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	99.83 113	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	99.82 124	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	98.83 177	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 88	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	99.22 109	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	99.38 284	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	99.11 127	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	99.04 137	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	99.04 137	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	99.48 209	99.08 56	99.91 31	99.81 139	99.20 8	99.96 41	98.91 158	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	99.28 101	99.84 101	99.83 64

DVP-MVS++		99.59 15	99.50 19	99.88 16	99.51 234	99.88 10	99.87 8	99.51 159	98.99 69	99.88 42	99.81 139	99.27 6	99.96 41	98.85 171	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	99.39 290	98.91 83	99.78 82	99.85 91	99.36 2	99.94 91	98.84 174	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	99.45 255	99.01 64	99.90 34	99.83 113	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	99.45 255	99.01 64	99.89 39	99.82 124	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	99.37 308	99.10 48	99.81 69	99.80 157	98.94 33	99.96 41	98.93 155	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	99.37 292	99.70 18	99.18 35	99.83 64	99.83 113	98.74 66	99.93 108	98.83 177	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	99.44 265	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	99.51 234	99.67 68	99.50 206	99.64 42	99.43 19	99.98 13	99.78 181	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	99.51 159	98.62 113	99.79 77	99.83 113	99.28 5	99.97 29	98.48 228	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	99.37 222	99.74 205	98.81 49	99.94 91	98.79 185	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	99.47 231	98.79 96	99.68 121	99.81 139	98.43 90	99.97 29	98.88 161	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	97.72 263	99.76 92	99.75 199	99.13 13	99.92 123	99.07 134	99.92 38	99.85 47

mvsany_test1		99.50 31	99.46 28	99.62 109	99.61 192	99.09 168	98.94 424	99.48 209	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 82	99.70 222	98.65 75	99.79 249	99.65 41	99.78 134	99.41 270

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 99	99.69 233	98.55 82	99.82 231	99.69 34	99.85 93	99.48 249

HFP-MVS		99.49 33	99.37 43	99.86 34	99.87 20	99.80 38	99.66 84	99.67 27	98.15 180	99.68 121	99.69 233	99.06 17	99.96 41	98.69 197	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	98.15 180	99.67 127	99.69 233	98.95 31	99.96 41	98.69 197	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	99.36 298	99.46 244	99.07 58	99.79 77	99.82 124	98.85 43	99.92 123	98.68 199	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	98.13 187	99.66 132	99.68 241	98.96 26	99.96 41	98.62 206	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	98.36 142	99.79 77	99.82 124	98.86 42	99.95 76	98.62 206	99.81 120	99.78 98

DELS-MVS		99.48 37	99.42 32	99.65 96	99.72 111	99.40 122	99.05 396	99.66 32	99.14 40	99.57 170	99.80 157	98.46 88	99.94 91	99.57 48	99.84 101	99.60 201
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	98.08 205	99.55 178	99.64 261	98.91 38	99.96 41	98.72 192	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	99.48 209	98.05 213	99.76 92	99.86 84	98.82 48	99.93 108	98.82 184	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	99.50 184	98.27 155	99.87 48	99.92 18	98.09 108	99.94 91	99.65 41	99.95 22	99.47 255

BridgeMVS		99.46 42	99.39 39	99.67 91	99.55 217	99.58 94	99.74 48	99.51 159	98.42 135	99.87 48	99.84 106	98.05 111	99.91 135	99.58 47	99.94 30	99.52 232

DPE-MVS		99.46 42	99.32 53	99.91 6	99.78 70	99.88 10	99.36 298	99.51 159	98.73 103	99.88 42	99.84 106	98.72 68	99.96 41	98.16 264	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	99.44 178	99.60 198	99.16 157	99.41 273	99.71 16	98.98 72	99.45 194	99.78 181	99.19 10	99.54 333	99.28 101	99.84 101	99.63 193

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	98.38 138	99.76 92	99.82 124	98.53 83	99.95 76	98.61 209	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	97.84 246	99.71 114	99.80 157	99.12 14	99.97 29	98.33 249	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	98.07 206	99.53 181	99.63 267	98.93 37	99.97 29	98.74 189	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	98.12 195	99.63 150	99.84 106	98.73 67	99.96 41	98.55 224	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	99.47 231	97.45 297	99.78 82	99.82 124	99.18 11	99.91 135	98.79 185	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	99.48 209	98.12 195	99.50 186	99.75 199	98.78 53	99.97 29	98.57 218	99.89 67	99.83 64

