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.

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 27	99.44 210	99.65 64	99.50 174	99.61 50	99.45 8	99.87 33	99.92 17	97.31 126	99.97 22	99.95 10	99.99 1	99.97 4

test_fmvsmconf_n		99.70 3	99.64 4	99.87 16	99.80 53	99.66 60	99.48 189	99.64 38	99.45 8	99.92 20	99.92 17	98.62 73	99.99 4	99.96 8	99.99 1	99.96 7

CHOSEN 280x420		99.12 105	99.13 81	99.08 190	99.66 128	97.89 259	98.43 399	99.71 13	98.88 67	99.62 115	99.76 143	96.63 152	99.70 241	99.46 53	99.99 1	99.66 133

patch_mono-2		99.26 78	99.62 5	98.16 311	99.81 47	94.59 379	99.52 158	99.64 38	99.33 17	99.73 74	99.90 30	99.00 22	99.99 4	99.69 25	99.98 4	99.89 22

dcpmvs_2		99.23 84	99.58 7	98.16 311	99.83 40	94.68 377	99.76 37	99.52 109	99.07 43	99.98 8	99.88 43	98.56 77	99.93 94	99.67 27	99.98 4	99.87 33

CANet		99.25 82	99.14 80	99.59 98	99.41 218	99.16 138	99.35 251	99.57 69	98.82 73	99.51 140	99.61 217	96.46 160	99.95 65	99.59 33	99.98 4	99.65 137

fmvsm_s_conf0.5_n_3		99.37 59	99.20 74	99.87 16	99.75 79	99.70 52	99.48 189	99.66 28	99.45 8	99.99 2	99.93 10	94.64 239	99.97 22	99.94 12	99.97 7	99.95 9

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 34	99.84 32	99.63 71	99.56 130	99.63 41	99.47 4	99.98 8	99.82 85	98.75 58	99.99 4	99.97 1	99.97 7	99.94 13

MM		99.40 55	99.28 61	99.74 68	99.67 118	99.31 119	99.52 158	98.87 358	99.55 1	99.74 72	99.80 112	96.47 159	99.98 14	99.97 1	99.97 7	99.94 13

MVS_0304		99.15 94	98.96 114	99.73 71	98.92 333	99.37 109	99.37 241	96.92 411	99.51 2	99.66 96	99.78 131	96.69 150	99.97 22	99.84 19	99.97 7	99.84 45

CHOSEN 1792x2688		99.19 86	99.10 85	99.45 136	99.89 8	98.52 220	99.39 234	99.94 1	98.73 85	99.11 231	99.89 35	95.50 195	99.94 76	99.50 45	99.97 7	99.89 22

DeepC-MVS	98.35 2	99.30 70	99.19 76	99.64 87	99.82 43	99.23 131	99.62 95	99.55 82	98.94 62	99.63 111	99.95 3	95.82 185	99.94 76	99.37 58	99.97 7	99.73 103
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 34	99.86 20	99.61 74	99.56 130	99.63 41	99.48 3	99.98 8	99.83 76	98.75 58	99.99 4	99.97 1	99.96 13	99.94 13

fmvsm_s_conf0.1_n		99.29 72	99.10 85	99.86 27	99.70 108	99.65 64	99.53 157	99.62 43	98.74 84	99.99 2	99.95 3	94.53 246	99.94 76	99.89 16	99.96 13	99.97 4

fmvsm_s_conf0.5_n		99.51 22	99.40 31	99.85 34	99.84 32	99.65 64	99.51 167	99.67 23	99.13 28	99.98 8	99.92 17	96.60 153	99.96 34	99.95 10	99.96 13	99.95 9

mamv4		99.33 65	99.42 26	99.07 191	99.67 118	97.73 266	99.42 219	99.60 56	98.15 146	99.94 19	99.91 23	98.42 88	99.94 76	99.72 23	99.96 13	99.54 172

CSCG		99.32 67	99.32 47	99.32 157	99.85 26	98.29 235	99.71 55	99.66 28	98.11 154	99.41 163	99.80 112	98.37 92	99.96 34	98.99 101	99.96 13	99.72 110

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 32	99.82 25	99.54 148	99.66 28	99.46 7	99.98 8	99.89 35	97.27 129	99.99 4	99.97 1	99.95 18	99.95 9

MVSMamba_PlusPlus		99.46 35	99.41 30	99.64 87	99.68 116	99.50 95	99.75 42	99.50 143	98.27 129	99.87 33	99.92 17	98.09 104	99.94 76	99.65 29	99.95 18	99.47 198

test_fmvsmconf0.01_n		99.22 85	99.03 96	99.79 56	98.42 385	99.48 98	99.55 144	99.51 123	99.39 14	99.78 58	99.93 10	94.80 223	99.95 65	99.93 14	99.95 18	99.94 13

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 59	99.84 32	99.44 103	99.58 117	99.69 18	99.43 11	99.98 8	99.91 23	98.62 73	100.00 1	99.97 1	99.95 18	99.90 19

CANet_DTU		98.97 133	98.87 128	99.25 173	99.33 240	98.42 232	99.08 324	99.30 288	99.16 24	99.43 156	99.75 146	95.27 203	99.97 22	98.56 173	99.95 18	99.36 221

EI-MVSNet-UG-set		99.58 13	99.57 8	99.64 87	99.78 58	99.14 143	99.60 102	99.45 206	99.01 48	99.90 23	99.83 76	98.98 24	99.93 94	99.59 33	99.95 18	99.86 35

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 87	99.78 58	99.15 142	99.61 101	99.45 206	99.01 48	99.89 25	99.82 85	99.01 18	99.92 106	99.56 37	99.95 18	99.85 39

balanced_conf03		99.46 35	99.39 33	99.67 76	99.55 168	99.58 82	99.74 46	99.51 123	98.42 112	99.87 33	99.84 71	98.05 107	99.91 118	99.58 35	99.94 25	99.52 179

UGNet		98.87 140	98.69 149	99.40 143	99.22 273	98.72 199	99.44 207	99.68 20	99.24 21	99.18 222	99.42 279	92.74 295	99.96 34	99.34 64	99.94 25	99.53 178
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
fmvsm_s_conf0.5_n_2		99.32 67	99.13 81	99.89 8	99.80 53	99.77 41	99.44 207	99.58 65	99.47 4	99.99 2	99.93 10	94.04 263	99.96 34	99.96 8	99.93 27	99.93 18

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 62	99.38 228	99.37 109	99.58 117	99.62 43	99.41 13	99.87 33	99.92 17	98.81 47	100.00 1	99.97 1	99.93 27	99.94 13

SD-MVS		99.41 52	99.52 12	99.05 195	99.74 87	99.68 55	99.46 199	99.52 109	99.11 34	99.88 28	99.91 23	99.43 1	97.70 406	98.72 144	99.93 27	99.77 88
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
fmvsm_s_conf0.1_n_a		99.26 78	99.06 91	99.85 34	99.52 177	99.62 72	99.54 148	99.62 43	98.69 88	99.99 2	99.96 1	94.47 248	99.94 76	99.88 17	99.92 30	99.98 2

fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 34	99.83 40	99.64 70	99.52 158	99.65 35	99.10 35	99.98 8	99.92 17	97.35 125	99.96 34	99.94 12	99.92 30	99.95 9

test_vis1_n_1920		98.63 172	98.40 179	99.31 158	99.86 20	97.94 258	99.67 69	99.62 43	99.43 11	99.99 2	99.91 23	87.29 383	100.00 1	99.92 15	99.92 30	99.98 2

test_fmvs1		98.88 139	98.79 140	99.16 183	99.69 112	97.61 275	99.55 144	99.49 153	99.32 18	99.98 8	99.91 23	91.41 333	99.96 34	99.82 20	99.92 30	99.90 19

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 65	99.89 4	99.75 42	99.56 74	99.02 46	99.88 28	99.85 61	99.18 10	99.96 34	99.22 77	99.92 30	99.90 19
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
HPM-MVS_fast		99.51 22	99.40 31	99.85 34	99.91 1	99.79 34	99.76 37	99.56 74	97.72 205	99.76 68	99.75 146	99.13 12	99.92 106	99.07 93	99.92 30	99.85 39

3Dnovator	97.25 9	99.24 83	99.05 92	99.81 50	99.12 298	99.66 60	99.84 12	99.74 10	99.09 40	98.92 266	99.90 30	95.94 179	99.98 14	98.95 106	99.92 30	99.79 80

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 58	99.88 8	99.56 130	99.55 82	99.15 25	99.90 23	99.90 30	99.00 22	99.97 22	99.11 87	99.91 37	99.86 35

test_cas_vis1_n_1920		99.16 92	99.01 104	99.61 95	99.81 47	98.86 185	99.65 81	99.64 38	99.39 14	99.97 17	99.94 6	93.20 285	99.98 14	99.55 38	99.91 37	99.99 1

MP-MVS-pluss		99.37 59	99.20 74	99.88 10	99.90 4	99.87 15	99.30 263	99.52 109	97.18 264	99.60 121	99.79 124	98.79 50	99.95 65	98.83 132	99.91 37	99.83 55
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.47 33	99.34 43	99.88 10	99.87 15	99.86 16	99.47 196	99.48 165	98.05 168	99.76 68	99.86 56	98.82 46	99.93 94	98.82 136	99.91 37	99.84 45

HPM-MVS		99.42 48	99.28 61	99.83 46	99.90 4	99.72 48	99.81 20	99.54 91	97.59 219	99.68 87	99.63 208	98.91 37	99.94 76	98.58 167	99.91 37	99.84 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
114514_t		98.93 135	98.67 151	99.72 73	99.85 26	99.53 90	99.62 95	99.59 61	92.65 399	99.71 81	99.78 131	98.06 106	99.90 130	98.84 129	99.91 37	99.74 98

CP-MVS		99.45 39	99.32 47	99.85 34	99.83 40	99.75 44	99.69 60	99.52 109	98.07 162	99.53 136	99.63 208	98.93 36	99.97 22	98.74 141	99.91 37	99.83 55

PHI-MVS		99.30 70	99.17 78	99.70 74	99.56 164	99.52 93	99.58 117	99.80 8	97.12 270	99.62 115	99.73 157	98.58 75	99.90 130	98.61 161	99.91 37	99.68 127

DeepPCF-MVS	98.18 3	98.81 154	99.37 37	97.12 364	99.60 154	91.75 404	98.61 389	99.44 214	99.35 16	99.83 45	99.85 61	98.70 66	99.81 193	99.02 99	99.91 37	99.81 67

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 69	99.88 8	99.52 158	99.54 91	99.13 28	99.89 25	99.89 35	98.96 25	99.96 34	99.04 95	99.90 46	99.85 39

our_new_method		99.61 8	99.52 12	99.90 5	99.76 69	99.88 8	99.52 158	99.54 91	99.13 28	99.89 25	99.89 35	98.96 25	99.96 34	99.04 95	99.90 46	99.85 39

ZNCC-MVS		99.47 33	99.33 45	99.87 16	99.87 15	99.81 29	99.64 84	99.67 23	98.08 161	99.55 133	99.64 202	98.91 37	99.96 34	98.72 144	99.90 46	99.82 60

test_0728_THIRD									98.99 53	99.81 47	99.80 112	99.09 14	99.96 34	98.85 126	99.90 46	99.88 28

MTAPA		99.52 21	99.39 33	99.89 8	99.90 4	99.86 16	99.66 75	99.47 186	98.79 78	99.68 87	99.81 99	98.43 86	99.97 22	98.88 116	99.90 46	99.83 55

UA-Net		99.42 48	99.29 59	99.80 53	99.62 145	99.55 85	99.50 174	99.70 15	98.79 78	99.77 62	99.96 1	97.45 120	99.96 34	98.92 112	99.90 46	99.89 22

jason		99.13 99	99.03 96	99.45 136	99.46 203	98.87 182	99.12 315	99.26 298	98.03 171	99.79 53	99.65 196	97.02 139	99.85 161	99.02 99	99.90 46	99.65 137
jason: jason.
SteuartSystems-ACMMP		99.54 19	99.42 26	99.87 16	99.82 43	99.81 29	99.59 109	99.51 123	98.62 93	99.79 53	99.83 76	99.28 4	99.97 22	98.48 180	99.90 46	99.84 45
Skip Steuart: Steuart Systems R&D Blog.
DP-MVS		99.16 92	98.95 116	99.78 59	99.77 65	99.53 90	99.41 222	99.50 143	97.03 282	99.04 247	99.88 43	97.39 121	99.92 106	98.66 153	99.90 46	99.87 33

MSDG		98.98 131	98.80 137	99.53 116	99.76 69	99.19 133	98.75 377	99.55 82	97.25 258	99.47 146	99.77 139	97.82 112	99.87 152	96.93 312	99.90 46	99.54 172

