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		97.23 101	96.80 108	98.51 107	99.99 1	95.60 165	99.09 252	98.84 58	93.32 167	96.74 170	99.72 83	86.04 222	100.00 1	98.01 118	99.43 111	99.94 74

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 15	98.69 68	98.20 7	99.93 1	99.98 2	96.82 22	100.00 1	99.75 28	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 76	98.47 2	99.13 86	99.92 13	96.38 30	100.00 1	99.74 30	100.00 1	100.00 1

mPP-MVS		98.39 47	98.20 46	98.97 75	99.97 3	96.92 113	99.95 53	98.38 159	95.04 99	98.61 113	99.80 51	93.39 101	100.00 1	98.64 91	100.00 1	99.98 48

CPTT-MVS		97.64 84	97.32 87	98.58 99	99.97 3	95.77 154	99.96 35	98.35 165	89.90 273	98.36 123	99.79 57	91.18 157	99.99 36	98.37 102	99.99 21	99.99 23

DP-MVS Recon		98.41 45	98.02 57	99.56 25	99.97 3	98.70 47	99.92 79	98.44 123	92.06 218	98.40 122	99.84 41	95.68 40	100.00 1	98.19 108	99.71 84	99.97 58

PAPR		98.52 35	98.16 49	99.58 24	99.97 3	98.77 41	99.95 53	98.43 131	95.35 93	98.03 135	99.75 71	94.03 87	99.98 43	98.11 113	99.83 73	99.99 23

HFP-MVS		98.56 32	98.37 36	99.14 60	99.96 8	97.43 95	99.95 53	98.61 82	94.77 107	99.31 77	99.85 30	94.22 80	100.00 1	98.70 86	99.98 32	99.98 48

region2R		98.54 33	98.37 36	99.05 67	99.96 8	97.18 102	99.96 35	98.55 98	94.87 105	99.45 65	99.85 30	94.07 86	100.00 1	98.67 88	100.00 1	99.98 48

ACMMPR		98.50 36	98.32 40	99.05 67	99.96 8	97.18 102	99.95 53	98.60 84	94.77 107	99.31 77	99.84 41	93.73 96	100.00 1	98.70 86	99.98 32	99.98 48

NCCC		99.37 2	99.25 2	99.71 14	99.96 8	99.15 21	99.97 28	98.62 81	98.02 13	99.90 3	99.95 3	97.33 16	100.00 1	99.54 39	100.00 1	100.00 1

CP-MVS		98.45 40	98.32 40	98.87 80	99.96 8	96.62 122	99.97 28	98.39 155	94.43 120	98.90 95	99.87 24	94.30 78	100.00 1	99.04 63	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 148	96.63 56	99.75 30	99.93 11	97.49 9

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 53	98.43 131					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 26	98.55 25	99.15 58	99.94 13	97.50 91	99.94 69	98.42 143	96.22 73	99.41 69	99.78 61	94.34 76	99.96 61	98.92 70	99.95 49	99.99 23

X-MVStestdata		93.83 212	92.06 245	99.15 58	99.94 13	97.50 91	99.94 69	98.42 143	96.22 73	99.41 69	41.37 408	94.34 76	99.96 61	98.92 70	99.95 49	99.99 23

test_prior				99.43 35	99.94 13	98.49 59		98.65 74					99.80 121			99.99 23

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 60	99.98 15	98.86 53	97.10 40	99.80 18	99.94 4	95.92 36	100.00 1	99.51 40	100.00 1	100.00 1

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 44	99.91 84	98.39 155	97.20 38	99.46 64	99.85 30	95.53 44	99.79 123	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 57	97.97 59	99.03 69	99.94 13	97.17 105	99.95 53	98.39 155	94.70 111	98.26 129	99.81 50	91.84 148	100.00 1	98.85 78	99.97 42	99.93 76
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDPH-MVS		98.65 28	98.36 38	99.49 32	99.94 13	98.73 45	99.87 106	98.33 170	93.97 145	99.76 29	99.87 24	94.99 58	99.75 132	98.55 95	100.00 1	99.98 48

PAPM_NR		98.12 60	97.93 64	98.70 88	99.94 13	96.13 144	99.82 136	98.43 131	94.56 115	97.52 148	99.70 87	94.40 71	99.98 43	97.00 152	99.98 32	99.99 23

MG-MVS		98.91 18	98.65 20	99.68 15	99.94 13	99.07 24	99.64 186	99.44 20	97.33 31	99.00 91	99.72 83	94.03 87	99.98 43	98.73 85	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	98.43 131	97.27 34	99.80 18	99.94 4	96.71 23	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 24	99.31 10		98.41 148	97.71 19	99.84 12				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 131	97.26 36	99.80 18	99.88 21	96.71 23	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 53	98.32 172	97.28 32	99.83 13	99.91 14	97.22 18	100.00 1	99.99 5	100.00 1	99.89 84
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	98.42 143	97.28 32	99.86 7	99.94 4	97.22 18

MSP-MVS		99.09 9	99.12 5	98.98 74	99.93 24	97.24 99	99.95 53	98.42 143	97.50 26	99.52 60	99.88 21	97.43 15	99.71 138	99.50 41	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 41		98.43 131		99.63 44			99.85 108

FOURS1					99.92 31	97.66 84	99.95 53	98.36 163	95.58 87	99.52 60

ZD-MVS					99.92 31	98.57 55		98.52 104	92.34 210	99.31 77	99.83 43	95.06 53	99.80 121	99.70 34	99.97 42

GST-MVS		98.27 52	97.97 59	99.17 54	99.92 31	97.57 86	99.93 76	98.39 155	94.04 143	98.80 100	99.74 78	92.98 116	100.00 1	98.16 110	99.76 81	99.93 76

TEST9					99.92 31	98.92 29	99.96 35	98.43 131	93.90 150	99.71 35	99.86 26	95.88 37	99.85 108

train_agg		98.88 19	98.65 20	99.59 23	99.92 31	98.92 29	99.96 35	98.43 131	94.35 125	99.71 35	99.86 26	95.94 34	99.85 108	99.69 35	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 35	98.43 131	94.35 125	99.69 37	99.85 30	95.94 34	99.85 108

PGM-MVS		98.34 48	98.13 51	98.99 73	99.92 31	97.00 109	99.75 156	99.50 18	93.90 150	99.37 74	99.76 65	93.24 110	100.00 1	97.75 136	99.96 46	99.98 48

ACMMP		97.74 79	97.44 81	98.66 91	99.92 31	96.13 144	99.18 247	99.45 19	94.84 106	96.41 180	99.71 85	91.40 151	99.99 36	97.99 120	98.03 158	99.87 87
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	98.43 131	96.48 61	99.80 18	99.93 11	97.44 13	100.00 1	99.92 12	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 148					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 148					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 92	97.56 25	99.44 66	99.85 30	95.38 47	100.00 1	99.31 51	99.99 21	99.87 87

APD-MVS		98.62 29	98.35 39	99.41 38	99.90 42	98.51 58	99.87 106	98.36 163	94.08 138	99.74 32	99.73 80	94.08 85	99.74 134	99.42 47	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 26	99.62 20	99.90 42	98.85 35	99.24 242	98.47 115	98.14 10	99.08 87	99.91 14	93.09 113	100.00 1	99.04 63	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 51	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	98.44 123	97.48 27	99.64 43	99.94 4	96.68 25	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		97.10 106	97.04 98	97.27 182	99.89 45	91.92 266	99.90 91	99.07 34	88.67 296	95.26 202	99.82 46	93.17 112	99.98 43	98.15 111	99.47 105	99.90 83

ZNCC-MVS		98.31 49	98.03 56	99.17 54	99.88 49	97.59 85	99.94 69	98.44 123	94.31 128	98.50 117	99.82 46	93.06 114	99.99 36	98.30 106	99.99 21	99.93 76

SR-MVS		98.46 39	98.30 43	98.93 78	99.88 49	97.04 108	99.84 126	98.35 165	94.92 103	99.32 76	99.80 51	93.35 103	99.78 125	99.30 52	99.95 49	99.96 64

9.14			98.38 34		99.87 51		99.91 84	98.33 170	93.22 170	99.78 27	99.89 19	94.57 68	99.85 108	99.84 22	99.97 42

SMA-MVS		98.76 24	98.48 29	99.62 20	99.87 51	98.87 33	99.86 118	98.38 159	93.19 171	99.77 28	99.94 4	95.54 42	100.00 1	99.74 30	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 45	98.21 45	99.03 69	99.86 53	97.10 107	99.98 15	98.80 62	90.78 259	99.62 47	99.78 61	95.30 48	100.00 1	99.80 25	99.93 60	99.99 23

MTAPA		98.29 51	97.96 62	99.30 43	99.85 54	97.93 74	99.39 223	98.28 179	95.76 82	97.18 158	99.88 21	92.74 124	100.00 1	98.67 88	99.88 69	99.99 23

LS3D		95.84 159	95.11 169	98.02 136	99.85 54	95.10 186	98.74 294	98.50 112	87.22 317	93.66 220	99.86 26	87.45 205	99.95 69	90.94 259	99.81 79	99.02 202

HPM-MVS		97.96 63	97.72 71	98.68 89	99.84 56	96.39 131	99.90 91	98.17 191	92.61 195	98.62 112	99.57 109	91.87 147	99.67 145	98.87 77	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 52	98.11 53	98.75 86	99.83 57	96.59 124	99.40 219	98.51 107	95.29 95	98.51 116	99.76 65	93.60 100	99.71 138	98.53 96	99.52 100	99.95 71

save fliter					99.82 58	98.79 39	99.96 35	98.40 152	97.66 21

PLC	95.54 3	97.93 65	97.89 67	98.05 135	99.82 58	94.77 196	99.92 79	98.46 117	93.93 148	97.20 157	99.27 135	95.44 46	99.97 53	97.41 141	99.51 103	99.41 165
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 55	98.08 55	98.78 83	99.81 60	96.60 123	99.82 136	98.30 177	93.95 147	99.37 74	99.77 63	92.84 120	99.76 131	98.95 67	99.92 63	99.97 58

EI-MVSNet-UG-set		98.14 59	97.99 58	98.60 96	99.80 61	96.27 134	99.36 228	98.50 112	95.21 97	98.30 126	99.75 71	93.29 107	99.73 137	98.37 102	99.30 117	99.81 94

SR-MVS-dyc-post		98.31 49	98.17 48	98.71 87	99.79 62	96.37 132	99.76 153	98.31 174	94.43 120	99.40 71	99.75 71	93.28 108	99.78 125	98.90 75	99.92 63	99.97 58

RE-MVS-def			98.13 51		99.79 62	96.37 132	99.76 153	98.31 174	94.43 120	99.40 71	99.75 71	92.95 117		98.90 75	99.92 63	99.97 58

HPM-MVS_fast		97.80 74	97.50 79	98.68 89	99.79 62	96.42 127	99.88 103	98.16 195	91.75 228	98.94 93	99.54 112	91.82 149	99.65 147	97.62 139	99.99 21	99.99 23

SF-MVS		98.67 27	98.40 32	99.50 30	99.77 65	98.67 48	99.90 91	98.21 186	93.53 160	99.81 15	99.89 19	94.70 66	99.86 107	99.84 22	99.93 60	99.96 64

旧先验1					99.76 66	97.52 88		98.64 76			99.85 30	95.63 41			99.94 54	99.99 23

OMC-MVS		97.28 98	97.23 90	97.41 173	99.76 66	93.36 235	99.65 182	97.95 214	96.03 77	97.41 152	99.70 87	89.61 181	99.51 153	96.73 161	98.25 150	99.38 167

新几何1				99.42 37	99.75 68	98.27 62		98.63 80	92.69 190	99.55 55	99.82 46	94.40 71	100.00 1	91.21 251	99.94 54	99.99 23

