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.

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 43	99.86 25	99.61 86	99.56 153	99.63 46	99.48 3	99.98 13	99.83 111	98.75 61	99.99 4	99.97 2	99.96 17	99.94 17

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 43	99.84 38	99.63 82	99.56 153	99.63 46	99.47 6	99.98 13	99.82 122	98.75 61	99.99 4	99.97 2	99.97 9	99.94 17

MED-MVS		99.70 3	99.64 4	99.90 8	99.88 13	99.81 33	99.69 63	99.87 6	99.48 3	99.90 34	99.89 45	99.30 4	99.95 76	98.83 175	99.89 67	99.93 22

TestfortrainingZip a		99.70 3	99.63 6	99.92 1	99.88 13	99.90 2	99.69 63	99.79 11	99.48 3	99.93 29	99.89 45	98.78 53	99.93 108	99.32 86	99.88 74	99.93 22

test_fmvsmconf_n		99.70 3	99.64 4	99.87 22	99.80 63	99.66 71	99.48 230	99.64 42	99.45 13	99.92 30	99.92 18	98.62 77	99.99 4	99.96 13	99.99 1	99.96 7

test_fmvsm_n_1920		99.69 6	99.66 3	99.78 71	99.84 38	99.44 117	99.58 137	99.69 22	99.43 19	99.98 13	99.91 26	98.62 77	100.00 1	99.97 2	99.95 22	99.90 27

APDe-MVS		99.66 7	99.57 10	99.92 1	99.77 78	99.89 6	99.75 43	99.56 89	99.02 62	99.88 42	99.85 89	99.18 11	99.96 41	99.22 107	99.92 38	99.90 27
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsmvis_n_1920		99.65 8	99.61 8	99.77 74	99.38 282	99.37 124	99.58 137	99.62 51	99.41 23	99.87 48	99.92 18	98.81 49	100.00 1	99.97 2	99.93 32	99.94 17

reproduce_model		99.63 9	99.54 13	99.90 8	99.78 70	99.88 10	99.56 153	99.55 99	99.15 38	99.90 34	99.90 36	99.00 23	99.97 29	99.11 125	99.91 45	99.86 43

fmvsm_l_conf0.5_n_3		99.61 10	99.51 18	99.92 1	99.84 38	99.82 28	99.54 173	99.66 32	99.46 9	99.98 13	99.89 45	97.27 133	99.99 4	99.97 2	99.95 22	99.95 11

reproduce-ours		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 184	99.54 108	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 135	99.90 56	99.85 47

our_new_method		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 184	99.54 108	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 135	99.90 56	99.85 47

SED-MVS		99.61 10	99.52 14	99.88 16	99.84 38	99.90 2	99.60 116	99.48 207	99.08 56	99.91 31	99.81 137	99.20 8	99.96 41	98.91 156	99.85 93	99.79 92

lecture		99.60 14	99.50 19	99.89 12	99.89 8	99.90 2	99.75 43	99.59 72	99.06 61	99.88 42	99.85 89	98.41 93	99.96 41	99.28 99	99.84 101	99.83 64

DVP-MVS++		99.59 15	99.50 19	99.88 16	99.51 232	99.88 10	99.87 8	99.51 158	98.99 69	99.88 42	99.81 137	99.27 6	99.96 41	98.85 169	99.80 125	99.81 79

fmvsm_l_conf0.5_n_9		99.58 16	99.47 24	99.92 1	99.85 31	99.82 28	99.47 240	99.63 46	99.45 13	99.98 13	99.89 45	97.02 148	99.99 4	99.98 1	99.96 17	99.95 11

TSAR-MVS + MP.		99.58 16	99.50 19	99.81 60	99.91 1	99.66 71	99.63 103	99.39 288	98.91 83	99.78 82	99.85 89	99.36 2	99.94 91	98.84 172	99.88 74	99.82 72
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EI-MVSNet-UG-set		99.58 16	99.57 10	99.64 102	99.78 70	99.14 162	99.60 116	99.45 253	99.01 64	99.90 34	99.83 111	98.98 25	99.93 108	99.59 45	99.95 22	99.86 43

EI-MVSNet-Vis-set		99.58 16	99.56 12	99.64 102	99.78 70	99.15 161	99.61 114	99.45 253	99.01 64	99.89 39	99.82 122	99.01 19	99.92 123	99.56 49	99.95 22	99.85 47

DVP-MVS		99.57 20	99.47 24	99.88 16	99.85 31	99.89 6	99.57 145	99.37 305	99.10 48	99.81 69	99.80 155	98.94 33	99.96 41	98.93 153	99.86 86	99.81 79
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
ME-MVS		99.56 21	99.46 28	99.86 34	99.80 63	99.81 33	99.37 291	99.70 18	99.18 35	99.83 64	99.83 111	98.74 66	99.93 108	98.83 175	99.89 67	99.83 64

fmvsm_s_conf0.5_n_a		99.56 21	99.47 24	99.85 43	99.83 47	99.64 81	99.52 184	99.65 39	99.10 48	99.98 13	99.92 18	97.35 129	99.96 41	99.94 21	99.92 38	99.95 11

test_fmvsmconf0.1_n		99.55 23	99.45 30	99.86 34	99.44 263	99.65 75	99.50 205	99.61 60	99.45 13	99.87 48	99.92 18	97.31 130	99.97 29	99.95 16	99.99 1	99.97 4

fmvsm_s_conf0.5_n_8		99.54 24	99.42 32	99.89 12	99.83 47	99.74 54	99.51 194	99.62 51	99.46 9	99.99 2	99.90 36	96.60 172	99.98 20	99.95 16	99.95 22	99.96 7

fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 232	99.67 68	99.50 205	99.64 42	99.43 19	99.98 13	99.78 179	97.26 136	99.95 76	99.95 16	99.93 32	99.92 25

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 22	99.82 53	99.81 33	99.59 127	99.51 158	98.62 113	99.79 77	99.83 111	99.28 5	99.97 29	98.48 226	99.90 56	99.84 54
Skip Steuart: Steuart Systems R&D Blog.
XVS		99.53 27	99.42 32	99.87 22	99.85 31	99.83 22	99.69 63	99.68 24	98.98 72	99.37 219	99.74 203	98.81 49	99.94 91	98.79 183	99.86 86	99.84 54

MTAPA		99.52 28	99.39 39	99.89 12	99.90 4	99.86 18	99.66 83	99.47 229	98.79 96	99.68 121	99.81 137	98.43 90	99.97 29	98.88 159	99.90 56	99.83 64

fmvsm_s_conf0.5_n		99.51 29	99.40 37	99.85 43	99.84 38	99.65 75	99.51 194	99.67 27	99.13 41	99.98 13	99.92 18	96.60 172	99.96 41	99.95 16	99.96 17	99.95 11

HPM-MVS_fast		99.51 29	99.40 37	99.85 43	99.91 1	99.79 41	99.76 38	99.56 89	97.72 260	99.76 92	99.75 197	99.13 13	99.92 123	99.07 132	99.92 38	99.85 47

mvsany_test1		99.50 31	99.46 28	99.62 109	99.61 191	99.09 167	98.94 422	99.48 207	99.10 48	99.96 27	99.91 26	98.85 43	99.96 41	99.72 32	99.58 169	99.82 72

CS-MVS		99.50 31	99.48 22	99.54 126	99.76 82	99.42 119	99.90 1	99.55 99	98.56 119	99.78 82	99.70 220	98.65 75	99.79 248	99.65 41	99.78 134	99.41 267

SPE-MVS-test		99.49 33	99.48 22	99.54 126	99.78 70	99.30 139	99.89 2	99.58 77	98.56 119	99.73 99	99.69 231	98.55 82	99.82 230	99.69 34	99.85 93	99.48 246

HFP-MVS		99.49 33	99.37 43	99.86 34	99.87 20	99.80 38	99.66 83	99.67 27	98.15 179	99.68 121	99.69 231	99.06 17	99.96 41	98.69 195	99.87 78	99.84 54

ACMMPR		99.49 33	99.36 45	99.86 34	99.87 20	99.79 41	99.66 83	99.67 27	98.15 179	99.67 127	99.69 231	98.95 31	99.96 41	98.69 195	99.87 78	99.84 54

DeepC-MVS_fast	98.69 1	99.49 33	99.39 39	99.77 74	99.63 171	99.59 89	99.36 297	99.46 242	99.07 58	99.79 77	99.82 122	98.85 43	99.92 123	98.68 197	99.87 78	99.82 72
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
region2R		99.48 37	99.35 47	99.87 22	99.88 13	99.80 38	99.65 89	99.66 32	98.13 186	99.66 132	99.68 239	98.96 26	99.96 41	98.62 204	99.87 78	99.84 54

APD-MVS_3200maxsize		99.48 37	99.35 47	99.85 43	99.76 82	99.83 22	99.63 103	99.54 108	98.36 142	99.79 77	99.82 122	98.86 42	99.95 76	98.62 204	99.81 120	99.78 98

DELS-MVS		99.48 37	99.42 32	99.65 96	99.72 111	99.40 122	99.05 394	99.66 32	99.14 40	99.57 169	99.80 155	98.46 88	99.94 91	99.57 48	99.84 101	99.60 199
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
ZNCC-MVS		99.47 40	99.33 51	99.87 22	99.87 20	99.81 33	99.64 97	99.67 27	98.08 204	99.55 176	99.64 258	98.91 38	99.96 41	98.72 190	99.90 56	99.82 72

ACMMP_NAP		99.47 40	99.34 49	99.88 16	99.87 20	99.86 18	99.47 240	99.48 207	98.05 212	99.76 92	99.86 82	98.82 48	99.93 108	98.82 182	99.91 45	99.84 54

MVSMamba_PlusPlus		99.46 42	99.41 36	99.64 102	99.68 135	99.50 109	99.75 43	99.50 182	98.27 154	99.87 48	99.92 18	98.09 108	99.94 91	99.65 41	99.95 22	99.47 252

BridgeMVS		99.46 42	99.39 39	99.67 91	99.55 215	99.58 94	99.74 48	99.51 158	98.42 135	99.87 48	99.84 104	98.05 111	99.91 135	99.58 47	99.94 30	99.52 229

DPE-MVS		99.46 42	99.32 53	99.91 6	99.78 70	99.88 10	99.36 297	99.51 158	98.73 103	99.88 42	99.84 104	98.72 68	99.96 41	98.16 262	99.87 78	99.88 36
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSLP-MVS++		99.46 42	99.47 24	99.44 177	99.60 197	99.16 156	99.41 272	99.71 16	98.98 72	99.45 192	99.78 179	99.19 10	99.54 330	99.28 99	99.84 101	99.63 191

SR-MVS-dyc-post		99.45 46	99.31 59	99.85 43	99.76 82	99.82 28	99.63 103	99.52 133	98.38 138	99.76 92	99.82 122	98.53 83	99.95 76	98.61 207	99.81 120	99.77 100

PGM-MVS		99.45 46	99.31 59	99.86 34	99.87 20	99.78 47	99.58 137	99.65 39	97.84 244	99.71 114	99.80 155	99.12 14	99.97 29	98.33 247	99.87 78	99.83 64

CP-MVS		99.45 46	99.32 53	99.85 43	99.83 47	99.75 51	99.69 63	99.52 133	98.07 205	99.53 179	99.63 264	98.93 37	99.97 29	98.74 187	99.91 45	99.83 64

ACMMP		99.45 46	99.32 53	99.82 57	99.89 8	99.67 68	99.62 108	99.69 22	98.12 194	99.63 150	99.84 104	98.73 67	99.96 41	98.55 222	99.83 113	99.81 79
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
SMA-MVS		99.44 50	99.30 61	99.85 43	99.73 107	99.83 22	99.56 153	99.47 229	97.45 294	99.78 82	99.82 122	99.18 11	99.91 135	98.79 183	99.89 67	99.81 79
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
mPP-MVS		99.44 50	99.30 61	99.86 34	99.88 13	99.79 41	99.69 63	99.48 207	98.12 194	99.50 184	99.75 197	98.78 53	99.97 29	98.57 216	99.89 67	99.83 64

EC-MVSNet		99.44 50	99.39 39	99.58 117	99.56 211	99.49 110	99.88 4	99.58 77	98.38 138	99.73 99	99.69 231	98.20 103	99.70 292	99.64 43	99.82 117	99.54 223

SR-MVS		99.43 53	99.29 65	99.86 34	99.75 92	99.83 22	99.59 127	99.62 51	98.21 170	99.73 99	99.79 172	98.68 71	99.96 41	98.44 233	99.77 137	99.79 92

MCST-MVS		99.43 53	99.30 61	99.82 57	99.79 68	99.74 54	99.29 322	99.40 285	98.79 96	99.52 181	99.62 269	98.91 38	99.90 148	98.64 201	99.75 142	99.82 72

MSP-MVS		99.42 55	99.27 72	99.88 16	99.89 8	99.80 38	99.67 76	99.50 182	98.70 107	99.77 86	99.49 316	98.21 102	99.95 76	98.46 231	99.77 137	99.88 36
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
UA-Net		99.42 55	99.29 65	99.80 64	99.62 180	99.55 97	99.50 205	99.70 18	98.79 96	99.77 86	99.96 1	97.45 124	99.96 41	98.92 155	99.90 56	99.89 30

HPM-MVS		99.42 55	99.28 68	99.83 56	99.90 4	99.72 56	99.81 20	99.54 108	97.59 275	99.68 121	99.63 264	98.91 38	99.94 91	98.58 213	99.91 45	99.84 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CNVR-MVS		99.42 55	99.30 61	99.78 71	99.62 180	99.71 58	99.26 342	99.52 133	98.82 90	99.39 215	99.71 216	98.96 26	99.85 190	98.59 212	99.80 125	99.77 100

fmvsm_s_conf0.5_n_10		99.41 59	99.24 77	99.92 1	99.83 47	99.84 20	99.53 182	99.56 89	99.45 13	99.99 2	99.92 18	94.92 260	99.99 4	99.97 2	99.97 9	99.95 11

fmvsm_s_conf0.5_n_9		99.41 59	99.28 68	99.81 60	99.84 38	99.52 106	99.48 230	99.62 51	99.46 9	99.99 2	99.92 18	95.24 247	99.96 41	99.97 2	99.97 9	99.96 7

SD-MVS		99.41 59	99.52 14	99.05 241	99.74 100	99.68 64	99.46 244	99.52 133	99.11 47	99.88 42	99.91 26	99.43 1	97.70 482	98.72 190	99.93 32	99.77 100
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
MVS_111021_LR		99.41 59	99.33 51	99.65 96	99.77 78	99.51 108	98.94 422	99.85 8	98.82 90	99.65 142	99.74 203	98.51 85	99.80 242	98.83 175	99.89 67	99.64 186

MVS_111021_HR		99.41 59	99.32 53	99.66 92	99.72 111	99.47 114	98.95 420	99.85 8	98.82 90	99.54 177	99.73 209	98.51 85	99.74 269	98.91 156	99.88 74	99.77 100

MM		99.40 64	99.28 68	99.74 80	99.67 138	99.31 136	99.52 184	98.87 426	99.55 1	99.74 97	99.80 155	96.47 180	99.98 20	99.97 2	99.97 9	99.94 17

GST-MVS		99.40 64	99.24 77	99.85 43	99.86 25	99.79 41	99.60 116	99.67 27	97.97 228	99.63 150	99.68 239	98.52 84	99.95 76	98.38 240	99.86 86	99.81 79

HPM-MVS++		99.39 66	99.23 81	99.87 22	99.75 92	99.84 20	99.43 261	99.51 158	98.68 110	99.27 249	99.53 302	98.64 76	99.96 41	98.44 233	99.80 125	99.79 92

