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 37	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 76	97.65 32	99.73 17	99.48 28	97.53 7	99.94 11	98.43 58	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 69	97.32 54	99.53 31	99.47 30	97.81 3	99.94 11	98.47 54	99.72 60	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 38	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	98.58 163	97.62 34	99.45 33	99.46 34	97.42 9	99.94 11	98.47 54	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 57	97.38 51	99.41 36	99.54 16	96.66 18	99.84 78	98.86 33	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 86	98.06 20	99.35 40	99.61 4	96.39 27	99.94 11	98.77 36	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 88	98.06 20	99.29 44	99.58 12	96.40 25	99.94 11	98.68 38	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 88	98.06 20	99.29 44	99.58 12	96.40 25	99.94 11	98.68 38	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	98.42 223	98.91 63	97.58 37	99.54 30	99.46 34	97.10 12	99.94 11	97.64 105	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 11	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 76	97.38 51	99.35 40	99.40 41	97.78 5	99.87 69	97.77 93	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 22	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	98.66 143	96.84 83	99.56 28	99.31 61	96.34 28	99.70 130	98.32 64	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	98.47 215	98.81 97	97.72 27	98.76 83	99.16 88	97.05 13	99.78 112	98.06 75	99.66 70	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 69	97.52 40	99.41 36	98.78 145	96.00 39	99.79 109	97.79 92	99.59 87	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 69	97.40 48	98.46 101	99.20 78	95.90 45	99.89 58	97.85 88	99.74 52	99.78 25

fmvsm_s_conf0.5_n_6		98.65 19	98.55 21	98.95 69	98.50 175	97.30 95	98.79 151	99.16 32	98.14 18	99.86 5	99.41 40	93.71 104	99.91 47	99.71 10	99.64 78	99.65 74

MCST-MVS		98.65 19	98.37 36	99.48 13	99.60 31	98.87 19	98.41 224	98.68 135	97.04 75	98.52 99	98.80 143	96.78 16	99.83 80	97.93 82	99.61 83	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 85	97.28 57	99.72 20	99.39 42	96.63 20	97.60 375	98.17 70	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 52	96.10 121	98.94 66	99.17 85	96.06 36	99.92 37	97.62 106	99.78 34	99.75 39

ACMMP_NAP		98.61 23	98.30 51	99.55 9	99.62 30	98.95 17	98.82 135	98.81 97	95.80 132	99.16 56	99.47 30	95.37 60	99.92 37	97.89 86	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 57	96.15 117	98.94 66	99.17 85	95.91 43	99.94 11	97.55 114	99.79 30	99.78 25

NCCC		98.61 23	98.35 39	99.38 18	99.28 81	98.61 26	98.45 216	98.76 115	97.82 26	98.45 104	98.93 127	96.65 19	99.83 80	97.38 123	99.41 118	99.71 54

SF-MVS		98.59 26	98.32 50	99.41 17	99.54 35	98.71 22	99.04 73	98.81 97	95.12 169	99.32 43	99.39 42	96.22 30	99.84 78	97.72 96	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 53	96.10 121	98.93 70	99.19 83	95.70 49	99.94 11	97.62 106	99.79 30	99.78 25

test_fmvsmconf0.1_n		98.58 28	98.44 31	98.99 62	97.73 255	97.15 106	98.84 131	98.97 49	98.75 6	99.43 35	99.54 16	93.29 109	99.93 30	99.64 15	99.79 30	99.89 4

SMA-MVS		98.58 28	98.25 54	99.56 8	99.51 40	99.04 15	98.95 95	98.80 104	93.67 254	99.37 39	99.52 19	96.52 22	99.89 58	98.06 75	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 52	99.46 14	99.76 2	98.64 25	98.90 106	98.74 119	97.27 61	98.02 128	99.39 42	94.81 83	99.96 4	97.91 84	99.79 30	99.77 31

HPM-MVS++		98.58 28	98.25 54	99.55 9	99.50 42	99.08 11	98.72 167	98.66 143	97.51 41	98.15 115	98.83 140	95.70 49	99.92 37	97.53 116	99.67 67	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 91	96.58 99	99.10 58	99.32 59	95.39 58	99.82 87	97.70 101	99.63 80	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 76	95.96 124	98.60 96	99.13 93	96.05 37	99.94 11	97.77 93	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 57	98.84 76	99.28 64	96.47 23	99.40 190	98.52 52	99.70 63	99.47 106

DeepC-MVS_fast	96.70 1	98.55 35	98.34 45	99.18 46	99.25 85	98.04 63	98.50 212	98.78 111	97.72 27	98.92 72	99.28 64	95.27 66	99.82 87	97.55 114	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	98.80 104	96.49 102	99.17 53	99.35 54	95.34 62	99.82 87	97.72 96	99.65 73	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 42	99.87 2	99.50 24	91.96 141	99.96 4	99.76 6	99.65 73	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	90.95 169	99.93 30	99.76 6	99.73 55	99.12 165

APD-MVS_3200maxsize		98.53 37	98.33 49	99.15 50	99.50 42	97.92 68	99.15 51	98.81 97	96.24 113	99.20 50	99.37 48	95.30 64	99.80 99	97.73 95	99.67 67	99.72 50

MM		98.51 40	98.24 56	99.33 30	99.12 109	98.14 60	98.93 101	97.02 361	98.96 1	99.17 53	99.47 30	91.97 140	99.94 11	99.85 3	99.69 64	99.91 2

mPP-MVS		98.51 40	98.26 53	99.25 39	99.75 3	98.04 63	99.28 24	98.81 97	96.24 113	98.35 111	99.23 73	95.46 55	99.94 11	97.42 121	99.81 15	99.77 31

ZNCC-MVS		98.49 42	98.20 62	99.35 25	99.73 11	98.39 34	99.19 44	98.86 82	95.77 134	98.31 114	99.10 97	95.46 55	99.93 30	97.57 113	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	98.50 185	97.45 47	98.88 73	99.14 92	95.25 68	99.15 218	98.83 34	99.56 97	99.20 150

PGM-MVS		98.49 42	98.23 58	99.27 38	99.72 12	98.08 62	98.99 86	99.49 5	95.43 150	99.03 59	99.32 59	95.56 52	99.94 11	96.80 152	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	98.30 235	98.69 132	97.21 64	98.84 76	99.36 52	95.41 57	99.78 112	98.62 41	99.65 73	99.80 22

MVS_111021_HR		98.47 45	98.34 45	98.88 74	99.22 95	97.32 92	97.91 287	99.58 3	97.20 65	98.33 112	99.00 116	95.99 40	99.64 143	98.05 77	99.76 42	99.69 61

balanced_conf03		98.45 47	98.35 39	98.74 80	98.65 164	97.55 79	99.19 44	98.60 154	96.72 93	99.35 40	98.77 147	95.06 78	99.55 166	98.95 30	99.87 1	99.12 165

test_fmvsmvis_n_1920		98.44 48	98.51 23	98.23 128	98.33 195	96.15 154	98.97 89	99.15 34	98.55 11	98.45 104	99.55 14	94.26 96	99.97 1	99.65 13	99.66 70	98.57 231

CS-MVS		98.44 48	98.49 27	98.31 120	99.08 114	96.73 124	99.67 3	98.47 192	97.17 67	98.94 66	99.10 97	95.73 48	99.13 221	98.71 37	99.49 108	99.09 170

GST-MVS		98.43 50	98.12 66	99.34 26	99.72 12	98.38 35	99.09 64	98.82 91	95.71 138	98.73 86	99.06 108	95.27 66	99.93 30	97.07 131	99.63 80	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 24	99.74 16	99.62 3	92.59 118	99.91 47	99.65 13	99.52 103	99.25 143

EI-MVSNet-UG-set		98.41 52	98.34 45	98.61 90	99.45 55	96.32 147	98.28 238	98.68 135	97.17 67	98.74 84	99.37 48	95.25 68	99.79 109	98.57 43	99.54 100	99.73 46

DELS-MVS		98.40 53	98.20 62	98.99 62	99.00 122	97.66 74	97.75 308	98.89 66	97.71 29	98.33 112	98.97 118	94.97 80	99.88 67	98.42 60	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 31	99.78 12	99.61 4	92.38 121	99.91 47	99.58 18	99.43 116	99.49 102

TSAR-MVS + GP.		98.38 54	98.24 56	98.81 76	99.22 95	97.25 101	98.11 262	98.29 231	97.19 66	98.99 64	99.02 111	96.22 30	99.67 137	98.52 52	98.56 166	99.51 95

HPM-MVS_fast		98.38 54	98.13 65	99.12 54	99.75 3	97.86 69	99.44 9	98.82 91	94.46 209	98.94 66	99.20 78	95.16 73	99.74 122	97.58 109	99.85 6	99.77 31

patch_mono-2		98.36 57	98.87 6	96.82 233	99.53 36	90.68 341	98.64 186	99.29 14	97.88 25	99.19 52	99.52 19	96.80 15	99.97 1	99.11 26	99.86 2	99.82 17

HPM-MVS		98.36 57	98.10 69	99.13 52	99.74 7	97.82 73	99.53 6	98.80 104	94.63 198	98.61 95	98.97 118	95.13 75	99.77 117	97.65 104	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 19	92.35 122	99.90 55	99.74 8	99.51 105	98.71 212

APD-MVS		98.35 59	98.00 75	99.42 16	99.51 40	98.72 21	98.80 144	98.82 91	94.52 206	99.23 49	99.25 72	95.54 54	99.80 99	96.52 159	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 58	98.67 86	99.27 82	96.90 116	97.95 280	99.58 3	97.14 70	98.44 106	99.01 115	95.03 79	99.62 150	97.91 84	99.75 48	99.50 97

PHI-MVS		98.34 61	98.06 70	99.18 46	99.15 107	98.12 61	99.04 73	99.09 37	93.32 269	98.83 78	99.10 97	96.54 21	99.83 80	97.70 101	99.76 42	99.59 85

MP-MVS		98.33 63	98.01 74	99.28 36	99.75 3	98.18 55	99.22 36	98.79 109	96.13 118	97.92 139	99.23 73	94.54 86	99.94 11	96.74 155	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 64	98.67 86	98.96 129	97.36 90	99.24 30	98.57 165	94.81 190	98.99 64	98.90 131	95.22 71	99.59 153	99.15 25	99.84 11	99.07 178

MP-MVS-pluss		98.31 64	97.92 77	99.49 12	99.72 12	98.88 18	98.43 221	98.78 111	94.10 219	97.69 154	99.42 38	95.25 68	99.92 37	98.09 74	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 60	98.57 92	99.25 85	97.11 107	98.66 182	99.20 27	98.82 2	99.79 11	99.60 8	89.38 200	99.92 37	99.80 4	99.38 123	98.69 214

fmvsm_s_conf0.5_n_7		98.23 67	98.35 39	97.89 156	98.86 139	94.99 215	98.58 195	99.00 45	98.29 15	99.73 17	99.60 8	91.70 145	99.92 37	99.63 16	99.73 55	98.76 208

MVS_0304		98.23 67	97.91 78	99.21 43	98.06 225	97.96 67	98.58 195	95.51 398	98.58 9	98.87 74	99.26 67	92.99 113	99.95 9	99.62 17	99.67 67	99.73 46

ACMMP		98.23 67	97.95 76	99.09 56	99.74 7	97.62 77	99.03 76	99.41 6	95.98 123	97.60 163	99.36 52	94.45 91	99.93 30	97.14 128	98.85 152	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 70	98.11 67	98.49 104	98.34 192	97.26 100	99.61 5	98.43 201	96.78 86	98.87 74	98.84 138	93.72 103	99.01 243	98.91 32	99.50 106	99.19 154

fmvsm_s_conf0.1_n		98.18 71	98.21 60	98.11 141	98.54 173	95.24 201	98.87 119	99.24 18	97.50 42	99.70 21	99.67 1	91.33 158	99.89 58	99.47 20	99.54 100	99.21 149

fmvsm_s_conf0.1_n_2		98.14 72	98.02 73	98.53 99	98.88 135	97.07 109	98.69 174	98.82 91	98.78 4	99.77 13	99.61 4	88.83 219	99.91 47	99.71 10	99.07 136	98.61 224

fmvsm_s_conf0.1_n_a		98.08 73	98.04 72	98.21 129	97.66 261	95.39 191	98.89 110	99.17 31	97.24 62	99.76 15	99.67 1	91.13 163	99.88 67	99.39 21	99.41 118	99.35 122

dcpmvs_2		98.08 73	98.59 18	96.56 258	99.57 33	90.34 350	99.15 51	98.38 211	96.82 85	99.29 44	99.49 27	95.78 47	99.57 156	98.94 31	99.86 2	99.77 31