MP-MVS-pluss		98.07 62	97.64 74	99.38 42	99.74 69	98.41 61	99.74 159	98.18 190	93.35 165	96.45 177	99.85 30	92.64 126	99.97 53	98.91 74	99.89 67	99.77 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + MP.		98.93 16	98.77 18	99.41 38	99.74 69	98.67 48	99.77 148	98.38 159	96.73 53	99.88 6	99.74 78	94.89 60	99.59 149	99.80 25	99.98 32	99.97 58
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 69	98.56 56		98.40 152		99.65 41		94.76 63	99.75 132		99.98 32	99.99 23

原ACMM1				98.96 76	99.73 72	96.99 110		98.51 107	94.06 141	99.62 47	99.85 30	94.97 59	99.96 61	95.11 181	99.95 49	99.92 81

TSAR-MVS + GP.		98.60 30	98.51 28	98.86 81	99.73 72	96.63 121	99.97 28	97.92 219	98.07 11	98.76 104	99.55 110	95.00 57	99.94 77	99.91 15	97.68 163	99.99 23

CANet		98.27 52	97.82 69	99.63 17	99.72 74	99.10 23	99.98 15	98.51 107	97.00 43	98.52 115	99.71 85	87.80 200	99.95 69	99.75 28	99.38 113	99.83 91

F-COLMAP		96.93 116	96.95 101	96.87 192	99.71 75	91.74 271	99.85 121	97.95 214	93.11 174	95.72 195	99.16 146	92.35 136	99.94 77	95.32 179	99.35 115	98.92 205

SD-MVS		98.92 17	98.70 19	99.56 25	99.70 76	98.73 45	99.94 69	98.34 169	96.38 67	99.81 15	99.76 65	94.59 67	99.98 43	99.84 22	99.96 46	99.97 58
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 56	99.12 5	95.59 225	99.67 77	86.91 344	99.95 53	98.89 49	97.60 22	99.90 3	99.76 65	96.54 28	99.98 43	99.94 11	99.82 77	99.88 85

ACMMP_NAP		98.49 37	98.14 50	99.54 27	99.66 78	98.62 54	99.85 121	98.37 162	94.68 112	99.53 58	99.83 43	92.87 119	100.00 1	98.66 90	99.84 72	99.99 23

DeepPCF-MVS	95.94 2	97.71 82	98.98 12	93.92 288	99.63 79	81.76 371	99.96 35	98.56 92	99.47 1	99.19 84	99.99 1	94.16 84	100.00 1	99.92 12	99.93 60	100.00 1

EPNet		98.49 37	98.40 32	98.77 85	99.62 80	96.80 118	99.90 91	99.51 17	97.60 22	99.20 82	99.36 129	93.71 97	99.91 89	97.99 120	98.71 138	99.61 130
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		98.83 21	98.53 27	99.76 10	99.59 81	99.33 8	99.99 5	99.76 6	98.39 3	99.39 73	99.80 51	90.49 171	99.96 61	99.89 16	99.43 111	99.98 48

PVSNet_BlendedMVS		96.05 153	95.82 148	96.72 197	99.59 81	96.99 110	99.95 53	99.10 31	94.06 141	98.27 127	95.80 292	89.00 192	99.95 69	99.12 58	87.53 285	93.24 343

PVSNet_Blended		97.94 64	97.64 74	98.83 82	99.59 81	96.99 110	100.00 1	99.10 31	95.38 92	98.27 127	99.08 149	89.00 192	99.95 69	99.12 58	99.25 119	99.57 140

PatchMatch-RL		96.04 154	95.40 158	97.95 139	99.59 81	95.22 182	99.52 204	99.07 34	93.96 146	96.49 176	98.35 217	82.28 251	99.82 120	90.15 275	99.22 122	98.81 212

dcpmvs_2		97.42 93	98.09 54	95.42 230	99.58 85	87.24 340	99.23 243	96.95 313	94.28 130	98.93 94	99.73 80	94.39 74	99.16 175	99.89 16	99.82 77	99.86 89

test222					99.55 86	97.41 97	99.34 229	98.55 98	91.86 223	99.27 81	99.83 43	93.84 94			99.95 49	99.99 23

CNLPA		97.76 78	97.38 83	98.92 79	99.53 87	96.84 115	99.87 106	98.14 199	93.78 153	96.55 175	99.69 89	92.28 138	99.98 43	97.13 148	99.44 109	99.93 76

API-MVS		97.86 68	97.66 73	98.47 109	99.52 88	95.41 173	99.47 213	98.87 52	91.68 229	98.84 97	99.85 30	92.34 137	99.99 36	98.44 99	99.96 46	100.00 1

PVSNet	91.05 13	97.13 105	96.69 113	98.45 111	99.52 88	95.81 152	99.95 53	99.65 12	94.73 109	99.04 89	99.21 142	84.48 237	99.95 69	94.92 187	98.74 137	99.58 139

114514_t		97.41 94	96.83 106	99.14 60	99.51 90	97.83 76	99.89 99	98.27 181	88.48 300	99.06 88	99.66 98	90.30 173	99.64 148	96.32 165	99.97 42	99.96 64

cl22		93.77 216	93.25 219	95.33 234	99.49 91	94.43 200	99.61 190	98.09 201	90.38 264	89.16 288	95.61 299	90.56 169	97.34 278	91.93 243	84.45 306	94.21 289

testdata				98.42 114	99.47 92	95.33 176		98.56 92	93.78 153	99.79 26	99.85 30	93.64 99	99.94 77	94.97 185	99.94 54	100.00 1

MAR-MVS		97.43 89	97.19 92	98.15 128	99.47 92	94.79 195	99.05 263	98.76 63	92.65 193	98.66 110	99.82 46	88.52 197	99.98 43	98.12 112	99.63 89	99.67 116
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		94.54 193	93.42 212	97.91 144	99.46 94	94.04 213	98.93 275	97.48 259	81.15 367	90.04 261	99.55 110	87.02 211	99.95 69	88.97 285	98.11 154	99.73 105

MVS_111021_LR		98.42 44	98.38 34	98.53 106	99.39 95	95.79 153	99.87 106	99.86 2	96.70 54	98.78 101	99.79 57	92.03 144	99.90 91	99.17 57	99.86 71	99.88 85

CHOSEN 280x420		99.01 13	99.03 10	98.95 77	99.38 96	98.87 33	98.46 311	99.42 22	97.03 42	99.02 90	99.09 148	99.35 1	98.21 242	99.73 32	99.78 80	99.77 101

MVS_111021_HR		98.72 25	98.62 22	99.01 72	99.36 97	97.18 102	99.93 76	99.90 1	96.81 51	98.67 109	99.77 63	93.92 89	99.89 96	99.27 53	99.94 54	99.96 64

DPM-MVS		98.83 21	98.46 30	99.97 1	99.33 98	99.92 1	99.96 35	98.44 123	97.96 14	99.55 55	99.94 4	97.18 20	100.00 1	93.81 215	99.94 54	99.98 48

TAPA-MVS	92.12 8	94.42 198	93.60 205	96.90 191	99.33 98	91.78 270	99.78 145	98.00 208	89.89 274	94.52 208	99.47 116	91.97 145	99.18 173	69.90 381	99.52 100	99.73 105
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CS-MVS-test		97.88 67	97.94 63	97.70 157	99.28 100	95.20 183	99.98 15	97.15 292	95.53 89	99.62 47	99.79 57	92.08 143	98.38 225	98.75 84	99.28 118	99.52 150

test_fmvsm_n_1920		98.44 41	98.61 23	97.92 142	99.27 101	95.18 184	100.00 1	98.90 47	98.05 12	99.80 18	99.73 80	92.64 126	99.99 36	99.58 38	99.51 103	98.59 222

fmvsm_l_conf0.5_n_a		99.00 14	98.91 14	99.28 44	99.21 102	97.91 75	99.98 15	98.85 56	98.25 4	99.92 2	99.75 71	94.72 64	99.97 53	99.87 19	99.64 88	99.95 71

test_yl		97.83 70	97.37 84	99.21 48	99.18 103	97.98 71	99.64 186	99.27 27	91.43 238	97.88 141	98.99 158	95.84 38	99.84 116	98.82 79	95.32 216	99.79 97

DCV-MVSNet		97.83 70	97.37 84	99.21 48	99.18 103	97.98 71	99.64 186	99.27 27	91.43 238	97.88 141	98.99 158	95.84 38	99.84 116	98.82 79	95.32 216	99.79 97

MVS_0304		98.87 20	98.61 23	99.67 16	99.18 103	99.13 22	99.87 106	99.65 12	98.17 8	98.75 106	99.75 71	92.76 123	99.94 77	99.88 18	99.44 109	99.94 74

fmvsm_l_conf0.5_n		98.94 15	98.84 17	99.25 45	99.17 106	97.81 78	99.98 15	98.86 53	98.25 4	99.90 3	99.76 65	94.21 82	99.97 53	99.87 19	99.52 100	99.98 48

DeepC-MVS	94.51 4	96.92 117	96.40 123	98.45 111	99.16 107	95.90 150	99.66 180	98.06 204	96.37 70	94.37 211	99.49 115	83.29 247	99.90 91	97.63 138	99.61 94	99.55 142
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 33	98.22 44	99.50 30	99.15 108	98.65 52	100.00 1	98.58 87	97.70 20	98.21 131	99.24 140	92.58 129	99.94 77	98.63 93	99.94 54	99.92 81
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 76	97.91 65	97.43 172	99.10 109	94.42 201	99.99 5	97.10 297	95.07 98	99.68 38	99.75 71	92.95 117	98.34 229	98.38 101	99.14 124	99.54 146

Anonymous202405211		93.10 234	91.99 246	96.40 207	99.10 109	89.65 315	98.88 280	97.93 216	83.71 354	94.00 217	98.75 187	68.79 348	99.88 102	95.08 183	91.71 245	99.68 112

fmvsm_s_conf0.5_n		97.80 74	97.85 68	97.67 158	99.06 111	94.41 202	99.98 15	98.97 40	97.34 29	99.63 44	99.69 89	87.27 207	99.97 53	99.62 37	99.06 128	98.62 221

HyFIR lowres test		96.66 131	96.43 122	97.36 178	99.05 112	93.91 218	99.70 174	99.80 3	90.54 262	96.26 183	98.08 224	92.15 141	98.23 241	96.84 160	95.46 211	99.93 76

LFMVS		94.75 187	93.56 208	98.30 120	99.03 113	95.70 159	98.74 294	97.98 211	87.81 310	98.47 118	99.39 126	67.43 357	99.53 150	98.01 118	95.20 219	99.67 116

AllTest		92.48 248	91.64 251	95.00 244	99.01 114	88.43 329	98.94 274	96.82 328	86.50 326	88.71 294	98.47 213	74.73 324	99.88 102	85.39 323	96.18 193	96.71 249

TestCases				95.00 244	99.01 114	88.43 329		96.82 328	86.50 326	88.71 294	98.47 213	74.73 324	99.88 102	85.39 323	96.18 193	96.71 249

COLMAP_ROB	90.47 14	92.18 255	91.49 257	94.25 276	99.00 116	88.04 335	98.42 316	96.70 335	82.30 363	88.43 301	99.01 155	76.97 300	99.85 108	86.11 319	96.50 188	94.86 260
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs1		95.35 173	95.68 153	94.36 273	98.99 117	84.98 353	99.96 35	96.65 337	97.60 22	99.73 33	98.96 164	71.58 337	99.93 85	98.31 105	99.37 114	98.17 229

HY-MVS	92.50 7	97.79 76	97.17 94	99.63 17	98.98 118	99.32 9	97.49 340	99.52 15	95.69 84	98.32 125	97.41 243	93.32 105	99.77 128	98.08 116	95.75 207	99.81 94

