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	99.56 154	99.63 46	99.48 3	99.98 13	99.83 114	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	99.56 154	99.63 46	99.47 6	99.98 13	99.82 125	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	98.83 178	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 89	99.88 74	99.93 22

test_fmvsmconf_n		99.70 3	99.64 4	99.87 22	99.80 63	99.66 71	99.48 231	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	99.58 138	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 91	99.18 11	99.96 41	99.22 110	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	99.38 285	99.37 124	99.58 138	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	99.56 154	99.55 99	99.15 38	99.90 34	99.90 36	99.00 23	99.97 29	99.11 128	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	99.54 174	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	99.52 185	99.54 108	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 138	99.90 56	99.85 47

our_new_method		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 185	99.54 108	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 138	99.90 56	99.85 47

SED-MVS		99.61 10	99.52 14	99.88 16	99.84 38	99.90 2	99.60 117	99.48 210	99.08 56	99.91 31	99.81 140	99.20 8	99.96 41	98.91 159	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 91	98.41 93	99.96 41	99.28 102	99.84 101	99.83 64

DVP-MVS++		99.59 15	99.50 19	99.88 16	99.51 235	99.88 10	99.87 8	99.51 160	98.99 69	99.88 42	99.81 140	99.27 6	99.96 41	98.85 172	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	99.47 241	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	99.63 104	99.39 291	98.91 83	99.78 83	99.85 91	99.36 2	99.94 91	98.84 175	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	99.14 163	99.60 117	99.45 256	99.01 64	99.90 34	99.83 114	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	99.15 162	99.61 115	99.45 256	99.01 64	99.89 39	99.82 125	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	99.57 146	99.37 309	99.10 48	99.81 70	99.80 158	98.94 33	99.96 41	98.93 156	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	99.37 293	99.70 18	99.18 35	99.83 64	99.83 114	98.74 66	99.93 108	98.83 178	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	99.52 185	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	99.44 266	99.65 75	99.50 206	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	99.51 195	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	99.51 235	99.67 68	99.50 206	99.64 42	99.43 19	99.98 13	99.78 182	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	99.59 128	99.51 160	98.62 113	99.79 78	99.83 114	99.28 5	99.97 29	98.48 229	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	99.37 223	99.74 206	98.81 49	99.94 91	98.79 186	99.86 86	99.84 54

MTAPA		99.52 28	99.39 39	99.89 12	99.90 4	99.86 18	99.66 84	99.47 232	98.79 96	99.68 122	99.81 140	98.43 90	99.97 29	98.88 162	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	99.51 195	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	97.72 265	99.76 93	99.75 200	99.13 13	99.92 123	99.07 135	99.92 38	99.85 47

mvsany_test1		99.50 31	99.46 28	99.62 109	99.61 193	99.09 168	98.94 426	99.48 210	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	99.54 127	99.76 82	99.42 119	99.90 1	99.55 99	98.56 119	99.78 83	99.70 223	98.65 75	99.79 250	99.65 41	99.78 134	99.41 271

SPE-MVS-test		99.49 33	99.48 22	99.54 127	99.78 70	99.30 139	99.89 2	99.58 77	98.56 119	99.73 100	99.69 234	98.55 82	99.82 231	99.69 34	99.85 93	99.48 250

HFP-MVS		99.49 33	99.37 43	99.86 34	99.87 20	99.80 38	99.66 84	99.67 27	98.15 181	99.68 122	99.69 234	99.06 17	99.96 41	98.69 198	99.87 78	99.84 54

ACMMPR		99.49 33	99.36 45	99.86 34	99.87 20	99.79 41	99.66 84	99.67 27	98.15 181	99.67 128	99.69 234	98.95 31	99.96 41	98.69 198	99.87 78	99.84 54

DeepC-MVS_fast	98.69 1	99.49 33	99.39 39	99.77 74	99.63 172	99.59 89	99.36 299	99.46 245	99.07 58	99.79 78	99.82 125	98.85 43	99.92 123	98.68 200	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 90	99.66 32	98.13 188	99.66 133	99.68 242	98.96 26	99.96 41	98.62 207	99.87 78	99.84 54

APD-MVS_3200maxsize		99.48 37	99.35 47	99.85 43	99.76 82	99.83 22	99.63 104	99.54 108	98.36 143	99.79 78	99.82 125	98.86 42	99.95 76	98.62 207	99.81 120	99.78 98

DELS-MVS		99.48 37	99.42 32	99.65 96	99.72 111	99.40 122	99.05 398	99.66 32	99.14 40	99.57 171	99.80 158	98.46 88	99.94 91	99.57 48	99.84 101	99.60 202
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 98	99.67 27	98.08 206	99.55 179	99.64 262	98.91 38	99.96 41	98.72 193	99.90 56	99.82 72

ACMMP_NAP		99.47 40	99.34 49	99.88 16	99.87 20	99.86 18	99.47 241	99.48 210	98.05 214	99.76 93	99.86 84	98.82 48	99.93 108	98.82 185	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	99.50 185	98.27 156	99.87 48	99.92 18	98.09 108	99.94 91	99.65 41	99.95 22	99.47 256

BridgeMVS		99.46 42	99.39 39	99.67 91	99.55 218	99.58 94	99.74 48	99.51 160	98.42 135	99.87 48	99.84 106	98.05 111	99.91 135	99.58 47	99.94 30	99.52 233

DPE-MVS		99.46 42	99.32 53	99.91 6	99.78 70	99.88 10	99.36 299	99.51 160	98.73 103	99.88 42	99.84 106	98.72 68	99.96 41	98.16 265	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	99.44 179	99.60 199	99.16 157	99.41 273	99.71 16	98.98 72	99.45 195	99.78 182	99.19 10	99.54 334	99.28 102	99.84 101	99.63 194

SR-MVS-dyc-post		99.45 46	99.31 59	99.85 43	99.76 82	99.82 28	99.63 104	99.52 133	98.38 139	99.76 93	99.82 125	98.53 83	99.95 76	98.61 210	99.81 120	99.77 100

PGM-MVS		99.45 46	99.31 59	99.86 34	99.87 20	99.78 47	99.58 138	99.65 39	97.84 248	99.71 115	99.80 158	99.12 14	99.97 29	98.33 250	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	98.07 207	99.53 182	99.63 268	98.93 37	99.97 29	98.74 190	99.91 45	99.83 64

ACMMP		99.45 46	99.32 53	99.82 57	99.89 8	99.67 68	99.62 109	99.69 22	98.12 196	99.63 151	99.84 106	98.73 67	99.96 41	98.55 225	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	99.56 154	99.47 232	97.45 299	99.78 83	99.82 125	99.18 11	99.91 135	98.79 186	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	99.48 210	98.12 196	99.50 187	99.75 200	98.78 53	99.97 29	98.57 219	99.89 67	99.83 64

EC-MVSNet		99.44 50	99.39 39	99.58 118	99.56 214	99.49 110	99.88 4	99.58 77	98.38 139	99.73 100	99.69 234	98.20 103	99.70 296	99.64 43	99.82 117	99.54 227

SR-MVS		99.43 53	99.29 65	99.86 34	99.75 92	99.83 22	99.59 128	99.62 51	98.21 172	99.73 100	99.79 175	98.68 71	99.96 41	98.44 236	99.77 137	99.79 92

MCST-MVS		99.43 53	99.30 61	99.82 57	99.79 68	99.74 54	99.29 325	99.40 288	98.79 96	99.52 184	99.62 273	98.91 38	99.90 148	98.64 204	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 77	99.50 185	98.70 107	99.77 87	99.49 321	98.21 102	99.95 76	98.46 234	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	99.62 182	99.55 97	99.50 206	99.70 18	98.79 96	99.77 87	99.96 1	97.45 124	99.96 41	98.92 158	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	97.59 280	99.68 122	99.63 268	98.91 38	99.94 91	98.58 216	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	99.62 182	99.71 58	99.26 345	99.52 133	98.82 90	99.39 218	99.71 219	98.96 26	99.85 190	98.59 215	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	99.53 183	99.56 89	99.45 13	99.99 2	99.92 18	94.92 264	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	99.48 231	99.62 51	99.46 9	99.99 2	99.92 18	95.24 251	99.96 41	99.97 2	99.97 9	99.96 7

SD-MVS		99.41 59	99.52 14	99.05 244	99.74 100	99.68 64	99.46 245	99.52 133	99.11 47	99.88 42	99.91 26	99.43 1	97.70 490	98.72 193	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	98.94 426	99.85 8	98.82 90	99.65 143	99.74 206	98.51 85	99.80 243	98.83 178	99.89 67	99.64 189

MVS_111021_HR		99.41 59	99.32 53	99.66 92	99.72 111	99.47 114	98.95 424	99.85 8	98.82 90	99.54 180	99.73 212	98.51 85	99.74 272	98.91 159	99.88 74	99.77 100

MM		99.40 64	99.28 68	99.74 80	99.67 138	99.31 136	99.52 185	98.87 433	99.55 1	99.74 98	99.80 158	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	99.60 117	99.67 27	97.97 232	99.63 151	99.68 242	98.52 84	99.95 76	98.38 243	99.86 86	99.81 79

HPM-MVS++		99.39 66	99.23 81	99.87 22	99.75 92	99.84 20	99.43 262	99.51 160	98.68 110	99.27 253	99.53 307	98.64 76	99.96 41	98.44 236	99.80 125	99.79 92

SF-MVS		99.38 67	99.24 77	99.79 68	99.79 68	99.68 64	99.57 146	99.54 108	97.82 254	99.71 115	99.80 158	98.95 31	99.93 108	98.19 261	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	99.42 269	99.61 60	99.37 26	99.97 25	99.86 84	94.96 259	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	99.48 231	99.66 32	99.45 13	99.99 2	99.93 10	94.64 292	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	99.46 245	99.60 67	99.47 6	99.98 13	99.94 6	94.98 258	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	99.30 320	99.52 133	97.18 326	99.60 163	99.79 175	98.79 52	99.95 76	98.83 178	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	99.49 223	99.60 67	99.42 22	99.99 2	99.86 84	95.15 254	99.95 76	99.95 16	99.89 67	99.73 128

TSAR-MVS + GP.		99.36 72	99.36 45	99.36 194	99.67 138	98.61 259	99.07 391	99.33 331	99.00 67	99.82 68	99.81 140	99.06 17	99.84 200	99.09 133	99.42 181	99.65 182

PVSNet_Blended_VisFu		99.36 72	99.28 68	99.61 110	99.86 25	99.07 173	99.47 241	99.93 2	97.66 274	99.71 115	99.86 84	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	99.48 164	99.70 122	98.63 254	99.42 269	99.63 46	99.46 9	99.98 13	99.88 58	95.59 234	99.96 41	99.97 2	99.98 4	99.85 47

NCCC		99.34 75	99.19 87	99.79 68	99.61 193	99.65 75	99.30 320	99.48 210	98.86 85	99.21 268	99.63 268	98.72 68	99.90 148	98.25 257	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 84	99.46 245	98.09 202	99.48 191	99.74 206	98.29 99	99.96 41	97.93 287	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	99.57 146	99.56 89	99.45 13	99.99 2	99.93 10	94.18 315	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	99.44 256	99.58 77	99.47 6	99.99 2	99.93 10	94.04 320	99.96 41	99.96 13	99.93 32	99.93 22

PS-MVSNAJ		99.32 78	99.32 53	99.30 211	99.57 210	98.94 201	98.97 420	99.46 245	98.92 82	99.71 115	99.24 393	99.01 19	99.98 20	99.35 81	99.66 159	98.97 327

CSCG		99.32 78	99.32 53	99.32 204	99.85 31	98.29 285	99.71 58	99.66 32	98.11 198	99.41 211	99.80 158	98.37 96	99.96 41	98.99 144	99.96 17	99.72 138

PHI-MVS		99.30 82	99.17 90	99.70 87	99.56 214	99.52 106	99.58 138	99.80 10	97.12 332	99.62 155	99.73 212	98.58 79	99.90 148	98.61 210	99.91 45	99.68 163

DeepC-MVS	98.35 2	99.30 82	99.19 87	99.64 102	99.82 53	99.23 149	99.62 109	99.55 99	98.94 79	99.63 151	99.95 3	95.82 222	99.94 91	99.37 79	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	99.53 183	99.62 51	98.74 102	99.99 2	99.95 3	94.53 300	99.94 91	99.89 25	99.96 17	99.97 4

xiu_mvs_v1_base_debu		99.29 84	99.27 72	99.34 198	99.63 172	98.97 187	99.12 381	99.51 160	98.86 85	99.84 55	99.47 332	98.18 104	99.99 4	99.50 57	99.31 191	99.08 309

xiu_mvs_v1_base		99.29 84	99.27 72	99.34 198	99.63 172	98.97 187	99.12 381	99.51 160	98.86 85	99.84 55	99.47 332	98.18 104	99.99 4	99.50 57	99.31 191	99.08 309

xiu_mvs_v1_base_debi		99.29 84	99.27 72	99.34 198	99.63 172	98.97 187	99.12 381	99.51 160	98.86 85	99.84 55	99.47 332	98.18 104	99.99 4	99.50 57	99.31 191	99.08 309

NormalMVS		99.27 88	99.19 87	99.52 142	99.89 8	98.83 232	99.65 90	99.52 133	99.10 48	99.84 55	99.76 195	95.80 224	99.99 4	99.30 94	99.84 101	99.74 118

APD-MVS		99.27 88	99.08 104	99.84 55	99.75 92	99.79 41	99.50 206	99.50 185	97.16 328	99.77 87	99.82 125	98.78 53	99.94 91	97.56 329	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	99.18 340	99.75 51	99.56 154	99.57 84	98.45 131	99.49 190	99.85 91	97.77 118	99.94 91	98.33 250	99.84 101	99.52 233

fmvsm_s_conf0.1_n_a		99.26 91	99.06 109	99.85 43	99.52 232	99.62 83	99.54 174	99.62 51	98.69 108	99.99 2	99.96 1	94.47 302	99.94 91	99.88 26	99.92 38	99.98 2

patch_mono-2		99.26 91	99.62 7	98.16 372	99.81 57	94.59 456	99.52 185	99.64 42	99.33 29	99.73 100	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	99.40 187	99.46 259	99.30 139	99.56 154	99.52 133	98.52 123	99.44 200	99.27 389	98.41 93	99.86 182	99.10 131	99.59 168	99.04 317

xiu_mvs_v2_base		99.26 91	99.25 76	99.29 214	99.53 226	98.91 208	99.02 406	99.45 256	98.80 95	99.71 115	99.26 391	98.94 33	99.98 20	99.34 86	99.23 200	98.98 325

CANet		99.25 95	99.14 93	99.59 114	99.41 274	99.16 157	99.35 304	99.57 84	98.82 90	99.51 186	99.61 277	96.46 181	99.95 76	99.59 45	99.98 4	99.65 182

3Dnovator	97.25 9	99.24 96	99.05 111	99.81 60	99.12 356	99.66 71	99.84 12	99.74 13	99.09 55	98.92 325	99.90 36	95.94 215	99.98 20	98.95 152	99.92 38	99.79 92

