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		97.23 107	96.80 115	98.51 113	99.99 1	95.60 173	99.09 259	98.84 59	93.32 170	96.74 179	99.72 84	86.04 234	100.00 1	98.01 127	99.43 115	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 69	98.20 8	99.93 1	99.98 2	96.82 22	100.00 1	99.75 31	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 28	98.64 77	98.47 3	99.13 89	99.92 13	96.38 32	100.00 1	99.74 33	100.00 1	100.00 1

mPP-MVS		98.39 50	98.20 49	98.97 81	99.97 3	96.92 118	99.95 53	98.38 163	95.04 101	98.61 117	99.80 54	93.39 109	100.00 1	98.64 96	100.00 1	99.98 51

CPTT-MVS		97.64 90	97.32 93	98.58 105	99.97 3	95.77 162	99.96 35	98.35 169	89.90 281	98.36 129	99.79 58	91.18 165	99.99 36	98.37 111	99.99 21	99.99 23

DP-MVS Recon		98.41 48	98.02 60	99.56 25	99.97 3	98.70 48	99.92 79	98.44 127	92.06 223	98.40 128	99.84 44	95.68 42	100.00 1	98.19 117	99.71 88	99.97 61

PAPR		98.52 38	98.16 52	99.58 24	99.97 3	98.77 42	99.95 53	98.43 135	95.35 95	98.03 141	99.75 72	94.03 95	99.98 47	98.11 122	99.83 77	99.99 23

HFP-MVS		98.56 35	98.37 39	99.14 61	99.96 8	97.43 97	99.95 53	98.61 83	94.77 109	99.31 78	99.85 33	94.22 88	100.00 1	98.70 91	99.98 32	99.98 51

region2R		98.54 36	98.37 39	99.05 71	99.96 8	97.18 106	99.96 35	98.55 99	94.87 107	99.45 65	99.85 33	94.07 94	100.00 1	98.67 93	100.00 1	99.98 51

ACMMPR		98.50 39	98.32 43	99.05 71	99.96 8	97.18 106	99.95 53	98.60 85	94.77 109	99.31 78	99.84 44	93.73 104	100.00 1	98.70 91	99.98 32	99.98 51

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 28	98.62 82	98.02 13	99.90 3	99.95 3	97.33 16	100.00 1	99.54 42	100.00 1	100.00 1

CP-MVS		98.45 43	98.32 43	98.87 86	99.96 8	96.62 128	99.97 28	98.39 159	94.43 123	98.90 100	99.87 27	94.30 85	100.00 1	99.04 67	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 152	96.63 60	99.75 29	99.93 11	97.49 9

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 53	98.43 135					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 29	98.55 28	99.15 59	99.94 13	97.50 93	99.94 69	98.42 147	96.22 75	99.41 70	99.78 62	94.34 82	99.96 65	98.92 76	99.95 50	99.99 23

X-MVStestdata		93.83 221	92.06 254	99.15 59	99.94 13	97.50 93	99.94 69	98.42 147	96.22 75	99.41 70	41.37 422	94.34 82	99.96 65	98.92 76	99.95 50	99.99 23

test_prior				99.43 35	99.94 13	98.49 60		98.65 75					99.80 124			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 40	99.80 17	99.94 4	95.92 38	100.00 1	99.51 43	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 85	98.39 159	97.20 38	99.46 64	99.85 33	95.53 46	99.79 126	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 61	97.97 63	99.03 73	99.94 13	97.17 109	99.95 53	98.39 159	94.70 113	98.26 135	99.81 53	91.84 156	100.00 1	98.85 82	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	99.87 106	98.33 174	93.97 148	99.76 28	99.87 27	94.99 60	99.75 135	98.55 100	100.00 1	99.98 51

PAPM_NR		98.12 64	97.93 68	98.70 94	99.94 13	96.13 152	99.82 135	98.43 135	94.56 117	97.52 155	99.70 88	94.40 77	99.98 47	97.00 161	99.98 32	99.99 23

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 188	99.44 19	97.33 31	99.00 96	99.72 84	94.03 95	99.98 47	98.73 90	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 35	98.43 135	97.27 34	99.80 17	99.94 4	96.71 25	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 24	99.31 10		98.41 152	97.71 19	99.84 12				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 135	97.26 36	99.80 17	99.88 24	96.71 25	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 53	98.32 176	97.28 32	99.83 13	99.91 14	97.22 18	100.00 1	99.99 5	100.00 1	99.89 87
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 35	98.42 147	97.28 32	99.86 7	99.94 4	97.22 18

MSP-MVS		99.09 9	99.12 5	98.98 80	99.93 24	97.24 103	99.95 53	98.42 147	97.50 26	99.52 60	99.88 24	97.43 15	99.71 141	99.50 44	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		98.43 135		99.63 44			99.85 111

FOURS1					99.92 31	97.66 87	99.95 53	98.36 167	95.58 89	99.52 60

ZD-MVS					99.92 31	98.57 56		98.52 107	92.34 215	99.31 78	99.83 46	95.06 55	99.80 124	99.70 37	99.97 42

GST-MVS		98.27 55	97.97 63	99.17 55	99.92 31	97.57 89	99.93 76	98.39 159	94.04 146	98.80 105	99.74 79	92.98 125	100.00 1	98.16 119	99.76 85	99.93 79

TEST9					99.92 31	98.92 29	99.96 35	98.43 135	93.90 154	99.71 35	99.86 29	95.88 39	99.85 111

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 35	98.43 135	94.35 128	99.71 35	99.86 29	95.94 36	99.85 111	99.69 38	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 35	98.43 135	94.35 128	99.69 37	99.85 33	95.94 36	99.85 111

PGM-MVS		98.34 51	98.13 54	98.99 78	99.92 31	97.00 114	99.75 156	99.50 17	93.90 154	99.37 75	99.76 66	93.24 118	100.00 1	97.75 146	99.96 46	99.98 51

ACMMP		97.74 85	97.44 87	98.66 97	99.92 31	96.13 152	99.18 254	99.45 18	94.84 108	96.41 189	99.71 86	91.40 159	99.99 36	97.99 129	98.03 165	99.87 90
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 53	98.43 135	96.48 63	99.80 17	99.93 11	97.44 13	100.00 1	99.92 13	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 152					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 152					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 53	98.56 93	97.56 25	99.44 66	99.85 33	95.38 49	100.00 1	99.31 54	99.99 21	99.87 90

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 106	98.36 167	94.08 141	99.74 31	99.73 81	94.08 93	99.74 137	99.42 50	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	99.24 249	98.47 119	98.14 10	99.08 92	99.91 14	93.09 122	100.00 1	99.04 67	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 35				99.80 54	97.44 13	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	99.87 106	98.44 127	97.48 27	99.64 43	99.94 4	96.68 27	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 63

CSCG		97.10 112	97.04 104	97.27 189	99.89 45	91.92 273	99.90 91	99.07 34	88.67 305	95.26 212	99.82 49	93.17 121	99.98 47	98.15 120	99.47 110	99.90 86

ZNCC-MVS		98.31 52	98.03 59	99.17 55	99.88 49	97.59 88	99.94 69	98.44 127	94.31 131	98.50 122	99.82 49	93.06 123	99.99 36	98.30 115	99.99 21	99.93 79

SR-MVS		98.46 42	98.30 46	98.93 84	99.88 49	97.04 113	99.84 125	98.35 169	94.92 105	99.32 77	99.80 54	93.35 111	99.78 128	99.30 55	99.95 50	99.96 67

9.14			98.38 37		99.87 51		99.91 85	98.33 174	93.22 173	99.78 26	99.89 22	94.57 73	99.85 111	99.84 22	99.97 42

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 117	98.38 163	93.19 174	99.77 27	99.94 4	95.54 44	100.00 1	99.74 33	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 73	99.86 53	97.10 111	99.98 15	98.80 63	90.78 264	99.62 47	99.78 62	95.30 50	100.00 1	99.80 25	99.93 61	99.99 23

MTAPA		98.29 54	97.96 66	99.30 44	99.85 54	97.93 77	99.39 229	98.28 183	95.76 84	97.18 167	99.88 24	92.74 132	100.00 1	98.67 93	99.88 73	99.99 23

LS3D		95.84 166	95.11 177	98.02 142	99.85 54	95.10 193	98.74 304	98.50 116	87.22 327	93.66 230	99.86 29	87.45 217	99.95 73	90.94 268	99.81 83	99.02 211

HPM-MVS		97.96 67	97.72 75	98.68 95	99.84 56	96.39 139	99.90 91	98.17 198	92.61 201	98.62 116	99.57 110	91.87 155	99.67 148	98.87 81	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 55	98.11 56	98.75 92	99.83 57	96.59 131	99.40 225	98.51 110	95.29 97	98.51 121	99.76 66	93.60 108	99.71 141	98.53 103	99.52 105	99.95 74

save fliter					99.82 58	98.79 40	99.96 35	98.40 156	97.66 21

PLC	95.54 3	97.93 69	97.89 71	98.05 141	99.82 58	94.77 203	99.92 79	98.46 121	93.93 151	97.20 165	99.27 137	95.44 48	99.97 57	97.41 151	99.51 108	99.41 173
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 59	98.08 58	98.78 89	99.81 60	96.60 129	99.82 135	98.30 181	93.95 150	99.37 75	99.77 64	92.84 129	99.76 134	98.95 73	99.92 64	99.97 61

EI-MVSNet-UG-set		98.14 63	97.99 61	98.60 102	99.80 61	96.27 142	99.36 234	98.50 116	95.21 99	98.30 132	99.75 72	93.29 115	99.73 140	98.37 111	99.30 122	99.81 97

SR-MVS-dyc-post		98.31 52	98.17 51	98.71 93	99.79 62	96.37 140	99.76 152	98.31 178	94.43 123	99.40 72	99.75 72	93.28 116	99.78 128	98.90 79	99.92 64	99.97 61

RE-MVS-def			98.13 54		99.79 62	96.37 140	99.76 152	98.31 178	94.43 123	99.40 72	99.75 72	92.95 126		98.90 79	99.92 64	99.97 61

HPM-MVS_fast		97.80 80	97.50 84	98.68 95	99.79 62	96.42 135	99.88 103	98.16 202	91.75 233	98.94 98	99.54 113	91.82 157	99.65 150	97.62 149	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 91	98.21 193	93.53 163	99.81 15	99.89 22	94.70 69	99.86 110	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 66	99.75 72	93.24 118	99.99 36	99.94 11	99.41 117	99.95 74

旧先验1					99.76 66	97.52 91		98.64 77			99.85 33	95.63 43			99.94 55	99.99 23

OMC-MVS		97.28 104	97.23 96	97.41 180	99.76 66	93.36 242	99.65 184	97.95 221	96.03 79	97.41 160	99.70 88	89.61 191	99.51 156	96.73 170	98.25 157	99.38 175

新几何1				99.42 37	99.75 69	98.27 64		98.63 81	92.69 196	99.55 55	99.82 49	94.40 77	100.00 1	91.21 260	99.94 55	99.99 23

MP-MVS-pluss		98.07 66	97.64 79	99.38 42	99.74 70	98.41 63	99.74 159	98.18 197	93.35 168	96.45 186	99.85 33	92.64 134	99.97 57	98.91 78	99.89 70	99.77 104
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	99.77 147	98.38 163	96.73 56	99.88 6	99.74 79	94.89 62	99.59 152	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		98.40 156		99.65 41		94.76 65	99.75 135		99.98 32	99.99 23

原ACMM1				98.96 82	99.73 73	96.99 115		98.51 110	94.06 144	99.62 47	99.85 33	94.97 61	99.96 65	95.11 190	99.95 50	99.92 84

TSAR-MVS + GP.		98.60 33	98.51 31	98.86 87	99.73 73	96.63 127	99.97 28	97.92 226	98.07 11	98.76 109	99.55 111	95.00 59	99.94 81	99.91 16	97.68 170	99.99 23

CANet		98.27 55	97.82 73	99.63 17	99.72 75	99.10 23	99.98 15	98.51 110	97.00 46	98.52 119	99.71 86	87.80 212	99.95 73	99.75 31	99.38 118	99.83 94

reproduce_model		98.75 27	98.66 23	99.03 73	99.71 76	97.10 111	99.73 166	98.23 191	97.02 45	99.18 87	99.90 18	94.54 74	99.99 36	99.77 28	99.90 69	99.99 23

