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		97.23 113	96.80 121	98.51 118	99.99 1	95.60 179	99.09 265	98.84 59	93.32 176	96.74 185	99.72 85	86.04 237	100.00 1	98.01 132	99.43 117	99.94 78

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 15	98.69 70	98.20 8	99.93 1	99.98 2	96.82 24	100.00 1	99.75 33	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 31	98.64 78	98.47 3	99.13 93	99.92 13	96.38 34	100.00 1	99.74 35	100.00 1	100.00 1

mPP-MVS		98.39 51	98.20 49	98.97 82	99.97 3	96.92 124	99.95 57	98.38 166	95.04 105	98.61 123	99.80 54	93.39 111	100.00 1	98.64 100	100.00 1	99.98 51

CPTT-MVS		97.64 94	97.32 97	98.58 109	99.97 3	95.77 168	99.96 38	98.35 172	89.90 287	98.36 135	99.79 58	91.18 167	99.99 36	98.37 115	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 84	98.44 130	92.06 229	98.40 134	99.84 44	95.68 44	100.00 1	98.19 122	99.71 88	99.97 61

PAPR		98.52 38	98.16 53	99.58 24	99.97 3	98.77 42	99.95 57	98.43 138	95.35 99	98.03 147	99.75 73	94.03 97	99.98 47	98.11 127	99.83 77	99.99 23

HFP-MVS		98.56 35	98.37 39	99.14 62	99.96 8	97.43 103	99.95 57	98.61 85	94.77 114	99.31 82	99.85 33	94.22 90	100.00 1	98.70 95	99.98 32	99.98 51

region2R		98.54 36	98.37 39	99.05 72	99.96 8	97.18 112	99.96 38	98.55 102	94.87 112	99.45 69	99.85 33	94.07 96	100.00 1	98.67 97	100.00 1	99.98 51

ACMMPR		98.50 39	98.32 43	99.05 72	99.96 8	97.18 112	99.95 57	98.60 87	94.77 114	99.31 82	99.84 44	93.73 106	100.00 1	98.70 95	99.98 32	99.98 51

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 31	98.62 84	98.02 17	99.90 3	99.95 3	97.33 17	100.00 1	99.54 46	100.00 1	100.00 1

CP-MVS		98.45 43	98.32 43	98.87 87	99.96 8	96.62 134	99.97 31	98.39 162	94.43 129	98.90 105	99.87 27	94.30 87	100.00 1	99.04 71	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 155	96.63 64	99.75 31	99.93 11	97.49 10

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 57	98.43 138					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 29	98.55 28	99.15 60	99.94 13	97.50 99	99.94 74	98.42 150	96.22 79	99.41 74	99.78 62	94.34 84	99.96 67	98.92 80	99.95 50	99.99 23

X-MVStestdata		93.83 227	92.06 260	99.15 60	99.94 13	97.50 99	99.94 74	98.42 150	96.22 79	99.41 74	41.37 428	94.34 84	99.96 67	98.92 80	99.95 50	99.99 23

test_prior				99.43 35	99.94 13	98.49 60		98.65 76					99.80 128			99.99 23

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 15	98.86 53	97.10 44	99.80 19	99.94 4	95.92 40	100.00 1	99.51 47	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 91	98.39 162	97.20 42	99.46 68	99.85 33	95.53 48	99.79 130	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 63	97.97 65	99.03 74	99.94 13	97.17 115	99.95 57	98.39 162	94.70 118	98.26 141	99.81 53	91.84 158	100.00 1	98.85 86	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	99.87 112	98.33 177	93.97 154	99.76 30	99.87 27	94.99 62	99.75 139	98.55 104	100.00 1	99.98 51

PAPM_NR		98.12 66	97.93 70	98.70 98	99.94 13	96.13 158	99.82 141	98.43 138	94.56 122	97.52 161	99.70 89	94.40 79	99.98 47	97.00 166	99.98 32	99.99 23

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 194	99.44 19	97.33 35	99.00 101	99.72 85	94.03 97	99.98 47	98.73 94	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 38	98.43 138	97.27 38	99.80 19	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		98.41 155	97.71 23	99.84 14				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 138	97.26 40	99.80 19	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 57	98.32 179	97.28 36	99.83 15	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 38	98.42 150	97.28 36	99.86 8	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 81	99.93 24	97.24 109	99.95 57	98.42 150	97.50 30	99.52 64	99.88 24	97.43 16	99.71 145	99.50 48	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		98.43 138		99.63 48			99.85 115

FOURS1					99.92 31	97.66 93	99.95 57	98.36 170	95.58 93	99.52 64

ZD-MVS					99.92 31	98.57 56		98.52 110	92.34 221	99.31 82	99.83 46	95.06 57	99.80 128	99.70 40	99.97 42

GST-MVS		98.27 57	97.97 65	99.17 56	99.92 31	97.57 95	99.93 81	98.39 162	94.04 152	98.80 110	99.74 80	92.98 127	100.00 1	98.16 124	99.76 85	99.93 79

TEST9					99.92 31	98.92 29	99.96 38	98.43 138	93.90 160	99.71 38	99.86 29	95.88 41	99.85 115

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 38	98.43 138	94.35 134	99.71 38	99.86 29	95.94 38	99.85 115	99.69 41	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 38	98.43 138	94.35 134	99.69 40	99.85 33	95.94 38	99.85 115

PGM-MVS		98.34 52	98.13 55	98.99 79	99.92 31	97.00 120	99.75 162	99.50 17	93.90 160	99.37 79	99.76 66	93.24 120	100.00 1	97.75 151	99.96 46	99.98 51

ACMMP		97.74 89	97.44 91	98.66 101	99.92 31	96.13 158	99.18 260	99.45 18	94.84 113	96.41 195	99.71 87	91.40 161	99.99 36	97.99 134	98.03 171	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 57	98.43 138	96.48 67	99.80 19	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		98.41 155					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 155					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 57	98.56 96	97.56 29	99.44 70	99.85 33	95.38 51	100.00 1	99.31 58	99.99 21	99.87 91

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 112	98.36 170	94.08 147	99.74 34	99.73 82	94.08 95	99.74 141	99.42 54	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	99.24 255	98.47 122	98.14 12	99.08 96	99.91 14	93.09 124	100.00 1	99.04 71	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 38				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	99.87 112	98.44 130	97.48 31	99.64 47	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 67

CSCG		97.10 118	97.04 109	97.27 195	99.89 45	91.92 279	99.90 97	99.07 34	88.67 311	95.26 218	99.82 49	93.17 123	99.98 47	98.15 125	99.47 112	99.90 87

ZNCC-MVS		98.31 54	98.03 61	99.17 56	99.88 49	97.59 94	99.94 74	98.44 130	94.31 137	98.50 128	99.82 49	93.06 125	99.99 36	98.30 119	99.99 21	99.93 79

SR-MVS		98.46 42	98.30 46	98.93 85	99.88 49	97.04 119	99.84 131	98.35 172	94.92 109	99.32 81	99.80 54	93.35 113	99.78 132	99.30 59	99.95 50	99.96 67

9.14			98.38 37		99.87 51		99.91 91	98.33 177	93.22 179	99.78 28	99.89 22	94.57 75	99.85 115	99.84 22	99.97 42

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 123	98.38 166	93.19 180	99.77 29	99.94 4	95.54 46	100.00 1	99.74 35	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 74	99.86 53	97.10 117	99.98 15	98.80 64	90.78 270	99.62 51	99.78 62	95.30 52	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 82	99.39 235	98.28 186	95.76 88	97.18 173	99.88 24	92.74 134	100.00 1	98.67 97	99.88 73	99.99 23

LS3D		95.84 172	95.11 183	98.02 148	99.85 54	95.10 199	98.74 310	98.50 119	87.22 333	93.66 236	99.86 29	87.45 220	99.95 75	90.94 274	99.81 83	99.02 214

HPM-MVS		97.96 69	97.72 77	98.68 99	99.84 56	96.39 145	99.90 97	98.17 201	92.61 207	98.62 122	99.57 116	91.87 157	99.67 152	98.87 85	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 95	99.83 57	96.59 137	99.40 231	98.51 113	95.29 101	98.51 127	99.76 66	93.60 110	99.71 145	98.53 107	99.52 106	99.95 74

save fliter					99.82 58	98.79 40	99.96 38	98.40 159	97.66 25

PLC	95.54 3	97.93 72	97.89 73	98.05 147	99.82 58	94.77 209	99.92 84	98.46 124	93.93 157	97.20 171	99.27 143	95.44 50	99.97 57	97.41 156	99.51 109	99.41 174
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 61	98.08 59	98.78 92	99.81 60	96.60 135	99.82 141	98.30 184	93.95 156	99.37 79	99.77 64	92.84 131	99.76 138	98.95 77	99.92 64	99.97 61

EI-MVSNet-UG-set		98.14 65	97.99 63	98.60 106	99.80 61	96.27 148	99.36 240	98.50 119	95.21 103	98.30 138	99.75 73	93.29 117	99.73 144	98.37 115	99.30 124	99.81 98

SR-MVS-dyc-post		98.31 54	98.17 52	98.71 97	99.79 62	96.37 146	99.76 158	98.31 181	94.43 129	99.40 76	99.75 73	93.28 118	99.78 132	98.90 83	99.92 64	99.97 61

RE-MVS-def			98.13 55		99.79 62	96.37 146	99.76 158	98.31 181	94.43 129	99.40 76	99.75 73	92.95 128		98.90 83	99.92 64	99.97 61

HPM-MVS_fast		97.80 84	97.50 88	98.68 99	99.79 62	96.42 141	99.88 109	98.16 206	91.75 239	98.94 103	99.54 119	91.82 159	99.65 154	97.62 154	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 97	98.21 196	93.53 169	99.81 17	99.89 22	94.70 71	99.86 114	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 4	99.34 25	98.70 2	99.44 70	99.75 73	93.24 120	99.99 36	99.94 11	99.41 119	99.95 74

旧先验1					99.76 66	97.52 97		98.64 78			99.85 33	95.63 45			99.94 55	99.99 23

OMC-MVS		97.28 109	97.23 101	97.41 186	99.76 66	93.36 248	99.65 190	97.95 225	96.03 83	97.41 166	99.70 89	89.61 193	99.51 160	96.73 175	98.25 161	99.38 176

新几何1				99.42 37	99.75 69	98.27 65		98.63 83	92.69 202	99.55 59	99.82 49	94.40 79	100.00 1	91.21 266	99.94 55	99.99 23

MP-MVS-pluss		98.07 68	97.64 82	99.38 43	99.74 70	98.41 63	99.74 165	98.18 200	93.35 174	96.45 192	99.85 33	92.64 136	99.97 57	98.91 82	99.89 70	99.77 105
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	99.77 153	98.38 166	96.73 60	99.88 7	99.74 80	94.89 64	99.59 156	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		98.40 159		99.65 44		94.76 67	99.75 139		99.98 32	99.99 23

原ACMM1				98.96 83	99.73 73	96.99 121		98.51 113	94.06 150	99.62 51	99.85 33	94.97 63	99.96 67	95.11 195	99.95 50	99.92 84

TSAR-MVS + GP.		98.60 33	98.51 31	98.86 88	99.73 73	96.63 133	99.97 31	97.92 230	98.07 14	98.76 115	99.55 117	95.00 61	99.94 83	99.91 16	97.68 176	99.99 23

CANet		98.27 57	97.82 75	99.63 17	99.72 75	99.10 23	99.98 15	98.51 113	97.00 50	98.52 125	99.71 87	87.80 215	99.95 75	99.75 33	99.38 120	99.83 95

reproduce_model		98.75 27	98.66 23	99.03 74	99.71 76	97.10 117	99.73 172	98.23 194	97.02 49	99.18 91	99.90 18	94.54 76	99.99 36	99.77 29	99.90 69	99.99 23

