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.

AdaColmap		97.23 130	96.80 139	98.51 132	99.99 1	95.60 200	99.09 312	98.84 65	93.32 203	96.74 214	99.72 94	86.04 260	100.00 1	98.01 152	99.43 129	99.94 86

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 21	98.69 81	98.20 9	99.93 2	99.98 2	96.82 26	100.00 1	99.75 41	100.00 1	99.99 24

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 39	98.64 90	98.47 3	99.13 104	99.92 17	96.38 36	100.00 1	99.74 43	100.00 1	100.00 1

mPP-MVS		98.39 56	98.20 54	98.97 92	99.97 3	96.92 138	99.95 72	98.38 183	95.04 123	98.61 138	99.80 58	93.39 117	100.00 1	98.64 114	100.00 1	99.98 56

CPTT-MVS		97.64 110	97.32 114	98.58 121	99.97 3	95.77 189	99.96 53	98.35 189	89.90 341	98.36 153	99.79 62	91.18 177	99.99 39	98.37 130	99.99 21	99.99 24

DP-MVS Recon		98.41 53	98.02 68	99.56 29	99.97 3	98.70 52	99.92 100	98.44 147	92.06 273	98.40 152	99.84 48	95.68 47	100.00 1	98.19 141	99.71 92	99.97 66

PAPR		98.52 43	98.16 58	99.58 28	99.97 3	98.77 46	99.95 72	98.43 155	95.35 117	98.03 167	99.75 80	94.03 102	99.98 50	98.11 146	99.83 81	99.99 24

MED-MVS test				99.60 23	99.96 8	98.79 41	99.97 39	98.88 54	96.36 88	99.07 109	99.93 11		100.00 1	99.98 9	99.96 46	99.99 24

MED-MVS		99.15 8	99.00 12	99.60 23	99.96 8	98.79 41	99.97 39	98.88 54	95.89 101	99.07 109	99.93 11	97.36 17	100.00 1	99.98 9	99.96 46	99.99 24

TestfortrainingZip a		99.09 10	98.87 19	99.76 10	99.96 8	99.27 18	99.97 39	98.88 54	96.36 88	99.07 109	99.93 11	97.36 17	100.00 1	98.32 133	99.96 46	100.00 1

HFP-MVS		98.56 39	98.37 43	99.14 72	99.96 8	97.43 114	99.95 72	98.61 98	94.77 133	99.31 92	99.85 37	94.22 95	100.00 1	98.70 109	99.98 32	99.98 56

region2R		98.54 41	98.37 43	99.05 82	99.96 8	97.18 124	99.96 53	98.55 118	94.87 130	99.45 79	99.85 37	94.07 101	100.00 1	98.67 111	100.00 1	99.98 56

ACMMPR		98.50 44	98.32 47	99.05 82	99.96 8	97.18 124	99.95 72	98.60 100	94.77 133	99.31 92	99.84 48	93.73 111	100.00 1	98.70 109	99.98 32	99.98 56

NCCC		99.37 2	99.25 2	99.71 16	99.96 8	99.15 23	99.97 39	98.62 97	98.02 22	99.90 6	99.95 3	97.33 19	100.00 1	99.54 58	100.00 1	100.00 1

CP-MVS		98.45 48	98.32 47	98.87 97	99.96 8	96.62 152	99.97 39	98.39 179	94.43 150	98.90 119	99.87 31	94.30 92	100.00 1	99.04 84	99.99 21	99.99 24

test_one_0601					99.94 16	99.30 12		98.41 172	96.63 73	99.75 40	99.93 11	97.49 10

test_0728_SECOND				99.82 7	99.94 16	99.47 7	99.95 72	98.43 155					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 32	98.55 31	99.15 70	99.94 16	97.50 110	99.94 90	98.42 167	96.22 92	99.41 84	99.78 66	94.34 89	99.96 75	98.92 94	99.95 54	99.99 24

X-MVStestdata		93.83 276	92.06 311	99.15 70	99.94 16	97.50 110	99.94 90	98.42 167	96.22 92	99.41 84	41.37 490	94.34 89	99.96 75	98.92 94	99.95 54	99.99 24

test_prior				99.43 40	99.94 16	98.49 65		98.65 87					99.80 142			99.99 24

MSLP-MVS++		99.13 9	99.01 11	99.49 36	99.94 16	98.46 66	99.98 21	98.86 59	97.10 53	99.80 26	99.94 4	95.92 43	100.00 1	99.51 59	100.00 1	100.00 1

APDe-MVS		99.06 14	98.91 15	99.51 33	99.94 16	98.76 49	99.91 108	98.39 179	97.20 51	99.46 78	99.85 37	95.53 51	99.79 144	99.86 27	100.00 1	99.99 24
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS		98.23 71	97.97 72	99.03 84	99.94 16	97.17 127	99.95 72	98.39 179	94.70 137	98.26 159	99.81 57	91.84 168	100.00 1	98.85 100	99.97 42	99.93 87
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDPH-MVS		98.65 35	98.36 45	99.49 36	99.94 16	98.73 50	99.87 130	98.33 194	93.97 175	99.76 39	99.87 31	94.99 67	99.75 153	98.55 118	100.00 1	99.98 56

PAPM_NR		98.12 75	97.93 78	98.70 108	99.94 16	96.13 178	99.82 160	98.43 155	94.56 141	97.52 184	99.70 100	94.40 84	99.98 50	97.00 192	99.98 32	99.99 24

MG-MVS		98.91 22	98.65 27	99.68 17	99.94 16	99.07 25	99.64 225	99.44 19	97.33 44	99.00 115	99.72 94	94.03 102	99.98 50	98.73 108	100.00 1	100.00 1

ME-MVS		99.07 12	98.89 17	99.59 26	99.93 27	98.79 41	99.95 72	98.80 71	95.89 101	99.28 96	99.93 11	96.28 37	99.98 50	99.98 9	99.96 46	99.99 24

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 27	99.30 12	99.96 53	98.43 155	97.27 47	99.80 26	99.94 4	96.71 29	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 27	99.31 10		98.41 172	97.71 31	99.84 21				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 27	99.30 12		98.43 155	97.26 49	99.80 26	99.88 28	96.71 29	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 13	99.93 27	99.29 15	99.95 72	98.32 196	97.28 45	99.83 22	99.91 18	97.22 21	100.00 1	99.99 5	100.00 1	99.89 96
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					99.93 27	99.29 15	99.96 53	98.42 167	97.28 45	99.86 15	99.94 4	97.22 21

MSP-MVS		99.09 10	99.12 5	98.98 91	99.93 27	97.24 121	99.95 72	98.42 167	97.50 38	99.52 74	99.88 28	97.43 16	99.71 159	99.50 61	99.98 32	100.00 1
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
agg_prior					99.93 27	98.77 46		98.43 155		99.63 57			99.85 129

FOURS1					99.92 35	97.66 104	99.95 72	98.36 187	95.58 111	99.52 74

ZD-MVS					99.92 35	98.57 60		98.52 127	92.34 261	99.31 92	99.83 50	95.06 62	99.80 142	99.70 49	99.97 42

GST-MVS		98.27 63	97.97 72	99.17 65	99.92 35	97.57 106	99.93 97	98.39 179	94.04 173	98.80 124	99.74 87	92.98 133	100.00 1	98.16 143	99.76 89	99.93 87

TEST9					99.92 35	98.92 30	99.96 53	98.43 155	93.90 181	99.71 47	99.86 33	95.88 44	99.85 129

train_agg		98.88 23	98.65 27	99.59 26	99.92 35	98.92 30	99.96 53	98.43 155	94.35 155	99.71 47	99.86 33	95.94 41	99.85 129	99.69 50	99.98 32	99.99 24

test_8					99.92 35	98.88 33	99.96 53	98.43 155	94.35 155	99.69 49	99.85 37	95.94 41	99.85 129

PGM-MVS		98.34 58	98.13 60	98.99 89	99.92 35	97.00 134	99.75 185	99.50 17	93.90 181	99.37 89	99.76 72	93.24 126	100.00 1	97.75 171	99.96 46	99.98 56

ACMMP		97.74 103	97.44 107	98.66 112	99.92 35	96.13 178	99.18 305	99.45 18	94.84 131	96.41 232	99.71 97	91.40 171	99.99 39	97.99 154	98.03 189	99.87 99
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
DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 43	99.31 10	99.95 72	98.43 155	96.48 78	99.80 26	99.93 11	97.44 14	100.00 1	99.92 16	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 43	99.80 2		98.41 172					100.00 1	99.96 12	100.00 1	100.00 1

No_MVS				99.93 2	99.91 43	99.80 2		98.41 172					100.00 1	99.96 12	100.00 1	100.00 1

HPM-MVS++		99.07 12	98.88 18	99.63 18	99.90 46	99.02 26	99.95 72	98.56 112	97.56 37	99.44 80	99.85 37	95.38 55	100.00 1	99.31 71	99.99 21	99.87 99

APD-MVS		98.62 36	98.35 46	99.41 43	99.90 46	98.51 63	99.87 130	98.36 187	94.08 168	99.74 43	99.73 91	94.08 100	99.74 155	99.42 67	99.99 21	99.99 24
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepC-MVS_fast	96.59 1	98.81 26	98.54 32	99.62 21	99.90 46	98.85 36	99.24 300	98.47 139	98.14 16	99.08 107	99.91 18	93.09 130	100.00 1	99.04 84	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OPU-MVS				99.93 2	99.89 49	99.80 2	99.96 53				99.80 58	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 12	99.89 49	99.24 20	99.87 130	98.44 147	97.48 39	99.64 56	99.94 4	96.68 31	99.99 39	99.99 5	100.00 1	99.99 24
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_part2					99.89 49	99.25 19				99.49 77

CSCG		97.10 136	97.04 126	97.27 231	99.89 49	91.92 324	99.90 114	99.07 37	88.67 365	95.26 264	99.82 53	93.17 129	99.98 50	98.15 144	99.47 124	99.90 95

ZNCC-MVS		98.31 60	98.03 67	99.17 65	99.88 53	97.59 105	99.94 90	98.44 147	94.31 158	98.50 145	99.82 53	93.06 131	99.99 39	98.30 135	99.99 21	99.93 87

SR-MVS		98.46 47	98.30 50	98.93 95	99.88 53	97.04 133	99.84 149	98.35 189	94.92 127	99.32 91	99.80 58	93.35 119	99.78 146	99.30 72	99.95 54	99.96 74

9.14			98.38 41		99.87 55		99.91 108	98.33 194	93.22 206	99.78 37	99.89 26	94.57 80	99.85 129	99.84 29	99.97 42

SMA-MVS		98.76 29	98.48 35	99.62 21	99.87 55	98.87 34	99.86 141	98.38 183	93.19 208	99.77 38	99.94 4	95.54 49	100.00 1	99.74 43	99.99 21	100.00 1
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
NormalMVS		97.90 85	97.85 85	98.04 165	99.86 57	95.39 210	99.61 232	97.78 265	96.52 76	98.61 138	99.31 156	92.73 141	99.67 167	96.77 206	99.48 121	99.06 243

lecture		98.67 33	98.46 36	99.28 52	99.86 57	97.88 91	99.97 39	99.25 30	96.07 96	99.79 35	99.70 100	92.53 149	99.98 50	99.51 59	99.48 121	99.97 66

PHI-MVS		98.41 53	98.21 53	99.03 84	99.86 57	97.10 131	99.98 21	98.80 71	90.78 320	99.62 60	99.78 66	95.30 56	100.00 1	99.80 32	99.93 65	99.99 24

MTAPA		98.29 62	97.96 75	99.30 51	99.85 60	97.93 89	99.39 275	98.28 203	95.76 105	97.18 199	99.88 28	92.74 140	100.00 1	98.67 111	99.88 77	99.99 24

LS3D		95.84 205	95.11 221	98.02 166	99.85 60	95.10 228	98.74 362	98.50 136	87.22 387	93.66 285	99.86 33	87.45 236	99.95 84	90.94 323	99.81 87	99.02 250

HPM-MVS		97.96 80	97.72 90	98.68 109	99.84 62	96.39 164	99.90 114	98.17 218	92.61 243	98.62 137	99.57 130	91.87 167	99.67 167	98.87 99	99.99 21	99.99 24
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EI-MVSNet-Vis-set		98.27 63	98.11 62	98.75 105	99.83 63	96.59 156	99.40 271	98.51 130	95.29 119	98.51 144	99.76 72	93.60 115	99.71 159	98.53 121	99.52 114	99.95 82

save fliter					99.82 64	98.79 41	99.96 53	98.40 176	97.66 33

PLC	95.54 3	97.93 83	97.89 82	98.05 164	99.82 64	94.77 239	99.92 100	98.46 141	93.93 178	97.20 197	99.27 162	95.44 54	99.97 63	97.41 177	99.51 117	99.41 193
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 68	98.08 64	98.78 102	99.81 66	96.60 154	99.82 160	98.30 201	93.95 177	99.37 89	99.77 70	92.84 137	99.76 152	98.95 90	99.92 68	99.97 66

EI-MVSNet-UG-set		98.14 74	97.99 70	98.60 117	99.80 67	96.27 167	99.36 281	98.50 136	95.21 121	98.30 156	99.75 80	93.29 123	99.73 158	98.37 130	99.30 138	99.81 108

SR-MVS-dyc-post		98.31 60	98.17 57	98.71 107	99.79 68	96.37 165	99.76 181	98.31 198	94.43 150	99.40 86	99.75 80	93.28 124	99.78 146	98.90 97	99.92 68	99.97 66

RE-MVS-def			98.13 60		99.79 68	96.37 165	99.76 181	98.31 198	94.43 150	99.40 86	99.75 80	92.95 134		98.90 97	99.92 68	99.97 66

HPM-MVS_fast		97.80 97	97.50 103	98.68 109	99.79 68	96.42 160	99.88 127	98.16 223	91.75 284	98.94 117	99.54 133	91.82 169	99.65 171	97.62 174	99.99 21	99.99 24

SF-MVS		98.67 33	98.40 39	99.50 34	99.77 71	98.67 53	99.90 114	98.21 213	93.53 193	99.81 24	99.89 26	94.70 76	99.86 128	99.84 29	99.93 65	99.96 74

MGCNet		99.06 14	98.84 20	99.72 14	99.76 72	99.21 22	99.99 5	99.34 25	98.70 2	99.44 80	99.75 80	93.24 126	99.99 39	99.94 14	99.41 131	99.95 82

旧先验1					99.76 72	97.52 108		98.64 90			99.85 37	95.63 48			99.94 59	99.99 24

OMC-MVS		97.28 126	97.23 118	97.41 221	99.76 72	93.36 291	99.65 221	97.95 245	96.03 97	97.41 190	99.70 100	89.61 203	99.51 177	96.73 208	98.25 179	99.38 195

