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 59	97.48 84	98.88 122	99.30 14	98.47 15	99.85 9	99.43 40	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 21	99.24 5	99.02 80	98.87 79	97.65 36	99.73 19	99.48 30	97.53 7	99.94 12	98.43 64	99.81 15	99.70 61

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 104	99.23 7	99.69 1	98.88 72	97.32 60	99.53 34	99.47 32	97.81 3	99.94 12	98.47 60	99.72 61	99.74 44

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 52	99.41 61	97.54 82	98.89 115	99.31 13	98.49 14	99.86 6	99.42 41	96.45 24	99.96 4	99.86 1	99.74 53	99.90 4

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 14	99.25 2	98.97 91	98.58 170	97.62 38	99.45 36	99.46 37	97.42 9	99.94 12	98.47 60	99.81 15	99.69 64
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 35	98.96 16	99.39 11	98.93 60	97.38 57	99.41 39	99.54 18	96.66 18	99.84 81	98.86 36	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 41	99.58 30	99.47 32	95.36 61	99.93 31	98.87 35	99.57 93	99.78 27

reproduce_model		98.94 8	98.81 10	99.34 27	99.52 41	98.26 50	98.94 100	98.84 89	98.06 22	99.35 43	99.61 4	96.39 27	99.94 12	98.77 39	99.82 14	99.83 15

reproduce-ours		98.93 9	98.78 11	99.38 19	99.49 48	98.38 36	98.86 129	98.83 91	98.06 22	99.29 47	99.58 14	96.40 25	99.94 12	98.68 42	99.81 15	99.81 21

our_new_method		98.93 9	98.78 11	99.38 19	99.49 48	98.38 36	98.86 129	98.83 91	98.06 22	99.29 47	99.58 14	96.40 25	99.94 12	98.68 42	99.81 15	99.81 21

test_fmvsmconf_n		98.92 11	98.87 6	99.04 62	98.88 140	97.25 106	98.82 141	99.34 11	98.75 8	99.80 11	99.61 4	95.16 74	99.95 9	99.70 14	99.80 24	99.93 1

DPE-MVS		98.92 11	98.67 17	99.65 2	99.58 34	99.20 9	98.42 236	98.91 66	97.58 42	99.54 33	99.46 37	97.10 12	99.94 12	97.64 111	99.84 11	99.83 15
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 63	98.25 51	98.89 115	99.24 19	98.77 7	99.89 2	99.59 12	93.39 108	99.96 4	99.78 7	99.76 42	99.89 5

SteuartSystems-ACMMP		98.90 13	98.75 14	99.36 25	99.22 99	98.43 34	99.10 64	98.87 79	97.38 57	99.35 43	99.40 44	97.78 5	99.87 72	97.77 99	99.85 6	99.78 27
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 15	99.01 3	98.45 116	99.42 60	96.43 148	98.96 96	99.36 10	98.63 10	99.86 6	99.51 24	95.91 43	99.97 1	99.72 11	99.75 49	98.94 198

TSAR-MVS + MP.		98.78 16	98.62 19	99.24 41	99.69 26	98.28 49	99.14 55	98.66 147	96.84 91	99.56 31	99.31 64	96.34 28	99.70 135	98.32 70	99.73 56	99.73 49
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 23	99.45 15	99.32 70	98.87 19	98.47 226	98.81 100	97.72 31	98.76 87	99.16 92	97.05 13	99.78 117	98.06 81	99.66 72	99.69 64

MSP-MVS		98.74 18	98.55 24	99.29 34	99.75 3	98.23 52	99.26 28	98.88 72	97.52 45	99.41 39	98.78 155	96.00 39	99.79 114	97.79 98	99.59 89	99.85 12
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 19	99.05 61	99.35 64	97.27 100	98.80 150	99.23 24	98.93 3	99.79 12	99.59 12	92.34 125	99.95 9	99.82 5	99.71 63	99.92 2

XVS		98.70 20	98.49 30	99.34 27	99.70 24	98.35 45	99.29 23	98.88 72	97.40 54	98.46 110	99.20 82	95.90 45	99.89 61	97.85 94	99.74 53	99.78 27

fmvsm_s_conf0.5_n_6		98.65 21	98.55 24	98.95 71	98.50 180	97.30 96	98.79 158	99.16 35	98.14 20	99.86 6	99.41 43	93.71 105	99.91 50	99.71 12	99.64 80	99.65 77

MCST-MVS		98.65 21	98.37 39	99.48 13	99.60 33	98.87 19	98.41 237	98.68 139	97.04 83	98.52 108	98.80 153	96.78 16	99.83 83	97.93 88	99.61 85	99.74 44

SD-MVS		98.64 23	98.68 16	98.53 105	99.33 67	98.36 44	98.90 111	98.85 88	97.28 64	99.72 22	99.39 45	96.63 20	97.60 390	98.17 76	99.85 6	99.64 80
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
fmvsm_s_conf0.5_n_9		98.63 24	98.66 18	98.54 102	99.40 62	95.83 184	98.79 158	99.17 33	98.94 2	99.92 1	99.61 4	92.49 120	99.93 31	99.86 1	99.76 42	99.86 9

HFP-MVS		98.63 24	98.40 36	99.32 33	99.72 14	98.29 48	99.23 33	98.96 55	96.10 130	98.94 70	99.17 89	96.06 36	99.92 40	97.62 112	99.78 34	99.75 42

ACMMP_NAP		98.61 26	98.30 54	99.55 9	99.62 32	98.95 17	98.82 141	98.81 100	95.80 142	99.16 59	99.47 32	95.37 60	99.92 40	97.89 92	99.75 49	99.79 25

region2R		98.61 26	98.38 38	99.29 34	99.74 9	98.16 58	99.23 33	98.93 60	96.15 126	98.94 70	99.17 89	95.91 43	99.94 12	97.55 120	99.79 30	99.78 27

NCCC		98.61 26	98.35 42	99.38 19	99.28 85	98.61 27	98.45 227	98.76 118	97.82 30	98.45 113	98.93 134	96.65 19	99.83 83	97.38 132	99.41 122	99.71 57

SF-MVS		98.59 29	98.32 53	99.41 18	99.54 37	98.71 22	99.04 74	98.81 100	95.12 179	99.32 46	99.39 45	96.22 30	99.84 81	97.72 102	99.73 56	99.67 73

ACMMPR		98.59 29	98.36 40	99.29 34	99.74 9	98.15 59	99.23 33	98.95 56	96.10 130	98.93 74	99.19 87	95.70 49	99.94 12	97.62 112	99.79 30	99.78 27

test_fmvsmconf0.1_n		98.58 31	98.44 34	98.99 64	97.73 266	97.15 111	98.84 137	98.97 52	98.75 8	99.43 38	99.54 18	93.29 110	99.93 31	99.64 17	99.79 30	99.89 5

SMA-MVS		98.58 31	98.25 57	99.56 8	99.51 42	99.04 15	98.95 97	98.80 107	93.67 266	99.37 42	99.52 21	96.52 22	99.89 61	98.06 81	99.81 15	99.76 41
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 31	98.29 55	99.46 14	99.76 2	98.64 25	98.90 111	98.74 122	97.27 68	98.02 137	99.39 45	94.81 84	99.96 4	97.91 90	99.79 30	99.77 34

HPM-MVS++		98.58 31	98.25 57	99.55 9	99.50 44	99.08 11	98.72 177	98.66 147	97.51 46	98.15 124	98.83 150	95.70 49	99.92 40	97.53 122	99.67 69	99.66 76

SR-MVS		98.57 35	98.35 42	99.24 41	99.53 38	98.18 56	99.09 65	98.82 94	96.58 107	99.10 61	99.32 62	95.39 58	99.82 90	97.70 107	99.63 82	99.72 53

CP-MVS		98.57 35	98.36 40	99.19 45	99.66 28	97.86 70	99.34 17	98.87 79	95.96 134	98.60 104	99.13 97	96.05 37	99.94 12	97.77 99	99.86 2	99.77 34

MSLP-MVS++		98.56 37	98.57 22	98.55 100	99.26 88	96.80 126	98.71 178	99.05 45	97.28 64	98.84 80	99.28 67	96.47 23	99.40 199	98.52 58	99.70 65	99.47 109

DeepC-MVS_fast	96.70 1	98.55 38	98.34 48	99.18 47	99.25 89	98.04 64	98.50 223	98.78 114	97.72 31	98.92 76	99.28 67	95.27 67	99.82 90	97.55 120	99.77 36	99.69 64
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 39	98.35 42	99.13 53	99.49 48	97.86 70	99.11 61	98.80 107	96.49 111	99.17 56	99.35 57	95.34 63	99.82 90	97.72 102	99.65 75	99.71 57

fmvsm_s_conf0.5_n_5		98.53 40	98.35 42	99.08 58	99.07 119	97.46 88	98.68 186	99.20 29	97.50 47	99.87 3	99.50 26	91.96 144	99.96 4	99.76 8	99.65 75	99.82 19

fmvsm_s_conf0.5_n_3		98.53 40	98.45 33	98.79 79	99.23 97	97.32 93	98.80 150	99.26 16	98.82 4	99.87 3	99.60 9	90.95 174	99.93 31	99.76 8	99.73 56	99.12 173

APD-MVS_3200maxsize		98.53 40	98.33 52	99.15 51	99.50 44	97.92 69	99.15 52	98.81 100	96.24 122	99.20 53	99.37 51	95.30 65	99.80 102	97.73 101	99.67 69	99.72 53

MM		98.51 43	98.24 59	99.33 31	99.12 113	98.14 61	98.93 106	97.02 375	98.96 1	99.17 56	99.47 32	91.97 143	99.94 12	99.85 4	99.69 66	99.91 3

mPP-MVS		98.51 43	98.26 56	99.25 40	99.75 3	98.04 64	99.28 25	98.81 100	96.24 122	98.35 120	99.23 77	95.46 55	99.94 12	97.42 128	99.81 15	99.77 34

ZNCC-MVS		98.49 45	98.20 65	99.35 26	99.73 13	98.39 35	99.19 45	98.86 85	95.77 144	98.31 123	99.10 101	95.46 55	99.93 31	97.57 119	99.81 15	99.74 44

SPE-MVS-test		98.49 45	98.50 28	98.46 115	99.20 102	97.05 116	99.64 4	98.50 192	97.45 53	98.88 77	99.14 96	95.25 69	99.15 229	98.83 37	99.56 101	99.20 158

PGM-MVS		98.49 45	98.23 61	99.27 39	99.72 14	98.08 63	98.99 87	99.49 5	95.43 160	99.03 62	99.32 62	95.56 52	99.94 12	96.80 161	99.77 36	99.78 27

EI-MVSNet-Vis-set		98.47 48	98.39 37	98.69 87	99.46 54	96.49 145	98.30 248	98.69 136	97.21 71	98.84 80	99.36 55	95.41 57	99.78 117	98.62 46	99.65 75	99.80 24

MVS_111021_HR		98.47 48	98.34 48	98.88 76	99.22 99	97.32 93	97.91 302	99.58 3	97.20 72	98.33 121	99.00 123	95.99 40	99.64 149	98.05 83	99.76 42	99.69 64

balanced_conf03		98.45 50	98.35 42	98.74 83	98.65 169	97.55 80	99.19 45	98.60 158	96.72 101	99.35 43	98.77 158	95.06 79	99.55 172	98.95 32	99.87 1	99.12 173

test_fmvsmvis_n_1920		98.44 51	98.51 26	98.23 137	98.33 202	96.15 162	98.97 91	99.15 37	98.55 13	98.45 113	99.55 16	94.26 97	99.97 1	99.65 15	99.66 72	98.57 242

CS-MVS		98.44 51	98.49 30	98.31 129	99.08 118	96.73 130	99.67 3	98.47 199	97.17 75	98.94 70	99.10 101	95.73 48	99.13 232	98.71 41	99.49 112	99.09 178

GST-MVS		98.43 53	98.12 69	99.34 27	99.72 14	98.38 36	99.09 65	98.82 94	95.71 148	98.73 90	99.06 114	95.27 67	99.93 31	97.07 140	99.63 82	99.72 53

fmvsm_s_conf0.5_n		98.42 54	98.51 26	98.13 147	99.30 76	95.25 210	98.85 133	99.39 7	97.94 26	99.74 18	99.62 3	92.59 119	99.91 50	99.65 15	99.52 107	99.25 151

EI-MVSNet-UG-set		98.41 55	98.34 48	98.61 94	99.45 57	96.32 155	98.28 251	98.68 139	97.17 75	98.74 88	99.37 51	95.25 69	99.79 114	98.57 49	99.54 104	99.73 49

DELS-MVS		98.40 56	98.20 65	98.99 64	99.00 127	97.66 75	97.75 323	98.89 69	97.71 33	98.33 121	98.97 125	94.97 81	99.88 70	98.42 66	99.76 42	99.42 121
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 57	98.42 35	98.27 131	99.09 117	95.41 200	98.86 129	99.37 9	97.69 35	99.78 14	99.61 4	92.38 123	99.91 50	99.58 20	99.43 120	99.49 105

TSAR-MVS + GP.		98.38 57	98.24 59	98.81 78	99.22 99	97.25 106	98.11 277	98.29 240	97.19 73	98.99 68	99.02 117	96.22 30	99.67 142	98.52 58	98.56 175	99.51 98

