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		97.23 105	96.80 112	98.51 111	99.99 1	95.60 168	99.09 254	98.84 58	93.32 170	96.74 174	99.72 83	86.04 227	100.00 1	98.01 121	99.43 114	99.94 74

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 16	98.69 68	98.20 7	99.93 1	99.98 2	96.82 21	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 29	98.64 76	98.47 2	99.13 89	99.92 13	96.38 29	100.00 1	99.74 30	100.00 1	100.00 1

mPP-MVS		98.39 47	98.20 46	98.97 77	99.97 3	96.92 116	99.95 54	98.38 159	95.04 99	98.61 116	99.80 53	93.39 100	100.00 1	98.64 93	100.00 1	99.98 48

CPTT-MVS		97.64 87	97.32 91	98.58 103	99.97 3	95.77 157	99.96 36	98.35 165	89.90 275	98.36 126	99.79 57	91.18 156	99.99 36	98.37 105	99.99 21	99.99 23

DP-MVS Recon		98.41 45	98.02 57	99.56 25	99.97 3	98.70 48	99.92 82	98.44 123	92.06 220	98.40 125	99.84 43	95.68 39	100.00 1	98.19 111	99.71 87	99.97 58

PAPR		98.52 35	98.16 49	99.58 24	99.97 3	98.77 42	99.95 54	98.43 131	95.35 93	98.03 138	99.75 71	94.03 86	99.98 43	98.11 116	99.83 76	99.99 23

HFP-MVS		98.56 32	98.37 36	99.14 61	99.96 8	97.43 98	99.95 54	98.61 82	94.77 107	99.31 80	99.85 32	94.22 79	100.00 1	98.70 88	99.98 32	99.98 48

region2R		98.54 33	98.37 36	99.05 69	99.96 8	97.18 105	99.96 36	98.55 98	94.87 105	99.45 68	99.85 32	94.07 85	100.00 1	98.67 90	100.00 1	99.98 48

ACMMPR		98.50 36	98.32 40	99.05 69	99.96 8	97.18 105	99.95 54	98.60 84	94.77 107	99.31 80	99.84 43	93.73 95	100.00 1	98.70 88	99.98 32	99.98 48

NCCC		99.37 2	99.25 2	99.71 14	99.96 8	99.15 21	99.97 29	98.62 81	98.02 13	99.90 3	99.95 3	97.33 15	100.00 1	99.54 39	100.00 1	100.00 1

CP-MVS		98.45 40	98.32 40	98.87 84	99.96 8	96.62 125	99.97 29	98.39 155	94.43 120	98.90 98	99.87 24	94.30 77	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 29	99.93 11	97.49 8

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 54	98.43 131					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 26	98.55 25	99.15 59	99.94 13	97.50 94	99.94 70	98.42 143	96.22 73	99.41 72	99.78 61	94.34 75	99.96 61	98.92 74	99.95 49	99.99 23

X-MVStestdata		93.83 215	92.06 247	99.15 59	99.94 13	97.50 94	99.94 70	98.42 143	96.22 73	99.41 72	41.37 410	94.34 75	99.96 61	98.92 74	99.95 49	99.99 23

test_prior				99.43 35	99.94 13	98.49 61		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 62	99.98 16	98.86 53	97.10 40	99.80 17	99.94 4	95.92 35	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 45	99.91 88	98.39 155	97.20 38	99.46 67	99.85 32	95.53 43	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 71	99.94 13	97.17 108	99.95 54	98.39 155	94.70 111	98.26 132	99.81 52	91.84 147	100.00 1	98.85 80	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 46	99.87 108	98.33 170	93.97 148	99.76 28	99.87 24	94.99 57	99.75 132	98.55 97	100.00 1	99.98 48

PAPM_NR		98.12 61	97.93 64	98.70 92	99.94 13	96.13 147	99.82 138	98.43 131	94.56 115	97.52 152	99.70 87	94.40 70	99.98 43	97.00 155	99.98 32	99.99 23

MG-MVS		98.91 18	98.65 20	99.68 15	99.94 13	99.07 24	99.64 188	99.44 20	97.33 31	99.00 94	99.72 83	94.03 86	99.98 43	98.73 87	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 36	98.43 131	97.27 34	99.80 17	99.94 4	96.71 22	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 17	99.88 21	96.71 22	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 54	98.32 172	97.28 32	99.83 13	99.91 14	97.22 17	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 36	98.42 143	97.28 32	99.86 7	99.94 4	97.22 17

MSP-MVS		99.09 9	99.12 5	98.98 76	99.93 24	97.24 102	99.95 54	98.42 143	97.50 26	99.52 63	99.88 21	97.43 14	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 42		98.43 131		99.63 47			99.85 108

FOURS1					99.92 31	97.66 88	99.95 54	98.36 163	95.58 87	99.52 63

ZD-MVS					99.92 31	98.57 56		98.52 104	92.34 212	99.31 80	99.83 45	95.06 52	99.80 121	99.70 34	99.97 42

GST-MVS		98.27 52	97.97 59	99.17 55	99.92 31	97.57 90	99.93 77	98.39 155	94.04 143	98.80 103	99.74 78	92.98 115	100.00 1	98.16 113	99.76 84	99.93 76

TEST9					99.92 31	98.92 29	99.96 36	98.43 131	93.90 153	99.71 36	99.86 28	95.88 36	99.85 108

train_agg		98.88 19	98.65 20	99.59 23	99.92 31	98.92 29	99.96 36	98.43 131	94.35 125	99.71 36	99.86 28	95.94 33	99.85 108	99.69 35	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 36	98.43 131	94.35 125	99.69 39	99.85 32	95.94 33	99.85 108

PGM-MVS		98.34 48	98.13 51	98.99 75	99.92 31	97.00 112	99.75 158	99.50 18	93.90 153	99.37 77	99.76 65	93.24 109	100.00 1	97.75 139	99.96 46	99.98 48

ACMMP		97.74 82	97.44 85	98.66 95	99.92 31	96.13 147	99.18 249	99.45 19	94.84 106	96.41 184	99.71 85	91.40 150	99.99 36	97.99 123	98.03 161	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 54	98.43 131	96.48 59	99.80 17	99.93 11	97.44 12	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 54	98.56 92	97.56 25	99.44 69	99.85 32	95.38 46	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 60	99.87 108	98.36 163	94.08 138	99.74 31	99.73 80	94.08 84	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	99.24 244	98.47 115	98.14 10	99.08 90	99.91 14	93.09 112	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 36				99.80 53	97.44 12	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	99.87 108	98.44 123	97.48 27	99.64 46	99.94 4	96.68 24	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		97.10 110	97.04 102	97.27 184	99.89 45	91.92 267	99.90 94	99.07 34	88.67 298	95.26 206	99.82 48	93.17 111	99.98 43	98.15 114	99.47 108	99.90 83

ZNCC-MVS		98.31 49	98.03 56	99.17 55	99.88 49	97.59 89	99.94 70	98.44 123	94.31 128	98.50 120	99.82 48	93.06 113	99.99 36	98.30 109	99.99 21	99.93 76

SR-MVS		98.46 39	98.30 43	98.93 81	99.88 49	97.04 111	99.84 128	98.35 165	94.92 103	99.32 79	99.80 53	93.35 102	99.78 125	99.30 52	99.95 49	99.96 64

9.14			98.38 34		99.87 51		99.91 88	98.33 170	93.22 173	99.78 26	99.89 19	94.57 67	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	99.86 120	98.38 159	93.19 174	99.77 27	99.94 4	95.54 41	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 71	99.86 53	97.10 110	99.98 16	98.80 62	90.78 261	99.62 50	99.78 61	95.30 47	100.00 1	99.80 25	99.93 60	99.99 23

MTAPA		98.29 51	97.96 62	99.30 44	99.85 54	97.93 78	99.39 225	98.28 179	95.76 82	97.18 162	99.88 21	92.74 123	100.00 1	98.67 90	99.88 70	99.99 23

LS3D		95.84 162	95.11 172	98.02 139	99.85 54	95.10 188	98.74 296	98.50 112	87.22 319	93.66 224	99.86 28	87.45 209	99.95 69	90.94 261	99.81 82	99.02 205

HPM-MVS		97.96 65	97.72 73	98.68 93	99.84 56	96.39 134	99.90 94	98.17 191	92.61 198	98.62 115	99.57 109	91.87 146	99.67 145	98.87 79	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 90	99.83 57	96.59 127	99.40 221	98.51 107	95.29 95	98.51 119	99.76 65	93.60 99	99.71 138	98.53 98	99.52 103	99.95 71

save fliter					99.82 58	98.79 40	99.96 36	98.40 152	97.66 21

PLC	95.54 3	97.93 67	97.89 68	98.05 138	99.82 58	94.77 197	99.92 82	98.46 117	93.93 151	97.20 161	99.27 136	95.44 45	99.97 53	97.41 144	99.51 106	99.41 168
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 87	99.81 60	96.60 126	99.82 138	98.30 177	93.95 150	99.37 77	99.77 63	92.84 119	99.76 131	98.95 71	99.92 63	99.97 58

EI-MVSNet-UG-set		98.14 60	97.99 58	98.60 100	99.80 61	96.27 137	99.36 230	98.50 112	95.21 97	98.30 129	99.75 71	93.29 106	99.73 137	98.37 105	99.30 120	99.81 94

SR-MVS-dyc-post		98.31 49	98.17 48	98.71 91	99.79 62	96.37 135	99.76 155	98.31 174	94.43 120	99.40 74	99.75 71	93.28 107	99.78 125	98.90 77	99.92 63	99.97 58

RE-MVS-def			98.13 51		99.79 62	96.37 135	99.76 155	98.31 174	94.43 120	99.40 74	99.75 71	92.95 116		98.90 77	99.92 63	99.97 58

HPM-MVS_fast		97.80 77	97.50 83	98.68 93	99.79 62	96.42 130	99.88 105	98.16 195	91.75 230	98.94 96	99.54 112	91.82 148	99.65 147	97.62 142	99.99 21	99.99 23

SF-MVS		98.67 27	98.40 32	99.50 30	99.77 65	98.67 49	99.90 94	98.21 186	93.53 163	99.81 15	99.89 19	94.70 65	99.86 107	99.84 22	99.93 60	99.96 64

旧先验1					99.76 66	97.52 92		98.64 76			99.85 32	95.63 40			99.94 54	99.99 23

OMC-MVS		97.28 102	97.23 94	97.41 175	99.76 66	93.36 236	99.65 184	97.95 214	96.03 77	97.41 156	99.70 87	89.61 185	99.51 153	96.73 164	98.25 153	99.38 170

新几何1				99.42 37	99.75 68	98.27 64		98.63 80	92.69 193	99.55 58	99.82 48	94.40 70	100.00 1	91.21 253	99.94 54	99.99 23

MP-MVS-pluss		98.07 63	97.64 77	99.38 42	99.74 69	98.41 63	99.74 161	98.18 190	93.35 168	96.45 181	99.85 32	92.64 125	99.97 53	98.91 76	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 49	99.77 150	98.38 159	96.73 53	99.88 6	99.74 78	94.89 59	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 57		98.40 152		99.65 43		94.76 62	99.75 132		99.98 32	99.99 23

原ACMM1				98.96 78	99.73 72	96.99 113		98.51 107	94.06 141	99.62 50	99.85 32	94.97 58	99.96 61	95.11 184	99.95 49	99.92 81

TSAR-MVS + GP.		98.60 30	98.51 28	98.86 85	99.73 72	96.63 124	99.97 29	97.92 219	98.07 11	98.76 107	99.55 110	95.00 56	99.94 77	99.91 15	97.68 166	99.99 23

CANet		98.27 52	97.82 70	99.63 17	99.72 74	99.10 23	99.98 16	98.51 107	97.00 43	98.52 118	99.71 85	87.80 204	99.95 69	99.75 28	99.38 116	99.83 91

