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		97.23 112	96.80 120	98.51 117	99.99 1	95.60 178	99.09 264	98.84 59	93.32 175	96.74 184	99.72 84	86.04 236	100.00 1	98.01 131	99.43 116	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 30	98.64 78	98.47 3	99.13 92	99.92 13	96.38 34	100.00 1	99.74 35	100.00 1	100.00 1

mPP-MVS		98.39 50	98.20 49	98.97 81	99.97 3	96.92 123	99.95 56	98.38 165	95.04 104	98.61 122	99.80 54	93.39 111	100.00 1	98.64 99	100.00 1	99.98 51

CPTT-MVS		97.64 93	97.32 96	98.58 108	99.97 3	95.77 167	99.96 37	98.35 171	89.90 286	98.36 134	99.79 58	91.18 167	99.99 36	98.37 114	99.99 21	99.99 23

DP-MVS Recon		98.41 48	98.02 61	99.56 25	99.97 3	98.70 48	99.92 83	98.44 129	92.06 228	98.40 133	99.84 44	95.68 44	100.00 1	98.19 121	99.71 88	99.97 61

PAPR		98.52 38	98.16 53	99.58 24	99.97 3	98.77 42	99.95 56	98.43 137	95.35 98	98.03 146	99.75 72	94.03 97	99.98 47	98.11 126	99.83 77	99.99 23

HFP-MVS		98.56 35	98.37 39	99.14 61	99.96 8	97.43 102	99.95 56	98.61 84	94.77 113	99.31 81	99.85 33	94.22 90	100.00 1	98.70 94	99.98 32	99.98 51

region2R		98.54 36	98.37 39	99.05 71	99.96 8	97.18 111	99.96 37	98.55 101	94.87 111	99.45 68	99.85 33	94.07 96	100.00 1	98.67 96	100.00 1	99.98 51

ACMMPR		98.50 39	98.32 43	99.05 71	99.96 8	97.18 111	99.95 56	98.60 86	94.77 113	99.31 81	99.84 44	93.73 106	100.00 1	98.70 94	99.98 32	99.98 51

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 30	98.62 83	98.02 16	99.90 3	99.95 3	97.33 17	100.00 1	99.54 45	100.00 1	100.00 1

CP-MVS		98.45 43	98.32 43	98.87 86	99.96 8	96.62 133	99.97 30	98.39 161	94.43 128	98.90 104	99.87 27	94.30 87	100.00 1	99.04 70	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 154	96.63 63	99.75 30	99.93 11	97.49 10

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 56	98.43 137					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 98	99.94 73	98.42 149	96.22 78	99.41 73	99.78 62	94.34 84	99.96 66	98.92 79	99.95 50	99.99 23

X-MVStestdata		93.83 226	92.06 259	99.15 59	99.94 13	97.50 98	99.94 73	98.42 149	96.22 78	99.41 73	41.37 427	94.34 84	99.96 66	98.92 79	99.95 50	99.99 23

test_prior				99.43 35	99.94 13	98.49 60		98.65 76					99.80 127			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 43	99.80 18	99.94 4	95.92 40	100.00 1	99.51 46	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 90	98.39 161	97.20 41	99.46 67	99.85 33	95.53 48	99.79 129	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 62	97.97 64	99.03 73	99.94 13	97.17 114	99.95 56	98.39 161	94.70 117	98.26 140	99.81 53	91.84 158	100.00 1	98.85 85	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	99.87 111	98.33 176	93.97 153	99.76 29	99.87 27	94.99 62	99.75 138	98.55 103	100.00 1	99.98 51

PAPM_NR		98.12 65	97.93 69	98.70 97	99.94 13	96.13 157	99.82 140	98.43 137	94.56 121	97.52 160	99.70 88	94.40 79	99.98 47	97.00 165	99.98 32	99.99 23

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 193	99.44 19	97.33 34	99.00 100	99.72 84	94.03 97	99.98 47	98.73 93	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 37	98.43 137	97.27 37	99.80 18	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		98.41 154	97.71 22	99.84 13				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 137	97.26 39	99.80 18	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 56	98.32 178	97.28 35	99.83 14	99.91 14	97.22 19	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 37	98.42 149	97.28 35	99.86 8	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 80	99.93 24	97.24 108	99.95 56	98.42 149	97.50 29	99.52 63	99.88 24	97.43 16	99.71 144	99.50 47	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		98.43 137		99.63 47			99.85 114

FOURS1					99.92 31	97.66 92	99.95 56	98.36 169	95.58 92	99.52 63

ZD-MVS					99.92 31	98.57 56		98.52 109	92.34 220	99.31 81	99.83 46	95.06 57	99.80 127	99.70 39	99.97 42

GST-MVS		98.27 56	97.97 64	99.17 55	99.92 31	97.57 94	99.93 80	98.39 161	94.04 151	98.80 109	99.74 79	92.98 127	100.00 1	98.16 123	99.76 85	99.93 79

TEST9					99.92 31	98.92 29	99.96 37	98.43 137	93.90 159	99.71 37	99.86 29	95.88 41	99.85 114

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 37	98.43 137	94.35 133	99.71 37	99.86 29	95.94 38	99.85 114	99.69 40	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 37	98.43 137	94.35 133	99.69 39	99.85 33	95.94 38	99.85 114

PGM-MVS		98.34 51	98.13 55	98.99 78	99.92 31	97.00 119	99.75 161	99.50 17	93.90 159	99.37 78	99.76 66	93.24 120	100.00 1	97.75 150	99.96 46	99.98 51

ACMMP		97.74 88	97.44 90	98.66 100	99.92 31	96.13 157	99.18 259	99.45 18	94.84 112	96.41 194	99.71 86	91.40 161	99.99 36	97.99 133	98.03 170	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 56	98.43 137	96.48 66	99.80 18	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		98.41 154					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 154					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 56	98.56 95	97.56 28	99.44 69	99.85 33	95.38 51	100.00 1	99.31 57	99.99 21	99.87 90

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 111	98.36 169	94.08 146	99.74 33	99.73 81	94.08 95	99.74 140	99.42 53	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	99.24 254	98.47 121	98.14 12	99.08 95	99.91 14	93.09 124	100.00 1	99.04 70	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 37				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	99.87 111	98.44 129	97.48 30	99.64 46	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 66

CSCG		97.10 117	97.04 108	97.27 194	99.89 45	91.92 278	99.90 96	99.07 34	88.67 310	95.26 217	99.82 49	93.17 123	99.98 47	98.15 124	99.47 111	99.90 86

ZNCC-MVS		98.31 53	98.03 60	99.17 55	99.88 49	97.59 93	99.94 73	98.44 129	94.31 136	98.50 127	99.82 49	93.06 125	99.99 36	98.30 118	99.99 21	99.93 79

SR-MVS		98.46 42	98.30 46	98.93 84	99.88 49	97.04 118	99.84 130	98.35 171	94.92 108	99.32 80	99.80 54	93.35 113	99.78 131	99.30 58	99.95 50	99.96 67

9.14			98.38 37		99.87 51		99.91 90	98.33 176	93.22 178	99.78 27	99.89 22	94.57 75	99.85 114	99.84 22	99.97 42

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 122	98.38 165	93.19 179	99.77 28	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 73	99.86 53	97.10 116	99.98 15	98.80 64	90.78 269	99.62 50	99.78 62	95.30 52	100.00 1	99.80 25	99.93 61	99.99 23

MTAPA		98.29 55	97.96 67	99.30 44	99.85 54	97.93 81	99.39 234	98.28 185	95.76 87	97.18 172	99.88 24	92.74 134	100.00 1	98.67 96	99.88 73	99.99 23

LS3D		95.84 171	95.11 182	98.02 147	99.85 54	95.10 198	98.74 309	98.50 118	87.22 332	93.66 235	99.86 29	87.45 219	99.95 74	90.94 273	99.81 83	99.02 213

HPM-MVS		97.96 68	97.72 76	98.68 98	99.84 56	96.39 144	99.90 96	98.17 200	92.61 206	98.62 121	99.57 115	91.87 157	99.67 151	98.87 84	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 56	98.11 57	98.75 94	99.83 57	96.59 136	99.40 230	98.51 112	95.29 100	98.51 126	99.76 66	93.60 110	99.71 144	98.53 106	99.52 105	99.95 74

save fliter					99.82 58	98.79 40	99.96 37	98.40 158	97.66 24

PLC	95.54 3	97.93 71	97.89 72	98.05 146	99.82 58	94.77 208	99.92 83	98.46 123	93.93 156	97.20 170	99.27 142	95.44 50	99.97 57	97.41 155	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 60	98.08 59	98.78 91	99.81 60	96.60 134	99.82 140	98.30 183	93.95 155	99.37 78	99.77 64	92.84 131	99.76 137	98.95 76	99.92 64	99.97 61

EI-MVSNet-UG-set		98.14 64	97.99 62	98.60 105	99.80 61	96.27 147	99.36 239	98.50 118	95.21 102	98.30 137	99.75 72	93.29 117	99.73 143	98.37 114	99.30 123	99.81 97

SR-MVS-dyc-post		98.31 53	98.17 52	98.71 96	99.79 62	96.37 145	99.76 157	98.31 180	94.43 128	99.40 75	99.75 72	93.28 118	99.78 131	98.90 82	99.92 64	99.97 61

RE-MVS-def			98.13 55		99.79 62	96.37 145	99.76 157	98.31 180	94.43 128	99.40 75	99.75 72	92.95 128		98.90 82	99.92 64	99.97 61

HPM-MVS_fast		97.80 83	97.50 87	98.68 98	99.79 62	96.42 140	99.88 108	98.16 205	91.75 238	98.94 102	99.54 118	91.82 159	99.65 153	97.62 153	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 96	98.21 195	93.53 168	99.81 16	99.89 22	94.70 71	99.86 113	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 69	99.75 72	93.24 120	99.99 36	99.94 11	99.41 118	99.95 74

旧先验1					99.76 66	97.52 96		98.64 78			99.85 33	95.63 45			99.94 55	99.99 23

OMC-MVS		97.28 108	97.23 100	97.41 185	99.76 66	93.36 247	99.65 189	97.95 224	96.03 82	97.41 165	99.70 88	89.61 193	99.51 159	96.73 174	98.25 160	99.38 175

新几何1				99.42 37	99.75 69	98.27 64		98.63 82	92.69 201	99.55 58	99.82 49	94.40 79	100.00 1	91.21 265	99.94 55	99.99 23

MP-MVS-pluss		98.07 67	97.64 81	99.38 42	99.74 70	98.41 63	99.74 164	98.18 199	93.35 173	96.45 191	99.85 33	92.64 136	99.97 57	98.91 81	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	99.77 152	98.38 165	96.73 59	99.88 7	99.74 79	94.89 64	99.59 155	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		98.40 158		99.65 43		94.76 67	99.75 138		99.98 32	99.99 23

原ACMM1				98.96 82	99.73 73	96.99 120		98.51 112	94.06 149	99.62 50	99.85 33	94.97 63	99.96 66	95.11 194	99.95 50	99.92 84

TSAR-MVS + GP.		98.60 33	98.51 31	98.86 87	99.73 73	96.63 132	99.97 30	97.92 229	98.07 13	98.76 114	99.55 116	95.00 61	99.94 82	99.91 16	97.68 175	99.99 23

CANet		98.27 56	97.82 74	99.63 17	99.72 75	99.10 23	99.98 15	98.51 112	97.00 49	98.52 124	99.71 86	87.80 214	99.95 74	99.75 33	99.38 119	99.83 94

reproduce_model		98.75 27	98.66 23	99.03 73	99.71 76	97.10 116	99.73 171	98.23 193	97.02 48	99.18 90	99.90 18	94.54 76	99.99 36	99.77 29	99.90 69	99.99 23

F-COLMAP		96.93 129	96.95 111	96.87 204	99.71 76	91.74 283	99.85 125	97.95 224	93.11 184	95.72 210	99.16 153	92.35 146	99.94 82	95.32 192	99.35 121	98.92 216

reproduce-ours		98.78 24	98.67 21	99.09 68	99.70 78	97.30 106	99.74 164	98.25 189	97.10 43	99.10 93	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 68	99.70 78	97.30 106	99.74 164	98.25 189	97.10 43	99.10 93	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 73	98.34 175	96.38 72	99.81 16	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 61	99.12 5	95.59 239	99.67 81	86.91 359	99.95 56	98.89 49	97.60 25	99.90 3	99.76 66	96.54 32	99.98 47	99.94 11	99.82 81	99.88 88