EC-MVSNet		99.44 50	99.39 39	99.58 118	99.56 213	99.49 110	99.88 4	99.58 77	98.38 138	99.73 99	99.69 233	98.20 103	99.70 295	99.64 43	99.82 117	99.54 226

SR-MVS		99.43 53	99.29 65	99.86 34	99.75 92	99.83 22	99.59 128	99.62 51	98.21 171	99.73 99	99.79 174	98.68 71	99.96 41	98.44 235	99.77 137	99.79 92

MCST-MVS		99.43 53	99.30 61	99.82 57	99.79 68	99.74 54	99.29 324	99.40 287	98.79 96	99.52 183	99.62 272	98.91 38	99.90 148	98.64 203	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	99.50 184	98.70 107	99.77 86	99.49 319	98.21 102	99.95 76	98.46 233	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	99.62 181	99.55 97	99.50 206	99.70 18	98.79 96	99.77 86	99.96 1	97.45 124	99.96 41	98.92 157	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	97.59 278	99.68 121	99.63 267	98.91 38	99.94 91	98.58 215	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	99.62 181	99.71 58	99.26 344	99.52 133	98.82 90	99.39 217	99.71 218	98.96 26	99.85 190	98.59 214	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	94.92 263	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	95.24 250	99.96 41	99.97 2	99.97 9	99.96 7

SD-MVS		99.41 59	99.52 14	99.05 243	99.74 100	99.68 64	99.46 245	99.52 133	99.11 47	99.88 42	99.91 26	99.43 1	97.70 486	98.72 192	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	98.94 424	99.85 8	98.82 90	99.65 142	99.74 205	98.51 85	99.80 243	98.83 177	99.89 67	99.64 188

MVS_111021_HR		99.41 59	99.32 53	99.66 92	99.72 111	99.47 114	98.95 422	99.85 8	98.82 90	99.54 179	99.73 211	98.51 85	99.74 271	98.91 158	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	98.87 429	99.55 1	99.74 97	99.80 157	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	97.97 230	99.63 150	99.68 241	98.52 84	99.95 76	98.38 242	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	99.51 159	98.68 110	99.27 252	99.53 305	98.64 76	99.96 41	98.44 235	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	97.82 252	99.71 114	99.80 157	98.95 31	99.93 108	98.19 260	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	94.96 258	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	94.64 291	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	94.98 257	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	99.30 319	99.52 133	97.18 324	99.60 162	99.79 174	98.79 52	99.95 76	98.83 177	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	95.15 253	99.95 76	99.95 16	99.89 67	99.73 128

TSAR-MVS + GP.		99.36 72	99.36 45	99.36 193	99.67 138	98.61 258	99.07 389	99.33 330	99.00 67	99.82 68	99.81 139	99.06 17	99.84 200	99.09 132	99.42 181	99.65 181

PVSNet_Blended_VisFu		99.36 72	99.28 68	99.61 110	99.86 25	99.07 173	99.47 241	99.93 2	97.66 272	99.71 114	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	98.63 253	99.42 269	99.63 46	99.46 9	99.98 13	99.88 58	95.59 233	99.96 41	99.97 2	99.98 4	99.85 47

NCCC		99.34 75	99.19 87	99.79 68	99.61 192	99.65 75	99.30 319	99.48 209	98.86 85	99.21 267	99.63 267	98.72 68	99.90 148	98.25 256	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	99.46 244	98.09 201	99.48 190	99.74 205	98.29 99	99.96 41	97.93 286	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	94.18 314	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	94.04 319	99.96 41	99.96 13	99.93 32	99.93 22

PS-MVSNAJ		99.32 78	99.32 53	99.30 210	99.57 209	98.94 201	98.97 418	99.46 244	98.92 82	99.71 114	99.24 391	99.01 19	99.98 20	99.35 80	99.66 159	98.97 326

CSCG		99.32 78	99.32 53	99.32 203	99.85 31	98.29 284	99.71 58	99.66 32	98.11 197	99.41 210	99.80 157	98.37 96	99.96 41	98.99 143	99.96 17	99.72 138