新几何1				99.42 42	99.75 75	98.27 70		98.63 96	92.69 238	99.55 69	99.82 53	94.40 84	100.00 1	91.21 315	99.94 59	99.99 24

MP-MVS-pluss		98.07 78	97.64 96	99.38 48	99.74 76	98.41 68	99.74 189	98.18 217	93.35 201	96.45 226	99.85 37	92.64 144	99.97 63	98.91 96	99.89 74	99.77 115
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + MP.		98.93 20	98.77 22	99.41 43	99.74 76	98.67 53	99.77 175	98.38 183	96.73 69	99.88 12	99.74 87	94.89 69	99.59 173	99.80 32	99.98 32	99.97 66
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test12				99.43 40	99.74 76	98.56 61		98.40 176		99.65 53		94.76 72	99.75 153		99.98 32	99.99 24

原ACMM1				98.96 93	99.73 79	96.99 135		98.51 130	94.06 171	99.62 60	99.85 37	94.97 68	99.96 75	95.11 236	99.95 54	99.92 92

TSAR-MVS + GP.		98.60 37	98.51 34	98.86 98	99.73 79	96.63 151	99.97 39	97.92 250	98.07 19	98.76 130	99.55 131	95.00 66	99.94 93	99.91 19	97.68 196	99.99 24

CANet		98.27 63	97.82 87	99.63 18	99.72 81	99.10 24	99.98 21	98.51 130	97.00 59	98.52 142	99.71 97	87.80 227	99.95 84	99.75 41	99.38 133	99.83 104

reproduce_model		98.75 30	98.66 26	99.03 84	99.71 82	97.10 131	99.73 196	98.23 211	97.02 58	99.18 102	99.90 22	94.54 81	99.99 39	99.77 37	99.90 73	99.99 24

F-COLMAP		96.93 148	96.95 129	96.87 247	99.71 82	91.74 331	99.85 144	97.95 245	93.11 215	95.72 253	99.16 180	92.35 155	99.94 93	95.32 232	99.35 136	98.92 258

reproduce-ours		98.78 27	98.67 24	99.09 79	99.70 84	97.30 118	99.74 189	98.25 207	97.10 53	99.10 105	99.90 22	94.59 77	99.99 39	99.77 37	99.91 71	99.99 24

our_new_method		98.78 27	98.67 24	99.09 79	99.70 84	97.30 118	99.74 189	98.25 207	97.10 53	99.10 105	99.90 22	94.59 77	99.99 39	99.77 37	99.91 71	99.99 24

SD-MVS		98.92 21	98.70 23	99.56 29	99.70 84	98.73 50	99.94 90	98.34 193	96.38 84	99.81 24	99.76 72	94.59 77	99.98 50	99.84 29	99.96 46	99.97 66
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
patch_mono-2		98.24 69	99.12 5	95.59 289	99.67 87	86.91 416	99.95 72	98.89 52	97.60 34	99.90 6	99.76 72	96.54 34	99.98 50	99.94 14	99.82 85	99.88 97

ACMMP_NAP		98.49 45	98.14 59	99.54 31	99.66 88	98.62 59	99.85 144	98.37 186	94.68 138	99.53 72	99.83 50	92.87 136	100.00 1	98.66 113	99.84 80	99.99 24

DeepPCF-MVS	95.94 2	97.71 107	98.98 13	93.92 358	99.63 89	81.76 451	99.96 53	98.56 112	99.47 1	99.19 101	99.99 1	94.16 99	100.00 1	99.92 16	99.93 65	100.00 1

EPNet		98.49 45	98.40 39	98.77 104	99.62 90	96.80 145	99.90 114	99.51 16	97.60 34	99.20 99	99.36 151	93.71 112	99.91 110	97.99 154	98.71 164	99.61 146
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		98.83 24	98.53 33	99.76 10	99.59 91	99.33 8	99.99 5	99.76 6	98.39 4	99.39 88	99.80 58	90.49 192	99.96 75	99.89 21	99.43 129	99.98 56

PVSNet_BlendedMVS		96.05 195	95.82 189	96.72 253	99.59 91	96.99 135	99.95 72	99.10 34	94.06 171	98.27 157	95.80 359	89.00 215	99.95 84	99.12 78	87.53 351	93.24 417

PVSNet_Blended		97.94 82	97.64 96	98.83 99	99.59 91	96.99 135	100.00 1	99.10 34	95.38 116	98.27 157	99.08 184	89.00 215	99.95 84	99.12 78	99.25 140	99.57 157

PatchMatch-RL		96.04 196	95.40 205	97.95 168	99.59 91	95.22 223	99.52 253	99.07 37	93.96 176	96.49 224	98.35 274	82.28 313	99.82 141	90.15 339	99.22 143	98.81 265

dcpmvs_2		97.42 121	98.09 63	95.42 296	99.58 95	87.24 412	99.23 301	96.95 389	94.28 161	98.93 118	99.73 91	94.39 87	99.16 205	99.89 21	99.82 85	99.86 101

test222					99.55 96	97.41 116	99.34 283	98.55 118	91.86 279	99.27 97	99.83 50	93.84 109			99.95 54	99.99 24

CNLPA		97.76 101	97.38 110	98.92 96	99.53 97	96.84 140	99.87 130	98.14 227	93.78 185	96.55 222	99.69 104	92.28 157	99.98 50	97.13 187	99.44 128	99.93 87

API-MVS		97.86 88	97.66 94	98.47 134	99.52 98	95.41 208	99.47 263	98.87 58	91.68 285	98.84 121	99.85 37	92.34 156	99.99 39	98.44 126	99.96 46	100.00 1

PVSNet	91.05 13	97.13 135	96.69 145	98.45 137	99.52 98	95.81 187	99.95 72	99.65 12	94.73 135	99.04 113	99.21 173	84.48 292	99.95 84	94.92 242	98.74 163	99.58 155

114514_t		97.41 122	96.83 136	99.14 72	99.51 100	97.83 93	99.89 124	98.27 205	88.48 369	99.06 112	99.66 115	90.30 195	99.64 172	96.32 217	99.97 42	99.96 74

cl22		93.77 281	93.25 285	95.33 300	99.49 101	94.43 249	99.61 232	98.09 230	90.38 329	89.16 356	95.61 367	90.56 190	97.34 341	91.93 306	84.45 373	94.21 359

testdata				98.42 141	99.47 102	95.33 214		98.56 112	93.78 185	99.79 35	99.85 37	93.64 114	99.94 93	94.97 240	99.94 59	100.00 1

MAR-MVS		97.43 117	97.19 120	98.15 157	99.47 102	94.79 238	99.05 323	98.76 73	92.65 241	98.66 135	99.82 53	88.52 221	99.98 50	98.12 145	99.63 99	99.67 129
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
DP-MVS		94.54 253	93.42 275	97.91 174	99.46 104	94.04 265	98.93 341	97.48 302	81.15 442	90.04 327	99.55 131	87.02 244	99.95 84	88.97 353	98.11 185	99.73 119

MVS_111021_LR		98.42 52	98.38 41	98.53 129	99.39 105	95.79 188	99.87 130	99.86 2	96.70 70	98.78 125	99.79 62	92.03 164	99.90 112	99.17 77	99.86 79	99.88 97

CHOSEN 280x420		99.01 17	99.03 10	98.95 94	99.38 106	98.87 34	98.46 381	99.42 21	97.03 57	99.02 114	99.09 183	99.35 2	98.21 303	99.73 45	99.78 88	99.77 115

MVS_111021_HR		98.72 31	98.62 29	99.01 88	99.36 107	97.18 124	99.93 97	99.90 1	96.81 67	98.67 134	99.77 70	93.92 104	99.89 117	99.27 73	99.94 59	99.96 74

fmvsm_s_conf0.5_n_11		98.03 79	97.89 82	98.46 136	99.35 108	97.76 97	99.99 5	98.04 236	98.20 9	99.90 6	99.78 66	86.21 258	99.95 84	99.89 21	99.68 94	97.65 303

DPM-MVS		98.83 24	98.46 36	99.97 1	99.33 109	99.92 1	99.96 53	98.44 147	97.96 23	99.55 69	99.94 4	97.18 23	100.00 1	93.81 273	99.94 59	99.98 56

TAPA-MVS	92.12 8	94.42 261	93.60 267	96.90 246	99.33 109	91.78 330	99.78 170	98.00 239	89.89 342	94.52 270	99.47 137	91.97 165	99.18 202	69.90 462	99.52 114	99.73 119
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 225	95.07 223	96.32 268	99.32 111	96.60 154	99.76 181	98.85 62	96.65 72	87.83 381	96.05 356	99.52 1	98.11 308	96.58 212	81.07 402	94.25 353

fmvsm_s_conf0.5_n_9		98.15 73	98.02 68	98.55 123	99.28 112	95.84 186	99.99 5	98.57 106	98.17 13	99.93 2	99.74 87	87.04 243	99.97 63	99.86 27	99.59 108	99.83 104

SPE-MVS-test		97.88 86	97.94 77	97.70 192	99.28 112	95.20 224	99.98 21	97.15 354	95.53 113	99.62 60	99.79 62	92.08 163	98.38 286	98.75 107	99.28 139	99.52 169

test_fmvsm_n_1920		98.44 49	98.61 30	97.92 172	99.27 114	95.18 225	100.00 1	98.90 50	98.05 20	99.80 26	99.73 91	92.64 144	99.99 39	99.58 57	99.51 117	98.59 275

fmvsm_s_conf0.5_n_10		98.24 69	97.90 80	99.26 54	99.24 115	97.88 91	99.99 5	98.76 73	98.20 9	99.92 4	99.74 87	85.97 262	99.94 93	99.72 46	99.53 113	99.96 74

fmvsm_l_conf0.5_n_a		99.00 18	98.91 15	99.28 52	99.21 116	97.91 90	99.98 21	98.85 62	98.25 5	99.92 4	99.75 80	94.72 74	99.97 63	99.87 25	99.64 97	99.95 82

fmvsm_s_conf0.5_n_8		98.38 57	98.05 66	99.35 49	99.20 117	98.12 76	99.98 21	98.81 67	98.22 7	99.80 26	99.71 97	87.37 238	99.97 63	99.91 19	99.48 121	99.97 66

test_yl		97.83 92	97.37 111	99.21 59	99.18 118	97.98 85	99.64 225	99.27 27	91.43 294	97.88 174	98.99 200	95.84 45	99.84 137	98.82 101	95.32 278	99.79 111

DCV-MVSNet		97.83 92	97.37 111	99.21 59	99.18 118	97.98 85	99.64 225	99.27 27	91.43 294	97.88 174	98.99 200	95.84 45	99.84 137	98.82 101	95.32 278	99.79 111

fmvsm_l_conf0.5_n		98.94 19	98.84 20	99.25 55	99.17 120	97.81 95	99.98 21	98.86 59	98.25 5	99.90 6	99.76 72	94.21 97	99.97 63	99.87 25	99.52 114	99.98 56

DeepC-MVS	94.51 4	96.92 149	96.40 159	98.45 137	99.16 121	95.90 184	99.66 220	98.06 233	96.37 87	94.37 276	99.49 136	83.29 306	99.90 112	97.63 173	99.61 104	99.55 159
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DELS-MVS		98.54 41	98.22 52	99.50 34	99.15 122	98.65 57	100.00 1	98.58 104	97.70 32	98.21 162	99.24 169	92.58 147	99.94 93	98.63 116	99.94 59	99.92 92
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
fmvsm_l_conf0.5_n_3		98.41 53	98.08 64	99.39 45	99.12 123	98.29 69	99.98 21	98.64 90	98.14 16	99.86 15	99.76 72	87.99 226	99.97 63	99.72 46	99.54 111	99.91 94

fmvsm_l_conf0.5_n_9		98.55 40	98.23 51	99.49 36	99.10 124	98.50 64	99.99 5	98.70 79	98.14 16	99.94 1	99.68 111	89.02 214	99.98 50	99.89 21	99.61 104	99.99 24

CS-MVS		97.79 99	97.91 79	97.43 219	99.10 124	94.42 250	99.99 5	97.10 366	95.07 122	99.68 50	99.75 80	92.95 134	98.34 290	98.38 128	99.14 145	99.54 163

Anonymous202405211		93.10 299	91.99 312	96.40 264	99.10 124	89.65 381	98.88 347	97.93 247	83.71 426	94.00 282	98.75 236	68.79 421	99.88 123	95.08 237	91.71 311	99.68 127

fmvsm_s_conf0.5_n		97.80 97	97.85 85	97.67 193	99.06 127	94.41 251	99.98 21	98.97 43	97.34 42	99.63 57	99.69 104	87.27 239	99.97 63	99.62 55	99.06 150	98.62 274

HyFIR lowres test		96.66 165	96.43 156	97.36 226	99.05 128	93.91 270	99.70 211	99.80 3	90.54 325	96.26 235	98.08 287	92.15 161	98.23 302	96.84 202	95.46 273	99.93 87

LFMVS		94.75 247	93.56 270	98.30 147	99.03 129	95.70 194	98.74 362	97.98 242	87.81 380	98.47 146	99.39 148	67.43 430	99.53 174	98.01 152	95.20 281	99.67 129

fmvsm_s_conf0.5_n_4		97.75 102	97.86 84	97.42 220	99.01 130	94.69 241	99.97 39	98.76 73	97.91 25	99.87 13	99.76 72	86.70 250	99.93 103	99.67 52	99.12 148	97.64 304

fmvsm_s_conf0.5_n_2		97.59 112	97.28 115	98.53 129	99.01 130	98.15 71	99.98 21	98.59 102	98.17 13	99.75 40	99.63 121	81.83 319	99.94 93	99.78 35	98.79 161	97.51 312

AllTest		92.48 315	91.64 318	95.00 309	99.01 130	88.43 399	98.94 339	96.82 403	86.50 396	88.71 361	98.47 269	74.73 396	99.88 123	85.39 395	96.18 248	96.71 318

TestCases				95.00 309	99.01 130	88.43 399		96.82 403	86.50 396	88.71 361	98.47 269	74.73 396	99.88 123	85.39 395	96.18 248	96.71 318

COLMAP_ROB	90.47 14	92.18 322	91.49 324	94.25 343	99.00 134	88.04 405	98.42 387	96.70 410	82.30 437	88.43 371	99.01 194	76.97 371	99.85 129	86.11 391	96.50 240	94.86 329
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_s_conf0.5_n_3		97.95 81	97.66 94	98.81 100	98.99 135	98.07 79	99.98 21	98.81 67	98.18 12	99.89 10	99.70 100	84.15 295	99.97 63	99.76 40	99.50 119	98.39 282

test_fmvs1		95.35 226	95.68 196	94.36 339	98.99 135	84.98 427	99.96 53	96.65 412	97.60 34	99.73 45	98.96 206	71.58 411	99.93 103	98.31 134	99.37 134	98.17 287