VNet		97.21 102	96.57 118	99.13 64	98.97 119	97.82 77	99.03 266	99.21 29	94.31 128	99.18 85	98.88 175	86.26 221	99.89 96	98.93 69	94.32 228	99.69 111

thres200		96.96 114	96.21 128	99.22 47	98.97 119	98.84 36	99.85 121	99.71 7	93.17 172	96.26 183	98.88 175	89.87 178	99.51 153	94.26 205	94.91 221	99.31 177

tfpn200view9		96.79 121	95.99 133	99.19 50	98.94 121	98.82 37	99.78 145	99.71 7	92.86 180	96.02 188	98.87 178	89.33 185	99.50 155	93.84 212	94.57 224	99.27 183

thres400		96.78 123	95.99 133	99.16 56	98.94 121	98.82 37	99.78 145	99.71 7	92.86 180	96.02 188	98.87 178	89.33 185	99.50 155	93.84 212	94.57 224	99.16 190

sasdasda		97.09 108	96.32 124	99.39 40	98.93 123	98.95 27	99.72 167	97.35 270	94.45 117	97.88 141	99.42 120	86.71 214	99.52 151	98.48 97	93.97 234	99.72 107

Anonymous20231211		89.86 304	88.44 311	94.13 279	98.93 123	90.68 293	98.54 308	98.26 182	76.28 379	86.73 322	95.54 303	70.60 343	97.56 271	90.82 262	80.27 341	94.15 297

canonicalmvs		97.09 108	96.32 124	99.39 40	98.93 123	98.95 27	99.72 167	97.35 270	94.45 117	97.88 141	99.42 120	86.71 214	99.52 151	98.48 97	93.97 234	99.72 107

SDMVSNet		94.80 183	93.96 196	97.33 180	98.92 126	95.42 172	99.59 192	98.99 37	92.41 207	92.55 235	97.85 233	75.81 314	98.93 184	97.90 126	91.62 246	97.64 240

sd_testset		93.55 223	92.83 227	95.74 223	98.92 126	90.89 290	98.24 322	98.85 56	92.41 207	92.55 235	97.85 233	71.07 342	98.68 201	93.93 209	91.62 246	97.64 240

EPNet_dtu		95.71 163	95.39 159	96.66 199	98.92 126	93.41 232	99.57 196	98.90 47	96.19 75	97.52 148	98.56 205	92.65 125	97.36 276	77.89 364	98.33 145	99.20 188
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 61	97.60 76	99.60 22	98.92 126	99.28 17	99.89 99	99.52 15	95.58 87	98.24 130	99.39 126	93.33 104	99.74 134	97.98 122	95.58 210	99.78 100

CHOSEN 1792x2688		96.81 120	96.53 119	97.64 160	98.91 130	93.07 237	99.65 182	99.80 3	95.64 85	95.39 199	98.86 180	84.35 240	99.90 91	96.98 154	99.16 123	99.95 71

thres100view900		96.74 126	95.92 144	99.18 51	98.90 131	98.77 41	99.74 159	99.71 7	92.59 197	95.84 191	98.86 180	89.25 187	99.50 155	93.84 212	94.57 224	99.27 183

thres600view7		96.69 129	95.87 147	99.14 60	98.90 131	98.78 40	99.74 159	99.71 7	92.59 197	95.84 191	98.86 180	89.25 187	99.50 155	93.44 224	94.50 227	99.16 190

MSDG		94.37 200	93.36 216	97.40 174	98.88 133	93.95 217	99.37 226	97.38 268	85.75 337	90.80 254	99.17 145	84.11 242	99.88 102	86.35 316	98.43 143	98.36 227

h-mvs33		94.92 181	94.36 185	96.59 201	98.85 134	91.29 282	98.93 275	98.94 41	95.90 78	98.77 102	98.42 216	90.89 165	99.77 128	97.80 129	70.76 375	98.72 218

Anonymous20240529		92.10 256	90.65 267	96.47 202	98.82 135	90.61 295	98.72 296	98.67 73	75.54 383	93.90 219	98.58 203	66.23 361	99.90 91	94.70 196	90.67 248	98.90 208

PVSNet_Blended_VisFu		97.27 99	96.81 107	98.66 91	98.81 136	96.67 120	99.92 79	98.64 76	94.51 116	96.38 181	98.49 209	89.05 191	99.88 102	97.10 150	98.34 144	99.43 163

PS-MVSNAJ		98.44 41	98.20 46	99.16 56	98.80 137	98.92 29	99.54 202	98.17 191	97.34 29	99.85 9	99.85 30	91.20 154	99.89 96	99.41 48	99.67 86	98.69 219

CANet_DTU		96.76 124	96.15 129	98.60 96	98.78 138	97.53 87	99.84 126	97.63 238	97.25 37	99.20 82	99.64 101	81.36 260	99.98 43	92.77 235	98.89 131	98.28 228

mvsany_test1		97.82 72	97.90 66	97.55 165	98.77 139	93.04 240	99.80 142	97.93 216	96.95 45	99.61 53	99.68 95	90.92 162	99.83 118	99.18 56	98.29 149	99.80 96

alignmvs		97.81 73	97.33 86	99.25 45	98.77 139	98.66 50	99.99 5	98.44 123	94.40 124	98.41 120	99.47 116	93.65 98	99.42 163	98.57 94	94.26 230	99.67 116

SteuartSystems-ACMMP		99.02 12	98.97 13	99.18 51	98.72 141	97.71 80	99.98 15	98.44 123	96.85 46	99.80 18	99.91 14	97.57 7	99.85 108	99.44 46	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 57	97.97 59	99.02 71	98.69 142	98.66 50	99.52 204	98.08 203	97.05 41	99.86 7	99.86 26	90.65 167	99.71 138	99.39 50	98.63 139	98.69 219

miper_enhance_ethall		94.36 202	93.98 195	95.49 226	98.68 143	95.24 180	99.73 164	97.29 279	93.28 169	89.86 266	95.97 290	94.37 75	97.05 299	92.20 239	84.45 306	94.19 290

ETVMVS		97.03 112	96.64 114	98.20 124	98.67 144	97.12 106	99.89 99	98.57 89	91.10 249	98.17 132	98.59 200	93.86 93	98.19 243	95.64 176	95.24 218	99.28 182

test2506		97.53 86	97.19 92	98.58 99	98.66 145	96.90 114	98.81 289	99.77 5	94.93 101	97.95 137	98.96 164	92.51 131	99.20 170	94.93 186	98.15 151	99.64 122

ECVR-MVS		95.66 166	95.05 171	97.51 168	98.66 145	93.71 222	98.85 286	98.45 118	94.93 101	96.86 166	98.96 164	75.22 320	99.20 170	95.34 178	98.15 151	99.64 122

fmvsm_s_conf0.5_n_a		97.73 81	97.72 71	97.77 152	98.63 147	94.26 207	99.96 35	98.92 46	97.18 39	99.75 30	99.69 89	87.00 212	99.97 53	99.46 44	98.89 131	99.08 198

iter_conf05_11		96.12 150	95.46 156	98.10 130	98.62 148	95.52 168	100.00 1	96.30 349	96.54 60	99.81 15	99.80 51	69.19 347	99.10 177	98.92 70	99.91 66	99.68 112

bld_raw_dy_0_64		94.22 206	92.97 223	97.98 137	98.62 148	95.09 187	99.89 99	93.09 390	96.55 59	92.59 233	99.80 51	68.57 351	99.19 172	98.92 70	88.69 265	99.68 112

testing222		97.08 111	96.75 110	98.06 134	98.56 150	96.82 116	99.85 121	98.61 82	92.53 201	98.84 97	98.84 184	93.36 102	98.30 233	95.84 173	94.30 229	99.05 200

test1111		95.57 168	94.98 174	97.37 176	98.56 150	93.37 234	98.86 284	98.45 118	94.95 100	96.63 172	98.95 169	75.21 321	99.11 176	95.02 184	98.14 153	99.64 122

MVSTER		95.53 169	95.22 165	96.45 204	98.56 150	97.72 79	99.91 84	97.67 236	92.38 209	91.39 246	97.14 250	97.24 17	97.30 282	94.80 192	87.85 280	94.34 281

VDD-MVS		93.77 216	92.94 224	96.27 211	98.55 153	90.22 304	98.77 293	97.79 230	90.85 255	96.82 168	99.42 120	61.18 378	99.77 128	98.95 67	94.13 231	98.82 211

tpmvs		94.28 204	93.57 207	96.40 207	98.55 153	91.50 280	95.70 374	98.55 98	87.47 312	92.15 239	94.26 349	91.42 150	98.95 183	88.15 295	95.85 203	98.76 214

UGNet		95.33 174	94.57 182	97.62 163	98.55 153	94.85 191	98.67 302	99.32 26	95.75 83	96.80 169	96.27 281	72.18 334	99.96 61	94.58 199	99.05 129	98.04 233
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	95.18 175	94.10 192	98.43 113	98.55 153	95.99 148	97.91 335	97.31 276	90.35 266	89.48 277	99.22 141	85.19 230	99.89 96	90.40 272	98.47 142	99.41 165
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		96.79 121	96.72 111	97.00 187	98.51 157	93.70 223	99.71 170	98.60 84	92.96 176	97.09 159	98.34 218	96.67 27	98.85 187	92.11 241	96.50 188	98.44 224

test_vis1_n_1920		95.44 171	95.31 162	95.82 221	98.50 158	88.74 323	99.98 15	97.30 277	97.84 16	99.85 9	99.19 143	66.82 359	99.97 53	98.82 79	99.46 107	98.76 214

BH-w/o		95.71 163	95.38 160	96.68 198	98.49 159	92.28 257	99.84 126	97.50 257	92.12 215	92.06 242	98.79 185	84.69 235	98.67 202	95.29 180	99.66 87	99.09 196

baseline1		95.78 160	94.86 176	98.54 104	98.47 160	98.07 66	99.06 259	97.99 209	92.68 191	94.13 216	98.62 199	93.28 108	98.69 200	93.79 217	85.76 294	98.84 210

iter_conf05		96.07 152	95.95 141	96.44 206	98.43 161	97.52 88	99.91 84	96.85 324	94.16 134	92.49 237	97.98 230	98.20 4	97.34 278	97.26 145	88.29 273	94.45 271

EPMVS		96.53 135	96.01 132	98.09 132	98.43 161	96.12 146	96.36 361	99.43 21	93.53 160	97.64 146	95.04 327	94.41 70	98.38 225	91.13 253	98.11 154	99.75 103

sss		97.57 85	97.03 99	99.18 51	98.37 163	98.04 68	99.73 164	99.38 23	93.46 162	98.76 104	99.06 151	91.21 153	99.89 96	96.33 164	97.01 180	99.62 127

testing11		97.48 88	97.27 88	98.10 130	98.36 164	96.02 147	99.92 79	98.45 118	93.45 164	98.15 133	98.70 190	95.48 45	99.22 166	97.85 128	95.05 220	99.07 199

BH-untuned		95.18 175	94.83 177	96.22 212	98.36 164	91.22 283	99.80 142	97.32 275	90.91 253	91.08 250	98.67 192	83.51 244	98.54 208	94.23 206	99.61 94	98.92 205

testing91		97.16 104	96.90 103	97.97 138	98.35 166	95.67 162	99.91 84	98.42 143	92.91 179	97.33 154	98.72 188	94.81 62	99.21 167	96.98 154	94.63 223	99.03 201

testing99		97.17 103	96.91 102	97.95 139	98.35 166	95.70 159	99.91 84	98.43 131	92.94 177	97.36 153	98.72 188	94.83 61	99.21 167	97.00 152	94.64 222	98.95 204

ET-MVSNet_ETH3D		94.37 200	93.28 218	97.64 160	98.30 168	97.99 70	99.99 5	97.61 243	94.35 125	71.57 386	99.45 119	96.23 31	95.34 356	96.91 159	85.14 301	99.59 133

AUN-MVS		93.28 228	92.60 233	95.34 233	98.29 169	90.09 307	99.31 233	98.56 92	91.80 227	96.35 182	98.00 227	89.38 184	98.28 236	92.46 236	69.22 380	97.64 240

FMVSNet3		92.69 244	91.58 253	95.99 216	98.29 169	97.42 96	99.26 241	97.62 240	89.80 275	89.68 270	95.32 317	81.62 258	96.27 336	87.01 312	85.65 295	94.29 283

