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		97.23 119	96.80 127	98.51 122	99.99 1	95.60 183	99.09 273	98.84 60	93.32 182	96.74 192	99.72 87	86.04 243	100.00 1	98.01 138	99.43 118	99.94 78

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 17	98.69 72	98.20 8	99.93 1	99.98 2	96.82 24	100.00 1	99.75 34	100.00 1	99.99 23

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 34	98.64 81	98.47 3	99.13 97	99.92 13	96.38 34	100.00 1	99.74 36	100.00 1	100.00 1

mPP-MVS		98.39 51	98.20 49	98.97 84	99.97 3	96.92 128	99.95 62	98.38 173	95.04 109	98.61 127	99.80 54	93.39 114	100.00 1	98.64 105	100.00 1	99.98 51

CPTT-MVS		97.64 100	97.32 103	98.58 113	99.97 3	95.77 172	99.96 43	98.35 179	89.90 295	98.36 139	99.79 58	91.18 170	99.99 36	98.37 121	99.99 21	99.99 23

DP-MVS Recon		98.41 48	98.02 62	99.56 25	99.97 3	98.70 48	99.92 89	98.44 137	92.06 236	98.40 138	99.84 44	95.68 44	100.00 1	98.19 128	99.71 88	99.97 61

PAPR		98.52 38	98.16 53	99.58 24	99.97 3	98.77 42	99.95 62	98.43 145	95.35 103	98.03 152	99.75 75	94.03 99	99.98 47	98.11 133	99.83 77	99.99 23

HFP-MVS		98.56 35	98.37 39	99.14 64	99.96 8	97.43 105	99.95 62	98.61 89	94.77 118	99.31 86	99.85 33	94.22 92	100.00 1	98.70 100	99.98 32	99.98 51

region2R		98.54 36	98.37 39	99.05 74	99.96 8	97.18 115	99.96 43	98.55 108	94.87 116	99.45 73	99.85 33	94.07 98	100.00 1	98.67 102	100.00 1	99.98 51

ACMMPR		98.50 39	98.32 43	99.05 74	99.96 8	97.18 115	99.95 62	98.60 91	94.77 118	99.31 86	99.84 44	93.73 108	100.00 1	98.70 100	99.98 32	99.98 51

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 34	98.62 88	98.02 17	99.90 3	99.95 3	97.33 17	100.00 1	99.54 50	100.00 1	100.00 1

CP-MVS		98.45 43	98.32 43	98.87 89	99.96 8	96.62 138	99.97 34	98.39 169	94.43 133	98.90 109	99.87 27	94.30 89	100.00 1	99.04 75	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 162	96.63 68	99.75 34	99.93 11	97.49 10

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 62	98.43 145					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 29	98.55 28	99.15 62	99.94 13	97.50 101	99.94 79	98.42 157	96.22 83	99.41 78	99.78 62	94.34 86	99.96 67	98.92 85	99.95 50	99.99 23

X-MVStestdata		93.83 234	92.06 267	99.15 62	99.94 13	97.50 101	99.94 79	98.42 157	96.22 83	99.41 78	41.37 436	94.34 86	99.96 67	98.92 85	99.95 50	99.99 23

test_prior				99.43 35	99.94 13	98.49 60		98.65 78					99.80 132			99.99 23

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 17	98.86 54	97.10 48	99.80 22	99.94 4	95.92 40	100.00 1	99.51 51	100.00 1	100.00 1

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 97	98.39 169	97.20 46	99.46 72	99.85 33	95.53 48	99.79 134	99.86 21	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS		98.23 64	97.97 65	99.03 76	99.94 13	97.17 118	99.95 62	98.39 169	94.70 122	98.26 145	99.81 53	91.84 161	100.00 1	98.85 91	99.97 42	99.93 79
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDPH-MVS		98.65 31	98.36 41	99.49 32	99.94 13	98.73 46	99.87 118	98.33 184	93.97 158	99.76 33	99.87 27	94.99 64	99.75 143	98.55 109	100.00 1	99.98 51

PAPM_NR		98.12 67	97.93 71	98.70 100	99.94 13	96.13 162	99.82 147	98.43 145	94.56 126	97.52 167	99.70 92	94.40 81	99.98 47	97.00 172	99.98 32	99.99 23

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 200	99.44 19	97.33 39	99.00 105	99.72 87	94.03 99	99.98 47	98.73 99	100.00 1	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 43	98.43 145	97.27 42	99.80 22	99.94 4	96.71 27	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 24	99.31 10		98.41 162	97.71 26	99.84 17				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 145	97.26 44	99.80 22	99.88 24	96.71 27	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 62	98.32 186	97.28 40	99.83 18	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 88
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 24	99.29 15	99.96 43	98.42 157	97.28 40	99.86 11	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 83	99.93 24	97.24 112	99.95 62	98.42 157	97.50 33	99.52 68	99.88 24	97.43 16	99.71 149	99.50 52	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 24	98.77 42		98.43 145		99.63 51			99.85 119

FOURS1					99.92 31	97.66 95	99.95 62	98.36 177	95.58 97	99.52 68

ZD-MVS					99.92 31	98.57 56		98.52 117	92.34 228	99.31 86	99.83 46	95.06 59	99.80 132	99.70 41	99.97 42

GST-MVS		98.27 57	97.97 65	99.17 57	99.92 31	97.57 97	99.93 86	98.39 169	94.04 156	98.80 114	99.74 82	92.98 130	100.00 1	98.16 130	99.76 85	99.93 79

TEST9					99.92 31	98.92 29	99.96 43	98.43 145	93.90 164	99.71 41	99.86 29	95.88 41	99.85 119

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 43	98.43 145	94.35 138	99.71 41	99.86 29	95.94 38	99.85 119	99.69 42	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 43	98.43 145	94.35 138	99.69 43	99.85 33	95.94 38	99.85 119

PGM-MVS		98.34 52	98.13 55	98.99 81	99.92 31	97.00 124	99.75 168	99.50 17	93.90 164	99.37 83	99.76 67	93.24 123	100.00 1	97.75 157	99.96 46	99.98 51

ACMMP		97.74 93	97.44 96	98.66 104	99.92 31	96.13 162	99.18 268	99.45 18	94.84 117	96.41 202	99.71 90	91.40 164	99.99 36	97.99 140	98.03 175	99.87 91
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 39	99.31 10	99.95 62	98.43 145	96.48 71	99.80 22	99.93 11	97.44 14	100.00 1	99.92 13	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 162					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 162					100.00 1	99.96 9	100.00 1	100.00 1

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 62	98.56 102	97.56 32	99.44 74	99.85 33	95.38 52	100.00 1	99.31 62	99.99 21	99.87 91

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 118	98.36 177	94.08 151	99.74 37	99.73 84	94.08 97	99.74 145	99.42 58	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepC-MVS_fast	96.59 1	98.81 23	98.54 29	99.62 20	99.90 42	98.85 35	99.24 263	98.47 129	98.14 12	99.08 100	99.91 14	93.09 127	100.00 1	99.04 75	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 45	99.80 2	99.96 43				99.80 54	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 11	99.89 45	99.24 19	99.87 118	98.44 137	97.48 34	99.64 50	99.94 4	96.68 29	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_part2					99.89 45	99.25 18				99.49 71

CSCG		97.10 124	97.04 115	97.27 201	99.89 45	91.92 285	99.90 103	99.07 35	88.67 319	95.26 225	99.82 49	93.17 126	99.98 47	98.15 131	99.47 113	99.90 87

ZNCC-MVS		98.31 54	98.03 61	99.17 57	99.88 49	97.59 96	99.94 79	98.44 137	94.31 141	98.50 132	99.82 49	93.06 128	99.99 36	98.30 125	99.99 21	99.93 79

SR-MVS		98.46 42	98.30 46	98.93 87	99.88 49	97.04 123	99.84 137	98.35 179	94.92 113	99.32 85	99.80 54	93.35 116	99.78 136	99.30 63	99.95 50	99.96 67

9.14			98.38 37		99.87 51		99.91 97	98.33 184	93.22 185	99.78 31	99.89 22	94.57 77	99.85 119	99.84 22	99.97 42

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 129	98.38 173	93.19 186	99.77 32	99.94 4	95.54 46	100.00 1	99.74 36	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
PHI-MVS		98.41 48	98.21 48	99.03 76	99.86 53	97.10 121	99.98 17	98.80 65	90.78 277	99.62 54	99.78 62	95.30 53	100.00 1	99.80 25	99.93 61	99.99 23

MTAPA		98.29 56	97.96 68	99.30 45	99.85 54	97.93 83	99.39 242	98.28 193	95.76 92	97.18 180	99.88 24	92.74 137	100.00 1	98.67 102	99.88 73	99.99 23

LS3D		95.84 179	95.11 190	98.02 152	99.85 54	95.10 204	98.74 318	98.50 126	87.22 341	93.66 243	99.86 29	87.45 224	99.95 76	90.94 281	99.81 83	99.02 217

HPM-MVS		97.96 71	97.72 80	98.68 101	99.84 56	96.39 149	99.90 103	98.17 208	92.61 214	98.62 126	99.57 120	91.87 160	99.67 157	98.87 90	99.99 21	99.99 23
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 57	98.11 57	98.75 97	99.83 57	96.59 141	99.40 238	98.51 120	95.29 105	98.51 131	99.76 67	93.60 112	99.71 149	98.53 112	99.52 106	99.95 74

save fliter					99.82 58	98.79 40	99.96 43	98.40 166	97.66 28

PLC	95.54 3	97.93 74	97.89 74	98.05 151	99.82 58	94.77 214	99.92 89	98.46 131	93.93 161	97.20 178	99.27 147	95.44 51	99.97 57	97.41 162	99.51 109	99.41 176
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 62	98.08 59	98.78 94	99.81 60	96.60 139	99.82 147	98.30 191	93.95 160	99.37 83	99.77 65	92.84 134	99.76 142	98.95 81	99.92 64	99.97 61

EI-MVSNet-UG-set		98.14 66	97.99 63	98.60 109	99.80 61	96.27 152	99.36 248	98.50 126	95.21 107	98.30 142	99.75 75	93.29 120	99.73 148	98.37 121	99.30 127	99.81 99

SR-MVS-dyc-post		98.31 54	98.17 52	98.71 99	99.79 62	96.37 150	99.76 164	98.31 188	94.43 133	99.40 80	99.75 75	93.28 121	99.78 136	98.90 88	99.92 64	99.97 61

RE-MVS-def			98.13 55		99.79 62	96.37 150	99.76 164	98.31 188	94.43 133	99.40 80	99.75 75	92.95 131		98.90 88	99.92 64	99.97 61

HPM-MVS_fast		97.80 87	97.50 93	98.68 101	99.79 62	96.42 145	99.88 115	98.16 213	91.75 246	98.94 107	99.54 123	91.82 162	99.65 159	97.62 160	99.99 21	99.99 23

SF-MVS		98.67 30	98.40 35	99.50 30	99.77 65	98.67 49	99.90 103	98.21 203	93.53 175	99.81 20	99.89 22	94.70 73	99.86 118	99.84 22	99.93 61	99.96 67

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 66	99.21 21	99.99 5	99.34 25	98.70 2	99.44 74	99.75 75	93.24 123	99.99 36	99.94 11	99.41 120	99.95 74

旧先验1					99.76 66	97.52 99		98.64 81			99.85 33	95.63 45			99.94 55	99.99 23

OMC-MVS		97.28 115	97.23 107	97.41 192	99.76 66	93.36 254	99.65 196	97.95 232	96.03 87	97.41 172	99.70 92	89.61 196	99.51 165	96.73 181	98.25 165	99.38 178

新几何1				99.42 37	99.75 69	98.27 65		98.63 87	92.69 209	99.55 63	99.82 49	94.40 81	100.00 1	91.21 273	99.94 55	99.99 23

MP-MVS-pluss		98.07 70	97.64 86	99.38 43	99.74 70	98.41 63	99.74 171	98.18 207	93.35 180	96.45 199	99.85 33	92.64 139	99.97 57	98.91 87	99.89 70	99.77 106
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + MP.		98.93 17	98.77 19	99.41 38	99.74 70	98.67 49	99.77 159	98.38 173	96.73 64	99.88 8	99.74 82	94.89 66	99.59 161	99.80 25	99.98 32	99.97 61
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 35	99.74 70	98.56 57		98.40 166		99.65 47		94.76 69	99.75 143		99.98 32	99.99 23

原ACMM1				98.96 85	99.73 73	96.99 125		98.51 120	94.06 154	99.62 54	99.85 33	94.97 65	99.96 67	95.11 201	99.95 50	99.92 84

TSAR-MVS + GP.		98.60 33	98.51 31	98.86 90	99.73 73	96.63 137	99.97 34	97.92 237	98.07 14	98.76 119	99.55 121	95.00 63	99.94 84	99.91 16	97.68 180	99.99 23