F-COLMAP		96.93 121	96.95 105	96.87 194	99.71 75	91.74 272	99.85 123	97.95 214	93.11 177	95.72 199	99.16 147	92.35 135	99.94 77	95.32 182	99.35 118	98.92 208

SD-MVS		98.92 17	98.70 19	99.56 25	99.70 76	98.73 46	99.94 70	98.34 169	96.38 65	99.81 15	99.76 65	94.59 66	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	95.59 227	99.67 77	86.91 346	99.95 54	98.89 49	97.60 22	99.90 3	99.76 65	96.54 27	99.98 43	99.94 11	99.82 80	99.88 85

ACMMP_NAP		98.49 37	98.14 50	99.54 27	99.66 78	98.62 55	99.85 123	98.37 162	94.68 112	99.53 61	99.83 45	92.87 118	100.00 1	98.66 92	99.84 75	99.99 23

DeepPCF-MVS	95.94 2	97.71 85	98.98 12	93.92 291	99.63 79	81.76 373	99.96 36	98.56 92	99.47 1	99.19 87	99.99 1	94.16 83	100.00 1	99.92 12	99.93 60	100.00 1

EPNet		98.49 37	98.40 32	98.77 89	99.62 80	96.80 121	99.90 94	99.51 17	97.60 22	99.20 85	99.36 130	93.71 96	99.91 89	97.99 123	98.71 141	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 6	99.76 6	98.39 3	99.39 76	99.80 53	90.49 172	99.96 61	99.89 16	99.43 114	99.98 48

PVSNet_BlendedMVS		96.05 156	95.82 152	96.72 199	99.59 81	96.99 113	99.95 54	99.10 31	94.06 141	98.27 130	95.80 294	89.00 196	99.95 69	99.12 58	87.53 288	93.24 345

PVSNet_Blended		97.94 66	97.64 77	98.83 86	99.59 81	96.99 113	100.00 1	99.10 31	95.38 92	98.27 130	99.08 150	89.00 196	99.95 69	99.12 58	99.25 122	99.57 143

PatchMatch-RL		96.04 157	95.40 161	97.95 141	99.59 81	95.22 184	99.52 206	99.07 34	93.96 149	96.49 180	98.35 221	82.28 255	99.82 120	90.15 277	99.22 125	98.81 215

dcpmvs_2		97.42 97	98.09 54	95.42 232	99.58 85	87.24 342	99.23 245	96.95 317	94.28 131	98.93 97	99.73 80	94.39 73	99.16 175	99.89 16	99.82 80	99.86 89

test222					99.55 86	97.41 100	99.34 231	98.55 98	91.86 225	99.27 84	99.83 45	93.84 93			99.95 49	99.99 23

CNLPA		97.76 81	97.38 87	98.92 82	99.53 87	96.84 118	99.87 108	98.14 199	93.78 156	96.55 179	99.69 89	92.28 137	99.98 43	97.13 150	99.44 112	99.93 76

API-MVS		97.86 71	97.66 76	98.47 113	99.52 88	95.41 175	99.47 215	98.87 52	91.68 231	98.84 100	99.85 32	92.34 136	99.99 36	98.44 101	99.96 46	100.00 1

PVSNet	91.05 13	97.13 109	96.69 117	98.45 115	99.52 88	95.81 155	99.95 54	99.65 12	94.73 109	99.04 92	99.21 143	84.48 242	99.95 69	94.92 189	98.74 140	99.58 141

114514_t		97.41 98	96.83 110	99.14 61	99.51 90	97.83 80	99.89 102	98.27 181	88.48 302	99.06 91	99.66 98	90.30 176	99.64 148	96.32 168	99.97 42	99.96 64

cl22		93.77 219	93.25 223	95.33 236	99.49 91	94.43 201	99.61 192	98.09 201	90.38 266	89.16 291	95.61 301	90.56 169	97.34 281	91.93 245	84.45 308	94.21 291

testdata				98.42 118	99.47 92	95.33 178		98.56 92	93.78 156	99.79 25	99.85 32	93.64 98	99.94 77	94.97 187	99.94 54	100.00 1

MAR-MVS		97.43 93	97.19 96	98.15 132	99.47 92	94.79 196	99.05 265	98.76 63	92.65 196	98.66 113	99.82 48	88.52 201	99.98 43	98.12 115	99.63 92	99.67 115
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		94.54 197	93.42 216	97.91 146	99.46 94	94.04 214	98.93 277	97.48 262	81.15 369	90.04 264	99.55 110	87.02 215	99.95 69	88.97 287	98.11 157	99.73 105

MVS_111021_LR		98.42 44	98.38 34	98.53 110	99.39 95	95.79 156	99.87 108	99.86 2	96.70 54	98.78 104	99.79 57	92.03 143	99.90 91	99.17 57	99.86 74	99.88 85

CHOSEN 280x420		99.01 13	99.03 10	98.95 79	99.38 96	98.87 33	98.46 313	99.42 22	97.03 42	99.02 93	99.09 149	99.35 1	98.21 245	99.73 32	99.78 83	99.77 101

MVS_111021_HR		98.72 25	98.62 22	99.01 74	99.36 97	97.18 105	99.93 77	99.90 1	96.81 51	98.67 112	99.77 63	93.92 88	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 36	98.44 123	97.96 14	99.55 58	99.94 4	97.18 19	100.00 1	93.81 217	99.94 54	99.98 48

TAPA-MVS	92.12 8	94.42 202	93.60 209	96.90 193	99.33 98	91.78 271	99.78 147	98.00 208	89.89 276	94.52 212	99.47 116	91.97 144	99.18 173	69.90 383	99.52 103	99.73 105
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CS-MVS-test		97.88 69	97.94 63	97.70 159	99.28 100	95.20 185	99.98 16	97.15 296	95.53 89	99.62 50	99.79 57	92.08 142	98.38 228	98.75 86	99.28 121	99.52 153

test_fmvsm_n_1920		98.44 41	98.61 23	97.92 144	99.27 101	95.18 186	100.00 1	98.90 47	98.05 12	99.80 17	99.73 80	92.64 125	99.99 36	99.58 38	99.51 106	98.59 225

fmvsm_l_conf0.5_n_a		99.00 14	98.91 14	99.28 45	99.21 102	97.91 79	99.98 16	98.85 56	98.25 4	99.92 2	99.75 71	94.72 63	99.97 53	99.87 19	99.64 91	99.95 71

test_yl		97.83 73	97.37 88	99.21 49	99.18 103	97.98 75	99.64 188	99.27 27	91.43 240	97.88 144	98.99 159	95.84 37	99.84 116	98.82 81	95.32 219	99.79 97

DCV-MVSNet		97.83 73	97.37 88	99.21 49	99.18 103	97.98 75	99.64 188	99.27 27	91.43 240	97.88 144	98.99 159	95.84 37	99.84 116	98.82 81	95.32 219	99.79 97

MVS_0304		98.87 20	98.61 23	99.67 16	99.18 103	99.13 22	99.87 108	99.65 12	98.17 8	98.75 109	99.75 71	92.76 122	99.94 77	99.88 18	99.44 112	99.94 74

fmvsm_l_conf0.5_n		98.94 15	98.84 17	99.25 46	99.17 106	97.81 82	99.98 16	98.86 53	98.25 4	99.90 3	99.76 65	94.21 81	99.97 53	99.87 19	99.52 103	99.98 48

DeepC-MVS	94.51 4	96.92 122	96.40 127	98.45 115	99.16 107	95.90 153	99.66 183	98.06 204	96.37 68	94.37 215	99.49 115	83.29 251	99.90 91	97.63 141	99.61 97	99.55 145
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 53	100.00 1	98.58 87	97.70 20	98.21 134	99.24 141	92.58 128	99.94 77	98.63 95	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 79	97.91 66	97.43 174	99.10 109	94.42 202	99.99 6	97.10 301	95.07 98	99.68 40	99.75 71	92.95 116	98.34 232	98.38 103	99.14 127	99.54 149

Anonymous202405211		93.10 236	91.99 248	96.40 209	99.10 109	89.65 317	98.88 282	97.93 216	83.71 356	94.00 221	98.75 188	68.79 351	99.88 102	95.08 185	91.71 249	99.68 113

fmvsm_s_conf0.5_n		97.80 77	97.85 69	97.67 160	99.06 111	94.41 203	99.98 16	98.97 40	97.34 29	99.63 47	99.69 89	87.27 211	99.97 53	99.62 37	99.06 131	98.62 224

HyFIR lowres test		96.66 136	96.43 126	97.36 180	99.05 112	93.91 219	99.70 176	99.80 3	90.54 264	96.26 187	98.08 228	92.15 140	98.23 244	96.84 163	95.46 214	99.93 76

LFMVS		94.75 190	93.56 212	98.30 124	99.03 113	95.70 162	98.74 296	97.98 211	87.81 312	98.47 121	99.39 127	67.43 359	99.53 150	98.01 121	95.20 222	99.67 115

AllTest		92.48 250	91.64 253	95.00 246	99.01 114	88.43 331	98.94 276	96.82 331	86.50 328	88.71 296	98.47 214	74.73 328	99.88 102	85.39 325	96.18 196	96.71 252

TestCases				95.00 246	99.01 114	88.43 331		96.82 331	86.50 328	88.71 296	98.47 214	74.73 328	99.88 102	85.39 325	96.18 196	96.71 252

COLMAP_ROB	90.47 14	92.18 257	91.49 259	94.25 279	99.00 116	88.04 337	98.42 318	96.70 338	82.30 365	88.43 303	99.01 156	76.97 304	99.85 108	86.11 321	96.50 191	94.86 263
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs1		95.35 176	95.68 157	94.36 275	98.99 117	84.98 355	99.96 36	96.65 340	97.60 22	99.73 32	98.96 165	71.58 341	99.93 85	98.31 108	99.37 117	98.17 232

HY-MVS	92.50 7	97.79 79	97.17 98	99.63 17	98.98 118	99.32 9	97.49 342	99.52 15	95.69 84	98.32 128	97.41 245	93.32 104	99.77 128	98.08 119	95.75 210	99.81 94

VNet		97.21 106	96.57 122	99.13 65	98.97 119	97.82 81	99.03 268	99.21 29	94.31 128	99.18 88	98.88 176	86.26 226	99.89 96	98.93 73	94.32 231	99.69 112

thres200		96.96 119	96.21 133	99.22 48	98.97 119	98.84 36	99.85 123	99.71 7	93.17 175	96.26 187	98.88 176	89.87 182	99.51 153	94.26 207	94.91 224	99.31 180

tfpn200view9		96.79 126	95.99 138	99.19 51	98.94 121	98.82 37	99.78 147	99.71 7	92.86 183	96.02 192	98.87 179	89.33 189	99.50 155	93.84 214	94.57 227	99.27 186

thres400		96.78 128	95.99 138	99.16 57	98.94 121	98.82 37	99.78 147	99.71 7	92.86 183	96.02 192	98.87 179	89.33 189	99.50 155	93.84 214	94.57 227	99.16 193

sasdasda		97.09 112	96.32 128	99.39 40	98.93 123	98.95 27	99.72 169	97.35 273	94.45 117	97.88 144	99.42 120	86.71 218	99.52 151	98.48 99	93.97 237	99.72 107

Anonymous20231211		89.86 306	88.44 313	94.13 282	98.93 123	90.68 296	98.54 310	98.26 182	76.28 381	86.73 324	95.54 305	70.60 347	97.56 274	90.82 264	80.27 343	94.15 299

canonicalmvs		97.09 112	96.32 128	99.39 40	98.93 123	98.95 27	99.72 169	97.35 273	94.45 117	97.88 144	99.42 120	86.71 218	99.52 151	98.48 99	93.97 237	99.72 107