F-COLMAP		96.93 124	96.95 107	96.87 199	99.71 76	91.74 278	99.85 120	97.95 221	93.11 179	95.72 205	99.16 148	92.35 144	99.94 81	95.32 188	99.35 120	98.92 214

reproduce-ours		98.78 24	98.67 21	99.09 68	99.70 78	97.30 101	99.74 159	98.25 187	97.10 40	99.10 90	99.90 18	94.59 70	99.99 36	99.77 28	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 68	99.70 78	97.30 101	99.74 159	98.25 187	97.10 40	99.10 90	99.90 18	94.59 70	99.99 36	99.77 28	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 69	98.34 173	96.38 69	99.81 15	99.76 66	94.59 70	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 60	99.12 5	95.59 234	99.67 81	86.91 354	99.95 53	98.89 49	97.60 22	99.90 3	99.76 66	96.54 30	99.98 47	99.94 11	99.82 81	99.88 88

ACMMP_NAP		98.49 40	98.14 53	99.54 27	99.66 82	98.62 55	99.85 120	98.37 166	94.68 114	99.53 58	99.83 46	92.87 128	100.00 1	98.66 95	99.84 76	99.99 23

DeepPCF-MVS	95.94 2	97.71 88	98.98 12	93.92 297	99.63 83	81.76 384	99.96 35	98.56 93	99.47 1	99.19 86	99.99 1	94.16 92	100.00 1	99.92 13	99.93 61	100.00 1

EPNet		98.49 40	98.40 35	98.77 91	99.62 84	96.80 123	99.90 91	99.51 16	97.60 22	99.20 84	99.36 131	93.71 105	99.91 92	97.99 129	98.71 144	99.61 134
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 74	99.80 54	90.49 180	99.96 65	99.89 17	99.43 115	99.98 51

PVSNet_BlendedMVS		96.05 160	95.82 156	96.72 204	99.59 85	96.99 115	99.95 53	99.10 31	94.06 144	98.27 133	95.80 301	89.00 202	99.95 73	99.12 61	87.53 294	93.24 353

PVSNet_Blended		97.94 68	97.64 79	98.83 88	99.59 85	96.99 115	100.00 1	99.10 31	95.38 94	98.27 133	99.08 151	89.00 202	99.95 73	99.12 61	99.25 124	99.57 145

PatchMatch-RL		96.04 161	95.40 166	97.95 144	99.59 85	95.22 189	99.52 208	99.07 34	93.96 149	96.49 185	98.35 220	82.28 263	99.82 123	90.15 284	99.22 127	98.81 221

dcpmvs_2		97.42 99	98.09 57	95.42 239	99.58 89	87.24 350	99.23 250	96.95 327	94.28 134	98.93 99	99.73 81	94.39 80	99.16 182	99.89 17	99.82 81	99.86 92

test222					99.55 90	97.41 99	99.34 235	98.55 99	91.86 228	99.27 82	99.83 46	93.84 102			99.95 50	99.99 23

CNLPA		97.76 84	97.38 89	98.92 85	99.53 91	96.84 120	99.87 106	98.14 206	93.78 157	96.55 184	99.69 90	92.28 146	99.98 47	97.13 157	99.44 114	99.93 79

API-MVS		97.86 72	97.66 78	98.47 115	99.52 92	95.41 180	99.47 217	98.87 52	91.68 234	98.84 102	99.85 33	92.34 145	99.99 36	98.44 107	99.96 46	100.00 1

PVSNet	91.05 13	97.13 111	96.69 121	98.45 117	99.52 92	95.81 160	99.95 53	99.65 12	94.73 111	99.04 94	99.21 144	84.48 249	99.95 73	94.92 195	98.74 143	99.58 143

114514_t		97.41 100	96.83 113	99.14 61	99.51 94	97.83 79	99.89 100	98.27 185	88.48 309	99.06 93	99.66 99	90.30 183	99.64 151	96.32 174	99.97 42	99.96 67

cl22		93.77 225	93.25 229	95.33 243	99.49 95	94.43 207	99.61 193	98.09 208	90.38 270	89.16 297	95.61 308	90.56 178	97.34 289	91.93 252	84.45 314	94.21 299

testdata				98.42 120	99.47 96	95.33 183		98.56 93	93.78 157	99.79 25	99.85 33	93.64 107	99.94 81	94.97 193	99.94 55	100.00 1

MAR-MVS		97.43 95	97.19 98	98.15 135	99.47 96	94.79 202	99.05 270	98.76 64	92.65 199	98.66 114	99.82 49	88.52 207	99.98 47	98.12 121	99.63 94	99.67 118
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		94.54 203	93.42 222	97.91 150	99.46 98	94.04 220	98.93 284	97.48 270	81.15 380	90.04 269	99.55 111	87.02 223	99.95 73	88.97 294	98.11 161	99.73 108

MVS_111021_LR		98.42 47	98.38 37	98.53 112	99.39 99	95.79 161	99.87 106	99.86 2	96.70 57	98.78 106	99.79 58	92.03 152	99.90 94	99.17 60	99.86 75	99.88 88

CHOSEN 280x420		99.01 14	99.03 10	98.95 83	99.38 100	98.87 33	98.46 322	99.42 21	97.03 44	99.02 95	99.09 150	99.35 2	98.21 251	99.73 35	99.78 84	99.77 104

MVS_111021_HR		98.72 28	98.62 26	99.01 77	99.36 101	97.18 106	99.93 76	99.90 1	96.81 54	98.67 113	99.77 64	93.92 97	99.89 99	99.27 56	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 35	98.44 127	97.96 14	99.55 55	99.94 4	97.18 20	100.00 1	93.81 224	99.94 55	99.98 51

TAPA-MVS	92.12 8	94.42 209	93.60 215	96.90 198	99.33 102	91.78 277	99.78 144	98.00 215	89.89 282	94.52 218	99.47 117	91.97 153	99.18 179	69.90 395	99.52 105	99.73 108
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 180	95.07 179	96.32 217	99.32 104	96.60 129	99.76 152	98.85 56	96.65 59	87.83 318	96.05 298	99.52 1	98.11 256	96.58 171	81.07 342	94.25 295

SPE-MVS-test		97.88 71	97.94 67	97.70 163	99.28 105	95.20 190	99.98 15	97.15 304	95.53 91	99.62 47	99.79 58	92.08 151	98.38 234	98.75 89	99.28 123	99.52 157

test_fmvsm_n_1920		98.44 44	98.61 27	97.92 148	99.27 106	95.18 191	100.00 1	98.90 47	98.05 12	99.80 17	99.73 81	92.64 134	99.99 36	99.58 41	99.51 108	98.59 231

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 45	99.21 107	97.91 78	99.98 15	98.85 56	98.25 5	99.92 2	99.75 72	94.72 67	99.97 57	99.87 19	99.64 92	99.95 74

test_yl		97.83 75	97.37 90	99.21 49	99.18 108	97.98 74	99.64 188	99.27 27	91.43 243	97.88 147	98.99 160	95.84 40	99.84 119	98.82 83	95.32 224	99.79 100

DCV-MVSNet		97.83 75	97.37 90	99.21 49	99.18 108	97.98 74	99.64 188	99.27 27	91.43 243	97.88 147	98.99 160	95.84 40	99.84 119	98.82 83	95.32 224	99.79 100

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 46	99.17 110	97.81 81	99.98 15	98.86 53	98.25 5	99.90 3	99.76 66	94.21 90	99.97 57	99.87 19	99.52 105	99.98 51

DeepC-MVS	94.51 4	96.92 125	96.40 131	98.45 117	99.16 111	95.90 158	99.66 183	98.06 211	96.37 72	94.37 221	99.49 116	83.29 258	99.90 94	97.63 148	99.61 99	99.55 147
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 88	97.70 20	98.21 137	99.24 142	92.58 137	99.94 81	98.63 98	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
CS-MVS		97.79 82	97.91 69	97.43 179	99.10 113	94.42 208	99.99 4	97.10 309	95.07 100	99.68 38	99.75 72	92.95 126	98.34 238	98.38 109	99.14 129	99.54 151

Anonymous202405211		93.10 243	91.99 255	96.40 213	99.10 113	89.65 322	98.88 290	97.93 223	83.71 365	94.00 227	98.75 189	68.79 360	99.88 105	95.08 191	91.71 256	99.68 116

fmvsm_s_conf0.5_n		97.80 80	97.85 72	97.67 164	99.06 115	94.41 209	99.98 15	98.97 40	97.34 29	99.63 44	99.69 90	87.27 219	99.97 57	99.62 40	99.06 133	98.62 230

HyFIR lowres test		96.66 139	96.43 130	97.36 185	99.05 116	93.91 225	99.70 177	99.80 3	90.54 268	96.26 192	98.08 230	92.15 149	98.23 250	96.84 169	95.46 219	99.93 79

LFMVS		94.75 197	93.56 218	98.30 126	99.03 117	95.70 167	98.74 304	97.98 218	87.81 320	98.47 123	99.39 128	67.43 369	99.53 153	98.01 127	95.20 227	99.67 118

AllTest		92.48 257	91.64 260	95.00 252	99.01 118	88.43 338	98.94 282	96.82 341	86.50 336	88.71 302	98.47 215	74.73 337	99.88 105	85.39 333	96.18 201	96.71 260

TestCases				95.00 252	99.01 118	88.43 338		96.82 341	86.50 336	88.71 302	98.47 215	74.73 337	99.88 105	85.39 333	96.18 201	96.71 260

COLMAP_ROB	90.47 14	92.18 264	91.49 266	94.25 285	99.00 120	88.04 344	98.42 328	96.70 348	82.30 376	88.43 310	99.01 157	76.97 313	99.85 111	86.11 329	96.50 195	94.86 271
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs1		95.35 181	95.68 161	94.36 282	98.99 121	84.98 364	99.96 35	96.65 350	97.60 22	99.73 33	98.96 166	71.58 350	99.93 88	98.31 114	99.37 119	98.17 238

HY-MVS	92.50 7	97.79 82	97.17 100	99.63 17	98.98 122	99.32 9	97.49 353	99.52 14	95.69 86	98.32 131	97.41 250	93.32 113	99.77 131	98.08 125	95.75 215	99.81 97

VNet		97.21 108	96.57 126	99.13 65	98.97 123	97.82 80	99.03 273	99.21 29	94.31 131	99.18 87	98.88 177	86.26 233	99.89 99	98.93 75	94.32 236	99.69 115

thres200		96.96 121	96.21 137	99.22 48	98.97 123	98.84 36	99.85 120	99.71 7	93.17 175	96.26 192	98.88 177	89.87 188	99.51 156	94.26 214	94.91 229	99.31 185

tfpn200view9		96.79 129	95.99 142	99.19 51	98.94 125	98.82 37	99.78 144	99.71 7	92.86 185	96.02 197	98.87 180	89.33 195	99.50 158	93.84 221	94.57 232	99.27 191

thres400		96.78 131	95.99 142	99.16 57	98.94 125	98.82 37	99.78 144	99.71 7	92.86 185	96.02 197	98.87 180	89.33 195	99.50 158	93.84 221	94.57 232	99.16 198

sasdasda		97.09 114	96.32 132	99.39 40	98.93 127	98.95 27	99.72 170	97.35 281	94.45 120	97.88 147	99.42 121	86.71 226	99.52 154	98.48 104	93.97 242	99.72 110

Anonymous20231211		89.86 314	88.44 321	94.13 288	98.93 127	90.68 301	98.54 319	98.26 186	76.28 392	86.73 332	95.54 312	70.60 356	97.56 282	90.82 271	80.27 351	94.15 307

canonicalmvs		97.09 114	96.32 132	99.39 40	98.93 127	98.95 27	99.72 170	97.35 281	94.45 120	97.88 147	99.42 121	86.71 226	99.52 154	98.48 104	93.97 242	99.72 110