CANet		98.05 75	97.76 81	98.90 73	98.73 149	97.27 96	98.35 226	98.78 111	97.37 53	97.72 151	98.96 123	91.53 154	99.92 37	98.79 35	99.65 73	99.51 95

train_agg		97.97 76	97.52 93	99.33 30	99.31 68	98.50 29	97.92 285	98.73 122	92.98 285	97.74 148	98.68 158	96.20 32	99.80 99	96.59 156	99.57 91	99.68 66

ETV-MVS		97.96 77	97.81 79	98.40 115	98.42 180	97.27 96	98.73 163	98.55 170	96.84 83	98.38 108	97.44 277	95.39 58	99.35 195	97.62 106	98.89 147	98.58 230

UA-Net		97.96 77	97.62 85	98.98 64	98.86 139	97.47 85	98.89 110	99.08 38	96.67 96	98.72 87	99.54 16	93.15 111	99.81 92	94.87 214	98.83 153	99.65 74

CDPH-MVS		97.94 79	97.49 95	99.28 36	99.47 50	98.44 31	97.91 287	98.67 140	92.57 301	98.77 82	98.85 137	95.93 42	99.72 124	95.56 193	99.69 64	99.68 66

DeepPCF-MVS	96.37 2	97.93 80	98.48 29	96.30 283	99.00 122	89.54 365	97.43 330	98.87 76	98.16 17	99.26 48	99.38 47	96.12 35	99.64 143	98.30 65	99.77 36	99.72 50

DeepC-MVS	95.98 3	97.88 81	97.58 87	98.77 78	99.25 85	96.93 114	98.83 133	98.75 117	96.96 79	96.89 189	99.50 24	90.46 177	99.87 69	97.84 90	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 82	97.54 92	98.83 75	95.48 380	96.83 119	98.95 95	98.60 154	98.58 9	98.93 70	99.55 14	88.57 224	99.91 47	99.54 19	99.61 83	99.77 31

DP-MVS Recon		97.86 82	97.46 98	99.06 59	99.53 36	98.35 44	98.33 228	98.89 66	92.62 298	98.05 123	98.94 126	95.34 62	99.65 140	96.04 175	99.42 117	99.19 154

CSCG		97.85 84	97.74 82	98.20 131	99.67 25	95.16 204	99.22 36	99.32 11	93.04 283	97.02 182	98.92 129	95.36 61	99.91 47	97.43 120	99.64 78	99.52 92

BP-MVS1		97.82 85	97.51 94	98.76 79	98.25 202	97.39 89	99.15 51	97.68 298	96.69 94	98.47 100	99.10 97	90.29 181	99.51 173	98.60 42	99.35 126	99.37 120

MG-MVS		97.81 86	97.60 86	98.44 110	99.12 109	95.97 163	97.75 308	98.78 111	96.89 82	98.46 101	99.22 75	93.90 102	99.68 136	94.81 218	99.52 103	99.67 70

VNet		97.79 87	97.40 102	98.96 67	98.88 135	97.55 79	98.63 189	98.93 57	96.74 90	99.02 60	98.84 138	90.33 180	99.83 80	98.53 46	96.66 230	99.50 97

EIA-MVS		97.75 88	97.58 87	98.27 122	98.38 184	96.44 139	99.01 81	98.60 154	95.88 128	97.26 170	97.53 271	94.97 80	99.33 198	97.38 123	99.20 132	99.05 179

PS-MVSNAJ		97.73 89	97.77 80	97.62 183	98.68 159	95.58 181	97.34 339	98.51 180	97.29 56	98.66 92	97.88 236	94.51 87	99.90 55	97.87 87	99.17 134	97.39 273

casdiffmvs_mvg		97.72 90	97.48 97	98.44 110	98.42 180	96.59 132	98.92 103	98.44 197	96.20 115	97.76 145	99.20 78	91.66 148	99.23 208	98.27 69	98.41 176	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 90	97.32 106	98.92 70	99.64 28	97.10 108	99.12 58	98.81 97	92.34 309	98.09 120	99.08 106	93.01 112	99.92 37	96.06 174	99.77 36	99.75 39

PVSNet_Blended_VisFu		97.70 92	97.46 98	98.44 110	99.27 82	95.91 171	98.63 189	99.16 32	94.48 208	97.67 155	98.88 134	92.80 115	99.91 47	97.11 129	99.12 135	99.50 97

mvsany_test1		97.69 93	97.70 83	97.66 181	98.24 203	94.18 256	97.53 324	97.53 316	95.52 146	99.66 23	99.51 22	94.30 94	99.56 159	98.38 61	98.62 162	99.23 145

sasdasda		97.67 94	97.23 110	98.98 64	98.70 154	98.38 35	99.34 16	98.39 207	96.76 88	97.67 155	97.40 281	92.26 126	99.49 177	98.28 66	96.28 248	99.08 174

canonicalmvs		97.67 94	97.23 110	98.98 64	98.70 154	98.38 35	99.34 16	98.39 207	96.76 88	97.67 155	97.40 281	92.26 126	99.49 177	98.28 66	96.28 248	99.08 174

xiu_mvs_v2_base		97.66 96	97.70 83	97.56 187	98.61 168	95.46 188	97.44 328	98.46 193	97.15 69	98.65 93	98.15 212	94.33 93	99.80 99	97.84 90	98.66 161	97.41 271

GDP-MVS		97.64 97	97.28 107	98.71 83	98.30 200	97.33 91	99.05 69	98.52 177	96.34 110	98.80 79	99.05 109	89.74 190	99.51 173	96.86 149	98.86 151	99.28 137

baseline		97.64 97	97.44 100	98.25 126	98.35 187	96.20 151	99.00 83	98.32 221	96.33 112	98.03 126	99.17 85	91.35 157	99.16 215	98.10 73	98.29 183	99.39 118

casdiffmvs		97.63 99	97.41 101	98.28 121	98.33 195	96.14 155	98.82 135	98.32 221	96.38 109	97.95 134	99.21 76	91.23 162	99.23 208	98.12 72	98.37 177	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		97.62 100	97.19 113	98.92 70	98.66 161	98.20 53	99.32 21	98.38 211	96.69 94	97.58 164	97.42 280	92.10 134	99.50 176	98.28 66	96.25 251	99.08 174

xiu_mvs_v1_base_debu		97.60 101	97.56 89	97.72 171	98.35 187	95.98 158	97.86 297	98.51 180	97.13 71	99.01 61	98.40 185	91.56 150	99.80 99	98.53 46	98.68 157	97.37 275

xiu_mvs_v1_base		97.60 101	97.56 89	97.72 171	98.35 187	95.98 158	97.86 297	98.51 180	97.13 71	99.01 61	98.40 185	91.56 150	99.80 99	98.53 46	98.68 157	97.37 275

xiu_mvs_v1_base_debi		97.60 101	97.56 89	97.72 171	98.35 187	95.98 158	97.86 297	98.51 180	97.13 71	99.01 61	98.40 185	91.56 150	99.80 99	98.53 46	98.68 157	97.37 275

diffmvs		97.58 104	97.40 102	98.13 137	98.32 198	95.81 176	98.06 268	98.37 213	96.20 115	98.74 84	98.89 133	91.31 160	99.25 205	98.16 71	98.52 168	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		97.57 105	97.49 95	97.84 158	98.07 222	95.76 177	99.47 7	98.40 205	94.98 179	98.79 80	98.83 140	92.34 123	98.41 316	96.91 137	99.59 87	99.34 124

alignmvs		97.56 106	97.07 119	99.01 61	98.66 161	98.37 42	98.83 133	98.06 278	96.74 90	98.00 132	97.65 259	90.80 171	99.48 182	98.37 62	96.56 234	99.19 154

DPM-MVS		97.55 107	96.99 122	99.23 42	99.04 117	98.55 27	97.17 354	98.35 216	94.85 189	97.93 138	98.58 168	95.07 77	99.71 129	92.60 286	99.34 127	99.43 115

OMC-MVS		97.55 107	97.34 105	98.20 131	99.33 63	95.92 170	98.28 238	98.59 158	95.52 146	97.97 133	99.10 97	93.28 110	99.49 177	95.09 209	98.88 148	99.19 154

PAPM_NR		97.46 109	97.11 116	98.50 102	99.50 42	96.41 142	98.63 189	98.60 154	95.18 166	97.06 180	98.06 218	94.26 96	99.57 156	93.80 254	98.87 150	99.52 92

EPP-MVSNet		97.46 109	97.28 107	97.99 149	98.64 165	95.38 192	99.33 20	98.31 223	93.61 258	97.19 173	99.07 107	94.05 99	99.23 208	96.89 141	98.43 175	99.37 120

3Dnovator	94.51 5	97.46 109	96.93 125	99.07 58	97.78 249	97.64 75	99.35 15	99.06 40	97.02 76	93.75 301	99.16 88	89.25 204	99.92 37	97.22 127	99.75 48	99.64 77

CNLPA		97.45 112	97.03 120	98.73 81	99.05 116	97.44 88	98.07 267	98.53 174	95.32 159	96.80 194	98.53 173	93.32 108	99.72 124	94.31 237	99.31 129	99.02 181

lupinMVS		97.44 113	97.22 112	98.12 140	98.07 222	95.76 177	97.68 313	97.76 295	94.50 207	98.79 80	98.61 163	92.34 123	99.30 201	97.58 109	99.59 87	99.31 130

3Dnovator+	94.38 6	97.43 114	96.78 133	99.38 18	97.83 246	98.52 28	99.37 12	98.71 127	97.09 74	92.99 330	99.13 93	89.36 201	99.89 58	96.97 134	99.57 91	99.71 54

Vis-MVSNet		97.42 115	97.11 116	98.34 118	98.66 161	96.23 150	99.22 36	99.00 45	96.63 98	98.04 125	99.21 76	88.05 240	99.35 195	96.01 177	99.21 131	99.45 112
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 116	97.25 109	97.91 153	98.70 154	96.80 120	98.82 135	98.69 132	94.53 204	98.11 118	98.28 200	94.50 90	99.57 156	94.12 243	99.49 108	97.37 275

sss		97.39 117	96.98 124	98.61 90	98.60 169	96.61 129	98.22 244	98.93 57	93.97 229	98.01 131	98.48 178	91.98 138	99.85 74	96.45 161	98.15 185	99.39 118

test_cas_vis1_n_1920		97.38 118	97.36 104	97.45 190	98.95 130	93.25 292	99.00 83	98.53 174	97.70 30	99.77 13	99.35 54	84.71 305	99.85 74	98.57 43	99.66 70	99.26 141

PVSNet_Blended		97.38 118	97.12 115	98.14 134	99.25 85	95.35 195	97.28 344	99.26 15	93.13 279	97.94 136	98.21 208	92.74 116	99.81 92	96.88 143	99.40 121	99.27 138

WTY-MVS		97.37 120	96.92 126	98.72 82	98.86 139	96.89 118	98.31 233	98.71 127	95.26 162	97.67 155	98.56 172	92.21 130	99.78 112	95.89 179	96.85 224	99.48 104

jason		97.32 121	97.08 118	98.06 145	97.45 281	95.59 180	97.87 295	97.91 289	94.79 191	98.55 98	98.83 140	91.12 164	99.23 208	97.58 109	99.60 85	99.34 124
jason: jason.
MVS_Test		97.28 122	97.00 121	98.13 137	98.33 195	95.97 163	98.74 159	98.07 273	94.27 214	98.44 106	98.07 217	92.48 119	99.26 204	96.43 162	98.19 184	99.16 160

EPNet		97.28 122	96.87 128	98.51 101	94.98 389	96.14 155	98.90 106	97.02 361	98.28 16	95.99 226	99.11 95	91.36 156	99.89 58	96.98 133	99.19 133	99.50 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsmamba		97.25 124	96.99 122	98.02 147	98.34 192	95.54 185	99.18 48	97.47 322	95.04 175	98.15 115	98.57 171	89.46 197	99.31 200	97.68 103	99.01 141	99.22 147

test_yl		97.22 125	96.78 133	98.54 97	98.73 149	96.60 130	98.45 216	98.31 223	94.70 192	98.02 128	98.42 183	90.80 171	99.70 130	96.81 150	96.79 226	99.34 124