PHI-MVS		99.30 82	99.17 90	99.70 87	99.56 213	99.52 106	99.58 138	99.80 10	97.12 330	99.62 154	99.73 211	98.58 79	99.90 148	98.61 209	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	99.63 150	99.95 3	95.82 221	99.94 91	99.37 78	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	94.53 299	99.94 91	99.89 25	99.96 17	99.97 4

xiu_mvs_v1_base_debu		99.29 84	99.27 72	99.34 197	99.63 172	98.97 187	99.12 379	99.51 159	98.86 85	99.84 55	99.47 330	98.18 104	99.99 4	99.50 57	99.31 191	99.08 308

xiu_mvs_v1_base		99.29 84	99.27 72	99.34 197	99.63 172	98.97 187	99.12 379	99.51 159	98.86 85	99.84 55	99.47 330	98.18 104	99.99 4	99.50 57	99.31 191	99.08 308

xiu_mvs_v1_base_debi		99.29 84	99.27 72	99.34 197	99.63 172	98.97 187	99.12 379	99.51 159	98.86 85	99.84 55	99.47 330	98.18 104	99.99 4	99.50 57	99.31 191	99.08 308

NormalMVS		99.27 88	99.19 87	99.52 142	99.89 8	98.83 231	99.65 90	99.52 133	99.10 48	99.84 55	99.76 194	95.80 223	99.99 4	99.30 93	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	99.50 184	97.16 326	99.77 86	99.82 124	98.78 53	99.94 91	97.56 328	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	99.18 339	99.75 51	99.56 154	99.57 84	98.45 131	99.49 189	99.85 91	97.77 118	99.94 91	98.33 249	99.84 101	99.52 232

fmvsm_s_conf0.1_n_a		99.26 91	99.06 109	99.85 43	99.52 231	99.62 83	99.54 174	99.62 51	98.69 108	99.99 2	99.96 1	94.47 301	99.94 91	99.88 26	99.92 38	99.98 2

patch_mono-2		99.26 91	99.62 7	98.16 371	99.81 57	94.59 454	99.52 185	99.64 42	99.33 29	99.73 99	99.90 36	99.00 23	99.99 4	99.69 34	99.98 4	99.89 30

ETV-MVS		99.26 91	99.21 83	99.40 186	99.46 258	99.30 139	99.56 154	99.52 133	98.52 123	99.44 199	99.27 387	98.41 93	99.86 182	99.10 130	99.59 168	99.04 316

xiu_mvs_v2_base		99.26 91	99.25 76	99.29 213	99.53 225	98.91 208	99.02 404	99.45 255	98.80 95	99.71 114	99.26 389	98.94 33	99.98 20	99.34 85	99.23 200	98.98 324

CANet		99.25 95	99.14 93	99.59 114	99.41 273	99.16 157	99.35 303	99.57 84	98.82 90	99.51 185	99.61 276	96.46 181	99.95 76	99.59 45	99.98 4	99.65 181

3Dnovator	97.25 9	99.24 96	99.05 111	99.81 60	99.12 355	99.66 71	99.84 12	99.74 13	99.09 55	98.92 324	99.90 36	95.94 214	99.98 20	98.95 151	99.92 38	99.79 92

LuminaMVS		99.23 97	99.10 98	99.61 110	99.35 291	99.31 136	99.46 245	99.13 387	98.61 114	99.86 52	99.89 45	96.41 186	99.91 135	99.67 37	99.51 174	99.63 193

dcpmvs_2		99.23 97	99.58 9	98.16 371	99.83 47	94.68 451	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	98.42 455	99.48 112	99.55 169	99.51 159	99.39 24	99.78 82	99.93 10	94.80 272	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	98.85 226	99.32 313	99.48 209	98.50 125	99.81 69	99.81 139	96.82 160	99.88 168	99.40 72	99.12 220	99.71 150

CHOSEN 1792x2688		99.19 100	99.10 98	99.45 173	99.89 8	98.52 268	99.39 285	99.94 1	98.73 103	99.11 287	99.89 45	95.50 236	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	97.29 314	99.41 210	99.59 281	98.42 92	99.93 108	98.19 260	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	99.50 184	98.06 210	99.72 104	99.84 106	97.27 133	99.84 200	99.10 130	99.13 215	99.67 169

viewcassd2359sk11		99.18 103	99.08 104	99.49 160	99.65 162	98.95 197	99.48 231	99.51 159	98.10 200	99.72 104	99.87 74	97.13 139	99.84 200	99.13 124	99.14 212	99.69 157

viewmanbaseed2359cas		99.18 103	99.07 108	99.50 153	99.62 181	99.01 181	99.50 206	99.52 133	98.25 163	99.68 121	99.82 124	96.93 153	99.80 243	99.15 123	99.11 222	99.70 154

