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		97.23 100	96.80 105	98.51 106	99.99 1	95.60 162	99.09 247	98.84 58	93.32 164	96.74 164	99.72 81	86.04 218	100.00 1	98.01 115	99.43 110	99.94 74

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 14	98.69 68	98.20 7	99.93 1	99.98 2	96.82 23	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 27	98.64 76	98.47 2	99.13 85	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 74	99.97 3	96.92 113	99.95 52	98.38 155	95.04 97	98.61 112	99.80 51	93.39 98	100.00 1	98.64 89	100.00 1	99.98 48

CPTT-MVS		97.64 84	97.32 87	98.58 98	99.97 3	95.77 153	99.96 34	98.35 161	89.90 268	98.36 122	99.79 55	91.18 154	99.99 36	98.37 99	99.99 21	99.99 23

DP-MVS Recon		98.41 45	98.02 57	99.56 25	99.97 3	98.70 46	99.92 78	98.44 121	92.06 213	98.40 121	99.84 41	95.68 40	100.00 1	98.19 105	99.71 83	99.97 58

PAPR		98.52 35	98.16 49	99.58 24	99.97 3	98.77 40	99.95 52	98.43 129	95.35 91	98.03 133	99.75 69	94.03 84	99.98 43	98.11 110	99.83 72	99.99 23

HFP-MVS		98.56 32	98.37 36	99.14 59	99.96 8	97.43 94	99.95 52	98.61 82	94.77 105	99.31 76	99.85 30	94.22 77	100.00 1	98.70 84	99.98 32	99.98 48

region2R		98.54 33	98.37 36	99.05 66	99.96 8	97.18 101	99.96 34	98.55 97	94.87 103	99.45 64	99.85 30	94.07 83	100.00 1	98.67 86	100.00 1	99.98 48

ACMMPR		98.50 36	98.32 40	99.05 66	99.96 8	97.18 101	99.95 52	98.60 84	94.77 105	99.31 76	99.84 41	93.73 93	100.00 1	98.70 84	99.98 32	99.98 48

NCCC		99.37 2	99.25 2	99.71 14	99.96 8	99.15 21	99.97 27	98.62 81	98.02 13	99.90 3	99.95 3	97.33 17	100.00 1	99.54 39	100.00 1	100.00 1

CP-MVS		98.45 40	98.32 40	98.87 79	99.96 8	96.62 122	99.97 27	98.39 151	94.43 117	98.90 94	99.87 24	94.30 75	100.00 1	99.04 63	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 144	96.63 56	99.75 29	99.93 11	97.49 10

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 52	98.43 129					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 26	98.55 25	99.15 57	99.94 13	97.50 90	99.94 68	98.42 140	96.22 71	99.41 68	99.78 59	94.34 73	99.96 61	98.92 70	99.95 49	99.99 23

X-MVStestdata		93.83 206	92.06 239	99.15 57	99.94 13	97.50 90	99.94 68	98.42 140	96.22 71	99.41 68	41.37 403	94.34 73	99.96 61	98.92 70	99.95 49	99.99 23

test_prior				99.43 35	99.94 13	98.49 58		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 59	99.98 14	98.86 53	97.10 40	99.80 17	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 43	99.91 82	98.39 151	97.20 38	99.46 63	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 68	99.94 13	97.17 104	99.95 52	98.39 151	94.70 109	98.26 128	99.81 50	91.84 145	100.00 1	98.85 76	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 44	99.87 101	98.33 166	93.97 143	99.76 28	99.87 24	94.99 57	99.75 132	98.55 93	100.00 1	99.98 48

PAPM_NR		98.12 60	97.93 64	98.70 87	99.94 13	96.13 144	99.82 132	98.43 129	94.56 113	97.52 145	99.70 85	94.40 68	99.98 43	97.00 149	99.98 32	99.99 23

MG-MVS		98.91 18	98.65 20	99.68 15	99.94 13	99.07 24	99.64 180	99.44 20	97.33 31	99.00 90	99.72 81	94.03 84	99.98 43	98.73 83	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 34	98.43 129	97.27 34	99.80 17	99.94 4	96.71 24	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 24	99.31 10		98.41 144	97.71 19	99.84 12				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 129	97.26 36	99.80 17	99.88 21	96.71 24	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 52	98.32 168	97.28 32	99.83 13	99.91 14	97.22 19	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 34	98.42 140	97.28 32	99.86 7	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 73	99.93 24	97.24 98	99.95 52	98.42 140	97.50 26	99.52 59	99.88 21	97.43 16	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 40		98.43 129		99.63 43			99.85 108

FOURS1					99.92 31	97.66 83	99.95 52	98.36 159	95.58 85	99.52 59

ZD-MVS					99.92 31	98.57 54		98.52 103	92.34 205	99.31 76	99.83 43	95.06 52	99.80 121	99.70 34	99.97 42

GST-MVS		98.27 52	97.97 59	99.17 53	99.92 31	97.57 85	99.93 75	98.39 151	94.04 141	98.80 99	99.74 76	92.98 113	100.00 1	98.16 107	99.76 80	99.93 76

TEST9					99.92 31	98.92 28	99.96 34	98.43 129	93.90 148	99.71 34	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 28	99.96 34	98.43 129	94.35 122	99.71 34	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 31	99.96 34	98.43 129	94.35 122	99.69 36	99.85 30	95.94 34	99.85 108

PGM-MVS		98.34 48	98.13 51	98.99 72	99.92 31	97.00 109	99.75 152	99.50 18	93.90 148	99.37 73	99.76 63	93.24 107	100.00 1	97.75 132	99.96 46	99.98 48

ACMMP		97.74 79	97.44 81	98.66 90	99.92 31	96.13 144	99.18 241	99.45 19	94.84 104	96.41 174	99.71 83	91.40 148	99.99 36	97.99 117	98.03 157	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 52	98.43 129	96.48 59	99.80 17	99.93 11	97.44 14	100.00 1	99.92 12	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 144					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 144					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 52	98.56 91	97.56 25	99.44 65	99.85 30	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 57	99.87 101	98.36 159	94.08 135	99.74 31	99.73 78	94.08 82	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 34	99.24 236	98.47 114	98.14 10	99.08 86	99.91 14	93.09 110	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 34				99.80 51	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 101	98.44 121	97.48 27	99.64 42	99.94 4	96.68 26	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 62

CSCG		97.10 103	97.04 97	97.27 176	99.89 45	91.92 261	99.90 87	99.07 34	88.67 291	95.26 196	99.82 46	93.17 109	99.98 43	98.15 108	99.47 104	99.90 83

ZNCC-MVS		98.31 49	98.03 56	99.17 53	99.88 49	97.59 84	99.94 68	98.44 121	94.31 125	98.50 116	99.82 46	93.06 111	99.99 36	98.30 103	99.99 21	99.93 76

SR-MVS		98.46 39	98.30 43	98.93 77	99.88 49	97.04 107	99.84 122	98.35 161	94.92 101	99.32 75	99.80 51	93.35 100	99.78 125	99.30 52	99.95 49	99.96 64

9.14			98.38 34		99.87 51		99.91 82	98.33 166	93.22 167	99.78 26	99.89 19	94.57 65	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 32	99.86 114	98.38 155	93.19 168	99.77 27	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 68	99.86 53	97.10 106	99.98 14	98.80 62	90.78 254	99.62 46	99.78 59	95.30 47	100.00 1	99.80 25	99.93 60	99.99 23

MTAPA		98.29 51	97.96 62	99.30 42	99.85 54	97.93 73	99.39 217	98.28 175	95.76 80	97.18 153	99.88 21	92.74 121	100.00 1	98.67 86	99.88 68	99.99 23

LS3D		95.84 154	95.11 164	98.02 133	99.85 54	95.10 182	98.74 289	98.50 111	87.22 312	93.66 214	99.86 26	87.45 202	99.95 69	90.94 254	99.81 78	99.02 197

HPM-MVS		97.96 63	97.72 71	98.68 88	99.84 56	96.39 131	99.90 87	98.17 187	92.61 190	98.62 111	99.57 107	91.87 144	99.67 145	98.87 75	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 85	99.83 57	96.59 124	99.40 213	98.51 106	95.29 93	98.51 115	99.76 63	93.60 97	99.71 138	98.53 94	99.52 99	99.95 71

save fliter					99.82 58	98.79 38	99.96 34	98.40 148	97.66 21

PLC	95.54 3	97.93 65	97.89 67	98.05 132	99.82 58	94.77 191	99.92 78	98.46 116	93.93 146	97.20 152	99.27 132	95.44 45	99.97 53	97.41 137	99.51 102	99.41 162
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 82	99.81 60	96.60 123	99.82 132	98.30 173	93.95 145	99.37 73	99.77 61	92.84 117	99.76 131	98.95 67	99.92 63	99.97 58

EI-MVSNet-UG-set		98.14 59	97.99 58	98.60 95	99.80 61	96.27 134	99.36 222	98.50 111	95.21 95	98.30 125	99.75 69	93.29 104	99.73 137	98.37 99	99.30 116	99.81 94

SR-MVS-dyc-post		98.31 49	98.17 48	98.71 86	99.79 62	96.37 132	99.76 149	98.31 170	94.43 117	99.40 70	99.75 69	93.28 105	99.78 125	98.90 73	99.92 63	99.97 58

RE-MVS-def			98.13 51		99.79 62	96.37 132	99.76 149	98.31 170	94.43 117	99.40 70	99.75 69	92.95 114		98.90 73	99.92 63	99.97 58

HPM-MVS_fast		97.80 74	97.50 79	98.68 88	99.79 62	96.42 127	99.88 98	98.16 191	91.75 223	98.94 92	99.54 110	91.82 146	99.65 147	97.62 135	99.99 21	99.99 23

SF-MVS		98.67 27	98.40 32	99.50 30	99.77 65	98.67 47	99.90 87	98.21 182	93.53 158	99.81 15	99.89 19	94.70 63	99.86 107	99.84 22	99.93 60	99.96 64

旧先验1					99.76 66	97.52 87		98.64 76			99.85 30	95.63 41			99.94 54	99.99 23

OMC-MVS		97.28 97	97.23 89	97.41 167	99.76 66	93.36 230	99.65 176	97.95 210	96.03 75	97.41 149	99.70 85	89.61 178	99.51 152	96.73 156	98.25 149	99.38 164

新几何1				99.42 37	99.75 68	98.27 61		98.63 80	92.69 185	99.55 54	99.82 46	94.40 68	100.00 1	91.21 246	99.94 54	99.99 23

MP-MVS-pluss		98.07 62	97.64 74	99.38 41	99.74 69	98.41 60	99.74 155	98.18 186	93.35 162	96.45 171	99.85 30	92.64 123	99.97 53	98.91 72	99.89 66	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 47	99.77 144	98.38 155	96.73 53	99.88 6	99.74 76	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 55		98.40 148		99.65 40		94.76 60	99.75 132		99.98 32	99.99 23

原ACMM1				98.96 75	99.73 72	96.99 110		98.51 106	94.06 138	99.62 46	99.85 30	94.97 58	99.96 61	95.11 176	99.95 49	99.92 81

TSAR-MVS + GP.		98.60 30	98.51 28	98.86 80	99.73 72	96.63 121	99.97 27	97.92 215	98.07 11	98.76 103	99.55 108	95.00 56	99.94 77	99.91 15	97.68 162	99.99 23

CANet		98.27 52	97.82 69	99.63 17	99.72 74	99.10 23	99.98 14	98.51 106	97.00 43	98.52 114	99.71 83	87.80 197	99.95 69	99.75 28	99.38 112	99.83 91