HY-MVS	92.50 7	97.79 99	97.17 122	99.63 18	98.98 137	99.32 9	97.49 416	99.52 14	95.69 108	98.32 155	97.41 307	93.32 121	99.77 149	98.08 149	95.75 263	99.81 108

VNet		97.21 131	96.57 150	99.13 76	98.97 138	97.82 94	99.03 326	99.21 32	94.31 158	99.18 102	98.88 218	86.26 257	99.89 117	98.93 92	94.32 291	99.69 126

thres200		96.96 145	96.21 166	99.22 58	98.97 138	98.84 37	99.85 144	99.71 7	93.17 210	96.26 235	98.88 218	89.87 200	99.51 177	94.26 261	94.91 283	99.31 212

tfpn200view9		96.79 153	95.99 173	99.19 61	98.94 140	98.82 38	99.78 170	99.71 7	92.86 225	96.02 243	98.87 225	89.33 207	99.50 179	93.84 270	94.57 287	99.27 221

thres400		96.78 155	95.99 173	99.16 68	98.94 140	98.82 38	99.78 170	99.71 7	92.86 225	96.02 243	98.87 225	89.33 207	99.50 179	93.84 270	94.57 287	99.16 231

sasdasda		97.09 138	96.32 160	99.39 45	98.93 142	98.95 28	99.72 200	97.35 315	94.45 146	97.88 174	99.42 141	86.71 248	99.52 175	98.48 123	93.97 297	99.72 121

Anonymous20231211		89.86 373	88.44 381	94.13 348	98.93 142	90.68 359	98.54 378	98.26 206	76.28 456	86.73 395	95.54 371	70.60 417	97.56 334	90.82 326	80.27 411	94.15 368

canonicalmvs		97.09 138	96.32 160	99.39 45	98.93 142	98.95 28	99.72 200	97.35 315	94.45 146	97.88 174	99.42 141	86.71 248	99.52 175	98.48 123	93.97 297	99.72 121

SDMVSNet		94.80 242	93.96 257	97.33 229	98.92 145	95.42 207	99.59 237	98.99 40	92.41 257	92.55 300	97.85 298	75.81 386	98.93 220	97.90 160	91.62 312	97.64 304

sd_testset		93.55 288	92.83 292	95.74 287	98.92 145	90.89 355	98.24 395	98.85 62	92.41 257	92.55 300	97.85 298	71.07 416	98.68 255	93.93 267	91.62 312	97.64 304

EPNet_dtu		95.71 214	95.39 206	96.66 255	98.92 145	93.41 287	99.57 242	98.90 50	96.19 94	97.52 184	98.56 259	92.65 143	97.36 339	77.89 443	98.33 174	99.20 229
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 76	97.60 98	99.60 23	98.92 145	99.28 17	99.89 124	99.52 14	95.58 111	98.24 161	99.39 148	93.33 120	99.74 155	97.98 156	95.58 272	99.78 114

CHOSEN 1792x2688		96.81 152	96.53 151	97.64 196	98.91 149	93.07 293	99.65 221	99.80 3	95.64 109	95.39 260	98.86 227	84.35 294	99.90 112	96.98 194	99.16 144	99.95 82

thres100view900		96.74 160	95.92 185	99.18 62	98.90 150	98.77 46	99.74 189	99.71 7	92.59 245	95.84 247	98.86 227	89.25 209	99.50 179	93.84 270	94.57 287	99.27 221

thres600view7		96.69 163	95.87 188	99.14 72	98.90 150	98.78 45	99.74 189	99.71 7	92.59 245	95.84 247	98.86 227	89.25 209	99.50 179	93.44 283	94.50 290	99.16 231

MSDG		94.37 263	93.36 282	97.40 222	98.88 152	93.95 269	99.37 279	97.38 311	85.75 407	90.80 319	99.17 177	84.11 297	99.88 123	86.35 387	98.43 172	98.36 284

MGCFI-Net		97.00 143	96.22 165	99.34 50	98.86 153	98.80 40	99.67 219	97.30 327	94.31 158	97.77 180	99.41 145	86.36 255	99.50 179	98.38 128	93.90 299	99.72 121

h-mvs33		94.92 239	94.36 243	96.59 257	98.85 154	91.29 347	98.93 341	98.94 44	95.90 99	98.77 127	98.42 272	90.89 185	99.77 149	97.80 164	70.76 451	98.72 271

Anonymous20240529		92.10 323	90.65 335	96.47 259	98.82 155	90.61 361	98.72 364	98.67 86	75.54 460	93.90 284	98.58 257	66.23 434	99.90 112	94.70 251	90.67 315	98.90 261

PVSNet_Blended_VisFu		97.27 127	96.81 138	98.66 112	98.81 156	96.67 150	99.92 100	98.64 90	94.51 143	96.38 233	98.49 265	89.05 213	99.88 123	97.10 189	98.34 173	99.43 190

PS-MVSNAJ		98.44 49	98.20 54	99.16 68	98.80 157	98.92 30	99.54 251	98.17 218	97.34 42	99.85 18	99.85 37	91.20 174	99.89 117	99.41 68	99.67 95	98.69 272

CANet_DTU		96.76 156	96.15 168	98.60 117	98.78 158	97.53 107	99.84 149	97.63 280	97.25 50	99.20 99	99.64 118	81.36 325	99.98 50	92.77 294	98.89 155	98.28 286

mvsany_test1		97.82 95	97.90 80	97.55 207	98.77 159	93.04 296	99.80 166	97.93 247	96.95 61	99.61 67	99.68 111	90.92 182	99.83 139	99.18 76	98.29 178	99.80 110

alignmvs		97.81 96	97.33 113	99.25 55	98.77 159	98.66 55	99.99 5	98.44 147	94.40 154	98.41 150	99.47 137	93.65 113	99.42 189	98.57 117	94.26 293	99.67 129

SymmetryMVS		97.64 110	97.46 104	98.17 153	98.74 161	95.39 210	99.61 232	99.26 29	96.52 76	98.61 138	99.31 156	92.73 141	99.67 167	96.77 206	95.63 270	99.45 186

SteuartSystems-ACMMP		99.02 16	98.97 14	99.18 62	98.72 162	97.71 99	99.98 21	98.44 147	96.85 62	99.80 26	99.91 18	97.57 8	99.85 129	99.44 66	99.99 21	99.99 24
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 71	97.97 72	99.02 87	98.69 163	98.66 55	99.52 253	98.08 232	97.05 56	99.86 15	99.86 33	90.65 187	99.71 159	99.39 70	98.63 165	98.69 272

miper_enhance_ethall		94.36 265	93.98 256	95.49 290	98.68 164	95.24 221	99.73 196	97.29 334	93.28 205	89.86 332	95.97 357	94.37 88	97.05 362	92.20 298	84.45 373	94.19 360

fmvsm_s_conf0.5_n_5		98.08 77	97.71 92	99.17 65	98.67 165	97.69 103	99.99 5	98.57 106	97.40 40	99.89 10	99.69 104	85.99 261	99.96 75	99.80 32	99.40 132	99.85 102

ETVMVS		97.03 142	96.64 146	98.20 152	98.67 165	97.12 128	99.89 124	98.57 106	91.10 306	98.17 163	98.59 254	93.86 108	98.19 304	95.64 229	95.24 280	99.28 219

test2506		97.53 114	97.19 120	98.58 121	98.66 167	96.90 139	98.81 356	99.77 5	94.93 125	97.95 169	98.96 206	92.51 150	99.20 200	94.93 241	98.15 182	99.64 135

ECVR-MVS		95.66 217	95.05 224	97.51 212	98.66 167	93.71 274	98.85 353	98.45 142	94.93 125	96.86 210	98.96 206	75.22 392	99.20 200	95.34 231	98.15 182	99.64 135

mamv4		95.24 229	96.90 131	90.25 420	98.65 169	72.11 469	98.28 392	97.64 279	89.99 340	95.93 245	98.25 282	94.74 73	99.11 206	99.01 89	99.64 97	99.53 167

balanced_conf03		98.27 63	97.99 70	99.11 77	98.64 170	98.43 67	99.47 263	97.79 262	94.56 141	99.74 43	98.35 274	94.33 91	99.25 194	99.12 78	99.96 46	99.64 135

fmvsm_s_conf0.5_n_a		97.73 105	97.72 90	97.77 186	98.63 171	94.26 258	99.96 53	98.92 49	97.18 52	99.75 40	99.69 104	87.00 245	99.97 63	99.46 64	98.89 155	99.08 241

MVSMamba_PlusPlus		97.83 92	97.45 106	98.99 89	98.60 172	98.15 71	99.58 239	97.74 270	90.34 332	99.26 98	98.32 277	94.29 93	99.23 195	99.03 87	99.89 74	99.58 155

testing222		97.08 141	96.75 141	98.06 163	98.56 173	96.82 141	99.85 144	98.61 98	92.53 252	98.84 121	98.84 231	93.36 118	98.30 294	95.84 225	94.30 292	99.05 245

test1111		95.57 220	94.98 227	97.37 224	98.56 173	93.37 290	98.86 351	98.45 142	94.95 124	96.63 216	98.95 211	75.21 393	99.11 206	95.02 238	98.14 184	99.64 135

MVSTER		95.53 221	95.22 216	96.45 262	98.56 173	97.72 98	99.91 108	97.67 275	92.38 260	91.39 310	97.14 314	97.24 20	97.30 346	94.80 247	87.85 344	94.34 348

testing3-2		97.72 106	97.43 109	98.60 117	98.55 176	97.11 130	100.00 1	99.23 31	93.78 185	97.90 171	98.73 238	95.50 52	99.69 163	98.53 121	94.63 285	98.99 252

VDD-MVS		93.77 281	92.94 290	96.27 269	98.55 176	90.22 370	98.77 361	97.79 262	90.85 312	96.82 212	99.42 141	61.18 454	99.77 149	98.95 90	94.13 294	98.82 264

tpmvs		94.28 267	93.57 269	96.40 264	98.55 176	91.50 345	95.70 454	98.55 118	87.47 382	92.15 303	94.26 423	91.42 170	98.95 219	88.15 366	95.85 259	98.76 267

UGNet		95.33 227	94.57 239	97.62 200	98.55 176	94.85 233	98.67 370	99.32 26	95.75 106	96.80 213	96.27 346	72.18 408	99.96 75	94.58 254	99.05 151	98.04 292
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
PCF-MVS	94.20 5	95.18 231	94.10 250	98.43 139	98.55 176	95.99 182	97.91 409	97.31 326	90.35 331	89.48 345	99.22 170	85.19 277	99.89 117	90.40 336	98.47 171	99.41 193
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		95.95 199	96.49 152	94.34 340	98.51 181	89.99 375	99.39 275	98.57 106	93.14 212	97.33 193	98.31 279	93.44 116	94.68 443	93.69 280	95.98 253	98.34 285

UWE-MVS		96.79 153	96.72 143	97.00 241	98.51 181	93.70 275	99.71 204	98.60 100	92.96 220	97.09 200	98.34 276	96.67 33	98.85 226	92.11 304	96.50 240	98.44 280

myMVS_eth3d28		97.86 88	97.59 100	98.68 109	98.50 183	97.26 120	99.92 100	98.55 118	93.79 184	98.26 159	98.75 236	95.20 57	99.48 185	98.93 92	96.40 243	99.29 217

test_vis1_n_1920		95.44 223	95.31 212	95.82 284	98.50 183	88.74 393	99.98 21	97.30 327	97.84 28	99.85 18	99.19 175	66.82 432	99.97 63	98.82 101	99.46 126	98.76 267

BH-w/o		95.71 214	95.38 210	96.68 254	98.49 185	92.28 315	99.84 149	97.50 300	92.12 270	92.06 306	98.79 234	84.69 288	98.67 257	95.29 233	99.66 96	99.09 239

baseline1		95.78 210	94.86 230	98.54 127	98.47 186	98.07 79	99.06 319	97.99 240	92.68 239	94.13 281	98.62 251	93.28 124	98.69 254	93.79 275	85.76 360	98.84 263

fmvsm_s_conf0.5_n_7		97.70 108	97.74 89	97.59 205	98.44 187	95.16 227	99.97 39	98.65 87	97.95 24	99.62 60	99.78 66	86.09 259	99.94 93	99.69 50	99.50 119	97.66 302

EPMVS		96.53 172	96.01 172	98.09 161	98.43 188	96.12 180	96.36 441	99.43 20	93.53 193	97.64 182	95.04 399	94.41 83	98.38 286	91.13 317	98.11 185	99.75 117

kuosan		93.17 296	92.60 298	94.86 316	98.40 189	89.54 383	98.44 383	98.53 125	84.46 421	88.49 367	97.92 295	90.57 189	97.05 362	83.10 412	93.49 302	97.99 293

WBMVS		94.52 256	94.03 254	95.98 275	98.38 190	96.68 149	99.92 100	97.63 280	90.75 321	89.64 340	95.25 392	96.77 27	96.90 374	94.35 259	83.57 380	94.35 346

UBG		97.84 91	97.69 93	98.29 148	98.38 190	96.59 156	99.90 114	98.53 125	93.91 180	98.52 142	98.42 272	96.77 27	99.17 203	98.54 119	96.20 247	99.11 238

sss		97.57 113	97.03 127	99.18 62	98.37 192	98.04 82	99.73 196	99.38 22	93.46 197	98.76 130	99.06 188	91.21 173	99.89 117	96.33 216	97.01 227	99.62 142

testing11		97.48 116	97.27 116	98.10 160	98.36 193	96.02 181	99.92 100	98.45 142	93.45 199	98.15 164	98.70 241	95.48 53	99.22 196	97.85 162	95.05 282	99.07 242

BH-untuned		95.18 231	94.83 231	96.22 270	98.36 193	91.22 348	99.80 166	97.32 325	90.91 310	91.08 313	98.67 243	83.51 300	98.54 268	94.23 262	99.61 104	98.92 258

testing91		97.16 133	96.90 131	97.97 167	98.35 195	95.67 197	99.91 108	98.42 167	92.91 223	97.33 193	98.72 239	94.81 71	99.21 197	96.98 194	94.63 285	99.03 249

testing99		97.17 132	96.91 130	97.95 168	98.35 195	95.70 194	99.91 108	98.43 155	92.94 221	97.36 191	98.72 239	94.83 70	99.21 197	97.00 192	94.64 284	98.95 254

ET-MVSNet_ETH3D		94.37 263	93.28 284	97.64 196	98.30 197	97.99 84	99.99 5	97.61 286	94.35 155	71.57 467	99.45 140	96.23 38	95.34 433	96.91 200	85.14 367	99.59 149