LuminaMVS		99.23 97	99.10 98	99.61 110	99.35 292	99.31 136	99.46 245	99.13 389	98.61 114	99.86 52	99.89 45	96.41 186	99.91 135	99.67 37	99.51 174	99.63 194

dcpmvs_2		99.23 97	99.58 9	98.16 372	99.83 47	94.68 452	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	98.42 458	99.48 112	99.55 169	99.51 160	99.39 24	99.78 83	99.93 10	94.80 273	99.95 76	99.93 23	99.95 22	99.94 17

diffmvs_AUTHOR		99.19 100	99.10 98	99.48 164	99.64 167	98.85 227	99.32 314	99.48 210	98.50 125	99.81 70	99.81 140	96.82 160	99.88 168	99.40 72	99.12 221	99.71 150

CHOSEN 1792x2688		99.19 100	99.10 98	99.45 174	99.89 8	98.52 269	99.39 285	99.94 1	98.73 103	99.11 288	99.89 45	95.50 237	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	99.42 269	99.54 108	97.29 316	99.41 211	99.59 282	98.42 92	99.93 108	98.19 261	99.69 153	99.73 128

E3new		99.18 103	99.08 104	99.48 164	99.63 172	98.94 201	99.46 245	99.50 185	98.06 211	99.72 105	99.84 106	97.27 133	99.84 200	99.10 131	99.13 216	99.67 170

viewcassd2359sk11		99.18 103	99.08 104	99.49 160	99.65 162	98.95 197	99.48 231	99.51 160	98.10 201	99.72 105	99.87 74	97.13 139	99.84 200	99.13 125	99.14 213	99.69 157

viewmanbaseed2359cas		99.18 103	99.07 108	99.50 153	99.62 182	99.01 181	99.50 206	99.52 133	98.25 164	99.68 122	99.82 125	96.93 153	99.80 243	99.15 124	99.11 223	99.70 154

EIA-MVS		99.18 103	99.09 103	99.45 174	99.49 249	99.18 154	99.67 77	99.53 124	97.66 274	99.40 216	99.44 339	98.10 107	99.81 236	98.94 153	99.62 165	99.35 281

3Dnovator+	97.12 13	99.18 103	98.97 146	99.82 57	99.17 348	99.68 64	99.81 20	99.51 160	99.20 34	98.72 355	99.89 45	95.68 231	99.97 29	98.86 170	99.86 86	99.81 79

MVSFormer		99.17 108	99.12 96	99.29 214	99.51 235	98.94 201	99.88 4	99.46 245	97.55 286	99.80 75	99.65 256	97.39 125	99.28 379	99.03 140	99.85 93	99.65 182

sss		99.17 108	99.05 111	99.53 135	99.62 182	98.97 187	99.36 299	99.62 51	97.83 249	99.67 128	99.65 256	97.37 128	99.95 76	99.19 114	99.19 204	99.68 163

cashybrid2		99.16 110	99.02 127	99.59 114	99.66 150	99.21 151	99.68 73	99.52 133	98.31 151	99.60 163	99.87 74	95.96 211	99.85 190	99.40 72	99.16 206	99.72 138

SSM_0404		99.16 110	99.06 109	99.44 179	99.65 162	98.96 191	99.49 223	99.50 185	98.14 185	99.62 155	99.85 91	96.85 155	99.85 190	99.19 114	99.26 196	99.52 233

guyue		99.16 110	99.04 113	99.52 142	99.69 128	98.92 207	99.59 128	98.81 441	98.73 103	99.90 34	99.87 74	95.34 244	99.88 168	99.66 40	99.81 120	99.74 118

test_cas_vis1_n_1920		99.16 110	99.01 135	99.61 110	99.81 57	98.86 226	99.65 90	99.64 42	99.39 24	99.97 25	99.94 6	93.20 344	99.98 20	99.55 50	99.91 45	99.99 1

DP-MVS		99.16 110	98.95 154	99.78 71	99.77 78	99.53 102	99.41 273	99.50 185	97.03 344	99.04 305	99.88 58	97.39 125	99.92 123	98.66 202	99.90 56	99.87 41

E6new		99.15 115	99.03 116	99.50 153	99.66 150	98.90 213	99.60 117	99.53 124	98.13 188	99.72 105	99.91 26	96.31 190	99.84 200	99.30 94	99.10 231	99.76 107

E6		99.15 115	99.03 116	99.50 153	99.66 150	98.90 213	99.60 117	99.53 124	98.13 188	99.72 105	99.91 26	96.31 190	99.84 200	99.30 94	99.10 231	99.76 107

E2		99.15 115	99.03 116	99.49 160	99.65 162	98.93 206	99.49 223	99.52 133	98.14 185	99.72 105	99.88 58	96.57 176	99.84 200	99.17 120	99.13 216	99.72 138

E3		99.15 115	99.03 116	99.49 160	99.62 182	98.91 208	99.49 223	99.52 133	98.13 188	99.72 105	99.88 58	96.61 171	99.84 200	99.17 120	99.13 216	99.72 138

SymmetryMVS		99.15 115	99.02 127	99.52 142	99.72 111	98.83 232	99.65 90	99.34 323	99.10 48	99.84 55	99.76 195	95.80 224	99.99 4	99.30 94	98.72 270	99.73 128

MGCNet		99.15 115	98.96 150	99.73 83	98.92 397	99.37 124	99.37 293	96.92 501	99.51 2	99.66 133	99.78 182	96.69 167	99.97 29	99.84 28	99.97 9	99.84 54

casdiffmvs_mvg		99.15 115	99.02 127	99.55 126	99.66 150	99.09 168	99.64 98	99.56 89	98.26 159	99.45 195	99.87 74	96.03 208	99.81 236	99.54 51	99.15 212	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		99.15 115	99.02 127	99.53 135	99.66 150	99.14 163	99.72 54	99.48 210	98.35 144	99.42 206	99.84 106	96.07 204	99.79 250	99.51 56	99.14 213	99.67 170

E5new		99.14 123	99.02 127	99.50 153	99.69 128	98.91 208	99.60 117	99.53 124	98.13 188	99.72 105	99.91 26	96.26 195	99.84 200	99.30 94	99.10 231	99.76 107

E5		99.14 123	99.02 127	99.50 153	99.69 128	98.91 208	99.60 117	99.53 124	98.13 188	99.72 105	99.91 26	96.26 195	99.84 200	99.30 94	99.10 231	99.76 107

diffmvs		99.14 123	99.02 127	99.51 147	99.61 193	98.96 191	99.28 331	99.49 198	98.46 129	99.72 105	99.71 219	96.50 179	99.88 168	99.31 91	99.11 223	99.67 170
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		99.14 123	98.99 141	99.59 114	99.58 204	99.41 121	99.16 371	99.44 265	98.45 131	99.19 275	99.49 321	98.08 109	99.89 163	97.73 311	99.75 142	99.48 250

hybridnocas07		99.13 127	99.03 116	99.46 172	99.63 172	98.90 213	99.38 290	99.52 133	98.41 136	99.82 68	99.84 106	96.09 203	99.80 243	99.40 72	99.16 206	99.68 163

hybridcas		99.13 127	99.00 139	99.51 147	99.70 122	99.04 177	99.65 90	99.52 133	98.20 174	99.75 97	99.88 58	95.78 226	99.78 258	99.41 70	99.16 206	99.71 150

E4		99.13 127	99.01 135	99.49 160	99.68 135	98.90 213	99.52 185	99.52 133	98.13 188	99.71 115	99.90 36	96.32 188	99.84 200	99.21 112	99.11 223	99.75 113

SSM_0407		99.13 127	99.03 116	99.43 182	99.62 182	98.88 219	99.51 195	99.50 185	98.14 185	99.37 223	99.85 91	96.85 155	99.83 222	99.19 114	99.25 197	99.60 202

CDPH-MVS		99.13 127	98.91 163	99.80 64	99.75 92	99.71 58	99.15 374	99.41 281	96.60 378	99.60 163	99.55 297	98.83 47	99.90 148	97.48 338	99.83 113	99.78 98

casdiffmvs		99.13 127	98.98 144	99.56 124	99.65 162	99.16 157	99.56 154	99.50 185	98.33 147	99.41 211	99.86 84	95.92 216	99.83 222	99.45 68	99.16 206	99.70 154
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		99.13 127	99.03 116	99.45 174	99.46 259	98.87 223	99.12 381	99.26 366	98.03 223	99.79 78	99.65 256	97.02 148	99.85 190	99.02 142	99.90 56	99.65 182
jason: jason.
lupinMVS		99.13 127	99.01 135	99.46 172	99.51 235	98.94 201	99.05 398	99.16 385	97.86 242	99.80 75	99.56 294	97.39 125	99.86 182	98.94 153	99.85 93	99.58 217

EPP-MVSNet		99.13 127	98.99 141	99.53 135	99.65 162	99.06 174	99.81 20	99.33 331	97.43 303	99.60 163	99.88 58	97.14 138	99.84 200	99.13 125	98.94 249	99.69 157

MG-MVS		99.13 127	99.02 127	99.45 174	99.57 210	98.63 254	99.07 391	99.34 323	98.99 69	99.61 160	99.82 125	97.98 113	99.87 175	97.00 376	99.80 125	99.85 47

KinetiMVS		99.12 137	98.92 159	99.70 87	99.67 138	99.40 122	99.67 77	99.63 46	98.73 103	99.94 28	99.81 140	94.54 298	99.96 41	98.40 241	99.93 32	99.74 118

BP-MVS1		99.12 137	98.94 156	99.65 96	99.51 235	99.30 139	99.67 77	98.92 420	98.48 127	99.84 55	99.69 234	94.96 259	99.92 123	99.62 44	99.79 132	99.71 150

CHOSEN 280x420		99.12 137	99.13 94	99.08 240	99.66 150	97.89 312	98.43 483	99.71 16	98.88 84	99.62 155	99.76 195	96.63 170	99.70 296	99.46 67	99.99 1	99.66 175

DP-MVS Recon		99.12 137	98.95 154	99.65 96	99.74 100	99.70 60	99.27 336	99.57 84	96.40 394	99.42 206	99.68 242	98.75 61	99.80 243	97.98 284	99.72 148	99.44 266

Vis-MVSNet		99.12 137	98.97 146	99.56 124	99.78 70	99.10 167	99.68 73	99.66 32	98.49 126	99.86 52	99.87 74	94.77 278	99.84 200	99.19 114	99.41 182	99.74 118
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 137	99.08 104	99.24 224	99.46 259	98.55 263	99.51 195	99.46 245	98.09 202	99.45 195	99.82 125	98.34 97	99.51 336	98.70 195	98.93 250	99.67 170

hybrid		99.11 143	99.01 135	99.41 185	99.64 167	98.76 242	99.35 304	99.52 133	98.31 151	99.80 75	99.84 106	96.16 199	99.79 250	99.40 72	99.06 239	99.68 163

viewdifsd2359ckpt07		99.11 143	99.00 139	99.43 182	99.63 172	98.73 244	99.45 249	99.54 108	98.33 147	99.62 155	99.81 140	96.17 198	99.87 175	99.27 105	99.14 213	99.69 157

SDMVSNet		99.11 143	98.90 165	99.75 77	99.81 57	99.59 89	99.81 20	99.65 39	98.78 99	99.64 148	99.88 58	94.56 295	99.93 108	99.67 37	98.26 300	99.72 138

VNet		99.11 143	98.90 165	99.73 83	99.52 232	99.56 95	99.41 273	99.39 291	99.01 64	99.74 98	99.78 182	95.56 235	99.92 123	99.52 55	98.18 308	99.72 138

CPTT-MVS		99.11 143	98.90 165	99.74 80	99.80 63	99.46 115	99.59 128	99.49 198	97.03 344	99.63 151	99.69 234	97.27 133	99.96 41	97.82 298	99.84 101	99.81 79

HyFIR lowres test		99.11 143	98.92 159	99.65 96	99.90 4	99.37 124	99.02 406	99.91 3	97.67 273	99.59 167	99.75 200	95.90 218	99.73 278	99.53 53	99.02 245	99.86 43

MVS_Test		99.10 149	98.97 146	99.48 164	99.49 249	99.14 163	99.67 77	99.34 323	97.31 314	99.58 168	99.76 195	97.65 121	99.82 231	98.87 165	99.07 238	99.46 261

AstraMVS		99.09 150	99.03 116	99.25 221	99.66 150	98.13 294	99.57 146	98.24 478	98.82 90	99.91 31	99.88 58	95.81 223	99.90 148	99.72 32	99.67 158	99.74 118

CDS-MVSNet		99.09 150	99.03 116	99.25 221	99.42 269	98.73 244	99.45 249	99.46 245	98.11 198	99.46 194	99.77 191	98.01 112	99.37 362	98.70 195	98.92 252	99.66 175
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmacassd2359aftdt		99.08 152	98.94 156	99.50 153	99.66 150	98.96 191	99.51 195	99.54 108	98.27 156	99.42 206	99.89 45	95.88 220	99.80 243	99.20 113	99.11 223	99.76 107

mamba_0408		99.08 152	98.96 150	99.44 179	99.62 182	98.88 219	99.25 347	99.47 232	98.05 214	99.37 223	99.81 140	96.85 155	99.85 190	98.98 145	99.25 197	99.60 202

GDP-MVS		99.08 152	98.89 169	99.64 102	99.53 226	99.34 128	99.64 98	99.48 210	98.32 149	99.77 87	99.66 254	95.14 255	99.93 108	98.97 150	99.50 176	99.64 189

PVSNet_Blended		99.08 152	98.97 146	99.42 184	99.76 82	98.79 238	98.78 448	99.91 3	96.74 363	99.67 128	99.49 321	97.53 122	99.88 168	98.98 145	99.85 93	99.60 202

OMC-MVS		99.08 152	99.04 113	99.20 228	99.67 138	98.22 289	99.28 331	99.52 133	98.07 207	99.66 133	99.81 140	97.79 117	99.78 258	97.79 302	99.81 120	99.60 202

viewdifsd2359ckpt13		99.06 157	98.93 158	99.45 174	99.63 172	98.96 191	99.50 206	99.51 160	97.83 249	99.28 247	99.80 158	96.68 169	99.71 288	99.05 137	99.12 221	99.68 163

SSM_04072		99.06 157	98.96 150	99.35 197	99.62 182	98.88 219	99.25 347	99.47 232	98.05 214	99.37 223	99.81 140	96.85 155	99.58 328	98.98 145	99.25 197	99.60 202

mvsmamba		99.06 157	98.96 150	99.36 194	99.47 257	98.64 253	99.70 59	99.05 401	97.61 279	99.65 143	99.83 114	96.54 177	99.92 123	99.19 114	99.62 165	99.51 242

WTY-MVS		99.06 157	98.88 172	99.61 110	99.62 182	99.16 157	99.37 293	99.56 89	98.04 221	99.53 182	99.62 273	96.84 159	99.94 91	98.85 172	98.49 285	99.72 138

IS-MVSNet		99.05 161	98.87 173	99.57 122	99.73 107	99.32 132	99.75 43	99.20 380	98.02 226	99.56 173	99.86 84	96.54 177	99.67 305	98.09 272	99.13 216	99.73 128

PAPM_NR		99.04 162	98.84 181	99.66 92	99.74 100	99.44 117	99.39 285	99.38 299	97.70 269	99.28 247	99.28 386	98.34 97	99.85 190	96.96 380	99.45 179	99.69 157