F-COLMAP		96.93 112	96.95 100	96.87 185	99.71 75	91.74 266	99.85 117	97.95 210	93.11 171	95.72 189	99.16 143	92.35 133	99.94 77	95.32 174	99.35 114	98.92 199

SD-MVS		98.92 17	98.70 19	99.56 25	99.70 76	98.73 44	99.94 68	98.34 165	96.38 65	99.81 15	99.76 63	94.59 64	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	95.59 219	99.67 77	86.91 339	99.95 52	98.89 49	97.60 22	99.90 3	99.76 63	96.54 28	99.98 43	99.94 11	99.82 76	99.88 85

ACMMP_NAP		98.49 37	98.14 50	99.54 27	99.66 78	98.62 53	99.85 117	98.37 158	94.68 110	99.53 57	99.83 43	92.87 116	100.00 1	98.66 88	99.84 71	99.99 23

DeepPCF-MVS	95.94 2	97.71 82	98.98 12	93.92 283	99.63 79	81.76 366	99.96 34	98.56 91	99.47 1	99.19 83	99.99 1	94.16 81	100.00 1	99.92 12	99.93 60	100.00 1

EPNet		98.49 37	98.40 32	98.77 84	99.62 80	96.80 118	99.90 87	99.51 17	97.60 22	99.20 81	99.36 126	93.71 94	99.91 89	97.99 117	98.71 137	99.61 127
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 4	99.76 6	98.39 3	99.39 72	99.80 51	90.49 168	99.96 61	99.89 16	99.43 110	99.98 48

PVSNet_BlendedMVS		96.05 147	95.82 144	96.72 190	99.59 81	96.99 110	99.95 52	99.10 31	94.06 138	98.27 126	95.80 287	89.00 189	99.95 69	99.12 58	87.53 280	93.24 338

PVSNet_Blended		97.94 64	97.64 74	98.83 81	99.59 81	96.99 110	100.00 1	99.10 31	95.38 90	98.27 126	99.08 146	89.00 189	99.95 69	99.12 58	99.25 118	99.57 137

PatchMatch-RL		96.04 148	95.40 153	97.95 134	99.59 81	95.22 178	99.52 198	99.07 34	93.96 144	96.49 170	98.35 211	82.28 247	99.82 120	90.15 270	99.22 121	98.81 206

dcpmvs_2		97.42 92	98.09 54	95.42 224	99.58 85	87.24 335	99.23 237	96.95 309	94.28 127	98.93 93	99.73 78	94.39 71	99.16 170	99.89 16	99.82 76	99.86 89

test222					99.55 86	97.41 96	99.34 223	98.55 97	91.86 218	99.27 80	99.83 43	93.84 91			99.95 49	99.99 23

CNLPA		97.76 78	97.38 83	98.92 78	99.53 87	96.84 115	99.87 101	98.14 195	93.78 151	96.55 169	99.69 87	92.28 135	99.98 43	97.13 144	99.44 108	99.93 76

API-MVS		97.86 68	97.66 73	98.47 108	99.52 88	95.41 169	99.47 207	98.87 52	91.68 224	98.84 96	99.85 30	92.34 134	99.99 36	98.44 96	99.96 46	100.00 1

PVSNet	91.05 13	97.13 102	96.69 109	98.45 110	99.52 88	95.81 151	99.95 52	99.65 12	94.73 107	99.04 88	99.21 139	84.48 233	99.95 69	94.92 182	98.74 136	99.58 136

114514_t		97.41 93	96.83 103	99.14 59	99.51 90	97.83 75	99.89 95	98.27 177	88.48 295	99.06 87	99.66 96	90.30 170	99.64 148	96.32 160	99.97 42	99.96 64

cl22		93.77 210	93.25 214	95.33 228	99.49 91	94.43 195	99.61 184	98.09 197	90.38 259	89.16 283	95.61 294	90.56 166	97.34 271	91.93 238	84.45 301	94.21 283

testdata				98.42 113	99.47 92	95.33 172		98.56 91	93.78 151	99.79 25	99.85 30	93.64 96	99.94 77	94.97 180	99.94 54	100.00 1

MAR-MVS		97.43 88	97.19 91	98.15 127	99.47 92	94.79 190	99.05 258	98.76 63	92.65 188	98.66 109	99.82 46	88.52 194	99.98 43	98.12 109	99.63 88	99.67 113
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		94.54 188	93.42 207	97.91 138	99.46 94	94.04 208	98.93 270	97.48 255	81.15 362	90.04 256	99.55 108	87.02 208	99.95 69	88.97 280	98.11 153	99.73 105

MVS_111021_LR		98.42 44	98.38 34	98.53 105	99.39 95	95.79 152	99.87 101	99.86 2	96.70 54	98.78 100	99.79 55	92.03 141	99.90 91	99.17 57	99.86 70	99.88 85

CHOSEN 280x420		99.01 13	99.03 10	98.95 76	99.38 96	98.87 32	98.46 306	99.42 22	97.03 42	99.02 89	99.09 145	99.35 1	98.21 235	99.73 32	99.78 79	99.77 101

MVS_111021_HR		98.72 25	98.62 22	99.01 71	99.36 97	97.18 101	99.93 75	99.90 1	96.81 51	98.67 108	99.77 61	93.92 86	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 34	98.44 121	97.96 14	99.55 54	99.94 4	97.18 21	100.00 1	93.81 211	99.94 54	99.98 48

TAPA-MVS	92.12 8	94.42 193	93.60 200	96.90 184	99.33 98	91.78 265	99.78 141	98.00 204	89.89 269	94.52 202	99.47 114	91.97 142	99.18 168	69.90 376	99.52 99	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	97.70 151	99.28 100	95.20 179	99.98 14	97.15 287	95.53 87	99.62 46	99.79 55	92.08 140	98.38 218	98.75 82	99.28 117	99.52 147

test_fmvsm_n_1920		98.44 41	98.61 23	97.92 136	99.27 101	95.18 180	100.00 1	98.90 47	98.05 12	99.80 17	99.73 78	92.64 123	99.99 36	99.58 38	99.51 102	98.59 216

fmvsm_l_conf0.5_n_a		99.00 14	98.91 14	99.28 43	99.21 102	97.91 74	99.98 14	98.85 56	98.25 4	99.92 2	99.75 69	94.72 61	99.97 53	99.87 19	99.64 87	99.95 71

test_yl		97.83 70	97.37 84	99.21 47	99.18 103	97.98 70	99.64 180	99.27 27	91.43 233	97.88 139	98.99 155	95.84 38	99.84 116	98.82 77	95.32 214	99.79 97

DCV-MVSNet		97.83 70	97.37 84	99.21 47	99.18 103	97.98 70	99.64 180	99.27 27	91.43 233	97.88 139	98.99 155	95.84 38	99.84 116	98.82 77	95.32 214	99.79 97

MVS_0304		98.87 20	98.61 23	99.67 16	99.18 103	99.13 22	99.87 101	99.65 12	98.17 8	98.75 105	99.75 69	92.76 120	99.94 77	99.88 18	99.44 108	99.94 74

fmvsm_l_conf0.5_n		98.94 15	98.84 17	99.25 44	99.17 106	97.81 77	99.98 14	98.86 53	98.25 4	99.90 3	99.76 63	94.21 79	99.97 53	99.87 19	99.52 99	99.98 48

DeepC-MVS	94.51 4	96.92 113	96.40 119	98.45 110	99.16 107	95.90 149	99.66 174	98.06 200	96.37 68	94.37 205	99.49 113	83.29 243	99.90 91	97.63 134	99.61 93	99.55 139
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 51	100.00 1	98.58 86	97.70 20	98.21 130	99.24 137	92.58 126	99.94 77	98.63 91	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	97.43 166	99.10 109	94.42 196	99.99 4	97.10 292	95.07 96	99.68 37	99.75 69	92.95 114	98.34 222	98.38 98	99.14 123	99.54 143

Anonymous202405211		93.10 228	91.99 241	96.40 200	99.10 109	89.65 310	98.88 275	97.93 212	83.71 349	94.00 211	98.75 184	68.79 344	99.88 102	95.08 178	91.71 239	99.68 111

fmvsm_s_conf0.5_n		97.80 74	97.85 68	97.67 152	99.06 111	94.41 197	99.98 14	98.97 40	97.34 29	99.63 43	99.69 87	87.27 204	99.97 53	99.62 37	99.06 127	98.62 215

HyFIR lowres test		96.66 126	96.43 118	97.36 172	99.05 112	93.91 213	99.70 168	99.80 3	90.54 257	96.26 177	98.08 217	92.15 138	98.23 234	96.84 155	95.46 209	99.93 76

LFMVS		94.75 182	93.56 203	98.30 119	99.03 113	95.70 158	98.74 289	97.98 207	87.81 305	98.47 117	99.39 123	67.43 352	99.53 150	98.01 115	95.20 217	99.67 113

AllTest		92.48 243	91.64 246	95.00 238	99.01 114	88.43 324	98.94 269	96.82 324	86.50 321	88.71 289	98.47 207	74.73 321	99.88 102	85.39 318	96.18 191	96.71 242

TestCases				95.00 238	99.01 114	88.43 324		96.82 324	86.50 321	88.71 289	98.47 207	74.73 321	99.88 102	85.39 318	96.18 191	96.71 242

COLMAP_ROB	90.47 14	92.18 250	91.49 252	94.25 271	99.00 116	88.04 330	98.42 311	96.70 331	82.30 358	88.43 296	99.01 152	76.97 297	99.85 108	86.11 314	96.50 187	94.86 253
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs1		95.35 168	95.68 149	94.36 268	98.99 117	84.98 348	99.96 34	96.65 333	97.60 22	99.73 32	98.96 161	71.58 334	99.93 85	98.31 102	99.37 113	98.17 222

HY-MVS	92.50 7	97.79 76	97.17 93	99.63 17	98.98 118	99.32 9	97.49 335	99.52 15	95.69 82	98.32 124	97.41 238	93.32 102	99.77 128	98.08 113	95.75 205	99.81 94

VNet		97.21 101	96.57 114	99.13 63	98.97 119	97.82 76	99.03 261	99.21 29	94.31 125	99.18 84	98.88 172	86.26 217	99.89 96	98.93 69	94.32 223	99.69 110

thres200		96.96 110	96.21 123	99.22 46	98.97 119	98.84 35	99.85 117	99.71 7	93.17 169	96.26 177	98.88 172	89.87 175	99.51 152	94.26 200	94.91 218	99.31 174

tfpn200view9		96.79 117	95.99 128	99.19 49	98.94 121	98.82 36	99.78 141	99.71 7	92.86 174	96.02 182	98.87 175	89.33 182	99.50 154	93.84 208	94.57 219	99.27 180

thres400		96.78 118	95.99 128	99.16 55	98.94 121	98.82 36	99.78 141	99.71 7	92.86 174	96.02 182	98.87 175	89.33 182	99.50 154	93.84 208	94.57 219	99.16 187

Anonymous20231211		89.86 299	88.44 306	94.13 274	98.93 123	90.68 288	98.54 303	98.26 178	76.28 374	86.73 317	95.54 298	70.60 340	97.56 264	90.82 257	80.27 336	94.15 291

canonicalmvs		97.09 105	96.32 120	99.39 40	98.93 123	98.95 27	99.72 163	97.35 266	94.45 115	97.88 139	99.42 118	86.71 211	99.52 151	98.48 95	93.97 229	99.72 107

