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 63	99.87 6	99.34 26	99.90 33	99.83 106	99.30 4	99.95 76	99.32 84	99.89 67	99.90 25

fmvsm_l_conf0.5_n_a		99.71 2	99.67 1	99.85 43	99.86 25	99.61 85	99.56 151	99.63 46	99.48 3	99.98 13	99.83 106	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	99.56 151	99.63 46	99.47 4	99.98 13	99.82 119	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	99.48 228	99.64 42	99.45 11	99.92 29	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	99.58 135	99.69 22	99.43 17	99.98 13	99.91 26	98.62 76	100.00 1	99.97 2	99.95 22	99.90 25

MED-MVS		99.66 6	99.60 8	99.87 21	99.88 13	99.81 33	99.69 63	99.87 6	99.18 34	99.90 33	99.83 106	99.30 4	99.95 76	98.83 172	99.89 67	99.83 63

APDe-MVS		99.66 6	99.57 10	99.92 1	99.77 78	99.89 6	99.75 43	99.56 89	99.02 62	99.88 42	99.85 85	99.18 12	99.96 41	99.22 104	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 8	99.61 7	99.77 74	99.38 278	99.37 123	99.58 135	99.62 51	99.41 21	99.87 48	99.92 18	98.81 49	100.00 1	99.97 2	99.93 32	99.94 17

reproduce_model		99.63 9	99.54 13	99.90 8	99.78 70	99.88 10	99.56 151	99.55 99	99.15 38	99.90 33	99.90 36	99.00 24	99.97 29	99.11 122	99.91 45	99.86 42

fmvsm_l_conf0.5_n_3		99.61 10	99.51 18	99.92 1	99.84 38	99.82 28	99.54 171	99.66 32	99.46 7	99.98 13	99.89 45	97.27 132	99.99 4	99.97 2	99.95 22	99.95 11

reproduce-ours		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 182	99.54 108	99.13 41	99.89 39	99.89 45	98.96 27	99.96 41	99.04 132	99.90 56	99.85 46

our_new_method		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 182	99.54 108	99.13 41	99.89 39	99.89 45	98.96 27	99.96 41	99.04 132	99.90 56	99.85 46

SED-MVS		99.61 10	99.52 14	99.88 15	99.84 38	99.90 3	99.60 114	99.48 204	99.08 56	99.91 30	99.81 134	99.20 9	99.96 41	98.91 153	99.85 93	99.79 92

lecture		99.60 14	99.50 19	99.89 11	99.89 8	99.90 3	99.75 43	99.59 72	99.06 61	99.88 42	99.85 85	98.41 92	99.96 41	99.28 96	99.84 101	99.83 63

DVP-MVS++		99.59 15	99.50 19	99.88 15	99.51 228	99.88 10	99.87 8	99.51 155	98.99 69	99.88 42	99.81 134	99.27 7	99.96 41	98.85 166	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	99.47 238	99.63 46	99.45 11	99.98 13	99.89 45	97.02 147	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	99.63 102	99.39 285	98.91 82	99.78 80	99.85 85	99.36 2	99.94 92	98.84 169	99.88 75	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	99.60 114	99.45 250	99.01 64	99.90 33	99.83 106	98.98 26	99.93 109	99.59 45	99.95 22	99.86 42

EI-MVSNet-Vis-set		99.58 16	99.56 12	99.64 101	99.78 70	99.15 159	99.61 113	99.45 250	99.01 64	99.89 39	99.82 119	99.01 20	99.92 123	99.56 49	99.95 22	99.85 46

DVP-MVS		99.57 20	99.47 24	99.88 15	99.85 31	99.89 6	99.57 143	99.37 301	99.10 48	99.81 68	99.80 152	98.94 34	99.96 41	98.93 150	99.86 86	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	99.37 289	99.70 18	99.18 34	99.83 63	99.83 106	98.74 65	99.93 109	98.83 172	99.89 67	99.83 63

fmvsm_s_conf0.5_n_a		99.56 21	99.47 24	99.85 43	99.83 47	99.64 81	99.52 182	99.65 39	99.10 48	99.98 13	99.92 18	97.35 128	99.96 41	99.94 21	99.92 38	99.95 11

test_fmvsmconf0.1_n		99.55 23	99.45 30	99.86 34	99.44 259	99.65 75	99.50 203	99.61 60	99.45 11	99.87 48	99.92 18	97.31 129	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	99.51 192	99.62 51	99.46 7	99.99 2	99.90 36	96.60 171	99.98 20	99.95 16	99.95 22	99.96 7

fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 228	99.67 68	99.50 203	99.64 42	99.43 17	99.98 13	99.78 176	97.26 135	99.95 76	99.95 16	99.93 32	99.92 23

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 21	99.82 53	99.81 33	99.59 125	99.51 155	98.62 112	99.79 75	99.83 106	99.28 6	99.97 29	98.48 223	99.90 56	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 63	99.68 24	98.98 72	99.37 216	99.74 199	98.81 49	99.94 92	98.79 180	99.86 86	99.84 53

MTAPA		99.52 28	99.39 39	99.89 11	99.90 4	99.86 18	99.66 83	99.47 226	98.79 95	99.68 118	99.81 134	98.43 89	99.97 29	98.88 156	99.90 56	99.83 63

fmvsm_s_conf0.5_n		99.51 29	99.40 37	99.85 43	99.84 38	99.65 75	99.51 192	99.67 27	99.13 41	99.98 13	99.92 18	96.60 171	99.96 41	99.95 16	99.96 17	99.95 11

HPM-MVS_fast		99.51 29	99.40 37	99.85 43	99.91 1	99.79 41	99.76 38	99.56 89	97.72 256	99.76 90	99.75 194	99.13 14	99.92 123	99.07 129	99.92 38	99.85 46

mvsany_test1		99.50 31	99.46 28	99.62 108	99.61 188	99.09 165	98.94 418	99.48 204	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 99	98.56 118	99.78 80	99.70 216	98.65 74	99.79 246	99.65 41	99.78 134	99.41 263

SPE-MVS-test		99.49 33	99.48 22	99.54 125	99.78 70	99.30 138	99.89 2	99.58 77	98.56 118	99.73 96	99.69 227	98.55 81	99.82 228	99.69 34	99.85 93	99.48 242

HFP-MVS		99.49 33	99.37 43	99.86 34	99.87 20	99.80 38	99.66 83	99.67 27	98.15 176	99.68 118	99.69 227	99.06 18	99.96 41	98.69 192	99.87 78	99.84 53

ACMMPR		99.49 33	99.36 45	99.86 34	99.87 20	99.79 41	99.66 83	99.67 27	98.15 176	99.67 124	99.69 227	98.95 32	99.96 41	98.69 192	99.87 78	99.84 53

DeepC-MVS_fast	98.69 1	99.49 33	99.39 39	99.77 74	99.63 168	99.59 88	99.36 295	99.46 239	99.07 58	99.79 75	99.82 119	98.85 44	99.92 123	98.68 194	99.87 78	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 47	99.87 21	99.88 13	99.80 38	99.65 89	99.66 32	98.13 183	99.66 129	99.68 235	98.96 27	99.96 41	98.62 201	99.87 78	99.84 53

APD-MVS_3200maxsize		99.48 37	99.35 47	99.85 43	99.76 82	99.83 22	99.63 102	99.54 108	98.36 141	99.79 75	99.82 119	98.86 43	99.95 76	98.62 201	99.81 120	99.78 98

DELS-MVS		99.48 37	99.42 32	99.65 95	99.72 111	99.40 121	99.05 390	99.66 32	99.14 40	99.57 166	99.80 152	98.46 87	99.94 92	99.57 48	99.84 101	99.60 195
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 51	99.87 21	99.87 20	99.81 33	99.64 96	99.67 27	98.08 201	99.55 173	99.64 254	98.91 39	99.96 41	98.72 187	99.90 56	99.82 72

ACMMP_NAP		99.47 40	99.34 49	99.88 15	99.87 20	99.86 18	99.47 238	99.48 204	98.05 209	99.76 90	99.86 78	98.82 48	99.93 109	98.82 179	99.91 45	99.84 53

MVSMamba_PlusPlus		99.46 42	99.41 36	99.64 101	99.68 134	99.50 108	99.75 43	99.50 179	98.27 152	99.87 48	99.92 18	98.09 107	99.94 92	99.65 41	99.95 22	99.47 248

balanced_conf03		99.46 42	99.39 39	99.67 90	99.55 211	99.58 93	99.74 48	99.51 155	98.42 134	99.87 48	99.84 100	98.05 110	99.91 135	99.58 47	99.94 30	99.52 225

DPE-MVS		99.46 42	99.32 53	99.91 6	99.78 70	99.88 10	99.36 295	99.51 155	98.73 102	99.88 42	99.84 100	98.72 67	99.96 41	98.16 257	99.87 78	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	99.44 174	99.60 194	99.16 155	99.41 270	99.71 16	98.98 72	99.45 189	99.78 176	99.19 11	99.54 324	99.28 96	99.84 101	99.63 187

SR-MVS-dyc-post		99.45 46	99.31 59	99.85 43	99.76 82	99.82 28	99.63 102	99.52 133	98.38 137	99.76 90	99.82 119	98.53 82	99.95 76	98.61 204	99.81 120	99.77 100

PGM-MVS		99.45 46	99.31 59	99.86 34	99.87 20	99.78 47	99.58 135	99.65 39	97.84 240	99.71 111	99.80 152	99.12 15	99.97 29	98.33 242	99.87 78	99.83 63

CP-MVS		99.45 46	99.32 53	99.85 43	99.83 47	99.75 51	99.69 63	99.52 133	98.07 202	99.53 176	99.63 260	98.93 38	99.97 29	98.74 184	99.91 45	99.83 63

ACMMP		99.45 46	99.32 53	99.82 57	99.89 8	99.67 68	99.62 107	99.69 22	98.12 191	99.63 147	99.84 100	98.73 66	99.96 41	98.55 219	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 61	99.85 43	99.73 107	99.83 22	99.56 151	99.47 226	97.45 290	99.78 80	99.82 119	99.18 12	99.91 135	98.79 180	99.89 67	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 61	99.86 34	99.88 13	99.79 41	99.69 63	99.48 204	98.12 191	99.50 181	99.75 194	98.78 53	99.97 29	98.57 213	99.89 67	99.83 63

EC-MVSNet		99.44 50	99.39 39	99.58 116	99.56 207	99.49 109	99.88 4	99.58 77	98.38 137	99.73 96	99.69 227	98.20 102	99.70 287	99.64 43	99.82 117	99.54 219

SR-MVS		99.43 53	99.29 65	99.86 34	99.75 92	99.83 22	99.59 125	99.62 51	98.21 168	99.73 96	99.79 169	98.68 70	99.96 41	98.44 229	99.77 137	99.79 92

MCST-MVS		99.43 53	99.30 61	99.82 57	99.79 68	99.74 54	99.29 319	99.40 282	98.79 95	99.52 178	99.62 265	98.91 39	99.90 148	98.64 198	99.75 142	99.82 72

MSP-MVS		99.42 55	99.27 72	99.88 15	99.89 8	99.80 38	99.67 76	99.50 179	98.70 106	99.77 84	99.49 312	98.21 101	99.95 76	98.46 227	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 65	99.80 64	99.62 177	99.55 96	99.50 203	99.70 18	98.79 95	99.77 84	99.96 1	97.45 123	99.96 41	98.92 152	99.90 56	99.89 29

HPM-MVS		99.42 55	99.28 68	99.83 56	99.90 4	99.72 56	99.81 20	99.54 108	97.59 271	99.68 118	99.63 260	98.91 39	99.94 92	98.58 210	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 55	99.30 61	99.78 71	99.62 177	99.71 58	99.26 339	99.52 133	98.82 89	99.39 212	99.71 212	98.96 27	99.85 188	98.59 209	99.80 125	99.77 100

fmvsm_s_conf0.5_n_10		99.41 59	99.24 77	99.92 1	99.83 47	99.84 20	99.53 180	99.56 89	99.45 11	99.99 2	99.92 18	94.92 257	99.99 4	99.97 2	99.97 9	99.95 11

fmvsm_s_conf0.5_n_9		99.41 59	99.28 68	99.81 60	99.84 38	99.52 105	99.48 228	99.62 51	99.46 7	99.99 2	99.92 18	95.24 244	99.96 41	99.97 2	99.97 9	99.96 7

SD-MVS		99.41 59	99.52 14	99.05 237	99.74 100	99.68 64	99.46 242	99.52 133	99.11 47	99.88 42	99.91 26	99.43 1	97.70 470	98.72 187	99.93 32	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 51	99.65 95	99.77 78	99.51 107	98.94 418	99.85 9	98.82 89	99.65 139	99.74 199	98.51 84	99.80 240	98.83 172	99.89 67	99.64 182

MVS_111021_HR		99.41 59	99.32 53	99.66 91	99.72 111	99.47 113	98.95 416	99.85 9	98.82 89	99.54 174	99.73 205	98.51 84	99.74 264	98.91 153	99.88 75	99.77 100

MM		99.40 64	99.28 68	99.74 80	99.67 137	99.31 135	99.52 182	98.87 419	99.55 1	99.74 94	99.80 152	96.47 179	99.98 20	99.97 2	99.97 9	99.94 17

GST-MVS		99.40 64	99.24 77	99.85 43	99.86 25	99.79 41	99.60 114	99.67 27	97.97 224	99.63 147	99.68 235	98.52 83	99.95 76	98.38 235	99.86 86	99.81 79

HPM-MVS++		99.39 66	99.23 81	99.87 21	99.75 92	99.84 20	99.43 259	99.51 155	98.68 109	99.27 246	99.53 298	98.64 75	99.96 41	98.44 229	99.80 125	99.79 92

SF-MVS		99.38 67	99.24 77	99.79 68	99.79 68	99.68 64	99.57 143	99.54 108	97.82 246	99.71 111	99.80 152	98.95 32	99.93 109	98.19 253	99.84 101	99.74 118

fmvsm_s_conf0.5_n_5		99.37 68	99.21 83	99.86 34	99.80 63	99.68 64	99.42 266	99.61 60	99.37 24	99.97 25	99.86 78	94.96 252	99.99 4	99.97 2	99.93 32	99.92 23

fmvsm_s_conf0.5_n_3		99.37 68	99.20 85	99.87 21	99.75 92	99.70 60	99.48 228	99.66 32	99.45 11	99.99 2	99.93 10	94.64 284	99.97 29	99.94 21	99.97 9	99.95 11

fmvsm_s_conf0.1_n_2		99.37 68	99.22 82	99.81 60	99.77 78	99.75 51	99.46 242	99.60 67	99.47 4	99.98 13	99.94 6	94.98 251	99.95 76	99.97 2	99.79 132	99.73 127

