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	99.83 100	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	99.83 100	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	99.82 113	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	99.48 221	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	99.83 100	99.30 4	99.95 76	98.83 166	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	99.38 272	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	99.04 126	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	99.04 126	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	99.48 198	99.08 56	99.91 31	99.81 128	99.20 9	99.96 41	98.91 147	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	99.51 223	99.88 10	99.87 8	99.51 151	98.99 69	99.88 43	99.81 128	99.27 7	99.96 41	98.85 160	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	99.47 231	99.63 46	99.45 11	99.98 13	99.89 41	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	99.63 101	99.39 277	98.91 82	99.78 81	99.85 80	99.36 2	99.94 92	98.84 163	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	99.45 242	99.01 64	99.90 34	99.83 100	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	99.45 242	99.01 64	99.89 40	99.82 113	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	99.37 294	99.10 48	99.81 69	99.80 146	98.94 34	99.96 41	98.93 144	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	99.37 282	99.70 18	99.18 34	99.83 64	99.83 100	98.74 65	99.93 110	98.83 166	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	99.44 254	99.65 75	99.50 196	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	96.60 171	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	99.51 223	99.67 68	99.50 196	99.64 42	99.43 17	99.98 13	99.78 170	97.26 135	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	99.83 100	99.28 6	99.97 29	98.48 217	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	99.37 210	99.74 193	98.81 49	99.94 92	98.79 174	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	99.47 220	98.79 95	99.68 113	99.81 128	98.43 89	99.97 29	98.88 150	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	96.60 171	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	97.72 250	99.76 91	99.75 188	99.13 14	99.92 123	99.07 123	99.92 39	99.85 46

mvsany_test1		99.50 31	99.46 28	99.62 108	99.61 183	99.09 165	98.94 410	99.48 198	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	99.70 210	98.65 74	99.79 239	99.65 41	99.78 134	99.41 258

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	99.69 221	98.55 81	99.82 221	99.69 35	99.85 94	99.48 237

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	99.68 113	99.69 221	99.06 18	99.96 41	98.69 186	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	99.67 119	99.69 221	98.95 32	99.96 41	98.69 186	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	99.36 288	99.46 231	99.07 58	99.79 76	99.82 113	98.85 44	99.92 123	98.68 188	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	99.66 124	99.68 229	98.96 27	99.96 41	98.62 195	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	99.82 113	98.86 43	99.95 76	98.62 195	99.81 120	99.78 98

DELS-MVS		99.48 37	99.42 32	99.65 95	99.72 111	99.40 121	99.05 382	99.66 32	99.14 40	99.57 160	99.80 146	98.46 87	99.94 92	99.57 48	99.84 102	99.60 189
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	99.55 167	99.64 248	98.91 39	99.96 41	98.72 181	99.90 57	99.82 72

ACMMP_NAP		99.47 40	99.34 50	99.88 15	99.87 20	99.86 18	99.47 231	99.48 198	98.05 203	99.76 91	99.86 73	98.82 48	99.93 110	98.82 173	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	99.47 243

balanced_conf03		99.46 42	99.39 40	99.67 90	99.55 206	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	99.52 220

DPE-MVS		99.46 42	99.32 54	99.91 6	99.78 70	99.88 10	99.36 288	99.51 151	98.73 102	99.88 43	99.84 95	98.72 67	99.96 41	98.16 250	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	99.44 168	99.60 189	99.16 155	99.41 263	99.71 16	98.98 72	99.45 183	99.78 170	99.19 11	99.54 317	99.28 92	99.84 102	99.63 181

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	99.82 113	98.53 82	99.95 76	98.61 198	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	97.84 234	99.71 107	99.80 146	99.12 15	99.97 29	98.33 235	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	99.53 170	99.63 254	98.93 38	99.97 29	98.74 178	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	99.63 141	99.84 95	98.73 66	99.96 41	98.55 213	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	99.47 220	97.45 284	99.78 81	99.82 113	99.18 12	99.91 135	98.79 174	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	99.48 198	98.12 186	99.50 175	99.75 188	98.78 53	99.97 29	98.57 207	99.89 68	99.83 63

EC-MVSNet		99.44 50	99.39 40	99.58 116	99.56 202	99.49 109	99.88 4	99.58 78	98.38 137	99.73 97	99.69 221	98.20 103	99.70 280	99.64 43	99.82 117	99.54 213

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	99.79 163	98.68 70	99.96 41	98.44 223	99.77 137	99.79 92

MCST-MVS		99.43 53	99.30 62	99.82 57	99.79 68	99.74 54	99.29 313	99.40 274	98.79 95	99.52 172	99.62 259	98.91 39	99.90 148	98.64 192	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	99.49 306	98.21 102	99.95 76	98.46 221	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	99.62 172	99.55 96	99.50 196	99.70 18	98.79 95	99.77 85	99.96 1	97.45 124	99.96 41	98.92 146	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	97.59 265	99.68 113	99.63 254	98.91 39	99.94 92	98.58 204	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	99.62 172	99.71 58	99.26 332	99.52 130	98.82 89	99.39 206	99.71 206	98.96 27	99.85 187	98.59 203	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	94.92 252	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	99.48 221	99.62 51	99.46 7	99.99 2	99.92 18	95.24 239	99.96 41	99.97 2	99.97 9	99.96 7

SD-MVS		99.41 59	99.52 14	99.05 231	99.74 100	99.68 64	99.46 235	99.52 130	99.11 47	99.88 43	99.91 26	99.43 1	97.70 455	98.72 181	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	98.94 410	99.85 9	98.82 89	99.65 133	99.74 193	98.51 84	99.80 233	98.83 166	99.89 68	99.64 176

MVS_111021_HR		99.41 59	99.32 54	99.66 91	99.72 111	99.47 113	98.95 408	99.85 9	98.82 89	99.54 168	99.73 199	98.51 84	99.74 257	98.91 147	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	98.87 405	99.55 1	99.74 95	99.80 146	96.47 179	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	97.97 218	99.63 141	99.68 229	98.52 83	99.95 76	98.38 228	99.86 87	99.81 79

HPM-MVS++		99.39 66	99.23 82	99.87 21	99.75 92	99.84 20	99.43 251	99.51 151	98.68 109	99.27 240	99.53 292	98.64 75	99.96 41	98.44 223	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	97.82 240	99.71 107	99.80 146	98.95 32	99.93 110	98.19 246	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	99.42 258	99.61 60	99.37 24	99.97 25	99.86 73	94.96 247	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	99.48 221	99.66 32	99.45 11	99.99 2	99.93 10	94.64 276	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	99.46 235	99.60 67	99.47 4	99.98 13	99.94 6	94.98 246	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	99.30 308	99.52 130	97.18 310	99.60 153	99.79 163	98.79 52	99.95 76	98.83 166	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	99.49 213	99.60 67	99.42 20	99.99 2	99.86 73	95.15 242	99.95 76	99.95 16	99.89 68	99.73 122

TSAR-MVS + GP.		99.36 72	99.36 46	99.36 182	99.67 134	98.61 244	99.07 376	99.33 315	99.00 67	99.82 68	99.81 128	99.06 18	99.84 196	99.09 121	99.42 181	99.65 169

PVSNet_Blended_VisFu		99.36 72	99.28 69	99.61 109	99.86 25	99.07 170	99.47 231	99.93 2	97.66 259	99.71 107	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	98.63 240	99.42 258	99.63 46	99.46 7	99.98 13	99.88 52	95.59 222	99.96 41	99.97 2	99.98 4	99.85 46

NCCC		99.34 75	99.19 88	99.79 68	99.61 183	99.65 75	99.30 308	99.48 198	98.86 84	99.21 255	99.63 254	98.72 67	99.90 148	98.25 242	99.63 164	99.80 88

mamv4		99.33 77	99.42 32	99.07 227	99.67 134	97.73 303	99.42 258	99.60 67	98.15 175	99.94 28	99.91 26	98.42 91	99.94 92	99.72 32	99.96 17	99.54 213

MP-MVS		99.33 77	99.15 93	99.87 21	99.88 13	99.82 28	99.66 82	99.46 231	98.09 192	99.48 179	99.74 193	98.29 99	99.96 41	97.93 272	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	94.18 299	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	99.44 245	99.58 78	99.47 4	99.99 2	99.93 10	94.04 304	99.96 41	99.96 13	99.93 33	99.93 22

PS-MVSNAJ		99.32 79	99.32 54	99.30 198	99.57 198	98.94 197	98.97 404	99.46 231	98.92 81	99.71 107	99.24 376	99.01 20	99.98 20	99.35 76	99.66 159	98.97 309

CSCG		99.32 79	99.32 54	99.32 191	99.85 31	98.29 270	99.71 57	99.66 32	98.11 188	99.41 199	99.80 146	98.37 96	99.96 41	98.99 132	99.96 17	99.72 132

PHI-MVS		99.30 83	99.17 91	99.70 87	99.56 202	99.52 105	99.58 130	99.80 11	97.12 316	99.62 145	99.73 199	98.58 78	99.90 148	98.61 198	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	99.63 141	99.95 3	95.82 211	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	94.53 284	99.94 92	99.89 25	99.96 17	99.97 4

xiu_mvs_v1_base_debu		99.29 85	99.27 73	99.34 185	99.63 164	98.97 183	99.12 366	99.51 151	98.86 84	99.84 56	99.47 315	98.18 104	99.99 4	99.50 57	99.31 191	99.08 294

xiu_mvs_v1_base		99.29 85	99.27 73	99.34 185	99.63 164	98.97 183	99.12 366	99.51 151	98.86 84	99.84 56	99.47 315	98.18 104	99.99 4	99.50 57	99.31 191	99.08 294

xiu_mvs_v1_base_debi		99.29 85	99.27 73	99.34 185	99.63 164	98.97 183	99.12 366	99.51 151	98.86 84	99.84 56	99.47 315	98.18 104	99.99 4	99.50 57	99.31 191	99.08 294

NormalMVS		99.27 89	99.19 88	99.52 139	99.89 8	98.83 219	99.65 88	99.52 130	99.10 48	99.84 56	99.76 183	95.80 213	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	99.50 196	99.50 174	97.16 312	99.77 85	99.82 113	98.78 53	99.94 92	97.56 313	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	99.18 327	99.75 51	99.56 146	99.57 85	98.45 130	99.49 178	99.85 80	97.77 118	99.94 92	98.33 235	99.84 102	99.52 220

fmvsm_s_conf0.1_n_a		99.26 92	99.06 109	99.85 43	99.52 220	99.62 83	99.54 166	99.62 51	98.69 107	99.99 2	99.96 1	94.47 286	99.94 92	99.88 26	99.92 39	99.98 2

patch_mono-2		99.26 92	99.62 6	98.16 355	99.81 57	94.59 428	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	99.40 175	99.46 247	99.30 138	99.56 146	99.52 130	98.52 122	99.44 188	99.27 372	98.41 93	99.86 181	99.10 120	99.59 168	99.04 301

xiu_mvs_v2_base		99.26 92	99.25 77	99.29 201	99.53 214	98.91 203	99.02 390	99.45 242	98.80 94	99.71 107	99.26 374	98.94 34	99.98 20	99.34 81	99.23 200	98.98 308

CANet		99.25 96	99.14 94	99.59 113	99.41 262	99.16 155	99.35 293	99.57 85	98.82 89	99.51 174	99.61 263	96.46 180	99.95 76	99.59 45	99.98 4	99.65 169

3Dnovator	97.25 9	99.24 97	99.05 111	99.81 60	99.12 343	99.66 71	99.84 12	99.74 13	99.09 55	98.92 311	99.90 33	95.94 204	99.98 20	98.95 140	99.92 39	99.79 92

LuminaMVS		99.23 98	99.10 99	99.61 109	99.35 279	99.31 135	99.46 235	99.13 365	98.61 113	99.86 53	99.89 41	96.41 185	99.91 135	99.67 37	99.51 174	99.63 181

dcpmvs_2		99.23 98	99.58 9	98.16 355	99.83 47	94.68 425	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	99.03 116	99.79 68	98.42 434	99.48 111	99.55 161	99.51 151	99.39 22	99.78 81	99.93 10	94.80 259	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	98.85 214	99.32 302	99.48 198	98.50 124	99.81 69	99.81 128	96.82 159	99.88 168	99.40 71	99.12 215	99.71 143

CHOSEN 1792x2688		99.19 101	99.10 99	99.45 163	99.89 8	98.52 254	99.39 275	99.94 1	98.73 102	99.11 274	99.89 41	95.50 225	99.94 92	99.50 57	99.97 9	99.89 29

F-COLMAP		99.19 101	99.04 113	99.64 101	99.78 70	99.27 143	99.42 258	99.54 109	97.29 301	99.41 199	99.59 268	98.42 91	99.93 110	98.19 246	99.69 153	99.73 122

viewcassd2359sk11		99.18 104	99.08 105	99.49 152	99.65 155	98.95 193	99.48 221	99.51 151	98.10 191	99.72 102	99.87 65	97.13 138	99.84 196	99.13 114	99.14 208	99.69 149

viewmanbaseed2359cas		99.18 104	99.07 108	99.50 149	99.62 172	99.01 177	99.50 196	99.52 130	98.25 160	99.68 113	99.82 113	96.93 152	99.80 233	99.15 113	99.11 217	99.70 146

