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.

SD-MVS		99.41 38	99.52 6	99.05 162	99.74 71	99.68 48	99.46 167	99.52 89	99.11 15	99.88 11	99.91 11	99.43 1	97.70 359	98.72 114	99.93 12	99.77 68
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
TSAR-MVS + MP.		99.58 4	99.50 8	99.81 36	99.91 1	99.66 53	99.63 77	99.39 210	98.91 46	99.78 35	99.85 42	99.36 2	99.94 57	98.84 99	99.88 37	99.82 40
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PC_three_1452									98.18 115	99.84 18	99.70 142	99.31 3	98.52 342	98.30 167	99.80 83	99.81 47

SteuartSystems-ACMMP		99.54 8	99.42 15	99.87 11	99.82 37	99.81 25	99.59 96	99.51 103	98.62 67	99.79 30	99.83 56	99.28 4	99.97 14	98.48 149	99.90 25	99.84 26
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		99.59 3	99.50 8	99.88 5	99.51 156	99.88 8	99.87 9	99.51 103	98.99 33	99.88 11	99.81 76	99.27 5	99.96 22	98.85 96	99.80 83	99.81 47

OPU-MVS				99.64 64	99.56 144	99.72 42	99.60 90				99.70 142	99.27 5	99.42 249	98.24 169	99.80 83	99.79 60

SED-MVS		99.61 2	99.52 6	99.88 5	99.84 31	99.90 2	99.60 90	99.48 142	99.08 21	99.91 7	99.81 76	99.20 7	99.96 22	98.91 83	99.85 55	99.79 60

test_241102_ONE					99.84 31	99.90 2		99.48 142	99.07 23	99.91 7	99.74 127	99.20 7	99.76 177

MSLP-MVS++		99.46 23	99.47 12	99.44 112	99.60 134	99.16 111	99.41 186	99.71 13	98.98 36	99.45 118	99.78 106	99.19 9	99.54 234	99.28 47	99.84 63	99.63 123

SMA-MVS		99.44 29	99.30 40	99.85 25	99.73 78	99.83 16	99.56 114	99.47 160	97.45 195	99.78 35	99.82 63	99.18 10	99.91 90	98.79 107	99.89 34	99.81 47
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
APDe-MVS		99.66 1	99.57 3	99.92 1	99.77 53	99.89 4	99.75 39	99.56 57	99.02 26	99.88 11	99.85 42	99.18 10	99.96 22	99.22 53	99.92 13	99.90 4

HPM-MVS_fast		99.51 11	99.40 18	99.85 25	99.91 1	99.79 30	99.76 36	99.56 57	97.72 168	99.76 43	99.75 122	99.13 12	99.92 80	99.07 67	99.92 13	99.85 22

PGM-MVS		99.45 25	99.31 38	99.86 20	99.87 15	99.78 36	99.58 104	99.65 31	97.84 154	99.71 54	99.80 89	99.12 13	99.97 14	98.33 163	99.87 40	99.83 35

test_one_0601					99.81 41	99.88 8		99.49 130	98.97 39	99.65 75	99.81 76	99.09 14

test_0728_THIRD									98.99 33	99.81 25	99.80 89	99.09 14	99.96 22	98.85 96	99.90 25	99.88 12

HFP-MVS		99.49 14	99.37 22	99.86 20	99.87 15	99.80 27	99.66 65	99.67 22	98.15 117	99.68 60	99.69 152	99.06 16	99.96 22	98.69 119	99.87 40	99.84 26

TSAR-MVS + GP.		99.36 45	99.36 24	99.36 120	99.67 100	98.61 183	99.07 276	99.33 241	99.00 31	99.82 24	99.81 76	99.06 16	99.84 135	99.09 64	99.42 133	99.65 113

pcd_1.5k_mvsjas		8.27 348	11.03 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.27 381	99.01 18	0.00 381	0.00 379	0.00 379	0.00 377

PS-MVSNAJss		98.92 106	98.92 93	98.90 188	98.78 308	98.53 189	99.78 31	99.54 73	98.07 131	99.00 221	99.76 119	99.01 18	99.37 258	99.13 60	97.23 260	98.81 224

PS-MVSNAJ		99.32 49	99.32 32	99.30 133	99.57 140	98.94 151	98.97 303	99.46 169	98.92 45	99.71 54	99.24 294	99.01 18	99.98 8	99.35 35	99.66 114	98.97 215

EI-MVSNet-Vis-set		99.58 4	99.56 5	99.64 64	99.78 47	99.15 116	99.61 89	99.45 180	99.01 28	99.89 10	99.82 63	99.01 18	99.92 80	99.56 14	99.95 8	99.85 22

patch_mono-2		99.26 58	99.62 1	98.16 272	99.81 41	94.59 333	99.52 134	99.64 32	99.33 3	99.73 48	99.90 16	99.00 22	99.99 2	99.69 6	99.98 2	99.89 6

EI-MVSNet-UG-set		99.58 4	99.57 3	99.64 64	99.78 47	99.14 117	99.60 90	99.45 180	99.01 28	99.90 9	99.83 56	98.98 23	99.93 70	99.59 11	99.95 8	99.86 19

region2R		99.48 18	99.35 26	99.87 11	99.88 11	99.80 27	99.65 71	99.66 26	98.13 120	99.66 69	99.68 158	98.96 24	99.96 22	98.62 127	99.87 40	99.84 26

segment_acmp												98.96 24

CNVR-MVS		99.42 34	99.30 40	99.78 43	99.62 125	99.71 44	99.26 243	99.52 89	98.82 53	99.39 139	99.71 138	98.96 24	99.85 129	98.59 135	99.80 83	99.77 68

SF-MVS		99.38 43	99.24 53	99.79 41	99.79 45	99.68 48	99.57 108	99.54 73	97.82 159	99.71 54	99.80 89	98.95 27	99.93 70	98.19 172	99.84 63	99.74 78

ACMMPR		99.49 14	99.36 24	99.86 20	99.87 15	99.79 30	99.66 65	99.67 22	98.15 117	99.67 64	99.69 152	98.95 27	99.96 22	98.69 119	99.87 40	99.84 26

test_241102_TWO								99.48 142	99.08 21	99.88 11	99.81 76	98.94 29	99.96 22	98.91 83	99.84 63	99.88 12

DVP-MVS		99.57 7	99.47 12	99.88 5	99.85 25	99.89 4	99.57 108	99.37 224	99.10 16	99.81 25	99.80 89	98.94 29	99.96 22	98.93 80	99.86 48	99.81 47
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
test0726					99.85 25	99.89 4	99.62 83	99.50 122	99.10 16	99.86 16	99.82 63	98.94 29

xiu_mvs_v2_base		99.26 58	99.25 52	99.29 136	99.53 150	98.91 155	99.02 290	99.45 180	98.80 57	99.71 54	99.26 292	98.94 29	99.98 8	99.34 39	99.23 148	98.98 214

CP-MVS		99.45 25	99.32 32	99.85 25	99.83 35	99.75 39	99.69 51	99.52 89	98.07 131	99.53 105	99.63 182	98.93 33	99.97 14	98.74 111	99.91 18	99.83 35

ZNCC-MVS		99.47 21	99.33 30	99.87 11	99.87 15	99.81 25	99.64 73	99.67 22	98.08 130	99.55 102	99.64 176	98.91 34	99.96 22	98.72 114	99.90 25	99.82 40

MCST-MVS		99.43 32	99.30 40	99.82 33	99.79 45	99.74 41	99.29 228	99.40 207	98.79 58	99.52 107	99.62 187	98.91 34	99.90 101	98.64 125	99.75 98	99.82 40

HPM-MVS		99.42 34	99.28 46	99.83 32	99.90 4	99.72 42	99.81 20	99.54 73	97.59 179	99.68 60	99.63 182	98.91 34	99.94 57	98.58 136	99.91 18	99.84 26
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testdata				99.54 82	99.75 64	98.95 148		99.51 103	97.07 231	99.43 124	99.70 142	98.87 37	99.94 57	97.76 208	99.64 117	99.72 89

APD-MVS_3200maxsize		99.48 18	99.35 26	99.85 25	99.76 56	99.83 16	99.63 77	99.54 73	98.36 90	99.79 30	99.82 63	98.86 38	99.95 48	98.62 127	99.81 79	99.78 66

mvsany_test1		99.50 12	99.46 14	99.62 69	99.61 129	99.09 122	98.94 309	99.48 142	99.10 16	99.96 6	99.91 11	98.85 39	99.96 22	99.72 5	99.58 123	99.82 40

DeepC-MVS_fast	98.69 1	99.49 14	99.39 19	99.77 45	99.63 119	99.59 62	99.36 209	99.46 169	99.07 23	99.79 30	99.82 63	98.85 39	99.92 80	98.68 121	99.87 40	99.82 40
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
9.14			99.10 66		99.72 82		99.40 194	99.51 103	97.53 188	99.64 79	99.78 106	98.84 41	99.91 90	97.63 220	99.82 76

CDPH-MVS		99.13 75	98.91 95	99.80 38	99.75 64	99.71 44	99.15 261	99.41 199	96.60 266	99.60 90	99.55 210	98.83 42	99.90 101	97.48 236	99.83 72	99.78 66

ACMMP_NAP		99.47 21	99.34 28	99.88 5	99.87 15	99.86 13	99.47 164	99.48 142	98.05 136	99.76 43	99.86 37	98.82 43	99.93 70	98.82 106	99.91 18	99.84 26

XVS		99.53 9	99.42 15	99.87 11	99.85 25	99.83 16	99.69 51	99.68 19	98.98 36	99.37 144	99.74 127	98.81 44	99.94 57	98.79 107	99.86 48	99.84 26

X-MVStestdata		96.55 291	95.45 308	99.87 11	99.85 25	99.83 16	99.69 51	99.68 19	98.98 36	99.37 144	64.01 378	98.81 44	99.94 57	98.79 107	99.86 48	99.84 26

MP-MVS-pluss		99.37 44	99.20 57	99.88 5	99.90 4	99.87 12	99.30 224	99.52 89	97.18 219	99.60 90	99.79 100	98.79 46	99.95 48	98.83 102	99.91 18	99.83 35
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mPP-MVS		99.44 29	99.30 40	99.86 20	99.88 11	99.79 30	99.69 51	99.48 142	98.12 121	99.50 110	99.75 122	98.78 47	99.97 14	98.57 139	99.89 34	99.83 35

APD-MVS		99.27 56	99.08 69	99.84 31	99.75 64	99.79 30	99.50 145	99.50 122	97.16 221	99.77 38	99.82 63	98.78 47	99.94 57	97.56 229	99.86 48	99.80 56
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TAPA-MVS	97.07 15	97.74 244	97.34 263	98.94 178	99.70 92	97.53 244	99.25 245	99.51 103	91.90 350	99.30 160	99.63 182	98.78 47	99.64 220	88.09 362	99.87 40	99.65 113
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TEST9					99.67 100	99.65 56	99.05 281	99.41 199	96.22 293	98.95 227	99.49 231	98.77 50	99.91 90

train_agg		99.02 97	98.77 112	99.77 45	99.67 100	99.65 56	99.05 281	99.41 199	96.28 287	98.95 227	99.49 231	98.76 51	99.91 90	97.63 220	99.72 104	99.75 74

test_8					99.67 100	99.61 60	99.03 287	99.41 199	96.28 287	98.93 231	99.48 236	98.76 51	99.91 90

API-MVS		99.04 94	99.03 75	99.06 160	99.40 193	99.31 95	99.55 123	99.56 57	98.54 73	99.33 155	99.39 260	98.76 51	99.78 171	96.98 267	99.78 90	98.07 335

