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.

TestfortrainingZip a		99.73 1	99.67 1	99.92 1	99.88 13	99.91 2	99.69 62	99.87 6	99.34 25	99.90 33	99.83 97	99.30 4	99.95 75	99.32 83	99.89 67	99.90 25

fmvsm_l_conf0.5_n_a		99.71 2	99.67 1	99.85 41	99.86 23	99.61 82	99.56 143	99.63 44	99.48 3	99.98 12	99.83 97	98.75 59	99.99 4	99.97 2	99.96 16	99.94 17

fmvsm_l_conf0.5_n		99.71 2	99.67 1	99.85 41	99.84 36	99.63 79	99.56 143	99.63 44	99.47 4	99.98 12	99.82 108	98.75 59	99.99 4	99.97 2	99.97 8	99.94 17

test_fmvsmconf_n		99.70 4	99.64 5	99.87 21	99.80 60	99.66 68	99.48 216	99.64 40	99.45 11	99.92 29	99.92 17	98.62 75	99.99 4	99.96 13	99.99 1	99.96 7

test_fmvsm_n_1920		99.69 5	99.66 4	99.78 68	99.84 36	99.44 113	99.58 128	99.69 20	99.43 16	99.98 12	99.91 25	98.62 75	100.00 1	99.97 2	99.95 22	99.90 25

APDe-MVS		99.66 6	99.57 9	99.92 1	99.77 75	99.89 6	99.75 42	99.56 88	99.02 59	99.88 40	99.85 77	99.18 11	99.96 40	99.22 99	99.92 38	99.90 25
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsmvis_n_1920		99.65 7	99.61 7	99.77 71	99.38 267	99.37 120	99.58 128	99.62 49	99.41 20	99.87 46	99.92 17	98.81 48	100.00 1	99.97 2	99.93 32	99.94 17

reproduce_model		99.63 8	99.54 12	99.90 8	99.78 67	99.88 10	99.56 143	99.55 97	99.15 35	99.90 33	99.90 32	99.00 23	99.97 28	99.11 114	99.91 45	99.86 42

fmvsm_l_conf0.5_n_3		99.61 9	99.51 17	99.92 1	99.84 36	99.82 28	99.54 163	99.66 30	99.46 7	99.98 12	99.89 40	97.27 132	99.99 4	99.97 2	99.95 22	99.95 11

reproduce-ours		99.61 9	99.52 13	99.90 8	99.76 79	99.88 10	99.52 174	99.54 106	99.13 38	99.89 37	99.89 40	98.96 26	99.96 40	99.04 123	99.90 56	99.85 46

our_new_method		99.61 9	99.52 13	99.90 8	99.76 79	99.88 10	99.52 174	99.54 106	99.13 38	99.89 37	99.89 40	98.96 26	99.96 40	99.04 123	99.90 56	99.85 46

SED-MVS		99.61 9	99.52 13	99.88 15	99.84 36	99.90 3	99.60 111	99.48 193	99.08 53	99.91 30	99.81 123	99.20 8	99.96 40	98.91 144	99.85 91	99.79 90

lecture		99.60 13	99.50 18	99.89 11	99.89 8	99.90 3	99.75 42	99.59 71	99.06 58	99.88 40	99.85 77	98.41 92	99.96 40	99.28 91	99.84 99	99.83 63

DVP-MVS++		99.59 14	99.50 18	99.88 15	99.51 218	99.88 10	99.87 8	99.51 146	98.99 66	99.88 40	99.81 123	99.27 6	99.96 40	98.85 157	99.80 122	99.81 77

fmvsm_l_conf0.5_n_9		99.58 15	99.47 23	99.92 1	99.85 29	99.82 28	99.47 226	99.63 44	99.45 11	99.98 12	99.89 40	97.02 146	99.99 4	99.98 1	99.96 16	99.95 11

TSAR-MVS + MP.		99.58 15	99.50 18	99.81 58	99.91 1	99.66 68	99.63 99	99.39 272	98.91 79	99.78 78	99.85 77	99.36 2	99.94 89	98.84 160	99.88 73	99.82 70
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 15	99.57 9	99.64 98	99.78 67	99.14 157	99.60 111	99.45 237	99.01 61	99.90 33	99.83 97	98.98 25	99.93 107	99.59 44	99.95 22	99.86 42

EI-MVSNet-Vis-set		99.58 15	99.56 11	99.64 98	99.78 67	99.15 156	99.61 110	99.45 237	99.01 61	99.89 37	99.82 108	99.01 19	99.92 120	99.56 48	99.95 22	99.85 46

DVP-MVS		99.57 19	99.47 23	99.88 15	99.85 29	99.89 6	99.57 136	99.37 288	99.10 45	99.81 66	99.80 141	98.94 33	99.96 40	98.93 141	99.86 84	99.81 77
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
MED-MVS		99.56 20	99.46 27	99.86 32	99.80 60	99.81 33	99.37 277	99.70 16	99.18 32	99.83 61	99.83 97	98.74 64	99.93 107	98.83 163	99.89 67	99.83 63

fmvsm_s_conf0.5_n_a		99.56 20	99.47 23	99.85 41	99.83 45	99.64 78	99.52 174	99.65 37	99.10 45	99.98 12	99.92 17	97.35 128	99.96 40	99.94 20	99.92 38	99.95 11

test_fmvsmconf0.1_n		99.55 22	99.45 29	99.86 32	99.44 249	99.65 72	99.50 193	99.61 58	99.45 11	99.87 46	99.92 17	97.31 129	99.97 28	99.95 15	99.99 1	99.97 4

fmvsm_s_conf0.5_n_8		99.54 23	99.42 31	99.89 11	99.83 45	99.74 52	99.51 183	99.62 49	99.46 7	99.99 2	99.90 32	96.60 169	99.98 19	99.95 15	99.95 22	99.96 7

fmvsm_s_conf0.5_n_6		99.54 23	99.44 30	99.85 41	99.51 218	99.67 65	99.50 193	99.64 40	99.43 16	99.98 12	99.78 165	97.26 134	99.95 75	99.95 15	99.93 32	99.92 23

SteuartSystems-ACMMP		99.54 23	99.42 31	99.87 21	99.82 50	99.81 33	99.59 118	99.51 146	98.62 109	99.79 73	99.83 97	99.28 5	99.97 28	98.48 212	99.90 56	99.84 53
Skip Steuart: Steuart Systems R&D Blog.
XVS		99.53 26	99.42 31	99.87 21	99.85 29	99.83 22	99.69 62	99.68 22	98.98 69	99.37 205	99.74 188	98.81 48	99.94 89	98.79 169	99.86 84	99.84 53

MTAPA		99.52 27	99.39 39	99.89 11	99.90 4	99.86 18	99.66 80	99.47 215	98.79 92	99.68 108	99.81 123	98.43 88	99.97 28	98.88 147	99.90 56	99.83 63

fmvsm_s_conf0.5_n		99.51 28	99.40 37	99.85 41	99.84 36	99.65 72	99.51 183	99.67 25	99.13 38	99.98 12	99.92 17	96.60 169	99.96 40	99.95 15	99.96 16	99.95 11

HPM-MVS_fast		99.51 28	99.40 37	99.85 41	99.91 1	99.79 39	99.76 37	99.56 88	97.72 245	99.76 88	99.75 183	99.13 13	99.92 120	99.07 120	99.92 38	99.85 46

mvsany_test1		99.50 30	99.46 27	99.62 105	99.61 178	99.09 162	98.94 404	99.48 193	99.10 45	99.96 26	99.91 25	98.85 43	99.96 40	99.72 31	99.58 166	99.82 70

CS-MVS		99.50 30	99.48 21	99.54 122	99.76 79	99.42 115	99.90 1	99.55 97	98.56 115	99.78 78	99.70 205	98.65 73	99.79 234	99.65 40	99.78 131	99.41 253

SPE-MVS-test		99.49 32	99.48 21	99.54 122	99.78 67	99.30 135	99.89 2	99.58 76	98.56 115	99.73 94	99.69 216	98.55 80	99.82 216	99.69 34	99.85 91	99.48 232

HFP-MVS		99.49 32	99.37 43	99.86 32	99.87 18	99.80 36	99.66 80	99.67 25	98.15 172	99.68 108	99.69 216	99.06 17	99.96 40	98.69 181	99.87 76	99.84 53

ACMMPR		99.49 32	99.36 45	99.86 32	99.87 18	99.79 39	99.66 80	99.67 25	98.15 172	99.67 114	99.69 216	98.95 31	99.96 40	98.69 181	99.87 76	99.84 53

DeepC-MVS_fast	98.69 1	99.49 32	99.39 39	99.77 71	99.63 160	99.59 85	99.36 283	99.46 226	99.07 55	99.79 73	99.82 108	98.85 43	99.92 120	98.68 183	99.87 76	99.82 70
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 36	99.35 47	99.87 21	99.88 13	99.80 36	99.65 86	99.66 30	98.13 179	99.66 119	99.68 224	98.96 26	99.96 40	98.62 190	99.87 76	99.84 53

APD-MVS_3200maxsize		99.48 36	99.35 47	99.85 41	99.76 79	99.83 22	99.63 99	99.54 106	98.36 138	99.79 73	99.82 108	98.86 42	99.95 75	98.62 190	99.81 117	99.78 96

DELS-MVS		99.48 36	99.42 31	99.65 92	99.72 108	99.40 118	99.05 376	99.66 30	99.14 37	99.57 155	99.80 141	98.46 86	99.94 89	99.57 47	99.84 99	99.60 184
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 39	99.33 51	99.87 21	99.87 18	99.81 33	99.64 93	99.67 25	98.08 191	99.55 162	99.64 243	98.91 38	99.96 40	98.72 176	99.90 56	99.82 70

ACMMP_NAP		99.47 39	99.34 49	99.88 15	99.87 18	99.86 18	99.47 226	99.48 193	98.05 198	99.76 88	99.86 70	98.82 47	99.93 107	98.82 168	99.91 45	99.84 53

MVSMamba_PlusPlus		99.46 41	99.41 36	99.64 98	99.68 129	99.50 105	99.75 42	99.50 169	98.27 149	99.87 46	99.92 17	98.09 107	99.94 89	99.65 40	99.95 22	99.47 238

balanced_conf03		99.46 41	99.39 39	99.67 87	99.55 201	99.58 90	99.74 47	99.51 146	98.42 131	99.87 46	99.84 92	98.05 110	99.91 132	99.58 46	99.94 30	99.52 215

DPE-MVS		99.46 41	99.32 53	99.91 6	99.78 67	99.88 10	99.36 283	99.51 146	98.73 99	99.88 40	99.84 92	98.72 66	99.96 40	98.16 245	99.87 76	99.88 35
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSLP-MVS++		99.46 41	99.47 23	99.44 163	99.60 184	99.16 152	99.41 258	99.71 14	98.98 69	99.45 178	99.78 165	99.19 10	99.54 312	99.28 91	99.84 99	99.63 176

SR-MVS-dyc-post		99.45 45	99.31 59	99.85 41	99.76 79	99.82 28	99.63 99	99.52 127	98.38 134	99.76 88	99.82 108	98.53 81	99.95 75	98.61 193	99.81 117	99.77 98

PGM-MVS		99.45 45	99.31 59	99.86 32	99.87 18	99.78 45	99.58 128	99.65 37	97.84 229	99.71 102	99.80 141	99.12 14	99.97 28	98.33 230	99.87 76	99.83 63

CP-MVS		99.45 45	99.32 53	99.85 41	99.83 45	99.75 49	99.69 62	99.52 127	98.07 192	99.53 165	99.63 249	98.93 37	99.97 28	98.74 173	99.91 45	99.83 63

ACMMP		99.45 45	99.32 53	99.82 55	99.89 8	99.67 65	99.62 104	99.69 20	98.12 181	99.63 136	99.84 92	98.73 65	99.96 40	98.55 208	99.83 110	99.81 77
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 49	99.30 61	99.85 41	99.73 104	99.83 22	99.56 143	99.47 215	97.45 279	99.78 78	99.82 108	99.18 11	99.91 132	98.79 169	99.89 67	99.81 77
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 49	99.30 61	99.86 32	99.88 13	99.79 39	99.69 62	99.48 193	98.12 181	99.50 170	99.75 183	98.78 52	99.97 28	98.57 202	99.89 67	99.83 63

EC-MVSNet		99.44 49	99.39 39	99.58 113	99.56 197	99.49 106	99.88 4	99.58 76	98.38 134	99.73 94	99.69 216	98.20 102	99.70 275	99.64 42	99.82 114	99.54 208

SR-MVS		99.43 52	99.29 65	99.86 32	99.75 89	99.83 22	99.59 118	99.62 49	98.21 165	99.73 94	99.79 158	98.68 69	99.96 40	98.44 218	99.77 134	99.79 90

MCST-MVS		99.43 52	99.30 61	99.82 55	99.79 65	99.74 52	99.29 307	99.40 269	98.79 92	99.52 167	99.62 254	98.91 38	99.90 145	98.64 187	99.75 139	99.82 70

MSP-MVS		99.42 54	99.27 72	99.88 15	99.89 8	99.80 36	99.67 73	99.50 169	98.70 103	99.77 82	99.49 301	98.21 101	99.95 75	98.46 216	99.77 134	99.88 35
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 54	99.29 65	99.80 62	99.62 168	99.55 93	99.50 193	99.70 16	98.79 92	99.77 82	99.96 1	97.45 123	99.96 40	98.92 143	99.90 56	99.89 29

HPM-MVS		99.42 54	99.28 68	99.83 54	99.90 4	99.72 54	99.81 20	99.54 106	97.59 260	99.68 108	99.63 249	98.91 38	99.94 89	98.58 199	99.91 45	99.84 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CNVR-MVS		99.42 54	99.30 61	99.78 68	99.62 168	99.71 56	99.26 326	99.52 127	98.82 86	99.39 201	99.71 201	98.96 26	99.85 184	98.59 198	99.80 122	99.77 98

fmvsm_s_conf0.5_n_10		99.41 58	99.24 77	99.92 1	99.83 45	99.84 20	99.53 172	99.56 88	99.45 11	99.99 2	99.92 17	94.92 249	99.99 4	99.97 2	99.97 8	99.95 11

fmvsm_s_conf0.5_n_9		99.41 58	99.28 68	99.81 58	99.84 36	99.52 102	99.48 216	99.62 49	99.46 7	99.99 2	99.92 17	95.24 236	99.96 40	99.97 2	99.97 8	99.96 7