COLMAP_ROB	97.56 6	98.86 143	98.75 143	99.17 182	99.88 11	98.53 216	99.34 254	99.59 61	97.55 225	98.70 301	99.89 35	95.83 184	99.90 130	98.10 213	99.90 46	99.08 249
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SMA-MVS		99.44 43	99.30 55	99.85 34	99.73 94	99.83 19	99.56 130	99.47 186	97.45 238	99.78 58	99.82 85	99.18 10	99.91 118	98.79 137	99.89 57	99.81 67
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 43	99.30 55	99.86 27	99.88 11	99.79 34	99.69 60	99.48 165	98.12 152	99.50 141	99.75 146	98.78 51	99.97 22	98.57 170	99.89 57	99.83 55

MVS_111021_LR		99.41 52	99.33 45	99.65 81	99.77 65	99.51 94	98.94 358	99.85 6	98.82 73	99.65 103	99.74 151	98.51 81	99.80 200	98.83 132	99.89 57	99.64 144

TSAR-MVS + MP.		99.58 13	99.50 17	99.81 50	99.91 1	99.66 60	99.63 90	99.39 234	98.91 66	99.78 58	99.85 61	99.36 2	99.94 76	98.84 129	99.88 60	99.82 60
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
QAPM		98.67 168	98.30 186	99.80 53	99.20 276	99.67 58	99.77 34	99.72 11	94.74 377	98.73 293	99.90 30	95.78 186	99.98 14	96.96 309	99.88 60	99.76 93

MVS_111021_HR		99.41 52	99.32 47	99.66 77	99.72 98	99.47 100	98.95 356	99.85 6	98.82 73	99.54 134	99.73 157	98.51 81	99.74 219	98.91 113	99.88 60	99.77 88

DPE-MVS		99.46 35	99.32 47	99.91 3	99.78 58	99.88 8	99.36 246	99.51 123	98.73 85	99.88 28	99.84 71	98.72 64	99.96 34	98.16 211	99.87 63	99.88 28
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
HFP-MVS		99.49 26	99.37 37	99.86 27	99.87 15	99.80 31	99.66 75	99.67 23	98.15 146	99.68 87	99.69 176	99.06 16	99.96 34	98.69 149	99.87 63	99.84 45

region2R		99.48 30	99.35 41	99.87 16	99.88 11	99.80 31	99.65 81	99.66 28	98.13 151	99.66 96	99.68 183	98.96 25	99.96 34	98.62 158	99.87 63	99.84 45

ACMMPR		99.49 26	99.36 39	99.86 27	99.87 15	99.79 34	99.66 75	99.67 23	98.15 146	99.67 91	99.69 176	98.95 30	99.96 34	98.69 149	99.87 63	99.84 45

MP-MVS		99.33 65	99.15 79	99.87 16	99.88 11	99.82 25	99.66 75	99.46 195	98.09 157	99.48 145	99.74 151	98.29 95	99.96 34	97.93 229	99.87 63	99.82 60
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		99.45 39	99.31 53	99.86 27	99.87 15	99.78 40	99.58 117	99.65 35	97.84 191	99.71 81	99.80 112	99.12 13	99.97 22	98.33 197	99.87 63	99.83 55

DeepC-MVS_fast	98.69 1	99.49 26	99.39 33	99.77 62	99.63 139	99.59 77	99.36 246	99.46 195	99.07 43	99.79 53	99.82 85	98.85 42	99.92 106	98.68 151	99.87 63	99.82 60
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TAPA-MVS	97.07 15	97.74 276	97.34 297	98.94 210	99.70 108	97.53 276	99.25 289	99.51 123	91.90 401	99.30 189	99.63 208	98.78 51	99.64 260	88.09 410	99.87 63	99.65 137
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DVP-MVS		99.57 16	99.47 21	99.88 10	99.85 26	99.89 4	99.57 124	99.37 250	99.10 35	99.81 47	99.80 112	98.94 32	99.96 34	98.93 110	99.86 71	99.81 67
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
test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 124	99.51 123					99.96 34	98.93 110	99.86 71	99.88 28

GST-MVS		99.40 55	99.24 69	99.85 34	99.86 20	99.79 34	99.60 102	99.67 23	97.97 176	99.63 111	99.68 183	98.52 80	99.95 65	98.38 190	99.86 71	99.81 67

XVS		99.53 20	99.42 26	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 56	99.37 174	99.74 151	98.81 47	99.94 76	98.79 137	99.86 71	99.84 45

X-MVStestdata		96.55 337	95.45 356	99.87 16	99.85 26	99.83 19	99.69 60	99.68 20	98.98 56	99.37 174	64.01 430	98.81 47	99.94 76	98.79 137	99.86 71	99.84 45

APD-MVS		99.27 76	99.08 89	99.84 45	99.75 79	99.79 34	99.50 174	99.50 143	97.16 266	99.77 62	99.82 85	98.78 51	99.94 76	97.56 268	99.86 71	99.80 76
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
3Dnovator+	97.12 13	99.18 88	98.97 110	99.82 47	99.17 290	99.68 55	99.81 20	99.51 123	99.20 22	98.72 294	99.89 35	95.68 190	99.97 22	98.86 124	99.86 71	99.81 67

SED-MVS		99.61 8	99.52 12	99.88 10	99.84 32	99.90 2	99.60 102	99.48 165	99.08 41	99.91 21	99.81 99	99.20 7	99.96 34	98.91 113	99.85 78	99.79 80

IU-MVS					99.84 32	99.88 8		99.32 280	98.30 126	99.84 39				98.86 124	99.85 78	99.89 22

SPE-MVS-test		99.49 26	99.48 19	99.54 108	99.78 58	99.30 121	99.89 2	99.58 65	98.56 98	99.73 74	99.69 176	98.55 78	99.82 188	99.69 25	99.85 78	99.48 192

MVSFormer		99.17 90	99.12 83	99.29 166	99.51 180	98.94 175	99.88 4	99.46 195	97.55 225	99.80 51	99.65 196	97.39 121	99.28 317	99.03 97	99.85 78	99.65 137

lupinMVS		99.13 99	99.01 104	99.46 135	99.51 180	98.94 175	99.05 330	99.16 315	97.86 186	99.80 51	99.56 234	97.39 121	99.86 155	98.94 107	99.85 78	99.58 164

PVSNet_Blended		99.08 116	98.97 110	99.42 141	99.76 69	98.79 194	98.78 374	99.91 3	96.74 299	99.67 91	99.49 259	97.53 118	99.88 147	98.98 102	99.85 78	99.60 156

MVS-HIRNet		95.75 354	95.16 359	97.51 354	99.30 249	93.69 392	98.88 364	95.78 419	85.09 416	98.78 289	92.65 419	91.29 337	99.37 300	94.85 365	99.85 78	99.46 203

PCF-MVS	97.08 14	97.66 292	97.06 318	99.47 133	99.61 149	99.09 148	98.04 413	99.25 300	91.24 404	98.51 323	99.70 166	94.55 244	99.91 118	92.76 392	99.85 78	99.42 210
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_fmvs1_n		98.41 183	98.14 195	99.21 178	99.82 43	97.71 271	99.74 46	99.49 153	99.32 18	99.99 2	99.95 3	85.32 395	99.97 22	99.82 20	99.84 86	99.96 7

MSC_two_6792asdad				99.87 16	99.51 180	99.76 42		99.33 270					99.96 34	98.87 119	99.84 86	99.89 22

No_MVS				99.87 16	99.51 180	99.76 42		99.33 270					99.96 34	98.87 119	99.84 86	99.89 22

test_241102_TWO								99.48 165	99.08 41	99.88 28	99.81 99	98.94 32	99.96 34	98.91 113	99.84 86	99.88 28

SF-MVS		99.38 58	99.24 69	99.79 56	99.79 56	99.68 55	99.57 124	99.54 91	97.82 196	99.71 81	99.80 112	98.95 30	99.93 94	98.19 207	99.84 86	99.74 98

MSLP-MVS++		99.46 35	99.47 21	99.44 140	99.60 154	99.16 138	99.41 222	99.71 13	98.98 56	99.45 149	99.78 131	99.19 9	99.54 275	99.28 71	99.84 86	99.63 149

DELS-MVS		99.48 30	99.42 26	99.65 81	99.72 98	99.40 108	99.05 330	99.66 28	99.14 27	99.57 128	99.80 112	98.46 84	99.94 76	99.57 36	99.84 86	99.60 156
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
CPTT-MVS		99.11 110	98.90 122	99.74 68	99.80 53	99.46 101	99.59 109	99.49 153	97.03 282	99.63 111	99.69 176	97.27 129	99.96 34	97.82 240	99.84 86	99.81 67

LS3D		99.27 76	99.12 83	99.74 68	99.18 282	99.75 44	99.56 130	99.57 69	98.45 108	99.49 144	99.85 61	97.77 114	99.94 76	98.33 197	99.84 86	99.52 179

AllTest		98.87 140	98.72 145	99.31 158	99.86 20	98.48 226	99.56 130	99.61 50	97.85 189	99.36 177	99.85 61	95.95 177	99.85 161	96.66 325	99.83 95	99.59 160

TestCases				99.31 158	99.86 20	98.48 226		99.61 50	97.85 189	99.36 177	99.85 61	95.95 177	99.85 161	96.66 325	99.83 95	99.59 160

CDPH-MVS		99.13 99	98.91 121	99.80 53	99.75 79	99.71 50	99.15 309	99.41 225	96.60 314	99.60 121	99.55 237	98.83 45	99.90 130	97.48 275	99.83 95	99.78 86

ACMMP		99.45 39	99.32 47	99.82 47	99.89 8	99.67 58	99.62 95	99.69 18	98.12 152	99.63 111	99.84 71	98.73 63	99.96 34	98.55 176	99.83 95	99.81 67
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
9.14			99.10 85		99.72 98		99.40 230	99.51 123	97.53 229	99.64 108	99.78 131	98.84 44	99.91 118	97.63 259	99.82 99

PVSNet_Blended_VisFu		99.36 62	99.28 61	99.61 95	99.86 20	99.07 153	99.47 196	99.93 2	97.66 214	99.71 81	99.86 56	97.73 115	99.96 34	99.47 52	99.82 99	99.79 80

EC-MVSNet		99.44 43	99.39 33	99.58 101	99.56 164	99.49 96	99.88 4	99.58 65	98.38 115	99.73 74	99.69 176	98.20 99	99.70 241	99.64 31	99.82 99	99.54 172

SR-MVS-dyc-post		99.45 39	99.31 53	99.85 34	99.76 69	99.82 25	99.63 90	99.52 109	98.38 115	99.76 68	99.82 85	98.53 79	99.95 65	98.61 161	99.81 102	99.77 88

RE-MVS-def			99.34 43		99.76 69	99.82 25	99.63 90	99.52 109	98.38 115	99.76 68	99.82 85	98.75 58		98.61 161	99.81 102	99.77 88

APD-MVS_3200maxsize		99.48 30	99.35 41	99.85 34	99.76 69	99.83 19	99.63 90	99.54 91	98.36 119	99.79 53	99.82 85	98.86 41	99.95 65	98.62 158	99.81 102	99.78 86

OMC-MVS		99.08 116	99.04 94	99.20 179	99.67 118	98.22 239	99.28 273	99.52 109	98.07 162	99.66 96	99.81 99	97.79 113	99.78 208	97.79 242	99.81 102	99.60 156

DVP-MVS++		99.59 12	99.50 17	99.88 10	99.51 180	99.88 8	99.87 8	99.51 123	98.99 53	99.88 28	99.81 99	99.27 5	99.96 34	98.85 126	99.80 106	99.81 67

PC_three_1452									98.18 144	99.84 39	99.70 166	99.31 3	98.52 389	98.30 201	99.80 106	99.81 67

OPU-MVS				99.64 87	99.56 164	99.72 48	99.60 102				99.70 166	99.27 5	99.42 293	98.24 204	99.80 106	99.79 80

MS-PatchMatch		97.24 322	97.32 301	96.99 366	98.45 384	93.51 395	98.82 370	99.32 280	97.41 245	98.13 346	99.30 316	88.99 362	99.56 272	95.68 348	99.80 106	97.90 397

HPM-MVS++		99.39 57	99.23 71	99.87 16	99.75 79	99.84 18	99.43 212	99.51 123	98.68 90	99.27 198	99.53 246	98.64 72	99.96 34	98.44 186	99.80 106	99.79 80

CNVR-MVS		99.42 48	99.30 55	99.78 59	99.62 145	99.71 50	99.26 287	99.52 109	98.82 73	99.39 170	99.71 162	98.96 25	99.85 161	98.59 166	99.80 106	99.77 88

MG-MVS		99.13 99	99.02 100	99.45 136	99.57 160	98.63 207	99.07 325	99.34 263	98.99 53	99.61 118	99.82 85	97.98 109	99.87 152	97.00 305	99.80 106	99.85 39

fmvsm_s_conf0.1_n_2		99.37 59	99.22 72	99.81 50	99.77 65	99.75 44	99.46 199	99.60 56	99.47 4	99.98 8	99.94 6	94.98 212	99.95 65	99.97 1	99.79 113	99.73 103

BP-MVS1		99.12 105	98.94 118	99.65 81	99.51 180	99.30 121	99.67 69	98.92 346	98.48 105	99.84 39	99.69 176	94.96 213	99.92 106	99.62 32	99.79 113	99.71 119