SDMVSNet		94.80 186	93.96 200	97.33 182	98.92 126	95.42 174	99.59 194	98.99 37	92.41 209	92.55 239	97.85 236	75.81 318	98.93 187	97.90 129	91.62 250	97.64 243

sd_testset		93.55 226	92.83 229	95.74 225	98.92 126	90.89 293	98.24 324	98.85 56	92.41 209	92.55 239	97.85 236	71.07 346	98.68 204	93.93 211	91.62 250	97.64 243

EPNet_dtu		95.71 166	95.39 162	96.66 202	98.92 126	93.41 233	99.57 198	98.90 47	96.19 75	97.52 152	98.56 206	92.65 124	97.36 279	77.89 366	98.33 148	99.20 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 62	97.60 79	99.60 22	98.92 126	99.28 17	99.89 102	99.52 15	95.58 87	98.24 133	99.39 127	93.33 103	99.74 134	97.98 125	95.58 213	99.78 100

CHOSEN 1792x2688		96.81 125	96.53 123	97.64 162	98.91 130	93.07 238	99.65 184	99.80 3	95.64 85	95.39 203	98.86 181	84.35 244	99.90 91	96.98 157	99.16 126	99.95 71

thres100view900		96.74 131	95.92 148	99.18 52	98.90 131	98.77 42	99.74 161	99.71 7	92.59 200	95.84 195	98.86 181	89.25 191	99.50 155	93.84 214	94.57 227	99.27 186

thres600view7		96.69 134	95.87 151	99.14 61	98.90 131	98.78 41	99.74 161	99.71 7	92.59 200	95.84 195	98.86 181	89.25 191	99.50 155	93.44 226	94.50 230	99.16 193

MSDG		94.37 204	93.36 220	97.40 176	98.88 133	93.95 218	99.37 228	97.38 271	85.75 339	90.80 257	99.17 146	84.11 246	99.88 102	86.35 318	98.43 146	98.36 230

MGCFI-Net		97.00 117	96.22 132	99.34 43	98.86 134	98.80 39	99.67 181	97.30 280	94.31 128	97.77 148	99.41 124	86.36 224	99.50 155	98.38 103	93.90 239	99.72 107

h-mvs33		94.92 184	94.36 189	96.59 204	98.85 135	91.29 284	98.93 277	98.94 41	95.90 78	98.77 105	98.42 220	90.89 164	99.77 128	97.80 132	70.76 377	98.72 221

Anonymous20240529		92.10 258	90.65 269	96.47 205	98.82 136	90.61 298	98.72 298	98.67 73	75.54 385	93.90 223	98.58 204	66.23 363	99.90 91	94.70 198	90.67 252	98.90 211

PVSNet_Blended_VisFu		97.27 103	96.81 111	98.66 95	98.81 137	96.67 123	99.92 82	98.64 76	94.51 116	96.38 185	98.49 210	89.05 195	99.88 102	97.10 153	98.34 147	99.43 166

PS-MVSNAJ		98.44 41	98.20 46	99.16 57	98.80 138	98.92 29	99.54 204	98.17 191	97.34 29	99.85 9	99.85 32	91.20 153	99.89 96	99.41 48	99.67 89	98.69 222

CANet_DTU		96.76 129	96.15 134	98.60 100	98.78 139	97.53 91	99.84 128	97.63 241	97.25 37	99.20 85	99.64 101	81.36 264	99.98 43	92.77 237	98.89 134	98.28 231

mvsany_test1		97.82 75	97.90 67	97.55 167	98.77 140	93.04 241	99.80 144	97.93 216	96.95 45	99.61 56	99.68 95	90.92 161	99.83 118	99.18 56	98.29 152	99.80 96

alignmvs		97.81 76	97.33 90	99.25 46	98.77 140	98.66 51	99.99 6	98.44 123	94.40 124	98.41 123	99.47 116	93.65 97	99.42 164	98.57 96	94.26 233	99.67 115

SteuartSystems-ACMMP		99.02 12	98.97 13	99.18 52	98.72 142	97.71 84	99.98 16	98.44 123	96.85 46	99.80 17	99.91 14	97.57 6	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 73	98.69 143	98.66 51	99.52 206	98.08 203	97.05 41	99.86 7	99.86 28	90.65 167	99.71 138	99.39 50	98.63 142	98.69 222

miper_enhance_ethall		94.36 206	93.98 199	95.49 228	98.68 144	95.24 182	99.73 166	97.29 283	93.28 172	89.86 269	95.97 292	94.37 74	97.05 302	92.20 241	84.45 308	94.19 292

ETVMVS		97.03 116	96.64 118	98.20 128	98.67 145	97.12 109	99.89 102	98.57 89	91.10 251	98.17 135	98.59 201	93.86 92	98.19 246	95.64 179	95.24 221	99.28 185

test2506		97.53 89	97.19 96	98.58 103	98.66 146	96.90 117	98.81 291	99.77 5	94.93 101	97.95 140	98.96 165	92.51 130	99.20 171	94.93 188	98.15 154	99.64 121

ECVR-MVS		95.66 169	95.05 174	97.51 170	98.66 146	93.71 223	98.85 288	98.45 118	94.93 101	96.86 170	98.96 165	75.22 324	99.20 171	95.34 181	98.15 154	99.64 121

fmvsm_s_conf0.5_n_a		97.73 84	97.72 73	97.77 154	98.63 148	94.26 208	99.96 36	98.92 46	97.18 39	99.75 29	99.69 89	87.00 216	99.97 53	99.46 44	98.89 134	99.08 201

MVSMamba_pp		98.05 64	97.76 72	98.92 82	98.56 149	98.06 70	99.92 82	97.75 234	96.28 71	99.71 36	98.43 219	90.37 174	99.11 177	98.99 69	99.88 70	99.58 141

testing222		97.08 115	96.75 114	98.06 137	98.56 149	96.82 119	99.85 123	98.61 82	92.53 204	98.84 100	98.84 185	93.36 101	98.30 236	95.84 176	94.30 232	99.05 203

iter_conf05_11		98.22 59	97.93 64	99.09 67	98.56 149	98.52 58	100.00 1	97.77 232	96.34 70	99.73 32	99.87 24	90.18 179	99.13 176	99.03 66	99.90 66	99.63 126

test1111		95.57 171	94.98 177	97.37 178	98.56 149	93.37 235	98.86 286	98.45 118	94.95 100	96.63 176	98.95 170	75.21 325	99.11 177	95.02 186	98.14 156	99.64 121

MVSTER		95.53 172	95.22 168	96.45 207	98.56 149	97.72 83	99.91 88	97.67 239	92.38 211	91.39 249	97.14 252	97.24 16	97.30 285	94.80 194	87.85 283	94.34 283

bld_raw_dy_0_64		97.44 92	97.68 75	96.72 199	98.55 154	91.46 283	100.00 1	97.77 232	94.03 144	99.72 35	99.87 24	90.31 175	99.11 177	98.99 69	99.88 70	99.59 133

mamv4		97.88 69	97.52 82	98.95 79	98.55 154	98.15 65	99.93 77	97.74 235	94.01 145	99.65 43	98.44 218	90.50 171	99.11 177	99.00 68	99.89 67	99.59 133

VDD-MVS		93.77 219	92.94 227	96.27 213	98.55 154	90.22 307	98.77 295	97.79 230	90.85 257	96.82 172	99.42 120	61.18 380	99.77 128	98.95 71	94.13 234	98.82 214

tpmvs		94.28 208	93.57 211	96.40 209	98.55 154	91.50 281	95.70 376	98.55 98	87.47 314	92.15 242	94.26 351	91.42 149	98.95 186	88.15 297	95.85 206	98.76 217

UGNet		95.33 177	94.57 186	97.62 165	98.55 154	94.85 192	98.67 304	99.32 26	95.75 83	96.80 173	96.27 283	72.18 338	99.96 61	94.58 201	99.05 132	98.04 236
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	95.18 178	94.10 196	98.43 117	98.55 154	95.99 151	97.91 337	97.31 279	90.35 268	89.48 280	99.22 142	85.19 235	99.89 96	90.40 274	98.47 145	99.41 168
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		96.79 126	96.72 115	97.00 189	98.51 160	93.70 224	99.71 172	98.60 84	92.96 179	97.09 163	98.34 222	96.67 26	98.85 190	92.11 243	96.50 191	98.44 227

test_vis1_n_1920		95.44 174	95.31 165	95.82 223	98.50 161	88.74 325	99.98 16	97.30 280	97.84 16	99.85 9	99.19 144	66.82 361	99.97 53	98.82 81	99.46 110	98.76 217

BH-w/o		95.71 166	95.38 163	96.68 201	98.49 162	92.28 258	99.84 128	97.50 260	92.12 217	92.06 245	98.79 186	84.69 240	98.67 205	95.29 183	99.66 90	99.09 199

baseline1		95.78 163	94.86 179	98.54 108	98.47 163	98.07 69	99.06 261	97.99 209	92.68 194	94.13 220	98.62 200	93.28 107	98.69 203	93.79 219	85.76 296	98.84 213

EPMVS		96.53 140	96.01 137	98.09 135	98.43 164	96.12 149	96.36 363	99.43 21	93.53 163	97.64 150	95.04 329	94.41 69	98.38 228	91.13 255	98.11 157	99.75 103

sss		97.57 88	97.03 103	99.18 52	98.37 165	98.04 72	99.73 166	99.38 23	93.46 165	98.76 107	99.06 152	91.21 152	99.89 96	96.33 167	97.01 183	99.62 127

testing11		97.48 91	97.27 92	98.10 134	98.36 166	96.02 150	99.92 82	98.45 118	93.45 167	98.15 136	98.70 191	95.48 44	99.22 167	97.85 131	95.05 223	99.07 202

BH-untuned		95.18 178	94.83 180	96.22 214	98.36 166	91.22 285	99.80 144	97.32 278	90.91 255	91.08 253	98.67 193	83.51 248	98.54 211	94.23 208	99.61 97	98.92 208

testing91		97.16 108	96.90 107	97.97 140	98.35 168	95.67 165	99.91 88	98.42 143	92.91 182	97.33 158	98.72 189	94.81 61	99.21 168	96.98 157	94.63 226	99.03 204

testing99		97.17 107	96.91 106	97.95 141	98.35 168	95.70 162	99.91 88	98.43 131	92.94 180	97.36 157	98.72 189	94.83 60	99.21 168	97.00 155	94.64 225	98.95 207

ET-MVSNet_ETH3D		94.37 204	93.28 222	97.64 162	98.30 170	97.99 74	99.99 6	97.61 246	94.35 125	71.57 388	99.45 119	96.23 30	95.34 358	96.91 162	85.14 303	99.59 133

AUN-MVS		93.28 231	92.60 235	95.34 235	98.29 171	90.09 310	99.31 235	98.56 92	91.80 229	96.35 186	98.00 231	89.38 188	98.28 239	92.46 238	69.22 382	97.64 243

FMVSNet3		92.69 246	91.58 255	95.99 218	98.29 171	97.42 99	99.26 243	97.62 243	89.80 277	89.68 273	95.32 319	81.62 262	96.27 338	87.01 314	85.65 297	94.29 285

PMMVS		96.76 129	96.76 113	96.76 197	98.28 173	92.10 262	99.91 88	97.98 211	94.12 136	99.53 61	99.39 127	86.93 217	98.73 198	96.95 160	97.73 164	99.45 163

hse-mvs2		94.38 203	94.08 197	95.31 237	98.27 174	90.02 311	99.29 240	98.56 92	95.90 78	98.77 105	98.00 231	90.89 164	98.26 243	97.80 132	69.20 383	97.64 243

PVSNet_0	88.03 19	91.80 265	90.27 278	96.38 211	98.27 174	90.46 302	99.94 70	99.61 14	93.99 147	86.26 334	97.39 247	71.13 345	99.89 96	98.77 84	67.05 388	98.79 216