AUN-MVS		93.28 293	92.60 298	95.34 299	98.29 198	90.09 373	99.31 288	98.56 112	91.80 283	96.35 234	98.00 290	89.38 206	98.28 297	92.46 295	69.22 457	97.64 304

FMVSNet3		92.69 310	91.58 320	95.99 274	98.29 198	97.42 115	99.26 299	97.62 283	89.80 343	89.68 336	95.32 386	81.62 323	96.27 409	87.01 383	85.65 361	94.29 350

PMMVS		96.76 156	96.76 140	96.76 251	98.28 200	92.10 319	99.91 108	97.98 242	94.12 166	99.53 72	99.39 148	86.93 246	98.73 247	96.95 197	97.73 193	99.45 186

hse-mvs2		94.38 262	94.08 253	95.31 301	98.27 201	90.02 374	99.29 295	98.56 112	95.90 99	98.77 127	98.00 290	90.89 185	98.26 301	97.80 164	69.20 458	97.64 304

PVSNet_0	88.03 19	91.80 330	90.27 344	96.38 266	98.27 201	90.46 365	99.94 90	99.61 13	93.99 174	86.26 405	97.39 309	71.13 415	99.89 117	98.77 105	67.05 464	98.79 266

UA-Net		96.54 171	95.96 179	98.27 149	98.23 203	95.71 193	98.00 407	98.45 142	93.72 189	98.41 150	99.27 162	88.71 220	99.66 170	91.19 316	97.69 194	99.44 189

test_cas_vis1_n_1920		96.59 168	96.23 163	97.65 195	98.22 204	94.23 259	99.99 5	97.25 339	97.77 29	99.58 68	99.08 184	77.10 366	99.97 63	97.64 172	99.45 127	98.74 269

FE-MVS		95.70 216	95.01 226	97.79 182	98.21 205	94.57 243	95.03 455	98.69 81	88.90 359	97.50 186	96.19 348	92.60 146	99.49 184	89.99 341	97.94 191	99.31 212

GG-mvs-BLEND				98.54 127	98.21 205	98.01 83	93.87 460	98.52 127		97.92 170	97.92 295	99.02 3	97.94 321	98.17 142	99.58 109	99.67 129

mvs_anonymous		95.65 218	95.03 225	97.53 209	98.19 207	95.74 191	99.33 284	97.49 301	90.87 311	90.47 322	97.10 316	88.23 223	97.16 353	95.92 223	97.66 197	99.68 127

MVS_Test		96.46 174	95.74 192	98.61 116	98.18 208	97.23 122	99.31 288	97.15 354	91.07 307	98.84 121	97.05 320	88.17 224	98.97 216	94.39 256	97.50 199	99.61 146

BH-RMVSNet		95.18 231	94.31 246	97.80 180	98.17 209	95.23 222	99.76 181	97.53 296	92.52 253	94.27 279	99.25 168	76.84 373	98.80 237	90.89 325	99.54 111	99.35 203

dongtai		91.55 336	91.13 329	92.82 388	98.16 210	86.35 417	99.47 263	98.51 130	83.24 429	85.07 415	97.56 303	90.33 194	94.94 439	76.09 451	91.73 310	97.18 315

RPSCF		91.80 330	92.79 294	88.83 432	98.15 211	69.87 471	98.11 403	96.60 414	83.93 424	94.33 277	99.27 162	79.60 347	99.46 188	91.99 305	93.16 307	97.18 315

ETV-MVS		97.92 84	97.80 88	98.25 150	98.14 212	96.48 158	99.98 21	97.63 280	95.61 110	99.29 95	99.46 139	92.55 148	98.82 230	99.02 88	98.54 169	99.46 181

IS-MVSNet		96.29 187	95.90 186	97.45 215	98.13 213	94.80 237	99.08 314	97.61 286	92.02 275	95.54 258	98.96 206	90.64 188	98.08 310	93.73 278	97.41 203	99.47 179

test_fmvsmconf_n		98.43 51	98.32 47	98.78 102	98.12 214	96.41 161	99.99 5	98.83 66	98.22 7	99.67 51	99.64 118	91.11 178	99.94 93	99.67 52	99.62 100	99.98 56

fmvsm_s_conf0.1_n_2		97.25 128	96.85 135	98.43 139	98.08 215	98.08 78	99.92 100	97.76 269	98.05 20	99.65 53	99.58 127	80.88 332	99.93 103	99.59 56	98.17 180	97.29 313

ab-mvs		94.69 248	93.42 275	98.51 132	98.07 216	96.26 168	96.49 439	98.68 83	90.31 333	94.54 269	97.00 322	76.30 381	99.71 159	95.98 222	93.38 305	99.56 158

XVG-OURS-SEG-HR		94.79 243	94.70 238	95.08 306	98.05 217	89.19 385	99.08 314	97.54 294	93.66 190	94.87 267	99.58 127	78.78 355	99.79 144	97.31 180	93.40 304	96.25 322

EIA-MVS		97.53 114	97.46 104	97.76 188	98.04 218	94.84 234	99.98 21	97.61 286	94.41 153	97.90 171	99.59 124	92.40 154	98.87 224	98.04 151	99.13 146	99.59 149

XVG-OURS		94.82 240	94.74 237	95.06 307	98.00 219	89.19 385	99.08 314	97.55 292	94.10 167	94.71 268	99.62 122	80.51 338	99.74 155	96.04 221	93.06 309	96.25 322

mvsmamba		96.94 146	96.73 142	97.55 207	97.99 220	94.37 255	99.62 228	97.70 272	93.13 213	98.42 149	97.92 295	88.02 225	98.75 245	98.78 104	99.01 152	99.52 169

dp		95.05 234	94.43 241	96.91 244	97.99 220	92.73 304	96.29 444	97.98 242	89.70 344	95.93 245	94.67 413	93.83 110	98.45 274	86.91 386	96.53 239	99.54 163

tpmrst		96.27 189	95.98 175	97.13 236	97.96 222	93.15 292	96.34 442	98.17 218	92.07 271	98.71 133	95.12 396	93.91 105	98.73 247	94.91 244	96.62 237	99.50 175

TR-MVS		94.54 253	93.56 270	97.49 214	97.96 222	94.34 256	98.71 365	97.51 299	90.30 334	94.51 271	98.69 242	75.56 387	98.77 241	92.82 293	95.99 252	99.35 203

Vis-MVSNet (Re-imp)		96.32 184	95.98 175	97.35 228	97.93 224	94.82 236	99.47 263	98.15 226	91.83 280	95.09 265	99.11 182	91.37 172	97.47 337	93.47 282	97.43 200	99.74 118

MDTV_nov1_ep13			95.69 194		97.90 225	94.15 262	95.98 450	98.44 147	93.12 214	97.98 168	95.74 361	95.10 60	98.58 264	90.02 340	96.92 229

Fast-Effi-MVS+		95.02 236	94.19 248	97.52 211	97.88 226	94.55 244	99.97 39	97.08 370	88.85 361	94.47 272	97.96 294	84.59 289	98.41 278	89.84 343	97.10 220	99.59 149

ADS-MVSNet2		93.80 280	93.88 260	93.55 371	97.87 227	85.94 421	94.24 456	96.84 400	90.07 337	96.43 230	94.48 418	90.29 196	95.37 432	87.44 373	97.23 211	99.36 199

ADS-MVSNet		94.79 243	94.02 255	97.11 238	97.87 227	93.79 271	94.24 456	98.16 223	90.07 337	96.43 230	94.48 418	90.29 196	98.19 304	87.44 373	97.23 211	99.36 199

Effi-MVS+		96.30 186	95.69 194	98.16 154	97.85 229	96.26 168	97.41 419	97.21 346	90.37 330	98.65 136	98.58 257	86.61 252	98.70 253	97.11 188	97.37 205	99.52 169

PatchmatchNet		95.94 200	95.45 202	97.39 223	97.83 230	94.41 251	96.05 448	98.40 176	92.86 225	97.09 200	95.28 391	94.21 97	98.07 312	89.26 351	98.11 185	99.70 124
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 251	93.61 265	97.74 190	97.82 231	96.26 168	99.96 53	97.78 265	85.76 405	94.00 282	97.54 304	76.95 372	99.21 197	97.23 185	95.43 275	97.76 301

1112_ss		96.01 197	95.20 217	98.42 141	97.80 232	96.41 161	99.65 221	96.66 411	92.71 236	92.88 296	99.40 146	92.16 160	99.30 192	91.92 307	93.66 300	99.55 159

E3new		96.75 158	96.43 156	97.71 191	97.79 233	94.83 235	99.80 166	97.33 319	93.52 195	97.49 187	99.31 156	87.73 228	98.83 227	97.52 175	97.40 204	99.48 178

Test_1112_low_res		95.72 212	94.83 231	98.42 141	97.79 233	96.41 161	99.65 221	96.65 412	92.70 237	92.86 297	96.13 352	92.15 161	99.30 192	91.88 308	93.64 301	99.55 159

Effi-MVS+-dtu		94.53 255	95.30 213	92.22 396	97.77 235	82.54 444	99.59 237	97.06 376	94.92 127	95.29 262	95.37 384	85.81 263	97.89 322	94.80 247	97.07 221	96.23 324

tpm cat1		93.51 289	92.52 304	96.47 259	97.77 235	91.47 346	96.13 446	98.06 233	80.98 443	92.91 295	93.78 427	89.66 201	98.87 224	87.03 382	96.39 244	99.09 239

FA-MVS(test-final)		95.86 203	95.09 222	98.15 157	97.74 237	95.62 199	96.31 443	98.17 218	91.42 296	96.26 235	96.13 352	90.56 190	99.47 187	92.18 299	97.07 221	99.35 203

xiu_mvs_v1_base_debu		97.43 117	97.06 123	98.55 123	97.74 237	98.14 73	99.31 288	97.86 256	96.43 81	99.62 60	99.69 104	85.56 270	99.68 164	99.05 81	98.31 175	97.83 297

xiu_mvs_v1_base		97.43 117	97.06 123	98.55 123	97.74 237	98.14 73	99.31 288	97.86 256	96.43 81	99.62 60	99.69 104	85.56 270	99.68 164	99.05 81	98.31 175	97.83 297

xiu_mvs_v1_base_debi		97.43 117	97.06 123	98.55 123	97.74 237	98.14 73	99.31 288	97.86 256	96.43 81	99.62 60	99.69 104	85.56 270	99.68 164	99.05 81	98.31 175	97.83 297

EPP-MVSNet		96.69 163	96.60 148	96.96 243	97.74 237	93.05 295	99.37 279	98.56 112	88.75 363	95.83 249	99.01 194	96.01 39	98.56 266	96.92 198	97.20 213	99.25 224

gg-mvs-nofinetune		93.51 289	91.86 316	98.47 134	97.72 242	97.96 88	92.62 466	98.51 130	74.70 463	97.33 193	69.59 481	98.91 4	97.79 325	97.77 169	99.56 110	99.67 129

IB-MVS	92.85 6	94.99 237	93.94 258	98.16 154	97.72 242	95.69 196	99.99 5	98.81 67	94.28 161	92.70 298	96.90 324	95.08 61	99.17 203	96.07 220	73.88 443	99.60 148
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
thisisatest0515		97.41 122	97.02 128	98.59 120	97.71 244	97.52 108	99.97 39	98.54 122	91.83 280	97.45 188	99.04 190	97.50 9	99.10 208	94.75 249	96.37 245	99.16 231

VortexMVS		94.11 269	93.50 272	95.94 277	97.70 245	96.61 153	99.35 282	97.18 349	93.52 195	89.57 343	95.74 361	87.55 233	96.97 370	95.76 228	85.13 368	94.23 355

viewdifsd2359ckpt09		96.21 191	95.77 190	97.53 209	97.69 246	94.50 247	99.78 170	97.23 344	92.88 224	96.58 219	99.26 166	84.85 282	98.66 260	96.61 210	97.02 226	99.43 190

Syy-MVS		90.00 371	90.63 336	88.11 439	97.68 247	74.66 467	99.71 204	98.35 189	90.79 318	92.10 304	98.67 243	79.10 353	93.09 459	63.35 474	95.95 256	96.59 320

myMVS_eth3d		94.46 260	94.76 236	93.55 371	97.68 247	90.97 350	99.71 204	98.35 189	90.79 318	92.10 304	98.67 243	92.46 153	93.09 459	87.13 379	95.95 256	96.59 320

test_fmvs1_n		94.25 268	94.36 243	93.92 358	97.68 247	83.70 434	99.90 114	96.57 415	97.40 40	99.67 51	98.88 218	61.82 451	99.92 109	98.23 140	99.13 146	98.14 290

fmvsm_s_conf0.5_n_6		98.27 63	97.96 75	99.23 57	97.66 250	98.11 77	99.98 21	98.64 90	97.85 27	99.87 13	99.72 94	88.86 217	99.93 103	99.64 54	99.36 135	99.63 141

RRT-MVS		96.24 190	95.68 196	97.94 171	97.65 251	94.92 232	99.27 298	97.10 366	92.79 231	97.43 189	97.99 292	81.85 318	99.37 191	98.46 125	98.57 166	99.53 167

diffmvs		97.00 143	96.64 146	98.09 161	97.64 252	96.17 177	99.81 162	97.19 347	94.67 139	98.95 116	99.28 159	86.43 253	98.76 243	98.37 130	97.42 202	99.33 206
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewcassd2359sk11		96.59 168	96.23 163	97.66 194	97.63 253	94.70 240	99.77 175	97.33 319	93.41 200	97.34 192	99.17 177	86.72 247	98.83 227	97.40 178	97.32 208	99.46 181

viewdifsd2359ckpt13		96.19 192	95.77 190	97.45 215	97.62 254	94.40 253	99.70 211	97.23 344	92.76 233	96.63 216	99.05 189	84.96 281	98.64 261	96.65 209	97.35 206	99.31 212

Vis-MVSNet		95.72 212	95.15 220	97.45 215	97.62 254	94.28 257	99.28 296	98.24 209	94.27 163	96.84 211	98.94 213	79.39 348	98.76 243	93.25 284	98.49 170	99.30 215
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 136	96.72 143	98.22 151	97.60 256	96.70 146	99.92 100	98.54 122	91.11 305	97.07 202	98.97 204	97.47 12	99.03 211	93.73 278	96.09 250	98.92 258