CS-MVS		99.50 24	99.48 19	99.54 108	99.76 69	99.42 105	99.90 1	99.55 82	98.56 98	99.78 58	99.70 166	98.65 71	99.79 203	99.65 29	99.78 115	99.41 213

MVP-Stereo		97.81 264	97.75 244	97.99 325	97.53 398	96.60 330	98.96 353	98.85 360	97.22 262	97.23 372	99.36 299	95.28 202	99.46 281	95.51 351	99.78 115	97.92 396
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
API-MVS		99.04 122	99.03 96	99.06 193	99.40 223	99.31 119	99.55 144	99.56 74	98.54 100	99.33 184	99.39 291	98.76 55	99.78 208	96.98 307	99.78 115	98.07 383

SR-MVS		99.43 46	99.29 59	99.86 27	99.75 79	99.83 19	99.59 109	99.62 43	98.21 139	99.73 74	99.79 124	98.68 67	99.96 34	98.44 186	99.77 118	99.79 80

MSP-MVS		99.42 48	99.27 64	99.88 10	99.89 8	99.80 31	99.67 69	99.50 143	98.70 87	99.77 62	99.49 259	98.21 98	99.95 65	98.46 184	99.77 118	99.88 28
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
AdaColmap		99.01 129	98.80 137	99.66 77	99.56 164	99.54 87	99.18 304	99.70 15	98.18 144	99.35 180	99.63 208	96.32 165	99.90 130	97.48 275	99.77 118	99.55 170

test_vis1_n		97.92 243	97.44 282	99.34 151	99.53 172	98.08 246	99.74 46	99.49 153	99.15 25	100.00 1	99.94 6	79.51 414	99.98 14	99.88 17	99.76 121	99.97 4

OpenMVS	96.50 16	98.47 177	98.12 198	99.52 122	99.04 316	99.53 90	99.82 16	99.72 11	94.56 380	98.08 347	99.88 43	94.73 231	99.98 14	97.47 277	99.76 121	99.06 255

ZD-MVS					99.71 103	99.79 34		99.61 50	96.84 295	99.56 129	99.54 242	98.58 75	99.96 34	96.93 312	99.75 123

MCST-MVS		99.43 46	99.30 55	99.82 47	99.79 56	99.74 47	99.29 268	99.40 231	98.79 78	99.52 138	99.62 213	98.91 37	99.90 130	98.64 155	99.75 123	99.82 60

CNLPA		99.14 97	98.99 106	99.59 98	99.58 158	99.41 107	99.16 306	99.44 214	98.45 108	99.19 218	99.49 259	98.08 105	99.89 142	97.73 251	99.75 123	99.48 192

test_prior2							98.96 353		98.34 121	99.01 250	99.52 249	98.68 67		97.96 227	99.74 126

test12				99.75 65	99.64 136	99.61 74		99.29 292		99.21 212		98.38 91	99.89 142		99.74 126	99.74 98

agg_prior2														97.21 292	99.73 128	99.75 94

test9_res														97.49 274	99.72 129	99.75 94

train_agg		99.02 125	98.77 141	99.77 62	99.67 118	99.65 64	99.05 330	99.41 225	96.28 334	98.95 262	99.49 259	98.76 55	99.91 118	97.63 259	99.72 129	99.75 94

EPNet		98.86 143	98.71 147	99.30 163	97.20 405	98.18 240	99.62 95	98.91 351	99.28 20	98.63 313	99.81 99	95.96 176	99.99 4	99.24 76	99.72 129	99.73 103
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DP-MVS Recon		99.12 105	98.95 116	99.65 81	99.74 87	99.70 52	99.27 278	99.57 69	96.40 330	99.42 159	99.68 183	98.75 58	99.80 200	97.98 226	99.72 129	99.44 208

PVSNet	96.02 17	98.85 150	98.84 134	98.89 223	99.73 94	97.28 285	98.32 405	99.60 56	97.86 186	99.50 141	99.57 231	96.75 148	99.86 155	98.56 173	99.70 133	99.54 172

原ACMM1				99.65 81	99.73 94	99.33 114		99.47 186	97.46 235	99.12 229	99.66 194	98.67 69	99.91 118	97.70 256	99.69 134	99.71 119

test222					99.75 79	99.49 96	98.91 362	99.49 153	96.42 328	99.34 183	99.65 196	98.28 96			99.69 134	99.72 110

F-COLMAP		99.19 86	99.04 94	99.64 87	99.78 58	99.27 126	99.42 219	99.54 91	97.29 255	99.41 163	99.59 222	98.42 88	99.93 94	98.19 207	99.69 134	99.73 103

DPM-MVS		98.95 134	98.71 147	99.66 77	99.63 139	99.55 85	98.64 388	99.10 321	97.93 179	99.42 159	99.55 237	98.67 69	99.80 200	95.80 344	99.68 137	99.61 153

旧先验1					99.74 87	99.59 77		99.54 91			99.69 176	98.47 83			99.68 137	99.73 103

PS-MVSNAJ		99.32 67	99.32 47	99.30 163	99.57 160	98.94 175	98.97 352	99.46 195	98.92 65	99.71 81	99.24 327	99.01 18	99.98 14	99.35 59	99.66 139	98.97 264

新几何1				99.75 65	99.75 79	99.59 77		99.54 91	96.76 298	99.29 192	99.64 202	98.43 86	99.94 76	96.92 314	99.66 139	99.72 110

EPNet_dtu		98.03 225	97.96 217	98.23 307	98.27 387	95.54 358	99.23 294	98.75 371	99.02 46	97.82 359	99.71 162	96.11 171	99.48 278	93.04 387	99.65 141	99.69 123
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				99.54 108	99.75 79	98.95 172		99.51 123	97.07 276	99.43 156	99.70 166	98.87 40	99.94 76	97.76 247	99.64 142	99.72 110

PatchMatch-RL		98.84 153	98.62 161	99.52 122	99.71 103	99.28 124	99.06 328	99.77 9	97.74 204	99.50 141	99.53 246	95.41 197	99.84 168	97.17 299	99.64 142	99.44 208

NCCC		99.34 64	99.19 76	99.79 56	99.61 149	99.65 64	99.30 263	99.48 165	98.86 68	99.21 212	99.63 208	98.72 64	99.90 130	98.25 203	99.63 144	99.80 76

EIA-MVS		99.18 88	99.09 88	99.45 136	99.49 193	99.18 135	99.67 69	99.53 104	97.66 214	99.40 168	99.44 275	98.10 103	99.81 193	98.94 107	99.62 145	99.35 222

mvsmamba		99.06 119	98.96 114	99.36 149	99.47 201	98.64 206	99.70 56	99.05 330	97.61 218	99.65 103	99.83 76	96.54 156	99.92 106	99.19 79	99.62 145	99.51 186

PLC	97.94 4	99.02 125	98.85 132	99.53 116	99.66 128	99.01 160	99.24 291	99.52 109	96.85 294	99.27 198	99.48 265	98.25 97	99.91 118	97.76 247	99.62 145	99.65 137
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ETV-MVS		99.26 78	99.21 73	99.40 143	99.46 203	99.30 121	99.56 130	99.52 109	98.52 102	99.44 154	99.27 323	98.41 90	99.86 155	99.10 90	99.59 148	99.04 256

mvsany_test1		99.50 24	99.46 24	99.62 94	99.61 149	99.09 148	98.94 358	99.48 165	99.10 35	99.96 18	99.91 23	98.85 42	99.96 34	99.72 23	99.58 149	99.82 60

thisisatest0530		98.35 190	98.03 210	99.31 158	99.63 139	98.56 213	99.54 148	96.75 414	97.53 229	99.73 74	99.65 196	91.25 338	99.89 142	98.62 158	99.56 150	99.48 192

tttt0517		98.42 181	98.14 195	99.28 170	99.66 128	98.38 233	99.74 46	96.85 412	97.68 211	99.79 53	99.74 151	91.39 334	99.89 142	98.83 132	99.56 150	99.57 167

BH-RMVSNet		98.41 183	98.08 204	99.40 143	99.41 218	98.83 190	99.30 263	98.77 370	97.70 209	98.94 264	99.65 196	92.91 291	99.74 219	96.52 329	99.55 152	99.64 144

MAR-MVS		98.86 143	98.63 156	99.54 108	99.37 231	99.66 60	99.45 201	99.54 91	96.61 311	99.01 250	99.40 287	97.09 134	99.86 155	97.68 258	99.53 153	99.10 244
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
thisisatest0515		98.14 208	97.79 234	99.19 180	99.50 191	98.50 223	98.61 389	96.82 413	96.95 288	99.54 134	99.43 277	91.66 329	99.86 155	98.08 218	99.51 154	99.22 238

GDP-MVS		99.08 116	98.89 125	99.64 87	99.53 172	99.34 113	99.64 84	99.48 165	98.32 124	99.77 62	99.66 194	95.14 209	99.93 94	98.97 105	99.50 155	99.64 144

FA-MVS(test-final)		98.75 161	98.53 172	99.41 142	99.55 168	99.05 156	99.80 25	99.01 335	96.59 316	99.58 125	99.59 222	95.39 198	99.90 130	97.78 243	99.49 156	99.28 230

FE-MVS		98.48 176	98.17 191	99.40 143	99.54 171	98.96 169	99.68 66	98.81 365	95.54 361	99.62 115	99.70 166	93.82 273	99.93 94	97.35 286	99.46 157	99.32 227

Fast-Effi-MVS+-dtu		98.77 160	98.83 136	98.60 259	99.41 218	96.99 308	99.52 158	99.49 153	98.11 154	99.24 204	99.34 306	96.96 142	99.79 203	97.95 228	99.45 158	99.02 259

PAPM_NR		99.04 122	98.84 134	99.66 77	99.74 87	99.44 103	99.39 234	99.38 242	97.70 209	99.28 193	99.28 320	98.34 93	99.85 161	96.96 309	99.45 158	99.69 123

TSAR-MVS + GP.		99.36 62	99.36 39	99.36 149	99.67 118	98.61 210	99.07 325	99.33 270	99.00 51	99.82 46	99.81 99	99.06 16	99.84 168	99.09 91	99.42 160	99.65 137

Vis-MVSNet		99.12 105	98.97 110	99.56 105	99.78 58	99.10 147	99.68 66	99.66 28	98.49 104	99.86 37	99.87 52	94.77 228	99.84 168	99.19 79	99.41 161	99.74 98
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test2506		96.81 333	96.65 329	97.29 360	99.74 87	92.21 403	99.60 102	85.06 434	99.13 28	99.77 62	99.93 10	87.82 381	99.85 161	99.38 57	99.38 162	99.80 76

test1111		98.04 223	98.11 199	97.83 338	99.74 87	93.82 388	99.58 117	95.40 421	99.12 33	99.65 103	99.93 10	90.73 343	99.84 168	99.43 55	99.38 162	99.82 60

ECVR-MVS		98.04 223	98.05 208	98.00 324	99.74 87	94.37 383	99.59 109	94.98 422	99.13 28	99.66 96	99.93 10	90.67 344	99.84 168	99.40 56	99.38 162	99.80 76

Effi-MVS+-dtu		98.78 158	98.89 125	98.47 280	99.33 240	96.91 314	99.57 124	99.30 288	98.47 106	99.41 163	98.99 355	96.78 146	99.74 219	98.73 143	99.38 162	98.74 286

test-LLR		98.06 217	97.90 224	98.55 269	98.79 349	97.10 295	98.67 383	97.75 403	97.34 250	98.61 316	98.85 367	94.45 249	99.45 283	97.25 290	99.38 162	99.10 244

TESTMET0.1,1		97.55 299	97.27 309	98.40 291	98.93 331	96.53 331	98.67 383	97.61 406	96.96 286	98.64 311	99.28 320	88.63 371	99.45 283	97.30 288	99.38 162	99.21 239

test-mter		97.49 309	97.13 315	98.55 269	98.79 349	97.10 295	98.67 383	97.75 403	96.65 306	98.61 316	98.85 367	88.23 375	99.45 283	97.25 290	99.38 162	99.10 244

PAPR		98.63 172	98.34 182	99.51 124	99.40 223	99.03 157	98.80 372	99.36 251	96.33 331	99.00 254	99.12 342	98.46 84	99.84 168	95.23 359	99.37 169	99.66 133

xiu_mvs_v1_base_debu		99.29 72	99.27 64	99.34 151	99.63 139	98.97 165	99.12 315	99.51 123	98.86 68	99.84 39	99.47 268	98.18 100	99.99 4	99.50 45	99.31 170	99.08 249

xiu_mvs_v1_base		99.29 72	99.27 64	99.34 151	99.63 139	98.97 165	99.12 315	99.51 123	98.86 68	99.84 39	99.47 268	98.18 100	99.99 4	99.50 45	99.31 170	99.08 249

xiu_mvs_v1_base_debi		99.29 72	99.27 64	99.34 151	99.63 139	98.97 165	99.12 315	99.51 123	98.86 68	99.84 39	99.47 268	98.18 100	99.99 4	99.50 45	99.31 170	99.08 249