HPM-MVS_fast		98.38 57	98.13 68	99.12 55	99.75 3	97.86 70	99.44 9	98.82 94	94.46 221	98.94 70	99.20 82	95.16 74	99.74 127	97.58 115	99.85 6	99.77 34

patch_mono-2		98.36 60	98.87 6	96.82 244	99.53 38	90.68 353	98.64 197	99.29 15	97.88 27	99.19 55	99.52 21	96.80 15	99.97 1	99.11 28	99.86 2	99.82 19

HPM-MVS		98.36 60	98.10 72	99.13 53	99.74 9	97.82 74	99.53 6	98.80 107	94.63 210	98.61 103	98.97 125	95.13 76	99.77 122	97.65 110	99.83 13	99.79 25
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 62	98.50 28	97.90 164	99.16 108	95.08 219	98.75 163	99.24 19	98.39 16	99.81 10	99.52 21	92.35 124	99.90 58	99.74 10	99.51 109	98.71 223

APD-MVS		98.35 62	98.00 78	99.42 17	99.51 42	98.72 21	98.80 150	98.82 94	94.52 218	99.23 52	99.25 76	95.54 54	99.80 102	96.52 168	99.77 36	99.74 44
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 64	98.23 61	98.67 89	99.27 86	96.90 122	97.95 295	99.58 3	97.14 78	98.44 115	99.01 121	95.03 80	99.62 156	97.91 90	99.75 49	99.50 100

PHI-MVS		98.34 64	98.06 73	99.18 47	99.15 111	98.12 62	99.04 74	99.09 40	93.32 281	98.83 82	99.10 101	96.54 21	99.83 83	97.70 107	99.76 42	99.59 88

MP-MVS		98.33 66	98.01 77	99.28 37	99.75 3	98.18 56	99.22 37	98.79 112	96.13 127	97.92 148	99.23 77	94.54 87	99.94 12	96.74 164	99.78 34	99.73 49
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 67	98.19 67	98.67 89	98.96 134	97.36 91	99.24 31	98.57 172	94.81 202	98.99 68	98.90 138	95.22 72	99.59 159	99.15 27	99.84 11	99.07 186

MP-MVS-pluss		98.31 67	97.92 80	99.49 12	99.72 14	98.88 18	98.43 233	98.78 114	94.10 231	97.69 165	99.42 41	95.25 69	99.92 40	98.09 80	99.80 24	99.67 73
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 69	98.21 63	98.57 97	99.25 89	97.11 113	98.66 193	99.20 29	98.82 4	99.79 12	99.60 9	89.38 209	99.92 40	99.80 6	99.38 127	98.69 225

fmvsm_s_conf0.5_n_7		98.23 70	98.35 42	97.89 166	98.86 144	94.99 225	98.58 206	99.00 48	98.29 17	99.73 19	99.60 9	91.70 148	99.92 40	99.63 18	99.73 56	98.76 217

MVS_0304		98.23 70	97.91 81	99.21 44	98.06 234	97.96 68	98.58 206	95.51 413	98.58 11	98.87 78	99.26 71	92.99 114	99.95 9	99.62 19	99.67 69	99.73 49

ACMMP		98.23 70	97.95 79	99.09 57	99.74 9	97.62 78	99.03 77	99.41 6	95.98 133	97.60 174	99.36 55	94.45 92	99.93 31	97.14 137	98.85 160	99.70 61
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 73	98.11 70	98.49 112	98.34 199	97.26 105	99.61 5	98.43 209	96.78 94	98.87 78	98.84 146	93.72 104	99.01 254	98.91 34	99.50 110	99.19 162

fmvsm_s_conf0.1_n		98.18 74	98.21 63	98.11 151	98.54 178	95.24 211	98.87 125	99.24 19	97.50 47	99.70 23	99.67 1	91.33 161	99.89 61	99.47 22	99.54 104	99.21 157

fmvsm_s_conf0.1_n_2		98.14 75	98.02 76	98.53 105	98.88 140	97.07 115	98.69 184	98.82 94	98.78 6	99.77 15	99.61 4	88.83 228	99.91 50	99.71 12	99.07 143	98.61 235

fmvsm_s_conf0.1_n_a		98.08 76	98.04 75	98.21 138	97.66 272	95.39 201	98.89 115	99.17 33	97.24 69	99.76 17	99.67 1	91.13 168	99.88 70	99.39 23	99.41 122	99.35 130

dcpmvs_2		98.08 76	98.59 21	96.56 269	99.57 35	90.34 365	99.15 52	98.38 219	96.82 93	99.29 47	99.49 29	95.78 47	99.57 162	98.94 33	99.86 2	99.77 34

NormalMVS		98.07 78	97.90 82	98.59 96	99.75 3	96.60 136	98.94 100	98.60 158	97.86 28	98.71 93	99.08 110	91.22 166	99.80 102	97.40 129	99.57 93	99.37 126

CANet		98.05 79	97.76 85	98.90 75	98.73 154	97.27 100	98.35 239	98.78 114	97.37 59	97.72 162	98.96 130	91.53 157	99.92 40	98.79 38	99.65 75	99.51 98

train_agg		97.97 80	97.52 98	99.33 31	99.31 72	98.50 30	97.92 300	98.73 125	92.98 297	97.74 159	98.68 169	96.20 32	99.80 102	96.59 165	99.57 93	99.68 69

ETV-MVS		97.96 81	97.81 83	98.40 124	98.42 186	97.27 100	98.73 173	98.55 177	96.84 91	98.38 117	97.44 290	95.39 58	99.35 204	97.62 112	98.89 154	98.58 241

UA-Net		97.96 81	97.62 89	98.98 66	98.86 144	97.47 86	98.89 115	99.08 41	96.67 104	98.72 92	99.54 18	93.15 112	99.81 95	94.87 224	98.83 161	99.65 77

CDPH-MVS		97.94 83	97.49 100	99.28 37	99.47 52	98.44 32	97.91 302	98.67 144	92.57 313	98.77 86	98.85 145	95.93 42	99.72 129	95.56 202	99.69 66	99.68 69

DeepPCF-MVS	96.37 2	97.93 84	98.48 32	96.30 295	99.00 127	89.54 380	97.43 345	98.87 79	98.16 19	99.26 51	99.38 50	96.12 35	99.64 149	98.30 71	99.77 36	99.72 53

DeepC-MVS	95.98 3	97.88 85	97.58 91	98.77 81	99.25 89	96.93 120	98.83 139	98.75 120	96.96 87	96.89 200	99.50 26	90.46 182	99.87 72	97.84 96	99.76 42	99.52 95
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 86	97.54 97	98.83 77	95.48 395	96.83 125	98.95 97	98.60 158	98.58 11	98.93 74	99.55 16	88.57 233	99.91 50	99.54 21	99.61 85	99.77 34

DP-MVS Recon		97.86 86	97.46 103	99.06 60	99.53 38	98.35 45	98.33 241	98.89 69	92.62 310	98.05 132	98.94 133	95.34 63	99.65 146	96.04 184	99.42 121	99.19 162

CSCG		97.85 88	97.74 86	98.20 140	99.67 27	95.16 214	99.22 37	99.32 12	93.04 295	97.02 193	98.92 136	95.36 61	99.91 50	97.43 127	99.64 80	99.52 95

SymmetryMVS		97.84 89	97.58 91	98.62 93	99.01 125	96.60 136	98.94 100	98.44 204	97.86 28	98.71 93	99.08 110	91.22 166	99.80 102	97.40 129	97.53 218	99.47 109

BP-MVS1		97.82 90	97.51 99	98.76 82	98.25 210	97.39 90	99.15 52	97.68 307	96.69 102	98.47 109	99.10 101	90.29 186	99.51 179	98.60 47	99.35 130	99.37 126

MG-MVS		97.81 91	97.60 90	98.44 118	99.12 113	95.97 171	97.75 323	98.78 114	96.89 90	98.46 110	99.22 79	93.90 103	99.68 141	94.81 228	99.52 107	99.67 73

VNet		97.79 92	97.40 107	98.96 69	98.88 140	97.55 80	98.63 200	98.93 60	96.74 98	99.02 63	98.84 146	90.33 185	99.83 83	98.53 52	96.66 241	99.50 100

EIA-MVS		97.75 93	97.58 91	98.27 131	98.38 190	96.44 147	99.01 82	98.60 158	95.88 138	97.26 181	97.53 284	94.97 81	99.33 207	97.38 132	99.20 139	99.05 187

PS-MVSNAJ		97.73 94	97.77 84	97.62 194	98.68 164	95.58 191	97.34 354	98.51 187	97.29 62	98.66 100	97.88 248	94.51 88	99.90 58	97.87 93	99.17 141	97.39 285

casdiffmvs_mvg		97.72 95	97.48 102	98.44 118	98.42 186	96.59 140	98.92 108	98.44 204	96.20 124	97.76 156	99.20 82	91.66 151	99.23 219	98.27 75	98.41 185	99.49 105
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 95	97.32 112	98.92 72	99.64 30	97.10 114	99.12 59	98.81 100	92.34 321	98.09 129	99.08 110	93.01 113	99.92 40	96.06 183	99.77 36	99.75 42

PVSNet_Blended_VisFu		97.70 97	97.46 103	98.44 118	99.27 86	95.91 179	98.63 200	99.16 35	94.48 220	97.67 166	98.88 142	92.80 116	99.91 50	97.11 138	99.12 142	99.50 100

mvsany_test1		97.69 98	97.70 87	97.66 191	98.24 211	94.18 266	97.53 339	97.53 328	95.52 156	99.66 25	99.51 24	94.30 95	99.56 165	98.38 67	98.62 170	99.23 153

sasdasda		97.67 99	97.23 117	98.98 66	98.70 159	98.38 36	99.34 17	98.39 215	96.76 96	97.67 166	97.40 294	92.26 129	99.49 183	98.28 72	96.28 259	99.08 182

canonicalmvs		97.67 99	97.23 117	98.98 66	98.70 159	98.38 36	99.34 17	98.39 215	96.76 96	97.67 166	97.40 294	92.26 129	99.49 183	98.28 72	96.28 259	99.08 182

xiu_mvs_v2_base		97.66 101	97.70 87	97.56 198	98.61 173	95.46 198	97.44 343	98.46 200	97.15 77	98.65 101	98.15 223	94.33 94	99.80 102	97.84 96	98.66 169	97.41 283

GDP-MVS		97.64 102	97.28 113	98.71 86	98.30 207	97.33 92	99.05 70	98.52 184	96.34 119	98.80 83	99.05 115	89.74 196	99.51 179	96.86 158	98.86 158	99.28 145

baseline		97.64 102	97.44 105	98.25 135	98.35 194	96.20 159	99.00 84	98.32 229	96.33 121	98.03 135	99.17 89	91.35 160	99.16 226	98.10 79	98.29 192	99.39 123

casdiffmvs		97.63 104	97.41 106	98.28 130	98.33 202	96.14 163	98.82 141	98.32 229	96.38 118	97.95 143	99.21 80	91.23 165	99.23 219	98.12 78	98.37 186	99.48 107
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		97.62 105	97.19 120	98.92 72	98.66 166	98.20 54	99.32 22	98.38 219	96.69 102	97.58 175	97.42 293	92.10 137	99.50 182	98.28 72	96.25 262	99.08 182

xiu_mvs_v1_base_debu		97.60 106	97.56 94	97.72 181	98.35 194	95.98 166	97.86 312	98.51 187	97.13 79	99.01 65	98.40 196	91.56 153	99.80 102	98.53 52	98.68 165	97.37 287

xiu_mvs_v1_base		97.60 106	97.56 94	97.72 181	98.35 194	95.98 166	97.86 312	98.51 187	97.13 79	99.01 65	98.40 196	91.56 153	99.80 102	98.53 52	98.68 165	97.37 287

xiu_mvs_v1_base_debi		97.60 106	97.56 94	97.72 181	98.35 194	95.98 166	97.86 312	98.51 187	97.13 79	99.01 65	98.40 196	91.56 153	99.80 102	98.53 52	98.68 165	97.37 287

diffmvs		97.58 109	97.40 107	98.13 147	98.32 205	95.81 186	98.06 283	98.37 221	96.20 124	98.74 88	98.89 141	91.31 163	99.25 216	98.16 77	98.52 177	99.34 132
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		97.57 110	97.37 109	98.20 140	98.50 180	95.86 183	98.89 115	97.03 372	97.29 62	98.73 90	98.90 138	89.41 208	99.32 208	98.68 42	98.86 158	99.42 121

MVSFormer		97.57 110	97.49 100	97.84 168	98.07 231	95.76 187	99.47 7	98.40 213	94.98 191	98.79 84	98.83 150	92.34 125	98.41 328	96.91 146	99.59 89	99.34 132

alignmvs		97.56 112	97.07 127	99.01 63	98.66 166	98.37 43	98.83 139	98.06 287	96.74 98	98.00 141	97.65 271	90.80 176	99.48 188	98.37 68	96.56 245	99.19 162

DPM-MVS		97.55 113	96.99 131	99.23 43	99.04 121	98.55 28	97.17 369	98.35 224	94.85 201	97.93 147	98.58 179	95.07 78	99.71 134	92.60 298	99.34 131	99.43 119

OMC-MVS		97.55 113	97.34 111	98.20 140	99.33 67	95.92 178	98.28 251	98.59 165	95.52 156	97.97 142	99.10 101	93.28 111	99.49 183	95.09 219	98.88 155	99.19 162

LuminaMVS		97.49 115	97.18 121	98.42 122	97.50 287	97.15 111	98.45 227	97.68 307	96.56 110	98.68 95	98.78 155	89.84 193	99.32 208	98.60 47	98.57 174	98.79 209