DCV-MVSNet		97.22 125	96.78 133	98.54 97	98.73 149	96.60 130	98.45 216	98.31 223	94.70 192	98.02 128	98.42 183	90.80 171	99.70 130	96.81 150	96.79 226	99.34 124

IS-MVSNet		97.22 125	96.88 127	98.25 126	98.85 142	96.36 145	99.19 44	97.97 283	95.39 153	97.23 171	98.99 117	91.11 165	98.93 255	94.60 225	98.59 164	99.47 106

PLC	95.07 4	97.20 128	96.78 133	98.44 110	99.29 77	96.31 149	98.14 257	98.76 115	92.41 307	96.39 214	98.31 198	94.92 82	99.78 112	94.06 246	98.77 156	99.23 145
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 129	97.18 114	97.20 203	98.81 145	93.27 289	95.78 399	99.15 34	95.25 163	96.79 195	98.11 215	92.29 125	99.07 233	98.56 45	99.85 6	99.25 143

LS3D		97.16 130	96.66 142	98.68 85	98.53 174	97.19 104	98.93 101	98.90 64	92.83 292	95.99 226	99.37 48	92.12 133	99.87 69	93.67 258	99.57 91	98.97 186

AdaColmap		97.15 131	96.70 138	98.48 105	99.16 104	96.69 126	98.01 274	98.89 66	94.44 210	96.83 190	98.68 158	90.69 174	99.76 118	94.36 233	99.29 130	98.98 185

mamv4		97.13 132	98.11 67	94.17 364	98.97 128	83.70 407	98.66 182	98.71 127	94.63 198	97.83 142	98.90 131	96.25 29	99.55 166	99.27 23	99.76 42	99.27 138

Effi-MVS+		97.12 133	96.69 139	98.39 116	98.19 211	96.72 125	97.37 335	98.43 201	93.71 247	97.65 159	98.02 221	92.20 131	99.25 205	96.87 146	97.79 197	99.19 154

CHOSEN 1792x2688		97.12 133	96.80 130	98.08 143	99.30 72	94.56 240	98.05 269	99.71 1	93.57 259	97.09 176	98.91 130	88.17 234	99.89 58	96.87 146	99.56 97	99.81 19

F-COLMAP		97.09 135	96.80 130	97.97 150	99.45 55	94.95 219	98.55 204	98.62 153	93.02 284	96.17 221	98.58 168	94.01 100	99.81 92	93.95 248	98.90 146	99.14 163

RRT-MVS		97.03 136	96.78 133	97.77 167	97.90 242	94.34 249	99.12 58	98.35 216	95.87 129	98.06 122	98.70 156	86.45 271	99.63 146	98.04 78	98.54 167	99.35 122

TAMVS		97.02 137	96.79 132	97.70 174	98.06 225	95.31 198	98.52 206	98.31 223	93.95 230	97.05 181	98.61 163	93.49 106	98.52 298	95.33 200	97.81 196	99.29 135

CDS-MVSNet		96.99 138	96.69 139	97.90 154	98.05 227	95.98 158	98.20 247	98.33 220	93.67 254	96.95 183	98.49 177	93.54 105	98.42 309	95.24 206	97.74 200	99.31 130
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 139	96.55 145	98.21 129	98.17 216	96.07 157	97.98 278	98.21 240	97.24 62	97.13 175	98.93 127	86.88 263	99.91 47	95.00 212	99.37 125	98.66 220

114514_t		96.93 140	96.27 155	98.92 70	99.50 42	97.63 76	98.85 127	98.90 64	84.80 406	97.77 144	99.11 95	92.84 114	99.66 139	94.85 215	99.77 36	99.47 106

MAR-MVS		96.91 141	96.40 151	98.45 108	98.69 157	96.90 116	98.66 182	98.68 135	92.40 308	97.07 179	97.96 228	91.54 153	99.75 120	93.68 256	98.92 145	98.69 214
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		96.90 142	96.49 148	98.14 134	99.33 63	95.56 182	97.38 333	99.65 2	92.34 309	97.61 162	98.20 209	89.29 203	99.10 230	96.97 134	97.60 205	99.77 31

Vis-MVSNet (Re-imp)		96.87 143	96.55 145	97.83 159	98.73 149	95.46 188	99.20 42	98.30 229	94.96 181	96.60 202	98.87 135	90.05 184	98.59 293	93.67 258	98.60 163	99.46 110

SDMVSNet		96.85 144	96.42 149	98.14 134	99.30 72	96.38 143	99.21 39	99.23 23	95.92 125	95.96 228	98.76 152	85.88 281	99.44 187	97.93 82	95.59 263	98.60 225

PAPR		96.84 145	96.24 157	98.65 88	98.72 153	96.92 115	97.36 337	98.57 165	93.33 268	96.67 197	97.57 268	94.30 94	99.56 159	91.05 328	98.59 164	99.47 106

HY-MVS	93.96 8	96.82 146	96.23 158	98.57 92	98.46 179	97.00 111	98.14 257	98.21 240	93.95 230	96.72 196	97.99 225	91.58 149	99.76 118	94.51 229	96.54 235	98.95 189

UGNet		96.78 147	96.30 154	98.19 133	98.24 203	95.89 173	98.88 116	98.93 57	97.39 50	96.81 193	97.84 240	82.60 332	99.90 55	96.53 158	99.49 108	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		96.73 148	96.60 143	97.12 212	99.25 85	95.35 195	98.26 241	99.26 15	94.28 213	97.94 136	97.46 274	92.74 116	99.81 92	96.88 143	93.32 299	96.20 366

test_vis1_n_1920		96.71 149	96.84 129	96.31 282	99.11 111	89.74 358	99.05 69	98.58 163	98.08 19	99.87 2	99.37 48	78.48 364	99.93 30	99.29 22	99.69 64	99.27 138

mvs_anonymous		96.70 150	96.53 147	97.18 206	98.19 211	93.78 265	98.31 233	98.19 244	94.01 226	94.47 260	98.27 203	92.08 136	98.46 304	97.39 122	97.91 192	99.31 130

1112_ss		96.63 151	96.00 165	98.50 102	98.56 170	96.37 144	98.18 255	98.10 266	92.92 288	94.84 248	98.43 181	92.14 132	99.58 155	94.35 234	96.51 236	99.56 91

PMMVS		96.60 152	96.33 153	97.41 194	97.90 242	93.93 261	97.35 338	98.41 203	92.84 291	97.76 145	97.45 276	91.10 166	99.20 212	96.26 167	97.91 192	99.11 168

DP-MVS		96.59 153	95.93 168	98.57 92	99.34 61	96.19 153	98.70 172	98.39 207	89.45 378	94.52 258	99.35 54	91.85 142	99.85 74	92.89 282	98.88 148	99.68 66

PatchMatch-RL		96.59 153	96.03 164	98.27 122	99.31 68	96.51 136	97.91 287	99.06 40	93.72 246	96.92 187	98.06 218	88.50 229	99.65 140	91.77 311	99.00 143	98.66 220

GeoE		96.58 155	96.07 161	98.10 142	98.35 187	95.89 173	99.34 16	98.12 260	93.12 280	96.09 222	98.87 135	89.71 191	98.97 245	92.95 278	98.08 188	99.43 115

XVG-OURS		96.55 156	96.41 150	96.99 219	98.75 148	93.76 266	97.50 327	98.52 177	95.67 140	96.83 190	99.30 62	88.95 217	99.53 169	95.88 180	96.26 250	97.69 264

FIs		96.51 157	96.12 160	97.67 178	97.13 305	97.54 81	99.36 13	99.22 26	95.89 127	94.03 287	98.35 191	91.98 138	98.44 307	96.40 163	92.76 307	97.01 283

XVG-OURS-SEG-HR		96.51 157	96.34 152	97.02 218	98.77 147	93.76 266	97.79 306	98.50 185	95.45 149	96.94 184	99.09 104	87.87 245	99.55 166	96.76 154	95.83 262	97.74 261

PS-MVSNAJss		96.43 159	96.26 156	96.92 228	95.84 369	95.08 209	99.16 50	98.50 185	95.87 129	93.84 296	98.34 195	94.51 87	98.61 290	96.88 143	93.45 296	97.06 281

test_fmvs1		96.42 160	96.67 141	95.66 311	98.82 144	88.53 385	98.80 144	98.20 242	96.39 108	99.64 25	99.20 78	80.35 352	99.67 137	99.04 28	99.57 91	98.78 204

FC-MVSNet-test		96.42 160	96.05 162	97.53 188	96.95 314	97.27 96	99.36 13	99.23 23	95.83 131	93.93 290	98.37 189	92.00 137	98.32 327	96.02 176	92.72 308	97.00 284

ab-mvs		96.42 160	95.71 178	98.55 95	98.63 166	96.75 123	97.88 294	98.74 119	93.84 236	96.54 207	98.18 211	85.34 291	99.75 120	95.93 178	96.35 240	99.15 161

FA-MVS(test-final)		96.41 163	95.94 167	97.82 161	98.21 207	95.20 203	97.80 304	97.58 306	93.21 274	97.36 168	97.70 252	89.47 196	99.56 159	94.12 243	97.99 189	98.71 212

PVSNet	91.96 18	96.35 164	96.15 159	96.96 223	99.17 100	92.05 314	96.08 392	98.68 135	93.69 250	97.75 147	97.80 246	88.86 218	99.69 135	94.26 239	99.01 141	99.15 161

Test_1112_low_res		96.34 165	95.66 183	98.36 117	98.56 170	95.94 166	97.71 311	98.07 273	92.10 318	94.79 252	97.29 289	91.75 144	99.56 159	94.17 241	96.50 237	99.58 89

Effi-MVS+-dtu		96.29 166	96.56 144	95.51 316	97.89 244	90.22 351	98.80 144	98.10 266	96.57 101	96.45 212	96.66 345	90.81 170	98.91 258	95.72 187	97.99 189	97.40 272

QAPM		96.29 166	95.40 188	98.96 67	97.85 245	97.60 78	99.23 32	98.93 57	89.76 372	93.11 327	99.02 111	89.11 209	99.93 30	91.99 305	99.62 82	99.34 124

Fast-Effi-MVS+		96.28 168	95.70 180	98.03 146	98.29 201	95.97 163	98.58 195	98.25 237	91.74 326	95.29 241	97.23 294	91.03 168	99.15 218	92.90 280	97.96 191	98.97 186

nrg030		96.28 168	95.72 175	97.96 152	96.90 319	98.15 58	99.39 10	98.31 223	95.47 148	94.42 266	98.35 191	92.09 135	98.69 282	97.50 118	89.05 357	97.04 282

1314		96.25 170	95.73 174	97.79 163	97.13 305	95.55 184	98.19 250	98.59 158	93.47 263	92.03 355	97.82 244	91.33 158	99.49 177	94.62 224	98.44 173	98.32 244

sd_testset		96.17 171	95.76 173	97.42 193	99.30 72	94.34 249	98.82 135	99.08 38	95.92 125	95.96 228	98.76 152	82.83 331	99.32 199	95.56 193	95.59 263	98.60 225

h-mvs33		96.17 171	95.62 184	97.81 162	99.03 118	94.45 242	98.64 186	98.75 117	97.48 44	98.67 88	98.72 155	89.76 188	99.86 73	97.95 80	81.59 403	99.11 168

HQP_MVS		96.14 173	95.90 169	96.85 231	97.42 283	94.60 238	98.80 144	98.56 168	97.28 57	95.34 237	98.28 200	87.09 258	99.03 238	96.07 171	94.27 271	96.92 290

tttt0517		96.07 174	95.51 186	97.78 164	98.41 182	94.84 223	99.28 24	94.33 411	94.26 215	97.64 160	98.64 162	84.05 320	99.47 184	95.34 199	97.60 205	99.03 180

MVSTER		96.06 175	95.72 175	97.08 215	98.23 205	95.93 169	98.73 163	98.27 232	94.86 187	95.07 243	98.09 216	88.21 233	98.54 296	96.59 156	93.46 294	96.79 309

thisisatest0530		96.01 176	95.36 193	97.97 150	98.38 184	95.52 186	98.88 116	94.19 413	94.04 221	97.64 160	98.31 198	83.82 327	99.46 185	95.29 203	97.70 202	98.93 191

test_djsdf		96.00 177	95.69 181	96.93 225	95.72 371	95.49 187	99.47 7	98.40 205	94.98 179	94.58 256	97.86 237	89.16 207	98.41 316	96.91 137	94.12 279	96.88 299