GDP-MVS		97.88 86	97.59 100	98.75 105	97.59 257	97.81 95	99.95 72	97.37 314	94.44 149	99.08 107	99.58 127	97.13 25	99.08 209	94.99 239	98.17 180	99.37 197

miper_ehance_all_eth		93.16 297	92.60 298	94.82 317	97.57 258	93.56 282	99.50 257	97.07 375	88.75 363	88.85 360	95.52 373	90.97 181	96.74 384	90.77 327	84.45 373	94.17 362

guyue		97.15 134	96.82 137	98.15 157	97.56 259	96.25 172	99.71 204	97.84 259	95.75 106	98.13 165	98.65 246	87.58 232	98.82 230	98.29 136	97.91 192	99.36 199

viewmanbaseed2359cas		96.45 175	96.07 169	97.59 205	97.55 260	94.59 242	99.70 211	97.33 319	93.62 192	97.00 206	99.32 153	85.57 269	98.71 250	97.26 184	97.33 207	99.47 179

testing3		93.92 274	94.23 247	92.99 385	97.54 261	90.23 369	99.99 5	99.16 33	90.57 324	91.33 312	98.63 250	92.99 132	92.52 463	82.46 416	95.39 276	96.22 325

SSM_0404		95.75 211	95.16 219	97.50 213	97.53 262	95.39 210	99.11 310	97.25 339	90.81 314	95.27 263	98.83 232	84.74 285	98.67 257	95.24 234	97.69 194	98.45 279

LCM-MVSNet-Re		92.31 319	92.60 298	91.43 405	97.53 262	79.27 461	99.02 328	91.83 476	92.07 271	80.31 439	94.38 421	83.50 301	95.48 429	97.22 186	97.58 198	99.54 163

GBi-Net		90.88 347	89.82 353	94.08 350	97.53 262	91.97 320	98.43 384	96.95 389	87.05 388	89.68 336	94.72 409	71.34 412	96.11 415	87.01 383	85.65 361	94.17 362

test1		90.88 347	89.82 353	94.08 350	97.53 262	91.97 320	98.43 384	96.95 389	87.05 388	89.68 336	94.72 409	71.34 412	96.11 415	87.01 383	85.65 361	94.17 362

FMVSNet2		91.02 344	89.56 358	95.41 297	97.53 262	95.74 191	98.98 331	97.41 309	87.05 388	88.43 371	95.00 403	71.34 412	96.24 411	85.12 398	85.21 366	94.25 353

tttt0517		96.85 150	96.49 152	97.92 172	97.48 267	95.89 185	99.85 144	98.54 122	90.72 322	96.63 216	98.93 216	97.47 12	99.02 212	93.03 291	95.76 262	98.85 262

BP-MVS1		98.33 59	98.18 56	98.81 100	97.44 268	97.98 85	99.96 53	98.17 218	94.88 129	98.77 127	99.59 124	97.59 7	99.08 209	98.24 139	98.93 154	99.36 199

casdiffmvs_mvg		96.43 176	95.94 183	97.89 176	97.44 268	95.47 203	99.86 141	97.29 334	93.35 201	96.03 242	99.19 175	85.39 274	98.72 249	97.89 161	97.04 223	99.49 177
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E2		96.36 181	95.95 181	97.60 202	97.41 270	94.52 245	99.71 204	97.33 319	93.20 207	97.02 203	99.07 186	85.37 275	98.82 230	97.27 181	97.14 217	99.46 181

EC-MVSNet		97.38 124	97.24 117	97.80 180	97.41 270	95.64 198	99.99 5	97.06 376	94.59 140	99.63 57	99.32 153	89.20 212	98.14 306	98.76 106	99.23 142	99.62 142

viewdifsd2359ckpt07		95.83 206	95.42 204	97.07 239	97.40 272	93.04 296	99.60 235	97.24 342	92.39 259	96.09 241	99.14 181	83.07 309	98.93 220	97.02 191	96.87 230	99.23 227

c3_l		92.53 314	91.87 315	94.52 329	97.40 272	92.99 298	99.40 271	96.93 394	87.86 378	88.69 363	95.44 378	89.95 199	96.44 400	90.45 333	80.69 407	94.14 371

viewmambaseed2359dif		95.92 202	95.55 200	97.04 240	97.38 274	93.41 287	99.78 170	96.97 387	91.14 304	96.58 219	99.27 162	84.85 282	98.75 245	96.87 201	97.12 219	98.97 253

fmvsm_s_conf0.1_n		97.30 125	97.21 119	97.60 202	97.38 274	94.40 253	99.90 114	98.64 90	96.47 80	99.51 76	99.65 117	84.99 280	99.93 103	99.22 75	99.09 149	98.46 278

E3		96.36 181	95.95 181	97.60 202	97.37 276	94.52 245	99.71 204	97.33 319	93.18 209	97.02 203	99.07 186	85.45 273	98.82 230	97.27 181	97.14 217	99.46 181

CDS-MVSNet		96.34 183	96.07 169	97.13 236	97.37 276	94.96 230	99.53 252	97.91 251	91.55 288	95.37 261	98.32 277	95.05 63	97.13 356	93.80 274	95.75 263	99.30 215
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 160	96.26 162	98.16 154	97.36 278	96.48 158	99.96 53	98.29 202	91.93 276	95.77 250	98.07 288	95.54 49	98.29 295	90.55 331	98.89 155	99.70 124

miper_lstm_enhance		91.81 327	91.39 326	93.06 384	97.34 279	89.18 387	99.38 277	96.79 405	86.70 395	87.47 387	95.22 393	90.00 198	95.86 424	88.26 363	81.37 396	94.15 368

baseline		96.43 176	95.98 175	97.76 188	97.34 279	95.17 226	99.51 255	97.17 351	93.92 179	96.90 209	99.28 159	85.37 275	98.64 261	97.50 176	96.86 232	99.46 181

cl____		92.31 319	91.58 320	94.52 329	97.33 281	92.77 300	99.57 242	96.78 406	86.97 392	87.56 385	95.51 374	89.43 205	96.62 390	88.60 356	82.44 388	94.16 367

SD_0403		92.63 313	93.38 279	90.40 419	97.32 282	77.91 463	97.75 414	98.03 238	91.89 277	90.83 318	98.29 281	82.00 315	93.79 452	88.51 360	95.75 263	99.52 169

DIV-MVS_self_test		92.32 318	91.60 319	94.47 333	97.31 283	92.74 302	99.58 239	96.75 407	86.99 391	87.64 383	95.54 371	89.55 204	96.50 395	88.58 357	82.44 388	94.17 362

casdiffmvs		96.42 178	95.97 178	97.77 186	97.30 284	94.98 229	99.84 149	97.09 369	93.75 188	96.58 219	99.26 166	85.07 278	98.78 240	97.77 169	97.04 223	99.54 163
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GeoE		94.36 265	93.48 273	96.99 242	97.29 285	93.54 283	99.96 53	96.72 409	88.35 372	93.43 286	98.94 213	82.05 314	98.05 313	88.12 368	96.48 242	99.37 197

eth_miper_zixun_eth		92.41 317	91.93 313	93.84 362	97.28 286	90.68 359	98.83 354	96.97 387	88.57 368	89.19 355	95.73 364	89.24 211	96.69 388	89.97 342	81.55 394	94.15 368

MVSFormer		96.94 146	96.60 148	97.95 168	97.28 286	97.70 101	99.55 249	97.27 336	91.17 301	99.43 82	99.54 133	90.92 182	96.89 375	94.67 252	99.62 100	99.25 224

lupinMVS		97.85 90	97.60 98	98.62 115	97.28 286	97.70 101	99.99 5	97.55 292	95.50 115	99.43 82	99.67 113	90.92 182	98.71 250	98.40 127	99.62 100	99.45 186

diffmvs_AUTHOR		96.75 158	96.41 158	97.79 182	97.20 289	95.46 204	99.69 214	97.15 354	94.46 145	98.78 125	99.21 173	85.64 267	98.77 241	98.27 137	97.31 209	99.13 235

mamba_0408		94.98 238	94.09 251	97.64 196	97.14 290	95.31 215	93.48 463	97.08 370	90.48 326	94.40 273	98.62 251	84.49 290	98.67 257	93.99 265	97.18 214	98.93 255

SSM_04072		94.77 245	94.09 251	96.82 248	97.14 290	95.31 215	93.48 463	97.08 370	90.48 326	94.40 273	98.62 251	84.49 290	96.21 412	93.99 265	97.18 214	98.93 255

SSM_0407		95.62 219	94.95 228	97.61 201	97.14 290	95.31 215	99.00 329	97.25 339	90.81 314	94.40 273	98.83 232	84.74 285	98.58 264	95.24 234	97.18 214	98.93 255

SCA		94.69 248	93.81 262	97.33 229	97.10 293	94.44 248	98.86 351	98.32 196	93.30 204	96.17 240	95.59 369	76.48 379	97.95 319	91.06 319	97.43 200	99.59 149

viewmacassd2359aftdt		95.93 201	95.45 202	97.36 226	97.09 294	94.12 264	99.57 242	97.26 338	93.05 218	96.50 223	99.17 177	82.76 310	98.68 255	96.61 210	97.04 223	99.28 219

KinetiMVS		96.10 193	95.29 214	98.53 129	97.08 295	97.12 128	99.56 246	98.12 229	94.78 132	98.44 147	98.94 213	80.30 342	99.39 190	91.56 312	98.79 161	99.06 243

TAMVS		95.85 204	95.58 198	96.65 256	97.07 296	93.50 284	99.17 306	97.82 261	91.39 298	95.02 266	98.01 289	92.20 159	97.30 346	93.75 277	95.83 260	99.14 234

Fast-Effi-MVS+-dtu		93.72 284	93.86 261	93.29 376	97.06 297	86.16 418	99.80 166	96.83 401	92.66 240	92.58 299	97.83 300	81.39 324	97.67 330	89.75 344	96.87 230	96.05 327

E4		96.01 197	95.53 201	97.44 218	97.05 298	94.23 259	99.57 242	97.30 327	92.72 234	96.47 225	99.03 191	83.98 298	98.83 227	96.92 198	96.77 233	99.27 221

E5		95.83 206	95.39 206	97.15 233	97.03 299	93.59 278	99.32 287	97.30 327	92.58 247	96.45 226	99.00 198	83.37 304	98.81 234	96.81 203	96.65 236	99.04 246

CostFormer		96.10 193	95.88 187	96.78 250	97.03 299	92.55 310	97.08 428	97.83 260	90.04 339	98.72 132	94.89 407	95.01 65	98.29 295	96.54 213	95.77 261	99.50 175

test_fmvsmvis_n_1920		97.67 109	97.59 100	97.91 174	97.02 301	95.34 213	99.95 72	98.45 142	97.87 26	97.02 203	99.59 124	89.64 202	99.98 50	99.41 68	99.34 137	98.42 281

test-LLR		96.47 173	96.04 171	97.78 184	97.02 301	95.44 205	99.96 53	98.21 213	94.07 169	95.55 256	96.38 341	93.90 106	98.27 299	90.42 334	98.83 159	99.64 135

test-mter		96.39 179	95.93 184	97.78 184	97.02 301	95.44 205	99.96 53	98.21 213	91.81 282	95.55 256	96.38 341	95.17 58	98.27 299	90.42 334	98.83 159	99.64 135

E6new		95.83 206	95.39 206	97.14 234	97.00 304	93.58 279	99.31 288	97.30 327	92.57 248	96.45 226	99.01 194	83.44 302	98.81 234	96.80 204	96.66 234	99.04 246

E6		95.83 206	95.39 206	97.14 234	97.00 304	93.58 279	99.31 288	97.30 327	92.57 248	96.45 226	99.01 194	83.44 302	98.81 234	96.80 204	96.66 234	99.04 246

icg_test_0407_2		95.04 235	94.78 235	95.84 283	96.97 306	91.64 338	98.63 373	97.12 359	92.33 262	95.60 254	98.88 218	85.65 265	96.56 393	92.12 300	95.70 266	99.32 208

IMVS_0407		95.21 230	94.80 234	96.46 261	96.97 306	91.64 338	98.81 356	97.12 359	92.33 262	95.60 254	98.88 218	85.65 265	98.42 276	92.12 300	95.70 266	99.32 208

IMVS_0404		93.83 276	93.17 286	95.80 285	96.97 306	91.64 338	97.78 413	97.12 359	92.33 262	90.87 317	98.88 218	76.78 374	96.43 401	92.12 300	95.70 266	99.32 208

IMVS_0403		95.25 228	94.81 233	96.58 258	96.97 306	91.64 338	98.97 336	97.12 359	92.33 262	95.43 259	98.88 218	85.78 264	98.79 238	92.12 300	95.70 266	99.32 208

gm-plane-assit					96.97 306	93.76 273			91.47 292		98.96 206		98.79 238	94.92 242

WB-MVSnew		92.90 303	92.77 295	93.26 378	96.95 311	93.63 277	99.71 204	98.16 223	91.49 289	94.28 278	98.14 285	81.33 326	96.48 398	79.47 433	95.46 273	89.68 460

QAPM		95.40 224	94.17 249	99.10 78	96.92 312	97.71 99	99.40 271	98.68 83	89.31 347	88.94 359	98.89 217	82.48 312	99.96 75	93.12 290	99.83 81	99.62 142

KD-MVS_2432*1600		88.00 393	86.10 397	93.70 367	96.91 313	94.04 265	97.17 425	97.12 359	84.93 416	81.96 429	92.41 441	92.48 151	94.51 445	79.23 434	52.68 480	92.56 429

miper_refine_blended		88.00 393	86.10 397	93.70 367	96.91 313	94.04 265	97.17 425	97.12 359	84.93 416	81.96 429	92.41 441	92.48 151	94.51 445	79.23 434	52.68 480	92.56 429

tpm2		95.47 222	95.18 218	96.35 267	96.91 313	91.70 336	96.96 431	97.93 247	88.04 376	98.44 147	95.40 380	93.32 121	97.97 316	94.00 264	95.61 271	99.38 195

FMVSNet5		88.32 389	87.47 391	90.88 408	96.90 316	88.39 401	97.28 422	95.68 437	82.60 436	84.67 417	92.40 443	79.83 345	91.16 468	76.39 450	81.51 395	93.09 420

3Dnovator+	91.53 11	96.31 185	95.24 215	99.52 32	96.88 317	98.64 58	99.72 200	98.24 209	95.27 120	88.42 373	98.98 202	82.76 310	99.94 93	97.10 189	99.83 81	99.96 74

Patchmatch-test		92.65 312	91.50 323	96.10 273	96.85 318	90.49 364	91.50 471	97.19 347	82.76 435	90.23 323	95.59 369	95.02 64	98.00 315	77.41 445	96.98 228	99.82 106

MVS		96.60 167	95.56 199	99.72 14	96.85 318	99.22 21	98.31 390	98.94 44	91.57 287	90.90 316	99.61 123	86.66 251	99.96 75	97.36 179	99.88 77	99.99 24

3Dnovator	91.47 12	96.28 188	95.34 211	99.08 81	96.82 320	97.47 113	99.45 268	98.81 67	95.52 114	89.39 346	99.00 198	81.97 316	99.95 84	97.27 181	99.83 81	99.84 103