RRT-MVS		98.91 137	98.75 143	99.39 147	99.46 203	98.61 210	99.76 37	99.50 143	98.06 166	99.81 47	99.88 43	93.91 270	99.94 76	99.11 87	99.27 173	99.61 153

1314		98.68 167	98.54 171	99.11 189	98.89 336	98.65 204	99.27 278	99.49 153	96.89 292	97.99 352	99.56 234	97.72 116	99.83 181	97.74 250	99.27 173	98.84 272

xiu_mvs_v2_base		99.26 78	99.25 68	99.29 166	99.53 172	98.91 179	99.02 338	99.45 206	98.80 77	99.71 81	99.26 325	98.94 32	99.98 14	99.34 64	99.23 175	98.98 263

PatchmatchNet		98.31 192	98.36 180	98.19 309	99.16 292	95.32 365	99.27 278	98.92 346	97.37 248	99.37 174	99.58 226	94.90 218	99.70 241	97.43 281	99.21 176	99.54 172
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		98.19 202	98.16 192	98.27 306	99.30 249	95.55 356	99.07 325	98.97 339	97.57 222	99.43 156	99.57 231	92.72 296	99.74 219	97.58 263	99.20 177	99.52 179

sss		99.17 90	99.05 92	99.53 116	99.62 145	98.97 165	99.36 246	99.62 43	97.83 192	99.67 91	99.65 196	97.37 124	99.95 65	99.19 79	99.19 178	99.68 127

MVS		97.28 318	96.55 331	99.48 130	98.78 352	98.95 172	99.27 278	99.39 234	83.53 417	98.08 347	99.54 242	96.97 141	99.87 152	94.23 373	99.16 179	99.63 149

casdiffmvs		99.13 99	98.98 109	99.56 105	99.65 134	99.16 138	99.56 130	99.50 143	98.33 123	99.41 163	99.86 56	95.92 180	99.83 181	99.45 54	99.16 179	99.70 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-untuned		98.42 181	98.36 180	98.59 260	99.49 193	96.70 322	99.27 278	99.13 319	97.24 260	98.80 286	99.38 293	95.75 187	99.74 219	97.07 303	99.16 179	99.33 226

casdiffmvs_mvg		99.15 94	99.02 100	99.55 107	99.66 128	99.09 148	99.64 84	99.56 74	98.26 131	99.45 149	99.87 52	96.03 174	99.81 193	99.54 39	99.15 182	99.73 103
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 94	99.02 100	99.53 116	99.66 128	99.14 143	99.72 52	99.48 165	98.35 120	99.42 159	99.84 71	96.07 172	99.79 203	99.51 44	99.14 183	99.67 130

IS-MVSNet		99.05 121	98.87 128	99.57 103	99.73 94	99.32 115	99.75 42	99.20 310	98.02 173	99.56 129	99.86 56	96.54 156	99.67 249	98.09 214	99.13 184	99.73 103

Patchmatch-test		97.93 240	97.65 253	98.77 246	99.18 282	97.07 299	99.03 335	99.14 318	96.16 345	98.74 292	99.57 231	94.56 242	99.72 229	93.36 383	99.11 185	99.52 179

diffmvs		99.14 97	99.02 100	99.51 124	99.61 149	98.96 169	99.28 273	99.49 153	98.46 107	99.72 79	99.71 162	96.50 158	99.88 147	99.31 67	99.11 185	99.67 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet (Re-imp)		98.87 140	98.72 145	99.31 158	99.71 103	98.88 181	99.80 25	99.44 214	97.91 181	99.36 177	99.78 131	95.49 196	99.43 292	97.91 230	99.11 185	99.62 151

RPSCF		98.22 198	98.62 161	96.99 366	99.82 43	91.58 405	99.72 52	99.44 214	96.61 311	99.66 96	99.89 35	95.92 180	99.82 188	97.46 278	99.10 188	99.57 167

gg-mvs-nofinetune		96.17 346	95.32 358	98.73 248	98.79 349	98.14 243	99.38 239	94.09 425	91.07 406	98.07 350	91.04 423	89.62 358	99.35 307	96.75 319	99.09 189	98.68 304

EPMVS		97.82 262	97.65 253	98.35 295	98.88 337	95.98 348	99.49 185	94.71 424	97.57 222	99.26 202	99.48 265	92.46 310	99.71 235	97.87 234	99.08 190	99.35 222

MVS_Test		99.10 114	98.97 110	99.48 130	99.49 193	99.14 143	99.67 69	99.34 263	97.31 253	99.58 125	99.76 143	97.65 117	99.82 188	98.87 119	99.07 191	99.46 203

ADS-MVSNet2		98.02 227	98.07 207	97.87 334	99.33 240	95.19 368	99.23 294	99.08 324	96.24 338	99.10 234	99.67 189	94.11 260	98.93 375	96.81 317	99.05 192	99.48 192

ADS-MVSNet		98.20 201	98.08 204	98.56 267	99.33 240	96.48 333	99.23 294	99.15 316	96.24 338	99.10 234	99.67 189	94.11 260	99.71 235	96.81 317	99.05 192	99.48 192

GeoE		98.85 150	98.62 161	99.53 116	99.61 149	99.08 151	99.80 25	99.51 123	97.10 274	99.31 186	99.78 131	95.23 207	99.77 210	98.21 205	99.03 194	99.75 94

baseline2		97.87 250	97.55 262	98.82 238	99.18 282	98.02 249	99.41 222	96.58 418	96.97 285	96.51 384	99.17 334	93.43 279	99.57 271	97.71 254	99.03 194	98.86 270

HyFIR lowres test		99.11 110	98.92 119	99.65 81	99.90 4	99.37 109	99.02 338	99.91 3	97.67 213	99.59 124	99.75 146	95.90 182	99.73 225	99.53 41	99.02 196	99.86 35

LCM-MVSNet-Re		97.83 259	98.15 194	96.87 372	99.30 249	92.25 402	99.59 109	98.26 393	97.43 242	96.20 388	99.13 339	96.27 167	98.73 385	98.17 210	98.99 197	99.64 144

mvs_anonymous		99.03 124	98.99 106	99.16 183	99.38 228	98.52 220	99.51 167	99.38 242	97.79 197	99.38 172	99.81 99	97.30 127	99.45 283	99.35 59	98.99 197	99.51 186

EPP-MVSNet		99.13 99	98.99 106	99.53 116	99.65 134	99.06 154	99.81 20	99.33 270	97.43 242	99.60 121	99.88 43	97.14 132	99.84 168	99.13 85	98.94 199	99.69 123

MIMVSNet		97.73 278	97.45 277	98.57 264	99.45 209	97.50 278	99.02 338	98.98 338	96.11 350	99.41 163	99.14 338	90.28 346	98.74 384	95.74 345	98.93 200	99.47 198

TAMVS		99.12 105	99.08 89	99.24 175	99.46 203	98.55 214	99.51 167	99.46 195	98.09 157	99.45 149	99.82 85	98.34 93	99.51 277	98.70 146	98.93 200	99.67 130

CDS-MVSNet		99.09 115	99.03 96	99.25 173	99.42 213	98.73 198	99.45 201	99.46 195	98.11 154	99.46 148	99.77 139	98.01 108	99.37 300	98.70 146	98.92 202	99.66 133
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPM		97.59 297	97.09 317	99.07 191	99.06 312	98.26 237	98.30 406	99.10 321	94.88 373	98.08 347	99.34 306	96.27 167	99.64 260	89.87 403	98.92 202	99.31 228

XVG-OURS-SEG-HR		98.69 166	98.62 161	98.89 223	99.71 103	97.74 265	99.12 315	99.54 91	98.44 111	99.42 159	99.71 162	94.20 256	99.92 106	98.54 177	98.90 204	99.00 260

PMMVS		98.80 157	98.62 161	99.34 151	99.27 258	98.70 200	98.76 376	99.31 284	97.34 250	99.21 212	99.07 344	97.20 131	99.82 188	98.56 173	98.87 205	99.52 179

DSMNet-mixed		97.25 320	97.35 294	96.95 369	97.84 393	93.61 394	99.57 124	96.63 416	96.13 349	98.87 275	98.61 380	94.59 240	97.70 406	95.08 361	98.86 206	99.55 170

test_vis1_rt		95.81 353	95.65 352	96.32 379	99.67 118	91.35 406	99.49 185	96.74 415	98.25 132	95.24 394	98.10 400	74.96 415	99.90 130	99.53 41	98.85 207	97.70 400

APD_test1		95.87 351	96.49 333	94.00 386	99.53 172	84.01 415	99.54 148	99.32 280	95.91 357	97.99 352	99.85 61	85.49 393	99.88 147	91.96 395	98.84 208	98.12 380

XVG-OURS		98.73 164	98.68 150	98.88 225	99.70 108	97.73 266	98.92 360	99.55 82	98.52 102	99.45 149	99.84 71	95.27 203	99.91 118	98.08 218	98.84 208	99.00 260

Fast-Effi-MVS+		98.70 165	98.43 176	99.51 124	99.51 180	99.28 124	99.52 158	99.47 186	96.11 350	99.01 250	99.34 306	96.20 169	99.84 168	97.88 232	98.82 210	99.39 216

ab-mvs		98.86 143	98.63 156	99.54 108	99.64 136	99.19 133	99.44 207	99.54 91	97.77 200	99.30 189	99.81 99	94.20 256	99.93 94	99.17 83	98.82 210	99.49 191

MDTV_nov1_ep13			98.32 184		99.11 300	94.44 381	99.27 278	98.74 374	97.51 232	99.40 168	99.62 213	94.78 225	99.76 214	97.59 262	98.81 212

Test_1112_low_res		98.89 138	98.66 154	99.57 103	99.69 112	98.95 172	99.03 335	99.47 186	96.98 284	99.15 225	99.23 328	96.77 147	99.89 142	98.83 132	98.78 213	99.86 35

1112_ss		98.98 131	98.77 141	99.59 98	99.68 116	99.02 158	99.25 289	99.48 165	97.23 261	99.13 227	99.58 226	96.93 143	99.90 130	98.87 119	98.78 213	99.84 45

PatchT		97.03 328	96.44 334	98.79 244	98.99 323	98.34 234	99.16 306	99.07 327	92.13 400	99.52 138	97.31 410	94.54 245	98.98 364	88.54 408	98.73 215	99.03 257

UWE-MVS		97.58 298	97.29 305	98.48 275	99.09 306	96.25 342	99.01 343	96.61 417	97.86 186	99.19 218	99.01 352	88.72 365	99.90 130	97.38 284	98.69 216	99.28 230

WB-MVSnew		97.65 293	97.65 253	97.63 349	98.78 352	97.62 274	99.13 312	98.33 392	97.36 249	99.07 239	98.94 361	95.64 192	99.15 339	92.95 388	98.68 217	96.12 415

tpmrst		98.33 191	98.48 174	97.90 332	99.16 292	94.78 375	99.31 261	99.11 320	97.27 256	99.45 149	99.59 222	95.33 201	99.84 168	98.48 180	98.61 218	99.09 248

BH-w/o		98.00 232	97.89 228	98.32 298	99.35 235	96.20 344	99.01 343	98.90 353	96.42 328	98.38 330	99.00 353	95.26 205	99.72 229	96.06 337	98.61 218	99.03 257

cascas		97.69 285	97.43 286	98.48 275	98.60 376	97.30 284	98.18 410	99.39 234	92.96 395	98.41 328	98.78 374	93.77 275	99.27 320	98.16 211	98.61 218	98.86 270

CR-MVSNet		98.17 205	97.93 222	98.87 229	99.18 282	98.49 224	99.22 298	99.33 270	96.96 286	99.56 129	99.38 293	94.33 252	99.00 362	94.83 366	98.58 221	99.14 241

RPMNet		96.72 334	95.90 347	99.19 180	99.18 282	98.49 224	99.22 298	99.52 109	88.72 413	99.56 129	97.38 407	94.08 262	99.95 65	86.87 415	98.58 221	99.14 241

dp		97.75 274	97.80 233	97.59 352	99.10 303	93.71 391	99.32 258	98.88 356	96.48 323	99.08 238	99.55 237	92.67 301	99.82 188	96.52 329	98.58 221	99.24 236

testing3		97.28 318	96.76 327	98.82 238	99.37 231	98.07 247	99.45 201	99.36 251	97.56 224	97.89 356	98.95 360	83.70 403	98.82 380	96.03 338	98.56 224	99.58 164

CVMVSNet		98.57 174	98.67 151	98.30 300	99.35 235	95.59 355	99.50 174	99.55 82	98.60 95	99.39 170	99.83 76	94.48 247	99.45 283	98.75 140	98.56 224	99.85 39