EI-MVSNet		95.96 178	95.83 171	96.36 278	97.93 240	93.70 272	98.12 260	98.27 232	93.70 249	95.07 243	99.02 111	92.23 129	98.54 296	94.68 220	93.46 294	96.84 305

ECVR-MVS		95.95 179	95.71 178	96.65 243	99.02 119	90.86 336	99.03 76	91.80 424	96.96 79	98.10 119	99.26 67	81.31 338	99.51 173	96.90 140	99.04 138	99.59 85

BH-untuned		95.95 179	95.72 175	96.65 243	98.55 172	92.26 308	98.23 243	97.79 294	93.73 244	94.62 255	98.01 223	88.97 216	99.00 244	93.04 275	98.51 169	98.68 216

test1111		95.94 181	95.78 172	96.41 275	98.99 125	90.12 352	99.04 73	92.45 423	96.99 78	98.03 126	99.27 66	81.40 337	99.48 182	96.87 146	99.04 138	99.63 79

MSDG		95.93 182	95.30 200	97.83 159	98.90 133	95.36 193	96.83 379	98.37 213	91.32 341	94.43 265	98.73 154	90.27 182	99.60 152	90.05 342	98.82 154	98.52 232

BH-RMVSNet		95.92 183	95.32 198	97.69 175	98.32 198	94.64 232	98.19 250	97.45 327	94.56 202	96.03 224	98.61 163	85.02 296	99.12 224	90.68 333	99.06 137	99.30 133

test_fmvs1_n		95.90 184	95.99 166	95.63 312	98.67 160	88.32 389	99.26 27	98.22 239	96.40 107	99.67 22	99.26 67	73.91 401	99.70 130	99.02 29	99.50 106	98.87 195

Fast-Effi-MVS+-dtu		95.87 185	95.85 170	95.91 299	97.74 254	91.74 320	98.69 174	98.15 256	95.56 144	94.92 246	97.68 257	88.98 215	98.79 276	93.19 270	97.78 198	97.20 279

LFMVS		95.86 186	94.98 215	98.47 106	98.87 138	96.32 147	98.84 131	96.02 390	93.40 266	98.62 94	99.20 78	74.99 395	99.63 146	97.72 96	97.20 212	99.46 110

baseline1		95.84 187	95.12 208	98.01 148	98.49 178	95.98 158	98.73 163	97.03 359	95.37 156	96.22 217	98.19 210	89.96 186	99.16 215	94.60 225	87.48 373	98.90 194

OpenMVS	93.04 13	95.83 188	95.00 213	98.32 119	97.18 302	97.32 92	99.21 39	98.97 49	89.96 368	91.14 364	99.05 109	86.64 266	99.92 37	93.38 264	99.47 111	97.73 262

VDD-MVS		95.82 189	95.23 202	97.61 184	98.84 143	93.98 260	98.68 176	97.40 331	95.02 177	97.95 134	99.34 58	74.37 400	99.78 112	98.64 40	96.80 225	99.08 174

UniMVSNet (Re)		95.78 190	95.19 204	97.58 185	96.99 312	97.47 85	98.79 151	99.18 30	95.60 142	93.92 291	97.04 316	91.68 146	98.48 300	95.80 184	87.66 372	96.79 309

VPA-MVSNet		95.75 191	95.11 209	97.69 175	97.24 294	97.27 96	98.94 98	99.23 23	95.13 168	95.51 235	97.32 287	85.73 283	98.91 258	97.33 125	89.55 348	96.89 298

HQP-MVS		95.72 192	95.40 188	96.69 241	97.20 298	94.25 254	98.05 269	98.46 193	96.43 104	94.45 261	97.73 249	86.75 264	98.96 249	95.30 201	94.18 275	96.86 304

hse-mvs2		95.71 193	95.30 200	96.93 225	98.50 175	93.53 277	98.36 225	98.10 266	97.48 44	98.67 88	97.99 225	89.76 188	99.02 241	97.95 80	80.91 408	98.22 247

UniMVSNet_NR-MVSNet		95.71 193	95.15 205	97.40 196	96.84 322	96.97 112	98.74 159	99.24 18	95.16 167	93.88 293	97.72 251	91.68 146	98.31 329	95.81 182	87.25 378	96.92 290

PatchmatchNet		95.71 193	95.52 185	96.29 284	97.58 267	90.72 340	96.84 378	97.52 317	94.06 220	97.08 177	96.96 326	89.24 205	98.90 261	92.03 304	98.37 177	99.26 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 196	95.33 197	96.76 236	96.16 357	94.63 233	98.43 221	98.39 207	96.64 97	95.02 245	98.78 145	85.15 295	99.05 234	95.21 208	94.20 274	96.60 332
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 196	95.38 192	96.61 251	97.61 264	93.84 264	98.91 105	98.44 197	95.25 163	94.28 273	98.47 179	86.04 280	99.12 224	95.50 196	93.95 284	96.87 302
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 198	95.69 181	95.44 320	97.54 272	88.54 384	96.97 364	97.56 309	93.50 261	97.52 166	96.93 330	89.49 194	99.16 215	95.25 205	96.42 239	98.64 222

FE-MVS		95.62 199	94.90 219	97.78 164	98.37 186	94.92 220	97.17 354	97.38 333	90.95 352	97.73 150	97.70 252	85.32 293	99.63 146	91.18 320	98.33 180	98.79 201

LPG-MVS_test		95.62 199	95.34 194	96.47 269	97.46 278	93.54 275	98.99 86	98.54 172	94.67 196	94.36 269	98.77 147	85.39 288	99.11 226	95.71 188	94.15 277	96.76 312

CLD-MVS		95.62 199	95.34 194	96.46 272	97.52 275	93.75 268	97.27 345	98.46 193	95.53 145	94.42 266	98.00 224	86.21 275	98.97 245	96.25 169	94.37 269	96.66 327
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 202	94.89 220	97.76 168	98.15 218	95.15 206	96.77 380	94.41 409	92.95 287	97.18 174	97.43 278	84.78 302	99.45 186	94.63 222	97.73 201	98.68 216

MonoMVSNet		95.51 203	95.45 187	95.68 309	95.54 376	90.87 335	98.92 103	97.37 334	95.79 133	95.53 234	97.38 283	89.58 193	97.68 372	96.40 163	92.59 309	98.49 234

thres600view7		95.49 204	94.77 223	97.67 178	98.98 126	95.02 211	98.85 127	96.90 368	95.38 154	96.63 199	96.90 332	84.29 312	99.59 153	88.65 364	96.33 241	98.40 238

test_vis1_n		95.47 205	95.13 206	96.49 266	97.77 250	90.41 348	99.27 26	98.11 263	96.58 99	99.66 23	99.18 84	67.00 414	99.62 150	99.21 24	99.40 121	99.44 113

SCA		95.46 206	95.13 206	96.46 272	97.67 259	91.29 328	97.33 340	97.60 305	94.68 195	96.92 187	97.10 301	83.97 322	98.89 262	92.59 288	98.32 182	99.20 150

IterMVS-LS		95.46 206	95.21 203	96.22 286	98.12 219	93.72 271	98.32 232	98.13 259	93.71 247	94.26 274	97.31 288	92.24 128	98.10 345	94.63 222	90.12 339	96.84 305
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 208	95.34 194	95.77 307	98.69 157	88.75 380	98.87 119	97.21 346	96.13 118	97.22 172	97.68 257	77.95 372	99.65 140	97.58 109	96.77 228	98.91 193

jajsoiax		95.45 208	95.03 212	96.73 237	95.42 384	94.63 233	99.14 54	98.52 177	95.74 135	93.22 320	98.36 190	83.87 325	98.65 287	96.95 136	94.04 280	96.91 295

CVMVSNet		95.43 210	96.04 163	93.57 370	97.93 240	83.62 408	98.12 260	98.59 158	95.68 139	96.56 203	99.02 111	87.51 251	97.51 380	93.56 262	97.44 208	99.60 83

anonymousdsp		95.42 211	94.91 218	96.94 224	95.10 388	95.90 172	99.14 54	98.41 203	93.75 241	93.16 323	97.46 274	87.50 253	98.41 316	95.63 192	94.03 281	96.50 351

DU-MVS		95.42 211	94.76 224	97.40 196	96.53 339	96.97 112	98.66 182	98.99 48	95.43 150	93.88 293	97.69 254	88.57 224	98.31 329	95.81 182	87.25 378	96.92 290

mvs_tets		95.41 213	95.00 213	96.65 243	95.58 375	94.42 244	99.00 83	98.55 170	95.73 137	93.21 321	98.38 188	83.45 329	98.63 288	97.09 130	94.00 282	96.91 295

thres100view900		95.38 214	94.70 228	97.41 194	98.98 126	94.92 220	98.87 119	96.90 368	95.38 154	96.61 201	96.88 333	84.29 312	99.56 159	88.11 367	96.29 245	97.76 259

thres400		95.38 214	94.62 232	97.65 182	98.94 131	94.98 216	98.68 176	96.93 366	95.33 157	96.55 205	96.53 351	84.23 316	99.56 159	88.11 367	96.29 245	98.40 238

BH-w/o		95.38 214	95.08 210	96.26 285	98.34 192	91.79 317	97.70 312	97.43 329	92.87 290	94.24 276	97.22 295	88.66 222	98.84 268	91.55 316	97.70 202	98.16 250

VDDNet		95.36 217	94.53 237	97.86 157	98.10 221	95.13 207	98.85 127	97.75 296	90.46 359	98.36 109	99.39 42	73.27 403	99.64 143	97.98 79	96.58 233	98.81 200

TAPA-MVS	93.98 7	95.35 218	94.56 236	97.74 170	99.13 108	94.83 225	98.33 228	98.64 148	86.62 394	96.29 216	98.61 163	94.00 101	99.29 202	80.00 409	99.41 118	99.09 170
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 219	94.98 215	96.43 274	97.67 259	93.48 279	98.73 163	98.44 197	94.94 185	92.53 343	98.53 173	84.50 311	99.14 220	95.48 197	94.00 282	96.66 327
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 220	94.87 221	96.71 238	99.29 77	93.24 293	98.58 195	98.11 263	89.92 369	93.57 305	99.10 97	86.37 273	99.79 109	90.78 331	98.10 187	97.09 280
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 221	94.72 227	97.13 210	98.05 227	93.26 290	97.87 295	97.20 347	94.96 181	96.18 220	95.66 383	80.97 344	99.35 195	94.47 231	97.08 215	98.78 204

tfpn200view9		95.32 221	94.62 232	97.43 192	98.94 131	94.98 216	98.68 176	96.93 366	95.33 157	96.55 205	96.53 351	84.23 316	99.56 159	88.11 367	96.29 245	97.76 259

Anonymous202405211		95.28 223	94.49 239	97.67 178	99.00 122	93.75 268	98.70 172	97.04 358	90.66 355	96.49 209	98.80 143	78.13 368	99.83 80	96.21 170	95.36 267	99.44 113

thres200		95.25 224	94.57 235	97.28 200	98.81 145	94.92 220	98.20 247	97.11 351	95.24 165	96.54 207	96.22 362	84.58 309	99.53 169	87.93 372	96.50 237	97.39 273

AllTest		95.24 225	94.65 231	96.99 219	99.25 85	93.21 294	98.59 193	98.18 247	91.36 337	93.52 307	98.77 147	84.67 306	99.72 124	89.70 349	97.87 194	98.02 254

LCM-MVSNet-Re		95.22 226	95.32 198	94.91 337	98.18 213	87.85 395	98.75 155	95.66 397	95.11 170	88.96 383	96.85 336	90.26 183	97.65 373	95.65 191	98.44 173	99.22 147

EPNet_dtu		95.21 227	94.95 217	95.99 294	96.17 355	90.45 346	98.16 256	97.27 342	96.77 87	93.14 326	98.33 196	90.34 179	98.42 309	85.57 385	98.81 155	99.09 170
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 228	94.45 244	97.46 189	96.75 329	96.56 134	98.86 123	98.65 147	93.30 271	93.27 319	98.27 203	84.85 300	98.87 265	94.82 217	91.26 325	96.96 286

D2MVS		95.18 229	95.08 210	95.48 317	97.10 307	92.07 313	98.30 235	99.13 36	94.02 223	92.90 331	96.73 342	89.48 195	98.73 280	94.48 230	93.60 293	95.65 379

WR-MVS		95.15 230	94.46 242	97.22 202	96.67 334	96.45 138	98.21 245	98.81 97	94.15 217	93.16 323	97.69 254	87.51 251	98.30 331	95.29 203	88.62 363	96.90 297

