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		99.71 1	99.67 1	99.85 31	99.86 20	99.61 70	99.56 128	99.63 39	99.48 3	99.98 6	99.83 72	98.75 58	99.99 4	99.97 1	99.96 12	99.94 11

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 31	99.84 32	99.63 67	99.56 128	99.63 39	99.47 4	99.98 6	99.82 81	98.75 58	99.99 4	99.97 1	99.97 7	99.94 11

test_fmvsmconf_n		99.70 3	99.64 4	99.87 14	99.80 52	99.66 56	99.48 186	99.64 36	99.45 5	99.92 16	99.92 14	98.62 73	99.99 4	99.96 6	99.99 1	99.96 7

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 55	99.84 32	99.44 99	99.58 115	99.69 18	99.43 7	99.98 6	99.91 20	98.62 73	100.00 1	99.97 1	99.95 17	99.90 16

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 63	99.89 4	99.75 42	99.56 70	99.02 42	99.88 24	99.85 57	99.18 10	99.96 32	99.22 72	99.92 27	99.90 16
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 58	99.38 222	99.37 105	99.58 115	99.62 41	99.41 9	99.87 29	99.92 14	98.81 47	100.00 1	99.97 1	99.93 25	99.94 11

reproduce_model		99.63 7	99.54 11	99.90 4	99.78 56	99.88 8	99.56 128	99.55 78	99.15 21	99.90 19	99.90 27	99.00 22	99.97 21	99.11 82	99.91 34	99.86 32

reproduce-ours		99.61 8	99.52 12	99.90 4	99.76 66	99.88 8	99.52 155	99.54 87	99.13 24	99.89 21	99.89 32	98.96 25	99.96 32	99.04 90	99.90 43	99.85 36

our_new_method		99.61 8	99.52 12	99.90 4	99.76 66	99.88 8	99.52 155	99.54 87	99.13 24	99.89 21	99.89 32	98.96 25	99.96 32	99.04 90	99.90 43	99.85 36

SED-MVS		99.61 8	99.52 12	99.88 8	99.84 32	99.90 2	99.60 100	99.48 161	99.08 37	99.91 17	99.81 95	99.20 7	99.96 32	98.91 107	99.85 75	99.79 77

DVP-MVS++		99.59 11	99.50 16	99.88 8	99.51 175	99.88 8	99.87 8	99.51 119	98.99 49	99.88 24	99.81 95	99.27 5	99.96 32	98.85 120	99.80 103	99.81 64

TSAR-MVS + MP.		99.58 12	99.50 16	99.81 47	99.91 1	99.66 56	99.63 88	99.39 229	98.91 62	99.78 53	99.85 57	99.36 2	99.94 72	98.84 123	99.88 57	99.82 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EI-MVSNet-UG-set		99.58 12	99.57 8	99.64 82	99.78 56	99.14 137	99.60 100	99.45 201	99.01 44	99.90 19	99.83 72	98.98 24	99.93 90	99.59 28	99.95 17	99.86 32

EI-MVSNet-Vis-set		99.58 12	99.56 10	99.64 82	99.78 56	99.15 136	99.61 99	99.45 201	99.01 44	99.89 21	99.82 81	99.01 18	99.92 101	99.56 32	99.95 17	99.85 36

DVP-MVS		99.57 15	99.47 20	99.88 8	99.85 26	99.89 4	99.57 122	99.37 245	99.10 31	99.81 42	99.80 108	98.94 32	99.96 32	98.93 104	99.86 68	99.81 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
fmvsm_s_conf0.5_n_a		99.56 16	99.47 20	99.85 31	99.83 39	99.64 66	99.52 155	99.65 33	99.10 31	99.98 6	99.92 14	97.35 125	99.96 32	99.94 9	99.92 27	99.95 9

test_fmvsmconf0.1_n		99.55 17	99.45 24	99.86 24	99.44 204	99.65 60	99.50 171	99.61 48	99.45 5	99.87 29	99.92 14	97.31 126	99.97 21	99.95 7	99.99 1	99.97 4

SteuartSystems-ACMMP		99.54 18	99.42 25	99.87 14	99.82 42	99.81 28	99.59 107	99.51 119	98.62 89	99.79 48	99.83 72	99.28 4	99.97 21	98.48 174	99.90 43	99.84 42
Skip Steuart: Steuart Systems R&D Blog.
XVS		99.53 19	99.42 25	99.87 14	99.85 26	99.83 19	99.69 60	99.68 20	98.98 52	99.37 168	99.74 147	98.81 47	99.94 72	98.79 131	99.86 68	99.84 42

MTAPA		99.52 20	99.39 32	99.89 7	99.90 4	99.86 16	99.66 74	99.47 181	98.79 74	99.68 81	99.81 95	98.43 86	99.97 21	98.88 110	99.90 43	99.83 52

fmvsm_s_conf0.5_n		99.51 21	99.40 30	99.85 31	99.84 32	99.65 60	99.51 164	99.67 23	99.13 24	99.98 6	99.92 14	96.60 152	99.96 32	99.95 7	99.96 12	99.95 9

HPM-MVS_fast		99.51 21	99.40 30	99.85 31	99.91 1	99.79 33	99.76 37	99.56 70	97.72 197	99.76 62	99.75 142	99.13 12	99.92 101	99.07 88	99.92 27	99.85 36

mvsany_test1		99.50 23	99.46 23	99.62 88	99.61 145	99.09 142	98.94 350	99.48 161	99.10 31	99.96 14	99.91 20	98.85 42	99.96 32	99.72 19	99.58 144	99.82 57

CS-MVS		99.50 23	99.48 18	99.54 102	99.76 66	99.42 101	99.90 1	99.55 78	98.56 94	99.78 53	99.70 162	98.65 71	99.79 197	99.65 25	99.78 110	99.41 207

CS-MVS-test		99.49 25	99.48 18	99.54 102	99.78 56	99.30 116	99.89 2	99.58 62	98.56 94	99.73 68	99.69 172	98.55 78	99.82 182	99.69 21	99.85 75	99.48 186

HFP-MVS		99.49 25	99.37 36	99.86 24	99.87 15	99.80 30	99.66 74	99.67 23	98.15 140	99.68 81	99.69 172	99.06 16	99.96 32	98.69 143	99.87 60	99.84 42

ACMMPR		99.49 25	99.36 38	99.86 24	99.87 15	99.79 33	99.66 74	99.67 23	98.15 140	99.67 85	99.69 172	98.95 30	99.96 32	98.69 143	99.87 60	99.84 42

DeepC-MVS_fast	98.69 1	99.49 25	99.39 32	99.77 58	99.63 135	99.59 73	99.36 240	99.46 190	99.07 39	99.79 48	99.82 81	98.85 42	99.92 101	98.68 145	99.87 60	99.82 57
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
region2R		99.48 29	99.35 40	99.87 14	99.88 11	99.80 30	99.65 80	99.66 28	98.13 145	99.66 90	99.68 178	98.96 25	99.96 32	98.62 152	99.87 60	99.84 42

APD-MVS_3200maxsize		99.48 29	99.35 40	99.85 31	99.76 66	99.83 19	99.63 88	99.54 87	98.36 114	99.79 48	99.82 81	98.86 41	99.95 62	98.62 152	99.81 99	99.78 83

DELS-MVS		99.48 29	99.42 25	99.65 77	99.72 94	99.40 104	99.05 322	99.66 28	99.14 23	99.57 122	99.80 108	98.46 84	99.94 72	99.57 31	99.84 83	99.60 150
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
ZNCC-MVS		99.47 32	99.33 44	99.87 14	99.87 15	99.81 28	99.64 83	99.67 23	98.08 155	99.55 127	99.64 196	98.91 37	99.96 32	98.72 138	99.90 43	99.82 57

ACMMP_NAP		99.47 32	99.34 42	99.88 8	99.87 15	99.86 16	99.47 192	99.48 161	98.05 162	99.76 62	99.86 52	98.82 46	99.93 90	98.82 130	99.91 34	99.84 42

MVSMamba_PlusPlus		99.46 34	99.41 29	99.64 82	99.68 112	99.50 91	99.75 42	99.50 139	98.27 123	99.87 29	99.92 14	98.09 104	99.94 72	99.65 25	99.95 17	99.47 192

balanced_conf03		99.46 34	99.39 32	99.67 72	99.55 164	99.58 78	99.74 46	99.51 119	98.42 107	99.87 29	99.84 67	98.05 107	99.91 112	99.58 30	99.94 23	99.52 173

DPE-MVS		99.46 34	99.32 46	99.91 2	99.78 56	99.88 8	99.36 240	99.51 119	98.73 81	99.88 24	99.84 67	98.72 64	99.96 32	98.16 204	99.87 60	99.88 25
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSLP-MVS++		99.46 34	99.47 20	99.44 134	99.60 150	99.16 132	99.41 216	99.71 13	98.98 52	99.45 143	99.78 127	99.19 9	99.54 269	99.28 66	99.84 83	99.63 143

SR-MVS-dyc-post		99.45 38	99.31 52	99.85 31	99.76 66	99.82 25	99.63 88	99.52 105	98.38 110	99.76 62	99.82 81	98.53 79	99.95 62	98.61 155	99.81 99	99.77 85

PGM-MVS		99.45 38	99.31 52	99.86 24	99.87 15	99.78 39	99.58 115	99.65 33	97.84 183	99.71 75	99.80 108	99.12 13	99.97 21	98.33 190	99.87 60	99.83 52

CP-MVS		99.45 38	99.32 46	99.85 31	99.83 39	99.75 42	99.69 60	99.52 105	98.07 156	99.53 130	99.63 202	98.93 36	99.97 21	98.74 135	99.91 34	99.83 52

ACMMP		99.45 38	99.32 46	99.82 44	99.89 8	99.67 54	99.62 93	99.69 18	98.12 146	99.63 105	99.84 67	98.73 63	99.96 32	98.55 170	99.83 92	99.81 64
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
SMA-MVS		99.44 42	99.30 54	99.85 31	99.73 90	99.83 19	99.56 128	99.47 181	97.45 230	99.78 53	99.82 81	99.18 10	99.91 112	98.79 131	99.89 54	99.81 64
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
mPP-MVS		99.44 42	99.30 54	99.86 24	99.88 11	99.79 33	99.69 60	99.48 161	98.12 146	99.50 135	99.75 142	98.78 51	99.97 21	98.57 164	99.89 54	99.83 52

EC-MVSNet		99.44 42	99.39 32	99.58 95	99.56 160	99.49 92	99.88 4	99.58 62	98.38 110	99.73 68	99.69 172	98.20 99	99.70 235	99.64 27	99.82 96	99.54 166

SR-MVS		99.43 45	99.29 58	99.86 24	99.75 76	99.83 19	99.59 107	99.62 41	98.21 133	99.73 68	99.79 120	98.68 67	99.96 32	98.44 180	99.77 113	99.79 77

MCST-MVS		99.43 45	99.30 54	99.82 44	99.79 54	99.74 44	99.29 261	99.40 226	98.79 74	99.52 132	99.62 207	98.91 37	99.90 124	98.64 149	99.75 118	99.82 57

MSP-MVS		99.42 47	99.27 63	99.88 8	99.89 8	99.80 30	99.67 69	99.50 139	98.70 83	99.77 57	99.49 253	98.21 98	99.95 62	98.46 178	99.77 113	99.88 25
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
UA-Net		99.42 47	99.29 58	99.80 49	99.62 141	99.55 81	99.50 171	99.70 15	98.79 74	99.77 57	99.96 1	97.45 120	99.96 32	98.92 106	99.90 43	99.89 19

HPM-MVS		99.42 47	99.28 60	99.83 43	99.90 4	99.72 45	99.81 20	99.54 87	97.59 211	99.68 81	99.63 202	98.91 37	99.94 72	98.58 161	99.91 34	99.84 42
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CNVR-MVS		99.42 47	99.30 54	99.78 55	99.62 141	99.71 47	99.26 280	99.52 105	98.82 69	99.39 164	99.71 158	98.96 25	99.85 155	98.59 160	99.80 103	99.77 85

SD-MVS		99.41 51	99.52 12	99.05 189	99.74 83	99.68 51	99.46 195	99.52 105	99.11 30	99.88 24	99.91 20	99.43 1	97.70 398	98.72 138	99.93 25	99.77 85
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
MVS_111021_LR		99.41 51	99.33 44	99.65 77	99.77 63	99.51 90	98.94 350	99.85 6	98.82 69	99.65 97	99.74 147	98.51 81	99.80 194	98.83 126	99.89 54	99.64 139

MVS_111021_HR		99.41 51	99.32 46	99.66 73	99.72 94	99.47 96	98.95 348	99.85 6	98.82 69	99.54 128	99.73 153	98.51 81	99.74 213	98.91 107	99.88 57	99.77 85