EIA-MVS		99.18 103	99.09 103	99.45 173	99.49 248	99.18 154	99.67 77	99.53 124	97.66 272	99.40 215	99.44 337	98.10 107	99.81 236	98.94 152	99.62 165	99.35 280

3Dnovator+	97.12 13	99.18 103	98.97 145	99.82 57	99.17 347	99.68 64	99.81 20	99.51 159	99.20 34	98.72 354	99.89 45	95.68 230	99.97 29	98.86 169	99.86 86	99.81 79

MVSFormer		99.17 108	99.12 96	99.29 213	99.51 234	98.94 201	99.88 4	99.46 244	97.55 284	99.80 74	99.65 255	97.39 125	99.28 376	99.03 139	99.85 93	99.65 181

sss		99.17 108	99.05 111	99.53 135	99.62 181	98.97 187	99.36 298	99.62 51	97.83 247	99.67 127	99.65 255	97.37 128	99.95 76	99.19 113	99.19 204	99.68 163

cashybrid2		99.16 110	99.02 126	99.59 114	99.66 150	99.21 151	99.68 73	99.52 133	98.31 150	99.60 162	99.87 74	95.96 210	99.85 190	99.40 72	99.16 206	99.72 138

SSM_0404		99.16 110	99.06 109	99.44 178	99.65 162	98.96 191	99.49 223	99.50 184	98.14 184	99.62 154	99.85 91	96.85 155	99.85 190	99.19 113	99.26 196	99.52 232

guyue		99.16 110	99.04 113	99.52 142	99.69 128	98.92 207	99.59 128	98.81 437	98.73 103	99.90 34	99.87 74	95.34 243	99.88 168	99.66 40	99.81 120	99.74 118

test_cas_vis1_n_1920		99.16 110	99.01 134	99.61 110	99.81 57	98.86 225	99.65 90	99.64 42	99.39 24	99.97 25	99.94 6	93.20 343	99.98 20	99.55 50	99.91 45	99.99 1

DP-MVS		99.16 110	98.95 153	99.78 71	99.77 78	99.53 102	99.41 273	99.50 184	97.03 342	99.04 304	99.88 58	97.39 125	99.92 123	98.66 201	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	98.13 187	99.72 104	99.91 26	96.31 190	99.84 200	99.30 93	99.10 230	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	98.13 187	99.72 104	99.91 26	96.31 190	99.84 200	99.30 93	99.10 230	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	98.14 184	99.72 104	99.88 58	96.57 176	99.84 200	99.17 119	99.13 215	99.72 138

E3		99.15 115	99.03 116	99.49 160	99.62 181	98.91 208	99.49 223	99.52 133	98.13 187	99.72 104	99.88 58	96.61 171	99.84 200	99.17 119	99.13 215	99.72 138

SymmetryMVS		99.15 115	99.02 126	99.52 142	99.72 111	98.83 231	99.65 90	99.34 322	99.10 48	99.84 55	99.76 194	95.80 223	99.99 4	99.30 93	98.72 269	99.73 128

MGCNet		99.15 115	98.96 149	99.73 83	98.92 395	99.37 124	99.37 292	96.92 497	99.51 2	99.66 132	99.78 181	96.69 167	99.97 29	99.84 28	99.97 9	99.84 54

casdiffmvs_mvg		99.15 115	99.02 126	99.55 126	99.66 150	99.09 168	99.64 98	99.56 89	98.26 158	99.45 194	99.87 74	96.03 207	99.81 236	99.54 51	99.15 211	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	99.02 126	99.53 135	99.66 150	99.14 163	99.72 54	99.48 209	98.35 143	99.42 205	99.84 106	96.07 203	99.79 249	99.51 56	99.14 212	99.67 169

E5new		99.14 123	99.02 126	99.50 153	99.69 128	98.91 208	99.60 117	99.53 124	98.13 187	99.72 104	99.91 26	96.26 195	99.84 200	99.30 93	99.10 230	99.76 107