SDMVSNet		94.80 193	93.96 207	97.33 187	98.92 130	95.42 179	99.59 195	98.99 37	92.41 212	92.55 245	97.85 241	75.81 327	98.93 192	97.90 135	91.62 257	97.64 250

sd_testset		93.55 232	92.83 235	95.74 232	98.92 130	90.89 297	98.24 335	98.85 56	92.41 212	92.55 245	97.85 241	71.07 355	98.68 210	93.93 218	91.62 257	97.64 250

EPNet_dtu		95.71 170	95.39 167	96.66 206	98.92 130	93.41 239	99.57 200	98.90 47	96.19 77	97.52 155	98.56 207	92.65 133	97.36 287	77.89 376	98.33 152	99.20 196
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 65	97.60 81	99.60 22	98.92 130	99.28 17	99.89 100	99.52 14	95.58 89	98.24 136	99.39 128	93.33 112	99.74 137	97.98 131	95.58 218	99.78 103

CHOSEN 1792x2688		96.81 128	96.53 127	97.64 166	98.91 134	93.07 244	99.65 184	99.80 3	95.64 87	95.39 209	98.86 182	84.35 251	99.90 94	96.98 163	99.16 128	99.95 74

thres100view900		96.74 134	95.92 152	99.18 52	98.90 135	98.77 42	99.74 159	99.71 7	92.59 203	95.84 201	98.86 182	89.25 197	99.50 158	93.84 221	94.57 232	99.27 191

thres600view7		96.69 137	95.87 155	99.14 61	98.90 135	98.78 41	99.74 159	99.71 7	92.59 203	95.84 201	98.86 182	89.25 197	99.50 158	93.44 233	94.50 235	99.16 198

MSDG		94.37 211	93.36 226	97.40 181	98.88 137	93.95 224	99.37 232	97.38 279	85.75 347	90.80 262	99.17 147	84.11 253	99.88 105	86.35 325	98.43 150	98.36 236

MGCFI-Net		97.00 119	96.22 136	99.34 43	98.86 138	98.80 39	99.67 182	97.30 288	94.31 131	97.77 151	99.41 125	86.36 232	99.50 158	98.38 109	93.90 244	99.72 110

h-mvs33		94.92 190	94.36 195	96.59 208	98.85 139	91.29 289	98.93 284	98.94 41	95.90 80	98.77 107	98.42 218	90.89 173	99.77 131	97.80 139	70.76 387	98.72 227

Anonymous20240529		92.10 265	90.65 277	96.47 209	98.82 140	90.61 303	98.72 306	98.67 74	75.54 396	93.90 229	98.58 205	66.23 373	99.90 94	94.70 204	90.67 260	98.90 217

PVSNet_Blended_VisFu		97.27 105	96.81 114	98.66 97	98.81 141	96.67 126	99.92 79	98.64 77	94.51 119	96.38 190	98.49 211	89.05 201	99.88 105	97.10 159	98.34 151	99.43 171

PS-MVSNAJ		98.44 44	98.20 49	99.16 57	98.80 142	98.92 29	99.54 206	98.17 198	97.34 29	99.85 9	99.85 33	91.20 162	99.89 99	99.41 51	99.67 90	98.69 228

CANet_DTU		96.76 132	96.15 138	98.60 102	98.78 143	97.53 90	99.84 125	97.63 248	97.25 37	99.20 84	99.64 102	81.36 273	99.98 47	92.77 244	98.89 137	98.28 237

mvsany_test1		97.82 78	97.90 70	97.55 171	98.77 144	93.04 247	99.80 141	97.93 223	96.95 48	99.61 53	99.68 96	90.92 170	99.83 121	99.18 59	98.29 156	99.80 99

alignmvs		97.81 79	97.33 92	99.25 46	98.77 144	98.66 51	99.99 4	98.44 127	94.40 127	98.41 126	99.47 117	93.65 106	99.42 167	98.57 99	94.26 238	99.67 118

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 52	98.72 146	97.71 83	99.98 15	98.44 127	96.85 49	99.80 17	99.91 14	97.57 7	99.85 111	99.44 49	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 61	97.97 63	99.02 76	98.69 147	98.66 51	99.52 208	98.08 210	97.05 43	99.86 7	99.86 29	90.65 175	99.71 141	99.39 53	98.63 145	98.69 228

miper_enhance_ethall		94.36 213	93.98 206	95.49 235	98.68 148	95.24 187	99.73 166	97.29 291	93.28 172	89.86 274	95.97 299	94.37 81	97.05 309	92.20 248	84.45 314	94.19 300

ETVMVS		97.03 118	96.64 122	98.20 131	98.67 149	97.12 110	99.89 100	98.57 90	91.10 254	98.17 138	98.59 202	93.86 101	98.19 252	95.64 185	95.24 226	99.28 190

test2506		97.53 92	97.19 98	98.58 105	98.66 150	96.90 119	98.81 299	99.77 5	94.93 103	97.95 143	98.96 166	92.51 139	99.20 177	94.93 194	98.15 158	99.64 124

ECVR-MVS		95.66 173	95.05 180	97.51 175	98.66 150	93.71 229	98.85 296	98.45 122	94.93 103	96.86 175	98.96 166	75.22 333	99.20 177	95.34 187	98.15 158	99.64 124

mamv4		95.24 183	96.90 109	90.25 354	98.65 152	72.11 401	98.28 333	97.64 247	89.99 280	95.93 199	98.25 225	94.74 66	99.11 183	99.01 72	99.64 92	99.53 155

balanced_conf03		98.27 55	97.99 61	99.11 66	98.64 153	98.43 62	99.47 217	97.79 237	94.56 117	99.74 31	98.35 220	94.33 84	99.25 171	99.12 61	99.96 46	99.64 124

fmvsm_s_conf0.5_n_a		97.73 87	97.72 75	97.77 158	98.63 154	94.26 215	99.96 35	98.92 46	97.18 39	99.75 29	99.69 90	87.00 224	99.97 57	99.46 47	98.89 137	99.08 207

MVSMamba_PlusPlus		97.83 75	97.45 86	98.99 78	98.60 155	98.15 65	99.58 197	97.74 240	90.34 273	99.26 83	98.32 223	94.29 86	99.23 172	99.03 70	99.89 70	99.58 143

testing222		97.08 117	96.75 117	98.06 140	98.56 156	96.82 121	99.85 120	98.61 83	92.53 207	98.84 102	98.84 186	93.36 110	98.30 242	95.84 182	94.30 237	99.05 209

test1111		95.57 175	94.98 183	97.37 183	98.56 156	93.37 241	98.86 294	98.45 122	94.95 102	96.63 181	98.95 171	75.21 334	99.11 183	95.02 192	98.14 160	99.64 124

MVSTER		95.53 176	95.22 173	96.45 211	98.56 156	97.72 82	99.91 85	97.67 245	92.38 214	91.39 255	97.14 257	97.24 17	97.30 293	94.80 200	87.85 289	94.34 290

VDD-MVS		93.77 225	92.94 233	96.27 218	98.55 159	90.22 312	98.77 303	97.79 237	90.85 260	96.82 177	99.42 121	61.18 392	99.77 131	98.95 73	94.13 239	98.82 220

tpmvs		94.28 215	93.57 217	96.40 213	98.55 159	91.50 287	95.70 387	98.55 99	87.47 322	92.15 248	94.26 362	91.42 158	98.95 191	88.15 304	95.85 211	98.76 223

UGNet		95.33 182	94.57 191	97.62 169	98.55 159	94.85 198	98.67 312	99.32 26	95.75 85	96.80 178	96.27 289	72.18 347	99.96 65	94.58 207	99.05 134	98.04 242
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	95.18 184	94.10 202	98.43 119	98.55 159	95.99 156	97.91 348	97.31 287	90.35 272	89.48 286	99.22 143	85.19 242	99.89 99	90.40 281	98.47 149	99.41 173
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		96.79 129	96.72 119	97.00 194	98.51 163	93.70 230	99.71 173	98.60 85	92.96 181	97.09 168	98.34 222	96.67 29	98.85 195	92.11 250	96.50 195	98.44 233

test_vis1_n_1920		95.44 178	95.31 170	95.82 230	98.50 164	88.74 332	99.98 15	97.30 288	97.84 16	99.85 9	99.19 145	66.82 371	99.97 57	98.82 83	99.46 112	98.76 223

BH-w/o		95.71 170	95.38 168	96.68 205	98.49 165	92.28 264	99.84 125	97.50 268	92.12 220	92.06 251	98.79 187	84.69 247	98.67 211	95.29 189	99.66 91	99.09 205

baseline1		95.78 167	94.86 185	98.54 110	98.47 166	98.07 69	99.06 266	97.99 216	92.68 197	94.13 226	98.62 201	93.28 116	98.69 209	93.79 226	85.76 302	98.84 219

EPMVS		96.53 143	96.01 141	98.09 138	98.43 167	96.12 154	96.36 374	99.43 20	93.53 163	97.64 153	95.04 339	94.41 76	98.38 234	91.13 262	98.11 161	99.75 106

kuosan		93.17 240	92.60 241	94.86 259	98.40 168	89.54 324	98.44 324	98.53 105	84.46 360	88.49 306	97.92 238	90.57 177	97.05 309	83.10 348	93.49 247	97.99 243

WBMVS		94.52 206	94.03 204	95.98 224	98.38 169	96.68 125	99.92 79	97.63 248	90.75 265	89.64 282	95.25 333	96.77 23	96.90 320	94.35 212	83.57 321	94.35 288

UBG		97.84 74	97.69 77	98.29 127	98.38 169	96.59 131	99.90 91	98.53 105	93.91 153	98.52 119	98.42 218	96.77 23	99.17 180	98.54 101	96.20 200	99.11 204

sss		97.57 91	97.03 105	99.18 52	98.37 171	98.04 71	99.73 166	99.38 22	93.46 165	98.76 109	99.06 153	91.21 161	99.89 99	96.33 173	97.01 187	99.62 130

testing11		97.48 94	97.27 94	98.10 137	98.36 172	96.02 155	99.92 79	98.45 122	93.45 167	98.15 139	98.70 192	95.48 47	99.22 173	97.85 137	95.05 228	99.07 208

BH-untuned		95.18 184	94.83 186	96.22 219	98.36 172	91.22 290	99.80 141	97.32 286	90.91 258	91.08 258	98.67 194	83.51 255	98.54 217	94.23 215	99.61 99	98.92 214

testing91		97.16 110	96.90 109	97.97 143	98.35 174	95.67 170	99.91 85	98.42 147	92.91 184	97.33 162	98.72 190	94.81 64	99.21 174	96.98 163	94.63 231	99.03 210

testing99		97.17 109	96.91 108	97.95 144	98.35 174	95.70 167	99.91 85	98.43 135	92.94 182	97.36 161	98.72 190	94.83 63	99.21 174	97.00 161	94.64 230	98.95 213

ET-MVSNet_ETH3D		94.37 211	93.28 228	97.64 166	98.30 176	97.99 73	99.99 4	97.61 254	94.35 128	71.57 399	99.45 120	96.23 33	95.34 369	96.91 168	85.14 309	99.59 137

AUN-MVS		93.28 237	92.60 241	95.34 242	98.29 177	90.09 315	99.31 239	98.56 93	91.80 232	96.35 191	98.00 233	89.38 194	98.28 245	92.46 245	69.22 392	97.64 250

FMVSNet3		92.69 253	91.58 262	95.99 223	98.29 177	97.42 98	99.26 248	97.62 251	89.80 283	89.68 278	95.32 327	81.62 271	96.27 348	87.01 321	85.65 303	94.29 292

PMMVS		96.76 132	96.76 116	96.76 202	98.28 179	92.10 268	99.91 85	97.98 218	94.12 139	99.53 58	99.39 128	86.93 225	98.73 204	96.95 166	97.73 168	99.45 168

hse-mvs2		94.38 210	94.08 203	95.31 244	98.27 180	90.02 316	99.29 244	98.56 93	95.90 80	98.77 107	98.00 233	90.89 173	98.26 249	97.80 139	69.20 393	97.64 250

PVSNet_0	88.03 19	91.80 272	90.27 286	96.38 215	98.27 180	90.46 307	99.94 69	99.61 13	93.99 147	86.26 342	97.39 252	71.13 354	99.89 99	98.77 87	67.05 398	98.79 222