MM		99.40 54	99.28 60	99.74 64	99.67 114	99.31 114	99.52 155	98.87 352	99.55 1	99.74 66	99.80 108	96.47 158	99.98 13	99.97 1	99.97 7	99.94 11

GST-MVS		99.40 54	99.24 68	99.85 31	99.86 20	99.79 33	99.60 100	99.67 23	97.97 168	99.63 105	99.68 178	98.52 80	99.95 62	98.38 183	99.86 68	99.81 64

HPM-MVS++		99.39 56	99.23 70	99.87 14	99.75 76	99.84 18	99.43 206	99.51 119	98.68 86	99.27 192	99.53 240	98.64 72	99.96 32	98.44 180	99.80 103	99.79 77

SF-MVS		99.38 57	99.24 68	99.79 52	99.79 54	99.68 51	99.57 122	99.54 87	97.82 188	99.71 75	99.80 108	98.95 30	99.93 90	98.19 200	99.84 83	99.74 95

MP-MVS-pluss		99.37 58	99.20 72	99.88 8	99.90 4	99.87 15	99.30 256	99.52 105	97.18 256	99.60 115	99.79 120	98.79 50	99.95 62	98.83 126	99.91 34	99.83 52
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + GP.		99.36 59	99.36 38	99.36 143	99.67 114	98.61 204	99.07 317	99.33 265	99.00 47	99.82 41	99.81 95	99.06 16	99.84 162	99.09 86	99.42 154	99.65 132

PVSNet_Blended_VisFu		99.36 59	99.28 60	99.61 89	99.86 20	99.07 147	99.47 192	99.93 2	97.66 206	99.71 75	99.86 52	97.73 115	99.96 32	99.47 47	99.82 96	99.79 77

NCCC		99.34 61	99.19 73	99.79 52	99.61 145	99.65 60	99.30 256	99.48 161	98.86 64	99.21 206	99.63 202	98.72 64	99.90 124	98.25 196	99.63 139	99.80 73

mamv4		99.33 62	99.42 25	99.07 185	99.67 114	97.73 260	99.42 213	99.60 54	98.15 140	99.94 15	99.91 20	98.42 88	99.94 72	99.72 19	99.96 12	99.54 166

MP-MVS		99.33 62	99.15 76	99.87 14	99.88 11	99.82 25	99.66 74	99.46 190	98.09 151	99.48 139	99.74 147	98.29 95	99.96 32	97.93 222	99.87 60	99.82 57
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PS-MVSNAJ		99.32 64	99.32 46	99.30 157	99.57 156	98.94 169	98.97 344	99.46 190	98.92 61	99.71 75	99.24 321	99.01 18	99.98 13	99.35 54	99.66 134	98.97 256

CSCG		99.32 64	99.32 46	99.32 151	99.85 26	98.29 229	99.71 55	99.66 28	98.11 148	99.41 157	99.80 108	98.37 92	99.96 32	98.99 96	99.96 12	99.72 106

PHI-MVS		99.30 66	99.17 75	99.70 70	99.56 160	99.52 89	99.58 115	99.80 8	97.12 262	99.62 109	99.73 153	98.58 75	99.90 124	98.61 155	99.91 34	99.68 122

DeepC-MVS	98.35 2	99.30 66	99.19 73	99.64 82	99.82 42	99.23 125	99.62 93	99.55 78	98.94 58	99.63 105	99.95 3	95.82 184	99.94 72	99.37 53	99.97 7	99.73 100
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.1_n		99.29 68	99.10 81	99.86 24	99.70 104	99.65 60	99.53 154	99.62 41	98.74 80	99.99 2	99.95 3	94.53 241	99.94 72	99.89 12	99.96 12	99.97 4

xiu_mvs_v1_base_debu		99.29 68	99.27 63	99.34 145	99.63 135	98.97 159	99.12 307	99.51 119	98.86 64	99.84 35	99.47 262	98.18 100	99.99 4	99.50 40	99.31 164	99.08 241

xiu_mvs_v1_base		99.29 68	99.27 63	99.34 145	99.63 135	98.97 159	99.12 307	99.51 119	98.86 64	99.84 35	99.47 262	98.18 100	99.99 4	99.50 40	99.31 164	99.08 241

xiu_mvs_v1_base_debi		99.29 68	99.27 63	99.34 145	99.63 135	98.97 159	99.12 307	99.51 119	98.86 64	99.84 35	99.47 262	98.18 100	99.99 4	99.50 40	99.31 164	99.08 241

APD-MVS		99.27 72	99.08 85	99.84 42	99.75 76	99.79 33	99.50 171	99.50 139	97.16 258	99.77 57	99.82 81	98.78 51	99.94 72	97.56 261	99.86 68	99.80 73
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
LS3D		99.27 72	99.12 79	99.74 64	99.18 275	99.75 42	99.56 128	99.57 65	98.45 103	99.49 138	99.85 57	97.77 114	99.94 72	98.33 190	99.84 83	99.52 173

fmvsm_s_conf0.1_n_a		99.26 74	99.06 87	99.85 31	99.52 172	99.62 68	99.54 146	99.62 41	98.69 84	99.99 2	99.96 1	94.47 243	99.94 72	99.88 13	99.92 27	99.98 2

patch_mono-2		99.26 74	99.62 5	98.16 304	99.81 46	94.59 372	99.52 155	99.64 36	99.33 13	99.73 68	99.90 27	99.00 22	99.99 4	99.69 21	99.98 4	99.89 19

ETV-MVS		99.26 74	99.21 71	99.40 137	99.46 197	99.30 116	99.56 128	99.52 105	98.52 98	99.44 148	99.27 317	98.41 90	99.86 149	99.10 85	99.59 143	99.04 248

xiu_mvs_v2_base		99.26 74	99.25 67	99.29 160	99.53 168	98.91 173	99.02 330	99.45 201	98.80 73	99.71 75	99.26 319	98.94 32	99.98 13	99.34 59	99.23 169	98.98 255

CANet		99.25 78	99.14 77	99.59 92	99.41 212	99.16 132	99.35 245	99.57 65	98.82 69	99.51 134	99.61 211	96.46 159	99.95 62	99.59 28	99.98 4	99.65 132

3Dnovator	97.25 9	99.24 79	99.05 88	99.81 47	99.12 291	99.66 56	99.84 12	99.74 10	99.09 36	98.92 259	99.90 27	95.94 178	99.98 13	98.95 100	99.92 27	99.79 77

dcpmvs_2		99.23 80	99.58 7	98.16 304	99.83 39	94.68 370	99.76 37	99.52 105	99.07 39	99.98 6	99.88 39	98.56 77	99.93 90	99.67 23	99.98 4	99.87 30

test_fmvsmconf0.01_n		99.22 81	99.03 92	99.79 52	98.42 377	99.48 94	99.55 142	99.51 119	99.39 10	99.78 53	99.93 9	94.80 219	99.95 62	99.93 10	99.95 17	99.94 11

CHOSEN 1792x2688		99.19 82	99.10 81	99.45 130	99.89 8	98.52 214	99.39 228	99.94 1	98.73 81	99.11 225	99.89 32	95.50 194	99.94 72	99.50 40	99.97 7	99.89 19

F-COLMAP		99.19 82	99.04 90	99.64 82	99.78 56	99.27 120	99.42 213	99.54 87	97.29 247	99.41 157	99.59 216	98.42 88	99.93 90	98.19 200	99.69 129	99.73 100

EIA-MVS		99.18 84	99.09 84	99.45 130	99.49 187	99.18 129	99.67 69	99.53 100	97.66 206	99.40 162	99.44 269	98.10 103	99.81 187	98.94 101	99.62 140	99.35 216

3Dnovator+	97.12 13	99.18 84	98.97 106	99.82 44	99.17 283	99.68 51	99.81 20	99.51 119	99.20 18	98.72 286	99.89 32	95.68 189	99.97 21	98.86 118	99.86 68	99.81 64

MVSFormer		99.17 86	99.12 79	99.29 160	99.51 175	98.94 169	99.88 4	99.46 190	97.55 217	99.80 46	99.65 190	97.39 121	99.28 309	99.03 92	99.85 75	99.65 132

sss		99.17 86	99.05 88	99.53 110	99.62 141	98.97 159	99.36 240	99.62 41	97.83 184	99.67 85	99.65 190	97.37 124	99.95 62	99.19 74	99.19 172	99.68 122

test_cas_vis1_n_1920		99.16 88	99.01 100	99.61 89	99.81 46	98.86 179	99.65 80	99.64 36	99.39 10	99.97 13	99.94 6	93.20 279	99.98 13	99.55 33	99.91 34	99.99 1

DP-MVS		99.16 88	98.95 112	99.78 55	99.77 63	99.53 86	99.41 216	99.50 139	97.03 274	99.04 241	99.88 39	97.39 121	99.92 101	98.66 147	99.90 43	99.87 30

MVS_0304		99.15 90	98.96 110	99.73 67	98.92 326	99.37 105	99.37 235	96.92 403	99.51 2	99.66 90	99.78 127	96.69 149	99.97 21	99.84 15	99.97 7	99.84 42

casdiffmvs_mvg		99.15 90	99.02 96	99.55 101	99.66 124	99.09 142	99.64 83	99.56 70	98.26 125	99.45 143	99.87 48	96.03 173	99.81 187	99.54 34	99.15 176	99.73 100
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.15 90	99.02 96	99.53 110	99.66 124	99.14 137	99.72 52	99.48 161	98.35 115	99.42 153	99.84 67	96.07 171	99.79 197	99.51 39	99.14 177	99.67 125

diffmvs		99.14 93	99.02 96	99.51 118	99.61 145	98.96 163	99.28 266	99.49 149	98.46 102	99.72 73	99.71 158	96.50 157	99.88 141	99.31 62	99.11 179	99.67 125
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CNLPA		99.14 93	98.99 102	99.59 92	99.58 154	99.41 103	99.16 298	99.44 209	98.45 103	99.19 212	99.49 253	98.08 105	99.89 136	97.73 244	99.75 118	99.48 186

CDPH-MVS		99.13 95	98.91 116	99.80 49	99.75 76	99.71 47	99.15 301	99.41 220	96.60 306	99.60 115	99.55 231	98.83 45	99.90 124	97.48 268	99.83 92	99.78 83

casdiffmvs		99.13 95	98.98 105	99.56 99	99.65 130	99.16 132	99.56 128	99.50 139	98.33 118	99.41 157	99.86 52	95.92 179	99.83 175	99.45 49	99.16 173	99.70 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jason		99.13 95	99.03 92	99.45 130	99.46 197	98.87 176	99.12 307	99.26 293	98.03 165	99.79 48	99.65 190	97.02 138	99.85 155	99.02 94	99.90 43	99.65 132
jason: jason.
lupinMVS		99.13 95	99.01 100	99.46 129	99.51 175	98.94 169	99.05 322	99.16 310	97.86 178	99.80 46	99.56 228	97.39 121	99.86 149	98.94 101	99.85 75	99.58 158

EPP-MVSNet		99.13 95	98.99 102	99.53 110	99.65 130	99.06 148	99.81 20	99.33 265	97.43 234	99.60 115	99.88 39	97.14 131	99.84 162	99.13 80	98.94 193	99.69 118

MG-MVS		99.13 95	99.02 96	99.45 130	99.57 156	98.63 201	99.07 317	99.34 258	98.99 49	99.61 112	99.82 81	97.98 109	99.87 146	97.00 298	99.80 103	99.85 36

CHOSEN 280x420		99.12 101	99.13 78	99.08 184	99.66 124	97.89 253	98.43 391	99.71 13	98.88 63	99.62 109	99.76 139	96.63 151	99.70 235	99.46 48	99.99 1	99.66 128

DP-MVS Recon		99.12 101	98.95 112	99.65 77	99.74 83	99.70 49	99.27 271	99.57 65	96.40 322	99.42 153	99.68 178	98.75 58	99.80 194	97.98 219	99.72 124	99.44 202

Vis-MVSNet		99.12 101	98.97 106	99.56 99	99.78 56	99.10 141	99.68 66	99.66 28	98.49 100	99.86 33	99.87 48	94.77 224	99.84 162	99.19 74	99.41 155	99.74 95
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 101	99.08 85	99.24 169	99.46 197	98.55 208	99.51 164	99.46 190	98.09 151	99.45 143	99.82 81	98.34 93	99.51 270	98.70 140	98.93 194	99.67 125

SDMVSNet		99.11 105	98.90 117	99.75 61	99.81 46	99.59 73	99.81 20	99.65 33	98.78 77	99.64 102	99.88 39	94.56 237	99.93 90	99.67 23	98.26 235	99.72 106

VNet		99.11 105	98.90 117	99.73 67	99.52 172	99.56 79	99.41 216	99.39 229	99.01 44	99.74 66	99.78 127	95.56 192	99.92 101	99.52 38	98.18 242	99.72 106