EIA-MVS		99.18 104	99.09 104	99.45 163	99.49 237	99.18 152	99.67 75	99.53 125	97.66 259	99.40 204	99.44 322	98.10 107	99.81 226	98.94 141	99.62 165	99.35 267

3Dnovator+	97.12 13	99.18 104	98.97 136	99.82 57	99.17 335	99.68 64	99.81 20	99.51 151	99.20 33	98.72 339	99.89 41	95.68 219	99.97 29	98.86 158	99.86 87	99.81 79

MVSFormer		99.17 108	99.12 97	99.29 201	99.51 223	98.94 197	99.88 4	99.46 231	97.55 271	99.80 74	99.65 242	97.39 125	99.28 360	99.03 128	99.85 94	99.65 169

sss		99.17 108	99.05 111	99.53 133	99.62 172	98.97 183	99.36 288	99.62 51	97.83 235	99.67 119	99.65 242	97.37 128	99.95 76	99.19 103	99.19 203	99.68 155

SSM_0404		99.16 110	99.06 109	99.44 168	99.65 155	98.96 187	99.49 213	99.50 174	98.14 180	99.62 145	99.85 80	96.85 154	99.85 187	99.19 103	99.26 196	99.52 220

guyue		99.16 110	99.04 113	99.52 139	99.69 127	98.92 202	99.59 120	98.81 412	98.73 102	99.90 34	99.87 65	95.34 232	99.88 168	99.66 40	99.81 120	99.74 113

test_cas_vis1_n_1920		99.16 110	99.01 129	99.61 109	99.81 57	98.86 213	99.65 88	99.64 42	99.39 22	99.97 25	99.94 6	93.20 328	99.98 20	99.55 50	99.91 46	99.99 1

DP-MVS		99.16 110	98.95 144	99.78 71	99.77 78	99.53 101	99.41 263	99.50 174	97.03 328	99.04 291	99.88 52	97.39 125	99.92 123	98.66 190	99.90 57	99.87 40

E2		99.15 114	99.03 116	99.49 152	99.65 155	98.93 201	99.49 213	99.52 130	98.14 180	99.72 102	99.88 52	96.57 175	99.84 196	99.17 109	99.13 211	99.72 132

E3		99.15 114	99.03 116	99.49 152	99.62 172	98.91 203	99.49 213	99.52 130	98.13 183	99.72 102	99.88 52	96.61 170	99.84 196	99.17 109	99.13 211	99.72 132

SymmetryMVS		99.15 114	99.02 124	99.52 139	99.72 111	98.83 219	99.65 88	99.34 307	99.10 48	99.84 56	99.76 183	95.80 213	99.99 4	99.30 89	98.72 256	99.73 122

MGCNet		99.15 114	98.96 140	99.73 83	98.92 380	99.37 123	99.37 282	96.92 462	99.51 2	99.66 124	99.78 170	96.69 166	99.97 29	99.84 28	99.97 9	99.84 53

casdiffmvs_mvg		99.15 114	99.02 124	99.55 124	99.66 147	99.09 165	99.64 95	99.56 90	98.26 155	99.45 183	99.87 65	96.03 198	99.81 226	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		99.15 114	99.02 124	99.53 133	99.66 147	99.14 160	99.72 53	99.48 198	98.35 142	99.42 194	99.84 95	96.07 195	99.79 239	99.51 56	99.14 208	99.67 159

diffmvs		99.14 120	99.02 124	99.51 144	99.61 183	98.96 187	99.28 318	99.49 186	98.46 128	99.72 102	99.71 206	96.50 178	99.88 168	99.31 86	99.11 217	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		99.14 120	98.99 132	99.59 113	99.58 193	99.41 120	99.16 357	99.44 251	98.45 130	99.19 261	99.49 306	98.08 109	99.89 163	97.73 296	99.75 142	99.48 237

SSM_0407		99.13 122	99.03 116	99.43 171	99.62 172	98.88 206	99.51 186	99.50 174	98.14 180	99.37 210	99.85 80	96.85 154	99.83 212	99.19 103	99.25 197	99.60 189

CDPH-MVS		99.13 122	98.91 152	99.80 64	99.75 92	99.71 58	99.15 360	99.41 267	96.60 360	99.60 153	99.55 283	98.83 47	99.90 148	97.48 320	99.83 113	99.78 98

casdiffmvs		99.13 122	98.98 135	99.56 122	99.65 155	99.16 155	99.56 146	99.50 174	98.33 145	99.41 199	99.86 73	95.92 205	99.83 212	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		99.13 122	99.03 116	99.45 163	99.46 247	98.87 210	99.12 366	99.26 344	98.03 212	99.79 76	99.65 242	97.02 147	99.85 187	99.02 130	99.90 57	99.65 169
jason: jason.
lupinMVS		99.13 122	99.01 129	99.46 162	99.51 223	98.94 197	99.05 382	99.16 361	97.86 228	99.80 74	99.56 280	97.39 125	99.86 181	98.94 141	99.85 94	99.58 204

EPP-MVSNet		99.13 122	98.99 132	99.53 133	99.65 155	99.06 171	99.81 20	99.33 315	97.43 288	99.60 153	99.88 52	97.14 137	99.84 196	99.13 114	98.94 235	99.69 149

MG-MVS		99.13 122	99.02 124	99.45 163	99.57 198	98.63 240	99.07 376	99.34 307	98.99 69	99.61 150	99.82 113	97.98 113	99.87 175	97.00 351	99.80 125	99.85 46

KinetiMVS		99.12 129	98.92 149	99.70 87	99.67 134	99.40 121	99.67 75	99.63 46	98.73 102	99.94 28	99.81 128	94.54 282	99.96 41	98.40 226	99.93 33	99.74 113

BP-MVS1		99.12 129	98.94 146	99.65 95	99.51 223	99.30 138	99.67 75	98.92 393	98.48 126	99.84 56	99.69 221	94.96 247	99.92 123	99.62 44	99.79 132	99.71 143

CHOSEN 280x420		99.12 129	99.13 95	99.08 226	99.66 147	97.89 296	98.43 451	99.71 16	98.88 83	99.62 145	99.76 183	96.63 169	99.70 280	99.46 67	99.99 1	99.66 163

DP-MVS Recon		99.12 129	98.95 144	99.65 95	99.74 100	99.70 60	99.27 323	99.57 85	96.40 376	99.42 194	99.68 229	98.75 60	99.80 233	97.98 269	99.72 148	99.44 253

Vis-MVSNet		99.12 129	98.97 136	99.56 122	99.78 70	99.10 164	99.68 72	99.66 32	98.49 125	99.86 53	99.87 65	94.77 264	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		99.12 129	99.08 105	99.24 211	99.46 247	98.55 248	99.51 186	99.46 231	98.09 192	99.45 183	99.82 113	98.34 97	99.51 319	98.70 183	98.93 236	99.67 159

viewdifsd2359ckpt07		99.11 135	99.00 131	99.43 171	99.63 164	98.73 230	99.45 238	99.54 109	98.33 145	99.62 145	99.81 128	96.17 192	99.87 175	99.27 95	99.14 208	99.69 149

SDMVSNet		99.11 135	98.90 154	99.75 77	99.81 57	99.59 88	99.81 20	99.65 39	98.78 98	99.64 138	99.88 52	94.56 279	99.93 110	99.67 37	98.26 286	99.72 132

VNet		99.11 135	98.90 154	99.73 83	99.52 220	99.56 94	99.41 263	99.39 277	99.01 64	99.74 95	99.78 170	95.56 223	99.92 123	99.52 55	98.18 294	99.72 132

CPTT-MVS		99.11 135	98.90 154	99.74 80	99.80 63	99.46 114	99.59 120	99.49 186	97.03 328	99.63 141	99.69 221	97.27 133	99.96 41	97.82 283	99.84 102	99.81 79

HyFIR lowres test		99.11 135	98.92 149	99.65 95	99.90 4	99.37 123	99.02 390	99.91 3	97.67 258	99.59 156	99.75 188	95.90 207	99.73 263	99.53 53	99.02 231	99.86 42

MVS_Test		99.10 140	98.97 136	99.48 155	99.49 237	99.14 160	99.67 75	99.34 307	97.31 299	99.58 157	99.76 183	97.65 121	99.82 221	98.87 153	99.07 226	99.46 248

AstraMVS		99.09 141	99.03 116	99.25 208	99.66 147	98.13 279	99.57 138	98.24 445	98.82 89	99.91 31	99.88 52	95.81 212	99.90 148	99.72 32	99.67 158	99.74 113

CDS-MVSNet		99.09 141	99.03 116	99.25 208	99.42 257	98.73 230	99.45 238	99.46 231	98.11 188	99.46 182	99.77 179	98.01 112	99.37 343	98.70 183	98.92 238	99.66 163
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmacassd2359aftdt		99.08 143	98.94 146	99.50 149	99.66 147	98.96 187	99.51 186	99.54 109	98.27 152	99.42 194	99.89 41	95.88 209	99.80 233	99.20 102	99.11 217	99.76 107

mamba_0408		99.08 143	98.96 140	99.44 168	99.62 172	98.88 206	99.25 334	99.47 220	98.05 203	99.37 210	99.81 128	96.85 154	99.85 187	98.98 133	99.25 197	99.60 189

GDP-MVS		99.08 143	98.89 158	99.64 101	99.53 214	99.34 127	99.64 95	99.48 198	98.32 147	99.77 85	99.66 240	95.14 243	99.93 110	98.97 138	99.50 176	99.64 176

PVSNet_Blended		99.08 143	98.97 136	99.42 173	99.76 82	98.79 225	98.78 426	99.91 3	96.74 345	99.67 119	99.49 306	97.53 122	99.88 168	98.98 133	99.85 94	99.60 189

OMC-MVS		99.08 143	99.04 113	99.20 215	99.67 134	98.22 274	99.28 318	99.52 130	98.07 197	99.66 124	99.81 128	97.79 117	99.78 245	97.79 287	99.81 120	99.60 189

viewdifsd2359ckpt13		99.06 148	98.93 148	99.45 163	99.63 164	98.96 187	99.50 196	99.51 151	97.83 235	99.28 234	99.80 146	96.68 168	99.71 273	99.05 125	99.12 215	99.68 155

SSM_04072		99.06 148	98.96 140	99.35 184	99.62 172	98.88 206	99.25 334	99.47 220	98.05 203	99.37 210	99.81 128	96.85 154	99.58 311	98.98 133	99.25 197	99.60 189

mvsmamba		99.06 148	98.96 140	99.36 182	99.47 245	98.64 239	99.70 58	99.05 377	97.61 264	99.65 133	99.83 100	96.54 176	99.92 123	99.19 103	99.62 165	99.51 229

WTY-MVS		99.06 148	98.88 161	99.61 109	99.62 172	99.16 155	99.37 282	99.56 90	98.04 210	99.53 170	99.62 259	96.84 158	99.94 92	98.85 160	98.49 271	99.72 132

IS-MVSNet		99.05 152	98.87 162	99.57 120	99.73 107	99.32 131	99.75 42	99.20 356	98.02 215	99.56 161	99.86 73	96.54 176	99.67 288	98.09 257	99.13 211	99.73 122

PAPM_NR		99.04 153	98.84 170	99.66 91	99.74 100	99.44 116	99.39 275	99.38 285	97.70 254	99.28 234	99.28 369	98.34 97	99.85 187	96.96 355	99.45 179	99.69 149

API-MVS		99.04 153	99.03 116	99.06 229	99.40 267	99.31 135	99.55 161	99.56 90	98.54 120	99.33 224	99.39 338	98.76 57	99.78 245	96.98 353	99.78 134	98.07 432

mvs_anonymous		99.03 155	98.99 132	99.16 219	99.38 272	98.52 254	99.51 186	99.38 285	97.79 241	99.38 208	99.81 128	97.30 131	99.45 325	99.35 76	98.99 233	99.51 229

sasdasda		99.02 156	98.86 165	99.51 144	99.42 257	99.32 131	99.80 25	99.48 198	98.63 110	99.31 226	98.81 419	97.09 142	99.75 254	99.27 95	97.90 305	99.47 243

train_agg		99.02 156	98.77 177	99.77 74	99.67 134	99.65 75	99.05 382	99.41 267	96.28 380	98.95 307	99.49 306	98.76 57	99.91 135	97.63 304	99.72 148	99.75 109

canonicalmvs		99.02 156	98.86 165	99.51 144	99.42 257	99.32 131	99.80 25	99.48 198	98.63 110	99.31 226	98.81 419	97.09 142	99.75 254	99.27 95	97.90 305	99.47 243