SDMVSNet		94.80 178	93.96 191	97.33 174	98.92 125	95.42 168	99.59 186	98.99 37	92.41 202	92.55 229	97.85 227	75.81 311	98.93 178	97.90 123	91.62 240	97.64 233

sd_testset		93.55 217	92.83 221	95.74 217	98.92 125	90.89 285	98.24 317	98.85 56	92.41 202	92.55 229	97.85 227	71.07 339	98.68 194	93.93 205	91.62 240	97.64 233

EPNet_dtu		95.71 158	95.39 154	96.66 192	98.92 125	93.41 227	99.57 190	98.90 47	96.19 73	97.52 145	98.56 199	92.65 122	97.36 269	77.89 359	98.33 144	99.20 185
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	98.92 125	99.28 17	99.89 95	99.52 15	95.58 85	98.24 129	99.39 123	93.33 101	99.74 134	97.98 119	95.58 208	99.78 100

CHOSEN 1792x2688		96.81 116	96.53 115	97.64 154	98.91 129	93.07 232	99.65 176	99.80 3	95.64 83	95.39 193	98.86 177	84.35 236	99.90 91	96.98 150	99.16 122	99.95 71

thres100view900		96.74 121	95.92 140	99.18 50	98.90 130	98.77 40	99.74 155	99.71 7	92.59 192	95.84 185	98.86 177	89.25 184	99.50 154	93.84 208	94.57 219	99.27 180

thres600view7		96.69 124	95.87 143	99.14 59	98.90 130	98.78 39	99.74 155	99.71 7	92.59 192	95.84 185	98.86 177	89.25 184	99.50 154	93.44 220	94.50 222	99.16 187

MSDG		94.37 195	93.36 211	97.40 168	98.88 132	93.95 212	99.37 220	97.38 264	85.75 332	90.80 248	99.17 142	84.11 238	99.88 102	86.35 311	98.43 142	98.36 220

h-mvs33		94.92 176	94.36 180	96.59 194	98.85 133	91.29 277	98.93 270	98.94 41	95.90 76	98.77 101	98.42 210	90.89 162	99.77 128	97.80 125	70.76 370	98.72 212

Anonymous20240529		92.10 251	90.65 262	96.47 195	98.82 134	90.61 290	98.72 291	98.67 73	75.54 378	93.90 213	98.58 197	66.23 356	99.90 91	94.70 191	90.67 242	98.90 202

PVSNet_Blended_VisFu		97.27 98	96.81 104	98.66 90	98.81 135	96.67 120	99.92 78	98.64 76	94.51 114	96.38 175	98.49 203	89.05 188	99.88 102	97.10 146	98.34 143	99.43 160

PS-MVSNAJ		98.44 41	98.20 46	99.16 55	98.80 136	98.92 28	99.54 196	98.17 187	97.34 29	99.85 9	99.85 30	91.20 151	99.89 96	99.41 48	99.67 85	98.69 213

CANet_DTU		96.76 119	96.15 124	98.60 95	98.78 137	97.53 86	99.84 122	97.63 234	97.25 37	99.20 81	99.64 99	81.36 256	99.98 43	92.77 231	98.89 130	98.28 221

mvsany_test1		97.82 72	97.90 66	97.55 159	98.77 138	93.04 235	99.80 138	97.93 212	96.95 45	99.61 52	99.68 93	90.92 159	99.83 118	99.18 56	98.29 148	99.80 96

alignmvs		97.81 73	97.33 86	99.25 44	98.77 138	98.66 49	99.99 4	98.44 121	94.40 121	98.41 119	99.47 114	93.65 95	99.42 162	98.57 92	94.26 225	99.67 113

SteuartSystems-ACMMP		99.02 12	98.97 13	99.18 50	98.72 140	97.71 79	99.98 14	98.44 121	96.85 46	99.80 17	99.91 14	97.57 8	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 70	98.69 141	98.66 49	99.52 198	98.08 199	97.05 41	99.86 7	99.86 26	90.65 164	99.71 138	99.39 50	98.63 138	98.69 213

miper_enhance_ethall		94.36 197	93.98 190	95.49 220	98.68 142	95.24 176	99.73 160	97.29 274	93.28 166	89.86 261	95.97 285	94.37 72	97.05 293	92.20 235	84.45 301	94.19 284

ETVMVS		97.03 108	96.64 110	98.20 123	98.67 143	97.12 105	99.89 95	98.57 88	91.10 244	98.17 131	98.59 194	93.86 90	98.19 236	95.64 171	95.24 216	99.28 179

test2506		97.53 86	97.19 91	98.58 98	98.66 144	96.90 114	98.81 284	99.77 5	94.93 99	97.95 135	98.96 161	92.51 128	99.20 166	94.93 181	98.15 150	99.64 119

ECVR-MVS		95.66 161	95.05 166	97.51 162	98.66 144	93.71 217	98.85 281	98.45 117	94.93 99	96.86 160	98.96 161	75.22 317	99.20 166	95.34 173	98.15 150	99.64 119

fmvsm_s_conf0.5_n_a		97.73 81	97.72 71	97.77 146	98.63 146	94.26 202	99.96 34	98.92 46	97.18 39	99.75 29	99.69 87	87.00 209	99.97 53	99.46 44	98.89 130	99.08 195

testing222		97.08 107	96.75 107	98.06 131	98.56 147	96.82 116	99.85 117	98.61 82	92.53 196	98.84 96	98.84 181	93.36 99	98.30 226	95.84 168	94.30 224	99.05 196

test1111		95.57 163	94.98 169	97.37 170	98.56 147	93.37 229	98.86 279	98.45 117	94.95 98	96.63 166	98.95 166	75.21 318	99.11 171	95.02 179	98.14 152	99.64 119

MVSTER		95.53 164	95.22 160	96.45 197	98.56 147	97.72 78	99.91 82	97.67 232	92.38 204	91.39 240	97.14 245	97.24 18	97.30 276	94.80 187	87.85 274	94.34 275

VDD-MVS		93.77 210	92.94 218	96.27 205	98.55 150	90.22 299	98.77 288	97.79 226	90.85 250	96.82 162	99.42 118	61.18 373	99.77 128	98.95 67	94.13 226	98.82 205

tpmvs		94.28 199	93.57 202	96.40 200	98.55 150	91.50 275	95.70 369	98.55 97	87.47 307	92.15 233	94.26 344	91.42 147	98.95 177	88.15 290	95.85 201	98.76 208

UGNet		95.33 169	94.57 177	97.62 157	98.55 150	94.85 186	98.67 297	99.32 26	95.75 81	96.80 163	96.27 276	72.18 331	99.96 61	94.58 194	99.05 128	98.04 226
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	95.18 170	94.10 187	98.43 112	98.55 150	95.99 147	97.91 330	97.31 271	90.35 261	89.48 272	99.22 138	85.19 226	99.89 96	90.40 267	98.47 141	99.41 162
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_vis1_n_1920		95.44 166	95.31 157	95.82 215	98.50 154	88.74 318	99.98 14	97.30 272	97.84 16	99.85 9	99.19 140	66.82 354	99.97 53	98.82 77	99.46 106	98.76 208

BH-w/o		95.71 158	95.38 155	96.68 191	98.49 155	92.28 252	99.84 122	97.50 253	92.12 210	92.06 236	98.79 182	84.69 231	98.67 195	95.29 175	99.66 86	99.09 193

baseline1		95.78 155	94.86 171	98.54 103	98.47 156	98.07 65	99.06 254	97.99 205	92.68 186	94.13 210	98.62 193	93.28 105	98.69 193	93.79 213	85.76 289	98.84 204

iter_conf05		96.07 146	95.95 136	96.44 199	98.43 157	97.52 87	99.91 82	96.85 320	94.16 131	92.49 231	97.98 223	98.20 4	97.34 271	97.26 141	88.29 267	94.45 265

EPMVS		96.53 130	96.01 127	98.09 129	98.43 157	96.12 146	96.36 356	99.43 21	93.53 158	97.64 143	95.04 322	94.41 67	98.38 218	91.13 248	98.11 153	99.75 103

iter_conf_final		96.01 149	95.93 138	96.28 204	98.38 159	97.03 108	99.87 101	97.03 300	94.05 140	92.61 227	97.98 223	98.01 5	97.34 271	97.02 148	88.39 266	94.47 259

sss		97.57 85	97.03 98	99.18 50	98.37 160	98.04 67	99.73 160	99.38 23	93.46 160	98.76 103	99.06 148	91.21 150	99.89 96	96.33 159	97.01 179	99.62 124

BH-untuned		95.18 170	94.83 172	96.22 206	98.36 161	91.22 278	99.80 138	97.32 270	90.91 248	91.08 244	98.67 186	83.51 240	98.54 201	94.23 201	99.61 93	98.92 199

ET-MVSNet_ETH3D		94.37 195	93.28 213	97.64 154	98.30 162	97.99 69	99.99 4	97.61 239	94.35 122	71.57 381	99.45 117	96.23 31	95.34 351	96.91 154	85.14 296	99.59 130

AUN-MVS		93.28 222	92.60 227	95.34 227	98.29 163	90.09 302	99.31 227	98.56 91	91.80 222	96.35 176	98.00 220	89.38 181	98.28 229	92.46 232	69.22 375	97.64 233

FMVSNet3		92.69 239	91.58 248	95.99 210	98.29 163	97.42 95	99.26 235	97.62 236	89.80 270	89.68 265	95.32 312	81.62 254	96.27 331	87.01 307	85.65 290	94.29 277

PMMVS		96.76 119	96.76 106	96.76 188	98.28 165	92.10 256	99.91 82	97.98 207	94.12 133	99.53 57	99.39 123	86.93 210	98.73 188	96.95 152	97.73 160	99.45 157

hse-mvs2		94.38 194	94.08 188	95.31 229	98.27 166	90.02 304	99.29 232	98.56 91	95.90 76	98.77 101	98.00 220	90.89 162	98.26 233	97.80 125	69.20 376	97.64 233

PVSNet_0	88.03 19	91.80 258	90.27 271	96.38 202	98.27 166	90.46 294	99.94 68	99.61 14	93.99 142	86.26 327	97.39 240	71.13 338	99.89 96	98.77 80	67.05 381	98.79 207

UA-Net		96.54 129	95.96 134	98.27 120	98.23 168	95.71 157	98.00 328	98.45 117	93.72 154	98.41 119	99.27 132	88.71 193	99.66 146	91.19 247	97.69 161	99.44 159

test_cas_vis1_n_1920		96.59 128	96.23 122	97.65 153	98.22 169	94.23 203	99.99 4	97.25 278	97.77 17	99.58 53	99.08 146	77.10 294	99.97 53	97.64 133	99.45 107	98.74 210

FE-MVS		95.70 160	95.01 168	97.79 143	98.21 170	94.57 192	95.03 370	98.69 68	88.90 286	97.50 147	96.19 278	92.60 125	99.49 158	89.99 272	97.94 159	99.31 174

GG-mvs-BLEND				98.54 103	98.21 170	98.01 68	93.87 375	98.52 103		97.92 136	97.92 226	99.02 2	97.94 252	98.17 106	99.58 96	99.67 113

mvs_anonymous		95.65 162	95.03 167	97.53 160	98.19 172	95.74 155	99.33 224	97.49 254	90.87 249	90.47 251	97.10 247	88.23 195	97.16 284	95.92 166	97.66 163	99.68 111

MVS_Test		96.46 132	95.74 145	98.61 94	98.18 173	97.23 99	99.31 227	97.15 287	91.07 245	98.84 96	97.05 251	88.17 196	98.97 175	94.39 196	97.50 165	99.61 127

BH-RMVSNet		95.18 170	94.31 183	97.80 141	98.17 174	95.23 177	99.76 149	97.53 249	92.52 198	94.27 208	99.25 136	76.84 299	98.80 182	90.89 256	99.54 98	99.35 169