CPTT-MVS		99.11 105	98.90 117	99.74 64	99.80 52	99.46 97	99.59 107	99.49 149	97.03 274	99.63 105	99.69 172	97.27 129	99.96 32	97.82 233	99.84 83	99.81 64

HyFIR lowres test		99.11 105	98.92 114	99.65 77	99.90 4	99.37 105	99.02 330	99.91 3	97.67 205	99.59 118	99.75 142	95.90 181	99.73 219	99.53 36	99.02 190	99.86 32

MVS_Test		99.10 109	98.97 106	99.48 124	99.49 187	99.14 137	99.67 69	99.34 258	97.31 245	99.58 119	99.76 139	97.65 117	99.82 182	98.87 113	99.07 185	99.46 197

CDS-MVSNet		99.09 110	99.03 92	99.25 167	99.42 207	98.73 192	99.45 196	99.46 190	98.11 148	99.46 142	99.77 135	98.01 108	99.37 292	98.70 140	98.92 196	99.66 128
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PVSNet_Blended		99.08 111	98.97 106	99.42 135	99.76 66	98.79 188	98.78 366	99.91 3	96.74 291	99.67 85	99.49 253	97.53 118	99.88 141	98.98 97	99.85 75	99.60 150

OMC-MVS		99.08 111	99.04 90	99.20 173	99.67 114	98.22 233	99.28 266	99.52 105	98.07 156	99.66 90	99.81 95	97.79 113	99.78 202	97.79 235	99.81 99	99.60 150

mvsmamba		99.06 113	98.96 110	99.36 143	99.47 195	98.64 200	99.70 56	99.05 325	97.61 210	99.65 97	99.83 72	96.54 155	99.92 101	99.19 74	99.62 140	99.51 180

WTY-MVS		99.06 113	98.88 121	99.61 89	99.62 141	99.16 132	99.37 235	99.56 70	98.04 163	99.53 130	99.62 207	96.84 143	99.94 72	98.85 120	98.49 223	99.72 106

IS-MVSNet		99.05 115	98.87 122	99.57 97	99.73 90	99.32 110	99.75 42	99.20 305	98.02 166	99.56 123	99.86 52	96.54 155	99.67 243	98.09 207	99.13 178	99.73 100

PAPM_NR		99.04 116	98.84 128	99.66 73	99.74 83	99.44 99	99.39 228	99.38 237	97.70 201	99.28 187	99.28 314	98.34 93	99.85 155	96.96 302	99.45 152	99.69 118

API-MVS		99.04 116	99.03 92	99.06 187	99.40 217	99.31 114	99.55 142	99.56 70	98.54 96	99.33 178	99.39 285	98.76 55	99.78 202	96.98 300	99.78 110	98.07 375

mvs_anonymous		99.03 118	98.99 102	99.16 177	99.38 222	98.52 214	99.51 164	99.38 237	97.79 189	99.38 166	99.81 95	97.30 127	99.45 275	99.35 54	98.99 191	99.51 180

sasdasda		99.02 119	98.86 124	99.51 118	99.42 207	99.32 110	99.80 25	99.48 161	98.63 87	99.31 180	98.81 363	97.09 133	99.75 211	99.27 68	97.90 253	99.47 192

train_agg		99.02 119	98.77 135	99.77 58	99.67 114	99.65 60	99.05 322	99.41 220	96.28 326	98.95 255	99.49 253	98.76 55	99.91 112	97.63 252	99.72 124	99.75 91

canonicalmvs		99.02 119	98.86 124	99.51 118	99.42 207	99.32 110	99.80 25	99.48 161	98.63 87	99.31 180	98.81 363	97.09 133	99.75 211	99.27 68	97.90 253	99.47 192

PLC	97.94 4	99.02 119	98.85 126	99.53 110	99.66 124	99.01 154	99.24 284	99.52 105	96.85 286	99.27 192	99.48 259	98.25 97	99.91 112	97.76 240	99.62 140	99.65 132
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MGCFI-Net		99.01 123	98.85 126	99.50 123	99.42 207	99.26 121	99.82 16	99.48 161	98.60 91	99.28 187	98.81 363	97.04 137	99.76 208	99.29 65	97.87 256	99.47 192

AdaColmap		99.01 123	98.80 131	99.66 73	99.56 160	99.54 83	99.18 296	99.70 15	98.18 138	99.35 174	99.63 202	96.32 164	99.90 124	97.48 268	99.77 113	99.55 164

1112_ss		98.98 125	98.77 135	99.59 92	99.68 112	99.02 152	99.25 282	99.48 161	97.23 253	99.13 221	99.58 220	96.93 142	99.90 124	98.87 113	98.78 207	99.84 42

MSDG		98.98 125	98.80 131	99.53 110	99.76 66	99.19 127	98.75 369	99.55 78	97.25 250	99.47 140	99.77 135	97.82 112	99.87 146	96.93 305	99.90 43	99.54 166

CANet_DTU		98.97 127	98.87 122	99.25 167	99.33 234	98.42 226	99.08 316	99.30 283	99.16 20	99.43 150	99.75 142	95.27 202	99.97 21	98.56 167	99.95 17	99.36 215

DPM-MVS		98.95 128	98.71 141	99.66 73	99.63 135	99.55 81	98.64 380	99.10 316	97.93 171	99.42 153	99.55 231	98.67 69	99.80 194	95.80 337	99.68 132	99.61 147

114514_t		98.93 129	98.67 145	99.72 69	99.85 26	99.53 86	99.62 93	99.59 58	92.65 391	99.71 75	99.78 127	98.06 106	99.90 124	98.84 123	99.91 34	99.74 95

PS-MVSNAJss		98.92 130	98.92 114	98.90 214	98.78 344	98.53 210	99.78 32	99.54 87	98.07 156	99.00 248	99.76 139	99.01 18	99.37 292	99.13 80	97.23 295	98.81 265

RRT-MVS		98.91 131	98.75 137	99.39 141	99.46 197	98.61 204	99.76 37	99.50 139	98.06 160	99.81 42	99.88 39	93.91 264	99.94 72	99.11 82	99.27 167	99.61 147

Test_1112_low_res		98.89 132	98.66 148	99.57 97	99.69 108	98.95 166	99.03 327	99.47 181	96.98 276	99.15 219	99.23 322	96.77 146	99.89 136	98.83 126	98.78 207	99.86 32

test_fmvs1		98.88 133	98.79 134	99.16 177	99.69 108	97.61 269	99.55 142	99.49 149	99.32 14	99.98 6	99.91 20	91.41 327	99.96 32	99.82 16	99.92 27	99.90 16

AllTest		98.87 134	98.72 139	99.31 152	99.86 20	98.48 220	99.56 128	99.61 48	97.85 181	99.36 171	99.85 57	95.95 176	99.85 155	96.66 318	99.83 92	99.59 154

UGNet		98.87 134	98.69 143	99.40 137	99.22 266	98.72 193	99.44 202	99.68 20	99.24 17	99.18 216	99.42 273	92.74 289	99.96 32	99.34 59	99.94 23	99.53 172
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
Vis-MVSNet (Re-imp)		98.87 134	98.72 139	99.31 152	99.71 99	98.88 175	99.80 25	99.44 209	97.91 173	99.36 171	99.78 127	95.49 195	99.43 284	97.91 223	99.11 179	99.62 145

test_yl		98.86 137	98.63 150	99.54 102	99.49 187	99.18 129	99.50 171	99.07 322	98.22 131	99.61 112	99.51 247	95.37 198	99.84 162	98.60 158	98.33 229	99.59 154

DCV-MVSNet		98.86 137	98.63 150	99.54 102	99.49 187	99.18 129	99.50 171	99.07 322	98.22 131	99.61 112	99.51 247	95.37 198	99.84 162	98.60 158	98.33 229	99.59 154

EPNet		98.86 137	98.71 141	99.30 157	97.20 397	98.18 234	99.62 93	98.91 345	99.28 16	98.63 305	99.81 95	95.96 175	99.99 4	99.24 71	99.72 124	99.73 100
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 137	98.80 131	99.03 191	99.76 66	98.79 188	99.28 266	99.91 3	97.42 236	99.67 85	99.37 290	97.53 118	99.88 141	98.98 97	97.29 293	98.42 353

ab-mvs		98.86 137	98.63 150	99.54 102	99.64 132	99.19 127	99.44 202	99.54 87	97.77 192	99.30 183	99.81 95	94.20 251	99.93 90	99.17 78	98.82 204	99.49 185

MAR-MVS		98.86 137	98.63 150	99.54 102	99.37 225	99.66 56	99.45 196	99.54 87	96.61 303	99.01 244	99.40 281	97.09 133	99.86 149	97.68 251	99.53 148	99.10 236
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
COLMAP_ROB	97.56 6	98.86 137	98.75 137	99.17 176	99.88 11	98.53 210	99.34 248	99.59 58	97.55 217	98.70 293	99.89 32	95.83 183	99.90 124	98.10 206	99.90 43	99.08 241
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 144	98.62 155	99.53 110	99.61 145	99.08 145	99.80 25	99.51 119	97.10 266	99.31 180	99.78 127	95.23 206	99.77 204	98.21 198	99.03 188	99.75 91

HY-MVS	97.30 7	98.85 144	98.64 149	99.47 127	99.42 207	99.08 145	99.62 93	99.36 246	97.39 239	99.28 187	99.68 178	96.44 161	99.92 101	98.37 185	98.22 237	99.40 209

PVSNet	96.02 17	98.85 144	98.84 128	98.89 217	99.73 90	97.28 278	98.32 397	99.60 54	97.86 178	99.50 135	99.57 225	96.75 147	99.86 149	98.56 167	99.70 128	99.54 166

PatchMatch-RL		98.84 147	98.62 155	99.52 116	99.71 99	99.28 118	99.06 320	99.77 9	97.74 196	99.50 135	99.53 240	95.41 196	99.84 162	97.17 292	99.64 137	99.44 202

Effi-MVS+		98.81 148	98.59 161	99.48 124	99.46 197	99.12 140	98.08 404	99.50 139	97.50 225	99.38 166	99.41 277	96.37 163	99.81 187	99.11 82	98.54 220	99.51 180

alignmvs		98.81 148	98.56 164	99.58 95	99.43 205	99.42 101	99.51 164	98.96 336	98.61 90	99.35 174	98.92 358	94.78 221	99.77 204	99.35 54	98.11 247	99.54 166

DeepPCF-MVS	98.18 3	98.81 148	99.37 36	97.12 356	99.60 150	91.75 396	98.61 381	99.44 209	99.35 12	99.83 40	99.85 57	98.70 66	99.81 187	99.02 94	99.91 34	99.81 64

PMMVS		98.80 151	98.62 155	99.34 145	99.27 252	98.70 194	98.76 368	99.31 279	97.34 242	99.21 206	99.07 338	97.20 130	99.82 182	98.56 167	98.87 199	99.52 173

Effi-MVS+-dtu		98.78 152	98.89 120	98.47 273	99.33 234	96.91 307	99.57 122	99.30 283	98.47 101	99.41 157	98.99 348	96.78 145	99.74 213	98.73 137	99.38 156	98.74 278

FIs		98.78 152	98.63 150	99.23 171	99.18 275	99.54 83	99.83 15	99.59 58	98.28 121	98.79 280	99.81 95	96.75 147	99.37 292	99.08 87	96.38 311	98.78 267

Fast-Effi-MVS+-dtu		98.77 154	98.83 130	98.60 252	99.41 212	96.99 301	99.52 155	99.49 149	98.11 148	99.24 198	99.34 300	96.96 141	99.79 197	97.95 221	99.45 152	99.02 251

sd_testset		98.75 155	98.57 162	99.29 160	99.81 46	98.26 231	99.56 128	99.62 41	98.78 77	99.64 102	99.88 39	92.02 311	99.88 141	99.54 34	98.26 235	99.72 106

FA-MVS(test-final)		98.75 155	98.53 166	99.41 136	99.55 164	99.05 150	99.80 25	99.01 330	96.59 308	99.58 119	99.59 216	95.39 197	99.90 124	97.78 236	99.49 150	99.28 224

FC-MVSNet-test		98.75 155	98.62 155	99.15 181	99.08 302	99.45 98	99.86 11	99.60 54	98.23 130	98.70 293	99.82 81	96.80 144	99.22 321	99.07 88	96.38 311	98.79 266

XVG-OURS		98.73 158	98.68 144	98.88 219	99.70 104	97.73 260	98.92 352	99.55 78	98.52 98	99.45 143	99.84 67	95.27 202	99.91 112	98.08 211	98.84 202	99.00 252

Fast-Effi-MVS+		98.70 159	98.43 170	99.51 118	99.51 175	99.28 118	99.52 155	99.47 181	96.11 342	99.01 244	99.34 300	96.20 168	99.84 162	97.88 225	98.82 204	99.39 210