API-MVS		99.04 162	99.03 116	99.06 242	99.40 279	99.31 136	99.55 169	99.56 89	98.54 121	99.33 237	99.39 355	98.76 58	99.78 258	96.98 378	99.78 134	98.07 461

dtuplus		99.03 164	98.92 159	99.36 194	99.60 199	98.62 256	99.35 304	99.51 160	97.99 229	99.38 220	99.88 58	96.04 206	99.79 250	99.37 79	99.17 205	99.68 163

mvs_anonymous		99.03 164	98.99 141	99.16 232	99.38 285	98.52 269	99.51 195	99.38 299	97.79 255	99.38 220	99.81 140	97.30 131	99.45 343	99.35 81	98.99 247	99.51 242

sasdasda		99.02 166	98.86 176	99.51 147	99.42 269	99.32 132	99.80 25	99.48 210	98.63 111	99.31 239	98.81 441	97.09 143	99.75 269	99.27 105	97.90 319	99.47 256

train_agg		99.02 166	98.77 189	99.77 74	99.67 138	99.65 75	99.05 398	99.41 281	96.28 398	98.95 321	99.49 321	98.76 58	99.91 135	97.63 320	99.72 148	99.75 113

canonicalmvs		99.02 166	98.86 176	99.51 147	99.42 269	99.32 132	99.80 25	99.48 210	98.63 111	99.31 239	98.81 441	97.09 143	99.75 269	99.27 105	97.90 319	99.47 256

balanced_ft_v1		99.02 166	98.98 144	99.15 236	99.39 282	98.12 296	99.79 31	99.51 160	98.20 174	99.66 133	99.87 74	94.84 269	99.93 108	99.69 34	99.84 101	99.41 271

PLC	97.94 4	99.02 166	98.85 179	99.53 135	99.66 150	99.01 181	99.24 352	99.52 133	96.85 356	99.27 253	99.48 329	98.25 101	99.91 135	97.76 307	99.62 165	99.65 182
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
viewdifsd2359ckpt09		99.01 171	98.87 173	99.40 187	99.62 182	98.79 238	99.44 256	99.51 160	97.76 260	99.35 232	99.69 234	96.42 185	99.75 269	98.97 150	99.11 223	99.66 175

viewmambaseed2359dif		99.01 171	98.90 165	99.32 204	99.58 204	98.51 271	99.33 311	99.54 108	97.85 245	99.44 200	99.85 91	96.01 209	99.79 250	99.41 70	99.13 216	99.67 170

MGCFI-Net		99.01 171	98.85 179	99.50 153	99.42 269	99.26 145	99.82 16	99.48 210	98.60 116	99.28 247	98.81 441	97.04 147	99.76 266	99.29 100	97.87 323	99.47 256

AdaColmap		99.01 171	98.80 184	99.66 92	99.56 214	99.54 99	99.18 369	99.70 18	98.18 179	99.35 232	99.63 268	96.32 188	99.90 148	97.48 338	99.77 137	99.55 225

1112_ss		98.98 175	98.77 189	99.59 114	99.68 135	99.02 179	99.25 347	99.48 210	97.23 322	99.13 284	99.58 286	96.93 153	99.90 148	98.87 165	98.78 267	99.84 54

MSDG		98.98 175	98.80 184	99.53 135	99.76 82	99.19 152	98.75 452	99.55 99	97.25 319	99.47 192	99.77 191	97.82 116	99.87 175	96.93 383	99.90 56	99.54 227

casdiffseed414692147		98.97 177	98.78 188	99.53 135	99.66 150	99.16 157	99.61 115	99.52 133	98.01 227	99.21 268	99.88 58	94.82 270	99.70 296	99.29 100	99.04 242	99.74 118

CANet_DTU		98.97 177	98.87 173	99.25 221	99.33 298	98.42 282	99.08 390	99.30 351	99.16 37	99.43 203	99.75 200	95.27 247	99.97 29	98.56 222	99.95 22	99.36 280

DPM-MVS		98.95 179	98.71 197	99.66 92	99.63 172	99.55 97	98.64 464	99.10 392	97.93 235	99.42 206	99.55 297	98.67 73	99.80 243	95.80 417	99.68 156	99.61 199

114514_t		98.93 180	98.67 201	99.72 86	99.85 31	99.53 102	99.62 109	99.59 72	92.65 471	99.71 115	99.78 182	98.06 110	99.90 148	98.84 175	99.91 45	99.74 118

PS-MVSNAJss		98.92 181	98.92 159	98.90 269	98.78 418	98.53 265	99.78 33	99.54 108	98.07 207	99.00 312	99.76 195	99.01 19	99.37 362	99.13 125	97.23 363	98.81 336

RRT-MVS		98.91 182	98.75 191	99.39 192	99.46 259	98.61 259	99.76 38	99.50 185	98.06 211	99.81 70	99.88 58	93.91 327	99.94 91	99.11 128	99.27 194	99.61 199

Test_1112_low_res		98.89 183	98.66 204	99.57 122	99.69 128	98.95 197	99.03 403	99.47 232	96.98 346	99.15 282	99.23 394	96.77 164	99.89 163	98.83 178	98.78 267	99.86 43

Elysia		98.88 184	98.65 206	99.58 118	99.58 204	99.34 128	99.65 90	99.52 133	98.26 159	99.83 64	99.87 74	93.37 338	99.90 148	97.81 300	99.91 45	99.49 247

StellarMVS		98.88 184	98.65 206	99.58 118	99.58 204	99.34 128	99.65 90	99.52 133	98.26 159	99.83 64	99.87 74	93.37 338	99.90 148	97.81 300	99.91 45	99.49 247

test_fmvs1		98.88 184	98.79 187	99.16 232	99.69 128	97.61 327	99.55 169	99.49 198	99.32 30	99.98 13	99.91 26	91.41 394	99.96 41	99.82 29	99.92 38	99.90 27

AllTest		98.87 187	98.72 195	99.31 206	99.86 25	98.48 276	99.56 154	99.61 60	97.85 245	99.36 229	99.85 91	95.95 213	99.85 190	96.66 396	99.83 113	99.59 213

UGNet		98.87 187	98.69 199	99.40 187	99.22 331	98.72 246	99.44 256	99.68 24	99.24 33	99.18 279	99.42 343	92.74 354	99.96 41	99.34 86	99.94 30	99.53 232
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)		98.87 187	98.72 195	99.31 206	99.71 117	98.88 219	99.80 25	99.44 265	97.91 237	99.36 229	99.78 182	95.49 238	99.43 352	97.91 288	99.11 223	99.62 197

IMVS_0407		98.86 190	98.91 163	98.72 304	99.55 218	96.93 367	99.50 206	99.44 265	98.05 214	99.66 133	99.80 158	97.13 139	99.65 313	98.15 267	98.92 252	99.60 202

IMVS_0403		98.86 190	98.89 169	98.78 299	99.55 218	96.93 367	99.58 138	99.44 265	98.05 214	99.68 122	99.80 158	96.81 161	99.80 243	98.15 267	98.92 252	99.60 202

test_yl		98.86 190	98.63 209	99.54 127	99.49 249	99.18 154	99.50 206	99.07 398	98.22 170	99.61 160	99.51 315	95.37 242	99.84 200	98.60 213	98.33 292	99.59 213

DCV-MVSNet		98.86 190	98.63 209	99.54 127	99.49 249	99.18 154	99.50 206	99.07 398	98.22 170	99.61 160	99.51 315	95.37 242	99.84 200	98.60 213	98.33 292	99.59 213

EPNet		98.86 190	98.71 197	99.30 211	97.20 486	98.18 290	99.62 109	98.91 425	99.28 32	98.63 374	99.81 140	95.96 211	99.99 4	99.24 109	99.72 148	99.73 128
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 190	98.80 184	99.03 246	99.76 82	98.79 238	99.28 331	99.91 3	97.42 305	99.67 128	99.37 361	97.53 122	99.88 168	98.98 145	97.29 361	98.42 438

ab-mvs		98.86 190	98.63 209	99.54 127	99.64 167	99.19 152	99.44 256	99.54 108	97.77 258	99.30 243	99.81 140	94.20 312	99.93 108	99.17 120	98.82 264	99.49 247

MAR-MVS		98.86 190	98.63 209	99.54 127	99.37 288	99.66 71	99.45 249	99.54 108	96.61 375	99.01 308	99.40 351	97.09 143	99.86 182	97.68 319	99.53 173	99.10 304
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	98.86 190	98.75 191	99.17 231	99.88 13	98.53 265	99.34 309	99.59 72	97.55 286	98.70 362	99.89 45	95.83 221	99.90 148	98.10 271	99.90 56	99.08 309
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 199	98.62 214	99.53 135	99.61 193	99.08 171	99.80 25	99.51 160	97.10 336	99.31 239	99.78 182	95.23 252	99.77 262	98.21 259	99.03 243	99.75 113

HY-MVS	97.30 7	98.85 199	98.64 208	99.47 170	99.42 269	99.08 171	99.62 109	99.36 311	97.39 308	99.28 247	99.68 242	96.44 183	99.92 123	98.37 245	98.22 303	99.40 274

PVSNet	96.02 17	98.85 199	98.84 181	98.89 273	99.73 107	97.28 337	98.32 489	99.60 67	97.86 242	99.50 187	99.57 291	96.75 165	99.86 182	98.56 222	99.70 152	99.54 227

PatchMatch-RL		98.84 202	98.62 214	99.52 142	99.71 117	99.28 142	99.06 395	99.77 12	97.74 264	99.50 187	99.53 307	95.41 240	99.84 200	97.17 368	99.64 162	99.44 266

Effi-MVS+		98.81 203	98.59 220	99.48 164	99.46 259	99.12 166	98.08 500	99.50 185	97.50 294	99.38 220	99.41 347	96.37 187	99.81 236	99.11 128	98.54 282	99.51 242

alignmvs		98.81 203	98.56 223	99.58 118	99.43 267	99.42 119	99.51 195	98.96 415	98.61 114	99.35 232	98.92 436	94.78 275	99.77 262	99.35 81	98.11 313	99.54 227

DeepPCF-MVS	98.18 3	98.81 203	99.37 43	97.12 440	99.60 199	91.75 483	98.61 466	99.44 265	99.35 27	99.83 64	99.85 91	98.70 70	99.81 236	99.02 142	99.91 45	99.81 79

PMMVS		98.80 206	98.62 214	99.34 198	99.27 316	98.70 247	98.76 451	99.31 346	97.34 311	99.21 268	99.07 411	97.20 137	99.82 231	98.56 222	98.87 259	99.52 233

icg_test_0407_2		98.79 207	98.86 176	98.57 321	99.55 218	96.93 367	99.07 391	99.44 265	98.05 214	99.66 133	99.80 158	97.13 139	99.18 406	98.15 267	98.92 252	99.60 202

viewdifsd2359ckpt11		98.78 208	98.74 193	98.89 273	99.67 138	97.04 356	99.50 206	99.58 77	98.26 159	99.56 173	99.90 36	94.36 305	99.87 175	99.49 61	98.32 296	99.77 100

viewmsd2359difaftdt		98.78 208	98.74 193	98.90 269	99.67 138	97.04 356	99.50 206	99.58 77	98.26 159	99.56 173	99.90 36	94.36 305	99.87 175	99.49 61	98.32 296	99.77 100

Effi-MVS+-dtu		98.78 208	98.89 169	98.47 339	99.33 298	96.91 372	99.57 146	99.30 351	98.47 128	99.41 211	98.99 426	96.78 163	99.74 272	98.73 192	99.38 183	98.74 351

FIs		98.78 208	98.63 209	99.23 226	99.18 340	99.54 99	99.83 15	99.59 72	98.28 154	98.79 349	99.81 140	96.75 165	99.37 362	99.08 134	96.38 381	98.78 339

Fast-Effi-MVS+-dtu		98.77 212	98.83 183	98.60 316	99.41 274	96.99 362	99.52 185	99.49 198	98.11 198	99.24 260	99.34 371	96.96 152	99.79 250	97.95 286	99.45 179	99.02 320

sd_testset		98.75 213	98.57 221	99.29 214	99.81 57	98.26 287	99.56 154	99.62 51	98.78 99	99.64 148	99.88 58	92.02 376	99.88 168	99.54 51	98.26 300	99.72 138

FA-MVS(test-final)		98.75 213	98.53 225	99.41 185	99.55 218	99.05 176	99.80 25	99.01 408	96.59 380	99.58 168	99.59 282	95.39 241	99.90 148	97.78 303	99.49 177	99.28 289

FC-MVSNet-test		98.75 213	98.62 214	99.15 236	99.08 367	99.45 116	99.86 11	99.60 67	98.23 169	98.70 362	99.82 125	96.80 162	99.22 397	99.07 135	96.38 381	98.79 337

XVG-OURS		98.73 216	98.68 200	98.88 278	99.70 122	97.73 319	98.92 428	99.55 99	98.52 123	99.45 195	99.84 106	95.27 247	99.91 135	98.08 276	98.84 262	99.00 321

Fast-Effi-MVS+		98.70 217	98.43 230	99.51 147	99.51 235	99.28 142	99.52 185	99.47 232	96.11 414	99.01 308	99.34 371	96.20 197	99.84 200	97.88 290	98.82 264	99.39 275

XVG-OURS-SEG-HR		98.69 218	98.62 214	98.89 273	99.71 117	97.74 318	99.12 381	99.54 108	98.44 134	99.42 206	99.71 219	94.20 312	99.92 123	98.54 226	98.90 258	99.00 321

1314		98.68 219	98.54 224	99.11 239	98.89 401	98.65 251	99.27 336	99.49 198	96.89 354	97.99 422	99.56 294	97.72 120	99.83 222	97.74 310	99.27 194	98.84 335

VortexMVS		98.67 220	98.66 204	98.68 311	99.62 182	97.96 306	99.59 128	99.41 281	98.13 188	99.31 239	99.70 223	95.48 239	99.27 382	99.40 72	97.32 360	98.79 337

EI-MVSNet		98.67 220	98.67 201	98.68 311	99.35 292	97.97 304	99.50 206	99.38 299	96.93 353	99.20 272	99.83 114	97.87 114	99.36 366	98.38 243	97.56 339	98.71 355

test_djsdf		98.67 220	98.57 221	98.98 252	98.70 433	98.91 208	99.88 4	99.46 245	97.55 286	99.22 265	99.88 58	95.73 229	99.28 379	99.03 140	97.62 334	98.75 347

QAPM		98.67 220	98.30 240	99.80 64	99.20 334	99.67 68	99.77 35	99.72 14	94.74 443	98.73 354	99.90 36	95.78 226	99.98 20	96.96 380	99.88 74	99.76 107

nrg030		98.64 224	98.42 231	99.28 218	99.05 377	99.69 63	99.81 20	99.46 245	98.04 221	99.01 308	99.82 125	96.69 167	99.38 359	99.34 86	94.59 427	98.78 339

test_vis1_n_1920		98.63 225	98.40 233	99.31 206	99.86 25	97.94 311	99.67 77	99.62 51	99.43 19	99.99 2	99.91 26	87.29 450	100.00 1	99.92 24	99.92 38	99.98 2

PAPR		98.63 225	98.34 236	99.51 147	99.40 279	99.03 178	98.80 445	99.36 311	96.33 395	99.00 312	99.12 409	98.46 88	99.84 200	95.23 433	99.37 190	99.66 175

CVMVSNet		98.57 227	98.67 201	98.30 359	99.35 292	95.59 424	99.50 206	99.55 99	98.60 116	99.39 218	99.83 114	94.48 301	99.45 343	98.75 189	98.56 280	99.85 47

