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 17	99.45 24	99.86 24	99.44 206	99.65 60	99.50 173	99.61 48	99.45 5	99.87 29	99.92 14	97.31 126	99.97 21	99.95 7	99.99 1	99.97 4

test_fmvsmconf_n		99.70 3	99.64 4	99.87 14	99.80 52	99.66 56	99.48 188	99.64 36	99.45 5	99.92 16	99.92 14	98.62 73	99.99 4	99.96 6	99.99 1	99.96 7

CHOSEN 280x420		99.12 101	99.13 78	99.08 186	99.66 124	97.89 255	98.43 393	99.71 13	98.88 63	99.62 111	99.76 139	96.63 151	99.70 237	99.46 49	99.99 1	99.66 129

patch_mono-2		99.26 74	99.62 5	98.16 306	99.81 46	94.59 374	99.52 157	99.64 36	99.33 13	99.73 70	99.90 27	99.00 22	99.99 4	99.69 21	99.98 4	99.89 19

dcpmvs_2		99.23 80	99.58 7	98.16 306	99.83 39	94.68 372	99.76 37	99.52 105	99.07 39	99.98 6	99.88 39	98.56 77	99.93 90	99.67 23	99.98 4	99.87 30

CANet		99.25 78	99.14 77	99.59 94	99.41 214	99.16 134	99.35 247	99.57 65	98.82 69	99.51 136	99.61 213	96.46 159	99.95 62	99.59 29	99.98 4	99.65 133

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 31	99.84 32	99.63 67	99.56 130	99.63 39	99.47 4	99.98 6	99.82 81	98.75 58	99.99 4	99.97 1	99.97 7	99.94 11

MM		99.40 54	99.28 60	99.74 64	99.67 114	99.31 115	99.52 157	98.87 354	99.55 1	99.74 68	99.80 108	96.47 158	99.98 13	99.97 1	99.97 7	99.94 11

MVS_0304		99.15 90	98.96 110	99.73 67	98.92 328	99.37 105	99.37 237	96.92 405	99.51 2	99.66 92	99.78 127	96.69 149	99.97 21	99.84 15	99.97 7	99.84 42

CHOSEN 1792x2688		99.19 82	99.10 81	99.45 132	99.89 8	98.52 216	99.39 230	99.94 1	98.73 81	99.11 227	99.89 32	95.50 194	99.94 72	99.50 41	99.97 7	99.89 19

DeepC-MVS	98.35 2	99.30 66	99.19 73	99.64 83	99.82 42	99.23 127	99.62 95	99.55 78	98.94 58	99.63 107	99.95 3	95.82 184	99.94 72	99.37 54	99.97 7	99.73 100
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 31	99.86 20	99.61 70	99.56 130	99.63 39	99.48 3	99.98 6	99.83 72	98.75 58	99.99 4	99.97 1	99.96 12	99.94 11

fmvsm_s_conf0.1_n		99.29 68	99.10 81	99.86 24	99.70 104	99.65 60	99.53 156	99.62 41	98.74 80	99.99 2	99.95 3	94.53 243	99.94 72	99.89 12	99.96 12	99.97 4

fmvsm_s_conf0.5_n		99.51 21	99.40 30	99.85 31	99.84 32	99.65 60	99.51 166	99.67 23	99.13 24	99.98 6	99.92 14	96.60 152	99.96 32	99.95 7	99.96 12	99.95 9

mamv4		99.33 62	99.42 25	99.07 187	99.67 114	97.73 262	99.42 215	99.60 54	98.15 142	99.94 15	99.91 20	98.42 88	99.94 72	99.72 19	99.96 12	99.54 168

CSCG		99.32 64	99.32 46	99.32 153	99.85 26	98.29 231	99.71 55	99.66 28	98.11 150	99.41 159	99.80 108	98.37 92	99.96 32	98.99 97	99.96 12	99.72 106

MVSMamba_PlusPlus		99.46 34	99.41 29	99.64 83	99.68 112	99.50 91	99.75 42	99.50 139	98.27 125	99.87 29	99.92 14	98.09 104	99.94 72	99.65 25	99.95 17	99.47 194

test_fmvsmconf0.01_n		99.22 81	99.03 92	99.79 52	98.42 379	99.48 94	99.55 144	99.51 119	99.39 10	99.78 54	99.93 9	94.80 221	99.95 62	99.93 10	99.95 17	99.94 11

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 55	99.84 32	99.44 99	99.58 117	99.69 18	99.43 7	99.98 6	99.91 20	98.62 73	100.00 1	99.97 1	99.95 17	99.90 16

CANet_DTU		98.97 129	98.87 124	99.25 169	99.33 236	98.42 228	99.08 318	99.30 284	99.16 20	99.43 152	99.75 142	95.27 202	99.97 21	98.56 169	99.95 17	99.36 217

EI-MVSNet-UG-set		99.58 12	99.57 8	99.64 83	99.78 56	99.14 139	99.60 102	99.45 202	99.01 44	99.90 19	99.83 72	98.98 24	99.93 90	99.59 29	99.95 17	99.86 32

EI-MVSNet-Vis-set		99.58 12	99.56 10	99.64 83	99.78 56	99.15 138	99.61 101	99.45 202	99.01 44	99.89 21	99.82 81	99.01 18	99.92 102	99.56 33	99.95 17	99.85 36

balanced_conf03		99.46 34	99.39 32	99.67 72	99.55 164	99.58 78	99.74 46	99.51 119	98.42 108	99.87 29	99.84 67	98.05 107	99.91 114	99.58 31	99.94 23	99.52 175

UGNet		98.87 136	98.69 145	99.40 139	99.22 268	98.72 195	99.44 204	99.68 20	99.24 17	99.18 218	99.42 275	92.74 291	99.96 32	99.34 60	99.94 23	99.53 174
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
test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 58	99.38 224	99.37 105	99.58 117	99.62 41	99.41 9	99.87 29	99.92 14	98.81 47	100.00 1	99.97 1	99.93 25	99.94 11

SD-MVS		99.41 51	99.52 12	99.05 191	99.74 83	99.68 51	99.46 197	99.52 105	99.11 30	99.88 24	99.91 20	99.43 1	97.70 400	98.72 140	99.93 25	99.77 85
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 74	99.06 87	99.85 31	99.52 173	99.62 68	99.54 148	99.62 41	98.69 84	99.99 2	99.96 1	94.47 245	99.94 72	99.88 13	99.92 27	99.98 2

fmvsm_s_conf0.5_n_a		99.56 16	99.47 20	99.85 31	99.83 39	99.64 66	99.52 157	99.65 33	99.10 31	99.98 6	99.92 14	97.35 125	99.96 32	99.94 9	99.92 27	99.95 9

test_vis1_n_1920		98.63 168	98.40 175	99.31 154	99.86 20	97.94 254	99.67 69	99.62 41	99.43 7	99.99 2	99.91 20	87.29 378	100.00 1	99.92 11	99.92 27	99.98 2

test_fmvs1		98.88 135	98.79 136	99.16 179	99.69 108	97.61 271	99.55 144	99.49 149	99.32 14	99.98 6	99.91 20	91.41 329	99.96 32	99.82 16	99.92 27	99.90 16

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 63	99.89 4	99.75 42	99.56 70	99.02 42	99.88 24	99.85 57	99.18 10	99.96 32	99.22 73	99.92 27	99.90 16
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
HPM-MVS_fast		99.51 21	99.40 30	99.85 31	99.91 1	99.79 33	99.76 37	99.56 70	97.72 199	99.76 64	99.75 142	99.13 12	99.92 102	99.07 89	99.92 27	99.85 36

3Dnovator	97.25 9	99.24 79	99.05 88	99.81 47	99.12 293	99.66 56	99.84 12	99.74 10	99.09 36	98.92 261	99.90 27	95.94 178	99.98 13	98.95 102	99.92 27	99.79 77

reproduce_model		99.63 7	99.54 11	99.90 4	99.78 56	99.88 8	99.56 130	99.55 78	99.15 21	99.90 19	99.90 27	99.00 22	99.97 21	99.11 83	99.91 34	99.86 32

test_cas_vis1_n_1920		99.16 88	99.01 100	99.61 91	99.81 46	98.86 181	99.65 81	99.64 36	99.39 10	99.97 13	99.94 6	93.20 281	99.98 13	99.55 34	99.91 34	99.99 1

MP-MVS-pluss		99.37 58	99.20 72	99.88 8	99.90 4	99.87 15	99.30 258	99.52 105	97.18 258	99.60 117	99.79 120	98.79 50	99.95 62	98.83 128	99.91 34	99.83 52
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.47 32	99.34 42	99.88 8	99.87 15	99.86 16	99.47 194	99.48 161	98.05 164	99.76 64	99.86 52	98.82 46	99.93 90	98.82 132	99.91 34	99.84 42

HPM-MVS		99.42 47	99.28 60	99.83 43	99.90 4	99.72 45	99.81 20	99.54 87	97.59 213	99.68 83	99.63 204	98.91 37	99.94 72	98.58 163	99.91 34	99.84 42
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
114514_t		98.93 131	98.67 147	99.72 69	99.85 26	99.53 86	99.62 95	99.59 58	92.65 393	99.71 77	99.78 127	98.06 106	99.90 126	98.84 125	99.91 34	99.74 95

CP-MVS		99.45 38	99.32 46	99.85 31	99.83 39	99.75 42	99.69 60	99.52 105	98.07 158	99.53 132	99.63 204	98.93 36	99.97 21	98.74 137	99.91 34	99.83 52

PHI-MVS		99.30 66	99.17 75	99.70 70	99.56 160	99.52 89	99.58 117	99.80 8	97.12 264	99.62 111	99.73 153	98.58 75	99.90 126	98.61 157	99.91 34	99.68 123

DeepPCF-MVS	98.18 3	98.81 150	99.37 36	97.12 358	99.60 150	91.75 398	98.61 383	99.44 210	99.35 12	99.83 41	99.85 57	98.70 66	99.81 189	99.02 95	99.91 34	99.81 64

reproduce-ours		99.61 8	99.52 12	99.90 4	99.76 66	99.88 8	99.52 157	99.54 87	99.13 24	99.89 21	99.89 32	98.96 25	99.96 32	99.04 91	99.90 43	99.85 36

our_new_method		99.61 8	99.52 12	99.90 4	99.76 66	99.88 8	99.52 157	99.54 87	99.13 24	99.89 21	99.89 32	98.96 25	99.96 32	99.04 91	99.90 43	99.85 36

ZNCC-MVS		99.47 32	99.33 44	99.87 14	99.87 15	99.81 28	99.64 84	99.67 23	98.08 157	99.55 129	99.64 198	98.91 37	99.96 32	98.72 140	99.90 43	99.82 57

test_0728_THIRD									98.99 49	99.81 43	99.80 108	99.09 14	99.96 32	98.85 122	99.90 43	99.88 25

MTAPA		99.52 20	99.39 32	99.89 7	99.90 4	99.86 16	99.66 75	99.47 182	98.79 74	99.68 83	99.81 95	98.43 86	99.97 21	98.88 112	99.90 43	99.83 52

UA-Net		99.42 47	99.29 58	99.80 49	99.62 141	99.55 81	99.50 173	99.70 15	98.79 74	99.77 58	99.96 1	97.45 120	99.96 32	98.92 108	99.90 43	99.89 19

jason		99.13 95	99.03 92	99.45 132	99.46 199	98.87 178	99.12 309	99.26 294	98.03 167	99.79 49	99.65 192	97.02 138	99.85 157	99.02 95	99.90 43	99.65 133
jason: jason.
SteuartSystems-ACMMP		99.54 18	99.42 25	99.87 14	99.82 42	99.81 28	99.59 109	99.51 119	98.62 89	99.79 49	99.83 72	99.28 4	99.97 21	98.48 176	99.90 43	99.84 42
Skip Steuart: Steuart Systems R&D Blog.
DP-MVS		99.16 88	98.95 112	99.78 55	99.77 63	99.53 86	99.41 218	99.50 139	97.03 276	99.04 243	99.88 39	97.39 121	99.92 102	98.66 149	99.90 43	99.87 30

MSDG		98.98 127	98.80 133	99.53 112	99.76 66	99.19 129	98.75 371	99.55 78	97.25 252	99.47 142	99.77 135	97.82 112	99.87 148	96.93 307	99.90 43	99.54 168

COLMAP_ROB	97.56 6	98.86 139	98.75 139	99.17 178	99.88 11	98.53 212	99.34 250	99.59 58	97.55 219	98.70 295	99.89 32	95.83 183	99.90 126	98.10 208	99.90 43	99.08 243
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 42	99.30 54	99.85 31	99.73 90	99.83 19	99.56 130	99.47 182	97.45 232	99.78 54	99.82 81	99.18 10	99.91 114	98.79 133	99.89 54	99.81 64
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 42	99.30 54	99.86 24	99.88 11	99.79 33	99.69 60	99.48 161	98.12 148	99.50 137	99.75 142	98.78 51	99.97 21	98.57 166	99.89 54	99.83 52