ACMMP_NAP		98.49 40	98.14 54	99.54 27	99.66 82	98.62 55	99.85 125	98.37 168	94.68 118	99.53 61	99.83 46	92.87 130	100.00 1	98.66 98	99.84 76	99.99 23

DeepPCF-MVS	95.94 2	97.71 91	98.98 12	93.92 302	99.63 83	81.76 389	99.96 37	98.56 95	99.47 1	99.19 89	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 93	99.62 84	96.80 128	99.90 96	99.51 16	97.60 25	99.20 87	99.36 136	93.71 107	99.91 95	97.99 133	98.71 147	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 77	99.80 54	90.49 182	99.96 66	99.89 17	99.43 116	99.98 51

PVSNet_BlendedMVS		96.05 165	95.82 161	96.72 209	99.59 85	96.99 120	99.95 56	99.10 31	94.06 149	98.27 138	95.80 306	89.00 204	99.95 74	99.12 64	87.53 299	93.24 358

PVSNet_Blended		97.94 70	97.64 81	98.83 88	99.59 85	96.99 120	100.00 1	99.10 31	95.38 97	98.27 138	99.08 156	89.00 204	99.95 74	99.12 64	99.25 125	99.57 145

PatchMatch-RL		96.04 166	95.40 171	97.95 149	99.59 85	95.22 194	99.52 213	99.07 34	93.96 154	96.49 190	98.35 225	82.28 266	99.82 126	90.15 289	99.22 128	98.81 223

dcpmvs_2		97.42 103	98.09 58	95.42 244	99.58 89	87.24 355	99.23 255	96.95 332	94.28 139	98.93 103	99.73 81	94.39 82	99.16 185	99.89 17	99.82 81	99.86 92

test222					99.55 90	97.41 104	99.34 240	98.55 101	91.86 233	99.27 85	99.83 46	93.84 104			99.95 50	99.99 23

CNLPA		97.76 87	97.38 92	98.92 85	99.53 91	96.84 125	99.87 111	98.14 209	93.78 162	96.55 189	99.69 91	92.28 148	99.98 47	97.13 161	99.44 115	99.93 79

API-MVS		97.86 75	97.66 79	98.47 119	99.52 92	95.41 185	99.47 222	98.87 52	91.68 239	98.84 106	99.85 33	92.34 147	99.99 36	98.44 110	99.96 46	100.00 1

PVSNet	91.05 13	97.13 116	96.69 126	98.45 121	99.52 92	95.81 165	99.95 56	99.65 12	94.73 115	99.04 98	99.21 149	84.48 251	99.95 74	94.92 200	98.74 146	99.58 143

114514_t		97.41 104	96.83 118	99.14 61	99.51 94	97.83 83	99.89 105	98.27 187	88.48 314	99.06 97	99.66 100	90.30 185	99.64 154	96.32 178	99.97 42	99.96 67

cl22		93.77 230	93.25 234	95.33 248	99.49 95	94.43 212	99.61 198	98.09 211	90.38 275	89.16 302	95.61 313	90.56 180	97.34 294	91.93 257	84.45 319	94.21 304

testdata				98.42 125	99.47 96	95.33 188		98.56 95	93.78 162	99.79 26	99.85 33	93.64 109	99.94 82	94.97 198	99.94 55	100.00 1

MAR-MVS		97.43 99	97.19 102	98.15 140	99.47 96	94.79 207	99.05 275	98.76 65	92.65 204	98.66 119	99.82 49	88.52 209	99.98 47	98.12 125	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		94.54 208	93.42 227	97.91 155	99.46 98	94.04 225	98.93 289	97.48 274	81.15 385	90.04 274	99.55 116	87.02 225	99.95 74	88.97 299	98.11 166	99.73 108

MVS_111021_LR		98.42 47	98.38 37	98.53 115	99.39 99	95.79 166	99.87 111	99.86 2	96.70 60	98.78 110	99.79 58	92.03 154	99.90 97	99.17 63	99.86 75	99.88 88

CHOSEN 280x420		99.01 14	99.03 10	98.95 83	99.38 100	98.87 33	98.46 327	99.42 21	97.03 47	99.02 99	99.09 155	99.35 2	98.21 256	99.73 37	99.78 84	99.77 104

MVS_111021_HR		98.72 28	98.62 26	99.01 77	99.36 101	97.18 111	99.93 80	99.90 1	96.81 57	98.67 118	99.77 64	93.92 99	99.89 102	99.27 59	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 37	98.44 129	97.96 17	99.55 58	99.94 4	97.18 21	100.00 1	93.81 229	99.94 55	99.98 51

TAPA-MVS	92.12 8	94.42 214	93.60 220	96.90 203	99.33 102	91.78 282	99.78 149	98.00 218	89.89 287	94.52 223	99.47 122	91.97 155	99.18 182	69.90 400	99.52 105	99.73 108
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 185	95.07 184	96.32 222	99.32 104	96.60 134	99.76 157	98.85 56	96.65 62	87.83 323	96.05 303	99.52 1	98.11 261	96.58 175	81.07 347	94.25 300

SPE-MVS-test		97.88 73	97.94 68	97.70 168	99.28 105	95.20 195	99.98 15	97.15 309	95.53 94	99.62 50	99.79 58	92.08 153	98.38 239	98.75 92	99.28 124	99.52 157

test_fmvsm_n_1920		98.44 44	98.61 27	97.92 153	99.27 106	95.18 196	100.00 1	98.90 47	98.05 14	99.80 18	99.73 81	92.64 136	99.99 36	99.58 44	99.51 108	98.59 233

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 45	99.21 107	97.91 82	99.98 15	98.85 56	98.25 5	99.92 2	99.75 72	94.72 69	99.97 57	99.87 19	99.64 92	99.95 74

test_yl		97.83 78	97.37 93	99.21 49	99.18 108	97.98 77	99.64 193	99.27 27	91.43 248	97.88 152	98.99 165	95.84 42	99.84 122	98.82 86	95.32 229	99.79 100

DCV-MVSNet		97.83 78	97.37 93	99.21 49	99.18 108	97.98 77	99.64 193	99.27 27	91.43 248	97.88 152	98.99 165	95.84 42	99.84 122	98.82 86	95.32 229	99.79 100

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 46	99.17 110	97.81 85	99.98 15	98.86 53	98.25 5	99.90 3	99.76 66	94.21 92	99.97 57	99.87 19	99.52 105	99.98 51

DeepC-MVS	94.51 4	96.92 130	96.40 136	98.45 121	99.16 111	95.90 163	99.66 188	98.06 214	96.37 75	94.37 226	99.49 121	83.29 261	99.90 97	97.63 152	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 90	97.70 23	98.21 142	99.24 147	92.58 139	99.94 82	98.63 101	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 85	97.91 70	97.43 184	99.10 113	94.42 213	99.99 4	97.10 314	95.07 103	99.68 40	99.75 72	92.95 128	98.34 243	98.38 112	99.14 130	99.54 151

Anonymous202405211		93.10 248	91.99 260	96.40 218	99.10 113	89.65 327	98.88 295	97.93 226	83.71 370	94.00 232	98.75 194	68.79 365	99.88 108	95.08 195	91.71 261	99.68 116

fmvsm_s_conf0.5_n		97.80 83	97.85 73	97.67 169	99.06 115	94.41 214	99.98 15	98.97 40	97.34 32	99.63 47	99.69 91	87.27 221	99.97 57	99.62 42	99.06 134	98.62 232

HyFIR lowres test		96.66 144	96.43 135	97.36 190	99.05 116	93.91 230	99.70 182	99.80 3	90.54 273	96.26 197	98.08 235	92.15 151	98.23 255	96.84 173	95.46 224	99.93 79

LFMVS		94.75 202	93.56 223	98.30 131	99.03 117	95.70 172	98.74 309	97.98 221	87.81 325	98.47 128	99.39 133	67.43 374	99.53 156	98.01 131	95.20 232	99.67 118

fmvsm_s_conf0.5_n_2		97.59 94	97.28 97	98.53 115	99.01 118	98.15 65	99.98 15	98.59 88	98.17 10	99.75 30	99.63 106	81.83 271	99.94 82	99.78 27	98.79 145	97.51 259

AllTest		92.48 262	91.64 265	95.00 257	99.01 118	88.43 343	98.94 287	96.82 346	86.50 341	88.71 307	98.47 220	74.73 342	99.88 108	85.39 338	96.18 206	96.71 265

TestCases				95.00 257	99.01 118	88.43 343		96.82 346	86.50 341	88.71 307	98.47 220	74.73 342	99.88 108	85.39 338	96.18 206	96.71 265

COLMAP_ROB	90.47 14	92.18 269	91.49 271	94.25 290	99.00 121	88.04 349	98.42 333	96.70 353	82.30 381	88.43 315	99.01 162	76.97 318	99.85 114	86.11 334	96.50 200	94.86 276
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 69	97.66 79	98.81 89	98.99 122	98.07 71	99.98 15	98.81 61	98.18 9	99.89 6	99.70 88	84.15 254	99.97 57	99.76 32	99.50 110	98.39 237

test_fmvs1		95.35 186	95.68 166	94.36 287	98.99 122	84.98 369	99.96 37	96.65 355	97.60 25	99.73 35	98.96 171	71.58 355	99.93 90	98.31 117	99.37 120	98.17 241

HY-MVS	92.50 7	97.79 85	97.17 104	99.63 17	98.98 124	99.32 9	97.49 358	99.52 14	95.69 89	98.32 136	97.41 255	93.32 115	99.77 134	98.08 129	95.75 220	99.81 97

VNet		97.21 113	96.57 131	99.13 65	98.97 125	97.82 84	99.03 278	99.21 29	94.31 136	99.18 90	98.88 182	86.26 235	99.89 102	98.93 78	94.32 241	99.69 115

thres200		96.96 126	96.21 142	99.22 48	98.97 125	98.84 36	99.85 125	99.71 7	93.17 180	96.26 197	98.88 182	89.87 190	99.51 159	94.26 219	94.91 234	99.31 187

tfpn200view9		96.79 134	95.99 147	99.19 51	98.94 127	98.82 37	99.78 149	99.71 7	92.86 190	96.02 202	98.87 185	89.33 197	99.50 161	93.84 226	94.57 237	99.27 193

thres400		96.78 136	95.99 147	99.16 57	98.94 127	98.82 37	99.78 149	99.71 7	92.86 190	96.02 202	98.87 185	89.33 197	99.50 161	93.84 226	94.57 237	99.16 200

sasdasda		97.09 119	96.32 137	99.39 40	98.93 129	98.95 27	99.72 175	97.35 286	94.45 124	97.88 152	99.42 126	86.71 228	99.52 157	98.48 107	93.97 247	99.72 110

Anonymous20231211		89.86 319	88.44 326	94.13 293	98.93 129	90.68 306	98.54 324	98.26 188	76.28 397	86.73 337	95.54 317	70.60 361	97.56 287	90.82 276	80.27 356	94.15 312

canonicalmvs		97.09 119	96.32 137	99.39 40	98.93 129	98.95 27	99.72 175	97.35 286	94.45 124	97.88 152	99.42 126	86.71 228	99.52 157	98.48 107	93.97 247	99.72 110

SDMVSNet		94.80 198	93.96 212	97.33 192	98.92 132	95.42 184	99.59 200	98.99 37	92.41 217	92.55 250	97.85 246	75.81 332	98.93 197	97.90 139	91.62 262	97.64 253

sd_testset		93.55 237	92.83 240	95.74 237	98.92 132	90.89 302	98.24 340	98.85 56	92.41 217	92.55 250	97.85 246	71.07 360	98.68 215	93.93 223	91.62 262	97.64 253