SF-MVS		99.38 67	99.24 77	99.79 68	99.79 68	99.68 64	99.57 145	99.54 108	97.82 250	99.71 114	99.80 155	98.95 31	99.93 108	98.19 258	99.84 101	99.74 118

fmvsm_s_conf0.5_n_5		99.37 68	99.21 83	99.86 34	99.80 63	99.68 64	99.42 268	99.61 60	99.37 26	99.97 25	99.86 82	94.96 255	99.99 4	99.97 2	99.93 32	99.92 25

fmvsm_s_conf0.5_n_3		99.37 68	99.20 85	99.87 22	99.75 92	99.70 60	99.48 230	99.66 32	99.45 13	99.99 2	99.93 10	94.64 288	99.97 29	99.94 21	99.97 9	99.95 11

fmvsm_s_conf0.1_n_2		99.37 68	99.22 82	99.81 60	99.77 78	99.75 51	99.46 244	99.60 67	99.47 6	99.98 13	99.94 6	94.98 254	99.95 76	99.97 2	99.79 132	99.73 128

MP-MVS-pluss		99.37 68	99.20 85	99.88 16	99.90 4	99.87 17	99.30 317	99.52 133	97.18 320	99.60 162	99.79 172	98.79 52	99.95 76	98.83 175	99.91 45	99.83 64
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_4		99.36 72	99.24 77	99.73 83	99.78 70	99.53 102	99.49 222	99.60 67	99.42 22	99.99 2	99.86 82	95.15 250	99.95 76	99.95 16	99.89 67	99.73 128

TSAR-MVS + GP.		99.36 72	99.36 45	99.36 192	99.67 138	98.61 256	99.07 387	99.33 327	99.00 67	99.82 68	99.81 137	99.06 17	99.84 199	99.09 130	99.42 181	99.65 179

PVSNet_Blended_VisFu		99.36 72	99.28 68	99.61 110	99.86 25	99.07 172	99.47 240	99.93 2	97.66 269	99.71 114	99.86 82	97.73 119	99.96 41	99.47 66	99.82 117	99.79 92

fmvsm_s_conf0.5_n_7		99.34 75	99.29 65	99.48 163	99.70 122	98.63 252	99.42 268	99.63 46	99.46 9	99.98 13	99.88 58	95.59 230	99.96 41	99.97 2	99.98 4	99.85 47

NCCC		99.34 75	99.19 87	99.79 68	99.61 191	99.65 75	99.30 317	99.48 207	98.86 85	99.21 264	99.63 264	98.72 68	99.90 148	98.25 254	99.63 164	99.80 88

MP-MVS		99.33 77	99.15 92	99.87 22	99.88 13	99.82 28	99.66 83	99.46 242	98.09 200	99.48 188	99.74 203	98.29 99	99.96 41	97.93 284	99.87 78	99.82 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_s_conf0.5_n_11		99.32 78	99.16 91	99.80 64	99.83 47	99.70 60	99.57 145	99.56 89	99.45 13	99.99 2	99.93 10	94.18 311	99.99 4	99.96 13	99.98 4	99.73 128

fmvsm_s_conf0.5_n_2		99.32 78	99.13 94	99.89 12	99.80 63	99.77 48	99.44 255	99.58 77	99.47 6	99.99 2	99.93 10	94.04 316	99.96 41	99.96 13	99.93 32	99.93 22

PS-MVSNAJ		99.32 78	99.32 53	99.30 208	99.57 207	98.94 200	98.97 416	99.46 242	98.92 82	99.71 114	99.24 387	99.01 19	99.98 20	99.35 78	99.66 159	98.97 322

CSCG		99.32 78	99.32 53	99.32 201	99.85 31	98.29 282	99.71 58	99.66 32	98.11 196	99.41 208	99.80 155	98.37 96	99.96 41	98.99 141	99.96 17	99.72 138

PHI-MVS		99.30 82	99.17 90	99.70 87	99.56 211	99.52 106	99.58 137	99.80 10	97.12 326	99.62 154	99.73 209	98.58 79	99.90 148	98.61 207	99.91 45	99.68 162

DeepC-MVS	98.35 2	99.30 82	99.19 87	99.64 102	99.82 53	99.23 149	99.62 108	99.55 99	98.94 79	99.63 150	99.95 3	95.82 218	99.94 91	99.37 77	99.97 9	99.73 128
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.1_n		99.29 84	99.10 98	99.86 34	99.70 122	99.65 75	99.53 182	99.62 51	98.74 102	99.99 2	99.95 3	94.53 296	99.94 91	99.89 25	99.96 17	99.97 4

xiu_mvs_v1_base_debu		99.29 84	99.27 72	99.34 195	99.63 171	98.97 186	99.12 377	99.51 158	98.86 85	99.84 55	99.47 326	98.18 104	99.99 4	99.50 57	99.31 191	99.08 304

xiu_mvs_v1_base		99.29 84	99.27 72	99.34 195	99.63 171	98.97 186	99.12 377	99.51 158	98.86 85	99.84 55	99.47 326	98.18 104	99.99 4	99.50 57	99.31 191	99.08 304

xiu_mvs_v1_base_debi		99.29 84	99.27 72	99.34 195	99.63 171	98.97 186	99.12 377	99.51 158	98.86 85	99.84 55	99.47 326	98.18 104	99.99 4	99.50 57	99.31 191	99.08 304

NormalMVS		99.27 88	99.19 87	99.52 141	99.89 8	98.83 230	99.65 89	99.52 133	99.10 48	99.84 55	99.76 192	95.80 220	99.99 4	99.30 91	99.84 101	99.74 118

APD-MVS		99.27 88	99.08 104	99.84 55	99.75 92	99.79 41	99.50 205	99.50 182	97.16 322	99.77 86	99.82 122	98.78 53	99.94 91	97.56 326	99.86 86	99.80 88
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
LS3D		99.27 88	99.12 96	99.74 80	99.18 337	99.75 51	99.56 153	99.57 84	98.45 131	99.49 187	99.85 89	97.77 118	99.94 91	98.33 247	99.84 101	99.52 229

fmvsm_s_conf0.1_n_a		99.26 91	99.06 109	99.85 43	99.52 229	99.62 83	99.54 173	99.62 51	98.69 108	99.99 2	99.96 1	94.47 298	99.94 91	99.88 26	99.92 38	99.98 2

patch_mono-2		99.26 91	99.62 7	98.16 368	99.81 57	94.59 451	99.52 184	99.64 42	99.33 29	99.73 99	99.90 36	99.00 23	99.99 4	99.69 34	99.98 4	99.89 30

ETV-MVS		99.26 91	99.21 83	99.40 185	99.46 256	99.30 139	99.56 153	99.52 133	98.52 123	99.44 197	99.27 383	98.41 93	99.86 182	99.10 128	99.59 168	99.04 312

xiu_mvs_v2_base		99.26 91	99.25 76	99.29 211	99.53 223	98.91 207	99.02 402	99.45 253	98.80 95	99.71 114	99.26 385	98.94 33	99.98 20	99.34 83	99.23 200	98.98 320

CANet		99.25 95	99.14 93	99.59 114	99.41 271	99.16 156	99.35 302	99.57 84	98.82 90	99.51 183	99.61 273	96.46 181	99.95 76	99.59 45	99.98 4	99.65 179

3Dnovator	97.25 9	99.24 96	99.05 111	99.81 60	99.12 353	99.66 71	99.84 12	99.74 13	99.09 55	98.92 321	99.90 36	95.94 211	99.98 20	98.95 149	99.92 38	99.79 92

LuminaMVS		99.23 97	99.10 98	99.61 110	99.35 289	99.31 136	99.46 244	99.13 384	98.61 114	99.86 52	99.89 45	96.41 186	99.91 135	99.67 37	99.51 174	99.63 191

dcpmvs_2		99.23 97	99.58 9	98.16 368	99.83 47	94.68 448	99.76 38	99.52 133	99.07 58	99.98 13	99.88 58	98.56 81	99.93 108	99.67 37	99.98 4	99.87 41

test_fmvsmconf0.01_n		99.22 99	99.03 116	99.79 68	98.42 451	99.48 112	99.55 168	99.51 158	99.39 24	99.78 82	99.93 10	94.80 269	99.95 76	99.93 23	99.95 22	99.94 17

diffmvs_AUTHOR		99.19 100	99.10 98	99.48 163	99.64 166	98.85 225	99.32 311	99.48 207	98.50 125	99.81 69	99.81 137	96.82 160	99.88 168	99.40 72	99.12 218	99.71 149

CHOSEN 1792x2688		99.19 100	99.10 98	99.45 172	99.89 8	98.52 266	99.39 284	99.94 1	98.73 103	99.11 284	99.89 45	95.50 233	99.94 91	99.50 57	99.97 9	99.89 30

F-COLMAP		99.19 100	99.04 113	99.64 102	99.78 70	99.27 144	99.42 268	99.54 108	97.29 311	99.41 208	99.59 278	98.42 92	99.93 108	98.19 258	99.69 153	99.73 128

E3new		99.18 103	99.08 104	99.48 163	99.63 171	98.94 200	99.46 244	99.50 182	98.06 209	99.72 104	99.84 104	97.27 133	99.84 199	99.10 128	99.13 213	99.67 167

viewcassd2359sk11		99.18 103	99.08 104	99.49 159	99.65 161	98.95 196	99.48 230	99.51 158	98.10 199	99.72 104	99.87 73	97.13 139	99.84 199	99.13 122	99.14 210	99.69 156

viewmanbaseed2359cas		99.18 103	99.07 108	99.50 152	99.62 180	99.01 180	99.50 205	99.52 133	98.25 162	99.68 121	99.82 122	96.93 153	99.80 242	99.15 121	99.11 220	99.70 153

EIA-MVS		99.18 103	99.09 103	99.45 172	99.49 246	99.18 153	99.67 76	99.53 124	97.66 269	99.40 213	99.44 333	98.10 107	99.81 235	98.94 150	99.62 165	99.35 277

3Dnovator+	97.12 13	99.18 103	98.97 144	99.82 57	99.17 345	99.68 64	99.81 20	99.51 158	99.20 34	98.72 351	99.89 45	95.68 227	99.97 29	98.86 167	99.86 86	99.81 79

MVSFormer		99.17 108	99.12 96	99.29 211	99.51 232	98.94 200	99.88 4	99.46 242	97.55 281	99.80 74	99.65 252	97.39 125	99.28 373	99.03 137	99.85 93	99.65 179

sss		99.17 108	99.05 111	99.53 134	99.62 180	98.97 186	99.36 297	99.62 51	97.83 245	99.67 127	99.65 252	97.37 128	99.95 76	99.19 111	99.19 204	99.68 162

SSM_0404		99.16 110	99.06 109	99.44 177	99.65 161	98.96 190	99.49 222	99.50 182	98.14 183	99.62 154	99.85 89	96.85 155	99.85 190	99.19 111	99.26 196	99.52 229

guyue		99.16 110	99.04 113	99.52 141	99.69 128	98.92 206	99.59 127	98.81 434	98.73 103	99.90 34	99.87 73	95.34 240	99.88 168	99.66 40	99.81 120	99.74 118

test_cas_vis1_n_1920		99.16 110	99.01 133	99.61 110	99.81 57	98.86 224	99.65 89	99.64 42	99.39 24	99.97 25	99.94 6	93.20 340	99.98 20	99.55 50	99.91 45	99.99 1

DP-MVS		99.16 110	98.95 152	99.78 71	99.77 78	99.53 102	99.41 272	99.50 182	97.03 338	99.04 301	99.88 58	97.39 125	99.92 123	98.66 199	99.90 56	99.87 41

E6new		99.15 114	99.03 116	99.50 152	99.66 150	98.90 212	99.60 116	99.53 124	98.13 186	99.72 104	99.91 26	96.31 190	99.84 199	99.30 91	99.10 227	99.76 107

E6		99.15 114	99.03 116	99.50 152	99.66 150	98.90 212	99.60 116	99.53 124	98.13 186	99.72 104	99.91 26	96.31 190	99.84 199	99.30 91	99.10 227	99.76 107

E2		99.15 114	99.03 116	99.49 159	99.65 161	98.93 205	99.49 222	99.52 133	98.14 183	99.72 104	99.88 58	96.57 176	99.84 199	99.17 117	99.13 213	99.72 138

E3		99.15 114	99.03 116	99.49 159	99.62 180	98.91 207	99.49 222	99.52 133	98.13 186	99.72 104	99.88 58	96.61 171	99.84 199	99.17 117	99.13 213	99.72 138

SymmetryMVS		99.15 114	99.02 126	99.52 141	99.72 111	98.83 230	99.65 89	99.34 319	99.10 48	99.84 55	99.76 192	95.80 220	99.99 4	99.30 91	98.72 266	99.73 128

MGCNet		99.15 114	98.96 148	99.73 83	98.92 391	99.37 124	99.37 291	96.92 493	99.51 2	99.66 132	99.78 179	96.69 167	99.97 29	99.84 28	99.97 9	99.84 54

casdiffmvs_mvg		99.15 114	99.02 126	99.55 125	99.66 150	99.09 167	99.64 97	99.56 89	98.26 157	99.45 192	99.87 73	96.03 205	99.81 235	99.54 51	99.15 209	99.73 128
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.15 114	99.02 126	99.53 134	99.66 150	99.14 162	99.72 54	99.48 207	98.35 143	99.42 203	99.84 104	96.07 202	99.79 248	99.51 56	99.14 210	99.67 167

E5new		99.14 122	99.02 126	99.50 152	99.69 128	98.91 207	99.60 116	99.53 124	98.13 186	99.72 104	99.91 26	96.26 195	99.84 199	99.30 91	99.10 227	99.76 107

E5		99.14 122	99.02 126	99.50 152	99.69 128	98.91 207	99.60 116	99.53 124	98.13 186	99.72 104	99.91 26	96.26 195	99.84 199	99.30 91	99.10 227	99.76 107

diffmvs		99.14 122	99.02 126	99.51 146	99.61 191	98.96 190	99.28 328	99.49 195	98.46 129	99.72 104	99.71 216	96.50 179	99.88 168	99.31 88	99.11 220	99.67 167
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CNLPA		99.14 122	98.99 139	99.59 114	99.58 201	99.41 121	99.16 367	99.44 262	98.45 131	99.19 271	99.49 316	98.08 109	99.89 163	97.73 308	99.75 142	99.48 246

hybridcas		99.13 126	99.00 137	99.51 146	99.70 122	99.04 176	99.65 89	99.52 133	98.20 172	99.75 96	99.88 58	95.78 222	99.78 255	99.41 70	99.16 205	99.71 149

E4		99.13 126	99.01 133	99.49 159	99.68 135	98.90 212	99.52 184	99.52 133	98.13 186	99.71 114	99.90 36	96.32 188	99.84 199	99.21 109	99.11 220	99.75 113

SSM_0407		99.13 126	99.03 116	99.43 180	99.62 180	98.88 217	99.51 194	99.50 182	98.14 183	99.37 219	99.85 89	96.85 155	99.83 221	99.19 111	99.25 197	99.60 199

CDPH-MVS		99.13 126	98.91 160	99.80 64	99.75 92	99.71 58	99.15 370	99.41 278	96.60 372	99.60 162	99.55 293	98.83 47	99.90 148	97.48 335	99.83 113	99.78 98

casdiffmvs		99.13 126	98.98 142	99.56 123	99.65 161	99.16 156	99.56 153	99.50 182	98.33 146	99.41 208	99.86 82	95.92 212	99.83 221	99.45 68	99.16 205	99.70 153
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jason		99.13 126	99.03 116	99.45 172	99.46 256	98.87 221	99.12 377	99.26 361	98.03 221	99.79 77	99.65 252	97.02 148	99.85 190	99.02 139	99.90 56	99.65 179
jason: jason.
lupinMVS		99.13 126	99.01 133	99.46 171	99.51 232	98.94 200	99.05 394	99.16 380	97.86 238	99.80 74	99.56 290	97.39 125	99.86 182	98.94 150	99.85 93	99.58 214

EPP-MVSNet		99.13 126	98.99 139	99.53 134	99.65 161	99.06 173	99.81 20	99.33 327	97.43 298	99.60 162	99.88 58	97.14 138	99.84 199	99.13 122	98.94 245	99.69 156

MG-MVS		99.13 126	99.02 126	99.45 172	99.57 207	98.63 252	99.07 387	99.34 319	98.99 69	99.61 159	99.82 122	97.98 113	99.87 175	97.00 372	99.80 125	99.85 47