E5		99.14 123	99.02 126	99.50 153	99.69 128	98.91 208	99.60 117	99.53 124	98.13 187	99.72 104	99.91 26	96.26 195	99.84 200	99.30 93	99.10 230	99.76 107

diffmvs		99.14 123	99.02 126	99.51 147	99.61 192	98.96 191	99.28 330	99.49 197	98.46 129	99.72 104	99.71 218	96.50 179	99.88 168	99.31 90	99.11 222	99.67 169
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	98.99 140	99.59 114	99.58 203	99.41 121	99.16 369	99.44 264	98.45 131	99.19 274	99.49 319	98.08 109	99.89 163	97.73 310	99.75 142	99.48 249

hybridcas		99.13 127	99.00 138	99.51 147	99.70 122	99.04 177	99.65 90	99.52 133	98.20 173	99.75 96	99.88 58	95.78 225	99.78 257	99.41 70	99.16 206	99.71 150

E4		99.13 127	99.01 134	99.49 160	99.68 135	98.90 213	99.52 185	99.52 133	98.13 187	99.71 114	99.90 36	96.32 188	99.84 200	99.21 111	99.11 222	99.75 113

SSM_0407		99.13 127	99.03 116	99.43 181	99.62 181	98.88 218	99.51 195	99.50 184	98.14 184	99.37 222	99.85 91	96.85 155	99.83 222	99.19 113	99.25 197	99.60 201

CDPH-MVS		99.13 127	98.91 162	99.80 64	99.75 92	99.71 58	99.15 372	99.41 280	96.60 376	99.60 162	99.55 296	98.83 47	99.90 148	97.48 337	99.83 113	99.78 98

casdiffmvs		99.13 127	98.98 143	99.56 124	99.65 162	99.16 157	99.56 154	99.50 184	98.33 146	99.41 210	99.86 84	95.92 215	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	99.45 173	99.46 258	98.87 222	99.12 379	99.26 364	98.03 222	99.79 77	99.65 255	97.02 148	99.85 190	99.02 141	99.90 56	99.65 181
jason: jason.
lupinMVS		99.13 127	99.01 134	99.46 172	99.51 234	98.94 201	99.05 396	99.16 383	97.86 240	99.80 74	99.56 293	97.39 125	99.86 182	98.94 152	99.85 93	99.58 216

EPP-MVSNet		99.13 127	98.99 140	99.53 135	99.65 162	99.06 174	99.81 20	99.33 330	97.43 301	99.60 162	99.88 58	97.14 138	99.84 200	99.13 124	98.94 248	99.69 157

MG-MVS		99.13 127	99.02 126	99.45 173	99.57 209	98.63 253	99.07 389	99.34 322	98.99 69	99.61 159	99.82 124	97.98 113	99.87 175	97.00 375	99.80 125	99.85 47

KinetiMVS		99.12 136	98.92 158	99.70 87	99.67 138	99.40 122	99.67 77	99.63 46	98.73 103	99.94 28	99.81 139	94.54 297	99.96 41	98.40 240	99.93 32	99.74 118

BP-MVS1		99.12 136	98.94 155	99.65 96	99.51 234	99.30 139	99.67 77	98.92 416	98.48 127	99.84 55	99.69 233	94.96 258	99.92 123	99.62 44	99.79 132	99.71 150

CHOSEN 280x420		99.12 136	99.13 94	99.08 239	99.66 150	97.89 311	98.43 479	99.71 16	98.88 84	99.62 154	99.76 194	96.63 170	99.70 295	99.46 67	99.99 1	99.66 174

DP-MVS Recon		99.12 136	98.95 153	99.65 96	99.74 100	99.70 60	99.27 335	99.57 84	96.40 392	99.42 205	99.68 241	98.75 61	99.80 243	97.98 283	99.72 148	99.44 265