EPNet_dtu		95.71 175	95.39 172	96.66 211	98.92 132	93.41 244	99.57 205	98.90 47	96.19 80	97.52 160	98.56 212	92.65 135	97.36 292	77.89 381	98.33 155	99.20 198
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 66	97.60 83	99.60 22	98.92 132	99.28 17	99.89 105	99.52 14	95.58 92	98.24 141	99.39 133	93.33 114	99.74 140	97.98 135	95.58 223	99.78 103

CHOSEN 1792x2688		96.81 133	96.53 132	97.64 171	98.91 136	93.07 249	99.65 189	99.80 3	95.64 90	95.39 214	98.86 187	84.35 253	99.90 97	96.98 167	99.16 129	99.95 74

thres100view900		96.74 139	95.92 157	99.18 52	98.90 137	98.77 42	99.74 164	99.71 7	92.59 208	95.84 206	98.86 187	89.25 199	99.50 161	93.84 226	94.57 237	99.27 193

thres600view7		96.69 142	95.87 160	99.14 61	98.90 137	98.78 41	99.74 164	99.71 7	92.59 208	95.84 206	98.86 187	89.25 199	99.50 161	93.44 238	94.50 240	99.16 200

MSDG		94.37 216	93.36 231	97.40 186	98.88 139	93.95 229	99.37 237	97.38 283	85.75 352	90.80 267	99.17 152	84.11 256	99.88 108	86.35 330	98.43 153	98.36 239

MGCFI-Net		97.00 124	96.22 141	99.34 43	98.86 140	98.80 39	99.67 187	97.30 293	94.31 136	97.77 156	99.41 130	86.36 234	99.50 161	98.38 112	93.90 249	99.72 110

h-mvs33		94.92 195	94.36 200	96.59 213	98.85 141	91.29 294	98.93 289	98.94 41	95.90 83	98.77 111	98.42 223	90.89 175	99.77 134	97.80 143	70.76 392	98.72 229

Anonymous20240529		92.10 270	90.65 282	96.47 214	98.82 142	90.61 308	98.72 311	98.67 75	75.54 401	93.90 234	98.58 210	66.23 378	99.90 97	94.70 209	90.67 265	98.90 219

PVSNet_Blended_VisFu		97.27 109	96.81 119	98.66 100	98.81 143	96.67 131	99.92 83	98.64 78	94.51 123	96.38 195	98.49 216	89.05 203	99.88 108	97.10 163	98.34 154	99.43 171

PS-MVSNAJ		98.44 44	98.20 49	99.16 57	98.80 144	98.92 29	99.54 211	98.17 200	97.34 32	99.85 10	99.85 33	91.20 164	99.89 102	99.41 54	99.67 90	98.69 230

CANet_DTU		96.76 137	96.15 143	98.60 105	98.78 145	97.53 95	99.84 130	97.63 252	97.25 40	99.20 87	99.64 103	81.36 277	99.98 47	92.77 249	98.89 139	98.28 240

mvsany_test1		97.82 81	97.90 71	97.55 176	98.77 146	93.04 252	99.80 146	97.93 226	96.95 51	99.61 56	99.68 97	90.92 172	99.83 124	99.18 62	98.29 159	99.80 99

alignmvs		97.81 82	97.33 95	99.25 46	98.77 146	98.66 51	99.99 4	98.44 129	94.40 132	98.41 131	99.47 122	93.65 108	99.42 170	98.57 102	94.26 243	99.67 118

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 52	98.72 148	97.71 88	99.98 15	98.44 129	96.85 52	99.80 18	99.91 14	97.57 8	99.85 114	99.44 52	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 62	97.97 64	99.02 76	98.69 149	98.66 51	99.52 213	98.08 213	97.05 46	99.86 8	99.86 29	90.65 177	99.71 144	99.39 56	98.63 148	98.69 230

miper_enhance_ethall		94.36 218	93.98 211	95.49 240	98.68 150	95.24 192	99.73 171	97.29 296	93.28 177	89.86 279	95.97 304	94.37 83	97.05 314	92.20 253	84.45 319	94.19 305

ETVMVS		97.03 123	96.64 127	98.20 136	98.67 151	97.12 115	99.89 105	98.57 92	91.10 259	98.17 143	98.59 207	93.86 103	98.19 257	95.64 189	95.24 231	99.28 192

test2506		97.53 96	97.19 102	98.58 108	98.66 152	96.90 124	98.81 304	99.77 5	94.93 106	97.95 148	98.96 171	92.51 141	99.20 180	94.93 199	98.15 163	99.64 124

ECVR-MVS		95.66 178	95.05 185	97.51 180	98.66 152	93.71 234	98.85 301	98.45 124	94.93 106	96.86 180	98.96 171	75.22 338	99.20 180	95.34 191	98.15 163	99.64 124

mamv4		95.24 188	96.90 113	90.25 359	98.65 154	72.11 406	98.28 338	97.64 251	89.99 285	95.93 204	98.25 230	94.74 68	99.11 186	99.01 75	99.64 92	99.53 155

balanced_conf03		98.27 56	97.99 62	99.11 66	98.64 155	98.43 62	99.47 222	97.79 240	94.56 121	99.74 33	98.35 225	94.33 86	99.25 174	99.12 64	99.96 46	99.64 124

fmvsm_s_conf0.5_n_a		97.73 90	97.72 76	97.77 163	98.63 156	94.26 220	99.96 37	98.92 46	97.18 42	99.75 30	99.69 91	87.00 226	99.97 57	99.46 50	98.89 139	99.08 209

MVSMamba_PlusPlus		97.83 78	97.45 89	98.99 78	98.60 157	98.15 65	99.58 202	97.74 244	90.34 278	99.26 86	98.32 228	94.29 88	99.23 175	99.03 73	99.89 70	99.58 143

testing222		97.08 122	96.75 122	98.06 145	98.56 158	96.82 126	99.85 125	98.61 84	92.53 212	98.84 106	98.84 191	93.36 112	98.30 247	95.84 186	94.30 242	99.05 211

test1111		95.57 180	94.98 188	97.37 188	98.56 158	93.37 246	98.86 299	98.45 124	94.95 105	96.63 186	98.95 176	75.21 339	99.11 186	95.02 196	98.14 165	99.64 124

MVSTER		95.53 181	95.22 178	96.45 216	98.56 158	97.72 87	99.91 90	97.67 249	92.38 219	91.39 260	97.14 262	97.24 18	97.30 298	94.80 205	87.85 294	94.34 295

VDD-MVS		93.77 230	92.94 238	96.27 223	98.55 161	90.22 317	98.77 308	97.79 240	90.85 265	96.82 182	99.42 126	61.18 397	99.77 134	98.95 76	94.13 244	98.82 222

tpmvs		94.28 220	93.57 222	96.40 218	98.55 161	91.50 292	95.70 392	98.55 101	87.47 327	92.15 253	94.26 367	91.42 160	98.95 196	88.15 309	95.85 216	98.76 225

UGNet		95.33 187	94.57 196	97.62 174	98.55 161	94.85 203	98.67 317	99.32 26	95.75 88	96.80 183	96.27 294	72.18 352	99.96 66	94.58 212	99.05 135	98.04 245
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	95.18 189	94.10 207	98.43 123	98.55 161	95.99 161	97.91 353	97.31 292	90.35 277	89.48 291	99.22 148	85.19 244	99.89 102	90.40 286	98.47 152	99.41 173
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		96.79 134	96.72 124	97.00 199	98.51 165	93.70 235	99.71 178	98.60 86	92.96 186	97.09 173	98.34 227	96.67 31	98.85 200	92.11 255	96.50 200	98.44 235

test_vis1_n_1920		95.44 183	95.31 175	95.82 235	98.50 166	88.74 337	99.98 15	97.30 293	97.84 19	99.85 10	99.19 150	66.82 376	99.97 57	98.82 86	99.46 113	98.76 225

BH-w/o		95.71 175	95.38 173	96.68 210	98.49 167	92.28 269	99.84 130	97.50 272	92.12 225	92.06 256	98.79 192	84.69 249	98.67 216	95.29 193	99.66 91	99.09 207

baseline1		95.78 172	94.86 190	98.54 113	98.47 168	98.07 71	99.06 271	97.99 219	92.68 202	94.13 231	98.62 206	93.28 118	98.69 214	93.79 231	85.76 307	98.84 221

EPMVS		96.53 148	96.01 146	98.09 143	98.43 169	96.12 159	96.36 379	99.43 20	93.53 168	97.64 158	95.04 344	94.41 78	98.38 239	91.13 267	98.11 166	99.75 106

kuosan		93.17 245	92.60 246	94.86 264	98.40 170	89.54 329	98.44 329	98.53 107	84.46 365	88.49 311	97.92 243	90.57 179	97.05 314	83.10 353	93.49 252	97.99 246

WBMVS		94.52 211	94.03 209	95.98 229	98.38 171	96.68 130	99.92 83	97.63 252	90.75 270	89.64 287	95.25 338	96.77 25	96.90 325	94.35 217	83.57 326	94.35 293

UBG		97.84 77	97.69 78	98.29 132	98.38 171	96.59 136	99.90 96	98.53 107	93.91 158	98.52 124	98.42 223	96.77 25	99.17 183	98.54 104	96.20 205	99.11 206

sss		97.57 95	97.03 109	99.18 52	98.37 173	98.04 74	99.73 171	99.38 22	93.46 170	98.76 114	99.06 158	91.21 163	99.89 102	96.33 177	97.01 192	99.62 130

testing11		97.48 98	97.27 98	98.10 142	98.36 174	96.02 160	99.92 83	98.45 124	93.45 172	98.15 144	98.70 197	95.48 49	99.22 176	97.85 141	95.05 233	99.07 210

BH-untuned		95.18 189	94.83 191	96.22 224	98.36 174	91.22 295	99.80 146	97.32 291	90.91 263	91.08 263	98.67 199	83.51 258	98.54 222	94.23 220	99.61 99	98.92 216

testing91		97.16 115	96.90 113	97.97 148	98.35 176	95.67 175	99.91 90	98.42 149	92.91 189	97.33 167	98.72 195	94.81 66	99.21 177	96.98 167	94.63 236	99.03 212

testing99		97.17 114	96.91 112	97.95 149	98.35 176	95.70 172	99.91 90	98.43 137	92.94 187	97.36 166	98.72 195	94.83 65	99.21 177	97.00 165	94.64 235	98.95 215

ET-MVSNet_ETH3D		94.37 216	93.28 233	97.64 171	98.30 178	97.99 76	99.99 4	97.61 258	94.35 133	71.57 404	99.45 125	96.23 35	95.34 374	96.91 172	85.14 314	99.59 137

AUN-MVS		93.28 242	92.60 246	95.34 247	98.29 179	90.09 320	99.31 244	98.56 95	91.80 237	96.35 196	98.00 238	89.38 196	98.28 250	92.46 250	69.22 397	97.64 253

FMVSNet3		92.69 258	91.58 267	95.99 228	98.29 179	97.42 103	99.26 253	97.62 255	89.80 288	89.68 283	95.32 332	81.62 275	96.27 353	87.01 326	85.65 308	94.29 297

PMMVS		96.76 137	96.76 121	96.76 207	98.28 181	92.10 273	99.91 90	97.98 221	94.12 144	99.53 61	99.39 133	86.93 227	98.73 209	96.95 170	97.73 173	99.45 168

hse-mvs2		94.38 215	94.08 208	95.31 249	98.27 182	90.02 321	99.29 249	98.56 95	95.90 83	98.77 111	98.00 238	90.89 175	98.26 254	97.80 143	69.20 398	97.64 253

PVSNet_0	88.03 19	91.80 277	90.27 291	96.38 220	98.27 182	90.46 312	99.94 73	99.61 13	93.99 152	86.26 347	97.39 257	71.13 359	99.89 102	98.77 90	67.05 403	98.79 224

UA-Net		96.54 147	95.96 153	98.27 133	98.23 184	95.71 171	98.00 351	98.45 124	93.72 165	98.41 131	99.27 142	88.71 208	99.66 152	91.19 266	97.69 174	99.44 170

test_cas_vis1_n_1920		96.59 146	96.23 140	97.65 170	98.22 185	94.23 221	99.99 4	97.25 300	97.77 20	99.58 57	99.08 156	77.10 315	99.97 57	97.64 151	99.45 114	98.74 227

