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 26	99.90 34	99.83 101	99.30 4	99.95 76	99.32 84	99.89 68	99.90 25

fmvsm_l_conf0.5_n_a		99.71 2	99.67 1	99.85 43	99.86 25	99.61 85	99.56 146	99.63 46	99.48 3	99.98 13	99.83 101	98.75 60	99.99 4	99.97 2	99.96 17	99.94 17

fmvsm_l_conf0.5_n		99.71 2	99.67 1	99.85 43	99.84 38	99.63 82	99.56 146	99.63 46	99.47 4	99.98 13	99.82 114	98.75 60	99.99 4	99.97 2	99.97 9	99.94 17

test_fmvsmconf_n		99.70 4	99.64 5	99.87 21	99.80 63	99.66 71	99.48 222	99.64 42	99.45 11	99.92 30	99.92 18	98.62 76	99.99 4	99.96 13	99.99 1	99.96 7

test_fmvsm_n_1920		99.69 5	99.66 4	99.78 71	99.84 38	99.44 116	99.58 130	99.69 22	99.43 17	99.98 13	99.91 26	98.62 76	100.00 1	99.97 2	99.95 23	99.90 25

MED-MVS		99.66 6	99.60 8	99.87 21	99.88 13	99.81 33	99.69 62	99.87 6	99.18 34	99.90 34	99.83 101	99.30 4	99.95 76	98.83 167	99.89 68	99.83 63

APDe-MVS		99.66 6	99.57 10	99.92 1	99.77 78	99.89 6	99.75 42	99.56 90	99.02 62	99.88 43	99.85 80	99.18 12	99.96 41	99.22 100	99.92 39	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 8	99.61 7	99.77 74	99.38 273	99.37 123	99.58 130	99.62 51	99.41 21	99.87 49	99.92 18	98.81 49	100.00 1	99.97 2	99.93 33	99.94 17

reproduce_model		99.63 9	99.54 13	99.90 8	99.78 70	99.88 10	99.56 146	99.55 100	99.15 38	99.90 34	99.90 33	99.00 24	99.97 29	99.11 117	99.91 46	99.86 42

fmvsm_l_conf0.5_n_3		99.61 10	99.51 18	99.92 1	99.84 38	99.82 28	99.54 166	99.66 32	99.46 7	99.98 13	99.89 41	97.27 133	99.99 4	99.97 2	99.95 23	99.95 11

reproduce-ours		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 177	99.54 109	99.13 41	99.89 40	99.89 41	98.96 27	99.96 41	99.04 127	99.90 57	99.85 46

our_new_method		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 177	99.54 109	99.13 41	99.89 40	99.89 41	98.96 27	99.96 41	99.04 127	99.90 57	99.85 46

SED-MVS		99.61 10	99.52 14	99.88 15	99.84 38	99.90 3	99.60 113	99.48 199	99.08 56	99.91 31	99.81 129	99.20 9	99.96 41	98.91 148	99.85 94	99.79 92

lecture		99.60 14	99.50 19	99.89 11	99.89 8	99.90 3	99.75 42	99.59 73	99.06 61	99.88 43	99.85 80	98.41 93	99.96 41	99.28 92	99.84 102	99.83 63

DVP-MVS++		99.59 15	99.50 19	99.88 15	99.51 224	99.88 10	99.87 8	99.51 151	98.99 69	99.88 43	99.81 129	99.27 7	99.96 41	98.85 161	99.80 125	99.81 79

fmvsm_l_conf0.5_n_9		99.58 16	99.47 24	99.92 1	99.85 31	99.82 28	99.47 232	99.63 46	99.45 11	99.98 13	99.89 41	97.02 148	99.99 4	99.98 1	99.96 17	99.95 11

TSAR-MVS + MP.		99.58 16	99.50 19	99.81 60	99.91 1	99.66 71	99.63 101	99.39 278	98.91 82	99.78 81	99.85 80	99.36 2	99.94 92	98.84 164	99.88 76	99.82 72
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 16	99.57 10	99.64 101	99.78 70	99.14 160	99.60 113	99.45 243	99.01 64	99.90 34	99.83 101	98.98 26	99.93 110	99.59 45	99.95 23	99.86 42

EI-MVSNet-Vis-set		99.58 16	99.56 12	99.64 101	99.78 70	99.15 159	99.61 112	99.45 243	99.01 64	99.89 40	99.82 114	99.01 20	99.92 123	99.56 49	99.95 23	99.85 46

DVP-MVS		99.57 20	99.47 24	99.88 15	99.85 31	99.89 6	99.57 138	99.37 295	99.10 48	99.81 69	99.80 147	98.94 34	99.96 41	98.93 145	99.86 87	99.81 79
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
ME-MVS		99.56 21	99.46 28	99.86 34	99.80 63	99.81 33	99.37 284	99.70 18	99.18 34	99.83 64	99.83 101	98.74 65	99.93 110	98.83 167	99.89 68	99.83 63

fmvsm_s_conf0.5_n_a		99.56 21	99.47 24	99.85 43	99.83 47	99.64 81	99.52 177	99.65 39	99.10 48	99.98 13	99.92 18	97.35 129	99.96 41	99.94 21	99.92 39	99.95 11

test_fmvsmconf0.1_n		99.55 23	99.45 30	99.86 34	99.44 255	99.65 75	99.50 197	99.61 60	99.45 11	99.87 49	99.92 18	97.31 130	99.97 29	99.95 16	99.99 1	99.97 4

fmvsm_s_conf0.5_n_8		99.54 24	99.42 32	99.89 11	99.83 47	99.74 54	99.51 186	99.62 51	99.46 7	99.99 2	99.90 33	96.60 172	99.98 20	99.95 16	99.95 23	99.96 7

fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 224	99.67 68	99.50 197	99.64 42	99.43 17	99.98 13	99.78 171	97.26 136	99.95 76	99.95 16	99.93 33	99.92 23

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 21	99.82 53	99.81 33	99.59 120	99.51 151	98.62 112	99.79 76	99.83 101	99.28 6	99.97 29	98.48 218	99.90 57	99.84 53
Skip Steuart: Steuart Systems R&D Blog.
XVS		99.53 27	99.42 32	99.87 21	99.85 31	99.83 22	99.69 62	99.68 24	98.98 72	99.37 211	99.74 194	98.81 49	99.94 92	98.79 175	99.86 87	99.84 53

MTAPA		99.52 28	99.39 40	99.89 11	99.90 4	99.86 18	99.66 82	99.47 221	98.79 95	99.68 114	99.81 129	98.43 89	99.97 29	98.88 151	99.90 57	99.83 63

fmvsm_s_conf0.5_n		99.51 29	99.40 38	99.85 43	99.84 38	99.65 75	99.51 186	99.67 27	99.13 41	99.98 13	99.92 18	96.60 172	99.96 41	99.95 16	99.96 17	99.95 11

HPM-MVS_fast		99.51 29	99.40 38	99.85 43	99.91 1	99.79 41	99.76 37	99.56 90	97.72 251	99.76 91	99.75 189	99.13 14	99.92 123	99.07 124	99.92 39	99.85 46

mvsany_test1		99.50 31	99.46 28	99.62 108	99.61 184	99.09 165	98.94 412	99.48 199	99.10 48	99.96 27	99.91 26	98.85 44	99.96 41	99.72 32	99.58 169	99.82 72

CS-MVS		99.50 31	99.48 22	99.54 125	99.76 82	99.42 118	99.90 1	99.55 100	98.56 118	99.78 81	99.70 211	98.65 74	99.79 240	99.65 41	99.78 134	99.41 259

SPE-MVS-test		99.49 33	99.48 22	99.54 125	99.78 70	99.30 138	99.89 2	99.58 78	98.56 118	99.73 97	99.69 222	98.55 81	99.82 222	99.69 35	99.85 94	99.48 238

HFP-MVS		99.49 33	99.37 44	99.86 34	99.87 20	99.80 38	99.66 82	99.67 27	98.15 175	99.68 114	99.69 222	99.06 18	99.96 41	98.69 187	99.87 79	99.84 53

ACMMPR		99.49 33	99.36 46	99.86 34	99.87 20	99.79 41	99.66 82	99.67 27	98.15 175	99.67 120	99.69 222	98.95 32	99.96 41	98.69 187	99.87 79	99.84 53

DeepC-MVS_fast	98.69 1	99.49 33	99.39 40	99.77 74	99.63 164	99.59 88	99.36 290	99.46 232	99.07 58	99.79 76	99.82 114	98.85 44	99.92 123	98.68 189	99.87 79	99.82 72
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 37	99.35 48	99.87 21	99.88 13	99.80 38	99.65 88	99.66 32	98.13 183	99.66 125	99.68 230	98.96 27	99.96 41	98.62 196	99.87 79	99.84 53

APD-MVS_3200maxsize		99.48 37	99.35 48	99.85 43	99.76 82	99.83 22	99.63 101	99.54 109	98.36 141	99.79 76	99.82 114	98.86 43	99.95 76	98.62 196	99.81 120	99.78 98

DELS-MVS		99.48 37	99.42 32	99.65 95	99.72 111	99.40 121	99.05 384	99.66 32	99.14 40	99.57 161	99.80 147	98.46 87	99.94 92	99.57 48	99.84 102	99.60 190
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 40	99.33 52	99.87 21	99.87 20	99.81 33	99.64 95	99.67 27	98.08 196	99.55 168	99.64 249	98.91 39	99.96 41	98.72 182	99.90 57	99.82 72

ACMMP_NAP		99.47 40	99.34 50	99.88 15	99.87 20	99.86 18	99.47 232	99.48 199	98.05 204	99.76 91	99.86 73	98.82 48	99.93 110	98.82 174	99.91 46	99.84 53

MVSMamba_PlusPlus		99.46 42	99.41 37	99.64 101	99.68 132	99.50 108	99.75 42	99.50 174	98.27 152	99.87 49	99.92 18	98.09 108	99.94 92	99.65 41	99.95 23	99.47 244

balanced_conf03		99.46 42	99.39 40	99.67 90	99.55 207	99.58 93	99.74 47	99.51 151	98.42 134	99.87 49	99.84 95	98.05 111	99.91 135	99.58 47	99.94 31	99.52 221

DPE-MVS		99.46 42	99.32 54	99.91 6	99.78 70	99.88 10	99.36 290	99.51 151	98.73 102	99.88 43	99.84 95	98.72 67	99.96 41	98.16 251	99.87 79	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 42	99.47 24	99.44 169	99.60 190	99.16 155	99.41 265	99.71 16	98.98 72	99.45 184	99.78 171	99.19 11	99.54 318	99.28 92	99.84 102	99.63 182

SR-MVS-dyc-post		99.45 46	99.31 60	99.85 43	99.76 82	99.82 28	99.63 101	99.52 130	98.38 137	99.76 91	99.82 114	98.53 82	99.95 76	98.61 199	99.81 120	99.77 100

PGM-MVS		99.45 46	99.31 60	99.86 34	99.87 20	99.78 47	99.58 130	99.65 39	97.84 235	99.71 108	99.80 147	99.12 15	99.97 29	98.33 236	99.87 79	99.83 63

CP-MVS		99.45 46	99.32 54	99.85 43	99.83 47	99.75 51	99.69 62	99.52 130	98.07 197	99.53 171	99.63 255	98.93 38	99.97 29	98.74 179	99.91 46	99.83 63

ACMMP		99.45 46	99.32 54	99.82 57	99.89 8	99.67 68	99.62 106	99.69 22	98.12 186	99.63 142	99.84 95	98.73 66	99.96 41	98.55 214	99.83 113	99.81 79
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 50	99.30 62	99.85 43	99.73 107	99.83 22	99.56 146	99.47 221	97.45 285	99.78 81	99.82 114	99.18 12	99.91 135	98.79 175	99.89 68	99.81 79
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 50	99.30 62	99.86 34	99.88 13	99.79 41	99.69 62	99.48 199	98.12 186	99.50 176	99.75 189	98.78 53	99.97 29	98.57 208	99.89 68	99.83 63

EC-MVSNet		99.44 50	99.39 40	99.58 116	99.56 203	99.49 109	99.88 4	99.58 78	98.38 137	99.73 97	99.69 222	98.20 103	99.70 281	99.64 43	99.82 117	99.54 214

SR-MVS		99.43 53	99.29 66	99.86 34	99.75 92	99.83 22	99.59 120	99.62 51	98.21 168	99.73 97	99.79 164	98.68 70	99.96 41	98.44 224	99.77 137	99.79 92

MCST-MVS		99.43 53	99.30 62	99.82 57	99.79 68	99.74 54	99.29 315	99.40 275	98.79 95	99.52 173	99.62 260	98.91 39	99.90 148	98.64 193	99.75 142	99.82 72

MSP-MVS		99.42 55	99.27 73	99.88 15	99.89 8	99.80 38	99.67 75	99.50 174	98.70 106	99.77 85	99.49 307	98.21 102	99.95 76	98.46 222	99.77 137	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 55	99.29 66	99.80 64	99.62 173	99.55 96	99.50 197	99.70 18	98.79 95	99.77 85	99.96 1	97.45 124	99.96 41	98.92 147	99.90 57	99.89 29

HPM-MVS		99.42 55	99.28 69	99.83 56	99.90 4	99.72 56	99.81 20	99.54 109	97.59 266	99.68 114	99.63 255	98.91 39	99.94 92	98.58 205	99.91 46	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 55	99.30 62	99.78 71	99.62 173	99.71 58	99.26 334	99.52 130	98.82 89	99.39 207	99.71 207	98.96 27	99.85 187	98.59 204	99.80 125	99.77 100

fmvsm_s_conf0.5_n_10		99.41 59	99.24 78	99.92 1	99.83 47	99.84 20	99.53 175	99.56 90	99.45 11	99.99 2	99.92 18	94.92 253	99.99 4	99.97 2	99.97 9	99.95 11

fmvsm_s_conf0.5_n_9		99.41 59	99.28 69	99.81 60	99.84 38	99.52 105	99.48 222	99.62 51	99.46 7	99.99 2	99.92 18	95.24 240	99.96 41	99.97 2	99.97 9	99.96 7

SD-MVS		99.41 59	99.52 14	99.05 232	99.74 100	99.68 64	99.46 236	99.52 130	99.11 47	99.88 43	99.91 26	99.43 1	97.70 456	98.72 182	99.93 33	99.77 100
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 59	99.33 52	99.65 95	99.77 78	99.51 107	98.94 412	99.85 9	98.82 89	99.65 134	99.74 194	98.51 84	99.80 234	98.83 167	99.89 68	99.64 177