UA-Net		96.54 142	95.96 148	98.27 128	98.23 182	95.71 166	98.00 346	98.45 122	93.72 160	98.41 126	99.27 137	88.71 206	99.66 149	91.19 261	97.69 169	99.44 170

test_cas_vis1_n_1920		96.59 141	96.23 135	97.65 165	98.22 183	94.23 216	99.99 4	97.25 295	97.77 17	99.58 54	99.08 151	77.10 310	99.97 57	97.64 147	99.45 113	98.74 225

FE-MVS		95.70 172	95.01 182	97.79 155	98.21 184	94.57 204	95.03 388	98.69 69	88.90 299	97.50 157	96.19 291	92.60 136	99.49 163	89.99 286	97.94 167	99.31 185

GG-mvs-BLEND				98.54 110	98.21 184	98.01 72	93.87 393	98.52 107		97.92 144	97.92 238	99.02 3	97.94 269	98.17 118	99.58 102	99.67 118

mvs_anonymous		95.65 174	95.03 181	97.53 173	98.19 186	95.74 164	99.33 236	97.49 269	90.87 259	90.47 265	97.10 259	88.23 209	97.16 300	95.92 180	97.66 171	99.68 116

MVS_Test		96.46 145	95.74 157	98.61 101	98.18 187	97.23 104	99.31 239	97.15 304	91.07 255	98.84 102	97.05 263	88.17 210	98.97 188	94.39 209	97.50 173	99.61 134

BH-RMVSNet		95.18 184	94.31 198	97.80 153	98.17 188	95.23 188	99.76 152	97.53 264	92.52 208	94.27 224	99.25 141	76.84 315	98.80 197	90.89 270	99.54 104	99.35 180

dongtai		91.55 278	91.13 271	92.82 327	98.16 189	86.35 355	99.47 217	98.51 110	83.24 368	85.07 351	97.56 246	90.33 182	94.94 375	76.09 384	91.73 255	97.18 257

RPSCF		91.80 272	92.79 237	88.83 365	98.15 190	69.87 403	98.11 342	96.60 352	83.93 363	94.33 222	99.27 137	79.60 293	99.46 166	91.99 251	93.16 252	97.18 257

ETV-MVS		97.92 70	97.80 74	98.25 129	98.14 191	96.48 133	99.98 15	97.63 248	95.61 88	99.29 81	99.46 119	92.55 138	98.82 196	99.02 71	98.54 147	99.46 166

IS-MVSNet		96.29 155	95.90 153	97.45 177	98.13 192	94.80 201	99.08 261	97.61 254	92.02 225	95.54 208	98.96 166	90.64 176	98.08 258	93.73 229	97.41 177	99.47 165

test_fmvsmconf_n		98.43 46	98.32 43	98.78 89	98.12 193	96.41 136	99.99 4	98.83 60	98.22 7	99.67 39	99.64 102	91.11 166	99.94 81	99.67 39	99.62 95	99.98 51

ab-mvs		94.69 198	93.42 222	98.51 113	98.07 194	96.26 143	96.49 372	98.68 71	90.31 274	94.54 217	97.00 265	76.30 322	99.71 141	95.98 179	93.38 250	99.56 146

XVG-OURS-SEG-HR		94.79 194	94.70 190	95.08 249	98.05 195	89.19 326	99.08 261	97.54 262	93.66 161	94.87 215	99.58 109	78.78 301	99.79 126	97.31 153	93.40 249	96.25 264

EIA-MVS		97.53 92	97.46 85	97.76 160	98.04 196	94.84 199	99.98 15	97.61 254	94.41 126	97.90 145	99.59 107	92.40 143	98.87 193	98.04 126	99.13 130	99.59 137

XVG-OURS		94.82 191	94.74 189	95.06 250	98.00 197	89.19 326	99.08 261	97.55 260	94.10 140	94.71 216	99.62 105	80.51 285	99.74 137	96.04 178	93.06 254	96.25 264

mvsmamba		96.94 122	96.73 118	97.55 171	97.99 198	94.37 212	99.62 191	97.70 242	93.13 177	98.42 125	97.92 238	88.02 211	98.75 203	98.78 86	99.01 135	99.52 157

dp		95.05 187	94.43 193	96.91 197	97.99 198	92.73 254	96.29 377	97.98 218	89.70 284	95.93 199	94.67 352	93.83 103	98.45 223	86.91 324	96.53 194	99.54 151

tpmrst		96.27 157	95.98 144	97.13 191	97.96 200	93.15 243	96.34 375	98.17 198	92.07 221	98.71 112	95.12 336	93.91 98	98.73 204	94.91 197	96.62 192	99.50 162

TR-MVS		94.54 203	93.56 218	97.49 176	97.96 200	94.34 213	98.71 307	97.51 267	90.30 275	94.51 219	98.69 193	75.56 328	98.77 200	92.82 243	95.99 205	99.35 180

Vis-MVSNet (Re-imp)		96.32 152	95.98 144	97.35 186	97.93 202	94.82 200	99.47 217	98.15 205	91.83 229	95.09 213	99.11 149	91.37 160	97.47 285	93.47 232	97.43 174	99.74 107

MDTV_nov1_ep13			95.69 159		97.90 203	94.15 218	95.98 383	98.44 127	93.12 178	97.98 142	95.74 303	95.10 53	98.58 214	90.02 285	96.92 189

Fast-Effi-MVS+		95.02 188	94.19 200	97.52 174	97.88 204	94.55 205	99.97 28	97.08 313	88.85 301	94.47 220	97.96 237	84.59 248	98.41 226	89.84 288	97.10 182	99.59 137

ADS-MVSNet2		93.80 224	93.88 210	93.55 310	97.87 205	85.94 358	94.24 389	96.84 338	90.07 277	96.43 187	94.48 357	90.29 184	95.37 368	87.44 311	97.23 179	99.36 178

ADS-MVSNet		94.79 194	94.02 205	97.11 193	97.87 205	93.79 226	94.24 389	98.16 202	90.07 277	96.43 187	94.48 357	90.29 184	98.19 252	87.44 311	97.23 179	99.36 178

Effi-MVS+		96.30 154	95.69 159	98.16 132	97.85 207	96.26 143	97.41 355	97.21 297	90.37 271	98.65 115	98.58 205	86.61 229	98.70 208	97.11 158	97.37 178	99.52 157

PatchmatchNet		95.94 163	95.45 165	97.39 182	97.83 208	94.41 209	96.05 381	98.40 156	92.86 185	97.09 168	95.28 332	94.21 90	98.07 260	89.26 292	98.11 161	99.70 113
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 201	93.61 213	97.74 162	97.82 209	96.26 143	99.96 35	97.78 239	85.76 345	94.00 227	97.54 247	76.95 314	99.21 174	97.23 155	95.43 221	97.76 249

1112_ss		96.01 162	95.20 174	98.42 120	97.80 210	96.41 136	99.65 184	96.66 349	92.71 194	92.88 241	99.40 126	92.16 148	99.30 169	91.92 253	93.66 245	99.55 147

Test_1112_low_res		95.72 168	94.83 186	98.42 120	97.79 211	96.41 136	99.65 184	96.65 350	92.70 195	92.86 242	96.13 294	92.15 149	99.30 169	91.88 254	93.64 246	99.55 147

Effi-MVS+-dtu		94.53 205	95.30 171	92.22 333	97.77 212	82.54 377	99.59 195	97.06 315	94.92 105	95.29 211	95.37 325	85.81 235	97.89 270	94.80 200	97.07 183	96.23 266

tpm cat1		93.51 233	92.52 247	96.47 209	97.77 212	91.47 288	96.13 379	98.06 211	80.98 381	92.91 240	93.78 366	89.66 189	98.87 193	87.03 320	96.39 198	99.09 205

FA-MVS(test-final)		95.86 164	95.09 178	98.15 135	97.74 214	95.62 172	96.31 376	98.17 198	91.42 245	96.26 192	96.13 294	90.56 178	99.47 165	92.18 249	97.07 183	99.35 180

xiu_mvs_v1_base_debu		97.43 95	97.06 101	98.55 107	97.74 214	98.14 66	99.31 239	97.86 232	96.43 66	99.62 47	99.69 90	85.56 237	99.68 145	99.05 64	98.31 153	97.83 245

xiu_mvs_v1_base		97.43 95	97.06 101	98.55 107	97.74 214	98.14 66	99.31 239	97.86 232	96.43 66	99.62 47	99.69 90	85.56 237	99.68 145	99.05 64	98.31 153	97.83 245

xiu_mvs_v1_base_debi		97.43 95	97.06 101	98.55 107	97.74 214	98.14 66	99.31 239	97.86 232	96.43 66	99.62 47	99.69 90	85.56 237	99.68 145	99.05 64	98.31 153	97.83 245

EPP-MVSNet		96.69 137	96.60 124	96.96 196	97.74 214	93.05 246	99.37 232	98.56 93	88.75 303	95.83 203	99.01 157	96.01 34	98.56 215	96.92 167	97.20 181	99.25 193

gg-mvs-nofinetune		93.51 233	91.86 259	98.47 115	97.72 219	97.96 76	92.62 397	98.51 110	74.70 399	97.33 162	69.59 413	98.91 4	97.79 273	97.77 144	99.56 103	99.67 118

IB-MVS	92.85 6	94.99 189	93.94 208	98.16 132	97.72 219	95.69 169	99.99 4	98.81 61	94.28 134	92.70 243	96.90 267	95.08 54	99.17 180	96.07 177	73.88 381	99.60 136
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		97.41 100	97.02 106	98.59 104	97.71 221	97.52 91	99.97 28	98.54 102	91.83 229	97.45 158	99.04 154	97.50 8	99.10 185	94.75 202	96.37 199	99.16 198

Syy-MVS		90.00 312	90.63 278	88.11 372	97.68 222	74.66 399	99.71 173	98.35 169	90.79 262	92.10 249	98.67 194	79.10 299	93.09 392	63.35 406	95.95 208	96.59 262

myMVS_eth3d		94.46 208	94.76 188	93.55 310	97.68 222	90.97 292	99.71 173	98.35 169	90.79 262	92.10 249	98.67 194	92.46 142	93.09 392	87.13 317	95.95 208	96.59 262

test_fmvs1_n		94.25 216	94.36 195	93.92 297	97.68 222	83.70 371	99.90 91	96.57 353	97.40 28	99.67 39	98.88 177	61.82 389	99.92 91	98.23 116	99.13 130	98.14 241

RRT-MVS		96.24 158	95.68 161	97.94 147	97.65 225	94.92 197	99.27 247	97.10 309	92.79 191	97.43 159	97.99 235	81.85 267	99.37 168	98.46 106	98.57 146	99.53 155

diffmvs		97.00 119	96.64 122	98.09 138	97.64 226	96.17 151	99.81 137	97.19 298	94.67 115	98.95 97	99.28 134	86.43 230	98.76 201	98.37 111	97.42 176	99.33 183
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		95.72 168	95.15 176	97.45 177	97.62 227	94.28 214	99.28 245	98.24 189	94.27 136	96.84 176	98.94 173	79.39 294	98.76 201	93.25 234	98.49 148	99.30 187
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 112	96.72 119	98.22 130	97.60 228	96.70 124	99.92 79	98.54 102	91.11 253	97.07 170	98.97 164	97.47 11	99.03 186	93.73 229	96.09 203	98.92 214

miper_ehance_all_eth		93.16 241	92.60 241	94.82 260	97.57 229	93.56 234	99.50 212	97.07 314	88.75 303	88.85 301	95.52 314	90.97 169	96.74 329	90.77 272	84.45 314	94.17 301

testing3		93.92 219	94.23 199	92.99 324	97.54 230	90.23 311	99.99 4	99.16 30	90.57 267	91.33 257	98.63 200	92.99 124	92.52 396	82.46 352	95.39 222	96.22 267

LCM-MVSNet-Re		92.31 261	92.60 241	91.43 342	97.53 231	79.27 394	99.02 275	91.83 409	92.07 221	80.31 374	94.38 360	83.50 256	95.48 366	97.22 156	97.58 172	99.54 151

