63 198	98.93 59	96.74 96	99.02 62	98.84 144	90.33 183	99.83 82	98.53 51	96.66 239	99.50 99

EIA-MVS		97.75 91	97.58 89	98.27 129	98.38 188	96.44 146	99.01 82	98.60 157	95.88 136	97.26 179	97.53 282	94.97 81	99.33 205	97.38 130	99.20 137	99.05 185

PS-MVSNAJ		97.73 92	97.77 82	97.62 192	98.68 162	95.58 189	97.34 352	98.51 185	97.29 60	98.66 98	97.88 246	94.51 88	99.90 57	97.87 92	99.17 139	97.39 283

casdiffmvs_mvg		97.72 93	97.48 100	98.44 116	98.42 184	96.59 139	98.92 107	98.44 202	96.20 122	97.76 154	99.20 81	91.66 150	99.23 217	98.27 74	98.41 183	99.49 104
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CPTT-MVS		97.72 93	97.32 110	98.92 72	99.64 29	97.10 114	99.12 59	98.81 99	92.34 319	98.09 127	99.08 109	93.01 113	99.92 39	96.06 181	99.77 36	99.75 41

PVSNet_Blended_VisFu		97.70 95	97.46 101	98.44 116	99.27 84	95.91 178	98.63 198	99.16 34	94.48 218	97.67 164	98.88 140	92.80 116	99.91 49	97.11 136	99.12 140	99.50 99

mvsany_test1		97.69 96	97.70 85	97.66 189	98.24 209	94.18 264	97.53 337	97.53 326	95.52 154	99.66 24	99.51 23	94.30 95	99.56 163	98.38 66	98.62 168	99.23 151

sasdasda		97.67 97	97.23 115	98.98 66	98.70 157	98.38 36	99.34 17	98.39 213	96.76 94	97.67 164	97.40 292	92.26 128	99.49 181	98.28 71	96.28 257	99.08 180

canonicalmvs		97.67 97	97.23 115	98.98 66	98.70 157	98.38 36	99.34 17	98.39 213	96.76 94	97.67 164	97.40 292	92.26 128	99.49 181	98.28 71	96.28 257	99.08 180

xiu_mvs_v2_base		97.66 99	97.70 85	97.56 196	98.61 171	95.46 196	97.44 341	98.46 198	97.15 75	98.65 99	98.15 221	94.33 94	99.80 101	97.84 95	98.66 167	97.41 281

GDP-MVS		97.64 100	97.28 111	98.71 86	98.30 205	97.33 92	99.05 70	98.52 182	96.34 117	98.80 82	99.05 113	89.74 194	99.51 177	96.86 156	98.86 156	99.28 143

baseline		97.64 100	97.44 103	98.25 133	98.35 192	96.20 158	99.00 84	98.32 227	96.33 119	98.03 133	99.17 88	91.35 159	99.16 224	98.10 78	98.29 190	99.39 122

casdiffmvs		97.63 102	97.41 104	98.28 128	98.33 200	96.14 162	98.82 140	98.32 227	96.38 116	97.95 141	99.21 79	91.23 164	99.23 217	98.12 77	98.37 184	99.48 106
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		97.62 103	97.19 118	98.92 72	98.66 164	98.20 54	99.32 22	98.38 217	96.69 100	97.58 173	97.42 291	92.10 136	99.50 180	98.28 71	96.25 260	99.08 180

xiu_mvs_v1_base_debu		97.60 104	97.56 92	97.72 179	98.35 192	95.98 165	97.86 310	98.51 185	97.13 77	99.01 64	98.40 194	91.56 152	99.80 101	98.53 51	98.68 163	97.37 285

xiu_mvs_v1_base		97.60 104	97.56 92	97.72 179	98.35 192	95.98 165	97.86 310	98.51 185	97.13 77	99.01 64	98.40 194	91.56 152	99.80 101	98.53 51	98.68 163	97.37 285

xiu_mvs_v1_base_debi		97.60 104	97.56 92	97.72 179	98.35 192	95.98 165	97.86 310	98.51 185	97.13 77	99.01 64	98.40 194	91.56 152	99.80 101	98.53 51	98.68 163	97.37 285

diffmvs		97.58 107	97.40 105	98.13 145	98.32 203	95.81 184	98.06 281	98.37 219	96.20 122	98.74 87	98.89 139	91.31 162	99.25 214	98.16 76	98.52 175	99.34 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
guyue		97.57 108	97.37 107	98.20 138	98.50 178	95.86 182	98.89 114	97.03 370	97.29 60	98.73 89	98.90 136	89.41 206	99.32 206	98.68 41	98.86 156	99.42 120

MVSFormer		97.57 108	97.49 98	97.84 166	98.07 229	95.76 185	99.47 7	98.40 211	94.98 189	98.79 83	98.83 148	92.34 124	98.41 326	96.91 144	99.59 88	99.34 130

alignmvs		97.56 110	97.07 125	99.01 63	98.66 164	98.37 43	98.83 138	98.06 285	96.74 96	98.00 139	97.65 269	90.80 174	99.48 186	98.37 67	96.56 243	99.19 160

DPM-MVS		97.55 111	96.99 129	99.23 43	99.04 119	98.55 28	97.17 367	98.35 222	94.85 199	97.93 145	98.58 177	95.07 78	99.71 132	92.60 296	99.34 129	99.43 118

OMC-MVS		97.55 111	97.34 109	98.20 138	99.33 65	95.92 177	98.28 249	98.59 163	95.52 154	97.97 140	99.10 100	93.28 111	99.49 181	95.09 217	98.88 153	99.19 160

LuminaMVS		97.49 113	97.18 119	98.42 120	97.50 285	97.15 111	98.45 225	97.68 305	96.56 108	98.68 93	98.78 153	89.84 191	99.32 206	98.60 46	98.57 172	98.79 207

KinetiMVS		97.48 114	97.05 126	98.78 80	98.37 190	97.30 96	98.99 87	98.70 133	97.18 72	99.02 62	99.01 119	87.50 260	99.67 140	95.33 207	99.33 131	99.37 125

PAPM_NR		97.46 115	97.11 122	98.50 108	99.50 43	96.41 149	98.63 198	98.60 157	95.18 174	97.06 189	98.06 227	94.26 97	99.57 160	93.80 264	98.87 155	99.52 94

EPP-MVSNet		97.46 115	97.28 111	97.99 157	98.64 168	95.38 200	99.33 21	98.31 229	93.61 268	97.19 182	99.07 111	94.05 100	99.23 217	96.89 148	98.43 182	99.37 125

3Dnovator	94.51 5	97.46 115	96.93 132	99.07 59	97.78 258	97.64 76	99.35 16	99.06 42	97.02 82	93.75 311	99.16 91	89.25 211	99.92 39	97.22 134	99.75 48	99.64 79

CNLPA		97.45 118	97.03 127	98.73 84	99.05 118	97.44 89	98.07 280	98.53 179	95.32 167	96.80 203	98.53 182	93.32 109	99.72 127	94.31 245	99.31 132	99.02 187

lupinMVS		97.44 119	97.22 117	98.12 148	98.07 229	95.76 185	97.68 326	97.76 302	94.50 217	98.79 83	98.61 172	92.34 124	99.30 210	97.58 114	99.59 88	99.31 136

3Dnovator+	94.38 6	97.43 120	96.78 140	99.38 19	97.83 255	98.52 29	99.37 13	98.71 129	97.09 80	92.99 340	99.13 96	89.36 208	99.89 60	96.97 141	99.57 92	99.71 56

Vis-MVSNet		97.42 121	97.11 122	98.34 125	98.66 164	96.23 157	99.22 37	99.00 47	96.63 104	98.04 132	99.21 79	88.05 247	99.35 202	96.01 184	99.21 136	99.45 115
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 122	97.25 113	97.91 161	98.70 157	96.80 126	98.82 140	98.69 135	94.53 214	98.11 125	98.28 209	94.50 91	99.57 160	94.12 253	99.49 110	97.37 285

sss		97.39 123	96.98 131	98.61 94	98.60 172	96.61 135	98.22 255	98.93 59	93.97 239	98.01 138	98.48 187	91.98 140	99.85 76	96.45 168	98.15 192	99.39 122

test_cas_vis1_n_1920		97.38 124	97.36 108	97.45 199	98.95 133	93.25 302	99.00 84	98.53 179	97.70 32	99.77 14	99.35 56	84.71 313	99.85 76	98.57 48	99.66 71	99.26 147

PVSNet_Blended		97.38 124	97.12 121	98.14 142	99.25 87	95.35 203	97.28 357	99.26 16	93.13 289	97.94 143	98.21 217	92.74 117	99.81 94	96.88 150	99.40 123	99.27 144

WTY-MVS		97.37 126	96.92 133	98.72 85	98.86 142	96.89 124	98.31 244	98.71 129	95.26 170	97.67 164	98.56 181	92.21 132	99.78 115	95.89 186	96.85 233	99.48 106

AstraMVS		97.34 127	97.24 114	97.65 190	98.13 225	94.15 265	98.94 100	96.25 402	97.47 49	98.60 102	99.28 66	89.67 196	99.41 196	98.73 39	98.07 196	99.38 124

jason		97.32 128	97.08 124	98.06 153	97.45 291	95.59 188	97.87 308	97.91 296	94.79 201	98.55 105	98.83 148	91.12 167	99.23 217	97.58 114	99.60 86	99.34 130
jason: jason.
MVS_Test		97.28 129	97.00 128	98.13 145	98.33 200	95.97 170	98.74 165	98.07 280	94.27 224	98.44 113	98.07 226	92.48 120	99.26 213	96.43 169	98.19 191	99.16 166

EPNet		97.28 129	96.87 135	98.51 105	94.98 402	96.14 162	98.90 110	97.02 373	98.28 17	95.99 235	99.11 98	91.36 158	99.89 60	96.98 140	99.19 138	99.50 99
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsmamba		97.25 131	96.99 129	98.02 155	98.34 197	95.54 193	99.18 49	97.47 332	95.04 183	98.15 122	98.57 180	89.46 203	99.31 209	97.68 108	99.01 146	99.22 153

test_yl		97.22 132	96.78 140	98.54 101	98.73 152	96.60 136	98.45 225	98.31 229	94.70 202	98.02 135	98.42 192	90.80 174	99.70 133	96.81 157	96.79 235	99.34 130

DCV-MVSNet		97.22 132	96.78 140	98.54 101	98.73 152	96.60 136	98.45 225	98.31 229	94.70 202	98.02 135	98.42 192	90.80 174	99.70 133	96.81 157	96.79 235	99.34 130

IS-MVSNet		97.22 132	96.88 134	98.25 133	98.85 145	96.36 152	99.19 45	97.97 290	95.39 161	97.23 180	98.99 122	91.11 168	98.93 264	94.60 233	98.59 170	99.47 108