UA-Net		96.54 139	95.96 144	98.27 125	98.23 176	95.71 161	98.00 335	98.45 118	93.72 159	98.41 123	99.27 136	88.71 200	99.66 146	91.19 254	97.69 165	99.44 165

test_cas_vis1_n_1920		96.59 138	96.23 131	97.65 161	98.22 177	94.23 209	99.99 6	97.25 287	97.77 17	99.58 57	99.08 150	77.10 301	99.97 53	97.64 140	99.45 111	98.74 219

FE-MVS		95.70 168	95.01 176	97.79 151	98.21 178	94.57 198	95.03 377	98.69 68	88.90 293	97.50 154	96.19 285	92.60 127	99.49 160	89.99 279	97.94 163	99.31 180

GG-mvs-BLEND				98.54 108	98.21 178	98.01 73	93.87 382	98.52 104		97.92 141	97.92 235	99.02 2	97.94 262	98.17 112	99.58 100	99.67 115

mvs_anonymous		95.65 170	95.03 175	97.53 168	98.19 180	95.74 159	99.33 232	97.49 261	90.87 256	90.47 260	97.10 254	88.23 202	97.16 293	95.92 174	97.66 167	99.68 113

MVS_Test		96.46 142	95.74 153	98.61 99	98.18 181	97.23 103	99.31 235	97.15 296	91.07 252	98.84 100	97.05 258	88.17 203	98.97 184	94.39 203	97.50 169	99.61 130

BH-RMVSNet		95.18 178	94.31 192	97.80 149	98.17 182	95.23 183	99.76 155	97.53 256	92.52 205	94.27 218	99.25 140	76.84 306	98.80 192	90.89 263	99.54 102	99.35 175

RPSCF		91.80 265	92.79 231	88.83 353	98.15 183	69.87 391	98.11 331	96.60 342	83.93 354	94.33 216	99.27 136	79.60 284	99.46 163	91.99 244	93.16 246	97.18 250

ETV-MVS		97.92 68	97.80 71	98.25 126	98.14 184	96.48 128	99.98 16	97.63 241	95.61 86	99.29 83	99.46 118	92.55 129	98.82 191	99.02 67	98.54 143	99.46 161

IS-MVSNet		96.29 152	95.90 149	97.45 172	98.13 185	94.80 195	99.08 256	97.61 246	92.02 222	95.54 202	98.96 165	90.64 168	98.08 251	93.73 222	97.41 173	99.47 160

test_fmvsmconf_n		98.43 43	98.32 40	98.78 87	98.12 186	96.41 131	99.99 6	98.83 59	98.22 6	99.67 41	99.64 101	91.11 157	99.94 77	99.67 36	99.62 93	99.98 48

ab-mvs		94.69 191	93.42 216	98.51 111	98.07 187	96.26 138	96.49 361	98.68 70	90.31 269	94.54 211	97.00 260	76.30 313	99.71 138	95.98 173	93.38 244	99.56 144

XVG-OURS-SEG-HR		94.79 187	94.70 185	95.08 243	98.05 188	89.19 320	99.08 256	97.54 254	93.66 160	94.87 209	99.58 108	78.78 292	99.79 123	97.31 146	93.40 243	96.25 256

EIA-MVS		97.53 89	97.46 84	97.76 156	98.04 189	94.84 193	99.98 16	97.61 246	94.41 123	97.90 142	99.59 106	92.40 134	98.87 188	98.04 120	99.13 128	99.59 133

XVG-OURS		94.82 185	94.74 183	95.06 244	98.00 190	89.19 320	99.08 256	97.55 252	94.10 137	94.71 210	99.62 104	80.51 276	99.74 134	96.04 172	93.06 248	96.25 256

dp		95.05 181	94.43 188	96.91 192	97.99 191	92.73 248	96.29 366	97.98 211	89.70 278	95.93 194	94.67 342	93.83 94	98.45 217	86.91 317	96.53 190	99.54 149

tpmrst		96.27 154	95.98 140	97.13 186	97.96 192	93.15 237	96.34 364	98.17 191	92.07 218	98.71 111	95.12 327	93.91 89	98.73 198	94.91 191	96.62 188	99.50 157

TR-MVS		94.54 197	93.56 212	97.49 171	97.96 192	94.34 206	98.71 299	97.51 259	90.30 270	94.51 213	98.69 192	75.56 319	98.77 195	92.82 236	95.99 200	99.35 175

Vis-MVSNet (Re-imp)		96.32 149	95.98 140	97.35 181	97.93 194	94.82 194	99.47 215	98.15 198	91.83 226	95.09 207	99.11 148	91.37 151	97.47 277	93.47 225	97.43 170	99.74 104

MDTV_nov1_ep13			95.69 155		97.90 195	94.15 211	95.98 372	98.44 123	93.12 176	97.98 139	95.74 296	95.10 50	98.58 208	90.02 278	96.92 185

Fast-Effi-MVS+		95.02 182	94.19 194	97.52 169	97.88 196	94.55 199	99.97 29	97.08 304	88.85 295	94.47 214	97.96 234	84.59 241	98.41 220	89.84 281	97.10 178	99.59 133

ADS-MVSNet2		93.80 218	93.88 203	93.55 304	97.87 197	85.94 349	94.24 378	96.84 328	90.07 272	96.43 182	94.48 347	90.29 177	95.37 357	87.44 304	97.23 175	99.36 173

ADS-MVSNet		94.79 187	94.02 198	97.11 188	97.87 197	93.79 220	94.24 378	98.16 195	90.07 272	96.43 182	94.48 347	90.29 177	98.19 246	87.44 304	97.23 175	99.36 173

Effi-MVS+		96.30 151	95.69 155	98.16 129	97.85 199	96.26 138	97.41 344	97.21 289	90.37 267	98.65 114	98.58 204	86.61 221	98.70 202	97.11 152	97.37 174	99.52 153

PatchmatchNet		95.94 159	95.45 160	97.39 177	97.83 200	94.41 203	96.05 370	98.40 152	92.86 183	97.09 163	95.28 324	94.21 81	98.07 253	89.26 285	98.11 157	99.70 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 194	93.61 207	97.74 158	97.82 201	96.26 138	99.96 36	97.78 231	85.76 337	94.00 221	97.54 242	76.95 305	99.21 168	97.23 148	95.43 216	97.76 242

1112_ss		96.01 158	95.20 169	98.42 118	97.80 202	96.41 131	99.65 184	96.66 339	92.71 191	92.88 235	99.40 125	92.16 139	99.30 165	91.92 246	93.66 240	99.55 145

Test_1112_low_res		95.72 164	94.83 180	98.42 118	97.79 203	96.41 131	99.65 184	96.65 340	92.70 192	92.86 236	96.13 288	92.15 140	99.30 165	91.88 247	93.64 241	99.55 145

Effi-MVS+-dtu		94.53 199	95.30 166	92.22 326	97.77 204	82.54 366	99.59 194	97.06 306	94.92 103	95.29 205	95.37 317	85.81 228	97.89 263	94.80 194	97.07 179	96.23 258

tpm cat1		93.51 227	92.52 240	96.47 205	97.77 204	91.47 282	96.13 368	98.06 204	80.98 370	92.91 234	93.78 355	89.66 183	98.87 188	87.03 313	96.39 194	99.09 199

FA-MVS(test-final)		95.86 160	95.09 173	98.15 132	97.74 206	95.62 167	96.31 365	98.17 191	91.42 242	96.26 187	96.13 288	90.56 169	99.47 162	92.18 242	97.07 179	99.35 175

xiu_mvs_v1_base_debu		97.43 93	97.06 99	98.55 105	97.74 206	98.14 66	99.31 235	97.86 225	96.43 62	99.62 50	99.69 89	85.56 230	99.68 142	99.05 60	98.31 149	97.83 238

xiu_mvs_v1_base		97.43 93	97.06 99	98.55 105	97.74 206	98.14 66	99.31 235	97.86 225	96.43 62	99.62 50	99.69 89	85.56 230	99.68 142	99.05 60	98.31 149	97.83 238

xiu_mvs_v1_base_debi		97.43 93	97.06 99	98.55 105	97.74 206	98.14 66	99.31 235	97.86 225	96.43 62	99.62 50	99.69 89	85.56 230	99.68 142	99.05 60	98.31 149	97.83 238

EPP-MVSNet		96.69 134	96.60 120	96.96 191	97.74 206	93.05 240	99.37 228	98.56 92	88.75 296	95.83 197	99.01 156	96.01 31	98.56 209	96.92 161	97.20 177	99.25 188

gg-mvs-nofinetune		93.51 227	91.86 252	98.47 113	97.72 211	97.96 77	92.62 386	98.51 107	74.70 388	97.33 158	69.59 401	98.91 3	97.79 266	97.77 137	99.56 101	99.67 115

IB-MVS	92.85 6	94.99 183	93.94 201	98.16 129	97.72 211	95.69 164	99.99 6	98.81 60	94.28 131	92.70 237	96.90 262	95.08 51	99.17 174	96.07 171	73.88 372	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 98	97.02 104	98.59 102	97.71 213	97.52 92	99.97 29	98.54 101	91.83 226	97.45 155	99.04 153	97.50 7	99.10 181	94.75 196	96.37 195	99.16 193

Syy-MVS		90.00 304	90.63 270	88.11 360	97.68 214	74.66 388	99.71 172	98.35 165	90.79 259	92.10 243	98.67 193	79.10 290	93.09 380	63.35 394	95.95 203	96.59 254

myMVS_eth3d		94.46 201	94.76 182	93.55 304	97.68 214	90.97 288	99.71 172	98.35 165	90.79 259	92.10 243	98.67 193	92.46 133	93.09 380	87.13 310	95.95 203	96.59 254

test_fmvs1_n		94.25 209	94.36 189	93.92 291	97.68 214	83.70 361	99.90 94	96.57 343	97.40 28	99.67 41	98.88 176	61.82 377	99.92 88	98.23 110	99.13 128	98.14 235

diffmvs		97.00 117	96.64 118	98.09 135	97.64 217	96.17 146	99.81 140	97.19 290	94.67 113	98.95 95	99.28 133	86.43 222	98.76 196	98.37 105	97.42 172	99.33 178
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		95.72 164	95.15 171	97.45 172	97.62 218	94.28 207	99.28 241	98.24 183	94.27 133	96.84 171	98.94 172	79.39 285	98.76 196	93.25 227	98.49 144	99.30 182
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 110	96.72 115	98.22 127	97.60 219	96.70 122	99.92 82	98.54 101	91.11 250	97.07 165	98.97 163	97.47 10	99.03 182	93.73 222	96.09 198	98.92 208

miper_ehance_all_eth		93.16 234	92.60 235	94.82 253	97.57 220	93.56 228	99.50 210	97.07 305	88.75 296	88.85 295	95.52 307	90.97 160	96.74 319	90.77 265	84.45 308	94.17 293

testing3		93.92 213	94.23 193	92.99 318	97.54 221	90.23 306	99.99 6	99.16 30	90.57 263	91.33 252	98.63 199	92.99 114	92.52 384	82.46 343	95.39 217	96.22 259

LCM-MVSNet-Re		92.31 254	92.60 235	91.43 333	97.53 222	79.27 383	99.02 269	91.83 397	92.07 218	80.31 363	94.38 350	83.50 249	95.48 355	97.22 149	97.58 168	99.54 149

GBi-Net		90.88 281	89.82 287	94.08 283	97.53 222	91.97 263	98.43 315	96.95 317	87.05 320	89.68 273	94.72 338	71.34 342	96.11 343	87.01 314	85.65 297	94.17 293

test1		90.88 281	89.82 287	94.08 283	97.53 222	91.97 263	98.43 315	96.95 317	87.05 320	89.68 273	94.72 338	71.34 342	96.11 343	87.01 314	85.65 297	94.17 293