FE-MVS		95.70 177	95.01 187	97.79 160	98.21 186	94.57 209	95.03 393	98.69 70	88.90 304	97.50 162	96.19 296	92.60 138	99.49 166	89.99 291	97.94 172	99.31 187

GG-mvs-BLEND				98.54 113	98.21 186	98.01 75	93.87 398	98.52 109		97.92 149	97.92 243	99.02 3	97.94 274	98.17 122	99.58 102	99.67 118

mvs_anonymous		95.65 179	95.03 186	97.53 178	98.19 188	95.74 169	99.33 241	97.49 273	90.87 264	90.47 270	97.10 264	88.23 211	97.16 305	95.92 184	97.66 176	99.68 116

MVS_Test		96.46 150	95.74 162	98.61 104	98.18 189	97.23 109	99.31 244	97.15 309	91.07 260	98.84 106	97.05 268	88.17 212	98.97 193	94.39 214	97.50 178	99.61 134

BH-RMVSNet		95.18 189	94.31 203	97.80 158	98.17 190	95.23 193	99.76 157	97.53 268	92.52 213	94.27 229	99.25 146	76.84 320	98.80 202	90.89 275	99.54 104	99.35 182

dongtai		91.55 283	91.13 276	92.82 332	98.16 191	86.35 360	99.47 222	98.51 112	83.24 373	85.07 356	97.56 251	90.33 184	94.94 380	76.09 389	91.73 260	97.18 262

RPSCF		91.80 277	92.79 242	88.83 370	98.15 192	69.87 408	98.11 347	96.60 357	83.93 368	94.33 227	99.27 142	79.60 298	99.46 169	91.99 256	93.16 257	97.18 262

ETV-MVS		97.92 72	97.80 75	98.25 134	98.14 193	96.48 138	99.98 15	97.63 252	95.61 91	99.29 84	99.46 124	92.55 140	98.82 201	99.02 74	98.54 150	99.46 166

IS-MVSNet		96.29 160	95.90 158	97.45 182	98.13 194	94.80 206	99.08 266	97.61 258	92.02 230	95.54 213	98.96 171	90.64 178	98.08 263	93.73 234	97.41 182	99.47 165

test_fmvsmconf_n		98.43 46	98.32 43	98.78 91	98.12 195	96.41 141	99.99 4	98.83 60	98.22 7	99.67 41	99.64 103	91.11 168	99.94 82	99.67 41	99.62 95	99.98 51

fmvsm_s_conf0.1_n_2		97.25 110	96.85 117	98.43 123	98.08 196	98.08 70	99.92 83	97.76 243	98.05 14	99.65 43	99.58 112	80.88 284	99.93 90	99.59 43	98.17 161	97.29 260

ab-mvs		94.69 203	93.42 227	98.51 117	98.07 197	96.26 148	96.49 377	98.68 72	90.31 279	94.54 222	97.00 270	76.30 327	99.71 144	95.98 183	93.38 255	99.56 146

XVG-OURS-SEG-HR		94.79 199	94.70 195	95.08 254	98.05 198	89.19 331	99.08 266	97.54 266	93.66 166	94.87 220	99.58 112	78.78 306	99.79 129	97.31 157	93.40 254	96.25 269

EIA-MVS		97.53 96	97.46 88	97.76 165	98.04 199	94.84 204	99.98 15	97.61 258	94.41 131	97.90 150	99.59 109	92.40 145	98.87 198	98.04 130	99.13 131	99.59 137

XVG-OURS		94.82 196	94.74 194	95.06 255	98.00 200	89.19 331	99.08 266	97.55 264	94.10 145	94.71 221	99.62 107	80.51 290	99.74 140	96.04 182	93.06 259	96.25 269

mvsmamba		96.94 127	96.73 123	97.55 176	97.99 201	94.37 217	99.62 196	97.70 246	93.13 182	98.42 130	97.92 243	88.02 213	98.75 208	98.78 89	99.01 136	99.52 157

dp		95.05 192	94.43 198	96.91 202	97.99 201	92.73 259	96.29 382	97.98 221	89.70 289	95.93 204	94.67 357	93.83 105	98.45 228	86.91 329	96.53 199	99.54 151

tpmrst		96.27 162	95.98 149	97.13 196	97.96 203	93.15 248	96.34 380	98.17 200	92.07 226	98.71 117	95.12 341	93.91 100	98.73 209	94.91 202	96.62 197	99.50 162

TR-MVS		94.54 208	93.56 223	97.49 181	97.96 203	94.34 218	98.71 312	97.51 271	90.30 280	94.51 224	98.69 198	75.56 333	98.77 205	92.82 248	95.99 210	99.35 182

Vis-MVSNet (Re-imp)		96.32 157	95.98 149	97.35 191	97.93 205	94.82 205	99.47 222	98.15 208	91.83 234	95.09 218	99.11 154	91.37 162	97.47 290	93.47 237	97.43 179	99.74 107

MDTV_nov1_ep13			95.69 164		97.90 206	94.15 223	95.98 388	98.44 129	93.12 183	97.98 147	95.74 308	95.10 55	98.58 219	90.02 290	96.92 194

Fast-Effi-MVS+		95.02 193	94.19 205	97.52 179	97.88 207	94.55 210	99.97 30	97.08 318	88.85 306	94.47 225	97.96 242	84.59 250	98.41 231	89.84 293	97.10 187	99.59 137

ADS-MVSNet2		93.80 229	93.88 215	93.55 315	97.87 208	85.94 363	94.24 394	96.84 343	90.07 282	96.43 192	94.48 362	90.29 186	95.37 373	87.44 316	97.23 184	99.36 179

ADS-MVSNet		94.79 199	94.02 210	97.11 198	97.87 208	93.79 231	94.24 394	98.16 205	90.07 282	96.43 192	94.48 362	90.29 186	98.19 257	87.44 316	97.23 184	99.36 179

Effi-MVS+		96.30 159	95.69 164	98.16 137	97.85 210	96.26 148	97.41 360	97.21 302	90.37 276	98.65 120	98.58 210	86.61 231	98.70 213	97.11 162	97.37 183	99.52 157

PatchmatchNet		95.94 168	95.45 170	97.39 187	97.83 211	94.41 214	96.05 386	98.40 158	92.86 190	97.09 173	95.28 337	94.21 92	98.07 265	89.26 297	98.11 166	99.70 113
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 206	93.61 218	97.74 167	97.82 212	96.26 148	99.96 37	97.78 242	85.76 350	94.00 232	97.54 252	76.95 319	99.21 177	97.23 159	95.43 226	97.76 252

1112_ss		96.01 167	95.20 179	98.42 125	97.80 213	96.41 141	99.65 189	96.66 354	92.71 199	92.88 246	99.40 131	92.16 150	99.30 172	91.92 258	93.66 250	99.55 147

Test_1112_low_res		95.72 173	94.83 191	98.42 125	97.79 214	96.41 141	99.65 189	96.65 355	92.70 200	92.86 247	96.13 299	92.15 151	99.30 172	91.88 259	93.64 251	99.55 147

Effi-MVS+-dtu		94.53 210	95.30 176	92.22 338	97.77 215	82.54 382	99.59 200	97.06 320	94.92 108	95.29 216	95.37 330	85.81 237	97.89 275	94.80 205	97.07 188	96.23 271

tpm cat1		93.51 238	92.52 252	96.47 214	97.77 215	91.47 293	96.13 384	98.06 214	80.98 386	92.91 245	93.78 371	89.66 191	98.87 198	87.03 325	96.39 203	99.09 207

FA-MVS(test-final)		95.86 169	95.09 183	98.15 140	97.74 217	95.62 177	96.31 381	98.17 200	91.42 250	96.26 197	96.13 299	90.56 180	99.47 168	92.18 254	97.07 188	99.35 182

xiu_mvs_v1_base_debu		97.43 99	97.06 105	98.55 110	97.74 217	98.14 67	99.31 244	97.86 235	96.43 69	99.62 50	99.69 91	85.56 239	99.68 148	99.05 67	98.31 156	97.83 248

xiu_mvs_v1_base		97.43 99	97.06 105	98.55 110	97.74 217	98.14 67	99.31 244	97.86 235	96.43 69	99.62 50	99.69 91	85.56 239	99.68 148	99.05 67	98.31 156	97.83 248

xiu_mvs_v1_base_debi		97.43 99	97.06 105	98.55 110	97.74 217	98.14 67	99.31 244	97.86 235	96.43 69	99.62 50	99.69 91	85.56 239	99.68 148	99.05 67	98.31 156	97.83 248

EPP-MVSNet		96.69 142	96.60 129	96.96 201	97.74 217	93.05 251	99.37 237	98.56 95	88.75 308	95.83 208	99.01 162	96.01 36	98.56 220	96.92 171	97.20 186	99.25 195

gg-mvs-nofinetune		93.51 238	91.86 264	98.47 119	97.72 222	97.96 80	92.62 402	98.51 112	74.70 404	97.33 167	69.59 418	98.91 4	97.79 278	97.77 148	99.56 103	99.67 118

IB-MVS	92.85 6	94.99 194	93.94 213	98.16 137	97.72 222	95.69 174	99.99 4	98.81 61	94.28 139	92.70 248	96.90 272	95.08 56	99.17 183	96.07 181	73.88 386	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		97.41 104	97.02 110	98.59 107	97.71 224	97.52 96	99.97 30	98.54 104	91.83 234	97.45 163	99.04 159	97.50 9	99.10 188	94.75 207	96.37 204	99.16 200

Syy-MVS		90.00 317	90.63 283	88.11 377	97.68 225	74.66 404	99.71 178	98.35 171	90.79 267	92.10 254	98.67 199	79.10 304	93.09 397	63.35 411	95.95 213	96.59 267

myMVS_eth3d		94.46 213	94.76 193	93.55 315	97.68 225	90.97 297	99.71 178	98.35 171	90.79 267	92.10 254	98.67 199	92.46 144	93.09 397	87.13 322	95.95 213	96.59 267

test_fmvs1_n		94.25 221	94.36 200	93.92 302	97.68 225	83.70 376	99.90 96	96.57 358	97.40 31	99.67 41	98.88 182	61.82 394	99.92 94	98.23 120	99.13 131	98.14 244

RRT-MVS		96.24 163	95.68 166	97.94 152	97.65 228	94.92 202	99.27 252	97.10 314	92.79 196	97.43 164	97.99 240	81.85 270	99.37 171	98.46 109	98.57 149	99.53 155

diffmvs		97.00 124	96.64 127	98.09 143	97.64 229	96.17 156	99.81 142	97.19 303	94.67 119	98.95 101	99.28 139	86.43 232	98.76 206	98.37 114	97.42 181	99.33 185
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		95.72 173	95.15 181	97.45 182	97.62 230	94.28 219	99.28 250	98.24 191	94.27 141	96.84 181	98.94 178	79.39 299	98.76 206	93.25 239	98.49 151	99.30 189
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 117	96.72 124	98.22 135	97.60 231	96.70 129	99.92 83	98.54 104	91.11 258	97.07 175	98.97 169	97.47 12	99.03 191	93.73 234	96.09 208	98.92 216

GDP-MVS		97.88 73	97.59 85	98.75 94	97.59 232	97.81 85	99.95 56	97.37 285	94.44 127	99.08 95	99.58 112	97.13 23	99.08 189	94.99 197	98.17 161	99.37 177

miper_ehance_all_eth		93.16 246	92.60 246	94.82 265	97.57 233	93.56 239	99.50 217	97.07 319	88.75 308	88.85 306	95.52 319	90.97 171	96.74 334	90.77 277	84.45 319	94.17 306

testing3		93.92 224	94.23 204	92.99 329	97.54 234	90.23 316	99.99 4	99.16 30	90.57 272	91.33 262	98.63 205	92.99 126	92.52 401	82.46 357	95.39 227	96.22 272

LCM-MVSNet-Re		92.31 266	92.60 246	91.43 347	97.53 235	79.27 399	99.02 280	91.83 414	92.07 226	80.31 379	94.38 365	83.50 259	95.48 371	97.22 160	97.58 177	99.54 151