PLC	95.07 4	97.20 135	96.78 140	98.44 116	99.29 79	96.31 156	98.14 270	98.76 117	92.41 317	96.39 223	98.31 207	94.92 83	99.78 115	94.06 256	98.77 162	99.23 151
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 136	97.18 119	97.20 212	98.81 148	93.27 299	95.78 412	99.15 36	95.25 171	96.79 204	98.11 224	92.29 127	99.07 242	98.56 50	99.85 6	99.25 149

LS3D		97.16 137	96.66 149	98.68 88	98.53 177	97.19 109	98.93 105	98.90 66	92.83 302	95.99 235	99.37 50	92.12 135	99.87 71	93.67 268	99.57 92	98.97 192

AdaColmap		97.15 138	96.70 145	98.48 111	99.16 106	96.69 132	98.01 287	98.89 68	94.44 220	96.83 199	98.68 167	90.69 177	99.76 121	94.36 241	99.29 133	98.98 191

mamv4		97.13 139	98.11 69	94.17 377	98.97 131	83.70 420	98.66 191	98.71 129	94.63 208	97.83 151	98.90 136	96.25 29	99.55 170	99.27 24	99.76 42	99.27 144

Effi-MVS+		97.12 140	96.69 146	98.39 123	98.19 217	96.72 131	97.37 348	98.43 207	93.71 257	97.65 168	98.02 230	92.20 133	99.25 214	96.87 153	97.79 205	99.19 160

CHOSEN 1792x2688		97.12 140	96.80 137	98.08 151	99.30 74	94.56 248	98.05 282	99.71 1	93.57 269	97.09 185	98.91 135	88.17 241	99.89 60	96.87 153	99.56 99	99.81 20

F-COLMAP		97.09 142	96.80 137	97.97 158	99.45 56	94.95 227	98.55 213	98.62 156	93.02 294	96.17 230	98.58 177	94.01 101	99.81 94	93.95 258	98.90 151	99.14 169

RRT-MVS		97.03 143	96.78 140	97.77 175	97.90 251	94.34 257	99.12 59	98.35 222	95.87 137	98.06 129	98.70 165	86.45 279	99.63 150	98.04 83	98.54 174	99.35 128

TAMVS		97.02 144	96.79 139	97.70 182	98.06 232	95.31 206	98.52 215	98.31 229	93.95 240	97.05 190	98.61 172	93.49 107	98.52 308	95.33 207	97.81 204	99.29 141

CDS-MVSNet		96.99 145	96.69 146	97.90 162	98.05 234	95.98 165	98.20 258	98.33 226	93.67 264	96.95 192	98.49 186	93.54 106	98.42 319	95.24 214	97.74 208	99.31 136
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 146	96.55 152	98.21 136	98.17 222	96.07 164	97.98 291	98.21 247	97.24 67	97.13 184	98.93 132	86.88 271	99.91 49	95.00 220	99.37 127	98.66 229

114514_t		96.93 147	96.27 162	98.92 72	99.50 43	97.63 77	98.85 132	98.90 66	84.80 416	97.77 153	99.11 98	92.84 115	99.66 143	94.85 223	99.77 36	99.47 108

MAR-MVS		96.91 148	96.40 158	98.45 114	98.69 160	96.90 122	98.66 191	98.68 138	92.40 318	97.07 188	97.96 237	91.54 155	99.75 123	93.68 266	98.92 150	98.69 223
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		96.90 149	96.49 155	98.14 142	99.33 65	95.56 190	97.38 346	99.65 2	92.34 319	97.61 171	98.20 218	89.29 210	99.10 239	96.97 141	97.60 213	99.77 33

Vis-MVSNet (Re-imp)		96.87 150	96.55 152	97.83 167	98.73 152	95.46 196	99.20 43	98.30 236	94.96 191	96.60 211	98.87 141	90.05 187	98.59 303	93.67 268	98.60 169	99.46 113

SDMVSNet		96.85 151	96.42 156	98.14 142	99.30 74	96.38 150	99.21 40	99.23 24	95.92 133	95.96 237	98.76 161	85.88 289	99.44 193	97.93 87	95.59 272	98.60 234

PAPR		96.84 152	96.24 164	98.65 91	98.72 156	96.92 121	97.36 350	98.57 170	93.33 278	96.67 206	97.57 278	94.30 95	99.56 163	91.05 339	98.59 170	99.47 108

HY-MVS	93.96 8	96.82 153	96.23 165	98.57 96	98.46 183	97.00 117	98.14 270	98.21 247	93.95 240	96.72 205	97.99 234	91.58 151	99.76 121	94.51 237	96.54 244	98.95 195

UGNet		96.78 154	96.30 161	98.19 141	98.24 209	95.89 180	98.88 121	98.93 59	97.39 54	96.81 202	97.84 250	82.60 342	99.90 57	96.53 165	99.49 110	98.79 207
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
PVSNet_BlendedMVS		96.73 155	96.60 150	97.12 221	99.25 87	95.35 203	98.26 252	99.26 16	94.28 223	97.94 143	97.46 285	92.74 117	99.81 94	96.88 150	93.32 308	96.20 378

test_vis1_n_1920		96.71 156	96.84 136	96.31 292	99.11 113	89.74 371	99.05 70	98.58 168	98.08 20	99.87 2	99.37 50	78.48 374	99.93 31	99.29 23	99.69 65	99.27 144

mvs_anonymous		96.70 157	96.53 154	97.18 215	98.19 217	93.78 275	98.31 244	98.19 251	94.01 236	94.47 269	98.27 212	92.08 138	98.46 314	97.39 129	97.91 200	99.31 136

Elysia		96.64 158	96.02 172	98.51 105	98.04 236	97.30 96	98.74 165	98.60 157	95.04 183	97.91 147	98.84 144	83.59 337	99.48 186	94.20 249	99.25 134	98.75 216

StellarMVS		96.64 158	96.02 172	98.51 105	98.04 236	97.30 96	98.74 165	98.60 157	95.04 183	97.91 147	98.84 144	83.59 337	99.48 186	94.20 249	99.25 134	98.75 216

1112_ss		96.63 160	96.00 174	98.50 108	98.56 173	96.37 151	98.18 266	98.10 273	92.92 298	94.84 257	98.43 190	92.14 134	99.58 159	94.35 242	96.51 245	99.56 93

PMMVS		96.60 161	96.33 160	97.41 203	97.90 251	93.93 271	97.35 351	98.41 209	92.84 301	97.76 154	97.45 287	91.10 169	99.20 221	96.26 174	97.91 200	99.11 174

DP-MVS		96.59 162	95.93 177	98.57 96	99.34 63	96.19 160	98.70 180	98.39 213	89.45 388	94.52 267	99.35 56	91.85 144	99.85 76	92.89 292	98.88 153	99.68 68

PatchMatch-RL		96.59 162	96.03 171	98.27 129	99.31 70	96.51 143	97.91 300	99.06 42	93.72 256	96.92 196	98.06 227	88.50 236	99.65 144	91.77 321	99.00 148	98.66 229

GeoE		96.58 164	96.07 168	98.10 150	98.35 192	95.89 180	99.34 17	98.12 267	93.12 290	96.09 231	98.87 141	89.71 195	98.97 254	92.95 288	98.08 195	99.43 118

XVG-OURS		96.55 165	96.41 157	96.99 228	98.75 151	93.76 276	97.50 340	98.52 182	95.67 148	96.83 199	99.30 64	88.95 224	99.53 173	95.88 187	96.26 259	97.69 274

FIs		96.51 166	96.12 167	97.67 186	97.13 315	97.54 82	99.36 14	99.22 28	95.89 135	94.03 297	98.35 200	91.98 140	98.44 317	96.40 170	92.76 316	97.01 293

XVG-OURS-SEG-HR		96.51 166	96.34 159	97.02 227	98.77 150	93.76 276	97.79 319	98.50 190	95.45 157	96.94 193	99.09 107	87.87 252	99.55 170	96.76 161	95.83 271	97.74 271

PS-MVSNAJss		96.43 168	96.26 163	96.92 237	95.84 382	95.08 217	99.16 51	98.50 190	95.87 137	93.84 306	98.34 204	94.51 88	98.61 299	96.88 150	93.45 305	97.06 291

test_fmvs1		96.42 169	96.67 148	95.66 322	98.82 147	88.53 398	98.80 149	98.20 249	96.39 115	99.64 26	99.20 81	80.35 362	99.67 140	99.04 29	99.57 92	98.78 211

FC-MVSNet-test		96.42 169	96.05 169	97.53 197	96.95 324	97.27 100	99.36 14	99.23 24	95.83 139	93.93 300	98.37 198	92.00 139	98.32 338	96.02 183	92.72 317	97.00 294

ab-mvs		96.42 169	95.71 188	98.55 99	98.63 169	96.75 129	97.88 307	98.74 121	93.84 246	96.54 216	98.18 220	85.34 299	99.75 123	95.93 185	96.35 249	99.15 167

FA-MVS(test-final)		96.41 172	95.94 176	97.82 169	98.21 213	95.20 211	97.80 317	97.58 316	93.21 284	97.36 177	97.70 262	89.47 201	99.56 163	94.12 253	97.99 197	98.71 221

PVSNet	91.96 18	96.35 173	96.15 166	96.96 232	99.17 102	92.05 324	96.08 405	98.68 138	93.69 260	97.75 156	97.80 256	88.86 225	99.69 138	94.26 247	99.01 146	99.15 167

Test_1112_low_res		96.34 174	95.66 193	98.36 124	98.56 173	95.94 173	97.71 324	98.07 280	92.10 328	94.79 261	97.29 300	91.75 146	99.56 163	94.17 251	96.50 246	99.58 91

Effi-MVS+-dtu		96.29 175	96.56 151	95.51 327	97.89 253	90.22 364	98.80 149	98.10 273	96.57 107	96.45 221	96.66 357	90.81 173	98.91 267	95.72 194	97.99 197	97.40 282

QAPM		96.29 175	95.40 198	98.96 69	97.85 254	97.60 79	99.23 33	98.93 59	89.76 382	93.11 337	99.02 115	89.11 216	99.93 31	91.99 315	99.62 83	99.34 130

Fast-Effi-MVS+		96.28 177	95.70 190	98.03 154	98.29 206	95.97 170	98.58 204	98.25 244	91.74 336	95.29 250	97.23 305	91.03 171	99.15 227	92.90 290	97.96 199	98.97 192

nrg030		96.28 177	95.72 185	97.96 160	96.90 329	98.15 59	99.39 11	98.31 229	95.47 156	94.42 275	98.35 200	92.09 137	98.69 291	97.50 124	89.05 367	97.04 292