FMVSNet2		91.02 278	89.56 292	95.41 233	97.53 222	95.74 159	98.98 271	97.41 269	87.05 320	88.43 303	95.00 332	71.34 342	96.24 340	85.12 327	85.21 302	94.25 288

tttt0517		96.85 123	96.49 124	97.92 144	97.48 226	95.89 154	99.85 123	98.54 101	90.72 262	96.63 176	98.93 174	97.47 10	99.02 183	93.03 234	95.76 209	98.85 212

casdiffmvs_mvg		96.43 143	95.94 146	97.89 148	97.44 227	95.47 171	99.86 120	97.29 283	93.35 168	96.03 191	99.19 144	85.39 233	98.72 200	97.89 130	97.04 181	99.49 159
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		97.38 100	97.24 93	97.80 149	97.41 228	95.64 166	99.99 6	97.06 306	94.59 114	99.63 47	99.32 132	89.20 194	98.14 248	98.76 85	99.23 124	99.62 127

c3_l		92.53 249	91.87 251	94.52 265	97.40 229	92.99 242	99.40 221	96.93 322	87.86 310	88.69 298	95.44 311	89.95 181	96.44 331	90.45 271	80.69 339	94.14 302

fmvsm_s_conf0.1_n		97.30 101	97.21 95	97.60 166	97.38 230	94.40 205	99.90 94	98.64 76	96.47 61	99.51 65	99.65 100	84.99 238	99.93 85	99.22 55	99.09 130	98.46 226

CDS-MVSNet		96.34 148	96.07 135	97.13 186	97.37 231	94.96 190	99.53 205	97.91 220	91.55 234	95.37 204	98.32 223	95.05 53	97.13 296	93.80 218	95.75 210	99.30 182
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 131	96.26 130	98.16 129	97.36 232	96.48 128	99.96 36	98.29 178	91.93 223	95.77 198	98.07 229	95.54 41	98.29 237	90.55 269	98.89 134	99.70 110

miper_lstm_enhance		91.81 262	91.39 261	93.06 317	97.34 233	89.18 322	99.38 226	96.79 333	86.70 327	87.47 316	95.22 325	90.00 180	95.86 352	88.26 295	81.37 329	94.15 299

baseline		96.43 143	95.98 140	97.76 156	97.34 233	95.17 187	99.51 208	97.17 293	93.92 152	96.90 169	99.28 133	85.37 234	98.64 206	97.50 143	96.86 187	99.46 161

cl____		92.31 254	91.58 255	94.52 265	97.33 235	92.77 244	99.57 198	96.78 334	86.97 324	87.56 314	95.51 308	89.43 187	96.62 324	88.60 290	82.44 321	94.16 298

DIV-MVS_self_test		92.32 253	91.60 254	94.47 269	97.31 236	92.74 246	99.58 196	96.75 335	86.99 323	87.64 312	95.54 305	89.55 186	96.50 328	88.58 291	82.44 321	94.17 293

casdiffmvs		96.42 145	95.97 143	97.77 154	97.30 237	94.98 189	99.84 128	97.09 303	93.75 158	96.58 178	99.26 139	85.07 236	98.78 194	97.77 137	97.04 181	99.54 149
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		94.36 206	93.48 214	96.99 190	97.29 238	93.54 229	99.96 36	96.72 337	88.35 305	93.43 225	98.94 172	82.05 256	98.05 254	88.12 299	96.48 193	99.37 172

eth_miper_zixun_eth		92.41 252	91.93 249	93.84 295	97.28 239	90.68 296	98.83 289	96.97 316	88.57 301	89.19 290	95.73 298	89.24 193	96.69 322	89.97 280	81.55 327	94.15 299

MVSFormer		96.94 120	96.60 120	97.95 141	97.28 239	97.70 86	99.55 202	97.27 285	91.17 247	99.43 70	99.54 112	90.92 161	96.89 312	94.67 199	99.62 93	99.25 188

lupinMVS		97.85 72	97.60 79	98.62 98	97.28 239	97.70 86	99.99 6	97.55 252	95.50 91	99.43 70	99.67 96	90.92 161	98.71 201	98.40 102	99.62 93	99.45 163

SCA		94.69 191	93.81 205	97.33 182	97.10 242	94.44 200	98.86 286	98.32 172	93.30 171	96.17 190	95.59 303	76.48 311	97.95 260	91.06 257	97.43 170	99.59 133

TAMVS		95.85 161	95.58 158	96.65 203	97.07 243	93.50 230	99.17 250	97.82 229	91.39 244	95.02 208	98.01 230	92.20 138	97.30 285	93.75 221	95.83 207	99.14 196

Fast-Effi-MVS+-dtu		93.72 222	93.86 204	93.29 309	97.06 244	86.16 347	99.80 144	96.83 329	92.66 195	92.58 238	97.83 238	81.39 263	97.67 271	89.75 282	96.87 186	96.05 261

CostFormer		96.10 155	95.88 150	96.78 196	97.03 245	92.55 254	97.08 352	97.83 228	90.04 274	98.72 110	94.89 336	95.01 55	98.29 237	96.54 166	95.77 208	99.50 157

test_fmvsmvis_n_1920		97.67 86	97.59 81	97.91 146	97.02 246	95.34 177	99.95 54	98.45 118	97.87 15	97.02 166	99.59 106	89.64 184	99.98 43	99.41 48	99.34 119	98.42 228

test-LLR		96.47 141	96.04 136	97.78 152	97.02 246	95.44 172	99.96 36	98.21 186	94.07 139	95.55 200	96.38 279	93.90 90	98.27 241	90.42 272	98.83 138	99.64 121

test-mter		96.39 146	95.93 147	97.78 152	97.02 246	95.44 172	99.96 36	98.21 186	91.81 228	95.55 200	96.38 279	95.17 48	98.27 241	90.42 272	98.83 138	99.64 121

gm-plane-assit					96.97 249	93.76 222			91.47 238		98.96 165		98.79 193	94.92 189

WB-MVSnew		92.90 240	92.77 232	93.26 311	96.95 250	93.63 226	99.71 172	98.16 195	91.49 235	94.28 217	98.14 226	81.33 265	96.48 329	79.47 358	95.46 214	89.68 381

QAPM		95.40 175	94.17 195	99.10 66	96.92 251	97.71 84	99.40 221	98.68 70	89.31 281	88.94 294	98.89 175	82.48 254	99.96 61	93.12 233	99.83 76	99.62 127

KD-MVS_2432*1600		88.00 323	86.10 327	93.70 300	96.91 252	94.04 214	97.17 349	97.12 299	84.93 347	81.96 354	92.41 366	92.48 131	94.51 368	79.23 359	52.68 400	92.56 355

miper_refine_blended		88.00 323	86.10 327	93.70 300	96.91 252	94.04 214	97.17 349	97.12 299	84.93 347	81.96 354	92.41 366	92.48 131	94.51 368	79.23 359	52.68 400	92.56 355

tpm2		95.47 173	95.18 170	96.35 212	96.91 252	91.70 276	96.96 355	97.93 216	88.04 309	98.44 122	95.40 313	93.32 104	97.97 257	94.00 210	95.61 212	99.38 170

FMVSNet5		88.32 320	87.47 322	90.88 336	96.90 255	88.39 333	97.28 346	95.68 364	82.60 364	84.67 343	92.40 368	79.83 282	91.16 389	76.39 373	81.51 328	93.09 347

3Dnovator+	91.53 11	96.31 150	95.24 167	99.52 28	96.88 256	98.64 54	99.72 169	98.24 183	95.27 96	88.42 305	98.98 161	82.76 253	99.94 77	97.10 153	99.83 76	99.96 64

Patchmatch-test		92.65 248	91.50 258	96.10 217	96.85 257	90.49 301	91.50 391	97.19 290	82.76 363	90.23 261	95.59 303	95.02 54	98.00 256	77.41 368	96.98 184	99.82 92

MVS		96.60 137	95.56 159	99.72 13	96.85 257	99.22 20	98.31 321	98.94 41	91.57 233	90.90 256	99.61 105	86.66 220	99.96 61	97.36 145	99.88 70	99.99 23

3Dnovator	91.47 12	96.28 153	95.34 164	99.08 68	96.82 259	97.47 97	99.45 218	98.81 60	95.52 90	89.39 281	99.00 158	81.97 257	99.95 69	97.27 147	99.83 76	99.84 90

EI-MVSNet		93.73 221	93.40 219	94.74 254	96.80 260	92.69 249	99.06 261	97.67 239	88.96 290	91.39 249	99.02 154	88.75 199	97.30 285	91.07 256	87.85 283	94.22 289

CVMVSNet		94.68 193	94.94 178	93.89 294	96.80 260	86.92 345	99.06 261	98.98 38	94.45 117	94.23 219	99.02 154	85.60 229	95.31 359	90.91 262	95.39 217	99.43 166

IterMVS-LS		92.69 246	92.11 245	94.43 273	96.80 260	92.74 246	99.45 218	96.89 325	88.98 288	89.65 276	95.38 316	88.77 198	96.34 335	90.98 260	82.04 324	94.22 289
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS		90.91 280	90.17 282	93.12 314	96.78 263	90.42 304	98.89 280	97.05 308	89.03 285	86.49 329	95.42 312	76.59 309	95.02 361	87.22 309	84.09 311	93.93 319
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 124	95.96 144	99.48 34	96.74 264	98.52 58	98.31 321	98.86 53	95.82 80	89.91 267	98.98 161	87.49 208	99.96 61	97.80 132	99.73 86	99.96 64

IterMVS-SCA-FT		90.85 283	90.16 283	92.93 319	96.72 265	89.96 312	98.89 280	96.99 312	88.95 291	86.63 326	95.67 299	76.48 311	95.00 362	87.04 312	84.04 314	93.84 326

MVS-HIRNet		86.22 330	83.19 343	95.31 237	96.71 266	90.29 305	92.12 388	97.33 277	62.85 395	86.82 323	70.37 400	69.37 350	97.49 276	75.12 375	97.99 162	98.15 233

VDDNet		93.12 235	91.91 250	96.76 197	96.67 267	92.65 252	98.69 302	98.21 186	82.81 362	97.75 149	99.28 133	61.57 378	99.48 161	98.09 118	94.09 235	98.15 233

dmvs_re		93.20 233	93.15 224	93.34 307	96.54 268	83.81 360	98.71 299	98.51 107	91.39 244	92.37 241	98.56 206	78.66 294	97.83 265	93.89 212	89.74 253	98.38 229

MIMVSNet		90.30 296	88.67 310	95.17 242	96.45 269	91.64 278	92.39 387	97.15 296	85.99 334	90.50 259	93.19 362	66.95 360	94.86 365	82.01 347	93.43 242	99.01 206

CR-MVSNet		93.45 230	92.62 234	95.94 219	96.29 270	92.66 250	92.01 389	96.23 353	92.62 197	96.94 167	93.31 360	91.04 158	96.03 348	79.23 359	95.96 201	99.13 197

RPMNet		89.76 308	87.28 323	97.19 185	96.29 270	92.66 250	92.01 389	98.31 174	70.19 394	96.94 167	85.87 393	87.25 212	99.78 125	62.69 395	95.96 201	99.13 197

tt0805		91.28 273	90.18 281	94.60 260	96.26 272	87.55 339	98.39 319	98.72 65	89.00 287	89.22 287	98.47 214	62.98 374	98.96 185	90.57 268	88.00 282	97.28 249

Patchmtry		89.70 309	88.49 312	93.33 308	96.24 273	89.94 315	91.37 392	96.23 353	78.22 378	87.69 311	93.31 360	91.04 158	96.03 348	80.18 357	82.10 323	94.02 309

test_vis1_rt		86.87 328	86.05 330	89.34 349	96.12 274	78.07 384	99.87 108	83.54 408	92.03 221	78.21 373	89.51 379	45.80 394	99.91 89	96.25 169	93.11 247	90.03 378

JIA-IIPM		91.76 268	90.70 268	94.94 248	96.11 275	87.51 340	93.16 385	98.13 200	75.79 384	97.58 151	77.68 398	92.84 119	97.97 257	88.47 294	96.54 189	99.33 178