MP-MVS-pluss		99.37 68	99.20 85	99.88 15	99.90 4	99.87 17	99.30 314	99.52 133	97.18 316	99.60 159	99.79 169	98.79 52	99.95 76	98.83 172	99.91 45	99.83 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_4		99.36 72	99.24 77	99.73 83	99.78 70	99.53 101	99.49 220	99.60 67	99.42 20	99.99 2	99.86 78	95.15 247	99.95 76	99.95 16	99.89 67	99.73 127

TSAR-MVS + GP.		99.36 72	99.36 45	99.36 188	99.67 137	98.61 252	99.07 384	99.33 323	99.00 67	99.82 67	99.81 134	99.06 18	99.84 197	99.09 127	99.42 181	99.65 175

PVSNet_Blended_VisFu		99.36 72	99.28 68	99.61 109	99.86 25	99.07 170	99.47 238	99.93 2	97.66 265	99.71 111	99.86 78	97.73 118	99.96 41	99.47 66	99.82 117	99.79 92

fmvsm_s_conf0.5_n_7		99.34 75	99.29 65	99.48 160	99.70 122	98.63 248	99.42 266	99.63 46	99.46 7	99.98 13	99.88 56	95.59 227	99.96 41	99.97 2	99.98 4	99.85 46

NCCC		99.34 75	99.19 87	99.79 68	99.61 188	99.65 75	99.30 314	99.48 204	98.86 84	99.21 261	99.63 260	98.72 67	99.90 148	98.25 249	99.63 164	99.80 88

MP-MVS		99.33 77	99.15 92	99.87 21	99.88 13	99.82 28	99.66 83	99.46 239	98.09 197	99.48 185	99.74 199	98.29 98	99.96 41	97.93 279	99.87 78	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 78	99.16 91	99.80 64	99.83 47	99.70 60	99.57 143	99.56 89	99.45 11	99.99 2	99.93 10	94.18 307	99.99 4	99.96 13	99.98 4	99.73 127

fmvsm_s_conf0.5_n_2		99.32 78	99.13 94	99.89 11	99.80 63	99.77 48	99.44 253	99.58 77	99.47 4	99.99 2	99.93 10	94.04 312	99.96 41	99.96 13	99.93 32	99.93 22

PS-MVSNAJ		99.32 78	99.32 53	99.30 204	99.57 203	98.94 197	98.97 412	99.46 239	98.92 81	99.71 111	99.24 382	99.01 20	99.98 20	99.35 76	99.66 159	98.97 316

CSCG		99.32 78	99.32 53	99.32 197	99.85 31	98.29 278	99.71 58	99.66 32	98.11 193	99.41 205	99.80 152	98.37 95	99.96 41	98.99 138	99.96 17	99.72 137

PHI-MVS		99.30 82	99.17 90	99.70 87	99.56 207	99.52 105	99.58 135	99.80 11	97.12 322	99.62 151	99.73 205	98.58 78	99.90 148	98.61 204	99.91 45	99.68 160

DeepC-MVS	98.35 2	99.30 82	99.19 87	99.64 101	99.82 53	99.23 148	99.62 107	99.55 99	98.94 78	99.63 147	99.95 3	95.82 216	99.94 92	99.37 75	99.97 9	99.73 127
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 84	99.10 98	99.86 34	99.70 122	99.65 75	99.53 180	99.62 51	98.74 101	99.99 2	99.95 3	94.53 292	99.94 92	99.89 25	99.96 17	99.97 4

xiu_mvs_v1_base_debu		99.29 84	99.27 72	99.34 191	99.63 168	98.97 183	99.12 374	99.51 155	98.86 84	99.84 55	99.47 321	98.18 103	99.99 4	99.50 57	99.31 191	99.08 300

xiu_mvs_v1_base		99.29 84	99.27 72	99.34 191	99.63 168	98.97 183	99.12 374	99.51 155	98.86 84	99.84 55	99.47 321	98.18 103	99.99 4	99.50 57	99.31 191	99.08 300

xiu_mvs_v1_base_debi		99.29 84	99.27 72	99.34 191	99.63 168	98.97 183	99.12 374	99.51 155	98.86 84	99.84 55	99.47 321	98.18 103	99.99 4	99.50 57	99.31 191	99.08 300

NormalMVS		99.27 88	99.19 87	99.52 139	99.89 8	98.83 227	99.65 89	99.52 133	99.10 48	99.84 55	99.76 189	95.80 218	99.99 4	99.30 89	99.84 101	99.74 118

APD-MVS		99.27 88	99.08 104	99.84 55	99.75 92	99.79 41	99.50 203	99.50 179	97.16 318	99.77 84	99.82 119	98.78 53	99.94 92	97.56 320	99.86 86	99.80 88
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
LS3D		99.27 88	99.12 96	99.74 80	99.18 333	99.75 51	99.56 151	99.57 84	98.45 130	99.49 184	99.85 85	97.77 117	99.94 92	98.33 242	99.84 101	99.52 225

fmvsm_s_conf0.1_n_a		99.26 91	99.06 109	99.85 43	99.52 225	99.62 83	99.54 171	99.62 51	98.69 107	99.99 2	99.96 1	94.47 294	99.94 92	99.88 26	99.92 38	99.98 2

patch_mono-2		99.26 91	99.62 6	98.16 363	99.81 57	94.59 444	99.52 182	99.64 42	99.33 28	99.73 96	99.90 36	99.00 24	99.99 4	99.69 34	99.98 4	99.89 29

ETV-MVS		99.26 91	99.21 83	99.40 181	99.46 252	99.30 138	99.56 151	99.52 133	98.52 122	99.44 194	99.27 378	98.41 92	99.86 181	99.10 125	99.59 168	99.04 307

xiu_mvs_v2_base		99.26 91	99.25 76	99.29 207	99.53 219	98.91 204	99.02 398	99.45 250	98.80 94	99.71 111	99.26 380	98.94 34	99.98 20	99.34 81	99.23 200	98.98 314

CANet		99.25 95	99.14 93	99.59 113	99.41 267	99.16 155	99.35 300	99.57 84	98.82 89	99.51 180	99.61 269	96.46 180	99.95 76	99.59 45	99.98 4	99.65 175

3Dnovator	97.25 9	99.24 96	99.05 111	99.81 60	99.12 349	99.66 71	99.84 12	99.74 13	99.09 55	98.92 317	99.90 36	95.94 209	99.98 20	98.95 146	99.92 38	99.79 92

LuminaMVS		99.23 97	99.10 98	99.61 109	99.35 285	99.31 135	99.46 242	99.13 379	98.61 113	99.86 52	99.89 45	96.41 185	99.91 135	99.67 37	99.51 174	99.63 187

dcpmvs_2		99.23 97	99.58 9	98.16 363	99.83 47	94.68 441	99.76 38	99.52 133	99.07 58	99.98 13	99.88 56	98.56 80	99.93 109	99.67 37	99.98 4	99.87 40

test_fmvsmconf0.01_n		99.22 99	99.03 116	99.79 68	98.42 442	99.48 111	99.55 166	99.51 155	99.39 22	99.78 80	99.93 10	94.80 265	99.95 76	99.93 23	99.95 22	99.94 17

diffmvs_AUTHOR		99.19 100	99.10 98	99.48 160	99.64 164	98.85 222	99.32 308	99.48 204	98.50 124	99.81 68	99.81 134	96.82 159	99.88 168	99.40 71	99.12 216	99.71 148

CHOSEN 1792x2688		99.19 100	99.10 98	99.45 169	99.89 8	98.52 262	99.39 282	99.94 1	98.73 102	99.11 280	99.89 45	95.50 230	99.94 92	99.50 57	99.97 9	99.89 29

F-COLMAP		99.19 100	99.04 113	99.64 101	99.78 70	99.27 143	99.42 266	99.54 108	97.29 307	99.41 205	99.59 274	98.42 91	99.93 109	98.19 253	99.69 153	99.73 127

E3new		99.18 103	99.08 104	99.48 160	99.63 168	98.94 197	99.46 242	99.50 179	98.06 206	99.72 101	99.84 100	97.27 132	99.84 197	99.10 125	99.13 211	99.67 164

viewcassd2359sk11		99.18 103	99.08 104	99.49 156	99.65 159	98.95 193	99.48 228	99.51 155	98.10 196	99.72 101	99.87 69	97.13 138	99.84 197	99.13 119	99.14 208	99.69 154

viewmanbaseed2359cas		99.18 103	99.07 108	99.50 149	99.62 177	99.01 177	99.50 203	99.52 133	98.25 160	99.68 118	99.82 119	96.93 152	99.80 240	99.15 118	99.11 218	99.70 151

EIA-MVS		99.18 103	99.09 103	99.45 169	99.49 242	99.18 152	99.67 76	99.53 124	97.66 265	99.40 210	99.44 328	98.10 106	99.81 233	98.94 147	99.62 165	99.35 273

3Dnovator+	97.12 13	99.18 103	98.97 142	99.82 57	99.17 341	99.68 64	99.81 20	99.51 155	99.20 33	98.72 347	99.89 45	95.68 224	99.97 29	98.86 164	99.86 86	99.81 79

MVSFormer		99.17 108	99.12 96	99.29 207	99.51 228	98.94 197	99.88 4	99.46 239	97.55 277	99.80 73	99.65 248	97.39 124	99.28 367	99.03 134	99.85 93	99.65 175

sss		99.17 108	99.05 111	99.53 133	99.62 177	98.97 183	99.36 295	99.62 51	97.83 241	99.67 124	99.65 248	97.37 127	99.95 76	99.19 108	99.19 203	99.68 160

SSM_0404		99.16 110	99.06 109	99.44 174	99.65 159	98.96 187	99.49 220	99.50 179	98.14 180	99.62 151	99.85 85	96.85 154	99.85 188	99.19 108	99.26 196	99.52 225

guyue		99.16 110	99.04 113	99.52 139	99.69 127	98.92 203	99.59 125	98.81 426	98.73 102	99.90 33	99.87 69	95.34 237	99.88 168	99.66 40	99.81 120	99.74 118

test_cas_vis1_n_1920		99.16 110	99.01 133	99.61 109	99.81 57	98.86 221	99.65 89	99.64 42	99.39 22	99.97 25	99.94 6	93.20 336	99.98 20	99.55 50	99.91 45	99.99 1

DP-MVS		99.16 110	98.95 150	99.78 71	99.77 78	99.53 101	99.41 270	99.50 179	97.03 334	99.04 297	99.88 56	97.39 124	99.92 123	98.66 196	99.90 56	99.87 40

E6new		99.15 114	99.03 116	99.50 149	99.66 149	98.90 209	99.60 114	99.53 124	98.13 183	99.72 101	99.91 26	96.31 189	99.84 197	99.30 89	99.10 225	99.76 107

E6		99.15 114	99.03 116	99.50 149	99.66 149	98.90 209	99.60 114	99.53 124	98.13 183	99.72 101	99.91 26	96.31 189	99.84 197	99.30 89	99.10 225	99.76 107

E2		99.15 114	99.03 116	99.49 156	99.65 159	98.93 202	99.49 220	99.52 133	98.14 180	99.72 101	99.88 56	96.57 175	99.84 197	99.17 114	99.13 211	99.72 137

E3		99.15 114	99.03 116	99.49 156	99.62 177	98.91 204	99.49 220	99.52 133	98.13 183	99.72 101	99.88 56	96.61 170	99.84 197	99.17 114	99.13 211	99.72 137

SymmetryMVS		99.15 114	99.02 126	99.52 139	99.72 111	98.83 227	99.65 89	99.34 315	99.10 48	99.84 55	99.76 189	95.80 218	99.99 4	99.30 89	98.72 262	99.73 127

MGCNet		99.15 114	98.96 146	99.73 83	98.92 386	99.37 123	99.37 289	96.92 478	99.51 2	99.66 129	99.78 176	96.69 166	99.97 29	99.84 28	99.97 9	99.84 53

casdiffmvs_mvg		99.15 114	99.02 126	99.55 124	99.66 149	99.09 165	99.64 96	99.56 89	98.26 155	99.45 189	99.87 69	96.03 203	99.81 233	99.54 51	99.15 207	99.73 127
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		99.15 114	99.02 126	99.53 133	99.66 149	99.14 160	99.72 54	99.48 204	98.35 142	99.42 200	99.84 100	96.07 200	99.79 246	99.51 56	99.14 208	99.67 164

E5new		99.14 122	99.02 126	99.50 149	99.69 127	98.91 204	99.60 114	99.53 124	98.13 183	99.72 101	99.91 26	96.26 194	99.84 197	99.30 89	99.10 225	99.76 107

E5		99.14 122	99.02 126	99.50 149	99.69 127	98.91 204	99.60 114	99.53 124	98.13 183	99.72 101	99.91 26	96.26 194	99.84 197	99.30 89	99.10 225	99.76 107

diffmvs		99.14 122	99.02 126	99.51 144	99.61 188	98.96 187	99.28 325	99.49 192	98.46 128	99.72 101	99.71 212	96.50 178	99.88 168	99.31 86	99.11 218	99.67 164
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		99.14 122	98.99 137	99.59 113	99.58 198	99.41 120	99.16 364	99.44 259	98.45 130	99.19 267	99.49 312	98.08 108	99.89 163	97.73 303	99.75 142	99.48 242

E4		99.13 126	99.01 133	99.49 156	99.68 134	98.90 209	99.52 182	99.52 133	98.13 183	99.71 111	99.90 36	96.32 187	99.84 197	99.21 106	99.11 218	99.75 113

SSM_0407		99.13 126	99.03 116	99.43 177	99.62 177	98.88 214	99.51 192	99.50 179	98.14 180	99.37 216	99.85 85	96.85 154	99.83 219	99.19 108	99.25 197	99.60 195

CDPH-MVS		99.13 126	98.91 158	99.80 64	99.75 92	99.71 58	99.15 367	99.41 275	96.60 368	99.60 159	99.55 289	98.83 47	99.90 148	97.48 329	99.83 113	99.78 98

casdiffmvs		99.13 126	98.98 140	99.56 122	99.65 159	99.16 155	99.56 151	99.50 179	98.33 145	99.41 205	99.86 78	95.92 210	99.83 219	99.45 68	99.16 204	99.70 151
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		99.13 126	99.03 116	99.45 169	99.46 252	98.87 218	99.12 374	99.26 357	98.03 218	99.79 75	99.65 248	97.02 147	99.85 188	99.02 136	99.90 56	99.65 175
jason: jason.
lupinMVS		99.13 126	99.01 133	99.46 168	99.51 228	98.94 197	99.05 390	99.16 375	97.86 234	99.80 73	99.56 286	97.39 124	99.86 181	98.94 147	99.85 93	99.58 210