CANet		98.27 57	97.82 77	99.63 17	99.72 75	99.10 23	99.98 17	98.51 120	97.00 54	98.52 129	99.71 90	87.80 219	99.95 76	99.75 34	99.38 122	99.83 96

reproduce_model		98.75 27	98.66 23	99.03 76	99.71 76	97.10 121	99.73 178	98.23 201	97.02 53	99.18 95	99.90 18	94.54 78	99.99 36	99.77 30	99.90 69	99.99 23

F-COLMAP		96.93 136	96.95 118	96.87 211	99.71 76	91.74 290	99.85 132	97.95 232	93.11 192	95.72 218	99.16 158	92.35 149	99.94 84	95.32 199	99.35 125	98.92 221

reproduce-ours		98.78 24	98.67 21	99.09 71	99.70 78	97.30 109	99.74 171	98.25 197	97.10 48	99.10 98	99.90 18	94.59 74	99.99 36	99.77 30	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 71	99.70 78	97.30 109	99.74 171	98.25 197	97.10 48	99.10 98	99.90 18	94.59 74	99.99 36	99.77 30	99.91 67	99.99 23

SD-MVS		98.92 18	98.70 20	99.56 25	99.70 78	98.73 46	99.94 79	98.34 183	96.38 77	99.81 20	99.76 67	94.59 74	99.98 47	99.84 22	99.96 46	99.97 61
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 63	99.12 5	95.59 246	99.67 81	86.91 367	99.95 62	98.89 50	97.60 29	99.90 3	99.76 67	96.54 32	99.98 47	99.94 11	99.82 81	99.88 89

ACMMP_NAP		98.49 40	98.14 54	99.54 27	99.66 82	98.62 55	99.85 132	98.37 176	94.68 123	99.53 66	99.83 46	92.87 133	100.00 1	98.66 104	99.84 76	99.99 23

DeepPCF-MVS	95.94 2	97.71 97	98.98 12	93.92 310	99.63 83	81.76 398	99.96 43	98.56 102	99.47 1	99.19 94	99.99 1	94.16 96	100.00 1	99.92 13	99.93 61	100.00 1

EPNet		98.49 40	98.40 35	98.77 96	99.62 84	96.80 133	99.90 103	99.51 16	97.60 29	99.20 92	99.36 141	93.71 109	99.91 100	97.99 140	98.71 152	99.61 137
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		98.83 21	98.53 30	99.76 10	99.59 85	99.33 8	99.99 5	99.76 6	98.39 4	99.39 82	99.80 54	90.49 185	99.96 67	99.89 17	99.43 118	99.98 51

PVSNet_BlendedMVS		96.05 172	95.82 169	96.72 216	99.59 85	96.99 125	99.95 62	99.10 32	94.06 154	98.27 143	95.80 314	89.00 207	99.95 76	99.12 69	87.53 307	93.24 367

PVSNet_Blended		97.94 73	97.64 86	98.83 91	99.59 85	96.99 125	100.00 1	99.10 32	95.38 102	98.27 143	99.08 161	89.00 207	99.95 76	99.12 69	99.25 129	99.57 148

PatchMatch-RL		96.04 173	95.40 179	97.95 154	99.59 85	95.22 199	99.52 220	99.07 35	93.96 159	96.49 198	98.35 232	82.28 274	99.82 131	90.15 297	99.22 132	98.81 228

dcpmvs_2		97.42 110	98.09 58	95.42 251	99.58 89	87.24 363	99.23 264	96.95 341	94.28 144	98.93 108	99.73 84	94.39 84	99.16 192	99.89 17	99.82 81	99.86 93

test222					99.55 90	97.41 107	99.34 249	98.55 108	91.86 241	99.27 90	99.83 46	93.84 106			99.95 50	99.99 23

CNLPA		97.76 91	97.38 99	98.92 88	99.53 91	96.84 130	99.87 118	98.14 217	93.78 168	96.55 197	99.69 95	92.28 151	99.98 47	97.13 168	99.44 117	99.93 79

API-MVS		97.86 78	97.66 84	98.47 124	99.52 92	95.41 190	99.47 230	98.87 53	91.68 247	98.84 111	99.85 33	92.34 150	99.99 36	98.44 117	99.96 46	100.00 1

PVSNet	91.05 13	97.13 123	96.69 133	98.45 126	99.52 92	95.81 170	99.95 62	99.65 12	94.73 120	99.04 103	99.21 154	84.48 259	99.95 76	94.92 207	98.74 151	99.58 146

114514_t		97.41 111	96.83 125	99.14 64	99.51 94	97.83 85	99.89 112	98.27 195	88.48 323	99.06 102	99.66 105	90.30 188	99.64 160	96.32 185	99.97 42	99.96 67

cl22		93.77 238	93.25 242	95.33 255	99.49 95	94.43 219	99.61 205	98.09 219	90.38 283	89.16 310	95.61 321	90.56 183	97.34 301	91.93 265	84.45 327	94.21 312

testdata				98.42 130	99.47 96	95.33 193		98.56 102	93.78 168	99.79 30	99.85 33	93.64 111	99.94 84	94.97 205	99.94 55	100.00 1

MAR-MVS		97.43 106	97.19 109	98.15 145	99.47 96	94.79 213	99.05 284	98.76 66	92.65 212	98.66 124	99.82 49	88.52 213	99.98 47	98.12 132	99.63 94	99.67 120
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		94.54 216	93.42 235	97.91 160	99.46 98	94.04 232	98.93 298	97.48 283	81.15 394	90.04 282	99.55 121	87.02 230	99.95 76	88.97 307	98.11 171	99.73 110

MVS_111021_LR		98.42 47	98.38 37	98.53 120	99.39 99	95.79 171	99.87 118	99.86 2	96.70 65	98.78 115	99.79 58	92.03 157	99.90 102	99.17 68	99.86 75	99.88 89

CHOSEN 280x420		99.01 14	99.03 10	98.95 86	99.38 100	98.87 33	98.46 336	99.42 21	97.03 52	99.02 104	99.09 160	99.35 2	98.21 263	99.73 38	99.78 84	99.77 106

MVS_111021_HR		98.72 28	98.62 26	99.01 80	99.36 101	97.18 115	99.93 86	99.90 1	96.81 62	98.67 123	99.77 65	93.92 101	99.89 107	99.27 64	99.94 55	99.96 67

DPM-MVS		98.83 21	98.46 33	99.97 1	99.33 102	99.92 1	99.96 43	98.44 137	97.96 18	99.55 63	99.94 4	97.18 21	100.00 1	93.81 236	99.94 55	99.98 51

TAPA-MVS	92.12 8	94.42 222	93.60 228	96.90 210	99.33 102	91.78 289	99.78 156	98.00 226	89.89 296	94.52 231	99.47 127	91.97 158	99.18 189	69.90 409	99.52 106	99.73 110
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 193	95.07 192	96.32 229	99.32 104	96.60 139	99.76 164	98.85 57	96.65 67	87.83 332	96.05 311	99.52 1	98.11 268	96.58 182	81.07 356	94.25 308

SPE-MVS-test		97.88 76	97.94 70	97.70 173	99.28 105	95.20 200	99.98 17	97.15 318	95.53 99	99.62 54	99.79 58	92.08 156	98.38 246	98.75 98	99.28 128	99.52 160

test_fmvsm_n_1920		98.44 44	98.61 27	97.92 158	99.27 106	95.18 201	100.00 1	98.90 48	98.05 15	99.80 22	99.73 84	92.64 139	99.99 36	99.58 49	99.51 109	98.59 238

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 46	99.21 107	97.91 84	99.98 17	98.85 57	98.25 5	99.92 2	99.75 75	94.72 71	99.97 57	99.87 19	99.64 92	99.95 74

test_yl		97.83 82	97.37 100	99.21 51	99.18 108	97.98 79	99.64 200	99.27 27	91.43 256	97.88 159	98.99 170	95.84 42	99.84 127	98.82 92	95.32 236	99.79 102

DCV-MVSNet		97.83 82	97.37 100	99.21 51	99.18 108	97.98 79	99.64 200	99.27 27	91.43 256	97.88 159	98.99 170	95.84 42	99.84 127	98.82 92	95.32 236	99.79 102

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 47	99.17 110	97.81 87	99.98 17	98.86 54	98.25 5	99.90 3	99.76 67	94.21 94	99.97 57	99.87 19	99.52 106	99.98 51

DeepC-MVS	94.51 4	96.92 137	96.40 144	98.45 126	99.16 111	95.90 168	99.66 195	98.06 222	96.37 80	94.37 234	99.49 126	83.29 269	99.90 102	97.63 159	99.61 99	99.55 150
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 36	98.22 47	99.50 30	99.15 112	98.65 53	100.00 1	98.58 95	97.70 27	98.21 148	99.24 152	92.58 142	99.94 84	98.63 107	99.94 55	99.92 84
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 48	98.08 59	99.39 40	99.12 113	98.29 64	99.98 17	98.64 81	98.14 12	99.86 11	99.76 67	87.99 218	99.97 57	99.72 39	99.54 104	99.91 86

CS-MVS		97.79 89	97.91 72	97.43 190	99.10 114	94.42 220	99.99 5	97.10 323	95.07 108	99.68 44	99.75 75	92.95 131	98.34 250	98.38 119	99.14 134	99.54 154

Anonymous202405211		93.10 256	91.99 268	96.40 225	99.10 114	89.65 335	98.88 304	97.93 234	83.71 379	94.00 240	98.75 199	68.79 373	99.88 113	95.08 202	91.71 269	99.68 118

fmvsm_s_conf0.5_n		97.80 87	97.85 76	97.67 174	99.06 116	94.41 221	99.98 17	98.97 41	97.34 37	99.63 51	99.69 95	87.27 226	99.97 57	99.62 47	99.06 139	98.62 237

HyFIR lowres test		96.66 151	96.43 143	97.36 197	99.05 117	93.91 237	99.70 189	99.80 3	90.54 281	96.26 205	98.08 243	92.15 154	98.23 262	96.84 180	95.46 231	99.93 79

LFMVS		94.75 210	93.56 231	98.30 136	99.03 118	95.70 177	98.74 318	97.98 229	87.81 334	98.47 133	99.39 138	67.43 382	99.53 162	98.01 138	95.20 239	99.67 120

fmvsm_s_conf0.5_n_4		97.75 92	97.86 75	97.42 191	99.01 119	94.69 215	99.97 34	98.76 66	97.91 20	99.87 9	99.76 67	86.70 235	99.93 93	99.67 44	99.12 137	97.64 260

fmvsm_s_conf0.5_n_2		97.59 101	97.28 104	98.53 120	99.01 119	98.15 66	99.98 17	98.59 93	98.17 10	99.75 34	99.63 111	81.83 279	99.94 84	99.78 28	98.79 150	97.51 267

AllTest		92.48 270	91.64 273	95.00 264	99.01 119	88.43 351	98.94 296	96.82 355	86.50 350	88.71 315	98.47 227	74.73 350	99.88 113	85.39 346	96.18 212	96.71 273

TestCases				95.00 264	99.01 119	88.43 351		96.82 355	86.50 350	88.71 315	98.47 227	74.73 350	99.88 113	85.39 346	96.18 212	96.71 273

COLMAP_ROB	90.47 14	92.18 277	91.49 279	94.25 298	99.00 123	88.04 357	98.42 342	96.70 362	82.30 390	88.43 324	99.01 167	76.97 326	99.85 119	86.11 342	96.50 205	94.86 284
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 72	97.66 84	98.81 92	98.99 124	98.07 73	99.98 17	98.81 62	98.18 9	99.89 6	99.70 92	84.15 262	99.97 57	99.76 33	99.50 111	98.39 242

test_fmvs1		95.35 194	95.68 174	94.36 294	98.99 124	84.98 378	99.96 43	96.65 364	97.60 29	99.73 39	98.96 176	71.58 363	99.93 93	98.31 124	99.37 123	98.17 247

HY-MVS	92.50 7	97.79 89	97.17 111	99.63 17	98.98 126	99.32 9	97.49 367	99.52 14	95.69 94	98.32 141	97.41 263	93.32 118	99.77 139	98.08 136	95.75 227	99.81 99