1314		96.25 179	95.73 184	97.79 171	97.13 315	95.55 192	98.19 261	98.59 163	93.47 273	92.03 366	97.82 254	91.33 160	99.49 181	94.62 232	98.44 180	98.32 254

sd_testset		96.17 180	95.76 183	97.42 202	99.30 74	94.34 257	98.82 140	99.08 40	95.92 133	95.96 237	98.76 161	82.83 341	99.32 206	95.56 200	95.59 272	98.60 234

h-mvs33		96.17 180	95.62 194	97.81 170	99.03 120	94.45 250	98.64 195	98.75 119	97.48 47	98.67 94	98.72 164	89.76 192	99.86 75	97.95 85	81.59 416	99.11 174

HQP_MVS		96.14 182	95.90 178	96.85 240	97.42 293	94.60 246	98.80 149	98.56 173	97.28 62	95.34 246	98.28 209	87.09 266	99.03 247	96.07 178	94.27 280	96.92 301

tttt0517		96.07 183	95.51 196	97.78 172	98.41 186	94.84 231	99.28 25	94.33 424	94.26 225	97.64 169	98.64 171	84.05 328	99.47 190	95.34 206	97.60 213	99.03 186

MVSTER		96.06 184	95.72 185	97.08 224	98.23 211	95.93 176	98.73 171	98.27 239	94.86 197	95.07 252	98.09 225	88.21 240	98.54 306	96.59 163	93.46 303	96.79 320

thisisatest0530		96.01 185	95.36 203	97.97 158	98.38 188	95.52 194	98.88 121	94.19 426	94.04 231	97.64 169	98.31 207	83.82 335	99.46 191	95.29 211	97.70 210	98.93 197

test_djsdf		96.00 186	95.69 191	96.93 234	95.72 384	95.49 195	99.47 7	98.40 211	94.98 189	94.58 265	97.86 247	89.16 214	98.41 326	96.91 144	94.12 288	96.88 310

EI-MVSNet		95.96 187	95.83 180	96.36 288	97.93 249	93.70 282	98.12 273	98.27 239	93.70 259	95.07 252	99.02 115	92.23 131	98.54 306	94.68 228	93.46 303	96.84 316

VortexMVS		95.95 188	95.79 181	96.42 284	98.29 206	93.96 270	98.68 184	98.31 229	96.02 130	94.29 282	97.57 278	89.47 201	98.37 333	97.51 123	91.93 324	96.94 299

ECVR-MVS		95.95 188	95.71 188	96.65 252	99.02 121	90.86 346	99.03 77	91.80 437	96.96 85	98.10 126	99.26 70	81.31 348	99.51 177	96.90 147	99.04 143	99.59 87

BH-untuned		95.95 188	95.72 185	96.65 252	98.55 175	92.26 318	98.23 254	97.79 301	93.73 254	94.62 264	98.01 232	88.97 223	99.00 253	93.04 285	98.51 176	98.68 225

test1111		95.94 191	95.78 182	96.41 285	98.99 128	90.12 365	99.04 74	92.45 436	96.99 84	98.03 133	99.27 69	81.40 347	99.48 186	96.87 153	99.04 143	99.63 81

MSDG		95.93 192	95.30 210	97.83 167	98.90 136	95.36 201	96.83 392	98.37 219	91.32 351	94.43 274	98.73 163	90.27 185	99.60 156	90.05 353	98.82 160	98.52 242

BH-RMVSNet		95.92 193	95.32 208	97.69 183	98.32 203	94.64 240	98.19 261	97.45 337	94.56 212	96.03 233	98.61 172	85.02 304	99.12 233	90.68 344	99.06 142	99.30 139

test_fmvs1_n		95.90 194	95.99 175	95.63 323	98.67 163	88.32 402	99.26 28	98.22 246	96.40 114	99.67 23	99.26 70	73.91 411	99.70 133	99.02 30	99.50 108	98.87 201

Fast-Effi-MVS+-dtu		95.87 195	95.85 179	95.91 309	97.74 263	91.74 330	98.69 182	98.15 263	95.56 152	94.92 255	97.68 267	88.98 222	98.79 285	93.19 280	97.78 206	97.20 289

LFMVS		95.86 196	94.98 225	98.47 112	98.87 141	96.32 154	98.84 136	96.02 403	93.40 276	98.62 100	99.20 81	74.99 405	99.63 150	97.72 101	97.20 221	99.46 113

baseline1		95.84 197	95.12 218	98.01 156	98.49 182	95.98 165	98.73 171	97.03 370	95.37 164	96.22 226	98.19 219	89.96 189	99.16 224	94.60 233	87.48 383	98.90 200

OpenMVS	93.04 13	95.83 198	95.00 223	98.32 126	97.18 312	97.32 93	99.21 40	98.97 51	89.96 378	91.14 375	99.05 113	86.64 274	99.92 39	93.38 274	99.47 113	97.73 272

VDD-MVS		95.82 199	95.23 212	97.61 193	98.84 146	93.98 269	98.68 184	97.40 341	95.02 187	97.95 141	99.34 60	74.37 410	99.78 115	98.64 44	96.80 234	99.08 180

UniMVSNet (Re)		95.78 200	95.19 214	97.58 194	96.99 322	97.47 86	98.79 157	99.18 32	95.60 150	93.92 301	97.04 327	91.68 148	98.48 310	95.80 191	87.66 382	96.79 320

VPA-MVSNet		95.75 201	95.11 219	97.69 183	97.24 304	97.27 100	98.94 100	99.23 24	95.13 176	95.51 244	97.32 298	85.73 291	98.91 267	97.33 132	89.55 358	96.89 309

HQP-MVS		95.72 202	95.40 198	96.69 250	97.20 308	94.25 262	98.05 282	98.46 198	96.43 111	94.45 270	97.73 259	86.75 272	98.96 258	95.30 209	94.18 284	96.86 315

hse-mvs2		95.71 203	95.30 210	96.93 234	98.50 178	93.53 287	98.36 236	98.10 273	97.48 47	98.67 94	97.99 234	89.76 192	99.02 250	97.95 85	80.91 421	98.22 257

UniMVSNet_NR-MVSNet		95.71 203	95.15 215	97.40 205	96.84 332	96.97 118	98.74 165	99.24 19	95.16 175	93.88 303	97.72 261	91.68 148	98.31 340	95.81 189	87.25 388	96.92 301

PatchmatchNet		95.71 203	95.52 195	96.29 294	97.58 276	90.72 350	96.84 391	97.52 327	94.06 230	97.08 186	96.96 337	89.24 212	98.90 270	92.03 314	98.37 184	99.26 147
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 206	95.33 207	96.76 245	96.16 368	94.63 241	98.43 231	98.39 213	96.64 103	95.02 254	98.78 153	85.15 303	99.05 243	95.21 216	94.20 283	96.60 343
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 206	95.38 202	96.61 260	97.61 273	93.84 274	98.91 109	98.44 202	95.25 171	94.28 283	98.47 188	86.04 288	99.12 233	95.50 203	93.95 293	96.87 313
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 208	95.69 191	95.44 331	97.54 281	88.54 397	96.97 377	97.56 319	93.50 271	97.52 175	96.93 341	89.49 199	99.16 224	95.25 213	96.42 248	98.64 231

FE-MVS		95.62 209	94.90 229	97.78 172	98.37 190	94.92 228	97.17 367	97.38 343	90.95 362	97.73 159	97.70 262	85.32 301	99.63 150	91.18 331	98.33 187	98.79 207

LPG-MVS_test		95.62 209	95.34 204	96.47 278	97.46 288	93.54 285	98.99 87	98.54 177	94.67 206	94.36 278	98.77 156	85.39 296	99.11 235	95.71 195	94.15 286	96.76 323

CLD-MVS		95.62 209	95.34 204	96.46 281	97.52 284	93.75 278	97.27 358	98.46 198	95.53 153	94.42 275	98.00 233	86.21 283	98.97 254	96.25 176	94.37 278	96.66 338
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 212	94.89 230	97.76 176	98.15 224	95.15 214	96.77 393	94.41 422	92.95 297	97.18 183	97.43 289	84.78 310	99.45 192	94.63 230	97.73 209	98.68 225

MonoMVSNet		95.51 213	95.45 197	95.68 320	95.54 389	90.87 345	98.92 107	97.37 344	95.79 141	95.53 243	97.38 294	89.58 198	97.68 384	96.40 170	92.59 318	98.49 244

thres600view7		95.49 214	94.77 233	97.67 186	98.98 129	95.02 219	98.85 132	96.90 380	95.38 162	96.63 208	96.90 343	84.29 320	99.59 157	88.65 377	96.33 250	98.40 248

test_vis1_n		95.47 215	95.13 216	96.49 275	97.77 259	90.41 360	99.27 27	98.11 270	96.58 105	99.66 24	99.18 87	67.00 425	99.62 154	99.21 25	99.40 123	99.44 116

SCA		95.46 216	95.13 216	96.46 281	97.67 268	91.29 338	97.33 353	97.60 315	94.68 205	96.92 196	97.10 312	83.97 330	98.89 271	92.59 298	98.32 189	99.20 156

IterMVS-LS		95.46 216	95.21 213	96.22 296	98.12 226	93.72 281	98.32 243	98.13 266	93.71 257	94.26 284	97.31 299	92.24 130	98.10 356	94.63 230	90.12 349	96.84 316
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 218	95.34 204	95.77 318	98.69 160	88.75 393	98.87 124	97.21 357	96.13 125	97.22 181	97.68 267	77.95 382	99.65 144	97.58 114	96.77 237	98.91 199

jajsoiax		95.45 218	95.03 222	96.73 246	95.42 397	94.63 241	99.14 55	98.52 182	95.74 143	93.22 330	98.36 199	83.87 333	98.65 296	96.95 143	94.04 289	96.91 306

CVMVSNet		95.43 220	96.04 170	93.57 383	97.93 249	83.62 421	98.12 273	98.59 163	95.68 147	96.56 212	99.02 115	87.51 258	97.51 393	93.56 272	97.44 217	99.60 85

anonymousdsp		95.42 221	94.91 228	96.94 233	95.10 401	95.90 179	99.14 55	98.41 209	93.75 251	93.16 333	97.46 285	87.50 260	98.41 326	95.63 199	94.03 290	96.50 362

DU-MVS		95.42 221	94.76 234	97.40 205	96.53 349	96.97 118	98.66 191	98.99 50	95.43 158	93.88 303	97.69 264	88.57 231	98.31 340	95.81 189	87.25 388	96.92 301

mvs_tets		95.41 223	95.00 223	96.65 252	95.58 388	94.42 252	99.00 84	98.55 175	95.73 145	93.21 331	98.38 197	83.45 339	98.63 297	97.09 137	94.00 291	96.91 306

thres100view900		95.38 224	94.70 238	97.41 203	98.98 129	94.92 228	98.87 124	96.90 380	95.38 162	96.61 210	96.88 344	84.29 320	99.56 163	88.11 380	96.29 254	97.76 269

thres400		95.38 224	94.62 242	97.65 190	98.94 134	94.98 224	98.68 184	96.93 378	95.33 165	96.55 214	96.53 363	84.23 324	99.56 163	88.11 380	96.29 254	98.40 248