F-COLMAP		96.93 130	96.95 112	96.87 205	99.71 76	91.74 284	99.85 126	97.95 225	93.11 185	95.72 211	99.16 154	92.35 146	99.94 83	95.32 193	99.35 122	98.92 217

reproduce-ours		98.78 24	98.67 21	99.09 69	99.70 78	97.30 107	99.74 165	98.25 190	97.10 44	99.10 94	99.90 18	94.59 72	99.99 36	99.77 29	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 69	99.70 78	97.30 107	99.74 165	98.25 190	97.10 44	99.10 94	99.90 18	94.59 72	99.99 36	99.77 29	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 74	98.34 176	96.38 73	99.81 17	99.76 66	94.59 72	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 62	99.12 5	95.59 240	99.67 81	86.91 360	99.95 57	98.89 49	97.60 26	99.90 3	99.76 66	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	99.85 126	98.37 169	94.68 119	99.53 62	99.83 46	92.87 130	100.00 1	98.66 99	99.84 76	99.99 23

DeepPCF-MVS	95.94 2	97.71 92	98.98 12	93.92 303	99.63 83	81.76 390	99.96 38	98.56 96	99.47 1	99.19 90	99.99 1	94.16 94	100.00 1	99.92 13	99.93 61	100.00 1

EPNet		98.49 40	98.40 35	98.77 94	99.62 84	96.80 129	99.90 97	99.51 16	97.60 26	99.20 88	99.36 137	93.71 107	99.91 96	97.99 134	98.71 148	99.61 135
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 4	99.76 6	98.39 4	99.39 78	99.80 54	90.49 182	99.96 67	99.89 17	99.43 117	99.98 51

PVSNet_BlendedMVS		96.05 166	95.82 162	96.72 210	99.59 85	96.99 121	99.95 57	99.10 31	94.06 150	98.27 139	95.80 307	89.00 204	99.95 75	99.12 65	87.53 300	93.24 359

PVSNet_Blended		97.94 71	97.64 82	98.83 89	99.59 85	96.99 121	100.00 1	99.10 31	95.38 98	98.27 139	99.08 157	89.00 204	99.95 75	99.12 65	99.25 126	99.57 146

PatchMatch-RL		96.04 167	95.40 172	97.95 150	99.59 85	95.22 195	99.52 214	99.07 34	93.96 155	96.49 191	98.35 226	82.28 267	99.82 127	90.15 290	99.22 129	98.81 224

dcpmvs_2		97.42 104	98.09 58	95.42 245	99.58 89	87.24 356	99.23 256	96.95 333	94.28 140	98.93 104	99.73 82	94.39 82	99.16 186	99.89 17	99.82 81	99.86 93

test222					99.55 90	97.41 105	99.34 241	98.55 102	91.86 234	99.27 86	99.83 46	93.84 104			99.95 50	99.99 23

CNLPA		97.76 88	97.38 93	98.92 86	99.53 91	96.84 126	99.87 112	98.14 210	93.78 163	96.55 190	99.69 92	92.28 148	99.98 47	97.13 162	99.44 116	99.93 79

API-MVS		97.86 76	97.66 80	98.47 120	99.52 92	95.41 186	99.47 223	98.87 52	91.68 240	98.84 107	99.85 33	92.34 147	99.99 36	98.44 111	99.96 46	100.00 1

PVSNet	91.05 13	97.13 117	96.69 127	98.45 122	99.52 92	95.81 166	99.95 57	99.65 12	94.73 116	99.04 99	99.21 150	84.48 252	99.95 75	94.92 201	98.74 147	99.58 144

114514_t		97.41 105	96.83 119	99.14 62	99.51 94	97.83 84	99.89 106	98.27 188	88.48 315	99.06 98	99.66 101	90.30 185	99.64 155	96.32 179	99.97 42	99.96 67

cl22		93.77 231	93.25 235	95.33 249	99.49 95	94.43 213	99.61 199	98.09 212	90.38 276	89.16 303	95.61 314	90.56 180	97.34 295	91.93 258	84.45 320	94.21 305

testdata				98.42 126	99.47 96	95.33 189		98.56 96	93.78 163	99.79 27	99.85 33	93.64 109	99.94 83	94.97 199	99.94 55	100.00 1

MAR-MVS		97.43 100	97.19 103	98.15 141	99.47 96	94.79 208	99.05 276	98.76 65	92.65 205	98.66 120	99.82 49	88.52 209	99.98 47	98.12 126	99.63 94	99.67 119
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		94.54 209	93.42 228	97.91 156	99.46 98	94.04 226	98.93 290	97.48 275	81.15 386	90.04 275	99.55 117	87.02 226	99.95 75	88.97 300	98.11 167	99.73 109

MVS_111021_LR		98.42 47	98.38 37	98.53 116	99.39 99	95.79 167	99.87 112	99.86 2	96.70 61	98.78 111	99.79 58	92.03 154	99.90 98	99.17 64	99.86 75	99.88 89

CHOSEN 280x420		99.01 14	99.03 10	98.95 84	99.38 100	98.87 33	98.46 328	99.42 21	97.03 48	99.02 100	99.09 156	99.35 2	98.21 257	99.73 37	99.78 84	99.77 105

MVS_111021_HR		98.72 28	98.62 26	99.01 78	99.36 101	97.18 112	99.93 81	99.90 1	96.81 58	98.67 119	99.77 64	93.92 99	99.89 103	99.27 60	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 38	98.44 130	97.96 18	99.55 59	99.94 4	97.18 21	100.00 1	93.81 230	99.94 55	99.98 51

TAPA-MVS	92.12 8	94.42 215	93.60 221	96.90 204	99.33 102	91.78 283	99.78 150	98.00 219	89.89 288	94.52 224	99.47 123	91.97 155	99.18 183	69.90 401	99.52 106	99.73 109
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 186	95.07 185	96.32 223	99.32 104	96.60 135	99.76 158	98.85 56	96.65 63	87.83 324	96.05 304	99.52 1	98.11 262	96.58 176	81.07 348	94.25 301

SPE-MVS-test		97.88 74	97.94 69	97.70 169	99.28 105	95.20 196	99.98 15	97.15 310	95.53 95	99.62 51	99.79 58	92.08 153	98.38 240	98.75 93	99.28 125	99.52 158

test_fmvsm_n_1920		98.44 44	98.61 27	97.92 154	99.27 106	95.18 197	100.00 1	98.90 47	98.05 15	99.80 19	99.73 82	92.64 136	99.99 36	99.58 45	99.51 109	98.59 234

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 46	99.21 107	97.91 83	99.98 15	98.85 56	98.25 5	99.92 2	99.75 73	94.72 69	99.97 57	99.87 19	99.64 92	99.95 74

test_yl		97.83 79	97.37 94	99.21 50	99.18 108	97.98 78	99.64 194	99.27 27	91.43 249	97.88 153	98.99 166	95.84 42	99.84 123	98.82 87	95.32 230	99.79 101

DCV-MVSNet		97.83 79	97.37 94	99.21 50	99.18 108	97.98 78	99.64 194	99.27 27	91.43 249	97.88 153	98.99 166	95.84 42	99.84 123	98.82 87	95.32 230	99.79 101

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 47	99.17 110	97.81 86	99.98 15	98.86 53	98.25 5	99.90 3	99.76 66	94.21 92	99.97 57	99.87 19	99.52 106	99.98 51

DeepC-MVS	94.51 4	96.92 131	96.40 137	98.45 122	99.16 111	95.90 164	99.66 189	98.06 215	96.37 76	94.37 227	99.49 122	83.29 262	99.90 98	97.63 153	99.61 99	99.55 148
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 91	97.70 24	98.21 143	99.24 148	92.58 139	99.94 83	98.63 102	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 15	98.64 78	98.14 12	99.86 8	99.76 66	87.99 214	99.97 57	99.72 38	99.54 104	99.91 86

CS-MVS		97.79 86	97.91 71	97.43 185	99.10 114	94.42 214	99.99 4	97.10 315	95.07 104	99.68 41	99.75 73	92.95 128	98.34 244	98.38 113	99.14 131	99.54 152

Anonymous202405211		93.10 249	91.99 261	96.40 219	99.10 114	89.65 328	98.88 296	97.93 227	83.71 371	94.00 233	98.75 195	68.79 366	99.88 109	95.08 196	91.71 262	99.68 117

fmvsm_s_conf0.5_n		97.80 84	97.85 74	97.67 170	99.06 116	94.41 215	99.98 15	98.97 40	97.34 33	99.63 48	99.69 92	87.27 222	99.97 57	99.62 43	99.06 135	98.62 233

HyFIR lowres test		96.66 145	96.43 136	97.36 191	99.05 117	93.91 231	99.70 183	99.80 3	90.54 274	96.26 198	98.08 236	92.15 151	98.23 256	96.84 174	95.46 225	99.93 79

LFMVS		94.75 203	93.56 224	98.30 132	99.03 118	95.70 173	98.74 310	97.98 222	87.81 326	98.47 129	99.39 134	67.43 375	99.53 157	98.01 132	95.20 233	99.67 119

fmvsm_s_conf0.5_n_2		97.59 95	97.28 98	98.53 116	99.01 119	98.15 66	99.98 15	98.59 89	98.17 10	99.75 31	99.63 107	81.83 272	99.94 83	99.78 27	98.79 146	97.51 260

AllTest		92.48 263	91.64 266	95.00 258	99.01 119	88.43 344	98.94 288	96.82 347	86.50 342	88.71 308	98.47 221	74.73 343	99.88 109	85.39 339	96.18 207	96.71 266

TestCases				95.00 258	99.01 119	88.43 344		96.82 347	86.50 342	88.71 308	98.47 221	74.73 343	99.88 109	85.39 339	96.18 207	96.71 266

COLMAP_ROB	90.47 14	92.18 270	91.49 272	94.25 291	99.00 122	88.04 350	98.42 334	96.70 354	82.30 382	88.43 316	99.01 163	76.97 319	99.85 115	86.11 335	96.50 201	94.86 277
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 70	97.66 80	98.81 90	98.99 123	98.07 72	99.98 15	98.81 61	98.18 9	99.89 6	99.70 89	84.15 255	99.97 57	99.76 32	99.50 111	98.39 238

test_fmvs1		95.35 187	95.68 167	94.36 288	98.99 123	84.98 370	99.96 38	96.65 356	97.60 26	99.73 36	98.96 172	71.58 356	99.93 91	98.31 118	99.37 121	98.17 242

HY-MVS	92.50 7	97.79 86	97.17 105	99.63 17	98.98 125	99.32 9	97.49 359	99.52 14	95.69 90	98.32 137	97.41 256	93.32 115	99.77 135	98.08 130	95.75 221	99.81 98

VNet		97.21 114	96.57 132	99.13 66	98.97 126	97.82 85	99.03 279	99.21 29	94.31 137	99.18 91	98.88 183	86.26 236	99.89 103	98.93 79	94.32 242	99.69 116

thres200		96.96 127	96.21 143	99.22 49	98.97 126	98.84 36	99.85 126	99.71 7	93.17 181	96.26 198	98.88 183	89.87 190	99.51 160	94.26 220	94.91 235	99.31 188

tfpn200view9		96.79 135	95.99 148	99.19 52	98.94 128	98.82 37	99.78 150	99.71 7	92.86 191	96.02 203	98.87 186	89.33 197	99.50 162	93.84 227	94.57 238	99.27 194

thres400		96.78 137	95.99 148	99.16 58	98.94 128	98.82 37	99.78 150	99.71 7	92.86 191	96.02 203	98.87 186	89.33 197	99.50 162	93.84 227	94.57 238	99.16 201

sasdasda		97.09 120	96.32 138	99.39 40	98.93 130	98.95 27	99.72 176	97.35 287	94.45 125	97.88 153	99.42 127	86.71 229	99.52 158	98.48 108	93.97 248	99.72 111

Anonymous20231211		89.86 320	88.44 327	94.13 294	98.93 130	90.68 307	98.54 325	98.26 189	76.28 398	86.73 338	95.54 318	70.60 362	97.56 288	90.82 277	80.27 357	94.15 313

canonicalmvs		97.09 120	96.32 138	99.39 40	98.93 130	98.95 27	99.72 176	97.35 287	94.45 125	97.88 153	99.42 127	86.71 229	99.52 158	98.48 108	93.97 248	99.72 111

SDMVSNet		94.80 199	93.96 213	97.33 193	98.92 133	95.42 185	99.59 201	98.99 37	92.41 218	92.55 251	97.85 247	75.81 333	98.93 198	97.90 140	91.62 263	97.64 254

sd_testset		93.55 238	92.83 241	95.74 238	98.92 133	90.89 303	98.24 341	98.85 56	92.41 218	92.55 251	97.85 247	71.07 361	98.68 216	93.93 224	91.62 263	97.64 254