VNet		97.21 120	96.57 138	99.13 68	98.97 127	97.82 86	99.03 287	99.21 30	94.31 141	99.18 95	98.88 187	86.26 241	99.89 107	98.93 83	94.32 249	99.69 117

thres200		96.96 133	96.21 150	99.22 50	98.97 127	98.84 36	99.85 132	99.71 7	93.17 187	96.26 205	98.88 187	89.87 193	99.51 165	94.26 226	94.91 241	99.31 190

tfpn200view9		96.79 141	95.99 155	99.19 53	98.94 129	98.82 37	99.78 156	99.71 7	92.86 198	96.02 210	98.87 190	89.33 200	99.50 167	93.84 233	94.57 245	99.27 197

thres400		96.78 143	95.99 155	99.16 60	98.94 129	98.82 37	99.78 156	99.71 7	92.86 198	96.02 210	98.87 190	89.33 200	99.50 167	93.84 233	94.57 245	99.16 204

sasdasda		97.09 126	96.32 145	99.39 40	98.93 131	98.95 27	99.72 182	97.35 295	94.45 129	97.88 159	99.42 131	86.71 233	99.52 163	98.48 114	93.97 255	99.72 112

Anonymous20231211		89.86 327	88.44 335	94.13 301	98.93 131	90.68 313	98.54 333	98.26 196	76.28 406	86.73 346	95.54 325	70.60 369	97.56 294	90.82 284	80.27 365	94.15 320

canonicalmvs		97.09 126	96.32 145	99.39 40	98.93 131	98.95 27	99.72 182	97.35 295	94.45 129	97.88 159	99.42 131	86.71 233	99.52 163	98.48 114	93.97 255	99.72 112

SDMVSNet		94.80 206	93.96 220	97.33 199	98.92 134	95.42 189	99.59 207	98.99 38	92.41 225	92.55 258	97.85 254	75.81 340	98.93 204	97.90 146	91.62 270	97.64 260

sd_testset		93.55 245	92.83 248	95.74 244	98.92 134	90.89 309	98.24 349	98.85 57	92.41 225	92.55 258	97.85 254	71.07 368	98.68 222	93.93 230	91.62 270	97.64 260

EPNet_dtu		95.71 183	95.39 180	96.66 218	98.92 134	93.41 251	99.57 212	98.90 48	96.19 85	97.52 167	98.56 219	92.65 138	97.36 299	77.89 390	98.33 160	99.20 202
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 68	97.60 88	99.60 22	98.92 134	99.28 17	99.89 112	99.52 14	95.58 97	98.24 147	99.39 138	93.33 117	99.74 145	97.98 142	95.58 230	99.78 105

CHOSEN 1792x2688		96.81 140	96.53 139	97.64 176	98.91 138	93.07 256	99.65 196	99.80 3	95.64 95	95.39 222	98.86 192	84.35 261	99.90 102	96.98 174	99.16 133	99.95 74

thres100view900		96.74 146	95.92 165	99.18 54	98.90 139	98.77 42	99.74 171	99.71 7	92.59 216	95.84 214	98.86 192	89.25 202	99.50 167	93.84 233	94.57 245	99.27 197

thres600view7		96.69 149	95.87 168	99.14 64	98.90 139	98.78 41	99.74 171	99.71 7	92.59 216	95.84 214	98.86 192	89.25 202	99.50 167	93.44 246	94.50 248	99.16 204

MSDG		94.37 224	93.36 239	97.40 193	98.88 141	93.95 236	99.37 246	97.38 292	85.75 361	90.80 275	99.17 157	84.11 264	99.88 113	86.35 338	98.43 158	98.36 244

MGCFI-Net		97.00 131	96.22 149	99.34 44	98.86 142	98.80 39	99.67 194	97.30 302	94.31 141	97.77 163	99.41 135	86.36 240	99.50 167	98.38 119	93.90 257	99.72 112

h-mvs33		94.92 203	94.36 208	96.59 220	98.85 143	91.29 301	98.93 298	98.94 42	95.90 88	98.77 116	98.42 230	90.89 178	99.77 139	97.80 150	70.76 401	98.72 234

Anonymous20240529		92.10 278	90.65 290	96.47 221	98.82 144	90.61 315	98.72 320	98.67 77	75.54 410	93.90 242	98.58 217	66.23 386	99.90 102	94.70 216	90.67 273	98.90 224

PVSNet_Blended_VisFu		97.27 116	96.81 126	98.66 104	98.81 145	96.67 136	99.92 89	98.64 81	94.51 128	96.38 203	98.49 223	89.05 206	99.88 113	97.10 170	98.34 159	99.43 174

PS-MVSNAJ		98.44 44	98.20 49	99.16 60	98.80 146	98.92 29	99.54 218	98.17 208	97.34 37	99.85 14	99.85 33	91.20 167	99.89 107	99.41 59	99.67 90	98.69 235

CANet_DTU		96.76 144	96.15 151	98.60 109	98.78 147	97.53 98	99.84 137	97.63 261	97.25 45	99.20 92	99.64 108	81.36 285	99.98 47	92.77 257	98.89 144	98.28 246

mvsany_test1		97.82 85	97.90 73	97.55 182	98.77 148	93.04 259	99.80 153	97.93 234	96.95 56	99.61 61	99.68 102	90.92 175	99.83 129	99.18 67	98.29 164	99.80 101

alignmvs		97.81 86	97.33 102	99.25 47	98.77 148	98.66 51	99.99 5	98.44 137	94.40 137	98.41 136	99.47 127	93.65 110	99.42 177	98.57 108	94.26 251	99.67 120

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 54	98.72 150	97.71 90	99.98 17	98.44 137	96.85 57	99.80 22	99.91 14	97.57 8	99.85 119	99.44 57	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 64	97.97 65	99.02 79	98.69 151	98.66 51	99.52 220	98.08 221	97.05 51	99.86 11	99.86 29	90.65 180	99.71 149	99.39 61	98.63 153	98.69 235

miper_enhance_ethall		94.36 226	93.98 219	95.49 247	98.68 152	95.24 197	99.73 178	97.29 305	93.28 184	89.86 287	95.97 312	94.37 85	97.05 321	92.20 261	84.45 327	94.19 313

fmvsm_s_conf0.5_n_5		98.08 69	97.71 82	99.17 57	98.67 153	97.69 94	99.99 5	98.57 97	97.40 35	99.89 6	99.69 95	85.99 244	99.96 67	99.80 25	99.40 121	99.85 94

ETVMVS		97.03 130	96.64 134	98.20 141	98.67 153	97.12 119	99.89 112	98.57 97	91.10 267	98.17 149	98.59 214	93.86 105	98.19 264	95.64 196	95.24 238	99.28 196

test2506		97.53 103	97.19 109	98.58 113	98.66 155	96.90 129	98.81 313	99.77 5	94.93 111	97.95 154	98.96 176	92.51 144	99.20 187	94.93 206	98.15 168	99.64 126

ECVR-MVS		95.66 186	95.05 193	97.51 186	98.66 155	93.71 241	98.85 310	98.45 132	94.93 111	96.86 188	98.96 176	75.22 346	99.20 187	95.34 198	98.15 168	99.64 126

mamv4		95.24 196	96.90 120	90.25 368	98.65 157	72.11 415	98.28 347	97.64 260	89.99 294	95.93 212	98.25 238	94.74 70	99.11 193	99.01 80	99.64 92	99.53 158

balanced_conf03		98.27 57	97.99 63	99.11 69	98.64 158	98.43 62	99.47 230	97.79 248	94.56 126	99.74 37	98.35 232	94.33 88	99.25 181	99.12 69	99.96 46	99.64 126

fmvsm_s_conf0.5_n_a		97.73 95	97.72 80	97.77 168	98.63 159	94.26 227	99.96 43	98.92 47	97.18 47	99.75 34	99.69 95	87.00 231	99.97 57	99.46 55	98.89 144	99.08 213

MVSMamba_PlusPlus		97.83 82	97.45 95	98.99 81	98.60 160	98.15 66	99.58 209	97.74 252	90.34 286	99.26 91	98.32 235	94.29 90	99.23 182	99.03 78	99.89 70	99.58 146

testing222		97.08 129	96.75 129	98.06 150	98.56 161	96.82 131	99.85 132	98.61 89	92.53 220	98.84 111	98.84 196	93.36 115	98.30 254	95.84 193	94.30 250	99.05 215

test1111		95.57 188	94.98 196	97.37 195	98.56 161	93.37 253	98.86 308	98.45 132	94.95 110	96.63 194	98.95 181	75.21 347	99.11 193	95.02 203	98.14 170	99.64 126

MVSTER		95.53 189	95.22 186	96.45 223	98.56 161	97.72 89	99.91 97	97.67 257	92.38 227	91.39 268	97.14 270	97.24 18	97.30 305	94.80 212	87.85 302	94.34 303

testing3-2		97.72 96	97.43 98	98.60 109	98.55 164	97.11 120	100.00 1	99.23 29	93.78 168	97.90 156	98.73 201	95.50 49	99.69 153	98.53 112	94.63 243	98.99 219

VDD-MVS		93.77 238	92.94 246	96.27 230	98.55 164	90.22 324	98.77 317	97.79 248	90.85 273	96.82 190	99.42 131	61.18 406	99.77 139	98.95 81	94.13 252	98.82 227

tpmvs		94.28 228	93.57 230	96.40 225	98.55 164	91.50 299	95.70 401	98.55 108	87.47 336	92.15 261	94.26 376	91.42 163	98.95 203	88.15 317	95.85 223	98.76 230

UGNet		95.33 195	94.57 204	97.62 179	98.55 164	94.85 209	98.67 326	99.32 26	95.75 93	96.80 191	96.27 302	72.18 360	99.96 67	94.58 219	99.05 140	98.04 251
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	95.18 197	94.10 215	98.43 128	98.55 164	95.99 166	97.91 362	97.31 301	90.35 285	89.48 299	99.22 153	85.19 252	99.89 107	90.40 294	98.47 157	99.41 176
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		95.95 175	96.49 140	94.34 295	98.51 169	89.99 329	99.39 242	98.57 97	93.14 189	97.33 174	98.31 237	93.44 113	94.68 392	93.69 243	95.98 217	98.34 245

UWE-MVS		96.79 141	96.72 131	97.00 206	98.51 169	93.70 242	99.71 185	98.60 91	92.96 194	97.09 181	98.34 234	96.67 31	98.85 207	92.11 263	96.50 205	98.44 240

myMVS_eth3d28		97.86 78	97.59 90	98.68 101	98.50 171	97.26 111	99.92 89	98.55 108	93.79 167	98.26 145	98.75 199	95.20 54	99.48 173	98.93 83	96.40 208	99.29 194

test_vis1_n_1920		95.44 191	95.31 183	95.82 242	98.50 171	88.74 345	99.98 17	97.30 302	97.84 23	99.85 14	99.19 155	66.82 384	99.97 57	98.82 92	99.46 115	98.76 230

BH-w/o		95.71 183	95.38 181	96.68 217	98.49 173	92.28 276	99.84 137	97.50 281	92.12 233	92.06 264	98.79 197	84.69 257	98.67 223	95.29 200	99.66 91	99.09 211

baseline1		95.78 180	94.86 198	98.54 118	98.47 174	98.07 73	99.06 280	97.99 227	92.68 210	94.13 239	98.62 213	93.28 121	98.69 221	93.79 238	85.76 315	98.84 226

fmvsm_s_conf0.5_n_7		97.70 98	97.74 79	97.59 181	98.44 175	95.16 203	99.97 34	98.65 78	97.95 19	99.62 54	99.78 62	86.09 242	99.94 84	99.69 42	99.50 111	97.66 259

EPMVS		96.53 155	96.01 154	98.09 148	98.43 176	96.12 164	96.36 388	99.43 20	93.53 175	97.64 165	95.04 353	94.41 80	98.38 246	91.13 275	98.11 171	99.75 108

kuosan		93.17 253	92.60 254	94.86 271	98.40 177	89.54 337	98.44 338	98.53 115	84.46 374	88.49 320	97.92 251	90.57 182	97.05 321	83.10 362	93.49 260	97.99 252

WBMVS		94.52 219	94.03 217	95.98 236	98.38 178	96.68 135	99.92 89	97.63 261	90.75 278	89.64 295	95.25 346	96.77 25	96.90 332	94.35 224	83.57 334	94.35 301

UBG		97.84 81	97.69 83	98.29 137	98.38 178	96.59 141	99.90 103	98.53 115	93.91 163	98.52 129	98.42 230	96.77 25	99.17 190	98.54 110	96.20 211	99.11 210

sss		97.57 102	97.03 116	99.18 54	98.37 180	98.04 76	99.73 178	99.38 22	93.46 177	98.76 119	99.06 163	91.21 166	99.89 107	96.33 184	97.01 197	99.62 133

testing11		97.48 105	97.27 105	98.10 147	98.36 181	96.02 165	99.92 89	98.45 132	93.45 179	98.15 150	98.70 204	95.48 50	99.22 183	97.85 148	95.05 240	99.07 214