IMVS_0404		98.53 228	98.52 226	98.55 327	99.55 218	96.93 367	99.20 364	99.44 265	98.05 214	98.96 319	99.80 158	94.66 290	99.13 414	98.15 267	98.92 252	99.60 202

MVSTER		98.49 229	98.32 238	99.00 250	99.35 292	99.02 179	99.54 174	99.38 299	97.41 306	99.20 272	99.73 212	93.86 329	99.36 366	98.87 165	97.56 339	98.62 399

FE-MVS		98.48 230	98.17 246	99.40 187	99.54 225	98.96 191	99.68 73	98.81 441	95.54 425	99.62 155	99.70 223	93.82 330	99.93 108	97.35 351	99.46 178	99.32 286

OpenMVS	96.50 16	98.47 231	98.12 253	99.52 142	99.04 379	99.53 102	99.82 16	99.72 14	94.56 446	98.08 417	99.88 58	94.73 283	99.98 20	97.47 340	99.76 140	99.06 315

IterMVS-LS		98.46 232	98.42 231	98.58 320	99.59 202	98.00 302	99.37 293	99.43 276	96.94 352	99.07 297	99.59 282	97.87 114	99.03 433	98.32 252	95.62 404	98.71 355
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 233	98.28 241	98.94 259	98.50 454	98.96 191	99.77 35	99.50 185	97.07 338	98.87 334	99.77 191	94.76 279	99.28 379	98.66 202	97.60 335	98.57 420

jajsoiax		98.43 234	98.28 241	98.88 278	98.60 447	98.43 280	99.82 16	99.53 124	98.19 176	98.63 374	99.80 158	93.22 343	99.44 348	99.22 110	97.50 346	98.77 343

tttt0517		98.42 235	98.14 250	99.28 218	99.66 150	98.38 283	99.74 48	96.85 502	97.68 271	99.79 78	99.74 206	91.39 395	99.89 163	98.83 178	99.56 170	99.57 220

BH-untuned		98.42 235	98.36 234	98.59 317	99.49 249	96.70 381	99.27 336	99.13 389	97.24 321	98.80 347	99.38 358	95.75 228	99.74 272	97.07 373	99.16 206	99.33 285

test_fmvs1_n		98.41 237	98.14 250	99.21 227	99.82 53	97.71 323	99.74 48	99.49 198	99.32 30	99.99 2	99.95 3	85.32 469	99.97 29	99.82 29	99.84 101	99.96 7

D2MVS		98.41 237	98.50 227	98.15 375	99.26 319	96.62 387	99.40 281	99.61 60	97.71 266	98.98 315	99.36 364	96.04 206	99.67 305	98.70 195	97.41 356	98.15 456

BH-RMVSNet		98.41 237	98.08 259	99.40 187	99.41 274	98.83 232	99.30 320	98.77 447	97.70 269	98.94 323	99.65 256	92.91 350	99.74 272	96.52 400	99.55 172	99.64 189

mvs_tets		98.40 240	98.23 244	98.91 267	98.67 438	98.51 271	99.66 84	99.53 124	98.19 176	98.65 371	99.81 140	92.75 352	99.44 348	99.31 91	97.48 350	98.77 343

MonoMVSNet		98.38 241	98.47 229	98.12 377	98.59 449	96.19 404	99.72 54	98.79 445	97.89 239	99.44 200	99.52 311	96.13 200	98.90 460	98.64 204	97.54 341	99.28 289

XXY-MVS		98.38 241	98.09 258	99.24 224	99.26 319	99.32 132	99.56 154	99.55 99	97.45 299	98.71 356	99.83 114	93.23 341	99.63 323	98.88 162	96.32 383	98.76 345

dtuonly		98.37 243	98.26 243	98.69 309	99.07 370	96.81 378	98.51 477	98.75 448	97.77 258	99.57 171	99.68 242	96.12 201	99.71 288	95.76 418	99.11 223	99.57 220

ACMM	97.58 5	98.37 243	98.34 236	98.48 334	99.41 274	97.10 347	99.56 154	99.45 256	98.53 122	99.04 305	99.85 91	93.00 346	99.71 288	98.74 190	97.45 351	98.64 390
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 245	98.03 265	99.31 206	99.63 172	98.56 262	99.54 174	96.75 504	97.53 290	99.73 100	99.65 256	91.25 399	99.89 163	98.62 207	99.56 170	99.48 250

tpmrst		98.33 246	98.48 228	97.90 396	99.16 350	94.78 448	99.31 318	99.11 391	97.27 317	99.45 195	99.59 282	95.33 245	99.84 200	98.48 229	98.61 274	99.09 308

baseline1		98.31 247	97.95 274	99.38 193	99.50 247	98.74 243	99.59 128	98.93 417	98.41 136	99.14 283	99.60 280	94.59 293	99.79 250	98.48 229	93.29 450	99.61 199

PatchmatchNet		98.31 247	98.36 234	98.19 370	99.16 350	95.32 436	99.27 336	98.92 420	97.37 309	99.37 223	99.58 286	94.90 266	99.70 296	97.43 346	99.21 201	99.54 227
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 249	97.98 270	99.26 220	99.57 210	98.16 291	99.41 273	98.55 469	96.03 419	99.19 275	99.74 206	91.87 379	99.92 123	99.16 123	98.29 299	99.70 154

VPA-MVSNet		98.29 250	97.95 274	99.30 211	99.16 350	99.54 99	99.50 206	99.58 77	98.27 156	99.35 232	99.37 361	92.53 364	99.65 313	99.35 81	94.46 428	98.72 353

UniMVSNet (Re)		98.29 250	98.00 268	99.13 238	99.00 384	99.36 127	99.49 223	99.51 160	97.95 233	98.97 317	99.13 405	96.30 192	99.38 359	98.36 247	93.34 449	98.66 386

HQP_MVS		98.27 252	98.22 245	98.44 345	99.29 311	96.97 364	99.39 285	99.47 232	98.97 76	99.11 288	99.61 277	92.71 357	99.69 302	97.78 303	97.63 332	98.67 377

UniMVSNet_NR-MVSNet		98.22 253	97.97 271	98.96 255	98.92 397	98.98 184	99.48 231	99.53 124	97.76 260	98.71 356	99.46 336	96.43 184	99.22 397	98.57 219	92.87 461	98.69 364

LPG-MVS_test		98.22 253	98.13 252	98.49 332	99.33 298	97.05 353	99.58 138	99.55 99	97.46 296	99.24 260	99.83 114	92.58 362	99.72 282	98.09 272	97.51 344	98.68 369

RPSCF		98.22 253	98.62 214	96.99 443	99.82 53	91.58 484	99.72 54	99.44 265	96.61 375	99.66 133	99.89 45	95.92 216	99.82 231	97.46 341	99.10 231	99.57 220

ADS-MVSNet		98.20 256	98.08 259	98.56 325	99.33 298	96.48 392	99.23 355	99.15 386	96.24 402	99.10 291	99.67 249	94.11 317	99.71 288	96.81 388	99.05 240	99.48 250

OPM-MVS		98.19 257	98.10 255	98.45 342	98.88 402	97.07 351	99.28 331	99.38 299	98.57 118	99.22 265	99.81 140	92.12 374	99.66 308	98.08 276	97.54 341	98.61 408
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 257	98.16 247	98.27 365	99.30 307	95.55 425	99.07 391	98.97 413	97.57 283	99.43 203	99.57 291	92.72 355	99.74 272	97.58 324	99.20 203	99.52 233

miper_ehance_all_eth		98.18 259	98.10 255	98.41 348	99.23 327	97.72 320	98.72 456	99.31 346	96.60 378	98.88 331	99.29 384	97.29 132	99.13 414	97.60 322	95.99 392	98.38 443

CR-MVSNet		98.17 260	97.93 277	98.87 282	99.18 340	98.49 274	99.22 359	99.33 331	96.96 348	99.56 173	99.38 358	94.33 308	99.00 442	94.83 440	98.58 277	99.14 300

miper_enhance_ethall		98.16 261	98.08 259	98.41 348	98.96 393	97.72 320	98.45 482	99.32 342	96.95 350	98.97 317	99.17 400	97.06 146	99.22 397	97.86 293	95.99 392	98.29 447

CLD-MVS		98.16 261	98.10 255	98.33 355	99.29 311	96.82 377	98.75 452	99.44 265	97.83 249	99.13 284	99.55 297	92.92 348	99.67 305	98.32 252	97.69 330	98.48 430
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 263	97.79 291	99.19 229	99.50 247	98.50 273	98.61 466	96.82 503	96.95 350	99.54 180	99.43 341	91.66 388	99.86 182	98.08 276	99.51 174	99.22 297

pmmvs4		98.13 264	97.90 279	98.81 294	98.61 445	98.87 223	98.99 414	99.21 379	96.44 390	99.06 302	99.58 286	95.90 218	99.11 420	97.18 367	96.11 388	98.46 435

WR-MVS_H		98.13 264	97.87 284	98.90 269	99.02 381	98.84 229	99.70 59	99.59 72	97.27 317	98.40 395	99.19 399	95.53 236	99.23 390	98.34 249	93.78 445	98.61 408

c3_l		98.12 266	98.04 264	98.38 352	99.30 307	97.69 324	98.81 444	99.33 331	96.67 368	98.83 342	99.34 371	97.11 142	98.99 444	97.58 324	95.34 411	98.48 430

ACMH	97.28 8	98.10 267	97.99 269	98.44 345	99.41 274	96.96 366	99.60 117	99.56 89	98.09 202	98.15 415	99.91 26	90.87 406	99.70 296	98.88 162	97.45 351	98.67 377
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
usedtu_dtu_shiyan1		98.09 268	97.82 288	98.89 273	98.70 433	98.90 213	98.57 469	99.47 232	96.78 360	98.87 334	99.05 415	94.75 280	99.23 390	97.45 343	96.74 371	98.53 424

FE-MVSNET3		98.09 268	97.82 288	98.89 273	98.70 433	98.90 213	98.57 469	99.47 232	96.78 360	98.87 334	99.05 415	94.75 280	99.23 390	97.45 343	96.74 371	98.53 424

Anonymous20240529		98.09 268	97.68 308	99.34 198	99.66 150	98.44 279	99.40 281	99.43 276	93.67 454	99.22 265	99.89 45	90.23 414	99.93 108	99.26 108	98.33 292	99.66 175

CP-MVSNet		98.09 268	97.78 294	99.01 248	98.97 392	99.24 148	99.67 77	99.46 245	97.25 319	98.48 389	99.64 262	93.79 331	99.06 429	98.63 206	94.10 439	98.74 351

dmvs_re		98.08 272	98.16 247	97.85 402	99.55 218	94.67 453	99.70 59	98.92 420	98.15 181	99.06 302	99.35 367	93.67 335	99.25 387	97.77 306	97.25 362	99.64 189

DU-MVS		98.08 272	97.79 291	98.96 255	98.87 405	98.98 184	99.41 273	99.45 256	97.87 241	98.71 356	99.50 318	94.82 270	99.22 397	98.57 219	92.87 461	98.68 369

v2v482		98.06 274	97.77 296	98.92 263	98.90 400	98.82 235	99.57 146	99.36 311	96.65 370	99.19 275	99.35 367	94.20 312	99.25 387	97.72 313	94.97 419	98.69 364

V42		98.06 274	97.79 291	98.86 285	98.98 390	98.84 229	99.69 63	99.34 323	96.53 382	99.30 243	99.37 361	94.67 288	99.32 374	97.57 328	94.66 425	98.42 438

test-LLR		98.06 274	97.90 279	98.55 327	98.79 415	97.10 347	98.67 459	97.75 487	97.34 311	98.61 378	98.85 438	94.45 303	99.45 343	97.25 359	99.38 183	99.10 304

WR-MVS		98.06 274	97.73 303	99.06 242	98.86 408	99.25 147	99.19 367	99.35 318	97.30 315	98.66 365	99.43 341	93.94 324	99.21 402	98.58 216	94.28 434	98.71 355

ACMP	97.20 11	98.06 274	97.94 276	98.45 342	99.37 288	97.01 360	99.44 256	99.49 198	97.54 289	98.45 392	99.79 175	91.95 378	99.72 282	97.91 288	97.49 349	98.62 399
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 279	97.96 272	98.33 355	99.26 319	97.38 334	98.56 473	99.31 346	96.65 370	98.88 331	99.52 311	96.58 174	99.12 419	97.39 348	95.53 408	98.47 432

test1111		98.04 280	98.11 254	97.83 408	99.74 100	93.82 465	99.58 138	95.40 514	99.12 46	99.65 143	99.93 10	90.73 407	99.84 200	99.43 69	99.38 183	99.82 72

ECVR-MVS		98.04 280	98.05 263	98.00 386	99.74 100	94.37 460	99.59 128	94.98 515	99.13 41	99.66 133	99.93 10	90.67 408	99.84 200	99.40 72	99.38 183	99.80 88

EPNet_dtu		98.03 282	97.96 272	98.23 368	98.27 461	95.54 427	99.23 355	98.75 448	99.02 62	97.82 431	99.71 219	96.11 202	99.48 337	93.04 465	99.65 161	99.69 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 282	97.76 300	98.84 289	99.39 282	98.98 184	99.40 281	99.38 299	96.67 368	99.07 297	99.28 386	92.93 347	98.98 445	97.10 369	96.65 374	98.56 421

ADS-MVSNet2		98.02 284	98.07 262	97.87 398	99.33 298	95.19 439	99.23 355	99.08 395	96.24 402	99.10 291	99.67 249	94.11 317	98.93 457	96.81 388	99.05 240	99.48 250

HQP-MVS		98.02 284	97.90 279	98.37 353	99.19 337	96.83 375	98.98 417	99.39 291	98.24 166	98.66 365	99.40 351	92.47 366	99.64 317	97.19 365	97.58 337	98.64 390

LTVRE_ROB	97.16 12	98.02 284	97.90 279	98.40 350	99.23 327	96.80 379	99.70 59	99.60 67	97.12 332	98.18 413	99.70 223	91.73 384	99.72 282	98.39 242	97.45 351	98.68 369
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____		98.01 287	97.84 287	98.55 327	99.25 323	97.97 304	98.71 457	99.34 323	96.47 389	98.59 381	99.54 302	95.65 232	99.21 402	97.21 361	95.77 398	98.46 435

DIV-MVS_self_test		98.01 287	97.85 286	98.48 334	99.24 325	97.95 309	98.71 457	99.35 318	96.50 383	98.60 380	99.54 302	95.72 230	99.03 433	97.21 361	95.77 398	98.46 435

miper_lstm_enhance		98.00 289	97.91 278	98.28 364	99.34 297	97.43 332	98.88 433	99.36 311	96.48 387	98.80 347	99.55 297	95.98 210	98.91 458	97.27 357	95.50 409	98.51 428

BH-w/o		98.00 289	97.89 283	98.32 357	99.35 292	96.20 403	99.01 411	98.90 427	96.42 392	98.38 396	99.00 424	95.26 249	99.72 282	96.06 410	98.61 274	99.03 318

v1144		97.98 291	97.69 307	98.85 288	98.87 405	98.66 250	99.54 174	99.35 318	96.27 400	99.23 264	99.35 367	94.67 288	99.23 390	96.73 391	95.16 415	98.68 369