GBi-Net		90.88 294	89.82 300	94.08 294	97.53 235	91.97 274	98.43 330	96.95 332	87.05 333	89.68 283	94.72 353	71.34 356	96.11 358	87.01 326	85.65 308	94.17 306

test1		90.88 294	89.82 300	94.08 294	97.53 235	91.97 274	98.43 330	96.95 332	87.05 333	89.68 283	94.72 353	71.34 356	96.11 358	87.01 326	85.65 308	94.17 306

FMVSNet2		91.02 291	89.56 305	95.41 245	97.53 235	95.74 169	98.98 282	97.41 281	87.05 333	88.43 315	95.00 347	71.34 356	96.24 355	85.12 340	85.21 313	94.25 300

tttt0517		96.85 131	96.49 133	97.92 153	97.48 239	95.89 164	99.85 125	98.54 104	90.72 271	96.63 186	98.93 180	97.47 12	99.02 192	93.03 246	95.76 219	98.85 220

BP-MVS1		98.33 52	98.18 51	98.81 89	97.44 240	97.98 77	99.96 37	98.17 200	94.88 110	98.77 111	99.59 109	97.59 7	99.08 189	98.24 119	98.93 138	99.36 179

casdiffmvs_mvg		96.43 151	95.94 155	97.89 157	97.44 240	95.47 181	99.86 122	97.29 296	93.35 173	96.03 201	99.19 150	85.39 242	98.72 211	97.89 140	97.04 190	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		97.38 106	97.24 99	97.80 158	97.41 242	95.64 176	99.99 4	97.06 320	94.59 120	99.63 47	99.32 138	89.20 202	98.14 259	98.76 91	99.23 127	99.62 130

c3_l		92.53 261	91.87 263	94.52 277	97.40 243	92.99 253	99.40 230	96.93 337	87.86 323	88.69 309	95.44 324	89.95 189	96.44 346	90.45 283	80.69 352	94.14 315

fmvsm_s_conf0.1_n		97.30 107	97.21 101	97.60 175	97.38 244	94.40 216	99.90 96	98.64 78	96.47 68	99.51 65	99.65 102	84.99 247	99.93 90	99.22 61	99.09 133	98.46 234

CDS-MVSNet		96.34 156	96.07 144	97.13 196	97.37 245	94.96 200	99.53 212	97.91 230	91.55 242	95.37 215	98.32 228	95.05 58	97.13 308	93.80 230	95.75 220	99.30 189
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 139	96.26 139	98.16 137	97.36 246	96.48 138	99.96 37	98.29 184	91.93 231	95.77 209	98.07 236	95.54 46	98.29 248	90.55 281	98.89 139	99.70 113

miper_lstm_enhance		91.81 274	91.39 273	93.06 328	97.34 247	89.18 333	99.38 235	96.79 348	86.70 340	87.47 329	95.22 339	90.00 188	95.86 367	88.26 307	81.37 341	94.15 312

baseline		96.43 151	95.98 149	97.76 165	97.34 247	95.17 197	99.51 215	97.17 306	93.92 157	96.90 179	99.28 139	85.37 243	98.64 217	97.50 154	96.86 196	99.46 166

cl____		92.31 266	91.58 267	94.52 277	97.33 249	92.77 255	99.57 205	96.78 349	86.97 337	87.56 327	95.51 320	89.43 195	96.62 339	88.60 302	82.44 333	94.16 311

DIV-MVS_self_test		92.32 265	91.60 266	94.47 281	97.31 250	92.74 257	99.58 202	96.75 350	86.99 336	87.64 325	95.54 317	89.55 194	96.50 343	88.58 303	82.44 333	94.17 306

casdiffmvs		96.42 153	95.97 152	97.77 163	97.30 251	94.98 199	99.84 130	97.09 317	93.75 164	96.58 188	99.26 145	85.07 245	98.78 204	97.77 148	97.04 190	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		94.36 218	93.48 225	96.99 200	97.29 252	93.54 240	99.96 37	96.72 352	88.35 317	93.43 236	98.94 178	82.05 267	98.05 266	88.12 311	96.48 202	99.37 177

eth_miper_zixun_eth		92.41 264	91.93 261	93.84 306	97.28 253	90.68 306	98.83 302	96.97 331	88.57 313	89.19 301	95.73 310	89.24 201	96.69 337	89.97 292	81.55 339	94.15 312

MVSFormer		96.94 127	96.60 129	97.95 149	97.28 253	97.70 90	99.55 209	97.27 298	91.17 255	99.43 71	99.54 118	90.92 172	96.89 326	94.67 210	99.62 95	99.25 195

lupinMVS		97.85 76	97.60 83	98.62 103	97.28 253	97.70 90	99.99 4	97.55 264	95.50 96	99.43 71	99.67 98	90.92 172	98.71 212	98.40 111	99.62 95	99.45 168

SCA		94.69 203	93.81 217	97.33 192	97.10 256	94.44 211	98.86 299	98.32 178	93.30 176	96.17 200	95.59 315	76.48 325	97.95 272	91.06 269	97.43 179	99.59 137

TAMVS		95.85 170	95.58 168	96.65 212	97.07 257	93.50 241	99.17 260	97.82 239	91.39 252	95.02 219	98.01 237	92.20 149	97.30 298	93.75 233	95.83 217	99.14 203

Fast-Effi-MVS+-dtu		93.72 233	93.86 216	93.29 320	97.06 258	86.16 361	99.80 146	96.83 344	92.66 203	92.58 249	97.83 248	81.39 276	97.67 283	89.75 294	96.87 195	96.05 274

CostFormer		96.10 164	95.88 159	96.78 206	97.03 259	92.55 265	97.08 368	97.83 238	90.04 284	98.72 116	94.89 351	95.01 60	98.29 248	96.54 176	95.77 218	99.50 162

test_fmvsmvis_n_1920		97.67 92	97.59 85	97.91 155	97.02 260	95.34 187	99.95 56	98.45 124	97.87 18	97.02 176	99.59 109	89.64 192	99.98 47	99.41 54	99.34 122	98.42 236

test-LLR		96.47 149	96.04 145	97.78 161	97.02 260	95.44 182	99.96 37	98.21 195	94.07 147	95.55 211	96.38 289	93.90 101	98.27 252	90.42 284	98.83 143	99.64 124

test-mter		96.39 154	95.93 156	97.78 161	97.02 260	95.44 182	99.96 37	98.21 195	91.81 236	95.55 211	96.38 289	95.17 53	98.27 252	90.42 284	98.83 143	99.64 124

gm-plane-assit					96.97 263	93.76 233			91.47 246		98.96 171		98.79 203	94.92 200

WB-MVSnew		92.90 252	92.77 243	93.26 322	96.95 264	93.63 237	99.71 178	98.16 205	91.49 243	94.28 228	98.14 233	81.33 278	96.48 344	79.47 372	95.46 224	89.68 398

QAPM		95.40 184	94.17 206	99.10 67	96.92 265	97.71 88	99.40 230	98.68 72	89.31 292	88.94 305	98.89 181	82.48 265	99.96 66	93.12 245	99.83 77	99.62 130

KD-MVS_2432*1600		88.00 338	86.10 342	93.70 311	96.91 266	94.04 225	97.17 365	97.12 312	84.93 360	81.96 370	92.41 382	92.48 142	94.51 385	79.23 373	52.68 417	92.56 368

miper_refine_blended		88.00 338	86.10 342	93.70 311	96.91 266	94.04 225	97.17 365	97.12 312	84.93 360	81.96 370	92.41 382	92.48 142	94.51 385	79.23 373	52.68 417	92.56 368

tpm2		95.47 182	95.18 180	96.35 221	96.91 266	91.70 287	96.96 371	97.93 226	88.04 321	98.44 129	95.40 326	93.32 115	97.97 269	94.00 222	95.61 222	99.38 175

FMVSNet5		88.32 334	87.47 336	90.88 350	96.90 269	88.39 345	97.28 362	95.68 378	82.60 380	84.67 358	92.40 384	79.83 296	91.16 406	76.39 388	81.51 340	93.09 360

3Dnovator+	91.53 11	96.31 158	95.24 177	99.52 28	96.88 270	98.64 54	99.72 175	98.24 191	95.27 101	88.42 317	98.98 167	82.76 264	99.94 82	97.10 163	99.83 77	99.96 67

Patchmatch-test		92.65 260	91.50 270	96.10 227	96.85 271	90.49 311	91.50 407	97.19 303	82.76 379	90.23 271	95.59 315	95.02 59	98.00 268	77.41 383	96.98 193	99.82 95

MVS		96.60 145	95.56 169	99.72 13	96.85 271	99.22 20	98.31 336	98.94 41	91.57 241	90.90 266	99.61 108	86.66 230	99.96 66	97.36 156	99.88 73	99.99 23

3Dnovator	91.47 12	96.28 161	95.34 174	99.08 70	96.82 273	97.47 101	99.45 227	98.81 61	95.52 95	89.39 292	99.00 164	81.97 268	99.95 74	97.27 158	99.83 77	99.84 93

EI-MVSNet		93.73 232	93.40 230	94.74 266	96.80 274	92.69 260	99.06 271	97.67 249	88.96 301	91.39 260	99.02 160	88.75 207	97.30 298	91.07 268	87.85 294	94.22 302

CVMVSNet		94.68 205	94.94 189	93.89 305	96.80 274	86.92 358	99.06 271	98.98 38	94.45 124	94.23 230	99.02 160	85.60 238	95.31 375	90.91 274	95.39 227	99.43 171

IterMVS-LS		92.69 258	92.11 257	94.43 285	96.80 274	92.74 257	99.45 227	96.89 340	88.98 299	89.65 286	95.38 329	88.77 206	96.34 350	90.98 272	82.04 336	94.22 302
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS		90.91 293	90.17 295	93.12 325	96.78 277	90.42 314	98.89 293	97.05 323	89.03 296	86.49 342	95.42 325	76.59 323	95.02 377	87.22 321	84.09 322	93.93 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 132	95.96 153	99.48 34	96.74 278	98.52 58	98.31 336	98.86 53	95.82 85	89.91 277	98.98 167	87.49 218	99.96 66	97.80 143	99.73 87	99.96 67

IterMVS-SCA-FT		90.85 296	90.16 296	92.93 330	96.72 279	89.96 322	98.89 293	96.99 327	88.95 302	86.63 339	95.67 311	76.48 325	95.00 378	87.04 324	84.04 325	93.84 339

MVS-HIRNet		86.22 345	83.19 358	95.31 249	96.71 280	90.29 315	92.12 404	97.33 290	62.85 412	86.82 336	70.37 417	69.37 364	97.49 289	75.12 391	97.99 171	98.15 242

VDDNet		93.12 247	91.91 262	96.76 207	96.67 281	92.65 263	98.69 315	98.21 195	82.81 378	97.75 157	99.28 139	61.57 395	99.48 167	98.09 128	94.09 245	98.15 242

dmvs_re		93.20 244	93.15 235	93.34 318	96.54 282	83.81 375	98.71 312	98.51 112	91.39 252	92.37 252	98.56 212	78.66 308	97.83 277	93.89 224	89.74 266	98.38 238

MIMVSNet		90.30 309	88.67 323	95.17 253	96.45 283	91.64 289	92.39 403	97.15 309	85.99 347	90.50 269	93.19 378	66.95 375	94.86 382	82.01 361	93.43 253	99.01 214

CR-MVSNet		93.45 241	92.62 245	95.94 231	96.29 284	92.66 261	92.01 405	96.23 366	92.62 205	96.94 177	93.31 376	91.04 169	96.03 363	79.23 373	95.96 211	99.13 204

RPMNet		89.76 321	87.28 337	97.19 195	96.29 284	92.66 261	92.01 405	98.31 180	70.19 411	96.94 177	85.87 410	87.25 222	99.78 131	62.69 412	95.96 211	99.13 204

tt0805		91.28 286	90.18 294	94.60 272	96.26 286	87.55 351	98.39 334	98.72 67	89.00 298	89.22 298	98.47 220	62.98 390	98.96 195	90.57 280	88.00 293	97.28 261

Patchmtry		89.70 322	88.49 325	93.33 319	96.24 287	89.94 325	91.37 408	96.23 366	78.22 394	87.69 324	93.31 376	91.04 169	96.03 363	80.18 371	82.10 335	94.02 322

test_vis1_rt		86.87 343	86.05 345	89.34 366	96.12 288	78.07 400	99.87 111	83.54 425	92.03 229	78.21 389	89.51 396	45.80 411	99.91 95	96.25 179	93.11 258	90.03 395