RE-MVS-def			99.34 28		99.76 56	99.82 22	99.63 77	99.52 89	98.38 86	99.76 43	99.82 63	98.75 54		98.61 130	99.81 79	99.77 68

DP-MVS Recon		99.12 81	98.95 91	99.65 59	99.74 71	99.70 46	99.27 235	99.57 52	96.40 283	99.42 127	99.68 158	98.75 54	99.80 163	97.98 189	99.72 104	99.44 170

Test By Simon												98.75 54

ACMMP		99.45 25	99.32 32	99.82 33	99.89 8	99.67 51	99.62 83	99.69 18	98.12 121	99.63 80	99.84 52	98.73 57	99.96 22	98.55 145	99.83 72	99.81 47
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
DPE-MVS		99.46 23	99.32 32	99.91 2	99.78 47	99.88 8	99.36 209	99.51 103	98.73 61	99.88 11	99.84 52	98.72 58	99.96 22	98.16 176	99.87 40	99.88 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
NCCC		99.34 47	99.19 58	99.79 41	99.61 129	99.65 56	99.30 224	99.48 142	98.86 48	99.21 182	99.63 182	98.72 58	99.90 101	98.25 168	99.63 119	99.80 56

DeepPCF-MVS	98.18 3	98.81 124	99.37 22	97.12 318	99.60 134	91.75 356	98.61 339	99.44 188	99.35 2	99.83 23	99.85 42	98.70 60	99.81 157	99.02 71	99.91 18	99.81 47

SR-MVS		99.43 32	99.29 44	99.86 20	99.75 64	99.83 16	99.59 96	99.62 33	98.21 108	99.73 48	99.79 100	98.68 61	99.96 22	98.44 154	99.77 93	99.79 60

test_prior2							98.96 304		98.34 92	99.01 217	99.52 222	98.68 61		97.96 190	99.74 101

DPM-MVS		98.95 104	98.71 117	99.66 55	99.63 119	99.55 68	98.64 338	99.10 289	97.93 145	99.42 127	99.55 210	98.67 63	99.80 163	95.80 302	99.68 112	99.61 127

原ACMM1				99.65 59	99.73 78	99.33 91		99.47 160	97.46 192	99.12 198	99.66 169	98.67 63	99.91 90	97.70 217	99.69 109	99.71 96

CS-MVS		99.50 12	99.48 10	99.54 82	99.76 56	99.42 85	99.90 1	99.55 65	98.56 71	99.78 35	99.70 142	98.65 65	99.79 166	99.65 9	99.78 90	99.41 174

HPM-MVS++		99.39 42	99.23 55	99.87 11	99.75 64	99.84 15	99.43 177	99.51 103	98.68 65	99.27 168	99.53 219	98.64 66	99.96 22	98.44 154	99.80 83	99.79 60

ZD-MVS					99.71 87	99.79 30		99.61 36	96.84 248	99.56 98	99.54 215	98.58 67	99.96 22	96.93 272	99.75 98

PHI-MVS		99.30 51	99.17 60	99.70 53	99.56 144	99.52 76	99.58 104	99.80 8	97.12 225	99.62 84	99.73 133	98.58 67	99.90 101	98.61 130	99.91 18	99.68 103

dcpmvs_2		99.23 63	99.58 2	98.16 272	99.83 35	94.68 332	99.76 36	99.52 89	99.07 23	99.98 4	99.88 26	98.56 69	99.93 70	99.67 8	99.98 2	99.87 17

CS-MVS-test		99.49 14	99.48 10	99.54 82	99.78 47	99.30 96	99.89 2	99.58 49	98.56 71	99.73 48	99.69 152	98.55 70	99.82 152	99.69 6	99.85 55	99.48 159

SR-MVS-dyc-post		99.45 25	99.31 38	99.85 25	99.76 56	99.82 22	99.63 77	99.52 89	98.38 86	99.76 43	99.82 63	98.53 71	99.95 48	98.61 130	99.81 79	99.77 68

GST-MVS		99.40 41	99.24 53	99.85 25	99.86 20	99.79 30	99.60 90	99.67 22	97.97 142	99.63 80	99.68 158	98.52 72	99.95 48	98.38 157	99.86 48	99.81 47

MVS_111021_LR		99.41 38	99.33 30	99.65 59	99.77 53	99.51 77	98.94 309	99.85 6	98.82 53	99.65 75	99.74 127	98.51 73	99.80 163	98.83 102	99.89 34	99.64 120

MVS_111021_HR		99.41 38	99.32 32	99.66 55	99.72 82	99.47 81	98.95 307	99.85 6	98.82 53	99.54 103	99.73 133	98.51 73	99.74 180	98.91 83	99.88 37	99.77 68

旧先验1					99.74 71	99.59 62		99.54 73			99.69 152	98.47 75			99.68 112	99.73 83

DELS-MVS		99.48 18	99.42 15	99.65 59	99.72 82	99.40 88	99.05 281	99.66 26	99.14 11	99.57 97	99.80 89	98.46 76	99.94 57	99.57 13	99.84 63	99.60 129
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
PAPR		98.63 144	98.34 154	99.51 98	99.40 193	99.03 131	98.80 323	99.36 225	96.33 284	99.00 221	99.12 309	98.46 76	99.84 135	95.23 315	99.37 142	99.66 109

MTAPA		99.52 10	99.39 19	99.89 4	99.90 4	99.86 13	99.66 65	99.47 160	98.79 58	99.68 60	99.81 76	98.43 78	99.97 14	98.88 86	99.90 25	99.83 35

新几何1				99.75 47	99.75 64	99.59 62		99.54 73	96.76 251	99.29 163	99.64 176	98.43 78	99.94 57	96.92 274	99.66 114	99.72 89

F-COLMAP		99.19 64	99.04 73	99.64 64	99.78 47	99.27 100	99.42 184	99.54 73	97.29 210	99.41 131	99.59 196	98.42 80	99.93 70	98.19 172	99.69 109	99.73 83

ETV-MVS		99.26 58	99.21 56	99.40 115	99.46 177	99.30 96	99.56 114	99.52 89	98.52 75	99.44 123	99.27 290	98.41 81	99.86 123	99.10 63	99.59 122	99.04 207

test12				99.75 47	99.64 116	99.61 60		99.29 263		99.21 182		98.38 82	99.89 111		99.74 101	99.74 78

CSCG		99.32 49	99.32 32	99.32 127	99.85 25	98.29 208	99.71 48	99.66 26	98.11 123	99.41 131	99.80 89	98.37 83	99.96 22	98.99 73	99.96 7	99.72 89

PAPM_NR		99.04 94	98.84 105	99.66 55	99.74 71	99.44 84	99.39 198	99.38 216	97.70 170	99.28 164	99.28 287	98.34 84	99.85 129	96.96 269	99.45 131	99.69 99

TAMVS		99.12 81	99.08 69	99.24 143	99.46 177	98.55 187	99.51 139	99.46 169	98.09 126	99.45 118	99.82 63	98.34 84	99.51 235	98.70 116	98.93 173	99.67 106

MP-MVS		99.33 48	99.15 61	99.87 11	99.88 11	99.82 22	99.66 65	99.46 169	98.09 126	99.48 114	99.74 127	98.29 86	99.96 22	97.93 192	99.87 40	99.82 40
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test222					99.75 64	99.49 78	98.91 313	99.49 130	96.42 281	99.34 154	99.65 170	98.28 87			99.69 109	99.72 89

PLC	97.94 4	99.02 97	98.85 104	99.53 90	99.66 108	99.01 134	99.24 247	99.52 89	96.85 247	99.27 168	99.48 236	98.25 88	99.91 90	97.76 208	99.62 120	99.65 113
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSP-MVS		99.42 34	99.27 48	99.88 5	99.89 8	99.80 27	99.67 60	99.50 122	98.70 63	99.77 38	99.49 231	98.21 89	99.95 48	98.46 153	99.77 93	99.88 12
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
DROMVSNet		99.44 29	99.39 19	99.58 75	99.56 144	99.49 78	99.88 4	99.58 49	98.38 86	99.73 48	99.69 152	98.20 90	99.70 202	99.64 10	99.82 76	99.54 142

xiu_mvs_v1_base_debu		99.29 53	99.27 48	99.34 121	99.63 119	98.97 139	99.12 266	99.51 103	98.86 48	99.84 18	99.47 239	98.18 91	99.99 2	99.50 20	99.31 143	99.08 200

xiu_mvs_v1_base		99.29 53	99.27 48	99.34 121	99.63 119	98.97 139	99.12 266	99.51 103	98.86 48	99.84 18	99.47 239	98.18 91	99.99 2	99.50 20	99.31 143	99.08 200

xiu_mvs_v1_base_debi		99.29 53	99.27 48	99.34 121	99.63 119	98.97 139	99.12 266	99.51 103	98.86 48	99.84 18	99.47 239	98.18 91	99.99 2	99.50 20	99.31 143	99.08 200

EIA-MVS		99.18 66	99.09 68	99.45 108	99.49 167	99.18 108	99.67 60	99.53 84	97.66 175	99.40 136	99.44 245	98.10 94	99.81 157	98.94 78	99.62 120	99.35 180

CNLPA		99.14 73	98.99 83	99.59 72	99.58 138	99.41 87	99.16 258	99.44 188	98.45 80	99.19 188	99.49 231	98.08 95	99.89 111	97.73 212	99.75 98	99.48 159

114514_t		98.93 105	98.67 121	99.72 52	99.85 25	99.53 73	99.62 83	99.59 44	92.65 348	99.71 54	99.78 106	98.06 96	99.90 101	98.84 99	99.91 18	99.74 78

CDS-MVSNet		99.09 89	99.03 75	99.25 141	99.42 185	98.73 172	99.45 168	99.46 169	98.11 123	99.46 117	99.77 113	98.01 97	99.37 258	98.70 116	98.92 175	99.66 109
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MG-MVS		99.13 75	99.02 78	99.45 108	99.57 140	98.63 180	99.07 276	99.34 234	98.99 33	99.61 87	99.82 63	97.98 98	99.87 120	97.00 265	99.80 83	99.85 22

EI-MVSNet		98.67 140	98.67 121	98.68 221	99.35 202	97.97 223	99.50 145	99.38 216	96.93 244	99.20 185	99.83 56	97.87 99	99.36 262	98.38 157	97.56 235	98.71 242

IterMVS-LS		98.46 151	98.42 149	98.58 228	99.59 136	98.00 221	99.37 205	99.43 194	96.94 243	99.07 208	99.59 196	97.87 99	99.03 315	98.32 165	95.62 296	98.71 242
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		98.98 101	98.80 108	99.53 90	99.76 56	99.19 106	98.75 328	99.55 65	97.25 213	99.47 115	99.77 113	97.82 101	99.87 120	96.93 272	99.90 25	99.54 142

OMC-MVS		99.08 90	99.04 73	99.20 147	99.67 100	98.22 211	99.28 230	99.52 89	98.07 131	99.66 69	99.81 76	97.79 102	99.78 171	97.79 204	99.81 79	99.60 129

LS3D		99.27 56	99.12 64	99.74 49	99.18 245	99.75 39	99.56 114	99.57 52	98.45 80	99.49 113	99.85 42	97.77 103	99.94 57	98.33 163	99.84 63	99.52 148

PVSNet_Blended_VisFu		99.36 45	99.28 46	99.61 70	99.86 20	99.07 127	99.47 164	99.93 2	97.66 175	99.71 54	99.86 37	97.73 104	99.96 22	99.47 27	99.82 76	99.79 60