MVS_111021_HR		99.41 59	99.32 54	99.66 91	99.72 111	99.47 113	98.95 410	99.85 9	98.82 89	99.54 169	99.73 200	98.51 84	99.74 258	98.91 148	99.88 76	99.77 100

MM		99.40 64	99.28 69	99.74 80	99.67 134	99.31 135	99.52 177	98.87 407	99.55 1	99.74 95	99.80 147	96.47 180	99.98 20	99.97 2	99.97 9	99.94 17

GST-MVS		99.40 64	99.24 78	99.85 43	99.86 25	99.79 41	99.60 113	99.67 27	97.97 219	99.63 142	99.68 230	98.52 83	99.95 76	98.38 229	99.86 87	99.81 79

HPM-MVS++		99.39 66	99.23 82	99.87 21	99.75 92	99.84 20	99.43 253	99.51 151	98.68 109	99.27 241	99.53 293	98.64 75	99.96 41	98.44 224	99.80 125	99.79 92

SF-MVS		99.38 67	99.24 78	99.79 68	99.79 68	99.68 64	99.57 138	99.54 109	97.82 241	99.71 108	99.80 147	98.95 32	99.93 110	98.19 247	99.84 102	99.74 113

fmvsm_s_conf0.5_n_5		99.37 68	99.21 84	99.86 34	99.80 63	99.68 64	99.42 260	99.61 60	99.37 24	99.97 25	99.86 73	94.96 248	99.99 4	99.97 2	99.93 33	99.92 23

fmvsm_s_conf0.5_n_3		99.37 68	99.20 86	99.87 21	99.75 92	99.70 60	99.48 222	99.66 32	99.45 11	99.99 2	99.93 10	94.64 277	99.97 29	99.94 21	99.97 9	99.95 11

fmvsm_s_conf0.1_n_2		99.37 68	99.22 83	99.81 60	99.77 78	99.75 51	99.46 236	99.60 67	99.47 4	99.98 13	99.94 6	94.98 247	99.95 76	99.97 2	99.79 132	99.73 122

MP-MVS-pluss		99.37 68	99.20 86	99.88 15	99.90 4	99.87 17	99.30 310	99.52 130	97.18 311	99.60 154	99.79 164	98.79 52	99.95 76	98.83 167	99.91 46	99.83 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_4		99.36 72	99.24 78	99.73 83	99.78 70	99.53 101	99.49 214	99.60 67	99.42 20	99.99 2	99.86 73	95.15 243	99.95 76	99.95 16	99.89 68	99.73 122

TSAR-MVS + GP.		99.36 72	99.36 46	99.36 183	99.67 134	98.61 245	99.07 378	99.33 317	99.00 67	99.82 68	99.81 129	99.06 18	99.84 196	99.09 122	99.42 181	99.65 170

PVSNet_Blended_VisFu		99.36 72	99.28 69	99.61 109	99.86 25	99.07 170	99.47 232	99.93 2	97.66 260	99.71 108	99.86 73	97.73 119	99.96 41	99.47 66	99.82 117	99.79 92

fmvsm_s_conf0.5_n_7		99.34 75	99.29 66	99.48 155	99.70 122	98.63 241	99.42 260	99.63 46	99.46 7	99.98 13	99.88 52	95.59 223	99.96 41	99.97 2	99.98 4	99.85 46

NCCC		99.34 75	99.19 88	99.79 68	99.61 184	99.65 75	99.30 310	99.48 199	98.86 84	99.21 256	99.63 255	98.72 67	99.90 148	98.25 243	99.63 164	99.80 88

mamv4		99.33 77	99.42 32	99.07 228	99.67 134	97.73 304	99.42 260	99.60 67	98.15 175	99.94 28	99.91 26	98.42 91	99.94 92	99.72 32	99.96 17	99.54 214

MP-MVS		99.33 77	99.15 93	99.87 21	99.88 13	99.82 28	99.66 82	99.46 232	98.09 192	99.48 180	99.74 194	98.29 99	99.96 41	97.93 273	99.87 79	99.82 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_s_conf0.5_n_11		99.32 79	99.16 92	99.80 64	99.83 47	99.70 60	99.57 138	99.56 90	99.45 11	99.99 2	99.93 10	94.18 300	99.99 4	99.96 13	99.98 4	99.73 122

fmvsm_s_conf0.5_n_2		99.32 79	99.13 95	99.89 11	99.80 63	99.77 48	99.44 247	99.58 78	99.47 4	99.99 2	99.93 10	94.04 305	99.96 41	99.96 13	99.93 33	99.93 22

PS-MVSNAJ		99.32 79	99.32 54	99.30 199	99.57 199	98.94 197	98.97 406	99.46 232	98.92 81	99.71 108	99.24 377	99.01 20	99.98 20	99.35 76	99.66 159	98.97 310

CSCG		99.32 79	99.32 54	99.32 192	99.85 31	98.29 271	99.71 57	99.66 32	98.11 188	99.41 200	99.80 147	98.37 96	99.96 41	98.99 133	99.96 17	99.72 132

PHI-MVS		99.30 83	99.17 91	99.70 87	99.56 203	99.52 105	99.58 130	99.80 11	97.12 317	99.62 146	99.73 200	98.58 78	99.90 148	98.61 199	99.91 46	99.68 155

DeepC-MVS	98.35 2	99.30 83	99.19 88	99.64 101	99.82 53	99.23 148	99.62 106	99.55 100	98.94 78	99.63 142	99.95 3	95.82 212	99.94 92	99.37 75	99.97 9	99.73 122
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 85	99.10 99	99.86 34	99.70 122	99.65 75	99.53 175	99.62 51	98.74 101	99.99 2	99.95 3	94.53 285	99.94 92	99.89 25	99.96 17	99.97 4

xiu_mvs_v1_base_debu		99.29 85	99.27 73	99.34 186	99.63 164	98.97 183	99.12 368	99.51 151	98.86 84	99.84 56	99.47 316	98.18 104	99.99 4	99.50 57	99.31 191	99.08 295

xiu_mvs_v1_base		99.29 85	99.27 73	99.34 186	99.63 164	98.97 183	99.12 368	99.51 151	98.86 84	99.84 56	99.47 316	98.18 104	99.99 4	99.50 57	99.31 191	99.08 295

xiu_mvs_v1_base_debi		99.29 85	99.27 73	99.34 186	99.63 164	98.97 183	99.12 368	99.51 151	98.86 84	99.84 56	99.47 316	98.18 104	99.99 4	99.50 57	99.31 191	99.08 295

NormalMVS		99.27 89	99.19 88	99.52 139	99.89 8	98.83 220	99.65 88	99.52 130	99.10 48	99.84 56	99.76 184	95.80 214	99.99 4	99.30 89	99.84 102	99.74 113

APD-MVS		99.27 89	99.08 105	99.84 55	99.75 92	99.79 41	99.50 197	99.50 174	97.16 313	99.77 85	99.82 114	98.78 53	99.94 92	97.56 314	99.86 87	99.80 88
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
LS3D		99.27 89	99.12 97	99.74 80	99.18 328	99.75 51	99.56 146	99.57 85	98.45 130	99.49 179	99.85 80	97.77 118	99.94 92	98.33 236	99.84 102	99.52 221

fmvsm_s_conf0.1_n_a		99.26 92	99.06 110	99.85 43	99.52 221	99.62 83	99.54 166	99.62 51	98.69 107	99.99 2	99.96 1	94.47 287	99.94 92	99.88 26	99.92 39	99.98 2

patch_mono-2		99.26 92	99.62 6	98.16 356	99.81 57	94.59 430	99.52 177	99.64 42	99.33 28	99.73 97	99.90 33	99.00 24	99.99 4	99.69 35	99.98 4	99.89 29

ETV-MVS		99.26 92	99.21 84	99.40 176	99.46 248	99.30 138	99.56 146	99.52 130	98.52 122	99.44 189	99.27 373	98.41 93	99.86 181	99.10 120	99.59 168	99.04 302

xiu_mvs_v2_base		99.26 92	99.25 77	99.29 202	99.53 215	98.91 204	99.02 392	99.45 243	98.80 94	99.71 108	99.26 375	98.94 34	99.98 20	99.34 81	99.23 200	98.98 309

CANet		99.25 96	99.14 94	99.59 113	99.41 263	99.16 155	99.35 295	99.57 85	98.82 89	99.51 175	99.61 264	96.46 181	99.95 76	99.59 45	99.98 4	99.65 170

3Dnovator	97.25 9	99.24 97	99.05 112	99.81 60	99.12 344	99.66 71	99.84 12	99.74 13	99.09 55	98.92 312	99.90 33	95.94 205	99.98 20	98.95 141	99.92 39	99.79 92

LuminaMVS		99.23 98	99.10 99	99.61 109	99.35 280	99.31 135	99.46 236	99.13 367	98.61 113	99.86 53	99.89 41	96.41 186	99.91 135	99.67 37	99.51 174	99.63 182

dcpmvs_2		99.23 98	99.58 9	98.16 356	99.83 47	94.68 427	99.76 37	99.52 130	99.07 58	99.98 13	99.88 52	98.56 80	99.93 110	99.67 37	99.98 4	99.87 40

test_fmvsmconf0.01_n		99.22 100	99.03 117	99.79 68	98.42 435	99.48 111	99.55 161	99.51 151	99.39 22	99.78 81	99.93 10	94.80 260	99.95 76	99.93 23	99.95 23	99.94 17

diffmvs_AUTHOR		99.19 101	99.10 99	99.48 155	99.64 160	98.85 215	99.32 304	99.48 199	98.50 124	99.81 69	99.81 129	96.82 160	99.88 168	99.40 71	99.12 216	99.71 143

CHOSEN 1792x2688		99.19 101	99.10 99	99.45 164	99.89 8	98.52 255	99.39 277	99.94 1	98.73 102	99.11 275	99.89 41	95.50 226	99.94 92	99.50 57	99.97 9	99.89 29

F-COLMAP		99.19 101	99.04 114	99.64 101	99.78 70	99.27 143	99.42 260	99.54 109	97.29 302	99.41 200	99.59 269	98.42 91	99.93 110	98.19 247	99.69 153	99.73 122

E3new		99.18 104	99.08 105	99.48 155	99.63 164	98.94 197	99.46 236	99.50 174	98.06 201	99.72 102	99.84 95	97.27 133	99.84 196	99.10 120	99.13 211	99.67 159

viewcassd2359sk11		99.18 104	99.08 105	99.49 152	99.65 155	98.95 193	99.48 222	99.51 151	98.10 191	99.72 102	99.87 65	97.13 139	99.84 196	99.13 114	99.14 208	99.69 149

viewmanbaseed2359cas		99.18 104	99.07 109	99.50 149	99.62 173	99.01 177	99.50 197	99.52 130	98.25 160	99.68 114	99.82 114	96.93 153	99.80 234	99.15 113	99.11 218	99.70 146

EIA-MVS		99.18 104	99.09 104	99.45 164	99.49 238	99.18 152	99.67 75	99.53 125	97.66 260	99.40 205	99.44 323	98.10 107	99.81 227	98.94 142	99.62 165	99.35 268

3Dnovator+	97.12 13	99.18 104	98.97 137	99.82 57	99.17 336	99.68 64	99.81 20	99.51 151	99.20 33	98.72 340	99.89 41	95.68 220	99.97 29	98.86 159	99.86 87	99.81 79

MVSFormer		99.17 109	99.12 97	99.29 202	99.51 224	98.94 197	99.88 4	99.46 232	97.55 272	99.80 74	99.65 243	97.39 125	99.28 361	99.03 129	99.85 94	99.65 170

sss		99.17 109	99.05 112	99.53 133	99.62 173	98.97 183	99.36 290	99.62 51	97.83 236	99.67 120	99.65 243	97.37 128	99.95 76	99.19 103	99.19 203	99.68 155

SSM_0404		99.16 111	99.06 110	99.44 169	99.65 155	98.96 187	99.49 214	99.50 174	98.14 180	99.62 146	99.85 80	96.85 155	99.85 187	99.19 103	99.26 196	99.52 221

guyue		99.16 111	99.04 114	99.52 139	99.69 127	98.92 203	99.59 120	98.81 414	98.73 102	99.90 34	99.87 65	95.34 233	99.88 168	99.66 40	99.81 120	99.74 113

test_cas_vis1_n_1920		99.16 111	99.01 130	99.61 109	99.81 57	98.86 214	99.65 88	99.64 42	99.39 22	99.97 25	99.94 6	93.20 329	99.98 20	99.55 50	99.91 46	99.99 1

DP-MVS		99.16 111	98.95 145	99.78 71	99.77 78	99.53 101	99.41 265	99.50 174	97.03 329	99.04 292	99.88 52	97.39 125	99.92 123	98.66 191	99.90 57	99.87 40

E2		99.15 115	99.03 117	99.49 152	99.65 155	98.93 202	99.49 214	99.52 130	98.14 180	99.72 102	99.88 52	96.57 176	99.84 196	99.17 109	99.13 211	99.72 132

E3		99.15 115	99.03 117	99.49 152	99.62 173	98.91 204	99.49 214	99.52 130	98.13 183	99.72 102	99.88 52	96.61 171	99.84 196	99.17 109	99.13 211	99.72 132

SymmetryMVS		99.15 115	99.02 125	99.52 139	99.72 111	98.83 220	99.65 88	99.34 309	99.10 48	99.84 56	99.76 184	95.80 214	99.99 4	99.30 89	98.72 257	99.73 122

MGCNet		99.15 115	98.96 141	99.73 83	98.92 381	99.37 123	99.37 284	96.92 464	99.51 2	99.66 125	99.78 171	96.69 167	99.97 29	99.84 28	99.97 9	99.84 53

casdiffmvs_mvg		99.15 115	99.02 125	99.55 124	99.66 147	99.09 165	99.64 95	99.56 90	98.26 155	99.45 184	99.87 65	96.03 199	99.81 227	99.54 51	99.15 207	99.73 122
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		99.15 115	99.02 125	99.53 133	99.66 147	99.14 160	99.72 53	99.48 199	98.35 142	99.42 195	99.84 95	96.07 196	99.79 240	99.51 56	99.14 208	99.67 159

diffmvs		99.14 121	99.02 125	99.51 144	99.61 184	98.96 187	99.28 320	99.49 187	98.46 128	99.72 102	99.71 207	96.50 179	99.88 168	99.31 86	99.11 218	99.67 159
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		99.14 121	98.99 133	99.59 113	99.58 194	99.41 120	99.16 359	99.44 252	98.45 130	99.19 262	99.49 307	98.08 109	99.89 163	97.73 297	99.75 142	99.48 238