MVS_111021_LR		99.41 51	99.33 44	99.65 77	99.77 63	99.51 90	98.94 352	99.85 6	98.82 69	99.65 99	99.74 147	98.51 81	99.80 196	98.83 128	99.89 54	99.64 140

TSAR-MVS + MP.		99.58 12	99.50 16	99.81 47	99.91 1	99.66 56	99.63 90	99.39 230	98.91 62	99.78 54	99.85 57	99.36 2	99.94 72	98.84 125	99.88 57	99.82 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
QAPM		98.67 164	98.30 182	99.80 49	99.20 271	99.67 54	99.77 34	99.72 11	94.74 371	98.73 287	99.90 27	95.78 185	99.98 13	96.96 304	99.88 57	99.76 90

MVS_111021_HR		99.41 51	99.32 46	99.66 73	99.72 94	99.47 96	98.95 350	99.85 6	98.82 69	99.54 130	99.73 153	98.51 81	99.74 215	98.91 109	99.88 57	99.77 85

DPE-MVS		99.46 34	99.32 46	99.91 2	99.78 56	99.88 8	99.36 242	99.51 119	98.73 81	99.88 24	99.84 67	98.72 64	99.96 32	98.16 206	99.87 60	99.88 25
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
HFP-MVS		99.49 25	99.37 36	99.86 24	99.87 15	99.80 30	99.66 75	99.67 23	98.15 142	99.68 83	99.69 172	99.06 16	99.96 32	98.69 145	99.87 60	99.84 42

region2R		99.48 29	99.35 40	99.87 14	99.88 11	99.80 30	99.65 81	99.66 28	98.13 147	99.66 92	99.68 179	98.96 25	99.96 32	98.62 154	99.87 60	99.84 42

ACMMPR		99.49 25	99.36 38	99.86 24	99.87 15	99.79 33	99.66 75	99.67 23	98.15 142	99.67 87	99.69 172	98.95 30	99.96 32	98.69 145	99.87 60	99.84 42

MP-MVS		99.33 62	99.15 76	99.87 14	99.88 11	99.82 25	99.66 75	99.46 191	98.09 153	99.48 141	99.74 147	98.29 95	99.96 32	97.93 224	99.87 60	99.82 57
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		99.45 38	99.31 52	99.86 24	99.87 15	99.78 39	99.58 117	99.65 33	97.84 185	99.71 77	99.80 108	99.12 13	99.97 21	98.33 192	99.87 60	99.83 52

DeepC-MVS_fast	98.69 1	99.49 25	99.39 32	99.77 58	99.63 135	99.59 73	99.36 242	99.46 191	99.07 39	99.79 49	99.82 81	98.85 42	99.92 102	98.68 147	99.87 60	99.82 57
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	97.74 272	97.34 293	98.94 206	99.70 104	97.53 272	99.25 284	99.51 119	91.90 395	99.30 185	99.63 204	98.78 51	99.64 256	88.09 404	99.87 60	99.65 133
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DVP-MVS		99.57 15	99.47 20	99.88 8	99.85 26	99.89 4	99.57 124	99.37 246	99.10 31	99.81 43	99.80 108	98.94 32	99.96 32	98.93 106	99.86 68	99.81 64
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 2	99.84 32	99.89 4	99.57 124	99.51 119					99.96 32	98.93 106	99.86 68	99.88 25

GST-MVS		99.40 54	99.24 68	99.85 31	99.86 20	99.79 33	99.60 102	99.67 23	97.97 170	99.63 107	99.68 179	98.52 80	99.95 62	98.38 185	99.86 68	99.81 64

XVS		99.53 19	99.42 25	99.87 14	99.85 26	99.83 19	99.69 60	99.68 20	98.98 52	99.37 170	99.74 147	98.81 47	99.94 72	98.79 133	99.86 68	99.84 42

X-MVStestdata		96.55 331	95.45 350	99.87 14	99.85 26	99.83 19	99.69 60	99.68 20	98.98 52	99.37 170	64.01 424	98.81 47	99.94 72	98.79 133	99.86 68	99.84 42

APD-MVS		99.27 72	99.08 85	99.84 42	99.75 76	99.79 33	99.50 173	99.50 139	97.16 260	99.77 58	99.82 81	98.78 51	99.94 72	97.56 263	99.86 68	99.80 73
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
3Dnovator+	97.12 13	99.18 84	98.97 106	99.82 44	99.17 285	99.68 51	99.81 20	99.51 119	99.20 18	98.72 288	99.89 32	95.68 189	99.97 21	98.86 120	99.86 68	99.81 64

SED-MVS		99.61 8	99.52 12	99.88 8	99.84 32	99.90 2	99.60 102	99.48 161	99.08 37	99.91 17	99.81 95	99.20 7	99.96 32	98.91 109	99.85 75	99.79 77

IU-MVS					99.84 32	99.88 8		99.32 276	98.30 122	99.84 35				98.86 120	99.85 75	99.89 19

SPE-MVS-test		99.49 25	99.48 18	99.54 104	99.78 56	99.30 117	99.89 2	99.58 62	98.56 94	99.73 70	99.69 172	98.55 78	99.82 184	99.69 21	99.85 75	99.48 188

MVSFormer		99.17 86	99.12 79	99.29 162	99.51 176	98.94 171	99.88 4	99.46 191	97.55 219	99.80 47	99.65 192	97.39 121	99.28 311	99.03 93	99.85 75	99.65 133

lupinMVS		99.13 95	99.01 100	99.46 131	99.51 176	98.94 171	99.05 324	99.16 311	97.86 180	99.80 47	99.56 230	97.39 121	99.86 151	98.94 103	99.85 75	99.58 160

PVSNet_Blended		99.08 112	98.97 106	99.42 137	99.76 66	98.79 190	98.78 368	99.91 3	96.74 293	99.67 87	99.49 255	97.53 118	99.88 143	98.98 98	99.85 75	99.60 152

MVS-HIRNet		95.75 348	95.16 353	97.51 348	99.30 245	93.69 386	98.88 358	95.78 413	85.09 410	98.78 283	92.65 413	91.29 332	99.37 294	94.85 360	99.85 75	99.46 199

PCF-MVS	97.08 14	97.66 287	97.06 312	99.47 129	99.61 145	99.09 144	98.04 407	99.25 296	91.24 398	98.51 317	99.70 162	94.55 241	99.91 114	92.76 386	99.85 75	99.42 206
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_fmvs1_n		98.41 179	98.14 191	99.21 174	99.82 42	97.71 267	99.74 46	99.49 149	99.32 14	99.99 2	99.95 3	85.32 389	99.97 21	99.82 16	99.84 83	99.96 7

MSC_two_6792asdad				99.87 14	99.51 176	99.76 40		99.33 266					99.96 32	98.87 115	99.84 83	99.89 19

No_MVS				99.87 14	99.51 176	99.76 40		99.33 266					99.96 32	98.87 115	99.84 83	99.89 19

test_241102_TWO								99.48 161	99.08 37	99.88 24	99.81 95	98.94 32	99.96 32	98.91 109	99.84 83	99.88 25

SF-MVS		99.38 57	99.24 68	99.79 52	99.79 54	99.68 51	99.57 124	99.54 87	97.82 190	99.71 77	99.80 108	98.95 30	99.93 90	98.19 202	99.84 83	99.74 95

MSLP-MVS++		99.46 34	99.47 20	99.44 136	99.60 150	99.16 134	99.41 218	99.71 13	98.98 52	99.45 145	99.78 127	99.19 9	99.54 271	99.28 67	99.84 83	99.63 145

DELS-MVS		99.48 29	99.42 25	99.65 77	99.72 94	99.40 104	99.05 324	99.66 28	99.14 23	99.57 124	99.80 108	98.46 84	99.94 72	99.57 32	99.84 83	99.60 152
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		99.11 106	98.90 118	99.74 64	99.80 52	99.46 97	99.59 109	99.49 149	97.03 276	99.63 107	99.69 172	97.27 129	99.96 32	97.82 235	99.84 83	99.81 64

LS3D		99.27 72	99.12 79	99.74 64	99.18 277	99.75 42	99.56 130	99.57 65	98.45 104	99.49 140	99.85 57	97.77 114	99.94 72	98.33 192	99.84 83	99.52 175

AllTest		98.87 136	98.72 141	99.31 154	99.86 20	98.48 222	99.56 130	99.61 48	97.85 183	99.36 173	99.85 57	95.95 176	99.85 157	96.66 320	99.83 92	99.59 156

TestCases				99.31 154	99.86 20	98.48 222		99.61 48	97.85 183	99.36 173	99.85 57	95.95 176	99.85 157	96.66 320	99.83 92	99.59 156

CDPH-MVS		99.13 95	98.91 117	99.80 49	99.75 76	99.71 47	99.15 303	99.41 221	96.60 308	99.60 117	99.55 233	98.83 45	99.90 126	97.48 270	99.83 92	99.78 83

ACMMP		99.45 38	99.32 46	99.82 44	99.89 8	99.67 54	99.62 95	99.69 18	98.12 148	99.63 107	99.84 67	98.73 63	99.96 32	98.55 172	99.83 92	99.81 64
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 81		99.72 94		99.40 226	99.51 119	97.53 223	99.64 104	99.78 127	98.84 44	99.91 114	97.63 254	99.82 96

PVSNet_Blended_VisFu		99.36 59	99.28 60	99.61 91	99.86 20	99.07 149	99.47 194	99.93 2	97.66 208	99.71 77	99.86 52	97.73 115	99.96 32	99.47 48	99.82 96	99.79 77

EC-MVSNet		99.44 42	99.39 32	99.58 97	99.56 160	99.49 92	99.88 4	99.58 62	98.38 111	99.73 70	99.69 172	98.20 99	99.70 237	99.64 27	99.82 96	99.54 168

SR-MVS-dyc-post		99.45 38	99.31 52	99.85 31	99.76 66	99.82 25	99.63 90	99.52 105	98.38 111	99.76 64	99.82 81	98.53 79	99.95 62	98.61 157	99.81 99	99.77 85

RE-MVS-def			99.34 42		99.76 66	99.82 25	99.63 90	99.52 105	98.38 111	99.76 64	99.82 81	98.75 58		98.61 157	99.81 99	99.77 85

APD-MVS_3200maxsize		99.48 29	99.35 40	99.85 31	99.76 66	99.83 19	99.63 90	99.54 87	98.36 115	99.79 49	99.82 81	98.86 41	99.95 62	98.62 154	99.81 99	99.78 83

OMC-MVS		99.08 112	99.04 90	99.20 175	99.67 114	98.22 235	99.28 268	99.52 105	98.07 158	99.66 92	99.81 95	97.79 113	99.78 204	97.79 237	99.81 99	99.60 152

DVP-MVS++		99.59 11	99.50 16	99.88 8	99.51 176	99.88 8	99.87 8	99.51 119	98.99 49	99.88 24	99.81 95	99.27 5	99.96 32	98.85 122	99.80 103	99.81 64

PC_three_1452									98.18 140	99.84 35	99.70 162	99.31 3	98.52 383	98.30 196	99.80 103	99.81 64

OPU-MVS				99.64 83	99.56 160	99.72 45	99.60 102				99.70 162	99.27 5	99.42 287	98.24 199	99.80 103	99.79 77

MS-PatchMatch		97.24 316	97.32 296	96.99 360	98.45 378	93.51 389	98.82 364	99.32 276	97.41 239	98.13 340	99.30 312	88.99 357	99.56 268	95.68 343	99.80 103	97.90 391

HPM-MVS++		99.39 56	99.23 70	99.87 14	99.75 76	99.84 18	99.43 208	99.51 119	98.68 86	99.27 194	99.53 242	98.64 72	99.96 32	98.44 182	99.80 103	99.79 77

CNVR-MVS		99.42 47	99.30 54	99.78 55	99.62 141	99.71 47	99.26 282	99.52 105	98.82 69	99.39 166	99.71 158	98.96 25	99.85 157	98.59 162	99.80 103	99.77 85

MG-MVS		99.13 95	99.02 96	99.45 132	99.57 156	98.63 203	99.07 319	99.34 259	98.99 49	99.61 114	99.82 81	97.98 109	99.87 148	97.00 300	99.80 103	99.85 36

BP-MVS1		99.12 101	98.94 114	99.65 77	99.51 176	99.30 117	99.67 69	98.92 342	98.48 101	99.84 35	99.69 172	94.96 211	99.92 102	99.62 28	99.79 110	99.71 115

CS-MVS		99.50 23	99.48 18	99.54 104	99.76 66	99.42 101	99.90 1	99.55 78	98.56 94	99.78 54	99.70 162	98.65 71	99.79 199	99.65 25	99.78 111	99.41 209