KinetiMVS		99.12 135	98.92 157	99.70 87	99.67 138	99.40 122	99.67 76	99.63 46	98.73 103	99.94 28	99.81 137	94.54 294	99.96 41	98.40 238	99.93 32	99.74 118

BP-MVS1		99.12 135	98.94 154	99.65 96	99.51 232	99.30 139	99.67 76	98.92 413	98.48 127	99.84 55	99.69 231	94.96 255	99.92 123	99.62 44	99.79 132	99.71 149

CHOSEN 280x420		99.12 135	99.13 94	99.08 237	99.66 150	97.89 309	98.43 475	99.71 16	98.88 84	99.62 154	99.76 192	96.63 170	99.70 292	99.46 67	99.99 1	99.66 172

DP-MVS Recon		99.12 135	98.95 152	99.65 96	99.74 100	99.70 60	99.27 333	99.57 84	96.40 388	99.42 203	99.68 239	98.75 61	99.80 242	97.98 281	99.72 148	99.44 262

Vis-MVSNet		99.12 135	98.97 144	99.56 123	99.78 70	99.10 166	99.68 73	99.66 32	98.49 126	99.86 52	99.87 73	94.77 274	99.84 199	99.19 111	99.41 182	99.74 118
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 135	99.08 104	99.24 221	99.46 256	98.55 260	99.51 194	99.46 242	98.09 200	99.45 192	99.82 122	98.34 97	99.51 332	98.70 192	98.93 246	99.67 167

hybrid		99.11 141	99.01 133	99.41 183	99.64 166	98.76 240	99.35 302	99.52 133	98.31 150	99.80 74	99.84 104	96.16 199	99.79 248	99.40 72	99.06 235	99.68 162

viewdifsd2359ckpt07		99.11 141	99.00 137	99.43 180	99.63 171	98.73 242	99.45 248	99.54 108	98.33 146	99.62 154	99.81 137	96.17 198	99.87 175	99.27 102	99.14 210	99.69 156

SDMVSNet		99.11 141	98.90 162	99.75 77	99.81 57	99.59 89	99.81 20	99.65 39	98.78 99	99.64 147	99.88 58	94.56 291	99.93 108	99.67 37	98.26 296	99.72 138

VNet		99.11 141	98.90 162	99.73 83	99.52 229	99.56 95	99.41 272	99.39 288	99.01 64	99.74 97	99.78 179	95.56 231	99.92 123	99.52 55	98.18 304	99.72 138

CPTT-MVS		99.11 141	98.90 162	99.74 80	99.80 63	99.46 115	99.59 127	99.49 195	97.03 338	99.63 150	99.69 231	97.27 133	99.96 41	97.82 295	99.84 101	99.81 79

HyFIR lowres test		99.11 141	98.92 157	99.65 96	99.90 4	99.37 124	99.02 402	99.91 3	97.67 268	99.59 165	99.75 197	95.90 214	99.73 275	99.53 53	99.02 241	99.86 43

MVS_Test		99.10 147	98.97 144	99.48 163	99.49 246	99.14 162	99.67 76	99.34 319	97.31 309	99.58 166	99.76 192	97.65 121	99.82 230	98.87 162	99.07 234	99.46 257

AstraMVS		99.09 148	99.03 116	99.25 218	99.66 150	98.13 291	99.57 145	98.24 470	98.82 90	99.91 31	99.88 58	95.81 219	99.90 148	99.72 32	99.67 158	99.74 118

CDS-MVSNet		99.09 148	99.03 116	99.25 218	99.42 266	98.73 242	99.45 248	99.46 242	98.11 196	99.46 191	99.77 188	98.01 112	99.37 356	98.70 192	98.92 248	99.66 172
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmacassd2359aftdt		99.08 150	98.94 154	99.50 152	99.66 150	98.96 190	99.51 194	99.54 108	98.27 154	99.42 203	99.89 45	95.88 216	99.80 242	99.20 110	99.11 220	99.76 107

mamba_0408		99.08 150	98.96 148	99.44 177	99.62 180	98.88 217	99.25 344	99.47 229	98.05 212	99.37 219	99.81 137	96.85 155	99.85 190	98.98 142	99.25 197	99.60 199

GDP-MVS		99.08 150	98.89 166	99.64 102	99.53 223	99.34 128	99.64 97	99.48 207	98.32 148	99.77 86	99.66 250	95.14 251	99.93 108	98.97 147	99.50 176	99.64 186

PVSNet_Blended		99.08 150	98.97 144	99.42 182	99.76 82	98.79 236	98.78 443	99.91 3	96.74 357	99.67 127	99.49 316	97.53 122	99.88 168	98.98 142	99.85 93	99.60 199

OMC-MVS		99.08 150	99.04 113	99.20 225	99.67 138	98.22 286	99.28 328	99.52 133	98.07 205	99.66 132	99.81 137	97.79 117	99.78 255	97.79 299	99.81 120	99.60 199

viewdifsd2359ckpt13		99.06 155	98.93 156	99.45 172	99.63 171	98.96 190	99.50 205	99.51 158	97.83 245	99.28 243	99.80 155	96.68 169	99.71 285	99.05 134	99.12 218	99.68 162

SSM_04072		99.06 155	98.96 148	99.35 194	99.62 180	98.88 217	99.25 344	99.47 229	98.05 212	99.37 219	99.81 137	96.85 155	99.58 324	98.98 142	99.25 197	99.60 199

mvsmamba		99.06 155	98.96 148	99.36 192	99.47 254	98.64 251	99.70 59	99.05 396	97.61 274	99.65 142	99.83 111	96.54 177	99.92 123	99.19 111	99.62 165	99.51 238

WTY-MVS		99.06 155	98.88 169	99.61 110	99.62 180	99.16 156	99.37 291	99.56 89	98.04 219	99.53 179	99.62 269	96.84 159	99.94 91	98.85 169	98.49 281	99.72 138

IS-MVSNet		99.05 159	98.87 170	99.57 121	99.73 107	99.32 132	99.75 43	99.20 375	98.02 224	99.56 170	99.86 82	96.54 177	99.67 301	98.09 269	99.13 213	99.73 128

PAPM_NR		99.04 160	98.84 178	99.66 92	99.74 100	99.44 117	99.39 284	99.38 296	97.70 264	99.28 243	99.28 380	98.34 97	99.85 190	96.96 376	99.45 179	99.69 156

API-MVS		99.04 160	99.03 116	99.06 239	99.40 276	99.31 136	99.55 168	99.56 89	98.54 121	99.33 233	99.39 349	98.76 58	99.78 255	96.98 374	99.78 134	98.07 455

mvs_anonymous		99.03 162	98.99 139	99.16 229	99.38 282	98.52 266	99.51 194	99.38 296	97.79 251	99.38 217	99.81 137	97.30 131	99.45 338	99.35 78	98.99 243	99.51 238

sasdasda		99.02 163	98.86 173	99.51 146	99.42 266	99.32 132	99.80 25	99.48 207	98.63 111	99.31 235	98.81 433	97.09 143	99.75 266	99.27 102	97.90 315	99.47 252

train_agg		99.02 163	98.77 186	99.77 74	99.67 138	99.65 75	99.05 394	99.41 278	96.28 392	98.95 317	99.49 316	98.76 58	99.91 135	97.63 317	99.72 148	99.75 113

canonicalmvs		99.02 163	98.86 173	99.51 146	99.42 266	99.32 132	99.80 25	99.48 207	98.63 111	99.31 235	98.81 433	97.09 143	99.75 266	99.27 102	97.90 315	99.47 252

balanced_ft_v1		99.02 163	98.98 142	99.15 233	99.39 279	98.12 293	99.79 31	99.51 158	98.20 172	99.66 132	99.87 73	94.84 265	99.93 108	99.69 34	99.84 101	99.41 267

PLC	97.94 4	99.02 163	98.85 176	99.53 134	99.66 150	99.01 180	99.24 349	99.52 133	96.85 350	99.27 249	99.48 323	98.25 101	99.91 135	97.76 304	99.62 165	99.65 179
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
viewdifsd2359ckpt09		99.01 168	98.87 170	99.40 185	99.62 180	98.79 236	99.44 255	99.51 158	97.76 255	99.35 228	99.69 231	96.42 185	99.75 266	98.97 147	99.11 220	99.66 172

viewmambaseed2359dif		99.01 168	98.90 162	99.32 201	99.58 201	98.51 268	99.33 308	99.54 108	97.85 241	99.44 197	99.85 89	96.01 206	99.79 248	99.41 70	99.13 213	99.67 167

MGCFI-Net		99.01 168	98.85 176	99.50 152	99.42 266	99.26 145	99.82 16	99.48 207	98.60 116	99.28 243	98.81 433	97.04 147	99.76 263	99.29 97	97.87 318	99.47 252

AdaColmap		99.01 168	98.80 181	99.66 92	99.56 211	99.54 99	99.18 365	99.70 18	98.18 177	99.35 228	99.63 264	96.32 188	99.90 148	97.48 335	99.77 137	99.55 221

1112_ss		98.98 172	98.77 186	99.59 114	99.68 135	99.02 178	99.25 344	99.48 207	97.23 317	99.13 280	99.58 282	96.93 153	99.90 148	98.87 162	98.78 263	99.84 54

MSDG		98.98 172	98.80 181	99.53 134	99.76 82	99.19 151	98.75 446	99.55 99	97.25 314	99.47 189	99.77 188	97.82 116	99.87 175	96.93 379	99.90 56	99.54 223

casdiffseed414692147		98.97 174	98.78 185	99.53 134	99.66 150	99.16 156	99.61 114	99.52 133	98.01 225	99.21 264	99.88 58	94.82 266	99.70 292	99.29 97	99.04 238	99.74 118

CANet_DTU		98.97 174	98.87 170	99.25 218	99.33 295	98.42 279	99.08 386	99.30 346	99.16 37	99.43 200	99.75 197	95.27 243	99.97 29	98.56 219	99.95 22	99.36 276

DPM-MVS		98.95 176	98.71 194	99.66 92	99.63 171	99.55 97	98.64 458	99.10 387	97.93 231	99.42 203	99.55 293	98.67 73	99.80 242	95.80 413	99.68 156	99.61 196

114514_t		98.93 177	98.67 198	99.72 86	99.85 31	99.53 102	99.62 108	99.59 72	92.65 463	99.71 114	99.78 179	98.06 110	99.90 148	98.84 172	99.91 45	99.74 118

PS-MVSNAJss		98.92 178	98.92 157	98.90 266	98.78 412	98.53 262	99.78 33	99.54 108	98.07 205	99.00 308	99.76 192	99.01 19	99.37 356	99.13 122	97.23 358	98.81 331

RRT-MVS		98.91 179	98.75 188	99.39 190	99.46 256	98.61 256	99.76 38	99.50 182	98.06 209	99.81 69	99.88 58	93.91 323	99.94 91	99.11 125	99.27 194	99.61 196

Test_1112_low_res		98.89 180	98.66 201	99.57 121	99.69 128	98.95 196	99.03 399	99.47 229	96.98 340	99.15 278	99.23 388	96.77 164	99.89 163	98.83 175	98.78 263	99.86 43

Elysia		98.88 181	98.65 203	99.58 117	99.58 201	99.34 128	99.65 89	99.52 133	98.26 157	99.83 64	99.87 73	93.37 334	99.90 148	97.81 297	99.91 45	99.49 243

StellarMVS		98.88 181	98.65 203	99.58 117	99.58 201	99.34 128	99.65 89	99.52 133	98.26 157	99.83 64	99.87 73	93.37 334	99.90 148	97.81 297	99.91 45	99.49 243

test_fmvs1		98.88 181	98.79 184	99.16 229	99.69 128	97.61 324	99.55 168	99.49 195	99.32 30	99.98 13	99.91 26	91.41 390	99.96 41	99.82 29	99.92 38	99.90 27

AllTest		98.87 184	98.72 192	99.31 203	99.86 25	98.48 273	99.56 153	99.61 60	97.85 241	99.36 225	99.85 89	95.95 209	99.85 190	96.66 392	99.83 113	99.59 210

UGNet		98.87 184	98.69 196	99.40 185	99.22 328	98.72 244	99.44 255	99.68 24	99.24 33	99.18 275	99.42 337	92.74 350	99.96 41	99.34 83	99.94 30	99.53 228
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
Vis-MVSNet (Re-imp)		98.87 184	98.72 192	99.31 203	99.71 117	98.88 217	99.80 25	99.44 262	97.91 233	99.36 225	99.78 179	95.49 234	99.43 347	97.91 285	99.11 220	99.62 194

IMVS_0407		98.86 187	98.91 160	98.72 301	99.55 215	96.93 364	99.50 205	99.44 262	98.05 212	99.66 132	99.80 155	97.13 139	99.65 309	98.15 264	98.92 248	99.60 199

IMVS_0403		98.86 187	98.89 166	98.78 296	99.55 215	96.93 364	99.58 137	99.44 262	98.05 212	99.68 121	99.80 155	96.81 161	99.80 242	98.15 264	98.92 248	99.60 199

test_yl		98.86 187	98.63 206	99.54 126	99.49 246	99.18 153	99.50 205	99.07 393	98.22 168	99.61 159	99.51 310	95.37 238	99.84 199	98.60 210	98.33 288	99.59 210

DCV-MVSNet		98.86 187	98.63 206	99.54 126	99.49 246	99.18 153	99.50 205	99.07 393	98.22 168	99.61 159	99.51 310	95.37 238	99.84 199	98.60 210	98.33 288	99.59 210

EPNet		98.86 187	98.71 194	99.30 208	97.20 478	98.18 287	99.62 108	98.91 418	99.28 32	98.63 370	99.81 137	95.96 208	99.99 4	99.24 106	99.72 148	99.73 128
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 187	98.80 181	99.03 243	99.76 82	98.79 236	99.28 328	99.91 3	97.42 300	99.67 127	99.37 355	97.53 122	99.88 168	98.98 142	97.29 356	98.42 433

ab-mvs		98.86 187	98.63 206	99.54 126	99.64 166	99.19 151	99.44 255	99.54 108	97.77 254	99.30 239	99.81 137	94.20 308	99.93 108	99.17 117	98.82 260	99.49 243

MAR-MVS		98.86 187	98.63 206	99.54 126	99.37 285	99.66 71	99.45 248	99.54 108	96.61 369	99.01 304	99.40 345	97.09 143	99.86 182	97.68 316	99.53 173	99.10 299
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
COLMAP_ROB	97.56 6	98.86 187	98.75 188	99.17 228	99.88 13	98.53 262	99.34 306	99.59 72	97.55 281	98.70 358	99.89 45	95.83 217	99.90 148	98.10 268	99.90 56	99.08 304
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 196	98.62 211	99.53 134	99.61 191	99.08 170	99.80 25	99.51 158	97.10 330	99.31 235	99.78 179	95.23 248	99.77 259	98.21 256	99.03 239	99.75 113

HY-MVS	97.30 7	98.85 196	98.64 205	99.47 169	99.42 266	99.08 170	99.62 108	99.36 307	97.39 303	99.28 243	99.68 239	96.44 183	99.92 123	98.37 242	98.22 299	99.40 270

PVSNet	96.02 17	98.85 196	98.84 178	98.89 270	99.73 107	97.28 334	98.32 481	99.60 67	97.86 238	99.50 184	99.57 287	96.75 165	99.86 182	98.56 219	99.70 152	99.54 223

PatchMatch-RL		98.84 199	98.62 211	99.52 141	99.71 117	99.28 142	99.06 391	99.77 12	97.74 259	99.50 184	99.53 302	95.41 236	99.84 199	97.17 365	99.64 162	99.44 262

Effi-MVS+		98.81 200	98.59 217	99.48 163	99.46 256	99.12 165	98.08 492	99.50 182	97.50 289	99.38 217	99.41 341	96.37 187	99.81 235	99.11 125	98.54 278	99.51 238

alignmvs		98.81 200	98.56 220	99.58 117	99.43 264	99.42 119	99.51 194	98.96 408	98.61 114	99.35 228	98.92 428	94.78 271	99.77 259	99.35 78	98.11 309	99.54 223

DeepPCF-MVS	98.18 3	98.81 200	99.37 43	97.12 435	99.60 197	91.75 477	98.61 460	99.44 262	99.35 27	99.83 64	99.85 89	98.70 70	99.81 235	99.02 139	99.91 45	99.81 79