SSM_0407		99.13 123	99.03 117	99.43 172	99.62 173	98.88 207	99.51 186	99.50 174	98.14 180	99.37 211	99.85 80	96.85 155	99.83 213	99.19 103	99.25 197	99.60 190

CDPH-MVS		99.13 123	98.91 153	99.80 64	99.75 92	99.71 58	99.15 362	99.41 268	96.60 361	99.60 154	99.55 284	98.83 47	99.90 148	97.48 321	99.83 113	99.78 98

casdiffmvs		99.13 123	98.98 136	99.56 122	99.65 155	99.16 155	99.56 146	99.50 174	98.33 145	99.41 200	99.86 73	95.92 206	99.83 213	99.45 68	99.16 204	99.70 146
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		99.13 123	99.03 117	99.45 164	99.46 248	98.87 211	99.12 368	99.26 346	98.03 213	99.79 76	99.65 243	97.02 148	99.85 187	99.02 131	99.90 57	99.65 170
jason: jason.
lupinMVS		99.13 123	99.01 130	99.46 163	99.51 224	98.94 197	99.05 384	99.16 363	97.86 229	99.80 74	99.56 281	97.39 125	99.86 181	98.94 142	99.85 94	99.58 205

EPP-MVSNet		99.13 123	98.99 133	99.53 133	99.65 155	99.06 171	99.81 20	99.33 317	97.43 289	99.60 154	99.88 52	97.14 138	99.84 196	99.13 114	98.94 236	99.69 149

MG-MVS		99.13 123	99.02 125	99.45 164	99.57 199	98.63 241	99.07 378	99.34 309	98.99 69	99.61 151	99.82 114	97.98 113	99.87 175	97.00 352	99.80 125	99.85 46

KinetiMVS		99.12 130	98.92 150	99.70 87	99.67 134	99.40 121	99.67 75	99.63 46	98.73 102	99.94 28	99.81 129	94.54 283	99.96 41	98.40 227	99.93 33	99.74 113

BP-MVS1		99.12 130	98.94 147	99.65 95	99.51 224	99.30 138	99.67 75	98.92 395	98.48 126	99.84 56	99.69 222	94.96 248	99.92 123	99.62 44	99.79 132	99.71 143

CHOSEN 280x420		99.12 130	99.13 95	99.08 227	99.66 147	97.89 297	98.43 453	99.71 16	98.88 83	99.62 146	99.76 184	96.63 170	99.70 281	99.46 67	99.99 1	99.66 164

DP-MVS Recon		99.12 130	98.95 145	99.65 95	99.74 100	99.70 60	99.27 325	99.57 85	96.40 377	99.42 195	99.68 230	98.75 60	99.80 234	97.98 270	99.72 148	99.44 254

Vis-MVSNet		99.12 130	98.97 137	99.56 122	99.78 70	99.10 164	99.68 72	99.66 32	98.49 125	99.86 53	99.87 65	94.77 265	99.84 196	99.19 103	99.41 182	99.74 113
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 130	99.08 105	99.24 212	99.46 248	98.55 249	99.51 186	99.46 232	98.09 192	99.45 184	99.82 114	98.34 97	99.51 320	98.70 184	98.93 237	99.67 159

viewdifsd2359ckpt07		99.11 136	99.00 132	99.43 172	99.63 164	98.73 231	99.45 240	99.54 109	98.33 145	99.62 146	99.81 129	96.17 193	99.87 175	99.27 95	99.14 208	99.69 149

SDMVSNet		99.11 136	98.90 155	99.75 77	99.81 57	99.59 88	99.81 20	99.65 39	98.78 98	99.64 139	99.88 52	94.56 280	99.93 110	99.67 37	98.26 287	99.72 132

VNet		99.11 136	98.90 155	99.73 83	99.52 221	99.56 94	99.41 265	99.39 278	99.01 64	99.74 95	99.78 171	95.56 224	99.92 123	99.52 55	98.18 295	99.72 132

CPTT-MVS		99.11 136	98.90 155	99.74 80	99.80 63	99.46 114	99.59 120	99.49 187	97.03 329	99.63 142	99.69 222	97.27 133	99.96 41	97.82 284	99.84 102	99.81 79

HyFIR lowres test		99.11 136	98.92 150	99.65 95	99.90 4	99.37 123	99.02 392	99.91 3	97.67 259	99.59 157	99.75 189	95.90 208	99.73 264	99.53 53	99.02 232	99.86 42

MVS_Test		99.10 141	98.97 137	99.48 155	99.49 238	99.14 160	99.67 75	99.34 309	97.31 300	99.58 158	99.76 184	97.65 121	99.82 222	98.87 154	99.07 227	99.46 249

AstraMVS		99.09 142	99.03 117	99.25 209	99.66 147	98.13 280	99.57 138	98.24 447	98.82 89	99.91 31	99.88 52	95.81 213	99.90 148	99.72 32	99.67 158	99.74 113

CDS-MVSNet		99.09 142	99.03 117	99.25 209	99.42 258	98.73 231	99.45 240	99.46 232	98.11 188	99.46 183	99.77 180	98.01 112	99.37 344	98.70 184	98.92 239	99.66 164
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmacassd2359aftdt		99.08 144	98.94 147	99.50 149	99.66 147	98.96 187	99.51 186	99.54 109	98.27 152	99.42 195	99.89 41	95.88 210	99.80 234	99.20 102	99.11 218	99.76 107

mamba_0408		99.08 144	98.96 141	99.44 169	99.62 173	98.88 207	99.25 336	99.47 221	98.05 204	99.37 211	99.81 129	96.85 155	99.85 187	98.98 134	99.25 197	99.60 190

GDP-MVS		99.08 144	98.89 159	99.64 101	99.53 215	99.34 127	99.64 95	99.48 199	98.32 147	99.77 85	99.66 241	95.14 244	99.93 110	98.97 139	99.50 176	99.64 177

PVSNet_Blended		99.08 144	98.97 137	99.42 174	99.76 82	98.79 226	98.78 428	99.91 3	96.74 346	99.67 120	99.49 307	97.53 122	99.88 168	98.98 134	99.85 94	99.60 190

OMC-MVS		99.08 144	99.04 114	99.20 216	99.67 134	98.22 275	99.28 320	99.52 130	98.07 197	99.66 125	99.81 129	97.79 117	99.78 246	97.79 288	99.81 120	99.60 190

viewdifsd2359ckpt13		99.06 149	98.93 149	99.45 164	99.63 164	98.96 187	99.50 197	99.51 151	97.83 236	99.28 235	99.80 147	96.68 169	99.71 274	99.05 126	99.12 216	99.68 155

SSM_04072		99.06 149	98.96 141	99.35 185	99.62 173	98.88 207	99.25 336	99.47 221	98.05 204	99.37 211	99.81 129	96.85 155	99.58 312	98.98 134	99.25 197	99.60 190

mvsmamba		99.06 149	98.96 141	99.36 183	99.47 246	98.64 240	99.70 58	99.05 379	97.61 265	99.65 134	99.83 101	96.54 177	99.92 123	99.19 103	99.62 165	99.51 230

WTY-MVS		99.06 149	98.88 162	99.61 109	99.62 173	99.16 155	99.37 284	99.56 90	98.04 211	99.53 171	99.62 260	96.84 159	99.94 92	98.85 161	98.49 272	99.72 132

IS-MVSNet		99.05 153	98.87 163	99.57 120	99.73 107	99.32 131	99.75 42	99.20 358	98.02 216	99.56 162	99.86 73	96.54 177	99.67 289	98.09 258	99.13 211	99.73 122

PAPM_NR		99.04 154	98.84 171	99.66 91	99.74 100	99.44 116	99.39 277	99.38 286	97.70 255	99.28 235	99.28 370	98.34 97	99.85 187	96.96 356	99.45 179	99.69 149

API-MVS		99.04 154	99.03 117	99.06 230	99.40 268	99.31 135	99.55 161	99.56 90	98.54 120	99.33 225	99.39 339	98.76 57	99.78 246	96.98 354	99.78 134	98.07 433

mvs_anonymous		99.03 156	98.99 133	99.16 220	99.38 273	98.52 255	99.51 186	99.38 286	97.79 242	99.38 209	99.81 129	97.30 131	99.45 326	99.35 76	98.99 234	99.51 230

sasdasda		99.02 157	98.86 166	99.51 144	99.42 258	99.32 131	99.80 25	99.48 199	98.63 110	99.31 227	98.81 420	97.09 143	99.75 255	99.27 95	97.90 306	99.47 244

train_agg		99.02 157	98.77 178	99.77 74	99.67 134	99.65 75	99.05 384	99.41 268	96.28 381	98.95 308	99.49 307	98.76 57	99.91 135	97.63 305	99.72 148	99.75 109

canonicalmvs		99.02 157	98.86 166	99.51 144	99.42 258	99.32 131	99.80 25	99.48 199	98.63 110	99.31 227	98.81 420	97.09 143	99.75 255	99.27 95	97.90 306	99.47 244

PLC	97.94 4	99.02 157	98.85 169	99.53 133	99.66 147	99.01 177	99.24 341	99.52 130	96.85 341	99.27 241	99.48 313	98.25 101	99.91 135	97.76 293	99.62 165	99.65 170
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
viewdifsd2359ckpt09		99.01 161	98.87 163	99.40 176	99.62 173	98.79 226	99.44 247	99.51 151	97.76 246	99.35 220	99.69 222	96.42 185	99.75 255	98.97 139	99.11 218	99.66 164

viewmambaseed2359dif		99.01 161	98.90 155	99.32 192	99.58 194	98.51 257	99.33 301	99.54 109	97.85 232	99.44 189	99.85 80	96.01 200	99.79 240	99.41 70	99.13 211	99.67 159

MGCFI-Net		99.01 161	98.85 169	99.50 149	99.42 258	99.26 144	99.82 16	99.48 199	98.60 115	99.28 235	98.81 420	97.04 147	99.76 252	99.29 91	97.87 309	99.47 244

AdaColmap		99.01 161	98.80 174	99.66 91	99.56 203	99.54 98	99.18 357	99.70 18	98.18 173	99.35 220	99.63 255	96.32 188	99.90 148	97.48 321	99.77 137	99.55 212

1112_ss		98.98 165	98.77 178	99.59 113	99.68 132	99.02 175	99.25 336	99.48 199	97.23 308	99.13 271	99.58 273	96.93 153	99.90 148	98.87 154	98.78 254	99.84 53

MSDG		98.98 165	98.80 174	99.53 133	99.76 82	99.19 150	98.75 431	99.55 100	97.25 305	99.47 181	99.77 180	97.82 116	99.87 175	96.93 359	99.90 57	99.54 214

CANet_DTU		98.97 167	98.87 163	99.25 209	99.33 286	98.42 268	99.08 377	99.30 336	99.16 37	99.43 192	99.75 189	95.27 236	99.97 29	98.56 211	99.95 23	99.36 267

DPM-MVS		98.95 168	98.71 186	99.66 91	99.63 164	99.55 96	98.64 442	99.10 370	97.93 222	99.42 195	99.55 284	98.67 72	99.80 234	95.80 393	99.68 156	99.61 187

114514_t		98.93 169	98.67 190	99.72 86	99.85 31	99.53 101	99.62 106	99.59 73	92.65 449	99.71 108	99.78 171	98.06 110	99.90 148	98.84 164	99.91 46	99.74 113

PS-MVSNAJss		98.92 170	98.92 150	98.90 257	98.78 402	98.53 251	99.78 32	99.54 109	98.07 197	99.00 299	99.76 184	99.01 20	99.37 344	99.13 114	97.23 349	98.81 319

RRT-MVS		98.91 171	98.75 180	99.39 181	99.46 248	98.61 245	99.76 37	99.50 174	98.06 201	99.81 69	99.88 52	93.91 312	99.94 92	99.11 117	99.27 194	99.61 187

Test_1112_low_res		98.89 172	98.66 193	99.57 120	99.69 127	98.95 193	99.03 389	99.47 221	96.98 331	99.15 269	99.23 378	96.77 164	99.89 163	98.83 167	98.78 254	99.86 42

Elysia		98.88 173	98.65 195	99.58 116	99.58 194	99.34 127	99.65 88	99.52 130	98.26 155	99.83 64	99.87 65	93.37 323	99.90 148	97.81 286	99.91 46	99.49 235

StellarMVS		98.88 173	98.65 195	99.58 116	99.58 194	99.34 127	99.65 88	99.52 130	98.26 155	99.83 64	99.87 65	93.37 323	99.90 148	97.81 286	99.91 46	99.49 235

test_fmvs1		98.88 173	98.79 177	99.16 220	99.69 127	97.61 313	99.55 161	99.49 187	99.32 29	99.98 13	99.91 26	91.41 377	99.96 41	99.82 29	99.92 39	99.90 25

AllTest		98.87 176	98.72 184	99.31 194	99.86 25	98.48 262	99.56 146	99.61 60	97.85 232	99.36 217	99.85 80	95.95 203	99.85 187	96.66 372	99.83 113	99.59 201

UGNet		98.87 176	98.69 188	99.40 176	99.22 319	98.72 233	99.44 247	99.68 24	99.24 32	99.18 266	99.42 327	92.74 339	99.96 41	99.34 81	99.94 31	99.53 220
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)		98.87 176	98.72 184	99.31 194	99.71 117	98.88 207	99.80 25	99.44 252	97.91 224	99.36 217	99.78 171	95.49 227	99.43 335	97.91 274	99.11 218	99.62 185

IMVS_0407		98.86 179	98.91 153	98.72 290	99.55 207	96.93 353	99.50 197	99.44 252	98.05 204	99.66 125	99.80 147	97.13 139	99.65 297	98.15 253	98.92 239	99.60 190

IMVS_0403		98.86 179	98.89 159	98.78 285	99.55 207	96.93 353	99.58 130	99.44 252	98.05 204	99.68 114	99.80 147	96.81 161	99.80 234	98.15 253	98.92 239	99.60 190

test_yl		98.86 179	98.63 198	99.54 125	99.49 238	99.18 152	99.50 197	99.07 376	98.22 166	99.61 151	99.51 301	95.37 231	99.84 196	98.60 202	98.33 279	99.59 201

DCV-MVSNet		98.86 179	98.63 198	99.54 125	99.49 238	99.18 152	99.50 197	99.07 376	98.22 166	99.61 151	99.51 301	95.37 231	99.84 196	98.60 202	98.33 279	99.59 201