SD-MVS		99.41 58	99.52 13	99.05 226	99.74 97	99.68 61	99.46 230	99.52 127	99.11 44	99.88 40	99.91 25	99.43 1	97.70 450	98.72 176	99.93 32	99.77 98
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 58	99.33 51	99.65 92	99.77 75	99.51 104	98.94 404	99.85 7	98.82 86	99.65 128	99.74 188	98.51 83	99.80 228	98.83 163	99.89 67	99.64 171

MVS_111021_HR		99.41 58	99.32 53	99.66 88	99.72 108	99.47 110	98.95 402	99.85 7	98.82 86	99.54 163	99.73 194	98.51 83	99.74 252	98.91 144	99.88 73	99.77 98

MM		99.40 63	99.28 68	99.74 77	99.67 131	99.31 132	99.52 174	98.87 399	99.55 1	99.74 92	99.80 141	96.47 176	99.98 19	99.97 2	99.97 8	99.94 17

GST-MVS		99.40 63	99.24 77	99.85 41	99.86 23	99.79 39	99.60 111	99.67 25	97.97 213	99.63 136	99.68 224	98.52 82	99.95 75	98.38 223	99.86 84	99.81 77

HPM-MVS++		99.39 65	99.23 81	99.87 21	99.75 89	99.84 20	99.43 246	99.51 146	98.68 106	99.27 235	99.53 287	98.64 74	99.96 40	98.44 218	99.80 122	99.79 90

SF-MVS		99.38 66	99.24 77	99.79 65	99.79 65	99.68 61	99.57 136	99.54 106	97.82 235	99.71 102	99.80 141	98.95 31	99.93 107	98.19 241	99.84 99	99.74 111

fmvsm_s_conf0.5_n_5		99.37 67	99.21 83	99.86 32	99.80 60	99.68 61	99.42 253	99.61 58	99.37 23	99.97 24	99.86 70	94.96 244	99.99 4	99.97 2	99.93 32	99.92 23

fmvsm_s_conf0.5_n_3		99.37 67	99.20 85	99.87 21	99.75 89	99.70 58	99.48 216	99.66 30	99.45 11	99.99 2	99.93 10	94.64 273	99.97 28	99.94 20	99.97 8	99.95 11

fmvsm_s_conf0.1_n_2		99.37 67	99.22 82	99.81 58	99.77 75	99.75 49	99.46 230	99.60 65	99.47 4	99.98 12	99.94 6	94.98 243	99.95 75	99.97 2	99.79 129	99.73 120

MP-MVS-pluss		99.37 67	99.20 85	99.88 15	99.90 4	99.87 17	99.30 302	99.52 127	97.18 305	99.60 148	99.79 158	98.79 51	99.95 75	98.83 163	99.91 45	99.83 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_4		99.36 71	99.24 77	99.73 80	99.78 67	99.53 98	99.49 210	99.60 65	99.42 19	99.99 2	99.86 70	95.15 239	99.95 75	99.95 15	99.89 67	99.73 120

TSAR-MVS + GP.		99.36 71	99.36 45	99.36 177	99.67 131	98.61 239	99.07 370	99.33 309	99.00 64	99.82 65	99.81 123	99.06 17	99.84 193	99.09 118	99.42 178	99.65 164

PVSNet_Blended_VisFu		99.36 71	99.28 68	99.61 106	99.86 23	99.07 167	99.47 226	99.93 2	97.66 254	99.71 102	99.86 70	97.73 118	99.96 40	99.47 65	99.82 114	99.79 90

fmvsm_s_conf0.5_n_7		99.34 74	99.29 65	99.48 150	99.70 119	98.63 235	99.42 253	99.63 44	99.46 7	99.98 12	99.88 51	95.59 219	99.96 40	99.97 2	99.98 4	99.85 46

NCCC		99.34 74	99.19 87	99.79 65	99.61 178	99.65 72	99.30 302	99.48 193	98.86 81	99.21 250	99.63 249	98.72 66	99.90 145	98.25 237	99.63 161	99.80 86

mamv4		99.33 76	99.42 31	99.07 222	99.67 131	97.73 298	99.42 253	99.60 65	98.15 172	99.94 27	99.91 25	98.42 90	99.94 89	99.72 31	99.96 16	99.54 208

MP-MVS		99.33 76	99.15 91	99.87 21	99.88 13	99.82 28	99.66 80	99.46 226	98.09 187	99.48 174	99.74 188	98.29 98	99.96 40	97.93 267	99.87 76	99.82 70
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_s_conf0.5_n_2		99.32 78	99.13 93	99.89 11	99.80 60	99.77 46	99.44 240	99.58 76	99.47 4	99.99 2	99.93 10	94.04 300	99.96 40	99.96 13	99.93 32	99.93 22

PS-MVSNAJ		99.32 78	99.32 53	99.30 193	99.57 193	98.94 194	98.97 398	99.46 226	98.92 78	99.71 102	99.24 371	99.01 19	99.98 19	99.35 75	99.66 156	98.97 304

CSCG		99.32 78	99.32 53	99.32 186	99.85 29	98.29 265	99.71 57	99.66 30	98.11 183	99.41 194	99.80 141	98.37 95	99.96 40	98.99 129	99.96 16	99.72 129

PHI-MVS		99.30 81	99.17 90	99.70 84	99.56 197	99.52 102	99.58 128	99.80 9	97.12 311	99.62 140	99.73 194	98.58 77	99.90 145	98.61 193	99.91 45	99.68 150

DeepC-MVS	98.35 2	99.30 81	99.19 87	99.64 98	99.82 50	99.23 145	99.62 104	99.55 97	98.94 75	99.63 136	99.95 3	95.82 208	99.94 89	99.37 74	99.97 8	99.73 120
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 83	99.10 97	99.86 32	99.70 119	99.65 72	99.53 172	99.62 49	98.74 98	99.99 2	99.95 3	94.53 281	99.94 89	99.89 24	99.96 16	99.97 4

xiu_mvs_v1_base_debu		99.29 83	99.27 72	99.34 180	99.63 160	98.97 180	99.12 360	99.51 146	98.86 81	99.84 53	99.47 310	98.18 103	99.99 4	99.50 56	99.31 188	99.08 289

xiu_mvs_v1_base		99.29 83	99.27 72	99.34 180	99.63 160	98.97 180	99.12 360	99.51 146	98.86 81	99.84 53	99.47 310	98.18 103	99.99 4	99.50 56	99.31 188	99.08 289

xiu_mvs_v1_base_debi		99.29 83	99.27 72	99.34 180	99.63 160	98.97 180	99.12 360	99.51 146	98.86 81	99.84 53	99.47 310	98.18 103	99.99 4	99.50 56	99.31 188	99.08 289

NormalMVS		99.27 87	99.19 87	99.52 136	99.89 8	98.83 214	99.65 86	99.52 127	99.10 45	99.84 53	99.76 178	95.80 210	99.99 4	99.30 88	99.84 99	99.74 111

APD-MVS		99.27 87	99.08 103	99.84 53	99.75 89	99.79 39	99.50 193	99.50 169	97.16 307	99.77 82	99.82 108	98.78 52	99.94 89	97.56 308	99.86 84	99.80 86
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
LS3D		99.27 87	99.12 95	99.74 77	99.18 322	99.75 49	99.56 143	99.57 83	98.45 127	99.49 173	99.85 77	97.77 117	99.94 89	98.33 230	99.84 99	99.52 215

fmvsm_s_conf0.1_n_a		99.26 90	99.06 107	99.85 41	99.52 215	99.62 80	99.54 163	99.62 49	98.69 104	99.99 2	99.96 1	94.47 283	99.94 89	99.88 25	99.92 38	99.98 2

patch_mono-2		99.26 90	99.62 6	98.16 350	99.81 54	94.59 423	99.52 174	99.64 40	99.33 26	99.73 94	99.90 32	99.00 23	99.99 4	99.69 34	99.98 4	99.89 29

ETV-MVS		99.26 90	99.21 83	99.40 170	99.46 242	99.30 135	99.56 143	99.52 127	98.52 119	99.44 183	99.27 367	98.41 92	99.86 178	99.10 117	99.59 165	99.04 296

xiu_mvs_v2_base		99.26 90	99.25 76	99.29 196	99.53 209	98.91 199	99.02 384	99.45 237	98.80 91	99.71 102	99.26 369	98.94 33	99.98 19	99.34 80	99.23 197	98.98 303

CANet		99.25 94	99.14 92	99.59 110	99.41 257	99.16 152	99.35 288	99.57 83	98.82 86	99.51 169	99.61 258	96.46 177	99.95 75	99.59 44	99.98 4	99.65 164

3Dnovator	97.25 9	99.24 95	99.05 109	99.81 58	99.12 338	99.66 68	99.84 12	99.74 11	99.09 52	98.92 306	99.90 32	95.94 201	99.98 19	98.95 137	99.92 38	99.79 90

LuminaMVS		99.23 96	99.10 97	99.61 106	99.35 274	99.31 132	99.46 230	99.13 359	98.61 110	99.86 50	99.89 40	96.41 182	99.91 132	99.67 36	99.51 171	99.63 176

dcpmvs_2		99.23 96	99.58 8	98.16 350	99.83 45	94.68 420	99.76 37	99.52 127	99.07 55	99.98 12	99.88 51	98.56 79	99.93 107	99.67 36	99.98 4	99.87 40

test_fmvsmconf0.01_n		99.22 98	99.03 114	99.79 65	98.42 429	99.48 108	99.55 158	99.51 146	99.39 21	99.78 78	99.93 10	94.80 256	99.95 75	99.93 22	99.95 22	99.94 17

diffmvs_AUTHOR		99.19 99	99.10 97	99.48 150	99.64 156	98.85 209	99.32 296	99.48 193	98.50 121	99.81 66	99.81 123	96.82 158	99.88 165	99.40 70	99.12 210	99.71 138

CHOSEN 1792x2688		99.19 99	99.10 97	99.45 158	99.89 8	98.52 249	99.39 270	99.94 1	98.73 99	99.11 269	99.89 40	95.50 222	99.94 89	99.50 56	99.97 8	99.89 29

F-COLMAP		99.19 99	99.04 111	99.64 98	99.78 67	99.27 140	99.42 253	99.54 106	97.29 296	99.41 194	99.59 263	98.42 90	99.93 107	98.19 241	99.69 150	99.73 120

viewcassd2359sk11		99.18 102	99.08 103	99.49 149	99.65 152	98.95 190	99.48 216	99.51 146	98.10 186	99.72 99	99.87 62	97.13 137	99.84 193	99.13 111	99.14 205	99.69 144

viewmanbaseed2359cas		99.18 102	99.07 106	99.50 146	99.62 168	99.01 174	99.50 193	99.52 127	98.25 157	99.68 108	99.82 108	96.93 151	99.80 228	99.15 110	99.11 212	99.70 141

EIA-MVS		99.18 102	99.09 102	99.45 158	99.49 232	99.18 149	99.67 73	99.53 122	97.66 254	99.40 199	99.44 317	98.10 106	99.81 221	98.94 138	99.62 162	99.35 262

3Dnovator+	97.12 13	99.18 102	98.97 132	99.82 55	99.17 330	99.68 61	99.81 20	99.51 146	99.20 31	98.72 334	99.89 40	95.68 216	99.97 28	98.86 155	99.86 84	99.81 77

MVSFormer		99.17 106	99.12 95	99.29 196	99.51 218	98.94 194	99.88 4	99.46 226	97.55 266	99.80 71	99.65 237	97.39 124	99.28 355	99.03 125	99.85 91	99.65 164

sss		99.17 106	99.05 109	99.53 130	99.62 168	98.97 180	99.36 283	99.62 49	97.83 230	99.67 114	99.65 237	97.37 127	99.95 75	99.19 102	99.19 200	99.68 150

SSM_0404		99.16 108	99.06 107	99.44 163	99.65 152	98.96 184	99.49 210	99.50 169	98.14 177	99.62 140	99.85 77	96.85 153	99.85 184	99.19 102	99.26 193	99.52 215

guyue		99.16 108	99.04 111	99.52 136	99.69 124	98.92 198	99.59 118	98.81 406	98.73 99	99.90 33	99.87 62	95.34 229	99.88 165	99.66 39	99.81 117	99.74 111

test_cas_vis1_n_1920		99.16 108	99.01 125	99.61 106	99.81 54	98.86 208	99.65 86	99.64 40	99.39 21	99.97 24	99.94 6	93.20 324	99.98 19	99.55 49	99.91 45	99.99 1

DP-MVS		99.16 108	98.95 140	99.78 68	99.77 75	99.53 98	99.41 258	99.50 169	97.03 323	99.04 286	99.88 51	97.39 124	99.92 120	98.66 185	99.90 56	99.87 40

SymmetryMVS		99.15 112	99.02 120	99.52 136	99.72 108	98.83 214	99.65 86	99.34 301	99.10 45	99.84 53	99.76 178	95.80 210	99.99 4	99.30 88	98.72 251	99.73 120

MGCNet		99.15 112	98.96 136	99.73 80	98.92 375	99.37 120	99.37 277	96.92 456	99.51 2	99.66 119	99.78 165	96.69 165	99.97 28	99.84 27	99.97 8	99.84 53

casdiffmvs_mvg		99.15 112	99.02 120	99.55 121	99.66 144	99.09 162	99.64 93	99.56 88	98.26 152	99.45 178	99.87 62	96.03 195	99.81 221	99.54 50	99.15 204	99.73 120
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		99.15 112	99.02 120	99.53 130	99.66 144	99.14 157	99.72 53	99.48 193	98.35 139	99.42 189	99.84 92	96.07 192	99.79 234	99.51 55	99.14 205	99.67 154

diffmvs		99.14 116	99.02 120	99.51 141	99.61 178	98.96 184	99.28 312	99.49 181	98.46 125	99.72 99	99.71 201	96.50 175	99.88 165	99.31 85	99.11 212	99.67 154
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		99.14 116	98.99 128	99.59 110	99.58 188	99.41 117	99.16 351	99.44 246	98.45 127	99.19 256	99.49 301	98.08 108	99.89 160	97.73 291	99.75 139	99.48 232

SSM_0407		99.13 118	99.03 114	99.43 166	99.62 168	98.88 201	99.51 183	99.50 169	98.14 177	99.37 205	99.85 77	96.85 153	99.83 207	99.19 102	99.25 194	99.60 184