JIA-IIPM		91.76 280	90.70 281	94.94 259	96.11 289	87.51 352	93.16 401	98.13 210	75.79 400	97.58 159	77.68 415	92.84 131	97.97 269	88.47 306	96.54 198	99.33 185

OpenMVS	90.15 15	94.77 201	93.59 221	98.33 129	96.07 290	97.48 100	99.56 207	98.57 92	90.46 274	86.51 341	98.95 176	78.57 309	99.94 82	93.86 225	99.74 86	97.57 257

PAPM		98.60 33	98.42 34	99.14 61	96.05 291	98.96 26	99.90 96	99.35 24	96.68 61	98.35 135	99.66 100	96.45 33	98.51 223	99.45 51	99.89 70	99.96 67

CLD-MVS		94.06 223	93.90 214	94.55 276	96.02 292	90.69 305	99.98 15	97.72 245	96.62 65	91.05 265	98.85 190	77.21 314	98.47 224	98.11 126	89.51 272	94.48 281
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 306	88.75 322	95.25 251	95.99 293	90.16 318	91.22 409	97.54 266	76.80 396	97.26 169	86.01 409	91.88 156	96.07 362	66.16 408	95.91 215	99.51 160

ACMH+	89.98 16	90.35 307	89.54 306	92.78 334	95.99 293	86.12 362	98.81 304	97.18 305	89.38 291	83.14 366	97.76 249	68.42 369	98.43 229	89.11 298	86.05 306	93.78 342

DeepMVS_CX				82.92 387	95.98 295	58.66 418		96.01 371	92.72 198	78.34 388	95.51 320	58.29 400	98.08 263	82.57 356	85.29 311	92.03 376

ACMP	92.05 9	92.74 256	92.42 254	93.73 307	95.91 296	88.72 338	99.81 142	97.53 268	94.13 143	87.00 335	98.23 231	74.07 346	98.47 224	96.22 180	88.86 279	93.99 327
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 236	93.03 237	95.35 246	95.86 297	86.94 357	99.87 111	96.36 364	96.85 52	99.54 60	98.79 192	52.41 407	99.83 124	98.64 99	98.97 137	99.29 191

HQP-NCC					95.78 298		99.87 111		96.82 54	93.37 237

ACMP_Plane					95.78 298		99.87 111		96.82 54	93.37 237

HQP-MVS		94.61 207	94.50 197	94.92 260	95.78 298	91.85 279	99.87 111	97.89 231	96.82 54	93.37 237	98.65 202	80.65 288	98.39 235	97.92 137	89.60 267	94.53 277

NP-MVS					95.77 301	91.79 281					98.65 202

test_fmvsmconf0.1_n		97.74 88	97.44 90	98.64 102	95.76 302	96.20 153	99.94 73	98.05 216	98.17 10	98.89 105	99.42 126	87.65 216	99.90 97	99.50 47	99.60 101	99.82 95

plane_prior6					95.76 302	91.72 286						80.47 292

ACMM	91.95 10	92.88 253	92.52 252	93.98 301	95.75 304	89.08 335	99.77 152	97.52 270	93.00 185	89.95 276	97.99 240	76.17 329	98.46 227	93.63 236	88.87 278	94.39 289
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 226	92.84 239	96.80 205	95.73 305	93.57 238	99.88 108	97.24 301	92.57 210	92.92 244	96.66 281	78.73 307	97.67 283	87.75 314	94.06 246	99.17 199

plane_prior1					95.73 305

jason		97.24 111	96.86 116	98.38 128	95.73 305	97.32 105	99.97 30	97.40 282	95.34 99	98.60 123	99.54 118	87.70 215	98.56 220	97.94 136	99.47 111	99.25 195
jason: jason.
mmtdpeth		88.52 332	87.75 334	90.85 352	95.71 308	83.47 378	98.94 287	94.85 392	88.78 307	97.19 171	89.58 395	63.29 388	98.97 193	98.54 104	62.86 411	90.10 394

HQP_MVS		94.49 212	94.36 200	94.87 261	95.71 308	91.74 283	99.84 130	97.87 233	96.38 72	93.01 242	98.59 207	80.47 292	98.37 241	97.79 146	89.55 270	94.52 279

plane_prior7					95.71 308	91.59 291

ITE_SJBPF				92.38 336	95.69 311	85.14 367		95.71 377	92.81 193	89.33 295	98.11 234	70.23 362	98.42 230	85.91 336	88.16 291	93.59 350

fmvsm_s_conf0.1_n_a		97.09 119	96.90 113	97.63 173	95.65 312	94.21 222	99.83 137	98.50 118	96.27 77	99.65 43	99.64 103	84.72 248	99.93 90	99.04 70	98.84 142	98.74 227

ACMH	89.72 17	90.64 300	89.63 303	93.66 313	95.64 313	88.64 341	98.55 322	97.45 275	89.03 296	81.62 373	97.61 250	69.75 363	98.41 231	89.37 295	87.62 298	93.92 333
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 141	96.49 133	97.37 188	95.63 314	95.96 162	99.74 164	98.88 51	92.94 187	91.61 258	98.97 169	97.72 6	98.62 218	94.83 204	98.08 169	97.53 258

FMVSNet1		88.50 333	86.64 340	94.08 294	95.62 315	91.97 274	98.43 330	96.95 332	83.00 376	86.08 349	94.72 353	59.09 399	96.11 358	81.82 363	84.07 323	94.17 306

LPG-MVS_test		92.96 250	92.71 244	93.71 309	95.43 316	88.67 339	99.75 161	97.62 255	92.81 193	90.05 272	98.49 216	75.24 336	98.40 233	95.84 186	89.12 274	94.07 319

LGP-MVS_train				93.71 309	95.43 316	88.67 339		97.62 255	92.81 193	90.05 272	98.49 216	75.24 336	98.40 233	95.84 186	89.12 274	94.07 319

tpm		93.70 234	93.41 229	94.58 274	95.36 318	87.41 353	97.01 369	96.90 339	90.85 265	96.72 185	94.14 368	90.40 183	96.84 329	90.75 278	88.54 286	99.51 160

D2MVS		92.76 255	92.59 250	93.27 321	95.13 319	89.54 329	99.69 183	99.38 22	92.26 222	87.59 326	94.61 359	85.05 246	97.79 278	91.59 262	88.01 292	92.47 371

VPA-MVSNet		92.70 257	91.55 269	96.16 225	95.09 320	96.20 153	98.88 295	99.00 36	91.02 262	91.82 257	95.29 336	76.05 331	97.96 271	95.62 190	81.19 342	94.30 296

LTVRE_ROB	88.28 18	90.29 310	89.05 317	94.02 297	95.08 321	90.15 319	97.19 364	97.43 277	84.91 362	83.99 362	97.06 267	74.00 347	98.28 250	84.08 345	87.71 296	93.62 349
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		87.87 340	86.51 341	91.94 341	95.05 322	85.57 365	97.65 357	94.08 401	84.40 366	81.82 372	96.85 276	62.14 393	98.33 244	80.25 370	86.37 305	91.91 378

test0.0.03 1		93.86 225	93.61 218	94.64 270	95.02 323	92.18 272	99.93 80	98.58 90	94.07 147	87.96 321	98.50 215	93.90 101	94.96 379	81.33 364	93.17 256	96.78 264

UniMVSNet (Re)		93.07 249	92.13 256	95.88 232	94.84 324	96.24 152	99.88 108	98.98 38	92.49 215	89.25 296	95.40 326	87.09 224	97.14 307	93.13 244	78.16 366	94.26 298

USDC		90.00 317	88.96 318	93.10 327	94.81 325	88.16 347	98.71 312	95.54 382	93.66 166	83.75 364	97.20 261	65.58 380	98.31 246	83.96 348	87.49 300	92.85 365

VPNet		91.81 274	90.46 285	95.85 234	94.74 326	95.54 180	98.98 282	98.59 88	92.14 224	90.77 268	97.44 254	68.73 367	97.54 288	94.89 203	77.89 368	94.46 282

FIs		94.10 222	93.43 226	96.11 226	94.70 327	96.82 126	99.58 202	98.93 45	92.54 211	89.34 294	97.31 258	87.62 217	97.10 311	94.22 221	86.58 303	94.40 288

UniMVSNet_ETH3D		90.06 316	88.58 324	94.49 280	94.67 328	88.09 348	97.81 356	97.57 263	83.91 369	88.44 313	97.41 255	57.44 401	97.62 285	91.41 263	88.59 285	97.77 251

UniMVSNet_NR-MVSNet		92.95 251	92.11 257	95.49 240	94.61 329	95.28 190	99.83 137	99.08 33	91.49 243	89.21 299	96.86 275	87.14 223	96.73 335	93.20 240	77.52 371	94.46 282

test_fmvs2		89.47 325	89.70 302	88.77 373	94.54 330	75.74 401	99.83 137	94.70 397	94.71 116	91.08 263	96.82 280	54.46 404	97.78 280	92.87 247	88.27 289	92.80 366

MonoMVSNet		94.82 196	94.43 198	95.98 229	94.54 330	90.73 304	99.03 278	97.06 320	93.16 181	93.15 241	95.47 323	88.29 210	97.57 286	97.85 141	91.33 264	99.62 130

WR-MVS		92.31 266	91.25 274	95.48 243	94.45 332	95.29 189	99.60 199	98.68 72	90.10 281	88.07 320	96.89 273	80.68 287	96.80 333	93.14 243	79.67 359	94.36 290

nrg030		93.51 238	92.53 251	96.45 216	94.36 333	97.20 110	99.81 142	97.16 308	91.60 240	89.86 279	97.46 253	86.37 233	97.68 282	95.88 185	80.31 355	94.46 282

tfpnnormal		89.29 328	87.61 335	94.34 288	94.35 334	94.13 224	98.95 286	98.94 41	83.94 367	84.47 359	95.51 320	74.84 341	97.39 291	77.05 386	80.41 353	91.48 381

FC-MVSNet-test		93.81 228	93.15 235	95.80 236	94.30 335	96.20 153	99.42 229	98.89 49	92.33 221	89.03 304	97.27 260	87.39 220	96.83 331	93.20 240	86.48 304	94.36 290

MS-PatchMatch		90.65 299	90.30 290	91.71 346	94.22 336	85.50 366	98.24 340	97.70 246	88.67 310	86.42 344	96.37 291	67.82 372	98.03 267	83.62 350	99.62 95	91.60 379

WR-MVS_H		91.30 284	90.35 288	94.15 291	94.17 337	92.62 264	99.17 260	98.94 41	88.87 305	86.48 343	94.46 364	84.36 252	96.61 340	88.19 308	78.51 364	93.21 359

DU-MVS		92.46 263	91.45 272	95.49 240	94.05 338	95.28 190	99.81 142	98.74 66	92.25 223	89.21 299	96.64 283	81.66 273	96.73 335	93.20 240	77.52 371	94.46 282

NR-MVSNet		91.56 282	90.22 292	95.60 238	94.05 338	95.76 168	98.25 339	98.70 69	91.16 257	80.78 378	96.64 283	83.23 262	96.57 341	91.41 263	77.73 370	94.46 282

CP-MVSNet		91.23 288	90.22 292	94.26 289	93.96 340	92.39 268	99.09 264	98.57 92	88.95 302	86.42 344	96.57 286	79.19 302	96.37 348	90.29 287	78.95 361	94.02 322

XXY-MVS		91.82 273	90.46 285	95.88 232	93.91 341	95.40 186	98.87 298	97.69 248	88.63 312	87.87 322	97.08 265	74.38 345	97.89 275	91.66 261	84.07 323	94.35 293

PS-CasMVS		90.63 301	89.51 308	93.99 300	93.83 342	91.70 287	98.98 282	98.52 109	88.48 314	86.15 348	96.53 288	75.46 334	96.31 352	88.83 300	78.86 363	93.95 330

test_0402		85.58 347	83.94 352	90.50 356	93.81 343	85.04 368	98.55 322	95.20 389	76.01 398	79.72 383	95.13 340	64.15 386	96.26 354	66.04 409	86.88 302	90.21 392