1314		98.68 139	98.54 143	99.11 156	98.89 292	98.65 178	99.27 235	99.49 130	96.89 245	97.99 311	99.56 207	97.72 105	99.83 146	97.74 211	99.27 146	98.84 223

MVS_Test		99.10 88	98.97 87	99.48 102	99.49 167	99.14 117	99.67 60	99.34 234	97.31 208	99.58 94	99.76 119	97.65 106	99.82 152	98.87 89	99.07 164	99.46 167

PVSNet_BlendedMVS		98.86 113	98.80 108	99.03 164	99.76 56	98.79 169	99.28 230	99.91 3	97.42 200	99.67 64	99.37 264	97.53 107	99.88 116	98.98 74	97.29 258	98.42 316

PVSNet_Blended		99.08 90	98.97 87	99.42 113	99.76 56	98.79 169	98.78 325	99.91 3	96.74 252	99.67 64	99.49 231	97.53 107	99.88 116	98.98 74	99.85 55	99.60 129

UA-Net		99.42 34	99.29 44	99.80 38	99.62 125	99.55 68	99.50 145	99.70 15	98.79 58	99.77 38	99.96 1	97.45 109	99.96 22	98.92 82	99.90 25	99.89 6

MVSFormer		99.17 68	99.12 64	99.29 136	99.51 156	98.94 151	99.88 4	99.46 169	97.55 184	99.80 28	99.65 170	97.39 110	99.28 277	99.03 69	99.85 55	99.65 113

lupinMVS		99.13 75	99.01 82	99.46 107	99.51 156	98.94 151	99.05 281	99.16 283	97.86 150	99.80 28	99.56 207	97.39 110	99.86 123	98.94 78	99.85 55	99.58 137

DP-MVS		99.16 70	98.95 91	99.78 43	99.77 53	99.53 73	99.41 186	99.50 122	97.03 235	99.04 214	99.88 26	97.39 110	99.92 80	98.66 123	99.90 25	99.87 17

sss		99.17 68	99.05 71	99.53 90	99.62 125	98.97 139	99.36 209	99.62 33	97.83 155	99.67 64	99.65 170	97.37 113	99.95 48	99.19 55	99.19 151	99.68 103

mvs_anonymous		99.03 96	98.99 83	99.16 151	99.38 197	98.52 193	99.51 139	99.38 216	97.79 160	99.38 142	99.81 76	97.30 114	99.45 239	99.35 35	98.99 170	99.51 154

miper_ehance_all_eth		98.18 176	98.10 171	98.41 251	99.23 233	97.72 238	98.72 331	99.31 255	96.60 266	98.88 238	99.29 285	97.29 115	99.13 301	97.60 222	95.99 285	98.38 321

CPTT-MVS		99.11 85	98.90 96	99.74 49	99.80 44	99.46 82	99.59 96	99.49 130	97.03 235	99.63 80	99.69 152	97.27 116	99.96 22	97.82 202	99.84 63	99.81 47

PMMVS		98.80 127	98.62 132	99.34 121	99.27 225	98.70 174	98.76 327	99.31 255	97.34 205	99.21 182	99.07 311	97.20 117	99.82 152	98.56 142	98.87 178	99.52 148

EPP-MVSNet		99.13 75	98.99 83	99.53 90	99.65 114	99.06 128	99.81 20	99.33 241	97.43 198	99.60 90	99.88 26	97.14 118	99.84 135	99.13 60	98.94 172	99.69 99

mvsmamba		98.92 106	98.87 100	99.08 157	99.07 268	99.16 111	99.88 4	99.51 103	98.15 117	99.40 136	99.89 20	97.12 119	99.33 268	99.38 32	97.40 254	98.73 239

c3_l		98.12 183	98.04 180	98.38 255	99.30 216	97.69 242	98.81 322	99.33 241	96.67 257	98.83 246	99.34 273	97.11 120	98.99 321	97.58 224	95.34 302	98.48 307

canonicalmvs		99.02 97	98.86 103	99.51 98	99.42 185	99.32 92	99.80 24	99.48 142	98.63 66	99.31 158	98.81 331	97.09 121	99.75 179	99.27 50	97.90 222	99.47 165

MAR-MVS		98.86 113	98.63 127	99.54 82	99.37 199	99.66 53	99.45 168	99.54 73	96.61 264	99.01 217	99.40 256	97.09 121	99.86 123	97.68 219	99.53 127	99.10 195
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
miper_enhance_ethall		98.16 178	98.08 175	98.41 251	98.96 286	97.72 238	98.45 348	99.32 251	96.95 241	98.97 225	99.17 301	97.06 123	99.22 288	97.86 198	95.99 285	98.29 325

jason		99.13 75	99.03 75	99.45 108	99.46 177	98.87 158	99.12 266	99.26 268	98.03 139	99.79 30	99.65 170	97.02 124	99.85 129	99.02 71	99.90 25	99.65 113
jason: jason.
our_test_3		97.65 259	97.68 220	97.55 307	98.62 326	94.97 327	98.84 319	99.30 259	96.83 250	98.19 302	99.34 273	97.01 125	99.02 317	95.00 319	96.01 283	98.64 275

RRT_MVS		98.70 135	98.66 124	98.83 207	98.90 290	98.45 201	99.89 2	99.28 265	97.76 163	98.94 229	99.92 10	96.98 126	99.25 282	99.28 47	97.00 266	98.80 225

MVS		97.28 277	96.55 287	99.48 102	98.78 308	98.95 148	99.27 235	99.39 210	83.53 365	98.08 306	99.54 215	96.97 127	99.87 120	94.23 328	99.16 152	99.63 123

Fast-Effi-MVS+-dtu		98.77 130	98.83 107	98.60 224	99.41 188	96.99 271	99.52 134	99.49 130	98.11 123	99.24 174	99.34 273	96.96 128	99.79 166	97.95 191	99.45 131	99.02 210

1112_ss		98.98 101	98.77 112	99.59 72	99.68 99	99.02 132	99.25 245	99.48 142	97.23 216	99.13 196	99.58 200	96.93 129	99.90 101	98.87 89	98.78 186	99.84 26

WTY-MVS		99.06 92	98.88 99	99.61 70	99.62 125	99.16 111	99.37 205	99.56 57	98.04 137	99.53 105	99.62 187	96.84 130	99.94 57	98.85 96	98.49 199	99.72 89

FC-MVSNet-test		98.75 131	98.62 132	99.15 154	99.08 267	99.45 83	99.86 12	99.60 41	98.23 105	98.70 265	99.82 63	96.80 131	99.22 288	99.07 67	96.38 276	98.79 226

Effi-MVS+-dtu		98.78 128	98.89 98	98.47 244	99.33 208	96.91 277	99.57 108	99.30 259	98.47 78	99.41 131	98.99 320	96.78 132	99.74 180	98.73 113	99.38 135	98.74 237

Test_1112_low_res		98.89 108	98.66 124	99.57 77	99.69 95	98.95 148	99.03 287	99.47 160	96.98 237	99.15 194	99.23 295	96.77 133	99.89 111	98.83 102	98.78 186	99.86 19

FIs		98.78 128	98.63 127	99.23 145	99.18 245	99.54 70	99.83 16	99.59 44	98.28 97	98.79 252	99.81 76	96.75 134	99.37 258	99.08 66	96.38 276	98.78 227

PVSNet	96.02 17	98.85 120	98.84 105	98.89 191	99.73 78	97.28 250	98.32 355	99.60 41	97.86 150	99.50 110	99.57 204	96.75 134	99.86 123	98.56 142	99.70 108	99.54 142

nrg030		98.64 143	98.42 149	99.28 138	99.05 274	99.69 47	99.81 20	99.46 169	98.04 137	99.01 217	99.82 63	96.69 136	99.38 253	99.34 39	94.59 316	98.78 227

CHOSEN 280x420		99.12 81	99.13 63	99.08 157	99.66 108	97.89 230	98.43 349	99.71 13	98.88 47	99.62 84	99.76 119	96.63 137	99.70 202	99.46 28	99.99 1	99.66 109

eth_miper_zixun_eth		98.05 193	97.96 188	98.33 258	99.26 227	97.38 248	98.56 344	99.31 255	96.65 259	98.88 238	99.52 222	96.58 138	99.12 305	97.39 244	95.53 299	98.47 309

cdsmvs_eth3d_5k		24.64 346	32.85 349	0.00 362	0.00 385	0.00 386	0.00 373	99.51 103	0.00 380	0.00 381	99.56 207	96.58 138	0.00 381	0.00 379	0.00 379	0.00 377

IS-MVSNet		99.05 93	98.87 100	99.57 77	99.73 78	99.32 92	99.75 39	99.20 278	98.02 140	99.56 98	99.86 37	96.54 140	99.67 209	98.09 179	99.13 157	99.73 83

diffmvs		99.14 73	99.02 78	99.51 98	99.61 129	98.96 143	99.28 230	99.49 130	98.46 79	99.72 53	99.71 138	96.50 141	99.88 116	99.31 42	99.11 158	99.67 106
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CANet		99.25 61	99.14 62	99.59 72	99.41 188	99.16 111	99.35 214	99.57 52	98.82 53	99.51 109	99.61 191	96.46 142	99.95 48	99.59 11	99.98 2	99.65 113

ppachtmachnet_test		97.49 271	97.45 243	97.61 304	98.62 326	95.24 321	98.80 323	99.46 169	96.11 303	98.22 301	99.62 187	96.45 143	98.97 329	93.77 332	95.97 288	98.61 295

HY-MVS	97.30 7	98.85 120	98.64 126	99.47 105	99.42 185	99.08 125	99.62 83	99.36 225	97.39 203	99.28 164	99.68 158	96.44 144	99.92 80	98.37 159	98.22 208	99.40 176

UniMVSNet_NR-MVSNet		98.22 170	97.97 187	98.96 175	98.92 289	98.98 136	99.48 159	99.53 84	97.76 163	98.71 259	99.46 243	96.43 145	99.22 288	98.57 139	92.87 338	98.69 251

Effi-MVS+		98.81 124	98.59 139	99.48 102	99.46 177	99.12 120	98.08 361	99.50 122	97.50 191	99.38 142	99.41 253	96.37 146	99.81 157	99.11 62	98.54 196	99.51 154

AdaColmap		99.01 100	98.80 108	99.66 55	99.56 144	99.54 70	99.18 256	99.70 15	98.18 115	99.35 151	99.63 182	96.32 147	99.90 101	97.48 236	99.77 93	99.55 140

UniMVSNet (Re)		98.29 167	98.00 184	99.13 155	99.00 279	99.36 90	99.49 155	99.51 103	97.95 143	98.97 225	99.13 306	96.30 148	99.38 253	98.36 161	93.34 331	98.66 271

LCM-MVSNet-Re		97.83 228	98.15 165	96.87 325	99.30 216	92.25 354	99.59 96	98.26 347	97.43 198	96.20 341	99.13 306	96.27 149	98.73 340	98.17 175	98.99 170	99.64 120

PAPM		97.59 262	97.09 278	99.07 159	99.06 271	98.26 210	98.30 356	99.10 289	94.88 325	98.08 306	99.34 273	96.27 149	99.64 220	89.87 355	98.92 175	99.31 185

Fast-Effi-MVS+		98.70 135	98.43 148	99.51 98	99.51 156	99.28 98	99.52 134	99.47 160	96.11 303	99.01 217	99.34 273	96.20 151	99.84 135	97.88 195	98.82 183	99.39 177

