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	99.83 103	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	99.56 147	99.63 46	99.48 3	99.98 13	99.83 103	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	99.56 147	99.63 46	99.47 4	99.98 13	99.82 116	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	99.48 224	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	99.58 131	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	99.83 103	99.30 4	99.95 76	98.83 169	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 82	99.18 12	99.96 41	99.22 101	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	99.38 275	99.37 123	99.58 131	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	99.56 147	99.55 100	99.15 38	99.90 34	99.90 34	99.00 24	99.97 29	99.11 119	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	99.54 167	99.66 32	99.46 7	99.98 13	99.89 43	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	99.52 178	99.54 109	99.13 41	99.89 40	99.89 43	98.96 27	99.96 41	99.04 129	99.90 57	99.85 46

our_new_method		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 178	99.54 109	99.13 41	99.89 40	99.89 43	98.96 27	99.96 41	99.04 129	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	99.48 201	99.08 56	99.91 31	99.81 131	99.20 9	99.96 41	98.91 150	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 82	98.41 93	99.96 41	99.28 93	99.84 102	99.83 63

DVP-MVS++		99.59 15	99.50 19	99.88 15	99.51 226	99.88 10	99.87 8	99.51 153	98.99 69	99.88 43	99.81 131	99.27 7	99.96 41	98.85 163	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	99.47 234	99.63 46	99.45 11	99.98 13	99.89 43	97.02 148	99.99 4	99.98 1	99.96 17	99.95 11

TSAR-MVS + MP.		99.58 16	99.50 19	99.81 60	99.91 1	99.66 71	99.63 101	99.39 281	98.91 82	99.78 81	99.85 82	99.36 2	99.94 92	98.84 166	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	99.45 246	99.01 64	99.90 34	99.83 103	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	99.45 246	99.01 64	99.89 40	99.82 116	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	99.57 139	99.37 297	99.10 48	99.81 69	99.80 149	98.94 34	99.96 41	98.93 147	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	99.37 286	99.70 18	99.18 34	99.83 64	99.83 103	98.74 65	99.93 110	98.83 169	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	99.52 178	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	99.44 257	99.65 75	99.50 199	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	99.51 188	99.62 51	99.46 7	99.99 2	99.90 34	96.60 172	99.98 20	99.95 16	99.95 23	99.96 7

fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 226	99.67 68	99.50 199	99.64 42	99.43 17	99.98 13	99.78 173	97.26 136	99.95 76	99.95 16	99.93 33	99.92 23

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 21	99.82 53	99.81 33	99.59 121	99.51 153	98.62 112	99.79 76	99.83 103	99.28 6	99.97 29	98.48 220	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	99.37 213	99.74 196	98.81 49	99.94 92	98.79 177	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	99.47 223	98.79 95	99.68 116	99.81 131	98.43 89	99.97 29	98.88 153	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	99.51 188	99.67 27	99.13 41	99.98 13	99.92 18	96.60 172	99.96 41	99.95 16	99.96 17	99.95 11

HPM-MVS_fast		99.51 29	99.40 38	99.85 43	99.91 1	99.79 41	99.76 37	99.56 90	97.72 253	99.76 91	99.75 191	99.13 14	99.92 123	99.07 126	99.92 39	99.85 46

mvsany_test1		99.50 31	99.46 28	99.62 108	99.61 186	99.09 165	98.94 413	99.48 201	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	99.70 213	98.65 74	99.79 242	99.65 41	99.78 134	99.41 261

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	99.69 224	98.55 81	99.82 224	99.69 35	99.85 94	99.48 240

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	99.68 116	99.69 224	99.06 18	99.96 41	98.69 189	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	99.67 122	99.69 224	98.95 32	99.96 41	98.69 189	99.87 79	99.84 53

DeepC-MVS_fast	98.69 1	99.49 33	99.39 40	99.77 74	99.63 166	99.59 88	99.36 292	99.46 235	99.07 58	99.79 76	99.82 116	98.85 44	99.92 123	98.68 191	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	99.66 127	99.68 232	98.96 27	99.96 41	98.62 198	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	99.82 116	98.86 43	99.95 76	98.62 198	99.81 120	99.78 98

DELS-MVS		99.48 37	99.42 32	99.65 95	99.72 111	99.40 121	99.05 385	99.66 32	99.14 40	99.57 163	99.80 149	98.46 87	99.94 92	99.57 48	99.84 102	99.60 192
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	98.08 198	99.55 170	99.64 251	98.91 39	99.96 41	98.72 184	99.90 57	99.82 72

ACMMP_NAP		99.47 40	99.34 50	99.88 15	99.87 20	99.86 18	99.47 234	99.48 201	98.05 206	99.76 91	99.86 75	98.82 48	99.93 110	98.82 176	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	99.50 176	98.27 152	99.87 49	99.92 18	98.09 108	99.94 92	99.65 41	99.95 23	99.47 246

balanced_conf03		99.46 42	99.39 40	99.67 90	99.55 209	99.58 93	99.74 47	99.51 153	98.42 134	99.87 49	99.84 97	98.05 111	99.91 135	99.58 47	99.94 31	99.52 223

DPE-MVS		99.46 42	99.32 54	99.91 6	99.78 70	99.88 10	99.36 292	99.51 153	98.73 102	99.88 43	99.84 97	98.72 67	99.96 41	98.16 253	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	99.44 171	99.60 192	99.16 155	99.41 267	99.71 16	98.98 72	99.45 186	99.78 173	99.19 11	99.54 320	99.28 93	99.84 102	99.63 184

SR-MVS-dyc-post		99.45 46	99.31 60	99.85 43	99.76 82	99.82 28	99.63 101	99.52 131	98.38 137	99.76 91	99.82 116	98.53 82	99.95 76	98.61 201	99.81 120	99.77 100

PGM-MVS		99.45 46	99.31 60	99.86 34	99.87 20	99.78 47	99.58 131	99.65 39	97.84 237	99.71 109	99.80 149	99.12 15	99.97 29	98.33 238	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	99.52 131	98.07 199	99.53 173	99.63 257	98.93 38	99.97 29	98.74 181	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	98.12 188	99.63 144	99.84 97	98.73 66	99.96 41	98.55 216	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	99.56 147	99.47 223	97.45 287	99.78 81	99.82 116	99.18 12	99.91 135	98.79 177	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	99.48 201	98.12 188	99.50 178	99.75 191	98.78 53	99.97 29	98.57 210	99.89 68	99.83 63

EC-MVSNet		99.44 50	99.39 40	99.58 116	99.56 205	99.49 109	99.88 4	99.58 78	98.38 137	99.73 97	99.69 224	98.20 103	99.70 283	99.64 43	99.82 117	99.54 216

SR-MVS		99.43 53	99.29 66	99.86 34	99.75 92	99.83 22	99.59 121	99.62 51	98.21 168	99.73 97	99.79 166	98.68 70	99.96 41	98.44 226	99.77 137	99.79 92

MCST-MVS		99.43 53	99.30 62	99.82 57	99.79 68	99.74 54	99.29 316	99.40 278	98.79 95	99.52 175	99.62 262	98.91 39	99.90 148	98.64 195	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	99.50 176	98.70 106	99.77 85	99.49 309	98.21 102	99.95 76	98.46 224	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	99.62 175	99.55 96	99.50 199	99.70 18	98.79 95	99.77 85	99.96 1	97.45 124	99.96 41	98.92 149	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	97.59 268	99.68 116	99.63 257	98.91 39	99.94 92	98.58 207	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	99.62 175	99.71 58	99.26 335	99.52 131	98.82 89	99.39 209	99.71 209	98.96 27	99.85 187	98.59 206	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	99.53 176	99.56 90	99.45 11	99.99 2	99.92 18	94.92 255	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	99.48 224	99.62 51	99.46 7	99.99 2	99.92 18	95.24 242	99.96 41	99.97 2	99.97 9	99.96 7

SD-MVS		99.41 59	99.52 14	99.05 234	99.74 100	99.68 64	99.46 238	99.52 131	99.11 47	99.88 43	99.91 26	99.43 1	97.70 459	98.72 184	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	98.94 413	99.85 9	98.82 89	99.65 136	99.74 196	98.51 84	99.80 236	98.83 169	99.89 68	99.64 179

MVS_111021_HR		99.41 59	99.32 54	99.66 91	99.72 111	99.47 113	98.95 411	99.85 9	98.82 89	99.54 171	99.73 202	98.51 84	99.74 260	98.91 150	99.88 76	99.77 100

MM		99.40 64	99.28 69	99.74 80	99.67 135	99.31 135	99.52 178	98.87 409	99.55 1	99.74 95	99.80 149	96.47 180	99.98 20	99.97 2	99.97 9	99.94 17

GST-MVS		99.40 64	99.24 78	99.85 43	99.86 25	99.79 41	99.60 113	99.67 27	97.97 221	99.63 144	99.68 232	98.52 83	99.95 76	98.38 231	99.86 87	99.81 79

HPM-MVS++		99.39 66	99.23 82	99.87 21	99.75 92	99.84 20	99.43 255	99.51 153	98.68 109	99.27 243	99.53 295	98.64 75	99.96 41	98.44 226	99.80 125	99.79 92

SF-MVS		99.38 67	99.24 78	99.79 68	99.79 68	99.68 64	99.57 139	99.54 109	97.82 243	99.71 109	99.80 149	98.95 32	99.93 110	98.19 249	99.84 102	99.74 115

fmvsm_s_conf0.5_n_5		99.37 68	99.21 84	99.86 34	99.80 63	99.68 64	99.42 262	99.61 60	99.37 24	99.97 25	99.86 75	94.96 250	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	99.48 224	99.66 32	99.45 11	99.99 2	99.93 10	94.64 280	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	99.46 238	99.60 67	99.47 4	99.98 13	99.94 6	94.98 249	99.95 76	99.97 2	99.79 132	99.73 124

MP-MVS-pluss		99.37 68	99.20 86	99.88 15	99.90 4	99.87 17	99.30 311	99.52 131	97.18 313	99.60 156	99.79 166	98.79 52	99.95 76	98.83 169	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	99.49 216	99.60 67	99.42 20	99.99 2	99.86 75	95.15 245	99.95 76	99.95 16	99.89 68	99.73 124

TSAR-MVS + GP.		99.36 72	99.36 46	99.36 185	99.67 135	98.61 248	99.07 379	99.33 319	99.00 67	99.82 68	99.81 131	99.06 18	99.84 196	99.09 124	99.42 181	99.65 172

PVSNet_Blended_VisFu		99.36 72	99.28 69	99.61 109	99.86 25	99.07 170	99.47 234	99.93 2	97.66 262	99.71 109	99.86 75	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	99.48 157	99.70 122	98.63 244	99.42 262	99.63 46	99.46 7	99.98 13	99.88 54	95.59 225	99.96 41	99.97 2	99.98 4	99.85 46

NCCC		99.34 75	99.19 88	99.79 68	99.61 186	99.65 75	99.30 311	99.48 201	98.86 84	99.21 258	99.63 257	98.72 67	99.90 148	98.25 245	99.63 164	99.80 88

mamv4		99.33 77	99.42 32	99.07 230	99.67 135	97.73 307	99.42 262	99.60 67	98.15 175	99.94 28	99.91 26	98.42 91	99.94 92	99.72 32	99.96 17	99.54 216

MP-MVS		99.33 77	99.15 93	99.87 21	99.88 13	99.82 28	99.66 82	99.46 235	98.09 194	99.48 182	99.74 196	98.29 99	99.96 41	97.93 275	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	99.57 139	99.56 90	99.45 11	99.99 2	99.93 10	94.18 303	99.99 4	99.96 13	99.98 4	99.73 124

fmvsm_s_conf0.5_n_2		99.32 79	99.13 95	99.89 11	99.80 63	99.77 48	99.44 249	99.58 78	99.47 4	99.99 2	99.93 10	94.04 308	99.96 41	99.96 13	99.93 33	99.93 22

PS-MVSNAJ		99.32 79	99.32 54	99.30 201	99.57 201	98.94 197	98.97 407	99.46 235	98.92 81	99.71 109	99.24 379	99.01 20	99.98 20	99.35 76	99.66 159	98.97 312

CSCG		99.32 79	99.32 54	99.32 194	99.85 31	98.29 274	99.71 57	99.66 32	98.11 190	99.41 202	99.80 149	98.37 96	99.96 41	98.99 135	99.96 17	99.72 134

PHI-MVS		99.30 83	99.17 91	99.70 87	99.56 205	99.52 105	99.58 131	99.80 11	97.12 319	99.62 148	99.73 202	98.58 78	99.90 148	98.61 201	99.91 46	99.68 157

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	99.63 144	99.95 3	95.82 214	99.94 92	99.37 75	99.97 9	99.73 124
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	99.53 176	99.62 51	98.74 101	99.99 2	99.95 3	94.53 288	99.94 92	99.89 25	99.96 17	99.97 4

xiu_mvs_v1_base_debu		99.29 85	99.27 73	99.34 188	99.63 166	98.97 183	99.12 369	99.51 153	98.86 84	99.84 56	99.47 318	98.18 104	99.99 4	99.50 57	99.31 191	99.08 297

xiu_mvs_v1_base		99.29 85	99.27 73	99.34 188	99.63 166	98.97 183	99.12 369	99.51 153	98.86 84	99.84 56	99.47 318	98.18 104	99.99 4	99.50 57	99.31 191	99.08 297

xiu_mvs_v1_base_debi		99.29 85	99.27 73	99.34 188	99.63 166	98.97 183	99.12 369	99.51 153	98.86 84	99.84 56	99.47 318	98.18 104	99.99 4	99.50 57	99.31 191	99.08 297