EPNet		98.86 179	98.71 186	99.30 199	97.20 455	98.18 276	99.62 106	98.91 400	99.28 31	98.63 359	99.81 129	95.96 202	99.99 4	99.24 99	99.72 148	99.73 122
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 179	98.80 174	99.03 234	99.76 82	98.79 226	99.28 320	99.91 3	97.42 291	99.67 120	99.37 345	97.53 122	99.88 168	98.98 134	97.29 347	98.42 411

ab-mvs		98.86 179	98.63 198	99.54 125	99.64 160	99.19 150	99.44 247	99.54 109	97.77 245	99.30 231	99.81 129	94.20 297	99.93 110	99.17 109	98.82 251	99.49 235

MAR-MVS		98.86 179	98.63 198	99.54 125	99.37 276	99.66 71	99.45 240	99.54 109	96.61 358	99.01 295	99.40 335	97.09 143	99.86 181	97.68 304	99.53 173	99.10 290
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	98.86 179	98.75 180	99.17 219	99.88 13	98.53 251	99.34 298	99.59 73	97.55 272	98.70 347	99.89 41	95.83 211	99.90 148	98.10 257	99.90 57	99.08 295
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 188	98.62 203	99.53 133	99.61 184	99.08 168	99.80 25	99.51 151	97.10 321	99.31 227	99.78 171	95.23 241	99.77 248	98.21 245	99.03 230	99.75 109

HY-MVS	97.30 7	98.85 188	98.64 197	99.47 161	99.42 258	99.08 168	99.62 106	99.36 297	97.39 294	99.28 235	99.68 230	96.44 183	99.92 123	98.37 231	98.22 290	99.40 261

PVSNet	96.02 17	98.85 188	98.84 171	98.89 261	99.73 107	97.28 323	98.32 459	99.60 67	97.86 229	99.50 176	99.57 278	96.75 165	99.86 181	98.56 211	99.70 152	99.54 214

PatchMatch-RL		98.84 191	98.62 203	99.52 139	99.71 117	99.28 141	99.06 382	99.77 12	97.74 250	99.50 176	99.53 293	95.41 229	99.84 196	97.17 345	99.64 162	99.44 254

Effi-MVS+		98.81 192	98.59 209	99.48 155	99.46 248	99.12 163	98.08 466	99.50 174	97.50 280	99.38 209	99.41 331	96.37 187	99.81 227	99.11 117	98.54 269	99.51 230

alignmvs		98.81 192	98.56 212	99.58 116	99.43 256	99.42 118	99.51 186	98.96 390	98.61 113	99.35 220	98.92 415	94.78 262	99.77 248	99.35 76	98.11 300	99.54 214

DeepPCF-MVS	98.18 3	98.81 192	99.37 44	97.12 414	99.60 190	91.75 457	98.61 443	99.44 252	99.35 25	99.83 64	99.85 80	98.70 69	99.81 227	99.02 131	99.91 46	99.81 79

PMMVS		98.80 195	98.62 203	99.34 186	99.27 304	98.70 234	98.76 430	99.31 331	97.34 297	99.21 256	99.07 394	97.20 137	99.82 222	98.56 211	98.87 246	99.52 221

icg_test_0407_2		98.79 196	98.86 166	98.57 306	99.55 207	96.93 353	99.07 378	99.44 252	98.05 204	99.66 125	99.80 147	97.13 139	99.18 383	98.15 253	98.92 239	99.60 190

viewdifsd2359ckpt11		98.78 197	98.74 182	98.89 261	99.67 134	97.04 342	99.50 197	99.58 78	98.26 155	99.56 162	99.90 33	94.36 290	99.87 175	99.49 61	98.32 283	99.77 100

viewmsd2359difaftdt		98.78 197	98.74 182	98.90 257	99.67 134	97.04 342	99.50 197	99.58 78	98.26 155	99.56 162	99.90 33	94.36 290	99.87 175	99.49 61	98.32 283	99.77 100

Effi-MVS+-dtu		98.78 197	98.89 159	98.47 324	99.33 286	96.91 358	99.57 138	99.30 336	98.47 127	99.41 200	98.99 405	96.78 163	99.74 258	98.73 181	99.38 183	98.74 334

FIs		98.78 197	98.63 198	99.23 214	99.18 328	99.54 98	99.83 15	99.59 73	98.28 150	98.79 334	99.81 129	96.75 165	99.37 344	99.08 123	96.38 365	98.78 322

Fast-Effi-MVS+-dtu		98.77 201	98.83 173	98.60 301	99.41 263	96.99 348	99.52 177	99.49 187	98.11 188	99.24 248	99.34 355	96.96 152	99.79 240	97.95 272	99.45 179	99.02 305

sd_testset		98.75 202	98.57 210	99.29 202	99.81 57	98.26 273	99.56 146	99.62 51	98.78 98	99.64 139	99.88 52	92.02 361	99.88 168	99.54 51	98.26 287	99.72 132

FA-MVS(test-final)		98.75 202	98.53 214	99.41 175	99.55 207	99.05 173	99.80 25	99.01 384	96.59 363	99.58 158	99.59 269	95.39 230	99.90 148	97.78 289	99.49 177	99.28 276

FC-MVSNet-test		98.75 202	98.62 203	99.15 224	99.08 355	99.45 115	99.86 11	99.60 67	98.23 165	98.70 347	99.82 114	96.80 162	99.22 375	99.07 124	96.38 365	98.79 320

XVG-OURS		98.73 205	98.68 189	98.88 264	99.70 122	97.73 304	98.92 414	99.55 100	98.52 122	99.45 184	99.84 95	95.27 236	99.91 135	98.08 262	98.84 249	99.00 306

Fast-Effi-MVS+		98.70 206	98.43 219	99.51 144	99.51 224	99.28 141	99.52 177	99.47 221	96.11 397	99.01 295	99.34 355	96.20 192	99.84 196	97.88 276	98.82 251	99.39 262

XVG-OURS-SEG-HR		98.69 207	98.62 203	98.89 261	99.71 117	97.74 303	99.12 368	99.54 109	98.44 133	99.42 195	99.71 207	94.20 297	99.92 123	98.54 215	98.90 245	99.00 306

1314		98.68 208	98.54 213	99.11 226	98.89 385	98.65 238	99.27 325	99.49 187	96.89 339	97.99 399	99.56 281	97.72 120	99.83 213	97.74 296	99.27 194	98.84 318

VortexMVS		98.67 209	98.66 193	98.68 296	99.62 173	97.96 291	99.59 120	99.41 268	98.13 183	99.31 227	99.70 211	95.48 228	99.27 364	99.40 71	97.32 346	98.79 320

EI-MVSNet		98.67 209	98.67 190	98.68 296	99.35 280	97.97 289	99.50 197	99.38 286	96.93 338	99.20 259	99.83 101	97.87 114	99.36 348	98.38 229	97.56 325	98.71 338

test_djsdf		98.67 209	98.57 210	98.98 240	98.70 416	98.91 204	99.88 4	99.46 232	97.55 272	99.22 253	99.88 52	95.73 218	99.28 361	99.03 129	97.62 320	98.75 330

QAPM		98.67 209	98.30 229	99.80 64	99.20 322	99.67 68	99.77 34	99.72 14	94.74 425	98.73 339	99.90 33	95.78 216	99.98 20	96.96 356	99.88 76	99.76 107

nrg030		98.64 213	98.42 220	99.28 206	99.05 361	99.69 63	99.81 20	99.46 232	98.04 211	99.01 295	99.82 114	96.69 167	99.38 341	99.34 81	94.59 410	98.78 322

test_vis1_n_1920		98.63 214	98.40 222	99.31 194	99.86 25	97.94 296	99.67 75	99.62 51	99.43 17	99.99 2	99.91 26	87.29 428	100.00 1	99.92 24	99.92 39	99.98 2

PAPR		98.63 214	98.34 225	99.51 144	99.40 268	99.03 174	98.80 426	99.36 297	96.33 378	99.00 299	99.12 392	98.46 87	99.84 196	95.23 408	99.37 190	99.66 164

CVMVSNet		98.57 216	98.67 190	98.30 344	99.35 280	95.59 401	99.50 197	99.55 100	98.60 115	99.39 207	99.83 101	94.48 286	99.45 326	98.75 178	98.56 267	99.85 46

IMVS_0404		98.53 217	98.52 215	98.55 312	99.55 207	96.93 353	99.20 353	99.44 252	98.05 204	98.96 306	99.80 147	94.66 275	99.13 391	98.15 253	98.92 239	99.60 190

MVSTER		98.49 218	98.32 227	99.00 238	99.35 280	99.02 175	99.54 166	99.38 286	97.41 292	99.20 259	99.73 200	93.86 314	99.36 348	98.87 154	97.56 325	98.62 382

FE-MVS		98.48 219	98.17 234	99.40 176	99.54 214	98.96 187	99.68 72	98.81 414	95.54 408	99.62 146	99.70 211	93.82 315	99.93 110	97.35 332	99.46 178	99.32 273

OpenMVS	96.50 16	98.47 220	98.12 241	99.52 139	99.04 363	99.53 101	99.82 16	99.72 14	94.56 428	98.08 394	99.88 52	94.73 268	99.98 20	97.47 323	99.76 140	99.06 301

IterMVS-LS		98.46 221	98.42 220	98.58 305	99.59 192	98.00 287	99.37 284	99.43 263	96.94 337	99.07 284	99.59 269	97.87 114	99.03 406	98.32 238	95.62 388	98.71 338
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 222	98.28 230	98.94 247	98.50 432	98.96 187	99.77 34	99.50 174	97.07 323	98.87 321	99.77 180	94.76 266	99.28 361	98.66 191	97.60 321	98.57 397

jajsoiax		98.43 223	98.28 230	98.88 264	98.60 426	98.43 266	99.82 16	99.53 125	98.19 170	98.63 359	99.80 147	93.22 328	99.44 331	99.22 100	97.50 332	98.77 326

tttt0517		98.42 224	98.14 238	99.28 206	99.66 147	98.38 269	99.74 47	96.85 465	97.68 257	99.79 76	99.74 194	91.39 378	99.89 163	98.83 167	99.56 170	99.57 208

BH-untuned		98.42 224	98.36 223	98.59 302	99.49 238	96.70 366	99.27 325	99.13 367	97.24 307	98.80 332	99.38 342	95.75 217	99.74 258	97.07 350	99.16 204	99.33 272

test_fmvs1_n		98.41 226	98.14 238	99.21 215	99.82 53	97.71 309	99.74 47	99.49 187	99.32 29	99.99 2	99.95 3	85.32 443	99.97 29	99.82 29	99.84 102	99.96 7

D2MVS		98.41 226	98.50 216	98.15 359	99.26 307	96.62 372	99.40 273	99.61 60	97.71 252	98.98 302	99.36 348	96.04 198	99.67 289	98.70 184	97.41 342	98.15 429

BH-RMVSNet		98.41 226	98.08 247	99.40 176	99.41 263	98.83 220	99.30 310	98.77 420	97.70 255	98.94 310	99.65 243	92.91 335	99.74 258	96.52 376	99.55 172	99.64 177

mvs_tets		98.40 229	98.23 232	98.91 255	98.67 419	98.51 257	99.66 82	99.53 125	98.19 170	98.65 356	99.81 129	92.75 337	99.44 331	99.31 86	97.48 336	98.77 326

MonoMVSNet		98.38 230	98.47 218	98.12 361	98.59 428	96.19 389	99.72 53	98.79 418	97.89 226	99.44 189	99.52 297	96.13 194	98.90 428	98.64 193	97.54 327	99.28 276

XXY-MVS		98.38 230	98.09 246	99.24 212	99.26 307	99.32 131	99.56 146	99.55 100	97.45 285	98.71 341	99.83 101	93.23 326	99.63 307	98.88 151	96.32 367	98.76 328

ACMM	97.58 5	98.37 232	98.34 225	98.48 319	99.41 263	97.10 333	99.56 146	99.45 243	98.53 121	99.04 292	99.85 80	93.00 331	99.71 274	98.74 179	97.45 337	98.64 373
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 233	98.03 253	99.31 194	99.63 164	98.56 248	99.54 166	96.75 467	97.53 276	99.73 97	99.65 243	91.25 382	99.89 163	98.62 196	99.56 170	99.48 238

tpmrst		98.33 234	98.48 217	97.90 378	99.16 338	94.78 423	99.31 308	99.11 369	97.27 303	99.45 184	99.59 269	95.33 234	99.84 196	98.48 218	98.61 261	99.09 294

baseline1		98.31 235	97.95 262	99.38 182	99.50 236	98.74 230	99.59 120	98.93 392	98.41 135	99.14 270	99.60 267	94.59 278	99.79 240	98.48 218	93.29 430	99.61 187

PatchmatchNet		98.31 235	98.36 223	98.19 354	99.16 338	95.32 412	99.27 325	98.92 395	97.37 295	99.37 211	99.58 273	94.90 255	99.70 281	97.43 327	99.21 201	99.54 214
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 237	97.98 258	99.26 208	99.57 199	98.16 277	99.41 265	98.55 439	96.03 402	99.19 262	99.74 194	91.87 364	99.92 123	99.16 112	98.29 286	99.70 146

VPA-MVSNet		98.29 238	97.95 262	99.30 199	99.16 338	99.54 98	99.50 197	99.58 78	98.27 152	99.35 220	99.37 345	92.53 349	99.65 297	99.35 76	94.46 411	98.72 336

UniMVSNet (Re)		98.29 238	98.00 256	99.13 225	99.00 368	99.36 126	99.49 214	99.51 151	97.95 220	98.97 304	99.13 389	96.30 189	99.38 341	98.36 233	93.34 429	98.66 369

HQP_MVS		98.27 240	98.22 233	98.44 330	99.29 299	96.97 350	99.39 277	99.47 221	98.97 75	99.11 275	99.61 264	92.71 342	99.69 286	97.78 289	97.63 318	98.67 360

UniMVSNet_NR-MVSNet		98.22 241	97.97 259	98.96 243	98.92 381	98.98 180	99.48 222	99.53 125	97.76 246	98.71 341	99.46 320	96.43 184	99.22 375	98.57 208	92.87 437	98.69 347

LPG-MVS_test		98.22 241	98.13 240	98.49 317	99.33 286	97.05 339	99.58 130	99.55 100	97.46 282	99.24 248	99.83 101	92.58 347	99.72 268	98.09 258	97.51 330	98.68 352

RPSCF		98.22 241	98.62 203	96.99 417	99.82 53	91.58 458	99.72 53	99.44 252	96.61 358	99.66 125	99.89 41	95.92 206	99.82 222	97.46 324	99.10 224	99.57 208