TranMVSNet+NR-MVSNet		95.14 231	94.48 240	97.11 213	96.45 345	96.36 145	99.03 76	99.03 43	95.04 175	93.58 304	97.93 230	88.27 232	98.03 351	94.13 242	86.90 383	96.95 288

myMVS_eth3d28		95.12 232	94.62 232	96.64 247	98.17 216	92.17 309	98.02 273	97.32 336	95.41 152	96.22 217	96.05 368	78.01 370	99.13 221	95.22 207	97.16 213	98.60 225

baseline2		95.11 233	94.52 238	96.87 230	96.65 335	93.56 274	98.27 240	94.10 415	93.45 264	92.02 356	97.43 278	87.45 255	99.19 213	93.88 251	97.41 210	97.87 257

miper_enhance_ethall		95.10 234	94.75 225	96.12 290	97.53 274	93.73 270	96.61 386	98.08 271	92.20 317	93.89 292	96.65 347	92.44 120	98.30 331	94.21 240	91.16 326	96.34 360

Anonymous20240529		95.10 234	94.22 254	97.75 169	99.01 121	94.26 253	98.87 119	98.83 88	85.79 402	96.64 198	98.97 118	78.73 361	99.85 74	96.27 166	94.89 268	99.12 165

test-LLR		95.10 234	94.87 221	95.80 304	96.77 326	89.70 360	96.91 369	95.21 401	95.11 170	94.83 250	95.72 380	87.71 247	98.97 245	93.06 273	98.50 170	98.72 209

WR-MVS_H		95.05 237	94.46 242	96.81 234	96.86 321	95.82 175	99.24 30	99.24 18	93.87 235	92.53 343	96.84 337	90.37 178	98.24 337	93.24 268	87.93 369	96.38 359

miper_ehance_all_eth		95.01 238	94.69 229	95.97 296	97.70 257	93.31 288	97.02 362	98.07 273	92.23 314	93.51 309	96.96 326	91.85 142	98.15 341	93.68 256	91.16 326	96.44 357

testing11		95.00 239	94.28 251	97.16 208	97.96 237	93.36 287	98.09 265	97.06 357	94.94 185	95.33 240	96.15 364	76.89 385	99.40 190	95.77 186	96.30 244	98.72 209

ADS-MVSNet		95.00 239	94.45 244	96.63 248	98.00 231	91.91 316	96.04 393	97.74 297	90.15 365	96.47 210	96.64 348	87.89 243	98.96 249	90.08 340	97.06 216	99.02 181

VPNet		94.99 241	94.19 256	97.40 196	97.16 303	96.57 133	98.71 168	98.97 49	95.67 140	94.84 248	98.24 207	80.36 351	98.67 286	96.46 160	87.32 377	96.96 286

EPMVS		94.99 241	94.48 240	96.52 264	97.22 296	91.75 319	97.23 346	91.66 425	94.11 218	97.28 169	96.81 339	85.70 284	98.84 268	93.04 275	97.28 211	98.97 186

testing91		94.98 243	94.25 253	97.20 203	97.94 238	93.41 282	98.00 276	97.58 306	94.99 178	95.45 236	96.04 369	77.20 380	99.42 189	94.97 213	96.02 258	98.78 204

NR-MVSNet		94.98 243	94.16 259	97.44 191	96.53 339	97.22 103	98.74 159	98.95 53	94.96 181	89.25 382	97.69 254	89.32 202	98.18 339	94.59 227	87.40 375	96.92 290

FMVSNet3		94.97 245	94.26 252	97.11 213	98.18 213	96.62 127	98.56 203	98.26 236	93.67 254	94.09 283	97.10 301	84.25 314	98.01 352	92.08 300	92.14 312	96.70 321

CostFormer		94.95 246	94.73 226	95.60 314	97.28 292	89.06 373	97.53 324	96.89 370	89.66 374	96.82 192	96.72 343	86.05 278	98.95 254	95.53 195	96.13 256	98.79 201

PAPM		94.95 246	94.00 272	97.78 164	97.04 309	95.65 179	96.03 395	98.25 237	91.23 346	94.19 279	97.80 246	91.27 161	98.86 267	82.61 402	97.61 204	98.84 198

CP-MVSNet		94.94 248	94.30 250	96.83 232	96.72 331	95.56 182	99.11 60	98.95 53	93.89 233	92.42 348	97.90 233	87.19 257	98.12 344	94.32 236	88.21 366	96.82 308

TR-MVS		94.94 248	94.20 255	97.17 207	97.75 251	94.14 257	97.59 321	97.02 361	92.28 313	95.75 232	97.64 262	83.88 324	98.96 249	89.77 346	96.15 255	98.40 238

RPSCF		94.87 250	95.40 188	93.26 376	98.89 134	82.06 414	98.33 228	98.06 278	90.30 364	96.56 203	99.26 67	87.09 258	99.49 177	93.82 253	96.32 242	98.24 245

testing99		94.83 251	94.08 264	97.07 216	97.94 238	93.13 296	98.10 264	97.17 349	94.86 187	95.34 237	96.00 372	76.31 388	99.40 190	95.08 210	95.90 259	98.68 216

GA-MVS		94.81 252	94.03 268	97.14 209	97.15 304	93.86 263	96.76 381	97.58 306	94.00 227	94.76 254	97.04 316	80.91 345	98.48 300	91.79 310	96.25 251	99.09 170

c3_l		94.79 253	94.43 246	95.89 301	97.75 251	93.12 298	97.16 356	98.03 280	92.23 314	93.46 313	97.05 315	91.39 155	98.01 352	93.58 261	89.21 355	96.53 343

V42		94.78 254	94.14 261	96.70 240	96.33 350	95.22 202	98.97 89	98.09 270	92.32 311	94.31 272	97.06 312	88.39 230	98.55 295	92.90 280	88.87 361	96.34 360

reproduce_monomvs		94.77 255	94.67 230	95.08 332	98.40 183	89.48 366	98.80 144	98.64 148	97.57 38	93.21 321	97.65 259	80.57 350	98.83 271	97.72 96	89.47 351	96.93 289

CR-MVSNet		94.76 256	94.15 260	96.59 254	97.00 310	93.43 280	94.96 406	97.56 309	92.46 302	96.93 185	96.24 358	88.15 235	97.88 365	87.38 374	96.65 231	98.46 236

v2v482		94.69 257	94.03 268	96.65 243	96.17 355	94.79 228	98.67 180	98.08 271	92.72 294	94.00 288	97.16 298	87.69 250	98.45 305	92.91 279	88.87 361	96.72 317

pmmvs4		94.69 257	93.99 274	96.81 234	95.74 370	95.94 166	97.40 331	97.67 300	90.42 361	93.37 316	97.59 266	89.08 210	98.20 338	92.97 277	91.67 319	96.30 363

cl22		94.68 259	94.19 256	96.13 289	98.11 220	93.60 273	96.94 366	98.31 223	92.43 306	93.32 318	96.87 335	86.51 267	98.28 335	94.10 245	91.16 326	96.51 349

eth_miper_zixun_eth		94.68 259	94.41 247	95.47 318	97.64 262	91.71 321	96.73 383	98.07 273	92.71 295	93.64 302	97.21 296	90.54 176	98.17 340	93.38 264	89.76 343	96.54 341

PCF-MVS	93.45 11	94.68 259	93.43 310	98.42 114	98.62 167	96.77 122	95.48 403	98.20 242	84.63 407	93.34 317	98.32 197	88.55 227	99.81 92	84.80 394	98.96 144	98.68 216
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 262	93.54 305	98.08 143	96.88 320	96.56 134	98.19 250	98.50 185	78.05 418	92.69 338	98.02 221	91.07 167	99.63 146	90.09 339	98.36 179	98.04 253

PS-CasMVS		94.67 262	93.99 274	96.71 238	96.68 333	95.26 199	99.13 57	99.03 43	93.68 252	92.33 349	97.95 229	85.35 290	98.10 345	93.59 260	88.16 368	96.79 309

cascas		94.63 264	93.86 284	96.93 225	96.91 318	94.27 252	96.00 396	98.51 180	85.55 403	94.54 257	96.23 360	84.20 318	98.87 265	95.80 184	96.98 221	97.66 265

tpmvs		94.60 265	94.36 249	95.33 324	97.46 278	88.60 383	96.88 375	97.68 298	91.29 343	93.80 298	96.42 355	88.58 223	99.24 207	91.06 326	96.04 257	98.17 249

LTVRE_ROB	92.95 15	94.60 265	93.90 280	96.68 242	97.41 286	94.42 244	98.52 206	98.59 158	91.69 329	91.21 363	98.35 191	84.87 299	99.04 237	91.06 326	93.44 297	96.60 332
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		94.59 267	93.92 277	96.60 253	96.21 352	94.78 229	98.59 193	98.14 258	91.86 325	94.21 278	97.02 319	87.97 241	98.41 316	91.72 312	89.57 346	96.61 331

ADS-MVSNet2		94.58 268	94.40 248	95.11 330	98.00 231	88.74 381	96.04 393	97.30 338	90.15 365	96.47 210	96.64 348	87.89 243	97.56 378	90.08 340	97.06 216	99.02 181

WBMVS		94.56 269	94.04 266	96.10 291	98.03 229	93.08 300	97.82 303	98.18 247	94.02 223	93.77 300	96.82 338	81.28 339	98.34 324	95.47 198	91.00 329	96.88 299

ACMH	92.88 16	94.55 270	93.95 276	96.34 280	97.63 263	93.26 290	98.81 143	98.49 190	93.43 265	89.74 377	98.53 173	81.91 334	99.08 232	93.69 255	93.30 300	96.70 321
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 271	93.85 285	96.63 248	97.98 235	93.06 301	98.77 154	97.84 292	93.67 254	93.80 298	98.04 220	76.88 386	98.96 249	94.79 219	92.86 305	97.86 258

XVG-ACMP-BASELINE		94.54 271	94.14 261	95.75 308	96.55 338	91.65 322	98.11 262	98.44 197	94.96 181	94.22 277	97.90 233	79.18 360	99.11 226	94.05 247	93.85 286	96.48 354

AUN-MVS		94.53 273	93.73 295	96.92 228	98.50 175	93.52 278	98.34 227	98.10 266	93.83 238	95.94 230	97.98 227	85.59 286	99.03 238	94.35 234	80.94 407	98.22 247

DIV-MVS_self_test		94.52 274	94.03 268	95.99 294	97.57 271	93.38 285	97.05 360	97.94 286	91.74 326	92.81 333	97.10 301	89.12 208	98.07 349	92.60 286	90.30 336	96.53 343

cl____		94.51 275	94.01 271	96.02 293	97.58 267	93.40 284	97.05 360	97.96 285	91.73 328	92.76 335	97.08 307	89.06 211	98.13 343	92.61 285	90.29 337	96.52 346

ETVMVS		94.50 276	93.44 309	97.68 177	98.18 213	95.35 195	98.19 250	97.11 351	93.73 244	96.40 213	95.39 386	74.53 397	98.84 268	91.10 322	96.31 243	98.84 198

GBi-Net		94.49 277	93.80 288	96.56 258	98.21 207	95.00 212	98.82 135	98.18 247	92.46 302	94.09 283	97.07 308	81.16 340	97.95 357	92.08 300	92.14 312	96.72 317

test1		94.49 277	93.80 288	96.56 258	98.21 207	95.00 212	98.82 135	98.18 247	92.46 302	94.09 283	97.07 308	81.16 340	97.95 357	92.08 300	92.14 312	96.72 317

dmvs_re		94.48 279	94.18 258	95.37 322	97.68 258	90.11 353	98.54 205	97.08 353	94.56 202	94.42 266	97.24 293	84.25 314	97.76 370	91.02 329	92.83 306	98.24 245

v8		94.47 280	93.77 291	96.57 257	96.36 348	94.83 225	99.05 69	98.19 244	91.92 322	93.16 323	96.97 324	88.82 221	98.48 300	91.69 313	87.79 370	96.39 358

FMVSNet2		94.47 280	93.61 301	97.04 217	98.21 207	96.43 140	98.79 151	98.27 232	92.46 302	93.50 310	97.09 305	81.16 340	98.00 354	91.09 323	91.93 315	96.70 321

test2506		94.44 282	93.91 279	96.04 292	99.02 119	88.99 376	99.06 67	79.47 437	96.96 79	98.36 109	99.26 67	77.21 379	99.52 172	96.78 153	99.04 138	99.59 85