PLC	97.94 4	99.02 156	98.85 168	99.53 133	99.66 147	99.01 177	99.24 339	99.52 130	96.85 340	99.27 240	99.48 312	98.25 101	99.91 135	97.76 292	99.62 165	99.65 169
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
viewdifsd2359ckpt09		99.01 160	98.87 162	99.40 175	99.62 172	98.79 225	99.44 245	99.51 151	97.76 245	99.35 219	99.69 221	96.42 184	99.75 254	98.97 138	99.11 217	99.66 163

viewmambaseed2359dif		99.01 160	98.90 154	99.32 191	99.58 193	98.51 256	99.33 299	99.54 109	97.85 231	99.44 188	99.85 80	96.01 199	99.79 239	99.41 70	99.13 211	99.67 159

MGCFI-Net		99.01 160	98.85 168	99.50 149	99.42 257	99.26 144	99.82 16	99.48 198	98.60 115	99.28 234	98.81 419	97.04 146	99.76 251	99.29 91	97.87 308	99.47 243

AdaColmap		99.01 160	98.80 173	99.66 91	99.56 202	99.54 98	99.18 355	99.70 18	98.18 173	99.35 219	99.63 254	96.32 187	99.90 148	97.48 320	99.77 137	99.55 211

1112_ss		98.98 164	98.77 177	99.59 113	99.68 132	99.02 175	99.25 334	99.48 198	97.23 307	99.13 270	99.58 272	96.93 152	99.90 148	98.87 153	98.78 253	99.84 53

MSDG		98.98 164	98.80 173	99.53 133	99.76 82	99.19 150	98.75 429	99.55 100	97.25 304	99.47 180	99.77 179	97.82 116	99.87 175	96.93 358	99.90 57	99.54 213

CANet_DTU		98.97 166	98.87 162	99.25 208	99.33 285	98.42 267	99.08 375	99.30 334	99.16 37	99.43 191	99.75 188	95.27 235	99.97 29	98.56 210	99.95 23	99.36 266

DPM-MVS		98.95 167	98.71 185	99.66 91	99.63 164	99.55 96	98.64 440	99.10 368	97.93 221	99.42 194	99.55 283	98.67 72	99.80 233	95.80 392	99.68 156	99.61 186

114514_t		98.93 168	98.67 189	99.72 86	99.85 31	99.53 101	99.62 106	99.59 73	92.65 447	99.71 107	99.78 170	98.06 110	99.90 148	98.84 163	99.91 46	99.74 113

PS-MVSNAJss		98.92 169	98.92 149	98.90 256	98.78 401	98.53 250	99.78 32	99.54 109	98.07 197	99.00 298	99.76 183	99.01 20	99.37 343	99.13 114	97.23 348	98.81 318

RRT-MVS		98.91 170	98.75 179	99.39 180	99.46 247	98.61 244	99.76 37	99.50 174	98.06 201	99.81 69	99.88 52	93.91 311	99.94 92	99.11 117	99.27 194	99.61 186

Test_1112_low_res		98.89 171	98.66 192	99.57 120	99.69 127	98.95 193	99.03 387	99.47 220	96.98 330	99.15 268	99.23 377	96.77 163	99.89 163	98.83 166	98.78 253	99.86 42

Elysia		98.88 172	98.65 194	99.58 116	99.58 193	99.34 127	99.65 88	99.52 130	98.26 155	99.83 64	99.87 65	93.37 322	99.90 148	97.81 285	99.91 46	99.49 234

StellarMVS		98.88 172	98.65 194	99.58 116	99.58 193	99.34 127	99.65 88	99.52 130	98.26 155	99.83 64	99.87 65	93.37 322	99.90 148	97.81 285	99.91 46	99.49 234

test_fmvs1		98.88 172	98.79 176	99.16 219	99.69 127	97.61 312	99.55 161	99.49 186	99.32 29	99.98 13	99.91 26	91.41 376	99.96 41	99.82 29	99.92 39	99.90 25

AllTest		98.87 175	98.72 183	99.31 193	99.86 25	98.48 261	99.56 146	99.61 60	97.85 231	99.36 216	99.85 80	95.95 202	99.85 187	96.66 371	99.83 113	99.59 200

UGNet		98.87 175	98.69 187	99.40 175	99.22 318	98.72 232	99.44 245	99.68 24	99.24 32	99.18 265	99.42 326	92.74 338	99.96 41	99.34 81	99.94 31	99.53 219
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)		98.87 175	98.72 183	99.31 193	99.71 117	98.88 206	99.80 25	99.44 251	97.91 223	99.36 216	99.78 170	95.49 226	99.43 334	97.91 273	99.11 217	99.62 184

IMVS_0407		98.86 178	98.91 152	98.72 289	99.55 206	96.93 352	99.50 196	99.44 251	98.05 203	99.66 124	99.80 146	97.13 138	99.65 296	98.15 252	98.92 238	99.60 189

IMVS_0403		98.86 178	98.89 158	98.78 284	99.55 206	96.93 352	99.58 130	99.44 251	98.05 203	99.68 113	99.80 146	96.81 160	99.80 233	98.15 252	98.92 238	99.60 189

test_yl		98.86 178	98.63 197	99.54 125	99.49 237	99.18 152	99.50 196	99.07 374	98.22 166	99.61 150	99.51 300	95.37 230	99.84 196	98.60 201	98.33 278	99.59 200

DCV-MVSNet		98.86 178	98.63 197	99.54 125	99.49 237	99.18 152	99.50 196	99.07 374	98.22 166	99.61 150	99.51 300	95.37 230	99.84 196	98.60 201	98.33 278	99.59 200

EPNet		98.86 178	98.71 185	99.30 198	97.20 454	98.18 275	99.62 106	98.91 398	99.28 31	98.63 358	99.81 128	95.96 201	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		98.86 178	98.80 173	99.03 233	99.76 82	98.79 225	99.28 318	99.91 3	97.42 290	99.67 119	99.37 344	97.53 122	99.88 168	98.98 133	97.29 346	98.42 410

ab-mvs		98.86 178	98.63 197	99.54 125	99.64 160	99.19 150	99.44 245	99.54 109	97.77 244	99.30 230	99.81 128	94.20 296	99.93 110	99.17 109	98.82 250	99.49 234

MAR-MVS		98.86 178	98.63 197	99.54 125	99.37 275	99.66 71	99.45 238	99.54 109	96.61 357	99.01 294	99.40 334	97.09 142	99.86 181	97.68 303	99.53 173	99.10 289
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	98.86 178	98.75 179	99.17 218	99.88 13	98.53 250	99.34 296	99.59 73	97.55 271	98.70 346	99.89 41	95.83 210	99.90 148	98.10 256	99.90 57	99.08 294
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 187	98.62 202	99.53 133	99.61 183	99.08 168	99.80 25	99.51 151	97.10 320	99.31 226	99.78 170	95.23 240	99.77 247	98.21 244	99.03 229	99.75 109

HY-MVS	97.30 7	98.85 187	98.64 196	99.47 160	99.42 257	99.08 168	99.62 106	99.36 295	97.39 293	99.28 234	99.68 229	96.44 182	99.92 123	98.37 230	98.22 289	99.40 260

PVSNet	96.02 17	98.85 187	98.84 170	98.89 260	99.73 107	97.28 322	98.32 457	99.60 67	97.86 228	99.50 175	99.57 277	96.75 164	99.86 181	98.56 210	99.70 152	99.54 213

PatchMatch-RL		98.84 190	98.62 202	99.52 139	99.71 117	99.28 141	99.06 380	99.77 12	97.74 249	99.50 175	99.53 292	95.41 228	99.84 196	97.17 344	99.64 162	99.44 253

Effi-MVS+		98.81 191	98.59 208	99.48 155	99.46 247	99.12 163	98.08 464	99.50 174	97.50 279	99.38 208	99.41 330	96.37 186	99.81 226	99.11 117	98.54 268	99.51 229

alignmvs		98.81 191	98.56 211	99.58 116	99.43 255	99.42 118	99.51 186	98.96 388	98.61 113	99.35 219	98.92 414	94.78 261	99.77 247	99.35 76	98.11 299	99.54 213

DeepPCF-MVS	98.18 3	98.81 191	99.37 44	97.12 413	99.60 189	91.75 455	98.61 441	99.44 251	99.35 25	99.83 64	99.85 80	98.70 69	99.81 226	99.02 130	99.91 46	99.81 79

PMMVS		98.80 194	98.62 202	99.34 185	99.27 303	98.70 233	98.76 428	99.31 329	97.34 296	99.21 255	99.07 393	97.20 136	99.82 221	98.56 210	98.87 245	99.52 220

icg_test_0407_2		98.79 195	98.86 165	98.57 305	99.55 206	96.93 352	99.07 376	99.44 251	98.05 203	99.66 124	99.80 146	97.13 138	99.18 382	98.15 252	98.92 238	99.60 189

viewdifsd2359ckpt11		98.78 196	98.74 181	98.89 260	99.67 134	97.04 341	99.50 196	99.58 78	98.26 155	99.56 161	99.90 33	94.36 289	99.87 175	99.49 61	98.32 282	99.77 100

viewmsd2359difaftdt		98.78 196	98.74 181	98.90 256	99.67 134	97.04 341	99.50 196	99.58 78	98.26 155	99.56 161	99.90 33	94.36 289	99.87 175	99.49 61	98.32 282	99.77 100

Effi-MVS+-dtu		98.78 196	98.89 158	98.47 323	99.33 285	96.91 357	99.57 138	99.30 334	98.47 127	99.41 199	98.99 404	96.78 162	99.74 257	98.73 180	99.38 183	98.74 333

FIs		98.78 196	98.63 197	99.23 213	99.18 327	99.54 98	99.83 15	99.59 73	98.28 150	98.79 333	99.81 128	96.75 164	99.37 343	99.08 122	96.38 364	98.78 321

Fast-Effi-MVS+-dtu		98.77 200	98.83 172	98.60 300	99.41 262	96.99 347	99.52 177	99.49 186	98.11 188	99.24 247	99.34 354	96.96 151	99.79 239	97.95 271	99.45 179	99.02 304

sd_testset		98.75 201	98.57 209	99.29 201	99.81 57	98.26 272	99.56 146	99.62 51	98.78 98	99.64 138	99.88 52	92.02 360	99.88 168	99.54 51	98.26 286	99.72 132

FA-MVS(test-final)		98.75 201	98.53 213	99.41 174	99.55 206	99.05 173	99.80 25	99.01 382	96.59 362	99.58 157	99.59 268	95.39 229	99.90 148	97.78 288	99.49 177	99.28 275

FC-MVSNet-test		98.75 201	98.62 202	99.15 223	99.08 354	99.45 115	99.86 11	99.60 67	98.23 165	98.70 346	99.82 113	96.80 161	99.22 374	99.07 123	96.38 364	98.79 319

XVG-OURS		98.73 204	98.68 188	98.88 263	99.70 122	97.73 303	98.92 412	99.55 100	98.52 122	99.45 183	99.84 95	95.27 235	99.91 135	98.08 261	98.84 248	99.00 305

Fast-Effi-MVS+		98.70 205	98.43 218	99.51 144	99.51 223	99.28 141	99.52 177	99.47 220	96.11 396	99.01 294	99.34 354	96.20 191	99.84 196	97.88 275	98.82 250	99.39 261

XVG-OURS-SEG-HR		98.69 206	98.62 202	98.89 260	99.71 117	97.74 302	99.12 366	99.54 109	98.44 133	99.42 194	99.71 206	94.20 296	99.92 123	98.54 214	98.90 244	99.00 305

1314		98.68 207	98.54 212	99.11 225	98.89 384	98.65 237	99.27 323	99.49 186	96.89 338	97.99 398	99.56 280	97.72 120	99.83 212	97.74 295	99.27 194	98.84 317

VortexMVS		98.67 208	98.66 192	98.68 295	99.62 172	97.96 290	99.59 120	99.41 267	98.13 183	99.31 226	99.70 210	95.48 227	99.27 363	99.40 71	97.32 345	98.79 319

EI-MVSNet		98.67 208	98.67 189	98.68 295	99.35 279	97.97 288	99.50 196	99.38 285	96.93 337	99.20 258	99.83 100	97.87 114	99.36 347	98.38 228	97.56 324	98.71 337

test_djsdf		98.67 208	98.57 209	98.98 239	98.70 415	98.91 203	99.88 4	99.46 231	97.55 271	99.22 252	99.88 52	95.73 217	99.28 360	99.03 128	97.62 319	98.75 329

QAPM		98.67 208	98.30 228	99.80 64	99.20 321	99.67 68	99.77 34	99.72 14	94.74 423	98.73 338	99.90 33	95.78 215	99.98 20	96.96 355	99.88 76	99.76 107

nrg030		98.64 212	98.42 219	99.28 205	99.05 360	99.69 63	99.81 20	99.46 231	98.04 210	99.01 294	99.82 113	96.69 166	99.38 340	99.34 81	94.59 409	98.78 321

test_vis1_n_1920		98.63 213	98.40 221	99.31 193	99.86 25	97.94 295	99.67 75	99.62 51	99.43 17	99.99 2	99.91 26	87.29 427	100.00 1	99.92 24	99.92 39	99.98 2