EI-MVSNet		93.73 283	93.40 278	94.74 318	96.80 321	92.69 305	99.06 319	97.67 275	88.96 356	91.39 310	99.02 192	88.75 219	97.30 346	91.07 318	87.85 344	94.22 357

CVMVSNet		94.68 250	94.94 229	93.89 361	96.80 321	86.92 415	99.06 319	98.98 41	94.45 146	94.23 280	99.02 192	85.60 268	95.31 434	90.91 324	95.39 276	99.43 190

IterMVS-LS		92.69 310	92.11 309	94.43 337	96.80 321	92.74 302	99.45 268	96.89 397	88.98 354	89.65 339	95.38 383	88.77 218	96.34 406	90.98 322	82.04 391	94.22 357
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AstraMVS		96.57 170	96.46 155	96.91 244	96.79 324	92.50 311	99.90 114	97.38 311	96.02 98	97.79 179	99.32 153	86.36 255	98.99 213	98.26 138	96.33 246	99.23 227

IterMVS		90.91 346	90.17 348	93.12 381	96.78 325	90.42 367	98.89 345	97.05 379	89.03 351	86.49 400	95.42 379	76.59 377	95.02 436	87.22 378	84.09 376	93.93 391
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 151	95.96 179	99.48 39	96.74 326	98.52 62	98.31 390	98.86 59	95.82 103	89.91 330	98.98 202	87.49 235	99.96 75	97.80 164	99.73 91	99.96 74

IterMVS-SCA-FT		90.85 349	90.16 349	92.93 386	96.72 327	89.96 376	98.89 345	96.99 383	88.95 357	86.63 397	95.67 365	76.48 379	95.00 437	87.04 381	84.04 379	93.84 398

MVS-HIRNet		86.22 402	83.19 415	95.31 301	96.71 328	90.29 368	92.12 468	97.33 319	62.85 475	86.82 394	70.37 480	69.37 420	97.49 336	75.12 453	97.99 190	98.15 288

viewdifsd2359ckpt11		94.09 271	93.63 264	95.46 294	96.68 329	88.92 390	99.62 228	97.12 359	93.07 216	95.73 251	99.22 170	77.05 367	98.88 223	96.52 214	87.69 349	98.58 276

viewmsd2359difaftdt		94.09 271	93.64 263	95.46 294	96.68 329	88.92 390	99.62 228	97.13 358	93.07 216	95.73 251	99.22 170	77.05 367	98.89 222	96.52 214	87.70 348	98.58 276

VDDNet		93.12 298	91.91 314	96.76 251	96.67 331	92.65 308	98.69 368	98.21 213	82.81 434	97.75 181	99.28 159	61.57 452	99.48 185	98.09 148	94.09 295	98.15 288

dmvs_re		93.20 295	93.15 287	93.34 374	96.54 332	83.81 433	98.71 365	98.51 130	91.39 298	92.37 302	98.56 259	78.66 357	97.83 324	93.89 268	89.74 316	98.38 283

Elysia		94.50 257	93.38 279	97.85 178	96.49 333	96.70 146	98.98 331	97.78 265	90.81 314	96.19 238	98.55 261	73.63 403	98.98 214	89.41 345	98.56 167	97.88 295

StellarMVS		94.50 257	93.38 279	97.85 178	96.49 333	96.70 146	98.98 331	97.78 265	90.81 314	96.19 238	98.55 261	73.63 403	98.98 214	89.41 345	98.56 167	97.88 295

MIMVSNet		90.30 362	88.67 377	95.17 305	96.45 335	91.64 338	92.39 467	97.15 354	85.99 402	90.50 321	93.19 435	66.95 431	94.86 441	82.01 420	93.43 303	99.01 251

CR-MVSNet		93.45 292	92.62 297	95.94 277	96.29 336	92.66 306	92.01 469	96.23 423	92.62 242	96.94 207	93.31 433	91.04 179	96.03 420	79.23 434	95.96 254	99.13 235

RPMNet		89.76 375	87.28 392	97.19 232	96.29 336	92.66 306	92.01 469	98.31 198	70.19 470	96.94 207	85.87 473	87.25 240	99.78 146	62.69 475	95.96 254	99.13 235

tt0805		91.28 339	90.18 347	94.60 324	96.26 338	87.55 408	98.39 388	98.72 77	89.00 353	89.22 352	98.47 269	62.98 447	98.96 218	90.57 330	88.00 343	97.28 314

Patchmtry		89.70 376	88.49 380	93.33 375	96.24 339	89.94 379	91.37 472	96.23 423	78.22 453	87.69 382	93.31 433	91.04 179	96.03 420	80.18 432	82.10 390	94.02 381

test_vis1_rt		86.87 399	86.05 400	89.34 428	96.12 340	78.07 462	99.87 130	83.54 488	92.03 274	78.21 450	89.51 457	45.80 473	99.91 110	96.25 218	93.11 308	90.03 456

JIA-IIPM		91.76 333	90.70 334	94.94 311	96.11 341	87.51 409	93.16 465	98.13 228	75.79 459	97.58 183	77.68 478	92.84 137	97.97 316	88.47 361	96.54 238	99.33 206

OpenMVS	90.15 15	94.77 245	93.59 268	98.33 145	96.07 342	97.48 112	99.56 246	98.57 106	90.46 328	86.51 399	98.95 211	78.57 358	99.94 93	93.86 269	99.74 90	97.57 309

PAPM		98.60 37	98.42 38	99.14 72	96.05 343	98.96 27	99.90 114	99.35 24	96.68 71	98.35 154	99.66 115	96.45 35	98.51 269	99.45 65	99.89 74	99.96 74

CLD-MVS		94.06 273	93.90 259	94.55 328	96.02 344	90.69 358	99.98 21	97.72 271	96.62 75	91.05 315	98.85 230	77.21 365	98.47 270	98.11 146	89.51 322	94.48 334
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 359	88.75 376	95.25 303	95.99 345	90.16 371	91.22 473	97.54 294	76.80 455	97.26 196	86.01 472	91.88 166	96.07 419	66.16 470	95.91 258	99.51 173

ACMH+	89.98 16	90.35 360	89.54 359	92.78 390	95.99 345	86.12 419	98.81 356	97.18 349	89.38 346	83.14 425	97.76 301	68.42 425	98.43 275	89.11 352	86.05 359	93.78 401

DeepMVS_CX				82.92 450	95.98 347	58.66 481		96.01 429	92.72 234	78.34 449	95.51 374	58.29 459	98.08 310	82.57 415	85.29 364	92.03 437

ACMP	92.05 9	92.74 308	92.42 306	93.73 363	95.91 348	88.72 394	99.81 162	97.53 296	94.13 165	87.00 393	98.23 283	74.07 400	98.47 270	96.22 219	88.86 329	93.99 386
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 287	93.03 289	95.35 298	95.86 349	86.94 414	99.87 130	96.36 421	96.85 62	99.54 71	98.79 234	52.41 467	99.83 139	98.64 114	98.97 153	99.29 217

HQP-NCC					95.78 350		99.87 130		96.82 64	93.37 287

ACMP_Plane					95.78 350		99.87 130		96.82 64	93.37 287

HQP-MVS		94.61 252	94.50 240	94.92 312	95.78 350	91.85 325	99.87 130	97.89 252	96.82 64	93.37 287	98.65 246	80.65 336	98.39 282	97.92 158	89.60 317	94.53 330

NP-MVS					95.77 353	91.79 329					98.65 246

test_fmvsmconf0.1_n		97.74 103	97.44 107	98.64 114	95.76 354	96.20 174	99.94 90	98.05 235	98.17 13	98.89 120	99.42 141	87.65 230	99.90 112	99.50 61	99.60 107	99.82 106

plane_prior6					95.76 354	91.72 335						80.47 340

ACMM	91.95 10	92.88 304	92.52 304	93.98 357	95.75 356	89.08 389	99.77 175	97.52 298	93.00 219	89.95 329	97.99 292	76.17 383	98.46 273	93.63 281	88.87 328	94.39 342
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 276	92.84 291	96.80 249	95.73 357	93.57 281	99.88 127	97.24 342	92.57 248	92.92 294	96.66 333	78.73 356	97.67 330	87.75 371	94.06 296	99.17 230

plane_prior1					95.73 357

jason		97.24 129	96.86 134	98.38 144	95.73 357	97.32 117	99.97 39	97.40 310	95.34 118	98.60 141	99.54 133	87.70 229	98.56 266	97.94 157	99.47 124	99.25 224
jason: jason.
mmtdpeth		88.52 387	87.75 389	90.85 410	95.71 360	83.47 439	98.94 339	94.85 453	88.78 362	97.19 198	89.58 456	63.29 445	98.97 216	98.54 119	62.86 472	90.10 455

HQP_MVS		94.49 259	94.36 243	94.87 313	95.71 360	91.74 331	99.84 149	97.87 254	96.38 84	93.01 292	98.59 254	80.47 340	98.37 288	97.79 167	89.55 320	94.52 332

plane_prior7					95.71 360	91.59 344

ITE_SJBPF				92.38 393	95.69 363	85.14 425		95.71 436	92.81 228	89.33 349	98.11 286	70.23 418	98.42 276	85.91 393	88.16 341	93.59 409

fmvsm_s_conf0.1_n_a		97.09 138	96.90 131	97.63 199	95.65 364	94.21 261	99.83 156	98.50 136	96.27 91	99.65 53	99.64 118	84.72 287	99.93 103	99.04 84	98.84 158	98.74 269

ACMH	89.72 17	90.64 353	89.63 356	93.66 369	95.64 365	88.64 397	98.55 376	97.45 303	89.03 351	81.62 432	97.61 302	69.75 419	98.41 278	89.37 347	87.62 350	93.92 392
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 162	96.49 152	97.37 224	95.63 366	95.96 183	99.74 189	98.88 54	92.94 221	91.61 308	98.97 204	97.72 6	98.62 263	94.83 246	98.08 188	97.53 311

FMVSNet1		88.50 388	86.64 395	94.08 350	95.62 367	91.97 320	98.43 384	96.95 389	83.00 432	86.08 407	94.72 409	59.09 458	96.11 415	81.82 422	84.07 377	94.17 362

LuminaMVS		96.63 166	96.21 166	97.87 177	95.58 368	96.82 141	99.12 308	97.67 275	94.47 144	97.88 174	98.31 279	87.50 234	98.71 250	98.07 150	97.29 210	98.10 291

LPG-MVS_test		92.96 301	92.71 296	93.71 365	95.43 369	88.67 395	99.75 185	97.62 283	92.81 228	90.05 325	98.49 265	75.24 390	98.40 280	95.84 225	89.12 324	94.07 378

LGP-MVS_train				93.71 365	95.43 369	88.67 395		97.62 283	92.81 228	90.05 325	98.49 265	75.24 390	98.40 280	95.84 225	89.12 324	94.07 378

tpm		93.70 285	93.41 277	94.58 326	95.36 371	87.41 410	97.01 429	96.90 396	90.85 312	96.72 215	94.14 424	90.40 193	96.84 379	90.75 328	88.54 336	99.51 173

D2MVS		92.76 307	92.59 302	93.27 377	95.13 372	89.54 383	99.69 214	99.38 22	92.26 267	87.59 384	94.61 415	85.05 279	97.79 325	91.59 311	88.01 342	92.47 432

VPA-MVSNet		92.70 309	91.55 322	96.16 271	95.09 373	96.20 174	98.88 347	99.00 39	91.02 309	91.82 307	95.29 390	76.05 385	97.96 318	95.62 230	81.19 397	94.30 349

LTVRE_ROB	88.28 18	90.29 363	89.05 370	94.02 353	95.08 374	90.15 372	97.19 424	97.43 305	84.91 418	83.99 421	97.06 319	74.00 401	98.28 297	84.08 404	87.71 346	93.62 408
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
TinyColmap		87.87 395	86.51 396	91.94 399	95.05 375	85.57 423	97.65 415	94.08 463	84.40 422	81.82 431	96.85 328	62.14 450	98.33 291	80.25 431	86.37 357	91.91 439

test0.0.03 1		93.86 275	93.61 265	94.64 322	95.02 376	92.18 318	99.93 97	98.58 104	94.07 169	87.96 379	98.50 264	93.90 106	94.96 438	81.33 423	93.17 306	96.78 317

UniMVSNet (Re)		93.07 300	92.13 308	95.88 280	94.84 377	96.24 173	99.88 127	98.98 41	92.49 255	89.25 350	95.40 380	87.09 242	97.14 355	93.13 289	78.16 421	94.26 351

USDC		90.00 371	88.96 371	93.10 383	94.81 378	88.16 403	98.71 365	95.54 441	93.66 190	83.75 423	97.20 313	65.58 436	98.31 293	83.96 407	87.49 352	92.85 426

VPNet		91.81 327	90.46 338	95.85 282	94.74 379	95.54 202	98.98 331	98.59 102	92.14 269	90.77 320	97.44 306	68.73 423	97.54 335	94.89 245	77.89 423	94.46 335

FIs		94.10 270	93.43 274	96.11 272	94.70 380	96.82 141	99.58 239	98.93 48	92.54 251	89.34 348	97.31 310	87.62 231	97.10 359	94.22 263	86.58 355	94.40 341

UniMVSNet_ETH3D		90.06 370	88.58 379	94.49 332	94.67 381	88.09 404	97.81 412	97.57 291	83.91 425	88.44 369	97.41 307	57.44 460	97.62 332	91.41 313	88.59 335	97.77 300

UniMVSNet_NR-MVSNet		92.95 302	92.11 309	95.49 290	94.61 382	95.28 219	99.83 156	99.08 36	91.49 289	89.21 353	96.86 327	87.14 241	96.73 385	93.20 285	77.52 426	94.46 335

test_fmvs2		89.47 380	89.70 355	88.77 435	94.54 383	75.74 464	99.83 156	94.70 459	94.71 136	91.08 313	96.82 332	54.46 463	97.78 327	92.87 292	88.27 339	92.80 427

MonoMVSNet		94.82 240	94.43 241	95.98 275	94.54 383	90.73 357	99.03 326	97.06 376	93.16 211	93.15 291	95.47 377	88.29 222	97.57 333	97.85 162	91.33 314	99.62 142

WR-MVS		92.31 319	91.25 327	95.48 293	94.45 385	95.29 218	99.60 235	98.68 83	90.10 336	88.07 378	96.89 325	80.68 335	96.80 383	93.14 288	79.67 414	94.36 343

nrg030		93.51 289	92.53 303	96.45 262	94.36 386	97.20 123	99.81 162	97.16 353	91.60 286	89.86 332	97.46 305	86.37 254	97.68 329	95.88 224	80.31 410	94.46 335

tfpnnormal		89.29 383	87.61 390	94.34 340	94.35 387	94.13 263	98.95 338	98.94 44	83.94 423	84.47 418	95.51 374	74.84 395	97.39 338	77.05 448	80.41 408	91.48 442