MVP-Stereo		97.81 260	97.75 240	97.99 320	97.53 392	96.60 325	98.96 347	98.85 356	97.22 256	97.23 366	99.36 295	95.28 201	99.46 276	95.51 346	99.78 111	97.92 390
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
API-MVS		99.04 118	99.03 92	99.06 189	99.40 219	99.31 115	99.55 144	99.56 70	98.54 96	99.33 180	99.39 287	98.76 55	99.78 204	96.98 302	99.78 111	98.07 377

SR-MVS		99.43 45	99.29 58	99.86 24	99.75 76	99.83 19	99.59 109	99.62 41	98.21 135	99.73 70	99.79 120	98.68 67	99.96 32	98.44 182	99.77 114	99.79 77

MSP-MVS		99.42 47	99.27 63	99.88 8	99.89 8	99.80 30	99.67 69	99.50 139	98.70 83	99.77 58	99.49 255	98.21 98	99.95 62	98.46 180	99.77 114	99.88 25
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		99.01 125	98.80 133	99.66 73	99.56 160	99.54 83	99.18 298	99.70 15	98.18 140	99.35 176	99.63 204	96.32 164	99.90 126	97.48 270	99.77 114	99.55 166

test_vis1_n		97.92 239	97.44 278	99.34 147	99.53 168	98.08 242	99.74 46	99.49 149	99.15 21	100.00 1	99.94 6	79.51 408	99.98 13	99.88 13	99.76 117	99.97 4

OpenMVS	96.50 16	98.47 173	98.12 194	99.52 118	99.04 311	99.53 86	99.82 16	99.72 11	94.56 374	98.08 341	99.88 39	94.73 229	99.98 13	97.47 272	99.76 117	99.06 249

ZD-MVS					99.71 99	99.79 33		99.61 48	96.84 289	99.56 125	99.54 238	98.58 75	99.96 32	96.93 307	99.75 119

MCST-MVS		99.43 45	99.30 54	99.82 44	99.79 54	99.74 44	99.29 263	99.40 227	98.79 74	99.52 134	99.62 209	98.91 37	99.90 126	98.64 151	99.75 119	99.82 57

CNLPA		99.14 93	98.99 102	99.59 94	99.58 154	99.41 103	99.16 300	99.44 210	98.45 104	99.19 214	99.49 255	98.08 105	99.89 138	97.73 246	99.75 119	99.48 188

test_prior2							98.96 347		98.34 117	99.01 246	99.52 245	98.68 67		97.96 222	99.74 122

test12				99.75 61	99.64 132	99.61 70		99.29 288		99.21 208		98.38 91	99.89 138		99.74 122	99.74 95

agg_prior2														97.21 287	99.73 124	99.75 91

test9_res														97.49 269	99.72 125	99.75 91

train_agg		99.02 121	98.77 137	99.77 58	99.67 114	99.65 60	99.05 324	99.41 221	96.28 328	98.95 257	99.49 255	98.76 55	99.91 114	97.63 254	99.72 125	99.75 91

EPNet		98.86 139	98.71 143	99.30 159	97.20 399	98.18 236	99.62 95	98.91 347	99.28 16	98.63 307	99.81 95	95.96 175	99.99 4	99.24 72	99.72 125	99.73 100
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DP-MVS Recon		99.12 101	98.95 112	99.65 77	99.74 83	99.70 49	99.27 273	99.57 65	96.40 324	99.42 155	99.68 179	98.75 58	99.80 196	97.98 221	99.72 125	99.44 204

PVSNet	96.02 17	98.85 146	98.84 130	98.89 219	99.73 90	97.28 280	98.32 399	99.60 54	97.86 180	99.50 137	99.57 227	96.75 147	99.86 151	98.56 169	99.70 129	99.54 168

原ACMM1				99.65 77	99.73 90	99.33 110		99.47 182	97.46 229	99.12 225	99.66 190	98.67 69	99.91 114	97.70 251	99.69 130	99.71 115

test222					99.75 76	99.49 92	98.91 356	99.49 149	96.42 322	99.34 179	99.65 192	98.28 96			99.69 130	99.72 106

F-COLMAP		99.19 82	99.04 90	99.64 83	99.78 56	99.27 122	99.42 215	99.54 87	97.29 249	99.41 159	99.59 218	98.42 88	99.93 90	98.19 202	99.69 130	99.73 100

DPM-MVS		98.95 130	98.71 143	99.66 73	99.63 135	99.55 81	98.64 382	99.10 317	97.93 173	99.42 155	99.55 233	98.67 69	99.80 196	95.80 339	99.68 133	99.61 149

旧先验1					99.74 83	99.59 73		99.54 87			99.69 172	98.47 83			99.68 133	99.73 100

PS-MVSNAJ		99.32 64	99.32 46	99.30 159	99.57 156	98.94 171	98.97 346	99.46 191	98.92 61	99.71 77	99.24 323	99.01 18	99.98 13	99.35 55	99.66 135	98.97 258

新几何1				99.75 61	99.75 76	99.59 73		99.54 87	96.76 292	99.29 188	99.64 198	98.43 86	99.94 72	96.92 309	99.66 135	99.72 106

EPNet_dtu		98.03 221	97.96 213	98.23 302	98.27 381	95.54 353	99.23 288	98.75 366	99.02 42	97.82 353	99.71 158	96.11 170	99.48 273	93.04 381	99.65 137	99.69 119
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				99.54 104	99.75 76	98.95 168		99.51 119	97.07 270	99.43 152	99.70 162	98.87 40	99.94 72	97.76 242	99.64 138	99.72 106

PatchMatch-RL		98.84 149	98.62 157	99.52 118	99.71 99	99.28 120	99.06 322	99.77 9	97.74 198	99.50 137	99.53 242	95.41 196	99.84 164	97.17 294	99.64 138	99.44 204

NCCC		99.34 61	99.19 73	99.79 52	99.61 145	99.65 60	99.30 258	99.48 161	98.86 64	99.21 208	99.63 204	98.72 64	99.90 126	98.25 198	99.63 140	99.80 73

EIA-MVS		99.18 84	99.09 84	99.45 132	99.49 189	99.18 131	99.67 69	99.53 100	97.66 208	99.40 164	99.44 271	98.10 103	99.81 189	98.94 103	99.62 141	99.35 218

mvsmamba		99.06 115	98.96 110	99.36 145	99.47 197	98.64 202	99.70 56	99.05 326	97.61 212	99.65 99	99.83 72	96.54 155	99.92 102	99.19 75	99.62 141	99.51 182

PLC	97.94 4	99.02 121	98.85 128	99.53 112	99.66 124	99.01 156	99.24 286	99.52 105	96.85 288	99.27 194	99.48 261	98.25 97	99.91 114	97.76 242	99.62 141	99.65 133
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ETV-MVS		99.26 74	99.21 71	99.40 139	99.46 199	99.30 117	99.56 130	99.52 105	98.52 98	99.44 150	99.27 319	98.41 90	99.86 151	99.10 86	99.59 144	99.04 250

mvsany_test1		99.50 23	99.46 23	99.62 90	99.61 145	99.09 144	98.94 352	99.48 161	99.10 31	99.96 14	99.91 20	98.85 42	99.96 32	99.72 19	99.58 145	99.82 57

thisisatest0530		98.35 186	98.03 206	99.31 154	99.63 135	98.56 209	99.54 148	96.75 408	97.53 223	99.73 70	99.65 192	91.25 333	99.89 138	98.62 154	99.56 146	99.48 188

tttt0517		98.42 177	98.14 191	99.28 166	99.66 124	98.38 229	99.74 46	96.85 406	97.68 205	99.79 49	99.74 147	91.39 330	99.89 138	98.83 128	99.56 146	99.57 163

BH-RMVSNet		98.41 179	98.08 200	99.40 139	99.41 214	98.83 186	99.30 258	98.77 365	97.70 203	98.94 259	99.65 192	92.91 287	99.74 215	96.52 324	99.55 148	99.64 140

MAR-MVS		98.86 139	98.63 152	99.54 104	99.37 227	99.66 56	99.45 198	99.54 87	96.61 305	99.01 246	99.40 283	97.09 133	99.86 151	97.68 253	99.53 149	99.10 238
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		98.14 204	97.79 230	99.19 176	99.50 187	98.50 219	98.61 383	96.82 407	96.95 282	99.54 130	99.43 273	91.66 325	99.86 151	98.08 213	99.51 150	99.22 232

GDP-MVS		99.08 112	98.89 121	99.64 83	99.53 168	99.34 109	99.64 84	99.48 161	98.32 120	99.77 58	99.66 190	95.14 208	99.93 90	98.97 101	99.50 151	99.64 140

FA-MVS(test-final)		98.75 157	98.53 168	99.41 138	99.55 164	99.05 152	99.80 25	99.01 331	96.59 310	99.58 121	99.59 218	95.39 197	99.90 126	97.78 238	99.49 152	99.28 226

FE-MVS		98.48 172	98.17 187	99.40 139	99.54 167	98.96 165	99.68 66	98.81 361	95.54 355	99.62 111	99.70 162	93.82 269	99.93 90	97.35 281	99.46 153	99.32 223

Fast-Effi-MVS+-dtu		98.77 156	98.83 132	98.60 254	99.41 214	96.99 303	99.52 157	99.49 149	98.11 150	99.24 200	99.34 302	96.96 141	99.79 199	97.95 223	99.45 154	99.02 253

PAPM_NR		99.04 118	98.84 130	99.66 73	99.74 83	99.44 99	99.39 230	99.38 238	97.70 203	99.28 189	99.28 316	98.34 93	99.85 157	96.96 304	99.45 154	99.69 119

TSAR-MVS + GP.		99.36 59	99.36 38	99.36 145	99.67 114	98.61 206	99.07 319	99.33 266	99.00 47	99.82 42	99.81 95	99.06 16	99.84 164	99.09 87	99.42 156	99.65 133

Vis-MVSNet		99.12 101	98.97 106	99.56 101	99.78 56	99.10 143	99.68 66	99.66 28	98.49 100	99.86 33	99.87 48	94.77 226	99.84 164	99.19 75	99.41 157	99.74 95
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test2506		96.81 327	96.65 323	97.29 354	99.74 83	92.21 397	99.60 102	85.06 428	99.13 24	99.77 58	99.93 9	87.82 376	99.85 157	99.38 53	99.38 158	99.80 73

test1111		98.04 219	98.11 195	97.83 333	99.74 83	93.82 382	99.58 117	95.40 415	99.12 29	99.65 99	99.93 9	90.73 338	99.84 164	99.43 51	99.38 158	99.82 57

ECVR-MVS		98.04 219	98.05 204	98.00 319	99.74 83	94.37 377	99.59 109	94.98 416	99.13 24	99.66 92	99.93 9	90.67 339	99.84 164	99.40 52	99.38 158	99.80 73

Effi-MVS+-dtu		98.78 154	98.89 121	98.47 275	99.33 236	96.91 309	99.57 124	99.30 284	98.47 102	99.41 159	98.99 350	96.78 145	99.74 215	98.73 139	99.38 158	98.74 280

test-LLR		98.06 213	97.90 220	98.55 264	98.79 343	97.10 290	98.67 377	97.75 398	97.34 244	98.61 310	98.85 362	94.45 246	99.45 277	97.25 285	99.38 158	99.10 238

TESTMET0.1,1		97.55 294	97.27 304	98.40 286	98.93 326	96.53 326	98.67 377	97.61 401	96.96 280	98.64 305	99.28 316	88.63 366	99.45 277	97.30 283	99.38 158	99.21 233

test-mter		97.49 304	97.13 309	98.55 264	98.79 343	97.10 290	98.67 377	97.75 398	96.65 300	98.61 310	98.85 362	88.23 370	99.45 277	97.25 285	99.38 158	99.10 238

PAPR		98.63 168	98.34 178	99.51 120	99.40 219	99.03 153	98.80 366	99.36 247	96.33 325	99.00 250	99.12 338	98.46 84	99.84 164	95.23 354	99.37 165	99.66 129

xiu_mvs_v1_base_debu		99.29 68	99.27 63	99.34 147	99.63 135	98.97 161	99.12 309	99.51 119	98.86 64	99.84 35	99.47 264	98.18 100	99.99 4	99.50 41	99.31 166	99.08 243

xiu_mvs_v1_base		99.29 68	99.27 63	99.34 147	99.63 135	98.97 161	99.12 309	99.51 119	98.86 64	99.84 35	99.47 264	98.18 100	99.99 4	99.50 41	99.31 166	99.08 243

xiu_mvs_v1_base_debi		99.29 68	99.27 63	99.34 147	99.63 135	98.97 161	99.12 309	99.51 119	98.86 64	99.84 35	99.47 264	98.18 100	99.99 4	99.50 41	99.31 166	99.08 243