PMMVS		98.80 203	98.62 211	99.34 195	99.27 313	98.70 245	98.76 445	99.31 341	97.34 306	99.21 264	99.07 404	97.20 137	99.82 230	98.56 219	98.87 255	99.52 229

icg_test_0407_2		98.79 204	98.86 173	98.57 317	99.55 215	96.93 364	99.07 387	99.44 262	98.05 212	99.66 132	99.80 155	97.13 139	99.18 399	98.15 264	98.92 248	99.60 199

viewdifsd2359ckpt11		98.78 205	98.74 190	98.89 270	99.67 138	97.04 353	99.50 205	99.58 77	98.26 157	99.56 170	99.90 36	94.36 301	99.87 175	99.49 61	98.32 292	99.77 100

viewmsd2359difaftdt		98.78 205	98.74 190	98.90 266	99.67 138	97.04 353	99.50 205	99.58 77	98.26 157	99.56 170	99.90 36	94.36 301	99.87 175	99.49 61	98.32 292	99.77 100

Effi-MVS+-dtu		98.78 205	98.89 166	98.47 335	99.33 295	96.91 369	99.57 145	99.30 346	98.47 128	99.41 208	98.99 418	96.78 163	99.74 269	98.73 189	99.38 183	98.74 346

FIs		98.78 205	98.63 206	99.23 223	99.18 337	99.54 99	99.83 15	99.59 72	98.28 152	98.79 345	99.81 137	96.75 165	99.37 356	99.08 131	96.38 376	98.78 334

Fast-Effi-MVS+-dtu		98.77 209	98.83 180	98.60 312	99.41 271	96.99 359	99.52 184	99.49 195	98.11 196	99.24 256	99.34 365	96.96 152	99.79 248	97.95 283	99.45 179	99.02 315

sd_testset		98.75 210	98.57 218	99.29 211	99.81 57	98.26 284	99.56 153	99.62 51	98.78 99	99.64 147	99.88 58	92.02 372	99.88 168	99.54 51	98.26 296	99.72 138

FA-MVS(test-final)		98.75 210	98.53 222	99.41 183	99.55 215	99.05 175	99.80 25	99.01 402	96.59 374	99.58 166	99.59 278	95.39 237	99.90 148	97.78 300	99.49 177	99.28 285

FC-MVSNet-test		98.75 210	98.62 211	99.15 233	99.08 364	99.45 116	99.86 11	99.60 67	98.23 167	98.70 358	99.82 122	96.80 162	99.22 391	99.07 132	96.38 376	98.79 332

XVG-OURS		98.73 213	98.68 197	98.88 275	99.70 122	97.73 316	98.92 424	99.55 99	98.52 123	99.45 192	99.84 104	95.27 243	99.91 135	98.08 273	98.84 258	99.00 316

Fast-Effi-MVS+		98.70 214	98.43 227	99.51 146	99.51 232	99.28 142	99.52 184	99.47 229	96.11 408	99.01 304	99.34 365	96.20 197	99.84 199	97.88 287	98.82 260	99.39 271

XVG-OURS-SEG-HR		98.69 215	98.62 211	98.89 270	99.71 117	97.74 315	99.12 377	99.54 108	98.44 134	99.42 203	99.71 216	94.20 308	99.92 123	98.54 223	98.90 254	99.00 316

1314		98.68 216	98.54 221	99.11 236	98.89 395	98.65 249	99.27 333	99.49 195	96.89 348	97.99 417	99.56 290	97.72 120	99.83 221	97.74 307	99.27 194	98.84 330

VortexMVS		98.67 217	98.66 201	98.68 307	99.62 180	97.96 303	99.59 127	99.41 278	98.13 186	99.31 235	99.70 220	95.48 235	99.27 376	99.40 72	97.32 355	98.79 332

EI-MVSNet		98.67 217	98.67 198	98.68 307	99.35 289	97.97 301	99.50 205	99.38 296	96.93 347	99.20 268	99.83 111	97.87 114	99.36 360	98.38 240	97.56 334	98.71 350

test_djsdf		98.67 217	98.57 218	98.98 249	98.70 426	98.91 207	99.88 4	99.46 242	97.55 281	99.22 261	99.88 58	95.73 225	99.28 373	99.03 137	97.62 329	98.75 342

QAPM		98.67 217	98.30 237	99.80 64	99.20 331	99.67 68	99.77 35	99.72 14	94.74 436	98.73 350	99.90 36	95.78 222	99.98 20	96.96 376	99.88 74	99.76 107

nrg030		98.64 221	98.42 228	99.28 215	99.05 371	99.69 63	99.81 20	99.46 242	98.04 219	99.01 304	99.82 122	96.69 167	99.38 353	99.34 83	94.59 421	98.78 334

test_vis1_n_1920		98.63 222	98.40 230	99.31 203	99.86 25	97.94 308	99.67 76	99.62 51	99.43 19	99.99 2	99.91 26	87.29 445	100.00 1	99.92 24	99.92 38	99.98 2

PAPR		98.63 222	98.34 233	99.51 146	99.40 276	99.03 177	98.80 441	99.36 307	96.33 389	99.00 308	99.12 402	98.46 88	99.84 199	95.23 428	99.37 190	99.66 172

CVMVSNet		98.57 224	98.67 198	98.30 355	99.35 289	95.59 420	99.50 205	99.55 99	98.60 116	99.39 215	99.83 111	94.48 297	99.45 338	98.75 186	98.56 276	99.85 47

IMVS_0404		98.53 225	98.52 223	98.55 323	99.55 215	96.93 364	99.20 361	99.44 262	98.05 212	98.96 315	99.80 155	94.66 286	99.13 407	98.15 264	98.92 248	99.60 199

MVSTER		98.49 226	98.32 235	99.00 247	99.35 289	99.02 178	99.54 173	99.38 296	97.41 301	99.20 268	99.73 209	93.86 325	99.36 360	98.87 162	97.56 334	98.62 394

FE-MVS		98.48 227	98.17 242	99.40 185	99.54 222	98.96 190	99.68 73	98.81 434	95.54 419	99.62 154	99.70 220	93.82 326	99.93 108	97.35 348	99.46 178	99.32 282

OpenMVS	96.50 16	98.47 228	98.12 249	99.52 141	99.04 373	99.53 102	99.82 16	99.72 14	94.56 439	98.08 412	99.88 58	94.73 279	99.98 20	97.47 337	99.76 140	99.06 310

IterMVS-LS		98.46 229	98.42 228	98.58 316	99.59 199	98.00 299	99.37 291	99.43 273	96.94 346	99.07 293	99.59 278	97.87 114	99.03 426	98.32 249	95.62 399	98.71 350
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 230	98.28 238	98.94 256	98.50 447	98.96 190	99.77 35	99.50 182	97.07 332	98.87 330	99.77 188	94.76 275	99.28 373	98.66 199	97.60 330	98.57 415

jajsoiax		98.43 231	98.28 238	98.88 275	98.60 440	98.43 277	99.82 16	99.53 124	98.19 174	98.63 370	99.80 155	93.22 339	99.44 343	99.22 107	97.50 341	98.77 338

tttt0517		98.42 232	98.14 246	99.28 215	99.66 150	98.38 280	99.74 48	96.85 494	97.68 266	99.79 77	99.74 203	91.39 391	99.89 163	98.83 175	99.56 170	99.57 217

BH-untuned		98.42 232	98.36 231	98.59 313	99.49 246	96.70 377	99.27 333	99.13 384	97.24 316	98.80 343	99.38 352	95.75 224	99.74 269	97.07 370	99.16 205	99.33 281

test_fmvs1_n		98.41 234	98.14 246	99.21 224	99.82 53	97.71 320	99.74 48	99.49 195	99.32 30	99.99 2	99.95 3	85.32 464	99.97 29	99.82 29	99.84 101	99.96 7

D2MVS		98.41 234	98.50 224	98.15 371	99.26 316	96.62 383	99.40 280	99.61 60	97.71 261	98.98 311	99.36 358	96.04 204	99.67 301	98.70 192	97.41 351	98.15 451

BH-RMVSNet		98.41 234	98.08 255	99.40 185	99.41 271	98.83 230	99.30 317	98.77 440	97.70 264	98.94 319	99.65 252	92.91 346	99.74 269	96.52 396	99.55 172	99.64 186

mvs_tets		98.40 237	98.23 240	98.91 264	98.67 431	98.51 268	99.66 83	99.53 124	98.19 174	98.65 367	99.81 137	92.75 348	99.44 343	99.31 88	97.48 345	98.77 338

MonoMVSNet		98.38 238	98.47 226	98.12 373	98.59 442	96.19 400	99.72 54	98.79 438	97.89 235	99.44 197	99.52 306	96.13 200	98.90 453	98.64 201	97.54 336	99.28 285

XXY-MVS		98.38 238	98.09 254	99.24 221	99.26 316	99.32 132	99.56 153	99.55 99	97.45 294	98.71 352	99.83 111	93.23 337	99.63 319	98.88 159	96.32 378	98.76 340

ACMM	97.58 5	98.37 240	98.34 233	98.48 330	99.41 271	97.10 344	99.56 153	99.45 253	98.53 122	99.04 301	99.85 89	93.00 342	99.71 285	98.74 187	97.45 346	98.64 385
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 241	98.03 261	99.31 203	99.63 171	98.56 259	99.54 173	96.75 496	97.53 285	99.73 99	99.65 252	91.25 395	99.89 163	98.62 204	99.56 170	99.48 246

tpmrst		98.33 242	98.48 225	97.90 392	99.16 347	94.78 444	99.31 315	99.11 386	97.27 312	99.45 192	99.59 278	95.33 241	99.84 199	98.48 226	98.61 270	99.09 303

baseline1		98.31 243	97.95 270	99.38 191	99.50 244	98.74 241	99.59 127	98.93 410	98.41 136	99.14 279	99.60 276	94.59 289	99.79 248	98.48 226	93.29 444	99.61 196

PatchmatchNet		98.31 243	98.36 231	98.19 366	99.16 347	95.32 432	99.27 333	98.92 413	97.37 304	99.37 219	99.58 282	94.90 262	99.70 292	97.43 343	99.21 201	99.54 223
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 245	97.98 266	99.26 217	99.57 207	98.16 288	99.41 272	98.55 461	96.03 413	99.19 271	99.74 203	91.87 375	99.92 123	99.16 120	98.29 295	99.70 153

VPA-MVSNet		98.29 246	97.95 270	99.30 208	99.16 347	99.54 99	99.50 205	99.58 77	98.27 154	99.35 228	99.37 355	92.53 360	99.65 309	99.35 78	94.46 422	98.72 348

UniMVSNet (Re)		98.29 246	98.00 264	99.13 235	99.00 378	99.36 127	99.49 222	99.51 158	97.95 229	98.97 313	99.13 399	96.30 192	99.38 353	98.36 244	93.34 443	98.66 381

HQP_MVS		98.27 248	98.22 241	98.44 341	99.29 308	96.97 361	99.39 284	99.47 229	98.97 76	99.11 284	99.61 273	92.71 353	99.69 298	97.78 300	97.63 327	98.67 372

UniMVSNet_NR-MVSNet		98.22 249	97.97 267	98.96 252	98.92 391	98.98 183	99.48 230	99.53 124	97.76 255	98.71 352	99.46 330	96.43 184	99.22 391	98.57 216	92.87 454	98.69 359

LPG-MVS_test		98.22 249	98.13 248	98.49 328	99.33 295	97.05 350	99.58 137	99.55 99	97.46 291	99.24 256	99.83 111	92.58 358	99.72 279	98.09 269	97.51 339	98.68 364

RPSCF		98.22 249	98.62 211	96.99 438	99.82 53	91.58 478	99.72 54	99.44 262	96.61 369	99.66 132	99.89 45	95.92 212	99.82 230	97.46 338	99.10 227	99.57 217

ADS-MVSNet		98.20 252	98.08 255	98.56 321	99.33 295	96.48 388	99.23 352	99.15 381	96.24 396	99.10 287	99.67 245	94.11 313	99.71 285	96.81 384	99.05 236	99.48 246

OPM-MVS		98.19 253	98.10 251	98.45 338	98.88 396	97.07 348	99.28 328	99.38 296	98.57 118	99.22 261	99.81 137	92.12 370	99.66 304	98.08 273	97.54 336	98.61 403
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 253	98.16 243	98.27 361	99.30 304	95.55 421	99.07 387	98.97 406	97.57 278	99.43 200	99.57 287	92.72 351	99.74 269	97.58 321	99.20 203	99.52 229

miper_ehance_all_eth		98.18 255	98.10 251	98.41 344	99.23 324	97.72 317	98.72 450	99.31 341	96.60 372	98.88 327	99.29 378	97.29 132	99.13 407	97.60 319	95.99 387	98.38 438

CR-MVSNet		98.17 256	97.93 273	98.87 279	99.18 337	98.49 271	99.22 356	99.33 327	96.96 342	99.56 170	99.38 352	94.33 304	99.00 435	94.83 435	98.58 273	99.14 296

miper_enhance_ethall		98.16 257	98.08 255	98.41 344	98.96 387	97.72 317	98.45 474	99.32 337	96.95 344	98.97 313	99.17 394	97.06 146	99.22 391	97.86 290	95.99 387	98.29 442

CLD-MVS		98.16 257	98.10 251	98.33 351	99.29 308	96.82 374	98.75 446	99.44 262	97.83 245	99.13 280	99.55 293	92.92 344	99.67 301	98.32 249	97.69 325	98.48 425
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 259	97.79 287	99.19 226	99.50 244	98.50 270	98.61 460	96.82 495	96.95 344	99.54 177	99.43 335	91.66 384	99.86 182	98.08 273	99.51 174	99.22 293

pmmvs4		98.13 260	97.90 275	98.81 291	98.61 438	98.87 221	98.99 410	99.21 374	96.44 384	99.06 298	99.58 282	95.90 214	99.11 413	97.18 364	96.11 383	98.46 430

WR-MVS_H		98.13 260	97.87 280	98.90 266	99.02 375	98.84 227	99.70 59	99.59 72	97.27 312	98.40 390	99.19 393	95.53 232	99.23 384	98.34 246	93.78 439	98.61 403

c3_l		98.12 262	98.04 260	98.38 348	99.30 304	97.69 321	98.81 440	99.33 327	96.67 362	98.83 338	99.34 365	97.11 142	98.99 437	97.58 321	95.34 406	98.48 425

ACMH	97.28 8	98.10 263	97.99 265	98.44 341	99.41 271	96.96 363	99.60 116	99.56 89	98.09 200	98.15 410	99.91 26	90.87 402	99.70 292	98.88 159	97.45 346	98.67 372
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
usedtu_dtu_shiyan1		98.09 264	97.82 284	98.89 270	98.70 426	98.90 212	98.57 463	99.47 229	96.78 354	98.87 330	99.05 408	94.75 276	99.23 384	97.45 340	96.74 366	98.53 419

FE-MVSNET3		98.09 264	97.82 284	98.89 270	98.70 426	98.90 212	98.57 463	99.47 229	96.78 354	98.87 330	99.05 408	94.75 276	99.23 384	97.45 340	96.74 366	98.53 419

Anonymous20240529		98.09 264	97.68 304	99.34 195	99.66 150	98.44 276	99.40 280	99.43 273	93.67 447	99.22 261	99.89 45	90.23 410	99.93 108	99.26 105	98.33 288	99.66 172

CP-MVSNet		98.09 264	97.78 290	99.01 245	98.97 386	99.24 148	99.67 76	99.46 242	97.25 314	98.48 384	99.64 258	93.79 327	99.06 422	98.63 203	94.10 433	98.74 346

dmvs_re		98.08 268	98.16 243	97.85 398	99.55 215	94.67 449	99.70 59	98.92 413	98.15 179	99.06 298	99.35 361	93.67 331	99.25 381	97.77 303	97.25 357	99.64 186