EPP-MVSNet		99.13 126	98.99 137	99.53 133	99.65 159	99.06 171	99.81 20	99.33 323	97.43 294	99.60 159	99.88 56	97.14 137	99.84 197	99.13 119	98.94 241	99.69 154

MG-MVS		99.13 126	99.02 126	99.45 169	99.57 203	98.63 248	99.07 384	99.34 315	98.99 69	99.61 156	99.82 119	97.98 112	99.87 175	97.00 366	99.80 125	99.85 46

KinetiMVS		99.12 134	98.92 155	99.70 87	99.67 137	99.40 121	99.67 76	99.63 46	98.73 102	99.94 28	99.81 134	94.54 290	99.96 41	98.40 233	99.93 32	99.74 118

BP-MVS1		99.12 134	98.94 152	99.65 95	99.51 228	99.30 138	99.67 76	98.92 407	98.48 126	99.84 55	99.69 227	94.96 252	99.92 123	99.62 44	99.79 132	99.71 148

CHOSEN 280x420		99.12 134	99.13 94	99.08 233	99.66 149	97.89 305	98.43 466	99.71 16	98.88 83	99.62 151	99.76 189	96.63 169	99.70 287	99.46 67	99.99 1	99.66 169

DP-MVS Recon		99.12 134	98.95 150	99.65 95	99.74 100	99.70 60	99.27 330	99.57 84	96.40 384	99.42 200	99.68 235	98.75 60	99.80 240	97.98 276	99.72 148	99.44 258

Vis-MVSNet		99.12 134	98.97 142	99.56 122	99.78 70	99.10 164	99.68 73	99.66 32	98.49 125	99.86 52	99.87 69	94.77 270	99.84 197	99.19 108	99.41 182	99.74 118
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 134	99.08 104	99.24 217	99.46 252	98.55 256	99.51 192	99.46 239	98.09 197	99.45 189	99.82 119	98.34 96	99.51 326	98.70 189	98.93 242	99.67 164

viewdifsd2359ckpt07		99.11 140	99.00 136	99.43 177	99.63 168	98.73 238	99.45 246	99.54 108	98.33 145	99.62 151	99.81 134	96.17 197	99.87 175	99.27 99	99.14 208	99.69 154

SDMVSNet		99.11 140	98.90 160	99.75 77	99.81 57	99.59 88	99.81 20	99.65 39	98.78 98	99.64 144	99.88 56	94.56 287	99.93 109	99.67 37	98.26 292	99.72 137

VNet		99.11 140	98.90 160	99.73 83	99.52 225	99.56 94	99.41 270	99.39 285	99.01 64	99.74 94	99.78 176	95.56 228	99.92 123	99.52 55	98.18 300	99.72 137

CPTT-MVS		99.11 140	98.90 160	99.74 80	99.80 63	99.46 114	99.59 125	99.49 192	97.03 334	99.63 147	99.69 227	97.27 132	99.96 41	97.82 290	99.84 101	99.81 79

HyFIR lowres test		99.11 140	98.92 155	99.65 95	99.90 4	99.37 123	99.02 398	99.91 3	97.67 264	99.59 162	99.75 194	95.90 212	99.73 270	99.53 53	99.02 237	99.86 42

MVS_Test		99.10 145	98.97 142	99.48 160	99.49 242	99.14 160	99.67 76	99.34 315	97.31 305	99.58 163	99.76 189	97.65 120	99.82 228	98.87 159	99.07 232	99.46 253

AstraMVS		99.09 146	99.03 116	99.25 214	99.66 149	98.13 287	99.57 143	98.24 460	98.82 89	99.91 30	99.88 56	95.81 217	99.90 148	99.72 32	99.67 158	99.74 118

CDS-MVSNet		99.09 146	99.03 116	99.25 214	99.42 262	98.73 238	99.45 246	99.46 239	98.11 193	99.46 188	99.77 185	98.01 111	99.37 350	98.70 189	98.92 244	99.66 169
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmacassd2359aftdt		99.08 148	98.94 152	99.50 149	99.66 149	98.96 187	99.51 192	99.54 108	98.27 152	99.42 200	99.89 45	95.88 214	99.80 240	99.20 107	99.11 218	99.76 107

mamba_0408		99.08 148	98.96 146	99.44 174	99.62 177	98.88 214	99.25 341	99.47 226	98.05 209	99.37 216	99.81 134	96.85 154	99.85 188	98.98 139	99.25 197	99.60 195

GDP-MVS		99.08 148	98.89 164	99.64 101	99.53 219	99.34 127	99.64 96	99.48 204	98.32 147	99.77 84	99.66 246	95.14 248	99.93 109	98.97 144	99.50 176	99.64 182

PVSNet_Blended		99.08 148	98.97 142	99.42 179	99.76 82	98.79 233	98.78 437	99.91 3	96.74 353	99.67 124	99.49 312	97.53 121	99.88 168	98.98 139	99.85 93	99.60 195

OMC-MVS		99.08 148	99.04 113	99.20 221	99.67 137	98.22 282	99.28 325	99.52 133	98.07 202	99.66 129	99.81 134	97.79 116	99.78 252	97.79 294	99.81 120	99.60 195

viewdifsd2359ckpt13		99.06 153	98.93 154	99.45 169	99.63 168	98.96 187	99.50 203	99.51 155	97.83 241	99.28 240	99.80 152	96.68 168	99.71 280	99.05 131	99.12 216	99.68 160

SSM_04072		99.06 153	98.96 146	99.35 190	99.62 177	98.88 214	99.25 341	99.47 226	98.05 209	99.37 216	99.81 134	96.85 154	99.58 318	98.98 139	99.25 197	99.60 195

mvsmamba		99.06 153	98.96 146	99.36 188	99.47 250	98.64 247	99.70 59	99.05 391	97.61 270	99.65 139	99.83 106	96.54 176	99.92 123	99.19 108	99.62 165	99.51 234

WTY-MVS		99.06 153	98.88 167	99.61 109	99.62 177	99.16 155	99.37 289	99.56 89	98.04 216	99.53 176	99.62 265	96.84 158	99.94 92	98.85 166	98.49 277	99.72 137

IS-MVSNet		99.05 157	98.87 168	99.57 120	99.73 107	99.32 131	99.75 43	99.20 370	98.02 221	99.56 167	99.86 78	96.54 176	99.67 295	98.09 264	99.13 211	99.73 127

PAPM_NR		99.04 158	98.84 176	99.66 91	99.74 100	99.44 116	99.39 282	99.38 293	97.70 260	99.28 240	99.28 375	98.34 96	99.85 188	96.96 370	99.45 179	99.69 154

API-MVS		99.04 158	99.03 116	99.06 235	99.40 272	99.31 135	99.55 166	99.56 89	98.54 120	99.33 230	99.39 344	98.76 57	99.78 252	96.98 368	99.78 134	98.07 448

mvs_anonymous		99.03 160	98.99 137	99.16 225	99.38 278	98.52 262	99.51 192	99.38 293	97.79 247	99.38 214	99.81 134	97.30 130	99.45 332	99.35 76	98.99 239	99.51 234

sasdasda		99.02 161	98.86 171	99.51 144	99.42 262	99.32 131	99.80 25	99.48 204	98.63 110	99.31 232	98.81 427	97.09 142	99.75 261	99.27 99	97.90 311	99.47 248

train_agg		99.02 161	98.77 183	99.77 74	99.67 137	99.65 75	99.05 390	99.41 275	96.28 388	98.95 313	99.49 312	98.76 57	99.91 135	97.63 311	99.72 148	99.75 113

canonicalmvs		99.02 161	98.86 171	99.51 144	99.42 262	99.32 131	99.80 25	99.48 204	98.63 110	99.31 232	98.81 427	97.09 142	99.75 261	99.27 99	97.90 311	99.47 248

balanced_ft_v1		99.02 161	98.98 140	99.15 229	99.39 275	98.12 289	99.79 31	99.51 155	98.20 170	99.66 129	99.87 69	94.84 262	99.93 109	99.69 34	99.84 101	99.41 263

PLC	97.94 4	99.02 161	98.85 174	99.53 133	99.66 149	99.01 177	99.24 346	99.52 133	96.85 346	99.27 246	99.48 318	98.25 100	99.91 135	97.76 299	99.62 165	99.65 175
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
viewdifsd2359ckpt09		99.01 166	98.87 168	99.40 181	99.62 177	98.79 233	99.44 253	99.51 155	97.76 251	99.35 225	99.69 227	96.42 184	99.75 261	98.97 144	99.11 218	99.66 169

viewmambaseed2359dif		99.01 166	98.90 160	99.32 197	99.58 198	98.51 264	99.33 305	99.54 108	97.85 237	99.44 194	99.85 85	96.01 204	99.79 246	99.41 70	99.13 211	99.67 164

MGCFI-Net		99.01 166	98.85 174	99.50 149	99.42 262	99.26 144	99.82 16	99.48 204	98.60 115	99.28 240	98.81 427	97.04 146	99.76 258	99.29 95	97.87 314	99.47 248

AdaColmap		99.01 166	98.80 179	99.66 91	99.56 207	99.54 98	99.18 362	99.70 18	98.18 174	99.35 225	99.63 260	96.32 187	99.90 148	97.48 329	99.77 137	99.55 217

1112_ss		98.98 170	98.77 183	99.59 113	99.68 134	99.02 175	99.25 341	99.48 204	97.23 313	99.13 276	99.58 278	96.93 152	99.90 148	98.87 159	98.78 259	99.84 53

MSDG		98.98 170	98.80 179	99.53 133	99.76 82	99.19 150	98.75 440	99.55 99	97.25 310	99.47 186	99.77 185	97.82 115	99.87 175	96.93 373	99.90 56	99.54 219

CANet_DTU		98.97 172	98.87 168	99.25 214	99.33 291	98.42 275	99.08 383	99.30 342	99.16 37	99.43 197	99.75 194	95.27 240	99.97 29	98.56 216	99.95 22	99.36 272

DPM-MVS		98.95 173	98.71 191	99.66 91	99.63 168	99.55 96	98.64 451	99.10 382	97.93 227	99.42 200	99.55 289	98.67 72	99.80 240	95.80 407	99.68 156	99.61 192

114514_t		98.93 174	98.67 195	99.72 86	99.85 31	99.53 101	99.62 107	99.59 72	92.65 456	99.71 111	99.78 176	98.06 109	99.90 148	98.84 169	99.91 45	99.74 118

PS-MVSNAJss		98.92 175	98.92 155	98.90 262	98.78 407	98.53 258	99.78 33	99.54 108	98.07 202	99.00 304	99.76 189	99.01 20	99.37 350	99.13 119	97.23 354	98.81 325

RRT-MVS		98.91 176	98.75 185	99.39 186	99.46 252	98.61 252	99.76 38	99.50 179	98.06 206	99.81 68	99.88 56	93.91 319	99.94 92	99.11 122	99.27 194	99.61 192

Test_1112_low_res		98.89 177	98.66 198	99.57 120	99.69 127	98.95 193	99.03 395	99.47 226	96.98 336	99.15 274	99.23 383	96.77 163	99.89 163	98.83 172	98.78 259	99.86 42

Elysia		98.88 178	98.65 200	99.58 116	99.58 198	99.34 127	99.65 89	99.52 133	98.26 155	99.83 63	99.87 69	93.37 330	99.90 148	97.81 292	99.91 45	99.49 239

StellarMVS		98.88 178	98.65 200	99.58 116	99.58 198	99.34 127	99.65 89	99.52 133	98.26 155	99.83 63	99.87 69	93.37 330	99.90 148	97.81 292	99.91 45	99.49 239

test_fmvs1		98.88 178	98.79 182	99.16 225	99.69 127	97.61 320	99.55 166	99.49 192	99.32 29	99.98 13	99.91 26	91.41 386	99.96 41	99.82 29	99.92 38	99.90 25

AllTest		98.87 181	98.72 189	99.31 199	99.86 25	98.48 269	99.56 151	99.61 60	97.85 237	99.36 222	99.85 85	95.95 207	99.85 188	96.66 386	99.83 113	99.59 206

UGNet		98.87 181	98.69 193	99.40 181	99.22 324	98.72 240	99.44 253	99.68 24	99.24 32	99.18 271	99.42 332	92.74 346	99.96 41	99.34 81	99.94 30	99.53 224
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)		98.87 181	98.72 189	99.31 199	99.71 117	98.88 214	99.80 25	99.44 259	97.91 229	99.36 222	99.78 176	95.49 231	99.43 341	97.91 280	99.11 218	99.62 190

IMVS_0407		98.86 184	98.91 158	98.72 297	99.55 211	96.93 360	99.50 203	99.44 259	98.05 209	99.66 129	99.80 152	97.13 138	99.65 303	98.15 259	98.92 244	99.60 195

IMVS_0403		98.86 184	98.89 164	98.78 292	99.55 211	96.93 360	99.58 135	99.44 259	98.05 209	99.68 118	99.80 152	96.81 160	99.80 240	98.15 259	98.92 244	99.60 195

test_yl		98.86 184	98.63 203	99.54 125	99.49 242	99.18 152	99.50 203	99.07 388	98.22 166	99.61 156	99.51 306	95.37 235	99.84 197	98.60 207	98.33 284	99.59 206

DCV-MVSNet		98.86 184	98.63 203	99.54 125	99.49 242	99.18 152	99.50 203	99.07 388	98.22 166	99.61 156	99.51 306	95.37 235	99.84 197	98.60 207	98.33 284	99.59 206

EPNet		98.86 184	98.71 191	99.30 204	97.20 462	98.18 283	99.62 107	98.91 412	99.28 31	98.63 366	99.81 134	95.96 206	99.99 4	99.24 103	99.72 148	99.73 127
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 184	98.80 179	99.03 239	99.76 82	98.79 233	99.28 325	99.91 3	97.42 296	99.67 124	99.37 350	97.53 121	99.88 168	98.98 139	97.29 352	98.42 426

ab-mvs		98.86 184	98.63 203	99.54 125	99.64 164	99.19 150	99.44 253	99.54 108	97.77 250	99.30 236	99.81 134	94.20 304	99.93 109	99.17 114	98.82 256	99.49 239

MAR-MVS		98.86 184	98.63 203	99.54 125	99.37 281	99.66 71	99.45 246	99.54 108	96.61 365	99.01 300	99.40 340	97.09 142	99.86 181	97.68 310	99.53 173	99.10 295
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	98.86 184	98.75 185	99.17 224	99.88 13	98.53 258	99.34 303	99.59 72	97.55 277	98.70 354	99.89 45	95.83 215	99.90 148	98.10 263	99.90 56	99.08 300
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 193	98.62 208	99.53 133	99.61 188	99.08 168	99.80 25	99.51 155	97.10 326	99.31 232	99.78 176	95.23 245	99.77 254	98.21 251	99.03 235	99.75 113