Patchmatch-test		94.42 283	93.68 299	96.63 248	97.60 265	91.76 318	94.83 410	97.49 321	89.45 378	94.14 281	97.10 301	88.99 212	98.83 271	85.37 388	98.13 186	99.29 135

PEN-MVS		94.42 283	93.73 295	96.49 266	96.28 351	94.84 223	99.17 49	99.00 45	93.51 260	92.23 351	97.83 243	86.10 277	97.90 361	92.55 291	86.92 382	96.74 314

v144192		94.39 285	93.70 297	96.48 268	96.06 360	94.35 248	98.58 195	98.16 255	91.45 334	94.33 271	97.02 319	87.50 253	98.45 305	91.08 325	89.11 356	96.63 329

Baseline_NR-MVSNet		94.35 286	93.81 287	95.96 297	96.20 353	94.05 259	98.61 192	96.67 380	91.44 335	93.85 295	97.60 265	88.57 224	98.14 342	94.39 232	86.93 381	95.68 378

miper_lstm_enhance		94.33 287	94.07 265	95.11 330	97.75 251	90.97 332	97.22 347	98.03 280	91.67 330	92.76 335	96.97 324	90.03 185	97.78 369	92.51 293	89.64 345	96.56 338

v1192		94.32 288	93.58 302	96.53 263	96.10 358	94.45 242	98.50 212	98.17 253	91.54 332	94.19 279	97.06 312	86.95 262	98.43 308	90.14 338	89.57 346	96.70 321

UWE-MVS		94.30 289	93.89 282	95.53 315	97.83 246	88.95 377	97.52 326	93.25 417	94.44 210	96.63 199	97.07 308	78.70 362	99.28 203	91.99 305	97.56 207	98.36 241

ACMH+	92.99 14	94.30 289	93.77 291	95.88 302	97.81 248	92.04 315	98.71 168	98.37 213	93.99 228	90.60 370	98.47 179	80.86 347	99.05 234	92.75 284	92.40 311	96.55 340

v148		94.29 291	93.76 293	95.91 299	96.10 358	92.93 302	98.58 195	97.97 283	92.59 300	93.47 312	96.95 328	88.53 228	98.32 327	92.56 290	87.06 380	96.49 352

v10		94.29 291	93.55 304	96.51 265	96.39 347	94.80 227	98.99 86	98.19 244	91.35 339	93.02 329	96.99 322	88.09 237	98.41 316	90.50 335	88.41 365	96.33 362

MVP-Stereo		94.28 293	93.92 277	95.35 323	94.95 390	92.60 305	97.97 279	97.65 301	91.61 331	90.68 369	97.09 305	86.32 274	98.42 309	89.70 349	99.34 127	95.02 392
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 294	93.33 312	96.97 222	97.19 301	93.38 285	98.74 159	98.57 165	91.21 348	93.81 297	98.58 168	72.85 404	98.77 278	95.05 211	93.93 285	98.77 207

OurMVSNet-221017-0		94.21 295	94.00 272	94.85 341	95.60 374	89.22 371	98.89 110	97.43 329	95.29 160	92.18 352	98.52 176	82.86 330	98.59 293	93.46 263	91.76 317	96.74 314

v1921920		94.20 296	93.47 308	96.40 277	95.98 363	94.08 258	98.52 206	98.15 256	91.33 340	94.25 275	97.20 297	86.41 272	98.42 309	90.04 343	89.39 353	96.69 326

WB-MVSnew		94.19 297	94.04 266	94.66 348	96.82 324	92.14 310	97.86 297	95.96 393	93.50 261	95.64 233	96.77 341	88.06 239	97.99 355	84.87 391	96.86 222	93.85 409

v7n		94.19 297	93.43 310	96.47 269	95.90 366	94.38 247	99.26 27	98.34 219	91.99 320	92.76 335	97.13 300	88.31 231	98.52 298	89.48 354	87.70 371	96.52 346

tpm2		94.19 297	93.76 293	95.46 319	97.23 295	89.04 374	97.31 342	96.85 374	87.08 393	96.21 219	96.79 340	83.75 328	98.74 279	92.43 296	96.23 253	98.59 228

TESTMET0.1,1		94.18 300	93.69 298	95.63 312	96.92 316	89.12 372	96.91 369	94.78 406	93.17 276	94.88 247	96.45 354	78.52 363	98.92 256	93.09 272	98.50 170	98.85 196

dp		94.15 301	93.90 280	94.90 338	97.31 291	86.82 400	96.97 364	97.19 348	91.22 347	96.02 225	96.61 350	85.51 287	99.02 241	90.00 344	94.30 270	98.85 196

ET-MVSNet_ETH3D		94.13 302	92.98 320	97.58 185	98.22 206	96.20 151	97.31 342	95.37 400	94.53 204	79.56 418	97.63 264	86.51 267	97.53 379	96.91 137	90.74 331	99.02 181

tpm		94.13 302	93.80 288	95.12 329	96.50 341	87.91 394	97.44 328	95.89 396	92.62 298	96.37 215	96.30 357	84.13 319	98.30 331	93.24 268	91.66 320	99.14 163

testing222		94.12 304	93.03 319	97.37 199	98.02 230	94.66 230	97.94 283	96.65 382	94.63 198	95.78 231	95.76 375	71.49 405	98.92 256	91.17 321	95.88 260	98.52 232

IterMVS-SCA-FT		94.11 305	93.87 283	94.85 341	97.98 235	90.56 345	97.18 352	98.11 263	93.75 241	92.58 341	97.48 273	83.97 322	97.41 382	92.48 295	91.30 323	96.58 334

Anonymous20231211		94.10 306	93.26 315	96.61 251	99.11 111	94.28 251	99.01 81	98.88 69	86.43 396	92.81 333	97.57 268	81.66 336	98.68 285	94.83 216	89.02 359	96.88 299

IterMVS		94.09 307	93.85 285	94.80 344	97.99 233	90.35 349	97.18 352	98.12 260	93.68 252	92.46 347	97.34 284	84.05 320	97.41 382	92.51 293	91.33 322	96.62 330
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 308	93.51 306	95.80 304	96.77 326	89.70 360	96.91 369	95.21 401	92.89 289	94.83 250	95.72 380	77.69 374	98.97 245	93.06 273	98.50 170	98.72 209

test0.0.03 1		94.08 308	93.51 306	95.80 304	95.53 378	92.89 303	97.38 333	95.97 392	95.11 170	92.51 345	96.66 345	87.71 247	96.94 389	87.03 376	93.67 289	97.57 269

v1240		94.06 310	93.29 314	96.34 280	96.03 362	93.90 262	98.44 219	98.17 253	91.18 349	94.13 282	97.01 321	86.05 278	98.42 309	89.13 359	89.50 350	96.70 321

X-MVStestdata		94.06 310	92.30 336	99.34 26	99.70 22	98.35 44	99.29 22	98.88 69	97.40 48	98.46 101	43.50 432	95.90 45	99.89 58	97.85 88	99.74 52	99.78 25

DTE-MVSNet		93.98 312	93.26 315	96.14 288	96.06 360	94.39 246	99.20 42	98.86 82	93.06 282	91.78 357	97.81 245	85.87 282	97.58 377	90.53 334	86.17 387	96.46 356

pm-mvs1		93.94 313	93.06 318	96.59 254	96.49 342	95.16 204	98.95 95	98.03 280	92.32 311	91.08 365	97.84 240	84.54 310	98.41 316	92.16 298	86.13 390	96.19 367

MS-PatchMatch		93.84 314	93.63 300	94.46 358	96.18 354	89.45 367	97.76 307	98.27 232	92.23 314	92.13 353	97.49 272	79.50 357	98.69 282	89.75 347	99.38 123	95.25 384

tfpnnormal		93.66 315	92.70 326	96.55 262	96.94 315	95.94 166	98.97 89	99.19 29	91.04 350	91.38 362	97.34 284	84.94 298	98.61 290	85.45 387	89.02 359	95.11 388

EU-MVSNet		93.66 315	94.14 261	92.25 386	95.96 365	83.38 410	98.52 206	98.12 260	94.69 194	92.61 340	98.13 214	87.36 256	96.39 402	91.82 309	90.00 341	96.98 285

our_test_3		93.65 317	93.30 313	94.69 346	95.45 382	89.68 362	96.91 369	97.65 301	91.97 321	91.66 360	96.88 333	89.67 192	97.93 360	88.02 370	91.49 321	96.48 354

pmmvs5		93.65 317	92.97 321	95.68 309	95.49 379	92.37 306	98.20 247	97.28 341	89.66 374	92.58 341	97.26 290	82.14 333	98.09 347	93.18 271	90.95 330	96.58 334

SSC-MVS3.2		93.59 319	93.13 317	94.97 335	96.81 325	89.71 359	97.95 280	98.49 190	94.59 201	93.50 310	96.91 331	77.74 373	98.37 323	91.69 313	90.47 334	96.83 307

test_fmvs2		93.43 320	93.58 302	92.95 380	96.97 313	83.91 406	99.19 44	97.24 344	95.74 135	95.20 242	98.27 203	69.65 407	98.72 281	96.26 167	93.73 288	96.24 364

tpm cat1		93.36 321	92.80 323	95.07 333	97.58 267	87.97 393	96.76 381	97.86 291	82.17 414	93.53 306	96.04 369	86.13 276	99.13 221	89.24 357	95.87 261	98.10 252

JIA-IIPM		93.35 322	92.49 332	95.92 298	96.48 343	90.65 342	95.01 405	96.96 364	85.93 400	96.08 223	87.33 422	87.70 249	98.78 277	91.35 318	95.58 265	98.34 242

SixPastTwentyTwo		93.34 323	92.86 322	94.75 345	95.67 372	89.41 369	98.75 155	96.67 380	93.89 233	90.15 375	98.25 206	80.87 346	98.27 336	90.90 330	90.64 332	96.57 336

USDC		93.33 324	92.71 325	95.21 326	96.83 323	90.83 338	96.91 369	97.50 319	93.84 236	90.72 368	98.14 213	77.69 374	98.82 273	89.51 353	93.21 302	95.97 372

IB-MVS	91.98 17	93.27 325	91.97 340	97.19 205	97.47 277	93.41 282	97.09 359	95.99 391	93.32 269	92.47 346	95.73 378	78.06 369	99.53 169	94.59 227	82.98 398	98.62 223
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		93.26 326	92.21 337	96.41 275	97.73 255	93.13 296	95.65 400	97.03 359	91.27 345	94.04 286	96.06 367	75.33 393	97.19 385	86.56 378	96.23 253	98.92 192

ppachtmachnet_test		93.22 327	92.63 327	94.97 335	95.45 382	90.84 337	96.88 375	97.88 290	90.60 356	92.08 354	97.26 290	88.08 238	97.86 366	85.12 390	90.33 335	96.22 365

Patchmtry		93.22 327	92.35 335	95.84 303	96.77 326	93.09 299	94.66 413	97.56 309	87.37 392	92.90 331	96.24 358	88.15 235	97.90 361	87.37 375	90.10 340	96.53 343

testing3		93.19 329	92.48 333	95.30 325	98.07 222	92.27 307	98.64 186	97.17 349	93.94 232	93.98 289	97.04 316	67.97 411	96.01 406	88.40 365	97.14 214	97.63 266

FMVSNet1		93.19 329	92.07 338	96.56 258	97.54 272	95.00 212	98.82 135	98.18 247	90.38 362	92.27 350	97.07 308	73.68 402	97.95 357	89.36 356	91.30 323	96.72 317

LF4IMVS		93.14 331	92.79 324	94.20 362	95.88 367	88.67 382	97.66 315	97.07 355	93.81 239	91.71 358	97.65 259	77.96 371	98.81 274	91.47 317	91.92 316	95.12 387

mmtdpeth		93.12 332	92.61 328	94.63 350	97.60 265	89.68 362	99.21 39	97.32 336	94.02 223	97.72 151	94.42 397	77.01 384	99.44 187	99.05 27	77.18 419	94.78 397

testgi		93.06 333	92.45 334	94.88 340	96.43 346	89.90 354	98.75 155	97.54 315	95.60 142	91.63 361	97.91 232	74.46 399	97.02 387	86.10 381	93.67 289	97.72 263

PatchT		93.06 333	91.97 340	96.35 279	96.69 332	92.67 304	94.48 416	97.08 353	86.62 394	97.08 177	92.23 416	87.94 242	97.90 361	78.89 413	96.69 229	98.49 234

RPMNet		92.81 335	91.34 346	97.24 201	97.00 310	93.43 280	94.96 406	98.80 104	82.27 413	96.93 185	92.12 417	86.98 261	99.82 87	76.32 418	96.65 231	98.46 236