RRT-MVS		98.91 133	98.75 139	99.39 143	99.46 199	98.61 206	99.76 37	99.50 139	98.06 162	99.81 43	99.88 39	93.91 266	99.94 72	99.11 83	99.27 169	99.61 149

1314		98.68 163	98.54 167	99.11 185	98.89 331	98.65 200	99.27 273	99.49 149	96.89 286	97.99 346	99.56 230	97.72 116	99.83 177	97.74 245	99.27 169	98.84 266

xiu_mvs_v2_base		99.26 74	99.25 67	99.29 162	99.53 168	98.91 175	99.02 332	99.45 202	98.80 73	99.71 77	99.26 321	98.94 32	99.98 13	99.34 60	99.23 171	98.98 257

PatchmatchNet		98.31 188	98.36 176	98.19 304	99.16 287	95.32 360	99.27 273	98.92 342	97.37 242	99.37 170	99.58 222	94.90 216	99.70 237	97.43 276	99.21 172	99.54 168
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		98.19 198	98.16 188	98.27 301	99.30 245	95.55 351	99.07 319	98.97 335	97.57 216	99.43 152	99.57 227	92.72 292	99.74 215	97.58 258	99.20 173	99.52 175

sss		99.17 86	99.05 88	99.53 112	99.62 141	98.97 161	99.36 242	99.62 41	97.83 186	99.67 87	99.65 192	97.37 124	99.95 62	99.19 75	99.19 174	99.68 123

MVS		97.28 312	96.55 325	99.48 126	98.78 346	98.95 168	99.27 273	99.39 230	83.53 411	98.08 341	99.54 238	96.97 140	99.87 148	94.23 368	99.16 175	99.63 145

casdiffmvs		99.13 95	98.98 105	99.56 101	99.65 130	99.16 134	99.56 130	99.50 139	98.33 119	99.41 159	99.86 52	95.92 179	99.83 177	99.45 50	99.16 175	99.70 117
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		98.42 177	98.36 176	98.59 255	99.49 189	96.70 317	99.27 273	99.13 315	97.24 254	98.80 280	99.38 289	95.75 186	99.74 215	97.07 298	99.16 175	99.33 222

casdiffmvs_mvg		99.15 90	99.02 96	99.55 103	99.66 124	99.09 144	99.64 84	99.56 70	98.26 127	99.45 145	99.87 48	96.03 173	99.81 189	99.54 35	99.15 178	99.73 100
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 90	99.02 96	99.53 112	99.66 124	99.14 139	99.72 52	99.48 161	98.35 116	99.42 155	99.84 67	96.07 171	99.79 199	99.51 40	99.14 179	99.67 126

IS-MVSNet		99.05 117	98.87 124	99.57 99	99.73 90	99.32 111	99.75 42	99.20 306	98.02 168	99.56 125	99.86 52	96.54 155	99.67 245	98.09 209	99.13 180	99.73 100

Patchmatch-test		97.93 236	97.65 249	98.77 242	99.18 277	97.07 294	99.03 329	99.14 314	96.16 339	98.74 286	99.57 227	94.56 239	99.72 225	93.36 377	99.11 181	99.52 175

diffmvs		99.14 93	99.02 96	99.51 120	99.61 145	98.96 165	99.28 268	99.49 149	98.46 103	99.72 75	99.71 158	96.50 157	99.88 143	99.31 63	99.11 181	99.67 126
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)		98.87 136	98.72 141	99.31 154	99.71 99	98.88 177	99.80 25	99.44 210	97.91 175	99.36 173	99.78 127	95.49 195	99.43 286	97.91 225	99.11 181	99.62 147

RPSCF		98.22 194	98.62 157	96.99 360	99.82 42	91.58 399	99.72 52	99.44 210	96.61 305	99.66 92	99.89 32	95.92 179	99.82 184	97.46 273	99.10 184	99.57 163

gg-mvs-nofinetune		96.17 340	95.32 352	98.73 244	98.79 343	98.14 239	99.38 235	94.09 419	91.07 400	98.07 344	91.04 417	89.62 353	99.35 301	96.75 314	99.09 185	98.68 298

EPMVS		97.82 258	97.65 249	98.35 290	98.88 332	95.98 343	99.49 184	94.71 418	97.57 216	99.26 198	99.48 261	92.46 306	99.71 231	97.87 229	99.08 186	99.35 218

MVS_Test		99.10 110	98.97 106	99.48 126	99.49 189	99.14 139	99.67 69	99.34 259	97.31 247	99.58 121	99.76 139	97.65 117	99.82 184	98.87 115	99.07 187	99.46 199

ADS-MVSNet2		98.02 223	98.07 203	97.87 329	99.33 236	95.19 363	99.23 288	99.08 320	96.24 332	99.10 230	99.67 185	94.11 257	98.93 369	96.81 312	99.05 188	99.48 188

ADS-MVSNet		98.20 197	98.08 200	98.56 262	99.33 236	96.48 328	99.23 288	99.15 312	96.24 332	99.10 230	99.67 185	94.11 257	99.71 231	96.81 312	99.05 188	99.48 188

GeoE		98.85 146	98.62 157	99.53 112	99.61 145	99.08 147	99.80 25	99.51 119	97.10 268	99.31 182	99.78 127	95.23 206	99.77 206	98.21 200	99.03 190	99.75 91

baseline2		97.87 246	97.55 258	98.82 234	99.18 277	98.02 245	99.41 218	96.58 412	96.97 279	96.51 378	99.17 330	93.43 275	99.57 267	97.71 249	99.03 190	98.86 264

HyFIR lowres test		99.11 106	98.92 115	99.65 77	99.90 4	99.37 105	99.02 332	99.91 3	97.67 207	99.59 120	99.75 142	95.90 181	99.73 221	99.53 37	99.02 192	99.86 32

LCM-MVSNet-Re		97.83 255	98.15 190	96.87 366	99.30 245	92.25 396	99.59 109	98.26 388	97.43 236	96.20 382	99.13 335	96.27 166	98.73 379	98.17 205	98.99 193	99.64 140

mvs_anonymous		99.03 120	98.99 102	99.16 179	99.38 224	98.52 216	99.51 166	99.38 238	97.79 191	99.38 168	99.81 95	97.30 127	99.45 277	99.35 55	98.99 193	99.51 182

EPP-MVSNet		99.13 95	98.99 102	99.53 112	99.65 130	99.06 150	99.81 20	99.33 266	97.43 236	99.60 117	99.88 39	97.14 131	99.84 164	99.13 81	98.94 195	99.69 119

MIMVSNet		97.73 274	97.45 273	98.57 259	99.45 205	97.50 273	99.02 332	98.98 334	96.11 344	99.41 159	99.14 334	90.28 341	98.74 378	95.74 340	98.93 196	99.47 194

TAMVS		99.12 101	99.08 85	99.24 171	99.46 199	98.55 210	99.51 166	99.46 191	98.09 153	99.45 145	99.82 81	98.34 93	99.51 272	98.70 142	98.93 196	99.67 126

CDS-MVSNet		99.09 111	99.03 92	99.25 169	99.42 209	98.73 194	99.45 198	99.46 191	98.11 150	99.46 144	99.77 135	98.01 108	99.37 294	98.70 142	98.92 198	99.66 129
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPM		97.59 292	97.09 311	99.07 187	99.06 307	98.26 233	98.30 400	99.10 317	94.88 367	98.08 341	99.34 302	96.27 166	99.64 256	89.87 397	98.92 198	99.31 224

XVG-OURS-SEG-HR		98.69 162	98.62 157	98.89 219	99.71 99	97.74 261	99.12 309	99.54 87	98.44 107	99.42 155	99.71 158	94.20 253	99.92 102	98.54 173	98.90 200	99.00 254

PMMVS		98.80 153	98.62 157	99.34 147	99.27 254	98.70 196	98.76 370	99.31 280	97.34 244	99.21 208	99.07 340	97.20 130	99.82 184	98.56 169	98.87 201	99.52 175

DSMNet-mixed		97.25 314	97.35 290	96.95 363	97.84 387	93.61 388	99.57 124	96.63 410	96.13 343	98.87 270	98.61 375	94.59 237	97.70 400	95.08 356	98.86 202	99.55 166

test_vis1_rt		95.81 347	95.65 346	96.32 373	99.67 114	91.35 400	99.49 184	96.74 409	98.25 128	95.24 388	98.10 394	74.96 409	99.90 126	99.53 37	98.85 203	97.70 394

APD_test1		95.87 345	96.49 327	94.00 380	99.53 168	84.01 409	99.54 148	99.32 276	95.91 351	97.99 346	99.85 57	85.49 387	99.88 143	91.96 389	98.84 204	98.12 374

XVG-OURS		98.73 160	98.68 146	98.88 221	99.70 104	97.73 262	98.92 354	99.55 78	98.52 98	99.45 145	99.84 67	95.27 202	99.91 114	98.08 213	98.84 204	99.00 254

Fast-Effi-MVS+		98.70 161	98.43 172	99.51 120	99.51 176	99.28 120	99.52 157	99.47 182	96.11 344	99.01 246	99.34 302	96.20 168	99.84 164	97.88 227	98.82 206	99.39 212

ab-mvs		98.86 139	98.63 152	99.54 104	99.64 132	99.19 129	99.44 204	99.54 87	97.77 194	99.30 185	99.81 95	94.20 253	99.93 90	99.17 79	98.82 206	99.49 187

MDTV_nov1_ep13			98.32 180		99.11 295	94.44 376	99.27 273	98.74 369	97.51 226	99.40 164	99.62 209	94.78 223	99.76 210	97.59 257	98.81 208

Test_1112_low_res		98.89 134	98.66 150	99.57 99	99.69 108	98.95 168	99.03 329	99.47 182	96.98 278	99.15 221	99.23 324	96.77 146	99.89 138	98.83 128	98.78 209	99.86 32

1112_ss		98.98 127	98.77 137	99.59 94	99.68 112	99.02 154	99.25 284	99.48 161	97.23 255	99.13 223	99.58 222	96.93 142	99.90 126	98.87 115	98.78 209	99.84 42

PatchT		97.03 322	96.44 328	98.79 240	98.99 318	98.34 230	99.16 300	99.07 323	92.13 394	99.52 134	97.31 404	94.54 242	98.98 358	88.54 402	98.73 211	99.03 251

UWE-MVS		97.58 293	97.29 300	98.48 270	99.09 301	96.25 337	99.01 337	96.61 411	97.86 180	99.19 214	99.01 348	88.72 360	99.90 126	97.38 279	98.69 212	99.28 226

WB-MVSnew		97.65 288	97.65 249	97.63 343	98.78 346	97.62 270	99.13 306	98.33 387	97.36 243	99.07 235	98.94 356	95.64 191	99.15 333	92.95 382	98.68 213	96.12 409

tpmrst		98.33 187	98.48 170	97.90 327	99.16 287	94.78 370	99.31 256	99.11 316	97.27 250	99.45 145	99.59 218	95.33 200	99.84 164	98.48 176	98.61 214	99.09 242

BH-w/o		98.00 228	97.89 224	98.32 293	99.35 231	96.20 339	99.01 337	98.90 349	96.42 322	98.38 324	99.00 349	95.26 204	99.72 225	96.06 332	98.61 214	99.03 251

cascas		97.69 281	97.43 282	98.48 270	98.60 370	97.30 279	98.18 404	99.39 230	92.96 389	98.41 322	98.78 369	93.77 271	99.27 314	98.16 206	98.61 214	98.86 264

CR-MVSNet		98.17 201	97.93 218	98.87 225	99.18 277	98.49 220	99.22 292	99.33 266	96.96 280	99.56 125	99.38 289	94.33 249	99.00 356	94.83 361	98.58 217	99.14 235

RPMNet		96.72 328	95.90 341	99.19 176	99.18 277	98.49 220	99.22 292	99.52 105	88.72 407	99.56 125	97.38 401	94.08 259	99.95 62	86.87 409	98.58 217	99.14 235

dp		97.75 270	97.80 229	97.59 346	99.10 298	93.71 385	99.32 253	98.88 352	96.48 317	99.08 234	99.55 233	92.67 297	99.82 184	96.52 324	98.58 217	99.24 231

testing3		97.28 312	96.76 321	98.82 234	99.37 227	98.07 243	99.45 198	99.36 247	97.56 218	97.89 350	98.95 355	83.70 397	98.82 374	96.03 333	98.56 220	99.58 160

CVMVSNet		98.57 170	98.67 147	98.30 295	99.35 231	95.59 350	99.50 173	99.55 78	98.60 91	99.39 166	99.83 72	94.48 244	99.45 277	98.75 136	98.56 220	99.85 36