RPSCF		91.80 258	92.79 223	88.83 346	98.15 175	69.87 384	98.11 324	96.60 335	83.93 347	94.33 206	99.27 132	79.60 276	99.46 161	91.99 237	93.16 236	97.18 240

ETV-MVS		97.92 66	97.80 70	98.25 121	98.14 176	96.48 125	99.98 14	97.63 234	95.61 84	99.29 79	99.46 116	92.55 127	98.82 181	99.02 66	98.54 139	99.46 155

IS-MVSNet		96.29 142	95.90 141	97.45 164	98.13 177	94.80 189	99.08 249	97.61 239	92.02 215	95.54 192	98.96 161	90.64 165	98.08 241	93.73 216	97.41 169	99.47 154

test_fmvsmconf_n		98.43 43	98.32 40	98.78 82	98.12 178	96.41 128	99.99 4	98.83 59	98.22 6	99.67 38	99.64 99	91.11 155	99.94 77	99.67 36	99.62 89	99.98 48

ab-mvs		94.69 183	93.42 207	98.51 106	98.07 179	96.26 135	96.49 354	98.68 70	90.31 262	94.54 201	97.00 253	76.30 306	99.71 138	95.98 165	93.38 234	99.56 138

XVG-OURS-SEG-HR		94.79 179	94.70 176	95.08 235	98.05 180	89.19 313	99.08 249	97.54 247	93.66 155	94.87 199	99.58 106	78.78 284	99.79 123	97.31 139	93.40 233	96.25 246

EIA-MVS		97.53 86	97.46 80	97.76 148	98.04 181	94.84 187	99.98 14	97.61 239	94.41 120	97.90 137	99.59 104	92.40 132	98.87 179	98.04 114	99.13 124	99.59 130

XVG-OURS		94.82 177	94.74 175	95.06 236	98.00 182	89.19 313	99.08 249	97.55 245	94.10 134	94.71 200	99.62 102	80.51 268	99.74 134	96.04 164	93.06 238	96.25 246

dp		95.05 173	94.43 179	96.91 183	97.99 183	92.73 242	96.29 359	97.98 207	89.70 271	95.93 184	94.67 335	93.83 92	98.45 207	86.91 310	96.53 186	99.54 143

tpmrst		96.27 144	95.98 130	97.13 178	97.96 184	93.15 231	96.34 357	98.17 187	92.07 211	98.71 107	95.12 320	93.91 87	98.73 188	94.91 184	96.62 184	99.50 151

TR-MVS		94.54 188	93.56 203	97.49 163	97.96 184	94.34 200	98.71 292	97.51 252	90.30 263	94.51 203	98.69 185	75.56 312	98.77 185	92.82 230	95.99 195	99.35 169

Vis-MVSNet (Re-imp)		96.32 139	95.98 130	97.35 173	97.93 186	94.82 188	99.47 207	98.15 194	91.83 219	95.09 197	99.11 144	91.37 149	97.47 267	93.47 219	97.43 166	99.74 104

MDTV_nov1_ep13			95.69 147		97.90 187	94.15 205	95.98 365	98.44 121	93.12 170	97.98 134	95.74 289	95.10 50	98.58 198	90.02 271	96.92 181

Fast-Effi-MVS+		95.02 174	94.19 185	97.52 161	97.88 188	94.55 193	99.97 27	97.08 295	88.85 288	94.47 204	97.96 225	84.59 232	98.41 210	89.84 274	97.10 174	99.59 130

ADS-MVSNet2		93.80 209	93.88 194	93.55 297	97.87 189	85.94 342	94.24 371	96.84 321	90.07 265	96.43 172	94.48 340	90.29 171	95.37 350	87.44 297	97.23 171	99.36 167

ADS-MVSNet		94.79 179	94.02 189	97.11 180	97.87 189	93.79 214	94.24 371	98.16 191	90.07 265	96.43 172	94.48 340	90.29 171	98.19 236	87.44 297	97.23 171	99.36 167

Effi-MVS+		96.30 141	95.69 147	98.16 124	97.85 191	96.26 135	97.41 337	97.21 280	90.37 260	98.65 110	98.58 197	86.61 213	98.70 192	97.11 145	97.37 170	99.52 147

PatchmatchNet		95.94 151	95.45 152	97.39 169	97.83 192	94.41 197	96.05 363	98.40 148	92.86 174	97.09 154	95.28 317	94.21 79	98.07 243	89.26 278	98.11 153	99.70 108
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 186	93.61 198	97.74 150	97.82 193	96.26 135	99.96 34	97.78 227	85.76 330	94.00 211	97.54 234	76.95 298	99.21 165	97.23 142	95.43 211	97.76 232

1112_ss		96.01 149	95.20 161	98.42 113	97.80 194	96.41 128	99.65 176	96.66 332	92.71 183	92.88 224	99.40 121	92.16 137	99.30 163	91.92 239	93.66 230	99.55 139

Test_1112_low_res		95.72 156	94.83 172	98.42 113	97.79 195	96.41 128	99.65 176	96.65 333	92.70 184	92.86 225	96.13 281	92.15 138	99.30 163	91.88 240	93.64 231	99.55 139

Effi-MVS+-dtu		94.53 190	95.30 158	92.22 319	97.77 196	82.54 359	99.59 186	97.06 297	94.92 101	95.29 195	95.37 310	85.81 219	97.89 253	94.80 187	97.07 175	96.23 248

tpm cat1		93.51 218	92.52 232	96.47 195	97.77 196	91.47 276	96.13 361	98.06 200	80.98 363	92.91 223	93.78 348	89.66 176	98.87 179	87.03 306	96.39 189	99.09 193

FA-MVS(test-final)		95.86 152	95.09 165	98.15 127	97.74 198	95.62 161	96.31 358	98.17 187	91.42 235	96.26 177	96.13 281	90.56 166	99.47 160	92.18 236	97.07 175	99.35 169

xiu_mvs_v1_base_debu		97.43 88	97.06 94	98.55 100	97.74 198	98.14 62	99.31 227	97.86 221	96.43 62	99.62 46	99.69 87	85.56 221	99.68 142	99.05 60	98.31 145	97.83 228

xiu_mvs_v1_base		97.43 88	97.06 94	98.55 100	97.74 198	98.14 62	99.31 227	97.86 221	96.43 62	99.62 46	99.69 87	85.56 221	99.68 142	99.05 60	98.31 145	97.83 228

xiu_mvs_v1_base_debi		97.43 88	97.06 94	98.55 100	97.74 198	98.14 62	99.31 227	97.86 221	96.43 62	99.62 46	99.69 87	85.56 221	99.68 142	99.05 60	98.31 145	97.83 228

EPP-MVSNet		96.69 124	96.60 112	96.96 182	97.74 198	93.05 234	99.37 220	98.56 91	88.75 289	95.83 187	99.01 152	96.01 32	98.56 199	96.92 153	97.20 173	99.25 182

gg-mvs-nofinetune		93.51 218	91.86 245	98.47 108	97.72 203	97.96 72	92.62 379	98.51 106	74.70 381	97.33 150	69.59 394	98.91 3	97.79 256	97.77 130	99.56 97	99.67 113

IB-MVS	92.85 6	94.99 175	93.94 192	98.16 124	97.72 203	95.69 159	99.99 4	98.81 60	94.28 127	92.70 226	96.90 255	95.08 51	99.17 169	96.07 163	73.88 365	99.60 129
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 93	97.02 99	98.59 97	97.71 205	97.52 87	99.97 27	98.54 100	91.83 219	97.45 148	99.04 149	97.50 9	99.10 172	94.75 189	96.37 190	99.16 187

Syy-MVS		90.00 297	90.63 263	88.11 353	97.68 206	74.66 381	99.71 165	98.35 161	90.79 252	92.10 234	98.67 186	79.10 282	93.09 373	63.35 387	95.95 198	96.59 244

myMVS_eth3d		94.46 192	94.76 174	93.55 297	97.68 206	90.97 280	99.71 165	98.35 161	90.79 252	92.10 234	98.67 186	92.46 131	93.09 373	87.13 303	95.95 198	96.59 244

test_fmvs1_n		94.25 200	94.36 180	93.92 283	97.68 206	83.70 354	99.90 87	96.57 336	97.40 28	99.67 38	98.88 172	61.82 370	99.92 88	98.23 104	99.13 124	98.14 225

diffmvs		97.00 109	96.64 110	98.09 129	97.64 209	96.17 143	99.81 134	97.19 281	94.67 111	98.95 91	99.28 129	86.43 214	98.76 186	98.37 99	97.42 168	99.33 172
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		95.72 156	95.15 163	97.45 164	97.62 210	94.28 201	99.28 233	98.24 179	94.27 129	96.84 161	98.94 168	79.39 277	98.76 186	93.25 221	98.49 140	99.30 176
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 103	96.72 108	98.22 122	97.60 211	96.70 119	99.92 78	98.54 100	91.11 243	97.07 155	98.97 159	97.47 12	99.03 173	93.73 216	96.09 193	98.92 199

miper_ehance_all_eth		93.16 225	92.60 227	94.82 246	97.57 212	93.56 221	99.50 202	97.07 296	88.75 289	88.85 288	95.52 300	90.97 158	96.74 312	90.77 258	84.45 301	94.17 285

testing3		93.92 204	94.23 184	92.99 311	97.54 213	90.23 298	99.99 4	99.16 30	90.57 256	91.33 243	98.63 192	92.99 112	92.52 377	82.46 336	95.39 212	96.22 249

LCM-MVSNet-Re		92.31 247	92.60 227	91.43 326	97.53 214	79.27 376	99.02 262	91.83 390	92.07 211	80.31 356	94.38 343	83.50 241	95.48 348	97.22 143	97.58 164	99.54 143

GBi-Net		90.88 274	89.82 280	94.08 275	97.53 214	91.97 257	98.43 308	96.95 309	87.05 313	89.68 265	94.72 331	71.34 335	96.11 336	87.01 307	85.65 290	94.17 285

test1		90.88 274	89.82 280	94.08 275	97.53 214	91.97 257	98.43 308	96.95 309	87.05 313	89.68 265	94.72 331	71.34 335	96.11 336	87.01 307	85.65 290	94.17 285

FMVSNet2		91.02 271	89.56 285	95.41 225	97.53 214	95.74 155	98.98 264	97.41 262	87.05 313	88.43 296	95.00 325	71.34 335	96.24 333	85.12 320	85.21 295	94.25 280

tttt0517		96.85 114	96.49 116	97.92 136	97.48 218	95.89 150	99.85 117	98.54 100	90.72 255	96.63 166	98.93 170	97.47 12	99.02 174	93.03 228	95.76 204	98.85 203

casdiffmvs_mvg		96.43 133	95.94 137	97.89 140	97.44 219	95.47 165	99.86 114	97.29 274	93.35 162	96.03 181	99.19 140	85.39 224	98.72 190	97.89 124	97.04 177	99.49 153
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 95	97.24 88	97.80 141	97.41 220	95.64 160	99.99 4	97.06 297	94.59 112	99.63 43	99.32 128	89.20 187	98.14 238	98.76 81	99.23 120	99.62 124

c3_l		92.53 242	91.87 244	94.52 258	97.40 221	92.99 236	99.40 213	96.93 314	87.86 303	88.69 291	95.44 304	89.95 174	96.44 324	90.45 264	80.69 332	94.14 294

fmvsm_s_conf0.1_n		97.30 96	97.21 90	97.60 158	97.38 222	94.40 199	99.90 87	98.64 76	96.47 61	99.51 61	99.65 98	84.99 229	99.93 85	99.22 55	99.09 126	98.46 217