PAPR		98.63 213	98.34 224	99.51 144	99.40 267	99.03 174	98.80 424	99.36 295	96.33 377	99.00 298	99.12 391	98.46 87	99.84 196	95.23 407	99.37 190	99.66 163

CVMVSNet		98.57 215	98.67 189	98.30 343	99.35 279	95.59 399	99.50 196	99.55 100	98.60 115	99.39 206	99.83 100	94.48 285	99.45 325	98.75 177	98.56 266	99.85 46

IMVS_0404		98.53 216	98.52 214	98.55 311	99.55 206	96.93 352	99.20 351	99.44 251	98.05 203	98.96 305	99.80 146	94.66 274	99.13 390	98.15 252	98.92 238	99.60 189

MVSTER		98.49 217	98.32 226	99.00 237	99.35 279	99.02 175	99.54 166	99.38 285	97.41 291	99.20 258	99.73 199	93.86 313	99.36 347	98.87 153	97.56 324	98.62 381

FE-MVS		98.48 218	98.17 233	99.40 175	99.54 213	98.96 187	99.68 72	98.81 412	95.54 407	99.62 145	99.70 210	93.82 314	99.93 110	97.35 331	99.46 178	99.32 272

OpenMVS	96.50 16	98.47 219	98.12 240	99.52 139	99.04 362	99.53 101	99.82 16	99.72 14	94.56 426	98.08 393	99.88 52	94.73 267	99.98 20	97.47 322	99.76 140	99.06 300

IterMVS-LS		98.46 220	98.42 219	98.58 304	99.59 191	98.00 286	99.37 282	99.43 262	96.94 336	99.07 283	99.59 268	97.87 114	99.03 405	98.32 237	95.62 387	98.71 337
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 221	98.28 229	98.94 246	98.50 431	98.96 187	99.77 34	99.50 174	97.07 322	98.87 320	99.77 179	94.76 265	99.28 360	98.66 190	97.60 320	98.57 396

jajsoiax		98.43 222	98.28 229	98.88 263	98.60 425	98.43 265	99.82 16	99.53 125	98.19 170	98.63 358	99.80 146	93.22 327	99.44 330	99.22 100	97.50 331	98.77 325

tttt0517		98.42 223	98.14 237	99.28 205	99.66 147	98.38 268	99.74 47	96.85 463	97.68 256	99.79 76	99.74 193	91.39 377	99.89 163	98.83 166	99.56 170	99.57 207

BH-untuned		98.42 223	98.36 222	98.59 301	99.49 237	96.70 365	99.27 323	99.13 365	97.24 306	98.80 331	99.38 341	95.75 216	99.74 257	97.07 349	99.16 204	99.33 271

test_fmvs1_n		98.41 225	98.14 237	99.21 214	99.82 53	97.71 308	99.74 47	99.49 186	99.32 29	99.99 2	99.95 3	85.32 441	99.97 29	99.82 29	99.84 102	99.96 7

D2MVS		98.41 225	98.50 215	98.15 358	99.26 306	96.62 371	99.40 271	99.61 60	97.71 251	98.98 301	99.36 347	96.04 197	99.67 288	98.70 183	97.41 341	98.15 428

BH-RMVSNet		98.41 225	98.08 246	99.40 175	99.41 262	98.83 219	99.30 308	98.77 418	97.70 254	98.94 309	99.65 242	92.91 334	99.74 257	96.52 375	99.55 172	99.64 176

mvs_tets		98.40 228	98.23 231	98.91 254	98.67 418	98.51 256	99.66 82	99.53 125	98.19 170	98.65 355	99.81 128	92.75 336	99.44 330	99.31 86	97.48 335	98.77 325

MonoMVSNet		98.38 229	98.47 217	98.12 360	98.59 427	96.19 388	99.72 53	98.79 416	97.89 225	99.44 188	99.52 296	96.13 193	98.90 427	98.64 192	97.54 326	99.28 275

XXY-MVS		98.38 229	98.09 245	99.24 211	99.26 306	99.32 131	99.56 146	99.55 100	97.45 284	98.71 340	99.83 100	93.23 325	99.63 306	98.88 150	96.32 366	98.76 327

ACMM	97.58 5	98.37 231	98.34 224	98.48 318	99.41 262	97.10 332	99.56 146	99.45 242	98.53 121	99.04 291	99.85 80	93.00 330	99.71 273	98.74 178	97.45 336	98.64 372
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 232	98.03 252	99.31 193	99.63 164	98.56 247	99.54 166	96.75 465	97.53 275	99.73 97	99.65 242	91.25 381	99.89 163	98.62 195	99.56 170	99.48 237

tpmrst		98.33 233	98.48 216	97.90 377	99.16 337	94.78 421	99.31 306	99.11 367	97.27 302	99.45 183	99.59 268	95.33 233	99.84 196	98.48 217	98.61 260	99.09 293

baseline1		98.31 234	97.95 261	99.38 181	99.50 235	98.74 229	99.59 120	98.93 390	98.41 135	99.14 269	99.60 266	94.59 277	99.79 239	98.48 217	93.29 429	99.61 186

PatchmatchNet		98.31 234	98.36 222	98.19 353	99.16 337	95.32 410	99.27 323	98.92 393	97.37 294	99.37 210	99.58 272	94.90 254	99.70 280	97.43 326	99.21 201	99.54 213
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 236	97.98 257	99.26 207	99.57 198	98.16 276	99.41 263	98.55 437	96.03 401	99.19 261	99.74 193	91.87 363	99.92 123	99.16 112	98.29 285	99.70 146

VPA-MVSNet		98.29 237	97.95 261	99.30 198	99.16 337	99.54 98	99.50 196	99.58 78	98.27 152	99.35 219	99.37 344	92.53 348	99.65 296	99.35 76	94.46 410	98.72 335

UniMVSNet (Re)		98.29 237	98.00 255	99.13 224	99.00 367	99.36 126	99.49 213	99.51 151	97.95 219	98.97 303	99.13 388	96.30 188	99.38 340	98.36 232	93.34 428	98.66 368

HQP_MVS		98.27 239	98.22 232	98.44 329	99.29 298	96.97 349	99.39 275	99.47 220	98.97 75	99.11 274	99.61 263	92.71 341	99.69 285	97.78 288	97.63 317	98.67 359

UniMVSNet_NR-MVSNet		98.22 240	97.97 258	98.96 242	98.92 380	98.98 180	99.48 221	99.53 125	97.76 245	98.71 340	99.46 319	96.43 183	99.22 374	98.57 207	92.87 436	98.69 346

LPG-MVS_test		98.22 240	98.13 239	98.49 316	99.33 285	97.05 338	99.58 130	99.55 100	97.46 281	99.24 247	99.83 100	92.58 346	99.72 267	98.09 257	97.51 329	98.68 351

RPSCF		98.22 240	98.62 202	96.99 415	99.82 53	91.58 456	99.72 53	99.44 251	96.61 357	99.66 124	99.89 41	95.92 205	99.82 221	97.46 323	99.10 223	99.57 207

ADS-MVSNet		98.20 243	98.08 246	98.56 309	99.33 285	96.48 376	99.23 342	99.15 362	96.24 384	99.10 277	99.67 235	94.11 301	99.71 273	96.81 363	99.05 227	99.48 237

OPM-MVS		98.19 244	98.10 242	98.45 326	98.88 385	97.07 336	99.28 318	99.38 285	98.57 117	99.22 252	99.81 128	92.12 358	99.66 291	98.08 261	97.54 326	98.61 390
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 244	98.16 234	98.27 349	99.30 294	95.55 400	99.07 376	98.97 386	97.57 268	99.43 191	99.57 277	92.72 339	99.74 257	97.58 308	99.20 202	99.52 220

miper_ehance_all_eth		98.18 246	98.10 242	98.41 332	99.23 314	97.72 305	98.72 432	99.31 329	96.60 360	98.88 317	99.29 367	97.29 132	99.13 390	97.60 306	95.99 375	98.38 415

CR-MVSNet		98.17 247	97.93 264	98.87 267	99.18 327	98.49 259	99.22 346	99.33 315	96.96 332	99.56 161	99.38 341	94.33 292	99.00 410	94.83 414	98.58 263	99.14 286

miper_enhance_ethall		98.16 248	98.08 246	98.41 332	98.96 376	97.72 305	98.45 450	99.32 325	96.95 334	98.97 303	99.17 383	97.06 145	99.22 374	97.86 278	95.99 375	98.29 419

CLD-MVS		98.16 248	98.10 242	98.33 339	99.29 298	96.82 362	98.75 429	99.44 251	97.83 235	99.13 270	99.55 283	92.92 332	99.67 288	98.32 237	97.69 315	98.48 402
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 250	97.79 276	99.19 216	99.50 235	98.50 258	98.61 441	96.82 464	96.95 334	99.54 168	99.43 324	91.66 372	99.86 181	98.08 261	99.51 174	99.22 283

pmmvs4		98.13 251	97.90 266	98.81 279	98.61 424	98.87 210	98.99 398	99.21 355	96.44 372	99.06 288	99.58 272	95.90 207	99.11 396	97.18 343	96.11 371	98.46 407

WR-MVS_H		98.13 251	97.87 271	98.90 256	99.02 364	98.84 216	99.70 58	99.59 73	97.27 302	98.40 375	99.19 382	95.53 224	99.23 370	98.34 234	93.78 424	98.61 390

c3_l		98.12 253	98.04 251	98.38 336	99.30 294	97.69 309	98.81 423	99.33 315	96.67 350	98.83 326	99.34 354	97.11 141	98.99 411	97.58 308	95.34 394	98.48 402

ACMH	97.28 8	98.10 254	97.99 256	98.44 329	99.41 262	96.96 351	99.60 113	99.56 90	98.09 192	98.15 391	99.91 26	90.87 385	99.70 280	98.88 150	97.45 336	98.67 359
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		98.09 255	97.68 293	99.34 185	99.66 147	98.44 264	99.40 271	99.43 262	93.67 433	99.22 252	99.89 41	90.23 393	99.93 110	99.26 98	98.33 278	99.66 163

CP-MVSNet		98.09 255	97.78 279	99.01 235	98.97 375	99.24 147	99.67 75	99.46 231	97.25 304	98.48 372	99.64 248	93.79 315	99.06 401	98.63 194	94.10 418	98.74 333

dmvs_re		98.08 257	98.16 234	97.85 381	99.55 206	94.67 426	99.70 58	98.92 393	98.15 175	99.06 288	99.35 350	93.67 319	99.25 367	97.77 291	97.25 347	99.64 176

DU-MVS		98.08 257	97.79 276	98.96 242	98.87 388	98.98 180	99.41 263	99.45 242	97.87 227	98.71 340	99.50 303	94.82 257	99.22 374	98.57 207	92.87 436	98.68 351

v2v482		98.06 259	97.77 281	98.92 250	98.90 383	98.82 222	99.57 138	99.36 295	96.65 352	99.19 261	99.35 350	94.20 296	99.25 367	97.72 298	94.97 402	98.69 346

V42		98.06 259	97.79 276	98.86 270	98.98 373	98.84 216	99.69 62	99.34 307	96.53 364	99.30 230	99.37 344	94.67 272	99.32 355	97.57 312	94.66 407	98.42 410

test-LLR		98.06 259	97.90 266	98.55 311	98.79 398	97.10 332	98.67 435	97.75 454	97.34 296	98.61 362	98.85 416	94.45 287	99.45 325	97.25 335	99.38 183	99.10 289

WR-MVS		98.06 259	97.73 288	99.06 229	98.86 391	99.25 146	99.19 353	99.35 302	97.30 300	98.66 349	99.43 324	93.94 308	99.21 379	98.58 204	94.28 414	98.71 337

ACMP	97.20 11	98.06 259	97.94 263	98.45 326	99.37 275	97.01 345	99.44 245	99.49 186	97.54 274	98.45 373	99.79 163	91.95 362	99.72 267	97.91 273	97.49 334	98.62 381
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 264	97.96 259	98.33 339	99.26 306	97.38 319	98.56 446	99.31 329	96.65 352	98.88 317	99.52 296	96.58 173	99.12 395	97.39 328	95.53 391	98.47 404

test1111		98.04 265	98.11 241	97.83 384	99.74 100	93.82 438	99.58 130	95.40 472	99.12 46	99.65 133	99.93 10	90.73 386	99.84 196	99.43 69	99.38 183	99.82 72

ECVR-MVS		98.04 265	98.05 250	98.00 368	99.74 100	94.37 432	99.59 120	94.98 473	99.13 41	99.66 124	99.93 10	90.67 387	99.84 196	99.40 71	99.38 183	99.80 88