CDPH-MVS		99.13 118	98.91 148	99.80 62	99.75 89	99.71 56	99.15 354	99.41 262	96.60 355	99.60 148	99.55 278	98.83 46	99.90 145	97.48 315	99.83 110	99.78 96

casdiffmvs		99.13 118	98.98 131	99.56 119	99.65 152	99.16 152	99.56 143	99.50 169	98.33 142	99.41 194	99.86 70	95.92 202	99.83 207	99.45 67	99.16 201	99.70 141
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		99.13 118	99.03 114	99.45 158	99.46 242	98.87 205	99.12 360	99.26 338	98.03 207	99.79 73	99.65 237	97.02 146	99.85 184	99.02 127	99.90 56	99.65 164
jason: jason.
lupinMVS		99.13 118	99.01 125	99.46 157	99.51 218	98.94 194	99.05 376	99.16 355	97.86 223	99.80 71	99.56 275	97.39 124	99.86 178	98.94 138	99.85 91	99.58 199

EPP-MVSNet		99.13 118	98.99 128	99.53 130	99.65 152	99.06 168	99.81 20	99.33 309	97.43 283	99.60 148	99.88 51	97.14 136	99.84 193	99.13 111	98.94 230	99.69 144

MG-MVS		99.13 118	99.02 120	99.45 158	99.57 193	98.63 235	99.07 370	99.34 301	98.99 66	99.61 145	99.82 108	97.98 112	99.87 172	97.00 346	99.80 122	99.85 46

KinetiMVS		99.12 125	98.92 145	99.70 84	99.67 131	99.40 118	99.67 73	99.63 44	98.73 99	99.94 27	99.81 123	94.54 279	99.96 40	98.40 221	99.93 32	99.74 111

BP-MVS1		99.12 125	98.94 142	99.65 92	99.51 218	99.30 135	99.67 73	98.92 387	98.48 123	99.84 53	99.69 216	94.96 244	99.92 120	99.62 43	99.79 129	99.71 138

CHOSEN 280x420		99.12 125	99.13 93	99.08 221	99.66 144	97.89 291	98.43 445	99.71 14	98.88 80	99.62 140	99.76 178	96.63 168	99.70 275	99.46 66	99.99 1	99.66 158

DP-MVS Recon		99.12 125	98.95 140	99.65 92	99.74 97	99.70 58	99.27 317	99.57 83	96.40 371	99.42 189	99.68 224	98.75 59	99.80 228	97.98 264	99.72 145	99.44 248

Vis-MVSNet		99.12 125	98.97 132	99.56 119	99.78 67	99.10 161	99.68 70	99.66 30	98.49 122	99.86 50	99.87 62	94.77 261	99.84 193	99.19 102	99.41 179	99.74 111
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 125	99.08 103	99.24 206	99.46 242	98.55 243	99.51 183	99.46 226	98.09 187	99.45 178	99.82 108	98.34 96	99.51 314	98.70 178	98.93 231	99.67 154

viewdifsd2359ckpt07		99.11 131	99.00 127	99.43 166	99.63 160	98.73 225	99.45 233	99.54 106	98.33 142	99.62 140	99.81 123	96.17 189	99.87 172	99.27 94	99.14 205	99.69 144

SDMVSNet		99.11 131	98.90 150	99.75 74	99.81 54	99.59 85	99.81 20	99.65 37	98.78 95	99.64 133	99.88 51	94.56 276	99.93 107	99.67 36	98.26 281	99.72 129

VNet		99.11 131	98.90 150	99.73 80	99.52 215	99.56 91	99.41 258	99.39 272	99.01 61	99.74 92	99.78 165	95.56 220	99.92 120	99.52 54	98.18 289	99.72 129

CPTT-MVS		99.11 131	98.90 150	99.74 77	99.80 60	99.46 111	99.59 118	99.49 181	97.03 323	99.63 136	99.69 216	97.27 132	99.96 40	97.82 278	99.84 99	99.81 77

HyFIR lowres test		99.11 131	98.92 145	99.65 92	99.90 4	99.37 120	99.02 384	99.91 3	97.67 253	99.59 151	99.75 183	95.90 204	99.73 258	99.53 52	99.02 226	99.86 42

MVS_Test		99.10 136	98.97 132	99.48 150	99.49 232	99.14 157	99.67 73	99.34 301	97.31 294	99.58 152	99.76 178	97.65 120	99.82 216	98.87 150	99.07 221	99.46 243

AstraMVS		99.09 137	99.03 114	99.25 203	99.66 144	98.13 274	99.57 136	98.24 439	98.82 86	99.91 30	99.88 51	95.81 209	99.90 145	99.72 31	99.67 155	99.74 111

CDS-MVSNet		99.09 137	99.03 114	99.25 203	99.42 252	98.73 225	99.45 233	99.46 226	98.11 183	99.46 177	99.77 174	98.01 111	99.37 338	98.70 178	98.92 233	99.66 158
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmacassd2359aftdt		99.08 139	98.94 142	99.50 146	99.66 144	98.96 184	99.51 183	99.54 106	98.27 149	99.42 189	99.89 40	95.88 206	99.80 228	99.20 101	99.11 212	99.76 105

mamba_0408		99.08 139	98.96 136	99.44 163	99.62 168	98.88 201	99.25 328	99.47 215	98.05 198	99.37 205	99.81 123	96.85 153	99.85 184	98.98 130	99.25 194	99.60 184

GDP-MVS		99.08 139	98.89 154	99.64 98	99.53 209	99.34 124	99.64 93	99.48 193	98.32 144	99.77 82	99.66 235	95.14 240	99.93 107	98.97 135	99.50 173	99.64 171

PVSNet_Blended		99.08 139	98.97 132	99.42 168	99.76 79	98.79 220	98.78 420	99.91 3	96.74 340	99.67 114	99.49 301	97.53 121	99.88 165	98.98 130	99.85 91	99.60 184

OMC-MVS		99.08 139	99.04 111	99.20 210	99.67 131	98.22 269	99.28 312	99.52 127	98.07 192	99.66 119	99.81 123	97.79 116	99.78 240	97.79 282	99.81 117	99.60 184

viewdifsd2359ckpt13		99.06 144	98.93 144	99.45 158	99.63 160	98.96 184	99.50 193	99.51 146	97.83 230	99.28 229	99.80 141	96.68 167	99.71 268	99.05 122	99.12 210	99.68 150

SSM_04072		99.06 144	98.96 136	99.35 179	99.62 168	98.88 201	99.25 328	99.47 215	98.05 198	99.37 205	99.81 123	96.85 153	99.58 306	98.98 130	99.25 194	99.60 184

mvsmamba		99.06 144	98.96 136	99.36 177	99.47 240	98.64 234	99.70 58	99.05 371	97.61 259	99.65 128	99.83 97	96.54 173	99.92 120	99.19 102	99.62 162	99.51 224

WTY-MVS		99.06 144	98.88 157	99.61 106	99.62 168	99.16 152	99.37 277	99.56 88	98.04 205	99.53 165	99.62 254	96.84 157	99.94 89	98.85 157	98.49 266	99.72 129

IS-MVSNet		99.05 148	98.87 158	99.57 117	99.73 104	99.32 128	99.75 42	99.20 350	98.02 210	99.56 156	99.86 70	96.54 173	99.67 283	98.09 252	99.13 208	99.73 120

PAPM_NR		99.04 149	98.84 166	99.66 88	99.74 97	99.44 113	99.39 270	99.38 280	97.70 249	99.28 229	99.28 364	98.34 96	99.85 184	96.96 350	99.45 176	99.69 144

API-MVS		99.04 149	99.03 114	99.06 224	99.40 262	99.31 132	99.55 158	99.56 88	98.54 117	99.33 219	99.39 333	98.76 56	99.78 240	96.98 348	99.78 131	98.07 427

mvs_anonymous		99.03 151	98.99 128	99.16 214	99.38 267	98.52 249	99.51 183	99.38 280	97.79 236	99.38 203	99.81 123	97.30 130	99.45 320	99.35 75	98.99 228	99.51 224

sasdasda		99.02 152	98.86 161	99.51 141	99.42 252	99.32 128	99.80 25	99.48 193	98.63 107	99.31 221	98.81 414	97.09 141	99.75 249	99.27 94	97.90 300	99.47 238

train_agg		99.02 152	98.77 173	99.77 71	99.67 131	99.65 72	99.05 376	99.41 262	96.28 375	98.95 302	99.49 301	98.76 56	99.91 132	97.63 299	99.72 145	99.75 107

canonicalmvs		99.02 152	98.86 161	99.51 141	99.42 252	99.32 128	99.80 25	99.48 193	98.63 107	99.31 221	98.81 414	97.09 141	99.75 249	99.27 94	97.90 300	99.47 238

PLC	97.94 4	99.02 152	98.85 164	99.53 130	99.66 144	99.01 174	99.24 333	99.52 127	96.85 335	99.27 235	99.48 307	98.25 100	99.91 132	97.76 287	99.62 162	99.65 164
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
viewdifsd2359ckpt09		99.01 156	98.87 158	99.40 170	99.62 168	98.79 220	99.44 240	99.51 146	97.76 240	99.35 214	99.69 216	96.42 181	99.75 249	98.97 135	99.11 212	99.66 158

viewmambaseed2359dif		99.01 156	98.90 150	99.32 186	99.58 188	98.51 251	99.33 293	99.54 106	97.85 226	99.44 183	99.85 77	96.01 196	99.79 234	99.41 69	99.13 208	99.67 154

MGCFI-Net		99.01 156	98.85 164	99.50 146	99.42 252	99.26 141	99.82 16	99.48 193	98.60 112	99.28 229	98.81 414	97.04 145	99.76 246	99.29 90	97.87 303	99.47 238

AdaColmap		99.01 156	98.80 169	99.66 88	99.56 197	99.54 95	99.18 349	99.70 16	98.18 170	99.35 214	99.63 249	96.32 184	99.90 145	97.48 315	99.77 134	99.55 206

1112_ss		98.98 160	98.77 173	99.59 110	99.68 129	99.02 172	99.25 328	99.48 193	97.23 302	99.13 265	99.58 267	96.93 151	99.90 145	98.87 150	98.78 248	99.84 53

MSDG		98.98 160	98.80 169	99.53 130	99.76 79	99.19 147	98.75 423	99.55 97	97.25 299	99.47 175	99.77 174	97.82 115	99.87 172	96.93 353	99.90 56	99.54 208

CANet_DTU		98.97 162	98.87 158	99.25 203	99.33 280	98.42 262	99.08 369	99.30 328	99.16 34	99.43 186	99.75 183	95.27 232	99.97 28	98.56 205	99.95 22	99.36 261

DPM-MVS		98.95 163	98.71 181	99.66 88	99.63 160	99.55 93	98.64 434	99.10 362	97.93 216	99.42 189	99.55 278	98.67 71	99.80 228	95.80 387	99.68 153	99.61 181

114514_t		98.93 164	98.67 185	99.72 83	99.85 29	99.53 98	99.62 104	99.59 71	92.65 441	99.71 102	99.78 165	98.06 109	99.90 145	98.84 160	99.91 45	99.74 111

PS-MVSNAJss		98.92 165	98.92 145	98.90 251	98.78 396	98.53 245	99.78 32	99.54 106	98.07 192	99.00 293	99.76 178	99.01 19	99.37 338	99.13 111	97.23 343	98.81 313

RRT-MVS		98.91 166	98.75 175	99.39 175	99.46 242	98.61 239	99.76 37	99.50 169	98.06 196	99.81 66	99.88 51	93.91 307	99.94 89	99.11 114	99.27 191	99.61 181

Test_1112_low_res		98.89 167	98.66 188	99.57 117	99.69 124	98.95 190	99.03 381	99.47 215	96.98 325	99.15 263	99.23 372	96.77 162	99.89 160	98.83 163	98.78 248	99.86 42

Elysia		98.88 168	98.65 190	99.58 113	99.58 188	99.34 124	99.65 86	99.52 127	98.26 152	99.83 61	99.87 62	93.37 318	99.90 145	97.81 280	99.91 45	99.49 229

StellarMVS		98.88 168	98.65 190	99.58 113	99.58 188	99.34 124	99.65 86	99.52 127	98.26 152	99.83 61	99.87 62	93.37 318	99.90 145	97.81 280	99.91 45	99.49 229

test_fmvs1		98.88 168	98.79 172	99.16 214	99.69 124	97.61 307	99.55 158	99.49 181	99.32 27	99.98 12	99.91 25	91.41 372	99.96 40	99.82 28	99.92 38	99.90 25

AllTest		98.87 171	98.72 179	99.31 188	99.86 23	98.48 256	99.56 143	99.61 58	97.85 226	99.36 211	99.85 77	95.95 199	99.85 184	96.66 366	99.83 110	99.59 195

UGNet		98.87 171	98.69 183	99.40 170	99.22 313	98.72 227	99.44 240	99.68 22	99.24 30	99.18 260	99.42 321	92.74 334	99.96 40	99.34 80	99.94 30	99.53 214
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)		98.87 171	98.72 179	99.31 188	99.71 114	98.88 201	99.80 25	99.44 246	97.91 218	99.36 211	99.78 165	95.49 223	99.43 329	97.91 268	99.11 212	99.62 179

IMVS_0407		98.86 174	98.91 148	98.72 284	99.55 201	96.93 347	99.50 193	99.44 246	98.05 198	99.66 119	99.80 141	97.13 137	99.65 291	98.15 247	98.92 233	99.60 184

IMVS_0403		98.86 174	98.89 154	98.78 279	99.55 201	96.93 347	99.58 128	99.44 246	98.05 198	99.68 108	99.80 141	96.81 159	99.80 228	98.15 247	98.92 233	99.60 184

test_yl		98.86 174	98.63 193	99.54 122	99.49 232	99.18 149	99.50 193	99.07 368	98.22 163	99.61 145	99.51 295	95.37 227	99.84 193	98.60 196	98.33 273	99.59 195

DCV-MVSNet		98.86 174	98.63 193	99.54 122	99.49 232	99.18 149	99.50 193	99.07 368	98.22 163	99.61 145	99.51 295	95.37 227	99.84 193	98.60 196	98.33 273	99.59 195