FC-MVSNet-test		93.81 279	93.15 287	95.80 285	94.30 388	96.20 174	99.42 270	98.89 52	92.33 262	89.03 358	97.27 312	87.39 237	96.83 381	93.20 285	86.48 356	94.36 343

SSC-MVS3.2		89.59 378	88.66 378	92.38 393	94.29 389	86.12 419	99.49 259	97.66 278	90.28 335	88.63 366	95.18 394	64.46 441	96.88 377	85.30 397	82.66 385	94.14 371

MS-PatchMatch		90.65 352	90.30 343	91.71 404	94.22 390	85.50 424	98.24 395	97.70 272	88.67 365	86.42 402	96.37 343	67.82 428	98.03 314	83.62 409	99.62 100	91.60 440

WR-MVS_H		91.30 337	90.35 341	94.15 346	94.17 391	92.62 309	99.17 306	98.94 44	88.87 360	86.48 401	94.46 420	84.36 293	96.61 391	88.19 365	78.51 419	93.21 418

DU-MVS		92.46 316	91.45 325	95.49 290	94.05 392	95.28 219	99.81 162	98.74 76	92.25 268	89.21 353	96.64 335	81.66 321	96.73 385	93.20 285	77.52 426	94.46 335

NR-MVSNet		91.56 335	90.22 345	95.60 288	94.05 392	95.76 190	98.25 394	98.70 79	91.16 303	80.78 438	96.64 335	83.23 307	96.57 392	91.41 313	77.73 425	94.46 335

CP-MVSNet		91.23 341	90.22 345	94.26 342	93.96 394	92.39 314	99.09 312	98.57 106	88.95 357	86.42 402	96.57 338	79.19 351	96.37 404	90.29 337	78.95 416	94.02 381

XXY-MVS		91.82 326	90.46 338	95.88 280	93.91 395	95.40 209	98.87 350	97.69 274	88.63 367	87.87 380	97.08 317	74.38 399	97.89 322	91.66 310	84.07 377	94.35 346

PS-CasMVS		90.63 354	89.51 361	93.99 356	93.83 396	91.70 336	98.98 331	98.52 127	88.48 369	86.15 406	96.53 340	75.46 388	96.31 408	88.83 354	78.86 418	93.95 389

test_0402		85.58 404	83.94 409	90.50 416	93.81 397	85.04 426	98.55 376	95.20 450	76.01 457	79.72 444	95.13 395	64.15 443	96.26 410	66.04 471	86.88 354	90.21 453

XVG-ACMP-BASELINE		91.22 342	90.75 333	92.63 392	93.73 398	85.61 422	98.52 380	97.44 304	92.77 232	89.90 331	96.85 328	66.64 433	98.39 282	92.29 297	88.61 333	93.89 394

TranMVSNet+NR-MVSNet		91.68 334	90.61 337	94.87 313	93.69 399	93.98 268	99.69 214	98.65 87	91.03 308	88.44 369	96.83 331	80.05 344	96.18 413	90.26 338	76.89 434	94.45 340

TransMVSNet (Re)		87.25 397	85.28 404	93.16 380	93.56 400	91.03 349	98.54 378	94.05 465	83.69 427	81.09 436	96.16 349	75.32 389	96.40 403	76.69 449	68.41 460	92.06 436

v10		90.25 364	88.82 373	94.57 327	93.53 401	93.43 286	99.08 314	96.87 399	85.00 415	87.34 391	94.51 416	80.93 331	97.02 369	82.85 414	79.23 415	93.26 416

testgi		89.01 385	88.04 386	91.90 400	93.49 402	84.89 428	99.73 196	95.66 438	93.89 183	85.14 413	98.17 284	59.68 456	94.66 444	77.73 444	88.88 327	96.16 326

v8		90.54 356	89.17 366	94.66 321	93.43 403	93.40 289	99.20 303	96.94 393	85.76 405	87.56 385	94.51 416	81.96 317	97.19 352	84.94 400	78.25 420	93.38 414

V42		91.28 339	90.12 350	94.74 318	93.42 404	93.46 285	99.68 217	97.02 380	87.36 384	89.85 334	95.05 398	81.31 327	97.34 341	87.34 376	80.07 412	93.40 412

pm-mvs1		89.36 382	87.81 388	94.01 354	93.40 405	91.93 323	98.62 374	96.48 419	86.25 400	83.86 422	96.14 351	73.68 402	97.04 365	86.16 390	75.73 439	93.04 422

v1144		91.09 343	89.83 352	94.87 313	93.25 406	93.69 276	99.62 228	96.98 385	86.83 394	89.64 340	94.99 404	80.94 330	97.05 362	85.08 399	81.16 398	93.87 396

v1192		90.62 355	89.25 365	94.72 320	93.13 407	93.07 293	99.50 257	97.02 380	86.33 399	89.56 344	95.01 401	79.22 350	97.09 361	82.34 418	81.16 398	94.01 383

v2v482		91.30 337	90.07 351	95.01 308	93.13 407	93.79 271	99.77 175	97.02 380	88.05 375	89.25 350	95.37 384	80.73 334	97.15 354	87.28 377	80.04 413	94.09 377

OPM-MVS		93.21 294	92.80 293	94.44 335	93.12 409	90.85 356	99.77 175	97.61 286	96.19 94	91.56 309	98.65 246	75.16 394	98.47 270	93.78 276	89.39 323	93.99 386
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 350	89.52 360	94.59 325	93.11 410	92.77 300	99.56 246	96.99 383	86.38 398	89.82 335	94.95 406	80.50 339	97.10 359	83.98 406	80.41 408	93.90 393

PEN-MVS		90.19 366	89.06 369	93.57 370	93.06 411	90.90 354	99.06 319	98.47 139	88.11 374	85.91 408	96.30 345	76.67 375	95.94 423	87.07 380	76.91 433	93.89 394

v1240		90.20 365	88.79 374	94.44 335	93.05 412	92.27 316	99.38 277	96.92 395	85.89 403	89.36 347	94.87 408	77.89 363	97.03 367	80.66 427	81.08 401	94.01 383

FE-MVSNET3		92.78 306	91.73 317	95.92 279	93.03 413	96.82 141	99.83 156	97.79 262	90.58 323	90.09 324	95.04 399	84.75 284	96.72 387	88.20 364	86.23 358	94.23 355

v148		90.70 351	89.63 356	93.92 358	92.97 414	90.97 350	99.75 185	96.89 397	87.51 381	88.27 375	95.01 401	81.67 320	97.04 365	87.40 375	77.17 431	93.75 402

v1921920		90.46 357	89.12 367	94.50 331	92.96 415	92.46 312	99.49 259	96.98 385	86.10 401	89.61 342	95.30 387	78.55 359	97.03 367	82.17 419	80.89 406	94.01 383

MVStest1		85.03 410	82.76 419	91.83 401	92.95 416	89.16 388	98.57 375	94.82 454	71.68 468	68.54 472	95.11 397	83.17 308	95.66 427	74.69 454	65.32 467	90.65 449

tt0320-xc		82.94 425	80.35 432	90.72 414	92.90 417	83.54 437	96.85 434	94.73 457	63.12 474	79.85 443	93.77 428	49.43 471	95.46 430	80.98 426	71.54 449	93.16 419

Baseline_NR-MVSNet		90.33 361	89.51 361	92.81 389	92.84 418	89.95 377	99.77 175	93.94 466	84.69 420	89.04 357	95.66 366	81.66 321	96.52 394	90.99 321	76.98 432	91.97 438

test_method		80.79 431	79.70 434	84.08 447	92.83 419	67.06 473	99.51 255	95.42 443	54.34 479	81.07 437	93.53 430	44.48 474	92.22 465	78.90 439	77.23 430	92.94 424

pmmvs4		92.10 323	91.07 331	95.18 304	92.82 420	94.96 230	99.48 262	96.83 401	87.45 383	88.66 365	96.56 339	83.78 299	96.83 381	89.29 350	84.77 371	93.75 402

LF4IMVS		89.25 384	88.85 372	90.45 418	92.81 421	81.19 454	98.12 402	94.79 455	91.44 293	86.29 404	97.11 315	65.30 439	98.11 308	88.53 359	85.25 365	92.07 435

tt0320		83.56 424	81.15 427	90.77 412	92.77 422	83.58 436	96.83 435	95.52 442	63.26 473	81.36 434	92.54 438	53.26 465	95.77 425	80.45 428	74.38 442	92.96 423

DTE-MVSNet		89.40 381	88.24 384	92.88 387	92.66 423	89.95 377	99.10 311	98.22 212	87.29 385	85.12 414	96.22 347	76.27 382	95.30 435	83.56 410	75.74 438	93.41 411

EU-MVSNet		90.14 368	90.34 342	89.54 427	92.55 424	81.06 455	98.69 368	98.04 236	91.41 297	86.59 398	96.84 330	80.83 333	93.31 457	86.20 389	81.91 392	94.26 351

APD_test1		81.15 429	80.92 429	81.86 451	92.45 425	59.76 480	96.04 449	93.61 469	73.29 466	77.06 453	96.64 335	44.28 475	96.16 414	72.35 458	82.52 386	89.67 461

sc_t1		85.01 411	82.46 421	92.67 391	92.44 426	83.09 440	97.39 420	95.72 435	65.06 472	85.64 411	96.16 349	49.50 470	97.34 341	84.86 401	75.39 440	97.57 309

our_test_3		90.39 358	89.48 363	93.12 381	92.40 427	89.57 382	99.33 284	96.35 422	87.84 379	85.30 412	94.99 404	84.14 296	96.09 418	80.38 429	84.56 372	93.71 407

ppachtmachnet_test		89.58 379	88.35 382	93.25 379	92.40 427	90.44 366	99.33 284	96.73 408	85.49 410	85.90 409	95.77 360	81.09 329	96.00 422	76.00 452	82.49 387	93.30 415

v7n		89.65 377	88.29 383	93.72 364	92.22 429	90.56 363	99.07 318	97.10 366	85.42 412	86.73 395	94.72 409	80.06 343	97.13 356	81.14 424	78.12 422	93.49 410

dmvs_testset		83.79 420	86.07 399	76.94 455	92.14 430	48.60 490	96.75 436	90.27 480	89.48 345	78.65 447	98.55 261	79.25 349	86.65 478	66.85 468	82.69 384	95.57 328

PS-MVSNAJss		93.64 286	93.31 283	94.61 323	92.11 431	92.19 317	99.12 308	97.38 311	92.51 254	88.45 368	96.99 323	91.20 174	97.29 349	94.36 257	87.71 346	94.36 343

pmmvs5		90.17 367	89.09 368	93.40 373	92.10 432	89.77 380	99.74 189	95.58 440	85.88 404	87.24 392	95.74 361	73.41 405	96.48 398	88.54 358	83.56 381	93.95 389

N_pmnet		80.06 434	80.78 430	77.89 454	91.94 433	45.28 492	98.80 359	56.82 494	78.10 454	80.08 441	93.33 431	77.03 369	95.76 426	68.14 466	82.81 383	92.64 428

test_djsdf		92.83 305	92.29 307	94.47 333	91.90 434	92.46 312	99.55 249	97.27 336	91.17 301	89.96 328	96.07 355	81.10 328	96.89 375	94.67 252	88.91 326	94.05 380

SixPastTwentyTwo		88.73 386	88.01 387	90.88 408	91.85 435	82.24 446	98.22 399	95.18 451	88.97 355	82.26 428	96.89 325	71.75 410	96.67 389	84.00 405	82.98 382	93.72 406

K. test v3		88.05 392	87.24 393	90.47 417	91.82 436	82.23 447	98.96 337	97.42 307	89.05 350	76.93 455	95.60 368	68.49 424	95.42 431	85.87 394	81.01 404	93.75 402

OurMVSNet-221017-0		89.81 374	89.48 363	90.83 411	91.64 437	81.21 453	98.17 401	95.38 445	91.48 291	85.65 410	97.31 310	72.66 406	97.29 349	88.15 366	84.83 370	93.97 388

mvs_tets		91.81 327	91.08 330	94.00 355	91.63 438	90.58 362	98.67 370	97.43 305	92.43 256	87.37 390	97.05 320	71.76 409	97.32 344	94.75 249	88.68 332	94.11 376

Gipuma		66.95 447	65.00 447	72.79 460	91.52 439	67.96 472	66.16 484	95.15 452	47.89 481	58.54 478	67.99 483	29.74 479	87.54 477	50.20 482	77.83 424	62.87 483
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 179	95.74 192	98.32 146	91.47 440	95.56 201	99.84 149	97.30 327	97.74 30	97.89 173	99.35 152	79.62 346	99.85 129	99.25 74	99.24 141	99.55 159

jajsoiax		91.92 325	91.18 328	94.15 346	91.35 441	90.95 353	99.00 329	97.42 307	92.61 243	87.38 389	97.08 317	72.46 407	97.36 339	94.53 255	88.77 330	94.13 374

MDA-MVSNet-bldmvs		84.09 418	81.52 425	91.81 402	91.32 442	88.00 406	98.67 370	95.92 431	80.22 446	55.60 481	93.32 432	68.29 426	93.60 455	73.76 455	76.61 435	93.82 400

MVP-Stereo		90.93 345	90.45 340	92.37 395	91.25 443	88.76 392	98.05 406	96.17 425	87.27 386	84.04 419	95.30 387	78.46 360	97.27 351	83.78 408	99.70 93	91.09 443
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 406	83.32 414	92.10 397	90.96 444	88.58 398	99.20 303	96.52 417	79.70 448	57.12 480	92.69 437	79.11 352	93.86 451	77.10 447	77.46 428	93.86 397

YYNet1		85.50 407	83.33 413	92.00 398	90.89 445	88.38 402	99.22 302	96.55 416	79.60 449	57.26 479	92.72 436	79.09 354	93.78 453	77.25 446	77.37 429	93.84 398

anonymousdsp		91.79 332	90.92 332	94.41 338	90.76 446	92.93 299	98.93 341	97.17 351	89.08 349	87.46 388	95.30 387	78.43 361	96.92 373	92.38 296	88.73 331	93.39 413

lessismore_v0				90.53 415	90.58 447	80.90 456		95.80 432		77.01 454	95.84 358	66.15 435	96.95 371	83.03 413	75.05 441	93.74 405

EG-PatchMatch MVS		85.35 408	83.81 411	89.99 425	90.39 448	81.89 449	98.21 400	96.09 427	81.78 439	74.73 461	93.72 429	51.56 469	97.12 358	79.16 437	88.61 333	90.96 446