NormalMVS		99.27 89	99.19 88	99.52 139	99.89 8	98.83 223	99.65 88	99.52 131	99.10 48	99.84 56	99.76 186	95.80 216	99.99 4	99.30 89	99.84 102	99.74 115

APD-MVS		99.27 89	99.08 105	99.84 55	99.75 92	99.79 41	99.50 199	99.50 176	97.16 315	99.77 85	99.82 116	98.78 53	99.94 92	97.56 316	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	99.18 330	99.75 51	99.56 147	99.57 85	98.45 130	99.49 181	99.85 82	97.77 118	99.94 92	98.33 238	99.84 102	99.52 223

fmvsm_s_conf0.1_n_a		99.26 92	99.06 110	99.85 43	99.52 223	99.62 83	99.54 167	99.62 51	98.69 107	99.99 2	99.96 1	94.47 290	99.94 92	99.88 26	99.92 39	99.98 2

patch_mono-2		99.26 92	99.62 6	98.16 359	99.81 57	94.59 433	99.52 178	99.64 42	99.33 28	99.73 97	99.90 34	99.00 24	99.99 4	99.69 35	99.98 4	99.89 29

ETV-MVS		99.26 92	99.21 84	99.40 178	99.46 250	99.30 138	99.56 147	99.52 131	98.52 122	99.44 191	99.27 375	98.41 93	99.86 181	99.10 122	99.59 168	99.04 304

xiu_mvs_v2_base		99.26 92	99.25 77	99.29 204	99.53 217	98.91 204	99.02 393	99.45 246	98.80 94	99.71 109	99.26 377	98.94 34	99.98 20	99.34 81	99.23 200	98.98 311

CANet		99.25 96	99.14 94	99.59 113	99.41 265	99.16 155	99.35 297	99.57 85	98.82 89	99.51 177	99.61 266	96.46 181	99.95 76	99.59 45	99.98 4	99.65 172

3Dnovator	97.25 9	99.24 97	99.05 112	99.81 60	99.12 346	99.66 71	99.84 12	99.74 13	99.09 55	98.92 314	99.90 34	95.94 207	99.98 20	98.95 143	99.92 39	99.79 92

LuminaMVS		99.23 98	99.10 99	99.61 109	99.35 282	99.31 135	99.46 238	99.13 369	98.61 113	99.86 53	99.89 43	96.41 186	99.91 135	99.67 37	99.51 174	99.63 184

dcpmvs_2		99.23 98	99.58 9	98.16 359	99.83 47	94.68 430	99.76 37	99.52 131	99.07 58	99.98 13	99.88 54	98.56 80	99.93 110	99.67 37	99.98 4	99.87 40

test_fmvsmconf0.01_n		99.22 100	99.03 117	99.79 68	98.42 438	99.48 111	99.55 162	99.51 153	99.39 22	99.78 81	99.93 10	94.80 262	99.95 76	99.93 23	99.95 23	99.94 17

diffmvs_AUTHOR		99.19 101	99.10 99	99.48 157	99.64 162	98.85 218	99.32 305	99.48 201	98.50 124	99.81 69	99.81 131	96.82 160	99.88 168	99.40 71	99.12 216	99.71 145

CHOSEN 1792x2688		99.19 101	99.10 99	99.45 166	99.89 8	98.52 258	99.39 279	99.94 1	98.73 102	99.11 277	99.89 43	95.50 228	99.94 92	99.50 57	99.97 9	99.89 29

F-COLMAP		99.19 101	99.04 114	99.64 101	99.78 70	99.27 143	99.42 262	99.54 109	97.29 304	99.41 202	99.59 271	98.42 91	99.93 110	98.19 249	99.69 153	99.73 124

E3new		99.18 104	99.08 105	99.48 157	99.63 166	98.94 197	99.46 238	99.50 176	98.06 203	99.72 102	99.84 97	97.27 133	99.84 196	99.10 122	99.13 211	99.67 161

viewcassd2359sk11		99.18 104	99.08 105	99.49 153	99.65 157	98.95 193	99.48 224	99.51 153	98.10 193	99.72 102	99.87 67	97.13 139	99.84 196	99.13 116	99.14 208	99.69 151

viewmanbaseed2359cas		99.18 104	99.07 109	99.50 149	99.62 175	99.01 177	99.50 199	99.52 131	98.25 160	99.68 116	99.82 116	96.93 153	99.80 236	99.15 115	99.11 218	99.70 148

EIA-MVS		99.18 104	99.09 104	99.45 166	99.49 240	99.18 152	99.67 75	99.53 125	97.66 262	99.40 207	99.44 325	98.10 107	99.81 229	98.94 144	99.62 165	99.35 270

3Dnovator+	97.12 13	99.18 104	98.97 139	99.82 57	99.17 338	99.68 64	99.81 20	99.51 153	99.20 33	98.72 343	99.89 43	95.68 222	99.97 29	98.86 161	99.86 87	99.81 79

MVSFormer		99.17 109	99.12 97	99.29 204	99.51 226	98.94 197	99.88 4	99.46 235	97.55 274	99.80 74	99.65 245	97.39 125	99.28 363	99.03 131	99.85 94	99.65 172

sss		99.17 109	99.05 112	99.53 133	99.62 175	98.97 183	99.36 292	99.62 51	97.83 238	99.67 122	99.65 245	97.37 128	99.95 76	99.19 105	99.19 203	99.68 157

SSM_0404		99.16 111	99.06 110	99.44 171	99.65 157	98.96 187	99.49 216	99.50 176	98.14 180	99.62 148	99.85 82	96.85 155	99.85 187	99.19 105	99.26 196	99.52 223

guyue		99.16 111	99.04 114	99.52 139	99.69 127	98.92 203	99.59 121	98.81 416	98.73 102	99.90 34	99.87 67	95.34 235	99.88 168	99.66 40	99.81 120	99.74 115

test_cas_vis1_n_1920		99.16 111	99.01 131	99.61 109	99.81 57	98.86 217	99.65 88	99.64 42	99.39 22	99.97 25	99.94 6	93.20 332	99.98 20	99.55 50	99.91 46	99.99 1

DP-MVS		99.16 111	98.95 147	99.78 71	99.77 78	99.53 101	99.41 267	99.50 176	97.03 331	99.04 294	99.88 54	97.39 125	99.92 123	98.66 193	99.90 57	99.87 40

E6		99.15 115	99.03 117	99.50 149	99.66 148	98.90 207	99.60 113	99.53 125	98.13 183	99.72 102	99.91 26	96.31 190	99.84 196	99.30 89	99.10 225	99.76 107

E2		99.15 115	99.03 117	99.49 153	99.65 157	98.93 202	99.49 216	99.52 131	98.14 180	99.72 102	99.88 54	96.57 176	99.84 196	99.17 111	99.13 211	99.72 134

E3		99.15 115	99.03 117	99.49 153	99.62 175	98.91 204	99.49 216	99.52 131	98.13 183	99.72 102	99.88 54	96.61 171	99.84 196	99.17 111	99.13 211	99.72 134

SymmetryMVS		99.15 115	99.02 126	99.52 139	99.72 111	98.83 223	99.65 88	99.34 311	99.10 48	99.84 56	99.76 186	95.80 216	99.99 4	99.30 89	98.72 259	99.73 124

MGCNet		99.15 115	98.96 143	99.73 83	98.92 383	99.37 123	99.37 286	96.92 466	99.51 2	99.66 127	99.78 173	96.69 167	99.97 29	99.84 28	99.97 9	99.84 53

casdiffmvs_mvg		99.15 115	99.02 126	99.55 124	99.66 148	99.09 165	99.64 95	99.56 90	98.26 155	99.45 186	99.87 67	96.03 201	99.81 229	99.54 51	99.15 207	99.73 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.15 115	99.02 126	99.53 133	99.66 148	99.14 160	99.72 53	99.48 201	98.35 142	99.42 197	99.84 97	96.07 198	99.79 242	99.51 56	99.14 208	99.67 161

diffmvs		99.14 122	99.02 126	99.51 144	99.61 186	98.96 187	99.28 321	99.49 189	98.46 128	99.72 102	99.71 209	96.50 179	99.88 168	99.31 86	99.11 218	99.67 161
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	98.99 135	99.59 113	99.58 196	99.41 120	99.16 360	99.44 255	98.45 130	99.19 264	99.49 309	98.08 109	99.89 163	97.73 299	99.75 142	99.48 240

E4		99.13 124	99.01 131	99.49 153	99.68 132	98.90 207	99.52 178	99.52 131	98.13 183	99.71 109	99.90 34	96.32 188	99.84 196	99.21 103	99.11 218	99.75 110

SSM_0407		99.13 124	99.03 117	99.43 174	99.62 175	98.88 210	99.51 188	99.50 176	98.14 180	99.37 213	99.85 82	96.85 155	99.83 215	99.19 105	99.25 197	99.60 192

CDPH-MVS		99.13 124	98.91 155	99.80 64	99.75 92	99.71 58	99.15 363	99.41 271	96.60 364	99.60 156	99.55 286	98.83 47	99.90 148	97.48 323	99.83 113	99.78 98

casdiffmvs		99.13 124	98.98 138	99.56 122	99.65 157	99.16 155	99.56 147	99.50 176	98.33 145	99.41 202	99.86 75	95.92 208	99.83 215	99.45 68	99.16 204	99.70 148
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		99.13 124	99.03 117	99.45 166	99.46 250	98.87 214	99.12 369	99.26 348	98.03 215	99.79 76	99.65 245	97.02 148	99.85 187	99.02 133	99.90 57	99.65 172
jason: jason.
lupinMVS		99.13 124	99.01 131	99.46 165	99.51 226	98.94 197	99.05 385	99.16 365	97.86 231	99.80 74	99.56 283	97.39 125	99.86 181	98.94 144	99.85 94	99.58 207

EPP-MVSNet		99.13 124	98.99 135	99.53 133	99.65 157	99.06 171	99.81 20	99.33 319	97.43 291	99.60 156	99.88 54	97.14 138	99.84 196	99.13 116	98.94 238	99.69 151

MG-MVS		99.13 124	99.02 126	99.45 166	99.57 201	98.63 244	99.07 379	99.34 311	98.99 69	99.61 153	99.82 116	97.98 113	99.87 175	97.00 355	99.80 125	99.85 46

KinetiMVS		99.12 132	98.92 152	99.70 87	99.67 135	99.40 121	99.67 75	99.63 46	98.73 102	99.94 28	99.81 131	94.54 286	99.96 41	98.40 229	99.93 33	99.74 115

BP-MVS1		99.12 132	98.94 149	99.65 95	99.51 226	99.30 138	99.67 75	98.92 397	98.48 126	99.84 56	99.69 224	94.96 250	99.92 123	99.62 44	99.79 132	99.71 145

CHOSEN 280x420		99.12 132	99.13 95	99.08 229	99.66 148	97.89 300	98.43 455	99.71 16	98.88 83	99.62 148	99.76 186	96.63 170	99.70 283	99.46 67	99.99 1	99.66 166

DP-MVS Recon		99.12 132	98.95 147	99.65 95	99.74 100	99.70 60	99.27 326	99.57 85	96.40 380	99.42 197	99.68 232	98.75 60	99.80 236	97.98 272	99.72 148	99.44 256

Vis-MVSNet		99.12 132	98.97 139	99.56 122	99.78 70	99.10 164	99.68 72	99.66 32	98.49 125	99.86 53	99.87 67	94.77 267	99.84 196	99.19 105	99.41 182	99.74 115
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 132	99.08 105	99.24 214	99.46 250	98.55 252	99.51 188	99.46 235	98.09 194	99.45 186	99.82 116	98.34 97	99.51 322	98.70 186	98.93 239	99.67 161

viewdifsd2359ckpt07		99.11 138	99.00 134	99.43 174	99.63 166	98.73 234	99.45 242	99.54 109	98.33 145	99.62 148	99.81 131	96.17 195	99.87 175	99.27 96	99.14 208	99.69 151

SDMVSNet		99.11 138	98.90 157	99.75 77	99.81 57	99.59 88	99.81 20	99.65 39	98.78 98	99.64 141	99.88 54	94.56 283	99.93 110	99.67 37	98.26 289	99.72 134

VNet		99.11 138	98.90 157	99.73 83	99.52 223	99.56 94	99.41 267	99.39 281	99.01 64	99.74 95	99.78 173	95.56 226	99.92 123	99.52 55	98.18 297	99.72 134

CPTT-MVS		99.11 138	98.90 157	99.74 80	99.80 63	99.46 114	99.59 121	99.49 189	97.03 331	99.63 144	99.69 224	97.27 133	99.96 41	97.82 286	99.84 102	99.81 79

HyFIR lowres test		99.11 138	98.92 152	99.65 95	99.90 4	99.37 123	99.02 393	99.91 3	97.67 261	99.59 159	99.75 191	95.90 210	99.73 266	99.53 53	99.02 234	99.86 42

MVS_Test		99.10 143	98.97 139	99.48 157	99.49 240	99.14 160	99.67 75	99.34 311	97.31 302	99.58 160	99.76 186	97.65 121	99.82 224	98.87 156	99.07 229	99.46 251

AstraMVS		99.09 144	99.03 117	99.25 211	99.66 148	98.13 283	99.57 139	98.24 449	98.82 89	99.91 31	99.88 54	95.81 215	99.90 148	99.72 32	99.67 158	99.74 115