DU-MVS		98.08 268	97.79 287	98.96 252	98.87 399	98.98 183	99.41 272	99.45 253	97.87 237	98.71 352	99.50 313	94.82 266	99.22 391	98.57 216	92.87 454	98.68 364

v2v482		98.06 270	97.77 292	98.92 260	98.90 394	98.82 233	99.57 145	99.36 307	96.65 364	99.19 271	99.35 361	94.20 308	99.25 381	97.72 310	94.97 414	98.69 359

V42		98.06 270	97.79 287	98.86 282	98.98 384	98.84 227	99.69 63	99.34 319	96.53 376	99.30 239	99.37 355	94.67 284	99.32 368	97.57 325	94.66 419	98.42 433

test-LLR		98.06 270	97.90 275	98.55 323	98.79 409	97.10 344	98.67 453	97.75 479	97.34 306	98.61 374	98.85 430	94.45 299	99.45 338	97.25 356	99.38 183	99.10 299

WR-MVS		98.06 270	97.73 299	99.06 239	98.86 402	99.25 147	99.19 363	99.35 314	97.30 310	98.66 361	99.43 335	93.94 320	99.21 396	98.58 213	94.28 428	98.71 350

ACMP	97.20 11	98.06 270	97.94 272	98.45 338	99.37 285	97.01 357	99.44 255	99.49 195	97.54 284	98.45 387	99.79 172	91.95 374	99.72 279	97.91 285	97.49 344	98.62 394
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 275	97.96 268	98.33 351	99.26 316	97.38 331	98.56 467	99.31 341	96.65 364	98.88 327	99.52 306	96.58 174	99.12 412	97.39 345	95.53 403	98.47 427

test1111		98.04 276	98.11 250	97.83 404	99.74 100	93.82 460	99.58 137	95.40 505	99.12 46	99.65 142	99.93 10	90.73 403	99.84 199	99.43 69	99.38 183	99.82 72

ECVR-MVS		98.04 276	98.05 259	98.00 382	99.74 100	94.37 455	99.59 127	94.98 506	99.13 41	99.66 132	99.93 10	90.67 404	99.84 199	99.40 72	99.38 183	99.80 88

EPNet_dtu		98.03 278	97.96 268	98.23 364	98.27 454	95.54 423	99.23 352	98.75 441	99.02 62	97.82 426	99.71 216	96.11 201	99.48 333	93.04 458	99.65 161	99.69 156
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 278	97.76 296	98.84 286	99.39 279	98.98 183	99.40 280	99.38 296	96.67 362	99.07 293	99.28 380	92.93 343	98.98 438	97.10 366	96.65 369	98.56 416

ADS-MVSNet2		98.02 280	98.07 258	97.87 394	99.33 295	95.19 435	99.23 352	99.08 390	96.24 396	99.10 287	99.67 245	94.11 313	98.93 450	96.81 384	99.05 236	99.48 246

HQP-MVS		98.02 280	97.90 275	98.37 349	99.19 334	96.83 372	98.98 413	99.39 288	98.24 164	98.66 361	99.40 345	92.47 362	99.64 313	97.19 362	97.58 332	98.64 385

LTVRE_ROB	97.16 12	98.02 280	97.90 275	98.40 346	99.23 324	96.80 375	99.70 59	99.60 67	97.12 326	98.18 408	99.70 220	91.73 380	99.72 279	98.39 239	97.45 346	98.68 364
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
cl____		98.01 283	97.84 283	98.55 323	99.25 320	97.97 301	98.71 451	99.34 319	96.47 383	98.59 377	99.54 298	95.65 228	99.21 396	97.21 358	95.77 393	98.46 430

DIV-MVS_self_test		98.01 283	97.85 282	98.48 330	99.24 322	97.95 306	98.71 451	99.35 314	96.50 377	98.60 376	99.54 298	95.72 226	99.03 426	97.21 358	95.77 393	98.46 430

miper_lstm_enhance		98.00 285	97.91 274	98.28 360	99.34 294	97.43 329	98.88 429	99.36 307	96.48 381	98.80 343	99.55 293	95.98 207	98.91 451	97.27 354	95.50 404	98.51 423

BH-w/o		98.00 285	97.89 279	98.32 353	99.35 289	96.20 399	99.01 407	98.90 420	96.42 386	98.38 391	99.00 416	95.26 245	99.72 279	96.06 406	98.61 270	99.03 313

v1144		97.98 287	97.69 303	98.85 285	98.87 399	98.66 248	99.54 173	99.35 314	96.27 394	99.23 260	99.35 361	94.67 284	99.23 384	96.73 387	95.16 410	98.68 364

EU-MVSNet		97.98 287	98.03 261	97.81 407	98.72 423	96.65 382	99.66 83	99.66 32	98.09 200	98.35 396	99.82 122	95.25 246	98.01 474	97.41 344	95.30 407	98.78 334

tpmvs		97.98 287	98.02 263	97.84 401	99.04 373	94.73 445	99.31 315	99.20 375	96.10 412	98.76 348	99.42 337	94.94 257	99.81 235	96.97 375	98.45 282	98.97 322

tt0805		97.97 290	97.77 292	98.57 317	99.59 199	96.61 384	99.45 248	99.08 390	98.21 170	98.88 327	99.80 155	88.66 429	99.70 292	98.58 213	97.72 324	99.39 271

NR-MVSNet		97.97 290	97.61 313	99.02 244	98.87 399	99.26 145	99.47 240	99.42 275	97.63 271	97.08 445	99.50 313	95.07 253	99.13 407	97.86 290	93.59 440	98.68 364

v8		97.95 292	97.63 311	98.93 258	98.95 388	98.81 235	99.80 25	99.41 278	96.03 413	99.10 287	99.42 337	94.92 260	99.30 371	96.94 378	94.08 434	98.66 381

Patchmatch-test		97.93 293	97.65 307	98.77 297	99.18 337	97.07 348	99.03 399	99.14 383	96.16 403	98.74 349	99.57 287	94.56 291	99.72 279	93.36 453	99.11 220	99.52 229

PS-CasMVS		97.93 293	97.59 315	98.95 254	98.99 381	99.06 173	99.68 73	99.52 133	97.13 324	98.31 398	99.68 239	92.44 366	99.05 423	98.51 224	94.08 434	98.75 342

TranMVSNet+NR-MVSNet		97.93 293	97.66 306	98.76 298	98.78 412	98.62 254	99.65 89	99.49 195	97.76 255	98.49 383	99.60 276	94.23 307	98.97 445	98.00 280	92.90 452	98.70 355

test_vis1_n		97.92 296	97.44 337	99.34 195	99.53 223	98.08 295	99.74 48	99.49 195	99.15 38	100.00 1	99.94 6	79.51 486	99.98 20	99.88 26	99.76 140	99.97 4

v144192		97.92 296	97.60 314	98.87 279	98.83 406	98.65 249	99.55 168	99.34 319	96.20 399	99.32 234	99.40 345	94.36 301	99.26 379	96.37 403	95.03 413	98.70 355

ACMH+	97.24 10	97.92 296	97.78 290	98.32 353	99.46 256	96.68 381	99.56 153	99.54 108	98.41 136	97.79 428	99.87 73	90.18 412	99.66 304	98.05 277	97.18 361	98.62 394

LFMVS		97.90 299	97.35 349	99.54 126	99.52 229	99.01 180	99.39 284	98.24 470	97.10 330	99.65 142	99.79 172	84.79 467	99.91 135	99.28 99	98.38 285	99.69 156

reproduce_monomvs		97.89 300	97.87 280	97.96 387	99.51 232	95.45 427	99.60 116	99.25 364	99.17 36	98.85 337	99.49 316	89.29 421	99.64 313	99.35 78	96.31 379	98.78 334

Anonymous20231211		97.88 301	97.54 319	98.90 266	99.71 117	98.53 262	99.48 230	99.57 84	94.16 442	98.81 341	99.68 239	93.23 337	99.42 349	98.84 172	94.42 425	98.76 340

OurMVSNet-221017-0		97.88 301	97.77 292	98.19 366	98.71 425	96.53 386	99.88 4	99.00 403	97.79 251	98.78 346	99.94 6	91.68 381	99.35 363	97.21 358	96.99 365	98.69 359

v7n		97.87 303	97.52 321	98.92 260	98.76 419	98.58 258	99.84 12	99.46 242	96.20 399	98.91 322	99.70 220	94.89 263	99.44 343	96.03 407	93.89 437	98.75 342

baseline2		97.87 303	97.55 316	98.82 288	99.18 337	98.02 298	99.41 272	96.58 500	96.97 341	96.51 452	99.17 394	93.43 332	99.57 325	97.71 311	99.03 239	98.86 328

thres600view7		97.86 305	97.51 323	98.92 260	99.72 111	97.95 306	99.59 127	98.74 444	97.94 230	99.27 249	98.62 441	91.75 378	99.86 182	93.73 448	98.19 303	98.96 324

UBG		97.85 306	97.48 326	98.95 254	99.25 320	97.64 322	99.24 349	98.74 444	97.90 234	98.64 368	98.20 459	88.65 430	99.81 235	98.27 252	98.40 283	99.42 264

cl22		97.85 306	97.64 310	98.48 330	99.09 361	97.87 310	98.60 462	99.33 327	97.11 329	98.87 330	99.22 389	92.38 367	99.17 401	98.21 256	95.99 387	98.42 433

v10		97.85 306	97.52 321	98.86 282	98.99 381	98.67 247	99.75 43	99.41 278	95.70 417	98.98 311	99.41 341	94.75 276	99.23 384	96.01 409	94.63 420	98.67 372

GA-MVS		97.85 306	97.47 329	99.00 247	99.38 282	97.99 300	98.57 463	99.15 381	97.04 337	98.90 324	99.30 376	89.83 415	99.38 353	96.70 389	98.33 288	99.62 194

testing3-2		97.84 310	97.70 302	98.24 363	99.53 223	95.37 431	99.55 168	98.67 455	98.46 129	99.27 249	99.34 365	86.58 452	99.83 221	99.32 86	98.63 269	99.52 229

tfpnnormal		97.84 310	97.47 329	98.98 249	99.20 331	99.22 150	99.64 97	99.61 60	96.32 390	98.27 402	99.70 220	93.35 336	99.44 343	95.69 416	95.40 405	98.27 443

VPNet		97.84 310	97.44 337	99.01 245	99.21 329	98.94 200	99.48 230	99.57 84	98.38 138	99.28 243	99.73 209	88.89 424	99.39 351	99.19 111	93.27 445	98.71 350

LCM-MVSNet-Re		97.83 313	98.15 245	96.87 444	99.30 304	92.25 475	99.59 127	98.26 468	97.43 298	96.20 456	99.13 399	96.27 193	98.73 460	98.17 261	98.99 243	99.64 186

XVG-ACMP-BASELINE		97.83 313	97.71 301	98.20 365	99.11 355	96.33 393	99.41 272	99.52 133	98.06 209	99.05 300	99.50 313	89.64 418	99.73 275	97.73 308	97.38 353	98.53 419

IterMVS		97.83 313	97.77 292	98.02 379	99.58 201	96.27 396	99.02 402	99.48 207	97.22 318	98.71 352	99.70 220	92.75 348	99.13 407	97.46 338	96.00 386	98.67 372
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 316	97.75 297	98.06 376	99.57 207	96.36 392	99.02 402	99.49 195	97.18 320	98.71 352	99.72 213	92.72 351	99.14 404	97.44 342	95.86 392	98.67 372

EPMVS		97.82 316	97.65 307	98.35 350	98.88 396	95.98 403	99.49 222	94.71 510	97.57 278	99.26 254	99.48 323	92.46 365	99.71 285	97.87 289	99.08 233	99.35 277

MVP-Stereo		97.81 318	97.75 297	97.99 383	97.53 470	96.60 385	98.96 417	98.85 429	97.22 318	97.23 439	99.36 358	95.28 242	99.46 336	95.51 420	99.78 134	97.92 468
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 318	97.44 337	98.91 264	98.88 396	98.68 246	99.51 194	99.34 319	96.18 401	99.20 268	99.34 365	94.03 317	99.36 360	95.32 426	95.18 409	98.69 359

ttmdpeth		97.80 320	97.63 311	98.29 356	98.77 417	97.38 331	99.64 97	99.36 307	98.78 99	96.30 455	99.58 282	92.34 369	99.39 351	98.36 244	95.58 400	98.10 453

v1921920		97.80 320	97.45 332	98.84 286	98.80 408	98.53 262	99.52 184	99.34 319	96.15 405	99.24 256	99.47 326	93.98 319	99.29 372	95.40 424	95.13 411	98.69 359

v148		97.79 322	97.55 316	98.50 327	98.74 420	97.72 317	99.54 173	99.33 327	96.26 395	98.90 324	99.51 310	94.68 283	99.14 404	97.83 294	93.15 449	98.63 392

thres400		97.77 323	97.38 345	98.92 260	99.69 128	97.96 303	99.50 205	98.73 450	97.83 245	99.17 276	98.45 448	91.67 382	99.83 221	93.22 455	98.18 304	98.96 324

thres100view900		97.76 324	97.45 332	98.69 306	99.72 111	97.86 312	99.59 127	98.74 444	97.93 231	99.26 254	98.62 441	91.75 378	99.83 221	93.22 455	98.18 304	98.37 439

PEN-MVS		97.76 324	97.44 337	98.72 301	98.77 417	98.54 261	99.78 33	99.51 158	97.06 334	98.29 401	99.64 258	92.63 357	98.89 454	98.09 269	93.16 448	98.72 348

Baseline_NR-MVSNet		97.76 324	97.45 332	98.68 307	99.09 361	98.29 282	99.41 272	98.85 429	95.65 418	98.63 370	99.67 245	94.82 266	99.10 416	98.07 276	92.89 453	98.64 385

TR-MVS		97.76 324	97.41 343	98.82 288	99.06 367	97.87 310	98.87 431	98.56 459	96.63 368	98.68 360	99.22 389	92.49 361	99.65 309	95.40 424	97.79 322	98.95 326

Patchmtry		97.75 328	97.40 344	98.81 291	99.10 358	98.87 221	99.11 383	99.33 327	94.83 434	98.81 341	99.38 352	94.33 304	99.02 430	96.10 405	95.57 401	98.53 419

dp		97.75 328	97.80 286	97.59 422	99.10 358	93.71 463	99.32 311	98.88 424	96.48 381	99.08 292	99.55 293	92.67 356	99.82 230	96.52 396	98.58 273	99.24 291

WBMVS		97.74 330	97.50 324	98.46 336	99.24 322	97.43 329	99.21 358	99.42 275	97.45 294	98.96 315	99.41 341	88.83 425	99.23 384	98.94 150	96.02 384	98.71 350

TAPA-MVS	97.07 15	97.74 330	97.34 352	98.94 256	99.70 122	97.53 325	99.25 344	99.51 158	91.90 472	99.30 239	99.63 264	98.78 53	99.64 313	88.09 484	99.87 78	99.65 179
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 332	97.35 349	98.88 275	99.47 254	97.12 343	99.34 306	98.85 429	98.19 174	99.67 127	99.85 89	82.98 475	99.92 123	99.49 61	98.32 292	99.60 199

MIMVSNet		97.73 332	97.45 332	98.57 317	99.45 262	97.50 327	99.02 402	98.98 405	96.11 408	99.41 208	99.14 398	90.28 406	98.74 459	95.74 414	98.93 246	99.47 252

tfpn200view9		97.72 334	97.38 345	98.72 301	99.69 128	97.96 303	99.50 205	98.73 450	97.83 245	99.17 276	98.45 448	91.67 382	99.83 221	93.22 455	98.18 304	98.37 439

CostFormer		97.72 334	97.73 299	97.71 414	99.15 351	94.02 459	99.54 173	99.02 401	94.67 437	99.04 301	99.35 361	92.35 368	99.77 259	98.50 225	97.94 314	99.34 280