EPNet_dtu		98.03 196	97.96 188	98.23 268	98.27 338	95.54 314	99.23 248	98.75 328	99.02 26	97.82 317	99.71 138	96.11 152	99.48 236	93.04 341	99.65 116	99.69 99
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline		99.15 71	99.02 78	99.53 90	99.66 108	99.14 117	99.72 46	99.48 142	98.35 91	99.42 127	99.84 52	96.07 153	99.79 166	99.51 19	99.14 156	99.67 106

D2MVS		98.41 156	98.50 145	98.15 275	99.26 227	96.62 287	99.40 194	99.61 36	97.71 169	98.98 223	99.36 267	96.04 154	99.67 209	98.70 116	97.41 253	98.15 332

casdiffmvs_mvg		99.15 71	99.02 78	99.55 81	99.66 108	99.09 122	99.64 73	99.56 57	98.26 100	99.45 118	99.87 32	96.03 155	99.81 157	99.54 15	99.15 155	99.73 83
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
miper_lstm_enhance		98.00 203	97.91 194	98.28 266	99.34 206	97.43 247	98.88 315	99.36 225	96.48 276	98.80 250	99.55 210	95.98 156	98.91 333	97.27 248	95.50 300	98.51 305

EPNet		98.86 113	98.71 117	99.30 133	97.20 356	98.18 212	99.62 83	98.91 313	99.28 6	98.63 276	99.81 76	95.96 157	99.99 2	99.24 52	99.72 104	99.73 83
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
AllTest		98.87 110	98.72 115	99.31 128	99.86 20	98.48 199	99.56 114	99.61 36	97.85 152	99.36 148	99.85 42	95.95 158	99.85 129	96.66 285	99.83 72	99.59 133

TestCases				99.31 128	99.86 20	98.48 199		99.61 36	97.85 152	99.36 148	99.85 42	95.95 158	99.85 129	96.66 285	99.83 72	99.59 133

3Dnovator	97.25 9	99.24 62	99.05 71	99.81 36	99.12 258	99.66 53	99.84 13	99.74 10	99.09 20	98.92 232	99.90 16	95.94 160	99.98 8	98.95 77	99.92 13	99.79 60

casdiffmvs		99.13 75	98.98 86	99.56 79	99.65 114	99.16 111	99.56 114	99.50 122	98.33 94	99.41 131	99.86 37	95.92 161	99.83 146	99.45 29	99.16 152	99.70 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
RPSCF		98.22 170	98.62 132	96.99 320	99.82 37	91.58 357	99.72 46	99.44 188	96.61 264	99.66 69	99.89 20	95.92 161	99.82 152	97.46 239	99.10 161	99.57 138

pmmvs4		98.13 181	97.90 195	98.81 210	98.61 328	98.87 158	98.99 297	99.21 277	96.44 279	99.06 212	99.58 200	95.90 163	99.11 306	97.18 257	96.11 282	98.46 313

HyFIR lowres test		99.11 85	98.92 93	99.65 59	99.90 4	99.37 89	99.02 290	99.91 3	97.67 174	99.59 93	99.75 122	95.90 163	99.73 186	99.53 16	99.02 169	99.86 19

COLMAP_ROB	97.56 6	98.86 113	98.75 114	99.17 150	99.88 11	98.53 189	99.34 217	99.59 44	97.55 184	98.70 265	99.89 20	95.83 165	99.90 101	98.10 178	99.90 25	99.08 200
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
DeepC-MVS	98.35 2	99.30 51	99.19 58	99.64 64	99.82 37	99.23 104	99.62 83	99.55 65	98.94 42	99.63 80	99.95 2	95.82 166	99.94 57	99.37 34	99.97 5	99.73 83
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
QAPM		98.67 140	98.30 158	99.80 38	99.20 240	99.67 51	99.77 33	99.72 11	94.74 328	98.73 257	99.90 16	95.78 167	99.98 8	96.96 269	99.88 37	99.76 73

BH-untuned		98.42 154	98.36 152	98.59 225	99.49 167	96.70 283	99.27 235	99.13 287	97.24 215	98.80 250	99.38 261	95.75 168	99.74 180	97.07 263	99.16 152	99.33 183

test_djsdf		98.67 140	98.57 141	98.98 172	98.70 319	98.91 155	99.88 4	99.46 169	97.55 184	99.22 179	99.88 26	95.73 169	99.28 277	99.03 69	97.62 230	98.75 234

DIV-MVS_self_test		98.01 201	97.85 201	98.48 240	99.24 232	97.95 227	98.71 332	99.35 230	96.50 271	98.60 281	99.54 215	95.72 170	99.03 315	97.21 251	95.77 291	98.46 313

bld_raw_dy_0_64		98.69 137	98.58 140	98.99 170	98.88 293	98.96 143	99.80 24	99.41 199	97.91 147	99.32 156	99.87 32	95.70 171	99.31 274	99.09 64	97.27 259	98.71 242

3Dnovator+	97.12 13	99.18 66	98.97 87	99.82 33	99.17 251	99.68 48	99.81 20	99.51 103	99.20 8	98.72 258	99.89 20	95.68 172	99.97 14	98.86 94	99.86 48	99.81 47

cl____		98.01 201	97.84 202	98.55 234	99.25 231	97.97 223	98.71 332	99.34 234	96.47 278	98.59 282	99.54 215	95.65 173	99.21 293	97.21 251	95.77 291	98.46 313

VNet		99.11 85	98.90 96	99.73 51	99.52 154	99.56 66	99.41 186	99.39 210	99.01 28	99.74 47	99.78 106	95.56 174	99.92 80	99.52 18	98.18 213	99.72 89

WR-MVS_H		98.13 181	97.87 200	98.90 188	99.02 277	98.84 162	99.70 49	99.59 44	97.27 211	98.40 292	99.19 300	95.53 175	99.23 285	98.34 162	93.78 328	98.61 295

CHOSEN 1792x2688		99.19 64	99.10 66	99.45 108	99.89 8	98.52 193	99.39 198	99.94 1	98.73 61	99.11 200	99.89 20	95.50 176	99.94 57	99.50 20	99.97 5	99.89 6

Vis-MVSNet (Re-imp)		98.87 110	98.72 115	99.31 128	99.71 87	98.88 157	99.80 24	99.44 188	97.91 147	99.36 148	99.78 106	95.49 177	99.43 248	97.91 193	99.11 158	99.62 125

PatchMatch-RL		98.84 123	98.62 132	99.52 96	99.71 87	99.28 98	99.06 279	99.77 9	97.74 167	99.50 110	99.53 219	95.41 178	99.84 135	97.17 258	99.64 117	99.44 170

FA-MVS(test-final)		98.75 131	98.53 144	99.41 114	99.55 148	99.05 130	99.80 24	99.01 300	96.59 268	99.58 94	99.59 196	95.39 179	99.90 101	97.78 205	99.49 129	99.28 187

test_yl		98.86 113	98.63 127	99.54 82	99.49 167	99.18 108	99.50 145	99.07 295	98.22 106	99.61 87	99.51 225	95.37 180	99.84 135	98.60 133	98.33 202	99.59 133

DCV-MVSNet		98.86 113	98.63 127	99.54 82	99.49 167	99.18 108	99.50 145	99.07 295	98.22 106	99.61 87	99.51 225	95.37 180	99.84 135	98.60 133	98.33 202	99.59 133

tpmrst		98.33 163	98.48 146	97.90 290	99.16 253	94.78 330	99.31 222	99.11 288	97.27 211	99.45 118	99.59 196	95.33 182	99.84 135	98.48 149	98.61 189	99.09 199

MVP-Stereo		97.81 233	97.75 214	97.99 285	97.53 349	96.60 289	98.96 304	98.85 320	97.22 217	97.23 328	99.36 267	95.28 183	99.46 238	95.51 309	99.78 90	97.92 347
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CANet_DTU		98.97 103	98.87 100	99.25 141	99.33 208	98.42 205	99.08 275	99.30 259	99.16 9	99.43 124	99.75 122	95.27 184	99.97 14	98.56 142	99.95 8	99.36 179

XVG-OURS		98.73 133	98.68 120	98.88 193	99.70 92	97.73 237	98.92 311	99.55 65	98.52 75	99.45 118	99.84 52	95.27 184	99.91 90	98.08 183	98.84 181	99.00 211

BH-w/o		98.00 203	97.89 199	98.32 260	99.35 202	96.20 301	99.01 295	98.90 315	96.42 281	98.38 293	99.00 319	95.26 186	99.72 190	96.06 296	98.61 189	99.03 208

EU-MVSNet		97.98 205	98.03 181	97.81 297	98.72 316	96.65 286	99.66 65	99.66 26	98.09 126	98.35 295	99.82 63	95.25 187	98.01 352	97.41 243	95.30 303	98.78 227

GeoE		98.85 120	98.62 132	99.53 90	99.61 129	99.08 125	99.80 24	99.51 103	97.10 229	99.31 158	99.78 106	95.23 188	99.77 173	98.21 170	99.03 167	99.75 74

MDTV_nov1_ep13_2view						95.18 324	99.35 214		96.84 248	99.58 94		95.19 189		97.82 202		99.46 167

JIA-IIPM		97.50 268	97.02 280	98.93 180	98.73 314	97.80 235	99.30 224	98.97 304	91.73 351	98.91 233	94.86 365	95.10 190	99.71 196	97.58 224	97.98 220	99.28 187

NR-MVSNet		97.97 208	97.61 227	99.02 165	98.87 297	99.26 101	99.47 164	99.42 196	97.63 177	97.08 333	99.50 228	95.07 191	99.13 301	97.86 198	93.59 329	98.68 256

tpmvs		97.98 205	98.02 183	97.84 293	99.04 275	94.73 331	99.31 222	99.20 278	96.10 307	98.76 255	99.42 249	94.94 192	99.81 157	96.97 268	98.45 200	98.97 215

h-mvs33		97.70 251	97.28 270	98.97 174	99.70 92	97.27 251	99.36 209	99.45 180	98.94 42	99.66 69	99.64 176	94.93 193	99.99 2	99.48 25	84.36 361	99.65 113

hse-mvs2		97.50 268	97.14 276	98.59 225	99.49 167	97.05 264	99.28 230	99.22 274	98.94 42	99.66 69	99.42 249	94.93 193	99.65 217	99.48 25	83.80 363	99.08 200

v8		97.95 210	97.63 226	98.93 180	98.95 287	98.81 168	99.80 24	99.41 199	96.03 308	99.10 203	99.42 249	94.92 195	99.30 275	96.94 271	94.08 325	98.66 271

PatchmatchNet		98.31 164	98.36 152	98.19 270	99.16 253	95.32 320	99.27 235	98.92 310	97.37 204	99.37 144	99.58 200	94.90 196	99.70 202	97.43 242	99.21 149	99.54 142
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v7n		97.87 220	97.52 234	98.92 182	98.76 312	98.58 185	99.84 13	99.46 169	96.20 294	98.91 233	99.70 142	94.89 197	99.44 244	96.03 297	93.89 327	98.75 234

sam_mvs1												94.86 198				99.52 148

iter_conf_final		98.71 134	98.61 138	98.99 170	99.49 167	98.96 143	99.63 77	99.41 199	98.19 111	99.39 139	99.77 113	94.82 199	99.38 253	99.30 45	97.52 238	98.64 275

DU-MVS		98.08 187	97.79 204	98.96 175	98.87 297	98.98 136	99.41 186	99.45 180	97.87 149	98.71 259	99.50 228	94.82 199	99.22 288	98.57 139	92.87 338	98.68 256