CDS-MVSNet		99.09 144	99.03 117	99.25 211	99.42 260	98.73 234	99.45 242	99.46 235	98.11 190	99.46 185	99.77 182	98.01 112	99.37 346	98.70 186	98.92 241	99.66 166
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmacassd2359aftdt		99.08 146	98.94 149	99.50 149	99.66 148	98.96 187	99.51 188	99.54 109	98.27 152	99.42 197	99.89 43	95.88 212	99.80 236	99.20 104	99.11 218	99.76 107

mamba_0408		99.08 146	98.96 143	99.44 171	99.62 175	98.88 210	99.25 337	99.47 223	98.05 206	99.37 213	99.81 131	96.85 155	99.85 187	98.98 136	99.25 197	99.60 192

GDP-MVS		99.08 146	98.89 161	99.64 101	99.53 217	99.34 127	99.64 95	99.48 201	98.32 147	99.77 85	99.66 243	95.14 246	99.93 110	98.97 141	99.50 176	99.64 179

PVSNet_Blended		99.08 146	98.97 139	99.42 176	99.76 82	98.79 229	98.78 429	99.91 3	96.74 349	99.67 122	99.49 309	97.53 122	99.88 168	98.98 136	99.85 94	99.60 192

OMC-MVS		99.08 146	99.04 114	99.20 218	99.67 135	98.22 278	99.28 321	99.52 131	98.07 199	99.66 127	99.81 131	97.79 117	99.78 248	97.79 290	99.81 120	99.60 192

viewdifsd2359ckpt13		99.06 151	98.93 151	99.45 166	99.63 166	98.96 187	99.50 199	99.51 153	97.83 238	99.28 237	99.80 149	96.68 169	99.71 276	99.05 128	99.12 216	99.68 157

SSM_04072		99.06 151	98.96 143	99.35 187	99.62 175	98.88 210	99.25 337	99.47 223	98.05 206	99.37 213	99.81 131	96.85 155	99.58 314	98.98 136	99.25 197	99.60 192

mvsmamba		99.06 151	98.96 143	99.36 185	99.47 248	98.64 243	99.70 58	99.05 381	97.61 267	99.65 136	99.83 103	96.54 177	99.92 123	99.19 105	99.62 165	99.51 232

WTY-MVS		99.06 151	98.88 164	99.61 109	99.62 175	99.16 155	99.37 286	99.56 90	98.04 213	99.53 173	99.62 262	96.84 159	99.94 92	98.85 163	98.49 274	99.72 134

IS-MVSNet		99.05 155	98.87 165	99.57 120	99.73 107	99.32 131	99.75 42	99.20 360	98.02 218	99.56 164	99.86 75	96.54 177	99.67 291	98.09 260	99.13 211	99.73 124

PAPM_NR		99.04 156	98.84 173	99.66 91	99.74 100	99.44 116	99.39 279	99.38 289	97.70 257	99.28 237	99.28 372	98.34 97	99.85 187	96.96 359	99.45 179	99.69 151

API-MVS		99.04 156	99.03 117	99.06 232	99.40 270	99.31 135	99.55 162	99.56 90	98.54 120	99.33 227	99.39 341	98.76 57	99.78 248	96.98 357	99.78 134	98.07 436

mvs_anonymous		99.03 158	98.99 135	99.16 222	99.38 275	98.52 258	99.51 188	99.38 289	97.79 244	99.38 211	99.81 131	97.30 131	99.45 328	99.35 76	98.99 236	99.51 232

sasdasda		99.02 159	98.86 168	99.51 144	99.42 260	99.32 131	99.80 25	99.48 201	98.63 110	99.31 229	98.81 423	97.09 143	99.75 257	99.27 96	97.90 308	99.47 246

train_agg		99.02 159	98.77 180	99.77 74	99.67 135	99.65 75	99.05 385	99.41 271	96.28 384	98.95 310	99.49 309	98.76 57	99.91 135	97.63 307	99.72 148	99.75 110

canonicalmvs		99.02 159	98.86 168	99.51 144	99.42 260	99.32 131	99.80 25	99.48 201	98.63 110	99.31 229	98.81 423	97.09 143	99.75 257	99.27 96	97.90 308	99.47 246

PLC	97.94 4	99.02 159	98.85 171	99.53 133	99.66 148	99.01 177	99.24 342	99.52 131	96.85 343	99.27 243	99.48 315	98.25 101	99.91 135	97.76 295	99.62 165	99.65 172
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
viewdifsd2359ckpt09		99.01 163	98.87 165	99.40 178	99.62 175	98.79 229	99.44 249	99.51 153	97.76 248	99.35 222	99.69 224	96.42 185	99.75 257	98.97 141	99.11 218	99.66 166

viewmambaseed2359dif		99.01 163	98.90 157	99.32 194	99.58 196	98.51 260	99.33 302	99.54 109	97.85 234	99.44 191	99.85 82	96.01 202	99.79 242	99.41 70	99.13 211	99.67 161

MGCFI-Net		99.01 163	98.85 171	99.50 149	99.42 260	99.26 144	99.82 16	99.48 201	98.60 115	99.28 237	98.81 423	97.04 147	99.76 254	99.29 92	97.87 311	99.47 246

AdaColmap		99.01 163	98.80 176	99.66 91	99.56 205	99.54 98	99.18 358	99.70 18	98.18 173	99.35 222	99.63 257	96.32 188	99.90 148	97.48 323	99.77 137	99.55 214

1112_ss		98.98 167	98.77 180	99.59 113	99.68 132	99.02 175	99.25 337	99.48 201	97.23 310	99.13 273	99.58 275	96.93 153	99.90 148	98.87 156	98.78 256	99.84 53

MSDG		98.98 167	98.80 176	99.53 133	99.76 82	99.19 150	98.75 432	99.55 100	97.25 307	99.47 183	99.77 182	97.82 116	99.87 175	96.93 362	99.90 57	99.54 216

CANet_DTU		98.97 169	98.87 165	99.25 211	99.33 288	98.42 271	99.08 378	99.30 338	99.16 37	99.43 194	99.75 191	95.27 238	99.97 29	98.56 213	99.95 23	99.36 269

DPM-MVS		98.95 170	98.71 188	99.66 91	99.63 166	99.55 96	98.64 443	99.10 372	97.93 224	99.42 197	99.55 286	98.67 72	99.80 236	95.80 396	99.68 156	99.61 189

114514_t		98.93 171	98.67 192	99.72 86	99.85 31	99.53 101	99.62 106	99.59 73	92.65 451	99.71 109	99.78 173	98.06 110	99.90 148	98.84 166	99.91 46	99.74 115

PS-MVSNAJss		98.92 172	98.92 152	98.90 259	98.78 404	98.53 254	99.78 32	99.54 109	98.07 199	99.00 301	99.76 186	99.01 20	99.37 346	99.13 116	97.23 351	98.81 321

RRT-MVS		98.91 173	98.75 182	99.39 183	99.46 250	98.61 248	99.76 37	99.50 176	98.06 203	99.81 69	99.88 54	93.91 315	99.94 92	99.11 119	99.27 194	99.61 189

Test_1112_low_res		98.89 174	98.66 195	99.57 120	99.69 127	98.95 193	99.03 390	99.47 223	96.98 333	99.15 271	99.23 380	96.77 164	99.89 163	98.83 169	98.78 256	99.86 42

Elysia		98.88 175	98.65 197	99.58 116	99.58 196	99.34 127	99.65 88	99.52 131	98.26 155	99.83 64	99.87 67	93.37 326	99.90 148	97.81 288	99.91 46	99.49 237

StellarMVS		98.88 175	98.65 197	99.58 116	99.58 196	99.34 127	99.65 88	99.52 131	98.26 155	99.83 64	99.87 67	93.37 326	99.90 148	97.81 288	99.91 46	99.49 237

test_fmvs1		98.88 175	98.79 179	99.16 222	99.69 127	97.61 316	99.55 162	99.49 189	99.32 29	99.98 13	99.91 26	91.41 380	99.96 41	99.82 29	99.92 39	99.90 25

AllTest		98.87 178	98.72 186	99.31 196	99.86 25	98.48 265	99.56 147	99.61 60	97.85 234	99.36 219	99.85 82	95.95 205	99.85 187	96.66 375	99.83 113	99.59 203

UGNet		98.87 178	98.69 190	99.40 178	99.22 321	98.72 236	99.44 249	99.68 24	99.24 32	99.18 268	99.42 329	92.74 342	99.96 41	99.34 81	99.94 31	99.53 222
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)		98.87 178	98.72 186	99.31 196	99.71 117	98.88 210	99.80 25	99.44 255	97.91 226	99.36 219	99.78 173	95.49 229	99.43 337	97.91 276	99.11 218	99.62 187

IMVS_0407		98.86 181	98.91 155	98.72 293	99.55 209	96.93 356	99.50 199	99.44 255	98.05 206	99.66 127	99.80 149	97.13 139	99.65 299	98.15 255	98.92 241	99.60 192

IMVS_0403		98.86 181	98.89 161	98.78 288	99.55 209	96.93 356	99.58 131	99.44 255	98.05 206	99.68 116	99.80 149	96.81 161	99.80 236	98.15 255	98.92 241	99.60 192

test_yl		98.86 181	98.63 200	99.54 125	99.49 240	99.18 152	99.50 199	99.07 378	98.22 166	99.61 153	99.51 303	95.37 233	99.84 196	98.60 204	98.33 281	99.59 203

DCV-MVSNet		98.86 181	98.63 200	99.54 125	99.49 240	99.18 152	99.50 199	99.07 378	98.22 166	99.61 153	99.51 303	95.37 233	99.84 196	98.60 204	98.33 281	99.59 203

EPNet		98.86 181	98.71 188	99.30 201	97.20 458	98.18 279	99.62 106	98.91 402	99.28 31	98.63 362	99.81 131	95.96 204	99.99 4	99.24 100	99.72 148	99.73 124
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 181	98.80 176	99.03 236	99.76 82	98.79 229	99.28 321	99.91 3	97.42 293	99.67 122	99.37 347	97.53 122	99.88 168	98.98 136	97.29 349	98.42 414

ab-mvs		98.86 181	98.63 200	99.54 125	99.64 162	99.19 150	99.44 249	99.54 109	97.77 247	99.30 233	99.81 131	94.20 300	99.93 110	99.17 111	98.82 253	99.49 237

MAR-MVS		98.86 181	98.63 200	99.54 125	99.37 278	99.66 71	99.45 242	99.54 109	96.61 361	99.01 297	99.40 337	97.09 143	99.86 181	97.68 306	99.53 173	99.10 292
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	98.86 181	98.75 182	99.17 221	99.88 13	98.53 254	99.34 300	99.59 73	97.55 274	98.70 350	99.89 43	95.83 213	99.90 148	98.10 259	99.90 57	99.08 297
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 190	98.62 205	99.53 133	99.61 186	99.08 168	99.80 25	99.51 153	97.10 323	99.31 229	99.78 173	95.23 243	99.77 250	98.21 247	99.03 232	99.75 110

HY-MVS	97.30 7	98.85 190	98.64 199	99.47 163	99.42 260	99.08 168	99.62 106	99.36 299	97.39 296	99.28 237	99.68 232	96.44 183	99.92 123	98.37 233	98.22 292	99.40 263

PVSNet	96.02 17	98.85 190	98.84 173	98.89 263	99.73 107	97.28 326	98.32 461	99.60 67	97.86 231	99.50 178	99.57 280	96.75 165	99.86 181	98.56 213	99.70 152	99.54 216

PatchMatch-RL		98.84 193	98.62 205	99.52 139	99.71 117	99.28 141	99.06 383	99.77 12	97.74 252	99.50 178	99.53 295	95.41 231	99.84 196	97.17 348	99.64 162	99.44 256

Effi-MVS+		98.81 194	98.59 211	99.48 157	99.46 250	99.12 163	98.08 468	99.50 176	97.50 282	99.38 211	99.41 333	96.37 187	99.81 229	99.11 119	98.54 271	99.51 232

alignmvs		98.81 194	98.56 214	99.58 116	99.43 258	99.42 118	99.51 188	98.96 392	98.61 113	99.35 222	98.92 418	94.78 264	99.77 250	99.35 76	98.11 302	99.54 216

DeepPCF-MVS	98.18 3	98.81 194	99.37 44	97.12 417	99.60 192	91.75 459	98.61 444	99.44 255	99.35 25	99.83 64	99.85 82	98.70 69	99.81 229	99.02 133	99.91 46	99.81 79

PMMVS		98.80 197	98.62 205	99.34 188	99.27 306	98.70 237	98.76 431	99.31 333	97.34 299	99.21 258	99.07 396	97.20 137	99.82 224	98.56 213	98.87 248	99.52 223

icg_test_0407_2		98.79 198	98.86 168	98.57 309	99.55 209	96.93 356	99.07 379	99.44 255	98.05 206	99.66 127	99.80 149	97.13 139	99.18 386	98.15 255	98.92 241	99.60 192

viewdifsd2359ckpt11		98.78 199	98.74 184	98.89 263	99.67 135	97.04 345	99.50 199	99.58 78	98.26 155	99.56 164	99.90 34	94.36 293	99.87 175	99.49 61	98.32 285	99.77 100

viewmsd2359difaftdt		98.78 199	98.74 184	98.90 259	99.67 135	97.04 345	99.50 199	99.58 78	98.26 155	99.56 164	99.90 34	94.36 293	99.87 175	99.49 61	98.32 285	99.77 100

Effi-MVS+-dtu		98.78 199	98.89 161	98.47 327	99.33 288	96.91 361	99.57 139	99.30 338	98.47 127	99.41 202	98.99 408	96.78 163	99.74 260	98.73 183	99.38 183	98.74 336

FIs		98.78 199	98.63 200	99.23 216	99.18 330	99.54 98	99.83 15	99.59 73	98.28 150	98.79 337	99.81 131	96.75 165	99.37 346	99.08 125	96.38 368	98.78 324