Vis-MVSNet		99.12 136	98.97 145	99.56 124	99.78 70	99.10 167	99.68 73	99.66 32	98.49 126	99.86 52	99.87 74	94.77 277	99.84 200	99.19 113	99.41 182	99.74 118
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 136	99.08 104	99.24 223	99.46 258	98.55 262	99.51 195	99.46 244	98.09 201	99.45 194	99.82 124	98.34 97	99.51 335	98.70 194	98.93 249	99.67 169

hybrid		99.11 142	99.01 134	99.41 184	99.64 167	98.76 241	99.35 303	99.52 133	98.31 150	99.80 74	99.84 106	96.16 199	99.79 249	99.40 72	99.06 238	99.68 163

viewdifsd2359ckpt07		99.11 142	99.00 138	99.43 181	99.63 172	98.73 243	99.45 249	99.54 108	98.33 146	99.62 154	99.81 139	96.17 198	99.87 175	99.27 104	99.14 212	99.69 157

SDMVSNet		99.11 142	98.90 164	99.75 77	99.81 57	99.59 89	99.81 20	99.65 39	98.78 99	99.64 147	99.88 58	94.56 294	99.93 108	99.67 37	98.26 299	99.72 138

VNet		99.11 142	98.90 164	99.73 83	99.52 231	99.56 95	99.41 273	99.39 290	99.01 64	99.74 97	99.78 181	95.56 234	99.92 123	99.52 55	98.18 307	99.72 138

CPTT-MVS		99.11 142	98.90 164	99.74 80	99.80 63	99.46 115	99.59 128	99.49 197	97.03 342	99.63 150	99.69 233	97.27 133	99.96 41	97.82 297	99.84 101	99.81 79

HyFIR lowres test		99.11 142	98.92 158	99.65 96	99.90 4	99.37 124	99.02 404	99.91 3	97.67 271	99.59 166	99.75 199	95.90 217	99.73 277	99.53 53	99.02 244	99.86 43

MVS_Test		99.10 148	98.97 145	99.48 164	99.49 248	99.14 163	99.67 77	99.34 322	97.31 312	99.58 167	99.76 194	97.65 121	99.82 231	98.87 164	99.07 237	99.46 260

AstraMVS		99.09 149	99.03 116	99.25 220	99.66 150	98.13 293	99.57 146	98.24 474	98.82 90	99.91 31	99.88 58	95.81 222	99.90 148	99.72 32	99.67 158	99.74 118

CDS-MVSNet		99.09 149	99.03 116	99.25 220	99.42 268	98.73 243	99.45 249	99.46 244	98.11 197	99.46 193	99.77 190	98.01 112	99.37 359	98.70 194	98.92 251	99.66 174
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmacassd2359aftdt		99.08 151	98.94 155	99.50 153	99.66 150	98.96 191	99.51 195	99.54 108	98.27 155	99.42 205	99.89 45	95.88 219	99.80 243	99.20 112	99.11 222	99.76 107

mamba_0408		99.08 151	98.96 149	99.44 178	99.62 181	98.88 218	99.25 346	99.47 231	98.05 213	99.37 222	99.81 139	96.85 155	99.85 190	98.98 144	99.25 197	99.60 201

GDP-MVS		99.08 151	98.89 168	99.64 102	99.53 225	99.34 128	99.64 98	99.48 209	98.32 148	99.77 86	99.66 253	95.14 254	99.93 108	98.97 149	99.50 176	99.64 188

PVSNet_Blended		99.08 151	98.97 145	99.42 183	99.76 82	98.79 237	98.78 446	99.91 3	96.74 361	99.67 127	99.49 319	97.53 122	99.88 168	98.98 144	99.85 93	99.60 201

OMC-MVS		99.08 151	99.04 113	99.20 227	99.67 138	98.22 288	99.28 330	99.52 133	98.07 206	99.66 132	99.81 139	97.79 117	99.78 257	97.79 301	99.81 120	99.60 201

viewdifsd2359ckpt13		99.06 156	98.93 157	99.45 173	99.63 172	98.96 191	99.50 206	99.51 159	97.83 247	99.28 246	99.80 157	96.68 169	99.71 287	99.05 136	99.12 220	99.68 163

SSM_04072		99.06 156	98.96 149	99.35 196	99.62 181	98.88 218	99.25 346	99.47 231	98.05 213	99.37 222	99.81 139	96.85 155	99.58 327	98.98 144	99.25 197	99.60 201

mvsmamba		99.06 156	98.96 149	99.36 193	99.47 256	98.64 252	99.70 59	99.05 399	97.61 277	99.65 142	99.83 113	96.54 177	99.92 123	99.19 113	99.62 165	99.51 241