KinetiMVS		97.48 116	97.05 128	98.78 80	98.37 192	97.30 96	98.99 87	98.70 134	97.18 74	99.02 63	99.01 121	87.50 262	99.67 142	95.33 209	99.33 133	99.37 126

PAPM_NR		97.46 117	97.11 124	98.50 110	99.50 44	96.41 150	98.63 200	98.60 158	95.18 176	97.06 191	98.06 229	94.26 97	99.57 162	93.80 266	98.87 157	99.52 95

EPP-MVSNet		97.46 117	97.28 113	97.99 159	98.64 170	95.38 202	99.33 21	98.31 231	93.61 270	97.19 184	99.07 113	94.05 100	99.23 219	96.89 150	98.43 184	99.37 126

3Dnovator	94.51 5	97.46 117	96.93 134	99.07 59	97.78 260	97.64 76	99.35 16	99.06 43	97.02 84	93.75 313	99.16 92	89.25 213	99.92 40	97.22 136	99.75 49	99.64 80

CNLPA		97.45 120	97.03 129	98.73 84	99.05 120	97.44 89	98.07 282	98.53 181	95.32 169	96.80 205	98.53 184	93.32 109	99.72 129	94.31 247	99.31 134	99.02 189

lupinMVS		97.44 121	97.22 119	98.12 150	98.07 231	95.76 187	97.68 328	97.76 304	94.50 219	98.79 84	98.61 174	92.34 125	99.30 212	97.58 115	99.59 89	99.31 138

3Dnovator+	94.38 6	97.43 122	96.78 142	99.38 19	97.83 257	98.52 29	99.37 13	98.71 130	97.09 82	92.99 342	99.13 97	89.36 210	99.89 61	96.97 143	99.57 93	99.71 57

Vis-MVSNet		97.42 123	97.11 124	98.34 127	98.66 166	96.23 158	99.22 37	99.00 48	96.63 106	98.04 134	99.21 80	88.05 249	99.35 204	96.01 186	99.21 138	99.45 116
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 124	97.25 115	97.91 163	98.70 159	96.80 126	98.82 141	98.69 136	94.53 216	98.11 127	98.28 211	94.50 91	99.57 162	94.12 255	99.49 112	97.37 287

sss		97.39 125	96.98 133	98.61 94	98.60 174	96.61 135	98.22 257	98.93 60	93.97 241	98.01 140	98.48 189	91.98 141	99.85 77	96.45 170	98.15 194	99.39 123

test_cas_vis1_n_1920		97.38 126	97.36 110	97.45 201	98.95 135	93.25 304	99.00 84	98.53 181	97.70 34	99.77 15	99.35 57	84.71 315	99.85 77	98.57 49	99.66 72	99.26 149

PVSNet_Blended		97.38 126	97.12 123	98.14 144	99.25 89	95.35 205	97.28 359	99.26 16	93.13 291	97.94 145	98.21 219	92.74 117	99.81 95	96.88 152	99.40 125	99.27 146

WTY-MVS		97.37 128	96.92 135	98.72 85	98.86 144	96.89 124	98.31 246	98.71 130	95.26 172	97.67 166	98.56 183	92.21 133	99.78 117	95.89 188	96.85 235	99.48 107

AstraMVS		97.34 129	97.24 116	97.65 192	98.13 227	94.15 267	98.94 100	96.25 404	97.47 51	98.60 104	99.28 67	89.67 198	99.41 198	98.73 40	98.07 198	99.38 125

jason		97.32 130	97.08 126	98.06 155	97.45 293	95.59 190	97.87 310	97.91 298	94.79 203	98.55 107	98.83 150	91.12 169	99.23 219	97.58 115	99.60 87	99.34 132
jason: jason.
MVS_Test		97.28 131	97.00 130	98.13 147	98.33 202	95.97 171	98.74 167	98.07 282	94.27 226	98.44 115	98.07 228	92.48 121	99.26 215	96.43 171	98.19 193	99.16 168

EPNet		97.28 131	96.87 137	98.51 107	94.98 404	96.14 163	98.90 111	97.02 375	98.28 18	95.99 237	99.11 99	91.36 159	99.89 61	96.98 142	99.19 140	99.50 100
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsmamba		97.25 133	96.99 131	98.02 157	98.34 199	95.54 195	99.18 49	97.47 334	95.04 185	98.15 124	98.57 182	89.46 205	99.31 211	97.68 109	99.01 148	99.22 155

test_yl		97.22 134	96.78 142	98.54 102	98.73 154	96.60 136	98.45 227	98.31 231	94.70 204	98.02 137	98.42 194	90.80 176	99.70 135	96.81 159	96.79 237	99.34 132

DCV-MVSNet		97.22 134	96.78 142	98.54 102	98.73 154	96.60 136	98.45 227	98.31 231	94.70 204	98.02 137	98.42 194	90.80 176	99.70 135	96.81 159	96.79 237	99.34 132

IS-MVSNet		97.22 134	96.88 136	98.25 135	98.85 147	96.36 153	99.19 45	97.97 292	95.39 163	97.23 182	98.99 124	91.11 170	98.93 266	94.60 235	98.59 172	99.47 109

PLC	95.07 4	97.20 137	96.78 142	98.44 118	99.29 81	96.31 157	98.14 272	98.76 118	92.41 319	96.39 225	98.31 209	94.92 83	99.78 117	94.06 258	98.77 164	99.23 153
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 138	97.18 121	97.20 214	98.81 150	93.27 301	95.78 414	99.15 37	95.25 173	96.79 206	98.11 226	92.29 128	99.07 244	98.56 51	99.85 6	99.25 151

LS3D		97.16 139	96.66 151	98.68 88	98.53 179	97.19 109	98.93 106	98.90 67	92.83 304	95.99 237	99.37 51	92.12 136	99.87 72	93.67 270	99.57 93	98.97 194

AdaColmap		97.15 140	96.70 147	98.48 113	99.16 108	96.69 132	98.01 289	98.89 69	94.44 222	96.83 201	98.68 169	90.69 179	99.76 123	94.36 243	99.29 135	98.98 193

mamv4		97.13 141	98.11 70	94.17 379	98.97 133	83.70 422	98.66 193	98.71 130	94.63 210	97.83 153	98.90 138	96.25 29	99.55 172	99.27 25	99.76 42	99.27 146

Effi-MVS+		97.12 142	96.69 148	98.39 125	98.19 219	96.72 131	97.37 350	98.43 209	93.71 259	97.65 170	98.02 232	92.20 134	99.25 216	96.87 155	97.79 207	99.19 162

CHOSEN 1792x2688		97.12 142	96.80 139	98.08 153	99.30 76	94.56 250	98.05 284	99.71 1	93.57 271	97.09 187	98.91 137	88.17 243	99.89 61	96.87 155	99.56 101	99.81 21

F-COLMAP		97.09 144	96.80 139	97.97 160	99.45 57	94.95 229	98.55 215	98.62 157	93.02 296	96.17 232	98.58 179	94.01 101	99.81 95	93.95 260	98.90 153	99.14 171

RRT-MVS		97.03 145	96.78 142	97.77 177	97.90 253	94.34 259	99.12 59	98.35 224	95.87 139	98.06 131	98.70 167	86.45 281	99.63 152	98.04 84	98.54 176	99.35 130

TAMVS		97.02 146	96.79 141	97.70 184	98.06 234	95.31 208	98.52 217	98.31 231	93.95 242	97.05 192	98.61 174	93.49 107	98.52 310	95.33 209	97.81 206	99.29 143

CDS-MVSNet		96.99 147	96.69 148	97.90 164	98.05 236	95.98 166	98.20 260	98.33 228	93.67 266	96.95 194	98.49 188	93.54 106	98.42 321	95.24 216	97.74 210	99.31 138
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 148	96.55 154	98.21 138	98.17 224	96.07 165	97.98 293	98.21 249	97.24 69	97.13 186	98.93 134	86.88 273	99.91 50	95.00 222	99.37 129	98.66 231

114514_t		96.93 149	96.27 164	98.92 72	99.50 44	97.63 77	98.85 133	98.90 67	84.80 418	97.77 155	99.11 99	92.84 115	99.66 145	94.85 225	99.77 36	99.47 109

MAR-MVS		96.91 150	96.40 160	98.45 116	98.69 162	96.90 122	98.66 193	98.68 139	92.40 320	97.07 190	97.96 239	91.54 156	99.75 125	93.68 268	98.92 152	98.69 225
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		96.90 151	96.49 157	98.14 144	99.33 67	95.56 192	97.38 348	99.65 2	92.34 321	97.61 173	98.20 220	89.29 212	99.10 241	96.97 143	97.60 215	99.77 34

Vis-MVSNet (Re-imp)		96.87 152	96.55 154	97.83 169	98.73 154	95.46 198	99.20 43	98.30 238	94.96 193	96.60 213	98.87 143	90.05 189	98.59 305	93.67 270	98.60 171	99.46 114

SDMVSNet		96.85 153	96.42 158	98.14 144	99.30 76	96.38 151	99.21 40	99.23 24	95.92 135	95.96 239	98.76 163	85.88 291	99.44 195	97.93 88	95.59 274	98.60 236

PAPR		96.84 154	96.24 166	98.65 91	98.72 158	96.92 121	97.36 352	98.57 172	93.33 280	96.67 208	97.57 280	94.30 95	99.56 165	91.05 341	98.59 172	99.47 109

HY-MVS	93.96 8	96.82 155	96.23 167	98.57 97	98.46 185	97.00 117	98.14 272	98.21 249	93.95 242	96.72 207	97.99 236	91.58 152	99.76 123	94.51 239	96.54 246	98.95 197

UGNet		96.78 156	96.30 163	98.19 143	98.24 211	95.89 181	98.88 122	98.93 60	97.39 56	96.81 204	97.84 252	82.60 344	99.90 58	96.53 167	99.49 112	98.79 209
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
PVSNet_BlendedMVS		96.73 157	96.60 152	97.12 223	99.25 89	95.35 205	98.26 254	99.26 16	94.28 225	97.94 145	97.46 287	92.74 117	99.81 95	96.88 152	93.32 310	96.20 380

test_vis1_n_1920		96.71 158	96.84 138	96.31 294	99.11 115	89.74 373	99.05 70	98.58 170	98.08 21	99.87 3	99.37 51	78.48 376	99.93 31	99.29 24	99.69 66	99.27 146

mvs_anonymous		96.70 159	96.53 156	97.18 217	98.19 219	93.78 277	98.31 246	98.19 253	94.01 238	94.47 271	98.27 214	92.08 139	98.46 316	97.39 131	97.91 202	99.31 138

Elysia		96.64 160	96.02 174	98.51 107	98.04 238	97.30 96	98.74 167	98.60 158	95.04 185	97.91 149	98.84 146	83.59 339	99.48 188	94.20 251	99.25 136	98.75 218

StellarMVS		96.64 160	96.02 174	98.51 107	98.04 238	97.30 96	98.74 167	98.60 158	95.04 185	97.91 149	98.84 146	83.59 339	99.48 188	94.20 251	99.25 136	98.75 218

1112_ss		96.63 162	96.00 176	98.50 110	98.56 175	96.37 152	98.18 268	98.10 275	92.92 300	94.84 259	98.43 192	92.14 135	99.58 161	94.35 244	96.51 247	99.56 94

PMMVS		96.60 163	96.33 162	97.41 205	97.90 253	93.93 273	97.35 353	98.41 211	92.84 303	97.76 156	97.45 289	91.10 171	99.20 223	96.26 176	97.91 202	99.11 176

DP-MVS		96.59 164	95.93 179	98.57 97	99.34 65	96.19 161	98.70 182	98.39 215	89.45 390	94.52 269	99.35 57	91.85 145	99.85 77	92.89 294	98.88 155	99.68 69

PatchMatch-RL		96.59 164	96.03 173	98.27 131	99.31 72	96.51 144	97.91 302	99.06 43	93.72 258	96.92 198	98.06 229	88.50 238	99.65 146	91.77 323	99.00 150	98.66 231

GeoE		96.58 166	96.07 170	98.10 152	98.35 194	95.89 181	99.34 17	98.12 269	93.12 292	96.09 233	98.87 143	89.71 197	98.97 256	92.95 290	98.08 197	99.43 119

XVG-OURS		96.55 167	96.41 159	96.99 230	98.75 153	93.76 278	97.50 342	98.52 184	95.67 150	96.83 201	99.30 65	88.95 226	99.53 175	95.88 189	96.26 261	97.69 276

FIs		96.51 168	96.12 169	97.67 188	97.13 317	97.54 82	99.36 14	99.22 28	95.89 137	94.03 299	98.35 202	91.98 141	98.44 319	96.40 172	92.76 318	97.01 295

XVG-OURS-SEG-HR		96.51 168	96.34 161	97.02 229	98.77 152	93.76 278	97.79 321	98.50 192	95.45 159	96.94 195	99.09 108	87.87 254	99.55 172	96.76 163	95.83 273	97.74 273

PS-MVSNAJss		96.43 170	96.26 165	96.92 239	95.84 384	95.08 219	99.16 51	98.50 192	95.87 139	93.84 308	98.34 206	94.51 88	98.61 301	96.88 152	93.45 307	97.06 293

test_fmvs1		96.42 171	96.67 150	95.66 324	98.82 149	88.53 400	98.80 150	98.20 251	96.39 117	99.64 27	99.20 82	80.35 364	99.67 142	99.04 30	99.57 93	98.78 213