EPNet_dtu		98.03 267	97.96 259	98.23 351	98.27 436	95.54 402	99.23 342	98.75 419	99.02 62	97.82 407	99.71 206	96.11 194	99.48 320	93.04 435	99.65 161	99.69 149
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 267	97.76 285	98.84 274	99.39 270	98.98 180	99.40 271	99.38 285	96.67 350	99.07 283	99.28 369	92.93 331	98.98 412	97.10 345	96.65 357	98.56 397

ADS-MVSNet2		98.02 269	98.07 249	97.87 379	99.33 285	95.19 413	99.23 342	99.08 371	96.24 384	99.10 277	99.67 235	94.11 301	98.93 424	96.81 363	99.05 227	99.48 237

HQP-MVS		98.02 269	97.90 266	98.37 337	99.19 324	96.83 360	98.98 401	99.39 277	98.24 162	98.66 349	99.40 334	92.47 350	99.64 300	97.19 341	97.58 322	98.64 372

LTVRE_ROB	97.16 12	98.02 269	97.90 266	98.40 334	99.23 314	96.80 363	99.70 58	99.60 67	97.12 316	98.18 390	99.70 210	91.73 368	99.72 267	98.39 227	97.45 336	98.68 351
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____		98.01 272	97.84 274	98.55 311	99.25 310	97.97 288	98.71 433	99.34 307	96.47 371	98.59 365	99.54 288	95.65 220	99.21 379	97.21 337	95.77 381	98.46 407

DIV-MVS_self_test		98.01 272	97.85 273	98.48 318	99.24 312	97.95 293	98.71 433	99.35 302	96.50 365	98.60 364	99.54 288	95.72 218	99.03 405	97.21 337	95.77 381	98.46 407

miper_lstm_enhance		98.00 274	97.91 265	98.28 348	99.34 284	97.43 317	98.88 416	99.36 295	96.48 369	98.80 331	99.55 283	95.98 200	98.91 425	97.27 334	95.50 392	98.51 400

BH-w/o		98.00 274	97.89 270	98.32 341	99.35 279	96.20 387	99.01 395	98.90 400	96.42 374	98.38 376	99.00 402	95.26 237	99.72 267	96.06 385	98.61 260	99.03 302

v1144		97.98 276	97.69 292	98.85 273	98.87 388	98.66 236	99.54 166	99.35 302	96.27 382	99.23 251	99.35 350	94.67 272	99.23 370	96.73 366	95.16 398	98.68 351

EU-MVSNet		97.98 276	98.03 252	97.81 387	98.72 412	96.65 370	99.66 82	99.66 32	98.09 192	98.35 378	99.82 113	95.25 238	98.01 448	97.41 327	95.30 395	98.78 321

tpmvs		97.98 276	98.02 254	97.84 383	99.04 362	94.73 422	99.31 306	99.20 356	96.10 400	98.76 336	99.42 326	94.94 249	99.81 226	96.97 354	98.45 272	98.97 309

tt0805		97.97 279	97.77 281	98.57 305	99.59 191	96.61 372	99.45 238	99.08 371	98.21 168	98.88 317	99.80 146	88.66 411	99.70 280	98.58 204	97.72 314	99.39 261

NR-MVSNet		97.97 279	97.61 302	99.02 234	98.87 388	99.26 144	99.47 231	99.42 264	97.63 261	97.08 426	99.50 303	95.07 245	99.13 390	97.86 278	93.59 425	98.68 351

v8		97.95 281	97.63 300	98.93 248	98.95 377	98.81 224	99.80 25	99.41 267	96.03 401	99.10 277	99.42 326	94.92 252	99.30 358	96.94 357	94.08 419	98.66 368

Patchmatch-test		97.93 282	97.65 296	98.77 285	99.18 327	97.07 336	99.03 387	99.14 364	96.16 391	98.74 337	99.57 277	94.56 279	99.72 267	93.36 431	99.11 217	99.52 220

PS-CasMVS		97.93 282	97.59 304	98.95 244	98.99 370	99.06 171	99.68 72	99.52 130	97.13 314	98.31 380	99.68 229	92.44 354	99.05 402	98.51 215	94.08 419	98.75 329

TranMVSNet+NR-MVSNet		97.93 282	97.66 295	98.76 286	98.78 401	98.62 242	99.65 88	99.49 186	97.76 245	98.49 371	99.60 266	94.23 295	98.97 419	98.00 268	92.90 434	98.70 342

test_vis1_n		97.92 285	97.44 326	99.34 185	99.53 214	98.08 282	99.74 47	99.49 186	99.15 38	100.00 1	99.94 6	79.51 463	99.98 20	99.88 26	99.76 140	99.97 4

v144192		97.92 285	97.60 303	98.87 267	98.83 395	98.65 237	99.55 161	99.34 307	96.20 387	99.32 225	99.40 334	94.36 289	99.26 366	96.37 382	95.03 401	98.70 342

ACMH+	97.24 10	97.92 285	97.78 279	98.32 341	99.46 247	96.68 369	99.56 146	99.54 109	98.41 135	97.79 409	99.87 65	90.18 394	99.66 291	98.05 265	97.18 351	98.62 381

LFMVS		97.90 288	97.35 338	99.54 125	99.52 220	99.01 177	99.39 275	98.24 445	97.10 320	99.65 133	99.79 163	84.79 444	99.91 135	99.28 92	98.38 275	99.69 149

reproduce_monomvs		97.89 289	97.87 271	97.96 372	99.51 223	95.45 405	99.60 113	99.25 346	99.17 36	98.85 325	99.49 306	89.29 403	99.64 300	99.35 76	96.31 367	98.78 321

Anonymous20231211		97.88 290	97.54 308	98.90 256	99.71 117	98.53 250	99.48 221	99.57 85	94.16 429	98.81 329	99.68 229	93.23 325	99.42 336	98.84 163	94.42 412	98.76 327

OurMVSNet-221017-0		97.88 290	97.77 281	98.19 353	98.71 414	96.53 374	99.88 4	99.00 383	97.79 241	98.78 334	99.94 6	91.68 369	99.35 350	97.21 337	96.99 355	98.69 346

v7n		97.87 292	97.52 310	98.92 250	98.76 408	98.58 246	99.84 12	99.46 231	96.20 387	98.91 312	99.70 210	94.89 255	99.44 330	96.03 386	93.89 422	98.75 329

baseline2		97.87 292	97.55 305	98.82 276	99.18 327	98.02 285	99.41 263	96.58 469	96.97 331	96.51 433	99.17 383	93.43 320	99.57 312	97.71 299	99.03 229	98.86 315

thres600view7		97.86 294	97.51 312	98.92 250	99.72 111	97.95 293	99.59 120	98.74 422	97.94 220	99.27 240	98.62 427	91.75 366	99.86 181	93.73 427	98.19 293	98.96 311

UBG		97.85 295	97.48 315	98.95 244	99.25 310	97.64 310	99.24 339	98.74 422	97.90 224	98.64 356	98.20 444	88.65 412	99.81 226	98.27 240	98.40 273	99.42 255

cl22		97.85 295	97.64 299	98.48 318	99.09 351	97.87 297	98.60 443	99.33 315	97.11 319	98.87 320	99.22 378	92.38 355	99.17 384	98.21 244	95.99 375	98.42 410

v10		97.85 295	97.52 310	98.86 270	98.99 370	98.67 235	99.75 42	99.41 267	95.70 405	98.98 301	99.41 330	94.75 266	99.23 370	96.01 388	94.63 408	98.67 359

GA-MVS		97.85 295	97.47 318	99.00 237	99.38 272	97.99 287	98.57 444	99.15 362	97.04 327	98.90 314	99.30 365	89.83 397	99.38 340	96.70 368	98.33 278	99.62 184

testing3-2		97.84 299	97.70 291	98.24 350	99.53 214	95.37 409	99.55 161	98.67 432	98.46 128	99.27 240	99.34 354	86.58 431	99.83 212	99.32 84	98.63 259	99.52 220

tfpnnormal		97.84 299	97.47 318	98.98 239	99.20 321	99.22 149	99.64 95	99.61 60	96.32 378	98.27 384	99.70 210	93.35 324	99.44 330	95.69 395	95.40 393	98.27 420

VPNet		97.84 299	97.44 326	99.01 235	99.21 319	98.94 197	99.48 221	99.57 85	98.38 137	99.28 234	99.73 199	88.89 406	99.39 338	99.19 103	93.27 430	98.71 337

LCM-MVSNet-Re		97.83 302	98.15 236	96.87 421	99.30 294	92.25 453	99.59 120	98.26 443	97.43 288	96.20 437	99.13 388	96.27 189	98.73 434	98.17 249	98.99 233	99.64 176

XVG-ACMP-BASELINE		97.83 302	97.71 290	98.20 352	99.11 345	96.33 381	99.41 263	99.52 130	98.06 201	99.05 290	99.50 303	89.64 400	99.73 263	97.73 296	97.38 343	98.53 398

IterMVS		97.83 302	97.77 281	98.02 365	99.58 193	96.27 384	99.02 390	99.48 198	97.22 308	98.71 340	99.70 210	92.75 336	99.13 390	97.46 323	96.00 374	98.67 359
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 305	97.75 286	98.06 362	99.57 198	96.36 380	99.02 390	99.49 186	97.18 310	98.71 340	99.72 203	92.72 339	99.14 387	97.44 325	95.86 380	98.67 359

EPMVS		97.82 305	97.65 296	98.35 338	98.88 385	95.98 391	99.49 213	94.71 475	97.57 268	99.26 245	99.48 312	92.46 353	99.71 273	97.87 277	99.08 225	99.35 267

MVP-Stereo		97.81 307	97.75 286	97.99 369	97.53 447	96.60 373	98.96 405	98.85 407	97.22 308	97.23 420	99.36 347	95.28 234	99.46 323	95.51 399	99.78 134	97.92 445
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 307	97.44 326	98.91 254	98.88 385	98.68 234	99.51 186	99.34 307	96.18 389	99.20 258	99.34 354	94.03 305	99.36 347	95.32 405	95.18 397	98.69 346

ttmdpeth		97.80 309	97.63 300	98.29 344	98.77 406	97.38 319	99.64 95	99.36 295	98.78 98	96.30 436	99.58 272	92.34 357	99.39 338	98.36 232	95.58 388	98.10 430

v1921920		97.80 309	97.45 321	98.84 274	98.80 397	98.53 250	99.52 177	99.34 307	96.15 393	99.24 247	99.47 315	93.98 307	99.29 359	95.40 403	95.13 399	98.69 346

v148		97.79 311	97.55 305	98.50 315	98.74 409	97.72 305	99.54 166	99.33 315	96.26 383	98.90 314	99.51 300	94.68 271	99.14 387	97.83 282	93.15 433	98.63 379

thres400		97.77 312	97.38 334	98.92 250	99.69 127	97.96 290	99.50 196	98.73 428	97.83 235	99.17 266	98.45 434	91.67 370	99.83 212	93.22 432	98.18 294	98.96 311

thres100view900		97.76 313	97.45 321	98.69 294	99.72 111	97.86 299	99.59 120	98.74 422	97.93 221	99.26 245	98.62 427	91.75 366	99.83 212	93.22 432	98.18 294	98.37 416

PEN-MVS		97.76 313	97.44 326	98.72 289	98.77 406	98.54 249	99.78 32	99.51 151	97.06 324	98.29 383	99.64 248	92.63 345	98.89 428	98.09 257	93.16 432	98.72 335

Baseline_NR-MVSNet		97.76 313	97.45 321	98.68 295	99.09 351	98.29 270	99.41 263	98.85 407	95.65 406	98.63 358	99.67 235	94.82 257	99.10 398	98.07 264	92.89 435	98.64 372

TR-MVS		97.76 313	97.41 332	98.82 276	99.06 357	97.87 297	98.87 418	98.56 436	96.63 356	98.68 348	99.22 378	92.49 349	99.65 296	95.40 403	97.79 312	98.95 313

Patchmtry		97.75 317	97.40 333	98.81 279	99.10 348	98.87 210	99.11 372	99.33 315	94.83 421	98.81 329	99.38 341	94.33 292	99.02 407	96.10 384	95.57 389	98.53 398

dp		97.75 317	97.80 275	97.59 400	99.10 348	93.71 441	99.32 302	98.88 403	96.48 369	99.08 282	99.55 283	92.67 344	99.82 221	96.52 375	98.58 263	99.24 281

WBMVS		97.74 319	97.50 313	98.46 324	99.24 312	97.43 317	99.21 348	99.42 264	97.45 284	98.96 305	99.41 330	88.83 407	99.23 370	98.94 141	96.02 372	98.71 337

TAPA-MVS	97.07 15	97.74 319	97.34 341	98.94 246	99.70 122	97.53 313	99.25 334	99.51 151	91.90 449	99.30 230	99.63 254	98.78 53	99.64 300	88.09 459	99.87 79	99.65 169
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 321	97.35 338	98.88 263	99.47 245	97.12 331	99.34 296	98.85 407	98.19 170	99.67 119	99.85 80	82.98 452	99.92 123	99.49 61	98.32 282	99.60 189