Fast-Effi-MVS+-dtu		98.77 203	98.83 175	98.60 304	99.41 265	96.99 351	99.52 178	99.49 189	98.11 190	99.24 250	99.34 357	96.96 152	99.79 242	97.95 274	99.45 179	99.02 307

sd_testset		98.75 204	98.57 212	99.29 204	99.81 57	98.26 276	99.56 147	99.62 51	98.78 98	99.64 141	99.88 54	92.02 364	99.88 168	99.54 51	98.26 289	99.72 134

FA-MVS(test-final)		98.75 204	98.53 216	99.41 177	99.55 209	99.05 173	99.80 25	99.01 386	96.59 366	99.58 160	99.59 271	95.39 232	99.90 148	97.78 291	99.49 177	99.28 278

FC-MVSNet-test		98.75 204	98.62 205	99.15 226	99.08 357	99.45 115	99.86 11	99.60 67	98.23 165	98.70 350	99.82 116	96.80 162	99.22 378	99.07 126	96.38 368	98.79 322

XVG-OURS		98.73 207	98.68 191	98.88 267	99.70 122	97.73 307	98.92 415	99.55 100	98.52 122	99.45 186	99.84 97	95.27 238	99.91 135	98.08 264	98.84 251	99.00 308

Fast-Effi-MVS+		98.70 208	98.43 221	99.51 144	99.51 226	99.28 141	99.52 178	99.47 223	96.11 400	99.01 297	99.34 357	96.20 194	99.84 196	97.88 278	98.82 253	99.39 264

XVG-OURS-SEG-HR		98.69 209	98.62 205	98.89 263	99.71 117	97.74 306	99.12 369	99.54 109	98.44 133	99.42 197	99.71 209	94.20 300	99.92 123	98.54 217	98.90 247	99.00 308

1314		98.68 210	98.54 215	99.11 228	98.89 387	98.65 241	99.27 326	99.49 189	96.89 341	97.99 402	99.56 283	97.72 120	99.83 215	97.74 298	99.27 194	98.84 320

VortexMVS		98.67 211	98.66 195	98.68 299	99.62 175	97.96 294	99.59 121	99.41 271	98.13 183	99.31 229	99.70 213	95.48 230	99.27 366	99.40 71	97.32 348	98.79 322

EI-MVSNet		98.67 211	98.67 192	98.68 299	99.35 282	97.97 292	99.50 199	99.38 289	96.93 340	99.20 261	99.83 103	97.87 114	99.36 350	98.38 231	97.56 327	98.71 340

test_djsdf		98.67 211	98.57 212	98.98 242	98.70 418	98.91 204	99.88 4	99.46 235	97.55 274	99.22 255	99.88 54	95.73 220	99.28 363	99.03 131	97.62 322	98.75 332

QAPM		98.67 211	98.30 231	99.80 64	99.20 324	99.67 68	99.77 34	99.72 14	94.74 428	98.73 342	99.90 34	95.78 218	99.98 20	96.96 359	99.88 76	99.76 107

nrg030		98.64 215	98.42 222	99.28 208	99.05 363	99.69 63	99.81 20	99.46 235	98.04 213	99.01 297	99.82 116	96.69 167	99.38 343	99.34 81	94.59 413	98.78 324

test_vis1_n_1920		98.63 216	98.40 224	99.31 196	99.86 25	97.94 299	99.67 75	99.62 51	99.43 17	99.99 2	99.91 26	87.29 431	100.00 1	99.92 24	99.92 39	99.98 2

PAPR		98.63 216	98.34 227	99.51 144	99.40 270	99.03 174	98.80 427	99.36 299	96.33 381	99.00 301	99.12 394	98.46 87	99.84 196	95.23 411	99.37 190	99.66 166

CVMVSNet		98.57 218	98.67 192	98.30 347	99.35 282	95.59 404	99.50 199	99.55 100	98.60 115	99.39 209	99.83 103	94.48 289	99.45 328	98.75 180	98.56 269	99.85 46

IMVS_0404		98.53 219	98.52 217	98.55 315	99.55 209	96.93 356	99.20 354	99.44 255	98.05 206	98.96 308	99.80 149	94.66 278	99.13 394	98.15 255	98.92 241	99.60 192

MVSTER		98.49 220	98.32 229	99.00 240	99.35 282	99.02 175	99.54 167	99.38 289	97.41 294	99.20 261	99.73 202	93.86 317	99.36 350	98.87 156	97.56 327	98.62 384

FE-MVS		98.48 221	98.17 236	99.40 178	99.54 216	98.96 187	99.68 72	98.81 416	95.54 411	99.62 148	99.70 213	93.82 318	99.93 110	97.35 335	99.46 178	99.32 275

OpenMVS	96.50 16	98.47 222	98.12 243	99.52 139	99.04 365	99.53 101	99.82 16	99.72 14	94.56 431	98.08 397	99.88 54	94.73 271	99.98 20	97.47 325	99.76 140	99.06 303

IterMVS-LS		98.46 223	98.42 222	98.58 308	99.59 194	98.00 290	99.37 286	99.43 266	96.94 339	99.07 286	99.59 271	97.87 114	99.03 409	98.32 240	95.62 391	98.71 340
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 224	98.28 232	98.94 249	98.50 435	98.96 187	99.77 34	99.50 176	97.07 325	98.87 323	99.77 182	94.76 268	99.28 363	98.66 193	97.60 323	98.57 399

jajsoiax		98.43 225	98.28 232	98.88 267	98.60 429	98.43 269	99.82 16	99.53 125	98.19 170	98.63 362	99.80 149	93.22 331	99.44 333	99.22 101	97.50 334	98.77 328

tttt0517		98.42 226	98.14 240	99.28 208	99.66 148	98.38 272	99.74 47	96.85 467	97.68 259	99.79 76	99.74 196	91.39 381	99.89 163	98.83 169	99.56 170	99.57 210

BH-untuned		98.42 226	98.36 225	98.59 305	99.49 240	96.70 369	99.27 326	99.13 369	97.24 309	98.80 335	99.38 344	95.75 219	99.74 260	97.07 353	99.16 204	99.33 274

test_fmvs1_n		98.41 228	98.14 240	99.21 217	99.82 53	97.71 312	99.74 47	99.49 189	99.32 29	99.99 2	99.95 3	85.32 446	99.97 29	99.82 29	99.84 102	99.96 7

D2MVS		98.41 228	98.50 218	98.15 362	99.26 309	96.62 375	99.40 275	99.61 60	97.71 254	98.98 304	99.36 350	96.04 200	99.67 291	98.70 186	97.41 344	98.15 432

BH-RMVSNet		98.41 228	98.08 249	99.40 178	99.41 265	98.83 223	99.30 311	98.77 422	97.70 257	98.94 312	99.65 245	92.91 338	99.74 260	96.52 379	99.55 172	99.64 179

mvs_tets		98.40 231	98.23 234	98.91 257	98.67 422	98.51 260	99.66 82	99.53 125	98.19 170	98.65 359	99.81 131	92.75 340	99.44 333	99.31 86	97.48 338	98.77 328

MonoMVSNet		98.38 232	98.47 220	98.12 364	98.59 431	96.19 392	99.72 53	98.79 420	97.89 228	99.44 191	99.52 299	96.13 196	98.90 431	98.64 195	97.54 329	99.28 278

XXY-MVS		98.38 232	98.09 248	99.24 214	99.26 309	99.32 131	99.56 147	99.55 100	97.45 287	98.71 344	99.83 103	93.23 329	99.63 309	98.88 153	96.32 370	98.76 330

ACMM	97.58 5	98.37 234	98.34 227	98.48 322	99.41 265	97.10 336	99.56 147	99.45 246	98.53 121	99.04 294	99.85 82	93.00 334	99.71 276	98.74 181	97.45 339	98.64 375
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 235	98.03 255	99.31 196	99.63 166	98.56 251	99.54 167	96.75 469	97.53 278	99.73 97	99.65 245	91.25 385	99.89 163	98.62 198	99.56 170	99.48 240

tpmrst		98.33 236	98.48 219	97.90 381	99.16 340	94.78 426	99.31 309	99.11 371	97.27 305	99.45 186	99.59 271	95.33 236	99.84 196	98.48 220	98.61 263	99.09 296

baseline1		98.31 237	97.95 264	99.38 184	99.50 238	98.74 233	99.59 121	98.93 394	98.41 135	99.14 272	99.60 269	94.59 281	99.79 242	98.48 220	93.29 433	99.61 189

PatchmatchNet		98.31 237	98.36 225	98.19 357	99.16 340	95.32 415	99.27 326	98.92 397	97.37 297	99.37 213	99.58 275	94.90 257	99.70 283	97.43 330	99.21 201	99.54 216
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 239	97.98 260	99.26 210	99.57 201	98.16 280	99.41 267	98.55 441	96.03 405	99.19 264	99.74 196	91.87 367	99.92 123	99.16 114	98.29 288	99.70 148

VPA-MVSNet		98.29 240	97.95 264	99.30 201	99.16 340	99.54 98	99.50 199	99.58 78	98.27 152	99.35 222	99.37 347	92.53 352	99.65 299	99.35 76	94.46 414	98.72 338

UniMVSNet (Re)		98.29 240	98.00 258	99.13 227	99.00 370	99.36 126	99.49 216	99.51 153	97.95 222	98.97 306	99.13 391	96.30 191	99.38 343	98.36 235	93.34 432	98.66 371

HQP_MVS		98.27 242	98.22 235	98.44 333	99.29 301	96.97 353	99.39 279	99.47 223	98.97 75	99.11 277	99.61 266	92.71 345	99.69 288	97.78 291	97.63 320	98.67 362

UniMVSNet_NR-MVSNet		98.22 243	97.97 261	98.96 245	98.92 383	98.98 180	99.48 224	99.53 125	97.76 248	98.71 344	99.46 322	96.43 184	99.22 378	98.57 210	92.87 440	98.69 349

LPG-MVS_test		98.22 243	98.13 242	98.49 320	99.33 288	97.05 342	99.58 131	99.55 100	97.46 284	99.24 250	99.83 103	92.58 350	99.72 270	98.09 260	97.51 332	98.68 354

RPSCF		98.22 243	98.62 205	96.99 420	99.82 53	91.58 460	99.72 53	99.44 255	96.61 361	99.66 127	99.89 43	95.92 208	99.82 224	97.46 326	99.10 225	99.57 210

ADS-MVSNet		98.20 246	98.08 249	98.56 313	99.33 288	96.48 380	99.23 345	99.15 366	96.24 388	99.10 280	99.67 238	94.11 305	99.71 276	96.81 367	99.05 230	99.48 240

OPM-MVS		98.19 247	98.10 245	98.45 330	98.88 388	97.07 340	99.28 321	99.38 289	98.57 117	99.22 255	99.81 131	92.12 362	99.66 294	98.08 264	97.54 329	98.61 393
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 247	98.16 237	98.27 353	99.30 297	95.55 405	99.07 379	98.97 390	97.57 271	99.43 194	99.57 280	92.72 343	99.74 260	97.58 311	99.20 202	99.52 223

miper_ehance_all_eth		98.18 249	98.10 245	98.41 336	99.23 317	97.72 309	98.72 435	99.31 333	96.60 364	98.88 320	99.29 370	97.29 132	99.13 394	97.60 309	95.99 379	98.38 419

CR-MVSNet		98.17 250	97.93 267	98.87 271	99.18 330	98.49 263	99.22 349	99.33 319	96.96 335	99.56 164	99.38 344	94.33 296	99.00 414	94.83 418	98.58 266	99.14 289

miper_enhance_ethall		98.16 251	98.08 249	98.41 336	98.96 379	97.72 309	98.45 454	99.32 329	96.95 337	98.97 306	99.17 386	97.06 146	99.22 378	97.86 281	95.99 379	98.29 423

CLD-MVS		98.16 251	98.10 245	98.33 343	99.29 301	96.82 366	98.75 432	99.44 255	97.83 238	99.13 273	99.55 286	92.92 336	99.67 291	98.32 240	97.69 318	98.48 406
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 253	97.79 280	99.19 219	99.50 238	98.50 262	98.61 444	96.82 468	96.95 337	99.54 171	99.43 327	91.66 376	99.86 181	98.08 264	99.51 174	99.22 286

pmmvs4		98.13 254	97.90 269	98.81 283	98.61 428	98.87 214	98.99 401	99.21 359	96.44 376	99.06 291	99.58 275	95.90 210	99.11 400	97.18 347	96.11 375	98.46 411

WR-MVS_H		98.13 254	97.87 274	98.90 259	99.02 367	98.84 220	99.70 58	99.59 73	97.27 305	98.40 379	99.19 385	95.53 227	99.23 373	98.34 237	93.78 428	98.61 393

c3_l		98.12 256	98.04 254	98.38 340	99.30 297	97.69 313	98.81 426	99.33 319	96.67 354	98.83 330	99.34 357	97.11 142	98.99 415	97.58 311	95.34 398	98.48 406

ACMH	97.28 8	98.10 257	97.99 259	98.44 333	99.41 265	96.96 355	99.60 113	99.56 90	98.09 194	98.15 395	99.91 26	90.87 389	99.70 283	98.88 153	97.45 339	98.67 362
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FE-MVSNET3		98.09 258	97.82 278	98.89 263	98.70 418	98.90 207	98.57 447	99.47 223	96.78 347	98.87 323	99.05 399	94.75 269	99.23 373	97.45 328	96.74 359	98.53 401

Anonymous20240529		98.09 258	97.68 297	99.34 188	99.66 148	98.44 268	99.40 275	99.43 266	93.67 438	99.22 255	99.89 43	90.23 397	99.93 110	99.26 99	98.33 281	99.66 166