HY-MVS	97.30 7	98.85 193	98.64 202	99.47 166	99.42 262	99.08 168	99.62 107	99.36 303	97.39 299	99.28 240	99.68 235	96.44 182	99.92 123	98.37 237	98.22 295	99.40 266

PVSNet	96.02 17	98.85 193	98.84 176	98.89 266	99.73 107	97.28 330	98.32 472	99.60 67	97.86 234	99.50 181	99.57 283	96.75 164	99.86 181	98.56 216	99.70 152	99.54 219

PatchMatch-RL		98.84 196	98.62 208	99.52 139	99.71 117	99.28 141	99.06 388	99.77 12	97.74 255	99.50 181	99.53 298	95.41 233	99.84 197	97.17 359	99.64 162	99.44 258

Effi-MVS+		98.81 197	98.59 214	99.48 160	99.46 252	99.12 163	98.08 479	99.50 179	97.50 285	99.38 214	99.41 336	96.37 186	99.81 233	99.11 122	98.54 274	99.51 234

alignmvs		98.81 197	98.56 217	99.58 116	99.43 260	99.42 118	99.51 192	98.96 402	98.61 113	99.35 225	98.92 422	94.78 267	99.77 254	99.35 76	98.11 305	99.54 219

DeepPCF-MVS	98.18 3	98.81 197	99.37 43	97.12 428	99.60 194	91.75 470	98.61 452	99.44 259	99.35 25	99.83 63	99.85 85	98.70 69	99.81 233	99.02 136	99.91 45	99.81 79

PMMVS		98.80 200	98.62 208	99.34 191	99.27 309	98.70 241	98.76 439	99.31 337	97.34 302	99.21 261	99.07 399	97.20 136	99.82 228	98.56 216	98.87 251	99.52 225

icg_test_0407_2		98.79 201	98.86 171	98.57 313	99.55 211	96.93 360	99.07 384	99.44 259	98.05 209	99.66 129	99.80 152	97.13 138	99.18 391	98.15 259	98.92 244	99.60 195

viewdifsd2359ckpt11		98.78 202	98.74 187	98.89 266	99.67 137	97.04 349	99.50 203	99.58 77	98.26 155	99.56 167	99.90 36	94.36 297	99.87 175	99.49 61	98.32 288	99.77 100

viewmsd2359difaftdt		98.78 202	98.74 187	98.90 262	99.67 137	97.04 349	99.50 203	99.58 77	98.26 155	99.56 167	99.90 36	94.36 297	99.87 175	99.49 61	98.32 288	99.77 100

Effi-MVS+-dtu		98.78 202	98.89 164	98.47 331	99.33 291	96.91 365	99.57 143	99.30 342	98.47 127	99.41 205	98.99 412	96.78 162	99.74 264	98.73 186	99.38 183	98.74 340

FIs		98.78 202	98.63 203	99.23 219	99.18 333	99.54 98	99.83 15	99.59 72	98.28 150	98.79 341	99.81 134	96.75 164	99.37 350	99.08 128	96.38 372	98.78 328

Fast-Effi-MVS+-dtu		98.77 206	98.83 178	98.60 308	99.41 267	96.99 355	99.52 182	99.49 192	98.11 193	99.24 253	99.34 360	96.96 151	99.79 246	97.95 278	99.45 179	99.02 310

sd_testset		98.75 207	98.57 215	99.29 207	99.81 57	98.26 280	99.56 151	99.62 51	98.78 98	99.64 144	99.88 56	92.02 368	99.88 168	99.54 51	98.26 292	99.72 137

FA-MVS(test-final)		98.75 207	98.53 219	99.41 180	99.55 211	99.05 173	99.80 25	99.01 396	96.59 370	99.58 163	99.59 274	95.39 234	99.90 148	97.78 295	99.49 177	99.28 281

FC-MVSNet-test		98.75 207	98.62 208	99.15 229	99.08 360	99.45 115	99.86 11	99.60 67	98.23 165	98.70 354	99.82 119	96.80 161	99.22 383	99.07 129	96.38 372	98.79 326

XVG-OURS		98.73 210	98.68 194	98.88 271	99.70 122	97.73 312	98.92 420	99.55 99	98.52 122	99.45 189	99.84 100	95.27 240	99.91 135	98.08 268	98.84 254	99.00 311

Fast-Effi-MVS+		98.70 211	98.43 224	99.51 144	99.51 228	99.28 141	99.52 182	99.47 226	96.11 404	99.01 300	99.34 360	96.20 196	99.84 197	97.88 282	98.82 256	99.39 267

XVG-OURS-SEG-HR		98.69 212	98.62 208	98.89 266	99.71 117	97.74 311	99.12 374	99.54 108	98.44 133	99.42 200	99.71 212	94.20 304	99.92 123	98.54 220	98.90 250	99.00 311

1314		98.68 213	98.54 218	99.11 232	98.89 390	98.65 245	99.27 330	99.49 192	96.89 344	97.99 412	99.56 286	97.72 119	99.83 219	97.74 302	99.27 194	98.84 324

VortexMVS		98.67 214	98.66 198	98.68 303	99.62 177	97.96 299	99.59 125	99.41 275	98.13 183	99.31 232	99.70 216	95.48 232	99.27 370	99.40 71	97.32 351	98.79 326

EI-MVSNet		98.67 214	98.67 195	98.68 303	99.35 285	97.97 297	99.50 203	99.38 293	96.93 343	99.20 264	99.83 106	97.87 113	99.36 354	98.38 235	97.56 330	98.71 344

test_djsdf		98.67 214	98.57 215	98.98 245	98.70 421	98.91 204	99.88 4	99.46 239	97.55 277	99.22 258	99.88 56	95.73 222	99.28 367	99.03 134	97.62 325	98.75 336

QAPM		98.67 214	98.30 234	99.80 64	99.20 327	99.67 68	99.77 35	99.72 14	94.74 432	98.73 346	99.90 36	95.78 220	99.98 20	96.96 370	99.88 75	99.76 107

nrg030		98.64 218	98.42 225	99.28 211	99.05 366	99.69 63	99.81 20	99.46 239	98.04 216	99.01 300	99.82 119	96.69 166	99.38 347	99.34 81	94.59 417	98.78 328

test_vis1_n_1920		98.63 219	98.40 227	99.31 199	99.86 25	97.94 304	99.67 76	99.62 51	99.43 17	99.99 2	99.91 26	87.29 440	100.00 1	99.92 24	99.92 38	99.98 2

PAPR		98.63 219	98.34 230	99.51 144	99.40 272	99.03 174	98.80 435	99.36 303	96.33 385	99.00 304	99.12 397	98.46 87	99.84 197	95.23 422	99.37 190	99.66 169

CVMVSNet		98.57 221	98.67 195	98.30 351	99.35 285	95.59 414	99.50 203	99.55 99	98.60 115	99.39 212	99.83 106	94.48 293	99.45 332	98.75 183	98.56 272	99.85 46

IMVS_0404		98.53 222	98.52 220	98.55 319	99.55 211	96.93 360	99.20 358	99.44 259	98.05 209	98.96 311	99.80 152	94.66 282	99.13 399	98.15 259	98.92 244	99.60 195

MVSTER		98.49 223	98.32 232	99.00 243	99.35 285	99.02 175	99.54 171	99.38 293	97.41 297	99.20 264	99.73 205	93.86 321	99.36 354	98.87 159	97.56 330	98.62 388

FE-MVS		98.48 224	98.17 239	99.40 181	99.54 218	98.96 187	99.68 73	98.81 426	95.54 415	99.62 151	99.70 216	93.82 322	99.93 109	97.35 342	99.46 178	99.32 278

OpenMVS	96.50 16	98.47 225	98.12 246	99.52 139	99.04 368	99.53 101	99.82 16	99.72 14	94.56 435	98.08 407	99.88 56	94.73 275	99.98 20	97.47 331	99.76 140	99.06 306

IterMVS-LS		98.46 226	98.42 225	98.58 312	99.59 196	98.00 295	99.37 289	99.43 270	96.94 342	99.07 289	99.59 274	97.87 113	99.03 417	98.32 244	95.62 395	98.71 344
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 227	98.28 235	98.94 252	98.50 439	98.96 187	99.77 35	99.50 179	97.07 328	98.87 326	99.77 185	94.76 271	99.28 367	98.66 196	97.60 326	98.57 408

jajsoiax		98.43 228	98.28 235	98.88 271	98.60 433	98.43 273	99.82 16	99.53 124	98.19 171	98.63 366	99.80 152	93.22 335	99.44 337	99.22 104	97.50 337	98.77 332

tttt0517		98.42 229	98.14 243	99.28 211	99.66 149	98.38 276	99.74 48	96.85 479	97.68 262	99.79 75	99.74 199	91.39 387	99.89 163	98.83 172	99.56 170	99.57 213

BH-untuned		98.42 229	98.36 228	98.59 309	99.49 242	96.70 373	99.27 330	99.13 379	97.24 312	98.80 339	99.38 347	95.75 221	99.74 264	97.07 364	99.16 204	99.33 277

test_fmvs1_n		98.41 231	98.14 243	99.21 220	99.82 53	97.71 316	99.74 48	99.49 192	99.32 29	99.99 2	99.95 3	85.32 457	99.97 29	99.82 29	99.84 101	99.96 7

D2MVS		98.41 231	98.50 221	98.15 366	99.26 312	96.62 379	99.40 278	99.61 60	97.71 257	98.98 307	99.36 353	96.04 202	99.67 295	98.70 189	97.41 347	98.15 444

BH-RMVSNet		98.41 231	98.08 252	99.40 181	99.41 267	98.83 227	99.30 314	98.77 432	97.70 260	98.94 315	99.65 248	92.91 342	99.74 264	96.52 390	99.55 172	99.64 182

mvs_tets		98.40 234	98.23 237	98.91 260	98.67 426	98.51 264	99.66 83	99.53 124	98.19 171	98.65 363	99.81 134	92.75 344	99.44 337	99.31 86	97.48 341	98.77 332

MonoMVSNet		98.38 235	98.47 223	98.12 368	98.59 435	96.19 396	99.72 54	98.79 430	97.89 231	99.44 194	99.52 302	96.13 198	98.90 442	98.64 198	97.54 332	99.28 281

XXY-MVS		98.38 235	98.09 251	99.24 217	99.26 312	99.32 131	99.56 151	99.55 99	97.45 290	98.71 348	99.83 106	93.23 333	99.63 313	98.88 156	96.32 374	98.76 334

ACMM	97.58 5	98.37 237	98.34 230	98.48 326	99.41 267	97.10 340	99.56 151	99.45 250	98.53 121	99.04 297	99.85 85	93.00 338	99.71 280	98.74 184	97.45 342	98.64 379
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 238	98.03 258	99.31 199	99.63 168	98.56 255	99.54 171	96.75 481	97.53 281	99.73 96	99.65 248	91.25 391	99.89 163	98.62 201	99.56 170	99.48 242

tpmrst		98.33 239	98.48 222	97.90 386	99.16 343	94.78 437	99.31 312	99.11 381	97.27 308	99.45 189	99.59 274	95.33 238	99.84 197	98.48 223	98.61 266	99.09 299

baseline1		98.31 240	97.95 267	99.38 187	99.50 240	98.74 237	99.59 125	98.93 404	98.41 135	99.14 275	99.60 272	94.59 285	99.79 246	98.48 223	93.29 437	99.61 192

PatchmatchNet		98.31 240	98.36 228	98.19 361	99.16 343	95.32 425	99.27 330	98.92 407	97.37 300	99.37 216	99.58 278	94.90 259	99.70 287	97.43 337	99.21 201	99.54 219
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 242	97.98 263	99.26 213	99.57 203	98.16 284	99.41 270	98.55 452	96.03 409	99.19 267	99.74 199	91.87 371	99.92 123	99.16 117	98.29 291	99.70 151

VPA-MVSNet		98.29 243	97.95 267	99.30 204	99.16 343	99.54 98	99.50 203	99.58 77	98.27 152	99.35 225	99.37 350	92.53 356	99.65 303	99.35 76	94.46 418	98.72 342

UniMVSNet (Re)		98.29 243	98.00 261	99.13 231	99.00 373	99.36 126	99.49 220	99.51 155	97.95 225	98.97 309	99.13 394	96.30 191	99.38 347	98.36 239	93.34 436	98.66 375

HQP_MVS		98.27 245	98.22 238	98.44 337	99.29 304	96.97 357	99.39 282	99.47 226	98.97 75	99.11 280	99.61 269	92.71 349	99.69 292	97.78 295	97.63 323	98.67 366

UniMVSNet_NR-MVSNet		98.22 246	97.97 264	98.96 248	98.92 386	98.98 180	99.48 228	99.53 124	97.76 251	98.71 348	99.46 325	96.43 183	99.22 383	98.57 213	92.87 444	98.69 353

LPG-MVS_test		98.22 246	98.13 245	98.49 324	99.33 291	97.05 346	99.58 135	99.55 99	97.46 287	99.24 253	99.83 106	92.58 354	99.72 274	98.09 264	97.51 335	98.68 358

RPSCF		98.22 246	98.62 208	96.99 431	99.82 53	91.58 471	99.72 54	99.44 259	96.61 365	99.66 129	99.89 45	95.92 210	99.82 228	97.46 332	99.10 225	99.57 213

ADS-MVSNet		98.20 249	98.08 252	98.56 317	99.33 291	96.48 384	99.23 349	99.15 376	96.24 392	99.10 283	99.67 241	94.11 309	99.71 280	96.81 378	99.05 233	99.48 242

OPM-MVS		98.19 250	98.10 248	98.45 334	98.88 391	97.07 344	99.28 325	99.38 293	98.57 117	99.22 258	99.81 134	92.12 366	99.66 298	98.08 268	97.54 332	98.61 397
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 250	98.16 240	98.27 357	99.30 300	95.55 415	99.07 384	98.97 400	97.57 274	99.43 197	99.57 283	92.72 347	99.74 264	97.58 315	99.20 202	99.52 225

miper_ehance_all_eth		98.18 252	98.10 248	98.41 340	99.23 320	97.72 313	98.72 443	99.31 337	96.60 368	98.88 323	99.29 373	97.29 131	99.13 399	97.60 313	95.99 383	98.38 431

CR-MVSNet		98.17 253	97.93 270	98.87 275	99.18 333	98.49 267	99.22 353	99.33 323	96.96 338	99.56 167	99.38 347	94.33 300	99.00 425	94.83 429	98.58 269	99.14 292

miper_enhance_ethall		98.16 254	98.08 252	98.41 340	98.96 382	97.72 313	98.45 465	99.32 333	96.95 340	98.97 309	99.17 389	97.06 145	99.22 383	97.86 285	95.99 383	98.29 435