EU-MVSNet		97.98 291	98.03 265	97.81 411	98.72 429	96.65 386	99.66 84	99.66 32	98.09 202	98.35 401	99.82 125	95.25 250	98.01 482	97.41 347	95.30 412	98.78 339

tpmvs		97.98 291	98.02 267	97.84 405	99.04 379	94.73 449	99.31 318	99.20 380	96.10 418	98.76 352	99.42 343	94.94 261	99.81 236	96.97 379	98.45 286	98.97 327

tt0805		97.97 294	97.77 296	98.57 321	99.59 202	96.61 388	99.45 249	99.08 395	98.21 172	98.88 331	99.80 158	88.66 434	99.70 296	98.58 216	97.72 329	99.39 275

NR-MVSNet		97.97 294	97.61 317	99.02 247	98.87 405	99.26 145	99.47 241	99.42 278	97.63 276	97.08 451	99.50 318	95.07 257	99.13 414	97.86 293	93.59 446	98.68 369

v8		97.95 296	97.63 315	98.93 261	98.95 394	98.81 237	99.80 25	99.41 281	96.03 419	99.10 291	99.42 343	94.92 264	99.30 377	96.94 382	94.08 440	98.66 386

Patchmatch-test		97.93 297	97.65 311	98.77 300	99.18 340	97.07 351	99.03 403	99.14 388	96.16 409	98.74 353	99.57 291	94.56 295	99.72 282	93.36 460	99.11 223	99.52 233

PS-CasMVS		97.93 297	97.59 319	98.95 257	98.99 387	99.06 174	99.68 73	99.52 133	97.13 330	98.31 403	99.68 242	92.44 370	99.05 430	98.51 227	94.08 440	98.75 347

TranMVSNet+NR-MVSNet		97.93 297	97.66 310	98.76 301	98.78 418	98.62 256	99.65 90	99.49 198	97.76 260	98.49 388	99.60 280	94.23 311	98.97 452	98.00 283	92.90 459	98.70 360

test_vis1_n		97.92 300	97.44 341	99.34 198	99.53 226	98.08 298	99.74 48	99.49 198	99.15 38	100.00 1	99.94 6	79.51 493	99.98 20	99.88 26	99.76 140	99.97 4

v144192		97.92 300	97.60 318	98.87 282	98.83 412	98.65 251	99.55 169	99.34 323	96.20 405	99.32 238	99.40 351	94.36 305	99.26 385	96.37 407	95.03 418	98.70 360

ACMH+	97.24 10	97.92 300	97.78 294	98.32 357	99.46 259	96.68 385	99.56 154	99.54 108	98.41 136	97.79 433	99.87 74	90.18 417	99.66 308	98.05 280	97.18 366	98.62 399

LFMVS		97.90 303	97.35 353	99.54 127	99.52 232	99.01 181	99.39 285	98.24 478	97.10 336	99.65 143	99.79 175	84.79 472	99.91 135	99.28 102	98.38 289	99.69 157

reproduce_monomvs		97.89 304	97.87 284	97.96 391	99.51 235	95.45 431	99.60 117	99.25 369	99.17 36	98.85 341	99.49 321	89.29 426	99.64 317	99.35 81	96.31 384	98.78 339

Anonymous20231211		97.88 305	97.54 323	98.90 269	99.71 117	98.53 265	99.48 231	99.57 84	94.16 449	98.81 345	99.68 242	93.23 341	99.42 355	98.84 175	94.42 431	98.76 345

OurMVSNet-221017-0		97.88 305	97.77 296	98.19 370	98.71 432	96.53 390	99.88 4	99.00 409	97.79 255	98.78 350	99.94 6	91.68 385	99.35 369	97.21 361	96.99 370	98.69 364

v7n		97.87 307	97.52 325	98.92 263	98.76 425	98.58 261	99.84 12	99.46 245	96.20 405	98.91 326	99.70 223	94.89 267	99.44 348	96.03 411	93.89 443	98.75 347

baseline2		97.87 307	97.55 320	98.82 291	99.18 340	98.02 301	99.41 273	96.58 508	96.97 347	96.51 459	99.17 400	93.43 336	99.57 329	97.71 314	99.03 243	98.86 333

thres600view7		97.86 309	97.51 327	98.92 263	99.72 111	97.95 309	99.59 128	98.74 452	97.94 234	99.27 253	98.62 449	91.75 382	99.86 182	93.73 454	98.19 307	98.96 329

UBG		97.85 310	97.48 330	98.95 257	99.25 323	97.64 325	99.24 352	98.74 452	97.90 238	98.64 372	98.20 467	88.65 435	99.81 236	98.27 255	98.40 287	99.42 268

cl22		97.85 310	97.64 314	98.48 334	99.09 364	97.87 313	98.60 468	99.33 331	97.11 335	98.87 334	99.22 395	92.38 371	99.17 408	98.21 259	95.99 392	98.42 438

v10		97.85 310	97.52 325	98.86 285	98.99 387	98.67 249	99.75 43	99.41 281	95.70 423	98.98 315	99.41 347	94.75 280	99.23 390	96.01 413	94.63 426	98.67 377

GA-MVS		97.85 310	97.47 333	99.00 250	99.38 285	97.99 303	98.57 469	99.15 386	97.04 343	98.90 328	99.30 382	89.83 420	99.38 359	96.70 393	98.33 292	99.62 197

testing3-2		97.84 314	97.70 306	98.24 367	99.53 226	95.37 435	99.55 169	98.67 463	98.46 129	99.27 253	99.34 371	86.58 457	99.83 222	99.32 89	98.63 273	99.52 233

tfpnnormal		97.84 314	97.47 333	98.98 252	99.20 334	99.22 150	99.64 98	99.61 60	96.32 396	98.27 407	99.70 223	93.35 340	99.44 348	95.69 421	95.40 410	98.27 448

VPNet		97.84 314	97.44 341	99.01 248	99.21 332	98.94 201	99.48 231	99.57 84	98.38 139	99.28 247	99.73 212	88.89 429	99.39 357	99.19 114	93.27 451	98.71 355

LCM-MVSNet-Re		97.83 317	98.15 249	96.87 449	99.30 307	92.25 481	99.59 128	98.26 476	97.43 303	96.20 463	99.13 405	96.27 193	98.73 468	98.17 264	98.99 247	99.64 189

XVG-ACMP-BASELINE		97.83 317	97.71 305	98.20 369	99.11 358	96.33 397	99.41 273	99.52 133	98.06 211	99.05 304	99.50 318	89.64 423	99.73 278	97.73 311	97.38 358	98.53 424

IterMVS		97.83 317	97.77 296	98.02 383	99.58 204	96.27 400	99.02 406	99.48 210	97.22 323	98.71 356	99.70 223	92.75 352	99.13 414	97.46 341	96.00 391	98.67 377
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 320	97.75 301	98.06 380	99.57 210	96.36 396	99.02 406	99.49 198	97.18 326	98.71 356	99.72 216	92.72 355	99.14 411	97.44 345	95.86 397	98.67 377

EPMVS		97.82 320	97.65 311	98.35 354	98.88 402	95.98 407	99.49 223	94.71 519	97.57 283	99.26 258	99.48 329	92.46 369	99.71 288	97.87 292	99.08 237	99.35 281

MVP-Stereo		97.81 322	97.75 301	97.99 387	97.53 478	96.60 389	98.96 421	98.85 436	97.22 323	97.23 445	99.36 364	95.28 246	99.46 341	95.51 425	99.78 134	97.92 475
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 322	97.44 341	98.91 267	98.88 402	98.68 248	99.51 195	99.34 323	96.18 407	99.20 272	99.34 371	94.03 321	99.36 366	95.32 431	95.18 414	98.69 364

ttmdpeth		97.80 324	97.63 315	98.29 360	98.77 423	97.38 334	99.64 98	99.36 311	98.78 99	96.30 462	99.58 286	92.34 373	99.39 357	98.36 247	95.58 405	98.10 458

v1921920		97.80 324	97.45 336	98.84 289	98.80 414	98.53 265	99.52 185	99.34 323	96.15 411	99.24 260	99.47 332	93.98 323	99.29 378	95.40 429	95.13 416	98.69 364

v148		97.79 326	97.55 320	98.50 331	98.74 426	97.72 320	99.54 174	99.33 331	96.26 401	98.90 328	99.51 315	94.68 287	99.14 411	97.83 297	93.15 455	98.63 397

thres400		97.77 327	97.38 349	98.92 263	99.69 128	97.96 306	99.50 206	98.73 458	97.83 249	99.17 280	98.45 456	91.67 386	99.83 222	93.22 462	98.18 308	98.96 329

thres100view900		97.76 328	97.45 336	98.69 309	99.72 111	97.86 315	99.59 128	98.74 452	97.93 235	99.26 258	98.62 449	91.75 382	99.83 222	93.22 462	98.18 308	98.37 444

PEN-MVS		97.76 328	97.44 341	98.72 304	98.77 423	98.54 264	99.78 33	99.51 160	97.06 340	98.29 406	99.64 262	92.63 361	98.89 461	98.09 272	93.16 454	98.72 353

Baseline_NR-MVSNet		97.76 328	97.45 336	98.68 311	99.09 364	98.29 285	99.41 273	98.85 436	95.65 424	98.63 374	99.67 249	94.82 270	99.10 423	98.07 279	92.89 460	98.64 390

TR-MVS		97.76 328	97.41 347	98.82 291	99.06 373	97.87 313	98.87 435	98.56 467	96.63 374	98.68 364	99.22 395	92.49 365	99.65 313	95.40 429	97.79 327	98.95 331

Patchmtry		97.75 332	97.40 348	98.81 294	99.10 361	98.87 223	99.11 387	99.33 331	94.83 441	98.81 345	99.38 358	94.33 308	99.02 437	96.10 409	95.57 406	98.53 424

dp		97.75 332	97.80 290	97.59 426	99.10 361	93.71 468	99.32 314	98.88 431	96.48 387	99.08 296	99.55 297	92.67 360	99.82 231	96.52 400	98.58 277	99.24 295

WBMVS		97.74 334	97.50 328	98.46 340	99.24 325	97.43 332	99.21 361	99.42 278	97.45 299	98.96 319	99.41 347	88.83 430	99.23 390	98.94 153	96.02 389	98.71 355

TAPA-MVS	97.07 15	97.74 334	97.34 356	98.94 259	99.70 122	97.53 328	99.25 347	99.51 160	91.90 480	99.30 243	99.63 268	98.78 53	99.64 317	88.09 493	99.87 78	99.65 182
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 336	97.35 353	98.88 278	99.47 257	97.12 346	99.34 309	98.85 436	98.19 176	99.67 128	99.85 91	82.98 481	99.92 123	99.49 61	98.32 296	99.60 202

MIMVSNet		97.73 336	97.45 336	98.57 321	99.45 265	97.50 330	99.02 406	98.98 412	96.11 414	99.41 211	99.14 404	90.28 410	98.74 467	95.74 419	98.93 250	99.47 256

tfpn200view9		97.72 338	97.38 349	98.72 304	99.69 128	97.96 306	99.50 206	98.73 458	97.83 249	99.17 280	98.45 456	91.67 386	99.83 222	93.22 462	98.18 308	98.37 444

CostFormer		97.72 338	97.73 303	97.71 418	99.15 354	94.02 464	99.54 174	99.02 406	94.67 444	99.04 305	99.35 367	92.35 372	99.77 262	98.50 228	97.94 318	99.34 284

FMVSNet2		97.72 338	97.36 351	98.80 296	99.51 235	98.84 229	99.45 249	99.42 278	96.49 384	98.86 340	99.29 384	90.26 411	98.98 445	96.44 402	96.56 377	98.58 418

test0.0.03 1		97.71 341	97.42 346	98.56 325	98.41 459	97.82 316	98.78 448	98.63 465	97.34 311	98.05 421	98.98 428	94.45 303	98.98 445	95.04 436	97.15 367	98.89 332

h-mvs33		97.70 342	97.28 366	98.97 254	99.70 122	97.27 338	99.36 299	99.45 256	98.94 79	99.66 133	99.64 262	94.93 262	99.99 4	99.48 64	84.36 497	99.65 182

myMVS_eth3d28		97.69 343	97.34 356	98.73 302	99.27 316	97.52 329	99.33 311	98.78 446	98.03 223	98.82 344	98.49 454	86.64 456	99.46 341	98.44 236	98.24 302	99.23 296

v1240		97.69 343	97.32 361	98.79 297	98.85 409	98.43 280	99.48 231	99.36 311	96.11 414	99.27 253	99.36 364	93.76 333	99.24 389	94.46 443	95.23 413	98.70 360

cascas		97.69 343	97.43 345	98.48 334	98.60 447	97.30 336	98.18 495	99.39 291	92.96 467	98.41 394	98.78 445	93.77 332	99.27 382	98.16 265	98.61 274	98.86 333

pm-mvs1		97.68 346	97.28 366	98.88 278	99.06 373	98.62 256	99.50 206	99.45 256	96.32 396	97.87 429	99.79 175	92.47 366	99.35 369	97.54 331	93.54 447	98.67 377

GBi-Net		97.68 346	97.48 330	98.29 360	99.51 235	97.26 340	99.43 262	99.48 210	96.49 384	99.07 297	99.32 379	90.26 411	98.98 445	97.10 369	96.65 374	98.62 399

test1		97.68 346	97.48 330	98.29 360	99.51 235	97.26 340	99.43 262	99.48 210	96.49 384	99.07 297	99.32 379	90.26 411	98.98 445	97.10 369	96.65 374	98.62 399

tpm		97.67 349	97.55 320	98.03 381	99.02 381	95.01 444	99.43 262	98.54 470	96.44 390	99.12 286	99.34 371	91.83 381	99.60 326	97.75 309	96.46 379	99.48 250

PCF-MVS	97.08 14	97.66 350	97.06 379	99.47 170	99.61 193	99.09 168	98.04 501	99.25 369	91.24 484	98.51 386	99.70 223	94.55 297	99.91 135	92.76 470	99.85 93	99.42 268
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 351	97.65 311	97.63 421	98.78 418	97.62 326	99.13 378	98.33 474	97.36 310	99.07 297	98.94 432	95.64 233	99.15 409	92.95 466	98.68 272	96.12 508

our_test_3		97.65 351	97.68 308	97.55 427	98.62 443	94.97 445	98.84 440	99.30 351	96.83 359	98.19 412	99.34 371	97.01 150	99.02 437	95.00 437	96.01 390	98.64 390

testgi		97.65 351	97.50 328	98.13 376	99.36 291	96.45 393	99.42 269	99.48 210	97.76 260	97.87 429	99.45 338	91.09 403	98.81 463	94.53 442	98.52 283	99.13 303

thres200		97.61 354	97.28 366	98.62 315	99.64 167	98.03 300	99.26 345	98.74 452	97.68 271	99.09 294	98.32 462	91.66 388	99.81 236	92.88 467	98.22 303	98.03 465

PAPM		97.59 355	97.09 378	99.07 241	99.06 373	98.26 287	98.30 490	99.10 392	94.88 439	98.08 417	99.34 371	96.27 193	99.64 317	89.87 484	98.92 252	99.31 287

UWE-MVS		97.58 356	97.29 365	98.48 334	99.09 364	96.25 401	99.01 411	96.61 507	97.86 242	99.19 275	99.01 422	88.72 431	99.90 148	97.38 349	98.69 271	99.28 289