MIMVSNet		97.73 321	97.45 321	98.57 305	99.45 253	97.50 315	99.02 390	98.98 385	96.11 396	99.41 199	99.14 387	90.28 389	98.74 433	95.74 393	98.93 236	99.47 243

tfpn200view9		97.72 323	97.38 334	98.72 289	99.69 127	97.96 290	99.50 196	98.73 428	97.83 235	99.17 266	98.45 434	91.67 370	99.83 212	93.22 432	98.18 294	98.37 416

CostFormer		97.72 323	97.73 288	97.71 392	99.15 341	94.02 437	99.54 166	99.02 381	94.67 424	99.04 291	99.35 350	92.35 356	99.77 247	98.50 216	97.94 304	99.34 270

FMVSNet2		97.72 323	97.36 336	98.80 281	99.51 223	98.84 216	99.45 238	99.42 264	96.49 366	98.86 324	99.29 367	90.26 390	98.98 412	96.44 377	96.56 360	98.58 395

test0.0.03 1		97.71 326	97.42 331	98.56 309	98.41 435	97.82 300	98.78 426	98.63 434	97.34 296	98.05 397	98.98 406	94.45 287	98.98 412	95.04 410	97.15 352	98.89 314

h-mvs33		97.70 327	97.28 350	98.97 241	99.70 122	97.27 323	99.36 288	99.45 242	98.94 78	99.66 124	99.64 248	94.93 250	99.99 4	99.48 64	84.36 464	99.65 169

myMVS_eth3d28		97.69 328	97.34 341	98.73 287	99.27 303	97.52 314	99.33 299	98.78 417	98.03 212	98.82 328	98.49 432	86.64 430	99.46 323	98.44 223	98.24 288	99.23 282

v1240		97.69 328	97.32 345	98.79 282	98.85 392	98.43 265	99.48 221	99.36 295	96.11 396	99.27 240	99.36 347	93.76 317	99.24 369	94.46 417	95.23 396	98.70 342

cascas		97.69 328	97.43 330	98.48 318	98.60 425	97.30 321	98.18 462	99.39 277	92.96 443	98.41 374	98.78 423	93.77 316	99.27 363	98.16 250	98.61 260	98.86 315

pm-mvs1		97.68 331	97.28 350	98.88 263	99.06 357	98.62 242	99.50 196	99.45 242	96.32 378	97.87 405	99.79 163	92.47 350	99.35 350	97.54 315	93.54 426	98.67 359

GBi-Net		97.68 331	97.48 315	98.29 344	99.51 223	97.26 325	99.43 251	99.48 198	96.49 366	99.07 283	99.32 362	90.26 390	98.98 412	97.10 345	96.65 357	98.62 381

test1		97.68 331	97.48 315	98.29 344	99.51 223	97.26 325	99.43 251	99.48 198	96.49 366	99.07 283	99.32 362	90.26 390	98.98 412	97.10 345	96.65 357	98.62 381

tpm		97.67 334	97.55 305	98.03 363	99.02 364	95.01 417	99.43 251	98.54 438	96.44 372	99.12 272	99.34 354	91.83 365	99.60 309	97.75 294	96.46 362	99.48 237

PCF-MVS	97.08 14	97.66 335	97.06 363	99.47 160	99.61 183	99.09 165	98.04 465	99.25 346	91.24 452	98.51 369	99.70 210	94.55 281	99.91 135	92.76 440	99.85 94	99.42 255
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 336	97.65 296	97.63 395	98.78 401	97.62 311	99.13 363	98.33 442	97.36 295	99.07 283	98.94 410	95.64 221	99.15 385	92.95 436	98.68 258	96.12 466

our_test_3		97.65 336	97.68 293	97.55 401	98.62 422	94.97 418	98.84 420	99.30 334	96.83 343	98.19 389	99.34 354	97.01 149	99.02 407	95.00 411	96.01 373	98.64 372

testgi		97.65 336	97.50 313	98.13 359	99.36 278	96.45 377	99.42 258	99.48 198	97.76 245	97.87 405	99.45 321	91.09 382	98.81 430	94.53 416	98.52 269	99.13 288

thres200		97.61 339	97.28 350	98.62 299	99.64 160	98.03 284	99.26 332	98.74 422	97.68 256	99.09 280	98.32 440	91.66 372	99.81 226	92.88 437	98.22 289	98.03 435

PAPM		97.59 340	97.09 362	99.07 227	99.06 357	98.26 272	98.30 458	99.10 368	94.88 419	98.08 393	99.34 354	96.27 189	99.64 300	89.87 452	98.92 238	99.31 273

UWE-MVS		97.58 341	97.29 349	98.48 318	99.09 351	96.25 385	99.01 395	96.61 468	97.86 228	99.19 261	99.01 401	88.72 408	99.90 148	97.38 329	98.69 257	99.28 275

SD_0403		97.55 342	97.53 309	97.62 396	99.61 183	93.64 444	99.72 53	99.44 251	98.03 212	98.62 361	99.39 338	96.06 196	99.57 312	87.88 461	99.01 232	99.66 163

VDDNet		97.55 342	97.02 364	99.16 219	99.49 237	98.12 281	99.38 280	99.30 334	95.35 409	99.68 113	99.90 33	82.62 454	99.93 110	99.31 86	98.13 298	99.42 255

TESTMET0.1,1		97.55 342	97.27 353	98.40 334	98.93 378	96.53 374	98.67 435	97.61 457	96.96 332	98.64 356	99.28 369	88.63 414	99.45 325	97.30 333	99.38 183	99.21 284

pmmvs5		97.52 345	97.30 347	98.16 355	98.57 428	96.73 364	99.27 323	98.90 400	96.14 394	98.37 377	99.53 292	91.54 375	99.14 387	97.51 317	95.87 379	98.63 379

LF4IMVS		97.52 345	97.46 320	97.70 393	98.98 373	95.55 400	99.29 313	98.82 410	98.07 197	98.66 349	99.64 248	89.97 395	99.61 308	97.01 350	96.68 356	97.94 443

DTE-MVSNet		97.51 347	97.19 356	98.46 324	98.63 421	98.13 279	99.84 12	99.48 198	96.68 349	97.97 400	99.67 235	92.92 332	98.56 437	96.88 362	92.60 440	98.70 342

testing11		97.50 348	97.10 361	98.71 292	99.20 321	96.91 357	99.29 313	98.82 410	97.89 225	98.21 388	98.40 436	85.63 438	99.83 212	98.45 222	98.04 301	99.37 265

ETVMVS		97.50 348	96.90 368	99.29 201	99.23 314	98.78 228	99.32 302	98.90 400	97.52 277	98.56 366	98.09 450	84.72 445	99.69 285	97.86 278	97.88 307	99.39 261

hse-mvs2		97.50 348	97.14 358	98.59 301	99.49 237	97.05 338	99.28 318	99.22 352	98.94 78	99.66 124	99.42 326	94.93 250	99.65 296	99.48 64	83.80 466	99.08 294

SixPastTwentyTwo		97.50 348	97.33 344	98.03 363	98.65 419	96.23 386	99.77 34	98.68 431	97.14 313	97.90 403	99.93 10	90.45 388	99.18 382	97.00 351	96.43 363	98.67 359

JIA-IIPM		97.50 348	97.02 364	98.93 248	98.73 410	97.80 301	99.30 308	98.97 386	91.73 450	98.91 312	94.86 468	95.10 244	99.71 273	97.58 308	97.98 302	99.28 275

ppachtmachnet_test		97.49 353	97.45 321	97.61 399	98.62 422	95.24 411	98.80 424	99.46 231	96.11 396	98.22 387	99.62 259	96.45 181	98.97 419	93.77 425	95.97 378	98.61 390

test-mter		97.49 353	97.13 360	98.55 311	98.79 398	97.10 332	98.67 435	97.75 454	96.65 352	98.61 362	98.85 416	88.23 418	99.45 325	97.25 335	99.38 183	99.10 289

testing91		97.44 355	97.02 364	98.71 292	99.18 327	96.89 359	99.19 353	99.04 378	97.78 243	98.31 380	98.29 441	85.41 440	99.85 187	98.01 267	97.95 303	99.39 261

tpm2		97.44 355	97.34 341	97.74 391	99.15 341	94.36 433	99.45 238	98.94 389	93.45 438	98.90 314	99.44 322	91.35 378	99.59 310	97.31 332	98.07 300	99.29 274

tpm cat1		97.39 357	97.36 336	97.50 403	99.17 335	93.73 440	99.43 251	99.31 329	91.27 451	98.71 340	99.08 392	94.31 294	99.77 247	96.41 380	98.50 270	99.00 305

UWE-MVS-28		97.36 358	97.24 354	97.75 389	98.84 394	94.44 430	99.24 339	97.58 458	97.98 217	99.00 298	99.00 402	91.35 378	99.53 318	93.75 426	98.39 274	99.27 279

testing99		97.36 358	96.94 367	98.63 298	99.18 327	96.70 365	99.30 308	98.93 390	97.71 251	98.23 385	98.26 442	84.92 443	99.84 196	98.04 266	97.85 310	99.35 267

SSC-MVS3.2		97.34 360	97.15 357	97.93 374	99.02 364	95.76 396	99.48 221	99.58 78	97.62 263	99.09 280	99.53 292	87.95 421	99.27 363	96.42 378	95.66 386	98.75 329

USDC		97.34 360	97.20 355	97.75 389	99.07 355	95.20 412	98.51 448	99.04 378	97.99 216	98.31 380	99.86 73	89.02 404	99.55 316	95.67 397	97.36 344	98.49 401

UniMVSNet_ETH3D		97.32 362	96.81 370	98.87 267	99.40 267	97.46 316	99.51 186	99.53 125	95.86 404	98.54 368	99.77 179	82.44 455	99.66 291	98.68 188	97.52 328	99.50 233

testing3		97.28 363	96.76 372	98.82 276	99.37 275	98.07 283	99.45 238	99.36 295	97.56 270	97.89 404	98.95 409	83.70 449	98.82 429	96.03 386	98.56 266	99.58 204

MVS		97.28 363	96.55 376	99.48 155	98.78 401	98.95 193	99.27 323	99.39 277	83.53 468	98.08 393	99.54 288	96.97 150	99.87 175	94.23 421	99.16 204	99.63 181

test_fmvs2		97.25 365	97.30 347	97.09 414	99.43 255	93.31 447	99.73 51	98.87 405	98.83 88	99.28 234	99.80 146	84.45 446	99.66 291	97.88 275	97.45 336	98.30 418

DSMNet-mixed		97.25 365	97.35 338	96.95 418	97.84 442	93.61 445	99.57 138	96.63 467	96.13 395	98.87 320	98.61 429	94.59 277	97.70 455	95.08 409	98.86 246	99.55 211

MS-PatchMatch		97.24 367	97.32 345	96.99 415	98.45 433	93.51 446	98.82 422	99.32 325	97.41 291	98.13 392	99.30 365	88.99 405	99.56 314	95.68 396	99.80 125	97.90 446

testing222		97.16 368	96.50 377	99.16 219	99.16 337	98.47 263	99.27 323	98.66 433	97.71 251	98.23 385	98.15 445	82.28 457	99.84 196	97.36 330	97.66 316	99.18 285

TransMVSNet (Re)		97.15 369	96.58 375	98.86 270	99.12 343	98.85 214	99.49 213	98.91 398	95.48 408	97.16 424	99.80 146	93.38 321	99.11 396	94.16 423	91.73 443	98.62 381

TinyColmap		97.12 370	96.89 369	97.83 384	99.07 355	95.52 403	98.57 444	98.74 422	97.58 267	97.81 408	99.79 163	88.16 419	99.56 314	95.10 408	97.21 349	98.39 414

K. test v3		97.10 371	96.79 371	98.01 366	98.72 412	96.33 381	99.87 8	97.05 461	97.59 265	96.16 438	99.80 146	88.71 409	99.04 403	96.69 369	96.55 361	98.65 370

Syy-MVS		97.09 372	97.14 358	96.95 418	99.00 367	92.73 451	99.29 313	99.39 277	97.06 324	97.41 414	98.15 445	93.92 310	98.68 435	91.71 445	98.34 276	99.45 251

PatchT		97.03 373	96.44 379	98.79 282	98.99 370	98.34 269	99.16 357	99.07 374	92.13 448	99.52 172	97.31 461	94.54 282	98.98 412	88.54 457	98.73 255	99.03 302

mmtdpeth		96.95 374	96.71 373	97.67 394	99.33 285	94.90 420	99.89 2	99.28 340	98.15 175	99.72 102	98.57 430	86.56 432	99.90 148	99.82 29	89.02 457	98.20 425

myMVS_eth3d		96.89 375	96.37 380	98.43 331	99.00 367	97.16 329	99.29 313	99.39 277	97.06 324	97.41 414	98.15 445	83.46 451	98.68 435	95.27 406	98.34 276	99.45 251