OpenMVS	90.15 15	94.77 189	93.59 210	98.33 122	96.07 276	97.48 96	99.56 200	98.57 89	90.46 265	86.51 328	98.95 170	78.57 295	99.94 77	93.86 213	99.74 85	97.57 247

PAPM		98.60 30	98.42 31	99.14 61	96.05 277	98.96 26	99.90 94	99.35 25	96.68 55	98.35 127	99.66 98	96.45 28	98.51 212	99.45 45	99.89 67	99.96 64

CLD-MVS		94.06 212	93.90 202	94.55 264	96.02 278	90.69 295	99.98 16	97.72 236	96.62 58	91.05 255	98.85 184	77.21 300	98.47 213	98.11 116	89.51 259	94.48 269
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 293	88.75 309	95.25 239	95.99 279	90.16 308	91.22 393	97.54 254	76.80 380	97.26 160	86.01 392	91.88 145	96.07 347	66.16 391	95.91 205	99.51 155

ACMH+	89.98 16	90.35 294	89.54 293	92.78 322	95.99 279	86.12 348	98.81 291	97.18 292	89.38 280	83.14 350	97.76 240	68.42 355	98.43 218	89.11 286	86.05 295	93.78 329

DeepMVS_CX				82.92 370	95.98 281	58.66 401		96.01 358	92.72 190	78.34 372	95.51 308	58.29 383	98.08 251	82.57 342	85.29 300	92.03 363

ACMP	92.05 9	92.74 244	92.42 242	93.73 296	95.91 282	88.72 326	99.81 140	97.53 256	94.13 135	87.00 322	98.23 224	74.07 332	98.47 213	96.22 170	88.86 266	93.99 314
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 225	93.03 226	95.35 234	95.86 283	86.94 344	99.87 108	96.36 350	96.85 46	99.54 60	98.79 186	52.41 390	99.83 118	98.64 93	98.97 133	99.29 184

HQP-NCC					95.78 284		99.87 108		96.82 48	93.37 226

ACMP_Plane					95.78 284		99.87 108		96.82 48	93.37 226

HQP-MVS		94.61 195	94.50 187	94.92 249	95.78 284	91.85 268	99.87 108	97.89 221	96.82 48	93.37 226	98.65 196	80.65 274	98.39 224	97.92 127	89.60 254	94.53 264

NP-MVS					95.77 287	91.79 270					98.65 196

test_fmvsmconf0.1_n		97.74 82	97.44 85	98.64 97	95.76 288	96.20 143	99.94 70	98.05 206	98.17 8	98.89 99	99.42 120	87.65 206	99.90 91	99.50 41	99.60 99	99.82 92

plane_prior6					95.76 288	91.72 275						80.47 278

ACMM	91.95 10	92.88 241	92.52 240	93.98 290	95.75 290	89.08 323	99.77 150	97.52 258	93.00 178	89.95 266	97.99 233	76.17 315	98.46 216	93.63 224	88.87 265	94.39 278
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 215	92.84 228	96.80 195	95.73 291	93.57 227	99.88 105	97.24 288	92.57 202	92.92 232	96.66 271	78.73 293	97.67 271	87.75 302	94.06 236	99.17 192

plane_prior1					95.73 291

jason		97.24 104	96.86 109	98.38 121	95.73 291	97.32 101	99.97 29	97.40 270	95.34 94	98.60 117	99.54 112	87.70 205	98.56 209	97.94 126	99.47 108	99.25 188
jason: jason.
HQP_MVS		94.49 200	94.36 189	94.87 250	95.71 294	91.74 272	99.84 128	97.87 223	96.38 65	93.01 230	98.59 201	80.47 278	98.37 230	97.79 135	89.55 257	94.52 266

plane_prior7					95.71 294	91.59 280

ITE_SJBPF				92.38 324	95.69 296	85.14 353		95.71 363	92.81 186	89.33 284	98.11 227	70.23 348	98.42 219	85.91 323	88.16 279	93.59 337

fmvsm_s_conf0.1_n_a		97.09 112	96.90 107	97.63 164	95.65 297	94.21 210	99.83 135	98.50 112	96.27 72	99.65 43	99.64 101	84.72 239	99.93 85	99.04 63	98.84 137	98.74 219

ACMH	89.72 17	90.64 287	89.63 290	93.66 302	95.64 298	88.64 329	98.55 308	97.45 263	89.03 285	81.62 357	97.61 241	69.75 349	98.41 220	89.37 283	87.62 287	93.92 320
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 133	96.49 124	97.37 178	95.63 299	95.96 152	99.74 161	98.88 51	92.94 180	91.61 247	98.97 163	97.72 5	98.62 207	94.83 193	98.08 160	97.53 248

FMVSNet1		88.50 319	86.64 325	94.08 283	95.62 300	91.97 263	98.43 315	96.95 317	83.00 360	86.08 336	94.72 338	59.09 382	96.11 343	81.82 349	84.07 312	94.17 293

LPG-MVS_test		92.96 238	92.71 233	93.71 298	95.43 301	88.67 327	99.75 158	97.62 243	92.81 186	90.05 262	98.49 210	75.24 322	98.40 222	95.84 176	89.12 261	94.07 306

LGP-MVS_train				93.71 298	95.43 301	88.67 327		97.62 243	92.81 186	90.05 262	98.49 210	75.24 322	98.40 222	95.84 176	89.12 261	94.07 306

tpm		93.70 223	93.41 218	94.58 262	95.36 303	87.41 341	97.01 353	96.90 324	90.85 257	96.72 175	94.14 352	90.40 173	96.84 315	90.75 266	88.54 274	99.51 155

D2MVS		92.76 243	92.59 238	93.27 310	95.13 304	89.54 319	99.69 177	99.38 23	92.26 214	87.59 313	94.61 344	85.05 237	97.79 266	91.59 250	88.01 281	92.47 358

VPA-MVSNet		92.70 245	91.55 257	96.16 215	95.09 305	96.20 143	98.88 282	99.00 36	91.02 254	91.82 246	95.29 323	76.05 317	97.96 259	95.62 180	81.19 330	94.30 284

LTVRE_ROB	88.28 18	90.29 297	89.05 304	94.02 286	95.08 306	90.15 309	97.19 348	97.43 265	84.91 349	83.99 346	97.06 257	74.00 333	98.28 239	84.08 332	87.71 285	93.62 336
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		87.87 325	86.51 326	91.94 329	95.05 307	85.57 351	97.65 341	94.08 385	84.40 352	81.82 356	96.85 266	62.14 376	98.33 233	80.25 356	86.37 294	91.91 365

test0.0.03 1		93.86 214	93.61 207	94.64 258	95.02 308	92.18 261	99.93 77	98.58 87	94.07 139	87.96 309	98.50 209	93.90 90	94.96 363	81.33 350	93.17 245	96.78 251

UniMVSNet (Re)		93.07 237	92.13 244	95.88 220	94.84 309	96.24 142	99.88 105	98.98 38	92.49 207	89.25 285	95.40 313	87.09 214	97.14 295	93.13 232	78.16 353	94.26 286

USDC		90.00 304	88.96 305	93.10 316	94.81 310	88.16 335	98.71 299	95.54 368	93.66 160	83.75 348	97.20 251	65.58 365	98.31 235	83.96 335	87.49 289	92.85 352

VPNet		91.81 262	90.46 272	95.85 222	94.74 311	95.54 170	98.98 271	98.59 86	92.14 216	90.77 258	97.44 244	68.73 353	97.54 275	94.89 192	77.89 355	94.46 270

FIs		94.10 210	93.43 215	96.11 216	94.70 312	96.82 119	99.58 196	98.93 45	92.54 203	89.34 283	97.31 248	87.62 207	97.10 299	94.22 209	86.58 292	94.40 276

UniMVSNet_ETH3D		90.06 303	88.58 311	94.49 268	94.67 313	88.09 336	97.81 340	97.57 251	83.91 355	88.44 301	97.41 245	57.44 384	97.62 273	91.41 251	88.59 273	97.77 241

UniMVSNet_NR-MVSNet		92.95 239	92.11 245	95.49 228	94.61 314	95.28 180	99.83 135	99.08 33	91.49 235	89.21 288	96.86 265	87.14 213	96.73 320	93.20 228	77.52 358	94.46 270

test_fmvs2		89.47 312	89.70 289	88.77 356	94.54 315	75.74 385	99.83 135	94.70 381	94.71 110	91.08 253	96.82 270	54.46 387	97.78 268	92.87 235	88.27 277	92.80 353

WR-MVS		92.31 254	91.25 262	95.48 231	94.45 316	95.29 179	99.60 193	98.68 70	90.10 271	88.07 308	96.89 263	80.68 273	96.80 318	93.14 231	79.67 346	94.36 279

nrg030		93.51 227	92.53 239	96.45 207	94.36 317	97.20 104	99.81 140	97.16 295	91.60 232	89.86 269	97.46 243	86.37 223	97.68 270	95.88 175	80.31 342	94.46 270

tfpnnormal		89.29 315	87.61 321	94.34 276	94.35 318	94.13 212	98.95 275	98.94 41	83.94 353	84.47 344	95.51 308	74.84 327	97.39 278	77.05 371	80.41 340	91.48 368

iter_conf05		94.61 195	94.72 184	94.27 277	94.31 319	91.01 287	99.93 77	96.30 352	94.01 145	92.92 232	98.46 217	90.66 166	97.32 283	97.12 151	88.75 268	94.49 268

FC-MVSNet-test		93.81 217	93.15 224	95.80 224	94.30 320	96.20 143	99.42 220	98.89 49	92.33 213	89.03 293	97.27 250	87.39 210	96.83 316	93.20 228	86.48 293	94.36 279

MS-PatchMatch		90.65 286	90.30 277	91.71 332	94.22 321	85.50 352	98.24 324	97.70 237	88.67 298	86.42 331	96.37 281	67.82 357	98.03 255	83.62 337	99.62 93	91.60 366

WR-MVS_H		91.30 271	90.35 275	94.15 280	94.17 322	92.62 253	99.17 250	98.94 41	88.87 294	86.48 330	94.46 349	84.36 243	96.61 325	88.19 296	78.51 351	93.21 346

DU-MVS		92.46 251	91.45 260	95.49 228	94.05 323	95.28 180	99.81 140	98.74 64	92.25 215	89.21 288	96.64 273	81.66 260	96.73 320	93.20 228	77.52 358	94.46 270

NR-MVSNet		91.56 270	90.22 279	95.60 226	94.05 323	95.76 158	98.25 323	98.70 67	91.16 249	80.78 362	96.64 273	83.23 252	96.57 326	91.41 251	77.73 357	94.46 270

CP-MVSNet		91.23 275	90.22 279	94.26 278	93.96 325	92.39 257	99.09 254	98.57 89	88.95 291	86.42 331	96.57 276	79.19 288	96.37 333	90.29 275	78.95 348	94.02 309

XXY-MVS		91.82 261	90.46 272	95.88 220	93.91 326	95.40 176	98.87 285	97.69 238	88.63 300	87.87 310	97.08 255	74.38 331	97.89 263	91.66 249	84.07 312	94.35 282

PS-CasMVS		90.63 288	89.51 295	93.99 289	93.83 327	91.70 276	98.98 271	98.52 104	88.48 302	86.15 335	96.53 278	75.46 320	96.31 337	88.83 288	78.86 350	93.95 317

test_0402		85.58 332	83.94 337	90.50 340	93.81 328	85.04 354	98.55 308	95.20 375	76.01 382	79.72 367	95.13 326	64.15 371	96.26 339	66.04 392	86.88 291	90.21 377

XVG-ACMP-BASELINE		91.22 276	90.75 267	92.63 323	93.73 329	85.61 350	98.52 312	97.44 264	92.77 189	89.90 268	96.85 266	66.64 362	98.39 224	92.29 240	88.61 271	93.89 322