FC-MVSNet-test		96.42 171	96.05 171	97.53 199	96.95 326	97.27 100	99.36 14	99.23 24	95.83 141	93.93 302	98.37 200	92.00 140	98.32 340	96.02 185	92.72 319	97.00 296

ab-mvs		96.42 171	95.71 190	98.55 100	98.63 171	96.75 129	97.88 309	98.74 122	93.84 248	96.54 218	98.18 222	85.34 301	99.75 125	95.93 187	96.35 251	99.15 169

FA-MVS(test-final)		96.41 174	95.94 178	97.82 171	98.21 215	95.20 213	97.80 319	97.58 318	93.21 286	97.36 179	97.70 264	89.47 203	99.56 165	94.12 255	97.99 199	98.71 223

PVSNet	91.96 18	96.35 175	96.15 168	96.96 234	99.17 104	92.05 326	96.08 407	98.68 139	93.69 262	97.75 158	97.80 258	88.86 227	99.69 140	94.26 249	99.01 148	99.15 169

Test_1112_low_res		96.34 176	95.66 195	98.36 126	98.56 175	95.94 174	97.71 326	98.07 282	92.10 330	94.79 263	97.29 302	91.75 147	99.56 165	94.17 253	96.50 248	99.58 92

Effi-MVS+-dtu		96.29 177	96.56 153	95.51 329	97.89 255	90.22 366	98.80 150	98.10 275	96.57 109	96.45 223	96.66 359	90.81 175	98.91 269	95.72 196	97.99 199	97.40 284

QAPM		96.29 177	95.40 200	98.96 69	97.85 256	97.60 79	99.23 33	98.93 60	89.76 384	93.11 339	99.02 117	89.11 218	99.93 31	91.99 317	99.62 84	99.34 132

Fast-Effi-MVS+		96.28 179	95.70 192	98.03 156	98.29 208	95.97 171	98.58 206	98.25 246	91.74 338	95.29 252	97.23 307	91.03 173	99.15 229	92.90 292	97.96 201	98.97 194

nrg030		96.28 179	95.72 187	97.96 162	96.90 331	98.15 59	99.39 11	98.31 231	95.47 158	94.42 277	98.35 202	92.09 138	98.69 293	97.50 125	89.05 369	97.04 294

1314		96.25 181	95.73 186	97.79 173	97.13 317	95.55 194	98.19 263	98.59 165	93.47 275	92.03 368	97.82 256	91.33 161	99.49 183	94.62 234	98.44 182	98.32 256

sd_testset		96.17 182	95.76 185	97.42 204	99.30 76	94.34 259	98.82 141	99.08 41	95.92 135	95.96 239	98.76 163	82.83 343	99.32 208	95.56 202	95.59 274	98.60 236

h-mvs33		96.17 182	95.62 196	97.81 172	99.03 122	94.45 252	98.64 197	98.75 120	97.48 49	98.67 96	98.72 166	89.76 194	99.86 76	97.95 86	81.59 418	99.11 176

HQP_MVS		96.14 184	95.90 180	96.85 242	97.42 295	94.60 248	98.80 150	98.56 175	97.28 64	95.34 248	98.28 211	87.09 268	99.03 249	96.07 180	94.27 282	96.92 303

tttt0517		96.07 185	95.51 198	97.78 174	98.41 188	94.84 233	99.28 25	94.33 426	94.26 227	97.64 171	98.64 173	84.05 330	99.47 192	95.34 208	97.60 215	99.03 188

MVSTER		96.06 186	95.72 187	97.08 226	98.23 213	95.93 177	98.73 173	98.27 241	94.86 199	95.07 254	98.09 227	88.21 242	98.54 308	96.59 165	93.46 305	96.79 322

thisisatest0530		96.01 187	95.36 205	97.97 160	98.38 190	95.52 196	98.88 122	94.19 428	94.04 233	97.64 171	98.31 209	83.82 337	99.46 193	95.29 213	97.70 212	98.93 199

test_djsdf		96.00 188	95.69 193	96.93 236	95.72 386	95.49 197	99.47 7	98.40 213	94.98 191	94.58 267	97.86 249	89.16 216	98.41 328	96.91 146	94.12 290	96.88 312

EI-MVSNet		95.96 189	95.83 182	96.36 290	97.93 251	93.70 284	98.12 275	98.27 241	93.70 261	95.07 254	99.02 117	92.23 132	98.54 308	94.68 230	93.46 305	96.84 318

VortexMVS		95.95 190	95.79 183	96.42 286	98.29 208	93.96 272	98.68 186	98.31 231	96.02 132	94.29 284	97.57 280	89.47 203	98.37 335	97.51 124	91.93 326	96.94 301

ECVR-MVS		95.95 190	95.71 190	96.65 254	99.02 123	90.86 348	99.03 77	91.80 439	96.96 87	98.10 128	99.26 71	81.31 350	99.51 179	96.90 149	99.04 145	99.59 88

BH-untuned		95.95 190	95.72 187	96.65 254	98.55 177	92.26 320	98.23 256	97.79 303	93.73 256	94.62 266	98.01 234	88.97 225	99.00 255	93.04 287	98.51 178	98.68 227

test1111		95.94 193	95.78 184	96.41 287	98.99 130	90.12 367	99.04 74	92.45 438	96.99 86	98.03 135	99.27 70	81.40 349	99.48 188	96.87 155	99.04 145	99.63 82

MSDG		95.93 194	95.30 212	97.83 169	98.90 138	95.36 203	96.83 394	98.37 221	91.32 353	94.43 276	98.73 165	90.27 187	99.60 158	90.05 355	98.82 162	98.52 244

BH-RMVSNet		95.92 195	95.32 210	97.69 185	98.32 205	94.64 242	98.19 263	97.45 339	94.56 214	96.03 235	98.61 174	85.02 306	99.12 235	90.68 346	99.06 144	99.30 141

test_fmvs1_n		95.90 196	95.99 177	95.63 325	98.67 165	88.32 404	99.26 28	98.22 248	96.40 116	99.67 24	99.26 71	73.91 413	99.70 135	99.02 31	99.50 110	98.87 203

Fast-Effi-MVS+-dtu		95.87 197	95.85 181	95.91 311	97.74 265	91.74 332	98.69 184	98.15 265	95.56 154	94.92 257	97.68 269	88.98 224	98.79 287	93.19 282	97.78 208	97.20 291

LFMVS		95.86 198	94.98 227	98.47 114	98.87 143	96.32 155	98.84 137	96.02 405	93.40 278	98.62 102	99.20 82	74.99 407	99.63 152	97.72 102	97.20 223	99.46 114

baseline1		95.84 199	95.12 220	98.01 158	98.49 184	95.98 166	98.73 173	97.03 372	95.37 166	96.22 228	98.19 221	89.96 191	99.16 226	94.60 235	87.48 385	98.90 202

OpenMVS	93.04 13	95.83 200	95.00 225	98.32 128	97.18 314	97.32 93	99.21 40	98.97 52	89.96 380	91.14 377	99.05 115	86.64 276	99.92 40	93.38 276	99.47 115	97.73 274

VDD-MVS		95.82 201	95.23 214	97.61 195	98.84 148	93.98 271	98.68 186	97.40 343	95.02 189	97.95 143	99.34 61	74.37 412	99.78 117	98.64 45	96.80 236	99.08 182

UniMVSNet (Re)		95.78 202	95.19 216	97.58 196	96.99 324	97.47 86	98.79 158	99.18 32	95.60 152	93.92 303	97.04 329	91.68 149	98.48 312	95.80 193	87.66 384	96.79 322

VPA-MVSNet		95.75 203	95.11 221	97.69 185	97.24 306	97.27 100	98.94 100	99.23 24	95.13 178	95.51 246	97.32 300	85.73 293	98.91 269	97.33 134	89.55 360	96.89 311

HQP-MVS		95.72 204	95.40 200	96.69 252	97.20 310	94.25 264	98.05 284	98.46 200	96.43 113	94.45 272	97.73 261	86.75 274	98.96 260	95.30 211	94.18 286	96.86 317

hse-mvs2		95.71 205	95.30 212	96.93 236	98.50 180	93.53 289	98.36 238	98.10 275	97.48 49	98.67 96	97.99 236	89.76 194	99.02 252	97.95 86	80.91 423	98.22 259

UniMVSNet_NR-MVSNet		95.71 205	95.15 217	97.40 207	96.84 334	96.97 118	98.74 167	99.24 19	95.16 177	93.88 305	97.72 263	91.68 149	98.31 342	95.81 191	87.25 390	96.92 303

PatchmatchNet		95.71 205	95.52 197	96.29 296	97.58 278	90.72 352	96.84 393	97.52 329	94.06 232	97.08 188	96.96 339	89.24 214	98.90 272	92.03 316	98.37 186	99.26 149
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 208	95.33 209	96.76 247	96.16 370	94.63 243	98.43 233	98.39 215	96.64 105	95.02 256	98.78 155	85.15 305	99.05 245	95.21 218	94.20 285	96.60 345
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 208	95.38 204	96.61 262	97.61 275	93.84 276	98.91 110	98.44 204	95.25 173	94.28 285	98.47 190	86.04 290	99.12 235	95.50 205	93.95 295	96.87 315
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 210	95.69 193	95.44 333	97.54 283	88.54 399	96.97 379	97.56 321	93.50 273	97.52 177	96.93 343	89.49 201	99.16 226	95.25 215	96.42 250	98.64 233

FE-MVS		95.62 211	94.90 231	97.78 174	98.37 192	94.92 230	97.17 369	97.38 345	90.95 364	97.73 161	97.70 264	85.32 303	99.63 152	91.18 333	98.33 189	98.79 209

LPG-MVS_test		95.62 211	95.34 206	96.47 280	97.46 290	93.54 287	98.99 87	98.54 179	94.67 208	94.36 280	98.77 158	85.39 298	99.11 237	95.71 197	94.15 288	96.76 325

CLD-MVS		95.62 211	95.34 206	96.46 283	97.52 286	93.75 280	97.27 360	98.46 200	95.53 155	94.42 277	98.00 235	86.21 285	98.97 256	96.25 178	94.37 280	96.66 340
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 214	94.89 232	97.76 178	98.15 226	95.15 216	96.77 395	94.41 424	92.95 299	97.18 185	97.43 291	84.78 312	99.45 194	94.63 232	97.73 211	98.68 227

MonoMVSNet		95.51 215	95.45 199	95.68 322	95.54 391	90.87 347	98.92 108	97.37 346	95.79 143	95.53 245	97.38 296	89.58 200	97.68 386	96.40 172	92.59 320	98.49 246

thres600view7		95.49 216	94.77 235	97.67 188	98.98 131	95.02 221	98.85 133	96.90 382	95.38 164	96.63 210	96.90 345	84.29 322	99.59 159	88.65 379	96.33 252	98.40 250

test_vis1_n		95.47 217	95.13 218	96.49 277	97.77 261	90.41 362	99.27 27	98.11 272	96.58 107	99.66 25	99.18 88	67.00 427	99.62 156	99.21 26	99.40 125	99.44 117

SCA		95.46 218	95.13 218	96.46 283	97.67 270	91.29 340	97.33 355	97.60 317	94.68 207	96.92 198	97.10 314	83.97 332	98.89 273	92.59 300	98.32 191	99.20 158

IterMVS-LS		95.46 218	95.21 215	96.22 298	98.12 228	93.72 283	98.32 245	98.13 268	93.71 259	94.26 286	97.31 301	92.24 131	98.10 358	94.63 232	90.12 351	96.84 318
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 220	95.34 206	95.77 320	98.69 162	88.75 395	98.87 125	97.21 359	96.13 127	97.22 183	97.68 269	77.95 384	99.65 146	97.58 115	96.77 239	98.91 201

jajsoiax		95.45 220	95.03 224	96.73 248	95.42 399	94.63 243	99.14 55	98.52 184	95.74 145	93.22 332	98.36 201	83.87 335	98.65 298	96.95 145	94.04 291	96.91 308

CVMVSNet		95.43 222	96.04 172	93.57 385	97.93 251	83.62 423	98.12 275	98.59 165	95.68 149	96.56 214	99.02 117	87.51 260	97.51 395	93.56 274	97.44 219	99.60 86

anonymousdsp		95.42 223	94.91 230	96.94 235	95.10 403	95.90 180	99.14 55	98.41 211	93.75 253	93.16 335	97.46 287	87.50 262	98.41 328	95.63 201	94.03 292	96.50 364

DU-MVS		95.42 223	94.76 236	97.40 207	96.53 351	96.97 118	98.66 193	98.99 51	95.43 160	93.88 305	97.69 266	88.57 233	98.31 342	95.81 191	87.25 390	96.92 303

mvs_tets		95.41 225	95.00 225	96.65 254	95.58 390	94.42 254	99.00 84	98.55 177	95.73 147	93.21 333	98.38 199	83.45 341	98.63 299	97.09 139	94.00 293	96.91 308

thres100view900		95.38 226	94.70 240	97.41 205	98.98 131	94.92 230	98.87 125	96.90 382	95.38 164	96.61 212	96.88 346	84.29 322	99.56 165	88.11 382	96.29 256	97.76 271

thres400		95.38 226	94.62 244	97.65 192	98.94 136	94.98 226	98.68 186	96.93 380	95.33 167	96.55 216	96.53 365	84.23 326	99.56 165	88.11 382	96.29 256	98.40 250

BH-w/o		95.38 226	95.08 222	96.26 297	98.34 199	91.79 329	97.70 327	97.43 341	92.87 302	94.24 288	97.22 308	88.66 231	98.84 279	91.55 329	97.70 212	98.16 262