BH-untuned		95.18 197	94.83 199	96.22 231	98.36 181	91.22 302	99.80 153	97.32 300	90.91 271	91.08 271	98.67 206	83.51 266	98.54 229	94.23 227	99.61 99	98.92 221

testing91		97.16 122	96.90 120	97.97 153	98.35 183	95.67 180	99.91 97	98.42 157	92.91 197	97.33 174	98.72 202	94.81 68	99.21 184	96.98 174	94.63 243	99.03 216

testing99		97.17 121	96.91 119	97.95 154	98.35 183	95.70 177	99.91 97	98.43 145	92.94 195	97.36 173	98.72 202	94.83 67	99.21 184	97.00 172	94.64 242	98.95 220

ET-MVSNet_ETH3D		94.37 224	93.28 241	97.64 176	98.30 185	97.99 78	99.99 5	97.61 267	94.35 138	71.57 413	99.45 130	96.23 35	95.34 382	96.91 179	85.14 322	99.59 140

AUN-MVS		93.28 250	92.60 254	95.34 254	98.29 186	90.09 327	99.31 253	98.56 102	91.80 245	96.35 204	98.00 246	89.38 199	98.28 257	92.46 258	69.22 406	97.64 260

FMVSNet3		92.69 266	91.58 275	95.99 235	98.29 186	97.42 106	99.26 262	97.62 264	89.80 297	89.68 291	95.32 340	81.62 283	96.27 361	87.01 334	85.65 316	94.29 305

PMMVS		96.76 144	96.76 128	96.76 214	98.28 188	92.10 280	99.91 97	97.98 229	94.12 149	99.53 66	99.39 138	86.93 232	98.73 216	96.95 177	97.73 178	99.45 171

hse-mvs2		94.38 223	94.08 216	95.31 256	98.27 189	90.02 328	99.29 258	98.56 102	95.90 88	98.77 116	98.00 246	90.89 178	98.26 261	97.80 150	69.20 407	97.64 260

PVSNet_0	88.03 19	91.80 285	90.27 299	96.38 227	98.27 189	90.46 319	99.94 79	99.61 13	93.99 157	86.26 356	97.39 265	71.13 367	99.89 107	98.77 96	67.05 412	98.79 229

UA-Net		96.54 154	95.96 161	98.27 138	98.23 191	95.71 176	98.00 360	98.45 132	93.72 172	98.41 136	99.27 147	88.71 212	99.66 158	91.19 274	97.69 179	99.44 173

test_cas_vis1_n_1920		96.59 153	96.23 148	97.65 175	98.22 192	94.23 228	99.99 5	97.25 309	97.77 24	99.58 62	99.08 161	77.10 323	99.97 57	97.64 158	99.45 116	98.74 232

FE-MVS		95.70 185	95.01 195	97.79 165	98.21 193	94.57 216	95.03 402	98.69 72	88.90 313	97.50 169	96.19 304	92.60 141	99.49 172	89.99 299	97.94 177	99.31 190

GG-mvs-BLEND				98.54 118	98.21 193	98.01 77	93.87 407	98.52 117		97.92 155	97.92 251	99.02 3	97.94 281	98.17 129	99.58 102	99.67 120

mvs_anonymous		95.65 187	95.03 194	97.53 184	98.19 195	95.74 174	99.33 250	97.49 282	90.87 272	90.47 278	97.10 272	88.23 215	97.16 312	95.92 191	97.66 181	99.68 118

MVS_Test		96.46 157	95.74 170	98.61 108	98.18 196	97.23 113	99.31 253	97.15 318	91.07 268	98.84 111	97.05 276	88.17 216	98.97 200	94.39 221	97.50 183	99.61 137

BH-RMVSNet		95.18 197	94.31 211	97.80 163	98.17 197	95.23 198	99.76 164	97.53 277	92.52 221	94.27 237	99.25 151	76.84 328	98.80 209	90.89 283	99.54 104	99.35 185

dongtai		91.55 291	91.13 284	92.82 340	98.16 198	86.35 368	99.47 230	98.51 120	83.24 382	85.07 365	97.56 259	90.33 187	94.94 388	76.09 398	91.73 268	97.18 270

RPSCF		91.80 285	92.79 250	88.83 379	98.15 199	69.87 417	98.11 356	96.60 366	83.93 377	94.33 235	99.27 147	79.60 306	99.46 176	91.99 264	93.16 265	97.18 270

ETV-MVS		97.92 75	97.80 78	98.25 139	98.14 200	96.48 143	99.98 17	97.63 261	95.61 96	99.29 89	99.46 129	92.55 143	98.82 208	99.02 79	98.54 155	99.46 169

IS-MVSNet		96.29 167	95.90 166	97.45 188	98.13 201	94.80 212	99.08 275	97.61 267	92.02 238	95.54 221	98.96 176	90.64 181	98.08 270	93.73 241	97.41 187	99.47 168

test_fmvsmconf_n		98.43 46	98.32 43	98.78 94	98.12 202	96.41 146	99.99 5	98.83 61	98.22 7	99.67 45	99.64 108	91.11 171	99.94 84	99.67 44	99.62 95	99.98 51

fmvsm_s_conf0.1_n_2		97.25 117	96.85 124	98.43 128	98.08 203	98.08 72	99.92 89	97.76 251	98.05 15	99.65 47	99.58 117	80.88 292	99.93 93	99.59 48	98.17 166	97.29 268

ab-mvs		94.69 211	93.42 235	98.51 122	98.07 204	96.26 153	96.49 386	98.68 74	90.31 287	94.54 230	97.00 278	76.30 335	99.71 149	95.98 190	93.38 263	99.56 149

XVG-OURS-SEG-HR		94.79 207	94.70 203	95.08 261	98.05 205	89.19 339	99.08 275	97.54 275	93.66 173	94.87 228	99.58 117	78.78 314	99.79 134	97.31 164	93.40 262	96.25 277

EIA-MVS		97.53 103	97.46 94	97.76 170	98.04 206	94.84 210	99.98 17	97.61 267	94.41 136	97.90 156	99.59 114	92.40 148	98.87 205	98.04 137	99.13 135	99.59 140

XVG-OURS		94.82 204	94.74 202	95.06 262	98.00 207	89.19 339	99.08 275	97.55 273	94.10 150	94.71 229	99.62 112	80.51 298	99.74 145	96.04 189	93.06 267	96.25 277

mvsmamba		96.94 134	96.73 130	97.55 182	97.99 208	94.37 224	99.62 203	97.70 254	93.13 190	98.42 135	97.92 251	88.02 217	98.75 215	98.78 95	99.01 141	99.52 160

dp		95.05 200	94.43 206	96.91 209	97.99 208	92.73 266	96.29 391	97.98 229	89.70 298	95.93 212	94.67 366	93.83 107	98.45 235	86.91 337	96.53 204	99.54 154

tpmrst		96.27 169	95.98 157	97.13 203	97.96 210	93.15 255	96.34 389	98.17 208	92.07 234	98.71 122	95.12 350	93.91 102	98.73 216	94.91 209	96.62 202	99.50 165

TR-MVS		94.54 216	93.56 231	97.49 187	97.96 210	94.34 225	98.71 321	97.51 280	90.30 288	94.51 232	98.69 205	75.56 341	98.77 212	92.82 256	95.99 216	99.35 185

Vis-MVSNet (Re-imp)		96.32 164	95.98 157	97.35 198	97.93 212	94.82 211	99.47 230	98.15 216	91.83 242	95.09 226	99.11 159	91.37 165	97.47 297	93.47 245	97.43 184	99.74 109

MDTV_nov1_ep13			95.69 172		97.90 213	94.15 230	95.98 397	98.44 137	93.12 191	97.98 153	95.74 316	95.10 57	98.58 226	90.02 298	96.92 199

Fast-Effi-MVS+		95.02 201	94.19 213	97.52 185	97.88 214	94.55 217	99.97 34	97.08 327	88.85 315	94.47 233	97.96 250	84.59 258	98.41 238	89.84 301	97.10 192	99.59 140

ADS-MVSNet2		93.80 237	93.88 223	93.55 323	97.87 215	85.94 372	94.24 403	96.84 352	90.07 291	96.43 200	94.48 371	90.29 189	95.37 381	87.44 324	97.23 189	99.36 182

ADS-MVSNet		94.79 207	94.02 218	97.11 205	97.87 215	93.79 238	94.24 403	98.16 213	90.07 291	96.43 200	94.48 371	90.29 189	98.19 264	87.44 324	97.23 189	99.36 182

Effi-MVS+		96.30 166	95.69 172	98.16 142	97.85 217	96.26 153	97.41 369	97.21 311	90.37 284	98.65 125	98.58 217	86.61 237	98.70 220	97.11 169	97.37 188	99.52 160

PatchmatchNet		95.94 176	95.45 178	97.39 194	97.83 218	94.41 221	96.05 395	98.40 166	92.86 198	97.09 181	95.28 345	94.21 94	98.07 272	89.26 305	98.11 171	99.70 115
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 214	93.61 226	97.74 172	97.82 219	96.26 153	99.96 43	97.78 250	85.76 359	94.00 240	97.54 260	76.95 327	99.21 184	97.23 166	95.43 233	97.76 258

1112_ss		96.01 174	95.20 187	98.42 130	97.80 220	96.41 146	99.65 196	96.66 363	92.71 207	92.88 254	99.40 136	92.16 153	99.30 179	91.92 266	93.66 258	99.55 150

Test_1112_low_res		95.72 181	94.83 199	98.42 130	97.79 221	96.41 146	99.65 196	96.65 364	92.70 208	92.86 255	96.13 307	92.15 154	99.30 179	91.88 267	93.64 259	99.55 150

Effi-MVS+-dtu		94.53 218	95.30 184	92.22 347	97.77 222	82.54 391	99.59 207	97.06 329	94.92 113	95.29 224	95.37 338	85.81 245	97.89 282	94.80 212	97.07 193	96.23 279

tpm cat1		93.51 246	92.52 260	96.47 221	97.77 222	91.47 300	96.13 393	98.06 222	80.98 395	92.91 253	93.78 380	89.66 194	98.87 205	87.03 333	96.39 209	99.09 211

FA-MVS(test-final)		95.86 177	95.09 191	98.15 145	97.74 224	95.62 182	96.31 390	98.17 208	91.42 258	96.26 205	96.13 307	90.56 183	99.47 175	92.18 262	97.07 193	99.35 185

xiu_mvs_v1_base_debu		97.43 106	97.06 112	98.55 115	97.74 224	98.14 68	99.31 253	97.86 243	96.43 74	99.62 54	99.69 95	85.56 247	99.68 154	99.05 72	98.31 161	97.83 254

xiu_mvs_v1_base		97.43 106	97.06 112	98.55 115	97.74 224	98.14 68	99.31 253	97.86 243	96.43 74	99.62 54	99.69 95	85.56 247	99.68 154	99.05 72	98.31 161	97.83 254

xiu_mvs_v1_base_debi		97.43 106	97.06 112	98.55 115	97.74 224	98.14 68	99.31 253	97.86 243	96.43 74	99.62 54	99.69 95	85.56 247	99.68 154	99.05 72	98.31 161	97.83 254

EPP-MVSNet		96.69 149	96.60 136	96.96 208	97.74 224	93.05 258	99.37 246	98.56 102	88.75 317	95.83 216	99.01 167	96.01 36	98.56 227	96.92 178	97.20 191	99.25 199

gg-mvs-nofinetune		93.51 246	91.86 272	98.47 124	97.72 229	97.96 82	92.62 411	98.51 120	74.70 413	97.33 174	69.59 427	98.91 4	97.79 285	97.77 155	99.56 103	99.67 120

IB-MVS	92.85 6	94.99 202	93.94 221	98.16 142	97.72 229	95.69 179	99.99 5	98.81 62	94.28 144	92.70 256	96.90 280	95.08 58	99.17 190	96.07 188	73.88 395	99.60 139
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		97.41 111	97.02 117	98.59 112	97.71 231	97.52 99	99.97 34	98.54 112	91.83 242	97.45 170	99.04 164	97.50 9	99.10 195	94.75 214	96.37 210	99.16 204

Syy-MVS		90.00 325	90.63 291	88.11 386	97.68 232	74.66 413	99.71 185	98.35 179	90.79 275	92.10 262	98.67 206	79.10 312	93.09 406	63.35 420	95.95 220	96.59 275

myMVS_eth3d		94.46 221	94.76 201	93.55 323	97.68 232	90.97 304	99.71 185	98.35 179	90.79 275	92.10 262	98.67 206	92.46 147	93.09 406	87.13 330	95.95 220	96.59 275

test_fmvs1_n		94.25 229	94.36 208	93.92 310	97.68 232	83.70 385	99.90 103	96.57 367	97.40 35	99.67 45	98.88 187	61.82 403	99.92 99	98.23 127	99.13 135	98.14 250

fmvsm_s_conf0.5_n_6		98.27 57	97.96 68	99.23 49	97.66 235	98.11 71	99.98 17	98.64 81	97.85 22	99.87 9	99.72 87	88.86 209	99.93 93	99.64 46	99.36 124	99.63 132