Effi-MVS+		98.81 154	98.59 167	99.48 130	99.46 203	99.12 146	98.08 412	99.50 143	97.50 233	99.38 172	99.41 283	96.37 164	99.81 193	99.11 87	98.54 226	99.51 186

testgi		97.65 293	97.50 269	98.13 315	99.36 234	96.45 334	99.42 219	99.48 165	97.76 201	97.87 357	99.45 274	91.09 339	98.81 381	94.53 368	98.52 227	99.13 243

tpm cat1		97.39 313	97.36 292	97.50 355	99.17 290	93.73 390	99.43 212	99.31 284	91.27 403	98.71 295	99.08 343	94.31 254	99.77 210	96.41 333	98.50 228	99.00 260

WTY-MVS		99.06 119	98.88 127	99.61 95	99.62 145	99.16 138	99.37 241	99.56 74	98.04 169	99.53 136	99.62 213	96.84 144	99.94 76	98.85 126	98.49 229	99.72 110

tpmvs		97.98 234	98.02 212	97.84 337	99.04 316	94.73 376	99.31 261	99.20 310	96.10 354	98.76 291	99.42 279	94.94 214	99.81 193	96.97 308	98.45 230	98.97 264

UBG		97.85 253	97.48 271	98.95 208	99.25 265	97.64 273	99.24 291	98.74 374	97.90 182	98.64 311	98.20 395	88.65 369	99.81 193	98.27 202	98.40 231	99.42 210

UWE-MVS-28		97.36 314	97.24 310	97.75 343	98.84 346	94.44 381	99.24 291	97.58 407	97.98 175	99.00 254	99.00 353	91.35 335	99.53 276	93.75 378	98.39 232	99.27 234

LFMVS		97.90 246	97.35 294	99.54 108	99.52 177	99.01 160	99.39 234	98.24 395	97.10 274	99.65 103	99.79 124	84.79 398	99.91 118	99.28 71	98.38 233	99.69 123

Syy-MVS		97.09 327	97.14 313	96.95 369	99.00 320	92.73 400	99.29 268	99.39 234	97.06 278	97.41 366	98.15 396	93.92 269	98.68 386	91.71 396	98.34 234	99.45 206

myMVS_eth3d		96.89 330	96.37 335	98.43 288	99.00 320	97.16 292	99.29 268	99.39 234	97.06 278	97.41 366	98.15 396	83.46 404	98.68 386	95.27 358	98.34 234	99.45 206

test_yl		98.86 143	98.63 156	99.54 108	99.49 193	99.18 135	99.50 174	99.07 327	98.22 137	99.61 118	99.51 253	95.37 199	99.84 168	98.60 164	98.33 236	99.59 160

Anonymous20240529		98.09 213	97.68 250	99.34 151	99.66 128	98.44 229	99.40 230	99.43 220	93.67 387	99.22 209	99.89 35	90.23 350	99.93 94	99.26 75	98.33 236	99.66 133

DCV-MVSNet		98.86 143	98.63 156	99.54 108	99.49 193	99.18 135	99.50 174	99.07 327	98.22 137	99.61 118	99.51 253	95.37 199	99.84 168	98.60 164	98.33 236	99.59 160

GA-MVS		97.85 253	97.47 274	99.00 201	99.38 228	97.99 251	98.57 392	99.15 316	97.04 281	98.90 269	99.30 316	89.83 354	99.38 297	96.70 322	98.33 236	99.62 151

VDD-MVS		97.73 278	97.35 294	98.88 225	99.47 201	97.12 294	99.34 254	98.85 360	98.19 141	99.67 91	99.85 61	82.98 405	99.92 106	99.49 49	98.32 240	99.60 156

Anonymous202405211		98.30 194	97.98 215	99.26 172	99.57 160	98.16 241	99.41 222	98.55 388	96.03 355	99.19 218	99.74 151	91.87 320	99.92 106	99.16 84	98.29 241	99.70 121

SDMVSNet		99.11 110	98.90 122	99.75 65	99.81 47	99.59 77	99.81 20	99.65 35	98.78 81	99.64 108	99.88 43	94.56 242	99.93 94	99.67 27	98.26 242	99.72 110

sd_testset		98.75 161	98.57 168	99.29 166	99.81 47	98.26 237	99.56 130	99.62 43	98.78 81	99.64 108	99.88 43	92.02 317	99.88 147	99.54 39	98.26 242	99.72 110

myMVS_eth3d28		97.69 285	97.34 297	98.73 248	99.27 258	97.52 277	99.33 256	98.78 369	98.03 171	98.82 283	98.49 383	86.64 386	99.46 281	98.44 186	98.24 244	99.23 237

EGC-MVSNET		82.80 388	77.86 394	97.62 350	97.91 391	96.12 346	99.33 256	99.28 294	8.40 431	25.05 432	99.27 323	84.11 401	99.33 310	89.20 405	98.22 245	97.42 405

GG-mvs-BLEND				98.45 283	98.55 380	98.16 241	99.43 212	93.68 426		97.23 372	98.46 384	89.30 359	99.22 329	95.43 354	98.22 245	97.98 392

thres200		97.61 296	97.28 306	98.62 258	99.64 136	98.03 248	99.26 287	98.74 374	97.68 211	99.09 237	98.32 391	91.66 329	99.81 193	92.88 389	98.22 245	98.03 386

HY-MVS	97.30 7	98.85 150	98.64 155	99.47 133	99.42 213	99.08 151	99.62 95	99.36 251	97.39 247	99.28 193	99.68 183	96.44 162	99.92 106	98.37 192	98.22 245	99.40 215

thres600view7		97.86 252	97.51 268	98.92 214	99.72 98	97.95 256	99.59 109	98.74 374	97.94 178	99.27 198	98.62 378	91.75 323	99.86 155	93.73 379	98.19 249	98.96 266

thres100view900		97.76 270	97.45 277	98.69 254	99.72 98	97.86 262	99.59 109	98.74 374	97.93 179	99.26 202	98.62 378	91.75 323	99.83 181	93.22 384	98.18 250	98.37 367

tfpn200view9		97.72 280	97.38 290	98.72 250	99.69 112	97.96 254	99.50 174	98.73 380	97.83 192	99.17 223	98.45 385	91.67 327	99.83 181	93.22 384	98.18 250	98.37 367

VNet		99.11 110	98.90 122	99.73 71	99.52 177	99.56 83	99.41 222	99.39 234	99.01 48	99.74 72	99.78 131	95.56 193	99.92 106	99.52 43	98.18 250	99.72 110

thres400		97.77 269	97.38 290	98.92 214	99.69 112	97.96 254	99.50 174	98.73 380	97.83 192	99.17 223	98.45 385	91.67 327	99.83 181	93.22 384	98.18 250	98.96 266

VDDNet		97.55 299	97.02 319	99.16 183	99.49 193	98.12 245	99.38 239	99.30 288	95.35 363	99.68 87	99.90 30	82.62 407	99.93 94	99.31 67	98.13 254	99.42 210

alignmvs		98.81 154	98.56 170	99.58 101	99.43 211	99.42 105	99.51 167	98.96 341	98.61 94	99.35 180	98.92 365	94.78 225	99.77 210	99.35 59	98.11 255	99.54 172

tpm2		97.44 311	97.34 297	97.74 345	99.15 296	94.36 384	99.45 201	98.94 342	93.45 392	98.90 269	99.44 275	91.35 335	99.59 270	97.31 287	98.07 256	99.29 229

testing11		97.50 304	97.10 316	98.71 252	99.20 276	96.91 314	99.29 268	98.82 363	97.89 183	98.21 342	98.40 387	85.63 392	99.83 181	98.45 185	98.04 257	99.37 220

JIA-IIPM		97.50 304	97.02 319	98.93 212	98.73 361	97.80 264	99.30 263	98.97 339	91.73 402	98.91 267	94.86 417	95.10 210	99.71 235	97.58 263	97.98 258	99.28 230

testing91		97.44 311	97.02 319	98.71 252	99.18 282	96.89 316	99.19 302	99.04 331	97.78 199	98.31 334	98.29 392	85.41 394	99.85 161	98.01 224	97.95 259	99.39 216

CostFormer		97.72 280	97.73 246	97.71 346	99.15 296	94.02 387	99.54 148	99.02 334	94.67 378	99.04 247	99.35 302	92.35 313	99.77 210	98.50 179	97.94 260	99.34 225

sasdasda		99.02 125	98.86 130	99.51 124	99.42 213	99.32 115	99.80 25	99.48 165	98.63 91	99.31 186	98.81 370	97.09 134	99.75 217	99.27 73	97.90 261	99.47 198

canonicalmvs		99.02 125	98.86 130	99.51 124	99.42 213	99.32 115	99.80 25	99.48 165	98.63 91	99.31 186	98.81 370	97.09 134	99.75 217	99.27 73	97.90 261	99.47 198

ETVMVS		97.50 304	96.90 323	99.29 166	99.23 269	98.78 196	99.32 258	98.90 353	97.52 231	98.56 320	98.09 401	84.72 399	99.69 246	97.86 235	97.88 263	99.39 216

MGCFI-Net		99.01 129	98.85 132	99.50 129	99.42 213	99.26 127	99.82 16	99.48 165	98.60 95	99.28 193	98.81 370	97.04 138	99.76 214	99.29 70	97.87 264	99.47 198

OpenMVS_ROB	92.34 20	94.38 368	93.70 374	96.41 378	97.38 400	93.17 397	99.06 328	98.75 371	86.58 414	94.84 400	98.26 393	81.53 411	99.32 312	89.01 406	97.87 264	96.76 408

testing99		97.36 314	96.94 322	98.63 257	99.18 282	96.70 322	99.30 263	98.93 343	97.71 206	98.23 339	98.26 393	84.92 397	99.84 168	98.04 223	97.85 266	99.35 222

dongtai		93.26 373	92.93 377	94.25 385	99.39 226	85.68 413	97.68 416	93.27 427	92.87 396	96.85 382	99.39 291	82.33 409	97.48 408	76.78 421	97.80 267	99.58 164

TR-MVS		97.76 270	97.41 288	98.82 238	99.06 312	97.87 260	98.87 366	98.56 387	96.63 310	98.68 303	99.22 329	92.49 306	99.65 257	95.40 355	97.79 268	98.95 268

DeepMVS_CX				93.34 389	99.29 253	82.27 418		99.22 306	85.15 415	96.33 386	99.05 347	90.97 341	99.73 225	93.57 381	97.77 269	98.01 387

tt0805		97.97 237	97.77 239	98.57 264	99.59 156	96.61 329	99.45 201	99.08 324	98.21 139	98.88 272	99.80 112	88.66 368	99.70 241	98.58 167	97.72 270	99.39 216

CLD-MVS		98.16 206	98.10 200	98.33 296	99.29 253	96.82 319	98.75 377	99.44 214	97.83 192	99.13 227	99.55 237	92.92 289	99.67 249	98.32 199	97.69 271	98.48 353
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
testing222		97.16 323	96.50 332	99.16 183	99.16 292	98.47 228	99.27 278	98.66 384	97.71 206	98.23 339	98.15 396	82.28 410	99.84 168	97.36 285	97.66 272	99.18 240

HQP_MVS		98.27 197	98.22 190	98.44 286	99.29 253	96.97 310	99.39 234	99.47 186	98.97 59	99.11 231	99.61 217	92.71 298	99.69 246	97.78 243	97.63 273	98.67 311

plane_prior5								99.47 186					99.69 246	97.78 243	97.63 273	98.67 311

test_djsdf		98.67 168	98.57 168	98.98 203	98.70 366	98.91 179	99.88 4	99.46 195	97.55 225	99.22 209	99.88 43	95.73 188	99.28 317	99.03 97	97.62 275	98.75 283

anonymousdsp		98.44 179	98.28 187	98.94 210	98.50 382	98.96 169	99.77 34	99.50 143	97.07 276	98.87 275	99.77 139	94.76 229	99.28 317	98.66 153	97.60 276	98.57 347

plane_prior						96.97 310	99.21 300		98.45 108						97.60 276

HQP3-MVS								99.39 234							97.58 278

HQP-MVS		98.02 227	97.90 224	98.37 294	99.19 279	96.83 317	98.98 349	99.39 234	98.24 133	98.66 304	99.40 287	92.47 307	99.64 260	97.19 296	97.58 278	98.64 323

EI-MVSNet		98.67 168	98.67 151	98.68 255	99.35 235	97.97 252	99.50 174	99.38 242	96.93 291	99.20 215	99.83 76	97.87 110	99.36 304	98.38 190	97.56 280	98.71 290

MVSTER		98.49 175	98.32 184	99.00 201	99.35 235	99.02 158	99.54 148	99.38 242	97.41 245	99.20 215	99.73 157	93.86 272	99.36 304	98.87 119	97.56 280	98.62 332

MonoMVSNet		98.38 187	98.47 175	98.12 316	98.59 378	96.19 345	99.72 52	98.79 368	97.89 183	99.44 154	99.52 249	96.13 170	98.90 378	98.64 155	97.54 282	99.28 230