AUN-MVS		96.88 376	96.31 382	98.59 301	99.48 244	97.04 341	99.27 323	99.22 352	97.44 287	98.51 369	99.41 330	91.97 361	99.66 291	97.71 299	83.83 465	99.07 299

FMVSNet1		96.84 377	96.36 381	98.29 344	99.32 292	97.26 325	99.43 251	99.48 198	95.11 413	98.55 367	99.32 362	83.95 448	98.98 412	95.81 391	96.26 368	98.62 381

test2506		96.81 378	96.65 374	97.29 409	99.74 100	92.21 454	99.60 113	85.06 485	99.13 41	99.77 85	99.93 10	87.82 425	99.85 187	99.38 74	99.38 183	99.80 88

RPMNet		96.72 379	95.90 392	99.19 216	99.18 327	98.49 259	99.22 346	99.52 130	88.72 461	99.56 161	97.38 458	94.08 303	99.95 76	86.87 466	98.58 263	99.14 286

mvs5depth		96.66 380	96.22 384	97.97 370	97.00 458	96.28 383	98.66 438	99.03 380	96.61 357	96.93 430	99.79 163	87.20 428	99.47 321	96.65 373	94.13 417	98.16 427

test_0402		96.64 381	96.24 383	97.85 381	98.85 392	96.43 378	99.44 245	99.26 344	93.52 435	96.98 428	99.52 296	88.52 415	99.20 381	92.58 442	97.50 331	97.93 444

X-MVStestdata		96.55 382	95.45 401	99.87 21	99.85 31	99.83 22	99.69 62	99.68 24	98.98 72	99.37 210	64.01 481	98.81 49	99.94 92	98.79 174	99.86 87	99.84 53

pmmvs6		96.53 383	96.09 388	97.82 386	98.69 416	95.47 404	99.37 282	99.47 220	93.46 437	97.41 414	99.78 170	87.06 429	99.33 353	96.92 360	92.70 438	98.65 370

ET-MVSNet_ETH3D		96.49 384	95.64 398	99.05 231	99.53 214	98.82 222	98.84 420	97.51 459	97.63 261	84.77 468	99.21 381	92.09 359	98.91 425	98.98 133	92.21 441	99.41 258

UnsupCasMVSNet_eth		96.44 385	96.12 386	97.40 406	98.65 419	95.65 397	99.36 288	99.51 151	97.13 314	96.04 440	98.99 404	88.40 416	98.17 444	96.71 367	90.27 451	98.40 413

FMVSNet5		96.43 386	96.19 385	97.15 410	99.11 345	95.89 393	99.32 302	99.52 130	94.47 428	98.34 379	99.07 393	87.54 426	97.07 461	92.61 441	95.72 384	98.47 404

new_pmnet		96.38 387	96.03 389	97.41 405	98.13 439	95.16 415	99.05 382	99.20 356	93.94 430	97.39 417	98.79 422	91.61 374	99.04 403	90.43 450	95.77 381	98.05 434

Anonymous20231206		96.22 388	96.03 389	96.79 423	97.31 452	94.14 436	99.63 101	99.08 371	96.17 390	97.04 427	99.06 395	93.94 308	97.76 454	86.96 465	95.06 400	98.47 404

IB-MVS	95.67 18	96.22 388	95.44 402	98.57 305	99.21 319	96.70 365	98.65 439	97.74 456	96.71 347	97.27 419	98.54 431	86.03 435	99.92 123	98.47 220	86.30 462	99.10 289
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		96.20 390	95.89 393	97.13 412	97.72 446	94.96 419	99.79 31	99.29 338	93.01 442	97.20 423	99.03 398	89.69 399	98.36 441	91.16 448	96.13 370	98.07 432

gg-mvs-nofinetune		96.17 391	95.32 403	98.73 287	98.79 398	98.14 278	99.38 280	94.09 476	91.07 454	98.07 396	91.04 474	89.62 401	99.35 350	96.75 365	99.09 224	98.68 351

test20.03		96.12 392	95.96 391	96.63 424	97.44 448	95.45 405	99.51 186	99.38 285	96.55 363	96.16 438	99.25 375	93.76 317	96.17 467	87.35 464	94.22 415	98.27 420

PVSNet_0	94.43 19	96.09 393	95.47 400	97.94 373	99.31 293	94.34 434	97.81 466	99.70 18	97.12 316	97.46 413	98.75 424	89.71 398	99.79 239	97.69 302	81.69 468	99.68 155

MVStest1		96.08 394	95.48 399	97.89 378	98.93 378	96.70 365	99.56 146	99.35 302	92.69 446	91.81 463	99.46 319	89.90 396	98.96 421	95.00 411	92.61 439	98.00 439

EG-PatchMatch MVS		95.97 395	95.69 396	96.81 422	97.78 443	92.79 450	99.16 357	98.93 390	96.16 391	94.08 451	99.22 378	82.72 453	99.47 321	95.67 397	97.50 331	98.17 426

APD_test1		95.87 396	96.49 378	94.00 437	99.53 214	84.01 466	99.54 166	99.32 325	95.91 403	97.99 398	99.85 80	85.49 439	99.88 168	91.96 444	98.84 248	98.12 429

Patchmatch-RL test		95.84 397	95.81 395	95.95 432	95.61 463	90.57 458	98.24 459	98.39 440	95.10 415	95.20 445	98.67 426	94.78 261	97.77 453	96.28 383	90.02 452	99.51 229

test_vis1_rt		95.81 398	95.65 397	96.32 429	99.67 134	91.35 457	99.49 213	96.74 466	98.25 160	95.24 443	98.10 449	74.96 464	99.90 148	99.53 53	98.85 247	97.70 449

sc_t1		95.75 399	95.05 406	97.87 379	98.83 395	94.61 427	99.21 348	99.45 242	87.45 462	97.97 400	99.85 80	81.19 460	99.43 334	98.27 240	93.20 431	99.57 207

MVS-HIRNet		95.75 399	95.16 404	97.51 402	99.30 294	93.69 442	98.88 416	95.78 470	85.09 467	98.78 334	92.65 470	91.29 380	99.37 343	94.85 413	99.85 94	99.46 248

tt0320		95.71 401	95.07 405	97.62 396	99.05 360	95.02 416	99.25 334	99.52 130	86.81 463	97.97 400	99.72 203	83.58 450	99.15 385	96.38 381	93.35 427	98.68 351

MIMVSNet1		95.51 402	95.04 407	96.92 420	97.38 449	95.60 398	99.52 177	99.50 174	93.65 434	96.97 429	99.17 383	85.28 442	96.56 465	88.36 458	95.55 390	98.60 393

MDA-MVSNet_test_wron		95.45 403	94.60 410	98.01 366	98.16 438	97.21 328	99.11 372	99.24 349	93.49 436	80.73 474	98.98 406	93.02 329	98.18 443	94.22 422	94.45 411	98.64 372

TDRefinement		95.42 404	94.57 412	97.97 370	89.83 478	96.11 390	99.48 221	98.75 419	96.74 345	96.68 432	99.88 52	88.65 412	99.71 273	98.37 230	82.74 467	98.09 431

YYNet1		95.36 405	94.51 413	97.92 375	97.89 441	97.10 332	99.10 374	99.23 350	93.26 440	80.77 473	99.04 397	92.81 335	98.02 447	94.30 418	94.18 416	98.64 372

pmmvs-eth3d		95.34 406	94.73 409	97.15 410	95.53 465	95.94 392	99.35 293	99.10 368	95.13 411	93.55 454	97.54 456	88.15 420	97.91 450	94.58 415	89.69 455	97.61 450

tt0320-xc		95.31 407	94.59 411	97.45 404	98.92 380	94.73 422	99.20 351	99.31 329	86.74 464	97.23 420	99.72 203	81.14 461	98.95 422	97.08 348	91.98 442	98.67 359

dmvs_testset		95.02 408	96.12 386	91.72 446	99.10 348	80.43 474	99.58 130	97.87 453	97.47 280	95.22 444	98.82 418	93.99 306	95.18 471	88.09 459	94.91 405	99.56 210

KD-MVS_self_test		95.00 409	94.34 414	96.96 417	97.07 457	95.39 408	99.56 146	99.44 251	95.11 413	97.13 425	97.32 460	91.86 364	97.27 460	90.35 451	81.23 469	98.23 424

MDA-MVSNet-bldmvs		94.96 410	93.98 417	97.92 375	98.24 437	97.27 323	99.15 360	99.33 315	93.80 432	80.09 475	99.03 398	88.31 417	97.86 452	93.49 430	94.36 413	98.62 381

N_pmnet		94.95 411	95.83 394	92.31 444	98.47 432	79.33 476	99.12 366	92.81 482	93.87 431	97.68 410	99.13 388	93.87 312	99.01 409	91.38 447	96.19 369	98.59 394

KD-MVS_2432*1600		94.62 412	93.72 420	97.31 407	97.19 455	95.82 394	98.34 454	99.20 356	95.00 417	97.57 411	98.35 438	87.95 421	98.10 445	92.87 438	77.00 472	98.01 436

miper_refine_blended		94.62 412	93.72 420	97.31 407	97.19 455	95.82 394	98.34 454	99.20 356	95.00 417	97.57 411	98.35 438	87.95 421	98.10 445	92.87 438	77.00 472	98.01 436

CL-MVSNet_self_test		94.49 414	93.97 418	96.08 431	96.16 460	93.67 443	98.33 456	99.38 285	95.13 411	97.33 418	98.15 445	92.69 343	96.57 464	88.67 456	79.87 470	97.99 440

new-patchmatchnet		94.48 415	94.08 416	95.67 433	95.08 468	92.41 452	99.18 355	99.28 340	94.55 427	93.49 455	97.37 459	87.86 424	97.01 462	91.57 446	88.36 458	97.61 450

OpenMVS_ROB	92.34 20	94.38 416	93.70 422	96.41 428	97.38 449	93.17 448	99.06 380	98.75 419	86.58 465	94.84 449	98.26 442	81.53 458	99.32 355	89.01 455	97.87 308	96.76 459

CMPMVS	69.68 23	94.13 417	94.90 408	91.84 445	97.24 453	80.01 475	98.52 447	99.48 198	89.01 459	91.99 462	99.67 235	85.67 437	99.13 390	95.44 401	97.03 354	96.39 463
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 418	93.25 425	96.60 425	94.76 470	94.49 429	98.92 412	98.18 449	89.66 455	96.48 434	98.06 451	86.28 434	97.33 459	89.68 453	87.20 461	97.97 442

FE-MVSNET		94.07 419	93.36 424	96.22 430	94.05 472	94.71 424	99.56 146	98.36 441	93.15 441	93.76 453	97.55 455	86.47 433	96.49 466	87.48 462	89.83 454	97.48 455

mvsany_test3		93.77 420	93.45 423	94.74 435	95.78 462	88.01 461	99.64 95	98.25 444	98.28 150	94.31 450	97.97 452	68.89 468	98.51 439	97.50 318	90.37 450	97.71 447

FE-MVSNET1		93.64 421	92.69 427	96.48 427	94.12 471	94.21 435	99.34 296	99.38 285	93.42 439	93.33 456	97.58 454	74.82 466	97.65 457	92.56 443	89.64 456	97.58 452

UnsupCasMVSNet_bld		93.53 422	92.51 428	96.58 426	97.38 449	93.82 438	98.24 459	99.48 198	91.10 453	93.10 457	96.66 463	74.89 465	98.37 440	94.03 424	87.71 460	97.56 453

dongtai		93.26 423	92.93 426	94.25 436	99.39 270	85.68 464	97.68 468	93.27 478	92.87 444	96.85 431	99.39 338	82.33 456	97.48 458	76.78 472	97.80 311	99.58 204

WB-MVS		93.10 424	94.10 415	90.12 451	95.51 467	81.88 471	99.73 51	99.27 343	95.05 416	93.09 458	98.91 415	94.70 270	91.89 475	76.62 473	94.02 421	96.58 461

PM-MVS		92.96 425	92.23 429	95.14 434	95.61 463	89.98 460	99.37 282	98.21 447	94.80 422	95.04 448	97.69 453	65.06 469	97.90 451	94.30 418	89.98 453	97.54 454

SSC-MVS		92.73 426	93.73 419	89.72 452	95.02 469	81.38 472	99.76 37	99.23 350	94.87 420	92.80 459	98.93 411	94.71 269	91.37 476	74.49 475	93.80 423	96.42 462

test_fmvs3		92.10 427	91.77 430	93.08 442	96.19 459	86.25 462	99.82 16	98.62 435	96.65 352	95.19 446	96.90 462	55.05 476	95.93 469	96.63 374	90.92 449	97.06 458

test_f		91.90 428	91.26 432	93.84 438	95.52 466	85.92 463	99.69 62	98.53 439	95.31 410	93.87 452	96.37 465	55.33 475	98.27 442	95.70 394	90.98 448	97.32 457

test_method		91.10 429	91.36 431	90.31 450	95.85 461	73.72 483	94.89 472	99.25 346	68.39 474	95.82 441	99.02 400	80.50 462	98.95 422	93.64 428	94.89 406	98.25 422