EPNet_dtu		95.71 176	95.39 173	96.66 212	98.92 133	93.41 245	99.57 206	98.90 47	96.19 81	97.52 161	98.56 213	92.65 135	97.36 293	77.89 382	98.33 156	99.20 199
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 67	97.60 84	99.60 22	98.92 133	99.28 17	99.89 106	99.52 14	95.58 93	98.24 142	99.39 134	93.33 114	99.74 141	97.98 136	95.58 224	99.78 104

CHOSEN 1792x2688		96.81 134	96.53 133	97.64 172	98.91 137	93.07 250	99.65 190	99.80 3	95.64 91	95.39 215	98.86 188	84.35 254	99.90 98	96.98 168	99.16 130	99.95 74

thres100view900		96.74 140	95.92 158	99.18 53	98.90 138	98.77 42	99.74 165	99.71 7	92.59 209	95.84 207	98.86 188	89.25 199	99.50 162	93.84 227	94.57 238	99.27 194

thres600view7		96.69 143	95.87 161	99.14 62	98.90 138	98.78 41	99.74 165	99.71 7	92.59 209	95.84 207	98.86 188	89.25 199	99.50 162	93.44 239	94.50 241	99.16 201

MSDG		94.37 217	93.36 232	97.40 187	98.88 140	93.95 230	99.37 238	97.38 284	85.75 353	90.80 268	99.17 153	84.11 257	99.88 109	86.35 331	98.43 154	98.36 240

MGCFI-Net		97.00 125	96.22 142	99.34 44	98.86 141	98.80 39	99.67 188	97.30 294	94.31 137	97.77 157	99.41 131	86.36 235	99.50 162	98.38 113	93.90 250	99.72 111

h-mvs33		94.92 196	94.36 201	96.59 214	98.85 142	91.29 295	98.93 290	98.94 41	95.90 84	98.77 112	98.42 224	90.89 175	99.77 135	97.80 144	70.76 393	98.72 230

Anonymous20240529		92.10 271	90.65 283	96.47 215	98.82 143	90.61 309	98.72 312	98.67 75	75.54 402	93.90 235	98.58 211	66.23 379	99.90 98	94.70 210	90.67 266	98.90 220

PVSNet_Blended_VisFu		97.27 110	96.81 120	98.66 101	98.81 144	96.67 132	99.92 84	98.64 78	94.51 124	96.38 196	98.49 217	89.05 203	99.88 109	97.10 164	98.34 155	99.43 172

PS-MVSNAJ		98.44 44	98.20 49	99.16 58	98.80 145	98.92 29	99.54 212	98.17 201	97.34 33	99.85 11	99.85 33	91.20 164	99.89 103	99.41 55	99.67 90	98.69 231

CANet_DTU		96.76 138	96.15 144	98.60 106	98.78 146	97.53 96	99.84 131	97.63 253	97.25 41	99.20 88	99.64 104	81.36 278	99.98 47	92.77 250	98.89 140	98.28 241

mvsany_test1		97.82 82	97.90 72	97.55 177	98.77 147	93.04 253	99.80 147	97.93 227	96.95 52	99.61 57	99.68 98	90.92 172	99.83 125	99.18 63	98.29 160	99.80 100

alignmvs		97.81 83	97.33 96	99.25 47	98.77 147	98.66 51	99.99 4	98.44 130	94.40 133	98.41 132	99.47 123	93.65 108	99.42 171	98.57 103	94.26 244	99.67 119

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 53	98.72 149	97.71 89	99.98 15	98.44 130	96.85 53	99.80 19	99.91 14	97.57 8	99.85 115	99.44 53	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 63	97.97 65	99.02 77	98.69 150	98.66 51	99.52 214	98.08 214	97.05 47	99.86 8	99.86 29	90.65 177	99.71 145	99.39 57	98.63 149	98.69 231

miper_enhance_ethall		94.36 219	93.98 212	95.49 241	98.68 151	95.24 193	99.73 172	97.29 297	93.28 178	89.86 280	95.97 305	94.37 83	97.05 315	92.20 254	84.45 320	94.19 306

ETVMVS		97.03 124	96.64 128	98.20 137	98.67 152	97.12 116	99.89 106	98.57 93	91.10 260	98.17 144	98.59 208	93.86 103	98.19 258	95.64 190	95.24 232	99.28 193

test2506		97.53 97	97.19 103	98.58 109	98.66 153	96.90 125	98.81 305	99.77 5	94.93 107	97.95 149	98.96 172	92.51 141	99.20 181	94.93 200	98.15 164	99.64 125

ECVR-MVS		95.66 179	95.05 186	97.51 181	98.66 153	93.71 235	98.85 302	98.45 125	94.93 107	96.86 181	98.96 172	75.22 339	99.20 181	95.34 192	98.15 164	99.64 125

mamv4		95.24 189	96.90 114	90.25 360	98.65 155	72.11 407	98.28 339	97.64 252	89.99 286	95.93 205	98.25 231	94.74 68	99.11 187	99.01 76	99.64 92	99.53 156

balanced_conf03		98.27 57	97.99 63	99.11 67	98.64 156	98.43 62	99.47 223	97.79 241	94.56 122	99.74 34	98.35 226	94.33 86	99.25 175	99.12 65	99.96 46	99.64 125

fmvsm_s_conf0.5_n_a		97.73 91	97.72 77	97.77 164	98.63 157	94.26 221	99.96 38	98.92 46	97.18 43	99.75 31	99.69 92	87.00 227	99.97 57	99.46 51	98.89 140	99.08 210

MVSMamba_PlusPlus		97.83 79	97.45 90	98.99 79	98.60 158	98.15 66	99.58 203	97.74 245	90.34 279	99.26 87	98.32 229	94.29 88	99.23 176	99.03 74	99.89 70	99.58 144

testing222		97.08 123	96.75 123	98.06 146	98.56 159	96.82 127	99.85 126	98.61 85	92.53 213	98.84 107	98.84 192	93.36 112	98.30 248	95.84 187	94.30 243	99.05 212

test1111		95.57 181	94.98 189	97.37 189	98.56 159	93.37 247	98.86 300	98.45 125	94.95 106	96.63 187	98.95 177	75.21 340	99.11 187	95.02 197	98.14 166	99.64 125

MVSTER		95.53 182	95.22 179	96.45 217	98.56 159	97.72 88	99.91 91	97.67 250	92.38 220	91.39 261	97.14 263	97.24 18	97.30 299	94.80 206	87.85 295	94.34 296

VDD-MVS		93.77 231	92.94 239	96.27 224	98.55 162	90.22 318	98.77 309	97.79 241	90.85 266	96.82 183	99.42 127	61.18 398	99.77 135	98.95 77	94.13 245	98.82 223

tpmvs		94.28 221	93.57 223	96.40 219	98.55 162	91.50 293	95.70 393	98.55 102	87.47 328	92.15 254	94.26 368	91.42 160	98.95 197	88.15 310	95.85 217	98.76 226

UGNet		95.33 188	94.57 197	97.62 175	98.55 162	94.85 204	98.67 318	99.32 26	95.75 89	96.80 184	96.27 295	72.18 353	99.96 67	94.58 213	99.05 136	98.04 246
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	95.18 190	94.10 208	98.43 124	98.55 162	95.99 162	97.91 354	97.31 293	90.35 278	89.48 292	99.22 149	85.19 245	99.89 103	90.40 287	98.47 153	99.41 174
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		96.79 135	96.72 125	97.00 200	98.51 166	93.70 236	99.71 179	98.60 87	92.96 187	97.09 174	98.34 228	96.67 31	98.85 201	92.11 256	96.50 201	98.44 236

test_vis1_n_1920		95.44 184	95.31 176	95.82 236	98.50 167	88.74 338	99.98 15	97.30 294	97.84 20	99.85 11	99.19 151	66.82 377	99.97 57	98.82 87	99.46 114	98.76 226

BH-w/o		95.71 176	95.38 174	96.68 211	98.49 168	92.28 270	99.84 131	97.50 273	92.12 226	92.06 257	98.79 193	84.69 250	98.67 217	95.29 194	99.66 91	99.09 208

baseline1		95.78 173	94.86 191	98.54 114	98.47 169	98.07 72	99.06 272	97.99 220	92.68 203	94.13 232	98.62 207	93.28 118	98.69 215	93.79 232	85.76 308	98.84 222

EPMVS		96.53 149	96.01 147	98.09 144	98.43 170	96.12 160	96.36 380	99.43 20	93.53 169	97.64 159	95.04 345	94.41 78	98.38 240	91.13 268	98.11 167	99.75 107

kuosan		93.17 246	92.60 247	94.86 265	98.40 171	89.54 330	98.44 330	98.53 108	84.46 366	88.49 312	97.92 244	90.57 179	97.05 315	83.10 354	93.49 253	97.99 247

WBMVS		94.52 212	94.03 210	95.98 230	98.38 172	96.68 131	99.92 84	97.63 253	90.75 271	89.64 288	95.25 339	96.77 25	96.90 326	94.35 218	83.57 327	94.35 294

UBG		97.84 78	97.69 79	98.29 133	98.38 172	96.59 137	99.90 97	98.53 108	93.91 159	98.52 125	98.42 224	96.77 25	99.17 184	98.54 105	96.20 206	99.11 207

sss		97.57 96	97.03 110	99.18 53	98.37 174	98.04 75	99.73 172	99.38 22	93.46 171	98.76 115	99.06 159	91.21 163	99.89 103	96.33 178	97.01 193	99.62 131

testing11		97.48 99	97.27 99	98.10 143	98.36 175	96.02 161	99.92 84	98.45 125	93.45 173	98.15 145	98.70 198	95.48 49	99.22 177	97.85 142	95.05 234	99.07 211

BH-untuned		95.18 190	94.83 192	96.22 225	98.36 175	91.22 296	99.80 147	97.32 292	90.91 264	91.08 264	98.67 200	83.51 259	98.54 223	94.23 221	99.61 99	98.92 217

testing91		97.16 116	96.90 114	97.97 149	98.35 177	95.67 176	99.91 91	98.42 150	92.91 190	97.33 168	98.72 196	94.81 66	99.21 178	96.98 168	94.63 237	99.03 213

testing99		97.17 115	96.91 113	97.95 150	98.35 177	95.70 173	99.91 91	98.43 138	92.94 188	97.36 167	98.72 196	94.83 65	99.21 178	97.00 166	94.64 236	98.95 216

ET-MVSNet_ETH3D		94.37 217	93.28 234	97.64 172	98.30 179	97.99 77	99.99 4	97.61 259	94.35 134	71.57 405	99.45 126	96.23 35	95.34 375	96.91 173	85.14 315	99.59 138

AUN-MVS		93.28 243	92.60 247	95.34 248	98.29 180	90.09 321	99.31 245	98.56 96	91.80 238	96.35 197	98.00 239	89.38 196	98.28 251	92.46 251	69.22 398	97.64 254

FMVSNet3		92.69 259	91.58 268	95.99 229	98.29 180	97.42 104	99.26 254	97.62 256	89.80 289	89.68 284	95.32 333	81.62 276	96.27 354	87.01 327	85.65 309	94.29 298

PMMVS		96.76 138	96.76 122	96.76 208	98.28 182	92.10 274	99.91 91	97.98 222	94.12 145	99.53 62	99.39 134	86.93 228	98.73 210	96.95 171	97.73 174	99.45 169

hse-mvs2		94.38 216	94.08 209	95.31 250	98.27 183	90.02 322	99.29 250	98.56 96	95.90 84	98.77 112	98.00 239	90.89 175	98.26 255	97.80 144	69.20 399	97.64 254

PVSNet_0	88.03 19	91.80 278	90.27 292	96.38 221	98.27 183	90.46 313	99.94 74	99.61 13	93.99 153	86.26 348	97.39 258	71.13 360	99.89 103	98.77 91	67.05 404	98.79 225

UA-Net		96.54 148	95.96 154	98.27 134	98.23 185	95.71 172	98.00 352	98.45 125	93.72 166	98.41 132	99.27 143	88.71 208	99.66 153	91.19 267	97.69 175	99.44 171

test_cas_vis1_n_1920		96.59 147	96.23 141	97.65 171	98.22 186	94.23 222	99.99 4	97.25 301	97.77 21	99.58 58	99.08 157	77.10 316	99.97 57	97.64 152	99.45 115	98.74 228