PMMVS		96.76 124	96.76 109	96.76 195	98.28 171	92.10 261	99.91 84	97.98 211	94.12 136	99.53 58	99.39 126	86.93 213	98.73 195	96.95 157	97.73 161	99.45 160

hse-mvs2		94.38 199	94.08 193	95.31 235	98.27 172	90.02 309	99.29 238	98.56 92	95.90 78	98.77 102	98.00 227	90.89 165	98.26 240	97.80 129	69.20 381	97.64 240

PVSNet_0	88.03 19	91.80 263	90.27 276	96.38 209	98.27 172	90.46 299	99.94 69	99.61 14	93.99 144	86.26 332	97.39 245	71.13 341	99.89 96	98.77 82	67.05 386	98.79 213

UA-Net		96.54 134	95.96 139	98.27 121	98.23 174	95.71 158	98.00 333	98.45 118	93.72 156	98.41 120	99.27 135	88.71 196	99.66 146	91.19 252	97.69 162	99.44 162

test_cas_vis1_n_1920		96.59 133	96.23 127	97.65 159	98.22 175	94.23 208	99.99 5	97.25 283	97.77 17	99.58 54	99.08 149	77.10 297	99.97 53	97.64 137	99.45 108	98.74 216

FE-MVS		95.70 165	95.01 173	97.79 149	98.21 176	94.57 197	95.03 375	98.69 68	88.90 291	97.50 150	96.19 283	92.60 128	99.49 159	89.99 277	97.94 160	99.31 177

GG-mvs-BLEND				98.54 104	98.21 176	98.01 69	93.87 380	98.52 104		97.92 138	97.92 232	99.02 2	97.94 259	98.17 109	99.58 97	99.67 116

mvs_anonymous		95.65 167	95.03 172	97.53 166	98.19 178	95.74 156	99.33 230	97.49 258	90.87 254	90.47 257	97.10 252	88.23 198	97.16 290	95.92 171	97.66 164	99.68 112

MVS_Test		96.46 137	95.74 149	98.61 95	98.18 179	97.23 100	99.31 233	97.15 292	91.07 250	98.84 97	97.05 256	88.17 199	98.97 181	94.39 201	97.50 166	99.61 130

BH-RMVSNet		95.18 175	94.31 188	97.80 147	98.17 180	95.23 181	99.76 153	97.53 253	92.52 203	94.27 214	99.25 139	76.84 302	98.80 189	90.89 261	99.54 99	99.35 172

RPSCF		91.80 263	92.79 229	88.83 351	98.15 181	69.87 389	98.11 329	96.60 339	83.93 352	94.33 212	99.27 135	79.60 280	99.46 162	91.99 242	93.16 242	97.18 247

ETV-MVS		97.92 66	97.80 70	98.25 122	98.14 182	96.48 125	99.98 15	97.63 238	95.61 86	99.29 80	99.46 118	92.55 130	98.82 188	99.02 66	98.54 140	99.46 158

IS-MVSNet		96.29 147	95.90 145	97.45 170	98.13 183	94.80 194	99.08 254	97.61 243	92.02 220	95.54 198	98.96 164	90.64 168	98.08 248	93.73 220	97.41 170	99.47 157

test_fmvsmconf_n		98.43 43	98.32 40	98.78 83	98.12 184	96.41 128	99.99 5	98.83 59	98.22 6	99.67 39	99.64 101	91.11 158	99.94 77	99.67 36	99.62 90	99.98 48

ab-mvs		94.69 188	93.42 212	98.51 107	98.07 185	96.26 135	96.49 359	98.68 70	90.31 267	94.54 207	97.00 258	76.30 309	99.71 138	95.98 170	93.38 240	99.56 141

XVG-OURS-SEG-HR		94.79 184	94.70 181	95.08 241	98.05 186	89.19 318	99.08 254	97.54 251	93.66 157	94.87 205	99.58 108	78.78 288	99.79 123	97.31 143	93.40 239	96.25 253

EIA-MVS		97.53 86	97.46 80	97.76 154	98.04 187	94.84 192	99.98 15	97.61 243	94.41 123	97.90 139	99.59 106	92.40 135	98.87 185	98.04 117	99.13 125	99.59 133

XVG-OURS		94.82 182	94.74 180	95.06 242	98.00 188	89.19 318	99.08 254	97.55 249	94.10 137	94.71 206	99.62 104	80.51 272	99.74 134	96.04 169	93.06 244	96.25 253

dp		95.05 178	94.43 184	96.91 190	97.99 189	92.73 247	96.29 364	97.98 211	89.70 276	95.93 190	94.67 340	93.83 95	98.45 214	86.91 315	96.53 187	99.54 146

tpmrst		96.27 149	95.98 135	97.13 184	97.96 190	93.15 236	96.34 362	98.17 191	92.07 216	98.71 108	95.12 325	93.91 90	98.73 195	94.91 189	96.62 185	99.50 154

TR-MVS		94.54 193	93.56 208	97.49 169	97.96 190	94.34 205	98.71 297	97.51 256	90.30 268	94.51 209	98.69 191	75.56 315	98.77 192	92.82 234	95.99 197	99.35 172

Vis-MVSNet (Re-imp)		96.32 144	95.98 135	97.35 179	97.93 192	94.82 193	99.47 213	98.15 198	91.83 224	95.09 203	99.11 147	91.37 152	97.47 274	93.47 223	97.43 167	99.74 104

MDTV_nov1_ep13			95.69 151		97.90 193	94.15 210	95.98 370	98.44 123	93.12 173	97.98 136	95.74 294	95.10 51	98.58 205	90.02 276	96.92 182

Fast-Effi-MVS+		95.02 179	94.19 190	97.52 167	97.88 194	94.55 198	99.97 28	97.08 300	88.85 293	94.47 210	97.96 231	84.59 236	98.41 217	89.84 279	97.10 175	99.59 133

ADS-MVSNet2		93.80 215	93.88 199	93.55 302	97.87 195	85.94 347	94.24 376	96.84 325	90.07 270	96.43 178	94.48 345	90.29 174	95.37 355	87.44 302	97.23 172	99.36 170

ADS-MVSNet		94.79 184	94.02 194	97.11 186	97.87 195	93.79 219	94.24 376	98.16 195	90.07 270	96.43 178	94.48 345	90.29 174	98.19 243	87.44 302	97.23 172	99.36 170

Effi-MVS+		96.30 146	95.69 151	98.16 125	97.85 197	96.26 135	97.41 342	97.21 285	90.37 265	98.65 111	98.58 203	86.61 217	98.70 199	97.11 149	97.37 171	99.52 150

PatchmatchNet		95.94 156	95.45 157	97.39 175	97.83 198	94.41 202	96.05 368	98.40 152	92.86 180	97.09 159	95.28 322	94.21 82	98.07 250	89.26 283	98.11 154	99.70 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 191	93.61 203	97.74 156	97.82 199	96.26 135	99.96 35	97.78 231	85.76 335	94.00 217	97.54 240	76.95 301	99.21 167	97.23 146	95.43 213	97.76 239

1112_ss		96.01 155	95.20 166	98.42 114	97.80 200	96.41 128	99.65 182	96.66 336	92.71 188	92.88 230	99.40 124	92.16 140	99.30 164	91.92 244	93.66 236	99.55 142

Test_1112_low_res		95.72 161	94.83 177	98.42 114	97.79 201	96.41 128	99.65 182	96.65 337	92.70 189	92.86 231	96.13 286	92.15 141	99.30 164	91.88 245	93.64 237	99.55 142

Effi-MVS+-dtu		94.53 195	95.30 163	92.22 324	97.77 202	82.54 364	99.59 192	97.06 302	94.92 103	95.29 201	95.37 315	85.81 223	97.89 260	94.80 192	97.07 176	96.23 255

tpm cat1		93.51 224	92.52 238	96.47 202	97.77 202	91.47 281	96.13 366	98.06 204	80.98 368	92.91 229	93.78 353	89.66 179	98.87 185	87.03 311	96.39 191	99.09 196

FA-MVS(test-final)		95.86 157	95.09 170	98.15 128	97.74 204	95.62 164	96.31 363	98.17 191	91.42 240	96.26 183	96.13 286	90.56 169	99.47 161	92.18 240	97.07 176	99.35 172

xiu_mvs_v1_base_debu		97.43 89	97.06 95	98.55 101	97.74 204	98.14 63	99.31 233	97.86 225	96.43 64	99.62 47	99.69 89	85.56 225	99.68 142	99.05 60	98.31 146	97.83 235

xiu_mvs_v1_base		97.43 89	97.06 95	98.55 101	97.74 204	98.14 63	99.31 233	97.86 225	96.43 64	99.62 47	99.69 89	85.56 225	99.68 142	99.05 60	98.31 146	97.83 235

xiu_mvs_v1_base_debi		97.43 89	97.06 95	98.55 101	97.74 204	98.14 63	99.31 233	97.86 225	96.43 64	99.62 47	99.69 89	85.56 225	99.68 142	99.05 60	98.31 146	97.83 235

EPP-MVSNet		96.69 129	96.60 116	96.96 189	97.74 204	93.05 239	99.37 226	98.56 92	88.75 294	95.83 193	99.01 155	96.01 32	98.56 206	96.92 158	97.20 174	99.25 185

gg-mvs-nofinetune		93.51 224	91.86 250	98.47 109	97.72 209	97.96 73	92.62 384	98.51 107	74.70 386	97.33 154	69.59 399	98.91 3	97.79 263	97.77 134	99.56 98	99.67 116

IB-MVS	92.85 6	94.99 180	93.94 197	98.16 125	97.72 209	95.69 161	99.99 5	98.81 60	94.28 130	92.70 232	96.90 260	95.08 52	99.17 174	96.07 168	73.88 370	99.60 132
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 94	97.02 100	98.59 98	97.71 211	97.52 88	99.97 28	98.54 101	91.83 224	97.45 151	99.04 152	97.50 8	99.10 177	94.75 194	96.37 192	99.16 190

Syy-MVS		90.00 302	90.63 268	88.11 358	97.68 212	74.66 386	99.71 170	98.35 165	90.79 257	92.10 240	98.67 192	79.10 286	93.09 378	63.35 392	95.95 200	96.59 251

myMVS_eth3d		94.46 197	94.76 179	93.55 302	97.68 212	90.97 285	99.71 170	98.35 165	90.79 257	92.10 240	98.67 192	92.46 134	93.09 378	87.13 308	95.95 200	96.59 251

test_fmvs1_n		94.25 205	94.36 185	93.92 288	97.68 212	83.70 359	99.90 91	96.57 340	97.40 28	99.67 39	98.88 175	61.82 375	99.92 88	98.23 107	99.13 125	98.14 232

diffmvs		97.00 113	96.64 114	98.09 132	97.64 215	96.17 143	99.81 138	97.19 286	94.67 113	98.95 92	99.28 132	86.43 218	98.76 193	98.37 102	97.42 169	99.33 175
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		95.72 161	95.15 168	97.45 170	97.62 216	94.28 206	99.28 239	98.24 183	94.27 132	96.84 167	98.94 171	79.39 281	98.76 193	93.25 225	98.49 141	99.30 179
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 106	96.72 111	98.22 123	97.60 217	96.70 119	99.92 79	98.54 101	91.11 248	97.07 161	98.97 162	97.47 11	99.03 179	93.73 220	96.09 195	98.92 205

miper_ehance_all_eth		93.16 231	92.60 233	94.82 251	97.57 218	93.56 227	99.50 208	97.07 301	88.75 294	88.85 293	95.52 305	90.97 161	96.74 317	90.77 263	84.45 306	94.17 291

testing3		93.92 210	94.23 189	92.99 316	97.54 219	90.23 303	99.99 5	99.16 30	90.57 261	91.33 249	98.63 198	92.99 115	92.52 382	82.46 341	95.39 214	96.22 256

LCM-MVSNet-Re		92.31 252	92.60 233	91.43 331	97.53 220	79.27 381	99.02 267	91.83 395	92.07 216	80.31 361	94.38 348	83.50 245	95.48 353	97.22 147	97.58 165	99.54 146