BH-w/o		95.38 224	95.08 220	96.26 295	98.34 197	91.79 327	97.70 325	97.43 339	92.87 300	94.24 286	97.22 306	88.66 229	98.84 277	91.55 327	97.70 210	98.16 260

VDDNet		95.36 227	94.53 247	97.86 165	98.10 228	95.13 215	98.85 132	97.75 303	90.46 369	98.36 116	99.39 44	73.27 413	99.64 147	97.98 84	96.58 242	98.81 206

TAPA-MVS	93.98 7	95.35 228	94.56 246	97.74 178	99.13 110	94.83 233	98.33 239	98.64 151	86.62 404	96.29 225	98.61 172	94.00 102	99.29 211	80.00 422	99.41 120	99.09 176
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 229	94.98 225	96.43 283	97.67 268	93.48 289	98.73 171	98.44 202	94.94 195	92.53 353	98.53 182	84.50 319	99.14 229	95.48 204	94.00 291	96.66 338
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 230	94.87 231	96.71 247	99.29 79	93.24 303	98.58 204	98.11 270	89.92 379	93.57 315	99.10 100	86.37 281	99.79 112	90.78 342	98.10 194	97.09 290
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 231	94.72 237	97.13 219	98.05 234	93.26 300	97.87 308	97.20 358	94.96 191	96.18 229	95.66 396	80.97 354	99.35 202	94.47 239	97.08 224	98.78 211

tfpn200view9		95.32 231	94.62 242	97.43 201	98.94 134	94.98 224	98.68 184	96.93 378	95.33 165	96.55 214	96.53 363	84.23 324	99.56 163	88.11 380	96.29 254	97.76 269

Anonymous202405211		95.28 233	94.49 249	97.67 186	99.00 125	93.75 278	98.70 180	97.04 369	90.66 365	96.49 218	98.80 151	78.13 378	99.83 82	96.21 177	95.36 276	99.44 116

thres200		95.25 234	94.57 245	97.28 209	98.81 148	94.92 228	98.20 258	97.11 362	95.24 173	96.54 216	96.22 374	84.58 317	99.53 173	87.93 385	96.50 246	97.39 283

AllTest		95.24 235	94.65 241	96.99 228	99.25 87	93.21 304	98.59 202	98.18 254	91.36 347	93.52 317	98.77 156	84.67 314	99.72 127	89.70 360	97.87 202	98.02 264

LCM-MVSNet-Re		95.22 236	95.32 208	94.91 348	98.18 219	87.85 408	98.75 161	95.66 410	95.11 178	88.96 395	96.85 347	90.26 186	97.65 385	95.65 198	98.44 180	99.22 153

EPNet_dtu		95.21 237	94.95 227	95.99 304	96.17 366	90.45 358	98.16 268	97.27 352	96.77 93	93.14 336	98.33 205	90.34 182	98.42 319	85.57 398	98.81 161	99.09 176
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 238	94.45 254	97.46 198	96.75 339	96.56 141	98.86 128	98.65 150	93.30 281	93.27 329	98.27 212	84.85 308	98.87 274	94.82 225	91.26 335	96.96 296

D2MVS		95.18 239	95.08 220	95.48 328	97.10 317	92.07 323	98.30 246	99.13 38	94.02 233	92.90 341	96.73 353	89.48 200	98.73 289	94.48 238	93.60 302	95.65 392

WR-MVS		95.15 240	94.46 252	97.22 211	96.67 344	96.45 145	98.21 256	98.81 99	94.15 227	93.16 333	97.69 264	87.51 258	98.30 342	95.29 211	88.62 373	96.90 308

TranMVSNet+NR-MVSNet		95.14 241	94.48 250	97.11 222	96.45 355	96.36 152	99.03 77	99.03 45	95.04 183	93.58 314	97.93 240	88.27 239	98.03 362	94.13 252	86.90 393	96.95 298

myMVS_eth3d28		95.12 242	94.62 242	96.64 256	98.17 222	92.17 319	98.02 286	97.32 346	95.41 160	96.22 226	96.05 380	78.01 380	99.13 230	95.22 215	97.16 222	98.60 234

baseline2		95.11 243	94.52 248	96.87 239	96.65 345	93.56 284	98.27 251	94.10 428	93.45 274	92.02 367	97.43 289	87.45 263	99.19 222	93.88 261	97.41 219	97.87 267

miper_enhance_ethall		95.10 244	94.75 235	96.12 300	97.53 283	93.73 280	96.61 399	98.08 278	92.20 327	93.89 302	96.65 359	92.44 121	98.30 342	94.21 248	91.16 336	96.34 371

Anonymous20240529		95.10 244	94.22 264	97.75 177	99.01 123	94.26 261	98.87 124	98.83 90	85.79 412	96.64 207	98.97 123	78.73 371	99.85 76	96.27 173	94.89 277	99.12 171

test-LLR		95.10 244	94.87 231	95.80 315	96.77 336	89.70 373	96.91 382	95.21 414	95.11 178	94.83 259	95.72 393	87.71 254	98.97 254	93.06 283	98.50 177	98.72 218

WR-MVS_H		95.05 247	94.46 252	96.81 243	96.86 331	95.82 183	99.24 31	99.24 19	93.87 245	92.53 353	96.84 348	90.37 181	98.24 348	93.24 278	87.93 379	96.38 370

miper_ehance_all_eth		95.01 248	94.69 239	95.97 306	97.70 266	93.31 298	97.02 375	98.07 280	92.23 324	93.51 319	96.96 337	91.85 144	98.15 352	93.68 266	91.16 336	96.44 368

testing11		95.00 249	94.28 261	97.16 217	97.96 246	93.36 297	98.09 278	97.06 368	94.94 195	95.33 249	96.15 376	76.89 395	99.40 197	95.77 193	96.30 253	98.72 218

ADS-MVSNet		95.00 249	94.45 254	96.63 257	98.00 240	91.91 326	96.04 406	97.74 304	90.15 375	96.47 219	96.64 360	87.89 250	98.96 258	90.08 351	97.06 225	99.02 187

VPNet		94.99 251	94.19 266	97.40 205	97.16 313	96.57 140	98.71 176	98.97 51	95.67 148	94.84 257	98.24 216	80.36 361	98.67 295	96.46 167	87.32 387	96.96 296

EPMVS		94.99 251	94.48 250	96.52 273	97.22 306	91.75 329	97.23 359	91.66 438	94.11 228	97.28 178	96.81 350	85.70 292	98.84 277	93.04 285	97.28 220	98.97 192

testing91		94.98 253	94.25 263	97.20 212	97.94 247	93.41 292	98.00 289	97.58 316	94.99 188	95.45 245	96.04 381	77.20 390	99.42 195	94.97 221	96.02 267	98.78 211

NR-MVSNet		94.98 253	94.16 269	97.44 200	96.53 349	97.22 108	98.74 165	98.95 55	94.96 191	89.25 394	97.69 264	89.32 209	98.18 350	94.59 235	87.40 385	96.92 301

FMVSNet3		94.97 255	94.26 262	97.11 222	98.18 219	96.62 133	98.56 212	98.26 243	93.67 264	94.09 293	97.10 312	84.25 322	98.01 363	92.08 310	92.14 321	96.70 332

CostFormer		94.95 256	94.73 236	95.60 325	97.28 302	89.06 386	97.53 337	96.89 382	89.66 384	96.82 201	96.72 354	86.05 286	98.95 263	95.53 202	96.13 265	98.79 207

PAPM		94.95 256	94.00 282	97.78 172	97.04 319	95.65 187	96.03 408	98.25 244	91.23 356	94.19 289	97.80 256	91.27 163	98.86 276	82.61 415	97.61 212	98.84 204

CP-MVSNet		94.94 258	94.30 260	96.83 241	96.72 341	95.56 190	99.11 61	98.95 55	93.89 243	92.42 358	97.90 243	87.19 265	98.12 355	94.32 244	88.21 376	96.82 319

TR-MVS		94.94 258	94.20 265	97.17 216	97.75 260	94.14 266	97.59 334	97.02 373	92.28 323	95.75 241	97.64 272	83.88 332	98.96 258	89.77 357	96.15 264	98.40 248

RPSCF		94.87 260	95.40 198	93.26 389	98.89 137	82.06 427	98.33 239	98.06 285	90.30 374	96.56 212	99.26 70	87.09 266	99.49 181	93.82 263	96.32 251	98.24 255

testing99		94.83 261	94.08 274	97.07 225	97.94 247	93.13 306	98.10 277	97.17 360	94.86 197	95.34 246	96.00 385	76.31 398	99.40 197	95.08 218	95.90 268	98.68 225

GA-MVS		94.81 262	94.03 278	97.14 218	97.15 314	93.86 273	96.76 394	97.58 316	94.00 237	94.76 263	97.04 327	80.91 355	98.48 310	91.79 320	96.25 260	99.09 176

c3_l		94.79 263	94.43 256	95.89 311	97.75 260	93.12 308	97.16 369	98.03 287	92.23 324	93.46 323	97.05 326	91.39 157	98.01 363	93.58 271	89.21 365	96.53 354

V42		94.78 264	94.14 271	96.70 249	96.33 360	95.22 210	98.97 91	98.09 277	92.32 321	94.31 281	97.06 323	88.39 237	98.55 305	92.90 290	88.87 371	96.34 371

reproduce_monomvs		94.77 265	94.67 240	95.08 343	98.40 187	89.48 379	98.80 149	98.64 151	97.57 41	93.21 331	97.65 269	80.57 360	98.83 280	97.72 101	89.47 361	96.93 300

CR-MVSNet		94.76 266	94.15 270	96.59 263	97.00 320	93.43 290	94.96 419	97.56 319	92.46 312	96.93 194	96.24 370	88.15 242	97.88 376	87.38 387	96.65 240	98.46 246

v2v482		94.69 267	94.03 278	96.65 252	96.17 366	94.79 236	98.67 189	98.08 278	92.72 304	94.00 298	97.16 309	87.69 257	98.45 315	92.91 289	88.87 371	96.72 328

pmmvs4		94.69 267	93.99 284	96.81 243	95.74 383	95.94 173	97.40 344	97.67 308	90.42 371	93.37 326	97.59 276	89.08 217	98.20 349	92.97 287	91.67 329	96.30 374

cl22		94.68 269	94.19 266	96.13 299	98.11 227	93.60 283	96.94 379	98.31 229	92.43 316	93.32 328	96.87 346	86.51 275	98.28 346	94.10 255	91.16 336	96.51 360

eth_miper_zixun_eth		94.68 269	94.41 257	95.47 329	97.64 271	91.71 331	96.73 396	98.07 280	92.71 305	93.64 312	97.21 307	90.54 179	98.17 351	93.38 274	89.76 353	96.54 352