ADS-MVSNet		98.20 244	98.08 247	98.56 310	99.33 286	96.48 377	99.23 344	99.15 364	96.24 385	99.10 278	99.67 236	94.11 302	99.71 274	96.81 364	99.05 228	99.48 238

OPM-MVS		98.19 245	98.10 243	98.45 327	98.88 386	97.07 337	99.28 320	99.38 286	98.57 117	99.22 253	99.81 129	92.12 359	99.66 292	98.08 262	97.54 327	98.61 391
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 245	98.16 235	98.27 350	99.30 295	95.55 402	99.07 378	98.97 388	97.57 269	99.43 192	99.57 278	92.72 340	99.74 258	97.58 309	99.20 202	99.52 221

miper_ehance_all_eth		98.18 247	98.10 243	98.41 333	99.23 315	97.72 306	98.72 434	99.31 331	96.60 361	98.88 318	99.29 368	97.29 132	99.13 391	97.60 307	95.99 376	98.38 416

CR-MVSNet		98.17 248	97.93 265	98.87 268	99.18 328	98.49 260	99.22 348	99.33 317	96.96 333	99.56 162	99.38 342	94.33 293	99.00 411	94.83 415	98.58 264	99.14 287

miper_enhance_ethall		98.16 249	98.08 247	98.41 333	98.96 377	97.72 306	98.45 452	99.32 327	96.95 335	98.97 304	99.17 384	97.06 146	99.22 375	97.86 279	95.99 376	98.29 420

CLD-MVS		98.16 249	98.10 243	98.33 340	99.29 299	96.82 363	98.75 431	99.44 252	97.83 236	99.13 271	99.55 284	92.92 333	99.67 289	98.32 238	97.69 316	98.48 403
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 251	97.79 277	99.19 217	99.50 236	98.50 259	98.61 443	96.82 466	96.95 335	99.54 169	99.43 325	91.66 373	99.86 181	98.08 262	99.51 174	99.22 284

pmmvs4		98.13 252	97.90 267	98.81 280	98.61 425	98.87 211	98.99 400	99.21 357	96.44 373	99.06 289	99.58 273	95.90 208	99.11 397	97.18 344	96.11 372	98.46 408

WR-MVS_H		98.13 252	97.87 272	98.90 257	99.02 365	98.84 217	99.70 58	99.59 73	97.27 303	98.40 376	99.19 383	95.53 225	99.23 371	98.34 235	93.78 425	98.61 391

c3_l		98.12 254	98.04 252	98.38 337	99.30 295	97.69 310	98.81 425	99.33 317	96.67 351	98.83 327	99.34 355	97.11 142	98.99 412	97.58 309	95.34 395	98.48 403

ACMH	97.28 8	98.10 255	97.99 257	98.44 330	99.41 263	96.96 352	99.60 113	99.56 90	98.09 192	98.15 392	99.91 26	90.87 386	99.70 281	98.88 151	97.45 337	98.67 360
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		98.09 256	97.68 294	99.34 186	99.66 147	98.44 265	99.40 273	99.43 263	93.67 435	99.22 253	99.89 41	90.23 394	99.93 110	99.26 98	98.33 279	99.66 164

CP-MVSNet		98.09 256	97.78 280	99.01 236	98.97 376	99.24 147	99.67 75	99.46 232	97.25 305	98.48 373	99.64 249	93.79 316	99.06 402	98.63 195	94.10 419	98.74 334

dmvs_re		98.08 258	98.16 235	97.85 382	99.55 207	94.67 428	99.70 58	98.92 395	98.15 175	99.06 289	99.35 351	93.67 320	99.25 368	97.77 292	97.25 348	99.64 177

DU-MVS		98.08 258	97.79 277	98.96 243	98.87 389	98.98 180	99.41 265	99.45 243	97.87 228	98.71 341	99.50 304	94.82 258	99.22 375	98.57 208	92.87 437	98.68 352

v2v482		98.06 260	97.77 282	98.92 251	98.90 384	98.82 223	99.57 138	99.36 297	96.65 353	99.19 262	99.35 351	94.20 297	99.25 368	97.72 299	94.97 403	98.69 347

V42		98.06 260	97.79 277	98.86 271	98.98 374	98.84 217	99.69 62	99.34 309	96.53 365	99.30 231	99.37 345	94.67 273	99.32 356	97.57 313	94.66 408	98.42 411

test-LLR		98.06 260	97.90 267	98.55 312	98.79 399	97.10 333	98.67 437	97.75 456	97.34 297	98.61 363	98.85 417	94.45 288	99.45 326	97.25 336	99.38 183	99.10 290

WR-MVS		98.06 260	97.73 289	99.06 230	98.86 392	99.25 146	99.19 355	99.35 304	97.30 301	98.66 350	99.43 325	93.94 309	99.21 380	98.58 205	94.28 415	98.71 338

ACMP	97.20 11	98.06 260	97.94 264	98.45 327	99.37 276	97.01 346	99.44 247	99.49 187	97.54 275	98.45 374	99.79 164	91.95 363	99.72 268	97.91 274	97.49 335	98.62 382
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 265	97.96 260	98.33 340	99.26 307	97.38 320	98.56 448	99.31 331	96.65 353	98.88 318	99.52 297	96.58 174	99.12 396	97.39 329	95.53 392	98.47 405

test1111		98.04 266	98.11 242	97.83 385	99.74 100	93.82 440	99.58 130	95.40 474	99.12 46	99.65 134	99.93 10	90.73 387	99.84 196	99.43 69	99.38 183	99.82 72

ECVR-MVS		98.04 266	98.05 251	98.00 369	99.74 100	94.37 434	99.59 120	94.98 475	99.13 41	99.66 125	99.93 10	90.67 388	99.84 196	99.40 71	99.38 183	99.80 88

EPNet_dtu		98.03 268	97.96 260	98.23 352	98.27 437	95.54 404	99.23 344	98.75 421	99.02 62	97.82 408	99.71 207	96.11 195	99.48 321	93.04 437	99.65 161	99.69 149
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 268	97.76 286	98.84 275	99.39 271	98.98 180	99.40 273	99.38 286	96.67 351	99.07 284	99.28 370	92.93 332	98.98 413	97.10 346	96.65 358	98.56 398

ADS-MVSNet2		98.02 270	98.07 250	97.87 380	99.33 286	95.19 415	99.23 344	99.08 373	96.24 385	99.10 278	99.67 236	94.11 302	98.93 425	96.81 364	99.05 228	99.48 238

HQP-MVS		98.02 270	97.90 267	98.37 338	99.19 325	96.83 361	98.98 403	99.39 278	98.24 162	98.66 350	99.40 335	92.47 351	99.64 301	97.19 342	97.58 323	98.64 373

LTVRE_ROB	97.16 12	98.02 270	97.90 267	98.40 335	99.23 315	96.80 364	99.70 58	99.60 67	97.12 317	98.18 391	99.70 211	91.73 369	99.72 268	98.39 228	97.45 337	98.68 352
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____		98.01 273	97.84 275	98.55 312	99.25 311	97.97 289	98.71 435	99.34 309	96.47 372	98.59 366	99.54 289	95.65 221	99.21 380	97.21 338	95.77 382	98.46 408

DIV-MVS_self_test		98.01 273	97.85 274	98.48 319	99.24 313	97.95 294	98.71 435	99.35 304	96.50 366	98.60 365	99.54 289	95.72 219	99.03 406	97.21 338	95.77 382	98.46 408

miper_lstm_enhance		98.00 275	97.91 266	98.28 349	99.34 285	97.43 318	98.88 418	99.36 297	96.48 370	98.80 332	99.55 284	95.98 201	98.91 426	97.27 335	95.50 393	98.51 401

BH-w/o		98.00 275	97.89 271	98.32 342	99.35 280	96.20 388	99.01 397	98.90 402	96.42 375	98.38 377	99.00 403	95.26 238	99.72 268	96.06 386	98.61 261	99.03 303

v1144		97.98 277	97.69 293	98.85 274	98.87 389	98.66 237	99.54 166	99.35 304	96.27 383	99.23 252	99.35 351	94.67 273	99.23 371	96.73 367	95.16 399	98.68 352

EU-MVSNet		97.98 277	98.03 253	97.81 388	98.72 413	96.65 371	99.66 82	99.66 32	98.09 192	98.35 379	99.82 114	95.25 239	98.01 449	97.41 328	95.30 396	98.78 322

tpmvs		97.98 277	98.02 255	97.84 384	99.04 363	94.73 424	99.31 308	99.20 358	96.10 401	98.76 337	99.42 327	94.94 250	99.81 227	96.97 355	98.45 273	98.97 310

tt0805		97.97 280	97.77 282	98.57 306	99.59 192	96.61 373	99.45 240	99.08 373	98.21 168	98.88 318	99.80 147	88.66 412	99.70 281	98.58 205	97.72 315	99.39 262

NR-MVSNet		97.97 280	97.61 303	99.02 235	98.87 389	99.26 144	99.47 232	99.42 265	97.63 262	97.08 427	99.50 304	95.07 246	99.13 391	97.86 279	93.59 426	98.68 352

v8		97.95 282	97.63 301	98.93 249	98.95 378	98.81 225	99.80 25	99.41 268	96.03 402	99.10 278	99.42 327	94.92 253	99.30 359	96.94 358	94.08 420	98.66 369

Patchmatch-test		97.93 283	97.65 297	98.77 286	99.18 328	97.07 337	99.03 389	99.14 366	96.16 392	98.74 338	99.57 278	94.56 280	99.72 268	93.36 432	99.11 218	99.52 221

PS-CasMVS		97.93 283	97.59 305	98.95 245	98.99 371	99.06 171	99.68 72	99.52 130	97.13 315	98.31 381	99.68 230	92.44 355	99.05 403	98.51 216	94.08 420	98.75 330

TranMVSNet+NR-MVSNet		97.93 283	97.66 296	98.76 287	98.78 402	98.62 243	99.65 88	99.49 187	97.76 246	98.49 372	99.60 267	94.23 296	98.97 420	98.00 269	92.90 435	98.70 343

test_vis1_n		97.92 286	97.44 327	99.34 186	99.53 215	98.08 283	99.74 47	99.49 187	99.15 38	100.00 1	99.94 6	79.51 465	99.98 20	99.88 26	99.76 140	99.97 4

v144192		97.92 286	97.60 304	98.87 268	98.83 396	98.65 238	99.55 161	99.34 309	96.20 388	99.32 226	99.40 335	94.36 290	99.26 367	96.37 383	95.03 402	98.70 343

ACMH+	97.24 10	97.92 286	97.78 280	98.32 342	99.46 248	96.68 370	99.56 146	99.54 109	98.41 135	97.79 410	99.87 65	90.18 395	99.66 292	98.05 266	97.18 352	98.62 382

LFMVS		97.90 289	97.35 339	99.54 125	99.52 221	99.01 177	99.39 277	98.24 447	97.10 321	99.65 134	99.79 164	84.79 446	99.91 135	99.28 92	98.38 276	99.69 149

reproduce_monomvs		97.89 290	97.87 272	97.96 373	99.51 224	95.45 407	99.60 113	99.25 348	99.17 36	98.85 326	99.49 307	89.29 404	99.64 301	99.35 76	96.31 368	98.78 322

Anonymous20231211		97.88 291	97.54 309	98.90 257	99.71 117	98.53 251	99.48 222	99.57 85	94.16 431	98.81 330	99.68 230	93.23 326	99.42 337	98.84 164	94.42 413	98.76 328

OurMVSNet-221017-0		97.88 291	97.77 282	98.19 354	98.71 415	96.53 375	99.88 4	99.00 385	97.79 242	98.78 335	99.94 6	91.68 370	99.35 351	97.21 338	96.99 356	98.69 347

v7n		97.87 293	97.52 311	98.92 251	98.76 409	98.58 247	99.84 12	99.46 232	96.20 388	98.91 313	99.70 211	94.89 256	99.44 331	96.03 387	93.89 423	98.75 330

baseline2		97.87 293	97.55 306	98.82 277	99.18 328	98.02 286	99.41 265	96.58 471	96.97 332	96.51 434	99.17 384	93.43 321	99.57 313	97.71 300	99.03 230	98.86 316

thres600view7		97.86 295	97.51 313	98.92 251	99.72 111	97.95 294	99.59 120	98.74 424	97.94 221	99.27 241	98.62 428	91.75 367	99.86 181	93.73 428	98.19 294	98.96 312

UBG		97.85 296	97.48 316	98.95 245	99.25 311	97.64 311	99.24 341	98.74 424	97.90 225	98.64 357	98.20 445	88.65 413	99.81 227	98.27 241	98.40 274	99.42 256

cl22		97.85 296	97.64 300	98.48 319	99.09 352	97.87 298	98.60 445	99.33 317	97.11 320	98.87 321	99.22 379	92.38 356	99.17 385	98.21 245	95.99 376	98.42 411

v10		97.85 296	97.52 311	98.86 271	98.99 371	98.67 236	99.75 42	99.41 268	95.70 406	98.98 302	99.41 331	94.75 267	99.23 371	96.01 389	94.63 409	98.67 360

GA-MVS		97.85 296	97.47 319	99.00 238	99.38 273	97.99 288	98.57 446	99.15 364	97.04 328	98.90 315	99.30 366	89.83 398	99.38 341	96.70 369	98.33 279	99.62 185

testing3-2		97.84 300	97.70 292	98.24 351	99.53 215	95.37 411	99.55 161	98.67 434	98.46 128	99.27 241	99.34 355	86.58 432	99.83 213	99.32 84	98.63 260	99.52 221

tfpnnormal		97.84 300	97.47 319	98.98 240	99.20 322	99.22 149	99.64 95	99.61 60	96.32 379	98.27 385	99.70 211	93.35 325	99.44 331	95.69 396	95.40 394	98.27 421

VPNet		97.84 300	97.44 327	99.01 236	99.21 320	98.94 197	99.48 222	99.57 85	98.38 137	99.28 235	99.73 200	88.89 407	99.39 339	99.19 103	93.27 431	98.71 338

LCM-MVSNet-Re		97.83 303	98.15 237	96.87 423	99.30 295	92.25 455	99.59 120	98.26 445	97.43 289	96.20 438	99.13 389	96.27 190	98.73 435	98.17 250	98.99 234	99.64 177

XVG-ACMP-BASELINE		97.83 303	97.71 291	98.20 353	99.11 346	96.33 382	99.41 265	99.52 130	98.06 201	99.05 291	99.50 304	89.64 401	99.73 264	97.73 297	97.38 344	98.53 399