GBi-Net		90.88 279	89.82 285	94.08 280	97.53 220	91.97 262	98.43 313	96.95 313	87.05 318	89.68 270	94.72 336	71.34 338	96.11 341	87.01 312	85.65 295	94.17 291

test1		90.88 279	89.82 285	94.08 280	97.53 220	91.97 262	98.43 313	96.95 313	87.05 318	89.68 270	94.72 336	71.34 338	96.11 341	87.01 312	85.65 295	94.17 291

FMVSNet2		91.02 276	89.56 290	95.41 231	97.53 220	95.74 156	98.98 269	97.41 266	87.05 318	88.43 301	95.00 330	71.34 338	96.24 338	85.12 325	85.21 300	94.25 286

tttt0517		96.85 118	96.49 120	97.92 142	97.48 224	95.89 151	99.85 121	98.54 101	90.72 260	96.63 172	98.93 173	97.47 11	99.02 180	93.03 232	95.76 206	98.85 209

casdiffmvs_mvg		96.43 138	95.94 142	97.89 146	97.44 225	95.47 169	99.86 118	97.29 279	93.35 165	96.03 187	99.19 143	85.39 228	98.72 197	97.89 127	97.04 178	99.49 156
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 96	97.24 89	97.80 147	97.41 226	95.64 163	99.99 5	97.06 302	94.59 114	99.63 44	99.32 131	89.20 190	98.14 245	98.76 83	99.23 121	99.62 127

c3_l		92.53 247	91.87 249	94.52 263	97.40 227	92.99 241	99.40 219	96.93 318	87.86 308	88.69 296	95.44 309	89.95 177	96.44 329	90.45 269	80.69 337	94.14 300

fmvsm_s_conf0.1_n		97.30 97	97.21 91	97.60 164	97.38 228	94.40 204	99.90 91	98.64 76	96.47 63	99.51 62	99.65 100	84.99 233	99.93 85	99.22 55	99.09 127	98.46 223

CDS-MVSNet		96.34 143	96.07 130	97.13 184	97.37 229	94.96 189	99.53 203	97.91 220	91.55 232	95.37 200	98.32 219	95.05 54	97.13 293	93.80 216	95.75 207	99.30 179
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 126	96.26 126	98.16 125	97.36 230	96.48 125	99.96 35	98.29 178	91.93 221	95.77 194	98.07 225	95.54 42	98.29 234	90.55 267	98.89 131	99.70 109

miper_lstm_enhance		91.81 260	91.39 259	93.06 315	97.34 231	89.18 320	99.38 224	96.79 330	86.70 325	87.47 314	95.22 323	90.00 176	95.86 350	88.26 293	81.37 327	94.15 297

baseline		96.43 138	95.98 135	97.76 154	97.34 231	95.17 185	99.51 206	97.17 289	93.92 149	96.90 165	99.28 132	85.37 229	98.64 203	97.50 140	96.86 184	99.46 158

cl____		92.31 252	91.58 253	94.52 263	97.33 233	92.77 243	99.57 196	96.78 331	86.97 322	87.56 312	95.51 306	89.43 183	96.62 322	88.60 288	82.44 319	94.16 296

DIV-MVS_self_test		92.32 251	91.60 252	94.47 267	97.31 234	92.74 245	99.58 194	96.75 332	86.99 321	87.64 310	95.54 303	89.55 182	96.50 326	88.58 289	82.44 319	94.17 291

casdiffmvs		96.42 140	95.97 138	97.77 152	97.30 235	94.98 188	99.84 126	97.09 299	93.75 155	96.58 174	99.26 138	85.07 231	98.78 191	97.77 134	97.04 178	99.54 146
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		94.36 202	93.48 210	96.99 188	97.29 236	93.54 228	99.96 35	96.72 334	88.35 303	93.43 221	98.94 171	82.05 252	98.05 251	88.12 297	96.48 190	99.37 169

eth_miper_zixun_eth		92.41 250	91.93 247	93.84 292	97.28 237	90.68 293	98.83 287	96.97 312	88.57 299	89.19 287	95.73 296	89.24 189	96.69 320	89.97 278	81.55 325	94.15 297

MVSFormer		96.94 115	96.60 116	97.95 139	97.28 237	97.70 82	99.55 200	97.27 281	91.17 245	99.43 67	99.54 112	90.92 162	96.89 310	94.67 197	99.62 90	99.25 185

lupinMVS		97.85 69	97.60 76	98.62 94	97.28 237	97.70 82	99.99 5	97.55 249	95.50 91	99.43 67	99.67 96	90.92 162	98.71 198	98.40 100	99.62 90	99.45 160

SCA		94.69 188	93.81 201	97.33 180	97.10 240	94.44 199	98.86 284	98.32 172	93.30 168	96.17 186	95.59 301	76.48 307	97.95 257	91.06 255	97.43 167	99.59 133

TAMVS		95.85 158	95.58 154	96.65 200	97.07 241	93.50 229	99.17 248	97.82 229	91.39 242	95.02 204	98.01 226	92.20 139	97.30 282	93.75 219	95.83 204	99.14 193

Fast-Effi-MVS+-dtu		93.72 219	93.86 200	93.29 307	97.06 242	86.16 345	99.80 142	96.83 326	92.66 192	92.58 234	97.83 235	81.39 259	97.67 268	89.75 280	96.87 183	96.05 258

CostFormer		96.10 151	95.88 146	96.78 194	97.03 243	92.55 253	97.08 350	97.83 228	90.04 272	98.72 107	94.89 334	95.01 56	98.29 234	96.54 163	95.77 205	99.50 154

test_fmvsmvis_n_1920		97.67 83	97.59 78	97.91 144	97.02 244	95.34 175	99.95 53	98.45 118	97.87 15	97.02 162	99.59 106	89.64 180	99.98 43	99.41 48	99.34 116	98.42 225

test-LLR		96.47 136	96.04 131	97.78 150	97.02 244	95.44 170	99.96 35	98.21 186	94.07 139	95.55 196	96.38 277	93.90 91	98.27 238	90.42 270	98.83 135	99.64 122

test-mter		96.39 141	95.93 143	97.78 150	97.02 244	95.44 170	99.96 35	98.21 186	91.81 226	95.55 196	96.38 277	95.17 49	98.27 238	90.42 270	98.83 135	99.64 122

gm-plane-assit					96.97 247	93.76 221			91.47 236		98.96 164		98.79 190	94.92 187

WB-MVSnew		92.90 238	92.77 230	93.26 309	96.95 248	93.63 225	99.71 170	98.16 195	91.49 233	94.28 213	98.14 222	81.33 261	96.48 327	79.47 356	95.46 211	89.68 379

QAPM		95.40 172	94.17 191	99.10 65	96.92 249	97.71 80	99.40 219	98.68 70	89.31 279	88.94 291	98.89 174	82.48 250	99.96 61	93.12 231	99.83 73	99.62 127

KD-MVS_2432*1600		88.00 321	86.10 325	93.70 298	96.91 250	94.04 213	97.17 347	97.12 295	84.93 345	81.96 352	92.41 364	92.48 132	94.51 366	79.23 357	52.68 398	92.56 353

miper_refine_blended		88.00 321	86.10 325	93.70 298	96.91 250	94.04 213	97.17 347	97.12 295	84.93 345	81.96 352	92.41 364	92.48 132	94.51 366	79.23 357	52.68 398	92.56 353

tpm2		95.47 170	95.18 167	96.35 210	96.91 250	91.70 275	96.96 353	97.93 216	88.04 307	98.44 119	95.40 311	93.32 105	97.97 254	94.00 208	95.61 209	99.38 167

FMVSNet5		88.32 318	87.47 320	90.88 334	96.90 253	88.39 331	97.28 344	95.68 361	82.60 362	84.67 341	92.40 366	79.83 278	91.16 387	76.39 371	81.51 326	93.09 345

3Dnovator+	91.53 11	96.31 145	95.24 164	99.52 28	96.88 254	98.64 53	99.72 167	98.24 183	95.27 96	88.42 303	98.98 160	82.76 249	99.94 77	97.10 150	99.83 73	99.96 64

Patchmatch-test		92.65 246	91.50 256	96.10 215	96.85 255	90.49 298	91.50 389	97.19 286	82.76 361	90.23 258	95.59 301	95.02 55	98.00 253	77.41 366	96.98 181	99.82 92

MVS		96.60 132	95.56 155	99.72 13	96.85 255	99.22 20	98.31 319	98.94 41	91.57 231	90.90 253	99.61 105	86.66 216	99.96 61	97.36 142	99.88 69	99.99 23

3Dnovator	91.47 12	96.28 148	95.34 161	99.08 66	96.82 257	97.47 94	99.45 216	98.81 60	95.52 90	89.39 278	99.00 157	81.97 253	99.95 69	97.27 144	99.83 73	99.84 90

EI-MVSNet		93.73 218	93.40 215	94.74 252	96.80 258	92.69 248	99.06 259	97.67 236	88.96 288	91.39 246	99.02 153	88.75 195	97.30 282	91.07 254	87.85 280	94.22 287

CVMVSNet		94.68 190	94.94 175	93.89 291	96.80 258	86.92 343	99.06 259	98.98 38	94.45 117	94.23 215	99.02 153	85.60 224	95.31 357	90.91 260	95.39 214	99.43 163

IterMVS-LS		92.69 244	92.11 243	94.43 271	96.80 258	92.74 245	99.45 216	96.89 321	88.98 286	89.65 273	95.38 314	88.77 194	96.34 333	90.98 258	82.04 322	94.22 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS		90.91 278	90.17 280	93.12 312	96.78 261	90.42 301	98.89 278	97.05 304	89.03 283	86.49 327	95.42 310	76.59 305	95.02 359	87.22 307	84.09 309	93.93 317
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 119	95.96 139	99.48 34	96.74 262	98.52 57	98.31 319	98.86 53	95.82 80	89.91 264	98.98 160	87.49 204	99.96 61	97.80 129	99.73 83	99.96 64

IterMVS-SCA-FT		90.85 281	90.16 281	92.93 317	96.72 263	89.96 310	98.89 278	96.99 308	88.95 289	86.63 324	95.67 297	76.48 307	95.00 360	87.04 310	84.04 312	93.84 324

MVS-HIRNet		86.22 328	83.19 341	95.31 235	96.71 264	90.29 302	92.12 386	97.33 274	62.85 393	86.82 321	70.37 398	69.37 346	97.49 273	75.12 373	97.99 159	98.15 230

VDDNet		93.12 233	91.91 248	96.76 195	96.67 265	92.65 251	98.69 300	98.21 186	82.81 360	97.75 145	99.28 132	61.57 376	99.48 160	98.09 115	94.09 232	98.15 230

dmvs_re		93.20 230	93.15 220	93.34 305	96.54 266	83.81 358	98.71 297	98.51 107	91.39 242	92.37 238	98.56 205	78.66 290	97.83 262	93.89 210	89.74 249	98.38 226

MIMVSNet		90.30 294	88.67 308	95.17 240	96.45 267	91.64 277	92.39 385	97.15 292	85.99 332	90.50 256	93.19 360	66.95 358	94.86 363	82.01 345	93.43 238	99.01 203

CR-MVSNet		93.45 227	92.62 232	95.94 217	96.29 268	92.66 249	92.01 387	96.23 350	92.62 194	96.94 163	93.31 358	91.04 159	96.03 346	79.23 357	95.96 198	99.13 194

RPMNet		89.76 306	87.28 321	97.19 183	96.29 268	92.66 249	92.01 387	98.31 174	70.19 392	96.94 163	85.87 391	87.25 208	99.78 125	62.69 393	95.96 198	99.13 194

tt0805		91.28 271	90.18 279	94.60 258	96.26 270	87.55 337	98.39 317	98.72 65	89.00 285	89.22 284	98.47 213	62.98 372	98.96 182	90.57 266	88.00 279	97.28 246

Patchmtry		89.70 307	88.49 310	93.33 306	96.24 271	89.94 313	91.37 390	96.23 350	78.22 376	87.69 309	93.31 358	91.04 159	96.03 346	80.18 355	82.10 321	94.02 307

test_vis1_rt		86.87 326	86.05 328	89.34 347	96.12 272	78.07 382	99.87 106	83.54 406	92.03 219	78.21 371	89.51 377	45.80 392	99.91 89	96.25 166	93.11 243	90.03 376