CDS-MVSNet		96.34 138	96.07 125	97.13 178	97.37 223	94.96 184	99.53 197	97.91 216	91.55 227	95.37 194	98.32 212	95.05 53	97.13 287	93.80 212	95.75 205	99.30 176
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 121	96.26 121	98.16 124	97.36 224	96.48 125	99.96 34	98.29 174	91.93 216	95.77 188	98.07 218	95.54 42	98.29 227	90.55 262	98.89 130	99.70 108

miper_lstm_enhance		91.81 255	91.39 254	93.06 310	97.34 225	89.18 315	99.38 218	96.79 326	86.70 320	87.47 309	95.22 318	90.00 173	95.86 345	88.26 288	81.37 322	94.15 291

baseline		96.43 133	95.98 130	97.76 148	97.34 225	95.17 181	99.51 200	97.17 284	93.92 147	96.90 159	99.28 129	85.37 225	98.64 196	97.50 136	96.86 183	99.46 155

cl____		92.31 247	91.58 248	94.52 258	97.33 227	92.77 238	99.57 190	96.78 327	86.97 317	87.56 307	95.51 301	89.43 180	96.62 317	88.60 283	82.44 314	94.16 290

DIV-MVS_self_test		92.32 246	91.60 247	94.47 262	97.31 228	92.74 240	99.58 188	96.75 328	86.99 316	87.64 305	95.54 298	89.55 179	96.50 321	88.58 284	82.44 314	94.17 285

casdiffmvs		96.42 135	95.97 133	97.77 146	97.30 229	94.98 183	99.84 122	97.09 294	93.75 153	96.58 168	99.26 135	85.07 227	98.78 184	97.77 130	97.04 177	99.54 143
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		94.36 197	93.48 205	96.99 181	97.29 230	93.54 222	99.96 34	96.72 330	88.35 298	93.43 215	98.94 168	82.05 248	98.05 244	88.12 292	96.48 188	99.37 166

eth_miper_zixun_eth		92.41 245	91.93 242	93.84 287	97.28 231	90.68 288	98.83 282	96.97 308	88.57 294	89.19 282	95.73 291	89.24 186	96.69 315	89.97 273	81.55 320	94.15 291

MVSFormer		96.94 111	96.60 112	97.95 134	97.28 231	97.70 81	99.55 194	97.27 276	91.17 240	99.43 66	99.54 110	90.92 159	96.89 305	94.67 192	99.62 89	99.25 182

lupinMVS		97.85 69	97.60 76	98.62 93	97.28 231	97.70 81	99.99 4	97.55 245	95.50 89	99.43 66	99.67 94	90.92 159	98.71 191	98.40 97	99.62 89	99.45 157

SCA		94.69 183	93.81 196	97.33 174	97.10 234	94.44 194	98.86 279	98.32 168	93.30 165	96.17 180	95.59 296	76.48 304	97.95 250	91.06 250	97.43 166	99.59 130

TAMVS		95.85 153	95.58 150	96.65 193	97.07 235	93.50 223	99.17 242	97.82 225	91.39 237	95.02 198	98.01 219	92.20 136	97.30 276	93.75 215	95.83 202	99.14 190

Fast-Effi-MVS+-dtu		93.72 213	93.86 195	93.29 302	97.06 236	86.16 340	99.80 138	96.83 322	92.66 187	92.58 228	97.83 229	81.39 255	97.67 261	89.75 275	96.87 182	96.05 251

CostFormer		96.10 145	95.88 142	96.78 187	97.03 237	92.55 248	97.08 345	97.83 224	90.04 267	98.72 106	94.89 329	95.01 55	98.29 227	96.54 158	95.77 203	99.50 151

test_fmvsmvis_n_1920		97.67 83	97.59 78	97.91 138	97.02 238	95.34 171	99.95 52	98.45 117	97.87 15	97.02 156	99.59 104	89.64 177	99.98 43	99.41 48	99.34 115	98.42 218

test-LLR		96.47 131	96.04 126	97.78 144	97.02 238	95.44 166	99.96 34	98.21 182	94.07 136	95.55 190	96.38 272	93.90 88	98.27 231	90.42 265	98.83 134	99.64 119

test-mter		96.39 136	95.93 138	97.78 144	97.02 238	95.44 166	99.96 34	98.21 182	91.81 221	95.55 190	96.38 272	95.17 48	98.27 231	90.42 265	98.83 134	99.64 119

gm-plane-assit					96.97 241	93.76 216			91.47 231		98.96 161		98.79 183	94.92 182

WB-MVSnew		92.90 232	92.77 224	93.26 304	96.95 242	93.63 219	99.71 165	98.16 191	91.49 228	94.28 207	98.14 215	81.33 257	96.48 322	79.47 351	95.46 209	89.68 374

QAPM		95.40 167	94.17 186	99.10 64	96.92 243	97.71 79	99.40 213	98.68 70	89.31 274	88.94 286	98.89 171	82.48 246	99.96 61	93.12 227	99.83 72	99.62 124

KD-MVS_2432*1600		88.00 316	86.10 320	93.70 293	96.91 244	94.04 208	97.17 342	97.12 290	84.93 340	81.96 347	92.41 359	92.48 129	94.51 361	79.23 352	52.68 393	92.56 348

miper_refine_blended		88.00 316	86.10 320	93.70 293	96.91 244	94.04 208	97.17 342	97.12 290	84.93 340	81.96 347	92.41 359	92.48 129	94.51 361	79.23 352	52.68 393	92.56 348

tpm2		95.47 165	95.18 162	96.35 203	96.91 244	91.70 270	96.96 348	97.93 212	88.04 302	98.44 118	95.40 306	93.32 102	97.97 247	94.00 203	95.61 207	99.38 164

FMVSNet5		88.32 313	87.47 315	90.88 329	96.90 247	88.39 326	97.28 339	95.68 356	82.60 357	84.67 336	92.40 361	79.83 274	91.16 382	76.39 366	81.51 321	93.09 340

3Dnovator+	91.53 11	96.31 140	95.24 159	99.52 28	96.88 248	98.64 52	99.72 163	98.24 179	95.27 94	88.42 298	98.98 157	82.76 245	99.94 77	97.10 146	99.83 72	99.96 64

Patchmatch-test		92.65 241	91.50 251	96.10 209	96.85 249	90.49 293	91.50 384	97.19 281	82.76 356	90.23 253	95.59 296	95.02 54	98.00 246	77.41 361	96.98 180	99.82 92

MVS		96.60 127	95.56 151	99.72 13	96.85 249	99.22 20	98.31 314	98.94 41	91.57 226	90.90 247	99.61 103	86.66 212	99.96 61	97.36 138	99.88 68	99.99 23

3Dnovator	91.47 12	96.28 143	95.34 156	99.08 65	96.82 251	97.47 93	99.45 210	98.81 60	95.52 88	89.39 273	99.00 154	81.97 249	99.95 69	97.27 140	99.83 72	99.84 90

EI-MVSNet		93.73 212	93.40 210	94.74 247	96.80 252	92.69 243	99.06 254	97.67 232	88.96 283	91.39 240	99.02 150	88.75 192	97.30 276	91.07 249	87.85 274	94.22 281

CVMVSNet		94.68 185	94.94 170	93.89 286	96.80 252	86.92 338	99.06 254	98.98 38	94.45 115	94.23 209	99.02 150	85.60 220	95.31 352	90.91 255	95.39 212	99.43 160

IterMVS-LS		92.69 239	92.11 237	94.43 266	96.80 252	92.74 240	99.45 210	96.89 317	88.98 281	89.65 268	95.38 309	88.77 191	96.34 328	90.98 253	82.04 317	94.22 281
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS		90.91 273	90.17 275	93.12 307	96.78 255	90.42 296	98.89 273	97.05 299	89.03 278	86.49 322	95.42 305	76.59 302	95.02 354	87.22 302	84.09 304	93.93 312
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 115	95.96 134	99.48 34	96.74 256	98.52 56	98.31 314	98.86 53	95.82 78	89.91 259	98.98 157	87.49 201	99.96 61	97.80 125	99.73 82	99.96 64

IterMVS-SCA-FT		90.85 276	90.16 276	92.93 312	96.72 257	89.96 305	98.89 273	96.99 304	88.95 284	86.63 319	95.67 292	76.48 304	95.00 355	87.04 305	84.04 307	93.84 319

MVS-HIRNet		86.22 323	83.19 336	95.31 229	96.71 258	90.29 297	92.12 381	97.33 269	62.85 388	86.82 316	70.37 393	69.37 343	97.49 266	75.12 368	97.99 158	98.15 223

VDDNet		93.12 227	91.91 243	96.76 188	96.67 259	92.65 246	98.69 295	98.21 182	82.81 355	97.75 142	99.28 129	61.57 371	99.48 159	98.09 112	94.09 227	98.15 223

dmvs_re		93.20 224	93.15 215	93.34 300	96.54 260	83.81 353	98.71 292	98.51 106	91.39 237	92.37 232	98.56 199	78.66 286	97.83 255	93.89 206	89.74 243	98.38 219

MIMVSNet		90.30 289	88.67 303	95.17 234	96.45 261	91.64 272	92.39 380	97.15 287	85.99 327	90.50 250	93.19 355	66.95 353	94.86 358	82.01 340	93.43 232	99.01 198

CR-MVSNet		93.45 221	92.62 226	95.94 211	96.29 262	92.66 244	92.01 382	96.23 345	92.62 189	96.94 157	93.31 353	91.04 156	96.03 341	79.23 352	95.96 196	99.13 191

RPMNet		89.76 301	87.28 316	97.19 177	96.29 262	92.66 244	92.01 382	98.31 170	70.19 387	96.94 157	85.87 386	87.25 205	99.78 125	62.69 388	95.96 196	99.13 191

tt0805		91.28 266	90.18 274	94.60 253	96.26 264	87.55 332	98.39 312	98.72 65	89.00 280	89.22 279	98.47 207	62.98 367	98.96 176	90.57 261	88.00 273	97.28 239

Patchmtry		89.70 302	88.49 305	93.33 301	96.24 265	89.94 308	91.37 385	96.23 345	78.22 371	87.69 304	93.31 353	91.04 156	96.03 341	80.18 350	82.10 316	94.02 302

test_vis1_rt		86.87 321	86.05 323	89.34 342	96.12 266	78.07 377	99.87 101	83.54 401	92.03 214	78.21 366	89.51 372	45.80 387	99.91 89	96.25 161	93.11 237	90.03 371

JIA-IIPM		91.76 261	90.70 261	94.94 240	96.11 267	87.51 333	93.16 378	98.13 196	75.79 377	97.58 144	77.68 391	92.84 117	97.97 247	88.47 287	96.54 185	99.33 172

OpenMVS	90.15 15	94.77 181	93.59 201	98.33 117	96.07 268	97.48 92	99.56 192	98.57 88	90.46 258	86.51 321	98.95 166	78.57 287	99.94 77	93.86 207	99.74 81	97.57 237

PAPM		98.60 30	98.42 31	99.14 59	96.05 269	98.96 26	99.90 87	99.35 25	96.68 55	98.35 123	99.66 96	96.45 29	98.51 202	99.45 45	99.89 66	99.96 64

CLD-MVS		94.06 203	93.90 193	94.55 257	96.02 270	90.69 287	99.98 14	97.72 228	96.62 58	91.05 246	98.85 180	77.21 293	98.47 203	98.11 110	89.51 249	94.48 258
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 286	88.75 302	95.25 231	95.99 271	90.16 300	91.22 386	97.54 247	76.80 373	97.26 151	86.01 385	91.88 143	96.07 340	66.16 384	95.91 200	99.51 149