XVG-ACMP-BASELINE		91.22 289	90.75 280	92.63 335	93.73 344	85.61 364	98.52 326	97.44 276	92.77 197	89.90 278	96.85 276	66.64 377	98.39 235	92.29 252	88.61 283	93.89 335

TranMVSNet+NR-MVSNet		91.68 281	90.61 284	94.87 261	93.69 345	93.98 228	99.69 183	98.65 76	91.03 261	88.44 313	96.83 279	80.05 295	96.18 356	90.26 288	76.89 379	94.45 287

TransMVSNet (Re)		87.25 341	85.28 348	93.16 324	93.56 346	91.03 296	98.54 324	94.05 403	83.69 371	81.09 376	96.16 297	75.32 335	96.40 347	76.69 387	68.41 399	92.06 375

v10		90.25 311	88.82 320	94.57 275	93.53 347	93.43 243	99.08 266	96.87 342	85.00 359	87.34 333	94.51 360	80.93 283	97.02 321	82.85 355	79.23 360	93.26 357

testgi		89.01 330	88.04 331	91.90 342	93.49 348	84.89 370	99.73 171	95.66 379	93.89 161	85.14 354	98.17 232	59.68 398	94.66 384	77.73 382	88.88 277	96.16 273

v8		90.54 303	89.17 313	94.66 269	93.43 349	93.40 245	99.20 257	96.94 336	85.76 350	87.56 327	94.51 360	81.96 269	97.19 304	84.94 342	78.25 365	93.38 355

V42		91.28 286	90.12 297	94.74 266	93.42 350	93.46 242	99.68 185	97.02 324	87.36 329	89.85 281	95.05 343	81.31 279	97.34 294	87.34 319	80.07 357	93.40 353

pm-mvs1		89.36 327	87.81 333	94.01 298	93.40 351	91.93 277	98.62 320	96.48 362	86.25 345	83.86 363	96.14 298	73.68 348	97.04 317	86.16 333	75.73 384	93.04 362

v1144		91.09 290	89.83 299	94.87 261	93.25 352	93.69 236	99.62 196	96.98 329	86.83 339	89.64 287	94.99 348	80.94 282	97.05 314	85.08 341	81.16 343	93.87 337

v1192		90.62 302	89.25 312	94.72 268	93.13 353	93.07 249	99.50 217	97.02 324	86.33 344	89.56 290	95.01 345	79.22 301	97.09 313	82.34 359	81.16 343	94.01 324

v2v482		91.30 284	90.07 298	95.01 256	93.13 353	93.79 231	99.77 152	97.02 324	88.05 320	89.25 296	95.37 330	80.73 286	97.15 306	87.28 320	80.04 358	94.09 318

OPM-MVS		93.21 243	92.80 241	94.44 283	93.12 355	90.85 303	99.77 152	97.61 258	96.19 80	91.56 259	98.65 202	75.16 340	98.47 224	93.78 232	89.39 273	93.99 327
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 297	89.52 307	94.59 273	93.11 356	92.77 255	99.56 207	96.99 327	86.38 343	89.82 282	94.95 350	80.50 291	97.10 311	83.98 347	80.41 353	93.90 334

PEN-MVS		90.19 313	89.06 316	93.57 314	93.06 357	90.90 301	99.06 271	98.47 121	88.11 319	85.91 350	96.30 293	76.67 321	95.94 366	87.07 323	76.91 378	93.89 335

v1240		90.20 312	88.79 321	94.44 283	93.05 358	92.27 270	99.38 235	96.92 338	85.89 348	89.36 293	94.87 352	77.89 313	97.03 319	80.66 367	81.08 346	94.01 324

v148		90.70 298	89.63 303	93.92 302	92.97 359	90.97 297	99.75 161	96.89 340	87.51 326	88.27 318	95.01 345	81.67 272	97.04 317	87.40 318	77.17 376	93.75 343

v1921920		90.46 304	89.12 314	94.50 279	92.96 360	92.46 266	99.49 219	96.98 329	86.10 346	89.61 289	95.30 333	78.55 310	97.03 319	82.17 360	80.89 351	94.01 324

MVStest1		85.03 353	82.76 362	91.83 343	92.95 361	89.16 334	98.57 321	94.82 393	71.68 409	68.54 409	95.11 342	83.17 263	95.66 369	74.69 392	65.32 406	90.65 388

Baseline_NR-MVSNet		90.33 308	89.51 308	92.81 333	92.84 362	89.95 323	99.77 152	93.94 404	84.69 364	89.04 303	95.66 312	81.66 273	96.52 342	90.99 271	76.98 377	91.97 377

test_method		80.79 369	79.70 373	84.08 384	92.83 363	67.06 410	99.51 215	95.42 383	54.34 416	81.07 377	93.53 373	44.48 412	92.22 403	78.90 377	77.23 375	92.94 363

pmmvs4		92.10 270	91.07 278	95.18 252	92.82 364	94.96 200	99.48 221	96.83 344	87.45 328	88.66 310	96.56 287	83.78 257	96.83 331	89.29 296	84.77 317	93.75 343

LF4IMVS		89.25 329	88.85 319	90.45 358	92.81 365	81.19 392	98.12 346	94.79 394	91.44 247	86.29 346	97.11 263	65.30 383	98.11 261	88.53 305	85.25 312	92.07 374

DTE-MVSNet		89.40 326	88.24 329	92.88 331	92.66 366	89.95 323	99.10 263	98.22 194	87.29 330	85.12 355	96.22 295	76.27 328	95.30 376	83.56 351	75.74 383	93.41 352

EU-MVSNet		90.14 315	90.34 289	89.54 365	92.55 367	81.06 393	98.69 315	98.04 217	91.41 251	86.59 340	96.84 278	80.83 285	93.31 396	86.20 332	81.91 337	94.26 298

APD_test1		81.15 368	80.92 369	81.86 388	92.45 368	59.76 417	96.04 387	93.61 407	73.29 407	77.06 392	96.64 283	44.28 413	96.16 357	72.35 396	82.52 331	89.67 399

our_test_3		90.39 305	89.48 310	93.12 325	92.40 369	89.57 328	99.33 241	96.35 365	87.84 324	85.30 353	94.99 348	84.14 255	96.09 361	80.38 368	84.56 318	93.71 348

ppachtmachnet_test		89.58 324	88.35 327	93.25 323	92.40 369	90.44 313	99.33 241	96.73 351	85.49 355	85.90 351	95.77 307	81.09 281	96.00 365	76.00 390	82.49 332	93.30 356

v7n		89.65 323	88.29 328	93.72 308	92.22 371	90.56 310	99.07 270	97.10 314	85.42 357	86.73 337	94.72 353	80.06 294	97.13 308	81.14 365	78.12 367	93.49 351

dmvs_testset		83.79 362	86.07 344	76.94 392	92.14 372	48.60 427	96.75 374	90.27 417	89.48 290	78.65 386	98.55 214	79.25 300	86.65 415	66.85 406	82.69 330	95.57 275

PS-MVSNAJss		93.64 235	93.31 232	94.61 271	92.11 373	92.19 271	99.12 262	97.38 283	92.51 214	88.45 312	96.99 271	91.20 164	97.29 301	94.36 215	87.71 296	94.36 290

pmmvs5		90.17 314	89.09 315	93.40 317	92.10 374	89.77 326	99.74 164	95.58 381	85.88 349	87.24 334	95.74 308	73.41 349	96.48 344	88.54 304	83.56 327	93.95 330

N_pmnet		80.06 372	80.78 370	77.89 391	91.94 375	45.28 429	98.80 306	56.82 431	78.10 395	80.08 381	93.33 374	77.03 316	95.76 368	68.14 404	82.81 329	92.64 367

test_djsdf		92.83 254	92.29 255	94.47 281	91.90 376	92.46 266	99.55 209	97.27 298	91.17 255	89.96 275	96.07 302	81.10 280	96.89 326	94.67 210	88.91 276	94.05 321

SixPastTwentyTwo		88.73 331	88.01 332	90.88 350	91.85 377	82.24 384	98.22 343	95.18 390	88.97 300	82.26 369	96.89 273	71.75 354	96.67 338	84.00 346	82.98 328	93.72 347

K. test v3		88.05 337	87.24 338	90.47 357	91.82 378	82.23 385	98.96 285	97.42 279	89.05 295	76.93 394	95.60 314	68.49 368	95.42 372	85.87 337	81.01 349	93.75 343

OurMVSNet-221017-0		89.81 320	89.48 310	90.83 353	91.64 379	81.21 391	98.17 345	95.38 385	91.48 245	85.65 352	97.31 258	72.66 350	97.29 301	88.15 309	84.83 316	93.97 329

mvs_tets		91.81 274	91.08 277	94.00 299	91.63 380	90.58 309	98.67 317	97.43 277	92.43 216	87.37 332	97.05 268	71.76 353	97.32 296	94.75 207	88.68 282	94.11 317

Gipuma		66.95 385	65.00 385	72.79 397	91.52 381	67.96 409	66.16 420	95.15 391	47.89 418	58.54 415	67.99 420	29.74 417	87.54 414	50.20 419	77.83 369	62.87 420
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 154	95.74 162	98.32 130	91.47 382	95.56 179	99.84 130	97.30 293	97.74 21	97.89 151	99.35 137	79.62 297	99.85 114	99.25 60	99.24 126	99.55 147

jajsoiax		91.92 272	91.18 275	94.15 291	91.35 383	90.95 300	99.00 281	97.42 279	92.61 206	87.38 331	97.08 265	72.46 351	97.36 292	94.53 213	88.77 280	94.13 316

MDA-MVSNet-bldmvs		84.09 360	81.52 367	91.81 344	91.32 384	88.00 350	98.67 317	95.92 373	80.22 389	55.60 418	93.32 375	68.29 370	93.60 394	73.76 393	76.61 380	93.82 341

MVP-Stereo		90.93 292	90.45 287	92.37 337	91.25 385	88.76 336	98.05 350	96.17 368	87.27 331	84.04 360	95.30 333	78.46 311	97.27 303	83.78 349	99.70 89	91.09 382
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 349	83.32 357	92.10 339	90.96 386	88.58 342	99.20 257	96.52 360	79.70 391	57.12 417	92.69 380	79.11 303	93.86 391	77.10 385	77.46 373	93.86 338

YYNet1		85.50 350	83.33 356	92.00 340	90.89 387	88.38 346	99.22 256	96.55 359	79.60 392	57.26 416	92.72 379	79.09 305	93.78 392	77.25 384	77.37 374	93.84 339

anonymousdsp		91.79 279	90.92 279	94.41 286	90.76 388	92.93 254	98.93 289	97.17 306	89.08 294	87.46 330	95.30 333	78.43 312	96.92 324	92.38 251	88.73 281	93.39 354

lessismore_v0				90.53 355	90.58 389	80.90 394		95.80 374		77.01 393	95.84 305	66.15 379	96.95 322	83.03 354	75.05 385	93.74 346

EG-PatchMatch MVS		85.35 351	83.81 354	89.99 363	90.39 390	81.89 387	98.21 344	96.09 370	81.78 383	74.73 400	93.72 372	51.56 409	97.12 310	79.16 376	88.61 283	90.96 385

EGC-MVSNET		69.38 378	63.76 388	86.26 381	90.32 391	81.66 390	96.24 383	93.85 405	0.99 428	3.22 429	92.33 385	52.44 406	92.92 399	59.53 415	84.90 315	84.21 409

CMPMVS	61.59 21	84.75 356	85.14 349	83.57 385	90.32 391	62.54 413	96.98 370	97.59 262	74.33 405	69.95 406	96.66 281	64.17 385	98.32 245	87.88 313	88.41 288	89.84 397
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 359	82.92 360	89.21 367	90.03 393	82.60 381	96.89 373	95.62 380	80.59 387	75.77 399	89.17 397	65.04 384	94.79 383	72.12 397	81.02 348	90.23 391

pmmvs6		85.69 346	83.84 353	91.26 349	90.00 394	84.41 373	97.82 355	96.15 369	75.86 399	81.29 375	95.39 328	61.21 396	96.87 328	83.52 352	73.29 387	92.50 370

ttmdpeth		88.23 336	87.06 339	91.75 345	89.91 395	87.35 354	98.92 292	95.73 376	87.92 322	84.02 361	96.31 292	68.23 371	96.84 329	86.33 331	76.12 381	91.06 383