EGC-MVSNET		69.38 440	63.76 450	86.26 444	90.32 449	81.66 452	96.24 445	93.85 467	0.99 491	3.22 492	92.33 445	52.44 466	92.92 461	59.53 478	84.90 369	84.21 472

CMPMVS	61.59 21	84.75 414	85.14 405	83.57 448	90.32 449	62.54 476	96.98 430	97.59 290	74.33 464	69.95 469	96.66 333	64.17 442	98.32 292	87.88 370	88.41 338	89.84 458
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 417	82.92 417	89.21 429	90.03 451	82.60 443	96.89 433	95.62 439	80.59 444	75.77 460	89.17 458	65.04 440	94.79 442	72.12 459	81.02 403	90.23 452

pmmvs6		85.69 403	83.84 410	91.26 407	90.00 452	84.41 431	97.82 411	96.15 426	75.86 458	81.29 435	95.39 382	61.21 453	96.87 378	83.52 411	73.29 444	92.50 431

ttmdpeth		88.23 391	87.06 394	91.75 403	89.91 453	87.35 411	98.92 344	95.73 434	87.92 377	84.02 420	96.31 344	68.23 427	96.84 379	86.33 388	76.12 436	91.06 444

DSMNet-mixed		88.28 390	88.24 384	88.42 437	89.64 454	75.38 466	98.06 405	89.86 481	85.59 409	88.20 377	92.14 447	76.15 384	91.95 466	78.46 441	96.05 251	97.92 294

UnsupCasMVSNet_eth		85.52 405	83.99 407	90.10 423	89.36 455	83.51 438	96.65 437	97.99 240	89.14 348	75.89 459	93.83 426	63.25 446	93.92 449	81.92 421	67.90 463	92.88 425

Anonymous20231206		86.32 401	85.42 403	89.02 431	89.11 456	80.53 459	99.05 323	95.28 446	85.43 411	82.82 426	93.92 425	74.40 398	93.44 456	66.99 467	81.83 393	93.08 421

Anonymous20240521		85.15 409	83.81 411	89.16 430	88.32 457	82.69 442	98.80 359	95.74 433	79.72 447	81.53 433	90.99 450	65.38 438	94.16 447	72.69 457	81.11 400	90.63 450

OpenMVS_ROB	79.82 20	83.77 421	81.68 424	90.03 424	88.30 458	82.82 441	98.46 381	95.22 449	73.92 465	76.00 458	91.29 449	55.00 462	96.94 372	68.40 465	88.51 337	90.34 451

test20.03		84.72 415	83.99 407	86.91 442	88.19 459	80.62 458	98.88 347	95.94 430	88.36 371	78.87 445	94.62 414	68.75 422	89.11 473	66.52 469	75.82 437	91.00 445

blend_shiyan4		90.13 369	88.79 374	94.17 344	87.12 460	91.83 327	99.75 185	97.08 370	79.27 451	88.69 363	92.53 439	92.25 158	96.50 395	89.35 348	73.04 446	94.18 361

KD-MVS_self_test		83.59 422	82.06 422	88.20 438	86.93 461	80.70 457	97.21 423	96.38 420	82.87 433	82.49 427	88.97 459	67.63 429	92.32 464	73.75 456	62.30 474	91.58 441

MIMVSNet1		82.58 426	80.51 431	88.78 433	86.68 462	84.20 432	96.65 437	95.41 444	78.75 452	78.59 448	92.44 440	51.88 468	89.76 472	65.26 472	78.95 416	92.38 434

usedtu_blend_shiyan5		86.75 400	84.29 406	94.16 345	86.66 463	91.83 327	97.42 417	95.23 448	69.94 471	88.37 374	92.36 444	78.01 362	96.50 395	89.35 348	61.26 475	94.14 371

blended_shiyan6		87.74 396	85.62 402	94.09 349	86.53 464	91.73 334	99.72 200	97.08 370	79.32 450	88.22 376	92.31 446	77.82 364	96.43 401	88.31 362	61.26 475	94.13 374

CL-MVSNet_self_test		84.50 416	83.15 416	88.53 436	86.00 465	81.79 450	98.82 355	97.35 315	85.12 414	83.62 424	90.91 452	76.66 376	91.40 467	69.53 463	60.36 477	92.40 433

UnsupCasMVSNet_bld		79.97 436	77.03 441	88.78 433	85.62 466	81.98 448	93.66 461	97.35 315	75.51 461	70.79 468	83.05 475	48.70 472	94.91 440	78.31 442	60.29 478	89.46 464

mvs5depth		84.87 412	82.90 418	90.77 412	85.59 467	84.84 429	91.10 474	93.29 471	83.14 430	85.07 415	94.33 422	62.17 449	97.32 344	78.83 440	72.59 448	90.14 454

Patchmatch-RL test		86.90 398	85.98 401	89.67 426	84.45 468	75.59 465	89.71 477	92.43 473	86.89 393	77.83 452	90.94 451	94.22 95	93.63 454	87.75 371	69.61 454	99.79 111

pmmvs-eth3d		84.03 419	81.97 423	90.20 421	84.15 469	87.09 413	98.10 404	94.73 457	83.05 431	74.10 465	87.77 465	65.56 437	94.01 448	81.08 425	69.24 456	89.49 463

test_fmvs3		79.99 435	80.17 433	79.45 453	84.02 470	62.83 474	99.05 323	93.49 470	88.29 373	80.06 442	86.65 470	28.09 481	88.00 474	88.63 355	73.27 445	87.54 470

PM-MVS		80.47 432	78.88 436	85.26 445	83.79 471	72.22 468	95.89 452	91.08 478	85.71 408	76.56 457	88.30 461	36.64 477	93.90 450	82.39 417	69.57 455	89.66 462

new-patchmatchnet		81.19 428	79.34 435	86.76 443	82.86 472	80.36 460	97.92 408	95.27 447	82.09 438	72.02 466	86.87 469	62.81 448	90.74 470	71.10 460	63.08 471	89.19 466

FE-MVSNET2		83.57 423	81.36 426	90.20 421	82.83 473	87.59 407	98.28 392	96.04 428	85.33 413	74.13 464	87.45 466	59.16 457	93.26 458	79.12 438	69.91 452	89.77 459

FE-MVSNET		81.05 430	78.81 437	87.79 440	81.98 474	83.70 434	98.23 397	91.78 477	81.27 441	74.29 463	87.44 467	60.92 455	90.67 471	64.92 473	68.43 459	89.01 467

mvsany_test3		82.12 427	81.14 428	85.06 446	81.87 475	70.41 470	97.09 427	92.14 474	91.27 300	77.84 451	88.73 460	39.31 476	95.49 428	90.75 328	71.24 450	89.29 465

WB-MVS		76.28 438	77.28 440	73.29 459	81.18 476	54.68 484	97.87 410	94.19 462	81.30 440	69.43 470	90.70 453	77.02 370	82.06 482	35.71 487	68.11 462	83.13 473

test_f		78.40 437	77.59 439	80.81 452	80.82 477	62.48 477	96.96 431	93.08 472	83.44 428	74.57 462	84.57 474	27.95 482	92.63 462	84.15 403	72.79 447	87.32 471

SSC-MVS		75.42 439	76.40 442	72.49 463	80.68 478	53.62 485	97.42 417	94.06 464	80.42 445	68.75 471	90.14 455	76.54 378	81.66 483	33.25 488	66.34 466	82.19 474

pmmvs3		80.27 433	77.77 438	87.76 441	80.32 479	82.43 445	98.23 397	91.97 475	72.74 467	78.75 446	87.97 464	57.30 461	90.99 469	70.31 461	62.37 473	89.87 457

testf1		68.38 443	66.92 444	72.78 461	78.80 480	50.36 487	90.95 475	87.35 486	55.47 477	58.95 476	88.14 462	20.64 486	87.60 475	57.28 479	64.69 468	80.39 476

APD_test2		68.38 443	66.92 444	72.78 461	78.80 480	50.36 487	90.95 475	87.35 486	55.47 477	58.95 476	88.14 462	20.64 486	87.60 475	57.28 479	64.69 468	80.39 476

ambc				83.23 449	77.17 482	62.61 475	87.38 479	94.55 461		76.72 456	86.65 470	30.16 478	96.36 405	84.85 402	69.86 453	90.73 448

test_vis3_rt		68.82 441	66.69 446	75.21 458	76.24 483	60.41 479	96.44 440	68.71 493	75.13 462	50.54 484	69.52 482	16.42 491	96.32 407	80.27 430	66.92 465	68.89 480

TDRefinement		84.76 413	82.56 420	91.38 406	74.58 484	84.80 430	97.36 421	94.56 460	84.73 419	80.21 440	96.12 354	63.56 444	98.39 282	87.92 369	63.97 470	90.95 447

E-PMN		52.30 451	52.18 453	52.67 469	71.51 485	45.40 491	93.62 462	76.60 491	36.01 485	43.50 486	64.13 485	27.11 483	67.31 488	31.06 489	26.06 484	45.30 487

EMVS		51.44 453	51.22 455	52.11 470	70.71 486	44.97 493	94.04 458	75.66 492	35.34 487	42.40 487	61.56 488	28.93 480	65.87 489	27.64 490	24.73 485	45.49 486

PMMVS2		67.15 446	64.15 449	76.14 457	70.56 487	62.07 478	93.89 459	87.52 485	58.09 476	60.02 475	78.32 477	22.38 485	84.54 480	59.56 477	47.03 482	81.80 475

FPMVS		68.72 442	68.72 443	68.71 465	65.95 488	44.27 494	95.97 451	94.74 456	51.13 480	53.26 482	90.50 454	25.11 484	83.00 481	60.80 476	80.97 405	78.87 478

wuyk23d		20.37 457	20.84 460	18.99 473	65.34 489	27.73 496	50.43 485	7.67 497	9.50 490	8.01 491	6.34 491	6.13 494	26.24 490	23.40 491	10.69 489	2.99 488

LCM-MVSNet		67.77 445	64.73 448	76.87 456	62.95 490	56.25 483	89.37 478	93.74 468	44.53 482	61.99 474	80.74 476	20.42 488	86.53 479	69.37 464	59.50 479	87.84 468

MVE	53.74 22	51.54 452	47.86 456	62.60 467	59.56 491	50.93 486	79.41 482	77.69 490	35.69 486	36.27 488	61.76 487	5.79 495	69.63 486	37.97 486	36.61 483	67.24 481
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 449	52.24 452	67.66 466	49.27 492	56.82 482	83.94 480	82.02 489	70.47 469	33.28 489	64.54 484	17.23 490	69.16 487	45.59 484	23.85 486	77.02 479

tmp_tt		65.23 448	62.94 451	72.13 464	44.90 493	50.03 489	81.05 481	89.42 484	38.45 483	48.51 485	99.90 22	54.09 464	78.70 485	91.84 309	18.26 487	87.64 469

PMVS	49.05 23	53.75 450	51.34 454	60.97 468	40.80 494	34.68 495	74.82 483	89.62 483	37.55 484	28.67 490	72.12 479	7.09 493	81.63 484	43.17 485	68.21 461	66.59 482
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 455	39.14 458	33.31 471	19.94 495	24.83 497	98.36 389	9.75 496	15.53 489	51.31 483	87.14 468	19.62 489	17.74 491	47.10 483	3.47 490	57.36 484

testmvs		40.60 454	44.45 457	29.05 472	19.49 496	14.11 498	99.68 217	18.47 495	20.74 488	64.59 473	98.48 268	10.95 492	17.09 492	56.66 481	11.01 488	55.94 485

mmdepth		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

monomultidepth		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

test_blank		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.02 492	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

eth-test2					0.00 497

eth-test					0.00 497

uanet_test		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

DCPMVS		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

cdsmvs_eth3d_5k		23.43 456	31.24 459	0.00 474	0.00 497	0.00 499	0.00 486	98.09 230	0.00 492	0.00 493	99.67 113	83.37 304	0.00 493	0.00 492	0.00 491	0.00 489

pcd_1.5k_mvsjas		7.60 459	10.13 462	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	91.20 174	0.00 493	0.00 492	0.00 491	0.00 489

sosnet-low-res		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

sosnet		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

uncertanet		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

Regformer		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

ab-mvs-re		8.28 458	11.04 461	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	99.40 146	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

uanet		0.00 460	0.00 463	0.00 474	0.00 497	0.00 499	0.00 486	0.00 498	0.00 492	0.00 493	0.00 493	0.00 496	0.00 493	0.00 492	0.00 491	0.00 489

TestfortrainingZip							99.97 39

WAC-MVS						90.97 350								86.10 392

PC_three_1452									96.96 60	99.80 26	99.79 62	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 155	97.27 47	99.80 26	99.94 4	97.18 23	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 78	99.83 22	99.91 18	97.87 5	100.00 1	99.92 16	100.00 1	100.00 1

GSMVS																99.59 149

sam_mvs1												94.72 74				99.59 149

sam_mvs												94.25 94

MTGPA								98.28 203

test_post1							95.78 453				59.23 489	93.20 128	97.74 328	91.06 319

test_post											63.35 486	94.43 82	98.13 307

patchmatchnet-post											91.70 448	95.12 59	97.95 319

MTMP							99.87 130	96.49 418

test9_res														99.71 48	99.99 21	100.00 1

agg_prior2														99.48 63	100.00 1	100.00 1

test_prior4						98.05 81	99.94 90

test_prior2							99.95 72		95.78 104	99.73 45	99.76 72	96.00 40		99.78 35	100.00 1

旧先验2							99.46 267		94.21 164	99.85 18			99.95 84	96.96 196

新几何2							99.40 271

无先验							99.49 259	98.71 78	93.46 197				100.00 1	94.36 257		99.99 24

原ACMM2							99.90 114

testdata2													99.99 39	90.54 332

segment_acmp												96.68 31

testdata1							99.28 296		96.35 90

plane_prior5								97.87 254					98.37 288	97.79 167	89.55 320	94.52 332

plane_prior4											98.59 254

plane_prior3						91.64 338			96.63 73	93.01 292

plane_prior2							99.84 149		96.38 84

plane_prior						91.74 331	99.86 141		96.76 68						89.59 319

n2								0.00 498

nn								0.00 498

door-mid								89.69 482

test11								98.44 147

door								90.31 479

HQP5-MVS						91.85 325

BP-MVS														97.92 158

HQP4-MVS										93.37 287			98.39 282			94.53 330

HQP3-MVS								97.89 252							89.60 317

HQP2-MVS												80.65 336

MDTV_nov1_ep13_2view						96.26 168	96.11 447		91.89 277	98.06 166		94.40 84		94.30 260		99.67 129

ACMMP++_ref															87.04 353

ACMMP++															88.23 340

Test By Simon												92.82 139

High-resolution multi-view benchmark