CP-MVSNet		98.09 258	97.78 283	99.01 238	98.97 378	99.24 147	99.67 75	99.46 235	97.25 307	98.48 376	99.64 251	93.79 319	99.06 405	98.63 197	94.10 422	98.74 336

dmvs_re		98.08 261	98.16 237	97.85 385	99.55 209	94.67 431	99.70 58	98.92 397	98.15 175	99.06 291	99.35 353	93.67 323	99.25 370	97.77 294	97.25 350	99.64 179

DU-MVS		98.08 261	97.79 280	98.96 245	98.87 391	98.98 180	99.41 267	99.45 246	97.87 230	98.71 344	99.50 306	94.82 260	99.22 378	98.57 210	92.87 440	98.68 354

v2v482		98.06 263	97.77 285	98.92 253	98.90 386	98.82 226	99.57 139	99.36 299	96.65 356	99.19 264	99.35 353	94.20 300	99.25 370	97.72 301	94.97 406	98.69 349

V42		98.06 263	97.79 280	98.86 274	98.98 376	98.84 220	99.69 62	99.34 311	96.53 368	99.30 233	99.37 347	94.67 276	99.32 358	97.57 315	94.66 411	98.42 414

test-LLR		98.06 263	97.90 269	98.55 315	98.79 401	97.10 336	98.67 438	97.75 458	97.34 299	98.61 366	98.85 420	94.45 291	99.45 328	97.25 339	99.38 183	99.10 292

WR-MVS		98.06 263	97.73 292	99.06 232	98.86 394	99.25 146	99.19 356	99.35 306	97.30 303	98.66 353	99.43 327	93.94 312	99.21 383	98.58 207	94.28 418	98.71 340

ACMP	97.20 11	98.06 263	97.94 266	98.45 330	99.37 278	97.01 349	99.44 249	99.49 189	97.54 277	98.45 377	99.79 166	91.95 366	99.72 270	97.91 276	97.49 337	98.62 384
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 268	97.96 262	98.33 343	99.26 309	97.38 323	98.56 450	99.31 333	96.65 356	98.88 320	99.52 299	96.58 174	99.12 399	97.39 332	95.53 395	98.47 408

test1111		98.04 269	98.11 244	97.83 388	99.74 100	93.82 442	99.58 131	95.40 476	99.12 46	99.65 136	99.93 10	90.73 390	99.84 196	99.43 69	99.38 183	99.82 72

ECVR-MVS		98.04 269	98.05 253	98.00 372	99.74 100	94.37 437	99.59 121	94.98 477	99.13 41	99.66 127	99.93 10	90.67 391	99.84 196	99.40 71	99.38 183	99.80 88

EPNet_dtu		98.03 271	97.96 262	98.23 355	98.27 440	95.54 407	99.23 345	98.75 423	99.02 62	97.82 411	99.71 209	96.11 197	99.48 323	93.04 440	99.65 161	99.69 151
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 271	97.76 289	98.84 278	99.39 273	98.98 180	99.40 275	99.38 289	96.67 354	99.07 286	99.28 372	92.93 335	98.98 416	97.10 349	96.65 361	98.56 400

ADS-MVSNet2		98.02 273	98.07 252	97.87 383	99.33 288	95.19 418	99.23 345	99.08 375	96.24 388	99.10 280	99.67 238	94.11 305	98.93 428	96.81 367	99.05 230	99.48 240

HQP-MVS		98.02 273	97.90 269	98.37 341	99.19 327	96.83 364	98.98 404	99.39 281	98.24 162	98.66 353	99.40 337	92.47 354	99.64 303	97.19 345	97.58 325	98.64 375

LTVRE_ROB	97.16 12	98.02 273	97.90 269	98.40 338	99.23 317	96.80 367	99.70 58	99.60 67	97.12 319	98.18 394	99.70 213	91.73 372	99.72 270	98.39 230	97.45 339	98.68 354
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____		98.01 276	97.84 277	98.55 315	99.25 313	97.97 292	98.71 436	99.34 311	96.47 375	98.59 369	99.54 291	95.65 223	99.21 383	97.21 341	95.77 385	98.46 411

DIV-MVS_self_test		98.01 276	97.85 276	98.48 322	99.24 315	97.95 297	98.71 436	99.35 306	96.50 369	98.60 368	99.54 291	95.72 221	99.03 409	97.21 341	95.77 385	98.46 411

miper_lstm_enhance		98.00 278	97.91 268	98.28 352	99.34 287	97.43 321	98.88 419	99.36 299	96.48 373	98.80 335	99.55 286	95.98 203	98.91 429	97.27 338	95.50 396	98.51 404

BH-w/o		98.00 278	97.89 273	98.32 345	99.35 282	96.20 391	99.01 398	98.90 404	96.42 378	98.38 380	99.00 406	95.26 240	99.72 270	96.06 389	98.61 263	99.03 305

v1144		97.98 280	97.69 296	98.85 277	98.87 391	98.66 240	99.54 167	99.35 306	96.27 386	99.23 254	99.35 353	94.67 276	99.23 373	96.73 370	95.16 402	98.68 354

EU-MVSNet		97.98 280	98.03 255	97.81 391	98.72 415	96.65 374	99.66 82	99.66 32	98.09 194	98.35 382	99.82 116	95.25 241	98.01 452	97.41 331	95.30 399	98.78 324

tpmvs		97.98 280	98.02 257	97.84 387	99.04 365	94.73 427	99.31 309	99.20 360	96.10 404	98.76 340	99.42 329	94.94 252	99.81 229	96.97 358	98.45 275	98.97 312

tt0805		97.97 283	97.77 285	98.57 309	99.59 194	96.61 376	99.45 242	99.08 375	98.21 168	98.88 320	99.80 149	88.66 415	99.70 283	98.58 207	97.72 317	99.39 264

NR-MVSNet		97.97 283	97.61 306	99.02 237	98.87 391	99.26 144	99.47 234	99.42 268	97.63 264	97.08 430	99.50 306	95.07 248	99.13 394	97.86 281	93.59 429	98.68 354

v8		97.95 285	97.63 304	98.93 251	98.95 380	98.81 228	99.80 25	99.41 271	96.03 405	99.10 280	99.42 329	94.92 255	99.30 361	96.94 361	94.08 423	98.66 371

Patchmatch-test		97.93 286	97.65 300	98.77 289	99.18 330	97.07 340	99.03 390	99.14 368	96.16 395	98.74 341	99.57 280	94.56 283	99.72 270	93.36 435	99.11 218	99.52 223

PS-CasMVS		97.93 286	97.59 308	98.95 247	98.99 373	99.06 171	99.68 72	99.52 131	97.13 317	98.31 384	99.68 232	92.44 358	99.05 406	98.51 218	94.08 423	98.75 332

TranMVSNet+NR-MVSNet		97.93 286	97.66 299	98.76 290	98.78 404	98.62 246	99.65 88	99.49 189	97.76 248	98.49 375	99.60 269	94.23 299	98.97 423	98.00 271	92.90 438	98.70 345

test_vis1_n		97.92 289	97.44 330	99.34 188	99.53 217	98.08 286	99.74 47	99.49 189	99.15 38	100.00 1	99.94 6	79.51 468	99.98 20	99.88 26	99.76 140	99.97 4

v144192		97.92 289	97.60 307	98.87 271	98.83 398	98.65 241	99.55 162	99.34 311	96.20 391	99.32 228	99.40 337	94.36 293	99.26 369	96.37 386	95.03 405	98.70 345

ACMH+	97.24 10	97.92 289	97.78 283	98.32 345	99.46 250	96.68 373	99.56 147	99.54 109	98.41 135	97.79 413	99.87 67	90.18 398	99.66 294	98.05 268	97.18 354	98.62 384

LFMVS		97.90 292	97.35 342	99.54 125	99.52 223	99.01 177	99.39 279	98.24 449	97.10 323	99.65 136	99.79 166	84.79 449	99.91 135	99.28 93	98.38 278	99.69 151

reproduce_monomvs		97.89 293	97.87 274	97.96 376	99.51 226	95.45 410	99.60 113	99.25 350	99.17 36	98.85 329	99.49 309	89.29 407	99.64 303	99.35 76	96.31 371	98.78 324

Anonymous20231211		97.88 294	97.54 312	98.90 259	99.71 117	98.53 254	99.48 224	99.57 85	94.16 434	98.81 333	99.68 232	93.23 329	99.42 339	98.84 166	94.42 416	98.76 330

OurMVSNet-221017-0		97.88 294	97.77 285	98.19 357	98.71 417	96.53 378	99.88 4	99.00 387	97.79 244	98.78 338	99.94 6	91.68 373	99.35 353	97.21 341	96.99 358	98.69 349

v7n		97.87 296	97.52 314	98.92 253	98.76 411	98.58 250	99.84 12	99.46 235	96.20 391	98.91 315	99.70 213	94.89 258	99.44 333	96.03 390	93.89 426	98.75 332

baseline2		97.87 296	97.55 309	98.82 280	99.18 330	98.02 289	99.41 267	96.58 473	96.97 334	96.51 437	99.17 386	93.43 324	99.57 315	97.71 302	99.03 232	98.86 318

thres600view7		97.86 298	97.51 316	98.92 253	99.72 111	97.95 297	99.59 121	98.74 426	97.94 223	99.27 243	98.62 431	91.75 370	99.86 181	93.73 431	98.19 296	98.96 314

UBG		97.85 299	97.48 319	98.95 247	99.25 313	97.64 314	99.24 342	98.74 426	97.90 227	98.64 360	98.20 448	88.65 416	99.81 229	98.27 243	98.40 276	99.42 258

cl22		97.85 299	97.64 303	98.48 322	99.09 354	97.87 301	98.60 446	99.33 319	97.11 322	98.87 323	99.22 381	92.38 359	99.17 388	98.21 247	95.99 379	98.42 414

v10		97.85 299	97.52 314	98.86 274	98.99 373	98.67 239	99.75 42	99.41 271	95.70 409	98.98 304	99.41 333	94.75 269	99.23 373	96.01 392	94.63 412	98.67 362

GA-MVS		97.85 299	97.47 322	99.00 240	99.38 275	97.99 291	98.57 447	99.15 366	97.04 330	98.90 317	99.30 368	89.83 401	99.38 343	96.70 372	98.33 281	99.62 187

testing3-2		97.84 303	97.70 295	98.24 354	99.53 217	95.37 414	99.55 162	98.67 436	98.46 128	99.27 243	99.34 357	86.58 435	99.83 215	99.32 84	98.63 262	99.52 223

tfpnnormal		97.84 303	97.47 322	98.98 242	99.20 324	99.22 149	99.64 95	99.61 60	96.32 382	98.27 388	99.70 213	93.35 328	99.44 333	95.69 399	95.40 397	98.27 424

VPNet		97.84 303	97.44 330	99.01 238	99.21 322	98.94 197	99.48 224	99.57 85	98.38 137	99.28 237	99.73 202	88.89 410	99.39 341	99.19 105	93.27 434	98.71 340

LCM-MVSNet-Re		97.83 306	98.15 239	96.87 426	99.30 297	92.25 457	99.59 121	98.26 447	97.43 291	96.20 441	99.13 391	96.27 192	98.73 438	98.17 252	98.99 236	99.64 179

XVG-ACMP-BASELINE		97.83 306	97.71 294	98.20 356	99.11 348	96.33 385	99.41 267	99.52 131	98.06 203	99.05 293	99.50 306	89.64 404	99.73 266	97.73 299	97.38 346	98.53 401

IterMVS		97.83 306	97.77 285	98.02 369	99.58 196	96.27 388	99.02 393	99.48 201	97.22 311	98.71 344	99.70 213	92.75 340	99.13 394	97.46 326	96.00 378	98.67 362
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 309	97.75 290	98.06 366	99.57 201	96.36 384	99.02 393	99.49 189	97.18 313	98.71 344	99.72 206	92.72 343	99.14 391	97.44 329	95.86 384	98.67 362

EPMVS		97.82 309	97.65 300	98.35 342	98.88 388	95.98 395	99.49 216	94.71 479	97.57 271	99.26 248	99.48 315	92.46 357	99.71 276	97.87 280	99.08 228	99.35 270

MVP-Stereo		97.81 311	97.75 290	97.99 373	97.53 451	96.60 377	98.96 408	98.85 411	97.22 311	97.23 424	99.36 350	95.28 237	99.46 326	95.51 403	99.78 134	97.92 449
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 311	97.44 330	98.91 257	98.88 388	98.68 238	99.51 188	99.34 311	96.18 393	99.20 261	99.34 357	94.03 309	99.36 350	95.32 409	95.18 401	98.69 349

ttmdpeth		97.80 313	97.63 304	98.29 348	98.77 409	97.38 323	99.64 95	99.36 299	98.78 98	96.30 440	99.58 275	92.34 361	99.39 341	98.36 235	95.58 392	98.10 434

v1921920		97.80 313	97.45 325	98.84 278	98.80 400	98.53 254	99.52 178	99.34 311	96.15 397	99.24 250	99.47 318	93.98 311	99.29 362	95.40 407	95.13 403	98.69 349

v148		97.79 315	97.55 309	98.50 319	98.74 412	97.72 309	99.54 167	99.33 319	96.26 387	98.90 317	99.51 303	94.68 275	99.14 391	97.83 285	93.15 437	98.63 382

thres400		97.77 316	97.38 338	98.92 253	99.69 127	97.96 294	99.50 199	98.73 432	97.83 238	99.17 269	98.45 438	91.67 374	99.83 215	93.22 437	98.18 297	98.96 314

thres100view900		97.76 317	97.45 325	98.69 298	99.72 111	97.86 303	99.59 121	98.74 426	97.93 224	99.26 248	98.62 431	91.75 370	99.83 215	93.22 437	98.18 297	98.37 420