GBi-Net		90.88 289	89.82 295	94.08 289	97.53 231	91.97 269	98.43 325	96.95 327	87.05 328	89.68 278	94.72 348	71.34 351	96.11 353	87.01 321	85.65 303	94.17 301

test1		90.88 289	89.82 295	94.08 289	97.53 231	91.97 269	98.43 325	96.95 327	87.05 328	89.68 278	94.72 348	71.34 351	96.11 353	87.01 321	85.65 303	94.17 301

FMVSNet2		91.02 286	89.56 300	95.41 240	97.53 231	95.74 164	98.98 277	97.41 277	87.05 328	88.43 310	95.00 342	71.34 351	96.24 350	85.12 335	85.21 308	94.25 295

tttt0517		96.85 126	96.49 128	97.92 148	97.48 235	95.89 159	99.85 120	98.54 102	90.72 266	96.63 181	98.93 175	97.47 11	99.02 187	93.03 241	95.76 214	98.85 218

casdiffmvs_mvg		96.43 146	95.94 150	97.89 152	97.44 236	95.47 176	99.86 117	97.29 291	93.35 168	96.03 196	99.19 145	85.39 240	98.72 206	97.89 136	97.04 185	99.49 164
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		97.38 102	97.24 95	97.80 153	97.41 237	95.64 171	99.99 4	97.06 315	94.59 116	99.63 44	99.32 133	89.20 200	98.14 254	98.76 88	99.23 126	99.62 130

c3_l		92.53 256	91.87 258	94.52 272	97.40 238	92.99 248	99.40 225	96.93 332	87.86 318	88.69 304	95.44 319	89.95 187	96.44 341	90.45 278	80.69 347	94.14 310

fmvsm_s_conf0.1_n		97.30 103	97.21 97	97.60 170	97.38 239	94.40 211	99.90 91	98.64 77	96.47 65	99.51 62	99.65 101	84.99 245	99.93 88	99.22 58	99.09 132	98.46 232

CDS-MVSNet		96.34 151	96.07 139	97.13 191	97.37 240	94.96 195	99.53 207	97.91 227	91.55 237	95.37 210	98.32 223	95.05 56	97.13 303	93.80 225	95.75 215	99.30 187
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 134	96.26 134	98.16 132	97.36 241	96.48 133	99.96 35	98.29 182	91.93 226	95.77 204	98.07 231	95.54 44	98.29 243	90.55 276	98.89 137	99.70 113

miper_lstm_enhance		91.81 269	91.39 268	93.06 323	97.34 242	89.18 328	99.38 230	96.79 343	86.70 335	87.47 324	95.22 334	90.00 186	95.86 362	88.26 302	81.37 336	94.15 307

baseline		96.43 146	95.98 144	97.76 160	97.34 242	95.17 192	99.51 210	97.17 301	93.92 152	96.90 174	99.28 134	85.37 241	98.64 212	97.50 150	96.86 191	99.46 166

cl____		92.31 261	91.58 262	94.52 272	97.33 244	92.77 250	99.57 200	96.78 344	86.97 332	87.56 322	95.51 315	89.43 193	96.62 334	88.60 297	82.44 328	94.16 306

DIV-MVS_self_test		92.32 260	91.60 261	94.47 276	97.31 245	92.74 252	99.58 197	96.75 345	86.99 331	87.64 320	95.54 312	89.55 192	96.50 338	88.58 298	82.44 328	94.17 301

casdiffmvs		96.42 148	95.97 147	97.77 158	97.30 246	94.98 194	99.84 125	97.09 312	93.75 159	96.58 183	99.26 140	85.07 243	98.78 199	97.77 144	97.04 185	99.54 151
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		94.36 213	93.48 220	96.99 195	97.29 247	93.54 235	99.96 35	96.72 347	88.35 312	93.43 231	98.94 173	82.05 264	98.05 261	88.12 306	96.48 197	99.37 177

eth_miper_zixun_eth		92.41 259	91.93 256	93.84 301	97.28 248	90.68 301	98.83 297	96.97 326	88.57 308	89.19 296	95.73 305	89.24 199	96.69 332	89.97 287	81.55 334	94.15 307

MVSFormer		96.94 122	96.60 124	97.95 144	97.28 248	97.70 85	99.55 204	97.27 293	91.17 250	99.43 68	99.54 113	90.92 170	96.89 321	94.67 205	99.62 95	99.25 193

lupinMVS		97.85 73	97.60 81	98.62 100	97.28 248	97.70 85	99.99 4	97.55 260	95.50 93	99.43 68	99.67 97	90.92 170	98.71 207	98.40 108	99.62 95	99.45 168

SCA		94.69 198	93.81 212	97.33 187	97.10 251	94.44 206	98.86 294	98.32 176	93.30 171	96.17 195	95.59 310	76.48 320	97.95 267	91.06 264	97.43 174	99.59 137

TAMVS		95.85 165	95.58 163	96.65 207	97.07 252	93.50 236	99.17 255	97.82 236	91.39 247	95.02 214	98.01 232	92.20 147	97.30 293	93.75 228	95.83 212	99.14 201

Fast-Effi-MVS+-dtu		93.72 228	93.86 211	93.29 315	97.06 253	86.16 356	99.80 141	96.83 339	92.66 198	92.58 244	97.83 243	81.39 272	97.67 278	89.75 289	96.87 190	96.05 269

CostFormer		96.10 159	95.88 154	96.78 201	97.03 254	92.55 260	97.08 363	97.83 235	90.04 279	98.72 111	94.89 346	95.01 58	98.29 243	96.54 172	95.77 213	99.50 162

test_fmvsmvis_n_1920		97.67 89	97.59 83	97.91 150	97.02 255	95.34 182	99.95 53	98.45 122	97.87 15	97.02 171	99.59 107	89.64 190	99.98 47	99.41 51	99.34 121	98.42 234

test-LLR		96.47 144	96.04 140	97.78 156	97.02 255	95.44 177	99.96 35	98.21 193	94.07 142	95.55 206	96.38 284	93.90 99	98.27 247	90.42 279	98.83 141	99.64 124

test-mter		96.39 149	95.93 151	97.78 156	97.02 255	95.44 177	99.96 35	98.21 193	91.81 231	95.55 206	96.38 284	95.17 51	98.27 247	90.42 279	98.83 141	99.64 124

gm-plane-assit					96.97 258	93.76 228			91.47 241		98.96 166		98.79 198	94.92 195

WB-MVSnew		92.90 247	92.77 238	93.26 317	96.95 259	93.63 232	99.71 173	98.16 202	91.49 238	94.28 223	98.14 228	81.33 274	96.48 339	79.47 367	95.46 219	89.68 393

QAPM		95.40 179	94.17 201	99.10 67	96.92 260	97.71 83	99.40 225	98.68 71	89.31 287	88.94 300	98.89 176	82.48 262	99.96 65	93.12 240	99.83 77	99.62 130

KD-MVS_2432*1600		88.00 333	86.10 337	93.70 306	96.91 261	94.04 220	97.17 360	97.12 307	84.93 355	81.96 365	92.41 377	92.48 140	94.51 380	79.23 368	52.68 412	92.56 363

miper_refine_blended		88.00 333	86.10 337	93.70 306	96.91 261	94.04 220	97.17 360	97.12 307	84.93 355	81.96 365	92.41 377	92.48 140	94.51 380	79.23 368	52.68 412	92.56 363

tpm2		95.47 177	95.18 175	96.35 216	96.91 261	91.70 282	96.96 366	97.93 223	88.04 316	98.44 124	95.40 321	93.32 113	97.97 264	94.00 217	95.61 217	99.38 175

FMVSNet5		88.32 329	87.47 331	90.88 345	96.90 264	88.39 340	97.28 357	95.68 373	82.60 375	84.67 353	92.40 379	79.83 291	91.16 401	76.39 383	81.51 335	93.09 355

3Dnovator+	91.53 11	96.31 153	95.24 172	99.52 28	96.88 265	98.64 54	99.72 170	98.24 189	95.27 98	88.42 312	98.98 162	82.76 261	99.94 81	97.10 159	99.83 77	99.96 67

Patchmatch-test		92.65 255	91.50 265	96.10 222	96.85 266	90.49 306	91.50 402	97.19 298	82.76 374	90.23 266	95.59 310	95.02 57	98.00 263	77.41 378	96.98 188	99.82 95

MVS		96.60 140	95.56 164	99.72 13	96.85 266	99.22 20	98.31 331	98.94 41	91.57 236	90.90 261	99.61 106	86.66 228	99.96 65	97.36 152	99.88 73	99.99 23

3Dnovator	91.47 12	96.28 156	95.34 169	99.08 70	96.82 268	97.47 96	99.45 222	98.81 61	95.52 92	89.39 287	99.00 159	81.97 265	99.95 73	97.27 154	99.83 77	99.84 93

EI-MVSNet		93.73 227	93.40 225	94.74 261	96.80 269	92.69 255	99.06 266	97.67 245	88.96 296	91.39 255	99.02 155	88.75 205	97.30 293	91.07 263	87.85 289	94.22 297

CVMVSNet		94.68 200	94.94 184	93.89 300	96.80 269	86.92 353	99.06 266	98.98 38	94.45 120	94.23 225	99.02 155	85.60 236	95.31 370	90.91 269	95.39 222	99.43 171

IterMVS-LS		92.69 253	92.11 252	94.43 280	96.80 269	92.74 252	99.45 222	96.89 335	88.98 294	89.65 281	95.38 324	88.77 204	96.34 345	90.98 267	82.04 331	94.22 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS		90.91 288	90.17 290	93.12 320	96.78 272	90.42 309	98.89 288	97.05 318	89.03 291	86.49 337	95.42 320	76.59 318	95.02 372	87.22 316	84.09 317	93.93 327
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 127	95.96 148	99.48 34	96.74 273	98.52 58	98.31 331	98.86 53	95.82 82	89.91 272	98.98 162	87.49 216	99.96 65	97.80 139	99.73 87	99.96 67

IterMVS-SCA-FT		90.85 291	90.16 291	92.93 325	96.72 274	89.96 317	98.89 288	96.99 322	88.95 297	86.63 334	95.67 306	76.48 320	95.00 373	87.04 319	84.04 320	93.84 334

MVS-HIRNet		86.22 340	83.19 353	95.31 244	96.71 275	90.29 310	92.12 399	97.33 285	62.85 407	86.82 331	70.37 412	69.37 359	97.49 284	75.12 386	97.99 166	98.15 239

VDDNet		93.12 242	91.91 257	96.76 202	96.67 276	92.65 258	98.69 310	98.21 193	82.81 373	97.75 152	99.28 134	61.57 390	99.48 164	98.09 124	94.09 240	98.15 239

dmvs_re		93.20 239	93.15 230	93.34 313	96.54 277	83.81 370	98.71 307	98.51 110	91.39 247	92.37 247	98.56 207	78.66 303	97.83 272	93.89 219	89.74 261	98.38 235

MIMVSNet		90.30 304	88.67 318	95.17 248	96.45 278	91.64 284	92.39 398	97.15 304	85.99 342	90.50 264	93.19 373	66.95 370	94.86 377	82.01 356	93.43 248	99.01 212

CR-MVSNet		93.45 236	92.62 240	95.94 226	96.29 279	92.66 256	92.01 400	96.23 361	92.62 200	96.94 172	93.31 371	91.04 167	96.03 358	79.23 368	95.96 206	99.13 202

RPMNet		89.76 316	87.28 332	97.19 190	96.29 279	92.66 256	92.01 400	98.31 178	70.19 406	96.94 172	85.87 405	87.25 220	99.78 128	62.69 407	95.96 206	99.13 202

tt0805		91.28 281	90.18 289	94.60 267	96.26 281	87.55 346	98.39 329	98.72 66	89.00 293	89.22 293	98.47 215	62.98 385	98.96 190	90.57 275	88.00 288	97.28 256

Patchmtry		89.70 317	88.49 320	93.33 314	96.24 282	89.94 320	91.37 403	96.23 361	78.22 389	87.69 319	93.31 371	91.04 167	96.03 358	80.18 366	82.10 330	94.02 317

test_vis1_rt		86.87 338	86.05 340	89.34 361	96.12 283	78.07 395	99.87 106	83.54 420	92.03 224	78.21 384	89.51 391	45.80 406	99.91 92	96.25 175	93.11 253	90.03 390