UWE-MVS-28		92.79 336	92.51 331	93.62 369	96.46 344	86.28 401	97.93 284	92.71 422	94.17 216	94.78 253	97.16 298	81.05 343	96.43 401	81.45 405	96.86 222	98.14 251

myMVS_eth3d		92.73 337	92.01 339	94.89 339	97.39 287	90.94 333	97.91 287	97.46 323	93.16 277	93.42 314	95.37 387	68.09 410	96.12 404	88.34 366	96.99 218	97.60 267

TransMVSNet (Re)		92.67 338	91.51 345	96.15 287	96.58 337	94.65 231	98.90 106	96.73 376	90.86 353	89.46 381	97.86 237	85.62 285	98.09 347	86.45 379	81.12 405	95.71 377

ttmdpeth		92.61 339	91.96 342	94.55 352	94.10 400	90.60 344	98.52 206	97.29 339	92.67 296	90.18 373	97.92 231	79.75 356	97.79 368	91.09 323	86.15 389	95.26 383

Syy-MVS		92.55 340	92.61 328	92.38 383	97.39 287	83.41 409	97.91 287	97.46 323	93.16 277	93.42 314	95.37 387	84.75 303	96.12 404	77.00 417	96.99 218	97.60 267

K. test v3		92.55 340	91.91 343	94.48 356	95.64 373	89.24 370	99.07 66	94.88 405	94.04 221	86.78 397	97.59 266	77.64 377	97.64 374	92.08 300	89.43 352	96.57 336

DSMNet-mixed		92.52 342	92.58 330	92.33 384	94.15 399	82.65 412	98.30 235	94.26 412	89.08 383	92.65 339	95.73 378	85.01 297	95.76 408	86.24 380	97.76 199	98.59 228

TinyColmap		92.31 343	91.53 344	94.65 349	96.92 316	89.75 357	96.92 367	96.68 379	90.45 360	89.62 378	97.85 239	76.06 391	98.81 274	86.74 377	92.51 310	95.41 381

gg-mvs-nofinetune		92.21 344	90.58 352	97.13 210	96.75 329	95.09 208	95.85 397	89.40 430	85.43 404	94.50 259	81.98 425	80.80 348	98.40 322	92.16 298	98.33 180	97.88 256

FMVSNet5		91.81 345	90.92 348	94.49 355	97.21 297	92.09 312	98.00 276	97.55 314	89.31 381	90.86 367	95.61 384	74.48 398	95.32 412	85.57 385	89.70 344	96.07 370

pmmvs6		91.77 346	90.63 351	95.17 328	94.69 396	91.24 329	98.67 180	97.92 288	86.14 398	89.62 378	97.56 270	75.79 392	98.34 324	90.75 332	84.56 392	95.94 373

Anonymous20231206		91.66 347	91.10 347	93.33 374	94.02 404	87.35 397	98.58 195	97.26 343	90.48 358	90.16 374	96.31 356	83.83 326	96.53 399	79.36 411	89.90 342	96.12 368

Patchmatch-RL test		91.49 348	90.85 349	93.41 372	91.37 415	84.40 404	92.81 420	95.93 395	91.87 324	87.25 393	94.87 393	88.99 212	96.53 399	92.54 292	82.00 400	99.30 133

test_0402		91.32 349	90.27 355	94.48 356	96.60 336	91.12 330	98.50 212	97.22 345	86.10 399	88.30 389	96.98 323	77.65 376	97.99 355	78.13 415	92.94 304	94.34 398

test_vis1_rt		91.29 350	90.65 350	93.19 378	97.45 281	86.25 402	98.57 202	90.90 428	93.30 271	86.94 396	93.59 406	62.07 420	99.11 226	97.48 119	95.58 265	94.22 401

PVSNet_0	88.72 19	91.28 351	90.03 358	95.00 334	97.99 233	87.29 398	94.84 409	98.50 185	92.06 319	89.86 376	95.19 389	79.81 355	99.39 193	92.27 297	69.79 425	98.33 243

mvs5depth		91.23 352	90.17 356	94.41 360	92.09 412	89.79 356	95.26 404	96.50 384	90.73 354	91.69 359	97.06 312	76.12 390	98.62 289	88.02 370	84.11 395	94.82 394

Anonymous20240521		91.18 353	90.44 353	93.42 371	93.70 405	88.47 386	98.94 98	97.56 309	88.46 387	89.56 380	95.08 392	77.15 382	96.97 388	83.92 397	89.55 348	94.82 394

EG-PatchMatch MVS		91.13 354	90.12 357	94.17 364	94.73 395	89.00 375	98.13 259	97.81 293	89.22 382	85.32 407	96.46 353	67.71 412	98.42 309	87.89 373	93.82 287	95.08 389

TDRefinement		91.06 355	89.68 360	95.21 326	85.35 430	91.49 325	98.51 211	97.07 355	91.47 333	88.83 387	97.84 240	77.31 378	99.09 231	92.79 283	77.98 417	95.04 391

UnsupCasMVSNet_eth		90.99 356	89.92 359	94.19 363	94.08 401	89.83 355	97.13 358	98.67 140	93.69 250	85.83 403	96.19 363	75.15 394	96.74 393	89.14 358	79.41 412	96.00 371

test20.03		90.89 357	90.38 354	92.43 382	93.48 406	88.14 392	98.33 228	97.56 309	93.40 266	87.96 390	96.71 344	80.69 349	94.13 417	79.15 412	86.17 387	95.01 393

MDA-MVSNet_test_wron		90.71 358	89.38 363	94.68 347	94.83 392	90.78 339	97.19 351	97.46 323	87.60 390	72.41 425	95.72 380	86.51 267	96.71 396	85.92 383	86.80 384	96.56 338

YYNet1		90.70 359	89.39 362	94.62 351	94.79 394	90.65 342	97.20 349	97.46 323	87.54 391	72.54 424	95.74 376	86.51 267	96.66 397	86.00 382	86.76 385	96.54 341

KD-MVS_self_test		90.38 360	89.38 363	93.40 373	92.85 409	88.94 378	97.95 280	97.94 286	90.35 363	90.25 372	93.96 403	79.82 354	95.94 407	84.62 396	76.69 420	95.33 382

pmmvs-eth3d		90.36 361	89.05 366	94.32 361	91.10 417	92.12 311	97.63 320	96.95 365	88.86 385	84.91 408	93.13 411	78.32 365	96.74 393	88.70 362	81.81 402	94.09 404

CL-MVSNet_self_test		90.11 362	89.14 365	93.02 379	91.86 414	88.23 391	96.51 389	98.07 273	90.49 357	90.49 371	94.41 398	84.75 303	95.34 411	80.79 407	74.95 422	95.50 380

new_pmnet		90.06 363	89.00 367	93.22 377	94.18 398	88.32 389	96.42 391	96.89 370	86.19 397	85.67 404	93.62 405	77.18 381	97.10 386	81.61 404	89.29 354	94.23 400

MDA-MVSNet-bldmvs		89.97 364	88.35 370	94.83 343	95.21 386	91.34 326	97.64 317	97.51 318	88.36 388	71.17 426	96.13 365	79.22 359	96.63 398	83.65 398	86.27 386	96.52 346

CMPMVS	66.06 21	89.70 365	89.67 361	89.78 391	93.19 407	76.56 417	97.00 363	98.35 216	80.97 415	81.57 413	97.75 248	74.75 396	98.61 290	89.85 345	93.63 291	94.17 402
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 366	88.28 371	93.82 367	92.81 410	91.08 331	98.01 274	97.45 327	87.95 389	87.90 391	95.87 374	67.63 413	94.56 416	78.73 414	88.18 367	95.83 375

KD-MVS_2432*1600		89.61 367	87.96 375	94.54 353	94.06 402	91.59 323	95.59 401	97.63 303	89.87 370	88.95 384	94.38 400	78.28 366	96.82 391	84.83 392	68.05 426	95.21 385

miper_refine_blended		89.61 367	87.96 375	94.54 353	94.06 402	91.59 323	95.59 401	97.63 303	89.87 370	88.95 384	94.38 400	78.28 366	96.82 391	84.83 392	68.05 426	95.21 385

MVStest1		89.53 369	87.99 374	94.14 366	94.39 397	90.42 347	98.25 242	96.84 375	82.81 410	81.18 415	97.33 286	77.09 383	96.94 389	85.27 389	78.79 413	95.06 390

MVS-HIRNet		89.46 370	88.40 369	92.64 381	97.58 267	82.15 413	94.16 419	93.05 421	75.73 421	90.90 366	82.52 424	79.42 358	98.33 326	83.53 399	98.68 157	97.43 270

OpenMVS_ROB	86.42 20	89.00 371	87.43 379	93.69 368	93.08 408	89.42 368	97.91 287	96.89 370	78.58 417	85.86 402	94.69 394	69.48 408	98.29 334	77.13 416	93.29 301	93.36 411

mvsany_test3		88.80 372	88.04 372	91.09 390	89.78 420	81.57 415	97.83 302	95.49 399	93.81 239	87.53 392	93.95 404	56.14 423	97.43 381	94.68 220	83.13 397	94.26 399

new-patchmatchnet		88.50 373	87.45 378	91.67 388	90.31 419	85.89 403	97.16 356	97.33 335	89.47 377	83.63 410	92.77 413	76.38 387	95.06 414	82.70 401	77.29 418	94.06 406

APD_test1		88.22 374	88.01 373	88.86 393	95.98 363	74.66 425	97.21 348	96.44 386	83.96 409	86.66 399	97.90 233	60.95 421	97.84 367	82.73 400	90.23 338	94.09 404

PM-MVS		87.77 375	86.55 381	91.40 389	91.03 418	83.36 411	96.92 367	95.18 403	91.28 344	86.48 401	93.42 407	53.27 424	96.74 393	89.43 355	81.97 401	94.11 403

dmvs_testset		87.64 376	88.93 368	83.79 402	95.25 385	63.36 434	97.20 349	91.17 426	93.07 281	85.64 405	95.98 373	85.30 294	91.52 424	69.42 423	87.33 376	96.49 352

test_fmvs3		87.17 377	87.06 380	87.50 395	91.21 416	75.66 420	99.05 69	96.61 383	92.79 293	88.85 386	92.78 412	43.72 427	93.49 418	93.95 248	84.56 392	93.34 412

UnsupCasMVSNet_bld		87.17 377	85.12 384	93.31 375	91.94 413	88.77 379	94.92 408	98.30 229	84.30 408	82.30 411	90.04 419	63.96 418	97.25 384	85.85 384	74.47 424	93.93 408

N_pmnet		87.12 379	87.77 377	85.17 399	95.46 381	61.92 435	97.37 335	70.66 440	85.83 401	88.73 388	96.04 369	85.33 292	97.76 370	80.02 408	90.48 333	95.84 374

pmmvs3		86.67 380	84.86 385	92.11 387	88.16 424	87.19 399	96.63 385	94.75 407	79.88 416	87.22 394	92.75 414	66.56 415	95.20 413	81.24 406	76.56 421	93.96 407

test_f		86.07 381	85.39 382	88.10 394	89.28 422	75.57 421	97.73 310	96.33 388	89.41 380	85.35 406	91.56 418	43.31 429	95.53 409	91.32 319	84.23 394	93.21 413

WB-MVS		84.86 382	85.33 383	83.46 403	89.48 421	69.56 429	98.19 250	96.42 387	89.55 376	81.79 412	94.67 395	84.80 301	90.12 425	52.44 429	80.64 409	90.69 416

SSC-MVS		84.27 383	84.71 386	82.96 407	89.19 423	68.83 430	98.08 266	96.30 389	89.04 384	81.37 414	94.47 396	84.60 308	89.89 426	49.80 431	79.52 411	90.15 417

dongtai		82.47 384	81.88 387	84.22 401	95.19 387	76.03 418	94.59 415	74.14 439	82.63 411	87.19 395	96.09 366	64.10 417	87.85 429	58.91 427	84.11 395	88.78 421

test_vis3_rt		79.22 385	77.40 392	84.67 400	86.44 428	74.85 424	97.66 315	81.43 435	84.98 405	67.12 428	81.91 426	28.09 437	97.60 375	88.96 360	80.04 410	81.55 426

test_method		79.03 386	78.17 388	81.63 408	86.06 429	54.40 440	82.75 428	96.89 370	39.54 432	80.98 416	95.57 385	58.37 422	94.73 415	84.74 395	78.61 414	95.75 376

testf1		79.02 387	77.70 389	82.99 405	88.10 425	66.90 431	94.67 411	93.11 418	71.08 423	74.02 421	93.41 408	34.15 433	93.25 419	72.25 421	78.50 415	88.82 419