PEN-MVS		97.76 317	97.44 330	98.72 293	98.77 409	98.54 253	99.78 32	99.51 153	97.06 327	98.29 387	99.64 251	92.63 349	98.89 432	98.09 260	93.16 436	98.72 338

Baseline_NR-MVSNet		97.76 317	97.45 325	98.68 299	99.09 354	98.29 274	99.41 267	98.85 411	95.65 410	98.63 362	99.67 238	94.82 260	99.10 402	98.07 267	92.89 439	98.64 375

TR-MVS		97.76 317	97.41 336	98.82 280	99.06 360	97.87 301	98.87 421	98.56 440	96.63 360	98.68 352	99.22 381	92.49 353	99.65 299	95.40 407	97.79 315	98.95 316

Patchmtry		97.75 321	97.40 337	98.81 283	99.10 351	98.87 214	99.11 375	99.33 319	94.83 426	98.81 333	99.38 344	94.33 296	99.02 411	96.10 388	95.57 393	98.53 401

dp		97.75 321	97.80 279	97.59 404	99.10 351	93.71 445	99.32 305	98.88 407	96.48 373	99.08 285	99.55 286	92.67 348	99.82 224	96.52 379	98.58 266	99.24 284

WBMVS		97.74 323	97.50 317	98.46 328	99.24 315	97.43 321	99.21 351	99.42 268	97.45 287	98.96 308	99.41 333	88.83 411	99.23 373	98.94 144	96.02 376	98.71 340

TAPA-MVS	97.07 15	97.74 323	97.34 345	98.94 249	99.70 122	97.53 317	99.25 337	99.51 153	91.90 453	99.30 233	99.63 257	98.78 53	99.64 303	88.09 463	99.87 79	99.65 172
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 325	97.35 342	98.88 267	99.47 248	97.12 335	99.34 300	98.85 411	98.19 170	99.67 122	99.85 82	82.98 457	99.92 123	99.49 61	98.32 285	99.60 192

MIMVSNet		97.73 325	97.45 325	98.57 309	99.45 256	97.50 319	99.02 393	98.98 389	96.11 400	99.41 202	99.14 390	90.28 393	98.74 437	95.74 397	98.93 239	99.47 246

tfpn200view9		97.72 327	97.38 338	98.72 293	99.69 127	97.96 294	99.50 199	98.73 432	97.83 238	99.17 269	98.45 438	91.67 374	99.83 215	93.22 437	98.18 297	98.37 420

CostFormer		97.72 327	97.73 292	97.71 396	99.15 344	94.02 441	99.54 167	99.02 385	94.67 429	99.04 294	99.35 353	92.35 360	99.77 250	98.50 219	97.94 307	99.34 273

FMVSNet2		97.72 327	97.36 340	98.80 285	99.51 226	98.84 220	99.45 242	99.42 268	96.49 370	98.86 328	99.29 370	90.26 394	98.98 416	96.44 381	96.56 364	98.58 398

test0.0.03 1		97.71 330	97.42 335	98.56 313	98.41 439	97.82 304	98.78 429	98.63 438	97.34 299	98.05 401	98.98 410	94.45 291	98.98 416	95.04 414	97.15 355	98.89 317

h-mvs33		97.70 331	97.28 354	98.97 244	99.70 122	97.27 327	99.36 292	99.45 246	98.94 78	99.66 127	99.64 251	94.93 253	99.99 4	99.48 64	84.36 468	99.65 172

myMVS_eth3d28		97.69 332	97.34 345	98.73 291	99.27 306	97.52 318	99.33 302	98.78 421	98.03 215	98.82 332	98.49 436	86.64 434	99.46 326	98.44 226	98.24 291	99.23 285

v1240		97.69 332	97.32 349	98.79 286	98.85 395	98.43 269	99.48 224	99.36 299	96.11 400	99.27 243	99.36 350	93.76 321	99.24 372	94.46 421	95.23 400	98.70 345

cascas		97.69 332	97.43 334	98.48 322	98.60 429	97.30 325	98.18 466	99.39 281	92.96 447	98.41 378	98.78 427	93.77 320	99.27 366	98.16 253	98.61 263	98.86 318

pm-mvs1		97.68 335	97.28 354	98.88 267	99.06 360	98.62 246	99.50 199	99.45 246	96.32 382	97.87 409	99.79 166	92.47 354	99.35 353	97.54 318	93.54 430	98.67 362

GBi-Net		97.68 335	97.48 319	98.29 348	99.51 226	97.26 329	99.43 255	99.48 201	96.49 370	99.07 286	99.32 365	90.26 394	98.98 416	97.10 349	96.65 361	98.62 384

test1		97.68 335	97.48 319	98.29 348	99.51 226	97.26 329	99.43 255	99.48 201	96.49 370	99.07 286	99.32 365	90.26 394	98.98 416	97.10 349	96.65 361	98.62 384

tpm		97.67 338	97.55 309	98.03 367	99.02 367	95.01 422	99.43 255	98.54 442	96.44 376	99.12 275	99.34 357	91.83 369	99.60 312	97.75 297	96.46 366	99.48 240

PCF-MVS	97.08 14	97.66 339	97.06 367	99.47 163	99.61 186	99.09 165	98.04 469	99.25 350	91.24 456	98.51 373	99.70 213	94.55 285	99.91 135	92.76 445	99.85 94	99.42 258
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 340	97.65 300	97.63 399	98.78 404	97.62 315	99.13 366	98.33 446	97.36 298	99.07 286	98.94 414	95.64 224	99.15 389	92.95 441	98.68 261	96.12 470

our_test_3		97.65 340	97.68 297	97.55 405	98.62 426	94.97 423	98.84 423	99.30 338	96.83 346	98.19 393	99.34 357	97.01 150	99.02 411	95.00 415	96.01 377	98.64 375

testgi		97.65 340	97.50 317	98.13 363	99.36 281	96.45 381	99.42 262	99.48 201	97.76 248	97.87 409	99.45 324	91.09 386	98.81 434	94.53 420	98.52 272	99.13 291

thres200		97.61 343	97.28 354	98.62 303	99.64 162	98.03 288	99.26 335	98.74 426	97.68 259	99.09 283	98.32 444	91.66 376	99.81 229	92.88 442	98.22 292	98.03 439

PAPM		97.59 344	97.09 366	99.07 230	99.06 360	98.26 276	98.30 462	99.10 372	94.88 424	98.08 397	99.34 357	96.27 192	99.64 303	89.87 456	98.92 241	99.31 276

UWE-MVS		97.58 345	97.29 353	98.48 322	99.09 354	96.25 389	99.01 398	96.61 472	97.86 231	99.19 264	99.01 405	88.72 412	99.90 148	97.38 333	98.69 260	99.28 278

SD_0403		97.55 346	97.53 313	97.62 400	99.61 186	93.64 448	99.72 53	99.44 255	98.03 215	98.62 365	99.39 341	96.06 199	99.57 315	87.88 465	99.01 235	99.66 166

VDDNet		97.55 346	97.02 368	99.16 222	99.49 240	98.12 285	99.38 284	99.30 338	95.35 413	99.68 116	99.90 34	82.62 459	99.93 110	99.31 86	98.13 301	99.42 258

TESTMET0.1,1		97.55 346	97.27 357	98.40 338	98.93 381	96.53 378	98.67 438	97.61 461	96.96 335	98.64 360	99.28 372	88.63 418	99.45 328	97.30 337	99.38 183	99.21 287

pmmvs5		97.52 349	97.30 351	98.16 359	98.57 432	96.73 368	99.27 326	98.90 404	96.14 398	98.37 381	99.53 295	91.54 379	99.14 391	97.51 320	95.87 383	98.63 382

LF4IMVS		97.52 349	97.46 324	97.70 397	98.98 376	95.55 405	99.29 316	98.82 414	98.07 199	98.66 353	99.64 251	89.97 399	99.61 311	97.01 354	96.68 360	97.94 447

DTE-MVSNet		97.51 351	97.19 360	98.46 328	98.63 425	98.13 283	99.84 12	99.48 201	96.68 353	97.97 404	99.67 238	92.92 336	98.56 441	96.88 366	92.60 444	98.70 345

testing11		97.50 352	97.10 365	98.71 296	99.20 324	96.91 361	99.29 316	98.82 414	97.89 228	98.21 392	98.40 440	85.63 443	99.83 215	98.45 225	98.04 304	99.37 268

ETVMVS		97.50 352	96.90 372	99.29 204	99.23 317	98.78 232	99.32 305	98.90 404	97.52 280	98.56 370	98.09 454	84.72 450	99.69 288	97.86 281	97.88 310	99.39 264

hse-mvs2		97.50 352	97.14 362	98.59 305	99.49 240	97.05 342	99.28 321	99.22 356	98.94 78	99.66 127	99.42 329	94.93 253	99.65 299	99.48 64	83.80 470	99.08 297

SixPastTwentyTwo		97.50 352	97.33 348	98.03 367	98.65 423	96.23 390	99.77 34	98.68 435	97.14 316	97.90 407	99.93 10	90.45 392	99.18 386	97.00 355	96.43 367	98.67 362

JIA-IIPM		97.50 352	97.02 368	98.93 251	98.73 413	97.80 305	99.30 311	98.97 390	91.73 454	98.91 315	94.86 472	95.10 247	99.71 276	97.58 311	97.98 305	99.28 278

ppachtmachnet_test		97.49 357	97.45 325	97.61 403	98.62 426	95.24 416	98.80 427	99.46 235	96.11 400	98.22 391	99.62 262	96.45 182	98.97 423	93.77 429	95.97 382	98.61 393

test-mter		97.49 357	97.13 364	98.55 315	98.79 401	97.10 336	98.67 438	97.75 458	96.65 356	98.61 366	98.85 420	88.23 422	99.45 328	97.25 339	99.38 183	99.10 292

testing91		97.44 359	97.02 368	98.71 296	99.18 330	96.89 363	99.19 356	99.04 382	97.78 246	98.31 384	98.29 445	85.41 445	99.85 187	98.01 270	97.95 306	99.39 264

tpm2		97.44 359	97.34 345	97.74 395	99.15 344	94.36 438	99.45 242	98.94 393	93.45 443	98.90 317	99.44 325	91.35 382	99.59 313	97.31 336	98.07 303	99.29 277

tpm cat1		97.39 361	97.36 340	97.50 407	99.17 338	93.73 444	99.43 255	99.31 333	91.27 455	98.71 344	99.08 395	94.31 298	99.77 250	96.41 384	98.50 273	99.00 308

UWE-MVS-28		97.36 362	97.24 358	97.75 393	98.84 397	94.44 435	99.24 342	97.58 462	97.98 220	99.00 301	99.00 406	91.35 382	99.53 321	93.75 430	98.39 277	99.27 282

testing99		97.36 362	96.94 371	98.63 302	99.18 330	96.70 369	99.30 311	98.93 394	97.71 254	98.23 389	98.26 446	84.92 448	99.84 196	98.04 269	97.85 313	99.35 270

SSC-MVS3.2		97.34 364	97.15 361	97.93 378	99.02 367	95.76 401	99.48 224	99.58 78	97.62 266	99.09 283	99.53 295	87.95 425	99.27 366	96.42 382	95.66 390	98.75 332

USDC		97.34 364	97.20 359	97.75 393	99.07 358	95.20 417	98.51 452	99.04 382	97.99 219	98.31 384	99.86 75	89.02 408	99.55 319	95.67 401	97.36 347	98.49 405

UniMVSNet_ETH3D		97.32 366	96.81 374	98.87 271	99.40 270	97.46 320	99.51 188	99.53 125	95.86 408	98.54 372	99.77 182	82.44 460	99.66 294	98.68 191	97.52 331	99.50 236

testing3		97.28 367	96.76 376	98.82 280	99.37 278	98.07 287	99.45 242	99.36 299	97.56 273	97.89 408	98.95 413	83.70 454	98.82 433	96.03 390	98.56 269	99.58 207

MVS		97.28 367	96.55 380	99.48 157	98.78 404	98.95 193	99.27 326	99.39 281	83.53 472	98.08 397	99.54 291	96.97 151	99.87 175	94.23 425	99.16 204	99.63 184

test_fmvs2		97.25 369	97.30 351	97.09 418	99.43 258	93.31 451	99.73 51	98.87 409	98.83 88	99.28 237	99.80 149	84.45 451	99.66 294	97.88 278	97.45 339	98.30 422

DSMNet-mixed		97.25 369	97.35 342	96.95 423	97.84 446	93.61 449	99.57 139	96.63 471	96.13 399	98.87 323	98.61 433	94.59 281	97.70 459	95.08 413	98.86 249	99.55 214

MS-PatchMatch		97.24 371	97.32 349	96.99 420	98.45 437	93.51 450	98.82 425	99.32 329	97.41 294	98.13 396	99.30 368	88.99 409	99.56 317	95.68 400	99.80 125	97.90 450

testing222		97.16 372	96.50 381	99.16 222	99.16 340	98.47 267	99.27 326	98.66 437	97.71 254	98.23 389	98.15 449	82.28 462	99.84 196	97.36 334	97.66 319	99.18 288

TransMVSNet (Re)		97.15 373	96.58 379	98.86 274	99.12 346	98.85 218	99.49 216	98.91 402	95.48 412	97.16 428	99.80 149	93.38 325	99.11 400	94.16 427	91.73 447	98.62 384

TinyColmap		97.12 374	96.89 373	97.83 388	99.07 358	95.52 408	98.57 447	98.74 426	97.58 270	97.81 412	99.79 166	88.16 423	99.56 317	95.10 412	97.21 352	98.39 418