JIA-IIPM		91.76 275	90.70 276	94.94 254	96.11 284	87.51 347	93.16 396	98.13 207	75.79 395	97.58 154	77.68 410	92.84 129	97.97 264	88.47 301	96.54 193	99.33 183

OpenMVS	90.15 15	94.77 196	93.59 216	98.33 124	96.07 285	97.48 95	99.56 202	98.57 90	90.46 269	86.51 336	98.95 171	78.57 304	99.94 81	93.86 220	99.74 86	97.57 254

PAPM		98.60 33	98.42 34	99.14 61	96.05 286	98.96 26	99.90 91	99.35 24	96.68 58	98.35 130	99.66 99	96.45 31	98.51 218	99.45 48	99.89 70	99.96 67

CLD-MVS		94.06 218	93.90 209	94.55 271	96.02 287	90.69 300	99.98 15	97.72 241	96.62 62	91.05 260	98.85 185	77.21 309	98.47 219	98.11 122	89.51 267	94.48 276
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 301	88.75 317	95.25 246	95.99 288	90.16 313	91.22 404	97.54 262	76.80 391	97.26 164	86.01 404	91.88 154	96.07 357	66.16 403	95.91 210	99.51 160

ACMH+	89.98 16	90.35 302	89.54 301	92.78 329	95.99 288	86.12 357	98.81 299	97.18 300	89.38 286	83.14 361	97.76 244	68.42 364	98.43 224	89.11 293	86.05 301	93.78 337

DeepMVS_CX				82.92 382	95.98 290	58.66 413		96.01 366	92.72 193	78.34 383	95.51 315	58.29 395	98.08 258	82.57 351	85.29 306	92.03 371

ACMP	92.05 9	92.74 251	92.42 249	93.73 302	95.91 291	88.72 333	99.81 137	97.53 264	94.13 138	87.00 330	98.23 226	74.07 341	98.47 219	96.22 176	88.86 274	93.99 322
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 231	93.03 232	95.35 241	95.86 292	86.94 352	99.87 106	96.36 359	96.85 49	99.54 57	98.79 187	52.41 402	99.83 121	98.64 96	98.97 136	99.29 189

HQP-NCC					95.78 293		99.87 106		96.82 51	93.37 232

ACMP_Plane					95.78 293		99.87 106		96.82 51	93.37 232

HQP-MVS		94.61 202	94.50 192	94.92 255	95.78 293	91.85 274	99.87 106	97.89 228	96.82 51	93.37 232	98.65 197	80.65 283	98.39 230	97.92 133	89.60 262	94.53 272

NP-MVS					95.77 296	91.79 276					98.65 197

test_fmvsmconf0.1_n		97.74 85	97.44 87	98.64 99	95.76 297	96.20 148	99.94 69	98.05 213	98.17 9	98.89 101	99.42 121	87.65 214	99.90 94	99.50 44	99.60 101	99.82 95

plane_prior6					95.76 297	91.72 281						80.47 287

ACMM	91.95 10	92.88 248	92.52 247	93.98 296	95.75 299	89.08 330	99.77 147	97.52 266	93.00 180	89.95 271	97.99 235	76.17 324	98.46 222	93.63 231	88.87 273	94.39 284
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 221	92.84 234	96.80 200	95.73 300	93.57 233	99.88 103	97.24 296	92.57 205	92.92 239	96.66 276	78.73 302	97.67 278	87.75 309	94.06 241	99.17 197

plane_prior1					95.73 300

jason		97.24 106	96.86 112	98.38 123	95.73 300	97.32 100	99.97 28	97.40 278	95.34 96	98.60 118	99.54 113	87.70 213	98.56 215	97.94 132	99.47 110	99.25 193
jason: jason.
mmtdpeth		88.52 327	87.75 329	90.85 347	95.71 303	83.47 373	98.94 282	94.85 387	88.78 302	97.19 166	89.58 390	63.29 383	98.97 188	98.54 101	62.86 406	90.10 389

HQP_MVS		94.49 207	94.36 195	94.87 256	95.71 303	91.74 278	99.84 125	97.87 230	96.38 69	93.01 237	98.59 202	80.47 287	98.37 236	97.79 142	89.55 265	94.52 274

plane_prior7					95.71 303	91.59 286

ITE_SJBPF				92.38 331	95.69 306	85.14 362		95.71 372	92.81 188	89.33 290	98.11 229	70.23 357	98.42 225	85.91 331	88.16 286	93.59 345

fmvsm_s_conf0.1_n_a		97.09 114	96.90 109	97.63 168	95.65 307	94.21 217	99.83 132	98.50 116	96.27 74	99.65 41	99.64 102	84.72 246	99.93 88	99.04 67	98.84 140	98.74 225

ACMH	89.72 17	90.64 295	89.63 298	93.66 308	95.64 308	88.64 336	98.55 317	97.45 271	89.03 291	81.62 368	97.61 245	69.75 358	98.41 226	89.37 290	87.62 293	93.92 328
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 136	96.49 128	97.37 183	95.63 309	95.96 157	99.74 159	98.88 51	92.94 182	91.61 253	98.97 164	97.72 6	98.62 213	94.83 199	98.08 164	97.53 255

FMVSNet1		88.50 328	86.64 335	94.08 289	95.62 310	91.97 269	98.43 325	96.95 327	83.00 371	86.08 344	94.72 348	59.09 394	96.11 353	81.82 358	84.07 318	94.17 301

LPG-MVS_test		92.96 245	92.71 239	93.71 304	95.43 311	88.67 334	99.75 156	97.62 251	92.81 188	90.05 267	98.49 211	75.24 331	98.40 228	95.84 182	89.12 269	94.07 314

LGP-MVS_train				93.71 304	95.43 311	88.67 334		97.62 251	92.81 188	90.05 267	98.49 211	75.24 331	98.40 228	95.84 182	89.12 269	94.07 314

tpm		93.70 229	93.41 224	94.58 269	95.36 313	87.41 348	97.01 364	96.90 334	90.85 260	96.72 180	94.14 363	90.40 181	96.84 324	90.75 273	88.54 281	99.51 160

D2MVS		92.76 250	92.59 245	93.27 316	95.13 314	89.54 324	99.69 178	99.38 22	92.26 217	87.59 321	94.61 354	85.05 244	97.79 273	91.59 257	88.01 287	92.47 366

VPA-MVSNet		92.70 252	91.55 264	96.16 220	95.09 315	96.20 148	98.88 290	99.00 36	91.02 257	91.82 252	95.29 331	76.05 326	97.96 266	95.62 186	81.19 337	94.30 291

LTVRE_ROB	88.28 18	90.29 305	89.05 312	94.02 292	95.08 316	90.15 314	97.19 359	97.43 273	84.91 357	83.99 357	97.06 262	74.00 342	98.28 245	84.08 340	87.71 291	93.62 344
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		87.87 335	86.51 336	91.94 336	95.05 317	85.57 360	97.65 352	94.08 396	84.40 361	81.82 367	96.85 271	62.14 388	98.33 239	80.25 365	86.37 300	91.91 373

test0.0.03 1		93.86 220	93.61 213	94.64 265	95.02 318	92.18 267	99.93 76	98.58 88	94.07 142	87.96 316	98.50 210	93.90 99	94.96 374	81.33 359	93.17 251	96.78 259

UniMVSNet (Re)		93.07 244	92.13 251	95.88 227	94.84 319	96.24 147	99.88 103	98.98 38	92.49 210	89.25 291	95.40 321	87.09 222	97.14 302	93.13 239	78.16 361	94.26 293

USDC		90.00 312	88.96 313	93.10 322	94.81 320	88.16 342	98.71 307	95.54 377	93.66 161	83.75 359	97.20 256	65.58 375	98.31 241	83.96 343	87.49 295	92.85 360

VPNet		91.81 269	90.46 280	95.85 229	94.74 321	95.54 175	98.98 277	98.59 87	92.14 219	90.77 263	97.44 249	68.73 362	97.54 283	94.89 198	77.89 363	94.46 277

FIs		94.10 217	93.43 221	96.11 221	94.70 322	96.82 121	99.58 197	98.93 45	92.54 206	89.34 289	97.31 253	87.62 215	97.10 306	94.22 216	86.58 298	94.40 283

UniMVSNet_ETH3D		90.06 311	88.58 319	94.49 275	94.67 323	88.09 343	97.81 351	97.57 259	83.91 364	88.44 308	97.41 250	57.44 396	97.62 280	91.41 258	88.59 280	97.77 248

UniMVSNet_NR-MVSNet		92.95 246	92.11 252	95.49 235	94.61 324	95.28 185	99.83 132	99.08 33	91.49 238	89.21 294	96.86 270	87.14 221	96.73 330	93.20 235	77.52 366	94.46 277

test_fmvs2		89.47 320	89.70 297	88.77 368	94.54 325	75.74 396	99.83 132	94.70 392	94.71 112	91.08 258	96.82 275	54.46 399	97.78 275	92.87 242	88.27 284	92.80 361

MonoMVSNet		94.82 191	94.43 193	95.98 224	94.54 325	90.73 299	99.03 273	97.06 315	93.16 176	93.15 236	95.47 318	88.29 208	97.57 281	97.85 137	91.33 259	99.62 130

WR-MVS		92.31 261	91.25 269	95.48 238	94.45 327	95.29 184	99.60 194	98.68 71	90.10 276	88.07 315	96.89 268	80.68 282	96.80 328	93.14 238	79.67 354	94.36 285

nrg030		93.51 233	92.53 246	96.45 211	94.36 328	97.20 105	99.81 137	97.16 303	91.60 235	89.86 274	97.46 248	86.37 231	97.68 277	95.88 181	80.31 350	94.46 277

tfpnnormal		89.29 323	87.61 330	94.34 283	94.35 329	94.13 219	98.95 281	98.94 41	83.94 362	84.47 354	95.51 315	74.84 336	97.39 286	77.05 381	80.41 348	91.48 376

FC-MVSNet-test		93.81 223	93.15 230	95.80 231	94.30 330	96.20 148	99.42 224	98.89 49	92.33 216	89.03 299	97.27 255	87.39 218	96.83 326	93.20 235	86.48 299	94.36 285

MS-PatchMatch		90.65 294	90.30 285	91.71 341	94.22 331	85.50 361	98.24 335	97.70 242	88.67 305	86.42 339	96.37 286	67.82 367	98.03 262	83.62 345	99.62 95	91.60 374

WR-MVS_H		91.30 279	90.35 283	94.15 286	94.17 332	92.62 259	99.17 255	98.94 41	88.87 300	86.48 338	94.46 359	84.36 250	96.61 335	88.19 303	78.51 359	93.21 354

DU-MVS		92.46 258	91.45 267	95.49 235	94.05 333	95.28 185	99.81 137	98.74 65	92.25 218	89.21 294	96.64 278	81.66 269	96.73 330	93.20 235	77.52 366	94.46 277

NR-MVSNet		91.56 277	90.22 287	95.60 233	94.05 333	95.76 163	98.25 334	98.70 68	91.16 252	80.78 373	96.64 278	83.23 259	96.57 336	91.41 258	77.73 365	94.46 277

CP-MVSNet		91.23 283	90.22 287	94.26 284	93.96 335	92.39 263	99.09 259	98.57 90	88.95 297	86.42 339	96.57 281	79.19 297	96.37 343	90.29 282	78.95 356	94.02 317

XXY-MVS		91.82 268	90.46 280	95.88 227	93.91 336	95.40 181	98.87 293	97.69 244	88.63 307	87.87 317	97.08 260	74.38 340	97.89 270	91.66 256	84.07 318	94.35 288

PS-CasMVS		90.63 296	89.51 303	93.99 295	93.83 337	91.70 282	98.98 277	98.52 107	88.48 309	86.15 343	96.53 283	75.46 329	96.31 347	88.83 295	78.86 358	93.95 325

test_0402		85.58 342	83.94 347	90.50 351	93.81 338	85.04 363	98.55 317	95.20 384	76.01 393	79.72 378	95.13 335	64.15 381	96.26 349	66.04 404	86.88 297	90.21 387