Effi-MVS+		98.81 150	98.59 163	99.48 126	99.46 199	99.12 142	98.08 406	99.50 139	97.50 227	99.38 168	99.41 279	96.37 163	99.81 189	99.11 83	98.54 222	99.51 182

testgi		97.65 288	97.50 265	98.13 310	99.36 230	96.45 329	99.42 215	99.48 161	97.76 195	97.87 351	99.45 270	91.09 334	98.81 375	94.53 363	98.52 223	99.13 237

tpm cat1		97.39 308	97.36 288	97.50 349	99.17 285	93.73 384	99.43 208	99.31 280	91.27 397	98.71 289	99.08 339	94.31 251	99.77 206	96.41 328	98.50 224	99.00 254

WTY-MVS		99.06 115	98.88 123	99.61 91	99.62 141	99.16 134	99.37 237	99.56 70	98.04 165	99.53 132	99.62 209	96.84 143	99.94 72	98.85 122	98.49 225	99.72 106

tpmvs		97.98 230	98.02 208	97.84 332	99.04 311	94.73 371	99.31 256	99.20 306	96.10 348	98.76 285	99.42 275	94.94 212	99.81 189	96.97 303	98.45 226	98.97 258

UBG		97.85 249	97.48 267	98.95 204	99.25 260	97.64 269	99.24 286	98.74 369	97.90 176	98.64 305	98.20 389	88.65 364	99.81 189	98.27 197	98.40 227	99.42 206

LFMVS		97.90 242	97.35 290	99.54 104	99.52 173	99.01 156	99.39 230	98.24 390	97.10 268	99.65 99	99.79 120	84.79 392	99.91 114	99.28 67	98.38 228	99.69 119

Syy-MVS		97.09 321	97.14 307	96.95 363	99.00 315	92.73 394	99.29 263	99.39 230	97.06 272	97.41 360	98.15 390	93.92 265	98.68 380	91.71 390	98.34 229	99.45 202

myMVS_eth3d		96.89 324	96.37 329	98.43 283	99.00 315	97.16 287	99.29 263	99.39 230	97.06 272	97.41 360	98.15 390	83.46 398	98.68 380	95.27 353	98.34 229	99.45 202

test_yl		98.86 139	98.63 152	99.54 104	99.49 189	99.18 131	99.50 173	99.07 323	98.22 133	99.61 114	99.51 249	95.37 198	99.84 164	98.60 160	98.33 231	99.59 156

Anonymous20240529		98.09 209	97.68 246	99.34 147	99.66 124	98.44 225	99.40 226	99.43 216	93.67 381	99.22 205	99.89 32	90.23 345	99.93 90	99.26 71	98.33 231	99.66 129

DCV-MVSNet		98.86 139	98.63 152	99.54 104	99.49 189	99.18 131	99.50 173	99.07 323	98.22 133	99.61 114	99.51 249	95.37 198	99.84 164	98.60 160	98.33 231	99.59 156

GA-MVS		97.85 249	97.47 270	99.00 197	99.38 224	97.99 247	98.57 386	99.15 312	97.04 275	98.90 264	99.30 312	89.83 349	99.38 291	96.70 317	98.33 231	99.62 147

VDD-MVS		97.73 274	97.35 290	98.88 221	99.47 197	97.12 289	99.34 250	98.85 356	98.19 137	99.67 87	99.85 57	82.98 399	99.92 102	99.49 45	98.32 235	99.60 152

Anonymous202405211		98.30 190	97.98 211	99.26 168	99.57 156	98.16 237	99.41 218	98.55 383	96.03 349	99.19 214	99.74 147	91.87 316	99.92 102	99.16 80	98.29 236	99.70 117

SDMVSNet		99.11 106	98.90 118	99.75 61	99.81 46	99.59 73	99.81 20	99.65 33	98.78 77	99.64 104	99.88 39	94.56 239	99.93 90	99.67 23	98.26 237	99.72 106

sd_testset		98.75 157	98.57 164	99.29 162	99.81 46	98.26 233	99.56 130	99.62 41	98.78 77	99.64 104	99.88 39	92.02 313	99.88 143	99.54 35	98.26 237	99.72 106

EGC-MVSNET		82.80 382	77.86 388	97.62 344	97.91 385	96.12 341	99.33 252	99.28 290	8.40 425	25.05 426	99.27 319	84.11 395	99.33 304	89.20 399	98.22 239	97.42 399

GG-mvs-BLEND				98.45 278	98.55 374	98.16 237	99.43 208	93.68 420		97.23 366	98.46 378	89.30 354	99.22 323	95.43 349	98.22 239	97.98 386

thres200		97.61 291	97.28 301	98.62 253	99.64 132	98.03 244	99.26 282	98.74 369	97.68 205	99.09 233	98.32 385	91.66 325	99.81 189	92.88 383	98.22 239	98.03 380

HY-MVS	97.30 7	98.85 146	98.64 151	99.47 129	99.42 209	99.08 147	99.62 95	99.36 247	97.39 241	99.28 189	99.68 179	96.44 161	99.92 102	98.37 187	98.22 239	99.40 211

thres600view7		97.86 248	97.51 264	98.92 210	99.72 94	97.95 252	99.59 109	98.74 369	97.94 172	99.27 194	98.62 373	91.75 319	99.86 151	93.73 373	98.19 243	98.96 260

thres100view900		97.76 266	97.45 273	98.69 249	99.72 94	97.86 258	99.59 109	98.74 369	97.93 173	99.26 198	98.62 373	91.75 319	99.83 177	93.22 378	98.18 244	98.37 361

tfpn200view9		97.72 276	97.38 286	98.72 245	99.69 108	97.96 250	99.50 173	98.73 375	97.83 186	99.17 219	98.45 379	91.67 323	99.83 177	93.22 378	98.18 244	98.37 361

VNet		99.11 106	98.90 118	99.73 67	99.52 173	99.56 79	99.41 218	99.39 230	99.01 44	99.74 68	99.78 127	95.56 192	99.92 102	99.52 39	98.18 244	99.72 106

thres400		97.77 265	97.38 286	98.92 210	99.69 108	97.96 250	99.50 173	98.73 375	97.83 186	99.17 219	98.45 379	91.67 323	99.83 177	93.22 378	98.18 244	98.96 260

VDDNet		97.55 294	97.02 313	99.16 179	99.49 189	98.12 241	99.38 235	99.30 284	95.35 357	99.68 83	99.90 27	82.62 401	99.93 90	99.31 63	98.13 248	99.42 206

alignmvs		98.81 150	98.56 166	99.58 97	99.43 207	99.42 101	99.51 166	98.96 337	98.61 90	99.35 176	98.92 360	94.78 223	99.77 206	99.35 55	98.11 249	99.54 168

tpm2		97.44 306	97.34 293	97.74 339	99.15 291	94.36 378	99.45 198	98.94 338	93.45 386	98.90 264	99.44 271	91.35 331	99.59 266	97.31 282	98.07 250	99.29 225

testing11		97.50 299	97.10 310	98.71 247	99.20 271	96.91 309	99.29 263	98.82 359	97.89 177	98.21 336	98.40 381	85.63 386	99.83 177	98.45 181	98.04 251	99.37 216

JIA-IIPM		97.50 299	97.02 313	98.93 208	98.73 355	97.80 260	99.30 258	98.97 335	91.73 396	98.91 262	94.86 411	95.10 209	99.71 231	97.58 258	97.98 252	99.28 226

testing91		97.44 306	97.02 313	98.71 247	99.18 277	96.89 311	99.19 296	99.04 327	97.78 193	98.31 328	98.29 386	85.41 388	99.85 157	98.01 219	97.95 253	99.39 212

CostFormer		97.72 276	97.73 242	97.71 340	99.15 291	94.02 381	99.54 148	99.02 330	94.67 372	99.04 243	99.35 298	92.35 309	99.77 206	98.50 175	97.94 254	99.34 221

sasdasda		99.02 121	98.86 126	99.51 120	99.42 209	99.32 111	99.80 25	99.48 161	98.63 87	99.31 182	98.81 365	97.09 133	99.75 213	99.27 69	97.90 255	99.47 194

canonicalmvs		99.02 121	98.86 126	99.51 120	99.42 209	99.32 111	99.80 25	99.48 161	98.63 87	99.31 182	98.81 365	97.09 133	99.75 213	99.27 69	97.90 255	99.47 194

ETVMVS		97.50 299	96.90 317	99.29 162	99.23 264	98.78 192	99.32 253	98.90 349	97.52 225	98.56 314	98.09 395	84.72 393	99.69 242	97.86 230	97.88 257	99.39 212

MGCFI-Net		99.01 125	98.85 128	99.50 125	99.42 209	99.26 123	99.82 16	99.48 161	98.60 91	99.28 189	98.81 365	97.04 137	99.76 210	99.29 66	97.87 258	99.47 194

OpenMVS_ROB	92.34 20	94.38 362	93.70 368	96.41 372	97.38 394	93.17 391	99.06 322	98.75 366	86.58 408	94.84 394	98.26 387	81.53 405	99.32 306	89.01 400	97.87 258	96.76 402

testing99		97.36 309	96.94 316	98.63 252	99.18 277	96.70 317	99.30 258	98.93 339	97.71 200	98.23 333	98.26 387	84.92 391	99.84 164	98.04 218	97.85 260	99.35 218

dongtai		93.26 367	92.93 371	94.25 379	99.39 222	85.68 407	97.68 410	93.27 421	92.87 390	96.85 376	99.39 287	82.33 403	97.48 402	76.78 415	97.80 261	99.58 160

TR-MVS		97.76 266	97.41 284	98.82 234	99.06 307	97.87 256	98.87 360	98.56 382	96.63 304	98.68 297	99.22 325	92.49 302	99.65 253	95.40 350	97.79 262	98.95 262

DeepMVS_CX				93.34 383	99.29 249	82.27 412		99.22 302	85.15 409	96.33 380	99.05 343	90.97 336	99.73 221	93.57 375	97.77 263	98.01 381

tt0805		97.97 233	97.77 235	98.57 259	99.59 152	96.61 324	99.45 198	99.08 320	98.21 135	98.88 267	99.80 108	88.66 363	99.70 237	98.58 163	97.72 264	99.39 212

CLD-MVS		98.16 202	98.10 196	98.33 291	99.29 249	96.82 314	98.75 371	99.44 210	97.83 186	99.13 223	99.55 233	92.92 285	99.67 245	98.32 194	97.69 265	98.48 347
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
testing222		97.16 317	96.50 326	99.16 179	99.16 287	98.47 224	99.27 273	98.66 379	97.71 200	98.23 333	98.15 390	82.28 404	99.84 164	97.36 280	97.66 266	99.18 234

HQP_MVS		98.27 193	98.22 186	98.44 281	99.29 249	96.97 305	99.39 230	99.47 182	98.97 55	99.11 227	99.61 213	92.71 294	99.69 242	97.78 238	97.63 267	98.67 305

plane_prior5								99.47 182					99.69 242	97.78 238	97.63 267	98.67 305

test_djsdf		98.67 164	98.57 164	98.98 199	98.70 360	98.91 175	99.88 4	99.46 191	97.55 219	99.22 205	99.88 39	95.73 187	99.28 311	99.03 93	97.62 269	98.75 277

anonymousdsp		98.44 175	98.28 183	98.94 206	98.50 376	98.96 165	99.77 34	99.50 139	97.07 270	98.87 270	99.77 135	94.76 227	99.28 311	98.66 149	97.60 270	98.57 341

plane_prior						96.97 305	99.21 294		98.45 104						97.60 270

HQP3-MVS								99.39 230							97.58 272

HQP-MVS		98.02 223	97.90 220	98.37 289	99.19 274	96.83 312	98.98 343	99.39 230	98.24 129	98.66 298	99.40 283	92.47 303	99.64 256	97.19 291	97.58 272	98.64 317

EI-MVSNet		98.67 164	98.67 147	98.68 250	99.35 231	97.97 248	99.50 173	99.38 238	96.93 285	99.20 211	99.83 72	97.87 110	99.36 298	98.38 185	97.56 274	98.71 284

MVSTER		98.49 171	98.32 180	99.00 197	99.35 231	99.02 154	99.54 148	99.38 238	97.41 239	99.20 211	99.73 153	93.86 268	99.36 298	98.87 115	97.56 274	98.62 326

MonoMVSNet		98.38 183	98.47 171	98.12 311	98.59 372	96.19 340	99.72 52	98.79 364	97.89 177	99.44 150	99.52 245	96.13 169	98.90 372	98.64 151	97.54 276	99.28 226

OPM-MVS		98.19 198	98.10 196	98.45 278	98.88 332	97.07 294	99.28 268	99.38 238	98.57 93	99.22 205	99.81 95	92.12 311	99.66 248	98.08 213	97.54 276	98.61 335
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
UniMVSNet_ETH3D		97.32 311	96.81 319	98.87 225	99.40 219	97.46 274	99.51 166	99.53 100	95.86 352	98.54 316	99.77 135	82.44 402	99.66 248	98.68 147	97.52 278	99.50 186