VDDNet		95.36 229	94.53 249	97.86 167	98.10 230	95.13 217	98.85 133	97.75 305	90.46 371	98.36 118	99.39 45	73.27 415	99.64 149	97.98 85	96.58 244	98.81 208

TAPA-MVS	93.98 7	95.35 230	94.56 248	97.74 180	99.13 112	94.83 235	98.33 241	98.64 152	86.62 406	96.29 227	98.61 174	94.00 102	99.29 213	80.00 424	99.41 122	99.09 178
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 231	94.98 227	96.43 285	97.67 270	93.48 291	98.73 173	98.44 204	94.94 197	92.53 355	98.53 184	84.50 321	99.14 231	95.48 206	94.00 293	96.66 340
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 232	94.87 233	96.71 249	99.29 81	93.24 305	98.58 206	98.11 272	89.92 381	93.57 317	99.10 101	86.37 283	99.79 114	90.78 344	98.10 196	97.09 292
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 233	94.72 239	97.13 221	98.05 236	93.26 302	97.87 310	97.20 360	94.96 193	96.18 231	95.66 398	80.97 356	99.35 204	94.47 241	97.08 226	98.78 213

tfpn200view9		95.32 233	94.62 244	97.43 203	98.94 136	94.98 226	98.68 186	96.93 380	95.33 167	96.55 216	96.53 365	84.23 326	99.56 165	88.11 382	96.29 256	97.76 271

Anonymous202405211		95.28 235	94.49 251	97.67 188	99.00 127	93.75 280	98.70 182	97.04 371	90.66 367	96.49 220	98.80 153	78.13 380	99.83 83	96.21 179	95.36 278	99.44 117

thres200		95.25 236	94.57 247	97.28 211	98.81 150	94.92 230	98.20 260	97.11 364	95.24 175	96.54 218	96.22 376	84.58 319	99.53 175	87.93 387	96.50 248	97.39 285

AllTest		95.24 237	94.65 243	96.99 230	99.25 89	93.21 306	98.59 204	98.18 256	91.36 349	93.52 319	98.77 158	84.67 316	99.72 129	89.70 362	97.87 204	98.02 266

LCM-MVSNet-Re		95.22 238	95.32 210	94.91 350	98.18 221	87.85 410	98.75 163	95.66 412	95.11 180	88.96 397	96.85 349	90.26 188	97.65 387	95.65 200	98.44 182	99.22 155

EPNet_dtu		95.21 239	94.95 229	95.99 306	96.17 368	90.45 360	98.16 270	97.27 354	96.77 95	93.14 338	98.33 207	90.34 184	98.42 321	85.57 400	98.81 163	99.09 178
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 240	94.45 256	97.46 200	96.75 341	96.56 142	98.86 129	98.65 151	93.30 283	93.27 331	98.27 214	84.85 310	98.87 276	94.82 227	91.26 337	96.96 298

D2MVS		95.18 241	95.08 222	95.48 330	97.10 319	92.07 325	98.30 248	99.13 39	94.02 235	92.90 343	96.73 355	89.48 202	98.73 291	94.48 240	93.60 304	95.65 394

WR-MVS		95.15 242	94.46 254	97.22 213	96.67 346	96.45 146	98.21 258	98.81 100	94.15 229	93.16 335	97.69 266	87.51 260	98.30 344	95.29 213	88.62 375	96.90 310

TranMVSNet+NR-MVSNet		95.14 243	94.48 252	97.11 224	96.45 357	96.36 153	99.03 77	99.03 46	95.04 185	93.58 316	97.93 242	88.27 241	98.03 364	94.13 254	86.90 395	96.95 300

myMVS_eth3d28		95.12 244	94.62 244	96.64 258	98.17 224	92.17 321	98.02 288	97.32 348	95.41 162	96.22 228	96.05 382	78.01 382	99.13 232	95.22 217	97.16 224	98.60 236

baseline2		95.11 245	94.52 250	96.87 241	96.65 347	93.56 286	98.27 253	94.10 430	93.45 276	92.02 369	97.43 291	87.45 265	99.19 224	93.88 263	97.41 221	97.87 269

miper_enhance_ethall		95.10 246	94.75 237	96.12 302	97.53 285	93.73 282	96.61 401	98.08 280	92.20 329	93.89 304	96.65 361	92.44 122	98.30 344	94.21 250	91.16 338	96.34 373

Anonymous20240529		95.10 246	94.22 266	97.75 179	99.01 125	94.26 263	98.87 125	98.83 91	85.79 414	96.64 209	98.97 125	78.73 373	99.85 77	96.27 175	94.89 279	99.12 173

test-LLR		95.10 246	94.87 233	95.80 317	96.77 338	89.70 375	96.91 384	95.21 416	95.11 180	94.83 261	95.72 395	87.71 256	98.97 256	93.06 285	98.50 179	98.72 220

WR-MVS_H		95.05 249	94.46 254	96.81 245	96.86 333	95.82 185	99.24 31	99.24 19	93.87 247	92.53 355	96.84 350	90.37 183	98.24 350	93.24 280	87.93 381	96.38 372

miper_ehance_all_eth		95.01 250	94.69 241	95.97 308	97.70 268	93.31 300	97.02 377	98.07 282	92.23 326	93.51 321	96.96 339	91.85 145	98.15 354	93.68 268	91.16 338	96.44 370

testing11		95.00 251	94.28 263	97.16 219	97.96 248	93.36 299	98.09 280	97.06 370	94.94 197	95.33 251	96.15 378	76.89 397	99.40 199	95.77 195	96.30 255	98.72 220

ADS-MVSNet		95.00 251	94.45 256	96.63 259	98.00 242	91.91 328	96.04 408	97.74 306	90.15 377	96.47 221	96.64 362	87.89 252	98.96 260	90.08 353	97.06 227	99.02 189

VPNet		94.99 253	94.19 268	97.40 207	97.16 315	96.57 141	98.71 178	98.97 52	95.67 150	94.84 259	98.24 218	80.36 363	98.67 297	96.46 169	87.32 389	96.96 298

EPMVS		94.99 253	94.48 252	96.52 275	97.22 308	91.75 331	97.23 361	91.66 440	94.11 230	97.28 180	96.81 352	85.70 294	98.84 279	93.04 287	97.28 222	98.97 194

testing91		94.98 255	94.25 265	97.20 214	97.94 249	93.41 294	98.00 291	97.58 318	94.99 190	95.45 247	96.04 383	77.20 392	99.42 197	94.97 223	96.02 269	98.78 213

NR-MVSNet		94.98 255	94.16 271	97.44 202	96.53 351	97.22 108	98.74 167	98.95 56	94.96 193	89.25 396	97.69 266	89.32 211	98.18 352	94.59 237	87.40 387	96.92 303

FMVSNet3		94.97 257	94.26 264	97.11 224	98.18 221	96.62 133	98.56 214	98.26 245	93.67 266	94.09 295	97.10 314	84.25 324	98.01 365	92.08 312	92.14 323	96.70 334

CostFormer		94.95 258	94.73 238	95.60 327	97.28 304	89.06 388	97.53 339	96.89 384	89.66 386	96.82 203	96.72 356	86.05 288	98.95 265	95.53 204	96.13 267	98.79 209

PAPM		94.95 258	94.00 284	97.78 174	97.04 321	95.65 189	96.03 410	98.25 246	91.23 358	94.19 291	97.80 258	91.27 164	98.86 278	82.61 417	97.61 214	98.84 206

CP-MVSNet		94.94 260	94.30 262	96.83 243	96.72 343	95.56 192	99.11 61	98.95 56	93.89 245	92.42 360	97.90 245	87.19 267	98.12 357	94.32 246	88.21 378	96.82 321

TR-MVS		94.94 260	94.20 267	97.17 218	97.75 262	94.14 268	97.59 336	97.02 375	92.28 325	95.75 243	97.64 274	83.88 334	98.96 260	89.77 359	96.15 266	98.40 250

RPSCF		94.87 262	95.40 200	93.26 391	98.89 139	82.06 429	98.33 241	98.06 287	90.30 376	96.56 214	99.26 71	87.09 268	99.49 183	93.82 265	96.32 253	98.24 257

testing99		94.83 263	94.08 276	97.07 227	97.94 249	93.13 308	98.10 279	97.17 362	94.86 199	95.34 248	96.00 387	76.31 400	99.40 199	95.08 220	95.90 270	98.68 227

GA-MVS		94.81 264	94.03 280	97.14 220	97.15 316	93.86 275	96.76 396	97.58 318	94.00 239	94.76 265	97.04 329	80.91 357	98.48 312	91.79 322	96.25 262	99.09 178

c3_l		94.79 265	94.43 258	95.89 313	97.75 262	93.12 310	97.16 371	98.03 289	92.23 326	93.46 325	97.05 328	91.39 158	98.01 365	93.58 273	89.21 367	96.53 356

V42		94.78 266	94.14 273	96.70 251	96.33 362	95.22 212	98.97 91	98.09 279	92.32 323	94.31 283	97.06 325	88.39 239	98.55 307	92.90 292	88.87 373	96.34 373

reproduce_monomvs		94.77 267	94.67 242	95.08 345	98.40 189	89.48 381	98.80 150	98.64 152	97.57 43	93.21 333	97.65 271	80.57 362	98.83 282	97.72 102	89.47 363	96.93 302

CR-MVSNet		94.76 268	94.15 272	96.59 265	97.00 322	93.43 292	94.96 421	97.56 321	92.46 314	96.93 196	96.24 372	88.15 244	97.88 378	87.38 389	96.65 242	98.46 248

v2v482		94.69 269	94.03 280	96.65 254	96.17 368	94.79 238	98.67 191	98.08 280	92.72 306	94.00 300	97.16 311	87.69 259	98.45 317	92.91 291	88.87 373	96.72 330

pmmvs4		94.69 269	93.99 286	96.81 245	95.74 385	95.94 174	97.40 346	97.67 310	90.42 373	93.37 328	97.59 278	89.08 219	98.20 351	92.97 289	91.67 331	96.30 376

cl22		94.68 271	94.19 268	96.13 301	98.11 229	93.60 285	96.94 381	98.31 231	92.43 318	93.32 330	96.87 348	86.51 277	98.28 348	94.10 257	91.16 338	96.51 362

eth_miper_zixun_eth		94.68 271	94.41 259	95.47 331	97.64 273	91.71 333	96.73 398	98.07 282	92.71 307	93.64 314	97.21 309	90.54 181	98.17 353	93.38 276	89.76 355	96.54 354

PCF-MVS	93.45 11	94.68 271	93.43 322	98.42 122	98.62 172	96.77 128	95.48 418	98.20 251	84.63 419	93.34 329	98.32 208	88.55 236	99.81 95	84.80 409	98.96 151	98.68 227
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 274	93.54 317	98.08 153	96.88 332	96.56 142	98.19 263	98.50 192	78.05 431	92.69 350	98.02 232	91.07 172	99.63 152	90.09 352	98.36 188	98.04 265

PS-CasMVS		94.67 274	93.99 286	96.71 249	96.68 345	95.26 209	99.13 58	99.03 46	93.68 264	92.33 361	97.95 240	85.35 300	98.10 358	93.59 272	88.16 380	96.79 322

cascas		94.63 276	93.86 296	96.93 236	96.91 330	94.27 262	96.00 411	98.51 187	85.55 415	94.54 268	96.23 374	84.20 328	98.87 276	95.80 193	96.98 232	97.66 277

tpmvs		94.60 277	94.36 261	95.33 337	97.46 290	88.60 398	96.88 390	97.68 307	91.29 355	93.80 310	96.42 369	88.58 232	99.24 218	91.06 339	96.04 268	98.17 261

LTVRE_ROB	92.95 15	94.60 277	93.90 292	96.68 253	97.41 298	94.42 254	98.52 217	98.59 165	91.69 341	91.21 376	98.35 202	84.87 309	99.04 248	91.06 339	93.44 308	96.60 345
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		94.59 279	93.92 289	96.60 264	96.21 364	94.78 239	98.59 204	98.14 267	91.86 337	94.21 290	97.02 332	87.97 250	98.41 328	91.72 324	89.57 358	96.61 344

ADS-MVSNet2		94.58 280	94.40 260	95.11 343	98.00 242	88.74 396	96.04 408	97.30 350	90.15 377	96.47 221	96.64 362	87.89 252	97.56 393	90.08 353	97.06 227	99.02 189

WBMVS		94.56 281	94.04 278	96.10 303	98.03 240	93.08 312	97.82 318	98.18 256	94.02 235	93.77 312	96.82 351	81.28 351	98.34 337	95.47 207	91.00 341	96.88 312

ACMH	92.88 16	94.55 282	93.95 288	96.34 292	97.63 274	93.26 302	98.81 149	98.49 197	93.43 277	89.74 390	98.53 184	81.91 346	99.08 243	93.69 267	93.30 311	96.70 334
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 283	93.85 297	96.63 259	97.98 246	93.06 313	98.77 162	97.84 301	93.67 266	93.80 310	98.04 231	76.88 398	98.96 260	94.79 229	92.86 316	97.86 270

XVG-ACMP-BASELINE		94.54 283	94.14 273	95.75 321	96.55 350	91.65 334	98.11 277	98.44 204	94.96 193	94.22 289	97.90 245	79.18 372	99.11 237	94.05 259	93.85 297	96.48 367

AUN-MVS		94.53 285	93.73 307	96.92 239	98.50 180	93.52 290	98.34 240	98.10 275	93.83 250	95.94 241	97.98 238	85.59 296	99.03 249	94.35 244	80.94 422	98.22 259