XVG-OURS-SEG-HR		98.69 160	98.62 155	98.89 217	99.71 99	97.74 259	99.12 307	99.54 87	98.44 106	99.42 153	99.71 158	94.20 251	99.92 101	98.54 171	98.90 198	99.00 252

1314		98.68 161	98.54 165	99.11 183	98.89 329	98.65 198	99.27 271	99.49 149	96.89 284	97.99 344	99.56 228	97.72 116	99.83 175	97.74 243	99.27 167	98.84 264

EI-MVSNet		98.67 162	98.67 145	98.68 248	99.35 229	97.97 246	99.50 171	99.38 237	96.93 283	99.20 209	99.83 72	97.87 110	99.36 296	98.38 183	97.56 272	98.71 282

test_djsdf		98.67 162	98.57 162	98.98 197	98.70 358	98.91 173	99.88 4	99.46 190	97.55 217	99.22 203	99.88 39	95.73 187	99.28 309	99.03 92	97.62 267	98.75 275

QAPM		98.67 162	98.30 180	99.80 49	99.20 269	99.67 54	99.77 34	99.72 11	94.74 369	98.73 285	99.90 27	95.78 185	99.98 13	96.96 302	99.88 57	99.76 90

nrg030		98.64 165	98.42 171	99.28 164	99.05 308	99.69 50	99.81 20	99.46 190	98.04 163	99.01 244	99.82 81	96.69 149	99.38 289	99.34 59	94.59 355	98.78 267

test_vis1_n_1920		98.63 166	98.40 173	99.31 152	99.86 20	97.94 252	99.67 69	99.62 41	99.43 7	99.99 2	99.91 20	87.29 376	100.00 1	99.92 11	99.92 27	99.98 2

PAPR		98.63 166	98.34 176	99.51 118	99.40 217	99.03 151	98.80 364	99.36 246	96.33 323	99.00 248	99.12 336	98.46 84	99.84 162	95.23 352	99.37 163	99.66 128

CVMVSNet		98.57 168	98.67 145	98.30 293	99.35 229	95.59 348	99.50 171	99.55 78	98.60 91	99.39 164	99.83 72	94.48 242	99.45 275	98.75 134	98.56 218	99.85 36

MVSTER		98.49 169	98.32 178	99.00 195	99.35 229	99.02 152	99.54 146	99.38 237	97.41 237	99.20 209	99.73 153	93.86 266	99.36 296	98.87 113	97.56 272	98.62 324

FE-MVS		98.48 170	98.17 185	99.40 137	99.54 167	98.96 163	99.68 66	98.81 359	95.54 353	99.62 109	99.70 162	93.82 267	99.93 90	97.35 279	99.46 151	99.32 221

OpenMVS	96.50 16	98.47 171	98.12 192	99.52 116	99.04 309	99.53 86	99.82 16	99.72 11	94.56 372	98.08 339	99.88 39	94.73 227	99.98 13	97.47 270	99.76 116	99.06 247

IterMVS-LS		98.46 172	98.42 171	98.58 256	99.59 152	98.00 244	99.37 235	99.43 215	96.94 282	99.07 233	99.59 216	97.87 110	99.03 349	98.32 192	95.62 333	98.71 282
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 173	98.28 181	98.94 204	98.50 374	98.96 163	99.77 34	99.50 139	97.07 268	98.87 268	99.77 135	94.76 225	99.28 309	98.66 147	97.60 268	98.57 339

jajsoiax		98.43 174	98.28 181	98.88 219	98.60 368	98.43 224	99.82 16	99.53 100	98.19 135	98.63 305	99.80 108	93.22 278	99.44 280	99.22 72	97.50 279	98.77 271

tttt0517		98.42 175	98.14 189	99.28 164	99.66 124	98.38 227	99.74 46	96.85 404	97.68 203	99.79 48	99.74 147	91.39 328	99.89 136	98.83 126	99.56 145	99.57 161

BH-untuned		98.42 175	98.36 174	98.59 253	99.49 187	96.70 315	99.27 271	99.13 314	97.24 252	98.80 278	99.38 287	95.75 186	99.74 213	97.07 296	99.16 173	99.33 220

test_fmvs1_n		98.41 177	98.14 189	99.21 172	99.82 42	97.71 265	99.74 46	99.49 149	99.32 14	99.99 2	99.95 3	85.32 387	99.97 21	99.82 16	99.84 83	99.96 7

D2MVS		98.41 177	98.50 167	98.15 307	99.26 254	96.62 321	99.40 224	99.61 48	97.71 198	98.98 250	99.36 293	96.04 172	99.67 243	98.70 140	97.41 289	98.15 371

BH-RMVSNet		98.41 177	98.08 198	99.40 137	99.41 212	98.83 184	99.30 256	98.77 363	97.70 201	98.94 257	99.65 190	92.91 285	99.74 213	96.52 322	99.55 147	99.64 139

mvs_tets		98.40 180	98.23 183	98.91 212	98.67 361	98.51 216	99.66 74	99.53 100	98.19 135	98.65 302	99.81 95	92.75 287	99.44 280	99.31 62	97.48 283	98.77 271

MonoMVSNet		98.38 181	98.47 169	98.12 309	98.59 370	96.19 338	99.72 52	98.79 362	97.89 175	99.44 148	99.52 243	96.13 169	98.90 370	98.64 149	97.54 274	99.28 224

XXY-MVS		98.38 181	98.09 197	99.24 169	99.26 254	99.32 110	99.56 128	99.55 78	97.45 230	98.71 287	99.83 72	93.23 276	99.63 260	98.88 110	96.32 313	98.76 273

ACMM	97.58 5	98.37 183	98.34 176	98.48 268	99.41 212	97.10 288	99.56 128	99.45 201	98.53 97	99.04 241	99.85 57	93.00 281	99.71 229	98.74 135	97.45 284	98.64 315
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 184	98.03 204	99.31 152	99.63 135	98.56 207	99.54 146	96.75 406	97.53 221	99.73 68	99.65 190	91.25 331	99.89 136	98.62 152	99.56 145	99.48 186

tpmrst		98.33 185	98.48 168	97.90 325	99.16 285	94.78 368	99.31 254	99.11 315	97.27 248	99.45 143	99.59 216	95.33 200	99.84 162	98.48 174	98.61 212	99.09 240

baseline1		98.31 186	97.95 213	99.38 142	99.50 185	98.74 191	99.59 107	98.93 338	98.41 108	99.14 220	99.60 214	94.59 235	99.79 197	98.48 174	93.29 374	99.61 147

PatchmatchNet		98.31 186	98.36 174	98.19 302	99.16 285	95.32 358	99.27 271	98.92 341	97.37 240	99.37 168	99.58 220	94.90 214	99.70 235	97.43 274	99.21 170	99.54 166
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 188	97.98 209	99.26 166	99.57 156	98.16 235	99.41 216	98.55 381	96.03 347	99.19 212	99.74 147	91.87 314	99.92 101	99.16 79	98.29 234	99.70 116

VPA-MVSNet		98.29 189	97.95 213	99.30 157	99.16 285	99.54 83	99.50 171	99.58 62	98.27 123	99.35 174	99.37 290	92.53 299	99.65 251	99.35 54	94.46 356	98.72 280

UniMVSNet (Re)		98.29 189	98.00 207	99.13 182	99.00 313	99.36 108	99.49 182	99.51 119	97.95 169	98.97 252	99.13 333	96.30 165	99.38 289	98.36 187	93.34 373	98.66 311

HQP_MVS		98.27 191	98.22 184	98.44 279	99.29 247	96.97 303	99.39 228	99.47 181	98.97 55	99.11 225	99.61 211	92.71 292	99.69 240	97.78 236	97.63 265	98.67 303

UniMVSNet_NR-MVSNet		98.22 192	97.97 210	98.96 200	98.92 326	98.98 156	99.48 186	99.53 100	97.76 193	98.71 287	99.46 266	96.43 162	99.22 321	98.57 164	92.87 380	98.69 291

LPG-MVS_test		98.22 192	98.13 191	98.49 266	99.33 234	97.05 294	99.58 115	99.55 78	97.46 227	99.24 198	99.83 72	92.58 297	99.72 223	98.09 207	97.51 277	98.68 296

RPSCF		98.22 192	98.62 155	96.99 358	99.82 42	91.58 397	99.72 52	99.44 209	96.61 303	99.66 90	99.89 32	95.92 179	99.82 182	97.46 271	99.10 182	99.57 161

ADS-MVSNet		98.20 195	98.08 198	98.56 260	99.33 234	96.48 326	99.23 286	99.15 311	96.24 330	99.10 228	99.67 184	94.11 255	99.71 229	96.81 310	99.05 186	99.48 186

OPM-MVS		98.19 196	98.10 194	98.45 276	98.88 330	97.07 292	99.28 266	99.38 237	98.57 93	99.22 203	99.81 95	92.12 309	99.66 246	98.08 211	97.54 274	98.61 333
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 196	98.16 186	98.27 299	99.30 243	95.55 349	99.07 317	98.97 334	97.57 214	99.43 150	99.57 225	92.72 290	99.74 213	97.58 256	99.20 171	99.52 173

miper_ehance_all_eth		98.18 198	98.10 194	98.41 282	99.23 262	97.72 262	98.72 372	99.31 279	96.60 306	98.88 265	99.29 312	97.29 128	99.13 335	97.60 254	95.99 322	98.38 358

CR-MVSNet		98.17 199	97.93 216	98.87 223	99.18 275	98.49 218	99.22 290	99.33 265	96.96 278	99.56 123	99.38 287	94.33 247	99.00 354	94.83 359	98.58 215	99.14 233

miper_enhance_ethall		98.16 200	98.08 198	98.41 282	98.96 322	97.72 262	98.45 390	99.32 275	96.95 280	98.97 252	99.17 328	97.06 136	99.22 321	97.86 228	95.99 322	98.29 362

CLD-MVS		98.16 200	98.10 194	98.33 289	99.29 247	96.82 312	98.75 369	99.44 209	97.83 184	99.13 221	99.55 231	92.92 283	99.67 243	98.32 192	97.69 263	98.48 345
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 202	97.79 228	99.19 174	99.50 185	98.50 217	98.61 381	96.82 405	96.95 280	99.54 128	99.43 271	91.66 323	99.86 149	98.08 211	99.51 149	99.22 230

pmmvs4		98.13 203	97.90 218	98.81 235	98.61 367	98.87 176	98.99 338	99.21 304	96.44 318	99.06 238	99.58 220	95.90 181	99.11 340	97.18 291	96.11 318	98.46 350

WR-MVS_H		98.13 203	97.87 223	98.90 214	99.02 311	98.84 181	99.70 56	99.59 58	97.27 248	98.40 321	99.19 327	95.53 193	99.23 317	98.34 189	93.78 370	98.61 333

c3_l		98.12 205	98.04 203	98.38 286	99.30 243	97.69 266	98.81 363	99.33 265	96.67 296	98.83 274	99.34 300	97.11 132	98.99 355	97.58 256	95.34 340	98.48 345

ACMH	97.28 8	98.10 206	97.99 208	98.44 279	99.41 212	96.96 305	99.60 100	99.56 70	98.09 151	98.15 337	99.91 20	90.87 335	99.70 235	98.88 110	97.45 284	98.67 303
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		98.09 207	97.68 244	99.34 145	99.66 124	98.44 223	99.40 224	99.43 215	93.67 379	99.22 203	99.89 32	90.23 343	99.93 90	99.26 70	98.33 229	99.66 128

CP-MVSNet		98.09 207	97.78 231	99.01 193	98.97 321	99.24 124	99.67 69	99.46 190	97.25 250	98.48 318	99.64 196	93.79 268	99.06 345	98.63 151	94.10 364	98.74 278

dmvs_re		98.08 209	98.16 186	97.85 328	99.55 164	94.67 371	99.70 56	98.92 341	98.15 140	99.06 238	99.35 296	93.67 272	99.25 314	97.77 239	97.25 294	99.64 139

DU-MVS		98.08 209	97.79 228	98.96 200	98.87 333	98.98 156	99.41 216	99.45 201	97.87 177	98.71 287	99.50 250	94.82 217	99.22 321	98.57 164	92.87 380	98.68 296

v2v482		98.06 211	97.77 233	98.92 208	98.90 328	98.82 185	99.57 122	99.36 246	96.65 298	99.19 212	99.35 296	94.20 251	99.25 314	97.72 246	94.97 348	98.69 291

V42		98.06 211	97.79 228	98.86 226	98.98 319	98.84 181	99.69 60	99.34 258	96.53 310	99.30 183	99.37 290	94.67 232	99.32 304	97.57 260	94.66 353	98.42 353

test-LLR		98.06 211	97.90 218	98.55 262	98.79 341	97.10 288	98.67 375	97.75 396	97.34 242	98.61 308	98.85 360	94.45 244	99.45 275	97.25 283	99.38 156	99.10 236