LPG-MVS_test		98.22 194	98.13 193	98.49 268	99.33 236	97.05 296	99.58 117	99.55 78	97.46 229	99.24 200	99.83 72	92.58 299	99.72 225	98.09 209	97.51 279	98.68 298

LGP-MVS_train				98.49 268	99.33 236	97.05 296		99.55 78	97.46 229	99.24 200	99.83 72	92.58 299	99.72 225	98.09 209	97.51 279	98.68 298

jajsoiax		98.43 176	98.28 183	98.88 221	98.60 370	98.43 226	99.82 16	99.53 100	98.19 137	98.63 307	99.80 108	93.22 280	99.44 282	99.22 73	97.50 281	98.77 273

EG-PatchMatch MVS		95.97 344	95.69 345	96.81 367	97.78 388	92.79 393	99.16 300	98.93 339	96.16 339	94.08 396	99.22 325	82.72 400	99.47 274	95.67 344	97.50 281	98.17 371

test_0402		96.64 330	96.24 332	97.85 330	98.85 339	96.43 330	99.44 204	99.26 294	93.52 383	96.98 373	99.52 245	88.52 367	99.20 330	92.58 388	97.50 281	97.93 389

ACMP	97.20 11	98.06 213	97.94 217	98.45 278	99.37 227	97.01 301	99.44 204	99.49 149	97.54 222	98.45 321	99.79 120	91.95 315	99.72 225	97.91 225	97.49 284	98.62 326
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
mvs_tets		98.40 182	98.23 185	98.91 214	98.67 363	98.51 218	99.66 75	99.53 100	98.19 137	98.65 304	99.81 95	92.75 289	99.44 282	99.31 63	97.48 285	98.77 273

test_fmvs2		97.25 314	97.30 298	97.09 359	99.43 207	93.31 390	99.73 50	98.87 354	98.83 68	99.28 189	99.80 108	84.45 394	99.66 248	97.88 227	97.45 286	98.30 363

ACMM	97.58 5	98.37 185	98.34 178	98.48 270	99.41 214	97.10 290	99.56 130	99.45 202	98.53 97	99.04 243	99.85 57	93.00 283	99.71 231	98.74 137	97.45 286	98.64 317
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH	97.28 8	98.10 208	97.99 210	98.44 281	99.41 214	96.96 307	99.60 102	99.56 70	98.09 153	98.15 339	99.91 20	90.87 337	99.70 237	98.88 112	97.45 286	98.67 305
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LTVRE_ROB	97.16 12	98.02 223	97.90 220	98.40 286	99.23 264	96.80 315	99.70 56	99.60 54	97.12 264	98.18 338	99.70 162	91.73 321	99.72 225	98.39 184	97.45 286	98.68 298
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++															97.43 290

D2MVS		98.41 179	98.50 169	98.15 309	99.26 256	96.62 323	99.40 226	99.61 48	97.71 200	98.98 252	99.36 295	96.04 172	99.67 245	98.70 142	97.41 291	98.15 373

ITE_SJBPF				98.08 312	99.29 249	96.37 331		98.92 342	98.34 117	98.83 276	99.75 142	91.09 334	99.62 263	95.82 337	97.40 292	98.25 367

XVG-ACMP-BASELINE		97.83 255	97.71 244	98.20 303	99.11 295	96.33 333	99.41 218	99.52 105	98.06 162	99.05 242	99.50 252	89.64 352	99.73 221	97.73 246	97.38 293	98.53 343

USDC		97.34 310	97.20 305	97.75 338	99.07 305	95.20 362	98.51 390	99.04 327	97.99 169	98.31 328	99.86 52	89.02 356	99.55 270	95.67 344	97.36 294	98.49 346

PVSNet_BlendedMVS		98.86 139	98.80 133	99.03 193	99.76 66	98.79 190	99.28 268	99.91 3	97.42 238	99.67 87	99.37 292	97.53 118	99.88 143	98.98 98	97.29 295	98.42 355

dmvs_re		98.08 211	98.16 188	97.85 330	99.55 164	94.67 373	99.70 56	98.92 342	98.15 142	99.06 240	99.35 298	93.67 274	99.25 316	97.77 241	97.25 296	99.64 140

PS-MVSNAJss		98.92 132	98.92 115	98.90 216	98.78 346	98.53 212	99.78 32	99.54 87	98.07 158	99.00 250	99.76 139	99.01 18	99.37 294	99.13 81	97.23 297	98.81 267

TinyColmap		97.12 319	96.89 318	97.83 333	99.07 305	95.52 354	98.57 386	98.74 369	97.58 215	97.81 354	99.79 120	88.16 371	99.56 268	95.10 355	97.21 298	98.39 359

ACMMP++_ref															97.19 299

ACMH+	97.24 10	97.92 239	97.78 233	98.32 293	99.46 199	96.68 321	99.56 130	99.54 87	98.41 109	97.79 355	99.87 48	90.18 346	99.66 248	98.05 217	97.18 300	98.62 326

test0.0.03 1		97.71 279	97.42 283	98.56 262	98.41 380	97.82 259	98.78 368	98.63 380	97.34 244	98.05 345	98.98 352	94.45 246	98.98 358	95.04 357	97.15 301	98.89 263

kuosan		90.92 375	90.11 380	93.34 383	98.78 346	85.59 408	98.15 405	93.16 423	89.37 404	92.07 404	98.38 382	81.48 406	95.19 413	62.54 422	97.04 302	99.25 230

CMPMVS	69.68 23	94.13 363	94.90 355	91.84 388	97.24 398	80.01 418	98.52 389	99.48 161	89.01 405	91.99 405	99.67 185	85.67 385	99.13 337	95.44 348	97.03 303	96.39 406
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
OurMVSNet-221017-0		97.88 244	97.77 235	98.19 304	98.71 359	96.53 326	99.88 4	99.00 332	97.79 191	98.78 283	99.94 6	91.68 322	99.35 301	97.21 287	96.99 304	98.69 293

LF4IMVS		97.52 296	97.46 272	97.70 341	98.98 321	95.55 351	99.29 263	98.82 359	98.07 158	98.66 298	99.64 198	89.97 347	99.61 264	97.01 299	96.68 305	97.94 388

GBi-Net		97.68 283	97.48 267	98.29 296	99.51 176	97.26 283	99.43 208	99.48 161	96.49 314	99.07 235	99.32 309	90.26 342	98.98 358	97.10 295	96.65 306	98.62 326

test1		97.68 283	97.48 267	98.29 296	99.51 176	97.26 283	99.43 208	99.48 161	96.49 314	99.07 235	99.32 309	90.26 342	98.98 358	97.10 295	96.65 306	98.62 326

FMVSNet3		98.03 221	97.76 239	98.84 232	99.39 222	98.98 158	99.40 226	99.38 238	96.67 298	99.07 235	99.28 316	92.93 284	98.98 358	97.10 295	96.65 306	98.56 342

FMVSNet2		97.72 276	97.36 288	98.80 239	99.51 176	98.84 183	99.45 198	99.42 218	96.49 314	98.86 274	99.29 314	90.26 342	98.98 358	96.44 326	96.56 309	98.58 340

K. test v3		97.10 320	96.79 320	98.01 317	98.72 357	96.33 333	99.87 8	97.05 404	97.59 213	96.16 383	99.80 108	88.71 361	99.04 349	96.69 318	96.55 310	98.65 315

tpm		97.67 286	97.55 258	98.03 314	99.02 313	95.01 366	99.43 208	98.54 384	96.44 320	99.12 225	99.34 302	91.83 318	99.60 265	97.75 244	96.46 311	99.48 188

SixPastTwentyTwo		97.50 299	97.33 295	98.03 314	98.65 364	96.23 338	99.77 34	98.68 378	97.14 261	97.90 349	99.93 9	90.45 340	99.18 331	97.00 300	96.43 312	98.67 305

FIs		98.78 154	98.63 152	99.23 173	99.18 277	99.54 83	99.83 15	99.59 58	98.28 123	98.79 282	99.81 95	96.75 147	99.37 294	99.08 88	96.38 313	98.78 269

FC-MVSNet-test		98.75 157	98.62 157	99.15 183	99.08 304	99.45 98	99.86 11	99.60 54	98.23 132	98.70 295	99.82 81	96.80 144	99.22 323	99.07 89	96.38 313	98.79 268

XXY-MVS		98.38 183	98.09 199	99.24 171	99.26 256	99.32 111	99.56 130	99.55 78	97.45 232	98.71 289	99.83 72	93.23 278	99.63 262	98.88 112	96.32 315	98.76 275

reproduce_monomvs		97.89 243	97.87 225	97.96 323	99.51 176	95.45 356	99.60 102	99.25 296	99.17 19	98.85 275	99.49 255	89.29 355	99.64 256	99.35 55	96.31 316	98.78 269

FMVSNet1		96.84 326	96.36 330	98.29 296	99.32 243	97.26 283	99.43 208	99.48 161	95.11 361	98.55 315	99.32 309	83.95 396	98.98 358	95.81 338	96.26 317	98.62 326

N_pmnet		94.95 357	95.83 343	92.31 387	98.47 377	79.33 419	99.12 309	92.81 425	93.87 379	97.68 356	99.13 335	93.87 267	99.01 355	91.38 392	96.19 318	98.59 339

Anonymous20240521		96.20 339	95.89 342	97.13 357	97.72 391	94.96 368	99.79 31	99.29 288	93.01 388	97.20 368	99.03 345	89.69 351	98.36 386	91.16 393	96.13 319	98.07 377

pmmvs4		98.13 205	97.90 220	98.81 237	98.61 369	98.87 178	98.99 340	99.21 305	96.44 320	99.06 240	99.58 222	95.90 181	99.11 342	97.18 293	96.11 320	98.46 352

WBMVS		97.74 272	97.50 265	98.46 276	99.24 262	97.43 275	99.21 294	99.42 218	97.45 232	98.96 256	99.41 279	88.83 359	99.23 319	98.94 103	96.02 321	98.71 284

our_test_3		97.65 288	97.68 246	97.55 347	98.62 367	94.97 367	98.84 362	99.30 284	96.83 291	98.19 337	99.34 302	97.01 139	99.02 353	95.00 358	96.01 322	98.64 317

IterMVS		97.83 255	97.77 235	98.02 316	99.58 154	96.27 336	99.02 332	99.48 161	97.22 256	98.71 289	99.70 162	92.75 289	99.13 337	97.46 273	96.00 323	98.67 305
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		97.85 249	97.64 252	98.48 270	99.09 301	97.87 256	98.60 385	99.33 266	97.11 267	98.87 270	99.22 325	92.38 308	99.17 332	98.21 200	95.99 324	98.42 355

miper_ehance_all_eth		98.18 200	98.10 196	98.41 284	99.23 264	97.72 264	98.72 374	99.31 280	96.60 308	98.88 267	99.29 314	97.29 128	99.13 337	97.60 256	95.99 324	98.38 360

miper_enhance_ethall		98.16 202	98.08 200	98.41 284	98.96 324	97.72 264	98.45 392	99.32 276	96.95 282	98.97 254	99.17 330	97.06 136	99.22 323	97.86 230	95.99 324	98.29 364

ppachtmachnet_test		97.49 304	97.45 273	97.61 345	98.62 367	95.24 361	98.80 366	99.46 191	96.11 344	98.22 335	99.62 209	96.45 160	98.97 365	93.77 372	95.97 327	98.61 335

pmmvs5		97.52 296	97.30 298	98.16 306	98.57 373	96.73 316	99.27 273	98.90 349	96.14 342	98.37 325	99.53 242	91.54 328	99.14 334	97.51 267	95.87 328	98.63 324

IterMVS-SCA-FT		97.82 258	97.75 240	98.06 313	99.57 156	96.36 332	99.02 332	99.49 149	97.18 258	98.71 289	99.72 157	92.72 292	99.14 334	97.44 275	95.86 329	98.67 305

cl____		98.01 226	97.84 228	98.55 264	99.25 260	97.97 248	98.71 375	99.34 259	96.47 319	98.59 313	99.54 238	95.65 190	99.21 328	97.21 287	95.77 330	98.46 352

DIV-MVS_self_test		98.01 226	97.85 227	98.48 270	99.24 262	97.95 252	98.71 375	99.35 254	96.50 313	98.60 312	99.54 238	95.72 188	99.03 351	97.21 287	95.77 330	98.46 352

new_pmnet		96.38 336	96.03 338	97.41 350	98.13 384	95.16 365	99.05 324	99.20 306	93.94 378	97.39 363	98.79 368	91.61 327	99.04 349	90.43 395	95.77 330	98.05 379