FE-MVS		95.70 178	95.01 188	97.79 161	98.21 187	94.57 210	95.03 394	98.69 70	88.90 305	97.50 163	96.19 297	92.60 138	99.49 167	89.99 292	97.94 173	99.31 188

GG-mvs-BLEND				98.54 114	98.21 187	98.01 76	93.87 399	98.52 110		97.92 150	97.92 244	99.02 3	97.94 275	98.17 123	99.58 102	99.67 119

mvs_anonymous		95.65 180	95.03 187	97.53 179	98.19 189	95.74 170	99.33 242	97.49 274	90.87 265	90.47 271	97.10 265	88.23 211	97.16 306	95.92 185	97.66 177	99.68 117

MVS_Test		96.46 151	95.74 163	98.61 105	98.18 190	97.23 110	99.31 245	97.15 310	91.07 261	98.84 107	97.05 269	88.17 212	98.97 194	94.39 215	97.50 179	99.61 135

BH-RMVSNet		95.18 190	94.31 204	97.80 159	98.17 191	95.23 194	99.76 158	97.53 269	92.52 214	94.27 230	99.25 147	76.84 321	98.80 203	90.89 276	99.54 104	99.35 183

dongtai		91.55 284	91.13 277	92.82 333	98.16 192	86.35 361	99.47 223	98.51 113	83.24 374	85.07 357	97.56 252	90.33 184	94.94 381	76.09 390	91.73 261	97.18 263

RPSCF		91.80 278	92.79 243	88.83 371	98.15 193	69.87 409	98.11 348	96.60 358	83.93 369	94.33 228	99.27 143	79.60 299	99.46 170	91.99 257	93.16 258	97.18 263

ETV-MVS		97.92 73	97.80 76	98.25 135	98.14 194	96.48 139	99.98 15	97.63 253	95.61 92	99.29 85	99.46 125	92.55 140	98.82 202	99.02 75	98.54 151	99.46 167

IS-MVSNet		96.29 161	95.90 159	97.45 183	98.13 195	94.80 207	99.08 267	97.61 259	92.02 231	95.54 214	98.96 172	90.64 178	98.08 264	93.73 235	97.41 183	99.47 166

test_fmvsmconf_n		98.43 46	98.32 43	98.78 92	98.12 196	96.41 142	99.99 4	98.83 60	98.22 7	99.67 42	99.64 104	91.11 168	99.94 83	99.67 42	99.62 95	99.98 51

fmvsm_s_conf0.1_n_2		97.25 111	96.85 118	98.43 124	98.08 197	98.08 71	99.92 84	97.76 244	98.05 15	99.65 44	99.58 113	80.88 285	99.93 91	99.59 44	98.17 162	97.29 261

ab-mvs		94.69 204	93.42 228	98.51 118	98.07 198	96.26 149	96.49 378	98.68 72	90.31 280	94.54 223	97.00 271	76.30 328	99.71 145	95.98 184	93.38 256	99.56 147

XVG-OURS-SEG-HR		94.79 200	94.70 196	95.08 255	98.05 199	89.19 332	99.08 267	97.54 267	93.66 167	94.87 221	99.58 113	78.78 307	99.79 130	97.31 158	93.40 255	96.25 270

EIA-MVS		97.53 97	97.46 89	97.76 166	98.04 200	94.84 205	99.98 15	97.61 259	94.41 132	97.90 151	99.59 110	92.40 145	98.87 199	98.04 131	99.13 132	99.59 138

XVG-OURS		94.82 197	94.74 195	95.06 256	98.00 201	89.19 332	99.08 267	97.55 265	94.10 146	94.71 222	99.62 108	80.51 291	99.74 141	96.04 183	93.06 260	96.25 270

mvsmamba		96.94 128	96.73 124	97.55 177	97.99 202	94.37 218	99.62 197	97.70 247	93.13 183	98.42 131	97.92 244	88.02 213	98.75 209	98.78 90	99.01 137	99.52 158

dp		95.05 193	94.43 199	96.91 203	97.99 202	92.73 260	96.29 383	97.98 222	89.70 290	95.93 205	94.67 358	93.83 105	98.45 229	86.91 330	96.53 200	99.54 152

tpmrst		96.27 163	95.98 150	97.13 197	97.96 204	93.15 249	96.34 381	98.17 201	92.07 227	98.71 118	95.12 342	93.91 100	98.73 210	94.91 203	96.62 198	99.50 163

TR-MVS		94.54 209	93.56 224	97.49 182	97.96 204	94.34 219	98.71 313	97.51 272	90.30 281	94.51 225	98.69 199	75.56 334	98.77 206	92.82 249	95.99 211	99.35 183

Vis-MVSNet (Re-imp)		96.32 158	95.98 150	97.35 192	97.93 206	94.82 206	99.47 223	98.15 209	91.83 235	95.09 219	99.11 155	91.37 162	97.47 291	93.47 238	97.43 180	99.74 108

MDTV_nov1_ep13			95.69 165		97.90 207	94.15 224	95.98 389	98.44 130	93.12 184	97.98 148	95.74 309	95.10 55	98.58 220	90.02 291	96.92 195

Fast-Effi-MVS+		95.02 194	94.19 206	97.52 180	97.88 208	94.55 211	99.97 31	97.08 319	88.85 307	94.47 226	97.96 243	84.59 251	98.41 232	89.84 294	97.10 188	99.59 138

ADS-MVSNet2		93.80 230	93.88 216	93.55 316	97.87 209	85.94 364	94.24 395	96.84 344	90.07 283	96.43 193	94.48 363	90.29 186	95.37 374	87.44 317	97.23 185	99.36 180

ADS-MVSNet		94.79 200	94.02 211	97.11 199	97.87 209	93.79 232	94.24 395	98.16 206	90.07 283	96.43 193	94.48 363	90.29 186	98.19 258	87.44 317	97.23 185	99.36 180

Effi-MVS+		96.30 160	95.69 165	98.16 138	97.85 211	96.26 149	97.41 361	97.21 303	90.37 277	98.65 121	98.58 211	86.61 232	98.70 214	97.11 163	97.37 184	99.52 158

PatchmatchNet		95.94 169	95.45 171	97.39 188	97.83 212	94.41 215	96.05 387	98.40 159	92.86 191	97.09 174	95.28 338	94.21 92	98.07 266	89.26 298	98.11 167	99.70 114
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 207	93.61 219	97.74 168	97.82 213	96.26 149	99.96 38	97.78 243	85.76 351	94.00 233	97.54 253	76.95 320	99.21 178	97.23 160	95.43 227	97.76 253

1112_ss		96.01 168	95.20 180	98.42 126	97.80 214	96.41 142	99.65 190	96.66 355	92.71 200	92.88 247	99.40 132	92.16 150	99.30 173	91.92 259	93.66 251	99.55 148

Test_1112_low_res		95.72 174	94.83 192	98.42 126	97.79 215	96.41 142	99.65 190	96.65 356	92.70 201	92.86 248	96.13 300	92.15 151	99.30 173	91.88 260	93.64 252	99.55 148

Effi-MVS+-dtu		94.53 211	95.30 177	92.22 339	97.77 216	82.54 383	99.59 201	97.06 321	94.92 109	95.29 217	95.37 331	85.81 238	97.89 276	94.80 206	97.07 189	96.23 272

tpm cat1		93.51 239	92.52 253	96.47 215	97.77 216	91.47 294	96.13 385	98.06 215	80.98 387	92.91 246	93.78 372	89.66 191	98.87 199	87.03 326	96.39 204	99.09 208

FA-MVS(test-final)		95.86 170	95.09 184	98.15 141	97.74 218	95.62 178	96.31 382	98.17 201	91.42 251	96.26 198	96.13 300	90.56 180	99.47 169	92.18 255	97.07 189	99.35 183

xiu_mvs_v1_base_debu		97.43 100	97.06 106	98.55 111	97.74 218	98.14 68	99.31 245	97.86 236	96.43 70	99.62 51	99.69 92	85.56 240	99.68 149	99.05 68	98.31 157	97.83 249

xiu_mvs_v1_base		97.43 100	97.06 106	98.55 111	97.74 218	98.14 68	99.31 245	97.86 236	96.43 70	99.62 51	99.69 92	85.56 240	99.68 149	99.05 68	98.31 157	97.83 249

xiu_mvs_v1_base_debi		97.43 100	97.06 106	98.55 111	97.74 218	98.14 68	99.31 245	97.86 236	96.43 70	99.62 51	99.69 92	85.56 240	99.68 149	99.05 68	98.31 157	97.83 249

EPP-MVSNet		96.69 143	96.60 130	96.96 202	97.74 218	93.05 252	99.37 238	98.56 96	88.75 309	95.83 209	99.01 163	96.01 36	98.56 221	96.92 172	97.20 187	99.25 196

gg-mvs-nofinetune		93.51 239	91.86 265	98.47 120	97.72 223	97.96 81	92.62 403	98.51 113	74.70 405	97.33 168	69.59 419	98.91 4	97.79 279	97.77 149	99.56 103	99.67 119

IB-MVS	92.85 6	94.99 195	93.94 214	98.16 138	97.72 223	95.69 175	99.99 4	98.81 61	94.28 140	92.70 249	96.90 273	95.08 56	99.17 184	96.07 182	73.88 387	99.60 137
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		97.41 105	97.02 111	98.59 108	97.71 225	97.52 97	99.97 31	98.54 105	91.83 235	97.45 164	99.04 160	97.50 9	99.10 189	94.75 208	96.37 205	99.16 201

Syy-MVS		90.00 318	90.63 284	88.11 378	97.68 226	74.66 405	99.71 179	98.35 172	90.79 268	92.10 255	98.67 200	79.10 305	93.09 398	63.35 412	95.95 214	96.59 268

myMVS_eth3d		94.46 214	94.76 194	93.55 316	97.68 226	90.97 298	99.71 179	98.35 172	90.79 268	92.10 255	98.67 200	92.46 144	93.09 398	87.13 323	95.95 214	96.59 268

test_fmvs1_n		94.25 222	94.36 201	93.92 303	97.68 226	83.70 377	99.90 97	96.57 359	97.40 32	99.67 42	98.88 183	61.82 395	99.92 95	98.23 121	99.13 132	98.14 245

RRT-MVS		96.24 164	95.68 167	97.94 153	97.65 229	94.92 203	99.27 253	97.10 315	92.79 197	97.43 165	97.99 241	81.85 271	99.37 172	98.46 110	98.57 150	99.53 156

diffmvs		97.00 125	96.64 128	98.09 144	97.64 230	96.17 157	99.81 143	97.19 304	94.67 120	98.95 102	99.28 140	86.43 233	98.76 207	98.37 115	97.42 182	99.33 186
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		95.72 174	95.15 182	97.45 183	97.62 231	94.28 220	99.28 251	98.24 192	94.27 142	96.84 182	98.94 179	79.39 300	98.76 207	93.25 240	98.49 152	99.30 190
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 118	96.72 125	98.22 136	97.60 232	96.70 130	99.92 84	98.54 105	91.11 259	97.07 176	98.97 170	97.47 12	99.03 192	93.73 235	96.09 209	98.92 217

GDP-MVS		97.88 74	97.59 86	98.75 95	97.59 233	97.81 86	99.95 57	97.37 286	94.44 128	99.08 96	99.58 113	97.13 23	99.08 190	94.99 198	98.17 162	99.37 178

miper_ehance_all_eth		93.16 247	92.60 247	94.82 266	97.57 234	93.56 240	99.50 218	97.07 320	88.75 309	88.85 307	95.52 320	90.97 171	96.74 335	90.77 278	84.45 320	94.17 307

testing3		93.92 225	94.23 205	92.99 330	97.54 235	90.23 317	99.99 4	99.16 30	90.57 273	91.33 263	98.63 206	92.99 126	92.52 402	82.46 358	95.39 228	96.22 273

LCM-MVSNet-Re		92.31 267	92.60 247	91.43 348	97.53 236	79.27 400	99.02 281	91.83 415	92.07 227	80.31 380	94.38 366	83.50 260	95.48 372	97.22 161	97.58 178	99.54 152