Baseline_NR-MVSNet		97.76 238	97.45 243	98.68 221	99.09 265	98.29 208	99.41 186	98.85 320	95.65 313	98.63 276	99.67 164	94.82 199	99.10 308	98.07 186	92.89 337	98.64 275

patchmatchnet-post											98.70 335	94.79 202	99.74 180

Patchmatch-RL test		95.84 305	95.81 303	95.95 334	95.61 364	90.57 359	98.24 357	98.39 346	95.10 322	95.20 348	98.67 336	94.78 203	97.77 357	96.28 294	90.02 352	99.51 154

alignmvs		98.81 124	98.56 142	99.58 75	99.43 183	99.42 85	99.51 139	98.96 306	98.61 68	99.35 151	98.92 328	94.78 203	99.77 173	99.35 35	98.11 218	99.54 142

MDTV_nov1_ep13			98.32 156		99.11 260	94.44 335	99.27 235	98.74 331	97.51 190	99.40 136	99.62 187	94.78 203	99.76 177	97.59 223	98.81 185

Vis-MVSNet		99.12 81	98.97 87	99.56 79	99.78 47	99.10 121	99.68 57	99.66 26	98.49 77	99.86 16	99.87 32	94.77 206	99.84 135	99.19 55	99.41 134	99.74 78
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
anonymousdsp		98.44 152	98.28 159	98.94 178	98.50 334	98.96 143	99.77 33	99.50 122	97.07 231	98.87 241	99.77 113	94.76 207	99.28 277	98.66 123	97.60 231	98.57 301

v10		97.85 223	97.52 234	98.86 201	98.99 280	98.67 176	99.75 39	99.41 199	95.70 312	98.98 223	99.41 253	94.75 208	99.23 285	96.01 298	94.63 315	98.67 263

OpenMVS	96.50 16	98.47 150	98.12 169	99.52 96	99.04 275	99.53 73	99.82 17	99.72 11	94.56 331	98.08 306	99.88 26	94.73 209	99.98 8	97.47 238	99.76 96	99.06 206

sam_mvs												94.72 210

v148		97.79 236	97.55 230	98.50 237	98.74 313	97.72 238	99.54 127	99.33 241	96.26 290	98.90 235	99.51 225	94.68 211	99.14 298	97.83 201	93.15 335	98.63 283

v1144		97.98 205	97.69 219	98.85 204	98.87 297	98.66 177	99.54 127	99.35 230	96.27 289	99.23 178	99.35 270	94.67 212	99.23 285	96.73 280	95.16 306	98.68 256

V42		98.06 188	97.79 204	98.86 201	98.98 283	98.84 162	99.69 51	99.34 234	96.53 270	99.30 160	99.37 264	94.67 212	99.32 271	97.57 228	94.66 314	98.42 316

test_post											65.99 376	94.65 214	99.73 186

baseline1		98.31 164	97.95 190	99.38 119	99.50 165	98.74 171	99.59 96	98.93 308	98.41 84	99.14 195	99.60 194	94.59 215	99.79 166	98.48 149	93.29 332	99.61 127

DSMNet-mixed		97.25 278	97.35 260	96.95 323	97.84 344	93.61 347	99.57 108	96.63 367	96.13 302	98.87 241	98.61 339	94.59 215	97.70 359	95.08 317	98.86 179	99.55 140

Patchmatch-test		97.93 211	97.65 223	98.77 215	99.18 245	97.07 262	99.03 287	99.14 286	96.16 298	98.74 256	99.57 204	94.56 217	99.72 190	93.36 337	99.11 158	99.52 148

PCF-MVS	97.08 14	97.66 258	97.06 279	99.47 105	99.61 129	99.09 122	98.04 362	99.25 270	91.24 353	98.51 285	99.70 142	94.55 218	99.91 90	92.76 345	99.85 55	99.42 172
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PatchT		97.03 284	96.44 290	98.79 213	98.99 280	98.34 207	99.16 258	99.07 295	92.13 349	99.52 107	97.31 358	94.54 219	98.98 322	88.54 360	98.73 188	99.03 208

CVMVSNet		98.57 146	98.67 121	98.30 262	99.35 202	95.59 311	99.50 145	99.55 65	98.60 69	99.39 139	99.83 56	94.48 220	99.45 239	98.75 110	98.56 195	99.85 22

test-LLR		98.06 188	97.90 195	98.55 234	98.79 305	97.10 258	98.67 334	97.75 356	97.34 205	98.61 279	98.85 329	94.45 221	99.45 239	97.25 249	99.38 135	99.10 195

test0.0.03 1		97.71 250	97.42 253	98.56 232	98.41 337	97.82 234	98.78 325	98.63 340	97.34 205	98.05 310	98.98 323	94.45 221	98.98 322	95.04 318	97.15 264	98.89 220

v144192		97.92 214	97.60 228	98.87 197	98.83 303	98.65 178	99.55 123	99.34 234	96.20 294	99.32 156	99.40 256	94.36 223	99.26 281	96.37 293	95.03 309	98.70 247

CR-MVSNet		98.17 177	97.93 193	98.87 197	99.18 245	98.49 197	99.22 252	99.33 241	96.96 239	99.56 98	99.38 261	94.33 224	99.00 320	94.83 321	98.58 192	99.14 192

Patchmtry		97.75 242	97.40 255	98.81 210	99.10 263	98.87 158	99.11 272	99.33 241	94.83 326	98.81 248	99.38 261	94.33 224	99.02 317	96.10 295	95.57 297	98.53 303

tpm cat1		97.39 274	97.36 258	97.50 309	99.17 251	93.73 343	99.43 177	99.31 255	91.27 352	98.71 259	99.08 310	94.31 226	99.77 173	96.41 292	98.50 198	99.00 211

TranMVSNet+NR-MVSNet		97.93 211	97.66 222	98.76 216	98.78 308	98.62 181	99.65 71	99.49 130	97.76 163	98.49 287	99.60 194	94.23 227	98.97 329	98.00 188	92.90 336	98.70 247

v2v482		98.06 188	97.77 209	98.92 182	98.90 290	98.82 166	99.57 108	99.36 225	96.65 259	99.19 188	99.35 270	94.20 228	99.25 282	97.72 214	94.97 310	98.69 251

XVG-OURS-SEG-HR		98.69 137	98.62 132	98.89 191	99.71 87	97.74 236	99.12 266	99.54 73	98.44 83	99.42 127	99.71 138	94.20 228	99.92 80	98.54 146	98.90 177	99.00 211

ab-mvs		98.86 113	98.63 127	99.54 82	99.64 116	99.19 106	99.44 173	99.54 73	97.77 162	99.30 160	99.81 76	94.20 228	99.93 70	99.17 58	98.82 183	99.49 158

test_post1							99.23 248				65.14 377	94.18 231	99.71 196	97.58 224

ADS-MVSNet2		98.02 198	98.07 178	97.87 291	99.33 208	95.19 323	99.23 248	99.08 292	96.24 291	99.10 203	99.67 164	94.11 232	98.93 332	96.81 277	99.05 165	99.48 159

ADS-MVSNet		98.20 173	98.08 175	98.56 232	99.33 208	96.48 292	99.23 248	99.15 284	96.24 291	99.10 203	99.67 164	94.11 232	99.71 196	96.81 277	99.05 165	99.48 159

RPMNet		96.72 289	95.90 300	99.19 148	99.18 245	98.49 197	99.22 252	99.52 89	88.72 361	99.56 98	97.38 355	94.08 234	99.95 48	86.87 366	98.58 192	99.14 192

v1192		97.81 233	97.44 248	98.91 186	98.88 293	98.68 175	99.51 139	99.34 234	96.18 296	99.20 185	99.34 273	94.03 235	99.36 262	95.32 314	95.18 305	98.69 251

v1921920		97.80 235	97.45 243	98.84 205	98.80 304	98.53 189	99.52 134	99.34 234	96.15 300	99.24 174	99.47 239	93.98 236	99.29 276	95.40 312	95.13 307	98.69 251

Anonymous20231206		96.22 297	96.03 297	96.79 327	97.31 354	94.14 339	99.63 77	99.08 292	96.17 297	97.04 334	99.06 313	93.94 237	97.76 358	86.96 365	95.06 308	98.47 309

WR-MVS		98.06 188	97.73 216	99.06 160	98.86 300	99.25 102	99.19 255	99.35 230	97.30 209	98.66 268	99.43 247	93.94 237	99.21 293	98.58 136	94.28 321	98.71 242

N_pmnet		94.95 315	95.83 302	92.31 344	98.47 335	79.33 372	99.12 266	92.81 379	93.87 336	97.68 320	99.13 306	93.87 239	99.01 319	91.38 350	96.19 280	98.59 299

MVSTER		98.49 148	98.32 156	99.00 168	99.35 202	99.02 132	99.54 127	99.38 216	97.41 201	99.20 185	99.73 133	93.86 240	99.36 262	98.87 89	97.56 235	98.62 286

FE-MVS		98.48 149	98.17 163	99.40 115	99.54 149	98.96 143	99.68 57	98.81 324	95.54 314	99.62 84	99.70 142	93.82 241	99.93 70	97.35 245	99.46 130	99.32 184

CP-MVSNet		98.09 185	97.78 207	99.01 166	98.97 285	99.24 103	99.67 60	99.46 169	97.25 213	98.48 288	99.64 176	93.79 242	99.06 311	98.63 126	94.10 324	98.74 237

cascas		97.69 252	97.43 252	98.48 240	98.60 329	97.30 249	98.18 360	99.39 210	92.96 346	98.41 291	98.78 333	93.77 243	99.27 280	98.16 176	98.61 189	98.86 221

v1240		97.69 252	97.32 266	98.79 213	98.85 301	98.43 203	99.48 159	99.36 225	96.11 303	99.27 168	99.36 267	93.76 244	99.24 284	94.46 324	95.23 304	98.70 247

test20.03		96.12 301	95.96 299	96.63 328	97.44 350	95.45 317	99.51 139	99.38 216	96.55 269	96.16 342	99.25 293	93.76 244	96.17 368	87.35 364	94.22 322	98.27 326

iter_conf05		98.55 147	98.44 147	98.87 197	99.34 206	98.60 184	99.55 123	99.42 196	98.21 108	99.37 144	99.77 113	93.55 246	99.38 253	99.30 45	97.48 246	98.63 283

baseline2		97.87 220	97.55 230	98.82 208	99.18 245	98.02 220	99.41 186	96.58 368	96.97 238	96.51 338	99.17 301	93.43 247	99.57 230	97.71 215	99.03 167	98.86 221

TransMVSNet (Re)		97.15 281	96.58 286	98.86 201	99.12 258	98.85 161	99.49 155	98.91 313	95.48 315	97.16 331	99.80 89	93.38 248	99.11 306	94.16 330	91.73 343	98.62 286

tfpnnormal		97.84 226	97.47 240	98.98 172	99.20 240	99.22 105	99.64 73	99.61 36	96.32 285	98.27 300	99.70 142	93.35 249	99.44 244	95.69 305	95.40 301	98.27 326

Anonymous20231211		97.88 218	97.54 233	98.90 188	99.71 87	98.53 189	99.48 159	99.57 52	94.16 334	98.81 248	99.68 158	93.23 250	99.42 249	98.84 99	94.42 319	98.76 232

XXY-MVS		98.38 160	98.09 174	99.24 143	99.26 227	99.32 92	99.56 114	99.55 65	97.45 195	98.71 259	99.83 56	93.23 250	99.63 225	98.88 86	96.32 278	98.76 232

jajsoiax		98.43 153	98.28 159	98.88 193	98.60 329	98.43 203	99.82 17	99.53 84	98.19 111	98.63 276	99.80 89	93.22 252	99.44 244	99.22 53	97.50 242	98.77 230