RRT-MVS		96.24 170	95.68 174	97.94 157	97.65 236	94.92 208	99.27 261	97.10 323	92.79 204	97.43 171	97.99 248	81.85 278	99.37 178	98.46 116	98.57 154	99.53 158

diffmvs		97.00 131	96.64 134	98.09 148	97.64 237	96.17 161	99.81 149	97.19 312	94.67 124	98.95 106	99.28 144	86.43 238	98.76 213	98.37 121	97.42 186	99.33 188
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		95.72 181	95.15 189	97.45 188	97.62 238	94.28 226	99.28 259	98.24 199	94.27 146	96.84 189	98.94 183	79.39 307	98.76 213	93.25 247	98.49 156	99.30 192
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 124	96.72 131	98.22 140	97.60 239	96.70 134	99.92 89	98.54 112	91.11 266	97.07 183	98.97 174	97.47 12	99.03 198	93.73 241	96.09 214	98.92 221

GDP-MVS		97.88 76	97.59 90	98.75 97	97.59 240	97.81 87	99.95 62	97.37 294	94.44 132	99.08 100	99.58 117	97.13 23	99.08 196	94.99 204	98.17 166	99.37 180

miper_ehance_all_eth		93.16 254	92.60 254	94.82 272	97.57 241	93.56 246	99.50 224	97.07 328	88.75 317	88.85 314	95.52 327	90.97 174	96.74 342	90.77 285	84.45 327	94.17 314

testing3		93.92 232	94.23 212	92.99 337	97.54 242	90.23 323	99.99 5	99.16 31	90.57 280	91.33 270	98.63 212	92.99 129	92.52 410	82.46 366	95.39 234	96.22 280

LCM-MVSNet-Re		92.31 274	92.60 254	91.43 356	97.53 243	79.27 408	99.02 289	91.83 423	92.07 234	80.31 388	94.38 374	83.50 267	95.48 379	97.22 167	97.58 182	99.54 154

GBi-Net		90.88 302	89.82 308	94.08 302	97.53 243	91.97 281	98.43 339	96.95 341	87.05 342	89.68 291	94.72 362	71.34 364	96.11 366	87.01 334	85.65 316	94.17 314

test1		90.88 302	89.82 308	94.08 302	97.53 243	91.97 281	98.43 339	96.95 341	87.05 342	89.68 291	94.72 362	71.34 364	96.11 366	87.01 334	85.65 316	94.17 314

FMVSNet2		91.02 299	89.56 313	95.41 252	97.53 243	95.74 174	98.98 291	97.41 290	87.05 342	88.43 324	95.00 356	71.34 364	96.24 363	85.12 349	85.21 321	94.25 308

tttt0517		96.85 138	96.49 140	97.92 158	97.48 247	95.89 169	99.85 132	98.54 112	90.72 279	96.63 194	98.93 185	97.47 12	99.02 199	93.03 254	95.76 226	98.85 225

BP-MVS1		98.33 53	98.18 51	98.81 92	97.44 248	97.98 79	99.96 43	98.17 208	94.88 115	98.77 116	99.59 114	97.59 7	99.08 196	98.24 126	98.93 143	99.36 182

casdiffmvs_mvg		96.43 158	95.94 163	97.89 162	97.44 248	95.47 186	99.86 129	97.29 305	93.35 180	96.03 209	99.19 155	85.39 250	98.72 218	97.89 147	97.04 195	99.49 167
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EC-MVSNet		97.38 113	97.24 106	97.80 163	97.41 250	95.64 181	99.99 5	97.06 329	94.59 125	99.63 51	99.32 143	89.20 205	98.14 266	98.76 97	99.23 131	99.62 133

c3_l		92.53 269	91.87 271	94.52 284	97.40 251	92.99 260	99.40 238	96.93 346	87.86 332	88.69 317	95.44 332	89.95 192	96.44 354	90.45 291	80.69 361	94.14 323

fmvsm_s_conf0.1_n		97.30 114	97.21 108	97.60 180	97.38 252	94.40 223	99.90 103	98.64 81	96.47 73	99.51 70	99.65 107	84.99 255	99.93 93	99.22 66	99.09 138	98.46 239

CDS-MVSNet		96.34 163	96.07 152	97.13 203	97.37 253	94.96 206	99.53 219	97.91 238	91.55 250	95.37 223	98.32 235	95.05 60	97.13 315	93.80 237	95.75 227	99.30 192
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 146	96.26 147	98.16 142	97.36 254	96.48 143	99.96 43	98.29 192	91.93 239	95.77 217	98.07 244	95.54 46	98.29 255	90.55 289	98.89 144	99.70 115

miper_lstm_enhance		91.81 282	91.39 281	93.06 336	97.34 255	89.18 341	99.38 244	96.79 357	86.70 349	87.47 338	95.22 347	90.00 191	95.86 375	88.26 315	81.37 350	94.15 320

baseline		96.43 158	95.98 157	97.76 170	97.34 255	95.17 202	99.51 222	97.17 315	93.92 162	96.90 187	99.28 144	85.37 251	98.64 224	97.50 161	96.86 201	99.46 169

cl____		92.31 274	91.58 275	94.52 284	97.33 257	92.77 262	99.57 212	96.78 358	86.97 346	87.56 336	95.51 328	89.43 198	96.62 347	88.60 310	82.44 342	94.16 319

DIV-MVS_self_test		92.32 273	91.60 274	94.47 288	97.31 258	92.74 264	99.58 209	96.75 359	86.99 345	87.64 334	95.54 325	89.55 197	96.50 351	88.58 311	82.44 342	94.17 314

casdiffmvs		96.42 160	95.97 160	97.77 168	97.30 259	94.98 205	99.84 137	97.09 326	93.75 171	96.58 196	99.26 150	85.07 253	98.78 211	97.77 155	97.04 195	99.54 154
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		94.36 226	93.48 233	96.99 207	97.29 260	93.54 247	99.96 43	96.72 361	88.35 326	93.43 244	98.94 183	82.05 275	98.05 273	88.12 319	96.48 207	99.37 180

eth_miper_zixun_eth		92.41 272	91.93 269	93.84 314	97.28 261	90.68 313	98.83 311	96.97 340	88.57 322	89.19 309	95.73 318	89.24 204	96.69 345	89.97 300	81.55 348	94.15 320

MVSFormer		96.94 134	96.60 136	97.95 154	97.28 261	97.70 92	99.55 216	97.27 307	91.17 263	99.43 76	99.54 123	90.92 175	96.89 333	94.67 217	99.62 95	99.25 199

lupinMVS		97.85 80	97.60 88	98.62 107	97.28 261	97.70 92	99.99 5	97.55 273	95.50 101	99.43 76	99.67 103	90.92 175	98.71 219	98.40 118	99.62 95	99.45 171

SCA		94.69 211	93.81 225	97.33 199	97.10 264	94.44 218	98.86 308	98.32 186	93.30 183	96.17 208	95.59 323	76.48 333	97.95 279	91.06 277	97.43 184	99.59 140

TAMVS		95.85 178	95.58 176	96.65 219	97.07 265	93.50 248	99.17 269	97.82 247	91.39 260	95.02 227	98.01 245	92.20 152	97.30 305	93.75 240	95.83 224	99.14 207

Fast-Effi-MVS+-dtu		93.72 241	93.86 224	93.29 328	97.06 266	86.16 369	99.80 153	96.83 353	92.66 211	92.58 257	97.83 256	81.39 284	97.67 290	89.75 302	96.87 200	96.05 282

CostFormer		96.10 171	95.88 167	96.78 213	97.03 267	92.55 272	97.08 377	97.83 246	90.04 293	98.72 121	94.89 360	95.01 62	98.29 255	96.54 183	95.77 225	99.50 165

test_fmvsmvis_n_1920		97.67 99	97.59 90	97.91 160	97.02 268	95.34 192	99.95 62	98.45 132	97.87 21	97.02 184	99.59 114	89.64 195	99.98 47	99.41 59	99.34 126	98.42 241

test-LLR		96.47 156	96.04 153	97.78 166	97.02 268	95.44 187	99.96 43	98.21 203	94.07 152	95.55 219	96.38 297	93.90 103	98.27 259	90.42 292	98.83 148	99.64 126

test-mter		96.39 161	95.93 164	97.78 166	97.02 268	95.44 187	99.96 43	98.21 203	91.81 244	95.55 219	96.38 297	95.17 55	98.27 259	90.42 292	98.83 148	99.64 126

gm-plane-assit					96.97 271	93.76 240			91.47 254		98.96 176		98.79 210	94.92 207

WB-MVSnew		92.90 260	92.77 251	93.26 330	96.95 272	93.63 244	99.71 185	98.16 213	91.49 251	94.28 236	98.14 241	81.33 286	96.48 352	79.47 381	95.46 231	89.68 407

QAPM		95.40 192	94.17 214	99.10 70	96.92 273	97.71 90	99.40 238	98.68 74	89.31 301	88.94 313	98.89 186	82.48 273	99.96 67	93.12 253	99.83 77	99.62 133

KD-MVS_2432*1600		88.00 347	86.10 351	93.70 319	96.91 274	94.04 232	97.17 374	97.12 321	84.93 369	81.96 379	92.41 391	92.48 145	94.51 394	79.23 382	52.68 426	92.56 377

miper_refine_blended		88.00 347	86.10 351	93.70 319	96.91 274	94.04 232	97.17 374	97.12 321	84.93 369	81.96 379	92.41 391	92.48 145	94.51 394	79.23 382	52.68 426	92.56 377

tpm2		95.47 190	95.18 188	96.35 228	96.91 274	91.70 294	96.96 380	97.93 234	88.04 330	98.44 134	95.40 334	93.32 118	97.97 276	94.00 229	95.61 229	99.38 178

FMVSNet5		88.32 343	87.47 345	90.88 359	96.90 277	88.39 353	97.28 371	95.68 387	82.60 389	84.67 367	92.40 393	79.83 304	91.16 415	76.39 397	81.51 349	93.09 369

3Dnovator+	91.53 11	96.31 165	95.24 185	99.52 28	96.88 278	98.64 54	99.72 182	98.24 199	95.27 106	88.42 326	98.98 172	82.76 272	99.94 84	97.10 170	99.83 77	99.96 67

Patchmatch-test		92.65 268	91.50 278	96.10 234	96.85 279	90.49 318	91.50 416	97.19 312	82.76 388	90.23 279	95.59 323	95.02 61	98.00 275	77.41 392	96.98 198	99.82 97

MVS		96.60 152	95.56 177	99.72 13	96.85 279	99.22 20	98.31 345	98.94 42	91.57 249	90.90 274	99.61 113	86.66 236	99.96 67	97.36 163	99.88 73	99.99 23

3Dnovator	91.47 12	96.28 168	95.34 182	99.08 73	96.82 281	97.47 104	99.45 235	98.81 62	95.52 100	89.39 300	99.00 169	81.97 276	99.95 76	97.27 165	99.83 77	99.84 95

EI-MVSNet		93.73 240	93.40 238	94.74 273	96.80 282	92.69 267	99.06 280	97.67 257	88.96 310	91.39 268	99.02 165	88.75 211	97.30 305	91.07 276	87.85 302	94.22 310

CVMVSNet		94.68 213	94.94 197	93.89 313	96.80 282	86.92 366	99.06 280	98.98 39	94.45 129	94.23 238	99.02 165	85.60 246	95.31 383	90.91 282	95.39 234	99.43 174

IterMVS-LS		92.69 266	92.11 265	94.43 292	96.80 282	92.74 264	99.45 235	96.89 349	88.98 308	89.65 294	95.38 337	88.77 210	96.34 358	90.98 280	82.04 345	94.22 310
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS		90.91 301	90.17 303	93.12 333	96.78 285	90.42 321	98.89 302	97.05 332	89.03 305	86.49 351	95.42 333	76.59 331	95.02 385	87.22 329	84.09 330	93.93 341
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 139	95.96 161	99.48 34	96.74 286	98.52 58	98.31 345	98.86 54	95.82 90	89.91 285	98.98 172	87.49 223	99.96 67	97.80 150	99.73 87	99.96 67

IterMVS-SCA-FT		90.85 304	90.16 304	92.93 338	96.72 287	89.96 330	98.89 302	96.99 336	88.95 311	86.63 348	95.67 319	76.48 333	95.00 386	87.04 332	84.04 333	93.84 348

MVS-HIRNet		86.22 354	83.19 367	95.31 256	96.71 288	90.29 322	92.12 413	97.33 299	62.85 421	86.82 345	70.37 426	69.37 372	97.49 296	75.12 400	97.99 176	98.15 248