PCF-MVS	93.45 11	94.68 269	93.43 320	98.42 120	98.62 170	96.77 128	95.48 416	98.20 249	84.63 417	93.34 327	98.32 206	88.55 234	99.81 94	84.80 407	98.96 149	98.68 225
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 272	93.54 315	98.08 151	96.88 330	96.56 141	98.19 261	98.50 190	78.05 429	92.69 348	98.02 230	91.07 170	99.63 150	90.09 350	98.36 186	98.04 263

PS-CasMVS		94.67 272	93.99 284	96.71 247	96.68 343	95.26 207	99.13 58	99.03 45	93.68 262	92.33 359	97.95 238	85.35 298	98.10 356	93.59 270	88.16 378	96.79 320

cascas		94.63 274	93.86 294	96.93 234	96.91 328	94.27 260	96.00 409	98.51 185	85.55 413	94.54 266	96.23 372	84.20 326	98.87 274	95.80 191	96.98 230	97.66 275

tpmvs		94.60 275	94.36 259	95.33 335	97.46 288	88.60 396	96.88 388	97.68 305	91.29 353	93.80 308	96.42 367	88.58 230	99.24 216	91.06 337	96.04 266	98.17 259

LTVRE_ROB	92.95 15	94.60 275	93.90 290	96.68 251	97.41 296	94.42 252	98.52 215	98.59 163	91.69 339	91.21 374	98.35 200	84.87 307	99.04 246	91.06 337	93.44 306	96.60 343
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		94.59 277	93.92 287	96.60 262	96.21 362	94.78 237	98.59 202	98.14 265	91.86 335	94.21 288	97.02 330	87.97 248	98.41 326	91.72 322	89.57 356	96.61 342

ADS-MVSNet2		94.58 278	94.40 258	95.11 341	98.00 240	88.74 394	96.04 406	97.30 348	90.15 375	96.47 219	96.64 360	87.89 250	97.56 391	90.08 351	97.06 225	99.02 187

WBMVS		94.56 279	94.04 276	96.10 301	98.03 238	93.08 310	97.82 316	98.18 254	94.02 233	93.77 310	96.82 349	81.28 349	98.34 335	95.47 205	91.00 339	96.88 310

ACMH	92.88 16	94.55 280	93.95 286	96.34 290	97.63 272	93.26 300	98.81 148	98.49 195	93.43 275	89.74 388	98.53 182	81.91 344	99.08 241	93.69 265	93.30 309	96.70 332
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 281	93.85 295	96.63 257	97.98 244	93.06 311	98.77 160	97.84 299	93.67 264	93.80 308	98.04 229	76.88 396	98.96 258	94.79 227	92.86 314	97.86 268

XVG-ACMP-BASELINE		94.54 281	94.14 271	95.75 319	96.55 348	91.65 332	98.11 275	98.44 202	94.96 191	94.22 287	97.90 243	79.18 370	99.11 235	94.05 257	93.85 295	96.48 365

AUN-MVS		94.53 283	93.73 305	96.92 237	98.50 178	93.52 288	98.34 238	98.10 273	93.83 248	95.94 239	97.98 236	85.59 294	99.03 247	94.35 242	80.94 420	98.22 257

DIV-MVS_self_test		94.52 284	94.03 278	95.99 304	97.57 280	93.38 295	97.05 373	97.94 293	91.74 336	92.81 343	97.10 312	89.12 215	98.07 360	92.60 296	90.30 346	96.53 354

cl____		94.51 285	94.01 281	96.02 303	97.58 276	93.40 294	97.05 373	97.96 292	91.73 338	92.76 345	97.08 318	89.06 218	98.13 354	92.61 295	90.29 347	96.52 357

ETVMVS		94.50 286	93.44 319	97.68 185	98.18 219	95.35 203	98.19 261	97.11 362	93.73 254	96.40 222	95.39 399	74.53 407	98.84 277	91.10 333	96.31 252	98.84 204

GBi-Net		94.49 287	93.80 298	96.56 267	98.21 213	95.00 220	98.82 140	98.18 254	92.46 312	94.09 293	97.07 319	81.16 350	97.95 368	92.08 310	92.14 321	96.72 328

test1		94.49 287	93.80 298	96.56 267	98.21 213	95.00 220	98.82 140	98.18 254	92.46 312	94.09 293	97.07 319	81.16 350	97.95 368	92.08 310	92.14 321	96.72 328

dmvs_re		94.48 289	94.18 268	95.37 333	97.68 267	90.11 366	98.54 214	97.08 364	94.56 212	94.42 275	97.24 304	84.25 322	97.76 382	91.02 340	92.83 315	98.24 255

v8		94.47 290	93.77 301	96.57 266	96.36 358	94.83 233	99.05 70	98.19 251	91.92 332	93.16 333	96.97 335	88.82 228	98.48 310	91.69 323	87.79 380	96.39 369

FMVSNet2		94.47 290	93.61 311	97.04 226	98.21 213	96.43 147	98.79 157	98.27 239	92.46 312	93.50 320	97.09 316	81.16 350	98.00 365	91.09 334	91.93 324	96.70 332

test2506		94.44 292	93.91 289	96.04 302	99.02 121	88.99 389	99.06 68	79.47 450	96.96 85	98.36 116	99.26 70	77.21 389	99.52 176	96.78 160	99.04 143	99.59 87

Patchmatch-test		94.42 293	93.68 309	96.63 257	97.60 274	91.76 328	94.83 423	97.49 331	89.45 388	94.14 291	97.10 312	88.99 219	98.83 280	85.37 401	98.13 193	99.29 141

PEN-MVS		94.42 293	93.73 305	96.49 275	96.28 361	94.84 231	99.17 50	99.00 47	93.51 270	92.23 361	97.83 253	86.10 285	97.90 372	92.55 301	86.92 392	96.74 325

v144192		94.39 295	93.70 307	96.48 277	96.06 372	94.35 256	98.58 204	98.16 262	91.45 344	94.33 280	97.02 330	87.50 260	98.45 315	91.08 336	89.11 366	96.63 340

Baseline_NR-MVSNet		94.35 296	93.81 297	95.96 307	96.20 363	94.05 268	98.61 201	96.67 392	91.44 345	93.85 305	97.60 275	88.57 231	98.14 353	94.39 240	86.93 391	95.68 391

miper_lstm_enhance		94.33 297	94.07 275	95.11 341	97.75 260	90.97 342	97.22 360	98.03 287	91.67 340	92.76 345	96.97 335	90.03 188	97.78 381	92.51 303	89.64 355	96.56 349

v1192		94.32 298	93.58 312	96.53 272	96.10 370	94.45 250	98.50 221	98.17 260	91.54 342	94.19 289	97.06 323	86.95 270	98.43 318	90.14 349	89.57 356	96.70 332

UWE-MVS		94.30 299	93.89 292	95.53 326	97.83 255	88.95 390	97.52 339	93.25 430	94.44 220	96.63 208	97.07 319	78.70 372	99.28 212	91.99 315	97.56 215	98.36 251

ACMH+	92.99 14	94.30 299	93.77 301	95.88 312	97.81 257	92.04 325	98.71 176	98.37 219	93.99 238	90.60 381	98.47 188	80.86 357	99.05 243	92.75 294	92.40 320	96.55 351

v148		94.29 301	93.76 303	95.91 309	96.10 370	92.93 312	98.58 204	97.97 290	92.59 310	93.47 322	96.95 339	88.53 235	98.32 338	92.56 300	87.06 390	96.49 363

v10		94.29 301	93.55 314	96.51 274	96.39 357	94.80 235	98.99 87	98.19 251	91.35 349	93.02 339	96.99 333	88.09 244	98.41 326	90.50 346	88.41 375	96.33 373

MVP-Stereo		94.28 303	93.92 287	95.35 334	94.95 403	92.60 315	97.97 292	97.65 309	91.61 341	90.68 380	97.09 316	86.32 282	98.42 319	89.70 360	99.34 129	95.02 405
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 304	93.33 322	96.97 231	97.19 311	93.38 295	98.74 165	98.57 170	91.21 358	93.81 307	98.58 177	72.85 414	98.77 287	95.05 219	93.93 294	98.77 214

OurMVSNet-221017-0		94.21 305	94.00 282	94.85 353	95.60 387	89.22 384	98.89 114	97.43 339	95.29 168	92.18 363	98.52 185	82.86 340	98.59 303	93.46 273	91.76 327	96.74 325

v1921920		94.20 306	93.47 318	96.40 287	95.98 376	94.08 267	98.52 215	98.15 263	91.33 350	94.25 285	97.20 308	86.41 280	98.42 319	90.04 354	89.39 363	96.69 337

WB-MVSnew		94.19 307	94.04 276	94.66 361	96.82 334	92.14 320	97.86 310	95.96 406	93.50 271	95.64 242	96.77 352	88.06 246	97.99 366	84.87 404	96.86 231	93.85 422

v7n		94.19 307	93.43 320	96.47 278	95.90 379	94.38 255	99.26 28	98.34 225	91.99 330	92.76 345	97.13 311	88.31 238	98.52 308	89.48 365	87.70 381	96.52 357

tpm2		94.19 307	93.76 303	95.46 330	97.23 305	89.04 387	97.31 355	96.85 386	87.08 403	96.21 228	96.79 351	83.75 336	98.74 288	92.43 306	96.23 262	98.59 237

TESTMET0.1,1		94.18 310	93.69 308	95.63 323	96.92 326	89.12 385	96.91 382	94.78 419	93.17 286	94.88 256	96.45 366	78.52 373	98.92 265	93.09 282	98.50 177	98.85 202

dp		94.15 311	93.90 290	94.90 349	97.31 301	86.82 413	96.97 377	97.19 359	91.22 357	96.02 234	96.61 362	85.51 295	99.02 250	90.00 355	94.30 279	98.85 202

ET-MVSNet_ETH3D		94.13 312	92.98 330	97.58 194	98.22 212	96.20 158	97.31 355	95.37 413	94.53 214	79.56 431	97.63 274	86.51 275	97.53 392	96.91 144	90.74 341	99.02 187

tpm		94.13 312	93.80 298	95.12 340	96.50 351	87.91 407	97.44 341	95.89 409	92.62 308	96.37 224	96.30 369	84.13 327	98.30 342	93.24 278	91.66 330	99.14 169

testing222		94.12 314	93.03 329	97.37 208	98.02 239	94.66 238	97.94 296	96.65 394	94.63 208	95.78 240	95.76 388	71.49 415	98.92 265	91.17 332	95.88 269	98.52 242

IterMVS-SCA-FT		94.11 315	93.87 293	94.85 353	97.98 244	90.56 357	97.18 365	98.11 270	93.75 251	92.58 351	97.48 284	83.97 330	97.41 395	92.48 305	91.30 333	96.58 345