MDA-MVSNet_test_wron		95.45 309	94.60 315	98.01 282	98.16 340	97.21 256	99.11 272	99.24 272	93.49 341	80.73 371	98.98 323	93.02 253	98.18 347	94.22 329	94.45 318	98.64 275

ACMM	97.58 5	98.37 161	98.34 154	98.48 240	99.41 188	97.10 258	99.56 114	99.45 180	98.53 74	99.04 214	99.85 42	93.00 254	99.71 196	98.74 111	97.45 248	98.64 275
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet3		98.03 196	97.76 213	98.84 205	99.39 196	98.98 136	99.40 194	99.38 216	96.67 257	99.07 208	99.28 287	92.93 255	98.98 322	97.10 260	96.65 269	98.56 302

DTE-MVSNet		97.51 267	97.19 275	98.46 245	98.63 325	98.13 216	99.84 13	99.48 142	96.68 256	97.97 313	99.67 164	92.92 256	98.56 341	96.88 276	92.60 341	98.70 247

CLD-MVS		98.16 178	98.10 171	98.33 258	99.29 220	96.82 280	98.75 328	99.44 188	97.83 155	99.13 196	99.55 210	92.92 256	99.67 209	98.32 165	97.69 227	98.48 307
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
BH-RMVSNet		98.41 156	98.08 175	99.40 115	99.41 188	98.83 165	99.30 224	98.77 327	97.70 170	98.94 229	99.65 170	92.91 258	99.74 180	96.52 288	99.55 126	99.64 120

YYNet1		95.36 311	94.51 317	97.92 288	97.89 343	97.10 258	99.10 274	99.23 273	93.26 344	80.77 370	99.04 315	92.81 259	98.02 351	94.30 325	94.18 323	98.64 275

mvs_tets		98.40 159	98.23 161	98.91 186	98.67 322	98.51 195	99.66 65	99.53 84	98.19 111	98.65 274	99.81 76	92.75 260	99.44 244	99.31 42	97.48 246	98.77 230

IterMVS		97.83 228	97.77 209	98.02 281	99.58 138	96.27 299	99.02 290	99.48 142	97.22 217	98.71 259	99.70 142	92.75 260	99.13 301	97.46 239	96.00 284	98.67 263
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UGNet		98.87 110	98.69 119	99.40 115	99.22 236	98.72 173	99.44 173	99.68 19	99.24 7	99.18 191	99.42 249	92.74 262	99.96 22	99.34 39	99.94 11	99.53 147
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
IterMVS-SCA-FT		97.82 231	97.75 214	98.06 278	99.57 140	96.36 296	99.02 290	99.49 130	97.18 219	98.71 259	99.72 137	92.72 263	99.14 298	97.44 241	95.86 290	98.67 263

SCA		98.19 174	98.16 164	98.27 267	99.30 216	95.55 312	99.07 276	98.97 304	97.57 182	99.43 124	99.57 204	92.72 263	99.74 180	97.58 224	99.20 150	99.52 148

HQP_MVS		98.27 169	98.22 162	98.44 249	99.29 220	96.97 273	99.39 198	99.47 160	98.97 39	99.11 200	99.61 191	92.71 265	99.69 207	97.78 205	97.63 228	98.67 263

plane_prior6					99.27 225	96.98 272						92.71 265

CL-MVSNet_self_test		94.49 318	93.97 321	96.08 333	96.16 361	93.67 346	98.33 354	99.38 216	95.13 318	97.33 326	98.15 348	92.69 267	96.57 366	88.67 359	79.87 367	97.99 342

dp		97.75 242	97.80 203	97.59 305	99.10 263	93.71 344	99.32 220	98.88 317	96.48 276	99.08 207	99.55 210	92.67 268	99.82 152	96.52 288	98.58 192	99.24 189

PEN-MVS		97.76 238	97.44 248	98.72 218	98.77 311	98.54 188	99.78 31	99.51 103	97.06 233	98.29 299	99.64 176	92.63 269	98.89 335	98.09 179	93.16 334	98.72 240

LPG-MVS_test		98.22 170	98.13 168	98.49 238	99.33 208	97.05 264	99.58 104	99.55 65	97.46 192	99.24 174	99.83 56	92.58 270	99.72 190	98.09 179	97.51 240	98.68 256

LGP-MVS_train				98.49 238	99.33 208	97.05 264		99.55 65	97.46 192	99.24 174	99.83 56	92.58 270	99.72 190	98.09 179	97.51 240	98.68 256

VPA-MVSNet		98.29 167	97.95 190	99.30 133	99.16 253	99.54 70	99.50 145	99.58 49	98.27 99	99.35 151	99.37 264	92.53 272	99.65 217	99.35 35	94.46 317	98.72 240

TR-MVS		97.76 238	97.41 254	98.82 208	99.06 271	97.87 231	98.87 317	98.56 342	96.63 263	98.68 267	99.22 296	92.49 273	99.65 217	95.40 312	97.79 224	98.95 219

pm-mvs1		97.68 254	97.28 270	98.88 193	99.06 271	98.62 181	99.50 145	99.45 180	96.32 285	97.87 315	99.79 100	92.47 274	99.35 265	97.54 231	93.54 330	98.67 263

HQP2-MVS												92.47 274

HQP-MVS		98.02 198	97.90 195	98.37 256	99.19 242	96.83 278	98.98 300	99.39 210	98.24 102	98.66 268	99.40 256	92.47 274	99.64 220	97.19 255	97.58 233	98.64 275

EPMVS		97.82 231	97.65 223	98.35 257	98.88 293	95.98 304	99.49 155	94.71 374	97.57 182	99.26 172	99.48 236	92.46 277	99.71 196	97.87 197	99.08 163	99.35 180

PS-CasMVS		97.93 211	97.59 229	98.95 177	98.99 280	99.06 128	99.68 57	99.52 89	97.13 223	98.31 297	99.68 158	92.44 278	99.05 312	98.51 147	94.08 325	98.75 234

cl22		97.85 223	97.64 225	98.48 240	99.09 265	97.87 231	98.60 341	99.33 241	97.11 228	98.87 241	99.22 296	92.38 279	99.17 297	98.21 170	95.99 285	98.42 316

CostFormer		97.72 247	97.73 216	97.71 301	99.15 256	94.02 340	99.54 127	99.02 299	94.67 329	99.04 214	99.35 270	92.35 280	99.77 173	98.50 148	97.94 221	99.34 182

OPM-MVS		98.19 174	98.10 171	98.45 246	98.88 293	97.07 262	99.28 230	99.38 216	98.57 70	99.22 179	99.81 76	92.12 281	99.66 212	98.08 183	97.54 237	98.61 295
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ET-MVSNet_ETH3D		96.49 293	95.64 306	99.05 162	99.53 150	98.82 166	98.84 319	97.51 360	97.63 177	84.77 365	99.21 299	92.09 282	98.91 333	98.98 74	92.21 342	99.41 174

AUN-MVS		96.88 285	96.31 292	98.59 225	99.48 175	97.04 267	99.27 235	99.22 274	97.44 197	98.51 285	99.41 253	91.97 283	99.66 212	97.71 215	83.83 362	99.07 205

ACMP	97.20 11	98.06 188	97.94 192	98.45 246	99.37 199	97.01 269	99.44 173	99.49 130	97.54 187	98.45 289	99.79 100	91.95 284	99.72 190	97.91 193	97.49 245	98.62 286
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous202405211		98.30 166	97.98 186	99.26 140	99.57 140	98.16 213	99.41 186	98.55 343	96.03 308	99.19 188	99.74 127	91.87 285	99.92 80	99.16 59	98.29 207	99.70 97

KD-MVS_self_test		95.00 313	94.34 318	96.96 322	97.07 359	95.39 319	99.56 114	99.44 188	95.11 320	97.13 332	97.32 357	91.86 286	97.27 362	90.35 354	81.23 366	98.23 330

tpm		97.67 257	97.55 230	98.03 279	99.02 277	95.01 326	99.43 177	98.54 344	96.44 279	99.12 198	99.34 273	91.83 287	99.60 228	97.75 210	96.46 274	99.48 159

thres100view900		97.76 238	97.45 243	98.69 220	99.72 82	97.86 233	99.59 96	98.74 331	97.93 145	99.26 172	98.62 337	91.75 288	99.83 146	93.22 338	98.18 213	98.37 322

thres600view7		97.86 222	97.51 236	98.92 182	99.72 82	97.95 227	99.59 96	98.74 331	97.94 144	99.27 168	98.62 337	91.75 288	99.86 123	93.73 333	98.19 212	98.96 217

LTVRE_ROB	97.16 12	98.02 198	97.90 195	98.40 253	99.23 233	96.80 281	99.70 49	99.60 41	97.12 225	98.18 303	99.70 142	91.73 290	99.72 190	98.39 156	97.45 248	98.68 256
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
OurMVSNet-221017-0		97.88 218	97.77 209	98.19 270	98.71 318	96.53 290	99.88 4	99.00 301	97.79 160	98.78 253	99.94 4	91.68 291	99.35 265	97.21 251	96.99 267	98.69 251

tfpn200view9		97.72 247	97.38 256	98.72 218	99.69 95	97.96 225	99.50 145	98.73 336	97.83 155	99.17 192	98.45 342	91.67 292	99.83 146	93.22 338	98.18 213	98.37 322

thres400		97.77 237	97.38 256	98.92 182	99.69 95	97.96 225	99.50 145	98.73 336	97.83 155	99.17 192	98.45 342	91.67 292	99.83 146	93.22 338	98.18 213	98.96 217

thisisatest0515		98.14 180	97.79 204	99.19 148	99.50 165	98.50 196	98.61 339	96.82 364	96.95 241	99.54 103	99.43 247	91.66 294	99.86 123	98.08 183	99.51 128	99.22 190

thres200		97.61 261	97.28 270	98.62 223	99.64 116	98.03 219	99.26 243	98.74 331	97.68 172	99.09 206	98.32 346	91.66 294	99.81 157	92.88 342	98.22 208	98.03 338

new_pmnet		96.38 296	96.03 297	97.41 310	98.13 341	95.16 325	99.05 281	99.20 278	93.94 335	97.39 325	98.79 332	91.61 296	99.04 313	90.43 353	95.77 291	98.05 337

pmmvs5		97.52 265	97.30 268	98.16 272	98.57 331	96.73 282	99.27 235	98.90 315	96.14 301	98.37 294	99.53 219	91.54 297	99.14 298	97.51 233	95.87 289	98.63 283

test_fmvs1		98.88 109	98.79 111	99.16 151	99.69 95	97.61 243	99.55 123	99.49 130	99.32 4	99.98 4	99.91 11	91.41 298	99.96 22	99.82 3	99.92 13	99.90 4

tttt0517		98.42 154	98.14 166	99.28 138	99.66 108	98.38 206	99.74 42	96.85 363	97.68 172	99.79 30	99.74 127	91.39 299	99.89 111	98.83 102	99.56 124	99.57 138

tpm2		97.44 273	97.34 263	97.74 300	99.15 256	94.36 337	99.45 168	98.94 307	93.45 343	98.90 235	99.44 245	91.35 300	99.59 229	97.31 246	98.07 219	99.29 186