VDDNet		93.12 255	91.91 270	96.76 214	96.67 289	92.65 270	98.69 324	98.21 203	82.81 387	97.75 164	99.28 144	61.57 404	99.48 173	98.09 135	94.09 253	98.15 248

dmvs_re		93.20 252	93.15 243	93.34 326	96.54 290	83.81 384	98.71 321	98.51 120	91.39 260	92.37 260	98.56 219	78.66 316	97.83 284	93.89 231	89.74 274	98.38 243

MIMVSNet		90.30 317	88.67 331	95.17 260	96.45 291	91.64 296	92.39 412	97.15 318	85.99 356	90.50 277	93.19 387	66.95 383	94.86 390	82.01 370	93.43 261	99.01 218

CR-MVSNet		93.45 249	92.62 253	95.94 238	96.29 292	92.66 268	92.01 414	96.23 375	92.62 213	96.94 185	93.31 385	91.04 172	96.03 371	79.23 382	95.96 218	99.13 208

RPMNet		89.76 329	87.28 346	97.19 202	96.29 292	92.66 268	92.01 414	98.31 188	70.19 420	96.94 185	85.87 419	87.25 227	99.78 136	62.69 421	95.96 218	99.13 208

tt0805		91.28 294	90.18 302	94.60 279	96.26 294	87.55 359	98.39 343	98.72 69	89.00 307	89.22 306	98.47 227	62.98 399	98.96 202	90.57 288	88.00 301	97.28 269

Patchmtry		89.70 330	88.49 334	93.33 327	96.24 295	89.94 333	91.37 417	96.23 375	78.22 403	87.69 333	93.31 385	91.04 172	96.03 371	80.18 380	82.10 344	94.02 331

test_vis1_rt		86.87 352	86.05 354	89.34 375	96.12 296	78.07 409	99.87 118	83.54 434	92.03 237	78.21 398	89.51 405	45.80 420	99.91 100	96.25 186	93.11 266	90.03 404

JIA-IIPM		91.76 288	90.70 289	94.94 266	96.11 297	87.51 360	93.16 410	98.13 218	75.79 409	97.58 166	77.68 424	92.84 134	97.97 276	88.47 314	96.54 203	99.33 188

OpenMVS	90.15 15	94.77 209	93.59 229	98.33 134	96.07 298	97.48 103	99.56 214	98.57 97	90.46 282	86.51 350	98.95 181	78.57 317	99.94 84	93.86 232	99.74 86	97.57 265

PAPM		98.60 33	98.42 34	99.14 64	96.05 299	98.96 26	99.90 103	99.35 24	96.68 66	98.35 140	99.66 105	96.45 33	98.51 230	99.45 56	99.89 70	99.96 67

CLD-MVS		94.06 231	93.90 222	94.55 283	96.02 300	90.69 312	99.98 17	97.72 253	96.62 70	91.05 273	98.85 195	77.21 322	98.47 231	98.11 133	89.51 280	94.48 289
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 314	88.75 330	95.25 258	95.99 301	90.16 325	91.22 418	97.54 275	76.80 405	97.26 177	86.01 418	91.88 159	96.07 370	66.16 417	95.91 222	99.51 163

ACMH+	89.98 16	90.35 315	89.54 314	92.78 342	95.99 301	86.12 370	98.81 313	97.18 314	89.38 300	83.14 375	97.76 257	68.42 377	98.43 236	89.11 306	86.05 314	93.78 351

DeepMVS_CX				82.92 396	95.98 303	58.66 427		96.01 380	92.72 206	78.34 397	95.51 328	58.29 409	98.08 270	82.57 365	85.29 319	92.03 385

ACMP	92.05 9	92.74 264	92.42 262	93.73 315	95.91 304	88.72 346	99.81 149	97.53 277	94.13 148	87.00 344	98.23 239	74.07 354	98.47 231	96.22 187	88.86 287	93.99 336
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 244	93.03 245	95.35 253	95.86 305	86.94 365	99.87 118	96.36 373	96.85 57	99.54 65	98.79 197	52.41 416	99.83 129	98.64 105	98.97 142	99.29 194

HQP-NCC					95.78 306		99.87 118		96.82 59	93.37 245

ACMP_Plane					95.78 306		99.87 118		96.82 59	93.37 245

HQP-MVS		94.61 215	94.50 205	94.92 267	95.78 306	91.85 286	99.87 118	97.89 239	96.82 59	93.37 245	98.65 209	80.65 296	98.39 242	97.92 144	89.60 275	94.53 285

NP-MVS					95.77 309	91.79 288					98.65 209

test_fmvsmconf0.1_n		97.74 93	97.44 96	98.64 106	95.76 310	96.20 158	99.94 79	98.05 224	98.17 10	98.89 110	99.42 131	87.65 221	99.90 102	99.50 52	99.60 101	99.82 97

plane_prior6					95.76 310	91.72 293						80.47 300

ACMM	91.95 10	92.88 261	92.52 260	93.98 309	95.75 312	89.08 343	99.77 159	97.52 279	93.00 193	89.95 284	97.99 248	76.17 337	98.46 234	93.63 244	88.87 286	94.39 297
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 234	92.84 247	96.80 212	95.73 313	93.57 245	99.88 115	97.24 310	92.57 218	92.92 252	96.66 289	78.73 315	97.67 290	87.75 322	94.06 254	99.17 203

plane_prior1					95.73 313

jason		97.24 118	96.86 123	98.38 133	95.73 313	97.32 108	99.97 34	97.40 291	95.34 104	98.60 128	99.54 123	87.70 220	98.56 227	97.94 143	99.47 113	99.25 199
jason: jason.
mmtdpeth		88.52 341	87.75 343	90.85 361	95.71 316	83.47 387	98.94 296	94.85 401	88.78 316	97.19 179	89.58 404	63.29 397	98.97 200	98.54 110	62.86 420	90.10 403

HQP_MVS		94.49 220	94.36 208	94.87 268	95.71 316	91.74 290	99.84 137	97.87 241	96.38 77	93.01 250	98.59 214	80.47 300	98.37 248	97.79 153	89.55 278	94.52 287

plane_prior7					95.71 316	91.59 298

ITE_SJBPF				92.38 344	95.69 319	85.14 376		95.71 386	92.81 201	89.33 303	98.11 242	70.23 370	98.42 237	85.91 344	88.16 299	93.59 359

fmvsm_s_conf0.1_n_a		97.09 126	96.90 120	97.63 178	95.65 320	94.21 229	99.83 144	98.50 126	96.27 82	99.65 47	99.64 108	84.72 256	99.93 93	99.04 75	98.84 147	98.74 232

ACMH	89.72 17	90.64 308	89.63 311	93.66 321	95.64 321	88.64 349	98.55 331	97.45 284	89.03 305	81.62 382	97.61 258	69.75 371	98.41 238	89.37 303	87.62 306	93.92 342
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 148	96.49 140	97.37 195	95.63 322	95.96 167	99.74 171	98.88 52	92.94 195	91.61 266	98.97 174	97.72 6	98.62 225	94.83 211	98.08 174	97.53 266

FMVSNet1		88.50 342	86.64 349	94.08 302	95.62 323	91.97 281	98.43 339	96.95 341	83.00 385	86.08 358	94.72 362	59.09 408	96.11 366	81.82 372	84.07 331	94.17 314

LPG-MVS_test		92.96 258	92.71 252	93.71 317	95.43 324	88.67 347	99.75 168	97.62 264	92.81 201	90.05 280	98.49 223	75.24 344	98.40 240	95.84 193	89.12 282	94.07 328

LGP-MVS_train				93.71 317	95.43 324	88.67 347		97.62 264	92.81 201	90.05 280	98.49 223	75.24 344	98.40 240	95.84 193	89.12 282	94.07 328

tpm		93.70 242	93.41 237	94.58 281	95.36 326	87.41 361	97.01 378	96.90 348	90.85 273	96.72 193	94.14 377	90.40 186	96.84 337	90.75 286	88.54 294	99.51 163

D2MVS		92.76 263	92.59 258	93.27 329	95.13 327	89.54 337	99.69 190	99.38 22	92.26 230	87.59 335	94.61 368	85.05 254	97.79 285	91.59 270	88.01 300	92.47 380

VPA-MVSNet		92.70 265	91.55 277	96.16 232	95.09 328	96.20 158	98.88 304	99.00 37	91.02 270	91.82 265	95.29 344	76.05 339	97.96 278	95.62 197	81.19 351	94.30 304

LTVRE_ROB	88.28 18	90.29 318	89.05 325	94.02 305	95.08 329	90.15 326	97.19 373	97.43 286	84.91 371	83.99 371	97.06 275	74.00 355	98.28 257	84.08 354	87.71 304	93.62 358
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		87.87 349	86.51 350	91.94 350	95.05 330	85.57 374	97.65 366	94.08 410	84.40 375	81.82 381	96.85 284	62.14 402	98.33 251	80.25 379	86.37 313	91.91 387

test0.0.03 1		93.86 233	93.61 226	94.64 277	95.02 331	92.18 279	99.93 86	98.58 95	94.07 152	87.96 330	98.50 222	93.90 103	94.96 387	81.33 373	93.17 264	96.78 272

UniMVSNet (Re)		93.07 257	92.13 264	95.88 239	94.84 332	96.24 157	99.88 115	98.98 39	92.49 223	89.25 304	95.40 334	87.09 229	97.14 314	93.13 252	78.16 375	94.26 306

USDC		90.00 325	88.96 326	93.10 335	94.81 333	88.16 355	98.71 321	95.54 391	93.66 173	83.75 373	97.20 269	65.58 388	98.31 253	83.96 357	87.49 308	92.85 374

VPNet		91.81 282	90.46 293	95.85 241	94.74 334	95.54 185	98.98 291	98.59 93	92.14 232	90.77 276	97.44 262	68.73 375	97.54 295	94.89 210	77.89 377	94.46 290

FIs		94.10 230	93.43 234	96.11 233	94.70 335	96.82 131	99.58 209	98.93 46	92.54 219	89.34 302	97.31 266	87.62 222	97.10 318	94.22 228	86.58 311	94.40 296

UniMVSNet_ETH3D		90.06 324	88.58 333	94.49 287	94.67 336	88.09 356	97.81 365	97.57 272	83.91 378	88.44 322	97.41 263	57.44 410	97.62 292	91.41 271	88.59 293	97.77 257

UniMVSNet_NR-MVSNet		92.95 259	92.11 265	95.49 247	94.61 337	95.28 195	99.83 144	99.08 34	91.49 251	89.21 307	96.86 283	87.14 228	96.73 343	93.20 248	77.52 380	94.46 290

test_fmvs2		89.47 334	89.70 310	88.77 382	94.54 338	75.74 410	99.83 144	94.70 406	94.71 121	91.08 271	96.82 288	54.46 413	97.78 287	92.87 255	88.27 297	92.80 375

MonoMVSNet		94.82 204	94.43 206	95.98 236	94.54 338	90.73 311	99.03 287	97.06 329	93.16 188	93.15 249	95.47 331	88.29 214	97.57 293	97.85 148	91.33 272	99.62 133

WR-MVS		92.31 274	91.25 282	95.48 250	94.45 340	95.29 194	99.60 206	98.68 74	90.10 290	88.07 329	96.89 281	80.68 295	96.80 341	93.14 251	79.67 368	94.36 298

nrg030		93.51 246	92.53 259	96.45 223	94.36 341	97.20 114	99.81 149	97.16 317	91.60 248	89.86 287	97.46 261	86.37 239	97.68 289	95.88 192	80.31 364	94.46 290

tfpnnormal		89.29 337	87.61 344	94.34 295	94.35 342	94.13 231	98.95 295	98.94 42	83.94 376	84.47 368	95.51 328	74.84 349	97.39 298	77.05 395	80.41 362	91.48 390

FC-MVSNet-test		93.81 236	93.15 243	95.80 243	94.30 343	96.20 158	99.42 237	98.89 50	92.33 229	89.03 312	97.27 268	87.39 225	96.83 339	93.20 248	86.48 312	94.36 298

SSC-MVS3.2		89.59 332	88.66 332	92.38 344	94.29 344	86.12 370	99.49 226	97.66 259	90.28 289	88.63 319	95.18 348	64.46 393	96.88 335	85.30 348	82.66 339	94.14 323

MS-PatchMatch		90.65 307	90.30 298	91.71 355	94.22 345	85.50 375	98.24 349	97.70 254	88.67 319	86.42 353	96.37 299	67.82 380	98.03 274	83.62 359	99.62 95	91.60 388

WR-MVS_H		91.30 292	90.35 296	94.15 299	94.17 346	92.62 271	99.17 269	98.94 42	88.87 314	86.48 352	94.46 373	84.36 260	96.61 348	88.19 316	78.51 373	93.21 368

DU-MVS		92.46 271	91.45 280	95.49 247	94.05 347	95.28 195	99.81 149	98.74 68	92.25 231	89.21 307	96.64 291	81.66 281	96.73 343	93.20 248	77.52 380	94.46 290