EPNet		98.86 174	98.71 181	99.30 193	97.20 449	98.18 270	99.62 104	98.91 392	99.28 29	98.63 353	99.81 123	95.96 198	99.99 4	99.24 98	99.72 145	99.73 120
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 174	98.80 169	99.03 228	99.76 79	98.79 220	99.28 312	99.91 3	97.42 285	99.67 114	99.37 339	97.53 121	99.88 165	98.98 130	97.29 341	98.42 405

ab-mvs		98.86 174	98.63 193	99.54 122	99.64 156	99.19 147	99.44 240	99.54 106	97.77 239	99.30 225	99.81 123	94.20 293	99.93 107	99.17 108	98.82 245	99.49 229

MAR-MVS		98.86 174	98.63 193	99.54 122	99.37 270	99.66 68	99.45 233	99.54 106	96.61 352	99.01 289	99.40 329	97.09 141	99.86 178	97.68 298	99.53 170	99.10 284
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	98.86 174	98.75 175	99.17 213	99.88 13	98.53 245	99.34 291	99.59 71	97.55 266	98.70 341	99.89 40	95.83 207	99.90 145	98.10 251	99.90 56	99.08 289
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 183	98.62 198	99.53 130	99.61 178	99.08 165	99.80 25	99.51 146	97.10 315	99.31 221	99.78 165	95.23 237	99.77 242	98.21 239	99.03 224	99.75 107

HY-MVS	97.30 7	98.85 183	98.64 192	99.47 155	99.42 252	99.08 165	99.62 104	99.36 289	97.39 288	99.28 229	99.68 224	96.44 179	99.92 120	98.37 225	98.22 284	99.40 255

PVSNet	96.02 17	98.85 183	98.84 166	98.89 255	99.73 104	97.28 317	98.32 451	99.60 65	97.86 223	99.50 170	99.57 272	96.75 163	99.86 178	98.56 205	99.70 149	99.54 208

PatchMatch-RL		98.84 186	98.62 198	99.52 136	99.71 114	99.28 138	99.06 374	99.77 10	97.74 244	99.50 170	99.53 287	95.41 225	99.84 193	97.17 339	99.64 159	99.44 248

Effi-MVS+		98.81 187	98.59 204	99.48 150	99.46 242	99.12 160	98.08 458	99.50 169	97.50 274	99.38 203	99.41 325	96.37 183	99.81 221	99.11 114	98.54 263	99.51 224

alignmvs		98.81 187	98.56 207	99.58 113	99.43 250	99.42 115	99.51 183	98.96 382	98.61 110	99.35 214	98.92 409	94.78 258	99.77 242	99.35 75	98.11 294	99.54 208

DeepPCF-MVS	98.18 3	98.81 187	99.37 43	97.12 408	99.60 184	91.75 449	98.61 435	99.44 246	99.35 24	99.83 61	99.85 77	98.70 68	99.81 221	99.02 127	99.91 45	99.81 77

PMMVS		98.80 190	98.62 198	99.34 180	99.27 298	98.70 228	98.76 422	99.31 323	97.34 291	99.21 250	99.07 388	97.20 135	99.82 216	98.56 205	98.87 240	99.52 215

icg_test_0407_2		98.79 191	98.86 161	98.57 300	99.55 201	96.93 347	99.07 370	99.44 246	98.05 198	99.66 119	99.80 141	97.13 137	99.18 377	98.15 247	98.92 233	99.60 184

viewdifsd2359ckpt11		98.78 192	98.74 177	98.89 255	99.67 131	97.04 336	99.50 193	99.58 76	98.26 152	99.56 156	99.90 32	94.36 286	99.87 172	99.49 60	98.32 277	99.77 98

viewmsd2359difaftdt		98.78 192	98.74 177	98.90 251	99.67 131	97.04 336	99.50 193	99.58 76	98.26 152	99.56 156	99.90 32	94.36 286	99.87 172	99.49 60	98.32 277	99.77 98

Effi-MVS+-dtu		98.78 192	98.89 154	98.47 318	99.33 280	96.91 352	99.57 136	99.30 328	98.47 124	99.41 194	98.99 399	96.78 161	99.74 252	98.73 175	99.38 180	98.74 328

FIs		98.78 192	98.63 193	99.23 208	99.18 322	99.54 95	99.83 15	99.59 71	98.28 147	98.79 328	99.81 123	96.75 163	99.37 338	99.08 119	96.38 359	98.78 316

Fast-Effi-MVS+-dtu		98.77 196	98.83 168	98.60 295	99.41 257	96.99 342	99.52 174	99.49 181	98.11 183	99.24 242	99.34 349	96.96 150	99.79 234	97.95 266	99.45 176	99.02 299

sd_testset		98.75 197	98.57 205	99.29 196	99.81 54	98.26 267	99.56 143	99.62 49	98.78 95	99.64 133	99.88 51	92.02 356	99.88 165	99.54 50	98.26 281	99.72 129

FA-MVS(test-final)		98.75 197	98.53 209	99.41 169	99.55 201	99.05 170	99.80 25	99.01 376	96.59 357	99.58 152	99.59 263	95.39 226	99.90 145	97.78 283	99.49 174	99.28 270

FC-MVSNet-test		98.75 197	98.62 198	99.15 218	99.08 349	99.45 112	99.86 11	99.60 65	98.23 162	98.70 341	99.82 108	96.80 160	99.22 369	99.07 120	96.38 359	98.79 314

XVG-OURS		98.73 200	98.68 184	98.88 258	99.70 119	97.73 298	98.92 406	99.55 97	98.52 119	99.45 178	99.84 92	95.27 232	99.91 132	98.08 256	98.84 243	99.00 300

Fast-Effi-MVS+		98.70 201	98.43 214	99.51 141	99.51 218	99.28 138	99.52 174	99.47 215	96.11 391	99.01 289	99.34 349	96.20 188	99.84 193	97.88 270	98.82 245	99.39 256

XVG-OURS-SEG-HR		98.69 202	98.62 198	98.89 255	99.71 114	97.74 297	99.12 360	99.54 106	98.44 130	99.42 189	99.71 201	94.20 293	99.92 120	98.54 209	98.90 239	99.00 300

1314		98.68 203	98.54 208	99.11 220	98.89 379	98.65 232	99.27 317	99.49 181	96.89 333	97.99 393	99.56 275	97.72 119	99.83 207	97.74 290	99.27 191	98.84 312

VortexMVS		98.67 204	98.66 188	98.68 290	99.62 168	97.96 285	99.59 118	99.41 262	98.13 179	99.31 221	99.70 205	95.48 224	99.27 358	99.40 70	97.32 340	98.79 314

EI-MVSNet		98.67 204	98.67 185	98.68 290	99.35 274	97.97 283	99.50 193	99.38 280	96.93 332	99.20 253	99.83 97	97.87 113	99.36 342	98.38 223	97.56 319	98.71 332

test_djsdf		98.67 204	98.57 205	98.98 234	98.70 410	98.91 199	99.88 4	99.46 226	97.55 266	99.22 247	99.88 51	95.73 214	99.28 355	99.03 125	97.62 314	98.75 324

QAPM		98.67 204	98.30 224	99.80 62	99.20 316	99.67 65	99.77 34	99.72 12	94.74 418	98.73 333	99.90 32	95.78 212	99.98 19	96.96 350	99.88 73	99.76 105

nrg030		98.64 208	98.42 215	99.28 200	99.05 355	99.69 60	99.81 20	99.46 226	98.04 205	99.01 289	99.82 108	96.69 165	99.38 335	99.34 80	94.59 404	98.78 316

test_vis1_n_1920		98.63 209	98.40 217	99.31 188	99.86 23	97.94 290	99.67 73	99.62 49	99.43 16	99.99 2	99.91 25	87.29 423	100.00 1	99.92 23	99.92 38	99.98 2

PAPR		98.63 209	98.34 220	99.51 141	99.40 262	99.03 171	98.80 418	99.36 289	96.33 372	99.00 293	99.12 386	98.46 86	99.84 193	95.23 402	99.37 187	99.66 158

CVMVSNet		98.57 211	98.67 185	98.30 338	99.35 274	95.59 394	99.50 193	99.55 97	98.60 112	99.39 201	99.83 97	94.48 282	99.45 320	98.75 172	98.56 261	99.85 46

IMVS_0404		98.53 212	98.52 210	98.55 306	99.55 201	96.93 347	99.20 345	99.44 246	98.05 198	98.96 300	99.80 141	94.66 271	99.13 385	98.15 247	98.92 233	99.60 184

MVSTER		98.49 213	98.32 222	99.00 232	99.35 274	99.02 172	99.54 163	99.38 280	97.41 286	99.20 253	99.73 194	93.86 309	99.36 342	98.87 150	97.56 319	98.62 376

FE-MVS		98.48 214	98.17 229	99.40 170	99.54 208	98.96 184	99.68 70	98.81 406	95.54 402	99.62 140	99.70 205	93.82 310	99.93 107	97.35 326	99.46 175	99.32 267

OpenMVS	96.50 16	98.47 215	98.12 236	99.52 136	99.04 357	99.53 98	99.82 16	99.72 12	94.56 421	98.08 388	99.88 51	94.73 264	99.98 19	97.47 317	99.76 137	99.06 295

IterMVS-LS		98.46 216	98.42 215	98.58 299	99.59 186	98.00 281	99.37 277	99.43 257	96.94 331	99.07 278	99.59 263	97.87 113	99.03 400	98.32 232	95.62 382	98.71 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 217	98.28 225	98.94 241	98.50 426	98.96 184	99.77 34	99.50 169	97.07 317	98.87 315	99.77 174	94.76 262	99.28 355	98.66 185	97.60 315	98.57 391

jajsoiax		98.43 218	98.28 225	98.88 258	98.60 420	98.43 260	99.82 16	99.53 122	98.19 167	98.63 353	99.80 141	93.22 323	99.44 325	99.22 99	97.50 326	98.77 320

tttt0517		98.42 219	98.14 233	99.28 200	99.66 144	98.38 263	99.74 47	96.85 457	97.68 251	99.79 73	99.74 188	91.39 373	99.89 160	98.83 163	99.56 167	99.57 202

BH-untuned		98.42 219	98.36 218	98.59 296	99.49 232	96.70 360	99.27 317	99.13 359	97.24 301	98.80 326	99.38 336	95.75 213	99.74 252	97.07 344	99.16 201	99.33 266

test_fmvs1_n		98.41 221	98.14 233	99.21 209	99.82 50	97.71 303	99.74 47	99.49 181	99.32 27	99.99 2	99.95 3	85.32 437	99.97 28	99.82 28	99.84 99	99.96 7

D2MVS		98.41 221	98.50 211	98.15 353	99.26 301	96.62 366	99.40 266	99.61 58	97.71 246	98.98 296	99.36 342	96.04 194	99.67 283	98.70 178	97.41 336	98.15 423

BH-RMVSNet		98.41 221	98.08 242	99.40 170	99.41 257	98.83 214	99.30 302	98.77 412	97.70 249	98.94 304	99.65 237	92.91 330	99.74 252	96.52 370	99.55 169	99.64 171

mvs_tets		98.40 224	98.23 227	98.91 249	98.67 413	98.51 251	99.66 80	99.53 122	98.19 167	98.65 350	99.81 123	92.75 332	99.44 325	99.31 85	97.48 330	98.77 320

MonoMVSNet		98.38 225	98.47 213	98.12 355	98.59 422	96.19 383	99.72 53	98.79 410	97.89 220	99.44 183	99.52 291	96.13 190	98.90 422	98.64 187	97.54 321	99.28 270

XXY-MVS		98.38 225	98.09 241	99.24 206	99.26 301	99.32 128	99.56 143	99.55 97	97.45 279	98.71 335	99.83 97	93.23 321	99.63 301	98.88 147	96.32 361	98.76 322

ACMM	97.58 5	98.37 227	98.34 220	98.48 313	99.41 257	97.10 327	99.56 143	99.45 237	98.53 118	99.04 286	99.85 77	93.00 326	99.71 268	98.74 173	97.45 331	98.64 367
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 228	98.03 248	99.31 188	99.63 160	98.56 242	99.54 163	96.75 459	97.53 270	99.73 94	99.65 237	91.25 377	99.89 160	98.62 190	99.56 167	99.48 232

tpmrst		98.33 229	98.48 212	97.90 372	99.16 332	94.78 416	99.31 300	99.11 361	97.27 297	99.45 178	99.59 263	95.33 230	99.84 193	98.48 212	98.61 255	99.09 288

baseline1		98.31 230	97.95 257	99.38 176	99.50 230	98.74 224	99.59 118	98.93 384	98.41 132	99.14 264	99.60 261	94.59 274	99.79 234	98.48 212	93.29 424	99.61 181

PatchmatchNet		98.31 230	98.36 218	98.19 348	99.16 332	95.32 405	99.27 317	98.92 387	97.37 289	99.37 205	99.58 267	94.90 251	99.70 275	97.43 321	99.21 198	99.54 208
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 232	97.98 253	99.26 202	99.57 193	98.16 271	99.41 258	98.55 431	96.03 396	99.19 256	99.74 188	91.87 359	99.92 120	99.16 109	98.29 280	99.70 141

VPA-MVSNet		98.29 233	97.95 257	99.30 193	99.16 332	99.54 95	99.50 193	99.58 76	98.27 149	99.35 214	99.37 339	92.53 344	99.65 291	99.35 75	94.46 405	98.72 330

UniMVSNet (Re)		98.29 233	98.00 251	99.13 219	99.00 362	99.36 123	99.49 210	99.51 146	97.95 214	98.97 298	99.13 383	96.30 185	99.38 335	98.36 227	93.34 423	98.66 363

HQP_MVS		98.27 235	98.22 228	98.44 324	99.29 293	96.97 344	99.39 270	99.47 215	98.97 72	99.11 269	99.61 258	92.71 337	99.69 280	97.78 283	97.63 312	98.67 354

UniMVSNet_NR-MVSNet		98.22 236	97.97 254	98.96 237	98.92 375	98.98 177	99.48 216	99.53 122	97.76 240	98.71 335	99.46 314	96.43 180	99.22 369	98.57 202	92.87 431	98.69 341

LPG-MVS_test		98.22 236	98.13 235	98.49 311	99.33 280	97.05 333	99.58 128	99.55 97	97.46 276	99.24 242	99.83 97	92.58 342	99.72 262	98.09 252	97.51 324	98.68 346

RPSCF		98.22 236	98.62 198	96.99 410	99.82 50	91.58 450	99.72 53	99.44 246	96.61 352	99.66 119	99.89 40	95.92 202	99.82 216	97.46 318	99.10 218	99.57 202