OPM-MVS		98.19 202	98.10 200	98.45 283	98.88 337	97.07 299	99.28 273	99.38 242	98.57 97	99.22 209	99.81 99	92.12 315	99.66 252	98.08 218	97.54 282	98.61 341
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
UniMVSNet_ETH3D		97.32 317	96.81 325	98.87 229	99.40 223	97.46 279	99.51 167	99.53 104	95.86 358	98.54 322	99.77 139	82.44 408	99.66 252	98.68 151	97.52 284	99.50 190

LPG-MVS_test		98.22 198	98.13 197	98.49 273	99.33 240	97.05 301	99.58 117	99.55 82	97.46 235	99.24 204	99.83 76	92.58 303	99.72 229	98.09 214	97.51 285	98.68 304

LGP-MVS_train				98.49 273	99.33 240	97.05 301		99.55 82	97.46 235	99.24 204	99.83 76	92.58 303	99.72 229	98.09 214	97.51 285	98.68 304

jajsoiax		98.43 180	98.28 187	98.88 225	98.60 376	98.43 230	99.82 16	99.53 104	98.19 141	98.63 313	99.80 112	93.22 284	99.44 288	99.22 77	97.50 287	98.77 279

EG-PatchMatch MVS		95.97 350	95.69 351	96.81 373	97.78 394	92.79 399	99.16 306	98.93 343	96.16 345	94.08 402	99.22 329	82.72 406	99.47 279	95.67 349	97.50 287	98.17 377

test_0402		96.64 336	96.24 338	97.85 335	98.85 344	96.43 335	99.44 207	99.26 298	93.52 389	96.98 379	99.52 249	88.52 372	99.20 336	92.58 394	97.50 287	97.93 395

ACMP	97.20 11	98.06 217	97.94 221	98.45 283	99.37 231	97.01 306	99.44 207	99.49 153	97.54 228	98.45 327	99.79 124	91.95 319	99.72 229	97.91 230	97.49 290	98.62 332
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
mvs_tets		98.40 186	98.23 189	98.91 218	98.67 369	98.51 222	99.66 75	99.53 104	98.19 141	98.65 310	99.81 99	92.75 293	99.44 288	99.31 67	97.48 291	98.77 279

test_fmvs2		97.25 320	97.30 303	97.09 365	99.43 211	93.31 396	99.73 50	98.87 358	98.83 72	99.28 193	99.80 112	84.45 400	99.66 252	97.88 232	97.45 292	98.30 369

ACMM	97.58 5	98.37 189	98.34 182	98.48 275	99.41 218	97.10 295	99.56 130	99.45 206	98.53 101	99.04 247	99.85 61	93.00 287	99.71 235	98.74 141	97.45 292	98.64 323
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH	97.28 8	98.10 212	97.99 214	98.44 286	99.41 218	96.96 312	99.60 102	99.56 74	98.09 157	98.15 345	99.91 23	90.87 342	99.70 241	98.88 116	97.45 292	98.67 311
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LTVRE_ROB	97.16 12	98.02 227	97.90 224	98.40 291	99.23 269	96.80 320	99.70 56	99.60 56	97.12 270	98.18 344	99.70 166	91.73 325	99.72 229	98.39 189	97.45 292	98.68 304
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
ACMMP++															97.43 296

D2MVS		98.41 183	98.50 173	98.15 314	99.26 261	96.62 328	99.40 230	99.61 50	97.71 206	98.98 257	99.36 299	96.04 173	99.67 249	98.70 146	97.41 297	98.15 379

ITE_SJBPF				98.08 317	99.29 253	96.37 336		98.92 346	98.34 121	98.83 281	99.75 146	91.09 339	99.62 267	95.82 342	97.40 298	98.25 373

XVG-ACMP-BASELINE		97.83 259	97.71 248	98.20 308	99.11 300	96.33 338	99.41 222	99.52 109	98.06 166	99.05 246	99.50 256	89.64 357	99.73 225	97.73 251	97.38 299	98.53 349

USDC		97.34 316	97.20 311	97.75 343	99.07 310	95.20 367	98.51 396	99.04 331	97.99 174	98.31 334	99.86 56	89.02 361	99.55 274	95.67 349	97.36 300	98.49 352

PVSNet_BlendedMVS		98.86 143	98.80 137	99.03 197	99.76 69	98.79 194	99.28 273	99.91 3	97.42 244	99.67 91	99.37 296	97.53 118	99.88 147	98.98 102	97.29 301	98.42 361

dmvs_re		98.08 215	98.16 192	97.85 335	99.55 168	94.67 378	99.70 56	98.92 346	98.15 146	99.06 244	99.35 302	93.67 278	99.25 322	97.77 246	97.25 302	99.64 144

PS-MVSNAJss		98.92 136	98.92 119	98.90 220	98.78 352	98.53 216	99.78 32	99.54 91	98.07 162	99.00 254	99.76 143	99.01 18	99.37 300	99.13 85	97.23 303	98.81 273

TinyColmap		97.12 325	96.89 324	97.83 338	99.07 310	95.52 359	98.57 392	98.74 374	97.58 221	97.81 360	99.79 124	88.16 376	99.56 272	95.10 360	97.21 304	98.39 365

ACMMP++_ref															97.19 305

ACMH+	97.24 10	97.92 243	97.78 237	98.32 298	99.46 203	96.68 326	99.56 130	99.54 91	98.41 113	97.79 361	99.87 52	90.18 351	99.66 252	98.05 222	97.18 306	98.62 332

test0.0.03 1		97.71 283	97.42 287	98.56 267	98.41 386	97.82 263	98.78 374	98.63 385	97.34 250	98.05 351	98.98 357	94.45 249	98.98 364	95.04 362	97.15 307	98.89 269

kuosan		90.92 381	90.11 386	93.34 389	98.78 352	85.59 414	98.15 411	93.16 429	89.37 410	92.07 410	98.38 388	81.48 412	95.19 419	62.54 428	97.04 308	99.25 235

CMPMVS	69.68 23	94.13 369	94.90 361	91.84 394	97.24 404	80.01 424	98.52 395	99.48 165	89.01 411	91.99 411	99.67 189	85.67 391	99.13 343	95.44 353	97.03 309	96.39 412
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
OurMVSNet-221017-0		97.88 248	97.77 239	98.19 309	98.71 365	96.53 331	99.88 4	99.00 336	97.79 197	98.78 289	99.94 6	91.68 326	99.35 307	97.21 292	96.99 310	98.69 299

LF4IMVS		97.52 301	97.46 276	97.70 347	98.98 326	95.55 356	99.29 268	98.82 363	98.07 162	98.66 304	99.64 202	89.97 352	99.61 268	97.01 304	96.68 311	97.94 394

GBi-Net		97.68 288	97.48 271	98.29 301	99.51 180	97.26 288	99.43 212	99.48 165	96.49 320	99.07 239	99.32 313	90.26 347	98.98 364	97.10 300	96.65 312	98.62 332

test1		97.68 288	97.48 271	98.29 301	99.51 180	97.26 288	99.43 212	99.48 165	96.49 320	99.07 239	99.32 313	90.26 347	98.98 364	97.10 300	96.65 312	98.62 332

FMVSNet3		98.03 225	97.76 243	98.84 236	99.39 226	98.98 162	99.40 230	99.38 242	96.67 304	99.07 239	99.28 320	92.93 288	98.98 364	97.10 300	96.65 312	98.56 348

FMVSNet2		97.72 280	97.36 292	98.80 243	99.51 180	98.84 187	99.45 201	99.42 222	96.49 320	98.86 279	99.29 318	90.26 347	98.98 364	96.44 331	96.56 315	98.58 346

K. test v3		97.10 326	96.79 326	98.01 322	98.72 363	96.33 338	99.87 8	97.05 410	97.59 219	96.16 389	99.80 112	88.71 366	99.04 355	96.69 323	96.55 316	98.65 321

tpm		97.67 291	97.55 262	98.03 319	99.02 318	95.01 371	99.43 212	98.54 389	96.44 326	99.12 229	99.34 306	91.83 322	99.60 269	97.75 249	96.46 317	99.48 192

SixPastTwentyTwo		97.50 304	97.33 300	98.03 319	98.65 370	96.23 343	99.77 34	98.68 383	97.14 267	97.90 355	99.93 10	90.45 345	99.18 337	97.00 305	96.43 318	98.67 311

FIs		98.78 158	98.63 156	99.23 177	99.18 282	99.54 87	99.83 15	99.59 61	98.28 127	98.79 288	99.81 99	96.75 148	99.37 300	99.08 92	96.38 319	98.78 275

FC-MVSNet-test		98.75 161	98.62 161	99.15 187	99.08 309	99.45 102	99.86 11	99.60 56	98.23 136	98.70 301	99.82 85	96.80 145	99.22 329	99.07 93	96.38 319	98.79 274

XXY-MVS		98.38 187	98.09 203	99.24 175	99.26 261	99.32 115	99.56 130	99.55 82	97.45 238	98.71 295	99.83 76	93.23 282	99.63 266	98.88 116	96.32 321	98.76 281

reproduce_monomvs		97.89 247	97.87 229	97.96 328	99.51 180	95.45 361	99.60 102	99.25 300	99.17 23	98.85 280	99.49 259	89.29 360	99.64 260	99.35 59	96.31 322	98.78 275

FMVSNet1		96.84 332	96.36 336	98.29 301	99.32 247	97.26 288	99.43 212	99.48 165	95.11 367	98.55 321	99.32 313	83.95 402	98.98 364	95.81 343	96.26 323	98.62 332

N_pmnet		94.95 363	95.83 349	92.31 393	98.47 383	79.33 425	99.12 315	92.81 431	93.87 385	97.68 362	99.13 339	93.87 271	99.01 361	91.38 398	96.19 324	98.59 345

Anonymous20240521		96.20 345	95.89 348	97.13 363	97.72 397	94.96 373	99.79 31	99.29 292	93.01 394	97.20 374	99.03 349	89.69 356	98.36 392	91.16 399	96.13 325	98.07 383

pmmvs4		98.13 209	97.90 224	98.81 241	98.61 375	98.87 182	98.99 346	99.21 309	96.44 326	99.06 244	99.58 226	95.90 182	99.11 348	97.18 298	96.11 326	98.46 358

WBMVS		97.74 276	97.50 269	98.46 281	99.24 267	97.43 280	99.21 300	99.42 222	97.45 238	98.96 261	99.41 283	88.83 364	99.23 325	98.94 107	96.02 327	98.71 290

our_test_3		97.65 293	97.68 250	97.55 353	98.62 373	94.97 372	98.84 368	99.30 288	96.83 297	98.19 343	99.34 306	97.01 140	99.02 359	95.00 363	96.01 328	98.64 323

IterMVS		97.83 259	97.77 239	98.02 321	99.58 158	96.27 341	99.02 338	99.48 165	97.22 262	98.71 295	99.70 166	92.75 293	99.13 343	97.46 278	96.00 329	98.67 311
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		97.85 253	97.64 256	98.48 275	99.09 306	97.87 260	98.60 391	99.33 270	97.11 273	98.87 275	99.22 329	92.38 312	99.17 338	98.21 205	95.99 330	98.42 361

miper_ehance_all_eth		98.18 204	98.10 200	98.41 289	99.23 269	97.72 268	98.72 380	99.31 284	96.60 314	98.88 272	99.29 318	97.29 128	99.13 343	97.60 261	95.99 330	98.38 366

miper_enhance_ethall		98.16 206	98.08 204	98.41 289	98.96 329	97.72 268	98.45 398	99.32 280	96.95 288	98.97 259	99.17 334	97.06 137	99.22 329	97.86 235	95.99 330	98.29 370

ppachtmachnet_test		97.49 309	97.45 277	97.61 351	98.62 373	95.24 366	98.80 372	99.46 195	96.11 350	98.22 341	99.62 213	96.45 161	98.97 371	93.77 377	95.97 333	98.61 341

pmmvs5		97.52 301	97.30 303	98.16 311	98.57 379	96.73 321	99.27 278	98.90 353	96.14 348	98.37 331	99.53 246	91.54 332	99.14 340	97.51 272	95.87 334	98.63 330

IterMVS-SCA-FT		97.82 262	97.75 244	98.06 318	99.57 160	96.36 337	99.02 338	99.49 153	97.18 264	98.71 295	99.72 161	92.72 296	99.14 340	97.44 280	95.86 335	98.67 311

cl____		98.01 230	97.84 232	98.55 269	99.25 265	97.97 252	98.71 381	99.34 263	96.47 325	98.59 319	99.54 242	95.65 191	99.21 334	97.21 292	95.77 336	98.46 358

DIV-MVS_self_test		98.01 230	97.85 231	98.48 275	99.24 267	97.95 256	98.71 381	99.35 258	96.50 319	98.60 318	99.54 242	95.72 189	99.03 357	97.21 292	95.77 336	98.46 358

new_pmnet		96.38 342	96.03 344	97.41 356	98.13 390	95.16 370	99.05 330	99.20 310	93.94 384	97.39 369	98.79 373	91.61 331	99.04 355	90.43 401	95.77 336	98.05 385

FMVSNet5		96.43 341	96.19 340	97.15 361	99.11 300	95.89 350	99.32 258	99.52 109	94.47 382	98.34 333	99.07 344	87.54 382	97.07 411	92.61 393	95.72 339	98.47 355