FMVSNet5		96.43 335	96.19 334	97.15 355	99.11 295	95.89 345	99.32 253	99.52 105	94.47 376	98.34 327	99.07 340	87.54 377	97.07 405	92.61 387	95.72 333	98.47 349

Gipuma		90.99 374	90.15 379	93.51 382	98.73 355	90.12 402	93.98 415	99.45 202	79.32 413	92.28 403	94.91 410	69.61 411	97.98 394	87.42 406	95.67 334	92.45 413
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
IterMVS-LS		98.46 174	98.42 173	98.58 258	99.59 152	98.00 246	99.37 237	99.43 216	96.94 284	99.07 235	99.59 218	97.87 110	99.03 351	98.32 194	95.62 335	98.71 284
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ttmdpeth		97.80 262	97.63 253	98.29 296	98.77 351	97.38 277	99.64 84	99.36 247	98.78 77	96.30 381	99.58 222	92.34 310	99.39 289	98.36 189	95.58 336	98.10 375

Patchmtry		97.75 270	97.40 285	98.81 237	99.10 298	98.87 178	99.11 315	99.33 266	94.83 369	98.81 278	99.38 289	94.33 249	99.02 353	96.10 331	95.57 337	98.53 343

MIMVSNet1		95.51 349	95.04 354	96.92 365	97.38 394	95.60 349	99.52 157	99.50 139	93.65 382	96.97 374	99.17 330	85.28 390	96.56 409	88.36 403	95.55 338	98.60 338

eth_miper_zixun_eth		98.05 218	97.96 213	98.33 291	99.26 256	97.38 277	98.56 388	99.31 280	96.65 300	98.88 267	99.52 245	96.58 153	99.12 341	97.39 278	95.53 339	98.47 349

miper_lstm_enhance		98.00 228	97.91 219	98.28 300	99.34 235	97.43 275	98.88 358	99.36 247	96.48 317	98.80 280	99.55 233	95.98 174	98.91 370	97.27 284	95.50 340	98.51 345

tfpnnormal		97.84 253	97.47 270	98.98 199	99.20 271	99.22 128	99.64 84	99.61 48	96.32 326	98.27 332	99.70 162	93.35 277	99.44 282	95.69 342	95.40 341	98.27 365

c3_l		98.12 207	98.04 205	98.38 288	99.30 245	97.69 268	98.81 365	99.33 266	96.67 298	98.83 276	99.34 302	97.11 132	98.99 357	97.58 258	95.34 342	98.48 347

EU-MVSNet		97.98 230	98.03 206	97.81 336	98.72 357	96.65 322	99.66 75	99.66 28	98.09 153	98.35 326	99.82 81	95.25 205	98.01 393	97.41 277	95.30 343	98.78 269

v1240		97.69 281	97.32 296	98.79 240	98.85 339	98.43 226	99.48 188	99.36 247	96.11 344	99.27 194	99.36 295	93.76 272	99.24 318	94.46 364	95.23 344	98.70 289

v1192		97.81 260	97.44 278	98.91 214	98.88 332	98.68 197	99.51 166	99.34 259	96.18 337	99.20 211	99.34 302	94.03 260	99.36 298	95.32 352	95.18 345	98.69 293

v1144		97.98 230	97.69 245	98.85 231	98.87 335	98.66 199	99.54 148	99.35 254	96.27 330	99.23 204	99.35 298	94.67 234	99.23 319	96.73 315	95.16 346	98.68 298

v1921920		97.80 262	97.45 273	98.84 232	98.80 342	98.53 212	99.52 157	99.34 259	96.15 341	99.24 200	99.47 264	93.98 262	99.29 310	95.40 350	95.13 347	98.69 293

Anonymous20231206		96.22 337	96.03 338	96.79 368	97.31 397	94.14 380	99.63 90	99.08 320	96.17 338	97.04 372	99.06 342	93.94 263	97.76 399	86.96 408	95.06 348	98.47 349

v144192		97.92 239	97.60 256	98.87 225	98.83 341	98.65 200	99.55 144	99.34 259	96.20 335	99.32 181	99.40 283	94.36 248	99.26 315	96.37 329	95.03 349	98.70 289

v2v482		98.06 213	97.77 235	98.92 210	98.90 330	98.82 187	99.57 124	99.36 247	96.65 300	99.19 214	99.35 298	94.20 253	99.25 316	97.72 248	94.97 350	98.69 293

FPMVS		84.93 381	85.65 382	82.75 402	86.77 423	63.39 428	98.35 395	98.92 342	74.11 414	83.39 413	98.98 352	50.85 421	92.40 417	84.54 413	94.97 350	92.46 412

lessismore_v0				97.79 337	98.69 361	95.44 358		94.75 417		95.71 387	99.87 48	88.69 362	99.32 306	95.89 336	94.93 352	98.62 326

dmvs_testset		95.02 354	96.12 335	91.72 389	99.10 298	80.43 417	99.58 117	97.87 397	97.47 228	95.22 389	98.82 364	93.99 261	95.18 414	88.09 404	94.91 353	99.56 165

test_method		91.10 373	91.36 375	90.31 393	95.85 406	73.72 426	94.89 414	99.25 296	68.39 417	95.82 386	99.02 347	80.50 407	98.95 368	93.64 374	94.89 354	98.25 367

V42		98.06 213	97.79 230	98.86 228	98.98 321	98.84 183	99.69 60	99.34 259	96.53 312	99.30 185	99.37 292	94.67 234	99.32 306	97.57 262	94.66 355	98.42 355

v10		97.85 249	97.52 262	98.86 228	98.99 318	98.67 198	99.75 42	99.41 221	95.70 353	98.98 252	99.41 279	94.75 228	99.23 319	96.01 335	94.63 356	98.67 305

nrg030		98.64 167	98.42 173	99.28 166	99.05 310	99.69 50	99.81 20	99.46 191	98.04 165	99.01 246	99.82 81	96.69 149	99.38 291	99.34 60	94.59 357	98.78 269

VPA-MVSNet		98.29 191	97.95 215	99.30 159	99.16 287	99.54 83	99.50 173	99.58 62	98.27 125	99.35 176	99.37 292	92.53 301	99.65 253	99.35 55	94.46 358	98.72 282

MDA-MVSNet_test_wron		95.45 350	94.60 357	98.01 317	98.16 383	97.21 286	99.11 315	99.24 299	93.49 384	80.73 417	98.98 352	93.02 282	98.18 388	94.22 369	94.45 359	98.64 317

Anonymous20231211		97.88 244	97.54 261	98.90 216	99.71 99	98.53 212	99.48 188	99.57 65	94.16 377	98.81 278	99.68 179	93.23 278	99.42 287	98.84 125	94.42 360	98.76 275

MDA-MVSNet-bldmvs		94.96 356	93.98 363	97.92 325	98.24 382	97.27 281	99.15 303	99.33 266	93.80 380	80.09 418	99.03 345	88.31 369	97.86 397	93.49 376	94.36 361	98.62 326

WR-MVS		98.06 213	97.73 242	99.06 189	98.86 338	99.25 125	99.19 296	99.35 254	97.30 248	98.66 298	99.43 273	93.94 263	99.21 328	98.58 163	94.28 362	98.71 284

test20.03		96.12 341	95.96 340	96.63 369	97.44 393	95.45 356	99.51 166	99.38 238	96.55 311	96.16 383	99.25 322	93.76 272	96.17 410	87.35 407	94.22 363	98.27 365

YYNet1		95.36 352	94.51 359	97.92 325	97.89 386	97.10 290	99.10 317	99.23 300	93.26 387	80.77 416	99.04 344	92.81 288	98.02 392	94.30 365	94.18 364	98.64 317

mvs5depth		96.66 329	96.22 333	97.97 321	97.00 403	96.28 335	98.66 380	99.03 329	96.61 305	96.93 375	99.79 120	87.20 379	99.47 274	96.65 322	94.13 365	98.16 372

CP-MVSNet		98.09 209	97.78 233	99.01 195	98.97 323	99.24 126	99.67 69	99.46 191	97.25 252	98.48 320	99.64 198	93.79 270	99.06 347	98.63 153	94.10 366	98.74 280

v8		97.95 235	97.63 253	98.93 208	98.95 325	98.81 189	99.80 25	99.41 221	96.03 349	99.10 230	99.42 275	94.92 215	99.30 309	96.94 306	94.08 367	98.66 313

PS-CasMVS		97.93 236	97.59 257	98.95 204	98.99 318	99.06 150	99.68 66	99.52 105	97.13 262	98.31 328	99.68 179	92.44 307	99.05 348	98.51 174	94.08 367	98.75 277

WB-MVS		93.10 368	94.10 361	90.12 394	95.51 412	81.88 414	99.73 50	99.27 293	95.05 364	93.09 401	98.91 361	94.70 232	91.89 418	76.62 416	94.02 369	96.58 404

v7n		97.87 246	97.52 262	98.92 210	98.76 353	98.58 208	99.84 12	99.46 191	96.20 335	98.91 262	99.70 162	94.89 217	99.44 282	96.03 333	93.89 370	98.75 277

SSC-MVS		92.73 370	93.73 365	89.72 395	95.02 414	81.38 415	99.76 37	99.23 300	94.87 368	92.80 402	98.93 357	94.71 231	91.37 419	74.49 418	93.80 371	96.42 405

WR-MVS_H		98.13 205	97.87 225	98.90 216	99.02 313	98.84 183	99.70 56	99.59 58	97.27 250	98.40 323	99.19 329	95.53 193	99.23 319	98.34 191	93.78 372	98.61 335

NR-MVSNet		97.97 233	97.61 255	99.02 194	98.87 335	99.26 123	99.47 194	99.42 218	97.63 210	97.08 371	99.50 252	95.07 210	99.13 337	97.86 230	93.59 373	98.68 298

pm-mvs1		97.68 283	97.28 301	98.88 221	99.06 307	98.62 204	99.50 173	99.45 202	96.32 326	97.87 351	99.79 120	92.47 303	99.35 301	97.54 265	93.54 374	98.67 305

UniMVSNet (Re)		98.29 191	98.00 209	99.13 184	99.00 315	99.36 108	99.49 184	99.51 119	97.95 171	98.97 254	99.13 335	96.30 165	99.38 291	98.36 189	93.34 375	98.66 313

baseline1		98.31 188	97.95 215	99.38 144	99.50 187	98.74 193	99.59 109	98.93 339	98.41 109	99.14 222	99.60 216	94.59 237	99.79 199	98.48 176	93.29 376	99.61 149

VPNet		97.84 253	97.44 278	99.01 195	99.21 269	98.94 171	99.48 188	99.57 65	98.38 111	99.28 189	99.73 153	88.89 358	99.39 289	99.19 75	93.27 377	98.71 284

PEN-MVS		97.76 266	97.44 278	98.72 245	98.77 351	98.54 211	99.78 32	99.51 119	97.06 272	98.29 331	99.64 198	92.63 298	98.89 373	98.09 209	93.16 378	98.72 282

v148		97.79 264	97.55 258	98.50 267	98.74 354	97.72 264	99.54 148	99.33 266	96.26 331	98.90 264	99.51 249	94.68 233	99.14 334	97.83 234	93.15 379	98.63 324

TranMVSNet+NR-MVSNet		97.93 236	97.66 248	98.76 243	98.78 346	98.62 204	99.65 81	99.49 149	97.76 195	98.49 319	99.60 216	94.23 252	98.97 365	98.00 220	92.90 380	98.70 289

Baseline_NR-MVSNet		97.76 266	97.45 273	98.68 250	99.09 301	98.29 231	99.41 218	98.85 356	95.65 354	98.63 307	99.67 185	94.82 219	99.10 344	98.07 216	92.89 381	98.64 317

UniMVSNet_NR-MVSNet		98.22 194	97.97 212	98.96 202	98.92 328	98.98 158	99.48 188	99.53 100	97.76 195	98.71 289	99.46 268	96.43 162	99.22 323	98.57 166	92.87 382	98.69 293

DU-MVS		98.08 211	97.79 230	98.96 202	98.87 335	98.98 158	99.41 218	99.45 202	97.87 179	98.71 289	99.50 252	94.82 219	99.22 323	98.57 166	92.87 382	98.68 298

pmmvs6		96.53 332	96.09 337	97.82 335	98.69 361	95.47 355	99.37 237	99.47 182	93.46 385	97.41 360	99.78 127	87.06 380	99.33 304	96.92 309	92.70 384	98.65 315

MVStest1		96.08 343	95.48 348	97.89 328	98.93 326	96.70 317	99.56 130	99.35 254	92.69 392	91.81 406	99.46 268	89.90 348	98.96 367	95.00 358	92.61 385	98.00 384

DTE-MVSNet		97.51 298	97.19 306	98.46 276	98.63 366	98.13 240	99.84 12	99.48 161	96.68 297	97.97 348	99.67 185	92.92 285	98.56 382	96.88 311	92.60 386	98.70 289