WR-MVS		98.06 211	97.73 240	99.06 187	98.86 336	99.25 123	99.19 294	99.35 253	97.30 246	98.66 296	99.43 271	93.94 261	99.21 326	98.58 161	94.28 360	98.71 282

ACMP	97.20 11	98.06 211	97.94 215	98.45 276	99.37 225	97.01 299	99.44 202	99.49 149	97.54 220	98.45 319	99.79 120	91.95 313	99.72 223	97.91 223	97.49 282	98.62 324
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 216	97.96 211	98.33 289	99.26 254	97.38 275	98.56 386	99.31 279	96.65 298	98.88 265	99.52 243	96.58 153	99.12 339	97.39 276	95.53 337	98.47 347

test1111		98.04 217	98.11 193	97.83 331	99.74 83	93.82 380	99.58 115	95.40 413	99.12 29	99.65 97	99.93 9	90.73 336	99.84 162	99.43 50	99.38 156	99.82 57

ECVR-MVS		98.04 217	98.05 202	98.00 317	99.74 83	94.37 375	99.59 107	94.98 414	99.13 24	99.66 90	99.93 9	90.67 337	99.84 162	99.40 51	99.38 156	99.80 73

EPNet_dtu		98.03 219	97.96 211	98.23 300	98.27 379	95.54 351	99.23 286	98.75 364	99.02 42	97.82 351	99.71 158	96.11 170	99.48 271	93.04 379	99.65 136	99.69 118
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 219	97.76 237	98.84 230	99.39 220	98.98 156	99.40 224	99.38 237	96.67 296	99.07 233	99.28 314	92.93 282	98.98 356	97.10 293	96.65 304	98.56 340

ADS-MVSNet2		98.02 221	98.07 201	97.87 327	99.33 234	95.19 361	99.23 286	99.08 319	96.24 330	99.10 228	99.67 184	94.11 255	98.93 367	96.81 310	99.05 186	99.48 186

HQP-MVS		98.02 221	97.90 218	98.37 287	99.19 272	96.83 310	98.98 341	99.39 229	98.24 127	98.66 296	99.40 281	92.47 301	99.64 254	97.19 289	97.58 270	98.64 315

LTVRE_ROB	97.16 12	98.02 221	97.90 218	98.40 284	99.23 262	96.80 313	99.70 56	99.60 54	97.12 262	98.18 336	99.70 162	91.73 319	99.72 223	98.39 182	97.45 284	98.68 296
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
cl____		98.01 224	97.84 226	98.55 262	99.25 258	97.97 246	98.71 373	99.34 258	96.47 317	98.59 311	99.54 236	95.65 190	99.21 326	97.21 285	95.77 328	98.46 350

DIV-MVS_self_test		98.01 224	97.85 225	98.48 268	99.24 260	97.95 250	98.71 373	99.35 253	96.50 311	98.60 310	99.54 236	95.72 188	99.03 349	97.21 285	95.77 328	98.46 350

miper_lstm_enhance		98.00 226	97.91 217	98.28 298	99.34 233	97.43 273	98.88 356	99.36 246	96.48 315	98.80 278	99.55 231	95.98 174	98.91 368	97.27 282	95.50 338	98.51 343

BH-w/o		98.00 226	97.89 222	98.32 291	99.35 229	96.20 337	99.01 335	98.90 347	96.42 320	98.38 322	99.00 347	95.26 204	99.72 223	96.06 330	98.61 212	99.03 249

v1144		97.98 228	97.69 243	98.85 229	98.87 333	98.66 197	99.54 146	99.35 253	96.27 328	99.23 202	99.35 296	94.67 232	99.23 317	96.73 313	95.16 344	98.68 296

EU-MVSNet		97.98 228	98.03 204	97.81 334	98.72 355	96.65 320	99.66 74	99.66 28	98.09 151	98.35 324	99.82 81	95.25 205	98.01 391	97.41 275	95.30 341	98.78 267

tpmvs		97.98 228	98.02 206	97.84 330	99.04 309	94.73 369	99.31 254	99.20 305	96.10 346	98.76 283	99.42 273	94.94 210	99.81 187	96.97 301	98.45 224	98.97 256

tt0805		97.97 231	97.77 233	98.57 257	99.59 152	96.61 322	99.45 196	99.08 319	98.21 133	98.88 265	99.80 108	88.66 361	99.70 235	98.58 161	97.72 262	99.39 210

NR-MVSNet		97.97 231	97.61 253	99.02 192	98.87 333	99.26 121	99.47 192	99.42 217	97.63 208	97.08 369	99.50 250	95.07 209	99.13 335	97.86 228	93.59 371	98.68 296

v8		97.95 233	97.63 251	98.93 206	98.95 323	98.81 187	99.80 25	99.41 220	96.03 347	99.10 228	99.42 273	94.92 213	99.30 307	96.94 304	94.08 365	98.66 311

Patchmatch-test		97.93 234	97.65 247	98.77 240	99.18 275	97.07 292	99.03 327	99.14 313	96.16 337	98.74 284	99.57 225	94.56 237	99.72 223	93.36 375	99.11 179	99.52 173

PS-CasMVS		97.93 234	97.59 255	98.95 202	98.99 316	99.06 148	99.68 66	99.52 105	97.13 260	98.31 326	99.68 178	92.44 305	99.05 346	98.51 172	94.08 365	98.75 275

TranMVSNet+NR-MVSNet		97.93 234	97.66 246	98.76 241	98.78 344	98.62 202	99.65 80	99.49 149	97.76 193	98.49 317	99.60 214	94.23 250	98.97 363	98.00 218	92.90 378	98.70 287

test_vis1_n		97.92 237	97.44 276	99.34 145	99.53 168	98.08 240	99.74 46	99.49 149	99.15 21	100.00 1	99.94 6	79.51 406	99.98 13	99.88 13	99.76 116	99.97 4

v144192		97.92 237	97.60 254	98.87 223	98.83 339	98.65 198	99.55 142	99.34 258	96.20 333	99.32 179	99.40 281	94.36 246	99.26 313	96.37 327	95.03 347	98.70 287

ACMH+	97.24 10	97.92 237	97.78 231	98.32 291	99.46 197	96.68 319	99.56 128	99.54 87	98.41 108	97.79 353	99.87 48	90.18 344	99.66 246	98.05 215	97.18 298	98.62 324

LFMVS		97.90 240	97.35 288	99.54 102	99.52 172	99.01 154	99.39 228	98.24 388	97.10 266	99.65 97	99.79 120	84.79 390	99.91 112	99.28 66	98.38 226	99.69 118

reproduce_monomvs		97.89 241	97.87 223	97.96 321	99.51 175	95.45 354	99.60 100	99.25 295	99.17 19	98.85 273	99.49 253	89.29 353	99.64 254	99.35 54	96.31 314	98.78 267

Anonymous20231211		97.88 242	97.54 259	98.90 214	99.71 99	98.53 210	99.48 186	99.57 65	94.16 375	98.81 276	99.68 178	93.23 276	99.42 285	98.84 123	94.42 358	98.76 273

OurMVSNet-221017-0		97.88 242	97.77 233	98.19 302	98.71 357	96.53 324	99.88 4	99.00 331	97.79 189	98.78 281	99.94 6	91.68 320	99.35 299	97.21 285	96.99 302	98.69 291

v7n		97.87 244	97.52 260	98.92 208	98.76 351	98.58 206	99.84 12	99.46 190	96.20 333	98.91 260	99.70 162	94.89 215	99.44 280	96.03 331	93.89 368	98.75 275

baseline2		97.87 244	97.55 256	98.82 232	99.18 275	98.02 243	99.41 216	96.58 410	96.97 277	96.51 376	99.17 328	93.43 273	99.57 265	97.71 247	99.03 188	98.86 262

thres600view7		97.86 246	97.51 262	98.92 208	99.72 94	97.95 250	99.59 107	98.74 367	97.94 170	99.27 192	98.62 371	91.75 317	99.86 149	93.73 371	98.19 241	98.96 258

UBG		97.85 247	97.48 265	98.95 202	99.25 258	97.64 267	99.24 284	98.74 367	97.90 174	98.64 303	98.20 387	88.65 362	99.81 187	98.27 195	98.40 225	99.42 204

cl22		97.85 247	97.64 250	98.48 268	99.09 299	97.87 254	98.60 383	99.33 265	97.11 265	98.87 268	99.22 323	92.38 306	99.17 330	98.21 198	95.99 322	98.42 353

v10		97.85 247	97.52 260	98.86 226	98.99 316	98.67 196	99.75 42	99.41 220	95.70 351	98.98 250	99.41 277	94.75 226	99.23 317	96.01 333	94.63 354	98.67 303

GA-MVS		97.85 247	97.47 268	99.00 195	99.38 222	97.99 245	98.57 384	99.15 311	97.04 273	98.90 262	99.30 310	89.83 347	99.38 289	96.70 315	98.33 229	99.62 145

tfpnnormal		97.84 251	97.47 268	98.98 197	99.20 269	99.22 126	99.64 83	99.61 48	96.32 324	98.27 330	99.70 162	93.35 275	99.44 280	95.69 340	95.40 339	98.27 363

VPNet		97.84 251	97.44 276	99.01 193	99.21 267	98.94 169	99.48 186	99.57 65	98.38 110	99.28 187	99.73 153	88.89 356	99.39 287	99.19 74	93.27 375	98.71 282

LCM-MVSNet-Re		97.83 253	98.15 188	96.87 364	99.30 243	92.25 394	99.59 107	98.26 386	97.43 234	96.20 380	99.13 333	96.27 166	98.73 377	98.17 203	98.99 191	99.64 139

XVG-ACMP-BASELINE		97.83 253	97.71 242	98.20 301	99.11 293	96.33 331	99.41 216	99.52 105	98.06 160	99.05 240	99.50 250	89.64 350	99.73 219	97.73 244	97.38 291	98.53 341

IterMVS		97.83 253	97.77 233	98.02 314	99.58 154	96.27 334	99.02 330	99.48 161	97.22 254	98.71 287	99.70 162	92.75 287	99.13 335	97.46 271	96.00 321	98.67 303
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 256	97.75 238	98.06 311	99.57 156	96.36 330	99.02 330	99.49 149	97.18 256	98.71 287	99.72 157	92.72 290	99.14 332	97.44 273	95.86 327	98.67 303

EPMVS		97.82 256	97.65 247	98.35 288	98.88 330	95.98 341	99.49 182	94.71 416	97.57 214	99.26 196	99.48 259	92.46 304	99.71 229	97.87 227	99.08 184	99.35 216

MVP-Stereo		97.81 258	97.75 238	97.99 318	97.53 390	96.60 323	98.96 345	98.85 354	97.22 254	97.23 364	99.36 293	95.28 201	99.46 274	95.51 344	99.78 110	97.92 388
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 258	97.44 276	98.91 212	98.88 330	98.68 195	99.51 164	99.34 258	96.18 335	99.20 209	99.34 300	94.03 258	99.36 296	95.32 350	95.18 343	98.69 291

ttmdpeth		97.80 260	97.63 251	98.29 294	98.77 349	97.38 275	99.64 83	99.36 246	98.78 77	96.30 379	99.58 220	92.34 308	99.39 287	98.36 187	95.58 334	98.10 373

v1921920		97.80 260	97.45 271	98.84 230	98.80 340	98.53 210	99.52 155	99.34 258	96.15 339	99.24 198	99.47 262	93.98 260	99.29 308	95.40 348	95.13 345	98.69 291

v148		97.79 262	97.55 256	98.50 265	98.74 352	97.72 262	99.54 146	99.33 265	96.26 329	98.90 262	99.51 247	94.68 231	99.14 332	97.83 232	93.15 377	98.63 322

thres400		97.77 263	97.38 284	98.92 208	99.69 108	97.96 248	99.50 171	98.73 373	97.83 184	99.17 217	98.45 377	91.67 321	99.83 175	93.22 376	98.18 242	98.96 258

thres100view900		97.76 264	97.45 271	98.69 247	99.72 94	97.86 256	99.59 107	98.74 367	97.93 171	99.26 196	98.62 371	91.75 317	99.83 175	93.22 376	98.18 242	98.37 359

PEN-MVS		97.76 264	97.44 276	98.72 243	98.77 349	98.54 209	99.78 32	99.51 119	97.06 270	98.29 329	99.64 196	92.63 296	98.89 371	98.09 207	93.16 376	98.72 280

Baseline_NR-MVSNet		97.76 264	97.45 271	98.68 248	99.09 299	98.29 229	99.41 216	98.85 354	95.65 352	98.63 305	99.67 184	94.82 217	99.10 342	98.07 214	92.89 379	98.64 315