Gipuma		90.99 380	90.15 385	93.51 388	98.73 361	90.12 408	93.98 421	99.45 206	79.32 419	92.28 409	94.91 416	69.61 417	97.98 400	87.42 412	95.67 340	92.45 419
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
IterMVS-LS		98.46 178	98.42 177	98.58 263	99.59 156	98.00 250	99.37 241	99.43 220	96.94 290	99.07 239	99.59 222	97.87 110	99.03 357	98.32 199	95.62 341	98.71 290
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ttmdpeth		97.80 266	97.63 257	98.29 301	98.77 357	97.38 282	99.64 84	99.36 251	98.78 81	96.30 387	99.58 226	92.34 314	99.39 295	98.36 194	95.58 342	98.10 381

Patchmtry		97.75 274	97.40 289	98.81 241	99.10 303	98.87 182	99.11 321	99.33 270	94.83 375	98.81 284	99.38 293	94.33 252	99.02 359	96.10 336	95.57 343	98.53 349

MIMVSNet1		95.51 355	95.04 360	96.92 371	97.38 400	95.60 354	99.52 158	99.50 143	93.65 388	96.97 380	99.17 334	85.28 396	96.56 415	88.36 409	95.55 344	98.60 344

eth_miper_zixun_eth		98.05 222	97.96 217	98.33 296	99.26 261	97.38 282	98.56 394	99.31 284	96.65 306	98.88 272	99.52 249	96.58 154	99.12 347	97.39 283	95.53 345	98.47 355

miper_lstm_enhance		98.00 232	97.91 223	98.28 305	99.34 239	97.43 280	98.88 364	99.36 251	96.48 323	98.80 286	99.55 237	95.98 175	98.91 376	97.27 289	95.50 346	98.51 351

tfpnnormal		97.84 257	97.47 274	98.98 203	99.20 276	99.22 132	99.64 84	99.61 50	96.32 332	98.27 338	99.70 166	93.35 281	99.44 288	95.69 347	95.40 347	98.27 371

c3_l		98.12 211	98.04 209	98.38 293	99.30 249	97.69 272	98.81 371	99.33 270	96.67 304	98.83 281	99.34 306	97.11 133	98.99 363	97.58 263	95.34 348	98.48 353

EU-MVSNet		97.98 234	98.03 210	97.81 341	98.72 363	96.65 327	99.66 75	99.66 28	98.09 157	98.35 332	99.82 85	95.25 206	98.01 399	97.41 282	95.30 349	98.78 275

v1240		97.69 285	97.32 301	98.79 244	98.85 344	98.43 230	99.48 189	99.36 251	96.11 350	99.27 198	99.36 299	93.76 276	99.24 324	94.46 369	95.23 350	98.70 295

v1192		97.81 264	97.44 282	98.91 218	98.88 337	98.68 201	99.51 167	99.34 263	96.18 343	99.20 215	99.34 306	94.03 264	99.36 304	95.32 357	95.18 351	98.69 299

v1144		97.98 234	97.69 249	98.85 235	98.87 340	98.66 203	99.54 148	99.35 258	96.27 336	99.23 208	99.35 302	94.67 236	99.23 325	96.73 320	95.16 352	98.68 304

v1921920		97.80 266	97.45 277	98.84 236	98.80 348	98.53 216	99.52 158	99.34 263	96.15 347	99.24 204	99.47 268	93.98 266	99.29 316	95.40 355	95.13 353	98.69 299

Anonymous20231206		96.22 343	96.03 344	96.79 374	97.31 403	94.14 386	99.63 90	99.08 324	96.17 344	97.04 378	99.06 346	93.94 267	97.76 405	86.96 414	95.06 354	98.47 355

v144192		97.92 243	97.60 260	98.87 229	98.83 347	98.65 204	99.55 144	99.34 263	96.20 341	99.32 185	99.40 287	94.36 251	99.26 321	96.37 334	95.03 355	98.70 295

v2v482		98.06 217	97.77 239	98.92 214	98.90 335	98.82 191	99.57 124	99.36 251	96.65 306	99.19 218	99.35 302	94.20 256	99.25 322	97.72 253	94.97 356	98.69 299

FPMVS		84.93 387	85.65 388	82.75 408	86.77 429	63.39 434	98.35 401	98.92 346	74.11 420	83.39 419	98.98 357	50.85 427	92.40 423	84.54 419	94.97 356	92.46 418

lessismore_v0				97.79 342	98.69 367	95.44 363		94.75 423		95.71 393	99.87 52	88.69 367	99.32 312	95.89 341	94.93 358	98.62 332

dmvs_testset		95.02 360	96.12 341	91.72 395	99.10 303	80.43 423	99.58 117	97.87 402	97.47 234	95.22 395	98.82 369	93.99 265	95.18 420	88.09 410	94.91 359	99.56 169

test_method		91.10 379	91.36 381	90.31 399	95.85 412	73.72 432	94.89 420	99.25 300	68.39 423	95.82 392	99.02 351	80.50 413	98.95 374	93.64 380	94.89 360	98.25 373

V42		98.06 217	97.79 234	98.86 232	98.98 326	98.84 187	99.69 60	99.34 263	96.53 318	99.30 189	99.37 296	94.67 236	99.32 312	97.57 267	94.66 361	98.42 361

v10		97.85 253	97.52 266	98.86 232	98.99 323	98.67 202	99.75 42	99.41 225	95.70 359	98.98 257	99.41 283	94.75 230	99.23 325	96.01 340	94.63 362	98.67 311

nrg030		98.64 171	98.42 177	99.28 170	99.05 315	99.69 54	99.81 20	99.46 195	98.04 169	99.01 250	99.82 85	96.69 150	99.38 297	99.34 64	94.59 363	98.78 275

VPA-MVSNet		98.29 195	97.95 219	99.30 163	99.16 292	99.54 87	99.50 174	99.58 65	98.27 129	99.35 180	99.37 296	92.53 305	99.65 257	99.35 59	94.46 364	98.72 288

MDA-MVSNet_test_wron		95.45 356	94.60 363	98.01 322	98.16 389	97.21 291	99.11 321	99.24 303	93.49 390	80.73 423	98.98 357	93.02 286	98.18 394	94.22 374	94.45 365	98.64 323

Anonymous20231211		97.88 248	97.54 265	98.90 220	99.71 103	98.53 216	99.48 189	99.57 69	94.16 383	98.81 284	99.68 183	93.23 282	99.42 293	98.84 129	94.42 366	98.76 281

MDA-MVSNet-bldmvs		94.96 362	93.98 369	97.92 330	98.24 388	97.27 286	99.15 309	99.33 270	93.80 386	80.09 424	99.03 349	88.31 374	97.86 403	93.49 382	94.36 367	98.62 332

WR-MVS		98.06 217	97.73 246	99.06 193	98.86 343	99.25 129	99.19 302	99.35 258	97.30 254	98.66 304	99.43 277	93.94 267	99.21 334	98.58 167	94.28 368	98.71 290

test20.03		96.12 347	95.96 346	96.63 375	97.44 399	95.45 361	99.51 167	99.38 242	96.55 317	96.16 389	99.25 326	93.76 276	96.17 416	87.35 413	94.22 369	98.27 371

YYNet1		95.36 358	94.51 365	97.92 330	97.89 392	97.10 295	99.10 323	99.23 304	93.26 393	80.77 422	99.04 348	92.81 292	98.02 398	94.30 370	94.18 370	98.64 323

mvs5depth		96.66 335	96.22 339	97.97 326	97.00 409	96.28 340	98.66 386	99.03 333	96.61 311	96.93 381	99.79 124	87.20 384	99.47 279	96.65 327	94.13 371	98.16 378

CP-MVSNet		98.09 213	97.78 237	99.01 199	98.97 328	99.24 130	99.67 69	99.46 195	97.25 258	98.48 326	99.64 202	93.79 274	99.06 353	98.63 157	94.10 372	98.74 286

v8		97.95 239	97.63 257	98.93 212	98.95 330	98.81 193	99.80 25	99.41 225	96.03 355	99.10 234	99.42 279	94.92 217	99.30 315	96.94 311	94.08 373	98.66 319

PS-CasMVS		97.93 240	97.59 261	98.95 208	98.99 323	99.06 154	99.68 66	99.52 109	97.13 268	98.31 334	99.68 183	92.44 311	99.05 354	98.51 178	94.08 373	98.75 283

WB-MVS		93.10 374	94.10 367	90.12 400	95.51 418	81.88 420	99.73 50	99.27 297	95.05 370	93.09 407	98.91 366	94.70 234	91.89 424	76.62 422	94.02 375	96.58 410

v7n		97.87 250	97.52 266	98.92 214	98.76 359	98.58 212	99.84 12	99.46 195	96.20 341	98.91 267	99.70 166	94.89 219	99.44 288	96.03 338	93.89 376	98.75 283

SSC-MVS		92.73 376	93.73 371	89.72 401	95.02 420	81.38 421	99.76 37	99.23 304	94.87 374	92.80 408	98.93 362	94.71 233	91.37 425	74.49 424	93.80 377	96.42 411

WR-MVS_H		98.13 209	97.87 229	98.90 220	99.02 318	98.84 187	99.70 56	99.59 61	97.27 256	98.40 329	99.19 333	95.53 194	99.23 325	98.34 196	93.78 378	98.61 341

NR-MVSNet		97.97 237	97.61 259	99.02 198	98.87 340	99.26 127	99.47 196	99.42 222	97.63 216	97.08 377	99.50 256	95.07 211	99.13 343	97.86 235	93.59 379	98.68 304

pm-mvs1		97.68 288	97.28 306	98.88 225	99.06 312	98.62 208	99.50 174	99.45 206	96.32 332	97.87 357	99.79 124	92.47 307	99.35 307	97.54 270	93.54 380	98.67 311

UniMVSNet (Re)		98.29 195	98.00 213	99.13 188	99.00 320	99.36 112	99.49 185	99.51 123	97.95 177	98.97 259	99.13 339	96.30 166	99.38 297	98.36 194	93.34 381	98.66 319

baseline1		98.31 192	97.95 219	99.38 148	99.50 191	98.74 197	99.59 109	98.93 343	98.41 113	99.14 226	99.60 220	94.59 240	99.79 203	98.48 180	93.29 382	99.61 153

VPNet		97.84 257	97.44 282	99.01 199	99.21 274	98.94 175	99.48 189	99.57 69	98.38 115	99.28 193	99.73 157	88.89 363	99.39 295	99.19 79	93.27 383	98.71 290

PEN-MVS		97.76 270	97.44 282	98.72 250	98.77 357	98.54 215	99.78 32	99.51 123	97.06 278	98.29 337	99.64 202	92.63 302	98.89 379	98.09 214	93.16 384	98.72 288

v148		97.79 268	97.55 262	98.50 272	98.74 360	97.72 268	99.54 148	99.33 270	96.26 337	98.90 269	99.51 253	94.68 235	99.14 340	97.83 239	93.15 385	98.63 330

TranMVSNet+NR-MVSNet		97.93 240	97.66 252	98.76 247	98.78 352	98.62 208	99.65 81	99.49 153	97.76 201	98.49 325	99.60 220	94.23 255	98.97 371	98.00 225	92.90 386	98.70 295

Baseline_NR-MVSNet		97.76 270	97.45 277	98.68 255	99.09 306	98.29 235	99.41 222	98.85 360	95.65 360	98.63 313	99.67 189	94.82 221	99.10 350	98.07 221	92.89 387	98.64 323

UniMVSNet_NR-MVSNet		98.22 198	97.97 216	98.96 206	98.92 333	98.98 162	99.48 189	99.53 104	97.76 201	98.71 295	99.46 272	96.43 163	99.22 329	98.57 170	92.87 388	98.69 299

DU-MVS		98.08 215	97.79 234	98.96 206	98.87 340	98.98 162	99.41 222	99.45 206	97.87 185	98.71 295	99.50 256	94.82 221	99.22 329	98.57 170	92.87 388	98.68 304

pmmvs6		96.53 338	96.09 343	97.82 340	98.69 367	95.47 360	99.37 241	99.47 186	93.46 391	97.41 366	99.78 131	87.06 385	99.33 310	96.92 314	92.70 390	98.65 321

MVStest1		96.08 349	95.48 354	97.89 333	98.93 331	96.70 322	99.56 130	99.35 258	92.69 398	91.81 412	99.46 272	89.90 353	98.96 373	95.00 363	92.61 391	98.00 390

DTE-MVSNet		97.51 303	97.19 312	98.46 281	98.63 372	98.13 244	99.84 12	99.48 165	96.68 303	97.97 354	99.67 189	92.92 289	98.56 388	96.88 316	92.60 392	98.70 295

ET-MVSNet_ETH3D		96.49 339	95.64 353	99.05 195	99.53 172	98.82 191	98.84 368	97.51 408	97.63 216	84.77 417	99.21 332	92.09 316	98.91 376	98.98 102	92.21 393	99.41 213