SD_0403		97.55 357	97.53 324	97.62 422	99.61 193	93.64 471	99.72 54	99.44 265	98.03 223	98.62 377	99.39 355	96.06 205	99.57 329	87.88 495	99.01 246	99.66 175

VDDNet		97.55 357	97.02 380	99.16 232	99.49 249	98.12 296	99.38 290	99.30 351	95.35 427	99.68 122	99.90 36	82.62 483	99.93 108	99.31 91	98.13 312	99.42 268

TESTMET0.1,1		97.55 357	97.27 369	98.40 350	98.93 395	96.53 390	98.67 459	97.61 492	96.96 348	98.64 372	99.28 386	88.63 437	99.45 343	97.30 355	99.38 183	99.21 298

pmmvs5		97.52 360	97.30 363	98.16 372	98.57 450	96.73 380	99.27 336	98.90 427	96.14 412	98.37 397	99.53 307	91.54 391	99.14 411	97.51 335	95.87 396	98.63 397

LF4IMVS		97.52 360	97.46 335	97.70 419	98.98 390	95.55 425	99.29 325	98.82 439	98.07 207	98.66 365	99.64 262	89.97 418	99.61 325	97.01 375	96.68 373	97.94 473

DTE-MVSNet		97.51 362	97.19 372	98.46 340	98.63 442	98.13 294	99.84 12	99.48 210	96.68 367	97.97 424	99.67 249	92.92 348	98.56 471	96.88 387	92.60 465	98.70 360

testing11		97.50 363	97.10 377	98.71 307	99.20 334	96.91 372	99.29 325	98.82 439	97.89 239	98.21 411	98.40 458	85.63 465	99.83 222	98.45 235	98.04 315	99.37 279

ETVMVS		97.50 363	96.90 384	99.29 214	99.23 327	98.78 241	99.32 314	98.90 427	97.52 292	98.56 382	98.09 474	84.72 473	99.69 302	97.86 293	97.88 322	99.39 275

hse-mvs2		97.50 363	97.14 374	98.59 317	99.49 249	97.05 353	99.28 331	99.22 375	98.94 79	99.66 133	99.42 343	94.93 262	99.65 313	99.48 64	83.80 501	99.08 309

SixPastTwentyTwo		97.50 363	97.33 359	98.03 381	98.65 440	96.23 402	99.77 35	98.68 461	97.14 329	97.90 427	99.93 10	90.45 409	99.18 406	97.00 376	96.43 380	98.67 377

JIA-IIPM		97.50 363	97.02 380	98.93 261	98.73 427	97.80 317	99.30 320	98.97 413	91.73 481	98.91 326	94.86 510	95.10 256	99.71 288	97.58 324	97.98 316	99.28 289

ppachtmachnet_test		97.49 368	97.45 336	97.61 425	98.62 443	95.24 437	98.80 445	99.46 245	96.11 414	98.22 410	99.62 273	96.45 182	98.97 452	93.77 452	95.97 395	98.61 408

test-mter		97.49 368	97.13 376	98.55 327	98.79 415	97.10 347	98.67 459	97.75 487	96.65 370	98.61 378	98.85 438	88.23 441	99.45 343	97.25 359	99.38 183	99.10 304

testing91		97.44 370	97.02 380	98.71 307	99.18 340	96.89 374	99.19 367	99.04 402	97.78 257	98.31 403	98.29 463	85.41 468	99.85 190	98.01 282	97.95 317	99.39 275

tpm2		97.44 370	97.34 356	97.74 417	99.15 354	94.36 461	99.45 249	98.94 416	93.45 460	98.90 328	99.44 339	91.35 396	99.59 327	97.31 352	98.07 314	99.29 288

tpm cat1		97.39 372	97.36 351	97.50 429	99.17 348	93.73 467	99.43 262	99.31 346	91.27 483	98.71 356	99.08 410	94.31 310	99.77 262	96.41 405	98.50 284	99.00 321

UWE-MVS-28		97.36 373	97.24 370	97.75 415	98.84 411	94.44 458	99.24 352	97.58 494	97.98 231	99.00 312	99.00 424	91.35 396	99.53 335	93.75 453	98.39 288	99.27 293

testing99		97.36 373	96.94 383	98.63 314	99.18 340	96.70 381	99.30 320	98.93 417	97.71 266	98.23 408	98.26 465	84.92 471	99.84 200	98.04 281	97.85 325	99.35 281

SSC-MVS3.2		97.34 375	97.15 373	97.93 393	99.02 381	95.76 419	99.48 231	99.58 77	97.62 278	99.09 294	99.53 307	87.95 444	99.27 382	96.42 403	95.66 403	98.75 347

USDC		97.34 375	97.20 371	97.75 415	99.07 370	95.20 438	98.51 477	99.04 402	97.99 229	98.31 403	99.86 84	89.02 427	99.55 333	95.67 423	97.36 359	98.49 429

UniMVSNet_ETH3D		97.32 377	96.81 386	98.87 282	99.40 279	97.46 331	99.51 195	99.53 124	95.86 422	98.54 384	99.77 191	82.44 484	99.66 308	98.68 200	97.52 343	99.50 246

testing3		97.28 378	96.76 388	98.82 291	99.37 288	98.07 299	99.45 249	99.36 311	97.56 285	97.89 428	98.95 431	83.70 477	98.82 462	96.03 411	98.56 280	99.58 217

MVS		97.28 378	96.55 392	99.48 164	98.78 418	98.95 197	99.27 336	99.39 291	83.53 505	98.08 417	99.54 302	96.97 151	99.87 175	94.23 447	99.16 206	99.63 194

test_fmvs2		97.25 380	97.30 363	97.09 441	99.43 267	93.31 474	99.73 52	98.87 433	98.83 89	99.28 247	99.80 158	84.45 474	99.66 308	97.88 290	97.45 351	98.30 446

DSMNet-mixed		97.25 380	97.35 353	96.95 446	97.84 472	93.61 472	99.57 146	96.63 506	96.13 413	98.87 334	98.61 451	94.59 293	97.70 490	95.08 435	98.86 260	99.55 225

MS-PatchMatch		97.24 382	97.32 361	96.99 443	98.45 457	93.51 473	98.82 443	99.32 342	97.41 306	98.13 416	99.30 382	88.99 428	99.56 331	95.68 422	99.80 125	97.90 477

testing222		97.16 383	96.50 393	99.16 232	99.16 350	98.47 278	99.27 336	98.66 464	97.71 266	98.23 408	98.15 469	82.28 486	99.84 200	97.36 350	97.66 331	99.18 299

TransMVSNet (Re)		97.15 384	96.58 391	98.86 285	99.12 356	98.85 227	99.49 223	98.91 425	95.48 426	97.16 449	99.80 158	93.38 337	99.11 420	94.16 449	91.73 469	98.62 399

TinyColmap		97.12 385	96.89 385	97.83 408	99.07 370	95.52 428	98.57 469	98.74 452	97.58 282	97.81 432	99.79 175	88.16 442	99.56 331	95.10 434	97.21 364	98.39 442

K. test v3		97.10 386	96.79 387	98.01 384	98.72 429	96.33 397	99.87 8	97.05 499	97.59 280	96.16 464	99.80 158	88.71 432	99.04 431	96.69 394	96.55 378	98.65 388

Syy-MVS		97.09 387	97.14 374	96.95 446	99.00 384	92.73 478	99.29 325	99.39 291	97.06 340	97.41 439	98.15 469	93.92 326	98.68 469	91.71 476	98.34 290	99.45 264

dtuonlycased		97.04 388	97.33 359	96.16 459	99.08 367	90.59 489	98.79 447	99.38 299	97.19 325	96.91 456	99.49 321	90.22 416	98.75 466	97.04 374	97.89 321	99.14 300

PatchT		97.03 389	96.44 395	98.79 297	98.99 387	98.34 284	99.16 371	99.07 398	92.13 478	99.52 184	97.31 496	94.54 298	98.98 445	88.54 491	98.73 269	99.03 318

mmtdpeth		96.95 390	96.71 389	97.67 420	99.33 298	94.90 447	99.89 2	99.28 357	98.15 181	99.72 105	98.57 452	86.56 458	99.90 148	99.82 29	89.02 488	98.20 453

myMVS_eth3d		96.89 391	96.37 396	98.43 347	99.00 384	97.16 344	99.29 325	99.39 291	97.06 340	97.41 439	98.15 469	83.46 479	98.68 469	95.27 432	98.34 290	99.45 264

AUN-MVS		96.88 392	96.31 398	98.59 317	99.48 256	97.04 356	99.27 336	99.22 375	97.44 302	98.51 386	99.41 347	91.97 377	99.66 308	97.71 314	83.83 500	99.07 314

FMVSNet1		96.84 393	96.36 397	98.29 360	99.32 305	97.26 340	99.43 262	99.48 210	95.11 432	98.55 383	99.32 379	83.95 476	98.98 445	95.81 416	96.26 385	98.62 399

test2506		96.81 394	96.65 390	97.29 436	99.74 100	92.21 482	99.60 117	85.06 536	99.13 41	99.77 87	99.93 10	87.82 448	99.85 190	99.38 78	99.38 183	99.80 88

RPMNet		96.72 395	95.90 408	99.19 229	99.18 340	98.49 274	99.22 359	99.52 133	88.72 495	99.56 173	97.38 492	94.08 319	99.95 76	86.87 502	98.58 277	99.14 300

mvs5depth		96.66 396	96.22 400	97.97 389	97.00 491	96.28 399	98.66 462	99.03 405	96.61 375	96.93 455	99.79 175	87.20 451	99.47 339	96.65 398	94.13 437	98.16 455

test_0402		96.64 397	96.24 399	97.85 402	98.85 409	96.43 394	99.44 256	99.26 366	93.52 457	96.98 453	99.52 311	88.52 438	99.20 404	92.58 473	97.50 346	97.93 474

X-MVStestdata		96.55 398	95.45 418	99.87 22	99.85 31	99.83 22	99.69 63	99.68 24	98.98 72	99.37 223	64.01 544	98.81 49	99.94 91	98.79 186	99.86 86	99.84 54

pmmvs6		96.53 399	96.09 404	97.82 410	98.69 436	95.47 429	99.37 293	99.47 232	93.46 459	97.41 439	99.78 182	87.06 455	99.33 372	96.92 385	92.70 463	98.65 388

ET-MVSNet_ETH3D		96.49 400	95.64 415	99.05 244	99.53 226	98.82 235	98.84 440	97.51 495	97.63 276	84.77 512	99.21 398	92.09 375	98.91 458	98.98 145	92.21 467	99.41 271

UnsupCasMVSNet_eth		96.44 401	96.12 402	97.40 432	98.65 440	95.65 422	99.36 299	99.51 160	97.13 330	96.04 466	98.99 426	88.40 439	98.17 478	96.71 392	90.27 481	98.40 441

FMVSNet5		96.43 402	96.19 401	97.15 437	99.11 358	95.89 414	99.32 314	99.52 133	94.47 448	98.34 402	99.07 411	87.54 449	97.07 496	92.61 472	95.72 401	98.47 432

new_pmnet		96.38 403	96.03 405	97.41 431	98.13 466	95.16 441	99.05 398	99.20 380	93.94 450	97.39 442	98.79 444	91.61 390	99.04 431	90.43 482	95.77 398	98.05 463

Anonymous20231206		96.22 404	96.03 405	96.79 451	97.31 484	94.14 463	99.63 104	99.08 395	96.17 408	97.04 452	99.06 413	93.94 324	97.76 488	86.96 501	95.06 417	98.47 432

IB-MVS	95.67 18	96.22 404	95.44 419	98.57 321	99.21 332	96.70 381	98.65 463	97.74 489	96.71 365	97.27 444	98.54 453	86.03 462	99.92 123	98.47 232	86.30 494	99.10 304
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		96.20 406	95.89 409	97.13 439	97.72 477	94.96 446	99.79 31	99.29 355	93.01 465	97.20 448	99.03 419	89.69 422	98.36 475	91.16 479	96.13 387	98.07 461

ArgMatch-SfM		96.18 407	95.78 412	97.38 433	99.08 367	94.64 454	99.20 364	99.33 331	98.01 227	98.54 384	99.54 302	83.13 480	99.43 352	93.86 451	91.29 471	98.08 460

gg-mvs-nofinetune		96.17 408	95.32 420	98.73 302	98.79 415	98.14 293	99.38 290	94.09 521	91.07 486	98.07 420	91.04 523	89.62 424	99.35 369	96.75 390	99.09 236	98.68 369

test20.03		96.12 409	95.96 407	96.63 452	97.44 479	95.45 431	99.51 195	99.38 299	96.55 381	96.16 464	99.25 392	93.76 333	96.17 505	87.35 498	94.22 435	98.27 448

PVSNet_0	94.43 19	96.09 410	95.47 417	97.94 392	99.31 306	94.34 462	97.81 506	99.70 18	97.12 332	97.46 438	98.75 446	89.71 421	99.79 250	97.69 318	81.69 510	99.68 163

MVStest1		96.08 411	95.48 416	97.89 397	98.93 395	96.70 381	99.56 154	99.35 318	92.69 470	91.81 497	99.46 336	89.90 419	98.96 454	95.00 437	92.61 464	98.00 469

EG-PatchMatch MVS		95.97 412	95.69 413	96.81 450	97.78 474	92.79 477	99.16 371	98.93 417	96.16 409	94.08 483	99.22 395	82.72 482	99.47 339	95.67 423	97.50 346	98.17 454

APD_test1		95.87 413	96.49 394	94.00 471	99.53 226	84.01 503	99.54 174	99.32 342	95.91 421	97.99 422	99.85 91	85.49 467	99.88 168	91.96 474	98.84 262	98.12 457

Patchmatch-RL test		95.84 414	95.81 411	95.95 462	95.61 508	90.57 490	98.24 491	98.39 472	95.10 434	95.20 471	98.67 448	94.78 275	97.77 487	96.28 408	90.02 482	99.51 242

test_vis1_rt		95.81 415	95.65 414	96.32 457	99.67 138	91.35 485	99.49 223	96.74 505	98.25 164	95.24 469	98.10 473	74.96 495	99.90 148	99.53 53	98.85 261	97.70 483

sc_t1		95.75 416	95.05 424	97.87 398	98.83 412	94.61 455	99.21 361	99.45 256	87.45 497	97.97 424	99.85 91	81.19 489	99.43 352	98.27 255	93.20 453	99.57 220

MVS-HIRNet		95.75 416	95.16 421	97.51 428	99.30 307	93.69 469	98.88 433	95.78 511	85.09 504	98.78 350	92.65 519	91.29 398	99.37 362	94.85 439	99.85 93	99.46 261

tt0320		95.71 418	95.07 423	97.62 422	99.05 377	95.02 443	99.25 347	99.52 133	86.81 498	97.97 424	99.72 216	83.58 478	99.15 409	96.38 406	93.35 448	98.68 369

blended_shiyan8		95.56 419	94.79 427	97.87 398	96.60 495	95.90 413	98.85 436	99.27 364	92.19 473	98.47 390	97.94 479	91.43 393	99.11 420	97.26 358	81.09 513	98.60 411

blended_shiyan6		95.54 420	94.78 428	97.84 405	96.60 495	95.89 414	98.85 436	99.28 357	92.17 477	98.43 393	97.95 477	91.44 392	99.02 437	97.30 355	80.97 514	98.60 411