TR-MVS		97.76 264	97.41 282	98.82 232	99.06 305	97.87 254	98.87 358	98.56 380	96.63 302	98.68 295	99.22 323	92.49 300	99.65 251	95.40 348	97.79 260	98.95 260

Patchmtry		97.75 268	97.40 283	98.81 235	99.10 296	98.87 176	99.11 313	99.33 265	94.83 367	98.81 276	99.38 287	94.33 247	99.02 351	96.10 329	95.57 335	98.53 341

dp		97.75 268	97.80 227	97.59 344	99.10 296	93.71 383	99.32 251	98.88 350	96.48 315	99.08 232	99.55 231	92.67 295	99.82 182	96.52 322	98.58 215	99.24 229

WBMVS		97.74 270	97.50 263	98.46 274	99.24 260	97.43 273	99.21 292	99.42 217	97.45 230	98.96 254	99.41 277	88.83 357	99.23 317	98.94 101	96.02 319	98.71 282

TAPA-MVS	97.07 15	97.74 270	97.34 291	98.94 204	99.70 104	97.53 270	99.25 282	99.51 119	91.90 393	99.30 183	99.63 202	98.78 51	99.64 254	88.09 402	99.87 60	99.65 132
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 272	97.35 288	98.88 219	99.47 195	97.12 287	99.34 248	98.85 354	98.19 135	99.67 85	99.85 57	82.98 397	99.92 101	99.49 44	98.32 233	99.60 150

MIMVSNet		97.73 272	97.45 271	98.57 257	99.45 203	97.50 271	99.02 330	98.98 333	96.11 342	99.41 157	99.14 332	90.28 339	98.74 376	95.74 338	98.93 194	99.47 192

tfpn200view9		97.72 274	97.38 284	98.72 243	99.69 108	97.96 248	99.50 171	98.73 373	97.83 184	99.17 217	98.45 377	91.67 321	99.83 175	93.22 376	98.18 242	98.37 359

CostFormer		97.72 274	97.73 240	97.71 338	99.15 289	94.02 379	99.54 146	99.02 329	94.67 370	99.04 241	99.35 296	92.35 307	99.77 204	98.50 173	97.94 252	99.34 219

FMVSNet2		97.72 274	97.36 286	98.80 237	99.51 175	98.84 181	99.45 196	99.42 217	96.49 312	98.86 272	99.29 312	90.26 340	98.98 356	96.44 324	96.56 307	98.58 338

test0.0.03 1		97.71 277	97.42 281	98.56 260	98.41 378	97.82 257	98.78 366	98.63 378	97.34 242	98.05 343	98.98 350	94.45 244	98.98 356	95.04 355	97.15 299	98.89 261

h-mvs33		97.70 278	97.28 299	98.97 199	99.70 104	97.27 279	99.36 240	99.45 201	98.94 58	99.66 90	99.64 196	94.93 211	99.99 4	99.48 45	84.36 405	99.65 132

v1240		97.69 279	97.32 294	98.79 238	98.85 337	98.43 224	99.48 186	99.36 246	96.11 342	99.27 192	99.36 293	93.76 270	99.24 316	94.46 362	95.23 342	98.70 287

cascas		97.69 279	97.43 280	98.48 268	98.60 368	97.30 277	98.18 402	99.39 229	92.96 387	98.41 320	98.78 367	93.77 269	99.27 312	98.16 204	98.61 212	98.86 262

pm-mvs1		97.68 281	97.28 299	98.88 219	99.06 305	98.62 202	99.50 171	99.45 201	96.32 324	97.87 349	99.79 120	92.47 301	99.35 299	97.54 263	93.54 372	98.67 303

GBi-Net		97.68 281	97.48 265	98.29 294	99.51 175	97.26 281	99.43 206	99.48 161	96.49 312	99.07 233	99.32 307	90.26 340	98.98 356	97.10 293	96.65 304	98.62 324

test1		97.68 281	97.48 265	98.29 294	99.51 175	97.26 281	99.43 206	99.48 161	96.49 312	99.07 233	99.32 307	90.26 340	98.98 356	97.10 293	96.65 304	98.62 324

tpm		97.67 284	97.55 256	98.03 312	99.02 311	95.01 364	99.43 206	98.54 382	96.44 318	99.12 223	99.34 300	91.83 316	99.60 263	97.75 242	96.46 309	99.48 186

PCF-MVS	97.08 14	97.66 285	97.06 310	99.47 127	99.61 145	99.09 142	98.04 405	99.25 295	91.24 396	98.51 315	99.70 162	94.55 239	99.91 112	92.76 384	99.85 75	99.42 204
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 286	97.65 247	97.63 341	98.78 344	97.62 268	99.13 304	98.33 385	97.36 241	99.07 233	98.94 354	95.64 191	99.15 331	92.95 380	98.68 211	96.12 407

our_test_3		97.65 286	97.68 244	97.55 345	98.62 365	94.97 365	98.84 360	99.30 283	96.83 289	98.19 335	99.34 300	97.01 139	99.02 351	95.00 356	96.01 320	98.64 315

testgi		97.65 286	97.50 263	98.13 308	99.36 228	96.45 327	99.42 213	99.48 161	97.76 193	97.87 349	99.45 268	91.09 332	98.81 373	94.53 361	98.52 221	99.13 235

thres200		97.61 289	97.28 299	98.62 251	99.64 132	98.03 242	99.26 280	98.74 367	97.68 203	99.09 231	98.32 383	91.66 323	99.81 187	92.88 381	98.22 237	98.03 378

PAPM		97.59 290	97.09 309	99.07 185	99.06 305	98.26 231	98.30 398	99.10 316	94.88 365	98.08 339	99.34 300	96.27 166	99.64 254	89.87 395	98.92 196	99.31 222

UWE-MVS		97.58 291	97.29 298	98.48 268	99.09 299	96.25 335	99.01 335	96.61 409	97.86 178	99.19 212	99.01 346	88.72 358	99.90 124	97.38 277	98.69 210	99.28 224

VDDNet		97.55 292	97.02 311	99.16 177	99.49 187	98.12 239	99.38 233	99.30 283	95.35 355	99.68 81	99.90 27	82.62 399	99.93 90	99.31 62	98.13 246	99.42 204

TESTMET0.1,1		97.55 292	97.27 302	98.40 284	98.93 324	96.53 324	98.67 375	97.61 399	96.96 278	98.64 303	99.28 314	88.63 364	99.45 275	97.30 281	99.38 156	99.21 231

pmmvs5		97.52 294	97.30 296	98.16 304	98.57 371	96.73 314	99.27 271	98.90 347	96.14 340	98.37 323	99.53 240	91.54 326	99.14 332	97.51 265	95.87 326	98.63 322

LF4IMVS		97.52 294	97.46 270	97.70 339	98.98 319	95.55 349	99.29 261	98.82 357	98.07 156	98.66 296	99.64 196	89.97 345	99.61 262	97.01 297	96.68 303	97.94 386

DTE-MVSNet		97.51 296	97.19 304	98.46 274	98.63 364	98.13 238	99.84 12	99.48 161	96.68 295	97.97 346	99.67 184	92.92 283	98.56 380	96.88 309	92.60 384	98.70 287

testing11		97.50 297	97.10 308	98.71 245	99.20 269	96.91 307	99.29 261	98.82 357	97.89 175	98.21 334	98.40 379	85.63 384	99.83 175	98.45 179	98.04 249	99.37 214

ETVMVS		97.50 297	96.90 315	99.29 160	99.23 262	98.78 190	99.32 251	98.90 347	97.52 223	98.56 312	98.09 393	84.72 391	99.69 240	97.86 228	97.88 255	99.39 210

hse-mvs2		97.50 297	97.14 305	98.59 253	99.49 187	97.05 294	99.28 266	99.22 301	98.94 58	99.66 90	99.42 273	94.93 211	99.65 251	99.48 45	83.80 407	99.08 241

SixPastTwentyTwo		97.50 297	97.33 293	98.03 312	98.65 362	96.23 336	99.77 34	98.68 376	97.14 259	97.90 347	99.93 9	90.45 338	99.18 329	97.00 298	96.43 310	98.67 303

JIA-IIPM		97.50 297	97.02 311	98.93 206	98.73 353	97.80 258	99.30 256	98.97 334	91.73 394	98.91 260	94.86 409	95.10 208	99.71 229	97.58 256	97.98 250	99.28 224

ppachtmachnet_test		97.49 302	97.45 271	97.61 343	98.62 365	95.24 359	98.80 364	99.46 190	96.11 342	98.22 333	99.62 207	96.45 160	98.97 363	93.77 370	95.97 325	98.61 333

test-mter		97.49 302	97.13 307	98.55 262	98.79 341	97.10 288	98.67 375	97.75 396	96.65 298	98.61 308	98.85 360	88.23 368	99.45 275	97.25 283	99.38 156	99.10 236

testing91		97.44 304	97.02 311	98.71 245	99.18 275	96.89 309	99.19 294	99.04 326	97.78 191	98.31 326	98.29 384	85.41 386	99.85 155	98.01 217	97.95 251	99.39 210

tpm2		97.44 304	97.34 291	97.74 337	99.15 289	94.36 376	99.45 196	98.94 337	93.45 384	98.90 262	99.44 269	91.35 329	99.59 264	97.31 280	98.07 248	99.29 223

tpm cat1		97.39 306	97.36 286	97.50 347	99.17 283	93.73 382	99.43 206	99.31 279	91.27 395	98.71 287	99.08 337	94.31 249	99.77 204	96.41 326	98.50 222	99.00 252

testing99		97.36 307	96.94 314	98.63 250	99.18 275	96.70 315	99.30 256	98.93 338	97.71 198	98.23 331	98.26 385	84.92 389	99.84 162	98.04 216	97.85 258	99.35 216

USDC		97.34 308	97.20 303	97.75 336	99.07 303	95.20 360	98.51 388	99.04 326	97.99 167	98.31 326	99.86 52	89.02 354	99.55 268	95.67 342	97.36 292	98.49 344

UniMVSNet_ETH3D		97.32 309	96.81 317	98.87 223	99.40 217	97.46 272	99.51 164	99.53 100	95.86 350	98.54 314	99.77 135	82.44 400	99.66 246	98.68 145	97.52 276	99.50 184

testing3		97.28 310	96.76 319	98.82 232	99.37 225	98.07 241	99.45 196	99.36 246	97.56 216	97.89 348	98.95 353	83.70 395	98.82 372	96.03 331	98.56 218	99.58 158

MVS		97.28 310	96.55 323	99.48 124	98.78 344	98.95 166	99.27 271	99.39 229	83.53 409	98.08 339	99.54 236	96.97 140	99.87 146	94.23 366	99.16 173	99.63 143

test_fmvs2		97.25 312	97.30 296	97.09 357	99.43 205	93.31 388	99.73 50	98.87 352	98.83 68	99.28 187	99.80 108	84.45 392	99.66 246	97.88 225	97.45 284	98.30 361

DSMNet-mixed		97.25 312	97.35 288	96.95 361	97.84 385	93.61 386	99.57 122	96.63 408	96.13 341	98.87 268	98.61 373	94.59 235	97.70 398	95.08 354	98.86 200	99.55 164

MS-PatchMatch		97.24 314	97.32 294	96.99 358	98.45 376	93.51 387	98.82 362	99.32 275	97.41 237	98.13 338	99.30 310	88.99 355	99.56 266	95.68 341	99.80 103	97.90 389

testing222		97.16 315	96.50 324	99.16 177	99.16 285	98.47 222	99.27 271	98.66 377	97.71 198	98.23 331	98.15 388	82.28 402	99.84 162	97.36 278	97.66 264	99.18 232

TransMVSNet (Re)		97.15 316	96.58 322	98.86 226	99.12 291	98.85 180	99.49 182	98.91 345	95.48 354	97.16 367	99.80 108	93.38 274	99.11 340	94.16 368	91.73 386	98.62 324

TinyColmap		97.12 317	96.89 316	97.83 331	99.07 303	95.52 352	98.57 384	98.74 367	97.58 213	97.81 352	99.79 120	88.16 369	99.56 266	95.10 353	97.21 296	98.39 357

K. test v3		97.10 318	96.79 318	98.01 315	98.72 355	96.33 331	99.87 8	97.05 402	97.59 211	96.16 381	99.80 108	88.71 359	99.04 347	96.69 316	96.55 308	98.65 313

Syy-MVS		97.09 319	97.14 305	96.95 361	99.00 313	92.73 392	99.29 261	99.39 229	97.06 270	97.41 358	98.15 388	93.92 263	98.68 378	91.71 388	98.34 227	99.45 200