TransMVSNet (Re)		97.15 324	96.58 330	98.86 232	99.12 298	98.85 186	99.49 185	98.91 351	95.48 362	97.16 375	99.80 112	93.38 280	99.11 348	94.16 375	91.73 394	98.62 332

ambc				93.06 392	92.68 423	82.36 417	98.47 397	98.73 380		95.09 398	97.41 406	55.55 424	99.10 350	96.42 332	91.32 395	97.71 398

testf1		90.42 382	90.68 383	89.65 402	97.78 394	73.97 430	99.13 312	98.81 365	89.62 408	91.80 413	98.93 362	62.23 422	98.80 382	86.61 416	91.17 396	96.19 413

APD_test2		90.42 382	90.68 383	89.65 402	97.78 394	73.97 430	99.13 312	98.81 365	89.62 408	91.80 413	98.93 362	62.23 422	98.80 382	86.61 416	91.17 396	96.19 413

PMVS	70.75 22	75.98 394	74.97 395	79.01 410	70.98 433	55.18 435	93.37 422	98.21 396	65.08 427	61.78 428	93.83 418	21.74 435	92.53 422	78.59 420	91.12 398	89.34 423
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_f		91.90 378	91.26 382	93.84 387	95.52 417	85.92 412	99.69 60	98.53 390	95.31 364	93.87 403	96.37 414	55.33 425	98.27 393	95.70 346	90.98 399	97.32 406

test_fmvs3		92.10 377	91.77 380	93.08 391	96.19 410	86.25 411	99.82 16	98.62 386	96.65 306	95.19 397	96.90 411	55.05 426	95.93 418	96.63 328	90.92 400	97.06 407

mvsany_test3		93.77 371	93.45 375	94.74 384	95.78 413	88.01 410	99.64 84	98.25 394	98.28 127	94.31 401	97.97 403	68.89 418	98.51 390	97.50 273	90.37 401	97.71 398

UnsupCasMVSNet_eth		96.44 340	96.12 341	97.40 357	98.65 370	95.65 353	99.36 246	99.51 123	97.13 268	96.04 391	98.99 355	88.40 373	98.17 395	96.71 321	90.27 402	98.40 364

Patchmatch-RL test		95.84 352	95.81 350	95.95 381	95.61 414	90.57 407	98.24 407	98.39 391	95.10 369	95.20 396	98.67 377	94.78 225	97.77 404	96.28 335	90.02 403	99.51 186

PM-MVS		92.96 375	92.23 379	95.14 383	95.61 414	89.98 409	99.37 241	98.21 396	94.80 376	95.04 399	97.69 404	65.06 419	97.90 402	94.30 370	89.98 404	97.54 404

pmmvs-eth3d		95.34 359	94.73 362	97.15 361	95.53 416	95.94 349	99.35 251	99.10 321	95.13 365	93.55 404	97.54 405	88.15 377	97.91 401	94.58 367	89.69 405	97.61 401

mmtdpeth		96.95 329	96.71 328	97.67 348	99.33 240	94.90 374	99.89 2	99.28 294	98.15 146	99.72 79	98.57 381	86.56 387	99.90 130	99.82 20	89.02 406	98.20 376

new-patchmatchnet		94.48 367	94.08 368	95.67 382	95.08 419	92.41 401	99.18 304	99.28 294	94.55 381	93.49 405	97.37 408	87.86 380	97.01 412	91.57 397	88.36 407	97.61 401

test_vis3_rt		87.04 384	85.81 387	90.73 398	93.99 422	81.96 419	99.76 37	90.23 433	92.81 397	81.35 421	91.56 421	40.06 430	99.07 352	94.27 372	88.23 408	91.15 421

UnsupCasMVSNet_bld		93.53 372	92.51 378	96.58 377	97.38 400	93.82 388	98.24 407	99.48 165	91.10 405	93.10 406	96.66 412	74.89 416	98.37 391	94.03 376	87.71 409	97.56 403

pmmvs3		94.09 370	93.25 376	96.60 376	94.76 421	94.49 380	98.92 360	98.18 398	89.66 407	96.48 385	98.06 402	86.28 388	97.33 409	89.68 404	87.20 410	97.97 393

IB-MVS	95.67 18	96.22 343	95.44 357	98.57 264	99.21 274	96.70 322	98.65 387	97.74 405	96.71 301	97.27 371	98.54 382	86.03 389	99.92 106	98.47 183	86.30 411	99.10 244
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
LCM-MVSNet		86.80 386	85.22 390	91.53 396	87.81 428	80.96 422	98.23 409	98.99 337	71.05 421	90.13 416	96.51 413	48.45 429	96.88 413	90.51 400	85.30 412	96.76 408

h-mvs33		97.70 284	97.28 306	98.97 205	99.70 108	97.27 286	99.36 246	99.45 206	98.94 62	99.66 96	99.64 202	94.93 215	99.99 4	99.48 50	84.36 413	99.65 137

AUN-MVS		96.88 331	96.31 337	98.59 260	99.48 200	97.04 304	99.27 278	99.22 306	97.44 241	98.51 323	99.41 283	91.97 318	99.66 252	97.71 254	83.83 414	99.07 254

hse-mvs2		97.50 304	97.14 313	98.59 260	99.49 193	97.05 301	99.28 273	99.22 306	98.94 62	99.66 96	99.42 279	94.93 215	99.65 257	99.48 50	83.80 415	99.08 249

TDRefinement		95.42 357	94.57 364	97.97 326	89.83 427	96.11 347	99.48 189	98.75 371	96.74 299	96.68 383	99.88 43	88.65 369	99.71 235	98.37 192	82.74 416	98.09 382

PVSNet_0	94.43 19	96.09 348	95.47 355	97.94 329	99.31 248	94.34 385	97.81 414	99.70 15	97.12 270	97.46 365	98.75 375	89.71 355	99.79 203	97.69 257	81.69 417	99.68 127

KD-MVS_self_test		95.00 361	94.34 366	96.96 368	97.07 408	95.39 364	99.56 130	99.44 214	95.11 367	97.13 376	97.32 409	91.86 321	97.27 410	90.35 402	81.23 418	98.23 375

CL-MVSNet_self_test		94.49 366	93.97 370	96.08 380	96.16 411	93.67 393	98.33 404	99.38 242	95.13 365	97.33 370	98.15 396	92.69 300	96.57 414	88.67 407	79.87 419	97.99 391

PMMVS2		86.87 385	85.37 389	91.35 397	90.21 426	83.80 416	98.89 363	97.45 409	83.13 418	91.67 415	95.03 415	48.49 428	94.70 421	85.86 418	77.62 420	95.54 416

KD-MVS_2432*1600		94.62 364	93.72 372	97.31 358	97.19 406	95.82 351	98.34 402	99.20 310	95.00 371	97.57 363	98.35 389	87.95 378	98.10 396	92.87 390	77.00 421	98.01 387

miper_refine_blended		94.62 364	93.72 372	97.31 358	97.19 406	95.82 351	98.34 402	99.20 310	95.00 371	97.57 363	98.35 389	87.95 378	98.10 396	92.87 390	77.00 421	98.01 387

MVE	76.82 21	76.91 393	74.31 397	84.70 405	85.38 431	76.05 429	96.88 419	93.17 428	67.39 424	71.28 426	89.01 425	21.66 436	87.69 426	71.74 425	72.29 423	90.35 422
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 390	79.88 392	82.81 407	90.75 425	76.38 428	97.69 415	95.76 420	66.44 425	83.52 418	92.25 420	62.54 421	87.16 427	68.53 426	61.40 424	84.89 425

EMVS		80.02 391	79.22 393	82.43 409	91.19 424	76.40 427	97.55 418	92.49 432	66.36 426	83.01 420	91.27 422	64.63 420	85.79 428	65.82 427	60.65 425	85.08 424

ANet_high		77.30 392	74.86 396	84.62 406	75.88 432	77.61 426	97.63 417	93.15 430	88.81 412	64.27 427	89.29 424	36.51 431	83.93 429	75.89 423	52.31 426	92.33 420

tmp_tt		82.80 388	81.52 391	86.66 404	66.61 434	68.44 433	92.79 423	97.92 400	68.96 422	80.04 425	99.85 61	85.77 390	96.15 417	97.86 235	43.89 427	95.39 417

testmvs		39.17 396	43.78 398	25.37 413	36.04 436	16.84 438	98.36 400	26.56 435	20.06 429	38.51 430	67.32 426	29.64 433	15.30 432	37.59 430	39.90 428	43.98 427

test123		39.01 397	42.50 399	28.53 412	39.17 435	20.91 437	98.75 377	19.17 437	19.83 430	38.57 429	66.67 427	33.16 432	15.42 431	37.50 431	29.66 429	49.26 426

wuyk23d		40.18 395	41.29 400	36.84 411	86.18 430	49.12 436	79.73 424	22.81 436	27.64 428	25.46 431	28.45 431	21.98 434	48.89 430	55.80 429	23.56 430	12.51 428

mmdepth		0.02 402	0.03 405	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

monomultidepth		0.02 402	0.03 405	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

test_blank		0.13 401	0.17 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	1.57 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

uanet_test		0.02 402	0.03 405	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

DCPMVS		0.02 402	0.03 405	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

cdsmvs_eth3d_5k		24.64 398	32.85 401	0.00 414	0.00 437	0.00 439	0.00 425	99.51 123	0.00 432	0.00 433	99.56 234	96.58 154	0.00 433	0.00 432	0.00 431	0.00 429

pcd_1.5k_mvsjas		8.27 400	11.03 403	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	99.01 18	0.00 433	0.00 432	0.00 431	0.00 429

sosnet-low-res		0.02 402	0.03 405	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

sosnet		0.02 402	0.03 405	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

uncertanet		0.02 402	0.03 405	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

Regformer		0.02 402	0.03 405	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

ab-mvs-re		8.30 399	11.06 402	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	99.58 226	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

uanet		0.02 402	0.03 405	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.27 433	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

WAC-MVS						97.16 292								95.47 352

FOURS1					99.91 1	99.93 1	99.87 8	99.56 74	99.10 35	99.81 47

test_one_0601					99.81 47	99.88 8		99.49 153	98.97 59	99.65 103	99.81 99	99.09 14

eth-test2					0.00 437

eth-test					0.00 437

test_241102_ONE					99.84 32	99.90 2		99.48 165	99.07 43	99.91 21	99.74 151	99.20 7	99.76 214

save fliter					99.76 69	99.59 77	99.14 311	99.40 231	99.00 51

test0726					99.85 26	99.89 4	99.62 95	99.50 143	99.10 35	99.86 37	99.82 85	98.94 32

GSMVS																99.52 179

test_part2					99.81 47	99.83 19				99.77 62

sam_mvs1												94.86 220				99.52 179

sam_mvs												94.72 232

MTGPA								99.47 186

test_post1							99.23 294				65.14 429	94.18 259	99.71 235	97.58 263

test_post											65.99 428	94.65 238	99.73 225

patchmatchnet-post											98.70 376	94.79 224	99.74 219

MTMP							99.54 148	98.88 356

gm-plane-assit					98.54 381	92.96 398			94.65 379		99.15 337		99.64 260	97.56 268

TEST9					99.67 118	99.65 64	99.05 330	99.41 225	96.22 340	98.95 262	99.49 259	98.77 54	99.91 118

test_8					99.67 118	99.61 74	99.03 335	99.41 225	96.28 334	98.93 265	99.48 265	98.76 55	99.91 118

agg_prior					99.67 118	99.62 72		99.40 231		98.87 275			99.91 118

test_prior4						99.56 83	98.99 346

test_prior				99.68 75	99.67 118	99.48 98		99.56 74					99.83 181			99.74 98

旧先验2							98.96 353		96.70 302	99.47 146			99.94 76	98.19 207

新几何2							99.01 343

无先验							98.99 346	99.51 123	96.89 292				99.93 94	97.53 271		99.72 110

原ACMM2							98.95 356

testdata2													99.95 65	96.67 324

segment_acmp												98.96 25

testdata1							98.85 367		98.32 124

plane_prior7					99.29 253	97.03 305

plane_prior6					99.27 258	96.98 309						92.71 298

plane_prior4											99.61 217

plane_prior3						97.00 307			98.69 88	99.11 231

plane_prior2							99.39 234		98.97 59

plane_prior1					99.26 261

n2								0.00 438

nn								0.00 438

door-mid								98.05 399

test11								99.35 258

door								97.92 400

HQP5-MVS						96.83 317

HQP-NCC					99.19 279		98.98 349		98.24 133	98.66 304

ACMP_Plane					99.19 279		98.98 349		98.24 133	98.66 304

BP-MVS														97.19 296

HQP4-MVS										98.66 304			99.64 260			98.64 323

HQP2-MVS												92.47 307

NP-MVS					99.23 269	96.92 313					99.40 287

MDTV_nov1_ep13_2view						95.18 369	99.35 251		96.84 295	99.58 125		95.19 208		97.82 240		99.46 203

Test By Simon												98.75 58

High-resolution multi-view benchmark