JIA-IIPM		91.76 266	90.70 266	94.94 246	96.11 273	87.51 338	93.16 383	98.13 200	75.79 382	97.58 147	77.68 396	92.84 120	97.97 254	88.47 292	96.54 186	99.33 175

OpenMVS	90.15 15	94.77 186	93.59 206	98.33 118	96.07 274	97.48 93	99.56 198	98.57 89	90.46 263	86.51 326	98.95 169	78.57 291	99.94 77	93.86 211	99.74 82	97.57 244

PAPM		98.60 30	98.42 31	99.14 60	96.05 275	98.96 26	99.90 91	99.35 25	96.68 55	98.35 124	99.66 98	96.45 29	98.51 209	99.45 45	99.89 67	99.96 64

CLD-MVS		94.06 209	93.90 198	94.55 262	96.02 276	90.69 292	99.98 15	97.72 232	96.62 58	91.05 252	98.85 183	77.21 296	98.47 210	98.11 113	89.51 255	94.48 265
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 291	88.75 307	95.25 237	95.99 277	90.16 305	91.22 391	97.54 251	76.80 378	97.26 156	86.01 390	91.88 146	96.07 345	66.16 389	95.91 202	99.51 152

ACMH+	89.98 16	90.35 292	89.54 291	92.78 320	95.99 277	86.12 346	98.81 289	97.18 288	89.38 278	83.14 348	97.76 237	68.42 353	98.43 215	89.11 284	86.05 293	93.78 327

DeepMVS_CX				82.92 368	95.98 279	58.66 399		96.01 355	92.72 187	78.34 370	95.51 306	58.29 381	98.08 248	82.57 340	85.29 298	92.03 361

ACMP	92.05 9	92.74 242	92.42 240	93.73 294	95.91 280	88.72 324	99.81 138	97.53 253	94.13 135	87.00 320	98.23 220	74.07 328	98.47 210	96.22 167	88.86 262	93.99 312
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 222	93.03 222	95.35 232	95.86 281	86.94 342	99.87 106	96.36 347	96.85 46	99.54 57	98.79 185	52.41 388	99.83 118	98.64 91	98.97 130	99.29 181

HQP-NCC					95.78 282		99.87 106		96.82 48	93.37 222

ACMP_Plane					95.78 282		99.87 106		96.82 48	93.37 222

HQP-MVS		94.61 192	94.50 183	94.92 247	95.78 282	91.85 267	99.87 106	97.89 221	96.82 48	93.37 222	98.65 195	80.65 270	98.39 221	97.92 124	89.60 250	94.53 261

NP-MVS					95.77 285	91.79 269					98.65 195

test_fmvsmconf0.1_n		97.74 79	97.44 81	98.64 93	95.76 286	96.20 140	99.94 69	98.05 206	98.17 8	98.89 96	99.42 120	87.65 202	99.90 91	99.50 41	99.60 96	99.82 92

plane_prior6					95.76 286	91.72 274						80.47 274

ACMM	91.95 10	92.88 239	92.52 238	93.98 287	95.75 288	89.08 321	99.77 148	97.52 255	93.00 175	89.95 263	97.99 229	76.17 311	98.46 213	93.63 222	88.87 261	94.39 275
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 212	92.84 226	96.80 193	95.73 289	93.57 226	99.88 103	97.24 284	92.57 199	92.92 228	96.66 269	78.73 289	97.67 268	87.75 300	94.06 233	99.17 189

plane_prior1					95.73 289

jason		97.24 100	96.86 105	98.38 117	95.73 289	97.32 98	99.97 28	97.40 267	95.34 94	98.60 114	99.54 112	87.70 201	98.56 206	97.94 123	99.47 105	99.25 185
jason: jason.
HQP_MVS		94.49 196	94.36 185	94.87 248	95.71 292	91.74 271	99.84 126	97.87 223	96.38 67	93.01 226	98.59 200	80.47 274	98.37 227	97.79 132	89.55 253	94.52 263

plane_prior7					95.71 292	91.59 279

ITE_SJBPF				92.38 322	95.69 294	85.14 351		95.71 360	92.81 183	89.33 281	98.11 223	70.23 344	98.42 216	85.91 321	88.16 276	93.59 335

fmvsm_s_conf0.1_n_a		97.09 108	96.90 103	97.63 162	95.65 295	94.21 209	99.83 133	98.50 112	96.27 72	99.65 41	99.64 101	84.72 234	99.93 85	99.04 63	98.84 134	98.74 216

ACMH	89.72 17	90.64 285	89.63 288	93.66 300	95.64 296	88.64 327	98.55 306	97.45 260	89.03 283	81.62 355	97.61 239	69.75 345	98.41 217	89.37 281	87.62 284	93.92 318
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 128	96.49 120	97.37 176	95.63 297	95.96 149	99.74 159	98.88 51	92.94 177	91.61 244	98.97 162	97.72 6	98.62 204	94.83 191	98.08 157	97.53 245

FMVSNet1		88.50 317	86.64 323	94.08 280	95.62 298	91.97 262	98.43 313	96.95 313	83.00 358	86.08 334	94.72 336	59.09 380	96.11 341	81.82 347	84.07 310	94.17 291

LPG-MVS_test		92.96 236	92.71 231	93.71 296	95.43 299	88.67 325	99.75 156	97.62 240	92.81 183	90.05 259	98.49 209	75.24 318	98.40 219	95.84 173	89.12 257	94.07 304

LGP-MVS_train				93.71 296	95.43 299	88.67 325		97.62 240	92.81 183	90.05 259	98.49 209	75.24 318	98.40 219	95.84 173	89.12 257	94.07 304

tpm		93.70 220	93.41 214	94.58 260	95.36 301	87.41 339	97.01 351	96.90 320	90.85 255	96.72 171	94.14 350	90.40 172	96.84 313	90.75 264	88.54 270	99.51 152

D2MVS		92.76 241	92.59 236	93.27 308	95.13 302	89.54 317	99.69 175	99.38 23	92.26 212	87.59 311	94.61 342	85.05 232	97.79 263	91.59 248	88.01 278	92.47 356

VPA-MVSNet		92.70 243	91.55 255	96.16 213	95.09 303	96.20 140	98.88 280	99.00 36	91.02 252	91.82 243	95.29 321	76.05 313	97.96 256	95.62 177	81.19 328	94.30 282

LTVRE_ROB	88.28 18	90.29 295	89.05 302	94.02 283	95.08 304	90.15 306	97.19 346	97.43 262	84.91 347	83.99 344	97.06 255	74.00 329	98.28 236	84.08 330	87.71 282	93.62 334
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		87.87 323	86.51 324	91.94 327	95.05 305	85.57 349	97.65 339	94.08 382	84.40 350	81.82 354	96.85 264	62.14 374	98.33 230	80.25 354	86.37 292	91.91 363

test0.0.03 1		93.86 211	93.61 203	94.64 256	95.02 306	92.18 260	99.93 76	98.58 87	94.07 139	87.96 307	98.50 208	93.90 91	94.96 361	81.33 348	93.17 241	96.78 248

UniMVSNet (Re)		93.07 235	92.13 242	95.88 218	94.84 307	96.24 139	99.88 103	98.98 38	92.49 205	89.25 282	95.40 311	87.09 210	97.14 292	93.13 230	78.16 351	94.26 284

USDC		90.00 302	88.96 303	93.10 314	94.81 308	88.16 333	98.71 297	95.54 365	93.66 157	83.75 346	97.20 249	65.58 363	98.31 232	83.96 333	87.49 286	92.85 350

VPNet		91.81 260	90.46 270	95.85 220	94.74 309	95.54 167	98.98 269	98.59 86	92.14 214	90.77 255	97.44 242	68.73 350	97.54 272	94.89 190	77.89 353	94.46 266

FIs		94.10 207	93.43 211	96.11 214	94.70 310	96.82 116	99.58 194	98.93 45	92.54 200	89.34 280	97.31 246	87.62 203	97.10 296	94.22 207	86.58 290	94.40 273

UniMVSNet_ETH3D		90.06 301	88.58 309	94.49 266	94.67 311	88.09 334	97.81 338	97.57 248	83.91 353	88.44 299	97.41 243	57.44 382	97.62 270	91.41 249	88.59 269	97.77 238

UniMVSNet_NR-MVSNet		92.95 237	92.11 243	95.49 226	94.61 312	95.28 178	99.83 133	99.08 33	91.49 233	89.21 285	96.86 263	87.14 209	96.73 318	93.20 226	77.52 356	94.46 266

test_fmvs2		89.47 310	89.70 287	88.77 354	94.54 313	75.74 383	99.83 133	94.70 378	94.71 110	91.08 250	96.82 268	54.46 385	97.78 265	92.87 233	88.27 274	92.80 351

WR-MVS		92.31 252	91.25 260	95.48 229	94.45 314	95.29 177	99.60 191	98.68 70	90.10 269	88.07 306	96.89 261	80.68 269	96.80 316	93.14 229	79.67 344	94.36 277

nrg030		93.51 224	92.53 237	96.45 204	94.36 315	97.20 101	99.81 138	97.16 291	91.60 230	89.86 266	97.46 241	86.37 219	97.68 267	95.88 172	80.31 340	94.46 266

tfpnnormal		89.29 313	87.61 319	94.34 274	94.35 316	94.13 211	98.95 273	98.94 41	83.94 351	84.47 342	95.51 306	74.84 323	97.39 275	77.05 369	80.41 338	91.48 366

FC-MVSNet-test		93.81 214	93.15 220	95.80 222	94.30 317	96.20 140	99.42 218	98.89 49	92.33 211	89.03 290	97.27 248	87.39 206	96.83 314	93.20 226	86.48 291	94.36 277

MS-PatchMatch		90.65 284	90.30 275	91.71 330	94.22 318	85.50 350	98.24 322	97.70 233	88.67 296	86.42 329	96.37 279	67.82 355	98.03 252	83.62 335	99.62 90	91.60 364

WR-MVS_H		91.30 269	90.35 273	94.15 277	94.17 319	92.62 252	99.17 248	98.94 41	88.87 292	86.48 328	94.46 347	84.36 238	96.61 323	88.19 294	78.51 349	93.21 344

DU-MVS		92.46 249	91.45 258	95.49 226	94.05 320	95.28 178	99.81 138	98.74 64	92.25 213	89.21 285	96.64 271	81.66 256	96.73 318	93.20 226	77.52 356	94.46 266

NR-MVSNet		91.56 268	90.22 277	95.60 224	94.05 320	95.76 155	98.25 321	98.70 67	91.16 247	80.78 360	96.64 271	83.23 248	96.57 324	91.41 249	77.73 355	94.46 266

CP-MVSNet		91.23 273	90.22 277	94.26 275	93.96 322	92.39 256	99.09 252	98.57 89	88.95 289	86.42 329	96.57 274	79.19 284	96.37 331	90.29 273	78.95 346	94.02 307

XXY-MVS		91.82 259	90.46 270	95.88 218	93.91 323	95.40 174	98.87 283	97.69 234	88.63 298	87.87 308	97.08 253	74.38 327	97.89 260	91.66 247	84.07 310	94.35 280

PS-CasMVS		90.63 286	89.51 293	93.99 286	93.83 324	91.70 275	98.98 269	98.52 104	88.48 300	86.15 333	96.53 276	75.46 316	96.31 335	88.83 286	78.86 348	93.95 315

test_0402		85.58 330	83.94 335	90.50 338	93.81 325	85.04 352	98.55 306	95.20 372	76.01 380	79.72 365	95.13 324	64.15 369	96.26 337	66.04 390	86.88 289	90.21 375

XVG-ACMP-BASELINE		91.22 274	90.75 265	92.63 321	93.73 326	85.61 348	98.52 310	97.44 261	92.77 186	89.90 265	96.85 264	66.64 360	98.39 221	92.29 238	88.61 267	93.89 320