NR-MVSNet		91.56 290	90.22 300	95.60 245	94.05 347	95.76 173	98.25 348	98.70 71	91.16 265	80.78 387	96.64 291	83.23 270	96.57 349	91.41 271	77.73 379	94.46 290

CP-MVSNet		91.23 296	90.22 300	94.26 297	93.96 349	92.39 275	99.09 273	98.57 97	88.95 311	86.42 353	96.57 294	79.19 310	96.37 356	90.29 295	78.95 370	94.02 331

XXY-MVS		91.82 281	90.46 293	95.88 239	93.91 350	95.40 191	98.87 307	97.69 256	88.63 321	87.87 331	97.08 273	74.38 353	97.89 282	91.66 269	84.07 331	94.35 301

PS-CasMVS		90.63 309	89.51 316	93.99 308	93.83 351	91.70 294	98.98 291	98.52 117	88.48 323	86.15 357	96.53 296	75.46 342	96.31 360	88.83 308	78.86 372	93.95 339

test_0402		85.58 356	83.94 361	90.50 365	93.81 352	85.04 377	98.55 331	95.20 398	76.01 407	79.72 392	95.13 349	64.15 395	96.26 362	66.04 418	86.88 310	90.21 401

XVG-ACMP-BASELINE		91.22 297	90.75 288	92.63 343	93.73 353	85.61 373	98.52 335	97.44 285	92.77 205	89.90 286	96.85 284	66.64 385	98.39 242	92.29 260	88.61 291	93.89 344

TranMVSNet+NR-MVSNet		91.68 289	90.61 292	94.87 268	93.69 354	93.98 235	99.69 190	98.65 78	91.03 269	88.44 322	96.83 287	80.05 303	96.18 364	90.26 296	76.89 388	94.45 295

TransMVSNet (Re)		87.25 350	85.28 357	93.16 332	93.56 355	91.03 303	98.54 333	94.05 412	83.69 380	81.09 385	96.16 305	75.32 343	96.40 355	76.69 396	68.41 408	92.06 384

v10		90.25 319	88.82 328	94.57 282	93.53 356	93.43 250	99.08 275	96.87 351	85.00 368	87.34 342	94.51 369	80.93 291	97.02 328	82.85 364	79.23 369	93.26 366

testgi		89.01 339	88.04 340	91.90 351	93.49 357	84.89 379	99.73 178	95.66 388	93.89 166	85.14 363	98.17 240	59.68 407	94.66 393	77.73 391	88.88 285	96.16 281

v8		90.54 311	89.17 321	94.66 276	93.43 358	93.40 252	99.20 266	96.94 345	85.76 359	87.56 336	94.51 369	81.96 277	97.19 311	84.94 351	78.25 374	93.38 364

V42		91.28 294	90.12 305	94.74 273	93.42 359	93.46 249	99.68 192	97.02 333	87.36 338	89.85 289	95.05 352	81.31 287	97.34 301	87.34 327	80.07 366	93.40 362

pm-mvs1		89.36 336	87.81 342	94.01 306	93.40 360	91.93 284	98.62 329	96.48 371	86.25 354	83.86 372	96.14 306	73.68 356	97.04 324	86.16 341	75.73 393	93.04 371

v1144		91.09 298	89.83 307	94.87 268	93.25 361	93.69 243	99.62 203	96.98 338	86.83 348	89.64 295	94.99 357	80.94 290	97.05 321	85.08 350	81.16 352	93.87 346

v1192		90.62 310	89.25 320	94.72 275	93.13 362	93.07 256	99.50 224	97.02 333	86.33 353	89.56 298	95.01 354	79.22 309	97.09 320	82.34 368	81.16 352	94.01 333

v2v482		91.30 292	90.07 306	95.01 263	93.13 362	93.79 238	99.77 159	97.02 333	88.05 329	89.25 304	95.37 338	80.73 294	97.15 313	87.28 328	80.04 367	94.09 327

OPM-MVS		93.21 251	92.80 249	94.44 290	93.12 364	90.85 310	99.77 159	97.61 267	96.19 85	91.56 267	98.65 209	75.16 348	98.47 231	93.78 239	89.39 281	93.99 336
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 305	89.52 315	94.59 280	93.11 365	92.77 262	99.56 214	96.99 336	86.38 352	89.82 290	94.95 359	80.50 299	97.10 318	83.98 356	80.41 362	93.90 343

PEN-MVS		90.19 321	89.06 324	93.57 322	93.06 366	90.90 308	99.06 280	98.47 129	88.11 328	85.91 359	96.30 301	76.67 329	95.94 374	87.07 331	76.91 387	93.89 344

v1240		90.20 320	88.79 329	94.44 290	93.05 367	92.27 277	99.38 244	96.92 347	85.89 357	89.36 301	94.87 361	77.89 321	97.03 326	80.66 376	81.08 355	94.01 333

v148		90.70 306	89.63 311	93.92 310	92.97 368	90.97 304	99.75 168	96.89 349	87.51 335	88.27 327	95.01 354	81.67 280	97.04 324	87.40 326	77.17 385	93.75 352

v1921920		90.46 312	89.12 322	94.50 286	92.96 369	92.46 273	99.49 226	96.98 338	86.10 355	89.61 297	95.30 341	78.55 318	97.03 326	82.17 369	80.89 360	94.01 333

MVStest1		85.03 362	82.76 371	91.83 352	92.95 370	89.16 342	98.57 330	94.82 402	71.68 418	68.54 418	95.11 351	83.17 271	95.66 377	74.69 401	65.32 415	90.65 397

Baseline_NR-MVSNet		90.33 316	89.51 316	92.81 341	92.84 371	89.95 331	99.77 159	93.94 413	84.69 373	89.04 311	95.66 320	81.66 281	96.52 350	90.99 279	76.98 386	91.97 386

test_method		80.79 378	79.70 382	84.08 393	92.83 372	67.06 419	99.51 222	95.42 392	54.34 425	81.07 386	93.53 382	44.48 421	92.22 412	78.90 386	77.23 384	92.94 372

pmmvs4		92.10 278	91.07 286	95.18 259	92.82 373	94.96 206	99.48 229	96.83 353	87.45 337	88.66 318	96.56 295	83.78 265	96.83 339	89.29 304	84.77 325	93.75 352

LF4IMVS		89.25 338	88.85 327	90.45 367	92.81 374	81.19 401	98.12 355	94.79 403	91.44 255	86.29 355	97.11 271	65.30 391	98.11 268	88.53 313	85.25 320	92.07 383

DTE-MVSNet		89.40 335	88.24 338	92.88 339	92.66 375	89.95 331	99.10 272	98.22 202	87.29 339	85.12 364	96.22 303	76.27 336	95.30 384	83.56 360	75.74 392	93.41 361

EU-MVSNet		90.14 323	90.34 297	89.54 374	92.55 376	81.06 402	98.69 324	98.04 225	91.41 259	86.59 349	96.84 286	80.83 293	93.31 405	86.20 340	81.91 346	94.26 306

APD_test1		81.15 377	80.92 378	81.86 397	92.45 377	59.76 426	96.04 396	93.61 416	73.29 416	77.06 401	96.64 291	44.28 422	96.16 365	72.35 405	82.52 340	89.67 408

our_test_3		90.39 313	89.48 318	93.12 333	92.40 378	89.57 336	99.33 250	96.35 374	87.84 333	85.30 362	94.99 357	84.14 263	96.09 369	80.38 377	84.56 326	93.71 357

ppachtmachnet_test		89.58 333	88.35 336	93.25 331	92.40 378	90.44 320	99.33 250	96.73 360	85.49 364	85.90 360	95.77 315	81.09 289	96.00 373	76.00 399	82.49 341	93.30 365

v7n		89.65 331	88.29 337	93.72 316	92.22 380	90.56 317	99.07 279	97.10 323	85.42 366	86.73 346	94.72 362	80.06 302	97.13 315	81.14 374	78.12 376	93.49 360

dmvs_testset		83.79 371	86.07 353	76.94 401	92.14 381	48.60 436	96.75 383	90.27 426	89.48 299	78.65 395	98.55 221	79.25 308	86.65 424	66.85 415	82.69 338	95.57 283

PS-MVSNAJss		93.64 243	93.31 240	94.61 278	92.11 382	92.19 278	99.12 271	97.38 292	92.51 222	88.45 321	96.99 279	91.20 167	97.29 308	94.36 222	87.71 304	94.36 298

pmmvs5		90.17 322	89.09 323	93.40 325	92.10 383	89.77 334	99.74 171	95.58 390	85.88 358	87.24 343	95.74 316	73.41 357	96.48 352	88.54 312	83.56 335	93.95 339

N_pmnet		80.06 381	80.78 379	77.89 400	91.94 384	45.28 438	98.80 315	56.82 440	78.10 404	80.08 390	93.33 383	77.03 324	95.76 376	68.14 413	82.81 337	92.64 376

test_djsdf		92.83 262	92.29 263	94.47 288	91.90 385	92.46 273	99.55 216	97.27 307	91.17 263	89.96 283	96.07 310	81.10 288	96.89 333	94.67 217	88.91 284	94.05 330

SixPastTwentyTwo		88.73 340	88.01 341	90.88 359	91.85 386	82.24 393	98.22 352	95.18 399	88.97 309	82.26 378	96.89 281	71.75 362	96.67 346	84.00 355	82.98 336	93.72 356

K. test v3		88.05 346	87.24 347	90.47 366	91.82 387	82.23 394	98.96 294	97.42 288	89.05 304	76.93 403	95.60 322	68.49 376	95.42 380	85.87 345	81.01 358	93.75 352

OurMVSNet-221017-0		89.81 328	89.48 318	90.83 362	91.64 388	81.21 400	98.17 354	95.38 394	91.48 253	85.65 361	97.31 266	72.66 358	97.29 308	88.15 317	84.83 324	93.97 338

mvs_tets		91.81 282	91.08 285	94.00 307	91.63 389	90.58 316	98.67 326	97.43 286	92.43 224	87.37 341	97.05 276	71.76 361	97.32 303	94.75 214	88.68 290	94.11 326

Gipuma		66.95 394	65.00 394	72.79 406	91.52 390	67.96 418	66.16 429	95.15 400	47.89 427	58.54 424	67.99 429	29.74 426	87.54 423	50.20 428	77.83 378	62.87 429
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 161	95.74 170	98.32 135	91.47 391	95.56 184	99.84 137	97.30 302	97.74 25	97.89 158	99.35 142	79.62 305	99.85 119	99.25 65	99.24 130	99.55 150

jajsoiax		91.92 280	91.18 283	94.15 299	91.35 392	90.95 307	99.00 290	97.42 288	92.61 214	87.38 340	97.08 273	72.46 359	97.36 299	94.53 220	88.77 288	94.13 325

MDA-MVSNet-bldmvs		84.09 369	81.52 376	91.81 353	91.32 393	88.00 358	98.67 326	95.92 382	80.22 398	55.60 427	93.32 384	68.29 378	93.60 403	73.76 402	76.61 389	93.82 350

MVP-Stereo		90.93 300	90.45 295	92.37 346	91.25 394	88.76 344	98.05 359	96.17 377	87.27 340	84.04 369	95.30 341	78.46 319	97.27 310	83.78 358	99.70 89	91.09 391
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 358	83.32 366	92.10 348	90.96 395	88.58 350	99.20 266	96.52 369	79.70 400	57.12 426	92.69 389	79.11 311	93.86 400	77.10 394	77.46 382	93.86 347

YYNet1		85.50 359	83.33 365	92.00 349	90.89 396	88.38 354	99.22 265	96.55 368	79.60 401	57.26 425	92.72 388	79.09 313	93.78 401	77.25 393	77.37 383	93.84 348

anonymousdsp		91.79 287	90.92 287	94.41 293	90.76 397	92.93 261	98.93 298	97.17 315	89.08 303	87.46 339	95.30 341	78.43 320	96.92 331	92.38 259	88.73 289	93.39 363

lessismore_v0				90.53 364	90.58 398	80.90 403		95.80 383		77.01 402	95.84 313	66.15 387	96.95 329	83.03 363	75.05 394	93.74 355

EG-PatchMatch MVS		85.35 360	83.81 363	89.99 372	90.39 399	81.89 396	98.21 353	96.09 379	81.78 392	74.73 409	93.72 381	51.56 418	97.12 317	79.16 385	88.61 291	90.96 394

EGC-MVSNET		69.38 387	63.76 397	86.26 390	90.32 400	81.66 399	96.24 392	93.85 414	0.99 437	3.22 438	92.33 394	52.44 415	92.92 408	59.53 424	84.90 323	84.21 418