Anonymous20231211		94.10 316	93.26 325	96.61 260	99.11 113	94.28 259	99.01 82	98.88 71	86.43 406	92.81 343	97.57 278	81.66 346	98.68 294	94.83 224	89.02 369	96.88 310

IterMVS		94.09 317	93.85 295	94.80 357	97.99 242	90.35 362	97.18 365	98.12 267	93.68 262	92.46 357	97.34 295	84.05 328	97.41 395	92.51 303	91.33 332	96.62 341
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 318	93.51 316	95.80 315	96.77 336	89.70 373	96.91 382	95.21 414	92.89 299	94.83 259	95.72 393	77.69 384	98.97 254	93.06 283	98.50 177	98.72 218

test0.0.03 1		94.08 318	93.51 316	95.80 315	95.53 391	92.89 313	97.38 346	95.97 405	95.11 178	92.51 355	96.66 357	87.71 254	96.94 402	87.03 389	93.67 298	97.57 279

v1240		94.06 320	93.29 324	96.34 290	96.03 374	93.90 272	98.44 229	98.17 260	91.18 359	94.13 292	97.01 332	86.05 286	98.42 319	89.13 371	89.50 360	96.70 332

X-MVStestdata		94.06 320	92.30 346	99.34 27	99.70 23	98.35 45	99.29 23	98.88 71	97.40 52	98.46 108	43.50 445	95.90 45	99.89 60	97.85 93	99.74 52	99.78 26

DTE-MVSNet		93.98 322	93.26 325	96.14 298	96.06 372	94.39 254	99.20 43	98.86 84	93.06 292	91.78 368	97.81 255	85.87 290	97.58 390	90.53 345	86.17 397	96.46 367

pm-mvs1		93.94 323	93.06 328	96.59 263	96.49 352	95.16 212	98.95 97	98.03 287	92.32 321	91.08 376	97.84 250	84.54 318	98.41 326	92.16 308	86.13 400	96.19 379

MS-PatchMatch		93.84 324	93.63 310	94.46 371	96.18 365	89.45 380	97.76 320	98.27 239	92.23 324	92.13 364	97.49 283	79.50 367	98.69 291	89.75 358	99.38 125	95.25 397

tfpnnormal		93.66 325	92.70 336	96.55 271	96.94 325	95.94 173	98.97 91	99.19 31	91.04 360	91.38 373	97.34 295	84.94 306	98.61 299	85.45 400	89.02 369	95.11 401

EU-MVSNet		93.66 325	94.14 271	92.25 399	95.96 378	83.38 423	98.52 215	98.12 267	94.69 204	92.61 350	98.13 223	87.36 264	96.39 415	91.82 319	90.00 351	96.98 295

our_test_3		93.65 327	93.30 323	94.69 359	95.45 395	89.68 375	96.91 382	97.65 309	91.97 331	91.66 371	96.88 344	89.67 196	97.93 371	88.02 383	91.49 331	96.48 365

pmmvs5		93.65 327	92.97 331	95.68 320	95.49 392	92.37 316	98.20 258	97.28 351	89.66 384	92.58 351	97.26 301	82.14 343	98.09 358	93.18 281	90.95 340	96.58 345

SSC-MVS3.2		93.59 329	93.13 327	94.97 346	96.81 335	89.71 372	97.95 293	98.49 195	94.59 211	93.50 320	96.91 342	77.74 383	98.37 333	91.69 323	90.47 344	96.83 318

test_fmvs2		93.43 330	93.58 312	92.95 393	96.97 323	83.91 419	99.19 45	97.24 354	95.74 143	95.20 251	98.27 212	69.65 417	98.72 290	96.26 174	93.73 297	96.24 376

tpm cat1		93.36 331	92.80 333	95.07 344	97.58 276	87.97 406	96.76 394	97.86 298	82.17 424	93.53 316	96.04 381	86.13 284	99.13 230	89.24 369	95.87 270	98.10 262

JIA-IIPM		93.35 332	92.49 342	95.92 308	96.48 353	90.65 352	95.01 418	96.96 376	85.93 410	96.08 232	87.33 435	87.70 256	98.78 286	91.35 329	95.58 274	98.34 252

SixPastTwentyTwo		93.34 333	92.86 332	94.75 358	95.67 385	89.41 382	98.75 161	96.67 392	93.89 243	90.15 386	98.25 215	80.87 356	98.27 347	90.90 341	90.64 342	96.57 347

USDC		93.33 334	92.71 335	95.21 337	96.83 333	90.83 348	96.91 382	97.50 329	93.84 246	90.72 379	98.14 222	77.69 384	98.82 282	89.51 364	93.21 311	95.97 385

IB-MVS	91.98 17	93.27 335	91.97 350	97.19 214	97.47 287	93.41 292	97.09 372	95.99 404	93.32 279	92.47 356	95.73 391	78.06 379	99.53 173	94.59 235	82.98 411	98.62 232
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		93.26 336	92.21 347	96.41 285	97.73 264	93.13 306	95.65 413	97.03 370	91.27 355	94.04 296	96.06 379	75.33 403	97.19 398	86.56 391	96.23 262	98.92 198

ppachtmachnet_test		93.22 337	92.63 337	94.97 346	95.45 395	90.84 347	96.88 388	97.88 297	90.60 366	92.08 365	97.26 301	88.08 245	97.86 377	85.12 403	90.33 345	96.22 377

Patchmtry		93.22 337	92.35 345	95.84 314	96.77 336	93.09 309	94.66 426	97.56 319	87.37 402	92.90 341	96.24 370	88.15 242	97.90 372	87.37 388	90.10 350	96.53 354

testing3		93.19 339	92.48 343	95.30 336	98.07 229	92.27 317	98.64 195	97.17 360	93.94 242	93.98 299	97.04 327	67.97 422	96.01 419	88.40 378	97.14 223	97.63 276

FMVSNet1		93.19 339	92.07 348	96.56 267	97.54 281	95.00 220	98.82 140	98.18 254	90.38 372	92.27 360	97.07 319	73.68 412	97.95 368	89.36 367	91.30 333	96.72 328

LF4IMVS		93.14 341	92.79 334	94.20 375	95.88 380	88.67 395	97.66 328	97.07 366	93.81 249	91.71 369	97.65 269	77.96 381	98.81 283	91.47 328	91.92 326	95.12 400

mmtdpeth		93.12 342	92.61 338	94.63 363	97.60 274	89.68 375	99.21 40	97.32 346	94.02 233	97.72 160	94.42 410	77.01 394	99.44 193	99.05 28	77.18 432	94.78 410

testgi		93.06 343	92.45 344	94.88 351	96.43 356	89.90 367	98.75 161	97.54 325	95.60 150	91.63 372	97.91 242	74.46 409	97.02 400	86.10 394	93.67 298	97.72 273

PatchT		93.06 343	91.97 350	96.35 289	96.69 342	92.67 314	94.48 429	97.08 364	86.62 404	97.08 186	92.23 429	87.94 249	97.90 372	78.89 426	96.69 238	98.49 244

RPMNet		92.81 345	91.34 356	97.24 210	97.00 320	93.43 290	94.96 419	98.80 106	82.27 423	96.93 194	92.12 430	86.98 269	99.82 89	76.32 431	96.65 240	98.46 246

UWE-MVS-28		92.79 346	92.51 341	93.62 382	96.46 354	86.28 414	97.93 297	92.71 435	94.17 226	94.78 262	97.16 309	81.05 353	96.43 414	81.45 418	96.86 231	98.14 261

myMVS_eth3d		92.73 347	92.01 349	94.89 350	97.39 297	90.94 343	97.91 300	97.46 333	93.16 287	93.42 324	95.37 400	68.09 421	96.12 417	88.34 379	96.99 227	97.60 277

TransMVSNet (Re)		92.67 348	91.51 355	96.15 297	96.58 347	94.65 239	98.90 110	96.73 388	90.86 363	89.46 393	97.86 247	85.62 293	98.09 358	86.45 392	81.12 418	95.71 390

ttmdpeth		92.61 349	91.96 352	94.55 365	94.10 413	90.60 356	98.52 215	97.29 349	92.67 306	90.18 384	97.92 241	79.75 366	97.79 379	91.09 334	86.15 399	95.26 396

Syy-MVS		92.55 350	92.61 338	92.38 396	97.39 297	83.41 422	97.91 300	97.46 333	93.16 287	93.42 324	95.37 400	84.75 311	96.12 417	77.00 430	96.99 227	97.60 277

K. test v3		92.55 350	91.91 353	94.48 369	95.64 386	89.24 383	99.07 67	94.88 418	94.04 231	86.78 410	97.59 276	77.64 387	97.64 386	92.08 310	89.43 362	96.57 347

DSMNet-mixed		92.52 352	92.58 340	92.33 397	94.15 412	82.65 425	98.30 246	94.26 425	89.08 393	92.65 349	95.73 391	85.01 305	95.76 421	86.24 393	97.76 207	98.59 237

TinyColmap		92.31 353	91.53 354	94.65 362	96.92 326	89.75 370	96.92 380	96.68 391	90.45 370	89.62 390	97.85 249	76.06 401	98.81 283	86.74 390	92.51 319	95.41 394

gg-mvs-nofinetune		92.21 354	90.58 362	97.13 219	96.75 339	95.09 216	95.85 410	89.40 443	85.43 414	94.50 268	81.98 438	80.80 358	98.40 332	92.16 308	98.33 187	97.88 266

FMVSNet5		91.81 355	90.92 358	94.49 368	97.21 307	92.09 322	98.00 289	97.55 324	89.31 391	90.86 378	95.61 397	74.48 408	95.32 425	85.57 398	89.70 354	96.07 383

pmmvs6		91.77 356	90.63 361	95.17 339	94.69 409	91.24 339	98.67 189	97.92 295	86.14 408	89.62 390	97.56 281	75.79 402	98.34 335	90.75 343	84.56 404	95.94 386

Anonymous20231206		91.66 357	91.10 357	93.33 387	94.02 417	87.35 410	98.58 204	97.26 353	90.48 368	90.16 385	96.31 368	83.83 334	96.53 412	79.36 424	89.90 352	96.12 381

Patchmatch-RL test		91.49 358	90.85 359	93.41 385	91.37 428	84.40 417	92.81 433	95.93 408	91.87 334	87.25 406	94.87 406	88.99 219	96.53 412	92.54 302	82.00 413	99.30 139

test_0402		91.32 359	90.27 365	94.48 369	96.60 346	91.12 340	98.50 221	97.22 355	86.10 409	88.30 402	96.98 334	77.65 386	97.99 366	78.13 428	92.94 313	94.34 411

test_vis1_rt		91.29 360	90.65 360	93.19 391	97.45 291	86.25 415	98.57 211	90.90 441	93.30 281	86.94 409	93.59 419	62.07 433	99.11 235	97.48 125	95.58 274	94.22 414