ACMH+	89.98 16	90.35 287	89.54 286	92.78 315	95.99 271	86.12 341	98.81 284	97.18 283	89.38 273	83.14 343	97.76 231	68.42 348	98.43 208	89.11 279	86.05 288	93.78 322

DeepMVS_CX				82.92 363	95.98 273	58.66 394		96.01 350	92.72 182	78.34 365	95.51 301	58.29 376	98.08 241	82.57 335	85.29 293	92.03 356

ACMP	92.05 9	92.74 236	92.42 234	93.73 289	95.91 274	88.72 319	99.81 134	97.53 249	94.13 132	87.00 315	98.23 213	74.07 325	98.47 203	96.22 162	88.86 256	93.99 307
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 216	93.03 217	95.35 226	95.86 275	86.94 337	99.87 101	96.36 343	96.85 46	99.54 56	98.79 182	52.41 383	99.83 118	98.64 89	98.97 129	99.29 178

HQP-NCC					95.78 276		99.87 101		96.82 48	93.37 216

ACMP_Plane					95.78 276		99.87 101		96.82 48	93.37 216

HQP-MVS		94.61 187	94.50 178	94.92 241	95.78 276	91.85 262	99.87 101	97.89 217	96.82 48	93.37 216	98.65 189	80.65 266	98.39 214	97.92 121	89.60 244	94.53 254

NP-MVS					95.77 279	91.79 264					98.65 189

test_fmvsmconf0.1_n		97.74 79	97.44 81	98.64 92	95.76 280	96.20 140	99.94 68	98.05 202	98.17 8	98.89 95	99.42 118	87.65 199	99.90 91	99.50 41	99.60 95	99.82 92

plane_prior6					95.76 280	91.72 269						80.47 270

ACMM	91.95 10	92.88 233	92.52 232	93.98 282	95.75 282	89.08 316	99.77 144	97.52 251	93.00 172	89.95 258	97.99 222	76.17 308	98.46 206	93.63 218	88.87 255	94.39 269
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 206	92.84 220	96.80 186	95.73 283	93.57 220	99.88 98	97.24 279	92.57 194	92.92 222	96.66 264	78.73 285	97.67 261	87.75 295	94.06 228	99.17 186

plane_prior1					95.73 283

jason		97.24 99	96.86 102	98.38 116	95.73 283	97.32 97	99.97 27	97.40 263	95.34 92	98.60 113	99.54 110	87.70 198	98.56 199	97.94 120	99.47 104	99.25 182
jason: jason.
HQP_MVS		94.49 191	94.36 180	94.87 242	95.71 286	91.74 266	99.84 122	97.87 219	96.38 65	93.01 220	98.59 194	80.47 270	98.37 220	97.79 128	89.55 247	94.52 256

plane_prior7					95.71 286	91.59 274

ITE_SJBPF				92.38 317	95.69 288	85.14 346		95.71 355	92.81 178	89.33 276	98.11 216	70.23 341	98.42 209	85.91 316	88.16 270	93.59 330

fmvsm_s_conf0.1_n_a		97.09 105	96.90 101	97.63 156	95.65 289	94.21 204	99.83 129	98.50 111	96.27 70	99.65 40	99.64 99	84.72 230	99.93 85	99.04 63	98.84 133	98.74 210

ACMH	89.72 17	90.64 280	89.63 283	93.66 295	95.64 290	88.64 322	98.55 301	97.45 256	89.03 278	81.62 350	97.61 233	69.75 342	98.41 210	89.37 276	87.62 279	93.92 313
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 123	96.49 116	97.37 170	95.63 291	95.96 148	99.74 155	98.88 51	92.94 173	91.61 238	98.97 159	97.72 7	98.62 197	94.83 186	98.08 156	97.53 238

FMVSNet1		88.50 312	86.64 318	94.08 275	95.62 292	91.97 257	98.43 308	96.95 309	83.00 353	86.08 329	94.72 331	59.09 375	96.11 336	81.82 342	84.07 305	94.17 285

LPG-MVS_test		92.96 230	92.71 225	93.71 291	95.43 293	88.67 320	99.75 152	97.62 236	92.81 178	90.05 254	98.49 203	75.24 315	98.40 212	95.84 168	89.12 251	94.07 299

LGP-MVS_train				93.71 291	95.43 293	88.67 320		97.62 236	92.81 178	90.05 254	98.49 203	75.24 315	98.40 212	95.84 168	89.12 251	94.07 299

tpm		93.70 214	93.41 209	94.58 255	95.36 295	87.41 334	97.01 346	96.90 316	90.85 250	96.72 165	94.14 345	90.40 169	96.84 308	90.75 259	88.54 263	99.51 149

D2MVS		92.76 235	92.59 230	93.27 303	95.13 296	89.54 312	99.69 169	99.38 23	92.26 207	87.59 306	94.61 337	85.05 228	97.79 256	91.59 243	88.01 272	92.47 351

VPA-MVSNet		92.70 238	91.55 250	96.16 207	95.09 297	96.20 140	98.88 275	99.00 36	91.02 247	91.82 237	95.29 316	76.05 310	97.96 249	95.62 172	81.19 323	94.30 276

LTVRE_ROB	88.28 18	90.29 290	89.05 297	94.02 278	95.08 298	90.15 301	97.19 341	97.43 258	84.91 342	83.99 339	97.06 250	74.00 326	98.28 229	84.08 325	87.71 277	93.62 329
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		87.87 318	86.51 319	91.94 322	95.05 299	85.57 344	97.65 334	94.08 378	84.40 345	81.82 349	96.85 259	62.14 369	98.33 223	80.25 349	86.37 287	91.91 358

test0.0.03 1		93.86 205	93.61 198	94.64 251	95.02 300	92.18 255	99.93 75	98.58 86	94.07 136	87.96 302	98.50 202	93.90 88	94.96 356	81.33 343	93.17 235	96.78 241

UniMVSNet (Re)		93.07 229	92.13 236	95.88 212	94.84 301	96.24 139	99.88 98	98.98 38	92.49 200	89.25 277	95.40 306	87.09 207	97.14 286	93.13 226	78.16 346	94.26 278

USDC		90.00 297	88.96 298	93.10 309	94.81 302	88.16 328	98.71 292	95.54 360	93.66 155	83.75 341	97.20 244	65.58 358	98.31 225	83.96 328	87.49 281	92.85 345

VPNet		91.81 255	90.46 265	95.85 214	94.74 303	95.54 164	98.98 264	98.59 85	92.14 209	90.77 249	97.44 237	68.73 346	97.54 265	94.89 185	77.89 348	94.46 260

FIs		94.10 201	93.43 206	96.11 208	94.70 304	96.82 116	99.58 188	98.93 45	92.54 195	89.34 275	97.31 241	87.62 200	97.10 290	94.22 202	86.58 285	94.40 267

UniMVSNet_ETH3D		90.06 296	88.58 304	94.49 261	94.67 305	88.09 329	97.81 333	97.57 244	83.91 348	88.44 294	97.41 238	57.44 377	97.62 263	91.41 244	88.59 262	97.77 231

UniMVSNet_NR-MVSNet		92.95 231	92.11 237	95.49 220	94.61 306	95.28 174	99.83 129	99.08 33	91.49 228	89.21 280	96.86 258	87.14 206	96.73 313	93.20 222	77.52 351	94.46 260

test_fmvs2		89.47 305	89.70 282	88.77 349	94.54 307	75.74 378	99.83 129	94.70 374	94.71 108	91.08 244	96.82 263	54.46 380	97.78 258	92.87 229	88.27 268	92.80 346

WR-MVS		92.31 247	91.25 255	95.48 223	94.45 308	95.29 173	99.60 185	98.68 70	90.10 264	88.07 301	96.89 256	80.68 265	96.80 311	93.14 225	79.67 339	94.36 271

nrg030		93.51 218	92.53 231	96.45 197	94.36 309	97.20 100	99.81 134	97.16 286	91.60 225	89.86 261	97.46 236	86.37 215	97.68 260	95.88 167	80.31 335	94.46 260

tfpnnormal		89.29 308	87.61 314	94.34 269	94.35 310	94.13 206	98.95 268	98.94 41	83.94 346	84.47 337	95.51 301	74.84 320	97.39 268	77.05 364	80.41 333	91.48 361

FC-MVSNet-test		93.81 208	93.15 215	95.80 216	94.30 311	96.20 140	99.42 212	98.89 49	92.33 206	89.03 285	97.27 243	87.39 203	96.83 309	93.20 222	86.48 286	94.36 271

MS-PatchMatch		90.65 279	90.30 270	91.71 325	94.22 312	85.50 345	98.24 317	97.70 229	88.67 291	86.42 324	96.37 274	67.82 350	98.03 245	83.62 330	99.62 89	91.60 359

WR-MVS_H		91.30 264	90.35 268	94.15 272	94.17 313	92.62 247	99.17 242	98.94 41	88.87 287	86.48 323	94.46 342	84.36 234	96.61 318	88.19 289	78.51 344	93.21 339

DU-MVS		92.46 244	91.45 253	95.49 220	94.05 314	95.28 174	99.81 134	98.74 64	92.25 208	89.21 280	96.64 266	81.66 252	96.73 313	93.20 222	77.52 351	94.46 260

NR-MVSNet		91.56 263	90.22 272	95.60 218	94.05 314	95.76 154	98.25 316	98.70 67	91.16 242	80.78 355	96.64 266	83.23 244	96.57 319	91.41 244	77.73 350	94.46 260

CP-MVSNet		91.23 268	90.22 272	94.26 270	93.96 316	92.39 251	99.09 247	98.57 88	88.95 284	86.42 324	96.57 269	79.19 280	96.37 326	90.29 268	78.95 341	94.02 302

XXY-MVS		91.82 254	90.46 265	95.88 212	93.91 317	95.40 170	98.87 278	97.69 230	88.63 293	87.87 303	97.08 248	74.38 324	97.89 253	91.66 242	84.07 305	94.35 274

PS-CasMVS		90.63 281	89.51 288	93.99 281	93.83 318	91.70 270	98.98 264	98.52 103	88.48 295	86.15 328	96.53 271	75.46 313	96.31 330	88.83 281	78.86 343	93.95 310

test_0402		85.58 325	83.94 330	90.50 333	93.81 319	85.04 347	98.55 301	95.20 368	76.01 375	79.72 360	95.13 319	64.15 364	96.26 332	66.04 385	86.88 284	90.21 370

XVG-ACMP-BASELINE		91.22 269	90.75 260	92.63 316	93.73 320	85.61 343	98.52 305	97.44 257	92.77 181	89.90 260	96.85 259	66.64 355	98.39 214	92.29 234	88.61 260	93.89 315

TranMVSNet+NR-MVSNet		91.68 262	90.61 264	94.87 242	93.69 321	93.98 211	99.69 169	98.65 74	91.03 246	88.44 294	96.83 262	80.05 273	96.18 334	90.26 269	76.89 359	94.45 265

mvsmamba		94.10 201	93.72 197	95.25 231	93.57 322	94.13 206	99.67 173	96.45 341	93.63 157	91.34 242	97.77 230	86.29 216	97.22 282	96.65 157	88.10 271	94.40 267