DIV-MVS_self_test		94.52 286	94.03 280	95.99 306	97.57 282	93.38 297	97.05 375	97.94 295	91.74 338	92.81 345	97.10 314	89.12 217	98.07 362	92.60 298	90.30 348	96.53 356

cl____		94.51 287	94.01 283	96.02 305	97.58 278	93.40 296	97.05 375	97.96 294	91.73 340	92.76 347	97.08 320	89.06 220	98.13 356	92.61 297	90.29 349	96.52 359

ETVMVS		94.50 288	93.44 321	97.68 187	98.18 221	95.35 205	98.19 263	97.11 364	93.73 256	96.40 224	95.39 401	74.53 409	98.84 279	91.10 335	96.31 254	98.84 206

GBi-Net		94.49 289	93.80 300	96.56 269	98.21 215	95.00 222	98.82 141	98.18 256	92.46 314	94.09 295	97.07 321	81.16 352	97.95 370	92.08 312	92.14 323	96.72 330

test1		94.49 289	93.80 300	96.56 269	98.21 215	95.00 222	98.82 141	98.18 256	92.46 314	94.09 295	97.07 321	81.16 352	97.95 370	92.08 312	92.14 323	96.72 330

dmvs_re		94.48 291	94.18 270	95.37 335	97.68 269	90.11 368	98.54 216	97.08 366	94.56 214	94.42 277	97.24 306	84.25 324	97.76 384	91.02 342	92.83 317	98.24 257

v8		94.47 292	93.77 303	96.57 268	96.36 360	94.83 235	99.05 70	98.19 253	91.92 334	93.16 335	96.97 337	88.82 230	98.48 312	91.69 325	87.79 382	96.39 371

FMVSNet2		94.47 292	93.61 313	97.04 228	98.21 215	96.43 148	98.79 158	98.27 241	92.46 314	93.50 322	97.09 318	81.16 352	98.00 367	91.09 336	91.93 326	96.70 334

test2506		94.44 294	93.91 291	96.04 304	99.02 123	88.99 391	99.06 68	79.47 452	96.96 87	98.36 118	99.26 71	77.21 391	99.52 178	96.78 162	99.04 145	99.59 88

Patchmatch-test		94.42 295	93.68 311	96.63 259	97.60 276	91.76 330	94.83 425	97.49 333	89.45 390	94.14 293	97.10 314	88.99 221	98.83 282	85.37 403	98.13 195	99.29 143

PEN-MVS		94.42 295	93.73 307	96.49 277	96.28 363	94.84 233	99.17 50	99.00 48	93.51 272	92.23 363	97.83 255	86.10 287	97.90 374	92.55 303	86.92 394	96.74 327

v144192		94.39 297	93.70 309	96.48 279	96.06 374	94.35 258	98.58 206	98.16 264	91.45 346	94.33 282	97.02 332	87.50 262	98.45 317	91.08 338	89.11 368	96.63 342

Baseline_NR-MVSNet		94.35 298	93.81 299	95.96 309	96.20 365	94.05 270	98.61 203	96.67 394	91.44 347	93.85 307	97.60 277	88.57 233	98.14 355	94.39 242	86.93 393	95.68 393

miper_lstm_enhance		94.33 299	94.07 277	95.11 343	97.75 262	90.97 344	97.22 362	98.03 289	91.67 342	92.76 347	96.97 337	90.03 190	97.78 383	92.51 305	89.64 357	96.56 351

v1192		94.32 300	93.58 314	96.53 274	96.10 372	94.45 252	98.50 223	98.17 262	91.54 344	94.19 291	97.06 325	86.95 272	98.43 320	90.14 351	89.57 358	96.70 334

UWE-MVS		94.30 301	93.89 294	95.53 328	97.83 257	88.95 392	97.52 341	93.25 432	94.44 222	96.63 210	97.07 321	78.70 374	99.28 214	91.99 317	97.56 217	98.36 253

ACMH+	92.99 14	94.30 301	93.77 303	95.88 314	97.81 259	92.04 327	98.71 178	98.37 221	93.99 240	90.60 383	98.47 190	80.86 359	99.05 245	92.75 296	92.40 322	96.55 353

v148		94.29 303	93.76 305	95.91 311	96.10 372	92.93 314	98.58 206	97.97 292	92.59 312	93.47 324	96.95 341	88.53 237	98.32 340	92.56 302	87.06 392	96.49 365

v10		94.29 303	93.55 316	96.51 276	96.39 359	94.80 237	98.99 87	98.19 253	91.35 351	93.02 341	96.99 335	88.09 246	98.41 328	90.50 348	88.41 377	96.33 375

MVP-Stereo		94.28 305	93.92 289	95.35 336	94.95 405	92.60 317	97.97 294	97.65 311	91.61 343	90.68 382	97.09 318	86.32 284	98.42 321	89.70 362	99.34 131	95.02 407
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 306	93.33 324	96.97 233	97.19 313	93.38 297	98.74 167	98.57 172	91.21 360	93.81 309	98.58 179	72.85 416	98.77 289	95.05 221	93.93 296	98.77 216

OurMVSNet-221017-0		94.21 307	94.00 284	94.85 355	95.60 389	89.22 386	98.89 115	97.43 341	95.29 170	92.18 365	98.52 187	82.86 342	98.59 305	93.46 275	91.76 329	96.74 327

v1921920		94.20 308	93.47 320	96.40 289	95.98 378	94.08 269	98.52 217	98.15 265	91.33 352	94.25 287	97.20 310	86.41 282	98.42 321	90.04 356	89.39 365	96.69 339

WB-MVSnew		94.19 309	94.04 278	94.66 363	96.82 336	92.14 322	97.86 312	95.96 408	93.50 273	95.64 244	96.77 354	88.06 248	97.99 368	84.87 406	96.86 233	93.85 424

v7n		94.19 309	93.43 322	96.47 280	95.90 381	94.38 257	99.26 28	98.34 227	91.99 332	92.76 347	97.13 313	88.31 240	98.52 310	89.48 367	87.70 383	96.52 359

tpm2		94.19 309	93.76 305	95.46 332	97.23 307	89.04 389	97.31 357	96.85 388	87.08 405	96.21 230	96.79 353	83.75 338	98.74 290	92.43 308	96.23 264	98.59 239

TESTMET0.1,1		94.18 312	93.69 310	95.63 325	96.92 328	89.12 387	96.91 384	94.78 421	93.17 288	94.88 258	96.45 368	78.52 375	98.92 267	93.09 284	98.50 179	98.85 204

dp		94.15 313	93.90 292	94.90 351	97.31 303	86.82 415	96.97 379	97.19 361	91.22 359	96.02 236	96.61 364	85.51 297	99.02 252	90.00 357	94.30 281	98.85 204

ET-MVSNet_ETH3D		94.13 314	92.98 332	97.58 196	98.22 214	96.20 159	97.31 357	95.37 415	94.53 216	79.56 433	97.63 276	86.51 277	97.53 394	96.91 146	90.74 343	99.02 189

tpm		94.13 314	93.80 300	95.12 342	96.50 353	87.91 409	97.44 343	95.89 411	92.62 310	96.37 226	96.30 371	84.13 329	98.30 344	93.24 280	91.66 332	99.14 171

testing222		94.12 316	93.03 331	97.37 210	98.02 241	94.66 240	97.94 298	96.65 396	94.63 210	95.78 242	95.76 390	71.49 417	98.92 267	91.17 334	95.88 271	98.52 244

IterMVS-SCA-FT		94.11 317	93.87 295	94.85 355	97.98 246	90.56 359	97.18 367	98.11 272	93.75 253	92.58 353	97.48 286	83.97 332	97.41 397	92.48 307	91.30 335	96.58 347

Anonymous20231211		94.10 318	93.26 327	96.61 262	99.11 115	94.28 261	99.01 82	98.88 72	86.43 408	92.81 345	97.57 280	81.66 348	98.68 296	94.83 226	89.02 371	96.88 312

IterMVS		94.09 319	93.85 297	94.80 359	97.99 244	90.35 364	97.18 367	98.12 269	93.68 264	92.46 359	97.34 297	84.05 330	97.41 397	92.51 305	91.33 334	96.62 343
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 320	93.51 318	95.80 317	96.77 338	89.70 375	96.91 384	95.21 416	92.89 301	94.83 261	95.72 395	77.69 386	98.97 256	93.06 285	98.50 179	98.72 220

test0.0.03 1		94.08 320	93.51 318	95.80 317	95.53 393	92.89 315	97.38 348	95.97 407	95.11 180	92.51 357	96.66 359	87.71 256	96.94 404	87.03 391	93.67 300	97.57 281

v1240		94.06 322	93.29 326	96.34 292	96.03 376	93.90 274	98.44 231	98.17 262	91.18 361	94.13 294	97.01 334	86.05 288	98.42 321	89.13 373	89.50 362	96.70 334

X-MVStestdata		94.06 322	92.30 348	99.34 27	99.70 24	98.35 45	99.29 23	98.88 72	97.40 54	98.46 110	43.50 447	95.90 45	99.89 61	97.85 94	99.74 53	99.78 27

DTE-MVSNet		93.98 324	93.26 327	96.14 300	96.06 374	94.39 256	99.20 43	98.86 85	93.06 294	91.78 370	97.81 257	85.87 292	97.58 392	90.53 347	86.17 399	96.46 369

pm-mvs1		93.94 325	93.06 330	96.59 265	96.49 354	95.16 214	98.95 97	98.03 289	92.32 323	91.08 378	97.84 252	84.54 320	98.41 328	92.16 310	86.13 402	96.19 381

MS-PatchMatch		93.84 326	93.63 312	94.46 373	96.18 367	89.45 382	97.76 322	98.27 241	92.23 326	92.13 366	97.49 285	79.50 369	98.69 293	89.75 360	99.38 127	95.25 399

tfpnnormal		93.66 327	92.70 338	96.55 273	96.94 327	95.94 174	98.97 91	99.19 31	91.04 362	91.38 375	97.34 297	84.94 308	98.61 301	85.45 402	89.02 371	95.11 403

EU-MVSNet		93.66 327	94.14 273	92.25 401	95.96 380	83.38 425	98.52 217	98.12 269	94.69 206	92.61 352	98.13 225	87.36 266	96.39 417	91.82 321	90.00 353	96.98 297

our_test_3		93.65 329	93.30 325	94.69 361	95.45 397	89.68 377	96.91 384	97.65 311	91.97 333	91.66 373	96.88 346	89.67 198	97.93 373	88.02 385	91.49 333	96.48 367

pmmvs5		93.65 329	92.97 333	95.68 322	95.49 394	92.37 318	98.20 260	97.28 353	89.66 386	92.58 353	97.26 303	82.14 345	98.09 360	93.18 283	90.95 342	96.58 347

SSC-MVS3.2		93.59 331	93.13 329	94.97 348	96.81 337	89.71 374	97.95 295	98.49 197	94.59 213	93.50 322	96.91 344	77.74 385	98.37 335	91.69 325	90.47 346	96.83 320

test_fmvs2		93.43 332	93.58 314	92.95 395	96.97 325	83.91 421	99.19 45	97.24 356	95.74 145	95.20 253	98.27 214	69.65 419	98.72 292	96.26 176	93.73 299	96.24 378

tpm cat1		93.36 333	92.80 335	95.07 346	97.58 278	87.97 408	96.76 396	97.86 300	82.17 426	93.53 318	96.04 383	86.13 286	99.13 232	89.24 371	95.87 272	98.10 264

JIA-IIPM		93.35 334	92.49 344	95.92 310	96.48 355	90.65 354	95.01 420	96.96 378	85.93 412	96.08 234	87.33 437	87.70 258	98.78 288	91.35 331	95.58 276	98.34 254

SixPastTwentyTwo		93.34 335	92.86 334	94.75 360	95.67 387	89.41 384	98.75 163	96.67 394	93.89 245	90.15 388	98.25 217	80.87 358	98.27 349	90.90 343	90.64 344	96.57 349

USDC		93.33 336	92.71 337	95.21 339	96.83 335	90.83 350	96.91 384	97.50 331	93.84 248	90.72 381	98.14 224	77.69 386	98.82 284	89.51 366	93.21 313	95.97 387

IB-MVS	91.98 17	93.27 337	91.97 352	97.19 216	97.47 289	93.41 294	97.09 374	95.99 406	93.32 281	92.47 358	95.73 393	78.06 381	99.53 175	94.59 237	82.98 413	98.62 234
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		93.26 338	92.21 349	96.41 287	97.73 266	93.13 308	95.65 415	97.03 372	91.27 357	94.04 298	96.06 381	75.33 405	97.19 400	86.56 393	96.23 264	98.92 200

ppachtmachnet_test		93.22 339	92.63 339	94.97 348	95.45 397	90.84 349	96.88 390	97.88 299	90.60 368	92.08 367	97.26 303	88.08 247	97.86 379	85.12 405	90.33 347	96.22 379

Patchmtry		93.22 339	92.35 347	95.84 316	96.77 338	93.09 311	94.66 428	97.56 321	87.37 404	92.90 343	96.24 372	88.15 244	97.90 374	87.37 390	90.10 352	96.53 356

testing3		93.19 341	92.48 345	95.30 338	98.07 231	92.27 319	98.64 197	97.17 362	93.94 244	93.98 301	97.04 329	67.97 424	96.01 421	88.40 380	97.14 225	97.63 278