FMVSNet2		97.72 334	97.36 347	98.80 293	99.51 232	98.84 227	99.45 248	99.42 275	96.49 378	98.86 336	99.29 378	90.26 407	98.98 438	96.44 398	96.56 372	98.58 413

test0.0.03 1		97.71 337	97.42 342	98.56 321	98.41 452	97.82 313	98.78 443	98.63 457	97.34 306	98.05 416	98.98 420	94.45 299	98.98 438	95.04 431	97.15 362	98.89 327

h-mvs33		97.70 338	97.28 361	98.97 251	99.70 122	97.27 335	99.36 297	99.45 253	98.94 79	99.66 132	99.64 258	94.93 258	99.99 4	99.48 64	84.36 489	99.65 179

myMVS_eth3d28		97.69 339	97.34 352	98.73 299	99.27 313	97.52 326	99.33 308	98.78 439	98.03 221	98.82 340	98.49 446	86.64 451	99.46 336	98.44 233	98.24 298	99.23 292

v1240		97.69 339	97.32 356	98.79 294	98.85 403	98.43 277	99.48 230	99.36 307	96.11 408	99.27 249	99.36 358	93.76 329	99.24 383	94.46 438	95.23 408	98.70 355

cascas		97.69 339	97.43 341	98.48 330	98.60 440	97.30 333	98.18 487	99.39 288	92.96 459	98.41 389	98.78 437	93.77 328	99.27 376	98.16 262	98.61 270	98.86 328

pm-mvs1		97.68 342	97.28 361	98.88 275	99.06 367	98.62 254	99.50 205	99.45 253	96.32 390	97.87 424	99.79 172	92.47 362	99.35 363	97.54 328	93.54 441	98.67 372

GBi-Net		97.68 342	97.48 326	98.29 356	99.51 232	97.26 337	99.43 261	99.48 207	96.49 378	99.07 293	99.32 373	90.26 407	98.98 438	97.10 366	96.65 369	98.62 394

test1		97.68 342	97.48 326	98.29 356	99.51 232	97.26 337	99.43 261	99.48 207	96.49 378	99.07 293	99.32 373	90.26 407	98.98 438	97.10 366	96.65 369	98.62 394

tpm		97.67 345	97.55 316	98.03 377	99.02 375	95.01 440	99.43 261	98.54 462	96.44 384	99.12 282	99.34 365	91.83 377	99.60 322	97.75 306	96.46 374	99.48 246

PCF-MVS	97.08 14	97.66 346	97.06 374	99.47 169	99.61 191	99.09 167	98.04 493	99.25 364	91.24 476	98.51 381	99.70 220	94.55 293	99.91 135	92.76 463	99.85 93	99.42 264
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 347	97.65 307	97.63 417	98.78 412	97.62 323	99.13 374	98.33 466	97.36 305	99.07 293	98.94 424	95.64 229	99.15 402	92.95 459	98.68 268	96.12 499

our_test_3		97.65 347	97.68 304	97.55 423	98.62 436	94.97 441	98.84 436	99.30 346	96.83 353	98.19 407	99.34 365	97.01 150	99.02 430	95.00 432	96.01 385	98.64 385

testgi		97.65 347	97.50 324	98.13 372	99.36 288	96.45 389	99.42 268	99.48 207	97.76 255	97.87 424	99.45 332	91.09 399	98.81 456	94.53 437	98.52 279	99.13 298

thres200		97.61 350	97.28 361	98.62 311	99.64 166	98.03 297	99.26 342	98.74 444	97.68 266	99.09 290	98.32 454	91.66 384	99.81 235	92.88 460	98.22 299	98.03 458

PAPM		97.59 351	97.09 373	99.07 238	99.06 367	98.26 284	98.30 482	99.10 387	94.88 432	98.08 412	99.34 365	96.27 193	99.64 313	89.87 476	98.92 248	99.31 283

UWE-MVS		97.58 352	97.29 360	98.48 330	99.09 361	96.25 397	99.01 407	96.61 499	97.86 238	99.19 271	99.01 415	88.72 426	99.90 148	97.38 346	98.69 267	99.28 285

SD_0403		97.55 353	97.53 320	97.62 418	99.61 191	93.64 466	99.72 54	99.44 262	98.03 221	98.62 373	99.39 349	96.06 203	99.57 325	87.88 486	99.01 242	99.66 172

VDDNet		97.55 353	97.02 375	99.16 229	99.49 246	98.12 293	99.38 289	99.30 346	95.35 421	99.68 121	99.90 36	82.62 477	99.93 108	99.31 88	98.13 308	99.42 264

TESTMET0.1,1		97.55 353	97.27 364	98.40 346	98.93 389	96.53 386	98.67 453	97.61 484	96.96 342	98.64 368	99.28 380	88.63 432	99.45 338	97.30 352	99.38 183	99.21 294

pmmvs5		97.52 356	97.30 358	98.16 368	98.57 443	96.73 376	99.27 333	98.90 420	96.14 406	98.37 392	99.53 302	91.54 387	99.14 404	97.51 332	95.87 391	98.63 392

LF4IMVS		97.52 356	97.46 331	97.70 415	98.98 384	95.55 421	99.29 322	98.82 432	98.07 205	98.66 361	99.64 258	89.97 413	99.61 321	97.01 371	96.68 368	97.94 466

DTE-MVSNet		97.51 358	97.19 367	98.46 336	98.63 435	98.13 291	99.84 12	99.48 207	96.68 361	97.97 419	99.67 245	92.92 344	98.56 463	96.88 383	92.60 458	98.70 355

testing11		97.50 359	97.10 372	98.71 304	99.20 331	96.91 369	99.29 322	98.82 432	97.89 235	98.21 406	98.40 450	85.63 460	99.83 221	98.45 232	98.04 311	99.37 275

ETVMVS		97.50 359	96.90 379	99.29 211	99.23 324	98.78 239	99.32 311	98.90 420	97.52 287	98.56 378	98.09 466	84.72 468	99.69 298	97.86 290	97.88 317	99.39 271

hse-mvs2		97.50 359	97.14 369	98.59 313	99.49 246	97.05 350	99.28 328	99.22 370	98.94 79	99.66 132	99.42 337	94.93 258	99.65 309	99.48 64	83.80 493	99.08 304

SixPastTwentyTwo		97.50 359	97.33 355	98.03 377	98.65 433	96.23 398	99.77 35	98.68 453	97.14 323	97.90 422	99.93 10	90.45 405	99.18 399	97.00 372	96.43 375	98.67 372

JIA-IIPM		97.50 359	97.02 375	98.93 258	98.73 421	97.80 314	99.30 317	98.97 406	91.73 473	98.91 322	94.86 501	95.10 252	99.71 285	97.58 321	97.98 312	99.28 285

ppachtmachnet_test		97.49 364	97.45 332	97.61 421	98.62 436	95.24 433	98.80 441	99.46 242	96.11 408	98.22 405	99.62 269	96.45 182	98.97 445	93.77 446	95.97 390	98.61 403

test-mter		97.49 364	97.13 371	98.55 323	98.79 409	97.10 344	98.67 453	97.75 479	96.65 364	98.61 374	98.85 430	88.23 436	99.45 338	97.25 356	99.38 183	99.10 299

testing91		97.44 366	97.02 375	98.71 304	99.18 337	96.89 371	99.19 363	99.04 397	97.78 253	98.31 398	98.29 455	85.41 463	99.85 190	98.01 279	97.95 313	99.39 271

tpm2		97.44 366	97.34 352	97.74 413	99.15 351	94.36 456	99.45 248	98.94 409	93.45 453	98.90 324	99.44 333	91.35 392	99.59 323	97.31 349	98.07 310	99.29 284

tpm cat1		97.39 368	97.36 347	97.50 425	99.17 345	93.73 462	99.43 261	99.31 341	91.27 475	98.71 352	99.08 403	94.31 306	99.77 259	96.41 401	98.50 280	99.00 316

UWE-MVS-28		97.36 369	97.24 365	97.75 411	98.84 405	94.44 453	99.24 349	97.58 486	97.98 227	99.00 308	99.00 416	91.35 392	99.53 331	93.75 447	98.39 284	99.27 289

testing99		97.36 369	96.94 378	98.63 310	99.18 337	96.70 377	99.30 317	98.93 410	97.71 261	98.23 403	98.26 457	84.92 466	99.84 199	98.04 278	97.85 320	99.35 277

SSC-MVS3.2		97.34 371	97.15 368	97.93 389	99.02 375	95.76 415	99.48 230	99.58 77	97.62 273	99.09 290	99.53 302	87.95 439	99.27 376	96.42 399	95.66 398	98.75 342

USDC		97.34 371	97.20 366	97.75 411	99.07 365	95.20 434	98.51 470	99.04 397	97.99 226	98.31 398	99.86 82	89.02 422	99.55 329	95.67 418	97.36 354	98.49 424

UniMVSNet_ETH3D		97.32 373	96.81 381	98.87 279	99.40 276	97.46 328	99.51 194	99.53 124	95.86 416	98.54 380	99.77 188	82.44 478	99.66 304	98.68 197	97.52 338	99.50 242

testing3		97.28 374	96.76 383	98.82 288	99.37 285	98.07 296	99.45 248	99.36 307	97.56 280	97.89 423	98.95 423	83.70 472	98.82 455	96.03 407	98.56 276	99.58 214

MVS		97.28 374	96.55 387	99.48 163	98.78 412	98.95 196	99.27 333	99.39 288	83.53 496	98.08 412	99.54 298	96.97 151	99.87 175	94.23 442	99.16 205	99.63 191

test_fmvs2		97.25 376	97.30 358	97.09 436	99.43 264	93.31 469	99.73 52	98.87 426	98.83 89	99.28 243	99.80 155	84.45 469	99.66 304	97.88 287	97.45 346	98.30 441

DSMNet-mixed		97.25 376	97.35 349	96.95 441	97.84 464	93.61 467	99.57 145	96.63 498	96.13 407	98.87 330	98.61 443	94.59 289	97.70 482	95.08 430	98.86 256	99.55 221

MS-PatchMatch		97.24 378	97.32 356	96.99 438	98.45 450	93.51 468	98.82 439	99.32 337	97.41 301	98.13 411	99.30 376	88.99 423	99.56 327	95.68 417	99.80 125	97.90 470

testing222		97.16 379	96.50 388	99.16 229	99.16 347	98.47 275	99.27 333	98.66 456	97.71 261	98.23 403	98.15 461	82.28 480	99.84 199	97.36 347	97.66 326	99.18 295

TransMVSNet (Re)		97.15 380	96.58 386	98.86 282	99.12 353	98.85 225	99.49 222	98.91 418	95.48 420	97.16 443	99.80 155	93.38 333	99.11 413	94.16 444	91.73 462	98.62 394

TinyColmap		97.12 381	96.89 380	97.83 404	99.07 365	95.52 424	98.57 463	98.74 444	97.58 277	97.81 427	99.79 172	88.16 437	99.56 327	95.10 429	97.21 359	98.39 437

K. test v3		97.10 382	96.79 382	98.01 380	98.72 423	96.33 393	99.87 8	97.05 491	97.59 275	96.16 457	99.80 155	88.71 427	99.04 424	96.69 390	96.55 373	98.65 383

Syy-MVS		97.09 383	97.14 369	96.95 441	99.00 378	92.73 473	99.29 322	99.39 288	97.06 334	97.41 433	98.15 461	93.92 322	98.68 461	91.71 469	98.34 286	99.45 260

PatchT		97.03 384	96.44 390	98.79 294	98.99 381	98.34 281	99.16 367	99.07 393	92.13 470	99.52 181	97.31 487	94.54 294	98.98 438	88.54 482	98.73 265	99.03 313

mmtdpeth		96.95 385	96.71 384	97.67 416	99.33 295	94.90 443	99.89 2	99.28 352	98.15 179	99.72 104	98.57 444	86.56 453	99.90 148	99.82 29	89.02 480	98.20 448

myMVS_eth3d		96.89 386	96.37 391	98.43 343	99.00 378	97.16 341	99.29 322	99.39 288	97.06 334	97.41 433	98.15 461	83.46 474	98.68 461	95.27 427	98.34 286	99.45 260

AUN-MVS		96.88 387	96.31 393	98.59 313	99.48 253	97.04 353	99.27 333	99.22 370	97.44 297	98.51 381	99.41 341	91.97 373	99.66 304	97.71 311	83.83 492	99.07 309

FMVSNet1		96.84 388	96.36 392	98.29 356	99.32 302	97.26 337	99.43 261	99.48 207	95.11 425	98.55 379	99.32 373	83.95 471	98.98 438	95.81 412	96.26 380	98.62 394

test2506		96.81 389	96.65 385	97.29 431	99.74 100	92.21 476	99.60 116	85.06 527	99.13 41	99.77 86	99.93 10	87.82 443	99.85 190	99.38 76	99.38 183	99.80 88

RPMNet		96.72 390	95.90 403	99.19 226	99.18 337	98.49 271	99.22 356	99.52 133	88.72 486	99.56 170	97.38 483	94.08 315	99.95 76	86.87 493	98.58 273	99.14 296

mvs5depth		96.66 391	96.22 395	97.97 385	97.00 483	96.28 395	98.66 456	99.03 400	96.61 369	96.93 449	99.79 172	87.20 446	99.47 334	96.65 394	94.13 431	98.16 450

test_0402		96.64 392	96.24 394	97.85 398	98.85 403	96.43 390	99.44 255	99.26 361	93.52 450	96.98 447	99.52 306	88.52 433	99.20 398	92.58 466	97.50 341	97.93 467

X-MVStestdata		96.55 393	95.45 412	99.87 22	99.85 31	99.83 22	99.69 63	99.68 24	98.98 72	99.37 219	64.01 535	98.81 49	99.94 91	98.79 183	99.86 86	99.84 54

pmmvs6		96.53 394	96.09 399	97.82 406	98.69 429	95.47 425	99.37 291	99.47 229	93.46 452	97.41 433	99.78 179	87.06 450	99.33 366	96.92 381	92.70 456	98.65 383

ET-MVSNet_ETH3D		96.49 395	95.64 409	99.05 241	99.53 223	98.82 233	98.84 436	97.51 487	97.63 271	84.77 504	99.21 392	92.09 371	98.91 451	98.98 142	92.21 460	99.41 267

UnsupCasMVSNet_eth		96.44 396	96.12 397	97.40 428	98.65 433	95.65 418	99.36 297	99.51 158	97.13 324	96.04 459	98.99 418	88.40 434	98.17 470	96.71 388	90.27 473	98.40 436

FMVSNet5		96.43 397	96.19 396	97.15 432	99.11 355	95.89 410	99.32 311	99.52 133	94.47 441	98.34 397	99.07 404	87.54 444	97.07 488	92.61 465	95.72 396	98.47 427

new_pmnet		96.38 398	96.03 400	97.41 427	98.13 459	95.16 437	99.05 394	99.20 375	93.94 443	97.39 436	98.79 436	91.61 386	99.04 424	90.43 474	95.77 393	98.05 457

Anonymous20231206		96.22 399	96.03 400	96.79 446	97.31 476	94.14 458	99.63 103	99.08 390	96.17 402	97.04 446	99.06 406	93.94 320	97.76 480	86.96 492	95.06 412	98.47 427

IB-MVS	95.67 18	96.22 399	95.44 413	98.57 317	99.21 329	96.70 377	98.65 457	97.74 481	96.71 359	97.27 438	98.54 445	86.03 457	99.92 123	98.47 229	86.30 486	99.10 299
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
Anonymous20240521		96.20 401	95.89 404	97.13 434	97.72 469	94.96 442	99.79 31	99.29 350	93.01 457	97.20 442	99.03 412	89.69 417	98.36 467	91.16 472	96.13 382	98.07 455

gg-mvs-nofinetune		96.17 402	95.32 414	98.73 299	98.79 409	98.14 290	99.38 289	94.09 512	91.07 478	98.07 415	91.04 514	89.62 419	99.35 363	96.75 386	99.09 232	98.68 364

test20.03		96.12 403	95.96 402	96.63 447	97.44 471	95.45 427	99.51 194	99.38 296	96.55 375	96.16 457	99.25 386	93.76 329	96.17 497	87.35 489	94.22 429	98.27 443

PVSNet_0	94.43 19	96.09 404	95.47 411	97.94 388	99.31 303	94.34 457	97.81 497	99.70 18	97.12 326	97.46 432	98.75 438	89.71 416	99.79 248	97.69 315	81.69 501	99.68 162

MVStest1		96.08 405	95.48 410	97.89 393	98.93 389	96.70 377	99.56 153	99.35 314	92.69 462	91.81 489	99.46 330	89.90 414	98.96 447	95.00 432	92.61 457	98.00 462