TransMVSNet (Re)		87.25 319	85.28 326	93.16 306	93.56 323	91.03 279	98.54 303	94.05 380	83.69 350	81.09 353	96.16 279	75.32 314	96.40 325	76.69 365	68.41 377	92.06 355

v10		90.25 291	88.82 300	94.57 256	93.53 324	93.43 226	99.08 249	96.87 319	85.00 339	87.34 313	94.51 338	80.93 262	97.02 300	82.85 334	79.23 340	93.26 337

testgi		89.01 310	88.04 311	91.90 323	93.49 325	84.89 349	99.73 160	95.66 357	93.89 150	85.14 334	98.17 214	59.68 374	94.66 360	77.73 360	88.88 254	96.16 250

v8		90.54 283	89.17 293	94.66 250	93.43 326	93.40 228	99.20 239	96.94 313	85.76 330	87.56 307	94.51 338	81.96 250	97.19 283	84.94 322	78.25 345	93.38 335

V42		91.28 266	90.12 277	94.74 247	93.42 327	93.46 224	99.68 171	97.02 301	87.36 309	89.85 263	95.05 321	81.31 258	97.34 271	87.34 300	80.07 337	93.40 333

pm-mvs1		89.36 307	87.81 313	94.01 279	93.40 328	91.93 260	98.62 300	96.48 340	86.25 325	83.86 340	96.14 280	73.68 327	97.04 295	86.16 313	75.73 363	93.04 342

RRT_MVS		93.14 226	92.92 219	93.78 288	93.31 329	90.04 303	99.66 174	97.69 230	92.53 196	88.91 287	97.76 231	84.36 234	96.93 303	95.10 177	86.99 283	94.37 270

v1144		91.09 270	89.83 279	94.87 242	93.25 330	93.69 218	99.62 183	96.98 306	86.83 319	89.64 269	94.99 326	80.94 261	97.05 293	85.08 321	81.16 324	93.87 317

v1192		90.62 282	89.25 292	94.72 249	93.13 331	93.07 232	99.50 202	97.02 301	86.33 324	89.56 271	95.01 323	79.22 279	97.09 292	82.34 338	81.16 324	94.01 304

v2v482		91.30 264	90.07 278	95.01 237	93.13 331	93.79 214	99.77 144	97.02 301	88.05 301	89.25 277	95.37 310	80.73 264	97.15 285	87.28 301	80.04 338	94.09 298

OPM-MVS		93.21 223	92.80 222	94.44 264	93.12 333	90.85 286	99.77 144	97.61 239	96.19 73	91.56 239	98.65 189	75.16 319	98.47 203	93.78 214	89.39 250	93.99 307
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 277	89.52 287	94.59 254	93.11 334	92.77 238	99.56 192	96.99 304	86.38 323	89.82 264	94.95 328	80.50 269	97.10 290	83.98 327	80.41 333	93.90 314

bld_raw_dy_0_64		92.74 236	92.03 240	94.87 242	93.09 335	93.46 224	99.12 244	95.41 362	92.84 177	90.44 252	97.54 234	78.08 291	97.04 295	93.94 204	87.77 276	94.11 296

PEN-MVS		90.19 293	89.06 296	93.57 296	93.06 336	90.90 284	99.06 254	98.47 114	88.11 300	85.91 330	96.30 275	76.67 300	95.94 344	87.07 304	76.91 358	93.89 315

v1240		90.20 292	88.79 301	94.44 264	93.05 337	92.27 253	99.38 218	96.92 315	85.89 328	89.36 274	94.87 330	77.89 292	97.03 298	80.66 346	81.08 327	94.01 304

v148		90.70 278	89.63 283	93.92 283	92.97 338	90.97 280	99.75 152	96.89 317	87.51 306	88.27 299	95.01 323	81.67 251	97.04 295	87.40 299	77.17 356	93.75 323

v1921920		90.46 284	89.12 294	94.50 260	92.96 339	92.46 249	99.49 204	96.98 306	86.10 326	89.61 270	95.30 313	78.55 288	97.03 298	82.17 339	80.89 331	94.01 304

Baseline_NR-MVSNet		90.33 288	89.51 288	92.81 314	92.84 340	89.95 306	99.77 144	93.94 381	84.69 344	89.04 284	95.66 293	81.66 252	96.52 320	90.99 252	76.98 357	91.97 357

test_method		80.79 345	79.70 349	84.08 360	92.83 341	67.06 386	99.51 200	95.42 361	54.34 392	81.07 354	93.53 350	44.48 388	92.22 379	78.90 356	77.23 355	92.94 343

pmmvs4		92.10 251	91.07 258	95.18 233	92.82 342	94.96 184	99.48 206	96.83 322	87.45 308	88.66 292	96.56 270	83.78 239	96.83 309	89.29 277	84.77 299	93.75 323

LF4IMVS		89.25 309	88.85 299	90.45 335	92.81 343	81.19 369	98.12 323	94.79 371	91.44 232	86.29 326	97.11 246	65.30 361	98.11 240	88.53 286	85.25 294	92.07 354

DTE-MVSNet		89.40 306	88.24 309	92.88 313	92.66 344	89.95 306	99.10 246	98.22 181	87.29 310	85.12 335	96.22 277	76.27 307	95.30 353	83.56 331	75.74 362	93.41 332

EU-MVSNet		90.14 295	90.34 269	89.54 341	92.55 345	81.06 370	98.69 295	98.04 203	91.41 236	86.59 320	96.84 261	80.83 263	93.31 372	86.20 312	81.91 318	94.26 278

APD_test1		81.15 344	80.92 345	81.86 364	92.45 346	59.76 393	96.04 364	93.61 384	73.29 384	77.06 369	96.64 266	44.28 389	96.16 335	72.35 372	82.52 312	89.67 375

our_test_3		90.39 285	89.48 290	93.12 307	92.40 347	89.57 311	99.33 224	96.35 344	87.84 304	85.30 333	94.99 326	84.14 237	96.09 339	80.38 347	84.56 300	93.71 328

ppachtmachnet_test		89.58 304	88.35 307	93.25 305	92.40 347	90.44 295	99.33 224	96.73 329	85.49 335	85.90 331	95.77 288	81.09 260	96.00 343	76.00 367	82.49 313	93.30 336

v7n		89.65 303	88.29 308	93.72 290	92.22 349	90.56 292	99.07 253	97.10 292	85.42 337	86.73 317	94.72 331	80.06 272	97.13 287	81.14 344	78.12 347	93.49 331

dmvs_testset		83.79 338	86.07 322	76.94 368	92.14 350	48.60 403	96.75 351	90.27 393	89.48 272	78.65 363	98.55 201	79.25 278	86.65 391	66.85 382	82.69 311	95.57 252

PS-MVSNAJss		93.64 215	93.31 212	94.61 252	92.11 351	92.19 254	99.12 244	97.38 264	92.51 199	88.45 293	96.99 254	91.20 151	97.29 279	94.36 197	87.71 277	94.36 271

pmmvs5		90.17 294	89.09 295	93.40 299	92.10 352	89.77 309	99.74 155	95.58 359	85.88 329	87.24 314	95.74 289	73.41 328	96.48 322	88.54 285	83.56 308	93.95 310

N_pmnet		80.06 348	80.78 346	77.89 367	91.94 353	45.28 405	98.80 286	56.82 407	78.10 372	80.08 358	93.33 351	77.03 295	95.76 346	68.14 380	82.81 310	92.64 347

test_djsdf		92.83 234	92.29 235	94.47 262	91.90 354	92.46 249	99.55 194	97.27 276	91.17 240	89.96 257	96.07 284	81.10 259	96.89 305	94.67 192	88.91 253	94.05 301

SixPastTwentyTwo		88.73 311	88.01 312	90.88 329	91.85 355	82.24 361	98.22 320	95.18 369	88.97 282	82.26 346	96.89 256	71.75 333	96.67 316	84.00 326	82.98 309	93.72 327

K. test v3		88.05 315	87.24 317	90.47 334	91.82 356	82.23 362	98.96 267	97.42 260	89.05 277	76.93 371	95.60 295	68.49 347	95.42 349	85.87 317	81.01 329	93.75 323

OurMVSNet-221017-0		89.81 300	89.48 290	90.83 331	91.64 357	81.21 368	98.17 322	95.38 364	91.48 230	85.65 332	97.31 241	72.66 329	97.29 279	88.15 290	84.83 298	93.97 309

mvs_tets		91.81 255	91.08 257	94.00 280	91.63 358	90.58 291	98.67 297	97.43 258	92.43 201	87.37 312	97.05 251	71.76 332	97.32 275	94.75 189	88.68 259	94.11 296

Gipuma		66.95 361	65.00 361	72.79 373	91.52 359	67.96 385	66.16 396	95.15 370	47.89 394	58.54 391	67.99 396	29.74 393	87.54 390	50.20 395	77.83 349	62.87 396
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 136	95.74 145	98.32 118	91.47 360	95.56 163	99.84 122	97.30 272	97.74 18	97.89 138	99.35 127	79.62 275	99.85 108	99.25 54	99.24 119	99.55 139

jajsoiax		91.92 253	91.18 256	94.15 272	91.35 361	90.95 283	99.00 263	97.42 260	92.61 190	87.38 311	97.08 248	72.46 330	97.36 269	94.53 195	88.77 257	94.13 295

MDA-MVSNet-bldmvs		84.09 336	81.52 343	91.81 324	91.32 362	88.00 331	98.67 297	95.92 352	80.22 366	55.60 394	93.32 352	68.29 349	93.60 370	73.76 369	76.61 360	93.82 321

MVP-Stereo		90.93 272	90.45 267	92.37 318	91.25 363	88.76 317	98.05 327	96.17 347	87.27 311	84.04 338	95.30 313	78.46 289	97.27 281	83.78 329	99.70 84	91.09 362
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 327	83.32 335	92.10 320	90.96 364	88.58 323	99.20 239	96.52 338	79.70 368	57.12 393	92.69 357	79.11 281	93.86 367	77.10 363	77.46 353	93.86 318

YYNet1		85.50 328	83.33 334	92.00 321	90.89 365	88.38 327	99.22 238	96.55 337	79.60 369	57.26 392	92.72 356	79.09 283	93.78 368	77.25 362	77.37 354	93.84 319

anonymousdsp		91.79 260	90.92 259	94.41 267	90.76 366	92.93 237	98.93 270	97.17 284	89.08 276	87.46 310	95.30 313	78.43 290	96.92 304	92.38 233	88.73 258	93.39 334

lessismore_v0				90.53 332	90.58 367	80.90 371		95.80 353		77.01 370	95.84 286	66.15 357	96.95 301	83.03 333	75.05 364	93.74 326

EG-PatchMatch MVS		85.35 329	83.81 332	89.99 339	90.39 368	81.89 364	98.21 321	96.09 349	81.78 360	74.73 377	93.72 349	51.56 385	97.12 289	79.16 355	88.61 260	90.96 364

EGC-MVSNET		69.38 354	63.76 364	86.26 357	90.32 369	81.66 367	96.24 360	93.85 382	0.99 404	3.22 405	92.33 362	52.44 382	92.92 375	59.53 391	84.90 297	84.21 385

CMPMVS	61.59 21	84.75 332	85.14 327	83.57 361	90.32 369	62.54 389	96.98 347	97.59 243	74.33 382	69.95 383	96.66 264	64.17 363	98.32 224	87.88 294	88.41 265	89.84 373
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 335	82.92 338	89.21 343	90.03 371	82.60 358	96.89 350	95.62 358	80.59 364	75.77 376	89.17 373	65.04 362	94.79 359	72.12 373	81.02 328	90.23 369

pmmvs6		85.69 324	83.84 331	91.26 328	90.00 372	84.41 351	97.82 332	96.15 348	75.86 376	81.29 352	95.39 308	61.21 372	96.87 307	83.52 332	73.29 366	92.50 350