PatchT		97.03 320	96.44 326	98.79 238	98.99 316	98.34 228	99.16 298	99.07 322	92.13 392	99.52 132	97.31 402	94.54 240	98.98 356	88.54 400	98.73 209	99.03 249

mmtdpeth		96.95 321	96.71 320	97.67 340	99.33 234	94.90 367	99.89 2	99.28 289	98.15 140	99.72 73	98.57 374	86.56 379	99.90 124	99.82 16	89.02 398	98.20 368

myMVS_eth3d		96.89 322	96.37 327	98.43 281	99.00 313	97.16 285	99.29 261	99.39 229	97.06 270	97.41 358	98.15 388	83.46 396	98.68 378	95.27 351	98.34 227	99.45 200

AUN-MVS		96.88 323	96.31 329	98.59 253	99.48 194	97.04 297	99.27 271	99.22 301	97.44 233	98.51 315	99.41 277	91.97 312	99.66 246	97.71 247	83.83 406	99.07 246

FMVSNet1		96.84 324	96.36 328	98.29 294	99.32 241	97.26 281	99.43 206	99.48 161	95.11 359	98.55 313	99.32 307	83.95 394	98.98 356	95.81 336	96.26 315	98.62 324

test2506		96.81 325	96.65 321	97.29 352	99.74 83	92.21 395	99.60 100	85.06 426	99.13 24	99.77 57	99.93 9	87.82 374	99.85 155	99.38 52	99.38 156	99.80 73

RPMNet		96.72 326	95.90 339	99.19 174	99.18 275	98.49 218	99.22 290	99.52 105	88.72 405	99.56 123	97.38 399	94.08 257	99.95 62	86.87 407	98.58 215	99.14 233

mvs5depth		96.66 327	96.22 331	97.97 319	97.00 401	96.28 333	98.66 378	99.03 328	96.61 303	96.93 373	99.79 120	87.20 377	99.47 272	96.65 320	94.13 363	98.16 370

test_0402		96.64 328	96.24 330	97.85 328	98.85 337	96.43 328	99.44 202	99.26 293	93.52 381	96.98 371	99.52 243	88.52 365	99.20 328	92.58 386	97.50 279	97.93 387

X-MVStestdata		96.55 329	95.45 348	99.87 14	99.85 26	99.83 19	99.69 60	99.68 20	98.98 52	99.37 168	64.01 422	98.81 47	99.94 72	98.79 131	99.86 68	99.84 42

pmmvs6		96.53 330	96.09 335	97.82 333	98.69 359	95.47 353	99.37 235	99.47 181	93.46 383	97.41 358	99.78 127	87.06 378	99.33 302	96.92 307	92.70 382	98.65 313

ET-MVSNet_ETH3D		96.49 331	95.64 345	99.05 189	99.53 168	98.82 185	98.84 360	97.51 400	97.63 208	84.77 409	99.21 326	92.09 310	98.91 368	98.98 97	92.21 385	99.41 207

UnsupCasMVSNet_eth		96.44 332	96.12 333	97.40 349	98.65 362	95.65 346	99.36 240	99.51 119	97.13 260	96.04 383	98.99 348	88.40 366	98.17 387	96.71 314	90.27 394	98.40 356

FMVSNet5		96.43 333	96.19 332	97.15 353	99.11 293	95.89 343	99.32 251	99.52 105	94.47 374	98.34 325	99.07 338	87.54 375	97.07 403	92.61 385	95.72 331	98.47 347

new_pmnet		96.38 334	96.03 336	97.41 348	98.13 382	95.16 363	99.05 322	99.20 305	93.94 376	97.39 361	98.79 366	91.61 325	99.04 347	90.43 393	95.77 328	98.05 377

Anonymous20231206		96.22 335	96.03 336	96.79 366	97.31 395	94.14 378	99.63 88	99.08 319	96.17 336	97.04 370	99.06 340	93.94 261	97.76 397	86.96 406	95.06 346	98.47 347

IB-MVS	95.67 18	96.22 335	95.44 349	98.57 257	99.21 267	96.70 315	98.65 379	97.74 398	96.71 293	97.27 363	98.54 375	86.03 381	99.92 101	98.47 177	86.30 403	99.10 236
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
Anonymous20240521		96.20 337	95.89 340	97.13 355	97.72 389	94.96 366	99.79 31	99.29 287	93.01 386	97.20 366	99.03 343	89.69 349	98.36 384	91.16 391	96.13 317	98.07 375

gg-mvs-nofinetune		96.17 338	95.32 350	98.73 242	98.79 341	98.14 237	99.38 233	94.09 417	91.07 398	98.07 342	91.04 415	89.62 351	99.35 299	96.75 312	99.09 183	98.68 296

test20.03		96.12 339	95.96 338	96.63 367	97.44 391	95.45 354	99.51 164	99.38 237	96.55 309	96.16 381	99.25 320	93.76 270	96.17 408	87.35 405	94.22 361	98.27 363

PVSNet_0	94.43 19	96.09 340	95.47 347	97.94 322	99.31 242	94.34 377	97.81 406	99.70 15	97.12 262	97.46 357	98.75 368	89.71 348	99.79 197	97.69 250	81.69 409	99.68 122

MVStest1		96.08 341	95.48 346	97.89 326	98.93 324	96.70 315	99.56 128	99.35 253	92.69 390	91.81 404	99.46 266	89.90 346	98.96 365	95.00 356	92.61 383	98.00 382

EG-PatchMatch MVS		95.97 342	95.69 343	96.81 365	97.78 386	92.79 391	99.16 298	98.93 338	96.16 337	94.08 394	99.22 323	82.72 398	99.47 272	95.67 342	97.50 279	98.17 369

APD_test1		95.87 343	96.49 325	94.00 378	99.53 168	84.01 407	99.54 146	99.32 275	95.91 349	97.99 344	99.85 57	85.49 385	99.88 141	91.96 387	98.84 202	98.12 372

Patchmatch-RL test		95.84 344	95.81 342	95.95 373	95.61 406	90.57 399	98.24 399	98.39 384	95.10 361	95.20 388	98.67 370	94.78 221	97.77 396	96.28 328	90.02 395	99.51 180

test_vis1_rt		95.81 345	95.65 344	96.32 371	99.67 114	91.35 398	99.49 182	96.74 407	98.25 126	95.24 386	98.10 392	74.96 407	99.90 124	99.53 36	98.85 201	97.70 392

MVS-HIRNet		95.75 346	95.16 351	97.51 346	99.30 243	93.69 384	98.88 356	95.78 411	85.09 408	98.78 281	92.65 411	91.29 330	99.37 292	94.85 358	99.85 75	99.46 197

MIMVSNet1		95.51 347	95.04 352	96.92 363	97.38 392	95.60 347	99.52 155	99.50 139	93.65 380	96.97 372	99.17 328	85.28 388	96.56 407	88.36 401	95.55 336	98.60 336

MDA-MVSNet_test_wron		95.45 348	94.60 355	98.01 315	98.16 381	97.21 284	99.11 313	99.24 298	93.49 382	80.73 415	98.98 350	93.02 280	98.18 386	94.22 367	94.45 357	98.64 315

TDRefinement		95.42 349	94.57 356	97.97 319	89.83 419	96.11 340	99.48 186	98.75 364	96.74 291	96.68 375	99.88 39	88.65 362	99.71 229	98.37 185	82.74 408	98.09 374

YYNet1		95.36 350	94.51 357	97.92 323	97.89 384	97.10 288	99.10 315	99.23 299	93.26 385	80.77 414	99.04 342	92.81 286	98.02 390	94.30 363	94.18 362	98.64 315

pmmvs-eth3d		95.34 351	94.73 354	97.15 353	95.53 408	95.94 342	99.35 245	99.10 316	95.13 357	93.55 396	97.54 397	88.15 370	97.91 393	94.58 360	89.69 397	97.61 393

dmvs_testset		95.02 352	96.12 333	91.72 387	99.10 296	80.43 415	99.58 115	97.87 395	97.47 226	95.22 387	98.82 362	93.99 259	95.18 412	88.09 402	94.91 351	99.56 163

KD-MVS_self_test		95.00 353	94.34 358	96.96 360	97.07 400	95.39 357	99.56 128	99.44 209	95.11 359	97.13 368	97.32 401	91.86 315	97.27 402	90.35 394	81.23 410	98.23 367

MDA-MVSNet-bldmvs		94.96 354	93.98 361	97.92 323	98.24 380	97.27 279	99.15 301	99.33 265	93.80 378	80.09 416	99.03 343	88.31 367	97.86 395	93.49 374	94.36 359	98.62 324

N_pmnet		94.95 355	95.83 341	92.31 385	98.47 375	79.33 417	99.12 307	92.81 423	93.87 377	97.68 354	99.13 333	93.87 265	99.01 353	91.38 390	96.19 316	98.59 337

KD-MVS_2432*1600		94.62 356	93.72 364	97.31 350	97.19 398	95.82 344	98.34 394	99.20 305	95.00 363	97.57 355	98.35 381	87.95 371	98.10 388	92.87 382	77.00 413	98.01 379

miper_refine_blended		94.62 356	93.72 364	97.31 350	97.19 398	95.82 344	98.34 394	99.20 305	95.00 363	97.57 355	98.35 381	87.95 371	98.10 388	92.87 382	77.00 413	98.01 379

CL-MVSNet_self_test		94.49 358	93.97 362	96.08 372	96.16 403	93.67 385	98.33 396	99.38 237	95.13 357	97.33 362	98.15 388	92.69 294	96.57 406	88.67 399	79.87 411	97.99 383

new-patchmatchnet		94.48 359	94.08 360	95.67 374	95.08 411	92.41 393	99.18 296	99.28 289	94.55 373	93.49 397	97.37 400	87.86 373	97.01 404	91.57 389	88.36 399	97.61 393

OpenMVS_ROB	92.34 20	94.38 360	93.70 366	96.41 370	97.38 392	93.17 389	99.06 320	98.75 364	86.58 406	94.84 392	98.26 385	81.53 403	99.32 304	89.01 398	97.87 256	96.76 400

CMPMVS	69.68 23	94.13 361	94.90 353	91.84 386	97.24 396	80.01 416	98.52 387	99.48 161	89.01 403	91.99 403	99.67 184	85.67 383	99.13 335	95.44 346	97.03 301	96.39 404
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 362	93.25 368	96.60 368	94.76 413	94.49 373	98.92 352	98.18 391	89.66 399	96.48 377	98.06 394	86.28 380	97.33 401	89.68 396	87.20 402	97.97 385

mvsany_test3		93.77 363	93.45 367	94.74 376	95.78 405	88.01 402	99.64 83	98.25 387	98.28 121	94.31 393	97.97 395	68.89 410	98.51 382	97.50 266	90.37 393	97.71 390

UnsupCasMVSNet_bld		93.53 364	92.51 370	96.58 369	97.38 392	93.82 380	98.24 399	99.48 161	91.10 397	93.10 398	96.66 404	74.89 408	98.37 383	94.03 369	87.71 401	97.56 395

dongtai		93.26 365	92.93 369	94.25 377	99.39 220	85.68 405	97.68 408	93.27 419	92.87 388	96.85 374	99.39 285	82.33 401	97.48 400	76.78 413	97.80 259	99.58 158

WB-MVS		93.10 366	94.10 359	90.12 392	95.51 410	81.88 412	99.73 50	99.27 292	95.05 362	93.09 399	98.91 359	94.70 230	91.89 416	76.62 414	94.02 367	96.58 402

PM-MVS		92.96 367	92.23 371	95.14 375	95.61 406	89.98 401	99.37 235	98.21 389	94.80 368	95.04 391	97.69 396	65.06 411	97.90 394	94.30 363	89.98 396	97.54 396

SSC-MVS		92.73 368	93.73 363	89.72 393	95.02 412	81.38 413	99.76 37	99.23 299	94.87 366	92.80 400	98.93 355	94.71 229	91.37 417	74.49 416	93.80 369	96.42 403

test_fmvs3		92.10 369	91.77 372	93.08 383	96.19 402	86.25 403	99.82 16	98.62 379	96.65 298	95.19 389	96.90 403	55.05 418	95.93 410	96.63 321	90.92 392	97.06 399

test_f		91.90 370	91.26 374	93.84 379	95.52 409	85.92 404	99.69 60	98.53 383	95.31 356	93.87 395	96.37 406	55.33 417	98.27 385	95.70 339	90.98 391	97.32 398

test_method		91.10 371	91.36 373	90.31 391	95.85 404	73.72 424	94.89 412	99.25 295	68.39 415	95.82 384	99.02 345	80.50 405	98.95 366	93.64 372	94.89 352	98.25 365