CLD-MVS		98.16 254	98.10 248	98.33 347	99.29 304	96.82 370	98.75 440	99.44 259	97.83 241	99.13 276	99.55 289	92.92 340	99.67 295	98.32 244	97.69 321	98.48 418
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 256	97.79 284	99.19 222	99.50 240	98.50 266	98.61 452	96.82 480	96.95 340	99.54 174	99.43 330	91.66 380	99.86 181	98.08 268	99.51 174	99.22 289

pmmvs4		98.13 257	97.90 272	98.81 287	98.61 432	98.87 218	98.99 406	99.21 369	96.44 380	99.06 294	99.58 278	95.90 212	99.11 405	97.18 358	96.11 379	98.46 423

WR-MVS_H		98.13 257	97.87 277	98.90 262	99.02 370	98.84 224	99.70 59	99.59 72	97.27 308	98.40 385	99.19 388	95.53 229	99.23 377	98.34 241	93.78 432	98.61 397

c3_l		98.12 259	98.04 257	98.38 344	99.30 300	97.69 317	98.81 434	99.33 323	96.67 358	98.83 334	99.34 360	97.11 141	98.99 426	97.58 315	95.34 402	98.48 418

ACMH	97.28 8	98.10 260	97.99 262	98.44 337	99.41 267	96.96 359	99.60 114	99.56 89	98.09 197	98.15 405	99.91 26	90.87 398	99.70 287	98.88 156	97.45 342	98.67 366
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
usedtu_dtu_shiyan1		98.09 261	97.82 281	98.89 266	98.70 421	98.90 209	98.57 455	99.47 226	96.78 350	98.87 326	99.05 402	94.75 272	99.23 377	97.45 334	96.74 362	98.53 412

FE-MVSNET3		98.09 261	97.82 281	98.89 266	98.70 421	98.90 209	98.57 455	99.47 226	96.78 350	98.87 326	99.05 402	94.75 272	99.23 377	97.45 334	96.74 362	98.53 412

Anonymous20240529		98.09 261	97.68 301	99.34 191	99.66 149	98.44 272	99.40 278	99.43 270	93.67 442	99.22 258	99.89 45	90.23 406	99.93 109	99.26 102	98.33 284	99.66 169

CP-MVSNet		98.09 261	97.78 287	99.01 241	98.97 381	99.24 147	99.67 76	99.46 239	97.25 310	98.48 380	99.64 254	93.79 323	99.06 413	98.63 200	94.10 426	98.74 340

dmvs_re		98.08 265	98.16 240	97.85 392	99.55 211	94.67 442	99.70 59	98.92 407	98.15 176	99.06 294	99.35 356	93.67 327	99.25 374	97.77 298	97.25 353	99.64 182

DU-MVS		98.08 265	97.79 284	98.96 248	98.87 394	98.98 180	99.41 270	99.45 250	97.87 233	98.71 348	99.50 309	94.82 263	99.22 383	98.57 213	92.87 444	98.68 358

v2v482		98.06 267	97.77 289	98.92 256	98.90 389	98.82 230	99.57 143	99.36 303	96.65 360	99.19 267	99.35 356	94.20 304	99.25 374	97.72 305	94.97 410	98.69 353

V42		98.06 267	97.79 284	98.86 278	98.98 379	98.84 224	99.69 63	99.34 315	96.53 372	99.30 236	99.37 350	94.67 280	99.32 362	97.57 319	94.66 415	98.42 426

test-LLR		98.06 267	97.90 272	98.55 319	98.79 404	97.10 340	98.67 446	97.75 469	97.34 302	98.61 370	98.85 424	94.45 295	99.45 332	97.25 350	99.38 183	99.10 295

WR-MVS		98.06 267	97.73 296	99.06 235	98.86 397	99.25 146	99.19 360	99.35 310	97.30 306	98.66 357	99.43 330	93.94 316	99.21 388	98.58 210	94.28 422	98.71 344

ACMP	97.20 11	98.06 267	97.94 269	98.45 334	99.37 281	97.01 353	99.44 253	99.49 192	97.54 280	98.45 382	99.79 169	91.95 370	99.72 274	97.91 280	97.49 340	98.62 388
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 272	97.96 265	98.33 347	99.26 312	97.38 327	98.56 459	99.31 337	96.65 360	98.88 323	99.52 302	96.58 173	99.12 404	97.39 339	95.53 399	98.47 420

test1111		98.04 273	98.11 247	97.83 397	99.74 100	93.82 453	99.58 135	95.40 488	99.12 46	99.65 139	99.93 10	90.73 399	99.84 197	99.43 69	99.38 183	99.82 72

ECVR-MVS		98.04 273	98.05 256	98.00 376	99.74 100	94.37 448	99.59 125	94.98 489	99.13 41	99.66 129	99.93 10	90.67 400	99.84 197	99.40 71	99.38 183	99.80 88

EPNet_dtu		98.03 275	97.96 265	98.23 359	98.27 444	95.54 417	99.23 349	98.75 433	99.02 62	97.82 421	99.71 212	96.11 199	99.48 327	93.04 451	99.65 161	99.69 154
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 275	97.76 293	98.84 282	99.39 275	98.98 180	99.40 278	99.38 293	96.67 358	99.07 289	99.28 375	92.93 339	98.98 427	97.10 360	96.65 365	98.56 409

ADS-MVSNet2		98.02 277	98.07 255	97.87 388	99.33 291	95.19 428	99.23 349	99.08 385	96.24 392	99.10 283	99.67 241	94.11 309	98.93 439	96.81 378	99.05 233	99.48 242

HQP-MVS		98.02 277	97.90 272	98.37 345	99.19 330	96.83 368	98.98 409	99.39 285	98.24 162	98.66 357	99.40 340	92.47 358	99.64 307	97.19 356	97.58 328	98.64 379

LTVRE_ROB	97.16 12	98.02 277	97.90 272	98.40 342	99.23 320	96.80 371	99.70 59	99.60 67	97.12 322	98.18 403	99.70 216	91.73 376	99.72 274	98.39 234	97.45 342	98.68 358
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____		98.01 280	97.84 280	98.55 319	99.25 316	97.97 297	98.71 444	99.34 315	96.47 379	98.59 373	99.54 294	95.65 225	99.21 388	97.21 352	95.77 389	98.46 423

DIV-MVS_self_test		98.01 280	97.85 279	98.48 326	99.24 318	97.95 302	98.71 444	99.35 310	96.50 373	98.60 372	99.54 294	95.72 223	99.03 417	97.21 352	95.77 389	98.46 423

miper_lstm_enhance		98.00 282	97.91 271	98.28 356	99.34 290	97.43 325	98.88 424	99.36 303	96.48 377	98.80 339	99.55 289	95.98 205	98.91 440	97.27 348	95.50 400	98.51 416

BH-w/o		98.00 282	97.89 276	98.32 349	99.35 285	96.20 395	99.01 403	98.90 414	96.42 382	98.38 386	99.00 410	95.26 242	99.72 274	96.06 400	98.61 266	99.03 308

v1144		97.98 284	97.69 300	98.85 281	98.87 394	98.66 244	99.54 171	99.35 310	96.27 390	99.23 257	99.35 356	94.67 280	99.23 377	96.73 381	95.16 406	98.68 358

EU-MVSNet		97.98 284	98.03 258	97.81 400	98.72 418	96.65 378	99.66 83	99.66 32	98.09 197	98.35 391	99.82 119	95.25 243	98.01 463	97.41 338	95.30 403	98.78 328

tpmvs		97.98 284	98.02 260	97.84 394	99.04 368	94.73 438	99.31 312	99.20 370	96.10 408	98.76 344	99.42 332	94.94 254	99.81 233	96.97 369	98.45 278	98.97 316

tt0805		97.97 287	97.77 289	98.57 313	99.59 196	96.61 380	99.45 246	99.08 385	98.21 168	98.88 323	99.80 152	88.66 424	99.70 287	98.58 210	97.72 320	99.39 267

NR-MVSNet		97.97 287	97.61 310	99.02 240	98.87 394	99.26 144	99.47 238	99.42 272	97.63 267	97.08 440	99.50 309	95.07 250	99.13 399	97.86 285	93.59 433	98.68 358

v8		97.95 289	97.63 308	98.93 254	98.95 383	98.81 232	99.80 25	99.41 275	96.03 409	99.10 283	99.42 332	94.92 257	99.30 365	96.94 372	94.08 427	98.66 375

Patchmatch-test		97.93 290	97.65 304	98.77 293	99.18 333	97.07 344	99.03 395	99.14 378	96.16 399	98.74 345	99.57 283	94.56 287	99.72 274	93.36 446	99.11 218	99.52 225

PS-CasMVS		97.93 290	97.59 312	98.95 250	98.99 376	99.06 171	99.68 73	99.52 133	97.13 320	98.31 393	99.68 235	92.44 362	99.05 414	98.51 221	94.08 427	98.75 336

TranMVSNet+NR-MVSNet		97.93 290	97.66 303	98.76 294	98.78 407	98.62 250	99.65 89	99.49 192	97.76 251	98.49 379	99.60 272	94.23 303	98.97 434	98.00 275	92.90 442	98.70 349

test_vis1_n		97.92 293	97.44 334	99.34 191	99.53 219	98.08 291	99.74 48	99.49 192	99.15 38	100.00 1	99.94 6	79.51 479	99.98 20	99.88 26	99.76 140	99.97 4

v144192		97.92 293	97.60 311	98.87 275	98.83 401	98.65 245	99.55 166	99.34 315	96.20 395	99.32 231	99.40 340	94.36 297	99.26 373	96.37 397	95.03 409	98.70 349

ACMH+	97.24 10	97.92 293	97.78 287	98.32 349	99.46 252	96.68 377	99.56 151	99.54 108	98.41 135	97.79 423	99.87 69	90.18 407	99.66 298	98.05 272	97.18 357	98.62 388

LFMVS		97.90 296	97.35 346	99.54 125	99.52 225	99.01 177	99.39 282	98.24 460	97.10 326	99.65 139	99.79 169	84.79 460	99.91 135	99.28 96	98.38 281	99.69 154

reproduce_monomvs		97.89 297	97.87 277	97.96 381	99.51 228	95.45 420	99.60 114	99.25 359	99.17 36	98.85 333	99.49 312	89.29 416	99.64 307	99.35 76	96.31 375	98.78 328

Anonymous20231211		97.88 298	97.54 316	98.90 262	99.71 117	98.53 258	99.48 228	99.57 84	94.16 438	98.81 337	99.68 235	93.23 333	99.42 343	98.84 169	94.42 420	98.76 334

OurMVSNet-221017-0		97.88 298	97.77 289	98.19 361	98.71 420	96.53 382	99.88 4	99.00 397	97.79 247	98.78 342	99.94 6	91.68 377	99.35 357	97.21 352	96.99 361	98.69 353

v7n		97.87 300	97.52 318	98.92 256	98.76 414	98.58 254	99.84 12	99.46 239	96.20 395	98.91 318	99.70 216	94.89 260	99.44 337	96.03 401	93.89 430	98.75 336

baseline2		97.87 300	97.55 313	98.82 284	99.18 333	98.02 294	99.41 270	96.58 485	96.97 337	96.51 447	99.17 389	93.43 328	99.57 319	97.71 306	99.03 235	98.86 322

thres600view7		97.86 302	97.51 320	98.92 256	99.72 111	97.95 302	99.59 125	98.74 436	97.94 226	99.27 246	98.62 435	91.75 374	99.86 181	93.73 442	98.19 299	98.96 318

UBG		97.85 303	97.48 323	98.95 250	99.25 316	97.64 318	99.24 346	98.74 436	97.90 230	98.64 364	98.20 453	88.65 425	99.81 233	98.27 247	98.40 279	99.42 260

cl22		97.85 303	97.64 307	98.48 326	99.09 357	97.87 306	98.60 454	99.33 323	97.11 325	98.87 326	99.22 384	92.38 363	99.17 393	98.21 251	95.99 383	98.42 426

v10		97.85 303	97.52 318	98.86 278	98.99 376	98.67 243	99.75 43	99.41 275	95.70 413	98.98 307	99.41 336	94.75 272	99.23 377	96.01 403	94.63 416	98.67 366

GA-MVS		97.85 303	97.47 326	99.00 243	99.38 278	97.99 296	98.57 455	99.15 376	97.04 333	98.90 320	99.30 371	89.83 410	99.38 347	96.70 383	98.33 284	99.62 190

testing3-2		97.84 307	97.70 299	98.24 358	99.53 219	95.37 424	99.55 166	98.67 447	98.46 128	99.27 246	99.34 360	86.58 446	99.83 219	99.32 84	98.63 265	99.52 225

tfpnnormal		97.84 307	97.47 326	98.98 245	99.20 327	99.22 149	99.64 96	99.61 60	96.32 386	98.27 397	99.70 216	93.35 332	99.44 337	95.69 410	95.40 401	98.27 436

VPNet		97.84 307	97.44 334	99.01 241	99.21 325	98.94 197	99.48 228	99.57 84	98.38 137	99.28 240	99.73 205	88.89 419	99.39 345	99.19 108	93.27 438	98.71 344

LCM-MVSNet-Re		97.83 310	98.15 242	96.87 437	99.30 300	92.25 468	99.59 125	98.26 458	97.43 294	96.20 451	99.13 394	96.27 192	98.73 449	98.17 256	98.99 239	99.64 182

XVG-ACMP-BASELINE		97.83 310	97.71 298	98.20 360	99.11 351	96.33 389	99.41 270	99.52 133	98.06 206	99.05 296	99.50 309	89.64 413	99.73 270	97.73 303	97.38 349	98.53 412

IterMVS		97.83 310	97.77 289	98.02 373	99.58 198	96.27 392	99.02 398	99.48 204	97.22 314	98.71 348	99.70 216	92.75 344	99.13 399	97.46 332	96.00 382	98.67 366
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 313	97.75 294	98.06 370	99.57 203	96.36 388	99.02 398	99.49 192	97.18 316	98.71 348	99.72 209	92.72 347	99.14 396	97.44 336	95.86 388	98.67 366

EPMVS		97.82 313	97.65 304	98.35 346	98.88 391	95.98 399	99.49 220	94.71 491	97.57 274	99.26 251	99.48 318	92.46 361	99.71 280	97.87 284	99.08 231	99.35 273