XVG-ACMP-BASELINE		91.22 284	90.75 275	92.63 330	93.73 339	85.61 359	98.52 321	97.44 272	92.77 192	89.90 273	96.85 271	66.64 372	98.39 230	92.29 247	88.61 278	93.89 330

TranMVSNet+NR-MVSNet		91.68 276	90.61 279	94.87 256	93.69 340	93.98 223	99.69 178	98.65 75	91.03 256	88.44 308	96.83 274	80.05 290	96.18 351	90.26 283	76.89 374	94.45 282

TransMVSNet (Re)		87.25 336	85.28 343	93.16 319	93.56 341	91.03 291	98.54 319	94.05 398	83.69 366	81.09 371	96.16 292	75.32 330	96.40 342	76.69 382	68.41 394	92.06 370

v10		90.25 306	88.82 315	94.57 270	93.53 342	93.43 238	99.08 261	96.87 337	85.00 354	87.34 328	94.51 355	80.93 279	97.02 316	82.85 350	79.23 355	93.26 352

testgi		89.01 325	88.04 326	91.90 337	93.49 343	84.89 365	99.73 166	95.66 374	93.89 156	85.14 349	98.17 227	59.68 393	94.66 379	77.73 377	88.88 272	96.16 268

v8		90.54 298	89.17 308	94.66 264	93.43 344	93.40 240	99.20 252	96.94 331	85.76 345	87.56 322	94.51 355	81.96 266	97.19 299	84.94 337	78.25 360	93.38 350

V42		91.28 281	90.12 292	94.74 261	93.42 345	93.46 237	99.68 180	97.02 319	87.36 324	89.85 276	95.05 338	81.31 275	97.34 289	87.34 314	80.07 352	93.40 348

pm-mvs1		89.36 322	87.81 328	94.01 293	93.40 346	91.93 272	98.62 315	96.48 357	86.25 340	83.86 358	96.14 293	73.68 343	97.04 312	86.16 328	75.73 379	93.04 357

v1144		91.09 285	89.83 294	94.87 256	93.25 347	93.69 231	99.62 191	96.98 324	86.83 334	89.64 282	94.99 343	80.94 278	97.05 309	85.08 336	81.16 338	93.87 332

v1192		90.62 297	89.25 307	94.72 263	93.13 348	93.07 244	99.50 212	97.02 319	86.33 339	89.56 285	95.01 340	79.22 296	97.09 308	82.34 354	81.16 338	94.01 319

v2v482		91.30 279	90.07 293	95.01 251	93.13 348	93.79 226	99.77 147	97.02 319	88.05 315	89.25 291	95.37 325	80.73 281	97.15 301	87.28 315	80.04 353	94.09 313

OPM-MVS		93.21 238	92.80 236	94.44 278	93.12 350	90.85 298	99.77 147	97.61 254	96.19 77	91.56 254	98.65 197	75.16 335	98.47 219	93.78 227	89.39 268	93.99 322
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 292	89.52 302	94.59 268	93.11 351	92.77 250	99.56 202	96.99 322	86.38 338	89.82 277	94.95 345	80.50 286	97.10 306	83.98 342	80.41 348	93.90 329

PEN-MVS		90.19 308	89.06 311	93.57 309	93.06 352	90.90 296	99.06 266	98.47 119	88.11 314	85.91 345	96.30 288	76.67 316	95.94 361	87.07 318	76.91 373	93.89 330

v1240		90.20 307	88.79 316	94.44 278	93.05 353	92.27 265	99.38 230	96.92 333	85.89 343	89.36 288	94.87 347	77.89 308	97.03 314	80.66 362	81.08 341	94.01 319

v148		90.70 293	89.63 298	93.92 297	92.97 354	90.97 292	99.75 156	96.89 335	87.51 321	88.27 313	95.01 340	81.67 268	97.04 312	87.40 313	77.17 371	93.75 338

v1921920		90.46 299	89.12 309	94.50 274	92.96 355	92.46 261	99.49 214	96.98 324	86.10 341	89.61 284	95.30 328	78.55 305	97.03 314	82.17 355	80.89 346	94.01 319

MVStest1		85.03 348	82.76 357	91.83 338	92.95 356	89.16 329	98.57 316	94.82 388	71.68 404	68.54 404	95.11 337	83.17 260	95.66 364	74.69 387	65.32 401	90.65 383

Baseline_NR-MVSNet		90.33 303	89.51 303	92.81 328	92.84 357	89.95 318	99.77 147	93.94 399	84.69 359	89.04 298	95.66 307	81.66 269	96.52 337	90.99 266	76.98 372	91.97 372

test_method		80.79 364	79.70 368	84.08 379	92.83 358	67.06 405	99.51 210	95.42 378	54.34 411	81.07 372	93.53 368	44.48 407	92.22 398	78.90 372	77.23 370	92.94 358

pmmvs4		92.10 265	91.07 273	95.18 247	92.82 359	94.96 195	99.48 216	96.83 339	87.45 323	88.66 305	96.56 282	83.78 254	96.83 326	89.29 291	84.77 312	93.75 338

LF4IMVS		89.25 324	88.85 314	90.45 353	92.81 360	81.19 387	98.12 341	94.79 389	91.44 242	86.29 341	97.11 258	65.30 378	98.11 256	88.53 300	85.25 307	92.07 369

DTE-MVSNet		89.40 321	88.24 324	92.88 326	92.66 361	89.95 318	99.10 258	98.22 192	87.29 325	85.12 350	96.22 290	76.27 323	95.30 371	83.56 346	75.74 378	93.41 347

EU-MVSNet		90.14 310	90.34 284	89.54 360	92.55 362	81.06 388	98.69 310	98.04 214	91.41 246	86.59 335	96.84 273	80.83 280	93.31 391	86.20 327	81.91 332	94.26 293

APD_test1		81.15 363	80.92 364	81.86 383	92.45 363	59.76 412	96.04 382	93.61 402	73.29 402	77.06 387	96.64 278	44.28 408	96.16 352	72.35 391	82.52 326	89.67 394

our_test_3		90.39 300	89.48 305	93.12 320	92.40 364	89.57 323	99.33 236	96.35 360	87.84 319	85.30 348	94.99 343	84.14 252	96.09 356	80.38 363	84.56 313	93.71 343

ppachtmachnet_test		89.58 319	88.35 322	93.25 318	92.40 364	90.44 308	99.33 236	96.73 346	85.49 350	85.90 346	95.77 302	81.09 277	96.00 360	76.00 385	82.49 327	93.30 351

v7n		89.65 318	88.29 323	93.72 303	92.22 366	90.56 305	99.07 265	97.10 309	85.42 352	86.73 332	94.72 348	80.06 289	97.13 303	81.14 360	78.12 362	93.49 346

dmvs_testset		83.79 357	86.07 339	76.94 387	92.14 367	48.60 422	96.75 369	90.27 412	89.48 285	78.65 381	98.55 209	79.25 295	86.65 410	66.85 401	82.69 325	95.57 270

PS-MVSNAJss		93.64 230	93.31 227	94.61 266	92.11 368	92.19 266	99.12 257	97.38 279	92.51 209	88.45 307	96.99 266	91.20 162	97.29 296	94.36 210	87.71 291	94.36 285

pmmvs5		90.17 309	89.09 310	93.40 312	92.10 369	89.77 321	99.74 159	95.58 376	85.88 344	87.24 329	95.74 303	73.41 344	96.48 339	88.54 299	83.56 322	93.95 325

N_pmnet		80.06 367	80.78 365	77.89 386	91.94 370	45.28 424	98.80 301	56.82 426	78.10 390	80.08 376	93.33 369	77.03 311	95.76 363	68.14 399	82.81 324	92.64 362

test_djsdf		92.83 249	92.29 250	94.47 276	91.90 371	92.46 261	99.55 204	97.27 293	91.17 250	89.96 270	96.07 297	81.10 276	96.89 321	94.67 205	88.91 271	94.05 316

SixPastTwentyTwo		88.73 326	88.01 327	90.88 345	91.85 372	82.24 379	98.22 338	95.18 385	88.97 295	82.26 364	96.89 268	71.75 349	96.67 333	84.00 341	82.98 323	93.72 342

K. test v3		88.05 332	87.24 333	90.47 352	91.82 373	82.23 380	98.96 280	97.42 275	89.05 290	76.93 389	95.60 309	68.49 363	95.42 367	85.87 332	81.01 344	93.75 338

OurMVSNet-221017-0		89.81 315	89.48 305	90.83 348	91.64 374	81.21 386	98.17 340	95.38 380	91.48 240	85.65 347	97.31 253	72.66 345	97.29 296	88.15 304	84.83 311	93.97 324

mvs_tets		91.81 269	91.08 272	94.00 294	91.63 375	90.58 304	98.67 312	97.43 273	92.43 211	87.37 327	97.05 263	71.76 348	97.32 291	94.75 202	88.68 277	94.11 312

Gipuma		66.95 380	65.00 380	72.79 392	91.52 376	67.96 404	66.16 415	95.15 386	47.89 413	58.54 410	67.99 415	29.74 412	87.54 409	50.20 414	77.83 364	62.87 415
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 149	95.74 157	98.32 125	91.47 377	95.56 174	99.84 125	97.30 288	97.74 18	97.89 146	99.35 132	79.62 292	99.85 111	99.25 57	99.24 125	99.55 147

jajsoiax		91.92 267	91.18 270	94.15 286	91.35 378	90.95 295	99.00 276	97.42 275	92.61 201	87.38 326	97.08 260	72.46 346	97.36 287	94.53 208	88.77 275	94.13 311

MDA-MVSNet-bldmvs		84.09 355	81.52 362	91.81 339	91.32 379	88.00 345	98.67 312	95.92 368	80.22 384	55.60 413	93.32 370	68.29 365	93.60 389	73.76 388	76.61 375	93.82 336

MVP-Stereo		90.93 287	90.45 282	92.37 332	91.25 380	88.76 331	98.05 345	96.17 363	87.27 326	84.04 355	95.30 328	78.46 306	97.27 298	83.78 344	99.70 89	91.09 377
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 344	83.32 352	92.10 334	90.96 381	88.58 337	99.20 252	96.52 355	79.70 386	57.12 412	92.69 375	79.11 298	93.86 386	77.10 380	77.46 368	93.86 333

YYNet1		85.50 345	83.33 351	92.00 335	90.89 382	88.38 341	99.22 251	96.55 354	79.60 387	57.26 411	92.72 374	79.09 300	93.78 387	77.25 379	77.37 369	93.84 334

anonymousdsp		91.79 274	90.92 274	94.41 281	90.76 383	92.93 249	98.93 284	97.17 301	89.08 289	87.46 325	95.30 328	78.43 307	96.92 319	92.38 246	88.73 276	93.39 349

lessismore_v0				90.53 350	90.58 384	80.90 389		95.80 369		77.01 388	95.84 300	66.15 374	96.95 317	83.03 349	75.05 380	93.74 341

EG-PatchMatch MVS		85.35 346	83.81 349	89.99 358	90.39 385	81.89 382	98.21 339	96.09 365	81.78 378	74.73 395	93.72 367	51.56 404	97.12 305	79.16 371	88.61 278	90.96 380

EGC-MVSNET		69.38 373	63.76 383	86.26 376	90.32 386	81.66 385	96.24 378	93.85 400	0.99 423	3.22 424	92.33 380	52.44 401	92.92 394	59.53 410	84.90 310	84.21 404

CMPMVS	61.59 21	84.75 351	85.14 344	83.57 380	90.32 386	62.54 408	96.98 365	97.59 258	74.33 400	69.95 401	96.66 276	64.17 380	98.32 240	87.88 308	88.41 283	89.84 392
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 354	82.92 355	89.21 362	90.03 388	82.60 376	96.89 368	95.62 375	80.59 382	75.77 394	89.17 392	65.04 379	94.79 378	72.12 392	81.02 343	90.23 386

pmmvs6		85.69 341	83.84 348	91.26 344	90.00 389	84.41 368	97.82 350	96.15 364	75.86 394	81.29 370	95.39 323	61.21 391	96.87 323	83.52 347	73.29 382	92.50 365

ttmdpeth		88.23 331	87.06 334	91.75 340	89.91 390	87.35 349	98.92 287	95.73 371	87.92 317	84.02 356	96.31 287	68.23 366	96.84 324	86.33 326	76.12 376	91.06 378