APD_test2		79.02 387	77.70 389	82.99 405	88.10 425	66.90 431	94.67 411	93.11 418	71.08 423	74.02 421	93.41 408	34.15 433	93.25 419	72.25 421	78.50 415	88.82 419

LCM-MVSNet		78.70 389	76.24 395	86.08 397	77.26 436	71.99 427	94.34 417	96.72 377	61.62 427	76.53 419	89.33 420	33.91 435	92.78 422	81.85 403	74.60 423	93.46 410

kuosan		78.45 390	77.69 391	80.72 409	92.73 411	75.32 422	94.63 414	74.51 438	75.96 419	80.87 417	93.19 410	63.23 419	79.99 433	42.56 433	81.56 404	86.85 425

Gipuma		78.40 391	76.75 394	83.38 404	95.54 376	80.43 416	79.42 429	97.40 331	64.67 426	73.46 423	80.82 427	45.65 426	93.14 421	66.32 425	87.43 374	76.56 429
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 392	75.44 396	85.46 398	82.54 431	74.95 423	94.23 418	93.08 420	72.80 422	74.68 420	87.38 421	36.36 432	91.56 423	73.95 419	63.94 428	89.87 418

FPMVS		77.62 393	77.14 393	79.05 411	79.25 434	60.97 436	95.79 398	95.94 394	65.96 425	67.93 427	94.40 399	37.73 431	88.88 428	68.83 424	88.46 364	87.29 422

EGC-MVSNET		75.22 394	69.54 397	92.28 385	94.81 393	89.58 364	97.64 317	96.50 384	1.82 437	5.57 438	95.74 376	68.21 409	96.26 403	73.80 420	91.71 318	90.99 415

ANet_high		69.08 395	65.37 399	80.22 410	65.99 438	71.96 428	90.91 424	90.09 429	82.62 412	49.93 433	78.39 428	29.36 436	81.75 430	62.49 426	38.52 432	86.95 424

tmp_tt		68.90 396	66.97 398	74.68 413	50.78 440	59.95 437	87.13 425	83.47 434	38.80 433	62.21 429	96.23 360	64.70 416	76.91 435	88.91 361	30.49 433	87.19 423

PMVS	61.03 23	65.95 397	63.57 401	73.09 414	57.90 439	51.22 441	85.05 427	93.93 416	54.45 428	44.32 434	83.57 423	13.22 438	89.15 427	58.68 428	81.00 406	78.91 428
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 398	64.25 400	67.02 415	82.28 432	59.36 438	91.83 423	85.63 432	52.69 429	60.22 430	77.28 429	41.06 430	80.12 432	46.15 432	41.14 430	61.57 431

EMVS		64.07 399	63.26 402	66.53 416	81.73 433	58.81 439	91.85 422	84.75 433	51.93 431	59.09 431	75.13 430	43.32 428	79.09 434	42.03 434	39.47 431	61.69 430

MVE	62.14 22	63.28 400	59.38 403	74.99 412	74.33 437	65.47 433	85.55 426	80.50 436	52.02 430	51.10 432	75.00 431	10.91 441	80.50 431	51.60 430	53.40 429	78.99 427
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 401	30.18 405	30.16 417	78.61 435	43.29 442	66.79 430	14.21 441	17.31 434	14.82 437	11.93 437	11.55 440	41.43 436	37.08 435	19.30 434	5.76 434

cdsmvs_eth3d_5k		23.98 402	31.98 404	0.00 420	0.00 443	0.00 445	0.00 431	98.59 158	0.00 438	0.00 439	98.61 163	90.60 175	0.00 439	0.00 438	0.00 437	0.00 435

testmvs		21.48 403	24.95 406	11.09 419	14.89 441	6.47 444	96.56 387	9.87 442	7.55 435	17.93 435	39.02 433	9.43 442	5.90 438	16.56 437	12.72 435	20.91 433

test123		20.95 404	23.72 407	12.64 418	13.54 442	8.19 443	96.55 388	6.13 443	7.48 436	16.74 436	37.98 434	12.97 439	6.05 437	16.69 436	5.43 436	23.68 432

ab-mvs-re		8.20 405	10.94 408	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	98.43 181	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

pcd_1.5k_mvsjas		7.88 406	10.50 409	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	94.51 87	0.00 439	0.00 438	0.00 437	0.00 435

mmdepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

monomultidepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

test_blank		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet_test		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

DCPMVS		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

sosnet-low-res		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

sosnet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uncertanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

Regformer		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

WAC-MVS						90.94 333								88.66 363

FOURS1					99.82 1	98.66 24	99.69 1	98.95 53	97.46 46	99.39 38

MSC_two_6792asdad				99.62 6	99.17 100	99.08 11		98.63 151					99.94 11	98.53 46	99.80 24	99.86 8

PC_three_1452									95.08 174	99.60 27	99.16 88	97.86 2	98.47 303	97.52 117	99.72 60	99.74 41

No_MVS				99.62 6	99.17 100	99.08 11		98.63 151					99.94 11	98.53 46	99.80 24	99.86 8

test_one_0601					99.66 26	99.25 2		98.86 82	97.55 39	99.20 50	99.47 30	97.57 6

eth-test2					0.00 443

eth-test					0.00 443

ZD-MVS					99.46 52	98.70 23		98.79 109	93.21 274	98.67 88	98.97 118	95.70 49	99.83 80	96.07 171	99.58 90

RE-MVS-def			98.34 45		99.49 46	97.86 69	99.11 60	98.80 104	96.49 102	99.17 53	99.35 54	95.29 65		97.72 96	99.65 73	99.71 54

IU-MVS					99.71 19	99.23 7		98.64 148	95.28 161	99.63 26				98.35 63	99.81 15	99.83 13

OPU-MVS				99.37 22	99.24 92	99.05 14	99.02 79				99.16 88	97.81 3	99.37 194	97.24 126	99.73 55	99.70 58

test_241102_TWO								98.87 76	97.65 32	99.53 31	99.48 28	97.34 11	99.94 11	98.43 58	99.80 24	99.83 13

test_241102_ONE					99.71 19	99.24 5		98.87 76	97.62 34	99.73 17	99.39 42	97.53 7	99.74 122

9.14			98.06 70		99.47 50		98.71 168	98.82 91	94.36 212	99.16 56	99.29 63	96.05 37	99.81 92	97.00 132	99.71 62

save fliter					99.46 52	98.38 35	98.21 245	98.71 127	97.95 23

test_0728_THIRD									97.32 54	99.45 33	99.46 34	97.88 1	99.94 11	98.47 54	99.86 2	99.85 10

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 89	98.88 69					99.94 11	98.47 54	99.81 15	99.84 12

test0726					99.72 12	99.25 2	99.06 67	98.88 69	97.62 34	99.56 28	99.50 24	97.42 9

GSMVS																99.20 150

test_part2					99.63 29	99.18 10				99.27 47

sam_mvs1												89.45 198				99.20 150

sam_mvs												88.99 212

ambc				89.49 392	86.66 427	75.78 419	92.66 421	96.72 377		86.55 400	92.50 415	46.01 425	97.90 361	90.32 336	82.09 399	94.80 396

MTGPA								98.74 119

test_post1							96.68 384				30.43 436	87.85 246	98.69 282	92.59 288

test_post											31.83 435	88.83 219	98.91 258

patchmatchnet-post											95.10 391	89.42 199	98.89 262

GG-mvs-BLEND				96.59 254	96.34 349	94.98 216	96.51 389	88.58 431		93.10 328	94.34 402	80.34 353	98.05 350	89.53 352	96.99 218	96.74 314

MTMP							98.89 110	94.14 414

gm-plane-assit					95.88 367	87.47 396			89.74 373		96.94 329		99.19 213	93.32 267

test9_res														96.39 165	99.57 91	99.69 61

TEST9					99.31 68	98.50 29	97.92 285	98.73 122	92.63 297	97.74 148	98.68 158	96.20 32	99.80 99

test_8					99.29 77	98.44 31	97.89 293	98.72 124	92.98 285	97.70 153	98.66 161	96.20 32	99.80 99

agg_prior2														95.87 181	99.57 91	99.68 66

agg_prior					99.30 72	98.38 35		98.72 124		97.57 165			99.81 92

TestCases				96.99 219	99.25 85	93.21 294		98.18 247	91.36 337	93.52 307	98.77 147	84.67 306	99.72 124	89.70 349	97.87 194	98.02 254

test_prior4						98.01 65	97.86 297

test_prior2							97.80 304		96.12 120	97.89 141	98.69 157	95.96 41		96.89 141	99.60 85

test_prior				99.19 44	99.31 68	98.22 52		98.84 86					99.70 130			99.65 74

旧先验2							97.57 323		91.30 342	98.67 88			99.80 99	95.70 190

新几何2							97.64 317

新几何1				99.16 49	99.34 61	98.01 65		98.69 132	90.06 367	98.13 117	98.95 125	94.60 85	99.89 58	91.97 307	99.47 111	99.59 85

旧先验1					99.29 77	97.48 83		98.70 131			99.09 104	95.56 52			99.47 111	99.61 81

无先验							97.58 322	98.72 124	91.38 336				99.87 69	93.36 266		99.60 83

原ACMM2							97.67 314

原ACMM1				98.65 88	99.32 66	96.62 127		98.67 140	93.27 273	97.81 143	98.97 118	95.18 72	99.83 80	93.84 252	99.46 114	99.50 97

test222					99.23 93	97.17 105	97.40 331	98.66 143	88.68 386	98.05 123	98.96 123	94.14 98			99.53 102	99.61 81

testdata2													99.89 58	91.65 315

segment_acmp												96.85 14

testdata				98.26 125	99.20 98	95.36 193		98.68 135	91.89 323	98.60 96	99.10 97	94.44 92	99.82 87	94.27 238	99.44 115	99.58 89

testdata1							97.32 341		96.34 110

test12				99.18 46	99.16 104	98.19 54		98.53 174		98.07 121		95.13 75	99.72 124		99.56 97	99.63 79

plane_prior7					97.42 283	94.63 233

plane_prior6					97.35 290	94.61 236						87.09 258

plane_prior5								98.56 168					99.03 238	96.07 171	94.27 271	96.92 290

plane_prior4											98.28 200

plane_prior3						94.61 236			97.02 76	95.34 237

plane_prior2							98.80 144		97.28 57

plane_prior1					97.37 289

plane_prior						94.60 238	98.44 219		96.74 90						94.22 273

n2								0.00 444

nn								0.00 444

door-mid								94.37 410

lessismore_v0				94.45 359	94.93 391	88.44 387		91.03 427		86.77 398	97.64 262	76.23 389	98.42 309	90.31 337	85.64 391	96.51 349

LGP-MVS_train				96.47 269	97.46 278	93.54 275		98.54 172	94.67 196	94.36 269	98.77 147	85.39 288	99.11 226	95.71 188	94.15 277	96.76 312

test11								98.66 143

door								94.64 408

HQP5-MVS						94.25 254

HQP-NCC					97.20 298		98.05 269		96.43 104	94.45 261

ACMP_Plane					97.20 298		98.05 269		96.43 104	94.45 261

BP-MVS														95.30 201

HQP4-MVS										94.45 261			98.96 249			96.87 302

HQP3-MVS								98.46 193							94.18 275

HQP2-MVS												86.75 264

NP-MVS					97.28 292	94.51 241					97.73 249

MDTV_nov1_ep13_2view						84.26 405	96.89 374		90.97 351	97.90 140		89.89 187		93.91 250		99.18 159

MDTV_nov1_ep13			95.40 188		97.48 276	88.34 388	96.85 377	97.29 339	93.74 243	97.48 167	97.26 290	89.18 206	99.05 234	91.92 308	97.43 209

ACMMP++_ref															92.97 303

ACMMP++															93.61 292

Test By Simon												94.64 84

ITE_SJBPF				95.44 320	97.42 283	91.32 327		97.50 319	95.09 173	93.59 303	98.35 191	81.70 335	98.88 264	89.71 348	93.39 298	96.12 368

DeepMVS_CX				86.78 396	97.09 308	72.30 426		95.17 404	75.92 420	84.34 409	95.19 389	70.58 406	95.35 410	79.98 410	89.04 358	92.68 414

High-resolution multi-view benchmark