MVP-Stereo		97.81 315	97.75 294	97.99 377	97.53 455	96.60 381	98.96 413	98.85 421	97.22 314	97.23 434	99.36 353	95.28 239	99.46 330	95.51 414	99.78 134	97.92 461
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 315	97.44 334	98.91 260	98.88 391	98.68 242	99.51 192	99.34 315	96.18 397	99.20 264	99.34 360	94.03 313	99.36 354	95.32 420	95.18 405	98.69 353

ttmdpeth		97.80 317	97.63 308	98.29 352	98.77 412	97.38 327	99.64 96	99.36 303	98.78 98	96.30 450	99.58 278	92.34 365	99.39 345	98.36 239	95.58 396	98.10 446

v1921920		97.80 317	97.45 329	98.84 282	98.80 403	98.53 258	99.52 182	99.34 315	96.15 401	99.24 253	99.47 321	93.98 315	99.29 366	95.40 418	95.13 407	98.69 353

v148		97.79 319	97.55 313	98.50 323	98.74 415	97.72 313	99.54 171	99.33 323	96.26 391	98.90 320	99.51 306	94.68 279	99.14 396	97.83 289	93.15 441	98.63 386

thres400		97.77 320	97.38 342	98.92 256	99.69 127	97.96 299	99.50 203	98.73 442	97.83 241	99.17 272	98.45 442	91.67 378	99.83 219	93.22 448	98.18 300	98.96 318

thres100view900		97.76 321	97.45 329	98.69 302	99.72 111	97.86 308	99.59 125	98.74 436	97.93 227	99.26 251	98.62 435	91.75 374	99.83 219	93.22 448	98.18 300	98.37 432

PEN-MVS		97.76 321	97.44 334	98.72 297	98.77 412	98.54 257	99.78 33	99.51 155	97.06 330	98.29 396	99.64 254	92.63 353	98.89 443	98.09 264	93.16 440	98.72 342

Baseline_NR-MVSNet		97.76 321	97.45 329	98.68 303	99.09 357	98.29 278	99.41 270	98.85 421	95.65 414	98.63 366	99.67 241	94.82 263	99.10 408	98.07 271	92.89 443	98.64 379

TR-MVS		97.76 321	97.41 340	98.82 284	99.06 363	97.87 306	98.87 426	98.56 451	96.63 364	98.68 356	99.22 384	92.49 357	99.65 303	95.40 418	97.79 318	98.95 320

Patchmtry		97.75 325	97.40 341	98.81 287	99.10 354	98.87 218	99.11 380	99.33 323	94.83 430	98.81 337	99.38 347	94.33 300	99.02 421	96.10 399	95.57 397	98.53 412

dp		97.75 325	97.80 283	97.59 415	99.10 354	93.71 456	99.32 308	98.88 417	96.48 377	99.08 288	99.55 289	92.67 352	99.82 228	96.52 390	98.58 269	99.24 287

WBMVS		97.74 327	97.50 321	98.46 332	99.24 318	97.43 325	99.21 355	99.42 272	97.45 290	98.96 311	99.41 336	88.83 420	99.23 377	98.94 147	96.02 380	98.71 344

TAPA-MVS	97.07 15	97.74 327	97.34 349	98.94 252	99.70 122	97.53 321	99.25 341	99.51 155	91.90 463	99.30 236	99.63 260	98.78 53	99.64 307	88.09 474	99.87 78	99.65 175
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 329	97.35 346	98.88 271	99.47 250	97.12 339	99.34 303	98.85 421	98.19 171	99.67 124	99.85 85	82.98 468	99.92 123	99.49 61	98.32 288	99.60 195

MIMVSNet		97.73 329	97.45 329	98.57 313	99.45 258	97.50 323	99.02 398	98.98 399	96.11 404	99.41 205	99.14 393	90.28 402	98.74 448	95.74 408	98.93 242	99.47 248

tfpn200view9		97.72 331	97.38 342	98.72 297	99.69 127	97.96 299	99.50 203	98.73 442	97.83 241	99.17 272	98.45 442	91.67 378	99.83 219	93.22 448	98.18 300	98.37 432

CostFormer		97.72 331	97.73 296	97.71 407	99.15 347	94.02 452	99.54 171	99.02 395	94.67 433	99.04 297	99.35 356	92.35 364	99.77 254	98.50 222	97.94 310	99.34 276

FMVSNet2		97.72 331	97.36 344	98.80 289	99.51 228	98.84 224	99.45 246	99.42 272	96.49 374	98.86 332	99.29 373	90.26 403	98.98 427	96.44 392	96.56 368	98.58 407

test0.0.03 1		97.71 334	97.42 339	98.56 317	98.41 443	97.82 309	98.78 437	98.63 449	97.34 302	98.05 411	98.98 414	94.45 295	98.98 427	95.04 425	97.15 358	98.89 321

h-mvs33		97.70 335	97.28 358	98.97 247	99.70 122	97.27 331	99.36 295	99.45 250	98.94 78	99.66 129	99.64 254	94.93 255	99.99 4	99.48 64	84.36 472	99.65 175

myMVS_eth3d28		97.69 336	97.34 349	98.73 295	99.27 309	97.52 322	99.33 305	98.78 431	98.03 218	98.82 336	98.49 440	86.64 445	99.46 330	98.44 229	98.24 294	99.23 288

v1240		97.69 336	97.32 353	98.79 290	98.85 398	98.43 273	99.48 228	99.36 303	96.11 404	99.27 246	99.36 353	93.76 325	99.24 376	94.46 432	95.23 404	98.70 349

cascas		97.69 336	97.43 338	98.48 326	98.60 433	97.30 329	98.18 477	99.39 285	92.96 452	98.41 384	98.78 431	93.77 324	99.27 370	98.16 257	98.61 266	98.86 322

pm-mvs1		97.68 339	97.28 358	98.88 271	99.06 363	98.62 250	99.50 203	99.45 250	96.32 386	97.87 419	99.79 169	92.47 358	99.35 357	97.54 322	93.54 434	98.67 366

GBi-Net		97.68 339	97.48 323	98.29 352	99.51 228	97.26 333	99.43 259	99.48 204	96.49 374	99.07 289	99.32 368	90.26 403	98.98 427	97.10 360	96.65 365	98.62 388

test1		97.68 339	97.48 323	98.29 352	99.51 228	97.26 333	99.43 259	99.48 204	96.49 374	99.07 289	99.32 368	90.26 403	98.98 427	97.10 360	96.65 365	98.62 388

tpm		97.67 342	97.55 313	98.03 371	99.02 370	95.01 433	99.43 259	98.54 453	96.44 380	99.12 278	99.34 360	91.83 373	99.60 316	97.75 301	96.46 370	99.48 242

PCF-MVS	97.08 14	97.66 343	97.06 371	99.47 166	99.61 188	99.09 165	98.04 480	99.25 359	91.24 466	98.51 377	99.70 216	94.55 289	99.91 135	92.76 456	99.85 93	99.42 260
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 344	97.65 304	97.63 410	98.78 407	97.62 319	99.13 371	98.33 457	97.36 301	99.07 289	98.94 418	95.64 226	99.15 394	92.95 452	98.68 264	96.12 482

our_test_3		97.65 344	97.68 301	97.55 416	98.62 430	94.97 434	98.84 430	99.30 342	96.83 349	98.19 402	99.34 360	97.01 149	99.02 421	95.00 426	96.01 381	98.64 379

testgi		97.65 344	97.50 321	98.13 367	99.36 284	96.45 385	99.42 266	99.48 204	97.76 251	97.87 419	99.45 327	91.09 395	98.81 445	94.53 431	98.52 275	99.13 294

thres200		97.61 347	97.28 358	98.62 307	99.64 164	98.03 293	99.26 339	98.74 436	97.68 262	99.09 286	98.32 448	91.66 380	99.81 233	92.88 453	98.22 295	98.03 451

PAPM		97.59 348	97.09 370	99.07 234	99.06 363	98.26 280	98.30 473	99.10 382	94.88 428	98.08 407	99.34 360	96.27 192	99.64 307	89.87 467	98.92 244	99.31 279

UWE-MVS		97.58 349	97.29 357	98.48 326	99.09 357	96.25 393	99.01 403	96.61 484	97.86 234	99.19 267	99.01 409	88.72 421	99.90 148	97.38 340	98.69 263	99.28 281

SD_0403		97.55 350	97.53 317	97.62 411	99.61 188	93.64 459	99.72 54	99.44 259	98.03 218	98.62 369	99.39 344	96.06 201	99.57 319	87.88 476	99.01 238	99.66 169

VDDNet		97.55 350	97.02 372	99.16 225	99.49 242	98.12 289	99.38 287	99.30 342	95.35 417	99.68 118	99.90 36	82.62 470	99.93 109	99.31 86	98.13 304	99.42 260

TESTMET0.1,1		97.55 350	97.27 361	98.40 342	98.93 384	96.53 382	98.67 446	97.61 473	96.96 338	98.64 364	99.28 375	88.63 427	99.45 332	97.30 346	99.38 183	99.21 290

pmmvs5		97.52 353	97.30 355	98.16 363	98.57 436	96.73 372	99.27 330	98.90 414	96.14 402	98.37 387	99.53 298	91.54 383	99.14 396	97.51 326	95.87 387	98.63 386

LF4IMVS		97.52 353	97.46 328	97.70 408	98.98 379	95.55 415	99.29 319	98.82 424	98.07 202	98.66 357	99.64 254	89.97 408	99.61 315	97.01 365	96.68 364	97.94 459

DTE-MVSNet		97.51 355	97.19 364	98.46 332	98.63 429	98.13 287	99.84 12	99.48 204	96.68 357	97.97 414	99.67 241	92.92 340	98.56 452	96.88 377	92.60 448	98.70 349

testing11		97.50 356	97.10 369	98.71 300	99.20 327	96.91 365	99.29 319	98.82 424	97.89 231	98.21 401	98.40 444	85.63 454	99.83 219	98.45 228	98.04 307	99.37 271

ETVMVS		97.50 356	96.90 376	99.29 207	99.23 320	98.78 236	99.32 308	98.90 414	97.52 283	98.56 374	98.09 459	84.72 461	99.69 292	97.86 285	97.88 313	99.39 267

hse-mvs2		97.50 356	97.14 366	98.59 309	99.49 242	97.05 346	99.28 325	99.22 365	98.94 78	99.66 129	99.42 332	94.93 255	99.65 303	99.48 64	83.80 474	99.08 300

SixPastTwentyTwo		97.50 356	97.33 352	98.03 371	98.65 427	96.23 394	99.77 35	98.68 445	97.14 319	97.90 417	99.93 10	90.45 401	99.18 391	97.00 366	96.43 371	98.67 366

JIA-IIPM		97.50 356	97.02 372	98.93 254	98.73 416	97.80 310	99.30 314	98.97 400	91.73 464	98.91 318	94.86 484	95.10 249	99.71 280	97.58 315	97.98 308	99.28 281

ppachtmachnet_test		97.49 361	97.45 329	97.61 414	98.62 430	95.24 426	98.80 435	99.46 239	96.11 404	98.22 400	99.62 265	96.45 181	98.97 434	93.77 440	95.97 386	98.61 397

test-mter		97.49 361	97.13 368	98.55 319	98.79 404	97.10 340	98.67 446	97.75 469	96.65 360	98.61 370	98.85 424	88.23 431	99.45 332	97.25 350	99.38 183	99.10 295

testing91		97.44 363	97.02 372	98.71 300	99.18 333	96.89 367	99.19 360	99.04 392	97.78 249	98.31 393	98.29 449	85.41 456	99.85 188	98.01 274	97.95 309	99.39 267

tpm2		97.44 363	97.34 349	97.74 406	99.15 347	94.36 449	99.45 246	98.94 403	93.45 447	98.90 320	99.44 328	91.35 388	99.59 317	97.31 343	98.07 306	99.29 280

tpm cat1		97.39 365	97.36 344	97.50 418	99.17 341	93.73 455	99.43 259	99.31 337	91.27 465	98.71 348	99.08 398	94.31 302	99.77 254	96.41 395	98.50 276	99.00 311

UWE-MVS-28		97.36 366	97.24 362	97.75 404	98.84 400	94.44 446	99.24 346	97.58 474	97.98 223	99.00 304	99.00 410	91.35 388	99.53 325	93.75 441	98.39 280	99.27 285

testing99		97.36 366	96.94 375	98.63 306	99.18 333	96.70 373	99.30 314	98.93 404	97.71 257	98.23 398	98.26 451	84.92 459	99.84 197	98.04 273	97.85 316	99.35 273

SSC-MVS3.2		97.34 368	97.15 365	97.93 383	99.02 370	95.76 409	99.48 228	99.58 77	97.62 269	99.09 286	99.53 298	87.95 434	99.27 370	96.42 393	95.66 394	98.75 336

USDC		97.34 368	97.20 363	97.75 404	99.07 361	95.20 427	98.51 461	99.04 392	97.99 222	98.31 393	99.86 78	89.02 417	99.55 323	95.67 412	97.36 350	98.49 417

UniMVSNet_ETH3D		97.32 370	96.81 378	98.87 275	99.40 272	97.46 324	99.51 192	99.53 124	95.86 412	98.54 376	99.77 185	82.44 471	99.66 298	98.68 194	97.52 334	99.50 238

testing3		97.28 371	96.76 380	98.82 284	99.37 281	98.07 292	99.45 246	99.36 303	97.56 276	97.89 418	98.95 417	83.70 465	98.82 444	96.03 401	98.56 272	99.58 210

MVS		97.28 371	96.55 384	99.48 160	98.78 407	98.95 193	99.27 330	99.39 285	83.53 484	98.08 407	99.54 294	96.97 150	99.87 175	94.23 436	99.16 204	99.63 187

test_fmvs2		97.25 373	97.30 355	97.09 429	99.43 260	93.31 462	99.73 52	98.87 419	98.83 88	99.28 240	99.80 152	84.45 462	99.66 298	97.88 282	97.45 342	98.30 434

DSMNet-mixed		97.25 373	97.35 346	96.95 434	97.84 450	93.61 460	99.57 143	96.63 483	96.13 403	98.87 326	98.61 437	94.59 285	97.70 470	95.08 424	98.86 252	99.55 217

MS-PatchMatch		97.24 375	97.32 353	96.99 431	98.45 441	93.51 461	98.82 433	99.32 333	97.41 297	98.13 406	99.30 371	88.99 418	99.56 321	95.68 411	99.80 125	97.90 462

testing222		97.16 376	96.50 385	99.16 225	99.16 343	98.47 271	99.27 330	98.66 448	97.71 257	98.23 398	98.15 454	82.28 473	99.84 197	97.36 341	97.66 322	99.18 291

TransMVSNet (Re)		97.15 377	96.58 383	98.86 278	99.12 349	98.85 222	99.49 220	98.91 412	95.48 416	97.16 438	99.80 152	93.38 329	99.11 405	94.16 438	91.73 451	98.62 388

TinyColmap		97.12 378	96.89 377	97.83 397	99.07 361	95.52 418	98.57 455	98.74 436	97.58 273	97.81 422	99.79 169	88.16 432	99.56 321	95.10 423	97.21 355	98.39 430