GBi-Net		90.88 295	89.82 301	94.08 295	97.53 236	91.97 275	98.43 331	96.95 333	87.05 334	89.68 284	94.72 354	71.34 357	96.11 359	87.01 327	85.65 309	94.17 307

test1		90.88 295	89.82 301	94.08 295	97.53 236	91.97 275	98.43 331	96.95 333	87.05 334	89.68 284	94.72 354	71.34 357	96.11 359	87.01 327	85.65 309	94.17 307

FMVSNet2		91.02 292	89.56 306	95.41 246	97.53 236	95.74 170	98.98 283	97.41 282	87.05 334	88.43 316	95.00 348	71.34 357	96.24 356	85.12 341	85.21 314	94.25 301

tttt0517		96.85 132	96.49 134	97.92 154	97.48 240	95.89 165	99.85 126	98.54 105	90.72 272	96.63 187	98.93 181	97.47 12	99.02 193	93.03 247	95.76 220	98.85 221

BP-MVS1		98.33 53	98.18 51	98.81 90	97.44 241	97.98 78	99.96 38	98.17 201	94.88 111	98.77 112	99.59 110	97.59 7	99.08 190	98.24 120	98.93 139	99.36 180

casdiffmvs_mvg		96.43 152	95.94 156	97.89 158	97.44 241	95.47 182	99.86 123	97.29 297	93.35 174	96.03 202	99.19 151	85.39 243	98.72 212	97.89 141	97.04 191	99.49 165
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		97.38 107	97.24 100	97.80 159	97.41 243	95.64 177	99.99 4	97.06 321	94.59 121	99.63 48	99.32 139	89.20 202	98.14 260	98.76 92	99.23 128	99.62 131

c3_l		92.53 262	91.87 264	94.52 278	97.40 244	92.99 254	99.40 231	96.93 338	87.86 324	88.69 310	95.44 325	89.95 189	96.44 347	90.45 284	80.69 353	94.14 316

fmvsm_s_conf0.1_n		97.30 108	97.21 102	97.60 176	97.38 245	94.40 217	99.90 97	98.64 78	96.47 69	99.51 66	99.65 103	84.99 248	99.93 91	99.22 62	99.09 134	98.46 235

CDS-MVSNet		96.34 157	96.07 145	97.13 197	97.37 246	94.96 201	99.53 213	97.91 231	91.55 243	95.37 216	98.32 229	95.05 58	97.13 309	93.80 231	95.75 221	99.30 190
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 140	96.26 140	98.16 138	97.36 247	96.48 139	99.96 38	98.29 185	91.93 232	95.77 210	98.07 237	95.54 46	98.29 249	90.55 282	98.89 140	99.70 114

miper_lstm_enhance		91.81 275	91.39 274	93.06 329	97.34 248	89.18 334	99.38 236	96.79 349	86.70 341	87.47 330	95.22 340	90.00 188	95.86 368	88.26 308	81.37 342	94.15 313

baseline		96.43 152	95.98 150	97.76 166	97.34 248	95.17 198	99.51 216	97.17 307	93.92 158	96.90 180	99.28 140	85.37 244	98.64 218	97.50 155	96.86 197	99.46 167

cl____		92.31 267	91.58 268	94.52 278	97.33 250	92.77 256	99.57 206	96.78 350	86.97 338	87.56 328	95.51 321	89.43 195	96.62 340	88.60 303	82.44 334	94.16 312

DIV-MVS_self_test		92.32 266	91.60 267	94.47 282	97.31 251	92.74 258	99.58 203	96.75 351	86.99 337	87.64 326	95.54 318	89.55 194	96.50 344	88.58 304	82.44 334	94.17 307

casdiffmvs		96.42 154	95.97 153	97.77 164	97.30 252	94.98 200	99.84 131	97.09 318	93.75 165	96.58 189	99.26 146	85.07 246	98.78 205	97.77 149	97.04 191	99.54 152
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		94.36 219	93.48 226	96.99 201	97.29 253	93.54 241	99.96 38	96.72 353	88.35 318	93.43 237	98.94 179	82.05 268	98.05 267	88.12 312	96.48 203	99.37 178

eth_miper_zixun_eth		92.41 265	91.93 262	93.84 307	97.28 254	90.68 307	98.83 303	96.97 332	88.57 314	89.19 302	95.73 311	89.24 201	96.69 338	89.97 293	81.55 340	94.15 313

MVSFormer		96.94 128	96.60 130	97.95 150	97.28 254	97.70 91	99.55 210	97.27 299	91.17 256	99.43 72	99.54 119	90.92 172	96.89 327	94.67 211	99.62 95	99.25 196

lupinMVS		97.85 77	97.60 84	98.62 104	97.28 254	97.70 91	99.99 4	97.55 265	95.50 97	99.43 72	99.67 99	90.92 172	98.71 213	98.40 112	99.62 95	99.45 169

SCA		94.69 204	93.81 218	97.33 193	97.10 257	94.44 212	98.86 300	98.32 179	93.30 177	96.17 201	95.59 316	76.48 326	97.95 273	91.06 270	97.43 180	99.59 138

TAMVS		95.85 171	95.58 169	96.65 213	97.07 258	93.50 242	99.17 261	97.82 240	91.39 253	95.02 220	98.01 238	92.20 149	97.30 299	93.75 234	95.83 218	99.14 204

Fast-Effi-MVS+-dtu		93.72 234	93.86 217	93.29 321	97.06 259	86.16 362	99.80 147	96.83 345	92.66 204	92.58 250	97.83 249	81.39 277	97.67 284	89.75 295	96.87 196	96.05 275

CostFormer		96.10 165	95.88 160	96.78 207	97.03 260	92.55 266	97.08 369	97.83 239	90.04 285	98.72 117	94.89 352	95.01 60	98.29 249	96.54 177	95.77 219	99.50 163

test_fmvsmvis_n_1920		97.67 93	97.59 86	97.91 156	97.02 261	95.34 188	99.95 57	98.45 125	97.87 19	97.02 177	99.59 110	89.64 192	99.98 47	99.41 55	99.34 123	98.42 237

test-LLR		96.47 150	96.04 146	97.78 162	97.02 261	95.44 183	99.96 38	98.21 196	94.07 148	95.55 212	96.38 290	93.90 101	98.27 253	90.42 285	98.83 144	99.64 125

test-mter		96.39 155	95.93 157	97.78 162	97.02 261	95.44 183	99.96 38	98.21 196	91.81 237	95.55 212	96.38 290	95.17 53	98.27 253	90.42 285	98.83 144	99.64 125

gm-plane-assit					96.97 264	93.76 234			91.47 247		98.96 172		98.79 204	94.92 201

WB-MVSnew		92.90 253	92.77 244	93.26 323	96.95 265	93.63 238	99.71 179	98.16 206	91.49 244	94.28 229	98.14 234	81.33 279	96.48 345	79.47 373	95.46 225	89.68 399

QAPM		95.40 185	94.17 207	99.10 68	96.92 266	97.71 89	99.40 231	98.68 72	89.31 293	88.94 306	98.89 182	82.48 266	99.96 67	93.12 246	99.83 77	99.62 131

KD-MVS_2432*1600		88.00 339	86.10 343	93.70 312	96.91 267	94.04 226	97.17 366	97.12 313	84.93 361	81.96 371	92.41 383	92.48 142	94.51 386	79.23 374	52.68 418	92.56 369

miper_refine_blended		88.00 339	86.10 343	93.70 312	96.91 267	94.04 226	97.17 366	97.12 313	84.93 361	81.96 371	92.41 383	92.48 142	94.51 386	79.23 374	52.68 418	92.56 369

tpm2		95.47 183	95.18 181	96.35 222	96.91 267	91.70 288	96.96 372	97.93 227	88.04 322	98.44 130	95.40 327	93.32 115	97.97 270	94.00 223	95.61 223	99.38 176

FMVSNet5		88.32 335	87.47 337	90.88 351	96.90 270	88.39 346	97.28 363	95.68 379	82.60 381	84.67 359	92.40 385	79.83 297	91.16 407	76.39 389	81.51 341	93.09 361

3Dnovator+	91.53 11	96.31 159	95.24 178	99.52 28	96.88 271	98.64 54	99.72 176	98.24 192	95.27 102	88.42 318	98.98 168	82.76 265	99.94 83	97.10 164	99.83 77	99.96 67

Patchmatch-test		92.65 261	91.50 271	96.10 228	96.85 272	90.49 312	91.50 408	97.19 304	82.76 380	90.23 272	95.59 316	95.02 59	98.00 269	77.41 384	96.98 194	99.82 96

MVS		96.60 146	95.56 170	99.72 13	96.85 272	99.22 20	98.31 337	98.94 41	91.57 242	90.90 267	99.61 109	86.66 231	99.96 67	97.36 157	99.88 73	99.99 23

3Dnovator	91.47 12	96.28 162	95.34 175	99.08 71	96.82 274	97.47 102	99.45 228	98.81 61	95.52 96	89.39 293	99.00 165	81.97 269	99.95 75	97.27 159	99.83 77	99.84 94

EI-MVSNet		93.73 233	93.40 231	94.74 267	96.80 275	92.69 261	99.06 272	97.67 250	88.96 302	91.39 261	99.02 161	88.75 207	97.30 299	91.07 269	87.85 295	94.22 303

CVMVSNet		94.68 206	94.94 190	93.89 306	96.80 275	86.92 359	99.06 272	98.98 38	94.45 125	94.23 231	99.02 161	85.60 239	95.31 376	90.91 275	95.39 228	99.43 172

IterMVS-LS		92.69 259	92.11 258	94.43 286	96.80 275	92.74 258	99.45 228	96.89 341	88.98 300	89.65 287	95.38 330	88.77 206	96.34 351	90.98 273	82.04 337	94.22 303
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS		90.91 294	90.17 296	93.12 326	96.78 278	90.42 315	98.89 294	97.05 324	89.03 297	86.49 343	95.42 326	76.59 324	95.02 378	87.22 322	84.09 323	93.93 333
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 133	95.96 154	99.48 34	96.74 279	98.52 58	98.31 337	98.86 53	95.82 86	89.91 278	98.98 168	87.49 219	99.96 67	97.80 144	99.73 87	99.96 67

IterMVS-SCA-FT		90.85 297	90.16 297	92.93 331	96.72 280	89.96 323	98.89 294	96.99 328	88.95 303	86.63 340	95.67 312	76.48 326	95.00 379	87.04 325	84.04 326	93.84 340

MVS-HIRNet		86.22 346	83.19 359	95.31 250	96.71 281	90.29 316	92.12 405	97.33 291	62.85 413	86.82 337	70.37 418	69.37 365	97.49 290	75.12 392	97.99 172	98.15 243

VDDNet		93.12 248	91.91 263	96.76 208	96.67 282	92.65 264	98.69 316	98.21 196	82.81 379	97.75 158	99.28 140	61.57 396	99.48 168	98.09 129	94.09 246	98.15 243

dmvs_re		93.20 245	93.15 236	93.34 319	96.54 283	83.81 376	98.71 313	98.51 113	91.39 253	92.37 253	98.56 213	78.66 309	97.83 278	93.89 225	89.74 267	98.38 239

MIMVSNet		90.30 310	88.67 324	95.17 254	96.45 284	91.64 290	92.39 404	97.15 310	85.99 348	90.50 270	93.19 379	66.95 376	94.86 383	82.01 362	93.43 254	99.01 215

CR-MVSNet		93.45 242	92.62 246	95.94 232	96.29 285	92.66 262	92.01 406	96.23 367	92.62 206	96.94 178	93.31 377	91.04 169	96.03 364	79.23 374	95.96 212	99.13 205

RPMNet		89.76 322	87.28 338	97.19 196	96.29 285	92.66 262	92.01 406	98.31 181	70.19 412	96.94 178	85.87 411	87.25 223	99.78 132	62.69 413	95.96 212	99.13 205

tt0805		91.28 287	90.18 295	94.60 273	96.26 287	87.55 352	98.39 335	98.72 67	89.00 299	89.22 299	98.47 221	62.98 391	98.96 196	90.57 281	88.00 294	97.28 262