K. test v3		97.10 375	96.79 375	98.01 370	98.72 415	96.33 385	99.87 8	97.05 465	97.59 268	96.16 442	99.80 149	88.71 413	99.04 407	96.69 373	96.55 365	98.65 373

Syy-MVS		97.09 376	97.14 362	96.95 423	99.00 370	92.73 455	99.29 316	99.39 281	97.06 327	97.41 418	98.15 449	93.92 314	98.68 439	91.71 449	98.34 279	99.45 254

PatchT		97.03 377	96.44 383	98.79 286	98.99 373	98.34 273	99.16 360	99.07 378	92.13 452	99.52 175	97.31 465	94.54 286	98.98 416	88.54 461	98.73 258	99.03 305

mmtdpeth		96.95 378	96.71 377	97.67 398	99.33 288	94.90 425	99.89 2	99.28 344	98.15 175	99.72 102	98.57 434	86.56 436	99.90 148	99.82 29	89.02 461	98.20 429

myMVS_eth3d		96.89 379	96.37 384	98.43 335	99.00 370	97.16 333	99.29 316	99.39 281	97.06 327	97.41 418	98.15 449	83.46 456	98.68 439	95.27 410	98.34 279	99.45 254

AUN-MVS		96.88 380	96.31 386	98.59 305	99.48 247	97.04 345	99.27 326	99.22 356	97.44 290	98.51 373	99.41 333	91.97 365	99.66 294	97.71 302	83.83 469	99.07 302

FMVSNet1		96.84 381	96.36 385	98.29 348	99.32 295	97.26 329	99.43 255	99.48 201	95.11 417	98.55 371	99.32 365	83.95 453	98.98 416	95.81 395	96.26 372	98.62 384

test2506		96.81 382	96.65 378	97.29 413	99.74 100	92.21 458	99.60 113	85.06 489	99.13 41	99.77 85	99.93 10	87.82 429	99.85 187	99.38 74	99.38 183	99.80 88

RPMNet		96.72 383	95.90 396	99.19 219	99.18 330	98.49 263	99.22 349	99.52 131	88.72 465	99.56 164	97.38 462	94.08 307	99.95 76	86.87 470	98.58 266	99.14 289

mvs5depth		96.66 384	96.22 388	97.97 374	97.00 462	96.28 387	98.66 441	99.03 384	96.61 361	96.93 434	99.79 166	87.20 432	99.47 324	96.65 377	94.13 421	98.16 431

test_0402		96.64 385	96.24 387	97.85 385	98.85 395	96.43 382	99.44 249	99.26 348	93.52 440	96.98 432	99.52 299	88.52 419	99.20 385	92.58 447	97.50 334	97.93 448

X-MVStestdata		96.55 386	95.45 405	99.87 21	99.85 31	99.83 22	99.69 62	99.68 24	98.98 72	99.37 213	64.01 485	98.81 49	99.94 92	98.79 177	99.86 87	99.84 53

pmmvs6		96.53 387	96.09 392	97.82 390	98.69 420	95.47 409	99.37 286	99.47 223	93.46 442	97.41 418	99.78 173	87.06 433	99.33 356	96.92 364	92.70 442	98.65 373

ET-MVSNet_ETH3D		96.49 388	95.64 402	99.05 234	99.53 217	98.82 226	98.84 423	97.51 463	97.63 264	84.77 472	99.21 384	92.09 363	98.91 429	98.98 136	92.21 445	99.41 261

UnsupCasMVSNet_eth		96.44 389	96.12 390	97.40 410	98.65 423	95.65 402	99.36 292	99.51 153	97.13 317	96.04 444	98.99 408	88.40 420	98.17 448	96.71 371	90.27 455	98.40 417

FMVSNet5		96.43 390	96.19 389	97.15 414	99.11 348	95.89 398	99.32 305	99.52 131	94.47 433	98.34 383	99.07 396	87.54 430	97.07 465	92.61 446	95.72 388	98.47 408

new_pmnet		96.38 391	96.03 393	97.41 409	98.13 443	95.16 420	99.05 385	99.20 360	93.94 435	97.39 421	98.79 426	91.61 378	99.04 407	90.43 454	95.77 385	98.05 438

Anonymous20231206		96.22 392	96.03 393	96.79 428	97.31 456	94.14 440	99.63 101	99.08 375	96.17 394	97.04 431	99.06 398	93.94 312	97.76 458	86.96 469	95.06 404	98.47 408

IB-MVS	95.67 18	96.22 392	95.44 406	98.57 309	99.21 322	96.70 369	98.65 442	97.74 460	96.71 351	97.27 423	98.54 435	86.03 440	99.92 123	98.47 223	86.30 466	99.10 292
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		96.20 394	95.89 397	97.13 416	97.72 450	94.96 424	99.79 31	99.29 342	93.01 446	97.20 427	99.03 402	89.69 403	98.36 445	91.16 452	96.13 374	98.07 436

gg-mvs-nofinetune		96.17 395	95.32 407	98.73 291	98.79 401	98.14 282	99.38 284	94.09 480	91.07 458	98.07 400	91.04 478	89.62 405	99.35 353	96.75 369	99.09 227	98.68 354

test20.03		96.12 396	95.96 395	96.63 429	97.44 452	95.45 410	99.51 188	99.38 289	96.55 367	96.16 442	99.25 378	93.76 321	96.17 471	87.35 468	94.22 419	98.27 424

PVSNet_0	94.43 19	96.09 397	95.47 404	97.94 377	99.31 296	94.34 439	97.81 470	99.70 18	97.12 319	97.46 417	98.75 428	89.71 402	99.79 242	97.69 305	81.69 472	99.68 157

MVStest1		96.08 398	95.48 403	97.89 382	98.93 381	96.70 369	99.56 147	99.35 306	92.69 450	91.81 467	99.46 322	89.90 400	98.96 425	95.00 415	92.61 443	98.00 443

EG-PatchMatch MVS		95.97 399	95.69 400	96.81 427	97.78 447	92.79 454	99.16 360	98.93 394	96.16 395	94.08 456	99.22 381	82.72 458	99.47 324	95.67 401	97.50 334	98.17 430

APD_test1		95.87 400	96.49 382	94.00 441	99.53 217	84.01 470	99.54 167	99.32 329	95.91 407	97.99 402	99.85 82	85.49 444	99.88 168	91.96 448	98.84 251	98.12 433

Patchmatch-RL test		95.84 401	95.81 399	95.95 436	95.61 467	90.57 462	98.24 463	98.39 444	95.10 419	95.20 449	98.67 430	94.78 264	97.77 457	96.28 387	90.02 456	99.51 232

test_vis1_rt		95.81 402	95.65 401	96.32 433	99.67 135	91.35 461	99.49 216	96.74 470	98.25 160	95.24 447	98.10 453	74.96 469	99.90 148	99.53 53	98.85 250	97.70 453

sc_t1		95.75 403	95.05 410	97.87 383	98.83 398	94.61 432	99.21 351	99.45 246	87.45 466	97.97 404	99.85 82	81.19 465	99.43 337	98.27 243	93.20 435	99.57 210

MVS-HIRNet		95.75 403	95.16 408	97.51 406	99.30 297	93.69 446	98.88 419	95.78 474	85.09 471	98.78 338	92.65 474	91.29 384	99.37 346	94.85 417	99.85 94	99.46 251

tt0320		95.71 405	95.07 409	97.62 400	99.05 363	95.02 421	99.25 337	99.52 131	86.81 467	97.97 404	99.72 206	83.58 455	99.15 389	96.38 385	93.35 431	98.68 354

MIMVSNet1		95.51 406	95.04 411	96.92 425	97.38 453	95.60 403	99.52 178	99.50 176	93.65 439	96.97 433	99.17 386	85.28 447	96.56 469	88.36 462	95.55 394	98.60 396

MDA-MVSNet_test_wron		95.45 407	94.60 414	98.01 370	98.16 442	97.21 332	99.11 375	99.24 353	93.49 441	80.73 478	98.98 410	93.02 333	98.18 447	94.22 426	94.45 415	98.64 375

TDRefinement		95.42 408	94.57 416	97.97 374	89.83 482	96.11 394	99.48 224	98.75 423	96.74 349	96.68 436	99.88 54	88.65 416	99.71 276	98.37 233	82.74 471	98.09 435

YYNet1		95.36 409	94.51 417	97.92 379	97.89 445	97.10 336	99.10 377	99.23 354	93.26 444	80.77 477	99.04 401	92.81 339	98.02 451	94.30 422	94.18 420	98.64 375

pmmvs-eth3d		95.34 410	94.73 413	97.15 414	95.53 469	95.94 397	99.35 297	99.10 372	95.13 415	93.55 459	97.54 460	88.15 424	97.91 454	94.58 419	89.69 460	97.61 454

tt0320-xc		95.31 411	94.59 415	97.45 408	98.92 383	94.73 427	99.20 354	99.31 333	86.74 468	97.23 424	99.72 206	81.14 466	98.95 426	97.08 352	91.98 446	98.67 362

FE-MVSNET2		95.10 412	94.44 418	97.08 419	95.08 472	95.97 396	99.51 188	99.37 297	95.02 421	94.10 455	97.57 458	86.18 439	97.66 461	93.28 436	89.86 458	97.61 454

dmvs_testset		95.02 413	96.12 390	91.72 450	99.10 351	80.43 478	99.58 131	97.87 457	97.47 283	95.22 448	98.82 422	93.99 310	95.18 475	88.09 463	94.91 409	99.56 213

KD-MVS_self_test		95.00 414	94.34 419	96.96 422	97.07 461	95.39 413	99.56 147	99.44 255	95.11 417	97.13 429	97.32 464	91.86 368	97.27 464	90.35 455	81.23 473	98.23 428

MDA-MVSNet-bldmvs		94.96 415	93.98 422	97.92 379	98.24 441	97.27 327	99.15 363	99.33 319	93.80 437	80.09 479	99.03 402	88.31 421	97.86 456	93.49 434	94.36 417	98.62 384

N_pmnet		94.95 416	95.83 398	92.31 448	98.47 436	79.33 480	99.12 369	92.81 486	93.87 436	97.68 414	99.13 391	93.87 316	99.01 413	91.38 451	96.19 373	98.59 397

KD-MVS_2432*1600		94.62 417	93.72 425	97.31 411	97.19 459	95.82 399	98.34 458	99.20 360	95.00 422	97.57 415	98.35 442	87.95 425	98.10 449	92.87 443	77.00 476	98.01 440

miper_refine_blended		94.62 417	93.72 425	97.31 411	97.19 459	95.82 399	98.34 458	99.20 360	95.00 422	97.57 415	98.35 442	87.95 425	98.10 449	92.87 443	77.00 476	98.01 440

CL-MVSNet_self_test		94.49 419	93.97 423	96.08 435	96.16 464	93.67 447	98.33 460	99.38 289	95.13 415	97.33 422	98.15 449	92.69 347	96.57 468	88.67 460	79.87 474	97.99 444

new-patchmatchnet		94.48 420	94.08 421	95.67 437	95.08 472	92.41 456	99.18 358	99.28 344	94.55 432	93.49 460	97.37 463	87.86 428	97.01 466	91.57 450	88.36 462	97.61 454

OpenMVS_ROB	92.34 20	94.38 421	93.70 427	96.41 432	97.38 453	93.17 452	99.06 383	98.75 423	86.58 469	94.84 453	98.26 446	81.53 463	99.32 358	89.01 459	97.87 311	96.76 463

CMPMVS	69.68 23	94.13 422	94.90 412	91.84 449	97.24 457	80.01 479	98.52 451	99.48 201	89.01 463	91.99 466	99.67 238	85.67 442	99.13 394	95.44 405	97.03 357	96.39 467
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 423	93.25 430	96.60 430	94.76 475	94.49 434	98.92 415	98.18 453	89.66 459	96.48 438	98.06 455	86.28 438	97.33 463	89.68 457	87.20 465	97.97 446

FE-MVSNET		94.07 424	93.36 429	96.22 434	94.05 476	94.71 429	99.56 147	98.36 445	93.15 445	93.76 458	97.55 459	86.47 437	96.49 470	87.48 466	89.83 459	97.48 459

mvsany_test3		93.77 425	93.45 428	94.74 439	95.78 466	88.01 465	99.64 95	98.25 448	98.28 150	94.31 454	97.97 456	68.89 472	98.51 443	97.50 321	90.37 454	97.71 451

UnsupCasMVSNet_bld		93.53 426	92.51 432	96.58 431	97.38 453	93.82 442	98.24 463	99.48 201	91.10 457	93.10 461	96.66 467	74.89 470	98.37 444	94.03 428	87.71 464	97.56 457

dongtai		93.26 427	92.93 431	94.25 440	99.39 273	85.68 468	97.68 472	93.27 482	92.87 448	96.85 435	99.39 341	82.33 461	97.48 462	76.78 476	97.80 314	99.58 207

WB-MVS		93.10 428	94.10 420	90.12 455	95.51 471	81.88 475	99.73 51	99.27 347	95.05 420	93.09 462	98.91 419	94.70 274	91.89 479	76.62 477	94.02 425	96.58 465

PM-MVS		92.96 429	92.23 433	95.14 438	95.61 467	89.98 464	99.37 286	98.21 451	94.80 427	95.04 452	97.69 457	65.06 473	97.90 455	94.30 422	89.98 457	97.54 458