FMVSNet1		93.19 341	92.07 350	96.56 269	97.54 283	95.00 222	98.82 141	98.18 256	90.38 374	92.27 362	97.07 321	73.68 414	97.95 370	89.36 369	91.30 335	96.72 330

LF4IMVS		93.14 343	92.79 336	94.20 377	95.88 382	88.67 397	97.66 330	97.07 368	93.81 251	91.71 371	97.65 271	77.96 383	98.81 285	91.47 330	91.92 328	95.12 402

mmtdpeth		93.12 344	92.61 340	94.63 365	97.60 276	89.68 377	99.21 40	97.32 348	94.02 235	97.72 162	94.42 412	77.01 396	99.44 195	99.05 29	77.18 434	94.78 412

testgi		93.06 345	92.45 346	94.88 353	96.43 358	89.90 369	98.75 163	97.54 327	95.60 152	91.63 374	97.91 244	74.46 411	97.02 402	86.10 396	93.67 300	97.72 275

PatchT		93.06 345	91.97 352	96.35 291	96.69 344	92.67 316	94.48 431	97.08 366	86.62 406	97.08 188	92.23 431	87.94 251	97.90 374	78.89 428	96.69 240	98.49 246

RPMNet		92.81 347	91.34 358	97.24 212	97.00 322	93.43 292	94.96 421	98.80 107	82.27 425	96.93 196	92.12 432	86.98 271	99.82 90	76.32 433	96.65 242	98.46 248

UWE-MVS-28		92.79 348	92.51 343	93.62 384	96.46 356	86.28 416	97.93 299	92.71 437	94.17 228	94.78 264	97.16 311	81.05 355	96.43 416	81.45 420	96.86 233	98.14 263

myMVS_eth3d		92.73 349	92.01 351	94.89 352	97.39 299	90.94 345	97.91 302	97.46 335	93.16 289	93.42 326	95.37 402	68.09 423	96.12 419	88.34 381	96.99 229	97.60 279

TransMVSNet (Re)		92.67 350	91.51 357	96.15 299	96.58 349	94.65 241	98.90 111	96.73 390	90.86 365	89.46 395	97.86 249	85.62 295	98.09 360	86.45 394	81.12 420	95.71 392

ttmdpeth		92.61 351	91.96 354	94.55 367	94.10 415	90.60 358	98.52 217	97.29 351	92.67 308	90.18 386	97.92 243	79.75 368	97.79 381	91.09 336	86.15 401	95.26 398

Syy-MVS		92.55 352	92.61 340	92.38 398	97.39 299	83.41 424	97.91 302	97.46 335	93.16 289	93.42 326	95.37 402	84.75 313	96.12 419	77.00 432	96.99 229	97.60 279

K. test v3		92.55 352	91.91 355	94.48 371	95.64 388	89.24 385	99.07 67	94.88 420	94.04 233	86.78 412	97.59 278	77.64 389	97.64 388	92.08 312	89.43 364	96.57 349

DSMNet-mixed		92.52 354	92.58 342	92.33 399	94.15 414	82.65 427	98.30 248	94.26 427	89.08 395	92.65 351	95.73 393	85.01 307	95.76 423	86.24 395	97.76 209	98.59 239

TinyColmap		92.31 355	91.53 356	94.65 364	96.92 328	89.75 372	96.92 382	96.68 393	90.45 372	89.62 392	97.85 251	76.06 403	98.81 285	86.74 392	92.51 321	95.41 396

gg-mvs-nofinetune		92.21 356	90.58 364	97.13 221	96.75 341	95.09 218	95.85 412	89.40 445	85.43 416	94.50 270	81.98 440	80.80 360	98.40 334	92.16 310	98.33 189	97.88 268

FMVSNet5		91.81 357	90.92 360	94.49 370	97.21 309	92.09 324	98.00 291	97.55 326	89.31 393	90.86 380	95.61 399	74.48 410	95.32 427	85.57 400	89.70 356	96.07 385

pmmvs6		91.77 358	90.63 363	95.17 341	94.69 411	91.24 341	98.67 191	97.92 297	86.14 410	89.62 392	97.56 283	75.79 404	98.34 337	90.75 345	84.56 406	95.94 388

Anonymous20231206		91.66 359	91.10 359	93.33 389	94.02 419	87.35 412	98.58 206	97.26 355	90.48 370	90.16 387	96.31 370	83.83 336	96.53 414	79.36 426	89.90 354	96.12 383

Patchmatch-RL test		91.49 360	90.85 361	93.41 387	91.37 430	84.40 419	92.81 435	95.93 410	91.87 336	87.25 408	94.87 408	88.99 221	96.53 414	92.54 304	82.00 415	99.30 141

test_0402		91.32 361	90.27 367	94.48 371	96.60 348	91.12 342	98.50 223	97.22 357	86.10 411	88.30 404	96.98 336	77.65 388	97.99 368	78.13 430	92.94 315	94.34 413

test_vis1_rt		91.29 362	90.65 362	93.19 393	97.45 293	86.25 417	98.57 213	90.90 443	93.30 283	86.94 411	93.59 421	62.07 435	99.11 237	97.48 126	95.58 276	94.22 416

PVSNet_0	88.72 19	91.28 363	90.03 370	95.00 347	97.99 244	87.29 413	94.84 424	98.50 192	92.06 331	89.86 389	95.19 404	79.81 367	99.39 202	92.27 309	69.79 440	98.33 255

mvs5depth		91.23 364	90.17 368	94.41 375	92.09 427	89.79 371	95.26 419	96.50 398	90.73 366	91.69 372	97.06 325	76.12 402	98.62 300	88.02 385	84.11 409	94.82 409

Anonymous20240521		91.18 365	90.44 365	93.42 386	93.70 420	88.47 401	98.94 100	97.56 321	88.46 399	89.56 394	95.08 407	77.15 394	96.97 403	83.92 412	89.55 360	94.82 409

EG-PatchMatch MVS		91.13 366	90.12 369	94.17 379	94.73 410	89.00 390	98.13 274	97.81 302	89.22 394	85.32 422	96.46 367	67.71 425	98.42 321	87.89 388	93.82 298	95.08 404

TDRefinement		91.06 367	89.68 372	95.21 339	85.35 445	91.49 337	98.51 222	97.07 368	91.47 345	88.83 401	97.84 252	77.31 390	99.09 242	92.79 295	77.98 432	95.04 406

sc_t1		91.01 368	89.39 374	95.85 315	95.99 377	90.39 363	98.43 233	97.64 313	78.79 429	92.20 364	97.94 241	66.00 429	98.60 304	91.59 328	85.94 403	98.57 242

UnsupCasMVSNet_eth		90.99 369	89.92 371	94.19 378	94.08 416	89.83 370	97.13 373	98.67 144	93.69 262	85.83 418	96.19 377	75.15 406	96.74 408	89.14 372	79.41 427	96.00 386

test20.03		90.89 370	90.38 366	92.43 397	93.48 421	88.14 407	98.33 241	97.56 321	93.40 278	87.96 405	96.71 357	80.69 361	94.13 432	79.15 427	86.17 399	95.01 408

MDA-MVSNet_test_wron		90.71 371	89.38 376	94.68 362	94.83 407	90.78 351	97.19 366	97.46 335	87.60 402	72.41 440	95.72 395	86.51 277	96.71 411	85.92 398	86.80 396	96.56 351

YYNet1		90.70 372	89.39 374	94.62 366	94.79 409	90.65 354	97.20 364	97.46 335	87.54 403	72.54 439	95.74 391	86.51 277	96.66 412	86.00 397	86.76 397	96.54 354

KD-MVS_self_test		90.38 373	89.38 376	93.40 388	92.85 424	88.94 393	97.95 295	97.94 295	90.35 375	90.25 385	93.96 418	79.82 366	95.94 422	84.62 411	76.69 435	95.33 397

pmmvs-eth3d		90.36 374	89.05 379	94.32 376	91.10 432	92.12 323	97.63 335	96.95 379	88.86 397	84.91 423	93.13 426	78.32 377	96.74 408	88.70 377	81.81 417	94.09 419

tt0320		90.26 375	88.73 382	94.86 354	96.12 371	90.62 356	98.17 269	97.63 314	77.46 432	89.68 391	96.04 383	69.19 421	97.79 381	88.98 374	85.29 405	96.16 382

CL-MVSNet_self_test		90.11 376	89.14 378	93.02 394	91.86 429	88.23 406	96.51 404	98.07 282	90.49 369	90.49 384	94.41 413	84.75 313	95.34 426	80.79 422	74.95 437	95.50 395

new_pmnet		90.06 377	89.00 380	93.22 392	94.18 413	88.32 404	96.42 406	96.89 384	86.19 409	85.67 419	93.62 420	77.18 393	97.10 401	81.61 419	89.29 366	94.23 415

MDA-MVSNet-bldmvs		89.97 378	88.35 384	94.83 358	95.21 401	91.34 338	97.64 332	97.51 330	88.36 400	71.17 441	96.13 379	79.22 371	96.63 413	83.65 413	86.27 398	96.52 359

tt0320-xc		89.79 379	88.11 386	94.84 357	96.19 366	90.61 357	98.16 270	97.22 357	77.35 433	88.75 402	96.70 358	65.94 430	97.63 389	89.31 370	83.39 411	96.28 377

CMPMVS	66.06 21	89.70 380	89.67 373	89.78 406	93.19 422	76.56 432	97.00 378	98.35 224	80.97 427	81.57 428	97.75 260	74.75 408	98.61 301	89.85 358	93.63 302	94.17 417
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 381	88.28 385	93.82 382	92.81 425	91.08 343	98.01 289	97.45 339	87.95 401	87.90 406	95.87 389	67.63 426	94.56 431	78.73 429	88.18 379	95.83 390

KD-MVS_2432*1600		89.61 382	87.96 390	94.54 368	94.06 417	91.59 335	95.59 416	97.63 314	89.87 382	88.95 398	94.38 415	78.28 378	96.82 406	84.83 407	68.05 441	95.21 400

miper_refine_blended		89.61 382	87.96 390	94.54 368	94.06 417	91.59 335	95.59 416	97.63 314	89.87 382	88.95 398	94.38 415	78.28 378	96.82 406	84.83 407	68.05 441	95.21 400

MVStest1		89.53 384	87.99 389	94.14 381	94.39 412	90.42 361	98.25 255	96.84 389	82.81 422	81.18 430	97.33 299	77.09 395	96.94 404	85.27 404	78.79 428	95.06 405

MVS-HIRNet		89.46 385	88.40 383	92.64 396	97.58 278	82.15 428	94.16 434	93.05 436	75.73 436	90.90 379	82.52 439	79.42 370	98.33 339	83.53 414	98.68 165	97.43 282

OpenMVS_ROB	86.42 20	89.00 386	87.43 394	93.69 383	93.08 423	89.42 383	97.91 302	96.89 384	78.58 430	85.86 417	94.69 409	69.48 420	98.29 347	77.13 431	93.29 312	93.36 426

mvsany_test3		88.80 387	88.04 387	91.09 405	89.78 435	81.57 430	97.83 317	95.49 414	93.81 251	87.53 407	93.95 419	56.14 438	97.43 396	94.68 230	83.13 412	94.26 414

new-patchmatchnet		88.50 388	87.45 393	91.67 403	90.31 434	85.89 418	97.16 371	97.33 347	89.47 389	83.63 425	92.77 428	76.38 399	95.06 429	82.70 416	77.29 433	94.06 421

APD_test1		88.22 389	88.01 388	88.86 408	95.98 378	74.66 440	97.21 363	96.44 400	83.96 421	86.66 414	97.90 245	60.95 436	97.84 380	82.73 415	90.23 350	94.09 419

PM-MVS		87.77 390	86.55 396	91.40 404	91.03 433	83.36 426	96.92 382	95.18 418	91.28 356	86.48 416	93.42 422	53.27 439	96.74 408	89.43 368	81.97 416	94.11 418

dmvs_testset		87.64 391	88.93 381	83.79 417	95.25 400	63.36 449	97.20 364	91.17 441	93.07 293	85.64 420	95.98 388	85.30 304	91.52 439	69.42 438	87.33 388	96.49 365

test_fmvs3		87.17 392	87.06 395	87.50 410	91.21 431	75.66 435	99.05 70	96.61 397	92.79 305	88.85 400	92.78 427	43.72 442	93.49 433	93.95 260	84.56 406	93.34 427

UnsupCasMVSNet_bld		87.17 392	85.12 399	93.31 390	91.94 428	88.77 394	94.92 423	98.30 238	84.30 420	82.30 426	90.04 434	63.96 433	97.25 399	85.85 399	74.47 439	93.93 423

N_pmnet		87.12 394	87.77 392	85.17 414	95.46 396	61.92 450	97.37 350	70.66 455	85.83 413	88.73 403	96.04 383	85.33 302	97.76 384	80.02 423	90.48 345	95.84 389

pmmvs3		86.67 395	84.86 400	92.11 402	88.16 439	87.19 414	96.63 400	94.75 422	79.88 428	87.22 409	92.75 429	66.56 428	95.20 428	81.24 421	76.56 436	93.96 422

test_f		86.07 396	85.39 397	88.10 409	89.28 437	75.57 436	97.73 325	96.33 402	89.41 392	85.35 421	91.56 433	43.31 444	95.53 424	91.32 332	84.23 408	93.21 428

WB-MVS		84.86 397	85.33 398	83.46 418	89.48 436	69.56 444	98.19 263	96.42 401	89.55 388	81.79 427	94.67 410	84.80 311	90.12 440	52.44 444	80.64 424	90.69 431