EG-PatchMatch MVS		95.97 406	95.69 407	96.81 445	97.78 466	92.79 472	99.16 367	98.93 410	96.16 403	94.08 475	99.22 389	82.72 476	99.47 334	95.67 418	97.50 341	98.17 449

APD_test1		95.87 407	96.49 389	94.00 464	99.53 223	84.01 494	99.54 173	99.32 337	95.91 415	97.99 417	99.85 89	85.49 462	99.88 168	91.96 467	98.84 258	98.12 452

Patchmatch-RL test		95.84 408	95.81 406	95.95 455	95.61 499	90.57 483	98.24 483	98.39 464	95.10 427	95.20 464	98.67 440	94.78 271	97.77 479	96.28 404	90.02 474	99.51 238

test_vis1_rt		95.81 409	95.65 408	96.32 451	99.67 138	91.35 479	99.49 222	96.74 497	98.25 162	95.24 462	98.10 465	74.96 488	99.90 148	99.53 53	98.85 257	97.70 476

sc_t1		95.75 410	95.05 417	97.87 394	98.83 406	94.61 450	99.21 358	99.45 253	87.45 488	97.97 419	99.85 89	81.19 483	99.43 347	98.27 252	93.20 447	99.57 217

MVS-HIRNet		95.75 410	95.16 415	97.51 424	99.30 304	93.69 464	98.88 429	95.78 502	85.09 495	98.78 346	92.65 510	91.29 394	99.37 356	94.85 434	99.85 93	99.46 257

tt0320		95.71 412	95.07 416	97.62 418	99.05 371	95.02 439	99.25 344	99.52 133	86.81 489	97.97 419	99.72 213	83.58 473	99.15 402	96.38 402	93.35 442	98.68 364

blended_shiyan8		95.56 413	94.79 420	97.87 394	96.60 487	95.90 409	98.85 432	99.27 359	92.19 465	98.47 385	97.94 470	91.43 389	99.11 413	97.26 355	81.09 504	98.60 406

blended_shiyan6		95.54 414	94.78 421	97.84 401	96.60 487	95.89 410	98.85 432	99.28 352	92.17 469	98.43 388	97.95 469	91.44 388	99.02 430	97.30 352	80.97 505	98.60 406

MIMVSNet1		95.51 415	95.04 418	96.92 443	97.38 473	95.60 419	99.52 184	99.50 182	93.65 448	96.97 448	99.17 394	85.28 465	96.56 494	88.36 483	95.55 402	98.60 406

MDA-MVSNet_test_wron		95.45 416	94.60 425	98.01 380	98.16 458	97.21 340	99.11 383	99.24 367	93.49 451	80.73 513	98.98 420	93.02 341	98.18 469	94.22 443	94.45 424	98.64 385

wanda-best-256-512		95.43 417	94.66 423	97.77 409	96.45 489	95.68 416	98.48 471	99.28 352	92.18 467	98.36 393	97.68 475	91.20 396	99.03 426	97.31 349	80.97 505	98.60 406

FE-blended-shiyan7		95.43 417	94.66 423	97.77 409	96.45 489	95.68 416	98.48 471	99.28 352	92.18 467	98.36 393	97.68 475	91.20 396	99.03 426	97.31 349	80.97 505	98.60 406

TDRefinement		95.42 419	94.57 428	97.97 385	89.83 529	96.11 402	99.48 230	98.75 441	96.74 357	96.68 451	99.88 58	88.65 430	99.71 285	98.37 242	82.74 499	98.09 454

gbinet_0.2-2-1-0.02		95.40 420	94.58 427	97.85 398	96.11 494	95.97 404	98.56 467	99.26 361	92.12 471	98.47 385	97.49 481	90.23 410	99.00 435	97.71 311	81.25 502	98.58 413

YYNet1		95.36 421	94.51 429	97.92 390	97.89 462	97.10 344	99.10 385	99.23 368	93.26 455	80.77 512	99.04 411	92.81 347	98.02 473	94.30 439	94.18 430	98.64 385

pmmvs-eth3d		95.34 422	94.73 422	97.15 432	95.53 501	95.94 406	99.35 302	99.10 387	95.13 423	93.55 479	97.54 480	88.15 438	97.91 476	94.58 436	89.69 478	97.61 478

tt0320-xc		95.31 423	94.59 426	97.45 426	98.92 391	94.73 445	99.20 361	99.31 341	86.74 490	97.23 439	99.72 213	81.14 484	98.95 448	97.08 369	91.98 461	98.67 372

blend_shiyan4		95.25 424	94.39 431	97.84 401	96.70 486	95.92 407	98.84 436	99.28 352	92.21 464	98.16 409	97.84 472	87.10 449	99.07 419	97.53 329	81.87 500	98.54 417

0.4-1-1-0.1		95.23 425	94.22 433	98.26 362	97.39 472	95.86 412	97.59 501	97.62 482	93.85 445	94.97 469	97.03 489	87.20 446	99.87 175	98.47 229	83.84 491	99.05 311

FE-MVSNET2		95.10 426	94.44 430	97.08 437	95.08 505	95.97 404	99.51 194	99.37 305	95.02 429	94.10 474	97.57 478	86.18 456	97.66 484	93.28 454	89.86 476	97.61 478

usedtu_blend_shiyan5		95.04 427	94.10 434	97.86 397	96.45 489	95.92 407	99.29 322	99.22 370	86.17 493	98.36 393	97.68 475	91.20 396	99.07 419	97.53 329	80.97 505	98.60 406

dmvs_testset		95.02 428	96.12 397	91.72 474	99.10 358	80.43 507	99.58 137	97.87 478	97.47 290	95.22 463	98.82 432	93.99 318	95.18 502	88.09 484	94.91 417	99.56 220

KD-MVS_self_test		95.00 429	94.34 432	96.96 440	97.07 482	95.39 430	99.56 153	99.44 262	95.11 425	97.13 444	97.32 486	91.86 376	97.27 487	90.35 475	81.23 503	98.23 447

MDA-MVSNet-bldmvs		94.96 430	93.98 437	97.92 390	98.24 455	97.27 335	99.15 370	99.33 327	93.80 446	80.09 514	99.03 412	88.31 435	97.86 478	93.49 451	94.36 426	98.62 394

N_pmnet		94.95 431	95.83 405	92.31 472	98.47 448	79.33 511	99.12 377	92.81 518	93.87 444	97.68 429	99.13 399	93.87 324	99.01 433	91.38 471	96.19 381	98.59 412

0.4-1-1-0.2		94.94 432	93.92 439	97.99 383	96.84 485	95.13 438	96.64 507	97.62 482	93.45 453	94.92 470	96.56 493	87.14 448	99.86 182	98.43 236	83.69 495	98.98 320

0.3-1-1-0.015		94.79 433	93.69 445	98.10 374	96.99 484	95.46 426	97.02 505	97.61 484	93.53 449	94.03 476	96.54 494	85.60 461	99.86 182	98.43 236	83.45 496	98.99 319

KD-MVS_2432*1600		94.62 434	93.72 442	97.31 429	97.19 479	95.82 413	98.34 478	99.20 375	95.00 430	97.57 430	98.35 452	87.95 439	98.10 471	92.87 461	77.00 514	98.01 459

miper_refine_blended		94.62 434	93.72 442	97.31 429	97.19 479	95.82 413	98.34 478	99.20 375	95.00 430	97.57 430	98.35 452	87.95 439	98.10 471	92.87 461	77.00 514	98.01 459

CL-MVSNet_self_test		94.49 436	93.97 438	96.08 453	96.16 493	93.67 465	98.33 480	99.38 296	95.13 423	97.33 437	98.15 461	92.69 355	96.57 493	88.67 481	79.87 512	97.99 463

new-patchmatchnet		94.48 437	94.08 436	95.67 457	95.08 505	92.41 474	99.18 365	99.28 352	94.55 440	93.49 480	97.37 484	87.86 442	97.01 490	91.57 470	88.36 481	97.61 478

OpenMVS_ROB	92.34 20	94.38 438	93.70 444	96.41 450	97.38 473	93.17 470	99.06 391	98.75 441	86.58 491	94.84 471	98.26 457	81.53 481	99.32 368	89.01 480	97.87 318	96.76 490

RoMa-SfM		94.36 439	93.86 440	95.88 456	98.61 438	90.62 482	98.85 432	99.04 397	91.63 474	94.14 473	99.49 316	77.16 487	99.09 418	92.66 464	93.13 450	97.91 469

CMPMVS	69.68 23	94.13 440	94.90 419	91.84 473	97.24 477	80.01 508	98.52 469	99.48 207	89.01 484	91.99 488	99.67 245	85.67 459	99.13 407	95.44 422	97.03 364	96.39 496
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 441	93.25 448	96.60 448	94.76 508	94.49 452	98.92 424	98.18 474	89.66 480	96.48 453	98.06 467	86.28 455	97.33 486	89.68 477	87.20 485	97.97 465

FE-MVSNET		94.07 442	93.36 447	96.22 452	94.05 512	94.71 447	99.56 153	98.36 465	93.15 456	93.76 478	97.55 479	86.47 454	96.49 495	87.48 487	89.83 477	97.48 483

mvsany_test3		93.77 443	93.45 446	94.74 462	95.78 497	88.01 488	99.64 97	98.25 469	98.28 152	94.31 472	97.97 468	68.89 503	98.51 465	97.50 333	90.37 471	97.71 473

UnsupCasMVSNet_bld		93.53 444	92.51 450	96.58 449	97.38 473	93.82 460	98.24 483	99.48 207	91.10 477	93.10 481	96.66 492	74.89 490	98.37 466	94.03 445	87.71 484	97.56 481

dongtai		93.26 445	92.93 449	94.25 463	99.39 279	85.68 492	97.68 499	93.27 514	92.87 460	96.85 450	99.39 349	82.33 479	97.48 485	76.78 506	97.80 321	99.58 214

LoFTR		93.25 446	92.33 452	95.99 454	97.91 460	90.83 480	99.06 391	98.56 459	92.19 465	90.24 493	98.18 460	72.97 491	99.26 379	89.37 478	92.52 459	97.89 471

DKM		93.17 447	92.50 451	95.21 460	98.53 446	90.26 484	98.74 449	98.90 420	93.00 458	92.61 484	99.06 406	70.06 500	97.74 481	91.92 468	89.65 479	97.62 477

WB-MVS		93.10 448	94.10 434	90.12 485	95.51 503	81.88 500	99.73 52	99.27 359	95.05 428	93.09 482	98.91 429	94.70 282	91.89 513	76.62 507	94.02 436	96.58 494

PM-MVS		92.96 449	92.23 453	95.14 461	95.61 499	89.98 486	99.37 291	98.21 472	94.80 435	95.04 468	97.69 474	65.06 506	97.90 477	94.30 439	89.98 475	97.54 482

SSC-MVS		92.73 450	93.73 441	89.72 488	95.02 507	81.38 502	99.76 38	99.23 368	94.87 433	92.80 483	98.93 425	94.71 281	91.37 515	74.49 512	93.80 438	96.42 495

test_fmvs3		92.10 451	91.77 454	93.08 470	96.19 492	86.25 489	99.82 16	98.62 458	96.65 364	95.19 465	96.90 490	55.05 515	95.93 499	96.63 395	90.92 470	97.06 489

MatchFormer		91.94 452	90.72 457	95.58 458	97.82 465	89.79 487	98.92 424	98.87 426	88.24 487	88.03 498	97.92 471	70.39 498	99.23 384	85.21 498	91.12 466	97.72 472

test_f		91.90 453	91.26 456	93.84 466	95.52 502	85.92 490	99.69 63	98.53 463	95.31 422	93.87 477	96.37 496	55.33 514	98.27 468	95.70 415	90.98 469	97.32 485

usedtu_dtu_shiyan2		91.34 454	89.96 463	95.47 459	93.61 516	90.81 481	99.15 370	98.68 453	86.37 492	95.19 465	98.27 456	72.64 493	97.05 489	85.40 497	80.32 510	98.54 417

test_method		91.10 455	91.36 455	90.31 482	95.85 496	73.72 520	94.89 509	99.25 364	68.39 511	95.82 460	99.02 414	80.50 485	98.95 448	93.64 449	94.89 418	98.25 445

Gipuma		90.99 456	90.15 461	93.51 467	98.73 421	90.12 485	93.98 514	99.45 253	79.32 499	92.28 485	94.91 500	69.61 501	97.98 475	87.42 488	95.67 397	92.45 507
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 457	90.11 462	93.34 468	98.78 412	85.59 493	98.15 490	93.16 516	89.37 483	92.07 487	98.38 451	81.48 482	95.19 501	62.54 518	97.04 363	99.25 290

SP-DiffGlue		90.78 458	90.71 458	90.98 478	95.45 504	81.30 503	97.92 496	97.30 489	75.18 502	92.09 486	95.93 497	74.93 489	94.89 505	93.46 452	94.12 432	96.74 492

testf1		90.42 459	90.68 459	89.65 489	97.78 466	73.97 518	99.13 374	98.81 434	89.62 481	91.80 490	98.93 425	62.23 510	98.80 457	86.61 494	91.17 464	96.19 497

APD_test2		90.42 459	90.68 459	89.65 489	97.78 466	73.97 518	99.13 374	98.81 434	89.62 481	91.80 490	98.93 425	62.23 510	98.80 457	86.61 494	91.17 464	96.19 497

ELoFTR		89.95 461	88.65 466	93.85 465	95.93 495	85.85 491	98.64 458	98.31 467	90.34 479	85.03 503	97.76 473	60.28 512	99.01 433	87.27 490	84.26 490	96.71 493

SP-LightGlue		89.28 462	88.68 464	91.06 477	98.21 457	80.90 505	98.19 486	96.96 492	72.38 505	89.60 496	94.43 503	72.44 494	95.06 503	82.91 500	93.03 451	97.22 486

SP-SuperGlue		89.23 463	88.68 464	90.88 479	98.23 456	80.60 506	98.16 488	97.30 489	73.08 504	89.64 495	94.62 502	71.80 496	94.91 504	82.11 502	93.22 446	97.14 488

SP-NN		88.62 464	88.17 467	89.96 486	97.89 462	78.51 512	97.19 503	96.09 501	71.28 507	88.29 497	94.00 506	71.98 495	93.65 509	82.37 501	94.46 422	97.71 473

SP-MNN		88.33 465	87.78 468	89.95 487	98.28 453	77.92 513	98.01 494	95.69 504	70.61 509	86.18 501	94.36 504	71.09 497	94.76 506	81.51 503	94.32 427	97.17 487

ALIKED-NN		88.27 466	87.61 469	90.24 483	98.46 449	79.97 509	97.04 504	94.61 511	75.25 501	86.99 499	96.90 490	72.78 492	95.78 500	75.45 510	91.01 468	94.97 502

ALIKED-LG		88.17 467	87.32 470	90.75 480	98.67 431	81.68 501	98.16 488	94.72 509	78.63 500	86.08 502	97.07 488	70.16 499	96.62 492	71.97 514	90.37 471	93.95 504

test_vis3_rt		87.04 468	85.81 472	90.73 481	93.99 513	81.96 499	99.76 38	90.23 522	92.81 461	81.35 511	91.56 512	40.06 530	99.07 419	94.27 441	88.23 482	91.15 510

ALIKED-MNN		86.97 469	85.90 471	90.16 484	99.06 367	79.59 510	97.93 495	94.82 507	72.37 506	84.41 505	95.46 498	68.55 504	96.43 496	72.40 513	88.11 483	94.47 503

PMMVS2		86.87 470	85.37 474	91.35 476	90.21 526	83.80 496	98.89 428	97.45 488	83.13 498	91.67 492	95.03 499	48.49 524	94.70 507	85.86 496	77.62 513	95.54 500

LCM-MVSNet		86.80 471	85.22 475	91.53 475	87.81 532	80.96 504	98.23 485	98.99 404	71.05 508	90.13 494	96.51 495	48.45 525	96.88 491	90.51 473	85.30 488	96.76 490