TranMVSNet+NR-MVSNet		91.68 267	90.61 269	94.87 248	93.69 327	93.98 216	99.69 175	98.65 74	91.03 251	88.44 299	96.83 267	80.05 277	96.18 339	90.26 274	76.89 364	94.45 271

mvsmamba		94.10 207	93.72 202	95.25 237	93.57 328	94.13 211	99.67 179	96.45 345	93.63 159	91.34 248	97.77 236	86.29 220	97.22 288	96.65 162	88.10 277	94.40 273

TransMVSNet (Re)		87.25 324	85.28 331	93.16 311	93.56 329	91.03 284	98.54 308	94.05 384	83.69 355	81.09 358	96.16 284	75.32 317	96.40 330	76.69 370	68.41 382	92.06 360

v10		90.25 296	88.82 305	94.57 261	93.53 330	93.43 231	99.08 254	96.87 323	85.00 344	87.34 318	94.51 343	80.93 266	97.02 305	82.85 339	79.23 345	93.26 342

testgi		89.01 315	88.04 316	91.90 328	93.49 331	84.89 354	99.73 164	95.66 362	93.89 152	85.14 339	98.17 221	59.68 379	94.66 365	77.73 365	88.88 260	96.16 257

v8		90.54 288	89.17 298	94.66 255	93.43 332	93.40 233	99.20 245	96.94 317	85.76 335	87.56 312	94.51 343	81.96 254	97.19 289	84.94 327	78.25 350	93.38 340

V42		91.28 271	90.12 282	94.74 252	93.42 333	93.46 230	99.68 177	97.02 305	87.36 314	89.85 268	95.05 326	81.31 262	97.34 278	87.34 305	80.07 342	93.40 338

pm-mvs1		89.36 312	87.81 318	94.01 284	93.40 334	91.93 265	98.62 305	96.48 344	86.25 330	83.86 345	96.14 285	73.68 330	97.04 301	86.16 318	75.73 368	93.04 347

RRT_MVS		93.14 232	92.92 225	93.78 293	93.31 335	90.04 308	99.66 180	97.69 234	92.53 201	88.91 292	97.76 237	84.36 238	96.93 308	95.10 182	86.99 288	94.37 276

v1144		91.09 275	89.83 284	94.87 248	93.25 336	93.69 224	99.62 189	96.98 310	86.83 324	89.64 274	94.99 331	80.94 265	97.05 299	85.08 326	81.16 329	93.87 322

v1192		90.62 287	89.25 297	94.72 254	93.13 337	93.07 237	99.50 208	97.02 305	86.33 329	89.56 276	95.01 328	79.22 283	97.09 298	82.34 343	81.16 329	94.01 309

v2v482		91.30 269	90.07 283	95.01 243	93.13 337	93.79 219	99.77 148	97.02 305	88.05 306	89.25 282	95.37 315	80.73 268	97.15 291	87.28 306	80.04 343	94.09 303

OPM-MVS		93.21 229	92.80 228	94.44 269	93.12 339	90.85 291	99.77 148	97.61 243	96.19 75	91.56 245	98.65 195	75.16 322	98.47 210	93.78 218	89.39 256	93.99 312
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 282	89.52 292	94.59 259	93.11 340	92.77 243	99.56 198	96.99 308	86.38 328	89.82 269	94.95 333	80.50 273	97.10 296	83.98 332	80.41 338	93.90 319

PEN-MVS		90.19 298	89.06 301	93.57 301	93.06 341	90.90 289	99.06 259	98.47 115	88.11 305	85.91 335	96.30 280	76.67 303	95.94 349	87.07 309	76.91 363	93.89 320

v1240		90.20 297	88.79 306	94.44 269	93.05 342	92.27 258	99.38 224	96.92 319	85.89 333	89.36 279	94.87 335	77.89 295	97.03 303	80.66 351	81.08 332	94.01 309

v148		90.70 283	89.63 288	93.92 288	92.97 343	90.97 285	99.75 156	96.89 321	87.51 311	88.27 304	95.01 328	81.67 255	97.04 301	87.40 304	77.17 361	93.75 328

v1921920		90.46 289	89.12 299	94.50 265	92.96 344	92.46 254	99.49 210	96.98 310	86.10 331	89.61 275	95.30 318	78.55 292	97.03 303	82.17 344	80.89 336	94.01 309

Baseline_NR-MVSNet		90.33 293	89.51 293	92.81 319	92.84 345	89.95 311	99.77 148	93.94 385	84.69 349	89.04 289	95.66 298	81.66 256	96.52 325	90.99 257	76.98 362	91.97 362

test_method		80.79 350	79.70 354	84.08 365	92.83 346	67.06 391	99.51 206	95.42 366	54.34 397	81.07 359	93.53 355	44.48 393	92.22 384	78.90 361	77.23 360	92.94 348

pmmvs4		92.10 256	91.07 263	95.18 239	92.82 347	94.96 189	99.48 212	96.83 326	87.45 313	88.66 297	96.56 275	83.78 243	96.83 314	89.29 282	84.77 304	93.75 328

LF4IMVS		89.25 314	88.85 304	90.45 340	92.81 348	81.19 374	98.12 328	94.79 375	91.44 237	86.29 331	97.11 251	65.30 366	98.11 247	88.53 291	85.25 299	92.07 359

DTE-MVSNet		89.40 311	88.24 314	92.88 318	92.66 349	89.95 311	99.10 251	98.22 185	87.29 315	85.12 340	96.22 282	76.27 310	95.30 358	83.56 336	75.74 367	93.41 337

EU-MVSNet		90.14 300	90.34 274	89.54 346	92.55 350	81.06 375	98.69 300	98.04 207	91.41 241	86.59 325	96.84 266	80.83 267	93.31 377	86.20 317	81.91 323	94.26 284

APD_test1		81.15 349	80.92 350	81.86 369	92.45 351	59.76 398	96.04 369	93.61 388	73.29 389	77.06 374	96.64 271	44.28 394	96.16 340	72.35 377	82.52 317	89.67 380

our_test_3		90.39 290	89.48 295	93.12 312	92.40 352	89.57 316	99.33 230	96.35 348	87.84 309	85.30 338	94.99 331	84.14 241	96.09 344	80.38 352	84.56 305	93.71 333

ppachtmachnet_test		89.58 309	88.35 312	93.25 310	92.40 352	90.44 300	99.33 230	96.73 333	85.49 340	85.90 336	95.77 293	81.09 264	96.00 348	76.00 372	82.49 318	93.30 341

v7n		89.65 308	88.29 313	93.72 295	92.22 354	90.56 297	99.07 258	97.10 297	85.42 342	86.73 322	94.72 336	80.06 276	97.13 293	81.14 349	78.12 352	93.49 336

dmvs_testset		83.79 343	86.07 327	76.94 373	92.14 355	48.60 408	96.75 356	90.27 398	89.48 277	78.65 368	98.55 207	79.25 282	86.65 396	66.85 387	82.69 316	95.57 259

PS-MVSNAJss		93.64 221	93.31 217	94.61 257	92.11 356	92.19 259	99.12 250	97.38 268	92.51 204	88.45 298	96.99 259	91.20 154	97.29 285	94.36 202	87.71 282	94.36 277

pmmvs5		90.17 299	89.09 300	93.40 304	92.10 357	89.77 314	99.74 159	95.58 364	85.88 334	87.24 319	95.74 294	73.41 331	96.48 327	88.54 290	83.56 313	93.95 315

N_pmnet		80.06 353	80.78 351	77.89 372	91.94 358	45.28 410	98.80 291	56.82 412	78.10 377	80.08 363	93.33 356	77.03 298	95.76 351	68.14 385	82.81 315	92.64 352

test_djsdf		92.83 240	92.29 241	94.47 267	91.90 359	92.46 254	99.55 200	97.27 281	91.17 245	89.96 262	96.07 289	81.10 263	96.89 310	94.67 197	88.91 259	94.05 306

SixPastTwentyTwo		88.73 316	88.01 317	90.88 334	91.85 360	82.24 366	98.22 325	95.18 373	88.97 287	82.26 351	96.89 261	71.75 336	96.67 321	84.00 331	82.98 314	93.72 332

K. test v3		88.05 320	87.24 322	90.47 339	91.82 361	82.23 367	98.96 272	97.42 264	89.05 282	76.93 376	95.60 300	68.49 352	95.42 354	85.87 322	81.01 334	93.75 328

OurMVSNet-221017-0		89.81 305	89.48 295	90.83 336	91.64 362	81.21 373	98.17 327	95.38 368	91.48 235	85.65 337	97.31 246	72.66 332	97.29 285	88.15 295	84.83 303	93.97 314

mvs_tets		91.81 260	91.08 262	94.00 285	91.63 363	90.58 296	98.67 302	97.43 262	92.43 206	87.37 317	97.05 256	71.76 335	97.32 281	94.75 194	88.68 266	94.11 302

Gipuma		66.95 366	65.00 366	72.79 378	91.52 364	67.96 390	66.16 401	95.15 374	47.89 399	58.54 396	67.99 401	29.74 398	87.54 395	50.20 400	77.83 354	62.87 401
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 141	95.74 149	98.32 119	91.47 365	95.56 166	99.84 126	97.30 277	97.74 18	97.89 140	99.35 130	79.62 279	99.85 108	99.25 54	99.24 120	99.55 142

jajsoiax		91.92 258	91.18 261	94.15 277	91.35 366	90.95 288	99.00 268	97.42 264	92.61 195	87.38 316	97.08 253	72.46 333	97.36 276	94.53 200	88.77 263	94.13 301

MDA-MVSNet-bldmvs		84.09 341	81.52 348	91.81 329	91.32 367	88.00 336	98.67 302	95.92 357	80.22 371	55.60 399	93.32 357	68.29 354	93.60 375	73.76 374	76.61 365	93.82 326

MVP-Stereo		90.93 277	90.45 272	92.37 323	91.25 368	88.76 322	98.05 332	96.17 352	87.27 316	84.04 343	95.30 318	78.46 293	97.27 287	83.78 334	99.70 85	91.09 367
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 332	83.32 340	92.10 325	90.96 369	88.58 328	99.20 245	96.52 342	79.70 373	57.12 398	92.69 362	79.11 285	93.86 372	77.10 368	77.46 358	93.86 323

YYNet1		85.50 333	83.33 339	92.00 326	90.89 370	88.38 332	99.22 244	96.55 341	79.60 374	57.26 397	92.72 361	79.09 287	93.78 373	77.25 367	77.37 359	93.84 324

anonymousdsp		91.79 265	90.92 264	94.41 272	90.76 371	92.93 242	98.93 275	97.17 289	89.08 281	87.46 315	95.30 318	78.43 294	96.92 309	92.38 237	88.73 264	93.39 339

lessismore_v0				90.53 337	90.58 372	80.90 376		95.80 358		77.01 375	95.84 291	66.15 362	96.95 306	83.03 338	75.05 369	93.74 331

EG-PatchMatch MVS		85.35 334	83.81 337	89.99 344	90.39 373	81.89 369	98.21 326	96.09 354	81.78 365	74.73 382	93.72 354	51.56 390	97.12 295	79.16 360	88.61 267	90.96 369

EGC-MVSNET		69.38 359	63.76 369	86.26 362	90.32 374	81.66 372	96.24 365	93.85 386	0.99 409	3.22 410	92.33 367	52.44 387	92.92 380	59.53 396	84.90 302	84.21 390

CMPMVS	61.59 21	84.75 337	85.14 332	83.57 366	90.32 374	62.54 394	96.98 352	97.59 247	74.33 387	69.95 388	96.66 269	64.17 368	98.32 231	87.88 299	88.41 272	89.84 378
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 340	82.92 343	89.21 348	90.03 376	82.60 363	96.89 355	95.62 363	80.59 369	75.77 381	89.17 378	65.04 367	94.79 364	72.12 378	81.02 333	90.23 374

pmmvs6		85.69 329	83.84 336	91.26 333	90.00 377	84.41 356	97.82 337	96.15 353	75.86 381	81.29 357	95.39 313	61.21 377	96.87 312	83.52 337	73.29 371	92.50 355