WTY-MVS		99.06 156	98.88 171	99.61 110	99.62 181	99.16 157	99.37 292	99.56 89	98.04 220	99.53 181	99.62 272	96.84 159	99.94 91	98.85 171	98.49 284	99.72 138

IS-MVSNet		99.05 160	98.87 172	99.57 122	99.73 107	99.32 132	99.75 43	99.20 378	98.02 225	99.56 172	99.86 84	96.54 177	99.67 304	98.09 271	99.13 215	99.73 128

PAPM_NR		99.04 161	98.84 180	99.66 92	99.74 100	99.44 117	99.39 285	99.38 298	97.70 267	99.28 246	99.28 384	98.34 97	99.85 190	96.96 379	99.45 179	99.69 157

API-MVS		99.04 161	99.03 116	99.06 241	99.40 278	99.31 136	99.55 169	99.56 89	98.54 121	99.33 236	99.39 353	98.76 58	99.78 257	96.98 377	99.78 134	98.07 459

dtuplus		99.03 163	98.92 158	99.36 193	99.60 198	98.62 255	99.35 303	99.51 159	97.99 227	99.38 219	99.88 58	96.04 205	99.79 249	99.37 78	99.17 205	99.68 163

mvs_anonymous		99.03 163	98.99 140	99.16 231	99.38 284	98.52 268	99.51 195	99.38 298	97.79 253	99.38 219	99.81 139	97.30 131	99.45 341	99.35 80	98.99 246	99.51 241

sasdasda		99.02 165	98.86 175	99.51 147	99.42 268	99.32 132	99.80 25	99.48 209	98.63 111	99.31 238	98.81 437	97.09 143	99.75 268	99.27 104	97.90 318	99.47 255

train_agg		99.02 165	98.77 188	99.77 74	99.67 138	99.65 75	99.05 396	99.41 280	96.28 396	98.95 320	99.49 319	98.76 58	99.91 135	97.63 319	99.72 148	99.75 113

canonicalmvs		99.02 165	98.86 175	99.51 147	99.42 268	99.32 132	99.80 25	99.48 209	98.63 111	99.31 238	98.81 437	97.09 143	99.75 268	99.27 104	97.90 318	99.47 255

balanced_ft_v1		99.02 165	98.98 143	99.15 235	99.39 281	98.12 295	99.79 31	99.51 159	98.20 173	99.66 132	99.87 74	94.84 268	99.93 108	99.69 34	99.84 101	99.41 270

PLC	97.94 4	99.02 165	98.85 178	99.53 135	99.66 150	99.01 181	99.24 351	99.52 133	96.85 354	99.27 252	99.48 327	98.25 101	99.91 135	97.76 306	99.62 165	99.65 181
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
viewdifsd2359ckpt09		99.01 170	98.87 172	99.40 186	99.62 181	98.79 237	99.44 256	99.51 159	97.76 258	99.35 231	99.69 233	96.42 185	99.75 268	98.97 149	99.11 222	99.66 174

viewmambaseed2359dif		99.01 170	98.90 164	99.32 203	99.58 203	98.51 270	99.33 310	99.54 108	97.85 243	99.44 199	99.85 91	96.01 208	99.79 249	99.41 70	99.13 215	99.67 169

MGCFI-Net		99.01 170	98.85 178	99.50 153	99.42 268	99.26 145	99.82 16	99.48 209	98.60 116	99.28 246	98.81 437	97.04 147	99.76 265	99.29 99	97.87 322	99.47 255

AdaColmap		99.01 170	98.80 183	99.66 92	99.56 213	99.54 99	99.18 367	99.70 18	98.18 178	99.35 231	99.63 267	96.32 188	99.90 148	97.48 337	99.77 137	99.55 224

1112_ss		98.98 174	98.77 188	99.59 114	99.68 135	99.02 179	99.25 346	99.48 209	97.23 320	99.13 283	99.58 285	96.93 153	99.90 148	98.87 164	98.78 266	99.84 54

MSDG		98.98 174	98.80 183	99.53 135	99.76 82	99.19 152	98.75 449	99.55 99	97.25 317	99.47 191	99.77 190	97.82 116	99.87 175	96.93 382	99.90 56	99.54 226

casdiffseed414692147		98.97 176	98.78 187	99.53 135	99.66 150	99.16 157	99.61 115	99.52 133	98.01 226	99.21 267	99.88 58	94.82 269	99.70 295	99.29 99	99.04 241	99.74 118