Patchmtry		89.70 323	88.49 326	93.33 320	96.24 288	89.94 326	91.37 409	96.23 367	78.22 395	87.69 325	93.31 377	91.04 169	96.03 364	80.18 372	82.10 336	94.02 323

test_vis1_rt		86.87 344	86.05 346	89.34 367	96.12 289	78.07 401	99.87 112	83.54 426	92.03 230	78.21 390	89.51 397	45.80 412	99.91 96	96.25 180	93.11 259	90.03 396

JIA-IIPM		91.76 281	90.70 282	94.94 260	96.11 290	87.51 353	93.16 402	98.13 211	75.79 401	97.58 160	77.68 416	92.84 131	97.97 270	88.47 307	96.54 199	99.33 186

OpenMVS	90.15 15	94.77 202	93.59 222	98.33 130	96.07 291	97.48 101	99.56 208	98.57 93	90.46 275	86.51 342	98.95 177	78.57 310	99.94 83	93.86 226	99.74 86	97.57 258

PAPM		98.60 33	98.42 34	99.14 62	96.05 292	98.96 26	99.90 97	99.35 24	96.68 62	98.35 136	99.66 101	96.45 33	98.51 224	99.45 52	99.89 70	99.96 67

CLD-MVS		94.06 224	93.90 215	94.55 277	96.02 293	90.69 306	99.98 15	97.72 246	96.62 66	91.05 266	98.85 191	77.21 315	98.47 225	98.11 127	89.51 273	94.48 282
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 307	88.75 323	95.25 252	95.99 294	90.16 319	91.22 410	97.54 267	76.80 397	97.26 170	86.01 410	91.88 156	96.07 363	66.16 409	95.91 216	99.51 161

ACMH+	89.98 16	90.35 308	89.54 307	92.78 335	95.99 294	86.12 363	98.81 305	97.18 306	89.38 292	83.14 367	97.76 250	68.42 370	98.43 230	89.11 299	86.05 307	93.78 343

DeepMVS_CX				82.92 388	95.98 296	58.66 419		96.01 372	92.72 199	78.34 389	95.51 321	58.29 401	98.08 264	82.57 357	85.29 312	92.03 377

ACMP	92.05 9	92.74 257	92.42 255	93.73 308	95.91 297	88.72 339	99.81 143	97.53 269	94.13 144	87.00 336	98.23 232	74.07 347	98.47 225	96.22 181	88.86 280	93.99 328
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 237	93.03 238	95.35 247	95.86 298	86.94 358	99.87 112	96.36 365	96.85 53	99.54 61	98.79 193	52.41 408	99.83 125	98.64 100	98.97 138	99.29 192

HQP-NCC					95.78 299		99.87 112		96.82 55	93.37 238

ACMP_Plane					95.78 299		99.87 112		96.82 55	93.37 238

HQP-MVS		94.61 208	94.50 198	94.92 261	95.78 299	91.85 280	99.87 112	97.89 232	96.82 55	93.37 238	98.65 203	80.65 289	98.39 236	97.92 138	89.60 268	94.53 278

NP-MVS					95.77 302	91.79 282					98.65 203

test_fmvsmconf0.1_n		97.74 89	97.44 91	98.64 103	95.76 303	96.20 154	99.94 74	98.05 217	98.17 10	98.89 106	99.42 127	87.65 217	99.90 98	99.50 48	99.60 101	99.82 96

plane_prior6					95.76 303	91.72 287						80.47 293

ACMM	91.95 10	92.88 254	92.52 253	93.98 302	95.75 305	89.08 336	99.77 153	97.52 271	93.00 186	89.95 277	97.99 241	76.17 330	98.46 228	93.63 237	88.87 279	94.39 290
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 227	92.84 240	96.80 206	95.73 306	93.57 239	99.88 109	97.24 302	92.57 211	92.92 245	96.66 282	78.73 308	97.67 284	87.75 315	94.06 247	99.17 200

plane_prior1					95.73 306

jason		97.24 112	96.86 117	98.38 129	95.73 306	97.32 106	99.97 31	97.40 283	95.34 100	98.60 124	99.54 119	87.70 216	98.56 221	97.94 137	99.47 112	99.25 196
jason: jason.
mmtdpeth		88.52 333	87.75 335	90.85 353	95.71 309	83.47 379	98.94 288	94.85 393	88.78 308	97.19 172	89.58 396	63.29 389	98.97 194	98.54 105	62.86 412	90.10 395

HQP_MVS		94.49 213	94.36 201	94.87 262	95.71 309	91.74 284	99.84 131	97.87 234	96.38 73	93.01 243	98.59 208	80.47 293	98.37 242	97.79 147	89.55 271	94.52 280

plane_prior7					95.71 309	91.59 292

ITE_SJBPF				92.38 337	95.69 312	85.14 368		95.71 378	92.81 194	89.33 296	98.11 235	70.23 363	98.42 231	85.91 337	88.16 292	93.59 351

fmvsm_s_conf0.1_n_a		97.09 120	96.90 114	97.63 174	95.65 313	94.21 223	99.83 138	98.50 119	96.27 78	99.65 44	99.64 104	84.72 249	99.93 91	99.04 71	98.84 143	98.74 228

ACMH	89.72 17	90.64 301	89.63 304	93.66 314	95.64 314	88.64 342	98.55 323	97.45 276	89.03 297	81.62 374	97.61 251	69.75 364	98.41 232	89.37 296	87.62 299	93.92 334
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 142	96.49 134	97.37 189	95.63 315	95.96 163	99.74 165	98.88 51	92.94 188	91.61 259	98.97 170	97.72 6	98.62 219	94.83 205	98.08 170	97.53 259

FMVSNet1		88.50 334	86.64 341	94.08 295	95.62 316	91.97 275	98.43 331	96.95 333	83.00 377	86.08 350	94.72 354	59.09 400	96.11 359	81.82 364	84.07 324	94.17 307

LPG-MVS_test		92.96 251	92.71 245	93.71 310	95.43 317	88.67 340	99.75 162	97.62 256	92.81 194	90.05 273	98.49 217	75.24 337	98.40 234	95.84 187	89.12 275	94.07 320

LGP-MVS_train				93.71 310	95.43 317	88.67 340		97.62 256	92.81 194	90.05 273	98.49 217	75.24 337	98.40 234	95.84 187	89.12 275	94.07 320

tpm		93.70 235	93.41 230	94.58 275	95.36 319	87.41 354	97.01 370	96.90 340	90.85 266	96.72 186	94.14 369	90.40 183	96.84 330	90.75 279	88.54 287	99.51 161

D2MVS		92.76 256	92.59 251	93.27 322	95.13 320	89.54 330	99.69 184	99.38 22	92.26 223	87.59 327	94.61 360	85.05 247	97.79 279	91.59 263	88.01 293	92.47 372

VPA-MVSNet		92.70 258	91.55 270	96.16 226	95.09 321	96.20 154	98.88 296	99.00 36	91.02 263	91.82 258	95.29 337	76.05 332	97.96 272	95.62 191	81.19 343	94.30 297

LTVRE_ROB	88.28 18	90.29 311	89.05 318	94.02 298	95.08 322	90.15 320	97.19 365	97.43 278	84.91 363	83.99 363	97.06 268	74.00 348	98.28 251	84.08 346	87.71 297	93.62 350
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		87.87 341	86.51 342	91.94 342	95.05 323	85.57 366	97.65 358	94.08 402	84.40 367	81.82 373	96.85 277	62.14 394	98.33 245	80.25 371	86.37 306	91.91 379

test0.0.03 1		93.86 226	93.61 219	94.64 271	95.02 324	92.18 273	99.93 81	98.58 91	94.07 148	87.96 322	98.50 216	93.90 101	94.96 380	81.33 365	93.17 257	96.78 265

UniMVSNet (Re)		93.07 250	92.13 257	95.88 233	94.84 325	96.24 153	99.88 109	98.98 38	92.49 216	89.25 297	95.40 327	87.09 225	97.14 308	93.13 245	78.16 367	94.26 299

USDC		90.00 318	88.96 319	93.10 328	94.81 326	88.16 348	98.71 313	95.54 383	93.66 167	83.75 365	97.20 262	65.58 381	98.31 247	83.96 349	87.49 301	92.85 366

VPNet		91.81 275	90.46 286	95.85 235	94.74 327	95.54 181	98.98 283	98.59 89	92.14 225	90.77 269	97.44 255	68.73 368	97.54 289	94.89 204	77.89 369	94.46 283

FIs		94.10 223	93.43 227	96.11 227	94.70 328	96.82 127	99.58 203	98.93 45	92.54 212	89.34 295	97.31 259	87.62 218	97.10 312	94.22 222	86.58 304	94.40 289

UniMVSNet_ETH3D		90.06 317	88.58 325	94.49 281	94.67 329	88.09 349	97.81 357	97.57 264	83.91 370	88.44 314	97.41 256	57.44 402	97.62 286	91.41 264	88.59 286	97.77 252

UniMVSNet_NR-MVSNet		92.95 252	92.11 258	95.49 241	94.61 330	95.28 191	99.83 138	99.08 33	91.49 244	89.21 300	96.86 276	87.14 224	96.73 336	93.20 241	77.52 372	94.46 283

test_fmvs2		89.47 326	89.70 303	88.77 374	94.54 331	75.74 402	99.83 138	94.70 398	94.71 117	91.08 264	96.82 281	54.46 405	97.78 281	92.87 248	88.27 290	92.80 367

MonoMVSNet		94.82 197	94.43 199	95.98 230	94.54 331	90.73 305	99.03 279	97.06 321	93.16 182	93.15 242	95.47 324	88.29 210	97.57 287	97.85 142	91.33 265	99.62 131

WR-MVS		92.31 267	91.25 275	95.48 244	94.45 333	95.29 190	99.60 200	98.68 72	90.10 282	88.07 321	96.89 274	80.68 288	96.80 334	93.14 244	79.67 360	94.36 291

nrg030		93.51 239	92.53 252	96.45 217	94.36 334	97.20 111	99.81 143	97.16 309	91.60 241	89.86 280	97.46 254	86.37 234	97.68 283	95.88 186	80.31 356	94.46 283

tfpnnormal		89.29 329	87.61 336	94.34 289	94.35 335	94.13 225	98.95 287	98.94 41	83.94 368	84.47 360	95.51 321	74.84 342	97.39 292	77.05 387	80.41 354	91.48 382

FC-MVSNet-test		93.81 229	93.15 236	95.80 237	94.30 336	96.20 154	99.42 230	98.89 49	92.33 222	89.03 305	97.27 261	87.39 221	96.83 332	93.20 241	86.48 305	94.36 291

MS-PatchMatch		90.65 300	90.30 291	91.71 347	94.22 337	85.50 367	98.24 341	97.70 247	88.67 311	86.42 345	96.37 292	67.82 373	98.03 268	83.62 351	99.62 95	91.60 380

WR-MVS_H		91.30 285	90.35 289	94.15 292	94.17 338	92.62 265	99.17 261	98.94 41	88.87 306	86.48 344	94.46 365	84.36 253	96.61 341	88.19 309	78.51 365	93.21 360

DU-MVS		92.46 264	91.45 273	95.49 241	94.05 339	95.28 191	99.81 143	98.74 66	92.25 224	89.21 300	96.64 284	81.66 274	96.73 336	93.20 241	77.52 372	94.46 283

NR-MVSNet		91.56 283	90.22 293	95.60 239	94.05 339	95.76 169	98.25 340	98.70 69	91.16 258	80.78 379	96.64 284	83.23 263	96.57 342	91.41 264	77.73 371	94.46 283

CP-MVSNet		91.23 289	90.22 293	94.26 290	93.96 341	92.39 269	99.09 265	98.57 93	88.95 303	86.42 345	96.57 287	79.19 303	96.37 349	90.29 288	78.95 362	94.02 323

XXY-MVS		91.82 274	90.46 286	95.88 233	93.91 342	95.40 187	98.87 299	97.69 249	88.63 313	87.87 323	97.08 266	74.38 346	97.89 276	91.66 262	84.07 324	94.35 294

PS-CasMVS		90.63 302	89.51 309	93.99 301	93.83 343	91.70 288	98.98 283	98.52 110	88.48 315	86.15 349	96.53 289	75.46 335	96.31 353	88.83 301	78.86 364	93.95 331

test_0402		85.58 348	83.94 353	90.50 357	93.81 344	85.04 369	98.55 323	95.20 390	76.01 399	79.72 384	95.13 341	64.15 387	96.26 355	66.04 410	86.88 303	90.21 393