SSC-MVS		92.73 430	93.73 424	89.72 456	95.02 474	81.38 476	99.76 37	99.23 354	94.87 425	92.80 463	98.93 415	94.71 273	91.37 480	74.49 479	93.80 427	96.42 466

test_fmvs3		92.10 431	91.77 434	93.08 446	96.19 463	86.25 466	99.82 16	98.62 439	96.65 356	95.19 450	96.90 466	55.05 480	95.93 473	96.63 378	90.92 453	97.06 462

test_f		91.90 432	91.26 436	93.84 442	95.52 470	85.92 467	99.69 62	98.53 443	95.31 414	93.87 457	96.37 469	55.33 479	98.27 446	95.70 398	90.98 452	97.32 461

test_method		91.10 433	91.36 435	90.31 454	95.85 465	73.72 487	94.89 476	99.25 350	68.39 478	95.82 445	99.02 404	80.50 467	98.95 426	93.64 432	94.89 410	98.25 426

Gipuma		90.99 434	90.15 439	93.51 443	98.73 413	90.12 463	93.98 477	99.45 246	79.32 474	92.28 464	94.91 471	69.61 471	97.98 453	87.42 467	95.67 389	92.45 474
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 435	90.11 440	93.34 444	98.78 404	85.59 469	98.15 467	93.16 484	89.37 462	92.07 465	98.38 441	81.48 464	95.19 474	62.54 483	97.04 356	99.25 283

testf1		90.42 436	90.68 437	89.65 457	97.78 447	73.97 485	99.13 366	98.81 416	89.62 460	91.80 468	98.93 415	62.23 476	98.80 435	86.61 471	91.17 449	96.19 468

APD_test2		90.42 436	90.68 437	89.65 457	97.78 447	73.97 485	99.13 366	98.81 416	89.62 460	91.80 468	98.93 415	62.23 476	98.80 435	86.61 471	91.17 449	96.19 468

test_vis3_rt		87.04 438	85.81 441	90.73 453	93.99 477	81.96 474	99.76 37	90.23 488	92.81 449	81.35 476	91.56 476	40.06 484	99.07 404	94.27 424	88.23 463	91.15 476

PMMVS2		86.87 439	85.37 443	91.35 452	90.21 481	83.80 471	98.89 418	97.45 464	83.13 473	91.67 470	95.03 470	48.49 482	94.70 476	85.86 473	77.62 475	95.54 471

LCM-MVSNet		86.80 440	85.22 444	91.53 451	87.81 483	80.96 477	98.23 465	98.99 388	71.05 476	90.13 471	96.51 468	48.45 483	96.88 467	90.51 453	85.30 467	96.76 463

FPMVS		84.93 441	85.65 442	82.75 463	86.77 484	63.39 489	98.35 457	98.92 397	74.11 475	83.39 474	98.98 410	50.85 481	92.40 478	84.54 474	94.97 406	92.46 473

EGC-MVSNET		82.80 442	77.86 448	97.62 400	97.91 444	96.12 393	99.33 302	99.28 344	8.40 486	25.05 487	99.27 375	84.11 452	99.33 356	89.20 458	98.22 292	97.42 460

tmp_tt		82.80 442	81.52 445	86.66 459	66.61 489	68.44 488	92.79 479	97.92 455	68.96 477	80.04 480	99.85 82	85.77 441	96.15 472	97.86 281	43.89 482	95.39 472

E-PMN		80.61 444	79.88 446	82.81 462	90.75 480	76.38 483	97.69 471	95.76 475	66.44 480	83.52 473	92.25 475	62.54 475	87.16 482	68.53 481	61.40 479	84.89 480

EMVS		80.02 445	79.22 447	82.43 464	91.19 479	76.40 482	97.55 474	92.49 487	66.36 481	83.01 475	91.27 477	64.63 474	85.79 483	65.82 482	60.65 480	85.08 479

ANet_high		77.30 446	74.86 450	84.62 461	75.88 487	77.61 481	97.63 473	93.15 485	88.81 464	64.27 482	89.29 479	36.51 485	83.93 484	75.89 478	52.31 481	92.33 475

MVE	76.82 21	76.91 447	74.31 451	84.70 460	85.38 486	76.05 484	96.88 475	93.17 483	67.39 479	71.28 481	89.01 480	21.66 490	87.69 481	71.74 480	72.29 478	90.35 477
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 448	74.97 449	79.01 465	70.98 488	55.18 490	93.37 478	98.21 451	65.08 482	61.78 483	93.83 473	21.74 489	92.53 477	78.59 475	91.12 451	89.34 478
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		40.18 449	41.29 454	36.84 466	86.18 485	49.12 491	79.73 480	22.81 491	27.64 483	25.46 486	28.45 486	21.98 488	48.89 485	55.80 484	23.56 485	12.51 483

testmvs		39.17 450	43.78 452	25.37 468	36.04 491	16.84 493	98.36 456	26.56 490	20.06 484	38.51 485	67.32 481	29.64 487	15.30 487	37.59 485	39.90 483	43.98 482

test123		39.01 451	42.50 453	28.53 467	39.17 490	20.91 492	98.75 432	19.17 492	19.83 485	38.57 484	66.67 482	33.16 486	15.42 486	37.50 486	29.66 484	49.26 481

cdsmvs_eth3d_5k		24.64 452	32.85 455	0.00 469	0.00 492	0.00 494	0.00 481	99.51 153	0.00 487	0.00 488	99.56 283	96.58 174	0.00 488	0.00 487	0.00 486	0.00 484

ab-mvs-re		8.30 453	11.06 456	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	99.58 275	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

pcd_1.5k_mvsjas		8.27 454	11.03 457	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	99.01 20	0.00 488	0.00 487	0.00 486	0.00 484

test_blank		0.13 455	0.17 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	1.57 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

mmdepth		0.02 456	0.03 459	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

monomultidepth		0.02 456	0.03 459	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

uanet_test		0.02 456	0.03 459	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

DCPMVS		0.02 456	0.03 459	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

sosnet-low-res		0.02 456	0.03 459	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

sosnet		0.02 456	0.03 459	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

uncertanet		0.02 456	0.03 459	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

Regformer		0.02 456	0.03 459	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

uanet		0.02 456	0.03 459	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.27 488	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

MED-MVS test				99.87 21	99.88 13	99.81 33	99.69 62	99.87 6	99.34 26	99.90 34	99.83 103		99.95 76	98.83 169	99.89 68	99.83 63

TestfortrainingZip							99.69 62

WAC-MVS						97.16 333								95.47 404

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	99.51 226	99.76 49		99.33 319					99.96 41	98.87 156	99.84 102	99.89 29

PC_three_1452									98.18 173	99.84 56	99.70 213	99.31 3	98.52 442	98.30 242	99.80 125	99.81 79

No_MVS				99.87 21	99.51 226	99.76 49		99.33 319					99.96 41	98.87 156	99.84 102	99.89 29

test_one_0601					99.81 57	99.88 10		99.49 189	98.97 75	99.65 136	99.81 131	99.09 16

eth-test2					0.00 492

eth-test					0.00 492

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 344	99.56 164	99.54 291	98.58 78	99.96 41	96.93 362	99.75 142

RE-MVS-def			99.34 50		99.76 82	99.82 28	99.63 101	99.52 131	98.38 137	99.76 91	99.82 116	98.75 60		98.61 201	99.81 120	99.77 100

IU-MVS					99.84 38	99.88 10		99.32 329	98.30 149	99.84 56				98.86 161	99.85 94	99.89 29

OPU-MVS				99.64 101	99.56 205	99.72 56	99.60 113				99.70 213	99.27 7	99.42 339	98.24 246	99.80 125	99.79 92

test_241102_TWO								99.48 201	99.08 56	99.88 43	99.81 131	98.94 34	99.96 41	98.91 150	99.84 102	99.88 35

test_241102_ONE					99.84 38	99.90 3		99.48 201	99.07 58	99.91 31	99.74 196	99.20 9	99.76 254

9.14			99.10 99		99.72 111		99.40 275	99.51 153	97.53 278	99.64 141	99.78 173	98.84 46	99.91 135	97.63 307	99.82 117

save fliter					99.76 82	99.59 88	99.14 365	99.40 278	99.00 67

test_0728_THIRD									98.99 69	99.81 69	99.80 149	99.09 16	99.96 41	98.85 163	99.90 57	99.88 35

test_0728_SECOND				99.91 6	99.84 38	99.89 6	99.57 139	99.51 153					99.96 41	98.93 147	99.86 87	99.88 35

test0726					99.85 31	99.89 6	99.62 106	99.50 176	99.10 48	99.86 53	99.82 116	98.94 34

GSMVS																99.52 223

test_part2					99.81 57	99.83 22				99.77 85

sam_mvs1												94.86 259				99.52 223

sam_mvs												94.72 272

ambc				93.06 447	92.68 478	82.36 472	98.47 453	98.73 432		95.09 451	97.41 461	55.55 478	99.10 402	96.42 382	91.32 448	97.71 451

MTGPA								99.47 223

test_post1							99.23 345				65.14 484	94.18 303	99.71 276	97.58 311

test_post											65.99 483	94.65 279	99.73 266

patchmatchnet-post											98.70 429	94.79 263	99.74 260

GG-mvs-BLEND				98.45 330	98.55 433	98.16 280	99.43 255	93.68 481		97.23 424	98.46 437	89.30 406	99.22 378	95.43 406	98.22 292	97.98 445

MTMP							99.54 167	98.88 407

gm-plane-assit					98.54 434	92.96 453			94.65 430		99.15 389		99.64 303	97.56 316

test9_res														97.49 322	99.72 148	99.75 110

TEST9					99.67 135	99.65 75	99.05 385	99.41 271	96.22 390	98.95 310	99.49 309	98.77 56	99.91 135

test_8					99.67 135	99.61 85	99.03 390	99.41 271	96.28 384	98.93 313	99.48 315	98.76 57	99.91 135

agg_prior2														97.21 341	99.73 147	99.75 110

agg_prior					99.67 135	99.62 83		99.40 278		98.87 323			99.91 135

TestCases				99.31 196	99.86 25	98.48 265		99.61 60	97.85 234	99.36 219	99.85 82	95.95 205	99.85 187	96.66 375	99.83 113	99.59 203

test_prior4						99.56 94	98.99 401

test_prior2							98.96 408		98.34 143	99.01 297	99.52 299	98.68 70		97.96 273	99.74 145

test_prior				99.68 89	99.67 135	99.48 111		99.56 90					99.83 215			99.74 115

旧先验2							98.96 408		96.70 352	99.47 183			99.94 92	98.19 249

新几何2							99.01 398

新几何1				99.75 77	99.75 92	99.59 88		99.54 109	96.76 348	99.29 236	99.64 251	98.43 89	99.94 92	96.92 364	99.66 159	99.72 134

旧先验1					99.74 100	99.59 88		99.54 109			99.69 224	98.47 86			99.68 156	99.73 124

无先验							98.99 401	99.51 153	96.89 341				99.93 110	97.53 319		99.72 134

原ACMM2							98.95 411

原ACMM1				99.65 95	99.73 107	99.33 130		99.47 223	97.46 284	99.12 275	99.66 243	98.67 72	99.91 135	97.70 304	99.69 153	99.71 145

test222					99.75 92	99.49 109	98.91 417	99.49 189	96.42 378	99.34 226	99.65 245	98.28 100			99.69 153	99.72 134

testdata2													99.95 76	96.67 374

segment_acmp												98.96 27

testdata				99.54 125	99.75 92	98.95 193		99.51 153	97.07 325	99.43 194	99.70 213	98.87 42	99.94 92	97.76 295	99.64 162	99.72 134

testdata1							98.85 422		98.32 147

test12				99.75 77	99.64 162	99.61 85		99.29 342		99.21 258		98.38 95	99.89 163		99.74 145	99.74 115

plane_prior7					99.29 301	97.03 348

plane_prior6					99.27 306	96.98 352						92.71 345

plane_prior5								99.47 223					99.69 288	97.78 291	97.63 320	98.67 362

plane_prior4											99.61 266

plane_prior3						97.00 350			98.69 107	99.11 277

plane_prior2							99.39 279		98.97 75

plane_prior1					99.26 309

plane_prior						96.97 353	99.21 351		98.45 130						97.60 323

n2								0.00 493

nn								0.00 493

door-mid								98.05 454

lessismore_v0				97.79 392	98.69 420	95.44 412		94.75 478		95.71 446	99.87 67	88.69 414	99.32 358	95.89 393	94.93 408	98.62 384

LGP-MVS_train				98.49 320	99.33 288	97.05 342		99.55 100	97.46 284	99.24 250	99.83 103	92.58 350	99.72 270	98.09 260	97.51 332	98.68 354

test11								99.35 306

door								97.92 455

HQP5-MVS						96.83 364

HQP-NCC					99.19 327		98.98 404		98.24 162	98.66 353

ACMP_Plane					99.19 327		98.98 404		98.24 162	98.66 353

BP-MVS														97.19 345

HQP4-MVS										98.66 353			99.64 303			98.64 375

HQP3-MVS								99.39 281							97.58 325

HQP2-MVS												92.47 354

NP-MVS					99.23 317	96.92 360					99.40 337

MDTV_nov1_ep13_2view						95.18 419	99.35 297		96.84 344	99.58 160		95.19 244		97.82 286		99.46 251

MDTV_nov1_ep13			98.32 229		99.11 348	94.44 435	99.27 326	98.74 426	97.51 281	99.40 207	99.62 262	94.78 264	99.76 254	97.59 310	98.81 255

ACMMP++_ref															97.19 353

ACMMP++															97.43 343

Test By Simon												98.75 60

ITE_SJBPF				98.08 365	99.29 301	96.37 383		98.92 397	98.34 143	98.83 330	99.75 191	91.09 386	99.62 310	95.82 394	97.40 345	98.25 426

DeepMVS_CX				93.34 444	99.29 301	82.27 473		99.22 356	85.15 470	96.33 439	99.05 399	90.97 388	99.73 266	93.57 433	97.77 316	98.01 440

High-resolution multi-view benchmark