SSC-MVS		84.27 398	84.71 401	82.96 422	89.19 438	68.83 445	98.08 281	96.30 403	89.04 396	81.37 429	94.47 411	84.60 318	89.89 441	49.80 446	79.52 426	90.15 432

dongtai		82.47 399	81.88 402	84.22 416	95.19 402	76.03 433	94.59 430	74.14 454	82.63 423	87.19 410	96.09 380	64.10 432	87.85 444	58.91 442	84.11 409	88.78 436

test_vis3_rt		79.22 400	77.40 407	84.67 415	86.44 443	74.85 439	97.66 330	81.43 450	84.98 417	67.12 443	81.91 441	28.09 452	97.60 390	88.96 375	80.04 425	81.55 441

test_method		79.03 401	78.17 403	81.63 423	86.06 444	54.40 455	82.75 443	96.89 384	39.54 447	80.98 431	95.57 400	58.37 437	94.73 430	84.74 410	78.61 429	95.75 391

testf1		79.02 402	77.70 404	82.99 420	88.10 440	66.90 446	94.67 426	93.11 433	71.08 438	74.02 436	93.41 423	34.15 448	93.25 434	72.25 436	78.50 430	88.82 434

APD_test2		79.02 402	77.70 404	82.99 420	88.10 440	66.90 446	94.67 426	93.11 433	71.08 438	74.02 436	93.41 423	34.15 448	93.25 434	72.25 436	78.50 430	88.82 434

LCM-MVSNet		78.70 404	76.24 410	86.08 412	77.26 451	71.99 442	94.34 432	96.72 391	61.62 442	76.53 434	89.33 435	33.91 450	92.78 437	81.85 418	74.60 438	93.46 425

kuosan		78.45 405	77.69 406	80.72 424	92.73 426	75.32 437	94.63 429	74.51 453	75.96 434	80.87 432	93.19 425	63.23 434	79.99 448	42.56 448	81.56 419	86.85 440

Gipuma		78.40 406	76.75 409	83.38 419	95.54 391	80.43 431	79.42 444	97.40 343	64.67 441	73.46 438	80.82 442	45.65 441	93.14 436	66.32 440	87.43 386	76.56 444
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 407	75.44 411	85.46 413	82.54 446	74.95 438	94.23 433	93.08 435	72.80 437	74.68 435	87.38 436	36.36 447	91.56 438	73.95 434	63.94 443	89.87 433

FPMVS		77.62 408	77.14 408	79.05 426	79.25 449	60.97 451	95.79 413	95.94 409	65.96 440	67.93 442	94.40 414	37.73 446	88.88 443	68.83 439	88.46 376	87.29 437

EGC-MVSNET		75.22 409	69.54 412	92.28 400	94.81 408	89.58 379	97.64 332	96.50 398	1.82 452	5.57 453	95.74 391	68.21 422	96.26 418	73.80 435	91.71 330	90.99 430

ANet_high		69.08 410	65.37 414	80.22 425	65.99 453	71.96 443	90.91 439	90.09 444	82.62 424	49.93 448	78.39 443	29.36 451	81.75 445	62.49 441	38.52 447	86.95 439

tmp_tt		68.90 411	66.97 413	74.68 428	50.78 455	59.95 452	87.13 440	83.47 449	38.80 448	62.21 444	96.23 374	64.70 431	76.91 450	88.91 376	30.49 448	87.19 438

PMVS	61.03 23	65.95 412	63.57 416	73.09 429	57.90 454	51.22 456	85.05 442	93.93 431	54.45 443	44.32 449	83.57 438	13.22 453	89.15 442	58.68 443	81.00 421	78.91 443
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 413	64.25 415	67.02 430	82.28 447	59.36 453	91.83 438	85.63 447	52.69 444	60.22 445	77.28 444	41.06 445	80.12 447	46.15 447	41.14 445	61.57 446

EMVS		64.07 414	63.26 417	66.53 431	81.73 448	58.81 454	91.85 437	84.75 448	51.93 446	59.09 446	75.13 445	43.32 443	79.09 449	42.03 449	39.47 446	61.69 445

MVE	62.14 22	63.28 415	59.38 418	74.99 427	74.33 452	65.47 448	85.55 441	80.50 451	52.02 445	51.10 447	75.00 446	10.91 456	80.50 446	51.60 445	53.40 444	78.99 442
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 416	30.18 420	30.16 432	78.61 450	43.29 457	66.79 445	14.21 456	17.31 449	14.82 452	11.93 452	11.55 455	41.43 451	37.08 450	19.30 449	5.76 449

cdsmvs_eth3d_5k		23.98 417	31.98 419	0.00 435	0.00 458	0.00 460	0.00 446	98.59 165	0.00 453	0.00 454	98.61 174	90.60 180	0.00 454	0.00 453	0.00 452	0.00 450

testmvs		21.48 418	24.95 421	11.09 434	14.89 456	6.47 459	96.56 402	9.87 457	7.55 450	17.93 450	39.02 448	9.43 457	5.90 453	16.56 452	12.72 450	20.91 448

test123		20.95 419	23.72 422	12.64 433	13.54 457	8.19 458	96.55 403	6.13 458	7.48 451	16.74 451	37.98 449	12.97 454	6.05 452	16.69 451	5.43 451	23.68 447

ab-mvs-re		8.20 420	10.94 423	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	98.43 192	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

pcd_1.5k_mvsjas		7.88 421	10.50 424	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	94.51 88	0.00 454	0.00 453	0.00 452	0.00 450

mmdepth		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

monomultidepth		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

test_blank		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

uanet_test		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

DCPMVS		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

sosnet-low-res		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

sosnet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

uncertanet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

Regformer		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

uanet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

WAC-MVS						90.94 345								88.66 378

FOURS1					99.82 1	98.66 24	99.69 1	98.95 56	97.46 52	99.39 41

MSC_two_6792asdad				99.62 6	99.17 104	99.08 11		98.63 155					99.94 12	98.53 52	99.80 24	99.86 9

PC_three_1452									95.08 184	99.60 29	99.16 92	97.86 2	98.47 315	97.52 123	99.72 61	99.74 44

No_MVS				99.62 6	99.17 104	99.08 11		98.63 155					99.94 12	98.53 52	99.80 24	99.86 9

test_one_0601					99.66 28	99.25 2		98.86 85	97.55 44	99.20 53	99.47 32	97.57 6

eth-test2					0.00 458

eth-test					0.00 458

ZD-MVS					99.46 54	98.70 23		98.79 112	93.21 286	98.67 96	98.97 125	95.70 49	99.83 83	96.07 180	99.58 92

RE-MVS-def			98.34 48		99.49 48	97.86 70	99.11 61	98.80 107	96.49 111	99.17 56	99.35 57	95.29 66		97.72 102	99.65 75	99.71 57

IU-MVS					99.71 21	99.23 7		98.64 152	95.28 171	99.63 28				98.35 69	99.81 15	99.83 15

OPU-MVS				99.37 23	99.24 96	99.05 14	99.02 80				99.16 92	97.81 3	99.37 203	97.24 135	99.73 56	99.70 61

test_241102_TWO								98.87 79	97.65 36	99.53 34	99.48 30	97.34 11	99.94 12	98.43 64	99.80 24	99.83 15

test_241102_ONE					99.71 21	99.24 5		98.87 79	97.62 38	99.73 19	99.39 45	97.53 7	99.74 127

9.14			98.06 73		99.47 52		98.71 178	98.82 94	94.36 224	99.16 59	99.29 66	96.05 37	99.81 95	97.00 141	99.71 63

save fliter					99.46 54	98.38 36	98.21 258	98.71 130	97.95 25

test_0728_THIRD									97.32 60	99.45 36	99.46 37	97.88 1	99.94 12	98.47 60	99.86 2	99.85 12

test_0728_SECOND				99.71 1	99.72 14	99.35 1	98.97 91	98.88 72					99.94 12	98.47 60	99.81 15	99.84 14

test0726					99.72 14	99.25 2	99.06 68	98.88 72	97.62 38	99.56 31	99.50 26	97.42 9

GSMVS																99.20 158

test_part2					99.63 31	99.18 10				99.27 50

sam_mvs1												89.45 206				99.20 158

sam_mvs												88.99 221

ambc				89.49 407	86.66 442	75.78 434	92.66 436	96.72 391		86.55 415	92.50 430	46.01 440	97.90 374	90.32 349	82.09 414	94.80 411

MTGPA								98.74 122

test_post1							96.68 399				30.43 451	87.85 255	98.69 293	92.59 300

test_post											31.83 450	88.83 228	98.91 269

patchmatchnet-post											95.10 406	89.42 207	98.89 273

GG-mvs-BLEND				96.59 265	96.34 361	94.98 226	96.51 404	88.58 446		93.10 340	94.34 417	80.34 365	98.05 363	89.53 365	96.99 229	96.74 327

MTMP							98.89 115	94.14 429

gm-plane-assit					95.88 382	87.47 411			89.74 385		96.94 342		99.19 224	93.32 279

test9_res														96.39 174	99.57 93	99.69 64

TEST9					99.31 72	98.50 30	97.92 300	98.73 125	92.63 309	97.74 159	98.68 169	96.20 32	99.80 102

test_8					99.29 81	98.44 32	97.89 308	98.72 127	92.98 297	97.70 164	98.66 172	96.20 32	99.80 102

agg_prior2														95.87 190	99.57 93	99.68 69

agg_prior					99.30 76	98.38 36		98.72 127		97.57 176			99.81 95

TestCases				96.99 230	99.25 89	93.21 306		98.18 256	91.36 349	93.52 319	98.77 158	84.67 316	99.72 129	89.70 362	97.87 204	98.02 266

test_prior4						98.01 66	97.86 312

test_prior2							97.80 319		96.12 129	97.89 152	98.69 168	95.96 41		96.89 150	99.60 87

test_prior				99.19 45	99.31 72	98.22 53		98.84 89					99.70 135			99.65 77

旧先验2							97.57 338		91.30 354	98.67 96			99.80 102	95.70 199

新几何2							97.64 332

新几何1				99.16 50	99.34 65	98.01 66		98.69 136	90.06 379	98.13 126	98.95 132	94.60 86	99.89 61	91.97 319	99.47 115	99.59 88

旧先验1					99.29 81	97.48 84		98.70 134			99.09 108	95.56 52			99.47 115	99.61 84

无先验							97.58 337	98.72 127	91.38 348				99.87 72	93.36 278		99.60 86

原ACMM2							97.67 329

原ACMM1				98.65 91	99.32 70	96.62 133		98.67 144	93.27 285	97.81 154	98.97 125	95.18 73	99.83 83	93.84 264	99.46 118	99.50 100

test222					99.23 97	97.17 110	97.40 346	98.66 147	88.68 398	98.05 132	98.96 130	94.14 99			99.53 106	99.61 84

testdata2													99.89 61	91.65 327

segment_acmp												96.85 14

testdata				98.26 134	99.20 102	95.36 203		98.68 139	91.89 335	98.60 104	99.10 101	94.44 93	99.82 90	94.27 248	99.44 119	99.58 92

testdata1							97.32 356		96.34 119

test12				99.18 47	99.16 108	98.19 55		98.53 181		98.07 130		95.13 76	99.72 129		99.56 101	99.63 82

plane_prior7					97.42 295	94.63 243

plane_prior6					97.35 302	94.61 246						87.09 268

plane_prior5								98.56 175					99.03 249	96.07 180	94.27 282	96.92 303

plane_prior4											98.28 211

plane_prior3						94.61 246			97.02 84	95.34 248

plane_prior2							98.80 150		97.28 64

plane_prior1					97.37 301

plane_prior						94.60 248	98.44 231		96.74 98						94.22 284

n2								0.00 459

nn								0.00 459

door-mid								94.37 425

lessismore_v0				94.45 374	94.93 406	88.44 402		91.03 442		86.77 413	97.64 274	76.23 401	98.42 321	90.31 350	85.64 404	96.51 362

LGP-MVS_train				96.47 280	97.46 290	93.54 287		98.54 179	94.67 208	94.36 280	98.77 158	85.39 298	99.11 237	95.71 197	94.15 288	96.76 325

test11								98.66 147

door								94.64 423

HQP5-MVS						94.25 264

HQP-NCC					97.20 310		98.05 284		96.43 113	94.45 272

ACMP_Plane					97.20 310		98.05 284		96.43 113	94.45 272

BP-MVS														95.30 211

HQP4-MVS										94.45 272			98.96 260			96.87 315

HQP3-MVS								98.46 200							94.18 286

HQP2-MVS												86.75 274

NP-MVS					97.28 304	94.51 251					97.73 261

MDTV_nov1_ep13_2view						84.26 420	96.89 389		90.97 363	97.90 151		89.89 192		93.91 262		99.18 167

MDTV_nov1_ep13			95.40 200		97.48 288	88.34 403	96.85 392	97.29 351	93.74 255	97.48 178	97.26 303	89.18 215	99.05 245	91.92 320	97.43 220

ACMMP++_ref															92.97 314

ACMMP++															93.61 303

Test By Simon												94.64 85

ITE_SJBPF				95.44 333	97.42 295	91.32 339		97.50 331	95.09 183	93.59 315	98.35 202	81.70 347	98.88 275	89.71 361	93.39 309	96.12 383

DeepMVS_CX				86.78 411	97.09 320	72.30 441		95.17 419	75.92 435	84.34 424	95.19 404	70.58 418	95.35 425	79.98 425	89.04 370	92.68 429

High-resolution multi-view benchmark