MIMVSNet1		95.51 421	95.04 425	96.92 448	97.38 481	95.60 423	99.52 185	99.50 185	93.65 455	96.97 454	99.17 400	85.28 470	96.56 502	88.36 492	95.55 407	98.60 411

MDA-MVSNet_test_wron		95.45 422	94.60 432	98.01 384	98.16 465	97.21 343	99.11 387	99.24 372	93.49 458	80.73 522	98.98 428	93.02 345	98.18 477	94.22 448	94.45 430	98.64 390

wanda-best-256-512		95.43 423	94.66 430	97.77 413	96.45 497	95.68 420	98.48 479	99.28 357	92.18 475	98.36 398	97.68 484	91.20 400	99.03 433	97.31 352	80.97 514	98.60 411

FE-blended-shiyan7		95.43 423	94.66 430	97.77 413	96.45 497	95.68 420	98.48 479	99.28 357	92.18 475	98.36 398	97.68 484	91.20 400	99.03 433	97.31 352	80.97 514	98.60 411

TDRefinement		95.42 425	94.57 435	97.97 389	89.83 538	96.11 406	99.48 231	98.75 448	96.74 363	96.68 458	99.88 58	88.65 435	99.71 288	98.37 245	82.74 507	98.09 459

gbinet_0.2-2-1-0.02		95.40 426	94.58 434	97.85 402	96.11 502	95.97 408	98.56 473	99.26 366	92.12 479	98.47 390	97.49 490	90.23 414	99.00 442	97.71 314	81.25 511	98.58 418

YYNet1		95.36 427	94.51 436	97.92 394	97.89 470	97.10 347	99.10 389	99.23 373	93.26 462	80.77 521	99.04 418	92.81 351	98.02 481	94.30 444	94.18 436	98.64 390

pmmvs-eth3d		95.34 428	94.73 429	97.15 437	95.53 510	95.94 410	99.35 304	99.10 392	95.13 430	93.55 487	97.54 489	88.15 443	97.91 484	94.58 441	89.69 486	97.61 485

tt0320-xc		95.31 429	94.59 433	97.45 430	98.92 397	94.73 449	99.20 364	99.31 346	86.74 499	97.23 445	99.72 216	81.14 490	98.95 455	97.08 372	91.98 468	98.67 377

blend_shiyan4		95.25 430	94.39 438	97.84 405	96.70 494	95.92 411	98.84 440	99.28 357	92.21 472	98.16 414	97.84 481	87.10 454	99.07 426	97.53 332	81.87 509	98.54 422

0.4-1-1-0.1		95.23 431	94.22 440	98.26 366	97.39 480	95.86 416	97.59 510	97.62 490	93.85 452	94.97 476	97.03 498	87.20 451	99.87 175	98.47 232	83.84 499	99.05 316

FE-MVSNET2		95.10 432	94.44 437	97.08 442	95.08 514	95.97 408	99.51 195	99.37 309	95.02 436	94.10 482	97.57 487	86.18 461	97.66 492	93.28 461	89.86 484	97.61 485

usedtu_blend_shiyan5		95.04 433	94.10 441	97.86 401	96.45 497	95.92 411	99.29 325	99.22 375	86.17 502	98.36 398	97.68 484	91.20 400	99.07 426	97.53 332	80.97 514	98.60 411

dmvs_testset		95.02 434	96.12 402	91.72 483	99.10 361	80.43 516	99.58 138	97.87 486	97.47 295	95.22 470	98.82 440	93.99 322	95.18 511	88.09 493	94.91 422	99.56 224

KD-MVS_self_test		95.00 435	94.34 439	96.96 445	97.07 490	95.39 434	99.56 154	99.44 265	95.11 432	97.13 450	97.32 495	91.86 380	97.27 495	90.35 483	81.23 512	98.23 452

MDA-MVSNet-bldmvs		94.96 436	93.98 444	97.92 394	98.24 462	97.27 338	99.15 374	99.33 331	93.80 453	80.09 523	99.03 419	88.31 440	97.86 486	93.49 458	94.36 432	98.62 399

N_pmnet		94.95 437	95.83 410	92.31 481	98.47 455	79.33 520	99.12 381	92.81 527	93.87 451	97.68 434	99.13 405	93.87 328	99.01 440	91.38 478	96.19 386	98.59 417

0.4-1-1-0.2		94.94 438	93.92 446	97.99 387	96.84 493	95.13 442	96.64 516	97.62 490	93.45 460	94.92 477	96.56 502	87.14 453	99.86 182	98.43 239	83.69 503	98.98 325

MASt3R-SfM		94.79 439	95.11 422	93.81 474	97.96 467	85.14 501	98.52 475	98.99 410	95.33 428	97.53 437	99.13 405	79.99 492	99.48 337	93.66 455	94.90 423	96.80 498

0.3-1-1-0.015		94.79 439	93.69 452	98.10 378	96.99 492	95.46 430	97.02 514	97.61 492	93.53 456	94.03 484	96.54 503	85.60 466	99.86 182	98.43 239	83.45 504	98.99 324

KD-MVS_2432*1600		94.62 441	93.72 449	97.31 434	97.19 487	95.82 417	98.34 486	99.20 380	95.00 437	97.57 435	98.35 460	87.95 444	98.10 479	92.87 468	77.00 523	98.01 466

miper_refine_blended		94.62 441	93.72 449	97.31 434	97.19 487	95.82 417	98.34 486	99.20 380	95.00 437	97.57 435	98.35 460	87.95 444	98.10 479	92.87 468	77.00 523	98.01 466

CL-MVSNet_self_test		94.49 443	93.97 445	96.08 460	96.16 501	93.67 470	98.33 488	99.38 299	95.13 430	97.33 443	98.15 469	92.69 359	96.57 501	88.67 490	79.87 521	97.99 470

new-patchmatchnet		94.48 444	94.08 443	95.67 464	95.08 514	92.41 479	99.18 369	99.28 357	94.55 447	93.49 488	97.37 493	87.86 447	97.01 498	91.57 477	88.36 489	97.61 485

OpenMVS_ROB	92.34 20	94.38 445	93.70 451	96.41 456	97.38 481	93.17 475	99.06 395	98.75 448	86.58 500	94.84 478	98.26 465	81.53 487	99.32 374	89.01 489	97.87 323	96.76 499

RoMa-SfM		94.36 446	93.86 447	95.88 463	98.61 445	90.62 488	98.85 436	99.04 402	91.63 482	94.14 481	99.49 321	77.16 494	99.09 425	92.66 471	93.13 456	97.91 476

DenseAffine		94.28 447	93.53 453	96.52 455	98.72 429	92.31 480	98.78 448	99.02 406	93.14 464	94.45 479	99.01 422	74.73 498	99.20 404	90.98 480	92.94 458	98.04 464

CMPMVS	69.68 23	94.13 448	94.90 426	91.84 482	97.24 485	80.01 517	98.52 475	99.48 210	89.01 492	91.99 496	99.67 249	85.67 464	99.13 414	95.44 427	97.03 369	96.39 505
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 449	93.25 456	96.60 453	94.76 517	94.49 457	98.92 428	98.18 482	89.66 488	96.48 460	98.06 475	86.28 460	97.33 494	89.68 485	87.20 493	97.97 472

FE-MVSNET		94.07 450	93.36 455	96.22 458	94.05 521	94.71 451	99.56 154	98.36 473	93.15 463	93.76 486	97.55 488	86.47 459	96.49 503	87.48 496	89.83 485	97.48 490

mvsany_test3		93.77 451	93.45 454	94.74 469	95.78 506	88.01 495	99.64 98	98.25 477	98.28 154	94.31 480	97.97 476	68.89 511	98.51 473	97.50 336	90.37 479	97.71 480

UnsupCasMVSNet_bld		93.53 452	92.51 458	96.58 454	97.38 481	93.82 465	98.24 491	99.48 210	91.10 485	93.10 489	96.66 501	74.89 497	98.37 474	94.03 450	87.71 492	97.56 488

dongtai		93.26 453	92.93 457	94.25 470	99.39 282	85.68 499	97.68 508	93.27 523	92.87 468	96.85 457	99.39 355	82.33 485	97.48 493	76.78 515	97.80 326	99.58 217

LoFTR		93.25 454	92.33 460	95.99 461	97.91 468	90.83 486	99.06 395	98.56 467	92.19 473	90.24 501	98.18 468	72.97 499	99.26 385	89.37 486	92.52 466	97.89 478

DKM		93.17 455	92.50 459	95.21 467	98.53 453	90.26 491	98.74 455	98.90 427	93.00 466	92.61 492	99.06 413	70.06 508	97.74 489	91.92 475	89.65 487	97.62 484

WB-MVS		93.10 456	94.10 441	90.12 494	95.51 512	81.88 509	99.73 52	99.27 364	95.05 435	93.09 490	98.91 437	94.70 286	91.89 522	76.62 516	94.02 442	96.58 503

PM-MVS		92.96 457	92.23 461	95.14 468	95.61 508	89.98 493	99.37 293	98.21 480	94.80 442	95.04 475	97.69 483	65.06 514	97.90 485	94.30 444	89.98 483	97.54 489

SSC-MVS		92.73 458	93.73 448	89.72 497	95.02 516	81.38 511	99.76 38	99.23 373	94.87 440	92.80 491	98.93 433	94.71 285	91.37 524	74.49 521	93.80 444	96.42 504

test_fmvs3		92.10 459	91.77 462	93.08 478	96.19 500	86.25 496	99.82 16	98.62 466	96.65 370	95.19 472	96.90 499	55.05 523	95.93 507	96.63 399	90.92 478	97.06 496

MatchFormer		91.94 460	90.72 465	95.58 465	97.82 473	89.79 494	98.92 428	98.87 433	88.24 496	88.03 506	97.92 480	70.39 506	99.23 390	85.21 507	91.12 474	97.72 479

test_f		91.90 461	91.26 464	93.84 473	95.52 511	85.92 497	99.69 63	98.53 471	95.31 429	93.87 485	96.37 505	55.33 522	98.27 476	95.70 420	90.98 477	97.32 492

usedtu_dtu_shiyan2		91.34 462	89.96 471	95.47 466	93.61 525	90.81 487	99.15 374	98.68 461	86.37 501	95.19 472	98.27 464	72.64 501	97.05 497	85.40 506	80.32 519	98.54 422

test_method		91.10 463	91.36 463	90.31 491	95.85 505	73.72 529	94.89 518	99.25 369	68.39 520	95.82 467	99.02 421	80.50 491	98.95 455	93.64 456	94.89 424	98.25 450

Gipuma		90.99 464	90.15 469	93.51 475	98.73 427	90.12 492	93.98 523	99.45 256	79.32 508	92.28 493	94.91 509	69.61 509	97.98 483	87.42 497	95.67 402	92.45 516
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 465	90.11 470	93.34 476	98.78 418	85.59 500	98.15 498	93.16 525	89.37 491	92.07 495	98.38 459	81.48 488	95.19 510	62.54 527	97.04 368	99.25 294

SP-DiffGlue		90.78 466	90.71 466	90.98 487	95.45 513	81.30 512	97.92 504	97.30 497	75.18 511	92.09 494	95.93 506	74.93 496	94.89 514	93.46 459	94.12 438	96.74 501

testf1		90.42 467	90.68 467	89.65 498	97.78 474	73.97 527	99.13 378	98.81 441	89.62 489	91.80 498	98.93 433	62.23 518	98.80 464	86.61 503	91.17 472	96.19 506

APD_test2		90.42 467	90.68 467	89.65 498	97.78 474	73.97 527	99.13 378	98.81 441	89.62 489	91.80 498	98.93 433	62.23 518	98.80 464	86.61 503	91.17 472	96.19 506

ELoFTR		89.95 469	88.65 474	93.85 472	95.93 503	85.85 498	98.64 464	98.31 475	90.34 487	85.03 511	97.76 482	60.28 520	99.01 440	87.27 499	84.26 498	96.71 502

SP-LightGlue		89.28 470	88.68 472	91.06 486	98.21 464	80.90 514	98.19 494	96.96 500	72.38 514	89.60 504	94.43 512	72.44 502	95.06 512	82.91 509	93.03 457	97.22 493

SP-SuperGlue		89.23 471	88.68 472	90.88 488	98.23 463	80.60 515	98.16 496	97.30 497	73.08 513	89.64 503	94.62 511	71.80 504	94.91 513	82.11 511	93.22 452	97.14 495

SP-NN		88.62 472	88.17 475	89.96 495	97.89 470	78.51 521	97.19 512	96.09 509	71.28 516	88.29 505	94.00 515	71.98 503	93.65 518	82.37 510	94.46 428	97.71 480

SP-MNN		88.33 473	87.78 476	89.95 496	98.28 460	77.92 522	98.01 502	95.69 513	70.61 518	86.18 509	94.36 513	71.09 505	94.76 515	81.51 512	94.32 433	97.17 494

PMatch-SfM		88.28 474	86.92 479	92.38 480	95.93 503	84.56 502	97.84 505	96.01 510	88.80 494	84.11 514	97.95 477	49.73 529	95.66 509	89.15 488	82.72 508	96.91 497

ALIKED-NN		88.27 475	87.61 477	90.24 492	98.46 456	79.97 518	97.04 513	94.61 520	75.25 510	86.99 507	96.90 499	72.78 500	95.78 508	75.45 519	91.01 476	94.97 511

ALIKED-LG		88.17 476	87.32 478	90.75 489	98.67 438	81.68 510	98.16 496	94.72 518	78.63 509	86.08 510	97.07 497	70.16 507	96.62 500	71.97 523	90.37 479	93.95 513

test_vis3_rt		87.04 477	85.81 481	90.73 490	93.99 522	81.96 508	99.76 38	90.23 531	92.81 469	81.35 520	91.56 521	40.06 539	99.07 426	94.27 446	88.23 490	91.15 519

ALIKED-MNN		86.97 478	85.90 480	90.16 493	99.06 373	79.59 519	97.93 503	94.82 516	72.37 515	84.41 513	95.46 507	68.55 512	96.43 504	72.40 522	88.11 491	94.47 512

PMMVS2		86.87 479	85.37 483	91.35 485	90.21 535	83.80 505	98.89 432	97.45 496	83.13 507	91.67 500	95.03 508	48.49 533	94.70 516	85.86 505	77.62 522	95.54 509

LCM-MVSNet		86.80 480	85.22 484	91.53 484	87.81 541	80.96 513	98.23 493	98.99 410	71.05 517	90.13 502	96.51 504	48.45 534	96.88 499	90.51 481	85.30 496	96.76 499

FPMVS		84.93 481	85.65 482	82.75 507	86.77 542	63.39 534	98.35 485	98.92 420	74.11 512	83.39 517	98.98 428	50.85 526	92.40 521	84.54 508	94.97 419	92.46 515

PDCNetPlus		84.77 482	83.24 485	89.36 500	94.33 520	83.93 504	98.13 499	76.80 541	83.26 506	86.31 508	97.33 494	62.90 516	92.65 519	87.20 500	62.90 527	91.50 518

XFeat-NN		82.84 483	83.12 486	82.00 509	94.35 519	67.14 533	93.32 528	89.27 532	62.21 526	84.06 515	93.50 517	69.15 510	89.40 525	78.92 513	83.33 505	89.46 522