ADS-MVSNet		98.20 239	98.08 242	98.56 304	99.33 280	96.48 371	99.23 336	99.15 356	96.24 379	99.10 272	99.67 230	94.11 297	99.71 268	96.81 358	99.05 222	99.48 232

OPM-MVS		98.19 240	98.10 238	98.45 321	98.88 380	97.07 331	99.28 312	99.38 280	98.57 114	99.22 247	99.81 123	92.12 354	99.66 286	98.08 256	97.54 321	98.61 385
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 240	98.16 230	98.27 344	99.30 289	95.55 395	99.07 370	98.97 380	97.57 263	99.43 186	99.57 272	92.72 335	99.74 252	97.58 303	99.20 199	99.52 215

miper_ehance_all_eth		98.18 242	98.10 238	98.41 327	99.23 309	97.72 300	98.72 426	99.31 323	96.60 355	98.88 312	99.29 362	97.29 131	99.13 385	97.60 301	95.99 370	98.38 410

CR-MVSNet		98.17 243	97.93 260	98.87 262	99.18 322	98.49 254	99.22 340	99.33 309	96.96 327	99.56 156	99.38 336	94.33 289	99.00 405	94.83 409	98.58 258	99.14 281

miper_enhance_ethall		98.16 244	98.08 242	98.41 327	98.96 371	97.72 300	98.45 444	99.32 319	96.95 329	98.97 298	99.17 378	97.06 144	99.22 369	97.86 273	95.99 370	98.29 414

CLD-MVS		98.16 244	98.10 238	98.33 334	99.29 293	96.82 357	98.75 423	99.44 246	97.83 230	99.13 265	99.55 278	92.92 328	99.67 283	98.32 232	97.69 310	98.48 397
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 246	97.79 272	99.19 211	99.50 230	98.50 253	98.61 435	96.82 458	96.95 329	99.54 163	99.43 319	91.66 368	99.86 178	98.08 256	99.51 171	99.22 278

pmmvs4		98.13 247	97.90 262	98.81 274	98.61 419	98.87 205	98.99 392	99.21 349	96.44 367	99.06 283	99.58 267	95.90 204	99.11 391	97.18 338	96.11 366	98.46 402

WR-MVS_H		98.13 247	97.87 267	98.90 251	99.02 359	98.84 211	99.70 58	99.59 71	97.27 297	98.40 370	99.19 377	95.53 221	99.23 365	98.34 229	93.78 419	98.61 385

c3_l		98.12 249	98.04 247	98.38 331	99.30 289	97.69 304	98.81 417	99.33 309	96.67 345	98.83 321	99.34 349	97.11 140	98.99 406	97.58 303	95.34 389	98.48 397

ACMH	97.28 8	98.10 250	97.99 252	98.44 324	99.41 257	96.96 346	99.60 111	99.56 88	98.09 187	98.15 386	99.91 25	90.87 381	99.70 275	98.88 147	97.45 331	98.67 354
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		98.09 251	97.68 289	99.34 180	99.66 144	98.44 259	99.40 266	99.43 257	93.67 428	99.22 247	99.89 40	90.23 389	99.93 107	99.26 97	98.33 273	99.66 158

CP-MVSNet		98.09 251	97.78 275	99.01 230	98.97 370	99.24 144	99.67 73	99.46 226	97.25 299	98.48 367	99.64 243	93.79 311	99.06 396	98.63 189	94.10 413	98.74 328

dmvs_re		98.08 253	98.16 230	97.85 376	99.55 201	94.67 421	99.70 58	98.92 387	98.15 172	99.06 283	99.35 345	93.67 315	99.25 362	97.77 286	97.25 342	99.64 171

DU-MVS		98.08 253	97.79 272	98.96 237	98.87 383	98.98 177	99.41 258	99.45 237	97.87 222	98.71 335	99.50 298	94.82 254	99.22 369	98.57 202	92.87 431	98.68 346

v2v482		98.06 255	97.77 277	98.92 245	98.90 378	98.82 217	99.57 136	99.36 289	96.65 347	99.19 256	99.35 345	94.20 293	99.25 362	97.72 293	94.97 397	98.69 341

V42		98.06 255	97.79 272	98.86 265	98.98 368	98.84 211	99.69 62	99.34 301	96.53 359	99.30 225	99.37 339	94.67 269	99.32 350	97.57 307	94.66 402	98.42 405

test-LLR		98.06 255	97.90 262	98.55 306	98.79 393	97.10 327	98.67 429	97.75 448	97.34 291	98.61 357	98.85 411	94.45 284	99.45 320	97.25 330	99.38 180	99.10 284

WR-MVS		98.06 255	97.73 284	99.06 224	98.86 386	99.25 143	99.19 347	99.35 296	97.30 295	98.66 344	99.43 319	93.94 304	99.21 374	98.58 199	94.28 409	98.71 332

ACMP	97.20 11	98.06 255	97.94 259	98.45 321	99.37 270	97.01 340	99.44 240	99.49 181	97.54 269	98.45 368	99.79 158	91.95 358	99.72 262	97.91 268	97.49 329	98.62 376
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 260	97.96 255	98.33 334	99.26 301	97.38 314	98.56 440	99.31 323	96.65 347	98.88 312	99.52 291	96.58 171	99.12 390	97.39 323	95.53 386	98.47 399

test1111		98.04 261	98.11 237	97.83 379	99.74 97	93.82 432	99.58 128	95.40 466	99.12 43	99.65 128	99.93 10	90.73 382	99.84 193	99.43 68	99.38 180	99.82 70

ECVR-MVS		98.04 261	98.05 246	98.00 363	99.74 97	94.37 427	99.59 118	94.98 467	99.13 38	99.66 119	99.93 10	90.67 383	99.84 193	99.40 70	99.38 180	99.80 86

EPNet_dtu		98.03 263	97.96 255	98.23 346	98.27 431	95.54 397	99.23 336	98.75 413	99.02 59	97.82 402	99.71 201	96.11 191	99.48 315	93.04 430	99.65 158	99.69 144
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 263	97.76 281	98.84 269	99.39 265	98.98 177	99.40 266	99.38 280	96.67 345	99.07 278	99.28 364	92.93 327	98.98 407	97.10 340	96.65 352	98.56 392

ADS-MVSNet2		98.02 265	98.07 245	97.87 374	99.33 280	95.19 408	99.23 336	99.08 365	96.24 379	99.10 272	99.67 230	94.11 297	98.93 419	96.81 358	99.05 222	99.48 232

HQP-MVS		98.02 265	97.90 262	98.37 332	99.19 319	96.83 355	98.98 395	99.39 272	98.24 159	98.66 344	99.40 329	92.47 346	99.64 295	97.19 336	97.58 317	98.64 367

LTVRE_ROB	97.16 12	98.02 265	97.90 262	98.40 329	99.23 309	96.80 358	99.70 58	99.60 65	97.12 311	98.18 385	99.70 205	91.73 364	99.72 262	98.39 222	97.45 331	98.68 346
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____		98.01 268	97.84 270	98.55 306	99.25 305	97.97 283	98.71 427	99.34 301	96.47 366	98.59 360	99.54 283	95.65 217	99.21 374	97.21 332	95.77 376	98.46 402

DIV-MVS_self_test		98.01 268	97.85 269	98.48 313	99.24 307	97.95 288	98.71 427	99.35 296	96.50 360	98.60 359	99.54 283	95.72 215	99.03 400	97.21 332	95.77 376	98.46 402

miper_lstm_enhance		98.00 270	97.91 261	98.28 343	99.34 279	97.43 312	98.88 410	99.36 289	96.48 364	98.80 326	99.55 278	95.98 197	98.91 420	97.27 329	95.50 387	98.51 395

BH-w/o		98.00 270	97.89 266	98.32 336	99.35 274	96.20 382	99.01 389	98.90 394	96.42 369	98.38 371	99.00 397	95.26 234	99.72 262	96.06 380	98.61 255	99.03 297

v1144		97.98 272	97.69 288	98.85 268	98.87 383	98.66 231	99.54 163	99.35 296	96.27 377	99.23 246	99.35 345	94.67 269	99.23 365	96.73 361	95.16 393	98.68 346

EU-MVSNet		97.98 272	98.03 248	97.81 382	98.72 407	96.65 365	99.66 80	99.66 30	98.09 187	98.35 373	99.82 108	95.25 235	98.01 443	97.41 322	95.30 390	98.78 316

tpmvs		97.98 272	98.02 250	97.84 378	99.04 357	94.73 417	99.31 300	99.20 350	96.10 395	98.76 331	99.42 321	94.94 246	99.81 221	96.97 349	98.45 267	98.97 304

tt0805		97.97 275	97.77 277	98.57 300	99.59 186	96.61 367	99.45 233	99.08 365	98.21 165	98.88 312	99.80 141	88.66 407	99.70 275	98.58 199	97.72 309	99.39 256

NR-MVSNet		97.97 275	97.61 298	99.02 229	98.87 383	99.26 141	99.47 226	99.42 259	97.63 256	97.08 421	99.50 298	95.07 242	99.13 385	97.86 273	93.59 420	98.68 346

v8		97.95 277	97.63 296	98.93 243	98.95 372	98.81 219	99.80 25	99.41 262	96.03 396	99.10 272	99.42 321	94.92 249	99.30 353	96.94 352	94.08 414	98.66 363

Patchmatch-test		97.93 278	97.65 292	98.77 280	99.18 322	97.07 331	99.03 381	99.14 358	96.16 386	98.74 332	99.57 272	94.56 276	99.72 262	93.36 426	99.11 212	99.52 215

PS-CasMVS		97.93 278	97.59 300	98.95 239	98.99 365	99.06 168	99.68 70	99.52 127	97.13 309	98.31 375	99.68 224	92.44 350	99.05 397	98.51 210	94.08 414	98.75 324

TranMVSNet+NR-MVSNet		97.93 278	97.66 291	98.76 281	98.78 396	98.62 237	99.65 86	99.49 181	97.76 240	98.49 366	99.60 261	94.23 292	98.97 414	98.00 263	92.90 429	98.70 337

test_vis1_n		97.92 281	97.44 322	99.34 180	99.53 209	98.08 277	99.74 47	99.49 181	99.15 35	100.00 1	99.94 6	79.51 459	99.98 19	99.88 25	99.76 137	99.97 4

v144192		97.92 281	97.60 299	98.87 262	98.83 390	98.65 232	99.55 158	99.34 301	96.20 382	99.32 220	99.40 329	94.36 286	99.26 361	96.37 377	95.03 396	98.70 337

ACMH+	97.24 10	97.92 281	97.78 275	98.32 336	99.46 242	96.68 364	99.56 143	99.54 106	98.41 132	97.79 404	99.87 62	90.18 390	99.66 286	98.05 260	97.18 346	98.62 376

LFMVS		97.90 284	97.35 334	99.54 122	99.52 215	99.01 174	99.39 270	98.24 439	97.10 315	99.65 128	99.79 158	84.79 440	99.91 132	99.28 91	98.38 270	99.69 144

reproduce_monomvs		97.89 285	97.87 267	97.96 367	99.51 218	95.45 400	99.60 111	99.25 340	99.17 33	98.85 320	99.49 301	89.29 399	99.64 295	99.35 75	96.31 362	98.78 316

Anonymous20231211		97.88 286	97.54 304	98.90 251	99.71 114	98.53 245	99.48 216	99.57 83	94.16 424	98.81 324	99.68 224	93.23 321	99.42 331	98.84 160	94.42 407	98.76 322

OurMVSNet-221017-0		97.88 286	97.77 277	98.19 348	98.71 409	96.53 369	99.88 4	99.00 377	97.79 236	98.78 329	99.94 6	91.68 365	99.35 345	97.21 332	96.99 350	98.69 341

v7n		97.87 288	97.52 306	98.92 245	98.76 403	98.58 241	99.84 12	99.46 226	96.20 382	98.91 307	99.70 205	94.89 252	99.44 325	96.03 381	93.89 417	98.75 324

baseline2		97.87 288	97.55 301	98.82 271	99.18 322	98.02 280	99.41 258	96.58 463	96.97 326	96.51 428	99.17 378	93.43 316	99.57 307	97.71 294	99.03 224	98.86 310

thres600view7		97.86 290	97.51 308	98.92 245	99.72 108	97.95 288	99.59 118	98.74 416	97.94 215	99.27 235	98.62 422	91.75 362	99.86 178	93.73 422	98.19 288	98.96 306

UBG		97.85 291	97.48 311	98.95 239	99.25 305	97.64 305	99.24 333	98.74 416	97.90 219	98.64 351	98.20 439	88.65 408	99.81 221	98.27 235	98.40 268	99.42 250

cl22		97.85 291	97.64 295	98.48 313	99.09 346	97.87 292	98.60 437	99.33 309	97.11 314	98.87 315	99.22 373	92.38 351	99.17 379	98.21 239	95.99 370	98.42 405

v10		97.85 291	97.52 306	98.86 265	98.99 365	98.67 230	99.75 42	99.41 262	95.70 400	98.98 296	99.41 325	94.75 263	99.23 365	96.01 383	94.63 403	98.67 354

GA-MVS		97.85 291	97.47 314	99.00 232	99.38 267	97.99 282	98.57 438	99.15 356	97.04 322	98.90 309	99.30 360	89.83 393	99.38 335	96.70 363	98.33 273	99.62 179

testing3-2		97.84 295	97.70 287	98.24 345	99.53 209	95.37 404	99.55 158	98.67 426	98.46 125	99.27 235	99.34 349	86.58 427	99.83 207	99.32 83	98.63 254	99.52 215

tfpnnormal		97.84 295	97.47 314	98.98 234	99.20 316	99.22 146	99.64 93	99.61 58	96.32 373	98.27 379	99.70 205	93.35 320	99.44 325	95.69 390	95.40 388	98.27 415

VPNet		97.84 295	97.44 322	99.01 230	99.21 314	98.94 194	99.48 216	99.57 83	98.38 134	99.28 229	99.73 194	88.89 402	99.39 333	99.19 102	93.27 425	98.71 332

LCM-MVSNet-Re		97.83 298	98.15 232	96.87 416	99.30 289	92.25 447	99.59 118	98.26 437	97.43 283	96.20 432	99.13 383	96.27 186	98.73 429	98.17 244	98.99 228	99.64 171

XVG-ACMP-BASELINE		97.83 298	97.71 286	98.20 347	99.11 340	96.33 376	99.41 258	99.52 127	98.06 196	99.05 285	99.50 298	89.64 396	99.73 258	97.73 291	97.38 338	98.53 393