XVG-ACMP-BASELINE		91.22 290	90.75 281	92.63 336	93.73 345	85.61 365	98.52 327	97.44 277	92.77 198	89.90 279	96.85 277	66.64 378	98.39 236	92.29 253	88.61 284	93.89 336

TranMVSNet+NR-MVSNet		91.68 282	90.61 285	94.87 262	93.69 346	93.98 229	99.69 184	98.65 76	91.03 262	88.44 314	96.83 280	80.05 296	96.18 357	90.26 289	76.89 380	94.45 288

TransMVSNet (Re)		87.25 342	85.28 349	93.16 325	93.56 347	91.03 297	98.54 325	94.05 404	83.69 372	81.09 377	96.16 298	75.32 336	96.40 348	76.69 388	68.41 400	92.06 376

v10		90.25 312	88.82 321	94.57 276	93.53 348	93.43 244	99.08 267	96.87 343	85.00 360	87.34 334	94.51 361	80.93 284	97.02 322	82.85 356	79.23 361	93.26 358

testgi		89.01 331	88.04 332	91.90 343	93.49 349	84.89 371	99.73 172	95.66 380	93.89 162	85.14 355	98.17 233	59.68 399	94.66 385	77.73 383	88.88 278	96.16 274

v8		90.54 304	89.17 314	94.66 270	93.43 350	93.40 246	99.20 258	96.94 337	85.76 351	87.56 328	94.51 361	81.96 270	97.19 305	84.94 343	78.25 366	93.38 356

V42		91.28 287	90.12 298	94.74 267	93.42 351	93.46 243	99.68 186	97.02 325	87.36 330	89.85 282	95.05 344	81.31 280	97.34 295	87.34 320	80.07 358	93.40 354

pm-mvs1		89.36 328	87.81 334	94.01 299	93.40 352	91.93 278	98.62 321	96.48 363	86.25 346	83.86 364	96.14 299	73.68 349	97.04 318	86.16 334	75.73 385	93.04 363

v1144		91.09 291	89.83 300	94.87 262	93.25 353	93.69 237	99.62 197	96.98 330	86.83 340	89.64 288	94.99 349	80.94 283	97.05 315	85.08 342	81.16 344	93.87 338

v1192		90.62 303	89.25 313	94.72 269	93.13 354	93.07 250	99.50 218	97.02 325	86.33 345	89.56 291	95.01 346	79.22 302	97.09 314	82.34 360	81.16 344	94.01 325

v2v482		91.30 285	90.07 299	95.01 257	93.13 354	93.79 232	99.77 153	97.02 325	88.05 321	89.25 297	95.37 331	80.73 287	97.15 307	87.28 321	80.04 359	94.09 319

OPM-MVS		93.21 244	92.80 242	94.44 284	93.12 356	90.85 304	99.77 153	97.61 259	96.19 81	91.56 260	98.65 203	75.16 341	98.47 225	93.78 233	89.39 274	93.99 328
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 298	89.52 308	94.59 274	93.11 357	92.77 256	99.56 208	96.99 328	86.38 344	89.82 283	94.95 351	80.50 292	97.10 312	83.98 348	80.41 354	93.90 335

PEN-MVS		90.19 314	89.06 317	93.57 315	93.06 358	90.90 302	99.06 272	98.47 122	88.11 320	85.91 351	96.30 294	76.67 322	95.94 367	87.07 324	76.91 379	93.89 336

v1240		90.20 313	88.79 322	94.44 284	93.05 359	92.27 271	99.38 236	96.92 339	85.89 349	89.36 294	94.87 353	77.89 314	97.03 320	80.66 368	81.08 347	94.01 325

v148		90.70 299	89.63 304	93.92 303	92.97 360	90.97 298	99.75 162	96.89 341	87.51 327	88.27 319	95.01 346	81.67 273	97.04 318	87.40 319	77.17 377	93.75 344

v1921920		90.46 305	89.12 315	94.50 280	92.96 361	92.46 267	99.49 220	96.98 330	86.10 347	89.61 290	95.30 334	78.55 311	97.03 320	82.17 361	80.89 352	94.01 325

MVStest1		85.03 354	82.76 363	91.83 344	92.95 362	89.16 335	98.57 322	94.82 394	71.68 410	68.54 410	95.11 343	83.17 264	95.66 370	74.69 393	65.32 407	90.65 389

Baseline_NR-MVSNet		90.33 309	89.51 309	92.81 334	92.84 363	89.95 324	99.77 153	93.94 405	84.69 365	89.04 304	95.66 313	81.66 274	96.52 343	90.99 272	76.98 378	91.97 378

test_method		80.79 370	79.70 374	84.08 385	92.83 364	67.06 411	99.51 216	95.42 384	54.34 417	81.07 378	93.53 374	44.48 413	92.22 404	78.90 378	77.23 376	92.94 364

pmmvs4		92.10 271	91.07 279	95.18 253	92.82 365	94.96 201	99.48 222	96.83 345	87.45 329	88.66 311	96.56 288	83.78 258	96.83 332	89.29 297	84.77 318	93.75 344

LF4IMVS		89.25 330	88.85 320	90.45 359	92.81 366	81.19 393	98.12 347	94.79 395	91.44 248	86.29 347	97.11 264	65.30 384	98.11 262	88.53 306	85.25 313	92.07 375

DTE-MVSNet		89.40 327	88.24 330	92.88 332	92.66 367	89.95 324	99.10 264	98.22 195	87.29 331	85.12 356	96.22 296	76.27 329	95.30 377	83.56 352	75.74 384	93.41 353

EU-MVSNet		90.14 316	90.34 290	89.54 366	92.55 368	81.06 394	98.69 316	98.04 218	91.41 252	86.59 341	96.84 279	80.83 286	93.31 397	86.20 333	81.91 338	94.26 299

APD_test1		81.15 369	80.92 370	81.86 389	92.45 369	59.76 418	96.04 388	93.61 408	73.29 408	77.06 393	96.64 284	44.28 414	96.16 358	72.35 397	82.52 332	89.67 400

our_test_3		90.39 306	89.48 311	93.12 326	92.40 370	89.57 329	99.33 242	96.35 366	87.84 325	85.30 354	94.99 349	84.14 256	96.09 362	80.38 369	84.56 319	93.71 349

ppachtmachnet_test		89.58 325	88.35 328	93.25 324	92.40 370	90.44 314	99.33 242	96.73 352	85.49 356	85.90 352	95.77 308	81.09 282	96.00 366	76.00 391	82.49 333	93.30 357

v7n		89.65 324	88.29 329	93.72 309	92.22 372	90.56 311	99.07 271	97.10 315	85.42 358	86.73 338	94.72 354	80.06 295	97.13 309	81.14 366	78.12 368	93.49 352

dmvs_testset		83.79 363	86.07 345	76.94 393	92.14 373	48.60 428	96.75 375	90.27 418	89.48 291	78.65 387	98.55 215	79.25 301	86.65 416	66.85 407	82.69 331	95.57 276

PS-MVSNAJss		93.64 236	93.31 233	94.61 272	92.11 374	92.19 272	99.12 263	97.38 284	92.51 215	88.45 313	96.99 272	91.20 164	97.29 302	94.36 216	87.71 297	94.36 291

pmmvs5		90.17 315	89.09 316	93.40 318	92.10 375	89.77 327	99.74 165	95.58 382	85.88 350	87.24 335	95.74 309	73.41 350	96.48 345	88.54 305	83.56 328	93.95 331

N_pmnet		80.06 373	80.78 371	77.89 392	91.94 376	45.28 430	98.80 307	56.82 432	78.10 396	80.08 382	93.33 375	77.03 317	95.76 369	68.14 405	82.81 330	92.64 368

test_djsdf		92.83 255	92.29 256	94.47 282	91.90 377	92.46 267	99.55 210	97.27 299	91.17 256	89.96 276	96.07 303	81.10 281	96.89 327	94.67 211	88.91 277	94.05 322

SixPastTwentyTwo		88.73 332	88.01 333	90.88 351	91.85 378	82.24 385	98.22 344	95.18 391	88.97 301	82.26 370	96.89 274	71.75 355	96.67 339	84.00 347	82.98 329	93.72 348

K. test v3		88.05 338	87.24 339	90.47 358	91.82 379	82.23 386	98.96 286	97.42 280	89.05 296	76.93 395	95.60 315	68.49 369	95.42 373	85.87 338	81.01 350	93.75 344

OurMVSNet-221017-0		89.81 321	89.48 311	90.83 354	91.64 380	81.21 392	98.17 346	95.38 386	91.48 246	85.65 353	97.31 259	72.66 351	97.29 302	88.15 310	84.83 317	93.97 330

mvs_tets		91.81 275	91.08 278	94.00 300	91.63 381	90.58 310	98.67 318	97.43 278	92.43 217	87.37 333	97.05 269	71.76 354	97.32 297	94.75 208	88.68 283	94.11 318

Gipuma		66.95 386	65.00 386	72.79 398	91.52 382	67.96 410	66.16 421	95.15 392	47.89 419	58.54 416	67.99 421	29.74 418	87.54 415	50.20 420	77.83 370	62.87 421
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 155	95.74 163	98.32 131	91.47 383	95.56 180	99.84 131	97.30 294	97.74 22	97.89 152	99.35 138	79.62 298	99.85 115	99.25 61	99.24 127	99.55 148

jajsoiax		91.92 273	91.18 276	94.15 292	91.35 384	90.95 301	99.00 282	97.42 280	92.61 207	87.38 332	97.08 266	72.46 352	97.36 293	94.53 214	88.77 281	94.13 317

MDA-MVSNet-bldmvs		84.09 361	81.52 368	91.81 345	91.32 385	88.00 351	98.67 318	95.92 374	80.22 390	55.60 419	93.32 376	68.29 371	93.60 395	73.76 394	76.61 381	93.82 342

MVP-Stereo		90.93 293	90.45 288	92.37 338	91.25 386	88.76 337	98.05 351	96.17 369	87.27 332	84.04 361	95.30 334	78.46 312	97.27 304	83.78 350	99.70 89	91.09 383
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 350	83.32 358	92.10 340	90.96 387	88.58 343	99.20 258	96.52 361	79.70 392	57.12 418	92.69 381	79.11 304	93.86 392	77.10 386	77.46 374	93.86 339

YYNet1		85.50 351	83.33 357	92.00 341	90.89 388	88.38 347	99.22 257	96.55 360	79.60 393	57.26 417	92.72 380	79.09 306	93.78 393	77.25 385	77.37 375	93.84 340

anonymousdsp		91.79 280	90.92 280	94.41 287	90.76 389	92.93 255	98.93 290	97.17 307	89.08 295	87.46 331	95.30 334	78.43 313	96.92 325	92.38 252	88.73 282	93.39 355

lessismore_v0				90.53 356	90.58 390	80.90 395		95.80 375		77.01 394	95.84 306	66.15 380	96.95 323	83.03 355	75.05 386	93.74 347

EG-PatchMatch MVS		85.35 352	83.81 355	89.99 364	90.39 391	81.89 388	98.21 345	96.09 371	81.78 384	74.73 401	93.72 373	51.56 410	97.12 311	79.16 377	88.61 284	90.96 386

EGC-MVSNET		69.38 379	63.76 389	86.26 382	90.32 392	81.66 391	96.24 384	93.85 406	0.99 429	3.22 430	92.33 386	52.44 407	92.92 400	59.53 416	84.90 316	84.21 410

CMPMVS	61.59 21	84.75 357	85.14 350	83.57 386	90.32 392	62.54 414	96.98 371	97.59 263	74.33 406	69.95 407	96.66 282	64.17 386	98.32 246	87.88 314	88.41 289	89.84 398
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 360	82.92 361	89.21 368	90.03 394	82.60 382	96.89 374	95.62 381	80.59 388	75.77 400	89.17 398	65.04 385	94.79 384	72.12 398	81.02 349	90.23 392

pmmvs6		85.69 347	83.84 354	91.26 350	90.00 395	84.41 374	97.82 356	96.15 370	75.86 400	81.29 376	95.39 329	61.21 397	96.87 329	83.52 353	73.29 388	92.50 371

ttmdpeth		88.23 337	87.06 340	91.75 346	89.91 396	87.35 355	98.92 293	95.73 377	87.92 323	84.02 362	96.31 293	68.23 372	96.84 330	86.33 332	76.12 382	91.06 384