MVS-HIRNet		95.75 307	95.16 311	97.51 308	99.30 216	93.69 345	98.88 315	95.78 369	85.09 364	98.78 253	92.65 367	91.29 301	99.37 258	94.85 320	99.85 55	99.46 167

thisisatest0530		98.35 162	98.03 181	99.31 128	99.63 119	98.56 186	99.54 127	96.75 365	97.53 188	99.73 48	99.65 170	91.25 302	99.89 111	98.62 127	99.56 124	99.48 159

testgi		97.65 259	97.50 237	98.13 276	99.36 201	96.45 293	99.42 184	99.48 142	97.76 163	97.87 315	99.45 244	91.09 303	98.81 336	94.53 323	98.52 197	99.13 194

ITE_SJBPF				98.08 277	99.29 220	96.37 295		98.92 310	98.34 92	98.83 246	99.75 122	91.09 303	99.62 226	95.82 300	97.40 254	98.25 328

DeepMVS_CX				93.34 341	99.29 220	82.27 368		99.22 274	85.15 363	96.33 340	99.05 314	90.97 305	99.73 186	93.57 335	97.77 225	98.01 339

ACMH	97.28 8	98.10 184	97.99 185	98.44 249	99.41 188	96.96 275	99.60 90	99.56 57	98.09 126	98.15 304	99.91 11	90.87 306	99.70 202	98.88 86	97.45 248	98.67 263
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test1111		98.04 194	98.11 170	97.83 294	99.74 71	93.82 341	99.58 104	95.40 371	99.12 14	99.65 75	99.93 6	90.73 307	99.84 135	99.43 30	99.38 135	99.82 40

ECVR-MVS		98.04 194	98.05 179	98.00 284	99.74 71	94.37 336	99.59 96	94.98 372	99.13 12	99.66 69	99.93 6	90.67 308	99.84 135	99.40 31	99.38 135	99.80 56

SixPastTwentyTwo		97.50 268	97.33 265	98.03 279	98.65 323	96.23 300	99.77 33	98.68 339	97.14 222	97.90 314	99.93 6	90.45 309	99.18 296	97.00 265	96.43 275	98.67 263

MIMVSNet		97.73 245	97.45 243	98.57 229	99.45 182	97.50 245	99.02 290	98.98 303	96.11 303	99.41 131	99.14 305	90.28 310	98.74 339	95.74 303	98.93 173	99.47 165

GBi-Net		97.68 254	97.48 238	98.29 263	99.51 156	97.26 253	99.43 177	99.48 142	96.49 272	99.07 208	99.32 280	90.26 311	98.98 322	97.10 260	96.65 269	98.62 286

test1		97.68 254	97.48 238	98.29 263	99.51 156	97.26 253	99.43 177	99.48 142	96.49 272	99.07 208	99.32 280	90.26 311	98.98 322	97.10 260	96.65 269	98.62 286

FMVSNet2		97.72 247	97.36 258	98.80 212	99.51 156	98.84 162	99.45 168	99.42 196	96.49 272	98.86 245	99.29 285	90.26 311	98.98 322	96.44 290	96.56 272	98.58 300

Anonymous20240529		98.09 185	97.68 220	99.34 121	99.66 108	98.44 202	99.40 194	99.43 194	93.67 338	99.22 179	99.89 20	90.23 314	99.93 70	99.26 51	98.33 202	99.66 109

ACMH+	97.24 10	97.92 214	97.78 207	98.32 260	99.46 177	96.68 285	99.56 114	99.54 73	98.41 84	97.79 319	99.87 32	90.18 315	99.66 212	98.05 187	97.18 263	98.62 286

LF4IMVS		97.52 265	97.46 242	97.70 302	98.98 283	95.55 312	99.29 228	98.82 323	98.07 131	98.66 268	99.64 176	89.97 316	99.61 227	97.01 264	96.68 268	97.94 345

GA-MVS		97.85 223	97.47 240	99.00 168	99.38 197	97.99 222	98.57 342	99.15 284	97.04 234	98.90 235	99.30 283	89.83 317	99.38 253	96.70 282	98.33 202	99.62 125

PVSNet_0	94.43 19	96.09 302	95.47 307	97.94 287	99.31 215	94.34 338	97.81 363	99.70 15	97.12 225	97.46 323	98.75 334	89.71 318	99.79 166	97.69 218	81.69 365	99.68 103

Anonymous20240521		96.20 299	95.89 301	97.13 317	97.72 348	94.96 328	99.79 30	99.29 263	93.01 345	97.20 330	99.03 316	89.69 319	98.36 345	91.16 351	96.13 281	98.07 335

XVG-ACMP-BASELINE		97.83 228	97.71 218	98.20 269	99.11 260	96.33 297	99.41 186	99.52 89	98.06 135	99.05 213	99.50 228	89.64 320	99.73 186	97.73 212	97.38 256	98.53 303

gg-mvs-nofinetune		96.17 300	95.32 310	98.73 217	98.79 305	98.14 215	99.38 203	94.09 375	91.07 355	98.07 309	91.04 371	89.62 321	99.35 265	96.75 279	99.09 162	98.68 256

GG-mvs-BLEND				98.45 246	98.55 332	98.16 213	99.43 177	93.68 376		97.23 328	98.46 341	89.30 322	99.22 288	95.43 311	98.22 208	97.98 343

USDC		97.34 275	97.20 274	97.75 299	99.07 268	95.20 322	98.51 346	99.04 298	97.99 141	98.31 297	99.86 37	89.02 323	99.55 233	95.67 307	97.36 257	98.49 306

MS-PatchMatch		97.24 280	97.32 266	96.99 320	98.45 336	93.51 348	98.82 321	99.32 251	97.41 201	98.13 305	99.30 283	88.99 324	99.56 231	95.68 306	99.80 83	97.90 348

VPNet		97.84 226	97.44 248	99.01 166	99.21 238	98.94 151	99.48 159	99.57 52	98.38 86	99.28 164	99.73 133	88.89 325	99.39 251	99.19 55	93.27 333	98.71 242

K. test v3		97.10 283	96.79 284	98.01 282	98.72 316	96.33 297	99.87 9	97.05 362	97.59 179	96.16 342	99.80 89	88.71 326	99.04 313	96.69 283	96.55 273	98.65 273

lessismore_v0				97.79 298	98.69 320	95.44 318		94.75 373		95.71 346	99.87 32	88.69 327	99.32 271	95.89 299	94.93 312	98.62 286

tt0805		97.97 208	97.77 209	98.57 229	99.59 136	96.61 288	99.45 168	99.08 292	98.21 108	98.88 238	99.80 89	88.66 328	99.70 202	98.58 136	97.72 226	99.39 177

TDRefinement		95.42 310	94.57 316	97.97 286	89.83 375	96.11 303	99.48 159	98.75 328	96.74 252	96.68 337	99.88 26	88.65 329	99.71 196	98.37 159	82.74 364	98.09 334

TESTMET0.1,1		97.55 263	97.27 273	98.40 253	98.93 288	96.53 290	98.67 334	97.61 359	96.96 239	98.64 275	99.28 287	88.63 330	99.45 239	97.30 247	99.38 135	99.21 191

test_0402		96.64 290	96.24 293	97.85 292	98.85 301	96.43 294	99.44 173	99.26 268	93.52 340	96.98 335	99.52 222	88.52 331	99.20 295	92.58 347	97.50 242	97.93 346

UnsupCasMVSNet_eth		96.44 294	96.12 295	97.40 311	98.65 323	95.65 309	99.36 209	99.51 103	97.13 223	96.04 344	98.99 320	88.40 332	98.17 348	96.71 281	90.27 351	98.40 319

MDA-MVSNet-bldmvs		94.96 314	93.98 320	97.92 288	98.24 339	97.27 251	99.15 261	99.33 241	93.80 337	80.09 372	99.03 316	88.31 333	97.86 356	93.49 336	94.36 320	98.62 286

test-mter		97.49 271	97.13 277	98.55 234	98.79 305	97.10 258	98.67 334	97.75 356	96.65 259	98.61 279	98.85 329	88.23 334	99.45 239	97.25 249	99.38 135	99.10 195

TinyColmap		97.12 282	96.89 282	97.83 294	99.07 268	95.52 315	98.57 342	98.74 331	97.58 181	97.81 318	99.79 100	88.16 335	99.56 231	95.10 316	97.21 261	98.39 320

pmmvs-eth3d		95.34 312	94.73 314	97.15 315	95.53 366	95.94 305	99.35 214	99.10 289	95.13 318	93.55 356	97.54 353	88.15 336	97.91 354	94.58 322	89.69 354	97.61 352

KD-MVS_2432*1600		94.62 316	93.72 322	97.31 312	97.19 357	95.82 307	98.34 352	99.20 278	95.00 323	97.57 321	98.35 344	87.95 337	98.10 349	92.87 343	77.00 369	98.01 339

miper_refine_blended		94.62 316	93.72 322	97.31 312	97.19 357	95.82 307	98.34 352	99.20 278	95.00 323	97.57 321	98.35 344	87.95 337	98.10 349	92.87 343	77.00 369	98.01 339

new-patchmatchnet		94.48 319	94.08 319	95.67 335	95.08 368	92.41 353	99.18 256	99.28 265	94.55 332	93.49 357	97.37 356	87.86 339	97.01 364	91.57 349	88.36 355	97.61 352

test2506		96.81 287	96.65 285	97.29 314	99.74 71	92.21 355	99.60 90	85.06 382	99.13 12	99.77 38	99.93 6	87.82 340	99.85 129	99.38 32	99.38 135	99.80 56

FMVSNet5		96.43 295	96.19 294	97.15 315	99.11 260	95.89 306	99.32 220	99.52 89	94.47 333	98.34 296	99.07 311	87.54 341	97.07 363	92.61 346	95.72 294	98.47 309

test_vis1_n_1920		98.63 144	98.40 151	99.31 128	99.86 20	97.94 229	99.67 60	99.62 33	99.43 1	99.99 2	99.91 11	87.29 342	100.00 1	99.92 1	99.92 13	99.98 1

pmmvs6		96.53 292	96.09 296	97.82 296	98.69 320	95.47 316	99.37 205	99.47 160	93.46 342	97.41 324	99.78 106	87.06 343	99.33 268	96.92 274	92.70 340	98.65 273

pmmvs3		94.09 322	93.25 326	96.60 329	94.76 369	94.49 334	98.92 311	98.18 352	89.66 356	96.48 339	98.06 350	86.28 344	97.33 361	89.68 356	87.20 358	97.97 344

IB-MVS	95.67 18	96.22 297	95.44 309	98.57 229	99.21 238	96.70 283	98.65 337	97.74 358	96.71 254	97.27 327	98.54 340	86.03 345	99.92 80	98.47 152	86.30 359	99.10 195
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
tmp_tt		82.80 336	81.52 339	86.66 352	66.61 382	68.44 380	92.79 371	97.92 354	68.96 370	80.04 373	99.85 42	85.77 346	96.15 369	97.86 198	43.89 375	95.39 365

CMPMVS	69.68 23	94.13 321	94.90 313	91.84 345	97.24 355	80.01 371	98.52 345	99.48 142	89.01 359	91.99 360	99.67 164	85.67 347	99.13 301	95.44 310	97.03 265	96.39 361
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
APD_test1		95.87 304	96.49 289	94.00 338	99.53 150	84.01 365	99.54 127	99.32 251	95.91 310	97.99 311	99.85 42	85.49 348	99.88 116	91.96 348	98.84 181	98.12 333

test_fmvs1_n		98.41 156	98.14 166	99.21 146	99.82 37	97.71 241	99.74 42	99.49 130	99.32 4	99.99 2	99.95 2	85.32 349	99.97 14	99.82 3	99.84 63	99.96 3