DSMNet-mixed		88.28 314	88.24 309	88.42 351	89.64 373	75.38 380	98.06 326	89.86 394	85.59 334	88.20 300	92.14 363	76.15 309	91.95 380	78.46 357	96.05 194	97.92 227

UnsupCasMVSNet_eth		85.52 326	83.99 328	90.10 337	89.36 374	83.51 355	96.65 352	97.99 205	89.14 275	75.89 375	93.83 347	63.25 366	93.92 365	81.92 341	67.90 380	92.88 344

Anonymous20231206		86.32 322	85.42 325	89.02 345	89.11 375	80.53 374	99.05 258	95.28 365	85.43 336	82.82 344	93.92 346	74.40 323	93.44 371	66.99 381	81.83 319	93.08 341

Anonymous20240521		85.15 330	83.81 332	89.16 344	88.32 376	82.69 357	98.80 286	95.74 354	79.72 367	81.53 351	90.99 366	65.38 360	94.16 363	72.69 371	81.11 326	90.63 367

OpenMVS_ROB	79.82 20	83.77 339	81.68 342	90.03 338	88.30 377	82.82 356	98.46 306	95.22 367	73.92 383	76.00 374	91.29 365	55.00 379	96.94 302	68.40 379	88.51 264	90.34 368

test20.03		84.72 333	83.99 328	86.91 355	88.19 378	80.62 373	98.88 275	95.94 351	88.36 297	78.87 361	94.62 336	68.75 345	89.11 386	66.52 383	75.82 361	91.00 363

KD-MVS_self_test		83.59 340	82.06 340	88.20 352	86.93 379	80.70 372	97.21 340	96.38 342	82.87 354	82.49 345	88.97 374	67.63 351	92.32 378	73.75 370	62.30 389	91.58 360

MIMVSNet1		82.58 341	80.51 347	88.78 347	86.68 380	84.20 352	96.65 352	95.41 362	78.75 370	78.59 364	92.44 358	51.88 384	89.76 385	65.26 386	78.95 341	92.38 353

CL-MVSNet_self_test		84.50 334	83.15 337	88.53 350	86.00 381	81.79 365	98.82 283	97.35 266	85.12 338	83.62 342	90.91 368	76.66 301	91.40 381	69.53 377	60.36 390	92.40 352

UnsupCasMVSNet_bld		79.97 350	77.03 355	88.78 347	85.62 382	81.98 363	93.66 376	97.35 266	75.51 379	70.79 382	83.05 388	48.70 386	94.91 357	78.31 358	60.29 391	89.46 378

Patchmatch-RL test		86.90 320	85.98 324	89.67 340	84.45 383	75.59 379	89.71 389	92.43 387	86.89 318	77.83 368	90.94 367	94.22 77	93.63 369	87.75 295	69.61 372	99.79 97

pmmvs-eth3d		84.03 337	81.97 341	90.20 336	84.15 384	87.09 336	98.10 325	94.73 373	83.05 352	74.10 379	87.77 380	65.56 359	94.01 364	81.08 345	69.24 374	89.49 377

test_fmvs3		79.99 349	80.17 348	79.45 366	84.02 385	62.83 387	99.05 258	93.49 385	88.29 299	80.06 359	86.65 383	28.09 395	88.00 387	88.63 282	73.27 367	87.54 383

PM-MVS		80.47 346	78.88 351	85.26 358	83.79 386	72.22 382	95.89 367	91.08 391	85.71 333	76.56 373	88.30 376	36.64 391	93.90 366	82.39 337	69.57 373	89.66 376

new-patchmatchnet		81.19 343	79.34 350	86.76 356	82.86 387	80.36 375	97.92 329	95.27 366	82.09 359	72.02 380	86.87 382	62.81 368	90.74 384	71.10 374	63.08 387	89.19 380

mvsany_test3		82.12 342	81.14 344	85.06 359	81.87 388	70.41 383	97.09 344	92.14 388	91.27 239	77.84 367	88.73 375	39.31 390	95.49 347	90.75 259	71.24 369	89.29 379

WB-MVS		76.28 352	77.28 354	73.29 372	81.18 389	54.68 397	97.87 331	94.19 377	81.30 361	69.43 384	90.70 369	77.02 296	82.06 395	35.71 400	68.11 379	83.13 386

test_f		78.40 351	77.59 353	80.81 365	80.82 390	62.48 390	96.96 348	93.08 386	83.44 351	74.57 378	84.57 387	27.95 396	92.63 376	84.15 324	72.79 368	87.32 384

SSC-MVS		75.42 353	76.40 356	72.49 376	80.68 391	53.62 398	97.42 336	94.06 379	80.42 365	68.75 385	90.14 371	76.54 303	81.66 396	33.25 401	66.34 383	82.19 387

pmmvs3		80.27 347	77.77 352	87.76 354	80.32 392	82.43 360	98.23 319	91.97 389	72.74 385	78.75 362	87.97 379	57.30 378	90.99 383	70.31 375	62.37 388	89.87 372

testf1		68.38 357	66.92 358	72.78 374	78.80 393	50.36 400	90.95 387	87.35 399	55.47 390	58.95 389	88.14 377	20.64 400	87.60 388	57.28 392	64.69 384	80.39 389

APD_test2		68.38 357	66.92 358	72.78 374	78.80 393	50.36 400	90.95 387	87.35 399	55.47 390	58.95 389	88.14 377	20.64 400	87.60 388	57.28 392	64.69 384	80.39 389

ambc				83.23 362	77.17 395	62.61 388	87.38 391	94.55 376		76.72 372	86.65 383	30.16 392	96.36 327	84.85 323	69.86 371	90.73 366

test_vis3_rt		68.82 355	66.69 360	75.21 371	76.24 396	60.41 392	96.44 355	68.71 406	75.13 380	50.54 397	69.52 395	16.42 405	96.32 329	80.27 348	66.92 382	68.89 393

TDRefinement		84.76 331	82.56 339	91.38 327	74.58 397	84.80 350	97.36 338	94.56 375	84.73 343	80.21 357	96.12 283	63.56 365	98.39 214	87.92 293	63.97 386	90.95 365

E-PMN		52.30 365	52.18 367	52.67 382	71.51 398	45.40 404	93.62 377	76.60 404	36.01 398	43.50 399	64.13 398	27.11 397	67.31 401	31.06 402	26.06 397	45.30 400

EMVS		51.44 367	51.22 369	52.11 383	70.71 399	44.97 406	94.04 373	75.66 405	35.34 400	42.40 400	61.56 401	28.93 394	65.87 402	27.64 403	24.73 398	45.49 399

PMMVS2		67.15 360	64.15 363	76.14 370	70.56 400	62.07 391	93.89 374	87.52 398	58.09 389	60.02 388	78.32 390	22.38 399	84.54 393	59.56 390	47.03 395	81.80 388

FPMVS		68.72 356	68.72 357	68.71 378	65.95 401	44.27 407	95.97 366	94.74 372	51.13 393	53.26 395	90.50 370	25.11 398	83.00 394	60.80 389	80.97 330	78.87 391

wuyk23d		20.37 371	20.84 374	18.99 386	65.34 402	27.73 409	50.43 397	7.67 410	9.50 403	8.01 404	6.34 404	6.13 408	26.24 403	23.40 404	10.69 402	2.99 401

LCM-MVSNet		67.77 359	64.73 362	76.87 369	62.95 403	56.25 396	89.37 390	93.74 383	44.53 395	61.99 387	80.74 389	20.42 402	86.53 392	69.37 378	59.50 392	87.84 381

MVE	53.74 22	51.54 366	47.86 370	62.60 380	59.56 404	50.93 399	79.41 394	77.69 403	35.69 399	36.27 401	61.76 400	5.79 409	69.63 399	37.97 399	36.61 396	67.24 394
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 363	52.24 366	67.66 379	49.27 405	56.82 395	83.94 392	82.02 402	70.47 386	33.28 402	64.54 397	17.23 404	69.16 400	45.59 397	23.85 399	77.02 392

tmp_tt		65.23 362	62.94 365	72.13 377	44.90 406	50.03 402	81.05 393	89.42 397	38.45 396	48.51 398	99.90 18	54.09 381	78.70 398	91.84 241	18.26 400	87.64 382

PMVS	49.05 23	53.75 364	51.34 368	60.97 381	40.80 407	34.68 408	74.82 395	89.62 396	37.55 397	28.67 403	72.12 392	7.09 407	81.63 397	43.17 398	68.21 378	66.59 395
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 369	39.14 372	33.31 384	19.94 408	24.83 410	98.36 313	9.75 409	15.53 402	51.31 396	87.14 381	19.62 403	17.74 404	47.10 396	3.47 403	57.36 397

testmvs		40.60 368	44.45 371	29.05 385	19.49 409	14.11 411	99.68 171	18.47 408	20.74 401	64.59 386	98.48 206	10.95 406	17.09 405	56.66 394	11.01 401	55.94 398

test_blank		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.02 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

eth-test2					0.00 410

eth-test					0.00 410

uanet_test		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 406	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

DCPMVS		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 406	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

cdsmvs_eth3d_5k		23.43 370	31.24 373	0.00 387	0.00 410	0.00 412	0.00 398	98.09 197	0.00 405	0.00 406	99.67 94	83.37 242	0.00 406	0.00 405	0.00 404	0.00 402

pcd_1.5k_mvsjas		7.60 373	10.13 376	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 406	91.20 151	0.00 406	0.00 405	0.00 404	0.00 402

sosnet-low-res		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 406	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

sosnet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 406	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uncertanet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 406	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

Regformer		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 406	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

ab-mvs-re		8.28 372	11.04 375	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	99.40 121	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uanet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 406	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

WAC-MVS						90.97 280								86.10 315

PC_three_1452									96.96 44	99.80 17	99.79 55	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 129	97.27 34	99.80 17	99.94 4	97.18 21	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 6	100.00 1	99.92 12	100.00 1	100.00 1

GSMVS																99.59 130

sam_mvs1												94.72 61				99.59 130

sam_mvs												94.25 76

MTGPA								98.28 175

test_post1							95.78 368				59.23 402	93.20 108	97.74 259	91.06 250

test_post											63.35 399	94.43 66	98.13 239

patchmatchnet-post											91.70 364	95.12 49	97.95 250

MTMP							99.87 101	96.49 339

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 66	99.94 68

test_prior2							99.95 52		95.78 79	99.73 32	99.76 63	96.00 33		99.78 27	100.00 1

旧先验2							99.46 209		94.21 130	99.85 9			99.95 69	96.96 151

新几何2							99.40 213

无先验							99.49 204	98.71 66	93.46 160				100.00 1	94.36 197		99.99 23

原ACMM2							99.90 87

testdata2													99.99 36	90.54 263

segment_acmp												96.68 26

testdata1							99.28 233		96.35 69

plane_prior5								97.87 219					98.37 220	97.79 128	89.55 247	94.52 256

plane_prior4											98.59 194

plane_prior3						91.64 272			96.63 56	93.01 220

plane_prior2							99.84 122		96.38 65

plane_prior						91.74 266	99.86 114		96.76 52						89.59 246

n2								0.00 411

nn								0.00 411

door-mid								89.69 395

test11								98.44 121

door								90.31 392

HQP5-MVS						91.85 262

BP-MVS														97.92 121

HQP4-MVS										93.37 216			98.39 214			94.53 254

HQP3-MVS								97.89 217							89.60 244

HQP2-MVS												80.65 266

MDTV_nov1_ep13_2view						96.26 135	96.11 362		91.89 217	98.06 132		94.40 68		94.30 199		99.67 113

ACMMP++_ref															87.04 282

ACMMP++															88.23 269

Test By Simon												92.82 119

High-resolution multi-view benchmark