DSMNet-mixed		88.28 336	88.24 330	88.42 376	89.64 397	75.38 404	98.06 350	89.86 419	85.59 355	88.20 320	92.14 387	76.15 331	91.95 405	78.46 380	96.05 210	97.92 248

UnsupCasMVSNet_eth		85.52 349	83.99 351	90.10 362	89.36 398	83.51 378	96.65 376	97.99 220	89.14 294	75.89 399	93.83 371	63.25 390	93.92 390	81.92 363	67.90 403	92.88 365

Anonymous20231206		86.32 345	85.42 348	89.02 370	89.11 399	80.53 398	99.05 276	95.28 387	85.43 357	82.82 368	93.92 370	74.40 345	93.44 396	66.99 406	81.83 339	93.08 362

Anonymous20240521		85.15 353	83.81 355	89.16 369	88.32 400	82.69 381	98.80 307	95.74 376	79.72 391	81.53 375	90.99 390	65.38 383	94.16 388	72.69 396	81.11 346	90.63 390

OpenMVS_ROB	79.82 20	83.77 364	81.68 367	90.03 363	88.30 401	82.82 380	98.46 328	95.22 389	73.92 407	76.00 398	91.29 389	55.00 404	96.94 324	68.40 404	88.51 288	90.34 391

test20.03		84.72 358	83.99 351	86.91 380	88.19 402	80.62 397	98.88 296	95.94 373	88.36 317	78.87 385	94.62 359	68.75 367	89.11 411	66.52 408	75.82 383	91.00 385

KD-MVS_self_test		83.59 365	82.06 365	88.20 377	86.93 403	80.70 396	97.21 364	96.38 364	82.87 378	82.49 369	88.97 399	67.63 374	92.32 403	73.75 395	62.30 414	91.58 381

MIMVSNet1		82.58 366	80.51 372	88.78 372	86.68 404	84.20 375	96.65 376	95.41 385	78.75 394	78.59 388	92.44 382	51.88 409	89.76 410	65.26 411	78.95 362	92.38 374

CL-MVSNet_self_test		84.50 359	83.15 360	88.53 375	86.00 405	81.79 389	98.82 304	97.35 287	85.12 359	83.62 366	90.91 392	76.66 323	91.40 406	69.53 402	60.36 415	92.40 373

UnsupCasMVSNet_bld		79.97 375	77.03 380	88.78 372	85.62 406	81.98 387	93.66 400	97.35 287	75.51 403	70.79 406	83.05 413	48.70 411	94.91 382	78.31 381	60.29 416	89.46 403

mvs5depth		84.87 355	82.90 362	90.77 355	85.59 407	84.84 372	91.10 411	93.29 410	83.14 375	85.07 357	94.33 367	62.17 393	97.32 297	78.83 379	72.59 391	90.14 394

Patchmatch-RL test		86.90 343	85.98 347	89.67 365	84.45 408	75.59 403	89.71 414	92.43 412	86.89 339	77.83 392	90.94 391	94.22 90	93.63 394	87.75 315	69.61 395	99.79 101

pmmvs-eth3d		84.03 362	81.97 366	90.20 361	84.15 409	87.09 357	98.10 349	94.73 397	83.05 376	74.10 403	87.77 405	65.56 382	94.01 389	81.08 367	69.24 397	89.49 402

test_fmvs3		79.99 374	80.17 373	79.45 391	84.02 410	62.83 412	99.05 276	93.49 409	88.29 319	80.06 383	86.65 408	28.09 420	88.00 412	88.63 302	73.27 389	87.54 408

PM-MVS		80.47 371	78.88 376	85.26 383	83.79 411	72.22 406	95.89 391	91.08 416	85.71 354	76.56 397	88.30 401	36.64 416	93.90 391	82.39 359	69.57 396	89.66 401

new-patchmatchnet		81.19 368	79.34 375	86.76 381	82.86 412	80.36 399	97.92 353	95.27 388	82.09 383	72.02 404	86.87 407	62.81 392	90.74 409	71.10 399	63.08 411	89.19 405

mvsany_test3		82.12 367	81.14 369	85.06 384	81.87 413	70.41 408	97.09 368	92.14 413	91.27 255	77.84 391	88.73 400	39.31 415	95.49 371	90.75 279	71.24 392	89.29 404

WB-MVS		76.28 377	77.28 379	73.29 397	81.18 414	54.68 422	97.87 355	94.19 401	81.30 385	69.43 408	90.70 393	77.02 318	82.06 420	35.71 425	68.11 402	83.13 411

test_f		78.40 376	77.59 378	80.81 390	80.82 415	62.48 415	96.96 372	93.08 411	83.44 373	74.57 402	84.57 412	27.95 421	92.63 401	84.15 345	72.79 390	87.32 409

SSC-MVS		75.42 378	76.40 381	72.49 401	80.68 416	53.62 423	97.42 360	94.06 403	80.42 389	68.75 409	90.14 395	76.54 325	81.66 421	33.25 426	66.34 406	82.19 412

pmmvs3		80.27 372	77.77 377	87.76 379	80.32 417	82.43 384	98.23 343	91.97 414	72.74 409	78.75 386	87.97 404	57.30 403	90.99 408	70.31 400	62.37 413	89.87 397

testf1		68.38 382	66.92 383	72.78 399	78.80 418	50.36 425	90.95 412	87.35 424	55.47 415	58.95 414	88.14 402	20.64 425	87.60 413	57.28 417	64.69 408	80.39 414

APD_test2		68.38 382	66.92 383	72.78 399	78.80 418	50.36 425	90.95 412	87.35 424	55.47 415	58.95 414	88.14 402	20.64 425	87.60 413	57.28 417	64.69 408	80.39 414

ambc				83.23 387	77.17 420	62.61 413	87.38 416	94.55 400		76.72 396	86.65 408	30.16 417	96.36 350	84.85 344	69.86 394	90.73 388

test_vis3_rt		68.82 380	66.69 385	75.21 396	76.24 421	60.41 417	96.44 379	68.71 431	75.13 404	50.54 422	69.52 420	16.42 430	96.32 352	80.27 370	66.92 405	68.89 418

TDRefinement		84.76 356	82.56 364	91.38 349	74.58 422	84.80 373	97.36 362	94.56 399	84.73 364	80.21 381	96.12 302	63.56 388	98.39 236	87.92 313	63.97 410	90.95 387

E-PMN		52.30 390	52.18 392	52.67 407	71.51 423	45.40 429	93.62 401	76.60 429	36.01 423	43.50 424	64.13 423	27.11 422	67.31 426	31.06 427	26.06 422	45.30 425

EMVS		51.44 392	51.22 394	52.11 408	70.71 424	44.97 431	94.04 397	75.66 430	35.34 425	42.40 425	61.56 426	28.93 419	65.87 427	27.64 428	24.73 423	45.49 424

PMMVS2		67.15 385	64.15 388	76.14 395	70.56 425	62.07 416	93.89 398	87.52 423	58.09 414	60.02 413	78.32 415	22.38 424	84.54 418	59.56 415	47.03 420	81.80 413

FPMVS		68.72 381	68.72 382	68.71 403	65.95 426	44.27 432	95.97 390	94.74 396	51.13 418	53.26 420	90.50 394	25.11 423	83.00 419	60.80 414	80.97 351	78.87 416

wuyk23d		20.37 396	20.84 399	18.99 411	65.34 427	27.73 434	50.43 422	7.67 435	9.50 428	8.01 429	6.34 429	6.13 433	26.24 428	23.40 429	10.69 427	2.99 426

LCM-MVSNet		67.77 384	64.73 387	76.87 394	62.95 428	56.25 421	89.37 415	93.74 407	44.53 420	61.99 412	80.74 414	20.42 427	86.53 417	69.37 403	59.50 417	87.84 406

MVE	53.74 22	51.54 391	47.86 395	62.60 405	59.56 429	50.93 424	79.41 419	77.69 428	35.69 424	36.27 426	61.76 425	5.79 434	69.63 424	37.97 424	36.61 421	67.24 419
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 388	52.24 391	67.66 404	49.27 430	56.82 420	83.94 417	82.02 427	70.47 411	33.28 427	64.54 422	17.23 429	69.16 425	45.59 422	23.85 424	77.02 417

tmp_tt		65.23 387	62.94 390	72.13 402	44.90 431	50.03 427	81.05 418	89.42 422	38.45 421	48.51 423	99.90 18	54.09 406	78.70 423	91.84 261	18.26 425	87.64 407

PMVS	49.05 23	53.75 389	51.34 393	60.97 406	40.80 432	34.68 433	74.82 420	89.62 421	37.55 422	28.67 428	72.12 417	7.09 432	81.63 422	43.17 423	68.21 401	66.59 420
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 394	39.14 397	33.31 409	19.94 433	24.83 435	98.36 336	9.75 434	15.53 427	51.31 421	87.14 406	19.62 428	17.74 429	47.10 421	3.47 428	57.36 422

testmvs		40.60 393	44.45 396	29.05 410	19.49 434	14.11 436	99.68 186	18.47 433	20.74 426	64.59 411	98.48 220	10.95 431	17.09 430	56.66 419	11.01 426	55.94 423

mmdepth		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

monomultidepth		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

test_blank		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.02 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

eth-test2					0.00 435

eth-test					0.00 435

uanet_test		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

DCPMVS		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

cdsmvs_eth3d_5k		23.43 395	31.24 398	0.00 412	0.00 435	0.00 437	0.00 423	98.09 212	0.00 430	0.00 431	99.67 99	83.37 261	0.00 431	0.00 430	0.00 429	0.00 427

pcd_1.5k_mvsjas		7.60 398	10.13 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	91.20 164	0.00 431	0.00 430	0.00 429	0.00 427

sosnet-low-res		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

sosnet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uncertanet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

Regformer		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

ab-mvs-re		8.28 397	11.04 400	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	99.40 132	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uanet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 431	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

WAC-MVS						90.97 298								86.10 336

PC_three_1452									96.96 51	99.80 19	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 138	97.27 38	99.80 19	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 67	99.83 15	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

GSMVS																99.59 138

sam_mvs1												94.72 69				99.59 138

sam_mvs												94.25 89

MTGPA								98.28 186

test_post1							95.78 392				59.23 427	93.20 122	97.74 282	91.06 270

test_post											63.35 424	94.43 77	98.13 261

patchmatchnet-post											91.70 388	95.12 54	97.95 273

MTMP							99.87 112	96.49 362

test9_res														99.71 39	99.99 21	100.00 1

agg_prior2														99.48 50	100.00 1	100.00 1

test_prior4						98.05 74	99.94 74

test_prior2							99.95 57		95.78 87	99.73 36	99.76 66	96.00 37		99.78 27	100.00 1

旧先验2							99.46 227		94.21 143	99.85 11			99.95 75	96.96 170

新几何2							99.40 231

无先验							99.49 220	98.71 68	93.46 171				100.00 1	94.36 216		99.99 23

原ACMM2							99.90 97

testdata2													99.99 36	90.54 283

segment_acmp												96.68 29

testdata1							99.28 251		96.35 77

plane_prior5								97.87 234					98.37 242	97.79 147	89.55 271	94.52 280

plane_prior4											98.59 208

plane_prior3						91.64 290			96.63 64	93.01 243

plane_prior2							99.84 131		96.38 73

plane_prior						91.74 284	99.86 123		96.76 59						89.59 270

n2								0.00 436

nn								0.00 436

door-mid								89.69 420

test11								98.44 130

door								90.31 417

HQP5-MVS						91.85 280

BP-MVS														97.92 138

HQP4-MVS										93.37 238			98.39 236			94.53 278

HQP3-MVS								97.89 232							89.60 268

HQP2-MVS												80.65 289

MDTV_nov1_ep13_2view						96.26 149	96.11 386		91.89 233	98.06 146		94.40 79		94.30 219		99.67 119

ACMMP++_ref															87.04 302

ACMMP++															88.23 291

Test By Simon												92.82 133

High-resolution multi-view benchmark