TranMVSNet+NR-MVSNet		91.68 269	90.61 271	94.87 250	93.69 330	93.98 217	99.69 177	98.65 74	91.03 253	88.44 301	96.83 269	80.05 281	96.18 341	90.26 276	76.89 366	94.45 275

mvsmamba		94.10 210	93.72 206	95.25 239	93.57 331	94.13 212	99.67 181	96.45 348	93.63 162	91.34 251	97.77 239	86.29 225	97.22 291	96.65 165	88.10 280	94.40 276

TransMVSNet (Re)		87.25 326	85.28 333	93.16 313	93.56 332	91.03 286	98.54 310	94.05 387	83.69 357	81.09 360	96.16 286	75.32 321	96.40 332	76.69 372	68.41 384	92.06 362

v10		90.25 298	88.82 307	94.57 263	93.53 333	93.43 232	99.08 256	96.87 327	85.00 346	87.34 320	94.51 345	80.93 270	97.02 308	82.85 341	79.23 347	93.26 344

testgi		89.01 317	88.04 318	91.90 330	93.49 334	84.89 356	99.73 166	95.66 365	93.89 155	85.14 341	98.17 225	59.68 381	94.66 367	77.73 367	88.88 264	96.16 260

v8		90.54 290	89.17 300	94.66 257	93.43 335	93.40 234	99.20 247	96.94 321	85.76 337	87.56 314	94.51 345	81.96 258	97.19 292	84.94 329	78.25 352	93.38 342

V42		91.28 273	90.12 284	94.74 254	93.42 336	93.46 231	99.68 179	97.02 309	87.36 316	89.85 271	95.05 328	81.31 266	97.34 281	87.34 307	80.07 344	93.40 340

pm-mvs1		89.36 314	87.81 320	94.01 287	93.40 337	91.93 266	98.62 307	96.48 347	86.25 332	83.86 347	96.14 287	73.68 334	97.04 304	86.16 320	75.73 370	93.04 349

v1144		91.09 277	89.83 286	94.87 250	93.25 338	93.69 225	99.62 191	96.98 314	86.83 326	89.64 277	94.99 333	80.94 269	97.05 302	85.08 328	81.16 331	93.87 324

v1192		90.62 289	89.25 299	94.72 256	93.13 339	93.07 238	99.50 210	97.02 309	86.33 331	89.56 279	95.01 330	79.22 287	97.09 301	82.34 345	81.16 331	94.01 311

v2v482		91.30 271	90.07 285	95.01 245	93.13 339	93.79 220	99.77 150	97.02 309	88.05 308	89.25 285	95.37 317	80.73 272	97.15 294	87.28 308	80.04 345	94.09 305

OPM-MVS		93.21 232	92.80 230	94.44 271	93.12 341	90.85 294	99.77 150	97.61 246	96.19 75	91.56 248	98.65 196	75.16 326	98.47 213	93.78 220	89.39 260	93.99 314
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 284	89.52 294	94.59 261	93.11 342	92.77 244	99.56 200	96.99 312	86.38 330	89.82 272	94.95 335	80.50 277	97.10 299	83.98 334	80.41 340	93.90 321

PEN-MVS		90.19 300	89.06 303	93.57 303	93.06 343	90.90 292	99.06 261	98.47 115	88.11 307	85.91 337	96.30 282	76.67 307	95.94 351	87.07 311	76.91 365	93.89 322

v1240		90.20 299	88.79 308	94.44 271	93.05 344	92.27 259	99.38 226	96.92 323	85.89 335	89.36 282	94.87 337	77.89 299	97.03 306	80.66 353	81.08 334	94.01 311

v148		90.70 285	89.63 290	93.92 291	92.97 345	90.97 288	99.75 158	96.89 325	87.51 313	88.27 306	95.01 330	81.67 259	97.04 304	87.40 306	77.17 363	93.75 330

v1921920		90.46 291	89.12 301	94.50 267	92.96 346	92.46 255	99.49 212	96.98 314	86.10 333	89.61 278	95.30 320	78.55 296	97.03 306	82.17 346	80.89 338	94.01 311

Baseline_NR-MVSNet		90.33 295	89.51 295	92.81 321	92.84 347	89.95 313	99.77 150	93.94 388	84.69 351	89.04 292	95.66 300	81.66 260	96.52 327	90.99 259	76.98 364	91.97 364

test_method		80.79 352	79.70 356	84.08 367	92.83 348	67.06 393	99.51 208	95.42 369	54.34 399	81.07 361	93.53 357	44.48 395	92.22 386	78.90 363	77.23 362	92.94 350

pmmvs4		92.10 258	91.07 265	95.18 241	92.82 349	94.96 190	99.48 214	96.83 329	87.45 315	88.66 299	96.56 277	83.78 247	96.83 316	89.29 284	84.77 306	93.75 330

LF4IMVS		89.25 316	88.85 306	90.45 342	92.81 350	81.19 376	98.12 330	94.79 378	91.44 239	86.29 333	97.11 253	65.30 368	98.11 250	88.53 293	85.25 301	92.07 361

DTE-MVSNet		89.40 313	88.24 316	92.88 320	92.66 351	89.95 313	99.10 253	98.22 185	87.29 317	85.12 342	96.22 284	76.27 314	95.30 360	83.56 338	75.74 369	93.41 339

EU-MVSNet		90.14 302	90.34 276	89.54 348	92.55 352	81.06 377	98.69 302	98.04 207	91.41 243	86.59 327	96.84 268	80.83 271	93.31 379	86.20 319	81.91 325	94.26 286

APD_test1		81.15 351	80.92 352	81.86 371	92.45 353	59.76 400	96.04 371	93.61 391	73.29 391	77.06 376	96.64 273	44.28 396	96.16 342	72.35 379	82.52 319	89.67 382

our_test_3		90.39 292	89.48 297	93.12 314	92.40 354	89.57 318	99.33 232	96.35 351	87.84 311	85.30 340	94.99 333	84.14 245	96.09 346	80.38 354	84.56 307	93.71 335

ppachtmachnet_test		89.58 311	88.35 314	93.25 312	92.40 354	90.44 303	99.33 232	96.73 336	85.49 342	85.90 338	95.77 295	81.09 268	96.00 350	76.00 374	82.49 320	93.30 343

v7n		89.65 310	88.29 315	93.72 297	92.22 356	90.56 300	99.07 260	97.10 301	85.42 344	86.73 324	94.72 338	80.06 280	97.13 296	81.14 351	78.12 354	93.49 338

dmvs_testset		83.79 345	86.07 329	76.94 375	92.14 357	48.60 410	96.75 358	90.27 400	89.48 279	78.65 370	98.55 208	79.25 286	86.65 398	66.85 389	82.69 318	95.57 262

PS-MVSNAJss		93.64 224	93.31 221	94.61 259	92.11 358	92.19 260	99.12 252	97.38 271	92.51 206	88.45 300	96.99 261	91.20 153	97.29 288	94.36 204	87.71 285	94.36 279

pmmvs5		90.17 301	89.09 302	93.40 306	92.10 359	89.77 316	99.74 161	95.58 367	85.88 336	87.24 321	95.74 296	73.41 335	96.48 329	88.54 292	83.56 315	93.95 317

N_pmnet		80.06 355	80.78 353	77.89 374	91.94 360	45.28 412	98.80 293	56.82 414	78.10 379	80.08 365	93.33 358	77.03 302	95.76 353	68.14 387	82.81 317	92.64 354

test_djsdf		92.83 242	92.29 243	94.47 269	91.90 361	92.46 255	99.55 202	97.27 285	91.17 247	89.96 265	96.07 291	81.10 267	96.89 312	94.67 199	88.91 263	94.05 308

SixPastTwentyTwo		88.73 318	88.01 319	90.88 336	91.85 362	82.24 368	98.22 327	95.18 376	88.97 289	82.26 353	96.89 263	71.75 340	96.67 323	84.00 333	82.98 316	93.72 334

K. test v3		88.05 322	87.24 324	90.47 341	91.82 363	82.23 369	98.96 274	97.42 267	89.05 284	76.93 378	95.60 302	68.49 354	95.42 356	85.87 324	81.01 336	93.75 330

OurMVSNet-221017-0		89.81 307	89.48 297	90.83 338	91.64 364	81.21 375	98.17 329	95.38 371	91.48 237	85.65 339	97.31 248	72.66 336	97.29 288	88.15 297	84.83 305	93.97 316

mvs_tets		91.81 262	91.08 264	94.00 288	91.63 365	90.58 299	98.67 304	97.43 265	92.43 208	87.37 319	97.05 258	71.76 339	97.32 283	94.75 196	88.68 270	94.11 304

Gipuma		66.95 368	65.00 368	72.79 380	91.52 366	67.96 392	66.16 403	95.15 377	47.89 401	58.54 398	67.99 403	29.74 400	87.54 397	50.20 402	77.83 356	62.87 403
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 146	95.74 153	98.32 123	91.47 367	95.56 169	99.84 128	97.30 280	97.74 18	97.89 143	99.35 131	79.62 283	99.85 108	99.25 54	99.24 123	99.55 145

jajsoiax		91.92 260	91.18 263	94.15 280	91.35 368	90.95 291	99.00 270	97.42 267	92.61 198	87.38 318	97.08 255	72.46 337	97.36 279	94.53 202	88.77 267	94.13 303

MDA-MVSNet-bldmvs		84.09 343	81.52 350	91.81 331	91.32 369	88.00 338	98.67 304	95.92 360	80.22 373	55.60 401	93.32 359	68.29 356	93.60 377	73.76 376	76.61 367	93.82 328

MVP-Stereo		90.93 279	90.45 274	92.37 325	91.25 370	88.76 324	98.05 334	96.17 355	87.27 318	84.04 345	95.30 320	78.46 297	97.27 290	83.78 336	99.70 88	91.09 369
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 334	83.32 342	92.10 327	90.96 371	88.58 330	99.20 247	96.52 345	79.70 375	57.12 400	92.69 364	79.11 289	93.86 374	77.10 370	77.46 360	93.86 325

YYNet1		85.50 335	83.33 341	92.00 328	90.89 372	88.38 334	99.22 246	96.55 344	79.60 376	57.26 399	92.72 363	79.09 291	93.78 375	77.25 369	77.37 361	93.84 326

anonymousdsp		91.79 267	90.92 266	94.41 274	90.76 373	92.93 243	98.93 277	97.17 293	89.08 283	87.46 317	95.30 320	78.43 298	96.92 311	92.38 239	88.73 269	93.39 341

lessismore_v0				90.53 339	90.58 374	80.90 378		95.80 361		77.01 377	95.84 293	66.15 364	96.95 309	83.03 340	75.05 371	93.74 333

EG-PatchMatch MVS		85.35 336	83.81 339	89.99 346	90.39 375	81.89 371	98.21 328	96.09 357	81.78 367	74.73 384	93.72 356	51.56 392	97.12 298	79.16 362	88.61 271	90.96 371

EGC-MVSNET		69.38 361	63.76 371	86.26 364	90.32 376	81.66 374	96.24 367	93.85 389	0.99 411	3.22 412	92.33 369	52.44 389	92.92 382	59.53 398	84.90 304	84.21 392

CMPMVS	61.59 21	84.75 339	85.14 334	83.57 368	90.32 376	62.54 396	96.98 354	97.59 250	74.33 389	69.95 390	96.66 271	64.17 370	98.32 234	87.88 301	88.41 276	89.84 380
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 342	82.92 345	89.21 350	90.03 378	82.60 365	96.89 357	95.62 366	80.59 371	75.77 383	89.17 380	65.04 369	94.79 366	72.12 380	81.02 335	90.23 376

pmmvs6		85.69 331	83.84 338	91.26 335	90.00 379	84.41 358	97.82 339	96.15 356	75.86 383	81.29 359	95.39 315	61.21 379	96.87 314	83.52 339	73.29 373	92.50 357

DSMNet-mixed		88.28 321	88.24 316	88.42 358	89.64 380	75.38 387	98.06 333	89.86 401	85.59 341	88.20 307	92.14 370	76.15 316	91.95 387	78.46 364	96.05 199	97.92 237