EGC-MVSNET		82.80 484	77.86 491	97.62 422	97.91 468	96.12 405	99.33 311	99.28 357	8.40 545	25.05 546	99.27 389	84.11 475	99.33 372	89.20 487	98.22 303	97.42 491

tmp_tt		82.80 484	81.52 488	86.66 502	66.61 548	68.44 532	92.79 531	97.92 484	68.96 519	80.04 524	99.85 91	85.77 463	96.15 506	97.86 293	43.89 536	95.39 510

XFeat-MNN		82.40 486	82.10 487	83.31 505	93.04 527	68.49 531	95.39 517	90.86 529	60.29 527	81.56 519	94.09 514	66.79 513	91.70 523	76.62 516	80.26 520	89.74 521

E-PMN		80.61 487	79.88 489	82.81 506	90.75 533	76.38 525	97.69 507	95.76 512	66.44 522	83.52 516	92.25 520	62.54 517	87.16 533	68.53 525	61.40 528	84.89 525

EMVS		80.02 488	79.22 490	82.43 508	91.19 532	76.40 524	97.55 511	92.49 528	66.36 524	83.01 518	91.27 522	64.63 515	85.79 536	65.82 526	60.65 529	85.08 524

GLUNet-SfM		78.99 489	76.32 493	86.99 501	89.16 540	73.30 530	93.36 527	90.45 530	66.38 523	74.95 529	93.30 518	52.29 525	94.61 517	75.35 520	51.65 534	93.07 514

ANet_high		77.30 490	74.86 497	84.62 504	75.88 546	77.61 523	97.63 509	93.15 526	88.81 493	64.27 532	89.29 534	36.51 542	83.93 537	75.89 518	52.31 532	92.33 517

SIFT-NN		76.99 491	77.37 492	75.84 511	97.10 489	62.39 535	94.15 522	87.21 534	59.41 528	79.90 525	90.73 525	54.60 524	88.56 528	47.22 529	86.03 495	76.57 527

MVE	76.82 21	76.91 492	74.31 498	84.70 503	85.38 545	76.05 526	96.88 515	93.17 524	67.39 521	71.28 530	89.01 536	21.66 549	87.69 531	71.74 524	72.29 525	90.35 520
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 493	74.97 496	79.01 510	70.98 547	55.18 546	93.37 526	98.21 480	65.08 525	61.78 535	93.83 516	21.74 548	92.53 520	78.59 514	91.12 474	89.34 523
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-MNN		75.73 494	75.71 494	75.77 512	95.65 507	60.92 537	94.36 520	87.62 533	58.67 529	75.90 527	90.94 524	49.64 531	89.04 527	44.85 534	83.80 501	77.35 526

SIFT-NN-NCMNet		75.53 495	75.57 495	75.42 513	93.93 523	61.35 536	94.41 519	86.44 535	58.51 530	76.23 526	90.44 527	50.56 527	89.34 526	46.60 530	83.04 506	75.58 529

SIFT-NN-CMatch		72.61 496	71.92 499	74.68 514	92.79 528	60.24 539	93.28 529	81.57 539	58.24 532	75.18 528	90.26 529	49.66 530	87.35 532	46.02 531	60.26 530	76.45 528

SIFT-NCM-Cal		71.65 497	70.76 501	74.34 515	94.61 518	60.18 540	94.16 521	81.72 538	57.21 534	55.36 538	89.56 533	42.48 535	88.45 529	41.31 539	80.41 518	74.39 531

SIFT-NN-UMatch		71.65 497	70.86 500	74.00 516	90.69 534	60.53 538	93.59 524	81.89 537	58.42 531	60.99 536	89.71 532	50.18 528	87.89 530	45.77 532	66.55 526	73.57 533

SIFT-NN-PointCN		70.32 499	69.71 502	72.13 519	90.01 536	58.29 544	93.45 525	76.20 542	56.66 537	70.25 531	89.20 535	48.94 532	83.41 538	45.45 533	57.26 531	74.70 530

SIFT-ConvMatch		69.43 500	68.09 503	73.45 517	93.86 524	60.02 541	92.57 532	77.69 540	57.58 533	62.69 533	90.53 526	42.14 536	86.65 535	43.98 535	51.72 533	73.67 532

SIFT-UMatch		68.14 501	66.40 504	73.38 518	92.20 531	59.42 542	92.84 530	76.01 543	56.87 535	58.37 537	90.35 528	41.97 537	87.16 533	42.64 536	46.35 535	73.55 534

SIFT-CM-Cal		66.94 502	65.48 505	71.33 520	93.05 526	58.77 543	91.46 535	70.45 545	56.64 538	61.97 534	89.98 530	40.72 538	83.32 539	42.57 537	42.47 537	71.90 535

SIFT-UM-Cal		64.60 503	62.65 506	70.42 521	92.22 530	58.07 545	92.29 533	66.92 546	56.70 536	50.16 540	89.97 531	37.90 540	82.95 540	42.33 538	35.40 540	70.24 537

SIFT-PointCN		62.71 504	61.56 507	66.18 522	89.53 539	50.88 547	91.81 534	72.35 544	53.65 539	50.49 539	86.32 538	33.30 543	76.23 542	35.91 543	40.66 538	71.43 536

SIFT-PCN-Cal		61.29 505	60.21 508	64.54 523	89.88 537	50.56 548	91.21 536	65.73 547	53.15 540	48.59 541	87.20 537	36.60 541	76.52 541	37.37 542	32.17 541	66.54 538

SIFT-NCMNet		55.02 506	53.54 509	59.46 524	86.55 543	47.35 550	87.85 537	46.22 548	51.77 541	44.11 542	83.50 539	27.88 546	68.75 543	32.81 544	21.14 544	62.27 539

wuyk23d		40.18 507	41.29 512	36.84 525	86.18 544	49.12 549	79.73 538	22.81 550	27.64 542	25.46 545	28.45 545	21.98 547	48.89 544	55.80 528	23.56 543	12.51 542

testmvs		39.17 508	43.78 510	25.37 527	36.04 550	16.84 552	98.36 484	26.56 549	20.06 543	38.51 544	67.32 540	29.64 545	15.30 546	37.59 540	39.90 539	43.98 541

test123		39.01 509	42.50 511	28.53 526	39.17 549	20.91 551	98.75 452	19.17 551	19.83 544	38.57 543	66.67 541	33.16 544	15.42 545	37.50 541	29.66 542	49.26 540

cdsmvs_eth3d_5k		24.64 510	32.85 513	0.00 528	0.00 551	0.00 553	0.00 539	99.51 160	0.00 546	0.00 547	99.56 294	96.58 174	0.00 547	0.00 545	0.00 545	0.00 543

ab-mvs-re		8.30 511	11.06 514	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	99.58 286	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

pcd_1.5k_mvsjas		8.27 512	11.03 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	99.01 19	0.00 547	0.00 545	0.00 545	0.00 543

test_blank		0.13 513	0.17 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	1.57 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

mmdepth		0.02 514	0.03 517	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

monomultidepth		0.02 514	0.03 517	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet_test		0.02 514	0.03 517	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

DCPMVS		0.02 514	0.03 517	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

sosnet-low-res		0.02 514	0.03 517	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

sosnet		0.02 514	0.03 517	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uncertanet		0.02 514	0.03 517	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

Regformer		0.02 514	0.03 517	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet		0.02 514	0.03 517	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.27 547	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

MED-MVS test				99.87 22	99.88 13	99.81 33	99.69 63	99.87 6	99.34 28	99.90 34	99.83 114		99.95 76	98.83 178	99.89 67	99.83 64

TestfortrainingZip				99.69 89	99.58 204	99.62 83	99.69 63	99.38 299	98.98 72	99.84 55	99.75 200	98.84 45	99.78 258		99.21 201	99.66 175

WAC-MVS						97.16 344								95.47 426

FOURS1					99.91 1	99.93 1	99.87 8	99.56 89	99.10 48	99.81 70

MSC_two_6792asdad				99.87 22	99.51 235	99.76 49		99.33 331					99.96 41	98.87 165	99.84 101	99.89 30

PC_three_1452									98.18 179	99.84 55	99.70 223	99.31 3	98.52 472	98.30 254	99.80 125	99.81 79

No_MVS				99.87 22	99.51 235	99.76 49		99.33 331					99.96 41	98.87 165	99.84 101	99.89 30

test_one_0601					99.81 57	99.88 10		99.49 198	98.97 76	99.65 143	99.81 140	99.09 15

eth-test2					0.00 551

eth-test					0.00 551

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 357	99.56 173	99.54 302	98.58 79	99.96 41	96.93 383	99.75 142

RE-MVS-def			99.34 49		99.76 82	99.82 28	99.63 104	99.52 133	98.38 139	99.76 93	99.82 125	98.75 61		98.61 210	99.81 120	99.77 100

IU-MVS					99.84 38	99.88 10		99.32 342	98.30 153	99.84 55				98.86 170	99.85 93	99.89 30

OPU-MVS				99.64 102	99.56 214	99.72 56	99.60 117				99.70 223	99.27 6	99.42 355	98.24 258	99.80 125	99.79 92

test_241102_TWO								99.48 210	99.08 56	99.88 42	99.81 140	98.94 33	99.96 41	98.91 159	99.84 101	99.88 36

test_241102_ONE					99.84 38	99.90 2		99.48 210	99.07 58	99.91 31	99.74 206	99.20 8	99.76 266

9.14			99.10 98		99.72 111		99.40 281	99.51 160	97.53 290	99.64 148	99.78 182	98.84 45	99.91 135	97.63 320	99.82 117

save fliter					99.76 82	99.59 89	99.14 377	99.40 288	99.00 67

test_0728_THIRD									98.99 69	99.81 70	99.80 158	99.09 15	99.96 41	98.85 172	99.90 56	99.88 36

test_0728_SECOND				99.91 6	99.84 38	99.89 6	99.57 146	99.51 160					99.96 41	98.93 156	99.86 86	99.88 36

test0726					99.85 31	99.89 6	99.62 109	99.50 185	99.10 48	99.86 52	99.82 125	98.94 33

GSMVS																99.52 233

test_part2					99.81 57	99.83 22				99.77 87

sam_mvs1												94.86 268				99.52 233

sam_mvs												94.72 284

ambc				93.06 479	92.68 529	82.36 506	98.47 481	98.73 458		95.09 474	97.41 491	55.55 521	99.10 423	96.42 403	91.32 470	97.71 480

MTGPA								99.47 232

test_post1							99.23 355				65.14 543	94.18 315	99.71 288	97.58 324

test_post											65.99 542	94.65 291	99.73 278

patchmatchnet-post											98.70 447	94.79 274	99.74 272

GG-mvs-BLEND				98.45 342	98.55 451	98.16 291	99.43 262	93.68 522		97.23 445	98.46 455	89.30 425	99.22 397	95.43 428	98.22 303	97.98 471

MTMP							99.54 174	98.88 431

gm-plane-assit					98.54 452	92.96 476			94.65 445		99.15 403		99.64 317	97.56 329

test9_res														97.49 337	99.72 148	99.75 113

TEST9					99.67 138	99.65 75	99.05 398	99.41 281	96.22 404	98.95 321	99.49 321	98.77 57	99.91 135

test_8					99.67 138	99.61 86	99.03 403	99.41 281	96.28 398	98.93 324	99.48 329	98.76 58	99.91 135

agg_prior2														97.21 361	99.73 147	99.75 113

agg_prior					99.67 138	99.62 83		99.40 288		98.87 334			99.91 135

TestCases				99.31 206	99.86 25	98.48 276		99.61 60	97.85 245	99.36 229	99.85 91	95.95 213	99.85 190	96.66 396	99.83 113	99.59 213

test_prior4						99.56 95	98.99 414

test_prior2							98.96 421		98.34 145	99.01 308	99.52 311	98.68 71		97.96 285	99.74 145

test_prior				99.68 90	99.67 138	99.48 112		99.56 89					99.83 222			99.74 118

旧先验2							98.96 421		96.70 366	99.47 192			99.94 91	98.19 261

新几何2							99.01 411

新几何1				99.75 77	99.75 92	99.59 89		99.54 108	96.76 362	99.29 246	99.64 262	98.43 90	99.94 91	96.92 385	99.66 159	99.72 138

旧先验1					99.74 100	99.59 89		99.54 108			99.69 234	98.47 87			99.68 156	99.73 128

无先验							98.99 414	99.51 160	96.89 354				99.93 108	97.53 332		99.72 138

原ACMM2							98.95 424

原ACMM1				99.65 96	99.73 107	99.33 131		99.47 232	97.46 296	99.12 286	99.66 254	98.67 73	99.91 135	97.70 317	99.69 153	99.71 150

test222					99.75 92	99.49 110	98.91 431	99.49 198	96.42 392	99.34 236	99.65 256	98.28 100			99.69 153	99.72 138

testdata2													99.95 76	96.67 395

segment_acmp												98.96 26

testdata				99.54 127	99.75 92	98.95 197		99.51 160	97.07 338	99.43 203	99.70 223	98.87 41	99.94 91	97.76 307	99.64 162	99.72 138

testdata1							98.85 436		98.32 149

test12				99.75 77	99.64 167	99.61 86		99.29 355		99.21 268		98.38 95	99.89 163		99.74 145	99.74 118

plane_prior7					99.29 311	97.03 359

plane_prior6					99.27 316	96.98 363						92.71 357

plane_prior5								99.47 232					99.69 302	97.78 303	97.63 332	98.67 377

plane_prior4											99.61 277

plane_prior3						97.00 361			98.69 108	99.11 288

plane_prior2							99.39 285		98.97 76

plane_prior1					99.26 319

plane_prior						96.97 364	99.21 361		98.45 131						97.60 335

n2								0.00 552

nn								0.00 552

door-mid								98.05 483

lessismore_v0				97.79 412	98.69 436	95.44 433		94.75 517		95.71 468	99.87 74	88.69 433	99.32 374	95.89 414	94.93 421	98.62 399

LGP-MVS_train				98.49 332	99.33 298	97.05 353		99.55 99	97.46 296	99.24 260	99.83 114	92.58 362	99.72 282	98.09 272	97.51 344	98.68 369

test11								99.35 318

door								97.92 484

HQP5-MVS						96.83 375

HQP-NCC					99.19 337		98.98 417		98.24 166	98.66 365

ACMP_Plane					99.19 337		98.98 417		98.24 166	98.66 365

BP-MVS														97.19 365

HQP4-MVS										98.66 365			99.64 317			98.64 390

HQP3-MVS								99.39 291							97.58 337

HQP2-MVS												92.47 366

NP-MVS					99.23 327	96.92 371					99.40 351

MDTV_nov1_ep13_2view						95.18 440	99.35 304		96.84 357	99.58 168		95.19 253		97.82 298		99.46 261

MDTV_nov1_ep13			98.32 238		99.11 358	94.44 458	99.27 336	98.74 452	97.51 293	99.40 216	99.62 273	94.78 275	99.76 266	97.59 323	98.81 266

ACMMP++_ref															97.19 365

ACMMP++															97.43 355

Test By Simon												98.75 61

ITE_SJBPF				98.08 379	99.29 311	96.37 395		98.92 420	98.34 145	98.83 342	99.75 200	91.09 403	99.62 324	95.82 415	97.40 357	98.25 450

DeepMVS_CX				93.34 476	99.29 311	82.27 507		99.22 375	85.15 503	96.33 461	99.05 415	90.97 405	99.73 278	93.57 457	97.77 328	98.01 466

High-resolution multi-view benchmark