PVSNet_0	88.72 19	91.28 361	90.03 368	95.00 345	97.99 242	87.29 411	94.84 422	98.50 190	92.06 329	89.86 387	95.19 402	79.81 365	99.39 200	92.27 307	69.79 438	98.33 253

mvs5depth		91.23 362	90.17 366	94.41 373	92.09 425	89.79 369	95.26 417	96.50 396	90.73 364	91.69 370	97.06 323	76.12 400	98.62 298	88.02 383	84.11 407	94.82 407

Anonymous20240521		91.18 363	90.44 363	93.42 384	93.70 418	88.47 399	98.94 100	97.56 319	88.46 397	89.56 392	95.08 405	77.15 392	96.97 401	83.92 410	89.55 358	94.82 407

EG-PatchMatch MVS		91.13 364	90.12 367	94.17 377	94.73 408	89.00 388	98.13 272	97.81 300	89.22 392	85.32 420	96.46 365	67.71 423	98.42 319	87.89 386	93.82 296	95.08 402

TDRefinement		91.06 365	89.68 370	95.21 337	85.35 443	91.49 335	98.51 220	97.07 366	91.47 343	88.83 399	97.84 250	77.31 388	99.09 240	92.79 293	77.98 430	95.04 404

sc_t1		91.01 366	89.39 372	95.85 313	95.99 375	90.39 361	98.43 231	97.64 311	78.79 427	92.20 362	97.94 239	66.00 427	98.60 302	91.59 326	85.94 401	98.57 240

UnsupCasMVSNet_eth		90.99 367	89.92 369	94.19 376	94.08 414	89.83 368	97.13 371	98.67 143	93.69 260	85.83 416	96.19 375	75.15 404	96.74 406	89.14 370	79.41 425	96.00 384

test20.03		90.89 368	90.38 364	92.43 395	93.48 419	88.14 405	98.33 239	97.56 319	93.40 276	87.96 403	96.71 355	80.69 359	94.13 430	79.15 425	86.17 397	95.01 406

MDA-MVSNet_test_wron		90.71 369	89.38 374	94.68 360	94.83 405	90.78 349	97.19 364	97.46 333	87.60 400	72.41 438	95.72 393	86.51 275	96.71 409	85.92 396	86.80 394	96.56 349

YYNet1		90.70 370	89.39 372	94.62 364	94.79 407	90.65 352	97.20 362	97.46 333	87.54 401	72.54 437	95.74 389	86.51 275	96.66 410	86.00 395	86.76 395	96.54 352

KD-MVS_self_test		90.38 371	89.38 374	93.40 386	92.85 422	88.94 391	97.95 293	97.94 293	90.35 373	90.25 383	93.96 416	79.82 364	95.94 420	84.62 409	76.69 433	95.33 395

pmmvs-eth3d		90.36 372	89.05 377	94.32 374	91.10 430	92.12 321	97.63 333	96.95 377	88.86 395	84.91 421	93.13 424	78.32 375	96.74 406	88.70 375	81.81 415	94.09 417

tt0320		90.26 373	88.73 380	94.86 352	96.12 369	90.62 354	98.17 267	97.63 312	77.46 430	89.68 389	96.04 381	69.19 419	97.79 379	88.98 372	85.29 403	96.16 380

CL-MVSNet_self_test		90.11 374	89.14 376	93.02 392	91.86 427	88.23 404	96.51 402	98.07 280	90.49 367	90.49 382	94.41 411	84.75 311	95.34 424	80.79 420	74.95 435	95.50 393

new_pmnet		90.06 375	89.00 378	93.22 390	94.18 411	88.32 402	96.42 404	96.89 382	86.19 407	85.67 417	93.62 418	77.18 391	97.10 399	81.61 417	89.29 364	94.23 413

MDA-MVSNet-bldmvs		89.97 376	88.35 382	94.83 356	95.21 399	91.34 336	97.64 330	97.51 328	88.36 398	71.17 439	96.13 377	79.22 369	96.63 411	83.65 411	86.27 396	96.52 357

tt0320-xc		89.79 377	88.11 384	94.84 355	96.19 364	90.61 355	98.16 268	97.22 355	77.35 431	88.75 400	96.70 356	65.94 428	97.63 387	89.31 368	83.39 409	96.28 375

CMPMVS	66.06 21	89.70 378	89.67 371	89.78 404	93.19 420	76.56 430	97.00 376	98.35 222	80.97 425	81.57 426	97.75 258	74.75 406	98.61 299	89.85 356	93.63 300	94.17 415
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 379	88.28 383	93.82 380	92.81 423	91.08 341	98.01 287	97.45 337	87.95 399	87.90 404	95.87 387	67.63 424	94.56 429	78.73 427	88.18 377	95.83 388

KD-MVS_2432*1600		89.61 380	87.96 388	94.54 366	94.06 415	91.59 333	95.59 414	97.63 312	89.87 380	88.95 396	94.38 413	78.28 376	96.82 404	84.83 405	68.05 439	95.21 398

miper_refine_blended		89.61 380	87.96 388	94.54 366	94.06 415	91.59 333	95.59 414	97.63 312	89.87 380	88.95 396	94.38 413	78.28 376	96.82 404	84.83 405	68.05 439	95.21 398

MVStest1		89.53 382	87.99 387	94.14 379	94.39 410	90.42 359	98.25 253	96.84 387	82.81 420	81.18 428	97.33 297	77.09 393	96.94 402	85.27 402	78.79 426	95.06 403

MVS-HIRNet		89.46 383	88.40 381	92.64 394	97.58 276	82.15 426	94.16 432	93.05 434	75.73 434	90.90 377	82.52 437	79.42 368	98.33 337	83.53 412	98.68 163	97.43 280

OpenMVS_ROB	86.42 20	89.00 384	87.43 392	93.69 381	93.08 421	89.42 381	97.91 300	96.89 382	78.58 428	85.86 415	94.69 407	69.48 418	98.29 345	77.13 429	93.29 310	93.36 424

mvsany_test3		88.80 385	88.04 385	91.09 403	89.78 433	81.57 428	97.83 315	95.49 412	93.81 249	87.53 405	93.95 417	56.14 436	97.43 394	94.68 228	83.13 410	94.26 412

new-patchmatchnet		88.50 386	87.45 391	91.67 401	90.31 432	85.89 416	97.16 369	97.33 345	89.47 387	83.63 423	92.77 426	76.38 397	95.06 427	82.70 414	77.29 431	94.06 419

APD_test1		88.22 387	88.01 386	88.86 406	95.98 376	74.66 438	97.21 361	96.44 398	83.96 419	86.66 412	97.90 243	60.95 434	97.84 378	82.73 413	90.23 348	94.09 417

PM-MVS		87.77 388	86.55 394	91.40 402	91.03 431	83.36 424	96.92 380	95.18 416	91.28 354	86.48 414	93.42 420	53.27 437	96.74 406	89.43 366	81.97 414	94.11 416

dmvs_testset		87.64 389	88.93 379	83.79 415	95.25 398	63.36 447	97.20 362	91.17 439	93.07 291	85.64 418	95.98 386	85.30 302	91.52 437	69.42 436	87.33 386	96.49 363

test_fmvs3		87.17 390	87.06 393	87.50 408	91.21 429	75.66 433	99.05 70	96.61 395	92.79 303	88.85 398	92.78 425	43.72 440	93.49 431	93.95 258	84.56 404	93.34 425

UnsupCasMVSNet_bld		87.17 390	85.12 397	93.31 388	91.94 426	88.77 392	94.92 421	98.30 236	84.30 418	82.30 424	90.04 432	63.96 431	97.25 397	85.85 397	74.47 437	93.93 421

N_pmnet		87.12 392	87.77 390	85.17 412	95.46 394	61.92 448	97.37 348	70.66 453	85.83 411	88.73 401	96.04 381	85.33 300	97.76 382	80.02 421	90.48 343	95.84 387

pmmvs3		86.67 393	84.86 398	92.11 400	88.16 437	87.19 412	96.63 398	94.75 420	79.88 426	87.22 407	92.75 427	66.56 426	95.20 426	81.24 419	76.56 434	93.96 420

test_f		86.07 394	85.39 395	88.10 407	89.28 435	75.57 434	97.73 323	96.33 400	89.41 390	85.35 419	91.56 431	43.31 442	95.53 422	91.32 330	84.23 406	93.21 426

WB-MVS		84.86 395	85.33 396	83.46 416	89.48 434	69.56 442	98.19 261	96.42 399	89.55 386	81.79 425	94.67 408	84.80 309	90.12 438	52.44 442	80.64 422	90.69 429

SSC-MVS		84.27 396	84.71 399	82.96 420	89.19 436	68.83 443	98.08 279	96.30 401	89.04 394	81.37 427	94.47 409	84.60 316	89.89 439	49.80 444	79.52 424	90.15 430

dongtai		82.47 397	81.88 400	84.22 414	95.19 400	76.03 431	94.59 428	74.14 452	82.63 421	87.19 408	96.09 378	64.10 430	87.85 442	58.91 440	84.11 407	88.78 434

test_vis3_rt		79.22 398	77.40 405	84.67 413	86.44 441	74.85 437	97.66 328	81.43 448	84.98 415	67.12 441	81.91 439	28.09 450	97.60 388	88.96 373	80.04 423	81.55 439

test_method		79.03 399	78.17 401	81.63 421	86.06 442	54.40 453	82.75 441	96.89 382	39.54 445	80.98 429	95.57 398	58.37 435	94.73 428	84.74 408	78.61 427	95.75 389

testf1		79.02 400	77.70 402	82.99 418	88.10 438	66.90 444	94.67 424	93.11 431	71.08 436	74.02 434	93.41 421	34.15 446	93.25 432	72.25 434	78.50 428	88.82 432

APD_test2		79.02 400	77.70 402	82.99 418	88.10 438	66.90 444	94.67 424	93.11 431	71.08 436	74.02 434	93.41 421	34.15 446	93.25 432	72.25 434	78.50 428	88.82 432

LCM-MVSNet		78.70 402	76.24 408	86.08 410	77.26 449	71.99 440	94.34 430	96.72 389	61.62 440	76.53 432	89.33 433	33.91 448	92.78 435	81.85 416	74.60 436	93.46 423

kuosan		78.45 403	77.69 404	80.72 422	92.73 424	75.32 435	94.63 427	74.51 451	75.96 432	80.87 430	93.19 423	63.23 432	79.99 446	42.56 446	81.56 417	86.85 438

Gipuma		78.40 404	76.75 407	83.38 417	95.54 389	80.43 429	79.42 442	97.40 341	64.67 439	73.46 436	80.82 440	45.65 439	93.14 434	66.32 438	87.43 384	76.56 442
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 405	75.44 409	85.46 411	82.54 444	74.95 436	94.23 431	93.08 433	72.80 435	74.68 433	87.38 434	36.36 445	91.56 436	73.95 432	63.94 441	89.87 431