DSMNet-mixed		88.28 319	88.24 314	88.42 356	89.64 378	75.38 385	98.06 331	89.86 399	85.59 339	88.20 305	92.14 368	76.15 312	91.95 385	78.46 362	96.05 196	97.92 234

UnsupCasMVSNet_eth		85.52 331	83.99 333	90.10 342	89.36 379	83.51 360	96.65 357	97.99 209	89.14 280	75.89 380	93.83 352	63.25 371	93.92 370	81.92 346	67.90 385	92.88 349

Anonymous20231206		86.32 327	85.42 330	89.02 350	89.11 380	80.53 379	99.05 263	95.28 369	85.43 341	82.82 349	93.92 351	74.40 326	93.44 376	66.99 386	81.83 324	93.08 346

Anonymous20240521		85.15 335	83.81 337	89.16 349	88.32 381	82.69 362	98.80 291	95.74 359	79.72 372	81.53 356	90.99 371	65.38 365	94.16 368	72.69 376	81.11 331	90.63 372

OpenMVS_ROB	79.82 20	83.77 344	81.68 347	90.03 343	88.30 382	82.82 361	98.46 311	95.22 371	73.92 388	76.00 379	91.29 370	55.00 384	96.94 307	68.40 384	88.51 271	90.34 373

test20.03		84.72 338	83.99 333	86.91 360	88.19 383	80.62 378	98.88 280	95.94 356	88.36 302	78.87 366	94.62 341	68.75 349	89.11 391	66.52 388	75.82 366	91.00 368

KD-MVS_self_test		83.59 345	82.06 345	88.20 357	86.93 384	80.70 377	97.21 345	96.38 346	82.87 359	82.49 350	88.97 379	67.63 356	92.32 383	73.75 375	62.30 394	91.58 365

MIMVSNet1		82.58 346	80.51 352	88.78 352	86.68 385	84.20 357	96.65 357	95.41 367	78.75 375	78.59 369	92.44 363	51.88 389	89.76 390	65.26 391	78.95 346	92.38 358

CL-MVSNet_self_test		84.50 339	83.15 342	88.53 355	86.00 386	81.79 370	98.82 288	97.35 270	85.12 343	83.62 347	90.91 373	76.66 304	91.40 386	69.53 382	60.36 395	92.40 357

UnsupCasMVSNet_bld		79.97 355	77.03 360	88.78 352	85.62 387	81.98 368	93.66 381	97.35 270	75.51 384	70.79 387	83.05 393	48.70 391	94.91 362	78.31 363	60.29 396	89.46 383

Patchmatch-RL test		86.90 325	85.98 329	89.67 345	84.45 388	75.59 384	89.71 394	92.43 392	86.89 323	77.83 373	90.94 372	94.22 80	93.63 374	87.75 300	69.61 377	99.79 97

pmmvs-eth3d		84.03 342	81.97 346	90.20 341	84.15 389	87.09 341	98.10 330	94.73 377	83.05 357	74.10 384	87.77 385	65.56 364	94.01 369	81.08 350	69.24 379	89.49 382

test_fmvs3		79.99 354	80.17 353	79.45 371	84.02 390	62.83 392	99.05 263	93.49 389	88.29 304	80.06 364	86.65 388	28.09 400	88.00 392	88.63 287	73.27 372	87.54 388

PM-MVS		80.47 351	78.88 356	85.26 363	83.79 391	72.22 387	95.89 372	91.08 396	85.71 338	76.56 378	88.30 381	36.64 396	93.90 371	82.39 342	69.57 378	89.66 381

new-patchmatchnet		81.19 348	79.34 355	86.76 361	82.86 392	80.36 380	97.92 334	95.27 370	82.09 364	72.02 385	86.87 387	62.81 373	90.74 389	71.10 379	63.08 392	89.19 385

mvsany_test3		82.12 347	81.14 349	85.06 364	81.87 393	70.41 388	97.09 349	92.14 393	91.27 244	77.84 372	88.73 380	39.31 395	95.49 352	90.75 264	71.24 374	89.29 384

WB-MVS		76.28 357	77.28 359	73.29 377	81.18 394	54.68 402	97.87 336	94.19 381	81.30 366	69.43 389	90.70 374	77.02 299	82.06 400	35.71 405	68.11 384	83.13 391

test_f		78.40 356	77.59 358	80.81 370	80.82 395	62.48 395	96.96 353	93.08 391	83.44 356	74.57 383	84.57 392	27.95 401	92.63 381	84.15 329	72.79 373	87.32 389

SSC-MVS		75.42 358	76.40 361	72.49 381	80.68 396	53.62 403	97.42 341	94.06 383	80.42 370	68.75 390	90.14 376	76.54 306	81.66 401	33.25 406	66.34 388	82.19 392

pmmvs3		80.27 352	77.77 357	87.76 359	80.32 397	82.43 365	98.23 324	91.97 394	72.74 390	78.75 367	87.97 384	57.30 383	90.99 388	70.31 380	62.37 393	89.87 377

testf1		68.38 362	66.92 363	72.78 379	78.80 398	50.36 405	90.95 392	87.35 404	55.47 395	58.95 394	88.14 382	20.64 405	87.60 393	57.28 397	64.69 389	80.39 394

APD_test2		68.38 362	66.92 363	72.78 379	78.80 398	50.36 405	90.95 392	87.35 404	55.47 395	58.95 394	88.14 382	20.64 405	87.60 393	57.28 397	64.69 389	80.39 394

ambc				83.23 367	77.17 400	62.61 393	87.38 396	94.55 380		76.72 377	86.65 388	30.16 397	96.36 332	84.85 328	69.86 376	90.73 371

test_vis3_rt		68.82 360	66.69 365	75.21 376	76.24 401	60.41 397	96.44 360	68.71 411	75.13 385	50.54 402	69.52 400	16.42 410	96.32 334	80.27 353	66.92 387	68.89 398

TDRefinement		84.76 336	82.56 344	91.38 332	74.58 402	84.80 355	97.36 343	94.56 379	84.73 348	80.21 362	96.12 288	63.56 370	98.39 221	87.92 298	63.97 391	90.95 370

E-PMN		52.30 370	52.18 372	52.67 387	71.51 403	45.40 409	93.62 382	76.60 409	36.01 403	43.50 404	64.13 403	27.11 402	67.31 406	31.06 407	26.06 402	45.30 405

EMVS		51.44 372	51.22 374	52.11 388	70.71 404	44.97 411	94.04 378	75.66 410	35.34 405	42.40 405	61.56 406	28.93 399	65.87 407	27.64 408	24.73 403	45.49 404

PMMVS2		67.15 365	64.15 368	76.14 375	70.56 405	62.07 396	93.89 379	87.52 403	58.09 394	60.02 393	78.32 395	22.38 404	84.54 398	59.56 395	47.03 400	81.80 393

FPMVS		68.72 361	68.72 362	68.71 383	65.95 406	44.27 412	95.97 371	94.74 376	51.13 398	53.26 400	90.50 375	25.11 403	83.00 399	60.80 394	80.97 335	78.87 396

wuyk23d		20.37 376	20.84 379	18.99 391	65.34 407	27.73 414	50.43 402	7.67 415	9.50 408	8.01 409	6.34 409	6.13 413	26.24 408	23.40 409	10.69 407	2.99 406

LCM-MVSNet		67.77 364	64.73 367	76.87 374	62.95 408	56.25 401	89.37 395	93.74 387	44.53 400	61.99 392	80.74 394	20.42 407	86.53 397	69.37 383	59.50 397	87.84 386

MVE	53.74 22	51.54 371	47.86 375	62.60 385	59.56 409	50.93 404	79.41 399	77.69 408	35.69 404	36.27 406	61.76 405	5.79 414	69.63 404	37.97 404	36.61 401	67.24 399
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 368	52.24 371	67.66 384	49.27 410	56.82 400	83.94 397	82.02 407	70.47 391	33.28 407	64.54 402	17.23 409	69.16 405	45.59 402	23.85 404	77.02 397

tmp_tt		65.23 367	62.94 370	72.13 382	44.90 411	50.03 407	81.05 398	89.42 402	38.45 401	48.51 403	99.90 18	54.09 386	78.70 403	91.84 246	18.26 405	87.64 387

PMVS	49.05 23	53.75 369	51.34 373	60.97 386	40.80 412	34.68 413	74.82 400	89.62 401	37.55 402	28.67 408	72.12 397	7.09 412	81.63 402	43.17 403	68.21 383	66.59 400
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 374	39.14 377	33.31 389	19.94 413	24.83 415	98.36 318	9.75 414	15.53 407	51.31 401	87.14 386	19.62 408	17.74 409	47.10 401	3.47 408	57.36 402

testmvs		40.60 373	44.45 376	29.05 390	19.49 414	14.11 416	99.68 177	18.47 413	20.74 406	64.59 391	98.48 212	10.95 411	17.09 410	56.66 399	11.01 406	55.94 403

test_blank		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.02 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

eth-test2					0.00 415

eth-test					0.00 415

uanet_test		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 411	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

DCPMVS		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 411	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

cdsmvs_eth3d_5k		23.43 375	31.24 378	0.00 392	0.00 415	0.00 417	0.00 403	98.09 201	0.00 410	0.00 411	99.67 96	83.37 246	0.00 411	0.00 410	0.00 409	0.00 407

pcd_1.5k_mvsjas		7.60 378	10.13 381	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 411	91.20 154	0.00 411	0.00 410	0.00 409	0.00 407

sosnet-low-res		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 411	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

sosnet		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 411	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

uncertanet		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 411	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

Regformer		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 411	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

ab-mvs-re		8.28 377	11.04 380	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	99.40 124	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

uanet		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 411	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

WAC-MVS						90.97 285								86.10 320

PC_three_1452									96.96 44	99.80 18	99.79 57	97.49 9	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 131	97.27 34	99.80 18	99.94 4	97.18 20	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 61	99.83 13	99.91 14	97.87 5	100.00 1	99.92 12	100.00 1	100.00 1

GSMVS																99.59 133

sam_mvs1												94.72 64				99.59 133

sam_mvs												94.25 79

MTGPA								98.28 179

test_post1							95.78 373				59.23 407	93.20 111	97.74 266	91.06 255

test_post											63.35 404	94.43 69	98.13 246

patchmatchnet-post											91.70 369	95.12 50	97.95 257

MTMP							99.87 106	96.49 343

test9_res														99.71 33	99.99 21	100.00 1

agg_prior2														99.48 43	100.00 1	100.00 1

test_prior4						98.05 67	99.94 69

test_prior2							99.95 53		95.78 81	99.73 33	99.76 65	96.00 33		99.78 27	100.00 1

旧先验2							99.46 215		94.21 133	99.85 9			99.95 69	96.96 156

新几何2							99.40 219

无先验							99.49 210	98.71 66	93.46 162				100.00 1	94.36 202		99.99 23

原ACMM2							99.90 91

testdata2													99.99 36	90.54 268

segment_acmp												96.68 25

testdata1							99.28 239		96.35 71

plane_prior5								97.87 223					98.37 227	97.79 132	89.55 253	94.52 263

plane_prior4											98.59 200

plane_prior3						91.64 277			96.63 56	93.01 226

plane_prior2							99.84 126		96.38 67

plane_prior						91.74 271	99.86 118		96.76 52						89.59 252

n2								0.00 416

nn								0.00 416

door-mid								89.69 400

test11								98.44 123

door								90.31 397

HQP5-MVS						91.85 267

BP-MVS														97.92 124

HQP4-MVS										93.37 222			98.39 221			94.53 261

HQP3-MVS								97.89 221							89.60 250

HQP2-MVS												80.65 270

MDTV_nov1_ep13_2view						96.26 135	96.11 367		91.89 222	98.06 134		94.40 71		94.30 204		99.67 116

ACMMP++_ref															87.04 287

ACMMP++															88.23 275

Test By Simon												92.82 122

High-resolution multi-view benchmark