IterMVS		97.83 298	97.77 277	98.02 360	99.58 188	96.27 379	99.02 384	99.48 193	97.22 303	98.71 335	99.70 205	92.75 332	99.13 385	97.46 318	96.00 369	98.67 354
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 301	97.75 282	98.06 357	99.57 193	96.36 375	99.02 384	99.49 181	97.18 305	98.71 335	99.72 198	92.72 335	99.14 382	97.44 320	95.86 375	98.67 354

EPMVS		97.82 301	97.65 292	98.35 333	98.88 380	95.98 386	99.49 210	94.71 469	97.57 263	99.26 240	99.48 307	92.46 349	99.71 268	97.87 272	99.08 220	99.35 262

MVP-Stereo		97.81 303	97.75 282	97.99 364	97.53 442	96.60 368	98.96 399	98.85 401	97.22 303	97.23 415	99.36 342	95.28 231	99.46 318	95.51 394	99.78 131	97.92 440
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 303	97.44 322	98.91 249	98.88 380	98.68 229	99.51 183	99.34 301	96.18 384	99.20 253	99.34 349	94.03 301	99.36 342	95.32 400	95.18 392	98.69 341

ttmdpeth		97.80 305	97.63 296	98.29 339	98.77 401	97.38 314	99.64 93	99.36 289	98.78 95	96.30 431	99.58 267	92.34 353	99.39 333	98.36 227	95.58 383	98.10 425

v1921920		97.80 305	97.45 317	98.84 269	98.80 392	98.53 245	99.52 174	99.34 301	96.15 388	99.24 242	99.47 310	93.98 303	99.29 354	95.40 398	95.13 394	98.69 341

v148		97.79 307	97.55 301	98.50 310	98.74 404	97.72 300	99.54 163	99.33 309	96.26 378	98.90 309	99.51 295	94.68 268	99.14 382	97.83 277	93.15 428	98.63 374

thres400		97.77 308	97.38 330	98.92 245	99.69 124	97.96 285	99.50 193	98.73 422	97.83 230	99.17 261	98.45 429	91.67 366	99.83 207	93.22 427	98.18 289	98.96 306

thres100view900		97.76 309	97.45 317	98.69 289	99.72 108	97.86 294	99.59 118	98.74 416	97.93 216	99.26 240	98.62 422	91.75 362	99.83 207	93.22 427	98.18 289	98.37 411

PEN-MVS		97.76 309	97.44 322	98.72 284	98.77 401	98.54 244	99.78 32	99.51 146	97.06 319	98.29 378	99.64 243	92.63 341	98.89 423	98.09 252	93.16 427	98.72 330

Baseline_NR-MVSNet		97.76 309	97.45 317	98.68 290	99.09 346	98.29 265	99.41 258	98.85 401	95.65 401	98.63 353	99.67 230	94.82 254	99.10 393	98.07 259	92.89 430	98.64 367

TR-MVS		97.76 309	97.41 328	98.82 271	99.06 352	97.87 292	98.87 412	98.56 430	96.63 351	98.68 343	99.22 373	92.49 345	99.65 291	95.40 398	97.79 307	98.95 308

Patchmtry		97.75 313	97.40 329	98.81 274	99.10 343	98.87 205	99.11 366	99.33 309	94.83 416	98.81 324	99.38 336	94.33 289	99.02 402	96.10 379	95.57 384	98.53 393

dp		97.75 313	97.80 271	97.59 395	99.10 343	93.71 435	99.32 296	98.88 397	96.48 364	99.08 277	99.55 278	92.67 340	99.82 216	96.52 370	98.58 258	99.24 276

WBMVS		97.74 315	97.50 309	98.46 319	99.24 307	97.43 312	99.21 342	99.42 259	97.45 279	98.96 300	99.41 325	88.83 403	99.23 365	98.94 138	96.02 367	98.71 332

TAPA-MVS	97.07 15	97.74 315	97.34 337	98.94 241	99.70 119	97.53 308	99.25 328	99.51 146	91.90 443	99.30 225	99.63 249	98.78 52	99.64 295	88.09 453	99.87 76	99.65 164
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 317	97.35 334	98.88 258	99.47 240	97.12 326	99.34 291	98.85 401	98.19 167	99.67 114	99.85 77	82.98 448	99.92 120	99.49 60	98.32 277	99.60 184

MIMVSNet		97.73 317	97.45 317	98.57 300	99.45 248	97.50 310	99.02 384	98.98 379	96.11 391	99.41 194	99.14 382	90.28 385	98.74 428	95.74 388	98.93 231	99.47 238

tfpn200view9		97.72 319	97.38 330	98.72 284	99.69 124	97.96 285	99.50 193	98.73 422	97.83 230	99.17 261	98.45 429	91.67 366	99.83 207	93.22 427	98.18 289	98.37 411

CostFormer		97.72 319	97.73 284	97.71 387	99.15 336	94.02 431	99.54 163	99.02 375	94.67 419	99.04 286	99.35 345	92.35 352	99.77 242	98.50 211	97.94 299	99.34 265

FMVSNet2		97.72 319	97.36 332	98.80 276	99.51 218	98.84 211	99.45 233	99.42 259	96.49 361	98.86 319	99.29 362	90.26 386	98.98 407	96.44 372	96.56 355	98.58 390

test0.0.03 1		97.71 322	97.42 327	98.56 304	98.41 430	97.82 295	98.78 420	98.63 428	97.34 291	98.05 392	98.98 401	94.45 284	98.98 407	95.04 405	97.15 347	98.89 309

h-mvs33		97.70 323	97.28 346	98.97 236	99.70 119	97.27 318	99.36 283	99.45 237	98.94 75	99.66 119	99.64 243	94.93 247	99.99 4	99.48 63	84.36 458	99.65 164

myMVS_eth3d28		97.69 324	97.34 337	98.73 282	99.27 298	97.52 309	99.33 293	98.78 411	98.03 207	98.82 323	98.49 427	86.64 426	99.46 318	98.44 218	98.24 283	99.23 277

v1240		97.69 324	97.32 341	98.79 277	98.85 387	98.43 260	99.48 216	99.36 289	96.11 391	99.27 235	99.36 342	93.76 313	99.24 364	94.46 412	95.23 391	98.70 337

cascas		97.69 324	97.43 326	98.48 313	98.60 420	97.30 316	98.18 456	99.39 272	92.96 437	98.41 369	98.78 418	93.77 312	99.27 358	98.16 245	98.61 255	98.86 310

pm-mvs1		97.68 327	97.28 346	98.88 258	99.06 352	98.62 237	99.50 193	99.45 237	96.32 373	97.87 400	99.79 158	92.47 346	99.35 345	97.54 310	93.54 421	98.67 354

GBi-Net		97.68 327	97.48 311	98.29 339	99.51 218	97.26 320	99.43 246	99.48 193	96.49 361	99.07 278	99.32 357	90.26 386	98.98 407	97.10 340	96.65 352	98.62 376

test1		97.68 327	97.48 311	98.29 339	99.51 218	97.26 320	99.43 246	99.48 193	96.49 361	99.07 278	99.32 357	90.26 386	98.98 407	97.10 340	96.65 352	98.62 376

tpm		97.67 330	97.55 301	98.03 358	99.02 359	95.01 412	99.43 246	98.54 432	96.44 367	99.12 267	99.34 349	91.83 361	99.60 304	97.75 289	96.46 357	99.48 232

PCF-MVS	97.08 14	97.66 331	97.06 359	99.47 155	99.61 178	99.09 162	98.04 459	99.25 340	91.24 446	98.51 364	99.70 205	94.55 278	99.91 132	92.76 435	99.85 91	99.42 250
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 332	97.65 292	97.63 390	98.78 396	97.62 306	99.13 357	98.33 436	97.36 290	99.07 278	98.94 405	95.64 218	99.15 380	92.95 431	98.68 253	96.12 460

our_test_3		97.65 332	97.68 289	97.55 396	98.62 417	94.97 413	98.84 414	99.30 328	96.83 338	98.19 384	99.34 349	97.01 148	99.02 402	95.00 406	96.01 368	98.64 367

testgi		97.65 332	97.50 309	98.13 354	99.36 273	96.45 372	99.42 253	99.48 193	97.76 240	97.87 400	99.45 316	91.09 378	98.81 425	94.53 411	98.52 264	99.13 283

thres200		97.61 335	97.28 346	98.62 294	99.64 156	98.03 279	99.26 326	98.74 416	97.68 251	99.09 275	98.32 435	91.66 368	99.81 221	92.88 432	98.22 284	98.03 430

PAPM		97.59 336	97.09 358	99.07 222	99.06 352	98.26 267	98.30 452	99.10 362	94.88 414	98.08 388	99.34 349	96.27 186	99.64 295	89.87 446	98.92 233	99.31 268

UWE-MVS		97.58 337	97.29 345	98.48 313	99.09 346	96.25 380	99.01 389	96.61 462	97.86 223	99.19 256	99.01 396	88.72 404	99.90 145	97.38 324	98.69 252	99.28 270

SD_0403		97.55 338	97.53 305	97.62 391	99.61 178	93.64 438	99.72 53	99.44 246	98.03 207	98.62 356	99.39 333	96.06 193	99.57 307	87.88 455	99.01 227	99.66 158

VDDNet		97.55 338	97.02 360	99.16 214	99.49 232	98.12 276	99.38 275	99.30 328	95.35 404	99.68 108	99.90 32	82.62 450	99.93 107	99.31 85	98.13 293	99.42 250

TESTMET0.1,1		97.55 338	97.27 349	98.40 329	98.93 373	96.53 369	98.67 429	97.61 451	96.96 327	98.64 351	99.28 364	88.63 410	99.45 320	97.30 328	99.38 180	99.21 279

pmmvs5		97.52 341	97.30 343	98.16 350	98.57 423	96.73 359	99.27 317	98.90 394	96.14 389	98.37 372	99.53 287	91.54 371	99.14 382	97.51 312	95.87 374	98.63 374

LF4IMVS		97.52 341	97.46 316	97.70 388	98.98 368	95.55 395	99.29 307	98.82 404	98.07 192	98.66 344	99.64 243	89.97 391	99.61 303	97.01 345	96.68 351	97.94 438

DTE-MVSNet		97.51 343	97.19 352	98.46 319	98.63 416	98.13 274	99.84 12	99.48 193	96.68 344	97.97 395	99.67 230	92.92 328	98.56 432	96.88 357	92.60 435	98.70 337

testing11		97.50 344	97.10 357	98.71 287	99.20 316	96.91 352	99.29 307	98.82 404	97.89 220	98.21 383	98.40 431	85.63 434	99.83 207	98.45 217	98.04 296	99.37 260

ETVMVS		97.50 344	96.90 364	99.29 196	99.23 309	98.78 223	99.32 296	98.90 394	97.52 272	98.56 361	98.09 445	84.72 441	99.69 280	97.86 273	97.88 302	99.39 256

hse-mvs2		97.50 344	97.14 354	98.59 296	99.49 232	97.05 333	99.28 312	99.22 346	98.94 75	99.66 119	99.42 321	94.93 247	99.65 291	99.48 63	83.80 460	99.08 289

SixPastTwentyTwo		97.50 344	97.33 340	98.03 358	98.65 414	96.23 381	99.77 34	98.68 425	97.14 308	97.90 398	99.93 10	90.45 384	99.18 377	97.00 346	96.43 358	98.67 354

JIA-IIPM		97.50 344	97.02 360	98.93 243	98.73 405	97.80 296	99.30 302	98.97 380	91.73 444	98.91 307	94.86 462	95.10 241	99.71 268	97.58 303	97.98 297	99.28 270

ppachtmachnet_test		97.49 349	97.45 317	97.61 394	98.62 417	95.24 406	98.80 418	99.46 226	96.11 391	98.22 382	99.62 254	96.45 178	98.97 414	93.77 420	95.97 373	98.61 385

test-mter		97.49 349	97.13 356	98.55 306	98.79 393	97.10 327	98.67 429	97.75 448	96.65 347	98.61 357	98.85 411	88.23 414	99.45 320	97.25 330	99.38 180	99.10 284

testing91		97.44 351	97.02 360	98.71 287	99.18 322	96.89 354	99.19 347	99.04 372	97.78 238	98.31 375	98.29 436	85.41 436	99.85 184	98.01 262	97.95 298	99.39 256

tpm2		97.44 351	97.34 337	97.74 386	99.15 336	94.36 428	99.45 233	98.94 383	93.45 433	98.90 309	99.44 317	91.35 374	99.59 305	97.31 327	98.07 295	99.29 269

tpm cat1		97.39 353	97.36 332	97.50 398	99.17 330	93.73 434	99.43 246	99.31 323	91.27 445	98.71 335	99.08 387	94.31 291	99.77 242	96.41 375	98.50 265	99.00 300

UWE-MVS-28		97.36 354	97.24 350	97.75 384	98.84 389	94.44 425	99.24 333	97.58 452	97.98 212	99.00 293	99.00 397	91.35 374	99.53 313	93.75 421	98.39 269	99.27 274

testing99		97.36 354	96.94 363	98.63 293	99.18 322	96.70 360	99.30 302	98.93 384	97.71 246	98.23 380	98.26 437	84.92 439	99.84 193	98.04 261	97.85 305	99.35 262

SSC-MVS3.2		97.34 356	97.15 353	97.93 369	99.02 359	95.76 391	99.48 216	99.58 76	97.62 258	99.09 275	99.53 287	87.95 417	99.27 358	96.42 373	95.66 381	98.75 324

USDC		97.34 356	97.20 351	97.75 384	99.07 350	95.20 407	98.51 442	99.04 372	97.99 211	98.31 375	99.86 70	89.02 400	99.55 311	95.67 392	97.36 339	98.49 396

UniMVSNet_ETH3D		97.32 358	96.81 366	98.87 262	99.40 262	97.46 311	99.51 183	99.53 122	95.86 399	98.54 363	99.77 174	82.44 451	99.66 286	98.68 183	97.52 323	99.50 228

testing3		97.28 359	96.76 368	98.82 271	99.37 270	98.07 278	99.45 233	99.36 289	97.56 265	97.89 399	98.95 404	83.70 445	98.82 424	96.03 381	98.56 261	99.58 199