Gipuma		90.99 430	90.15 435	93.51 439	98.73 410	90.12 459	93.98 473	99.45 242	79.32 470	92.28 460	94.91 467	69.61 467	97.98 449	87.42 463	95.67 385	92.45 470
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 431	90.11 436	93.34 440	98.78 401	85.59 465	98.15 463	93.16 480	89.37 458	92.07 461	98.38 437	81.48 459	95.19 470	62.54 479	97.04 353	99.25 280

testf1		90.42 432	90.68 433	89.65 453	97.78 443	73.97 481	99.13 363	98.81 412	89.62 456	91.80 464	98.93 411	62.23 472	98.80 431	86.61 467	91.17 445	96.19 464

APD_test2		90.42 432	90.68 433	89.65 453	97.78 443	73.97 481	99.13 363	98.81 412	89.62 456	91.80 464	98.93 411	62.23 472	98.80 431	86.61 467	91.17 445	96.19 464

test_vis3_rt		87.04 434	85.81 437	90.73 449	93.99 473	81.96 470	99.76 37	90.23 484	92.81 445	81.35 472	91.56 472	40.06 480	99.07 400	94.27 420	88.23 459	91.15 472

PMMVS2		86.87 435	85.37 439	91.35 448	90.21 477	83.80 467	98.89 415	97.45 460	83.13 469	91.67 466	95.03 466	48.49 478	94.70 472	85.86 469	77.62 471	95.54 467

LCM-MVSNet		86.80 436	85.22 440	91.53 447	87.81 479	80.96 473	98.23 461	98.99 384	71.05 472	90.13 467	96.51 464	48.45 479	96.88 463	90.51 449	85.30 463	96.76 459

FPMVS		84.93 437	85.65 438	82.75 459	86.77 480	63.39 485	98.35 453	98.92 393	74.11 471	83.39 470	98.98 406	50.85 477	92.40 474	84.54 470	94.97 402	92.46 469

EGC-MVSNET		82.80 438	77.86 444	97.62 396	97.91 440	96.12 389	99.33 299	99.28 340	8.40 482	25.05 483	99.27 372	84.11 447	99.33 353	89.20 454	98.22 289	97.42 456

tmp_tt		82.80 438	81.52 441	86.66 455	66.61 485	68.44 484	92.79 475	97.92 451	68.96 473	80.04 476	99.85 80	85.77 436	96.15 468	97.86 278	43.89 478	95.39 468

E-PMN		80.61 440	79.88 442	82.81 458	90.75 476	76.38 479	97.69 467	95.76 471	66.44 476	83.52 469	92.25 471	62.54 471	87.16 478	68.53 477	61.40 475	84.89 476

EMVS		80.02 441	79.22 443	82.43 460	91.19 475	76.40 478	97.55 470	92.49 483	66.36 477	83.01 471	91.27 473	64.63 470	85.79 479	65.82 478	60.65 476	85.08 475

ANet_high		77.30 442	74.86 446	84.62 457	75.88 483	77.61 477	97.63 469	93.15 481	88.81 460	64.27 478	89.29 475	36.51 481	83.93 480	75.89 474	52.31 477	92.33 471

MVE	76.82 21	76.91 443	74.31 447	84.70 456	85.38 482	76.05 480	96.88 471	93.17 479	67.39 475	71.28 477	89.01 476	21.66 486	87.69 477	71.74 476	72.29 474	90.35 473
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 444	74.97 445	79.01 461	70.98 484	55.18 486	93.37 474	98.21 447	65.08 478	61.78 479	93.83 469	21.74 485	92.53 473	78.59 471	91.12 447	89.34 474
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		40.18 445	41.29 450	36.84 462	86.18 481	49.12 487	79.73 476	22.81 487	27.64 479	25.46 482	28.45 482	21.98 484	48.89 481	55.80 480	23.56 481	12.51 479

testmvs		39.17 446	43.78 448	25.37 464	36.04 487	16.84 489	98.36 452	26.56 486	20.06 480	38.51 481	67.32 477	29.64 483	15.30 483	37.59 481	39.90 479	43.98 478

test123		39.01 447	42.50 449	28.53 463	39.17 486	20.91 488	98.75 429	19.17 488	19.83 481	38.57 480	66.67 478	33.16 482	15.42 482	37.50 482	29.66 480	49.26 477

cdsmvs_eth3d_5k		24.64 448	32.85 451	0.00 465	0.00 488	0.00 490	0.00 477	99.51 151	0.00 483	0.00 484	99.56 280	96.58 173	0.00 484	0.00 483	0.00 482	0.00 480

ab-mvs-re		8.30 449	11.06 452	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	99.58 272	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

pcd_1.5k_mvsjas		8.27 450	11.03 453	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	99.01 20	0.00 484	0.00 483	0.00 482	0.00 480

test_blank		0.13 451	0.17 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	1.57 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

mmdepth		0.02 452	0.03 455	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

monomultidepth		0.02 452	0.03 455	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

uanet_test		0.02 452	0.03 455	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

DCPMVS		0.02 452	0.03 455	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

sosnet-low-res		0.02 452	0.03 455	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

sosnet		0.02 452	0.03 455	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

uncertanet		0.02 452	0.03 455	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

Regformer		0.02 452	0.03 455	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

uanet		0.02 452	0.03 455	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.27 484	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

MED-MVS test				99.87 21	99.88 13	99.81 33	99.69 62	99.87 6	99.34 26	99.90 34	99.83 100		99.95 76	98.83 166	99.89 68	99.83 63

TestfortrainingZip							99.69 62

WAC-MVS						97.16 329								95.47 400

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	99.51 223	99.76 49		99.33 315					99.96 41	98.87 153	99.84 102	99.89 29

PC_three_1452									98.18 173	99.84 56	99.70 210	99.31 3	98.52 438	98.30 239	99.80 125	99.81 79

No_MVS				99.87 21	99.51 223	99.76 49		99.33 315					99.96 41	98.87 153	99.84 102	99.89 29

test_one_0601					99.81 57	99.88 10		99.49 186	98.97 75	99.65 133	99.81 128	99.09 16

eth-test2					0.00 488

eth-test					0.00 488

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 341	99.56 161	99.54 288	98.58 78	99.96 41	96.93 358	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	99.82 113	98.75 60		98.61 198	99.81 120	99.77 100

IU-MVS					99.84 38	99.88 10		99.32 325	98.30 149	99.84 56				98.86 158	99.85 94	99.89 29

OPU-MVS				99.64 101	99.56 202	99.72 56	99.60 113				99.70 210	99.27 7	99.42 336	98.24 243	99.80 125	99.79 92

test_241102_TWO								99.48 198	99.08 56	99.88 43	99.81 128	98.94 34	99.96 41	98.91 147	99.84 102	99.88 35

test_241102_ONE					99.84 38	99.90 3		99.48 198	99.07 58	99.91 31	99.74 193	99.20 9	99.76 251

9.14			99.10 99		99.72 111		99.40 271	99.51 151	97.53 275	99.64 138	99.78 170	98.84 46	99.91 135	97.63 304	99.82 117

save fliter					99.76 82	99.59 88	99.14 362	99.40 274	99.00 67

test_0728_THIRD									98.99 69	99.81 69	99.80 146	99.09 16	99.96 41	98.85 160	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	98.93 144	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	99.82 113	98.94 34

GSMVS																99.52 220

test_part2					99.81 57	99.83 22				99.77 85

sam_mvs1												94.86 256				99.52 220

sam_mvs												94.72 268

ambc				93.06 443	92.68 474	82.36 468	98.47 449	98.73 428		95.09 447	97.41 457	55.55 474	99.10 398	96.42 378	91.32 444	97.71 447

MTGPA								99.47 220

test_post1							99.23 342				65.14 480	94.18 299	99.71 273	97.58 308

test_post											65.99 479	94.65 275	99.73 263

patchmatchnet-post											98.70 425	94.79 260	99.74 257

GG-mvs-BLEND				98.45 326	98.55 429	98.16 276	99.43 251	93.68 477		97.23 420	98.46 433	89.30 402	99.22 374	95.43 402	98.22 289	97.98 441

MTMP							99.54 166	98.88 403

gm-plane-assit					98.54 430	92.96 449			94.65 425		99.15 386		99.64 300	97.56 313

test9_res														97.49 319	99.72 148	99.75 109

TEST9					99.67 134	99.65 75	99.05 382	99.41 267	96.22 386	98.95 307	99.49 306	98.77 56	99.91 135

test_8					99.67 134	99.61 85	99.03 387	99.41 267	96.28 380	98.93 310	99.48 312	98.76 57	99.91 135

agg_prior2														97.21 337	99.73 147	99.75 109

agg_prior					99.67 134	99.62 83		99.40 274		98.87 320			99.91 135

TestCases				99.31 193	99.86 25	98.48 261		99.61 60	97.85 231	99.36 216	99.85 80	95.95 202	99.85 187	96.66 371	99.83 113	99.59 200

test_prior4						99.56 94	98.99 398

test_prior2							98.96 405		98.34 143	99.01 294	99.52 296	98.68 70		97.96 270	99.74 145

test_prior				99.68 89	99.67 134	99.48 111		99.56 90					99.83 212			99.74 113

旧先验2							98.96 405		96.70 348	99.47 180			99.94 92	98.19 246

新几何2							99.01 395

新几何1				99.75 77	99.75 92	99.59 88		99.54 109	96.76 344	99.29 233	99.64 248	98.43 89	99.94 92	96.92 360	99.66 159	99.72 132

旧先验1					99.74 100	99.59 88		99.54 109			99.69 221	98.47 86			99.68 156	99.73 122

无先验							98.99 398	99.51 151	96.89 338				99.93 110	97.53 316		99.72 132

原ACMM2							98.95 408

原ACMM1				99.65 95	99.73 107	99.33 130		99.47 220	97.46 281	99.12 272	99.66 240	98.67 72	99.91 135	97.70 301	99.69 153	99.71 143

test222					99.75 92	99.49 109	98.91 414	99.49 186	96.42 374	99.34 223	99.65 242	98.28 100			99.69 153	99.72 132

testdata2													99.95 76	96.67 370

segment_acmp												98.96 27

testdata				99.54 125	99.75 92	98.95 193		99.51 151	97.07 322	99.43 191	99.70 210	98.87 42	99.94 92	97.76 292	99.64 162	99.72 132

testdata1							98.85 419		98.32 147

test12				99.75 77	99.64 160	99.61 85		99.29 338		99.21 255		98.38 95	99.89 163		99.74 145	99.74 113

plane_prior7					99.29 298	97.03 344

plane_prior6					99.27 303	96.98 348						92.71 341

plane_prior5								99.47 220					99.69 285	97.78 288	97.63 317	98.67 359

plane_prior4											99.61 263

plane_prior3						97.00 346			98.69 107	99.11 274

plane_prior2							99.39 275		98.97 75

plane_prior1					99.26 306

plane_prior						96.97 349	99.21 348		98.45 130						97.60 320

n2								0.00 489

nn								0.00 489

door-mid								98.05 450

lessismore_v0				97.79 388	98.69 416	95.44 407		94.75 474		95.71 442	99.87 65	88.69 410	99.32 355	95.89 389	94.93 404	98.62 381

LGP-MVS_train				98.49 316	99.33 285	97.05 338		99.55 100	97.46 281	99.24 247	99.83 100	92.58 346	99.72 267	98.09 257	97.51 329	98.68 351

test11								99.35 302

door								97.92 451

HQP5-MVS						96.83 360

HQP-NCC					99.19 324		98.98 401		98.24 162	98.66 349

ACMP_Plane					99.19 324		98.98 401		98.24 162	98.66 349

BP-MVS														97.19 341

HQP4-MVS										98.66 349			99.64 300			98.64 372

HQP3-MVS								99.39 277							97.58 322

HQP2-MVS												92.47 350

NP-MVS					99.23 314	96.92 356					99.40 334

MDTV_nov1_ep13_2view						95.18 414	99.35 293		96.84 341	99.58 157		95.19 241		97.82 283		99.46 248

MDTV_nov1_ep13			98.32 226		99.11 345	94.44 430	99.27 323	98.74 422	97.51 278	99.40 204	99.62 259	94.78 261	99.76 251	97.59 307	98.81 252

ACMMP++_ref															97.19 350

ACMMP++															97.43 340

Test By Simon												98.75 60

ITE_SJBPF				98.08 361	99.29 298	96.37 379		98.92 393	98.34 143	98.83 326	99.75 188	91.09 382	99.62 307	95.82 390	97.40 342	98.25 422

DeepMVS_CX				93.34 440	99.29 298	82.27 469		99.22 352	85.15 466	96.33 435	99.05 396	90.97 384	99.73 263	93.57 429	97.77 313	98.01 436

High-resolution multi-view benchmark