ET-MVSNet_ETH3D		96.49 333	95.64 347	99.05 191	99.53 168	98.82 187	98.84 362	97.51 402	97.63 210	84.77 411	99.21 328	92.09 312	98.91 370	98.98 98	92.21 387	99.41 209

TransMVSNet (Re)		97.15 318	96.58 324	98.86 228	99.12 293	98.85 182	99.49 184	98.91 347	95.48 356	97.16 369	99.80 108	93.38 276	99.11 342	94.16 370	91.73 388	98.62 326

ambc				93.06 386	92.68 417	82.36 411	98.47 391	98.73 375		95.09 392	97.41 400	55.55 418	99.10 344	96.42 327	91.32 389	97.71 392

testf1		90.42 376	90.68 377	89.65 396	97.78 388	73.97 424	99.13 306	98.81 361	89.62 402	91.80 407	98.93 357	62.23 416	98.80 376	86.61 410	91.17 390	96.19 407

APD_test2		90.42 376	90.68 377	89.65 396	97.78 388	73.97 424	99.13 306	98.81 361	89.62 402	91.80 407	98.93 357	62.23 416	98.80 376	86.61 410	91.17 390	96.19 407

PMVS	70.75 22	75.98 388	74.97 389	79.01 404	70.98 427	55.18 429	93.37 416	98.21 391	65.08 421	61.78 422	93.83 412	21.74 429	92.53 416	78.59 414	91.12 392	89.34 417
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_f		91.90 372	91.26 376	93.84 381	95.52 411	85.92 406	99.69 60	98.53 385	95.31 358	93.87 397	96.37 408	55.33 419	98.27 387	95.70 341	90.98 393	97.32 400

test_fmvs3		92.10 371	91.77 374	93.08 385	96.19 404	86.25 405	99.82 16	98.62 381	96.65 300	95.19 391	96.90 405	55.05 420	95.93 412	96.63 323	90.92 394	97.06 401

mvsany_test3		93.77 365	93.45 369	94.74 378	95.78 407	88.01 404	99.64 84	98.25 389	98.28 123	94.31 395	97.97 397	68.89 412	98.51 384	97.50 268	90.37 395	97.71 392

UnsupCasMVSNet_eth		96.44 334	96.12 335	97.40 351	98.65 364	95.65 348	99.36 242	99.51 119	97.13 262	96.04 385	98.99 350	88.40 368	98.17 389	96.71 316	90.27 396	98.40 358

Patchmatch-RL test		95.84 346	95.81 344	95.95 375	95.61 408	90.57 401	98.24 401	98.39 386	95.10 363	95.20 390	98.67 372	94.78 223	97.77 398	96.28 330	90.02 397	99.51 182

PM-MVS		92.96 369	92.23 373	95.14 377	95.61 408	89.98 403	99.37 237	98.21 391	94.80 370	95.04 393	97.69 398	65.06 413	97.90 396	94.30 365	89.98 398	97.54 398

pmmvs-eth3d		95.34 353	94.73 356	97.15 355	95.53 410	95.94 344	99.35 247	99.10 317	95.13 359	93.55 398	97.54 399	88.15 372	97.91 395	94.58 362	89.69 399	97.61 395

mmtdpeth		96.95 323	96.71 322	97.67 342	99.33 236	94.90 369	99.89 2	99.28 290	98.15 142	99.72 75	98.57 376	86.56 381	99.90 126	99.82 16	89.02 400	98.20 370

new-patchmatchnet		94.48 361	94.08 362	95.67 376	95.08 413	92.41 395	99.18 298	99.28 290	94.55 375	93.49 399	97.37 402	87.86 375	97.01 406	91.57 391	88.36 401	97.61 395

test_vis3_rt		87.04 378	85.81 381	90.73 392	93.99 416	81.96 413	99.76 37	90.23 427	92.81 391	81.35 415	91.56 415	40.06 424	99.07 346	94.27 367	88.23 402	91.15 415

UnsupCasMVSNet_bld		93.53 366	92.51 372	96.58 371	97.38 394	93.82 382	98.24 401	99.48 161	91.10 399	93.10 400	96.66 406	74.89 410	98.37 385	94.03 371	87.71 403	97.56 397

pmmvs3		94.09 364	93.25 370	96.60 370	94.76 415	94.49 375	98.92 354	98.18 393	89.66 401	96.48 379	98.06 396	86.28 382	97.33 403	89.68 398	87.20 404	97.97 387

IB-MVS	95.67 18	96.22 337	95.44 351	98.57 259	99.21 269	96.70 317	98.65 381	97.74 400	96.71 295	97.27 365	98.54 377	86.03 383	99.92 102	98.47 179	86.30 405	99.10 238
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		86.80 380	85.22 384	91.53 390	87.81 422	80.96 416	98.23 403	98.99 333	71.05 415	90.13 410	96.51 407	48.45 423	96.88 407	90.51 394	85.30 406	96.76 402

h-mvs33		97.70 280	97.28 301	98.97 201	99.70 104	97.27 281	99.36 242	99.45 202	98.94 58	99.66 92	99.64 198	94.93 213	99.99 4	99.48 46	84.36 407	99.65 133

AUN-MVS		96.88 325	96.31 331	98.59 255	99.48 196	97.04 299	99.27 273	99.22 302	97.44 235	98.51 317	99.41 279	91.97 314	99.66 248	97.71 249	83.83 408	99.07 248

hse-mvs2		97.50 299	97.14 307	98.59 255	99.49 189	97.05 296	99.28 268	99.22 302	98.94 58	99.66 92	99.42 275	94.93 213	99.65 253	99.48 46	83.80 409	99.08 243

TDRefinement		95.42 351	94.57 358	97.97 321	89.83 421	96.11 342	99.48 188	98.75 366	96.74 293	96.68 377	99.88 39	88.65 364	99.71 231	98.37 187	82.74 410	98.09 376

PVSNet_0	94.43 19	96.09 342	95.47 349	97.94 324	99.31 244	94.34 379	97.81 408	99.70 15	97.12 264	97.46 359	98.75 370	89.71 350	99.79 199	97.69 252	81.69 411	99.68 123

KD-MVS_self_test		95.00 355	94.34 360	96.96 362	97.07 402	95.39 359	99.56 130	99.44 210	95.11 361	97.13 370	97.32 403	91.86 317	97.27 404	90.35 396	81.23 412	98.23 369

CL-MVSNet_self_test		94.49 360	93.97 364	96.08 374	96.16 405	93.67 387	98.33 398	99.38 238	95.13 359	97.33 364	98.15 390	92.69 296	96.57 408	88.67 401	79.87 413	97.99 385

PMMVS2		86.87 379	85.37 383	91.35 391	90.21 420	83.80 410	98.89 357	97.45 403	83.13 412	91.67 409	95.03 409	48.49 422	94.70 415	85.86 412	77.62 414	95.54 410

KD-MVS_2432*1600		94.62 358	93.72 366	97.31 352	97.19 400	95.82 346	98.34 396	99.20 306	95.00 365	97.57 357	98.35 383	87.95 373	98.10 390	92.87 384	77.00 415	98.01 381

miper_refine_blended		94.62 358	93.72 366	97.31 352	97.19 400	95.82 346	98.34 396	99.20 306	95.00 365	97.57 357	98.35 383	87.95 373	98.10 390	92.87 384	77.00 415	98.01 381

MVE	76.82 21	76.91 387	74.31 391	84.70 399	85.38 425	76.05 423	96.88 413	93.17 422	67.39 418	71.28 420	89.01 419	21.66 430	87.69 420	71.74 419	72.29 417	90.35 416
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 384	79.88 386	82.81 401	90.75 419	76.38 422	97.69 409	95.76 414	66.44 419	83.52 412	92.25 414	62.54 415	87.16 421	68.53 420	61.40 418	84.89 419

EMVS		80.02 385	79.22 387	82.43 403	91.19 418	76.40 421	97.55 412	92.49 426	66.36 420	83.01 414	91.27 416	64.63 414	85.79 422	65.82 421	60.65 419	85.08 418

ANet_high		77.30 386	74.86 390	84.62 400	75.88 426	77.61 420	97.63 411	93.15 424	88.81 406	64.27 421	89.29 418	36.51 425	83.93 423	75.89 417	52.31 420	92.33 414

tmp_tt		82.80 382	81.52 385	86.66 398	66.61 428	68.44 427	92.79 417	97.92 395	68.96 416	80.04 419	99.85 57	85.77 384	96.15 411	97.86 230	43.89 421	95.39 411

testmvs		39.17 390	43.78 392	25.37 407	36.04 430	16.84 432	98.36 394	26.56 429	20.06 423	38.51 424	67.32 420	29.64 427	15.30 426	37.59 424	39.90 422	43.98 421

test123		39.01 391	42.50 393	28.53 406	39.17 429	20.91 431	98.75 371	19.17 431	19.83 424	38.57 423	66.67 421	33.16 426	15.42 425	37.50 425	29.66 423	49.26 420

wuyk23d		40.18 389	41.29 394	36.84 405	86.18 424	49.12 430	79.73 418	22.81 430	27.64 422	25.46 425	28.45 425	21.98 428	48.89 424	55.80 423	23.56 424	12.51 422

mmdepth		0.02 396	0.03 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.02 396	0.03 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.13 395	0.17 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	1.57 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.02 396	0.03 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.02 396	0.03 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

cdsmvs_eth3d_5k		24.64 392	32.85 395	0.00 408	0.00 431	0.00 433	0.00 419	99.51 119	0.00 426	0.00 427	99.56 230	96.58 153	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		8.27 394	11.03 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	99.01 18	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.02 396	0.03 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.02 396	0.03 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.02 396	0.03 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.02 396	0.03 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		8.30 393	11.06 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	99.58 222	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.02 396	0.03 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.27 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						97.16 287								95.47 347

FOURS1					99.91 1	99.93 1	99.87 8	99.56 70	99.10 31	99.81 43

test_one_0601					99.81 46	99.88 8		99.49 149	98.97 55	99.65 99	99.81 95	99.09 14

eth-test2					0.00 431

eth-test					0.00 431

test_241102_ONE					99.84 32	99.90 2		99.48 161	99.07 39	99.91 17	99.74 147	99.20 7	99.76 210

save fliter					99.76 66	99.59 73	99.14 305	99.40 227	99.00 47

test0726					99.85 26	99.89 4	99.62 95	99.50 139	99.10 31	99.86 33	99.82 81	98.94 32

GSMVS																99.52 175

test_part2					99.81 46	99.83 19				99.77 58

sam_mvs1												94.86 218				99.52 175

sam_mvs												94.72 230

MTGPA								99.47 182

test_post1							99.23 288				65.14 423	94.18 256	99.71 231	97.58 258

test_post											65.99 422	94.65 236	99.73 221

patchmatchnet-post											98.70 371	94.79 222	99.74 215

MTMP							99.54 148	98.88 352

gm-plane-assit					98.54 375	92.96 392			94.65 373		99.15 333		99.64 256	97.56 263

TEST9					99.67 114	99.65 60	99.05 324	99.41 221	96.22 334	98.95 257	99.49 255	98.77 54	99.91 114

test_8					99.67 114	99.61 70	99.03 329	99.41 221	96.28 328	98.93 260	99.48 261	98.76 55	99.91 114

agg_prior					99.67 114	99.62 68		99.40 227		98.87 270			99.91 114

test_prior4						99.56 79	98.99 340

test_prior				99.68 71	99.67 114	99.48 94		99.56 70					99.83 177			99.74 95

旧先验2							98.96 347		96.70 296	99.47 142			99.94 72	98.19 202

新几何2							99.01 337

无先验							98.99 340	99.51 119	96.89 286				99.93 90	97.53 266		99.72 106

原ACMM2							98.95 350

testdata2													99.95 62	96.67 319

segment_acmp												98.96 25

testdata1							98.85 361		98.32 120

plane_prior7					99.29 249	97.03 300

plane_prior6					99.27 254	96.98 304						92.71 294

plane_prior4											99.61 213

plane_prior3						97.00 302			98.69 84	99.11 227

plane_prior2							99.39 230		98.97 55

plane_prior1					99.26 256

n2								0.00 432

nn								0.00 432

door-mid								98.05 394

test11								99.35 254

door								97.92 395

HQP5-MVS						96.83 312

HQP-NCC					99.19 274		98.98 343		98.24 129	98.66 298

ACMP_Plane					99.19 274		98.98 343		98.24 129	98.66 298

BP-MVS														97.19 291

HQP4-MVS										98.66 298			99.64 256			98.64 317

HQP2-MVS												92.47 303

NP-MVS					99.23 264	96.92 308					99.40 283

MDTV_nov1_ep13_2view						95.18 364	99.35 247		96.84 289	99.58 121		95.19 207		97.82 235		99.46 199

Test By Simon												98.75 58

High-resolution multi-view benchmark