K. test v3		97.10 379	96.79 379	98.01 374	98.72 418	96.33 389	99.87 8	97.05 477	97.59 271	96.16 452	99.80 152	88.71 422	99.04 415	96.69 384	96.55 369	98.65 377

Syy-MVS		97.09 380	97.14 366	96.95 434	99.00 373	92.73 466	99.29 319	99.39 285	97.06 330	97.41 428	98.15 454	93.92 318	98.68 450	91.71 460	98.34 282	99.45 256

PatchT		97.03 381	96.44 387	98.79 290	98.99 376	98.34 277	99.16 364	99.07 388	92.13 462	99.52 178	97.31 476	94.54 290	98.98 427	88.54 472	98.73 261	99.03 308

mmtdpeth		96.95 382	96.71 381	97.67 409	99.33 291	94.90 436	99.89 2	99.28 348	98.15 176	99.72 101	98.57 438	86.56 447	99.90 148	99.82 29	89.02 465	98.20 441

myMVS_eth3d		96.89 383	96.37 388	98.43 339	99.00 373	97.16 337	99.29 319	99.39 285	97.06 330	97.41 428	98.15 454	83.46 467	98.68 450	95.27 421	98.34 282	99.45 256

AUN-MVS		96.88 384	96.31 390	98.59 309	99.48 249	97.04 349	99.27 330	99.22 365	97.44 293	98.51 377	99.41 336	91.97 369	99.66 298	97.71 306	83.83 473	99.07 305

FMVSNet1		96.84 385	96.36 389	98.29 352	99.32 298	97.26 333	99.43 259	99.48 204	95.11 421	98.55 375	99.32 368	83.95 464	98.98 427	95.81 406	96.26 376	98.62 388

test2506		96.81 386	96.65 382	97.29 424	99.74 100	92.21 469	99.60 114	85.06 501	99.13 41	99.77 84	99.93 10	87.82 438	99.85 188	99.38 74	99.38 183	99.80 88

RPMNet		96.72 387	95.90 400	99.19 222	99.18 333	98.49 267	99.22 353	99.52 133	88.72 475	99.56 167	97.38 473	94.08 311	99.95 76	86.87 481	98.58 269	99.14 292

mvs5depth		96.66 388	96.22 392	97.97 379	97.00 466	96.28 391	98.66 449	99.03 394	96.61 365	96.93 444	99.79 169	87.20 441	99.47 328	96.65 388	94.13 425	98.16 443

test_0402		96.64 389	96.24 391	97.85 392	98.85 398	96.43 386	99.44 253	99.26 357	93.52 444	96.98 442	99.52 302	88.52 428	99.20 390	92.58 458	97.50 337	97.93 460

X-MVStestdata		96.55 390	95.45 409	99.87 21	99.85 31	99.83 22	99.69 63	99.68 24	98.98 72	99.37 216	64.01 497	98.81 49	99.94 92	98.79 180	99.86 86	99.84 53

pmmvs6		96.53 391	96.09 396	97.82 399	98.69 424	95.47 419	99.37 289	99.47 226	93.46 446	97.41 428	99.78 176	87.06 444	99.33 360	96.92 375	92.70 446	98.65 377

ET-MVSNet_ETH3D		96.49 392	95.64 406	99.05 237	99.53 219	98.82 230	98.84 430	97.51 475	97.63 267	84.77 484	99.21 387	92.09 367	98.91 440	98.98 139	92.21 449	99.41 263

UnsupCasMVSNet_eth		96.44 393	96.12 394	97.40 421	98.65 427	95.65 412	99.36 295	99.51 155	97.13 320	96.04 454	98.99 412	88.40 429	98.17 459	96.71 382	90.27 459	98.40 429

FMVSNet5		96.43 394	96.19 393	97.15 425	99.11 351	95.89 405	99.32 308	99.52 133	94.47 437	98.34 392	99.07 399	87.54 439	97.07 476	92.61 457	95.72 392	98.47 420

new_pmnet		96.38 395	96.03 397	97.41 420	98.13 447	95.16 430	99.05 390	99.20 370	93.94 439	97.39 431	98.79 430	91.61 382	99.04 415	90.43 465	95.77 389	98.05 450

Anonymous20231206		96.22 396	96.03 397	96.79 439	97.31 460	94.14 451	99.63 102	99.08 385	96.17 398	97.04 441	99.06 401	93.94 316	97.76 469	86.96 480	95.06 408	98.47 420

IB-MVS	95.67 18	96.22 396	95.44 410	98.57 313	99.21 325	96.70 373	98.65 450	97.74 471	96.71 355	97.27 433	98.54 439	86.03 451	99.92 123	98.47 226	86.30 470	99.10 295
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		96.20 398	95.89 401	97.13 427	97.72 454	94.96 435	99.79 31	99.29 346	93.01 451	97.20 437	99.03 406	89.69 412	98.36 456	91.16 463	96.13 378	98.07 448

gg-mvs-nofinetune		96.17 399	95.32 411	98.73 295	98.79 404	98.14 286	99.38 287	94.09 492	91.07 468	98.07 410	91.04 490	89.62 414	99.35 357	96.75 380	99.09 230	98.68 358

test20.03		96.12 400	95.96 399	96.63 440	97.44 456	95.45 420	99.51 192	99.38 293	96.55 371	96.16 452	99.25 381	93.76 325	96.17 483	87.35 479	94.22 423	98.27 436

PVSNet_0	94.43 19	96.09 401	95.47 408	97.94 382	99.31 299	94.34 450	97.81 481	99.70 18	97.12 322	97.46 427	98.75 432	89.71 411	99.79 246	97.69 309	81.69 478	99.68 160

MVStest1		96.08 402	95.48 407	97.89 387	98.93 384	96.70 373	99.56 151	99.35 310	92.69 455	91.81 479	99.46 325	89.90 409	98.96 436	95.00 426	92.61 447	98.00 455

EG-PatchMatch MVS		95.97 403	95.69 404	96.81 438	97.78 451	92.79 465	99.16 364	98.93 404	96.16 399	94.08 468	99.22 384	82.72 469	99.47 328	95.67 412	97.50 337	98.17 442

APD_test1		95.87 404	96.49 386	94.00 453	99.53 219	84.01 482	99.54 171	99.32 333	95.91 411	97.99 412	99.85 85	85.49 455	99.88 168	91.96 459	98.84 254	98.12 445

Patchmatch-RL test		95.84 405	95.81 403	95.95 447	95.61 478	90.57 474	98.24 474	98.39 455	95.10 423	95.20 459	98.67 434	94.78 267	97.77 468	96.28 398	90.02 460	99.51 234

test_vis1_rt		95.81 406	95.65 405	96.32 444	99.67 137	91.35 472	99.49 220	96.74 482	98.25 160	95.24 457	98.10 458	74.96 480	99.90 148	99.53 53	98.85 253	97.70 465

sc_t1		95.75 407	95.05 414	97.87 388	98.83 401	94.61 443	99.21 355	99.45 250	87.45 476	97.97 414	99.85 85	81.19 476	99.43 341	98.27 247	93.20 439	99.57 213

MVS-HIRNet		95.75 407	95.16 412	97.51 417	99.30 300	93.69 457	98.88 424	95.78 486	85.09 483	98.78 342	92.65 486	91.29 390	99.37 350	94.85 428	99.85 93	99.46 253

tt0320		95.71 409	95.07 413	97.62 411	99.05 366	95.02 432	99.25 341	99.52 133	86.81 477	97.97 414	99.72 209	83.58 466	99.15 394	96.38 396	93.35 435	98.68 358

blended_shiyan8		95.56 410	94.79 417	97.87 388	96.60 469	95.90 404	98.85 427	99.27 355	92.19 458	98.47 381	97.94 463	91.43 385	99.11 405	97.26 349	81.09 480	98.60 400

blended_shiyan6		95.54 411	94.78 418	97.84 394	96.60 469	95.89 405	98.85 427	99.28 348	92.17 461	98.43 383	97.95 462	91.44 384	99.02 421	97.30 346	80.97 481	98.60 400

MIMVSNet1		95.51 412	95.04 415	96.92 436	97.38 457	95.60 413	99.52 182	99.50 179	93.65 443	96.97 443	99.17 389	85.28 458	96.56 481	88.36 473	95.55 398	98.60 400

MDA-MVSNet_test_wron		95.45 413	94.60 422	98.01 374	98.16 446	97.21 336	99.11 380	99.24 362	93.49 445	80.73 490	98.98 414	93.02 337	98.18 458	94.22 437	94.45 419	98.64 379

wanda-best-256-512		95.43 414	94.66 420	97.77 402	96.45 471	95.68 410	98.48 462	99.28 348	92.18 459	98.36 388	97.68 466	91.20 392	99.03 417	97.31 343	80.97 481	98.60 400

FE-blended-shiyan7		95.43 414	94.66 420	97.77 402	96.45 471	95.68 410	98.48 462	99.28 348	92.18 459	98.36 388	97.68 466	91.20 392	99.03 417	97.31 343	80.97 481	98.60 400

TDRefinement		95.42 416	94.57 424	97.97 379	89.83 494	96.11 398	99.48 228	98.75 433	96.74 353	96.68 446	99.88 56	88.65 425	99.71 280	98.37 237	82.74 476	98.09 447

YYNet1		95.36 417	94.51 425	97.92 384	97.89 449	97.10 340	99.10 382	99.23 363	93.26 449	80.77 489	99.04 405	92.81 343	98.02 462	94.30 433	94.18 424	98.64 379

pmmvs-eth3d		95.34 418	94.73 419	97.15 425	95.53 480	95.94 401	99.35 300	99.10 382	95.13 419	93.55 471	97.54 471	88.15 433	97.91 465	94.58 430	89.69 464	97.61 466

tt0320-xc		95.31 419	94.59 423	97.45 419	98.92 386	94.73 438	99.20 358	99.31 337	86.74 478	97.23 434	99.72 209	81.14 477	98.95 437	97.08 363	91.98 450	98.67 366

blend_shiyan4		95.25 420	94.39 427	97.84 394	96.70 468	95.92 402	98.84 430	99.28 348	92.21 457	98.16 404	97.84 464	87.10 443	99.07 410	97.53 323	81.87 477	98.54 410

FE-MVSNET2		95.10 421	94.44 426	97.08 430	95.08 483	95.97 400	99.51 192	99.37 301	95.02 425	94.10 467	97.57 469	86.18 450	97.66 472	93.28 447	89.86 462	97.61 466

usedtu_blend_shiyan5		95.04 422	94.10 429	97.86 391	96.45 471	95.92 402	99.29 319	99.22 365	86.17 481	98.36 388	97.68 466	91.20 392	99.07 410	97.53 323	80.97 481	98.60 400

dmvs_testset		95.02 423	96.12 394	91.72 462	99.10 354	80.43 490	99.58 135	97.87 468	97.47 286	95.22 458	98.82 426	93.99 314	95.18 487	88.09 474	94.91 413	99.56 216

KD-MVS_self_test		95.00 424	94.34 428	96.96 433	97.07 465	95.39 423	99.56 151	99.44 259	95.11 421	97.13 439	97.32 475	91.86 372	97.27 475	90.35 466	81.23 479	98.23 440

MDA-MVSNet-bldmvs		94.96 425	93.98 432	97.92 384	98.24 445	97.27 331	99.15 367	99.33 323	93.80 441	80.09 491	99.03 406	88.31 430	97.86 467	93.49 445	94.36 421	98.62 388

N_pmnet		94.95 426	95.83 402	92.31 460	98.47 440	79.33 492	99.12 374	92.81 498	93.87 440	97.68 424	99.13 394	93.87 320	99.01 424	91.38 462	96.19 377	98.59 406

0.4-1-1-0.2		94.94 427	93.92 434	97.99 377	96.84 467	95.13 431	96.64 487	97.62 472	93.45 447	94.92 464	96.56 479	87.14 442	99.86 181	98.43 232	83.69 475	98.98 314

KD-MVS_2432*1600		94.62 428	93.72 436	97.31 422	97.19 463	95.82 407	98.34 469	99.20 370	95.00 426	97.57 425	98.35 446	87.95 434	98.10 460	92.87 454	77.00 488	98.01 452

miper_refine_blended		94.62 428	93.72 436	97.31 422	97.19 463	95.82 407	98.34 469	99.20 370	95.00 426	97.57 425	98.35 446	87.95 434	98.10 460	92.87 454	77.00 488	98.01 452

CL-MVSNet_self_test		94.49 430	93.97 433	96.08 446	96.16 475	93.67 458	98.33 471	99.38 293	95.13 419	97.33 432	98.15 454	92.69 351	96.57 480	88.67 471	79.87 486	97.99 456

new-patchmatchnet		94.48 431	94.08 431	95.67 448	95.08 483	92.41 467	99.18 362	99.28 348	94.55 436	93.49 472	97.37 474	87.86 437	97.01 478	91.57 461	88.36 466	97.61 466

OpenMVS_ROB	92.34 20	94.38 432	93.70 438	96.41 443	97.38 457	93.17 463	99.06 388	98.75 433	86.58 479	94.84 465	98.26 451	81.53 474	99.32 362	89.01 470	97.87 314	96.76 475

CMPMVS	69.68 23	94.13 433	94.90 416	91.84 461	97.24 461	80.01 491	98.52 460	99.48 204	89.01 473	91.99 478	99.67 241	85.67 453	99.13 399	95.44 416	97.03 360	96.39 479
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 434	93.25 441	96.60 441	94.76 486	94.49 445	98.92 420	98.18 464	89.66 469	96.48 448	98.06 460	86.28 449	97.33 474	89.68 468	87.20 469	97.97 458

FE-MVSNET		94.07 435	93.36 440	96.22 445	94.05 487	94.71 440	99.56 151	98.36 456	93.15 450	93.76 470	97.55 470	86.47 448	96.49 482	87.48 477	89.83 463	97.48 471

mvsany_test3		93.77 436	93.45 439	94.74 451	95.78 477	88.01 477	99.64 96	98.25 459	98.28 150	94.31 466	97.97 461	68.89 484	98.51 454	97.50 327	90.37 458	97.71 463

UnsupCasMVSNet_bld		93.53 437	92.51 443	96.58 442	97.38 457	93.82 453	98.24 474	99.48 204	91.10 467	93.10 473	96.66 478	74.89 481	98.37 455	94.03 439	87.71 468	97.56 469

dongtai		93.26 438	92.93 442	94.25 452	99.39 275	85.68 480	97.68 483	93.27 494	92.87 453	96.85 445	99.39 344	82.33 472	97.48 473	76.78 488	97.80 317	99.58 210

WB-MVS		93.10 439	94.10 429	90.12 467	95.51 482	81.88 487	99.73 52	99.27 355	95.05 424	93.09 474	98.91 423	94.70 278	91.89 491	76.62 489	94.02 429	96.58 477