Gipuma		90.99 372	90.15 377	93.51 380	98.73 353	90.12 400	93.98 413	99.45 201	79.32 411	92.28 401	94.91 408	69.61 409	97.98 392	87.42 404	95.67 332	92.45 411
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 373	90.11 378	93.34 381	98.78 344	85.59 406	98.15 403	93.16 421	89.37 402	92.07 402	98.38 380	81.48 404	95.19 411	62.54 420	97.04 300	99.25 228

testf1		90.42 374	90.68 375	89.65 394	97.78 386	73.97 422	99.13 304	98.81 359	89.62 400	91.80 405	98.93 355	62.23 414	98.80 374	86.61 408	91.17 388	96.19 405

APD_test2		90.42 374	90.68 375	89.65 394	97.78 386	73.97 422	99.13 304	98.81 359	89.62 400	91.80 405	98.93 355	62.23 414	98.80 374	86.61 408	91.17 388	96.19 405

test_vis3_rt		87.04 376	85.81 379	90.73 390	93.99 414	81.96 411	99.76 37	90.23 425	92.81 389	81.35 413	91.56 413	40.06 422	99.07 344	94.27 365	88.23 400	91.15 413

PMMVS2		86.87 377	85.37 381	91.35 389	90.21 418	83.80 408	98.89 355	97.45 401	83.13 410	91.67 407	95.03 407	48.49 420	94.70 413	85.86 410	77.62 412	95.54 408

LCM-MVSNet		86.80 378	85.22 382	91.53 388	87.81 420	80.96 414	98.23 401	98.99 332	71.05 413	90.13 408	96.51 405	48.45 421	96.88 405	90.51 392	85.30 404	96.76 400

FPMVS		84.93 379	85.65 380	82.75 400	86.77 421	63.39 426	98.35 393	98.92 341	74.11 412	83.39 411	98.98 350	50.85 419	92.40 415	84.54 411	94.97 348	92.46 410

EGC-MVSNET		82.80 380	77.86 386	97.62 342	97.91 383	96.12 339	99.33 250	99.28 289	8.40 423	25.05 424	99.27 317	84.11 393	99.33 302	89.20 397	98.22 237	97.42 397

tmp_tt		82.80 380	81.52 383	86.66 396	66.61 426	68.44 425	92.79 415	97.92 393	68.96 414	80.04 417	99.85 57	85.77 382	96.15 409	97.86 228	43.89 419	95.39 409

E-PMN		80.61 382	79.88 384	82.81 399	90.75 417	76.38 420	97.69 407	95.76 412	66.44 417	83.52 410	92.25 412	62.54 413	87.16 419	68.53 418	61.40 416	84.89 417

EMVS		80.02 383	79.22 385	82.43 401	91.19 416	76.40 419	97.55 410	92.49 424	66.36 418	83.01 412	91.27 414	64.63 412	85.79 420	65.82 419	60.65 417	85.08 416

ANet_high		77.30 384	74.86 388	84.62 398	75.88 424	77.61 418	97.63 409	93.15 422	88.81 404	64.27 419	89.29 416	36.51 423	83.93 421	75.89 415	52.31 418	92.33 412

MVE	76.82 21	76.91 385	74.31 389	84.70 397	85.38 423	76.05 421	96.88 411	93.17 420	67.39 416	71.28 418	89.01 417	21.66 428	87.69 418	71.74 417	72.29 415	90.35 414
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 386	74.97 387	79.01 402	70.98 425	55.18 427	93.37 414	98.21 389	65.08 419	61.78 420	93.83 410	21.74 427	92.53 414	78.59 412	91.12 390	89.34 415
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		40.18 387	41.29 392	36.84 403	86.18 422	49.12 428	79.73 416	22.81 428	27.64 420	25.46 423	28.45 423	21.98 426	48.89 422	55.80 421	23.56 422	12.51 420

testmvs		39.17 388	43.78 390	25.37 405	36.04 428	16.84 430	98.36 392	26.56 427	20.06 421	38.51 422	67.32 418	29.64 425	15.30 424	37.59 422	39.90 420	43.98 419

test123		39.01 389	42.50 391	28.53 404	39.17 427	20.91 429	98.75 369	19.17 429	19.83 422	38.57 421	66.67 419	33.16 424	15.42 423	37.50 423	29.66 421	49.26 418

cdsmvs_eth3d_5k		24.64 390	32.85 393	0.00 406	0.00 429	0.00 431	0.00 417	99.51 119	0.00 424	0.00 425	99.56 228	96.58 153	0.00 425	0.00 424	0.00 423	0.00 421

ab-mvs-re		8.30 391	11.06 394	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	99.58 220	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

pcd_1.5k_mvsjas		8.27 392	11.03 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	99.01 18	0.00 425	0.00 424	0.00 423	0.00 421

test_blank		0.13 393	0.17 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	1.57 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

mmdepth		0.02 394	0.03 397	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

monomultidepth		0.02 394	0.03 397	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet_test		0.02 394	0.03 397	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

DCPMVS		0.02 394	0.03 397	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet-low-res		0.02 394	0.03 397	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet		0.02 394	0.03 397	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uncertanet		0.02 394	0.03 397	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

Regformer		0.02 394	0.03 397	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet		0.02 394	0.03 397	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.27 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

WAC-MVS						97.16 285								95.47 345

FOURS1					99.91 1	99.93 1	99.87 8	99.56 70	99.10 31	99.81 42

MSC_two_6792asdad				99.87 14	99.51 175	99.76 40		99.33 265					99.96 32	98.87 113	99.84 83	99.89 19

PC_three_1452									98.18 138	99.84 35	99.70 162	99.31 3	98.52 381	98.30 194	99.80 103	99.81 64

No_MVS				99.87 14	99.51 175	99.76 40		99.33 265					99.96 32	98.87 113	99.84 83	99.89 19

test_one_0601					99.81 46	99.88 8		99.49 149	98.97 55	99.65 97	99.81 95	99.09 14

eth-test2					0.00 429

eth-test					0.00 429

ZD-MVS					99.71 99	99.79 33		99.61 48	96.84 287	99.56 123	99.54 236	98.58 75	99.96 32	96.93 305	99.75 118

RE-MVS-def			99.34 42		99.76 66	99.82 25	99.63 88	99.52 105	98.38 110	99.76 62	99.82 81	98.75 58		98.61 155	99.81 99	99.77 85

IU-MVS					99.84 32	99.88 8		99.32 275	98.30 120	99.84 35				98.86 118	99.85 75	99.89 19

OPU-MVS				99.64 82	99.56 160	99.72 45	99.60 100				99.70 162	99.27 5	99.42 285	98.24 197	99.80 103	99.79 77

test_241102_TWO								99.48 161	99.08 37	99.88 24	99.81 95	98.94 32	99.96 32	98.91 107	99.84 83	99.88 25

test_241102_ONE					99.84 32	99.90 2		99.48 161	99.07 39	99.91 17	99.74 147	99.20 7	99.76 208

9.14			99.10 81		99.72 94		99.40 224	99.51 119	97.53 221	99.64 102	99.78 127	98.84 44	99.91 112	97.63 252	99.82 96

save fliter					99.76 66	99.59 73	99.14 303	99.40 226	99.00 47

test_0728_THIRD									98.99 49	99.81 42	99.80 108	99.09 14	99.96 32	98.85 120	99.90 43	99.88 25

test_0728_SECOND				99.91 2	99.84 32	99.89 4	99.57 122	99.51 119					99.96 32	98.93 104	99.86 68	99.88 25

test0726					99.85 26	99.89 4	99.62 93	99.50 139	99.10 31	99.86 33	99.82 81	98.94 32

GSMVS																99.52 173

test_part2					99.81 46	99.83 19				99.77 57

sam_mvs1												94.86 216				99.52 173

sam_mvs												94.72 228

ambc				93.06 384	92.68 415	82.36 409	98.47 389	98.73 373		95.09 390	97.41 398	55.55 416	99.10 342	96.42 325	91.32 387	97.71 390

MTGPA								99.47 181

test_post1							99.23 286				65.14 421	94.18 254	99.71 229	97.58 256

test_post											65.99 420	94.65 234	99.73 219

patchmatchnet-post											98.70 369	94.79 220	99.74 213

GG-mvs-BLEND				98.45 276	98.55 372	98.16 235	99.43 206	93.68 418		97.23 364	98.46 376	89.30 352	99.22 321	95.43 347	98.22 237	97.98 384

MTMP							99.54 146	98.88 350

gm-plane-assit					98.54 373	92.96 390			94.65 371		99.15 331		99.64 254	97.56 261

test9_res														97.49 267	99.72 124	99.75 91

TEST9					99.67 114	99.65 60	99.05 322	99.41 220	96.22 332	98.95 255	99.49 253	98.77 54	99.91 112

test_8					99.67 114	99.61 70	99.03 327	99.41 220	96.28 326	98.93 258	99.48 259	98.76 55	99.91 112

agg_prior2														97.21 285	99.73 123	99.75 91

agg_prior					99.67 114	99.62 68		99.40 226		98.87 268			99.91 112

TestCases				99.31 152	99.86 20	98.48 220		99.61 48	97.85 181	99.36 171	99.85 57	95.95 176	99.85 155	96.66 318	99.83 92	99.59 154

test_prior4						99.56 79	98.99 338

test_prior2							98.96 345		98.34 116	99.01 244	99.52 243	98.68 67		97.96 220	99.74 121

test_prior				99.68 71	99.67 114	99.48 94		99.56 70					99.83 175			99.74 95

旧先验2							98.96 345		96.70 294	99.47 140			99.94 72	98.19 200

新几何2							99.01 335

新几何1				99.75 61	99.75 76	99.59 73		99.54 87	96.76 290	99.29 186	99.64 196	98.43 86	99.94 72	96.92 307	99.66 134	99.72 106

旧先验1					99.74 83	99.59 73		99.54 87			99.69 172	98.47 83			99.68 132	99.73 100

无先验							98.99 338	99.51 119	96.89 284				99.93 90	97.53 264		99.72 106

原ACMM2							98.95 348

原ACMM1				99.65 77	99.73 90	99.33 109		99.47 181	97.46 227	99.12 223	99.66 189	98.67 69	99.91 112	97.70 249	99.69 129	99.71 115

test222					99.75 76	99.49 92	98.91 354	99.49 149	96.42 320	99.34 177	99.65 190	98.28 96			99.69 129	99.72 106

testdata2													99.95 62	96.67 317

segment_acmp												98.96 25

testdata				99.54 102	99.75 76	98.95 166		99.51 119	97.07 268	99.43 150	99.70 162	98.87 40	99.94 72	97.76 240	99.64 137	99.72 106

testdata1							98.85 359		98.32 119

test12				99.75 61	99.64 132	99.61 70		99.29 287		99.21 206		98.38 91	99.89 136		99.74 121	99.74 95

plane_prior7					99.29 247	97.03 298

plane_prior6					99.27 252	96.98 302						92.71 292

plane_prior5								99.47 181					99.69 240	97.78 236	97.63 265	98.67 303

plane_prior4											99.61 211

plane_prior3						97.00 300			98.69 84	99.11 225

plane_prior2							99.39 228		98.97 55

plane_prior1					99.26 254

plane_prior						96.97 303	99.21 292		98.45 103						97.60 268

n2								0.00 430

nn								0.00 430

door-mid								98.05 392

lessismore_v0				97.79 335	98.69 359	95.44 356		94.75 415		95.71 385	99.87 48	88.69 360	99.32 304	95.89 334	94.93 350	98.62 324

LGP-MVS_train				98.49 266	99.33 234	97.05 294		99.55 78	97.46 227	99.24 198	99.83 72	92.58 297	99.72 223	98.09 207	97.51 277	98.68 296

test11								99.35 253

door								97.92 393

HQP5-MVS						96.83 310

HQP-NCC					99.19 272		98.98 341		98.24 127	98.66 296

ACMP_Plane					99.19 272		98.98 341		98.24 127	98.66 296

BP-MVS														97.19 289

HQP4-MVS										98.66 296			99.64 254			98.64 315

HQP3-MVS								99.39 229							97.58 270

HQP2-MVS												92.47 301

NP-MVS					99.23 262	96.92 306					99.40 281

MDTV_nov1_ep13_2view						95.18 362	99.35 245		96.84 287	99.58 119		95.19 207		97.82 233		99.46 197

MDTV_nov1_ep13			98.32 178		99.11 293	94.44 374	99.27 271	98.74 367	97.51 224	99.40 162	99.62 207	94.78 221	99.76 208	97.59 255	98.81 206

ACMMP++_ref															97.19 297

ACMMP++															97.43 288

Test By Simon												98.75 58

ITE_SJBPF				98.08 310	99.29 247	96.37 329		98.92 341	98.34 116	98.83 274	99.75 142	91.09 332	99.62 261	95.82 335	97.40 290	98.25 365

DeepMVS_CX				93.34 381	99.29 247	82.27 410		99.22 301	85.15 407	96.33 378	99.05 341	90.97 334	99.73 219	93.57 373	97.77 261	98.01 379

High-resolution multi-view benchmark