IterMVS		97.83 303	97.77 282	98.02 366	99.58 194	96.27 385	99.02 392	99.48 199	97.22 309	98.71 341	99.70 211	92.75 337	99.13 391	97.46 324	96.00 375	98.67 360
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 306	97.75 287	98.06 363	99.57 199	96.36 381	99.02 392	99.49 187	97.18 311	98.71 341	99.72 204	92.72 340	99.14 388	97.44 326	95.86 381	98.67 360

EPMVS		97.82 306	97.65 297	98.35 339	98.88 386	95.98 392	99.49 214	94.71 477	97.57 269	99.26 246	99.48 313	92.46 354	99.71 274	97.87 278	99.08 226	99.35 268

MVP-Stereo		97.81 308	97.75 287	97.99 370	97.53 448	96.60 374	98.96 407	98.85 409	97.22 309	97.23 421	99.36 348	95.28 235	99.46 324	95.51 400	99.78 134	97.92 446
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 308	97.44 327	98.91 255	98.88 386	98.68 235	99.51 186	99.34 309	96.18 390	99.20 259	99.34 355	94.03 306	99.36 348	95.32 406	95.18 398	98.69 347

ttmdpeth		97.80 310	97.63 301	98.29 345	98.77 407	97.38 320	99.64 95	99.36 297	98.78 98	96.30 437	99.58 273	92.34 358	99.39 339	98.36 233	95.58 389	98.10 431

v1921920		97.80 310	97.45 322	98.84 275	98.80 398	98.53 251	99.52 177	99.34 309	96.15 394	99.24 248	99.47 316	93.98 308	99.29 360	95.40 404	95.13 400	98.69 347

v148		97.79 312	97.55 306	98.50 316	98.74 410	97.72 306	99.54 166	99.33 317	96.26 384	98.90 315	99.51 301	94.68 272	99.14 388	97.83 283	93.15 434	98.63 380

thres400		97.77 313	97.38 335	98.92 251	99.69 127	97.96 291	99.50 197	98.73 430	97.83 236	99.17 267	98.45 435	91.67 371	99.83 213	93.22 434	98.18 295	98.96 312

thres100view900		97.76 314	97.45 322	98.69 295	99.72 111	97.86 300	99.59 120	98.74 424	97.93 222	99.26 246	98.62 428	91.75 367	99.83 213	93.22 434	98.18 295	98.37 417

PEN-MVS		97.76 314	97.44 327	98.72 290	98.77 407	98.54 250	99.78 32	99.51 151	97.06 325	98.29 384	99.64 249	92.63 346	98.89 429	98.09 258	93.16 433	98.72 336

Baseline_NR-MVSNet		97.76 314	97.45 322	98.68 296	99.09 352	98.29 271	99.41 265	98.85 409	95.65 407	98.63 359	99.67 236	94.82 258	99.10 399	98.07 265	92.89 436	98.64 373

TR-MVS		97.76 314	97.41 333	98.82 277	99.06 358	97.87 298	98.87 420	98.56 438	96.63 357	98.68 349	99.22 379	92.49 350	99.65 297	95.40 404	97.79 313	98.95 314

Patchmtry		97.75 318	97.40 334	98.81 280	99.10 349	98.87 211	99.11 374	99.33 317	94.83 423	98.81 330	99.38 342	94.33 293	99.02 408	96.10 385	95.57 390	98.53 399

dp		97.75 318	97.80 276	97.59 401	99.10 349	93.71 443	99.32 304	98.88 405	96.48 370	99.08 283	99.55 284	92.67 345	99.82 222	96.52 376	98.58 264	99.24 282

WBMVS		97.74 320	97.50 314	98.46 325	99.24 313	97.43 318	99.21 350	99.42 265	97.45 285	98.96 306	99.41 331	88.83 408	99.23 371	98.94 142	96.02 373	98.71 338

TAPA-MVS	97.07 15	97.74 320	97.34 342	98.94 247	99.70 122	97.53 314	99.25 336	99.51 151	91.90 451	99.30 231	99.63 255	98.78 53	99.64 301	88.09 461	99.87 79	99.65 170
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 322	97.35 339	98.88 264	99.47 246	97.12 332	99.34 298	98.85 409	98.19 170	99.67 120	99.85 80	82.98 454	99.92 123	99.49 61	98.32 283	99.60 190

MIMVSNet		97.73 322	97.45 322	98.57 306	99.45 254	97.50 316	99.02 392	98.98 387	96.11 397	99.41 200	99.14 388	90.28 390	98.74 434	95.74 394	98.93 237	99.47 244

tfpn200view9		97.72 324	97.38 335	98.72 290	99.69 127	97.96 291	99.50 197	98.73 430	97.83 236	99.17 267	98.45 435	91.67 371	99.83 213	93.22 434	98.18 295	98.37 417

CostFormer		97.72 324	97.73 289	97.71 393	99.15 342	94.02 439	99.54 166	99.02 383	94.67 426	99.04 292	99.35 351	92.35 357	99.77 248	98.50 217	97.94 305	99.34 271

FMVSNet2		97.72 324	97.36 337	98.80 282	99.51 224	98.84 217	99.45 240	99.42 265	96.49 367	98.86 325	99.29 368	90.26 391	98.98 413	96.44 378	96.56 361	98.58 396

test0.0.03 1		97.71 327	97.42 332	98.56 310	98.41 436	97.82 301	98.78 428	98.63 436	97.34 297	98.05 398	98.98 407	94.45 288	98.98 413	95.04 411	97.15 353	98.89 315

h-mvs33		97.70 328	97.28 351	98.97 242	99.70 122	97.27 324	99.36 290	99.45 243	98.94 78	99.66 125	99.64 249	94.93 251	99.99 4	99.48 64	84.36 466	99.65 170

myMVS_eth3d28		97.69 329	97.34 342	98.73 288	99.27 304	97.52 315	99.33 301	98.78 419	98.03 213	98.82 329	98.49 433	86.64 431	99.46 324	98.44 224	98.24 289	99.23 283

v1240		97.69 329	97.32 346	98.79 283	98.85 393	98.43 266	99.48 222	99.36 297	96.11 397	99.27 241	99.36 348	93.76 318	99.24 370	94.46 418	95.23 397	98.70 343

cascas		97.69 329	97.43 331	98.48 319	98.60 426	97.30 322	98.18 464	99.39 278	92.96 445	98.41 375	98.78 424	93.77 317	99.27 364	98.16 251	98.61 261	98.86 316

pm-mvs1		97.68 332	97.28 351	98.88 264	99.06 358	98.62 243	99.50 197	99.45 243	96.32 379	97.87 406	99.79 164	92.47 351	99.35 351	97.54 316	93.54 427	98.67 360

GBi-Net		97.68 332	97.48 316	98.29 345	99.51 224	97.26 326	99.43 253	99.48 199	96.49 367	99.07 284	99.32 363	90.26 391	98.98 413	97.10 346	96.65 358	98.62 382

test1		97.68 332	97.48 316	98.29 345	99.51 224	97.26 326	99.43 253	99.48 199	96.49 367	99.07 284	99.32 363	90.26 391	98.98 413	97.10 346	96.65 358	98.62 382

tpm		97.67 335	97.55 306	98.03 364	99.02 365	95.01 419	99.43 253	98.54 440	96.44 373	99.12 273	99.34 355	91.83 366	99.60 310	97.75 295	96.46 363	99.48 238

PCF-MVS	97.08 14	97.66 336	97.06 364	99.47 161	99.61 184	99.09 165	98.04 467	99.25 348	91.24 454	98.51 370	99.70 211	94.55 282	99.91 135	92.76 442	99.85 94	99.42 256
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 337	97.65 297	97.63 396	98.78 402	97.62 312	99.13 365	98.33 444	97.36 296	99.07 284	98.94 411	95.64 222	99.15 386	92.95 438	98.68 259	96.12 468

our_test_3		97.65 337	97.68 294	97.55 402	98.62 423	94.97 420	98.84 422	99.30 336	96.83 344	98.19 390	99.34 355	97.01 150	99.02 408	95.00 412	96.01 374	98.64 373

testgi		97.65 337	97.50 314	98.13 360	99.36 279	96.45 378	99.42 260	99.48 199	97.76 246	97.87 406	99.45 322	91.09 383	98.81 431	94.53 417	98.52 270	99.13 289

thres200		97.61 340	97.28 351	98.62 300	99.64 160	98.03 285	99.26 334	98.74 424	97.68 257	99.09 281	98.32 441	91.66 373	99.81 227	92.88 439	98.22 290	98.03 436

PAPM		97.59 341	97.09 363	99.07 228	99.06 358	98.26 273	98.30 460	99.10 370	94.88 421	98.08 394	99.34 355	96.27 190	99.64 301	89.87 454	98.92 239	99.31 274

UWE-MVS		97.58 342	97.29 350	98.48 319	99.09 352	96.25 386	99.01 397	96.61 470	97.86 229	99.19 262	99.01 402	88.72 409	99.90 148	97.38 330	98.69 258	99.28 276

SD_0403		97.55 343	97.53 310	97.62 397	99.61 184	93.64 446	99.72 53	99.44 252	98.03 213	98.62 362	99.39 339	96.06 197	99.57 313	87.88 463	99.01 233	99.66 164

VDDNet		97.55 343	97.02 365	99.16 220	99.49 238	98.12 282	99.38 282	99.30 336	95.35 410	99.68 114	99.90 33	82.62 456	99.93 110	99.31 86	98.13 299	99.42 256

TESTMET0.1,1		97.55 343	97.27 354	98.40 335	98.93 379	96.53 375	98.67 437	97.61 459	96.96 333	98.64 357	99.28 370	88.63 415	99.45 326	97.30 334	99.38 183	99.21 285

pmmvs5		97.52 346	97.30 348	98.16 356	98.57 429	96.73 365	99.27 325	98.90 402	96.14 395	98.37 378	99.53 293	91.54 376	99.14 388	97.51 318	95.87 380	98.63 380

LF4IMVS		97.52 346	97.46 321	97.70 394	98.98 374	95.55 402	99.29 315	98.82 412	98.07 197	98.66 350	99.64 249	89.97 396	99.61 309	97.01 351	96.68 357	97.94 444

DTE-MVSNet		97.51 348	97.19 357	98.46 325	98.63 422	98.13 280	99.84 12	99.48 199	96.68 350	97.97 401	99.67 236	92.92 333	98.56 438	96.88 363	92.60 441	98.70 343

testing11		97.50 349	97.10 362	98.71 293	99.20 322	96.91 358	99.29 315	98.82 412	97.89 226	98.21 389	98.40 437	85.63 440	99.83 213	98.45 223	98.04 302	99.37 266

ETVMVS		97.50 349	96.90 369	99.29 202	99.23 315	98.78 229	99.32 304	98.90 402	97.52 278	98.56 367	98.09 451	84.72 447	99.69 286	97.86 279	97.88 308	99.39 262

hse-mvs2		97.50 349	97.14 359	98.59 302	99.49 238	97.05 339	99.28 320	99.22 354	98.94 78	99.66 125	99.42 327	94.93 251	99.65 297	99.48 64	83.80 468	99.08 295

SixPastTwentyTwo		97.50 349	97.33 345	98.03 364	98.65 420	96.23 387	99.77 34	98.68 433	97.14 314	97.90 404	99.93 10	90.45 389	99.18 383	97.00 352	96.43 364	98.67 360

JIA-IIPM		97.50 349	97.02 365	98.93 249	98.73 411	97.80 302	99.30 310	98.97 388	91.73 452	98.91 313	94.86 470	95.10 245	99.71 274	97.58 309	97.98 303	99.28 276

ppachtmachnet_test		97.49 354	97.45 322	97.61 400	98.62 423	95.24 413	98.80 426	99.46 232	96.11 397	98.22 388	99.62 260	96.45 182	98.97 420	93.77 426	95.97 379	98.61 391

test-mter		97.49 354	97.13 361	98.55 312	98.79 399	97.10 333	98.67 437	97.75 456	96.65 353	98.61 363	98.85 417	88.23 419	99.45 326	97.25 336	99.38 183	99.10 290

testing91		97.44 356	97.02 365	98.71 293	99.18 328	96.89 360	99.19 355	99.04 380	97.78 244	98.31 381	98.29 442	85.41 442	99.85 187	98.01 268	97.95 304	99.39 262

tpm2		97.44 356	97.34 342	97.74 392	99.15 342	94.36 435	99.45 240	98.94 391	93.45 440	98.90 315	99.44 323	91.35 379	99.59 311	97.31 333	98.07 301	99.29 275

tpm cat1		97.39 358	97.36 337	97.50 404	99.17 336	93.73 442	99.43 253	99.31 331	91.27 453	98.71 341	99.08 393	94.31 295	99.77 248	96.41 381	98.50 271	99.00 306

UWE-MVS-28		97.36 359	97.24 355	97.75 390	98.84 395	94.44 432	99.24 341	97.58 460	97.98 218	99.00 299	99.00 403	91.35 379	99.53 319	93.75 427	98.39 275	99.27 280

testing99		97.36 359	96.94 368	98.63 299	99.18 328	96.70 366	99.30 310	98.93 392	97.71 252	98.23 386	98.26 443	84.92 445	99.84 196	98.04 267	97.85 311	99.35 268

SSC-MVS3.2		97.34 361	97.15 358	97.93 375	99.02 365	95.76 398	99.48 222	99.58 78	97.62 264	99.09 281	99.53 293	87.95 422	99.27 364	96.42 379	95.66 387	98.75 330

USDC		97.34 361	97.20 356	97.75 390	99.07 356	95.20 414	98.51 450	99.04 380	97.99 217	98.31 381	99.86 73	89.02 405	99.55 317	95.67 398	97.36 345	98.49 402

UniMVSNet_ETH3D		97.32 363	96.81 371	98.87 268	99.40 268	97.46 317	99.51 186	99.53 125	95.86 405	98.54 369	99.77 180	82.44 457	99.66 292	98.68 189	97.52 329	99.50 234

testing3		97.28 364	96.76 373	98.82 277	99.37 276	98.07 284	99.45 240	99.36 297	97.56 271	97.89 405	98.95 410	83.70 451	98.82 430	96.03 387	98.56 267	99.58 205

MVS		97.28 364	96.55 377	99.48 155	98.78 402	98.95 193	99.27 325	99.39 278	83.53 470	98.08 394	99.54 289	96.97 151	99.87 175	94.23 422	99.16 204	99.63 182

test_fmvs2		97.25 366	97.30 348	97.09 415	99.43 256	93.31 449	99.73 51	98.87 407	98.83 88	99.28 235	99.80 147	84.45 448	99.66 292	97.88 276	97.45 337	98.30 419