PM-MVS		92.96 440	92.23 444	95.14 450	95.61 478	89.98 476	99.37 289	98.21 462	94.80 431	95.04 463	97.69 465	65.06 485	97.90 466	94.30 433	89.98 461	97.54 470

SSC-MVS		92.73 441	93.73 435	89.72 468	95.02 485	81.38 488	99.76 38	99.23 363	94.87 429	92.80 475	98.93 419	94.71 277	91.37 492	74.49 491	93.80 431	96.42 478

test_fmvs3		92.10 442	91.77 445	93.08 458	96.19 474	86.25 478	99.82 16	98.62 450	96.65 360	95.19 460	96.90 477	55.05 492	95.93 485	96.63 389	90.92 457	97.06 474

test_f		91.90 443	91.26 447	93.84 454	95.52 481	85.92 479	99.69 63	98.53 454	95.31 418	93.87 469	96.37 481	55.33 491	98.27 457	95.70 409	90.98 456	97.32 473

usedtu_dtu_shiyan2		91.34 444	89.96 452	95.47 449	93.61 489	90.81 473	99.15 367	98.68 445	86.37 480	95.19 460	98.27 450	72.64 482	97.05 477	85.40 485	80.32 485	98.54 410

test_method		91.10 445	91.36 446	90.31 466	95.85 476	73.72 499	94.89 488	99.25 359	68.39 490	95.82 455	99.02 408	80.50 478	98.95 437	93.64 443	94.89 414	98.25 438

Gipuma		90.99 446	90.15 450	93.51 455	98.73 416	90.12 475	93.98 489	99.45 250	79.32 486	92.28 476	94.91 483	69.61 483	97.98 464	87.42 478	95.67 393	92.45 486
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 447	90.11 451	93.34 456	98.78 407	85.59 481	98.15 478	93.16 496	89.37 472	92.07 477	98.38 445	81.48 475	95.19 486	62.54 495	97.04 359	99.25 286

testf1		90.42 448	90.68 448	89.65 469	97.78 451	73.97 497	99.13 371	98.81 426	89.62 470	91.80 480	98.93 419	62.23 488	98.80 446	86.61 482	91.17 453	96.19 480

APD_test2		90.42 448	90.68 448	89.65 469	97.78 451	73.97 497	99.13 371	98.81 426	89.62 470	91.80 480	98.93 419	62.23 488	98.80 446	86.61 482	91.17 453	96.19 480

test_vis3_rt		87.04 450	85.81 453	90.73 465	93.99 488	81.96 486	99.76 38	90.23 500	92.81 454	81.35 488	91.56 488	40.06 496	99.07 410	94.27 435	88.23 467	91.15 488

PMMVS2		86.87 451	85.37 455	91.35 464	90.21 493	83.80 483	98.89 423	97.45 476	83.13 485	91.67 482	95.03 482	48.49 494	94.70 488	85.86 484	77.62 487	95.54 483

LCM-MVSNet		86.80 452	85.22 456	91.53 463	87.81 495	80.96 489	98.23 476	98.99 398	71.05 488	90.13 483	96.51 480	48.45 495	96.88 479	90.51 464	85.30 471	96.76 475

FPMVS		84.93 453	85.65 454	82.75 475	86.77 496	63.39 501	98.35 468	98.92 407	74.11 487	83.39 486	98.98 414	50.85 493	92.40 490	84.54 486	94.97 410	92.46 485

EGC-MVSNET		82.80 454	77.86 460	97.62 411	97.91 448	96.12 397	99.33 305	99.28 348	8.40 498	25.05 499	99.27 378	84.11 463	99.33 360	89.20 469	98.22 295	97.42 472

tmp_tt		82.80 454	81.52 457	86.66 471	66.61 501	68.44 500	92.79 491	97.92 466	68.96 489	80.04 492	99.85 85	85.77 452	96.15 484	97.86 285	43.89 494	95.39 484

E-PMN		80.61 456	79.88 458	82.81 474	90.75 492	76.38 495	97.69 482	95.76 487	66.44 492	83.52 485	92.25 487	62.54 487	87.16 494	68.53 493	61.40 491	84.89 492

EMVS		80.02 457	79.22 459	82.43 476	91.19 491	76.40 494	97.55 485	92.49 499	66.36 493	83.01 487	91.27 489	64.63 486	85.79 495	65.82 494	60.65 492	85.08 491

ANet_high		77.30 458	74.86 462	84.62 473	75.88 499	77.61 493	97.63 484	93.15 497	88.81 474	64.27 494	89.29 491	36.51 497	83.93 496	75.89 490	52.31 493	92.33 487

MVE	76.82 21	76.91 459	74.31 463	84.70 472	85.38 498	76.05 496	96.88 486	93.17 495	67.39 491	71.28 493	89.01 492	21.66 502	87.69 493	71.74 492	72.29 490	90.35 489
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 460	74.97 461	79.01 477	70.98 500	55.18 502	93.37 490	98.21 462	65.08 494	61.78 495	93.83 485	21.74 501	92.53 489	78.59 487	91.12 455	89.34 490
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		40.18 461	41.29 466	36.84 478	86.18 497	49.12 503	79.73 492	22.81 503	27.64 495	25.46 498	28.45 498	21.98 500	48.89 497	55.80 496	23.56 497	12.51 495

testmvs		39.17 462	43.78 464	25.37 480	36.04 503	16.84 505	98.36 467	26.56 502	20.06 496	38.51 497	67.32 493	29.64 499	15.30 499	37.59 497	39.90 495	43.98 494

test123		39.01 463	42.50 465	28.53 479	39.17 502	20.91 504	98.75 440	19.17 504	19.83 497	38.57 496	66.67 494	33.16 498	15.42 498	37.50 498	29.66 496	49.26 493

cdsmvs_eth3d_5k		24.64 464	32.85 467	0.00 481	0.00 504	0.00 506	0.00 493	99.51 155	0.00 499	0.00 500	99.56 286	96.58 173	0.00 500	0.00 499	0.00 498	0.00 496

ab-mvs-re		8.30 465	11.06 468	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	99.58 278	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

pcd_1.5k_mvsjas		8.27 466	11.03 469	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	99.01 20	0.00 500	0.00 499	0.00 498	0.00 496

test_blank		0.13 467	0.17 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	1.57 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

mmdepth		0.02 468	0.03 471	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

monomultidepth		0.02 468	0.03 471	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

uanet_test		0.02 468	0.03 471	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

DCPMVS		0.02 468	0.03 471	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

sosnet-low-res		0.02 468	0.03 471	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

sosnet		0.02 468	0.03 471	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

uncertanet		0.02 468	0.03 471	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

Regformer		0.02 468	0.03 471	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

uanet		0.02 468	0.03 471	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.27 500	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

MED-MVS test				99.87 21	99.88 13	99.81 33	99.69 63	99.87 6	99.34 26	99.90 33	99.83 106		99.95 76	98.83 172	99.89 67	99.83 63

TestfortrainingZip							99.69 63

WAC-MVS						97.16 337								95.47 415

FOURS1					99.91 1	99.93 1	99.87 8	99.56 89	99.10 48	99.81 68

MSC_two_6792asdad				99.87 21	99.51 228	99.76 49		99.33 323					99.96 41	98.87 159	99.84 101	99.89 29

PC_three_1452									98.18 174	99.84 55	99.70 216	99.31 3	98.52 453	98.30 246	99.80 125	99.81 79

No_MVS				99.87 21	99.51 228	99.76 49		99.33 323					99.96 41	98.87 159	99.84 101	99.89 29

test_one_0601					99.81 57	99.88 10		99.49 192	98.97 75	99.65 139	99.81 134	99.09 16

eth-test2					0.00 504

eth-test					0.00 504

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 347	99.56 167	99.54 294	98.58 78	99.96 41	96.93 373	99.75 142

RE-MVS-def			99.34 49		99.76 82	99.82 28	99.63 102	99.52 133	98.38 137	99.76 90	99.82 119	98.75 60		98.61 204	99.81 120	99.77 100

IU-MVS					99.84 38	99.88 10		99.32 333	98.30 149	99.84 55				98.86 164	99.85 93	99.89 29

OPU-MVS				99.64 101	99.56 207	99.72 56	99.60 114				99.70 216	99.27 7	99.42 343	98.24 250	99.80 125	99.79 92

test_241102_TWO								99.48 204	99.08 56	99.88 42	99.81 134	98.94 34	99.96 41	98.91 153	99.84 101	99.88 35

test_241102_ONE					99.84 38	99.90 3		99.48 204	99.07 58	99.91 30	99.74 199	99.20 9	99.76 258

9.14			99.10 98		99.72 111		99.40 278	99.51 155	97.53 281	99.64 144	99.78 176	98.84 46	99.91 135	97.63 311	99.82 117

save fliter					99.76 82	99.59 88	99.14 370	99.40 282	99.00 67

test_0728_THIRD									98.99 69	99.81 68	99.80 152	99.09 16	99.96 41	98.85 166	99.90 56	99.88 35

test_0728_SECOND				99.91 6	99.84 38	99.89 6	99.57 143	99.51 155					99.96 41	98.93 150	99.86 86	99.88 35

test0726					99.85 31	99.89 6	99.62 107	99.50 179	99.10 48	99.86 52	99.82 119	98.94 34

GSMVS																99.52 225

test_part2					99.81 57	99.83 22				99.77 84

sam_mvs1												94.86 261				99.52 225

sam_mvs												94.72 276

ambc				93.06 459	92.68 490	82.36 484	98.47 464	98.73 442		95.09 462	97.41 472	55.55 490	99.10 408	96.42 393	91.32 452	97.71 463

MTGPA								99.47 226

test_post1							99.23 349				65.14 496	94.18 307	99.71 280	97.58 315

test_post											65.99 495	94.65 283	99.73 270

patchmatchnet-post											98.70 433	94.79 266	99.74 264

GG-mvs-BLEND				98.45 334	98.55 437	98.16 284	99.43 259	93.68 493		97.23 434	98.46 441	89.30 415	99.22 383	95.43 417	98.22 295	97.98 457

MTMP							99.54 171	98.88 417

gm-plane-assit					98.54 438	92.96 464			94.65 434		99.15 392		99.64 307	97.56 320

test9_res														97.49 328	99.72 148	99.75 113

TEST9					99.67 137	99.65 75	99.05 390	99.41 275	96.22 394	98.95 313	99.49 312	98.77 56	99.91 135

test_8					99.67 137	99.61 85	99.03 395	99.41 275	96.28 388	98.93 316	99.48 318	98.76 57	99.91 135

agg_prior2														97.21 352	99.73 147	99.75 113

agg_prior					99.67 137	99.62 83		99.40 282		98.87 326			99.91 135

TestCases				99.31 199	99.86 25	98.48 269		99.61 60	97.85 237	99.36 222	99.85 85	95.95 207	99.85 188	96.66 386	99.83 113	99.59 206

test_prior4						99.56 94	98.99 406

test_prior2							98.96 413		98.34 143	99.01 300	99.52 302	98.68 70		97.96 277	99.74 145

test_prior				99.68 89	99.67 137	99.48 111		99.56 89					99.83 219			99.74 118

旧先验2							98.96 413		96.70 356	99.47 186			99.94 92	98.19 253

新几何2							99.01 403

新几何1				99.75 77	99.75 92	99.59 88		99.54 108	96.76 352	99.29 239	99.64 254	98.43 89	99.94 92	96.92 375	99.66 159	99.72 137

旧先验1					99.74 100	99.59 88		99.54 108			99.69 227	98.47 86			99.68 156	99.73 127

无先验							98.99 406	99.51 155	96.89 344				99.93 109	97.53 323		99.72 137

原ACMM2							98.95 416

原ACMM1				99.65 95	99.73 107	99.33 130		99.47 226	97.46 287	99.12 278	99.66 246	98.67 72	99.91 135	97.70 308	99.69 153	99.71 148

test222					99.75 92	99.49 109	98.91 422	99.49 192	96.42 382	99.34 229	99.65 248	98.28 99			99.69 153	99.72 137

testdata2													99.95 76	96.67 385

segment_acmp												98.96 27

testdata				99.54 125	99.75 92	98.95 193		99.51 155	97.07 328	99.43 197	99.70 216	98.87 42	99.94 92	97.76 299	99.64 162	99.72 137

testdata1							98.85 427		98.32 147

test12				99.75 77	99.64 164	99.61 85		99.29 346		99.21 261		98.38 94	99.89 163		99.74 145	99.74 118

plane_prior7					99.29 304	97.03 352

plane_prior6					99.27 309	96.98 356						92.71 349

plane_prior5								99.47 226					99.69 292	97.78 295	97.63 323	98.67 366

plane_prior4											99.61 269

plane_prior3						97.00 354			98.69 107	99.11 280

plane_prior2							99.39 282		98.97 75

plane_prior1					99.26 312

plane_prior						96.97 357	99.21 355		98.45 130						97.60 326

n2								0.00 505

nn								0.00 505

door-mid								98.05 465

lessismore_v0				97.79 401	98.69 424	95.44 422		94.75 490		95.71 456	99.87 69	88.69 423	99.32 362	95.89 404	94.93 412	98.62 388

LGP-MVS_train				98.49 324	99.33 291	97.05 346		99.55 99	97.46 287	99.24 253	99.83 106	92.58 354	99.72 274	98.09 264	97.51 335	98.68 358

test11								99.35 310

door								97.92 466

HQP5-MVS						96.83 368

HQP-NCC					99.19 330		98.98 409		98.24 162	98.66 357

ACMP_Plane					99.19 330		98.98 409		98.24 162	98.66 357

BP-MVS														97.19 356

HQP4-MVS										98.66 357			99.64 307			98.64 379

HQP3-MVS								99.39 285							97.58 328

HQP2-MVS												92.47 358

NP-MVS					99.23 320	96.92 364					99.40 340

MDTV_nov1_ep13_2view						95.18 429	99.35 300		96.84 347	99.58 163		95.19 246		97.82 290		99.46 253

MDTV_nov1_ep13			98.32 232		99.11 351	94.44 446	99.27 330	98.74 436	97.51 284	99.40 210	99.62 265	94.78 267	99.76 258	97.59 314	98.81 258

ACMMP++_ref															97.19 356

ACMMP++															97.43 346

Test By Simon												98.75 60

ITE_SJBPF				98.08 369	99.29 304	96.37 387		98.92 407	98.34 143	98.83 334	99.75 194	91.09 395	99.62 314	95.82 405	97.40 348	98.25 438

DeepMVS_CX				93.34 456	99.29 304	82.27 485		99.22 365	85.15 482	96.33 449	99.05 402	90.97 397	99.73 270	93.57 444	97.77 319	98.01 452

High-resolution multi-view benchmark