MIMVSNet1		95.51 308	95.04 312	96.92 324	97.38 351	95.60 310	99.52 134	99.50 122	93.65 339	96.97 336	99.17 301	85.28 350	96.56 367	88.36 361	95.55 298	98.60 298

LFMVS		97.90 217	97.35 260	99.54 82	99.52 154	99.01 134	99.39 198	98.24 349	97.10 229	99.65 75	99.79 100	84.79 351	99.91 90	99.28 47	98.38 201	99.69 99

test_fmvs2		97.25 278	97.30 268	97.09 319	99.43 183	93.31 349	99.73 45	98.87 319	98.83 52	99.28 164	99.80 89	84.45 352	99.66 212	97.88 195	97.45 248	98.30 324

EGC-MVSNET		82.80 336	77.86 342	97.62 303	97.91 342	96.12 302	99.33 219	99.28 265	8.40 379	25.05 380	99.27 290	84.11 353	99.33 268	89.20 357	98.22 208	97.42 356

FMVSNet1		96.84 286	96.36 291	98.29 263	99.32 214	97.26 253	99.43 177	99.48 142	95.11 320	98.55 283	99.32 280	83.95 354	98.98 322	95.81 301	96.26 279	98.62 286

VDD-MVS		97.73 245	97.35 260	98.88 193	99.47 176	97.12 257	99.34 217	98.85 320	98.19 111	99.67 64	99.85 42	82.98 355	99.92 80	99.49 24	98.32 206	99.60 129

EG-PatchMatch MVS		95.97 303	95.69 304	96.81 326	97.78 345	92.79 352	99.16 258	98.93 308	96.16 298	94.08 354	99.22 296	82.72 356	99.47 237	95.67 307	97.50 242	98.17 331

VDDNet		97.55 263	97.02 280	99.16 151	99.49 167	98.12 217	99.38 203	99.30 259	95.35 316	99.68 60	99.90 16	82.62 357	99.93 70	99.31 42	98.13 217	99.42 172

UniMVSNet_ETH3D		97.32 276	96.81 283	98.87 197	99.40 193	97.46 246	99.51 139	99.53 84	95.86 311	98.54 284	99.77 113	82.44 358	99.66 212	98.68 121	97.52 238	99.50 157

OpenMVS_ROB	92.34 20	94.38 320	93.70 324	96.41 331	97.38 351	93.17 350	99.06 279	98.75 328	86.58 362	94.84 352	98.26 347	81.53 359	99.32 271	89.01 358	97.87 223	96.76 359

test_method		91.10 328	91.36 330	90.31 349	95.85 362	73.72 379	94.89 368	99.25 270	68.39 371	95.82 345	99.02 318	80.50 360	98.95 331	93.64 334	94.89 313	98.25 328

MVS_0304		96.79 288	96.52 288	97.59 305	99.22 236	94.92 329	99.04 286	99.59 44	96.49 272	98.43 290	98.99 320	80.48 361	99.39 251	97.15 259	99.27 146	98.47 309

test_vis1_n		97.92 214	97.44 248	99.34 121	99.53 150	98.08 218	99.74 42	99.49 130	99.15 10	100.00 1	99.94 4	79.51 362	99.98 8	99.88 2	99.76 96	99.97 2

test_vis1_rt		95.81 306	95.65 305	96.32 332	99.67 100	91.35 358	99.49 155	96.74 366	98.25 101	95.24 347	98.10 349	74.96 363	99.90 101	99.53 16	98.85 180	97.70 351

UnsupCasMVSNet_bld		93.53 324	92.51 327	96.58 330	97.38 351	93.82 341	98.24 357	99.48 142	91.10 354	93.10 358	96.66 360	74.89 364	98.37 344	94.03 331	87.71 357	97.56 354

Gipuma		90.99 329	90.15 334	93.51 340	98.73 314	90.12 360	93.98 369	99.45 180	79.32 367	92.28 359	94.91 364	69.61 365	97.98 353	87.42 363	95.67 295	92.45 367
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
mvsany_test3		93.77 323	93.45 325	94.74 337	95.78 363	88.01 362	99.64 73	98.25 348	98.28 97	94.31 353	97.97 351	68.89 366	98.51 343	97.50 234	90.37 350	97.71 349

PM-MVS		92.96 325	92.23 328	95.14 336	95.61 364	89.98 361	99.37 205	98.21 350	94.80 327	95.04 351	97.69 352	65.06 367	97.90 355	94.30 325	89.98 353	97.54 355

EMVS		80.02 339	79.22 341	82.43 357	91.19 372	76.40 374	97.55 366	92.49 380	66.36 374	83.01 368	91.27 370	64.63 368	85.79 376	65.82 375	60.65 373	85.08 372

E-PMN		80.61 338	79.88 340	82.81 355	90.75 373	76.38 375	97.69 364	95.76 370	66.44 373	83.52 366	92.25 368	62.54 369	87.16 375	68.53 374	61.40 372	84.89 373

testf1		90.42 330	90.68 332	89.65 350	97.78 345	73.97 377	99.13 264	98.81 324	89.62 357	91.80 361	98.93 326	62.23 370	98.80 337	86.61 367	91.17 345	96.19 362

APD_test2		90.42 330	90.68 332	89.65 350	97.78 345	73.97 377	99.13 264	98.81 324	89.62 357	91.80 361	98.93 326	62.23 370	98.80 337	86.61 367	91.17 345	96.19 362

ambc				93.06 343	92.68 371	82.36 367	98.47 347	98.73 336		95.09 350	97.41 354	55.55 372	99.10 308	96.42 291	91.32 344	97.71 349

test_f		91.90 327	91.26 331	93.84 339	95.52 367	85.92 364	99.69 51	98.53 345	95.31 317	93.87 355	96.37 362	55.33 373	98.27 346	95.70 304	90.98 348	97.32 357

test_fmvs3		92.10 326	91.77 329	93.08 342	96.19 360	86.25 363	99.82 17	98.62 341	96.65 259	95.19 349	96.90 359	55.05 374	95.93 370	96.63 287	90.92 349	97.06 358

FPMVS		84.93 335	85.65 336	82.75 356	86.77 377	63.39 381	98.35 351	98.92 310	74.11 368	83.39 367	98.98 323	50.85 375	92.40 373	84.54 370	94.97 310	92.46 366

PMMVS2		86.87 333	85.37 337	91.35 347	90.21 374	83.80 366	98.89 314	97.45 361	83.13 366	91.67 363	95.03 363	48.49 376	94.70 371	85.86 369	77.62 368	95.54 364

LCM-MVSNet		86.80 334	85.22 338	91.53 346	87.81 376	80.96 370	98.23 359	98.99 302	71.05 369	90.13 364	96.51 361	48.45 377	96.88 365	90.51 352	85.30 360	96.76 359

test_vis3_rt		87.04 332	85.81 335	90.73 348	93.99 370	81.96 369	99.76 36	90.23 381	92.81 347	81.35 369	91.56 369	40.06 378	99.07 310	94.27 327	88.23 356	91.15 369

ANet_high		77.30 340	74.86 344	84.62 354	75.88 380	77.61 373	97.63 365	93.15 378	88.81 360	64.27 375	89.29 372	36.51 379	83.93 377	75.89 372	52.31 374	92.33 368

test123		39.01 345	42.50 347	28.53 360	39.17 383	20.91 384	98.75 328	19.17 385	19.83 378	38.57 377	66.67 375	33.16 380	15.42 379	37.50 378	29.66 377	49.26 374

testmvs		39.17 344	43.78 346	25.37 361	36.04 384	16.84 385	98.36 350	26.56 383	20.06 377	38.51 378	67.32 374	29.64 381	15.30 380	37.59 377	39.90 376	43.98 375

wuyk23d		40.18 343	41.29 348	36.84 359	86.18 378	49.12 383	79.73 372	22.81 384	27.64 376	25.46 379	28.45 379	21.98 382	48.89 378	55.80 376	23.56 378	12.51 376

PMVS	70.75 22	75.98 342	74.97 343	79.01 358	70.98 381	55.18 382	93.37 370	98.21 350	65.08 375	61.78 376	93.83 366	21.74 383	92.53 372	78.59 371	91.12 347	89.34 371
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	76.82 21	76.91 341	74.31 345	84.70 353	85.38 379	76.05 376	96.88 367	93.17 377	67.39 372	71.28 374	89.01 373	21.66 384	87.69 374	71.74 373	72.29 371	90.35 370
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_blank		0.13 349	0.17 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	1.57 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		0.02 350	0.03 353	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.27 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		0.02 350	0.03 353	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.27 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		0.02 350	0.03 353	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.27 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		0.02 350	0.03 353	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.27 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		0.02 350	0.03 353	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.27 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		0.02 350	0.03 353	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.27 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		8.30 347	11.06 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	99.58 200	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		0.02 350	0.03 353	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.27 381	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

FOURS1					99.91 1	99.93 1	99.87 9	99.56 57	99.10 16	99.81 25

MSC_two_6792asdad				99.87 11	99.51 156	99.76 37		99.33 241					99.96 22	98.87 89	99.84 63	99.89 6

No_MVS				99.87 11	99.51 156	99.76 37		99.33 241					99.96 22	98.87 89	99.84 63	99.89 6

eth-test2					0.00 385

eth-test					0.00 385

IU-MVS					99.84 31	99.88 8		99.32 251	98.30 96	99.84 18				98.86 94	99.85 55	99.89 6

save fliter					99.76 56	99.59 62	99.14 263	99.40 207	99.00 31

test_0728_SECOND				99.91 2	99.84 31	99.89 4	99.57 108	99.51 103					99.96 22	98.93 80	99.86 48	99.88 12

GSMVS																99.52 148

test_part2					99.81 41	99.83 16				99.77 38

MTGPA								99.47 160

MTMP							99.54 127	98.88 317

gm-plane-assit					98.54 333	92.96 351			94.65 330		99.15 304		99.64 220	97.56 229

test9_res														97.49 235	99.72 104	99.75 74

agg_prior2														97.21 251	99.73 103	99.75 74

agg_prior					99.67 100	99.62 59		99.40 207		98.87 241			99.91 90

test_prior4						99.56 66	98.99 297

test_prior				99.68 54	99.67 100	99.48 80		99.56 57					99.83 146			99.74 78

旧先验2							98.96 304		96.70 255	99.47 115			99.94 57	98.19 172

新几何2							99.01 295

无先验							98.99 297	99.51 103	96.89 245				99.93 70	97.53 232		99.72 89

原ACMM2							98.95 307

testdata2													99.95 48	96.67 284

testdata1							98.85 318		98.32 95

plane_prior7					99.29 220	97.03 268

plane_prior5								99.47 160					99.69 207	97.78 205	97.63 228	98.67 263

plane_prior4											99.61 191

plane_prior3						97.00 270			98.69 64	99.11 200

plane_prior2							99.39 198		98.97 39

plane_prior1					99.26 227

plane_prior						96.97 273	99.21 254		98.45 80						97.60 231

n2								0.00 386

nn								0.00 386

door-mid								98.05 353

test11								99.35 230

door								97.92 354

HQP5-MVS						96.83 278

HQP-NCC					99.19 242		98.98 300		98.24 102	98.66 268

ACMP_Plane					99.19 242		98.98 300		98.24 102	98.66 268

BP-MVS														97.19 255

HQP4-MVS										98.66 268			99.64 220			98.64 275

HQP3-MVS								99.39 210							97.58 233

NP-MVS					99.23 233	96.92 276					99.40 256

ACMMP++_ref															97.19 262

ACMMP++															97.43 252

High-resolution multi-view benchmark