DSMNet-mixed		97.25 366	97.35 339	96.95 420	97.84 443	93.61 447	99.57 138	96.63 469	96.13 396	98.87 321	98.61 430	94.59 278	97.70 456	95.08 410	98.86 247	99.55 212

MS-PatchMatch		97.24 368	97.32 346	96.99 417	98.45 434	93.51 448	98.82 424	99.32 327	97.41 292	98.13 393	99.30 366	88.99 406	99.56 315	95.68 397	99.80 125	97.90 447

testing222		97.16 369	96.50 378	99.16 220	99.16 338	98.47 264	99.27 325	98.66 435	97.71 252	98.23 386	98.15 446	82.28 459	99.84 196	97.36 331	97.66 317	99.18 286

TransMVSNet (Re)		97.15 370	96.58 376	98.86 271	99.12 344	98.85 215	99.49 214	98.91 400	95.48 409	97.16 425	99.80 147	93.38 322	99.11 397	94.16 424	91.73 444	98.62 382

TinyColmap		97.12 371	96.89 370	97.83 385	99.07 356	95.52 405	98.57 446	98.74 424	97.58 268	97.81 409	99.79 164	88.16 420	99.56 315	95.10 409	97.21 350	98.39 415

K. test v3		97.10 372	96.79 372	98.01 367	98.72 413	96.33 382	99.87 8	97.05 463	97.59 266	96.16 439	99.80 147	88.71 410	99.04 404	96.69 370	96.55 362	98.65 371

Syy-MVS		97.09 373	97.14 359	96.95 420	99.00 368	92.73 453	99.29 315	99.39 278	97.06 325	97.41 415	98.15 446	93.92 311	98.68 436	91.71 447	98.34 277	99.45 252

PatchT		97.03 374	96.44 380	98.79 283	98.99 371	98.34 270	99.16 359	99.07 376	92.13 450	99.52 173	97.31 463	94.54 283	98.98 413	88.54 459	98.73 256	99.03 303

mmtdpeth		96.95 375	96.71 374	97.67 395	99.33 286	94.90 422	99.89 2	99.28 342	98.15 175	99.72 102	98.57 431	86.56 433	99.90 148	99.82 29	89.02 459	98.20 426

myMVS_eth3d		96.89 376	96.37 381	98.43 332	99.00 368	97.16 330	99.29 315	99.39 278	97.06 325	97.41 415	98.15 446	83.46 453	98.68 436	95.27 407	98.34 277	99.45 252

AUN-MVS		96.88 377	96.31 383	98.59 302	99.48 245	97.04 342	99.27 325	99.22 354	97.44 288	98.51 370	99.41 331	91.97 362	99.66 292	97.71 300	83.83 467	99.07 300

FMVSNet1		96.84 378	96.36 382	98.29 345	99.32 293	97.26 326	99.43 253	99.48 199	95.11 414	98.55 368	99.32 363	83.95 450	98.98 413	95.81 392	96.26 369	98.62 382

test2506		96.81 379	96.65 375	97.29 410	99.74 100	92.21 456	99.60 113	85.06 487	99.13 41	99.77 85	99.93 10	87.82 426	99.85 187	99.38 74	99.38 183	99.80 88

RPMNet		96.72 380	95.90 393	99.19 217	99.18 328	98.49 260	99.22 348	99.52 130	88.72 463	99.56 162	97.38 460	94.08 304	99.95 76	86.87 468	98.58 264	99.14 287

mvs5depth		96.66 381	96.22 385	97.97 371	97.00 459	96.28 384	98.66 440	99.03 382	96.61 358	96.93 431	99.79 164	87.20 429	99.47 322	96.65 374	94.13 418	98.16 428

test_0402		96.64 382	96.24 384	97.85 382	98.85 393	96.43 379	99.44 247	99.26 346	93.52 437	96.98 429	99.52 297	88.52 416	99.20 382	92.58 444	97.50 332	97.93 445

X-MVStestdata		96.55 383	95.45 402	99.87 21	99.85 31	99.83 22	99.69 62	99.68 24	98.98 72	99.37 211	64.01 483	98.81 49	99.94 92	98.79 175	99.86 87	99.84 53

pmmvs6		96.53 384	96.09 389	97.82 387	98.69 417	95.47 406	99.37 284	99.47 221	93.46 439	97.41 415	99.78 171	87.06 430	99.33 354	96.92 361	92.70 439	98.65 371

ET-MVSNet_ETH3D		96.49 385	95.64 399	99.05 232	99.53 215	98.82 223	98.84 422	97.51 461	97.63 262	84.77 470	99.21 382	92.09 360	98.91 426	98.98 134	92.21 442	99.41 259

UnsupCasMVSNet_eth		96.44 386	96.12 387	97.40 407	98.65 420	95.65 399	99.36 290	99.51 151	97.13 315	96.04 441	98.99 405	88.40 417	98.17 445	96.71 368	90.27 452	98.40 414

FMVSNet5		96.43 387	96.19 386	97.15 411	99.11 346	95.89 395	99.32 304	99.52 130	94.47 430	98.34 380	99.07 394	87.54 427	97.07 463	92.61 443	95.72 385	98.47 405

new_pmnet		96.38 388	96.03 390	97.41 406	98.13 440	95.16 417	99.05 384	99.20 358	93.94 432	97.39 418	98.79 423	91.61 375	99.04 404	90.43 452	95.77 382	98.05 435

Anonymous20231206		96.22 389	96.03 390	96.79 425	97.31 453	94.14 438	99.63 101	99.08 373	96.17 391	97.04 428	99.06 396	93.94 309	97.76 455	86.96 467	95.06 401	98.47 405

IB-MVS	95.67 18	96.22 389	95.44 403	98.57 306	99.21 320	96.70 366	98.65 441	97.74 458	96.71 348	97.27 420	98.54 432	86.03 437	99.92 123	98.47 221	86.30 464	99.10 290
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		96.20 391	95.89 394	97.13 413	97.72 447	94.96 421	99.79 31	99.29 340	93.01 444	97.20 424	99.03 399	89.69 400	98.36 442	91.16 450	96.13 371	98.07 433

gg-mvs-nofinetune		96.17 392	95.32 404	98.73 288	98.79 399	98.14 279	99.38 282	94.09 478	91.07 456	98.07 397	91.04 476	89.62 402	99.35 351	96.75 366	99.09 225	98.68 352

test20.03		96.12 393	95.96 392	96.63 426	97.44 449	95.45 407	99.51 186	99.38 286	96.55 364	96.16 439	99.25 376	93.76 318	96.17 469	87.35 466	94.22 416	98.27 421

PVSNet_0	94.43 19	96.09 394	95.47 401	97.94 374	99.31 294	94.34 436	97.81 468	99.70 18	97.12 317	97.46 414	98.75 425	89.71 399	99.79 240	97.69 303	81.69 470	99.68 155

MVStest1		96.08 395	95.48 400	97.89 379	98.93 379	96.70 366	99.56 146	99.35 304	92.69 448	91.81 465	99.46 320	89.90 397	98.96 422	95.00 412	92.61 440	98.00 440

EG-PatchMatch MVS		95.97 396	95.69 397	96.81 424	97.78 444	92.79 452	99.16 359	98.93 392	96.16 392	94.08 453	99.22 379	82.72 455	99.47 322	95.67 398	97.50 332	98.17 427

APD_test1		95.87 397	96.49 379	94.00 439	99.53 215	84.01 468	99.54 166	99.32 327	95.91 404	97.99 399	99.85 80	85.49 441	99.88 168	91.96 446	98.84 249	98.12 430

Patchmatch-RL test		95.84 398	95.81 396	95.95 434	95.61 464	90.57 460	98.24 461	98.39 442	95.10 416	95.20 446	98.67 427	94.78 262	97.77 454	96.28 384	90.02 453	99.51 230

test_vis1_rt		95.81 399	95.65 398	96.32 431	99.67 134	91.35 459	99.49 214	96.74 468	98.25 160	95.24 444	98.10 450	74.96 466	99.90 148	99.53 53	98.85 248	97.70 450

sc_t1		95.75 400	95.05 407	97.87 380	98.83 396	94.61 429	99.21 350	99.45 243	87.45 464	97.97 401	99.85 80	81.19 462	99.43 335	98.27 241	93.20 432	99.57 208

MVS-HIRNet		95.75 400	95.16 405	97.51 403	99.30 295	93.69 444	98.88 418	95.78 472	85.09 469	98.78 335	92.65 472	91.29 381	99.37 344	94.85 414	99.85 94	99.46 249

tt0320		95.71 402	95.07 406	97.62 397	99.05 361	95.02 418	99.25 336	99.52 130	86.81 465	97.97 401	99.72 204	83.58 452	99.15 386	96.38 382	93.35 428	98.68 352

MIMVSNet1		95.51 403	95.04 408	96.92 422	97.38 450	95.60 400	99.52 177	99.50 174	93.65 436	96.97 430	99.17 384	85.28 444	96.56 467	88.36 460	95.55 391	98.60 394

MDA-MVSNet_test_wron		95.45 404	94.60 411	98.01 367	98.16 439	97.21 329	99.11 374	99.24 351	93.49 438	80.73 476	98.98 407	93.02 330	98.18 444	94.22 423	94.45 412	98.64 373

TDRefinement		95.42 405	94.57 413	97.97 371	89.83 480	96.11 391	99.48 222	98.75 421	96.74 346	96.68 433	99.88 52	88.65 413	99.71 274	98.37 231	82.74 469	98.09 432

YYNet1		95.36 406	94.51 414	97.92 376	97.89 442	97.10 333	99.10 376	99.23 352	93.26 442	80.77 475	99.04 398	92.81 336	98.02 448	94.30 419	94.18 417	98.64 373

pmmvs-eth3d		95.34 407	94.73 410	97.15 411	95.53 466	95.94 394	99.35 295	99.10 370	95.13 412	93.55 456	97.54 458	88.15 421	97.91 451	94.58 416	89.69 457	97.61 451

tt0320-xc		95.31 408	94.59 412	97.45 405	98.92 381	94.73 424	99.20 353	99.31 331	86.74 466	97.23 421	99.72 204	81.14 463	98.95 423	97.08 349	91.98 443	98.67 360

FE-MVSNET2		95.10 409	94.44 415	97.08 416	95.08 469	95.97 393	99.51 186	99.37 295	95.02 418	94.10 452	97.57 456	86.18 436	97.66 458	93.28 433	89.86 455	97.61 451

dmvs_testset		95.02 410	96.12 387	91.72 448	99.10 349	80.43 476	99.58 130	97.87 455	97.47 281	95.22 445	98.82 419	93.99 307	95.18 473	88.09 461	94.91 406	99.56 211

KD-MVS_self_test		95.00 411	94.34 416	96.96 419	97.07 458	95.39 410	99.56 146	99.44 252	95.11 414	97.13 426	97.32 462	91.86 365	97.27 462	90.35 453	81.23 471	98.23 425

MDA-MVSNet-bldmvs		94.96 412	93.98 419	97.92 376	98.24 438	97.27 324	99.15 362	99.33 317	93.80 434	80.09 477	99.03 399	88.31 418	97.86 453	93.49 431	94.36 414	98.62 382

N_pmnet		94.95 413	95.83 395	92.31 446	98.47 433	79.33 478	99.12 368	92.81 484	93.87 433	97.68 411	99.13 389	93.87 313	99.01 410	91.38 449	96.19 370	98.59 395

KD-MVS_2432*1600		94.62 414	93.72 422	97.31 408	97.19 456	95.82 396	98.34 456	99.20 358	95.00 419	97.57 412	98.35 439	87.95 422	98.10 446	92.87 440	77.00 474	98.01 437

miper_refine_blended		94.62 414	93.72 422	97.31 408	97.19 456	95.82 396	98.34 456	99.20 358	95.00 419	97.57 412	98.35 439	87.95 422	98.10 446	92.87 440	77.00 474	98.01 437

CL-MVSNet_self_test		94.49 416	93.97 420	96.08 433	96.16 461	93.67 445	98.33 458	99.38 286	95.13 412	97.33 419	98.15 446	92.69 344	96.57 466	88.67 458	79.87 472	97.99 441

new-patchmatchnet		94.48 417	94.08 418	95.67 435	95.08 469	92.41 454	99.18 357	99.28 342	94.55 429	93.49 457	97.37 461	87.86 425	97.01 464	91.57 448	88.36 460	97.61 451

OpenMVS_ROB	92.34 20	94.38 418	93.70 424	96.41 430	97.38 450	93.17 450	99.06 382	98.75 421	86.58 467	94.84 450	98.26 443	81.53 460	99.32 356	89.01 457	97.87 309	96.76 461

CMPMVS	69.68 23	94.13 419	94.90 409	91.84 447	97.24 454	80.01 477	98.52 449	99.48 199	89.01 461	91.99 464	99.67 236	85.67 439	99.13 391	95.44 402	97.03 355	96.39 465
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 420	93.25 427	96.60 427	94.76 472	94.49 431	98.92 414	98.18 451	89.66 457	96.48 435	98.06 452	86.28 435	97.33 461	89.68 455	87.20 463	97.97 443

FE-MVSNET		94.07 421	93.36 426	96.22 432	94.05 474	94.71 426	99.56 146	98.36 443	93.15 443	93.76 455	97.55 457	86.47 434	96.49 468	87.48 464	89.83 456	97.48 457

mvsany_test3		93.77 422	93.45 425	94.74 437	95.78 463	88.01 463	99.64 95	98.25 446	98.28 150	94.31 451	97.97 453	68.89 470	98.51 440	97.50 319	90.37 451	97.71 448

FE-MVSNET1		93.64 423	92.69 429	96.48 429	94.12 473	94.21 437	99.34 298	99.38 286	93.42 441	93.33 458	97.58 455	74.82 468	97.65 459	92.56 445	89.64 458	97.58 454

UnsupCasMVSNet_bld		93.53 424	92.51 430	96.58 428	97.38 450	93.82 440	98.24 461	99.48 199	91.10 455	93.10 459	96.66 465	74.89 467	98.37 441	94.03 425	87.71 462	97.56 455

dongtai		93.26 425	92.93 428	94.25 438	99.39 271	85.68 466	97.68 470	93.27 480	92.87 446	96.85 432	99.39 339	82.33 458	97.48 460	76.78 474	97.80 312	99.58 205

WB-MVS		93.10 426	94.10 417	90.12 453	95.51 468	81.88 473	99.73 51	99.27 345	95.05 417	93.09 460	98.91 416	94.70 271	91.89 477	76.62 475	94.02 422	96.58 463