FPMVS		77.62 406	77.14 406	79.05 424	79.25 447	60.97 449	95.79 411	95.94 407	65.96 438	67.93 440	94.40 412	37.73 444	88.88 441	68.83 437	88.46 374	87.29 435

EGC-MVSNET		75.22 407	69.54 410	92.28 398	94.81 406	89.58 377	97.64 330	96.50 396	1.82 450	5.57 451	95.74 389	68.21 420	96.26 416	73.80 433	91.71 328	90.99 428

ANet_high		69.08 408	65.37 412	80.22 423	65.99 451	71.96 441	90.91 437	90.09 442	82.62 422	49.93 446	78.39 441	29.36 449	81.75 443	62.49 439	38.52 445	86.95 437

tmp_tt		68.90 409	66.97 411	74.68 426	50.78 453	59.95 450	87.13 438	83.47 447	38.80 446	62.21 442	96.23 372	64.70 429	76.91 448	88.91 374	30.49 446	87.19 436

PMVS	61.03 23	65.95 410	63.57 414	73.09 427	57.90 452	51.22 454	85.05 440	93.93 429	54.45 441	44.32 447	83.57 436	13.22 451	89.15 440	58.68 441	81.00 419	78.91 441
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 411	64.25 413	67.02 428	82.28 445	59.36 451	91.83 436	85.63 445	52.69 442	60.22 443	77.28 442	41.06 443	80.12 445	46.15 445	41.14 443	61.57 444

EMVS		64.07 412	63.26 415	66.53 429	81.73 446	58.81 452	91.85 435	84.75 446	51.93 444	59.09 444	75.13 443	43.32 441	79.09 447	42.03 447	39.47 444	61.69 443

MVE	62.14 22	63.28 413	59.38 416	74.99 425	74.33 450	65.47 446	85.55 439	80.50 449	52.02 443	51.10 445	75.00 444	10.91 454	80.50 444	51.60 443	53.40 442	78.99 440
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 414	30.18 418	30.16 430	78.61 448	43.29 455	66.79 443	14.21 454	17.31 447	14.82 450	11.93 450	11.55 453	41.43 449	37.08 448	19.30 447	5.76 447

cdsmvs_eth3d_5k		23.98 415	31.98 417	0.00 433	0.00 456	0.00 458	0.00 444	98.59 163	0.00 451	0.00 452	98.61 172	90.60 178	0.00 452	0.00 451	0.00 450	0.00 448

testmvs		21.48 416	24.95 419	11.09 432	14.89 454	6.47 457	96.56 400	9.87 455	7.55 448	17.93 448	39.02 446	9.43 455	5.90 451	16.56 450	12.72 448	20.91 446

test123		20.95 417	23.72 420	12.64 431	13.54 455	8.19 456	96.55 401	6.13 456	7.48 449	16.74 449	37.98 447	12.97 452	6.05 450	16.69 449	5.43 449	23.68 445

ab-mvs-re		8.20 418	10.94 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	98.43 190	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		7.88 419	10.50 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	94.51 88	0.00 452	0.00 451	0.00 450	0.00 448

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						90.94 343								88.66 376

FOURS1					99.82 1	98.66 24	99.69 1	98.95 55	97.46 50	99.39 40

MSC_two_6792asdad				99.62 6	99.17 102	99.08 11		98.63 154					99.94 12	98.53 51	99.80 24	99.86 9

PC_three_1452									95.08 182	99.60 28	99.16 91	97.86 2	98.47 313	97.52 122	99.72 60	99.74 43

No_MVS				99.62 6	99.17 102	99.08 11		98.63 154					99.94 12	98.53 51	99.80 24	99.86 9

test_one_0601					99.66 27	99.25 2		98.86 84	97.55 42	99.20 52	99.47 31	97.57 6

eth-test2					0.00 456

eth-test					0.00 456

ZD-MVS					99.46 53	98.70 23		98.79 111	93.21 284	98.67 94	98.97 123	95.70 49	99.83 82	96.07 178	99.58 91

RE-MVS-def			98.34 47		99.49 47	97.86 70	99.11 61	98.80 106	96.49 109	99.17 55	99.35 56	95.29 66		97.72 101	99.65 74	99.71 56

IU-MVS					99.71 20	99.23 7		98.64 151	95.28 169	99.63 27				98.35 68	99.81 15	99.83 14

OPU-MVS				99.37 23	99.24 94	99.05 14	99.02 80				99.16 91	97.81 3	99.37 201	97.24 133	99.73 55	99.70 60

test_241102_TWO								98.87 78	97.65 34	99.53 33	99.48 29	97.34 11	99.94 12	98.43 63	99.80 24	99.83 14

test_241102_ONE					99.71 20	99.24 5		98.87 78	97.62 36	99.73 18	99.39 44	97.53 7	99.74 125

9.14			98.06 72		99.47 51		98.71 176	98.82 93	94.36 222	99.16 58	99.29 65	96.05 37	99.81 94	97.00 139	99.71 62

save fliter					99.46 53	98.38 36	98.21 256	98.71 129	97.95 24

test_0728_THIRD									97.32 58	99.45 35	99.46 36	97.88 1	99.94 12	98.47 59	99.86 2	99.85 11

test_0728_SECOND				99.71 1	99.72 13	99.35 1	98.97 91	98.88 71					99.94 12	98.47 59	99.81 15	99.84 13

test0726					99.72 13	99.25 2	99.06 68	98.88 71	97.62 36	99.56 30	99.50 25	97.42 9

GSMVS																99.20 156

test_part2					99.63 30	99.18 10				99.27 49

sam_mvs1												89.45 204				99.20 156

sam_mvs												88.99 219

ambc				89.49 405	86.66 440	75.78 432	92.66 434	96.72 389		86.55 413	92.50 428	46.01 438	97.90 372	90.32 347	82.09 412	94.80 409

MTGPA								98.74 121

test_post1							96.68 397				30.43 449	87.85 253	98.69 291	92.59 298

test_post											31.83 448	88.83 226	98.91 267

patchmatchnet-post											95.10 404	89.42 205	98.89 271

GG-mvs-BLEND				96.59 263	96.34 359	94.98 224	96.51 402	88.58 444		93.10 338	94.34 415	80.34 363	98.05 361	89.53 363	96.99 227	96.74 325

MTMP							98.89 114	94.14 427

gm-plane-assit					95.88 380	87.47 409			89.74 383		96.94 340		99.19 222	93.32 277

test9_res														96.39 172	99.57 92	99.69 63

TEST9					99.31 70	98.50 30	97.92 298	98.73 124	92.63 307	97.74 157	98.68 167	96.20 32	99.80 101

test_8					99.29 79	98.44 32	97.89 306	98.72 126	92.98 295	97.70 162	98.66 170	96.20 32	99.80 101

agg_prior2														95.87 188	99.57 92	99.68 68

agg_prior					99.30 74	98.38 36		98.72 126		97.57 174			99.81 94

TestCases				96.99 228	99.25 87	93.21 304		98.18 254	91.36 347	93.52 317	98.77 156	84.67 314	99.72 127	89.70 360	97.87 202	98.02 264

test_prior4						98.01 66	97.86 310

test_prior2							97.80 317		96.12 127	97.89 150	98.69 166	95.96 41		96.89 148	99.60 86

test_prior				99.19 45	99.31 70	98.22 53		98.84 88					99.70 133			99.65 76

旧先验2							97.57 336		91.30 352	98.67 94			99.80 101	95.70 197

新几何2							97.64 330

新几何1				99.16 50	99.34 63	98.01 66		98.69 135	90.06 377	98.13 124	98.95 130	94.60 86	99.89 60	91.97 317	99.47 113	99.59 87

旧先验1					99.29 79	97.48 84		98.70 133			99.09 107	95.56 52			99.47 113	99.61 83

无先验							97.58 335	98.72 126	91.38 346				99.87 71	93.36 276		99.60 85

原ACMM2							97.67 327

原ACMM1				98.65 91	99.32 68	96.62 133		98.67 143	93.27 283	97.81 152	98.97 123	95.18 73	99.83 82	93.84 262	99.46 116	99.50 99

test222					99.23 95	97.17 110	97.40 344	98.66 146	88.68 396	98.05 130	98.96 128	94.14 99			99.53 104	99.61 83

testdata2													99.89 60	91.65 325

segment_acmp												96.85 14

testdata				98.26 132	99.20 100	95.36 201		98.68 138	91.89 333	98.60 102	99.10 100	94.44 93	99.82 89	94.27 246	99.44 117	99.58 91

testdata1							97.32 354		96.34 117

test12				99.18 47	99.16 106	98.19 55		98.53 179		98.07 128		95.13 76	99.72 127		99.56 99	99.63 81

plane_prior7					97.42 293	94.63 241

plane_prior6					97.35 300	94.61 244						87.09 266

plane_prior5								98.56 173					99.03 247	96.07 178	94.27 280	96.92 301

plane_prior4											98.28 209

plane_prior3						94.61 244			97.02 82	95.34 246

plane_prior2							98.80 149		97.28 62

plane_prior1					97.37 299

plane_prior						94.60 246	98.44 229		96.74 96						94.22 282

n2								0.00 457

nn								0.00 457

door-mid								94.37 423

lessismore_v0				94.45 372	94.93 404	88.44 400		91.03 440		86.77 411	97.64 272	76.23 399	98.42 319	90.31 348	85.64 402	96.51 360

LGP-MVS_train				96.47 278	97.46 288	93.54 285		98.54 177	94.67 206	94.36 278	98.77 156	85.39 296	99.11 235	95.71 195	94.15 286	96.76 323

test11								98.66 146

door								94.64 421

HQP5-MVS						94.25 262

HQP-NCC					97.20 308		98.05 282		96.43 111	94.45 270

ACMP_Plane					97.20 308		98.05 282		96.43 111	94.45 270

BP-MVS														95.30 209

HQP4-MVS										94.45 270			98.96 258			96.87 313

HQP3-MVS								98.46 198							94.18 284

HQP2-MVS												86.75 272

NP-MVS					97.28 302	94.51 249					97.73 259

MDTV_nov1_ep13_2view						84.26 418	96.89 387		90.97 361	97.90 149		89.89 190		93.91 260		99.18 165

MDTV_nov1_ep13			95.40 198		97.48 286	88.34 401	96.85 390	97.29 349	93.74 253	97.48 176	97.26 301	89.18 213	99.05 243	91.92 318	97.43 218

ACMMP++_ref															92.97 312

ACMMP++															93.61 301

Test By Simon												94.64 85

ITE_SJBPF				95.44 331	97.42 293	91.32 337		97.50 329	95.09 181	93.59 313	98.35 200	81.70 345	98.88 273	89.71 359	93.39 307	96.12 381

DeepMVS_CX				86.78 409	97.09 318	72.30 439		95.17 417	75.92 433	84.34 422	95.19 402	70.58 416	95.35 423	79.98 423	89.04 368	92.68 427

High-resolution multi-view benchmark