DSMNet-mixed		88.28 330	88.24 324	88.42 370	89.64 391	75.38 398	98.06 344	89.86 413	85.59 349	88.20 314	92.14 381	76.15 325	91.95 399	78.46 374	96.05 204	97.92 244

UnsupCasMVSNet_eth		85.52 343	83.99 345	90.10 356	89.36 392	83.51 372	96.65 370	97.99 216	89.14 288	75.89 393	93.83 365	63.25 384	93.92 384	81.92 357	67.90 397	92.88 359

Anonymous20231206		86.32 339	85.42 342	89.02 364	89.11 393	80.53 392	99.05 270	95.28 381	85.43 351	82.82 362	93.92 364	74.40 339	93.44 390	66.99 400	81.83 333	93.08 356

Anonymous20240521		85.15 347	83.81 349	89.16 363	88.32 394	82.69 375	98.80 301	95.74 370	79.72 385	81.53 369	90.99 384	65.38 377	94.16 382	72.69 390	81.11 340	90.63 384

OpenMVS_ROB	79.82 20	83.77 358	81.68 361	90.03 357	88.30 395	82.82 374	98.46 322	95.22 383	73.92 401	76.00 392	91.29 383	55.00 398	96.94 318	68.40 398	88.51 282	90.34 385

test20.03		84.72 352	83.99 345	86.91 374	88.19 396	80.62 391	98.88 290	95.94 367	88.36 311	78.87 379	94.62 353	68.75 361	89.11 405	66.52 402	75.82 377	91.00 379

KD-MVS_self_test		83.59 359	82.06 359	88.20 371	86.93 397	80.70 390	97.21 358	96.38 358	82.87 372	82.49 363	88.97 393	67.63 368	92.32 397	73.75 389	62.30 408	91.58 375

MIMVSNet1		82.58 360	80.51 366	88.78 366	86.68 398	84.20 369	96.65 370	95.41 379	78.75 388	78.59 382	92.44 376	51.88 403	89.76 404	65.26 405	78.95 356	92.38 368

CL-MVSNet_self_test		84.50 353	83.15 354	88.53 369	86.00 399	81.79 383	98.82 298	97.35 281	85.12 353	83.62 360	90.91 386	76.66 317	91.40 400	69.53 396	60.36 409	92.40 367

UnsupCasMVSNet_bld		79.97 369	77.03 374	88.78 366	85.62 400	81.98 381	93.66 394	97.35 281	75.51 397	70.79 400	83.05 407	48.70 405	94.91 376	78.31 375	60.29 410	89.46 397

mvs5depth		84.87 349	82.90 356	90.77 349	85.59 401	84.84 366	91.10 405	93.29 404	83.14 369	85.07 351	94.33 361	62.17 387	97.32 291	78.83 373	72.59 385	90.14 388

Patchmatch-RL test		86.90 337	85.98 341	89.67 359	84.45 402	75.59 397	89.71 408	92.43 406	86.89 333	77.83 386	90.94 385	94.22 88	93.63 388	87.75 309	69.61 389	99.79 100

pmmvs-eth3d		84.03 356	81.97 360	90.20 355	84.15 403	87.09 351	98.10 343	94.73 391	83.05 370	74.10 397	87.77 399	65.56 376	94.01 383	81.08 361	69.24 391	89.49 396

test_fmvs3		79.99 368	80.17 367	79.45 385	84.02 404	62.83 406	99.05 270	93.49 403	88.29 313	80.06 377	86.65 402	28.09 414	88.00 406	88.63 296	73.27 383	87.54 402

PM-MVS		80.47 365	78.88 370	85.26 377	83.79 405	72.22 400	95.89 385	91.08 410	85.71 348	76.56 391	88.30 395	36.64 410	93.90 385	82.39 353	69.57 390	89.66 395

new-patchmatchnet		81.19 362	79.34 369	86.76 375	82.86 406	80.36 393	97.92 347	95.27 382	82.09 377	72.02 398	86.87 401	62.81 386	90.74 403	71.10 393	63.08 405	89.19 399

mvsany_test3		82.12 361	81.14 363	85.06 378	81.87 407	70.41 402	97.09 362	92.14 407	91.27 249	77.84 385	88.73 394	39.31 409	95.49 365	90.75 273	71.24 386	89.29 398

WB-MVS		76.28 371	77.28 373	73.29 391	81.18 408	54.68 416	97.87 349	94.19 395	81.30 379	69.43 402	90.70 387	77.02 312	82.06 414	35.71 419	68.11 396	83.13 405

test_f		78.40 370	77.59 372	80.81 384	80.82 409	62.48 409	96.96 366	93.08 405	83.44 367	74.57 396	84.57 406	27.95 415	92.63 395	84.15 339	72.79 384	87.32 403

SSC-MVS		75.42 372	76.40 375	72.49 395	80.68 410	53.62 417	97.42 354	94.06 397	80.42 383	68.75 403	90.14 389	76.54 319	81.66 415	33.25 420	66.34 400	82.19 406

pmmvs3		80.27 366	77.77 371	87.76 373	80.32 411	82.43 378	98.23 337	91.97 408	72.74 403	78.75 380	87.97 398	57.30 397	90.99 402	70.31 394	62.37 407	89.87 391

testf1		68.38 376	66.92 377	72.78 393	78.80 412	50.36 419	90.95 406	87.35 418	55.47 409	58.95 408	88.14 396	20.64 419	87.60 407	57.28 411	64.69 402	80.39 408

APD_test2		68.38 376	66.92 377	72.78 393	78.80 412	50.36 419	90.95 406	87.35 418	55.47 409	58.95 408	88.14 396	20.64 419	87.60 407	57.28 411	64.69 402	80.39 408

ambc				83.23 381	77.17 414	62.61 407	87.38 410	94.55 394		76.72 390	86.65 402	30.16 411	96.36 344	84.85 338	69.86 388	90.73 382

test_vis3_rt		68.82 374	66.69 379	75.21 390	76.24 415	60.41 411	96.44 373	68.71 425	75.13 398	50.54 416	69.52 414	16.42 424	96.32 346	80.27 364	66.92 399	68.89 412

TDRefinement		84.76 350	82.56 358	91.38 343	74.58 416	84.80 367	97.36 356	94.56 393	84.73 358	80.21 375	96.12 296	63.56 382	98.39 230	87.92 307	63.97 404	90.95 381

E-PMN		52.30 384	52.18 386	52.67 401	71.51 417	45.40 423	93.62 395	76.60 423	36.01 417	43.50 418	64.13 417	27.11 416	67.31 420	31.06 421	26.06 416	45.30 419

EMVS		51.44 386	51.22 388	52.11 402	70.71 418	44.97 425	94.04 391	75.66 424	35.34 419	42.40 419	61.56 420	28.93 413	65.87 421	27.64 422	24.73 417	45.49 418

PMMVS2		67.15 379	64.15 382	76.14 389	70.56 419	62.07 410	93.89 392	87.52 417	58.09 408	60.02 407	78.32 409	22.38 418	84.54 412	59.56 409	47.03 414	81.80 407

FPMVS		68.72 375	68.72 376	68.71 397	65.95 420	44.27 426	95.97 384	94.74 390	51.13 412	53.26 414	90.50 388	25.11 417	83.00 413	60.80 408	80.97 345	78.87 410

wuyk23d		20.37 390	20.84 393	18.99 405	65.34 421	27.73 428	50.43 416	7.67 429	9.50 422	8.01 423	6.34 423	6.13 427	26.24 422	23.40 423	10.69 421	2.99 420

LCM-MVSNet		67.77 378	64.73 381	76.87 388	62.95 422	56.25 415	89.37 409	93.74 401	44.53 414	61.99 406	80.74 408	20.42 421	86.53 411	69.37 397	59.50 411	87.84 400

MVE	53.74 22	51.54 385	47.86 389	62.60 399	59.56 423	50.93 418	79.41 413	77.69 422	35.69 418	36.27 420	61.76 419	5.79 428	69.63 418	37.97 418	36.61 415	67.24 413
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 382	52.24 385	67.66 398	49.27 424	56.82 414	83.94 411	82.02 421	70.47 405	33.28 421	64.54 416	17.23 423	69.16 419	45.59 416	23.85 418	77.02 411

tmp_tt		65.23 381	62.94 384	72.13 396	44.90 425	50.03 421	81.05 412	89.42 416	38.45 415	48.51 417	99.90 18	54.09 400	78.70 417	91.84 255	18.26 419	87.64 401

PMVS	49.05 23	53.75 383	51.34 387	60.97 400	40.80 426	34.68 427	74.82 414	89.62 415	37.55 416	28.67 422	72.12 411	7.09 426	81.63 416	43.17 417	68.21 395	66.59 414
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 388	39.14 391	33.31 403	19.94 427	24.83 429	98.36 330	9.75 428	15.53 421	51.31 415	87.14 400	19.62 422	17.74 423	47.10 415	3.47 422	57.36 416

testmvs		40.60 387	44.45 390	29.05 404	19.49 428	14.11 430	99.68 180	18.47 427	20.74 420	64.59 405	98.48 214	10.95 425	17.09 424	56.66 413	11.01 420	55.94 417

mmdepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.02 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

eth-test2					0.00 429

eth-test					0.00 429

uanet_test		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

cdsmvs_eth3d_5k		23.43 389	31.24 392	0.00 406	0.00 429	0.00 431	0.00 417	98.09 208	0.00 424	0.00 425	99.67 97	83.37 257	0.00 425	0.00 424	0.00 423	0.00 421

pcd_1.5k_mvsjas		7.60 392	10.13 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	91.20 162	0.00 425	0.00 424	0.00 423	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

ab-mvs-re		8.28 391	11.04 394	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	99.40 126	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 425	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

WAC-MVS						90.97 292								86.10 330

PC_three_1452									96.96 47	99.80 17	99.79 58	97.49 9	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 135	97.27 34	99.80 17	99.94 4	97.18 20	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 63	99.83 13	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

GSMVS																99.59 137

sam_mvs1												94.72 67				99.59 137

sam_mvs												94.25 87

MTGPA								98.28 183

test_post1							95.78 386				59.23 421	93.20 120	97.74 276	91.06 264

test_post											63.35 418	94.43 75	98.13 255

patchmatchnet-post											91.70 382	95.12 52	97.95 267

MTMP							99.87 106	96.49 356

test9_res														99.71 36	99.99 21	100.00 1

agg_prior2														99.48 46	100.00 1	100.00 1

test_prior4						98.05 70	99.94 69

test_prior2							99.95 53		95.78 83	99.73 33	99.76 66	96.00 35		99.78 27	100.00 1

旧先验2							99.46 221		94.21 137	99.85 9			99.95 73	96.96 165

新几何2							99.40 225

无先验							99.49 214	98.71 67	93.46 165				100.00 1	94.36 210		99.99 23

原ACMM2							99.90 91

testdata2													99.99 36	90.54 277

segment_acmp												96.68 27

testdata1							99.28 245		96.35 73

plane_prior5								97.87 230					98.37 236	97.79 142	89.55 265	94.52 274

plane_prior4											98.59 202

plane_prior3						91.64 284			96.63 60	93.01 237

plane_prior2							99.84 125		96.38 69

plane_prior						91.74 278	99.86 117		96.76 55						89.59 264

n2								0.00 430

nn								0.00 430

door-mid								89.69 414

test11								98.44 127

door								90.31 411

HQP5-MVS						91.85 274

BP-MVS														97.92 133

HQP4-MVS										93.37 232			98.39 230			94.53 272

HQP3-MVS								97.89 228							89.60 262

HQP2-MVS												80.65 283

MDTV_nov1_ep13_2view						96.26 143	96.11 380		91.89 227	98.06 140		94.40 77		94.30 213		99.67 118

ACMMP++_ref															87.04 296

ACMMP++															88.23 285

Test By Simon												92.82 131

High-resolution multi-view benchmark