PM-MVS		92.96 427	92.23 431	95.14 436	95.61 464	89.98 462	99.37 284	98.21 449	94.80 424	95.04 449	97.69 454	65.06 471	97.90 452	94.30 419	89.98 454	97.54 456

SSC-MVS		92.73 428	93.73 421	89.72 454	95.02 471	81.38 474	99.76 37	99.23 352	94.87 422	92.80 461	98.93 412	94.71 270	91.37 478	74.49 477	93.80 424	96.42 464

test_fmvs3		92.10 429	91.77 432	93.08 444	96.19 460	86.25 464	99.82 16	98.62 437	96.65 353	95.19 447	96.90 464	55.05 478	95.93 471	96.63 375	90.92 450	97.06 460

test_f		91.90 430	91.26 434	93.84 440	95.52 467	85.92 465	99.69 62	98.53 441	95.31 411	93.87 454	96.37 467	55.33 477	98.27 443	95.70 395	90.98 449	97.32 459

test_method		91.10 431	91.36 433	90.31 452	95.85 462	73.72 485	94.89 474	99.25 348	68.39 476	95.82 442	99.02 401	80.50 464	98.95 423	93.64 429	94.89 407	98.25 423

Gipuma		90.99 432	90.15 437	93.51 441	98.73 411	90.12 461	93.98 475	99.45 243	79.32 472	92.28 462	94.91 469	69.61 469	97.98 450	87.42 465	95.67 386	92.45 472
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 433	90.11 438	93.34 442	98.78 402	85.59 467	98.15 465	93.16 482	89.37 460	92.07 463	98.38 438	81.48 461	95.19 472	62.54 481	97.04 354	99.25 281

testf1		90.42 434	90.68 435	89.65 455	97.78 444	73.97 483	99.13 365	98.81 414	89.62 458	91.80 466	98.93 412	62.23 474	98.80 432	86.61 469	91.17 446	96.19 466

APD_test2		90.42 434	90.68 435	89.65 455	97.78 444	73.97 483	99.13 365	98.81 414	89.62 458	91.80 466	98.93 412	62.23 474	98.80 432	86.61 469	91.17 446	96.19 466

test_vis3_rt		87.04 436	85.81 439	90.73 451	93.99 475	81.96 472	99.76 37	90.23 486	92.81 447	81.35 474	91.56 474	40.06 482	99.07 401	94.27 421	88.23 461	91.15 474

PMMVS2		86.87 437	85.37 441	91.35 450	90.21 479	83.80 469	98.89 417	97.45 462	83.13 471	91.67 468	95.03 468	48.49 480	94.70 474	85.86 471	77.62 473	95.54 469

LCM-MVSNet		86.80 438	85.22 442	91.53 449	87.81 481	80.96 475	98.23 463	98.99 386	71.05 474	90.13 469	96.51 466	48.45 481	96.88 465	90.51 451	85.30 465	96.76 461

FPMVS		84.93 439	85.65 440	82.75 461	86.77 482	63.39 487	98.35 455	98.92 395	74.11 473	83.39 472	98.98 407	50.85 479	92.40 476	84.54 472	94.97 403	92.46 471

EGC-MVSNET		82.80 440	77.86 446	97.62 397	97.91 441	96.12 390	99.33 301	99.28 342	8.40 484	25.05 485	99.27 373	84.11 449	99.33 354	89.20 456	98.22 290	97.42 458

tmp_tt		82.80 440	81.52 443	86.66 457	66.61 487	68.44 486	92.79 477	97.92 453	68.96 475	80.04 478	99.85 80	85.77 438	96.15 470	97.86 279	43.89 480	95.39 470

E-PMN		80.61 442	79.88 444	82.81 460	90.75 478	76.38 481	97.69 469	95.76 473	66.44 478	83.52 471	92.25 473	62.54 473	87.16 480	68.53 479	61.40 477	84.89 478

EMVS		80.02 443	79.22 445	82.43 462	91.19 477	76.40 480	97.55 472	92.49 485	66.36 479	83.01 473	91.27 475	64.63 472	85.79 481	65.82 480	60.65 478	85.08 477

ANet_high		77.30 444	74.86 448	84.62 459	75.88 485	77.61 479	97.63 471	93.15 483	88.81 462	64.27 480	89.29 477	36.51 483	83.93 482	75.89 476	52.31 479	92.33 473

MVE	76.82 21	76.91 445	74.31 449	84.70 458	85.38 484	76.05 482	96.88 473	93.17 481	67.39 477	71.28 479	89.01 478	21.66 488	87.69 479	71.74 478	72.29 476	90.35 475
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 446	74.97 447	79.01 463	70.98 486	55.18 488	93.37 476	98.21 449	65.08 480	61.78 481	93.83 471	21.74 487	92.53 475	78.59 473	91.12 448	89.34 476
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		40.18 447	41.29 452	36.84 464	86.18 483	49.12 489	79.73 478	22.81 489	27.64 481	25.46 484	28.45 484	21.98 486	48.89 483	55.80 482	23.56 483	12.51 481

testmvs		39.17 448	43.78 450	25.37 466	36.04 489	16.84 491	98.36 454	26.56 488	20.06 482	38.51 483	67.32 479	29.64 485	15.30 485	37.59 483	39.90 481	43.98 480

test123		39.01 449	42.50 451	28.53 465	39.17 488	20.91 490	98.75 431	19.17 490	19.83 483	38.57 482	66.67 480	33.16 484	15.42 484	37.50 484	29.66 482	49.26 479

cdsmvs_eth3d_5k		24.64 450	32.85 453	0.00 467	0.00 490	0.00 492	0.00 479	99.51 151	0.00 485	0.00 486	99.56 281	96.58 174	0.00 486	0.00 485	0.00 484	0.00 482

ab-mvs-re		8.30 451	11.06 454	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	99.58 273	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

pcd_1.5k_mvsjas		8.27 452	11.03 455	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	99.01 20	0.00 486	0.00 485	0.00 484	0.00 482

test_blank		0.13 453	0.17 456	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	1.57 485	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

mmdepth		0.02 454	0.03 457	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

monomultidepth		0.02 454	0.03 457	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

uanet_test		0.02 454	0.03 457	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

DCPMVS		0.02 454	0.03 457	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

sosnet-low-res		0.02 454	0.03 457	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

sosnet		0.02 454	0.03 457	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

uncertanet		0.02 454	0.03 457	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

Regformer		0.02 454	0.03 457	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

uanet		0.02 454	0.03 457	0.00 467	0.00 490	0.00 492	0.00 479	0.00 491	0.00 485	0.00 486	0.27 486	0.00 489	0.00 486	0.00 485	0.00 484	0.00 482

MED-MVS test				99.87 21	99.88 13	99.81 33	99.69 62	99.87 6	99.34 26	99.90 34	99.83 101		99.95 76	98.83 167	99.89 68	99.83 63

TestfortrainingZip							99.69 62

WAC-MVS						97.16 330								95.47 401

FOURS1					99.91 1	99.93 1	99.87 8	99.56 90	99.10 48	99.81 69

MSC_two_6792asdad				99.87 21	99.51 224	99.76 49		99.33 317					99.96 41	98.87 154	99.84 102	99.89 29

PC_three_1452									98.18 173	99.84 56	99.70 211	99.31 3	98.52 439	98.30 240	99.80 125	99.81 79

No_MVS				99.87 21	99.51 224	99.76 49		99.33 317					99.96 41	98.87 154	99.84 102	99.89 29

test_one_0601					99.81 57	99.88 10		99.49 187	98.97 75	99.65 134	99.81 129	99.09 16

eth-test2					0.00 490

eth-test					0.00 490

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 342	99.56 162	99.54 289	98.58 78	99.96 41	96.93 359	99.75 142

RE-MVS-def			99.34 50		99.76 82	99.82 28	99.63 101	99.52 130	98.38 137	99.76 91	99.82 114	98.75 60		98.61 199	99.81 120	99.77 100

IU-MVS					99.84 38	99.88 10		99.32 327	98.30 149	99.84 56				98.86 159	99.85 94	99.89 29

OPU-MVS				99.64 101	99.56 203	99.72 56	99.60 113				99.70 211	99.27 7	99.42 337	98.24 244	99.80 125	99.79 92

test_241102_TWO								99.48 199	99.08 56	99.88 43	99.81 129	98.94 34	99.96 41	98.91 148	99.84 102	99.88 35

test_241102_ONE					99.84 38	99.90 3		99.48 199	99.07 58	99.91 31	99.74 194	99.20 9	99.76 252

9.14			99.10 99		99.72 111		99.40 273	99.51 151	97.53 276	99.64 139	99.78 171	98.84 46	99.91 135	97.63 305	99.82 117

save fliter					99.76 82	99.59 88	99.14 364	99.40 275	99.00 67

test_0728_THIRD									98.99 69	99.81 69	99.80 147	99.09 16	99.96 41	98.85 161	99.90 57	99.88 35

test_0728_SECOND				99.91 6	99.84 38	99.89 6	99.57 138	99.51 151					99.96 41	98.93 145	99.86 87	99.88 35

test0726					99.85 31	99.89 6	99.62 106	99.50 174	99.10 48	99.86 53	99.82 114	98.94 34

GSMVS																99.52 221

test_part2					99.81 57	99.83 22				99.77 85

sam_mvs1												94.86 257				99.52 221

sam_mvs												94.72 269

ambc				93.06 445	92.68 476	82.36 470	98.47 451	98.73 430		95.09 448	97.41 459	55.55 476	99.10 399	96.42 379	91.32 445	97.71 448

MTGPA								99.47 221

test_post1							99.23 344				65.14 482	94.18 300	99.71 274	97.58 309

test_post											65.99 481	94.65 276	99.73 264

patchmatchnet-post											98.70 426	94.79 261	99.74 258

GG-mvs-BLEND				98.45 327	98.55 430	98.16 277	99.43 253	93.68 479		97.23 421	98.46 434	89.30 403	99.22 375	95.43 403	98.22 290	97.98 442

MTMP							99.54 166	98.88 405

gm-plane-assit					98.54 431	92.96 451			94.65 427		99.15 387		99.64 301	97.56 314

test9_res														97.49 320	99.72 148	99.75 109

TEST9					99.67 134	99.65 75	99.05 384	99.41 268	96.22 387	98.95 308	99.49 307	98.77 56	99.91 135

test_8					99.67 134	99.61 85	99.03 389	99.41 268	96.28 381	98.93 311	99.48 313	98.76 57	99.91 135

agg_prior2														97.21 338	99.73 147	99.75 109

agg_prior					99.67 134	99.62 83		99.40 275		98.87 321			99.91 135

TestCases				99.31 194	99.86 25	98.48 262		99.61 60	97.85 232	99.36 217	99.85 80	95.95 203	99.85 187	96.66 372	99.83 113	99.59 201

test_prior4						99.56 94	98.99 400

test_prior2							98.96 407		98.34 143	99.01 295	99.52 297	98.68 70		97.96 271	99.74 145

test_prior				99.68 89	99.67 134	99.48 111		99.56 90					99.83 213			99.74 113

旧先验2							98.96 407		96.70 349	99.47 181			99.94 92	98.19 247

新几何2							99.01 397

新几何1				99.75 77	99.75 92	99.59 88		99.54 109	96.76 345	99.29 234	99.64 249	98.43 89	99.94 92	96.92 361	99.66 159	99.72 132

旧先验1					99.74 100	99.59 88		99.54 109			99.69 222	98.47 86			99.68 156	99.73 122

无先验							98.99 400	99.51 151	96.89 339				99.93 110	97.53 317		99.72 132

原ACMM2							98.95 410

原ACMM1				99.65 95	99.73 107	99.33 130		99.47 221	97.46 282	99.12 273	99.66 241	98.67 72	99.91 135	97.70 302	99.69 153	99.71 143

test222					99.75 92	99.49 109	98.91 416	99.49 187	96.42 375	99.34 224	99.65 243	98.28 100			99.69 153	99.72 132

testdata2													99.95 76	96.67 371

segment_acmp												98.96 27

testdata				99.54 125	99.75 92	98.95 193		99.51 151	97.07 323	99.43 192	99.70 211	98.87 42	99.94 92	97.76 293	99.64 162	99.72 132

testdata1							98.85 421		98.32 147

test12				99.75 77	99.64 160	99.61 85		99.29 340		99.21 256		98.38 95	99.89 163		99.74 145	99.74 113

plane_prior7					99.29 299	97.03 345

plane_prior6					99.27 304	96.98 349						92.71 342

plane_prior5								99.47 221					99.69 286	97.78 289	97.63 318	98.67 360

plane_prior4											99.61 264

plane_prior3						97.00 347			98.69 107	99.11 275

plane_prior2							99.39 277		98.97 75

plane_prior1					99.26 307

plane_prior						96.97 350	99.21 350		98.45 130						97.60 321

n2								0.00 491

nn								0.00 491

door-mid								98.05 452

lessismore_v0				97.79 389	98.69 417	95.44 409		94.75 476		95.71 443	99.87 65	88.69 411	99.32 356	95.89 390	94.93 405	98.62 382

LGP-MVS_train				98.49 317	99.33 286	97.05 339		99.55 100	97.46 282	99.24 248	99.83 101	92.58 347	99.72 268	98.09 258	97.51 330	98.68 352

test11								99.35 304

door								97.92 453

HQP5-MVS						96.83 361

HQP-NCC					99.19 325		98.98 403		98.24 162	98.66 350

ACMP_Plane					99.19 325		98.98 403		98.24 162	98.66 350

BP-MVS														97.19 342

HQP4-MVS										98.66 350			99.64 301			98.64 373

HQP3-MVS								99.39 278							97.58 323

HQP2-MVS												92.47 351

NP-MVS					99.23 315	96.92 357					99.40 335

MDTV_nov1_ep13_2view						95.18 416	99.35 295		96.84 342	99.58 158		95.19 242		97.82 284		99.46 249

MDTV_nov1_ep13			98.32 227		99.11 346	94.44 432	99.27 325	98.74 424	97.51 279	99.40 205	99.62 260	94.78 262	99.76 252	97.59 308	98.81 253

ACMMP++_ref															97.19 351

ACMMP++															97.43 341

Test By Simon												98.75 60

ITE_SJBPF				98.08 362	99.29 299	96.37 380		98.92 395	98.34 143	98.83 327	99.75 189	91.09 383	99.62 308	95.82 391	97.40 343	98.25 423

DeepMVS_CX				93.34 442	99.29 299	82.27 471		99.22 354	85.15 468	96.33 436	99.05 397	90.97 385	99.73 264	93.57 430	97.77 314	98.01 437

High-resolution multi-view benchmark