DSMNet-mixed		88.28 335	88.24 329	88.42 375	89.64 396	75.38 403	98.06 349	89.86 418	85.59 354	88.20 319	92.14 386	76.15 330	91.95 404	78.46 379	96.05 209	97.92 247

UnsupCasMVSNet_eth		85.52 348	83.99 350	90.10 361	89.36 397	83.51 377	96.65 375	97.99 219	89.14 293	75.89 398	93.83 370	63.25 389	93.92 389	81.92 362	67.90 402	92.88 364

Anonymous20231206		86.32 344	85.42 347	89.02 369	89.11 398	80.53 397	99.05 275	95.28 386	85.43 356	82.82 367	93.92 369	74.40 344	93.44 395	66.99 405	81.83 338	93.08 361

Anonymous20240521		85.15 352	83.81 354	89.16 368	88.32 399	82.69 380	98.80 306	95.74 375	79.72 390	81.53 374	90.99 389	65.38 382	94.16 387	72.69 395	81.11 345	90.63 389

OpenMVS_ROB	79.82 20	83.77 363	81.68 366	90.03 362	88.30 400	82.82 379	98.46 327	95.22 388	73.92 406	76.00 397	91.29 388	55.00 403	96.94 323	68.40 403	88.51 287	90.34 390

test20.03		84.72 357	83.99 350	86.91 379	88.19 401	80.62 396	98.88 295	95.94 372	88.36 316	78.87 384	94.62 358	68.75 366	89.11 410	66.52 407	75.82 382	91.00 384

KD-MVS_self_test		83.59 364	82.06 364	88.20 376	86.93 402	80.70 395	97.21 363	96.38 363	82.87 377	82.49 368	88.97 398	67.63 373	92.32 402	73.75 394	62.30 413	91.58 380

MIMVSNet1		82.58 365	80.51 371	88.78 371	86.68 403	84.20 374	96.65 375	95.41 384	78.75 393	78.59 387	92.44 381	51.88 408	89.76 409	65.26 410	78.95 361	92.38 373

CL-MVSNet_self_test		84.50 358	83.15 359	88.53 374	86.00 404	81.79 388	98.82 303	97.35 286	85.12 358	83.62 365	90.91 391	76.66 322	91.40 405	69.53 401	60.36 414	92.40 372

UnsupCasMVSNet_bld		79.97 374	77.03 379	88.78 371	85.62 405	81.98 386	93.66 399	97.35 286	75.51 402	70.79 405	83.05 412	48.70 410	94.91 381	78.31 380	60.29 415	89.46 402

mvs5depth		84.87 354	82.90 361	90.77 354	85.59 406	84.84 371	91.10 410	93.29 409	83.14 374	85.07 356	94.33 366	62.17 392	97.32 296	78.83 378	72.59 390	90.14 393

Patchmatch-RL test		86.90 342	85.98 346	89.67 364	84.45 407	75.59 402	89.71 413	92.43 411	86.89 338	77.83 391	90.94 390	94.22 90	93.63 393	87.75 314	69.61 394	99.79 100

pmmvs-eth3d		84.03 361	81.97 365	90.20 360	84.15 408	87.09 356	98.10 348	94.73 396	83.05 375	74.10 402	87.77 404	65.56 381	94.01 388	81.08 366	69.24 396	89.49 401

test_fmvs3		79.99 373	80.17 372	79.45 390	84.02 409	62.83 411	99.05 275	93.49 408	88.29 318	80.06 382	86.65 407	28.09 419	88.00 411	88.63 301	73.27 388	87.54 407

PM-MVS		80.47 370	78.88 375	85.26 382	83.79 410	72.22 405	95.89 390	91.08 415	85.71 353	76.56 396	88.30 400	36.64 415	93.90 390	82.39 358	69.57 395	89.66 400

new-patchmatchnet		81.19 367	79.34 374	86.76 380	82.86 411	80.36 398	97.92 352	95.27 387	82.09 382	72.02 403	86.87 406	62.81 391	90.74 408	71.10 398	63.08 410	89.19 404

mvsany_test3		82.12 366	81.14 368	85.06 383	81.87 412	70.41 407	97.09 367	92.14 412	91.27 254	77.84 390	88.73 399	39.31 414	95.49 370	90.75 278	71.24 391	89.29 403

WB-MVS		76.28 376	77.28 378	73.29 396	81.18 413	54.68 421	97.87 354	94.19 400	81.30 384	69.43 407	90.70 392	77.02 317	82.06 419	35.71 424	68.11 401	83.13 410

test_f		78.40 375	77.59 377	80.81 389	80.82 414	62.48 414	96.96 371	93.08 410	83.44 372	74.57 401	84.57 411	27.95 420	92.63 400	84.15 344	72.79 389	87.32 408

SSC-MVS		75.42 377	76.40 380	72.49 400	80.68 415	53.62 422	97.42 359	94.06 402	80.42 388	68.75 408	90.14 394	76.54 324	81.66 420	33.25 425	66.34 405	82.19 411

pmmvs3		80.27 371	77.77 376	87.76 378	80.32 416	82.43 383	98.23 342	91.97 413	72.74 408	78.75 385	87.97 403	57.30 402	90.99 407	70.31 399	62.37 412	89.87 396

testf1		68.38 381	66.92 382	72.78 398	78.80 417	50.36 424	90.95 411	87.35 423	55.47 414	58.95 413	88.14 401	20.64 424	87.60 412	57.28 416	64.69 407	80.39 413

APD_test2		68.38 381	66.92 382	72.78 398	78.80 417	50.36 424	90.95 411	87.35 423	55.47 414	58.95 413	88.14 401	20.64 424	87.60 412	57.28 416	64.69 407	80.39 413

ambc				83.23 386	77.17 419	62.61 412	87.38 415	94.55 399		76.72 395	86.65 407	30.16 416	96.36 349	84.85 343	69.86 393	90.73 387

test_vis3_rt		68.82 379	66.69 384	75.21 395	76.24 420	60.41 416	96.44 378	68.71 430	75.13 403	50.54 421	69.52 419	16.42 429	96.32 351	80.27 369	66.92 404	68.89 417

TDRefinement		84.76 355	82.56 363	91.38 348	74.58 421	84.80 372	97.36 361	94.56 398	84.73 363	80.21 380	96.12 301	63.56 387	98.39 235	87.92 312	63.97 409	90.95 386

E-PMN		52.30 389	52.18 391	52.67 406	71.51 422	45.40 428	93.62 400	76.60 428	36.01 422	43.50 423	64.13 422	27.11 421	67.31 425	31.06 426	26.06 421	45.30 424

EMVS		51.44 391	51.22 393	52.11 407	70.71 423	44.97 430	94.04 396	75.66 429	35.34 424	42.40 424	61.56 425	28.93 418	65.87 426	27.64 427	24.73 422	45.49 423

PMMVS2		67.15 384	64.15 387	76.14 394	70.56 424	62.07 415	93.89 397	87.52 422	58.09 413	60.02 412	78.32 414	22.38 423	84.54 417	59.56 414	47.03 419	81.80 412

FPMVS		68.72 380	68.72 381	68.71 402	65.95 425	44.27 431	95.97 389	94.74 395	51.13 417	53.26 419	90.50 393	25.11 422	83.00 418	60.80 413	80.97 350	78.87 415

wuyk23d		20.37 395	20.84 398	18.99 410	65.34 426	27.73 433	50.43 421	7.67 434	9.50 427	8.01 428	6.34 428	6.13 432	26.24 427	23.40 428	10.69 426	2.99 425

LCM-MVSNet		67.77 383	64.73 386	76.87 393	62.95 427	56.25 420	89.37 414	93.74 406	44.53 419	61.99 411	80.74 413	20.42 426	86.53 416	69.37 402	59.50 416	87.84 405

MVE	53.74 22	51.54 390	47.86 394	62.60 404	59.56 428	50.93 423	79.41 418	77.69 427	35.69 423	36.27 425	61.76 424	5.79 433	69.63 423	37.97 423	36.61 420	67.24 418
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 387	52.24 390	67.66 403	49.27 429	56.82 419	83.94 416	82.02 426	70.47 410	33.28 426	64.54 421	17.23 428	69.16 424	45.59 421	23.85 423	77.02 416

tmp_tt		65.23 386	62.94 389	72.13 401	44.90 430	50.03 426	81.05 417	89.42 421	38.45 420	48.51 422	99.90 18	54.09 405	78.70 422	91.84 260	18.26 424	87.64 406

PMVS	49.05 23	53.75 388	51.34 392	60.97 405	40.80 431	34.68 432	74.82 419	89.62 420	37.55 421	28.67 427	72.12 416	7.09 431	81.63 421	43.17 422	68.21 400	66.59 419
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 393	39.14 396	33.31 408	19.94 432	24.83 434	98.36 335	9.75 433	15.53 426	51.31 420	87.14 405	19.62 427	17.74 428	47.10 420	3.47 427	57.36 421

testmvs		40.60 392	44.45 395	29.05 409	19.49 433	14.11 435	99.68 185	18.47 432	20.74 425	64.59 410	98.48 219	10.95 430	17.09 429	56.66 418	11.01 425	55.94 422

mmdepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

monomultidepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

test_blank		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.02 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

eth-test2					0.00 434

eth-test					0.00 434

uanet_test		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

DCPMVS		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

cdsmvs_eth3d_5k		23.43 394	31.24 397	0.00 411	0.00 434	0.00 436	0.00 422	98.09 211	0.00 429	0.00 430	99.67 98	83.37 260	0.00 430	0.00 429	0.00 428	0.00 426

pcd_1.5k_mvsjas		7.60 397	10.13 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	91.20 164	0.00 430	0.00 429	0.00 428	0.00 426

sosnet-low-res		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

sosnet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uncertanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

Regformer		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

ab-mvs-re		8.28 396	11.04 399	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	99.40 131	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 430	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

WAC-MVS						90.97 297								86.10 335

PC_three_1452									96.96 50	99.80 18	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 137	97.27 37	99.80 18	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 66	99.83 14	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 69				99.59 137

sam_mvs												94.25 89

MTGPA								98.28 185

test_post1							95.78 391				59.23 426	93.20 122	97.74 281	91.06 269

test_post											63.35 423	94.43 77	98.13 260

patchmatchnet-post											91.70 387	95.12 54	97.95 272

MTMP							99.87 111	96.49 361

test9_res														99.71 38	99.99 21	100.00 1

agg_prior2														99.48 49	100.00 1	100.00 1

test_prior4						98.05 73	99.94 73

test_prior2							99.95 56		95.78 86	99.73 35	99.76 66	96.00 37		99.78 27	100.00 1

旧先验2							99.46 226		94.21 142	99.85 10			99.95 74	96.96 169

新几何2							99.40 230

无先验							99.49 219	98.71 68	93.46 170				100.00 1	94.36 215		99.99 23

原ACMM2							99.90 96

testdata2													99.99 36	90.54 282

segment_acmp												96.68 29

testdata1							99.28 250		96.35 76

plane_prior5								97.87 233					98.37 241	97.79 146	89.55 270	94.52 279

plane_prior4											98.59 207

plane_prior3						91.64 289			96.63 63	93.01 242

plane_prior2							99.84 130		96.38 72

plane_prior						91.74 283	99.86 122		96.76 58						89.59 269

n2								0.00 435

nn								0.00 435

door-mid								89.69 419

test11								98.44 129

door								90.31 416

HQP5-MVS						91.85 279

BP-MVS														97.92 137

HQP4-MVS										93.37 237			98.39 235			94.53 277

HQP3-MVS								97.89 231							89.60 267

HQP2-MVS												80.65 288

MDTV_nov1_ep13_2view						96.26 148	96.11 385		91.89 232	98.06 145		94.40 79		94.30 218		99.67 118

ACMMP++_ref															87.04 301

ACMMP++															88.23 290

Test By Simon												92.82 133

High-resolution multi-view benchmark