UnsupCasMVSNet_eth		85.52 333	83.99 335	90.10 344	89.36 381	83.51 362	96.65 359	97.99 209	89.14 282	75.89 382	93.83 354	63.25 373	93.92 372	81.92 348	67.90 387	92.88 351

Anonymous20231206		86.32 329	85.42 332	89.02 352	89.11 382	80.53 381	99.05 265	95.28 372	85.43 343	82.82 351	93.92 353	74.40 330	93.44 378	66.99 388	81.83 326	93.08 348

Anonymous20240521		85.15 337	83.81 339	89.16 351	88.32 383	82.69 364	98.80 293	95.74 362	79.72 374	81.53 358	90.99 373	65.38 367	94.16 370	72.69 378	81.11 333	90.63 374

OpenMVS_ROB	79.82 20	83.77 346	81.68 349	90.03 345	88.30 384	82.82 363	98.46 313	95.22 374	73.92 390	76.00 381	91.29 372	55.00 386	96.94 310	68.40 386	88.51 275	90.34 375

test20.03		84.72 340	83.99 335	86.91 362	88.19 385	80.62 380	98.88 282	95.94 359	88.36 304	78.87 368	94.62 343	68.75 352	89.11 393	66.52 390	75.82 368	91.00 370

KD-MVS_self_test		83.59 347	82.06 347	88.20 359	86.93 386	80.70 379	97.21 347	96.38 349	82.87 361	82.49 352	88.97 381	67.63 358	92.32 385	73.75 377	62.30 396	91.58 367

MIMVSNet1		82.58 348	80.51 354	88.78 354	86.68 387	84.20 359	96.65 359	95.41 370	78.75 377	78.59 371	92.44 365	51.88 391	89.76 392	65.26 393	78.95 348	92.38 360

CL-MVSNet_self_test		84.50 341	83.15 344	88.53 357	86.00 388	81.79 372	98.82 290	97.35 273	85.12 345	83.62 349	90.91 375	76.66 308	91.40 388	69.53 384	60.36 397	92.40 359

UnsupCasMVSNet_bld		79.97 357	77.03 362	88.78 354	85.62 389	81.98 370	93.66 383	97.35 273	75.51 386	70.79 389	83.05 395	48.70 393	94.91 364	78.31 365	60.29 398	89.46 385

Patchmatch-RL test		86.90 327	85.98 331	89.67 347	84.45 390	75.59 386	89.71 396	92.43 394	86.89 325	77.83 375	90.94 374	94.22 79	93.63 376	87.75 302	69.61 379	99.79 97

pmmvs-eth3d		84.03 344	81.97 348	90.20 343	84.15 391	87.09 343	98.10 332	94.73 380	83.05 359	74.10 386	87.77 387	65.56 366	94.01 371	81.08 352	69.24 381	89.49 384

test_fmvs3		79.99 356	80.17 355	79.45 373	84.02 392	62.83 394	99.05 265	93.49 392	88.29 306	80.06 366	86.65 390	28.09 402	88.00 394	88.63 289	73.27 374	87.54 390

PM-MVS		80.47 353	78.88 358	85.26 365	83.79 393	72.22 389	95.89 374	91.08 398	85.71 340	76.56 380	88.30 383	36.64 398	93.90 373	82.39 344	69.57 380	89.66 383

new-patchmatchnet		81.19 350	79.34 357	86.76 363	82.86 394	80.36 382	97.92 336	95.27 373	82.09 366	72.02 387	86.87 389	62.81 375	90.74 391	71.10 381	63.08 394	89.19 387

mvsany_test3		82.12 349	81.14 351	85.06 366	81.87 395	70.41 390	97.09 351	92.14 395	91.27 246	77.84 374	88.73 382	39.31 397	95.49 354	90.75 266	71.24 376	89.29 386

WB-MVS		76.28 359	77.28 361	73.29 379	81.18 396	54.68 404	97.87 338	94.19 384	81.30 368	69.43 391	90.70 376	77.02 303	82.06 402	35.71 407	68.11 386	83.13 393

test_f		78.40 358	77.59 360	80.81 372	80.82 397	62.48 397	96.96 355	93.08 393	83.44 358	74.57 385	84.57 394	27.95 403	92.63 383	84.15 331	72.79 375	87.32 391

SSC-MVS		75.42 360	76.40 363	72.49 383	80.68 398	53.62 405	97.42 343	94.06 386	80.42 372	68.75 392	90.14 378	76.54 310	81.66 403	33.25 408	66.34 390	82.19 394

pmmvs3		80.27 354	77.77 359	87.76 361	80.32 399	82.43 367	98.23 326	91.97 396	72.74 392	78.75 369	87.97 386	57.30 385	90.99 390	70.31 382	62.37 395	89.87 379

testf1		68.38 364	66.92 365	72.78 381	78.80 400	50.36 407	90.95 394	87.35 406	55.47 397	58.95 396	88.14 384	20.64 407	87.60 395	57.28 399	64.69 391	80.39 396

APD_test2		68.38 364	66.92 365	72.78 381	78.80 400	50.36 407	90.95 394	87.35 406	55.47 397	58.95 396	88.14 384	20.64 407	87.60 395	57.28 399	64.69 391	80.39 396

ambc				83.23 369	77.17 402	62.61 395	87.38 398	94.55 383		76.72 379	86.65 390	30.16 399	96.36 334	84.85 330	69.86 378	90.73 373

test_vis3_rt		68.82 362	66.69 367	75.21 378	76.24 403	60.41 399	96.44 362	68.71 413	75.13 387	50.54 404	69.52 402	16.42 412	96.32 336	80.27 355	66.92 389	68.89 400

TDRefinement		84.76 338	82.56 346	91.38 334	74.58 404	84.80 357	97.36 345	94.56 382	84.73 350	80.21 364	96.12 290	63.56 372	98.39 224	87.92 300	63.97 393	90.95 372

E-PMN		52.30 372	52.18 374	52.67 389	71.51 405	45.40 411	93.62 384	76.60 411	36.01 405	43.50 406	64.13 405	27.11 404	67.31 408	31.06 409	26.06 404	45.30 407

EMVS		51.44 374	51.22 376	52.11 390	70.71 406	44.97 413	94.04 380	75.66 412	35.34 407	42.40 407	61.56 408	28.93 401	65.87 409	27.64 410	24.73 405	45.49 406

PMMVS2		67.15 367	64.15 370	76.14 377	70.56 407	62.07 398	93.89 381	87.52 405	58.09 396	60.02 395	78.32 397	22.38 406	84.54 400	59.56 397	47.03 402	81.80 395

FPMVS		68.72 363	68.72 364	68.71 385	65.95 408	44.27 414	95.97 373	94.74 379	51.13 400	53.26 402	90.50 377	25.11 405	83.00 401	60.80 396	80.97 337	78.87 398

wuyk23d		20.37 378	20.84 381	18.99 393	65.34 409	27.73 416	50.43 404	7.67 417	9.50 410	8.01 411	6.34 411	6.13 415	26.24 410	23.40 411	10.69 409	2.99 408

LCM-MVSNet		67.77 366	64.73 369	76.87 376	62.95 410	56.25 403	89.37 397	93.74 390	44.53 402	61.99 394	80.74 396	20.42 409	86.53 399	69.37 385	59.50 399	87.84 388

MVE	53.74 22	51.54 373	47.86 377	62.60 387	59.56 411	50.93 406	79.41 401	77.69 410	35.69 406	36.27 408	61.76 407	5.79 416	69.63 406	37.97 406	36.61 403	67.24 401
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 370	52.24 373	67.66 386	49.27 412	56.82 402	83.94 399	82.02 409	70.47 393	33.28 409	64.54 404	17.23 411	69.16 407	45.59 404	23.85 406	77.02 399

tmp_tt		65.23 369	62.94 372	72.13 384	44.90 413	50.03 409	81.05 400	89.42 404	38.45 403	48.51 405	99.90 18	54.09 388	78.70 405	91.84 248	18.26 407	87.64 389

PMVS	49.05 23	53.75 371	51.34 375	60.97 388	40.80 414	34.68 415	74.82 402	89.62 403	37.55 404	28.67 410	72.12 399	7.09 414	81.63 404	43.17 405	68.21 385	66.59 402
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 376	39.14 379	33.31 391	19.94 415	24.83 417	98.36 320	9.75 416	15.53 409	51.31 403	87.14 388	19.62 410	17.74 411	47.10 403	3.47 410	57.36 404

testmvs		40.60 375	44.45 378	29.05 392	19.49 416	14.11 418	99.68 179	18.47 415	20.74 408	64.59 393	98.48 213	10.95 413	17.09 412	56.66 401	11.01 408	55.94 405

test_blank		0.00 381	0.00 384	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.02 412	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

eth-test2					0.00 417

eth-test					0.00 417

uanet_test		0.00 381	0.00 384	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.00 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

DCPMVS		0.00 381	0.00 384	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.00 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

cdsmvs_eth3d_5k		23.43 377	31.24 380	0.00 394	0.00 417	0.00 419	0.00 405	98.09 201	0.00 412	0.00 413	99.67 96	83.37 250	0.00 413	0.00 412	0.00 411	0.00 409

pcd_1.5k_mvsjas		7.60 380	10.13 383	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.00 413	91.20 153	0.00 413	0.00 412	0.00 411	0.00 409

sosnet-low-res		0.00 381	0.00 384	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.00 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

sosnet		0.00 381	0.00 384	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.00 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

uncertanet		0.00 381	0.00 384	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.00 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

Regformer		0.00 381	0.00 384	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.00 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

ab-mvs-re		8.28 379	11.04 382	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	99.40 125	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

uanet		0.00 381	0.00 384	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.00 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

WAC-MVS						90.97 288								86.10 322

PC_three_1452									96.96 44	99.80 17	99.79 57	97.49 8	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 131	97.27 34	99.80 17	99.94 4	97.18 19	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 59	99.83 13	99.91 14	97.87 4	100.00 1	99.92 12	100.00 1	100.00 1

GSMVS																99.59 133

sam_mvs1												94.72 63				99.59 133

sam_mvs												94.25 78

MTGPA								98.28 179

test_post1							95.78 375				59.23 409	93.20 110	97.74 269	91.06 257

test_post											63.35 406	94.43 68	98.13 249

patchmatchnet-post											91.70 371	95.12 49	97.95 260

MTMP							99.87 108	96.49 346

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 71	99.94 70

test_prior2							99.95 54		95.78 81	99.73 32	99.76 65	96.00 32		99.78 27	100.00 1

旧先验2							99.46 217		94.21 134	99.85 9			99.95 69	96.96 159

新几何2							99.40 221

无先验							99.49 212	98.71 66	93.46 165				100.00 1	94.36 204		99.99 23

原ACMM2							99.90 94

testdata2													99.99 36	90.54 270

segment_acmp												96.68 24

testdata1							99.28 241		96.35 69

plane_prior5								97.87 223					98.37 230	97.79 135	89.55 257	94.52 266

plane_prior4											98.59 201

plane_prior3						91.64 278			96.63 56	93.01 230

plane_prior2							99.84 128		96.38 65

plane_prior						91.74 272	99.86 120		96.76 52						89.59 256

n2								0.00 418

nn								0.00 418

door-mid								89.69 402

test11								98.44 123

door								90.31 399

HQP5-MVS						91.85 268

BP-MVS														97.92 127

HQP4-MVS										93.37 226			98.39 224			94.53 264

HQP3-MVS								97.89 221							89.60 254

HQP2-MVS												80.65 274

MDTV_nov1_ep13_2view						96.26 138	96.11 369		91.89 224	98.06 137		94.40 70		94.30 206		99.67 115

ACMMP++_ref															87.04 290

ACMMP++															88.23 278

Test By Simon												92.82 121

High-resolution multi-view benchmark