MVS		97.28 359	96.55 372	99.48 150	98.78 396	98.95 190	99.27 317	99.39 272	83.53 462	98.08 388	99.54 283	96.97 149	99.87 172	94.23 416	99.16 201	99.63 176

test_fmvs2		97.25 361	97.30 343	97.09 409	99.43 250	93.31 441	99.73 51	98.87 399	98.83 85	99.28 229	99.80 141	84.45 442	99.66 286	97.88 270	97.45 331	98.30 413

DSMNet-mixed		97.25 361	97.35 334	96.95 413	97.84 437	93.61 439	99.57 136	96.63 461	96.13 390	98.87 315	98.61 424	94.59 274	97.70 450	95.08 404	98.86 241	99.55 206

MS-PatchMatch		97.24 363	97.32 341	96.99 410	98.45 428	93.51 440	98.82 416	99.32 319	97.41 286	98.13 387	99.30 360	88.99 401	99.56 309	95.68 391	99.80 122	97.90 441

testing222		97.16 364	96.50 373	99.16 214	99.16 332	98.47 258	99.27 317	98.66 427	97.71 246	98.23 380	98.15 440	82.28 453	99.84 193	97.36 325	97.66 311	99.18 280

TransMVSNet (Re)		97.15 365	96.58 371	98.86 265	99.12 338	98.85 209	99.49 210	98.91 392	95.48 403	97.16 419	99.80 141	93.38 317	99.11 391	94.16 418	91.73 438	98.62 376

TinyColmap		97.12 366	96.89 365	97.83 379	99.07 350	95.52 398	98.57 438	98.74 416	97.58 262	97.81 403	99.79 158	88.16 415	99.56 309	95.10 403	97.21 344	98.39 409

K. test v3		97.10 367	96.79 367	98.01 361	98.72 407	96.33 376	99.87 8	97.05 455	97.59 260	96.16 433	99.80 141	88.71 405	99.04 398	96.69 364	96.55 356	98.65 365

Syy-MVS		97.09 368	97.14 354	96.95 413	99.00 362	92.73 445	99.29 307	99.39 272	97.06 319	97.41 409	98.15 440	93.92 306	98.68 430	91.71 439	98.34 271	99.45 246

PatchT		97.03 369	96.44 375	98.79 277	98.99 365	98.34 264	99.16 351	99.07 368	92.13 442	99.52 167	97.31 455	94.54 279	98.98 407	88.54 451	98.73 250	99.03 297

mmtdpeth		96.95 370	96.71 369	97.67 389	99.33 280	94.90 415	99.89 2	99.28 334	98.15 172	99.72 99	98.57 425	86.56 428	99.90 145	99.82 28	89.02 451	98.20 420

myMVS_eth3d		96.89 371	96.37 376	98.43 326	99.00 362	97.16 324	99.29 307	99.39 272	97.06 319	97.41 409	98.15 440	83.46 447	98.68 430	95.27 401	98.34 271	99.45 246

AUN-MVS		96.88 372	96.31 378	98.59 296	99.48 239	97.04 336	99.27 317	99.22 346	97.44 282	98.51 364	99.41 325	91.97 357	99.66 286	97.71 294	83.83 459	99.07 294

FMVSNet1		96.84 373	96.36 377	98.29 339	99.32 287	97.26 320	99.43 246	99.48 193	95.11 408	98.55 362	99.32 357	83.95 444	98.98 407	95.81 386	96.26 363	98.62 376

test2506		96.81 374	96.65 370	97.29 404	99.74 97	92.21 448	99.60 111	85.06 479	99.13 38	99.77 82	99.93 10	87.82 421	99.85 184	99.38 73	99.38 180	99.80 86

RPMNet		96.72 375	95.90 388	99.19 211	99.18 322	98.49 254	99.22 340	99.52 127	88.72 455	99.56 156	97.38 452	94.08 299	99.95 75	86.87 460	98.58 258	99.14 281

mvs5depth		96.66 376	96.22 380	97.97 365	97.00 453	96.28 378	98.66 432	99.03 374	96.61 352	96.93 425	99.79 158	87.20 424	99.47 316	96.65 368	94.13 412	98.16 422

test_0402		96.64 377	96.24 379	97.85 376	98.85 387	96.43 373	99.44 240	99.26 338	93.52 430	96.98 423	99.52 291	88.52 411	99.20 376	92.58 437	97.50 326	97.93 439

X-MVStestdata		96.55 378	95.45 397	99.87 21	99.85 29	99.83 22	99.69 62	99.68 22	98.98 69	99.37 205	64.01 475	98.81 48	99.94 89	98.79 169	99.86 84	99.84 53

pmmvs6		96.53 379	96.09 384	97.82 381	98.69 411	95.47 399	99.37 277	99.47 215	93.46 432	97.41 409	99.78 165	87.06 425	99.33 348	96.92 355	92.70 433	98.65 365

ET-MVSNet_ETH3D		96.49 380	95.64 394	99.05 226	99.53 209	98.82 217	98.84 414	97.51 453	97.63 256	84.77 462	99.21 376	92.09 355	98.91 420	98.98 130	92.21 436	99.41 253

UnsupCasMVSNet_eth		96.44 381	96.12 382	97.40 401	98.65 414	95.65 392	99.36 283	99.51 146	97.13 309	96.04 435	98.99 399	88.40 412	98.17 439	96.71 362	90.27 446	98.40 408

FMVSNet5		96.43 382	96.19 381	97.15 405	99.11 340	95.89 388	99.32 296	99.52 127	94.47 423	98.34 374	99.07 388	87.54 422	97.07 455	92.61 436	95.72 379	98.47 399

new_pmnet		96.38 383	96.03 385	97.41 400	98.13 434	95.16 410	99.05 376	99.20 350	93.94 425	97.39 412	98.79 417	91.61 370	99.04 398	90.43 444	95.77 376	98.05 429

Anonymous20231206		96.22 384	96.03 385	96.79 418	97.31 447	94.14 430	99.63 99	99.08 365	96.17 385	97.04 422	99.06 390	93.94 304	97.76 449	86.96 459	95.06 395	98.47 399

IB-MVS	95.67 18	96.22 384	95.44 398	98.57 300	99.21 314	96.70 360	98.65 433	97.74 450	96.71 342	97.27 414	98.54 426	86.03 431	99.92 120	98.47 215	86.30 456	99.10 284
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		96.20 386	95.89 389	97.13 407	97.72 441	94.96 414	99.79 31	99.29 332	93.01 436	97.20 418	99.03 393	89.69 395	98.36 436	91.16 442	96.13 365	98.07 427

gg-mvs-nofinetune		96.17 387	95.32 399	98.73 282	98.79 393	98.14 273	99.38 275	94.09 470	91.07 448	98.07 391	91.04 468	89.62 397	99.35 345	96.75 360	99.09 219	98.68 346

test20.03		96.12 388	95.96 387	96.63 419	97.44 443	95.45 400	99.51 183	99.38 280	96.55 358	96.16 433	99.25 370	93.76 313	96.17 461	87.35 458	94.22 410	98.27 415

PVSNet_0	94.43 19	96.09 389	95.47 396	97.94 368	99.31 288	94.34 429	97.81 460	99.70 16	97.12 311	97.46 408	98.75 419	89.71 394	99.79 234	97.69 297	81.69 462	99.68 150

MVStest1		96.08 390	95.48 395	97.89 373	98.93 373	96.70 360	99.56 143	99.35 296	92.69 440	91.81 457	99.46 314	89.90 392	98.96 416	95.00 406	92.61 434	98.00 434

EG-PatchMatch MVS		95.97 391	95.69 392	96.81 417	97.78 438	92.79 444	99.16 351	98.93 384	96.16 386	94.08 446	99.22 373	82.72 449	99.47 316	95.67 392	97.50 326	98.17 421

APD_test1		95.87 392	96.49 374	94.00 431	99.53 209	84.01 460	99.54 163	99.32 319	95.91 398	97.99 393	99.85 77	85.49 435	99.88 165	91.96 438	98.84 243	98.12 424

Patchmatch-RL test		95.84 393	95.81 391	95.95 426	95.61 458	90.57 452	98.24 453	98.39 434	95.10 410	95.20 440	98.67 421	94.78 258	97.77 448	96.28 378	90.02 447	99.51 224

test_vis1_rt		95.81 394	95.65 393	96.32 423	99.67 131	91.35 451	99.49 210	96.74 460	98.25 157	95.24 438	98.10 444	74.96 460	99.90 145	99.53 52	98.85 242	97.70 444

sc_t1		95.75 395	95.05 402	97.87 374	98.83 390	94.61 422	99.21 342	99.45 237	87.45 456	97.97 395	99.85 77	81.19 456	99.43 329	98.27 235	93.20 426	99.57 202

MVS-HIRNet		95.75 395	95.16 400	97.51 397	99.30 289	93.69 436	98.88 410	95.78 464	85.09 461	98.78 329	92.65 464	91.29 376	99.37 338	94.85 408	99.85 91	99.46 243

tt0320		95.71 397	95.07 401	97.62 391	99.05 355	95.02 411	99.25 328	99.52 127	86.81 457	97.97 395	99.72 198	83.58 446	99.15 380	96.38 376	93.35 422	98.68 346

MIMVSNet1		95.51 398	95.04 403	96.92 415	97.38 444	95.60 393	99.52 174	99.50 169	93.65 429	96.97 424	99.17 378	85.28 438	96.56 459	88.36 452	95.55 385	98.60 388

MDA-MVSNet_test_wron		95.45 399	94.60 406	98.01 361	98.16 433	97.21 323	99.11 366	99.24 343	93.49 431	80.73 468	98.98 401	93.02 325	98.18 438	94.22 417	94.45 406	98.64 367

TDRefinement		95.42 400	94.57 408	97.97 365	89.83 472	96.11 385	99.48 216	98.75 413	96.74 340	96.68 427	99.88 51	88.65 408	99.71 268	98.37 225	82.74 461	98.09 426

YYNet1		95.36 401	94.51 409	97.92 370	97.89 436	97.10 327	99.10 368	99.23 344	93.26 434	80.77 467	99.04 392	92.81 331	98.02 442	94.30 413	94.18 411	98.64 367

pmmvs-eth3d		95.34 402	94.73 405	97.15 405	95.53 460	95.94 387	99.35 288	99.10 362	95.13 406	93.55 449	97.54 450	88.15 416	97.91 445	94.58 410	89.69 450	97.61 445

tt0320-xc		95.31 403	94.59 407	97.45 399	98.92 375	94.73 417	99.20 345	99.31 323	86.74 458	97.23 415	99.72 198	81.14 457	98.95 417	97.08 343	91.98 437	98.67 354

dmvs_testset		95.02 404	96.12 382	91.72 440	99.10 343	80.43 468	99.58 128	97.87 447	97.47 275	95.22 439	98.82 413	93.99 302	95.18 465	88.09 453	94.91 400	99.56 205

KD-MVS_self_test		95.00 405	94.34 410	96.96 412	97.07 452	95.39 403	99.56 143	99.44 246	95.11 408	97.13 420	97.32 454	91.86 360	97.27 454	90.35 445	81.23 463	98.23 419

MDA-MVSNet-bldmvs		94.96 406	93.98 413	97.92 370	98.24 432	97.27 318	99.15 354	99.33 309	93.80 427	80.09 469	99.03 393	88.31 413	97.86 447	93.49 425	94.36 408	98.62 376

N_pmnet		94.95 407	95.83 390	92.31 438	98.47 427	79.33 470	99.12 360	92.81 476	93.87 426	97.68 405	99.13 383	93.87 308	99.01 404	91.38 441	96.19 364	98.59 389

KD-MVS_2432*1600		94.62 408	93.72 416	97.31 402	97.19 450	95.82 389	98.34 448	99.20 350	95.00 412	97.57 406	98.35 433	87.95 417	98.10 440	92.87 433	77.00 466	98.01 431

miper_refine_blended		94.62 408	93.72 416	97.31 402	97.19 450	95.82 389	98.34 448	99.20 350	95.00 412	97.57 406	98.35 433	87.95 417	98.10 440	92.87 433	77.00 466	98.01 431

CL-MVSNet_self_test		94.49 410	93.97 414	96.08 425	96.16 455	93.67 437	98.33 450	99.38 280	95.13 406	97.33 413	98.15 440	92.69 339	96.57 458	88.67 450	79.87 464	97.99 435

new-patchmatchnet		94.48 411	94.08 412	95.67 427	95.08 463	92.41 446	99.18 349	99.28 334	94.55 422	93.49 450	97.37 453	87.86 420	97.01 456	91.57 440	88.36 452	97.61 445

OpenMVS_ROB	92.34 20	94.38 412	93.70 418	96.41 422	97.38 444	93.17 442	99.06 374	98.75 413	86.58 459	94.84 444	98.26 437	81.53 454	99.32 350	89.01 449	97.87 303	96.76 453

CMPMVS	69.68 23	94.13 413	94.90 404	91.84 439	97.24 448	80.01 469	98.52 441	99.48 193	89.01 453	91.99 456	99.67 230	85.67 433	99.13 385	95.44 396	97.03 349	96.39 457
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 414	93.25 421	96.60 420	94.76 465	94.49 424	98.92 406	98.18 443	89.66 449	96.48 429	98.06 446	86.28 430	97.33 453	89.68 447	87.20 455	97.97 437

FE-MVSNET		94.07 415	93.36 420	96.22 424	94.05 466	94.71 419	99.56 143	98.36 435	93.15 435	93.76 448	97.55 449	86.47 429	96.49 460	87.48 456	89.83 449	97.48 449

mvsany_test3		93.77 416	93.45 419	94.74 429	95.78 457	88.01 455	99.64 93	98.25 438	98.28 147	94.31 445	97.97 447	68.89 463	98.51 434	97.50 313	90.37 445	97.71 442

UnsupCasMVSNet_bld		93.53 417	92.51 423	96.58 421	97.38 444	93.82 432	98.24 453	99.48 193	91.10 447	93.10 451	96.66 457	74.89 461	98.37 435	94.03 419	87.71 454	97.56 447

dongtai		93.26 418	92.93 422	94.25 430	99.39 265	85.68 458	97.68 462	93.27 472	92.87 438	96.85 426	99.39 333	82.33 452	97.48 452	76.78 466	97.80 306	99.58 199

WB-MVS		93.10 419	94.10 411	90.12 445	95.51 462	81.88 465	99.73 51	99.27 337	95.05 411	93.09 452	98.91 410	94.70 267	91.89 469	76.62 467	94.02 416	96.58 455