FPMVS		84.93 472	85.65 473	82.75 498	86.77 533	63.39 525	98.35 477	98.92 413	74.11 503	83.39 508	98.98 420	50.85 518	92.40 512	84.54 499	94.97 414	92.46 506

PDCNetPlus		84.77 473	83.24 476	89.36 491	94.33 511	83.93 495	98.13 491	76.80 532	83.26 497	86.31 500	97.33 485	62.90 508	92.65 510	87.20 491	62.90 518	91.50 509

XFeat-NN		82.84 474	83.12 477	82.00 500	94.35 510	67.14 524	93.32 519	89.27 523	62.21 517	84.06 506	93.50 508	69.15 502	89.40 516	78.92 504	83.33 497	89.46 513

EGC-MVSNET		82.80 475	77.86 482	97.62 418	97.91 460	96.12 401	99.33 308	99.28 352	8.40 536	25.05 537	99.27 383	84.11 470	99.33 366	89.20 479	98.22 299	97.42 484

tmp_tt		82.80 475	81.52 479	86.66 493	66.61 539	68.44 523	92.79 522	97.92 476	68.96 510	80.04 515	99.85 89	85.77 458	96.15 498	97.86 290	43.89 527	95.39 501

XFeat-MNN		82.40 477	82.10 478	83.31 496	93.04 518	68.49 522	95.39 508	90.86 520	60.29 518	81.56 510	94.09 505	66.79 505	91.70 514	76.62 507	80.26 511	89.74 512

E-PMN		80.61 478	79.88 480	82.81 497	90.75 524	76.38 516	97.69 498	95.76 503	66.44 513	83.52 507	92.25 511	62.54 509	87.16 524	68.53 516	61.40 519	84.89 516

EMVS		80.02 479	79.22 481	82.43 499	91.19 523	76.40 515	97.55 502	92.49 519	66.36 515	83.01 509	91.27 513	64.63 507	85.79 527	65.82 517	60.65 520	85.08 515

GLUNet-SfM		78.99 480	76.32 484	86.99 492	89.16 531	73.30 521	93.36 518	90.45 521	66.38 514	74.95 520	93.30 509	52.29 517	94.61 508	75.35 511	51.65 525	93.07 505

ANet_high		77.30 481	74.86 488	84.62 495	75.88 537	77.61 514	97.63 500	93.15 517	88.81 485	64.27 523	89.29 525	36.51 533	83.93 528	75.89 509	52.31 523	92.33 508

SIFT-NN		76.99 482	77.37 483	75.84 502	97.10 481	62.39 526	94.15 513	87.21 525	59.41 519	79.90 516	90.73 516	54.60 516	88.56 519	47.22 520	86.03 487	76.57 518

MVE	76.82 21	76.91 483	74.31 489	84.70 494	85.38 536	76.05 517	96.88 506	93.17 515	67.39 512	71.28 521	89.01 527	21.66 540	87.69 522	71.74 515	72.29 516	90.35 511
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 484	74.97 487	79.01 501	70.98 538	55.18 537	93.37 517	98.21 472	65.08 516	61.78 526	93.83 507	21.74 539	92.53 511	78.59 505	91.12 466	89.34 514
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-MNN		75.73 485	75.71 485	75.77 503	95.65 498	60.92 528	94.36 511	87.62 524	58.67 520	75.90 518	90.94 515	49.64 522	89.04 518	44.85 525	83.80 493	77.35 517

SIFT-NN-NCMNet		75.53 486	75.57 486	75.42 504	93.93 514	61.35 527	94.41 510	86.44 526	58.51 521	76.23 517	90.44 518	50.56 519	89.34 517	46.60 521	83.04 498	75.58 520

SIFT-NN-CMatch		72.61 487	71.92 490	74.68 505	92.79 519	60.24 530	93.28 520	81.57 530	58.24 523	75.18 519	90.26 520	49.66 521	87.35 523	46.02 522	60.26 521	76.45 519

SIFT-NCM-Cal		71.65 488	70.76 492	74.34 506	94.61 509	60.18 531	94.16 512	81.72 529	57.21 525	55.36 529	89.56 524	42.48 526	88.45 520	41.31 530	80.41 509	74.39 522

SIFT-NN-UMatch		71.65 488	70.86 491	74.00 507	90.69 525	60.53 529	93.59 515	81.89 528	58.42 522	60.99 527	89.71 523	50.18 520	87.89 521	45.77 523	66.55 517	73.57 524

SIFT-NN-PointCN		70.32 490	69.71 493	72.13 510	90.01 527	58.29 535	93.45 516	76.20 533	56.66 528	70.25 522	89.20 526	48.94 523	83.41 529	45.45 524	57.26 522	74.70 521

SIFT-ConvMatch		69.43 491	68.09 494	73.45 508	93.86 515	60.02 532	92.57 523	77.69 531	57.58 524	62.69 524	90.53 517	42.14 527	86.65 526	43.98 526	51.72 524	73.67 523

SIFT-UMatch		68.14 492	66.40 495	73.38 509	92.20 522	59.42 533	92.84 521	76.01 534	56.87 526	58.37 528	90.35 519	41.97 528	87.16 524	42.64 527	46.35 526	73.55 525

SIFT-CM-Cal		66.94 493	65.48 496	71.33 511	93.05 517	58.77 534	91.46 526	70.45 536	56.64 529	61.97 525	89.98 521	40.72 529	83.32 530	42.57 528	42.47 528	71.90 526

SIFT-UM-Cal		64.60 494	62.65 497	70.42 512	92.22 521	58.07 536	92.29 524	66.92 537	56.70 527	50.16 531	89.97 522	37.90 531	82.95 531	42.33 529	35.40 531	70.24 528

SIFT-PointCN		62.71 495	61.56 498	66.18 513	89.53 530	50.88 538	91.81 525	72.35 535	53.65 530	50.49 530	86.32 529	33.30 534	76.23 533	35.91 534	40.66 529	71.43 527

SIFT-PCN-Cal		61.29 496	60.21 499	64.54 514	89.88 528	50.56 539	91.21 527	65.73 538	53.15 531	48.59 532	87.20 528	36.60 532	76.52 532	37.37 533	32.17 532	66.54 529

SIFT-NCMNet		55.02 497	53.54 500	59.46 515	86.55 534	47.35 541	87.85 528	46.22 539	51.77 532	44.11 533	83.50 530	27.88 537	68.75 534	32.81 535	21.14 535	62.27 530

wuyk23d		40.18 498	41.29 503	36.84 516	86.18 535	49.12 540	79.73 529	22.81 541	27.64 533	25.46 536	28.45 536	21.98 538	48.89 535	55.80 519	23.56 534	12.51 533

testmvs		39.17 499	43.78 501	25.37 518	36.04 541	16.84 543	98.36 476	26.56 540	20.06 534	38.51 535	67.32 531	29.64 536	15.30 537	37.59 531	39.90 530	43.98 532

test123		39.01 500	42.50 502	28.53 517	39.17 540	20.91 542	98.75 446	19.17 542	19.83 535	38.57 534	66.67 532	33.16 535	15.42 536	37.50 532	29.66 533	49.26 531

cdsmvs_eth3d_5k		24.64 501	32.85 504	0.00 519	0.00 542	0.00 544	0.00 530	99.51 158	0.00 537	0.00 538	99.56 290	96.58 174	0.00 538	0.00 536	0.00 536	0.00 534

ab-mvs-re		8.30 502	11.06 505	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	99.58 282	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

pcd_1.5k_mvsjas		8.27 503	11.03 506	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	99.01 19	0.00 538	0.00 536	0.00 536	0.00 534

test_blank		0.13 504	0.17 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	1.57 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

mmdepth		0.02 505	0.03 508	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

monomultidepth		0.02 505	0.03 508	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet_test		0.02 505	0.03 508	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

DCPMVS		0.02 505	0.03 508	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

sosnet-low-res		0.02 505	0.03 508	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

sosnet		0.02 505	0.03 508	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uncertanet		0.02 505	0.03 508	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

Regformer		0.02 505	0.03 508	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet		0.02 505	0.03 508	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.27 538	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

MED-MVS test				99.87 22	99.88 13	99.81 33	99.69 63	99.87 6	99.34 28	99.90 34	99.83 111		99.95 76	98.83 175	99.89 67	99.83 64

TestfortrainingZip				99.69 89	99.58 201	99.62 83	99.69 63	99.38 296	98.98 72	99.84 55	99.75 197	98.84 45	99.78 255		99.21 201	99.66 172

WAC-MVS						97.16 341								95.47 421

FOURS1					99.91 1	99.93 1	99.87 8	99.56 89	99.10 48	99.81 69

MSC_two_6792asdad				99.87 22	99.51 232	99.76 49		99.33 327					99.96 41	98.87 162	99.84 101	99.89 30

PC_three_1452									98.18 177	99.84 55	99.70 220	99.31 3	98.52 464	98.30 251	99.80 125	99.81 79

No_MVS				99.87 22	99.51 232	99.76 49		99.33 327					99.96 41	98.87 162	99.84 101	99.89 30

test_one_0601					99.81 57	99.88 10		99.49 195	98.97 76	99.65 142	99.81 137	99.09 15

eth-test2					0.00 542

eth-test					0.00 542

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 351	99.56 170	99.54 298	98.58 79	99.96 41	96.93 379	99.75 142

RE-MVS-def			99.34 49		99.76 82	99.82 28	99.63 103	99.52 133	98.38 138	99.76 92	99.82 122	98.75 61		98.61 207	99.81 120	99.77 100

IU-MVS					99.84 38	99.88 10		99.32 337	98.30 151	99.84 55				98.86 167	99.85 93	99.89 30

OPU-MVS				99.64 102	99.56 211	99.72 56	99.60 116				99.70 220	99.27 6	99.42 349	98.24 255	99.80 125	99.79 92

test_241102_TWO								99.48 207	99.08 56	99.88 42	99.81 137	98.94 33	99.96 41	98.91 156	99.84 101	99.88 36

test_241102_ONE					99.84 38	99.90 2		99.48 207	99.07 58	99.91 31	99.74 203	99.20 8	99.76 263

9.14			99.10 98		99.72 111		99.40 280	99.51 158	97.53 285	99.64 147	99.78 179	98.84 45	99.91 135	97.63 317	99.82 117

save fliter					99.76 82	99.59 89	99.14 373	99.40 285	99.00 67

test_0728_THIRD									98.99 69	99.81 69	99.80 155	99.09 15	99.96 41	98.85 169	99.90 56	99.88 36

test_0728_SECOND				99.91 6	99.84 38	99.89 6	99.57 145	99.51 158					99.96 41	98.93 153	99.86 86	99.88 36

test0726					99.85 31	99.89 6	99.62 108	99.50 182	99.10 48	99.86 52	99.82 122	98.94 33

GSMVS																99.52 229

test_part2					99.81 57	99.83 22				99.77 86

sam_mvs1												94.86 264				99.52 229

sam_mvs												94.72 280

ambc				93.06 471	92.68 520	82.36 497	98.47 473	98.73 450		95.09 467	97.41 482	55.55 513	99.10 416	96.42 399	91.32 463	97.71 473

MTGPA								99.47 229

test_post1							99.23 352				65.14 534	94.18 311	99.71 285	97.58 321

test_post											65.99 533	94.65 287	99.73 275

patchmatchnet-post											98.70 439	94.79 270	99.74 269

GG-mvs-BLEND				98.45 338	98.55 444	98.16 288	99.43 261	93.68 513		97.23 439	98.46 447	89.30 420	99.22 391	95.43 423	98.22 299	97.98 464

MTMP							99.54 173	98.88 424

gm-plane-assit					98.54 445	92.96 471			94.65 438		99.15 397		99.64 313	97.56 326

test9_res														97.49 334	99.72 148	99.75 113

TEST9					99.67 138	99.65 75	99.05 394	99.41 278	96.22 398	98.95 317	99.49 316	98.77 57	99.91 135

test_8					99.67 138	99.61 86	99.03 399	99.41 278	96.28 392	98.93 320	99.48 323	98.76 58	99.91 135

agg_prior2														97.21 358	99.73 147	99.75 113

agg_prior					99.67 138	99.62 83		99.40 285		98.87 330			99.91 135

TestCases				99.31 203	99.86 25	98.48 273		99.61 60	97.85 241	99.36 225	99.85 89	95.95 209	99.85 190	96.66 392	99.83 113	99.59 210

test_prior4						99.56 95	98.99 410

test_prior2							98.96 417		98.34 144	99.01 304	99.52 306	98.68 71		97.96 282	99.74 145

test_prior				99.68 90	99.67 138	99.48 112		99.56 89					99.83 221			99.74 118

旧先验2							98.96 417		96.70 360	99.47 189			99.94 91	98.19 258

新几何2							99.01 407

新几何1				99.75 77	99.75 92	99.59 89		99.54 108	96.76 356	99.29 242	99.64 258	98.43 90	99.94 91	96.92 381	99.66 159	99.72 138

旧先验1					99.74 100	99.59 89		99.54 108			99.69 231	98.47 87			99.68 156	99.73 128

无先验							98.99 410	99.51 158	96.89 348				99.93 108	97.53 329		99.72 138

原ACMM2							98.95 420

原ACMM1				99.65 96	99.73 107	99.33 131		99.47 229	97.46 291	99.12 282	99.66 250	98.67 73	99.91 135	97.70 314	99.69 153	99.71 149

test222					99.75 92	99.49 110	98.91 427	99.49 195	96.42 386	99.34 232	99.65 252	98.28 100			99.69 153	99.72 138

testdata2													99.95 76	96.67 391

segment_acmp												98.96 26

testdata				99.54 126	99.75 92	98.95 196		99.51 158	97.07 332	99.43 200	99.70 220	98.87 41	99.94 91	97.76 304	99.64 162	99.72 138

testdata1							98.85 432		98.32 148

test12				99.75 77	99.64 166	99.61 86		99.29 350		99.21 264		98.38 95	99.89 163		99.74 145	99.74 118

plane_prior7					99.29 308	97.03 356

plane_prior6					99.27 313	96.98 360						92.71 353

plane_prior5								99.47 229					99.69 298	97.78 300	97.63 327	98.67 372

plane_prior4											99.61 273

plane_prior3						97.00 358			98.69 108	99.11 284

plane_prior2							99.39 284		98.97 76

plane_prior1					99.26 316

plane_prior						96.97 361	99.21 358		98.45 131						97.60 330

n2								0.00 543

nn								0.00 543

door-mid								98.05 475

lessismore_v0				97.79 408	98.69 429	95.44 429		94.75 508		95.71 461	99.87 73	88.69 428	99.32 368	95.89 410	94.93 416	98.62 394

LGP-MVS_train				98.49 328	99.33 295	97.05 350		99.55 99	97.46 291	99.24 256	99.83 111	92.58 358	99.72 279	98.09 269	97.51 339	98.68 364

test11								99.35 314

door								97.92 476

HQP5-MVS						96.83 372

HQP-NCC					99.19 334		98.98 413		98.24 164	98.66 361

ACMP_Plane					99.19 334		98.98 413		98.24 164	98.66 361

BP-MVS														97.19 362

HQP4-MVS										98.66 361			99.64 313			98.64 385

HQP3-MVS								99.39 288							97.58 332

HQP2-MVS												92.47 362

NP-MVS					99.23 324	96.92 368					99.40 345

MDTV_nov1_ep13_2view						95.18 436	99.35 302		96.84 351	99.58 166		95.19 249		97.82 295		99.46 257

MDTV_nov1_ep13			98.32 235		99.11 355	94.44 453	99.27 333	98.74 444	97.51 288	99.40 213	99.62 269	94.78 271	99.76 263	97.59 320	98.81 262

ACMMP++_ref															97.19 360

ACMMP++															97.43 350

Test By Simon												98.75 61

ITE_SJBPF				98.08 375	99.29 308	96.37 391		98.92 413	98.34 144	98.83 338	99.75 197	91.09 399	99.62 320	95.82 411	97.40 352	98.25 445

DeepMVS_CX				93.34 468	99.29 308	82.27 498		99.22 370	85.15 494	96.33 454	99.05 408	90.97 401	99.73 275	93.57 450	97.77 323	98.01 459

High-resolution multi-view benchmark