CMPMVS	61.59 21	84.75 365	85.14 358	83.57 394	90.32 400	62.54 422	96.98 379	97.59 271	74.33 414	69.95 415	96.66 289	64.17 394	98.32 252	87.88 321	88.41 296	89.84 406
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 368	82.92 369	89.21 376	90.03 402	82.60 390	96.89 382	95.62 389	80.59 396	75.77 408	89.17 406	65.04 392	94.79 391	72.12 406	81.02 357	90.23 400

pmmvs6		85.69 355	83.84 362	91.26 358	90.00 403	84.41 382	97.82 364	96.15 378	75.86 408	81.29 384	95.39 336	61.21 405	96.87 336	83.52 361	73.29 396	92.50 379

ttmdpeth		88.23 345	87.06 348	91.75 354	89.91 404	87.35 362	98.92 301	95.73 385	87.92 331	84.02 370	96.31 300	68.23 379	96.84 337	86.33 339	76.12 390	91.06 392

DSMNet-mixed		88.28 344	88.24 338	88.42 384	89.64 405	75.38 412	98.06 358	89.86 427	85.59 363	88.20 328	92.14 395	76.15 338	91.95 413	78.46 388	96.05 215	97.92 253

UnsupCasMVSNet_eth		85.52 357	83.99 359	90.10 370	89.36 406	83.51 386	96.65 384	97.99 227	89.14 302	75.89 407	93.83 379	63.25 398	93.92 398	81.92 371	67.90 411	92.88 373

Anonymous20231206		86.32 353	85.42 356	89.02 378	89.11 407	80.53 406	99.05 284	95.28 395	85.43 365	82.82 376	93.92 378	74.40 352	93.44 404	66.99 414	81.83 347	93.08 370

Anonymous20240521		85.15 361	83.81 363	89.16 377	88.32 408	82.69 389	98.80 315	95.74 384	79.72 399	81.53 383	90.99 398	65.38 390	94.16 396	72.69 404	81.11 354	90.63 398

OpenMVS_ROB	79.82 20	83.77 372	81.68 375	90.03 371	88.30 409	82.82 388	98.46 336	95.22 397	73.92 415	76.00 406	91.29 397	55.00 412	96.94 330	68.40 412	88.51 295	90.34 399

test20.03		84.72 366	83.99 359	86.91 388	88.19 410	80.62 405	98.88 304	95.94 381	88.36 325	78.87 393	94.62 367	68.75 374	89.11 419	66.52 416	75.82 391	91.00 393

KD-MVS_self_test		83.59 373	82.06 373	88.20 385	86.93 411	80.70 404	97.21 372	96.38 372	82.87 386	82.49 377	88.97 407	67.63 381	92.32 411	73.75 403	62.30 422	91.58 389

MIMVSNet1		82.58 374	80.51 380	88.78 380	86.68 412	84.20 383	96.65 384	95.41 393	78.75 402	78.59 396	92.44 390	51.88 417	89.76 418	65.26 419	78.95 370	92.38 382

CL-MVSNet_self_test		84.50 367	83.15 368	88.53 383	86.00 413	81.79 397	98.82 312	97.35 295	85.12 367	83.62 374	90.91 400	76.66 330	91.40 414	69.53 410	60.36 423	92.40 381

UnsupCasMVSNet_bld		79.97 383	77.03 388	88.78 380	85.62 414	81.98 395	93.66 408	97.35 295	75.51 411	70.79 414	83.05 421	48.70 419	94.91 389	78.31 389	60.29 424	89.46 411

mvs5depth		84.87 363	82.90 370	90.77 363	85.59 415	84.84 380	91.10 419	93.29 418	83.14 383	85.07 365	94.33 375	62.17 401	97.32 303	78.83 387	72.59 399	90.14 402

Patchmatch-RL test		86.90 351	85.98 355	89.67 373	84.45 416	75.59 411	89.71 422	92.43 420	86.89 347	77.83 400	90.94 399	94.22 92	93.63 402	87.75 322	69.61 403	99.79 102

pmmvs-eth3d		84.03 370	81.97 374	90.20 369	84.15 417	87.09 364	98.10 357	94.73 405	83.05 384	74.10 411	87.77 413	65.56 389	94.01 397	81.08 375	69.24 405	89.49 410

test_fmvs3		79.99 382	80.17 381	79.45 399	84.02 418	62.83 420	99.05 284	93.49 417	88.29 327	80.06 391	86.65 416	28.09 428	88.00 420	88.63 309	73.27 397	87.54 416

PM-MVS		80.47 379	78.88 384	85.26 391	83.79 419	72.22 414	95.89 399	91.08 424	85.71 362	76.56 405	88.30 409	36.64 424	93.90 399	82.39 367	69.57 404	89.66 409

new-patchmatchnet		81.19 376	79.34 383	86.76 389	82.86 420	80.36 407	97.92 361	95.27 396	82.09 391	72.02 412	86.87 415	62.81 400	90.74 417	71.10 407	63.08 419	89.19 413

mvsany_test3		82.12 375	81.14 377	85.06 392	81.87 421	70.41 416	97.09 376	92.14 421	91.27 262	77.84 399	88.73 408	39.31 423	95.49 378	90.75 286	71.24 400	89.29 412

WB-MVS		76.28 385	77.28 387	73.29 405	81.18 422	54.68 430	97.87 363	94.19 409	81.30 393	69.43 416	90.70 401	77.02 325	82.06 428	35.71 433	68.11 410	83.13 419

test_f		78.40 384	77.59 386	80.81 398	80.82 423	62.48 423	96.96 380	93.08 419	83.44 381	74.57 410	84.57 420	27.95 429	92.63 409	84.15 353	72.79 398	87.32 417

SSC-MVS		75.42 386	76.40 389	72.49 409	80.68 424	53.62 431	97.42 368	94.06 411	80.42 397	68.75 417	90.14 403	76.54 332	81.66 429	33.25 434	66.34 414	82.19 420

pmmvs3		80.27 380	77.77 385	87.76 387	80.32 425	82.43 392	98.23 351	91.97 422	72.74 417	78.75 394	87.97 412	57.30 411	90.99 416	70.31 408	62.37 421	89.87 405

testf1		68.38 390	66.92 391	72.78 407	78.80 426	50.36 433	90.95 420	87.35 432	55.47 423	58.95 422	88.14 410	20.64 433	87.60 421	57.28 425	64.69 416	80.39 422

APD_test2		68.38 390	66.92 391	72.78 407	78.80 426	50.36 433	90.95 420	87.35 432	55.47 423	58.95 422	88.14 410	20.64 433	87.60 421	57.28 425	64.69 416	80.39 422

ambc				83.23 395	77.17 428	62.61 421	87.38 424	94.55 408		76.72 404	86.65 416	30.16 425	96.36 357	84.85 352	69.86 402	90.73 396

test_vis3_rt		68.82 388	66.69 393	75.21 404	76.24 429	60.41 425	96.44 387	68.71 439	75.13 412	50.54 430	69.52 428	16.42 438	96.32 359	80.27 378	66.92 413	68.89 426

TDRefinement		84.76 364	82.56 372	91.38 357	74.58 430	84.80 381	97.36 370	94.56 407	84.73 372	80.21 389	96.12 309	63.56 396	98.39 242	87.92 320	63.97 418	90.95 395

E-PMN		52.30 398	52.18 400	52.67 415	71.51 431	45.40 437	93.62 409	76.60 437	36.01 431	43.50 432	64.13 431	27.11 430	67.31 434	31.06 435	26.06 430	45.30 433

EMVS		51.44 400	51.22 402	52.11 416	70.71 432	44.97 439	94.04 405	75.66 438	35.34 433	42.40 433	61.56 434	28.93 427	65.87 435	27.64 436	24.73 431	45.49 432

PMMVS2		67.15 393	64.15 396	76.14 403	70.56 433	62.07 424	93.89 406	87.52 431	58.09 422	60.02 421	78.32 423	22.38 432	84.54 426	59.56 423	47.03 428	81.80 421

FPMVS		68.72 389	68.72 390	68.71 411	65.95 434	44.27 440	95.97 398	94.74 404	51.13 426	53.26 428	90.50 402	25.11 431	83.00 427	60.80 422	80.97 359	78.87 424

wuyk23d		20.37 404	20.84 407	18.99 419	65.34 435	27.73 442	50.43 430	7.67 443	9.50 436	8.01 437	6.34 437	6.13 441	26.24 436	23.40 437	10.69 435	2.99 434

LCM-MVSNet		67.77 392	64.73 395	76.87 402	62.95 436	56.25 429	89.37 423	93.74 415	44.53 428	61.99 420	80.74 422	20.42 435	86.53 425	69.37 411	59.50 425	87.84 414

MVE	53.74 22	51.54 399	47.86 403	62.60 413	59.56 437	50.93 432	79.41 427	77.69 436	35.69 432	36.27 434	61.76 433	5.79 442	69.63 432	37.97 432	36.61 429	67.24 427
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 396	52.24 399	67.66 412	49.27 438	56.82 428	83.94 425	82.02 435	70.47 419	33.28 435	64.54 430	17.23 437	69.16 433	45.59 430	23.85 432	77.02 425

tmp_tt		65.23 395	62.94 398	72.13 410	44.90 439	50.03 435	81.05 426	89.42 430	38.45 429	48.51 431	99.90 18	54.09 414	78.70 431	91.84 268	18.26 433	87.64 415

PMVS	49.05 23	53.75 397	51.34 401	60.97 414	40.80 440	34.68 441	74.82 428	89.62 429	37.55 430	28.67 436	72.12 425	7.09 440	81.63 430	43.17 431	68.21 409	66.59 428
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 402	39.14 405	33.31 417	19.94 441	24.83 443	98.36 344	9.75 442	15.53 435	51.31 429	87.14 414	19.62 436	17.74 437	47.10 429	3.47 436	57.36 430

testmvs		40.60 401	44.45 404	29.05 418	19.49 442	14.11 444	99.68 192	18.47 441	20.74 434	64.59 419	98.48 226	10.95 439	17.09 438	56.66 427	11.01 434	55.94 431

mmdepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

monomultidepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

test_blank		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.02 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

eth-test2					0.00 443

eth-test					0.00 443

uanet_test		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

DCPMVS		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

cdsmvs_eth3d_5k		23.43 403	31.24 406	0.00 420	0.00 443	0.00 445	0.00 431	98.09 219	0.00 438	0.00 439	99.67 103	83.37 268	0.00 439	0.00 438	0.00 437	0.00 435

pcd_1.5k_mvsjas		7.60 406	10.13 409	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	91.20 167	0.00 439	0.00 438	0.00 437	0.00 435

sosnet-low-res		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

sosnet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uncertanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

Regformer		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

ab-mvs-re		8.28 405	11.04 408	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	99.40 136	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 439	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

WAC-MVS						90.97 304								86.10 343

PC_three_1452									96.96 55	99.80 22	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 145	97.27 42	99.80 22	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 71	99.83 18	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

GSMVS																99.59 140

sam_mvs1												94.72 71				99.59 140

sam_mvs												94.25 91

MTGPA								98.28 193

test_post1							95.78 400				59.23 435	93.20 125	97.74 288	91.06 277

test_post											63.35 432	94.43 79	98.13 267

patchmatchnet-post											91.70 396	95.12 56	97.95 279

MTMP							99.87 118	96.49 370

test9_res														99.71 40	99.99 21	100.00 1

agg_prior2														99.48 54	100.00 1	100.00 1

test_prior4						98.05 75	99.94 79

test_prior2							99.95 62		95.78 91	99.73 39	99.76 67	96.00 37		99.78 28	100.00 1

旧先验2							99.46 234		94.21 147	99.85 14			99.95 76	96.96 176

新几何2							99.40 238

无先验							99.49 226	98.71 70	93.46 177				100.00 1	94.36 222		99.99 23

原ACMM2							99.90 103

testdata2													99.99 36	90.54 290

segment_acmp												96.68 29

testdata1							99.28 259		96.35 81

plane_prior5								97.87 241					98.37 248	97.79 153	89.55 278	94.52 287

plane_prior4											98.59 214

plane_prior3						91.64 296			96.63 68	93.01 250

plane_prior2							99.84 137		96.38 77

plane_prior						91.74 290	99.86 129		96.76 63						89.59 277

n2								0.00 444

nn								0.00 444

door-mid								89.69 428

test11								98.44 137

door								90.31 425

HQP5-MVS						91.85 286

BP-MVS														97.92 144

HQP4-MVS										93.37 245			98.39 242			94.53 285

HQP3-MVS								97.89 239							89.60 275

HQP2-MVS												80.65 296

MDTV_nov1_ep13_2view						96.26 153	96.11 394		91.89 240	98.06 151		94.40 81		94.30 225		99.67 120

ACMMP++_ref															87.04 309

ACMMP++															88.23 298

Test By Simon												92.82 136

High-resolution multi-view benchmark