PM-MVS		92.96 420	92.23 424	95.14 428	95.61 458	89.98 454	99.37 277	98.21 441	94.80 417	95.04 443	97.69 448	65.06 464	97.90 446	94.30 413	89.98 448	97.54 448

SSC-MVS		92.73 421	93.73 415	89.72 446	95.02 464	81.38 466	99.76 37	99.23 344	94.87 415	92.80 453	98.93 406	94.71 266	91.37 470	74.49 469	93.80 418	96.42 456

test_fmvs3		92.10 422	91.77 425	93.08 436	96.19 454	86.25 456	99.82 16	98.62 429	96.65 347	95.19 441	96.90 456	55.05 471	95.93 463	96.63 369	90.92 444	97.06 452

test_f		91.90 423	91.26 427	93.84 432	95.52 461	85.92 457	99.69 62	98.53 433	95.31 405	93.87 447	96.37 459	55.33 470	98.27 437	95.70 389	90.98 443	97.32 451

test_method		91.10 424	91.36 426	90.31 444	95.85 456	73.72 477	94.89 466	99.25 340	68.39 468	95.82 436	99.02 395	80.50 458	98.95 417	93.64 423	94.89 401	98.25 417

Gipuma		90.99 425	90.15 430	93.51 433	98.73 405	90.12 453	93.98 467	99.45 237	79.32 464	92.28 454	94.91 461	69.61 462	97.98 444	87.42 457	95.67 380	92.45 464
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 426	90.11 431	93.34 434	98.78 396	85.59 459	98.15 457	93.16 474	89.37 452	92.07 455	98.38 432	81.48 455	95.19 464	62.54 473	97.04 348	99.25 275

testf1		90.42 427	90.68 428	89.65 447	97.78 438	73.97 475	99.13 357	98.81 406	89.62 450	91.80 458	98.93 406	62.23 467	98.80 426	86.61 461	91.17 440	96.19 458

APD_test2		90.42 427	90.68 428	89.65 447	97.78 438	73.97 475	99.13 357	98.81 406	89.62 450	91.80 458	98.93 406	62.23 467	98.80 426	86.61 461	91.17 440	96.19 458

test_vis3_rt		87.04 429	85.81 432	90.73 443	93.99 467	81.96 464	99.76 37	90.23 478	92.81 439	81.35 466	91.56 466	40.06 475	99.07 395	94.27 415	88.23 453	91.15 466

PMMVS2		86.87 430	85.37 434	91.35 442	90.21 471	83.80 461	98.89 409	97.45 454	83.13 463	91.67 460	95.03 460	48.49 473	94.70 466	85.86 463	77.62 465	95.54 461

LCM-MVSNet		86.80 431	85.22 435	91.53 441	87.81 473	80.96 467	98.23 455	98.99 378	71.05 466	90.13 461	96.51 458	48.45 474	96.88 457	90.51 443	85.30 457	96.76 453

FPMVS		84.93 432	85.65 433	82.75 453	86.77 474	63.39 479	98.35 447	98.92 387	74.11 465	83.39 464	98.98 401	50.85 472	92.40 468	84.54 464	94.97 397	92.46 463

EGC-MVSNET		82.80 433	77.86 439	97.62 391	97.91 435	96.12 384	99.33 293	99.28 334	8.40 476	25.05 477	99.27 367	84.11 443	99.33 348	89.20 448	98.22 284	97.42 450

tmp_tt		82.80 433	81.52 436	86.66 449	66.61 479	68.44 478	92.79 469	97.92 445	68.96 467	80.04 470	99.85 77	85.77 432	96.15 462	97.86 273	43.89 472	95.39 462

E-PMN		80.61 435	79.88 437	82.81 452	90.75 470	76.38 473	97.69 461	95.76 465	66.44 470	83.52 463	92.25 465	62.54 466	87.16 472	68.53 471	61.40 469	84.89 470

EMVS		80.02 436	79.22 438	82.43 454	91.19 469	76.40 472	97.55 464	92.49 477	66.36 471	83.01 465	91.27 467	64.63 465	85.79 473	65.82 472	60.65 470	85.08 469

ANet_high		77.30 437	74.86 441	84.62 451	75.88 477	77.61 471	97.63 463	93.15 475	88.81 454	64.27 472	89.29 469	36.51 476	83.93 474	75.89 468	52.31 471	92.33 465

MVE	76.82 21	76.91 438	74.31 442	84.70 450	85.38 476	76.05 474	96.88 465	93.17 473	67.39 469	71.28 471	89.01 470	21.66 481	87.69 471	71.74 470	72.29 468	90.35 467
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 439	74.97 440	79.01 455	70.98 478	55.18 480	93.37 468	98.21 441	65.08 472	61.78 473	93.83 463	21.74 480	92.53 467	78.59 465	91.12 442	89.34 468
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		40.18 440	41.29 445	36.84 456	86.18 475	49.12 481	79.73 470	22.81 481	27.64 473	25.46 476	28.45 476	21.98 479	48.89 475	55.80 474	23.56 475	12.51 473

testmvs		39.17 441	43.78 443	25.37 458	36.04 481	16.84 483	98.36 446	26.56 480	20.06 474	38.51 475	67.32 471	29.64 478	15.30 477	37.59 475	39.90 473	43.98 472

test123		39.01 442	42.50 444	28.53 457	39.17 480	20.91 482	98.75 423	19.17 482	19.83 475	38.57 474	66.67 472	33.16 477	15.42 476	37.50 476	29.66 474	49.26 471

cdsmvs_eth3d_5k		24.64 443	32.85 446	0.00 459	0.00 482	0.00 484	0.00 471	99.51 146	0.00 477	0.00 478	99.56 275	96.58 171	0.00 478	0.00 477	0.00 476	0.00 474

ab-mvs-re		8.30 444	11.06 447	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	99.58 267	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

pcd_1.5k_mvsjas		8.27 445	11.03 448	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	99.01 19	0.00 478	0.00 477	0.00 476	0.00 474

test_blank		0.13 446	0.17 449	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	1.57 477	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

mmdepth		0.02 447	0.03 450	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

monomultidepth		0.02 447	0.03 450	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

uanet_test		0.02 447	0.03 450	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

DCPMVS		0.02 447	0.03 450	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

sosnet-low-res		0.02 447	0.03 450	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

sosnet		0.02 447	0.03 450	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

uncertanet		0.02 447	0.03 450	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

Regformer		0.02 447	0.03 450	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

uanet		0.02 447	0.03 450	0.00 459	0.00 482	0.00 484	0.00 471	0.00 483	0.00 477	0.00 478	0.27 478	0.00 482	0.00 478	0.00 477	0.00 476	0.00 474

TestfortrainingZip							99.69 62

WAC-MVS						97.16 324								95.47 395

FOURS1					99.91 1	99.93 1	99.87 8	99.56 88	99.10 45	99.81 66

MSC_two_6792asdad				99.87 21	99.51 218	99.76 47		99.33 309					99.96 40	98.87 150	99.84 99	99.89 29

PC_three_1452									98.18 170	99.84 53	99.70 205	99.31 3	98.52 433	98.30 234	99.80 122	99.81 77

No_MVS				99.87 21	99.51 218	99.76 47		99.33 309					99.96 40	98.87 150	99.84 99	99.89 29

test_one_0601					99.81 54	99.88 10		99.49 181	98.97 72	99.65 128	99.81 123	99.09 15

eth-test2					0.00 482

eth-test					0.00 482

ZD-MVS					99.71 114	99.79 39		99.61 58	96.84 336	99.56 156	99.54 283	98.58 77	99.96 40	96.93 353	99.75 139

RE-MVS-def			99.34 49		99.76 79	99.82 28	99.63 99	99.52 127	98.38 134	99.76 88	99.82 108	98.75 59		98.61 193	99.81 117	99.77 98

IU-MVS					99.84 36	99.88 10		99.32 319	98.30 146	99.84 53				98.86 155	99.85 91	99.89 29

OPU-MVS				99.64 98	99.56 197	99.72 54	99.60 111				99.70 205	99.27 6	99.42 331	98.24 238	99.80 122	99.79 90

test_241102_TWO								99.48 193	99.08 53	99.88 40	99.81 123	98.94 33	99.96 40	98.91 144	99.84 99	99.88 35

test_241102_ONE					99.84 36	99.90 3		99.48 193	99.07 55	99.91 30	99.74 188	99.20 8	99.76 246

9.14			99.10 97		99.72 108		99.40 266	99.51 146	97.53 270	99.64 133	99.78 165	98.84 45	99.91 132	97.63 299	99.82 114

save fliter					99.76 79	99.59 85	99.14 356	99.40 269	99.00 64

test_0728_THIRD									98.99 66	99.81 66	99.80 141	99.09 15	99.96 40	98.85 157	99.90 56	99.88 35

test_0728_SECOND				99.91 6	99.84 36	99.89 6	99.57 136	99.51 146					99.96 40	98.93 141	99.86 84	99.88 35

test0726					99.85 29	99.89 6	99.62 104	99.50 169	99.10 45	99.86 50	99.82 108	98.94 33

GSMVS																99.52 215

test_part2					99.81 54	99.83 22				99.77 82

sam_mvs1												94.86 253				99.52 215

sam_mvs												94.72 265

ambc				93.06 437	92.68 468	82.36 462	98.47 443	98.73 422		95.09 442	97.41 451	55.55 469	99.10 393	96.42 373	91.32 439	97.71 442

MTGPA								99.47 215

test_post1							99.23 336				65.14 474	94.18 296	99.71 268	97.58 303

test_post											65.99 473	94.65 272	99.73 258

patchmatchnet-post											98.70 420	94.79 257	99.74 252

GG-mvs-BLEND				98.45 321	98.55 424	98.16 271	99.43 246	93.68 471		97.23 415	98.46 428	89.30 398	99.22 369	95.43 397	98.22 284	97.98 436

MTMP							99.54 163	98.88 397

gm-plane-assit					98.54 425	92.96 443			94.65 420		99.15 381		99.64 295	97.56 308

test9_res														97.49 314	99.72 145	99.75 107

TEST9					99.67 131	99.65 72	99.05 376	99.41 262	96.22 381	98.95 302	99.49 301	98.77 55	99.91 132

test_8					99.67 131	99.61 82	99.03 381	99.41 262	96.28 375	98.93 305	99.48 307	98.76 56	99.91 132

agg_prior2														97.21 332	99.73 144	99.75 107

agg_prior					99.67 131	99.62 80		99.40 269		98.87 315			99.91 132

TestCases				99.31 188	99.86 23	98.48 256		99.61 58	97.85 226	99.36 211	99.85 77	95.95 199	99.85 184	96.66 366	99.83 110	99.59 195

test_prior4						99.56 91	98.99 392

test_prior2							98.96 399		98.34 140	99.01 289	99.52 291	98.68 69		97.96 265	99.74 142

test_prior				99.68 86	99.67 131	99.48 108		99.56 88					99.83 207			99.74 111

旧先验2							98.96 399		96.70 343	99.47 175			99.94 89	98.19 241

新几何2							99.01 389

新几何1				99.75 74	99.75 89	99.59 85		99.54 106	96.76 339	99.29 228	99.64 243	98.43 88	99.94 89	96.92 355	99.66 156	99.72 129

旧先验1					99.74 97	99.59 85		99.54 106			99.69 216	98.47 85			99.68 153	99.73 120

无先验							98.99 392	99.51 146	96.89 333				99.93 107	97.53 311		99.72 129

原ACMM2							98.95 402

原ACMM1				99.65 92	99.73 104	99.33 127		99.47 215	97.46 276	99.12 267	99.66 235	98.67 71	99.91 132	97.70 296	99.69 150	99.71 138

test222					99.75 89	99.49 106	98.91 408	99.49 181	96.42 369	99.34 218	99.65 237	98.28 99			99.69 150	99.72 129

testdata2													99.95 75	96.67 365

segment_acmp												98.96 26

testdata				99.54 122	99.75 89	98.95 190		99.51 146	97.07 317	99.43 186	99.70 205	98.87 41	99.94 89	97.76 287	99.64 159	99.72 129

testdata1							98.85 413		98.32 144

test12				99.75 74	99.64 156	99.61 82		99.29 332		99.21 250		98.38 94	99.89 160		99.74 142	99.74 111

plane_prior7					99.29 293	97.03 339

plane_prior6					99.27 298	96.98 343						92.71 337

plane_prior5								99.47 215					99.69 280	97.78 283	97.63 312	98.67 354

plane_prior4											99.61 258

plane_prior3						97.00 341			98.69 104	99.11 269

plane_prior2							99.39 270		98.97 72

plane_prior1					99.26 301

plane_prior						96.97 344	99.21 342		98.45 127						97.60 315

n2								0.00 483

nn								0.00 483

door-mid								98.05 444

lessismore_v0				97.79 383	98.69 411	95.44 402		94.75 468		95.71 437	99.87 62	88.69 406	99.32 350	95.89 384	94.93 399	98.62 376

LGP-MVS_train				98.49 311	99.33 280	97.05 333		99.55 97	97.46 276	99.24 242	99.83 97	92.58 342	99.72 262	98.09 252	97.51 324	98.68 346

test11								99.35 296

door								97.92 445

HQP5-MVS						96.83 355

HQP-NCC					99.19 319		98.98 395		98.24 159	98.66 344

ACMP_Plane					99.19 319		98.98 395		98.24 159	98.66 344

BP-MVS														97.19 336

HQP4-MVS										98.66 344			99.64 295			98.64 367

HQP3-MVS								99.39 272							97.58 317

HQP2-MVS												92.47 346

NP-MVS					99.23 309	96.92 351					99.40 329

MDTV_nov1_ep13_2view						95.18 409	99.35 288		96.84 336	99.58 152		95.19 238		97.82 278		99.46 243

MDTV_nov1_ep13			98.32 222		99.11 340	94.44 425	99.27 317	98.74 416	97.51 273	99.40 199	99.62 254	94.78 258	99.76 246	97.59 302	98.81 247

ACMMP++_ref															97.19 345

ACMMP++															97.43 335

Test By Simon												98.75 59

ITE_SJBPF				98.08 356	99.29 293	96.37 374		98.92 387	98.34 140	98.83 321	99.75 183	91.09 378	99.62 302	95.82 385	97.40 337	98.25 417

DeepMVS_CX				93.34 434	99.29 293	82.27 463		99.22 346	85.15 460	96.33 430	99.05 391	90.97 380	99.73 258	93.57 424	97.77 308	98.01 431

High-resolution multi-view benchmark