CANet_DTU		98.97 176	98.87 172	99.25 220	99.33 297	98.42 281	99.08 388	99.30 349	99.16 37	99.43 202	99.75 199	95.27 246	99.97 29	98.56 221	99.95 22	99.36 279

DPM-MVS		98.95 178	98.71 196	99.66 92	99.63 172	99.55 97	98.64 461	99.10 390	97.93 233	99.42 205	99.55 296	98.67 73	99.80 243	95.80 416	99.68 156	99.61 198

114514_t		98.93 179	98.67 200	99.72 86	99.85 31	99.53 102	99.62 109	99.59 72	92.65 467	99.71 114	99.78 181	98.06 110	99.90 148	98.84 174	99.91 45	99.74 118

PS-MVSNAJss		98.92 180	98.92 158	98.90 268	98.78 416	98.53 264	99.78 33	99.54 108	98.07 206	99.00 311	99.76 194	99.01 19	99.37 359	99.13 124	97.23 362	98.81 335

RRT-MVS		98.91 181	98.75 190	99.39 191	99.46 258	98.61 258	99.76 38	99.50 184	98.06 210	99.81 69	99.88 58	93.91 326	99.94 91	99.11 127	99.27 194	99.61 198

Test_1112_low_res		98.89 182	98.66 203	99.57 122	99.69 128	98.95 197	99.03 401	99.47 231	96.98 344	99.15 281	99.23 392	96.77 164	99.89 163	98.83 177	98.78 266	99.86 43

Elysia		98.88 183	98.65 205	99.58 118	99.58 203	99.34 128	99.65 90	99.52 133	98.26 158	99.83 64	99.87 74	93.37 337	99.90 148	97.81 299	99.91 45	99.49 246

StellarMVS		98.88 183	98.65 205	99.58 118	99.58 203	99.34 128	99.65 90	99.52 133	98.26 158	99.83 64	99.87 74	93.37 337	99.90 148	97.81 299	99.91 45	99.49 246

test_fmvs1		98.88 183	98.79 186	99.16 231	99.69 128	97.61 326	99.55 169	99.49 197	99.32 30	99.98 13	99.91 26	91.41 393	99.96 41	99.82 29	99.92 38	99.90 27

AllTest		98.87 186	98.72 194	99.31 205	99.86 25	98.48 275	99.56 154	99.61 60	97.85 243	99.36 228	99.85 91	95.95 212	99.85 190	96.66 395	99.83 113	99.59 212

UGNet		98.87 186	98.69 198	99.40 186	99.22 330	98.72 245	99.44 256	99.68 24	99.24 33	99.18 278	99.42 341	92.74 353	99.96 41	99.34 85	99.94 30	99.53 231
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)		98.87 186	98.72 194	99.31 205	99.71 117	98.88 218	99.80 25	99.44 264	97.91 235	99.36 228	99.78 181	95.49 237	99.43 350	97.91 287	99.11 222	99.62 196

IMVS_0407		98.86 189	98.91 162	98.72 303	99.55 217	96.93 366	99.50 206	99.44 264	98.05 213	99.66 132	99.80 157	97.13 139	99.65 312	98.15 266	98.92 251	99.60 201

IMVS_0403		98.86 189	98.89 168	98.78 298	99.55 217	96.93 366	99.58 138	99.44 264	98.05 213	99.68 121	99.80 157	96.81 161	99.80 243	98.15 266	98.92 251	99.60 201

test_yl		98.86 189	98.63 208	99.54 127	99.49 248	99.18 154	99.50 206	99.07 396	98.22 169	99.61 159	99.51 313	95.37 241	99.84 200	98.60 212	98.33 291	99.59 212

DCV-MVSNet		98.86 189	98.63 208	99.54 127	99.49 248	99.18 154	99.50 206	99.07 396	98.22 169	99.61 159	99.51 313	95.37 241	99.84 200	98.60 212	98.33 291	99.59 212

EPNet		98.86 189	98.71 196	99.30 210	97.20 482	98.18 289	99.62 109	98.91 421	99.28 32	98.63 373	99.81 139	95.96 210	99.99 4	99.24 108	99.72 148	99.73 128
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 189	98.80 183	99.03 245	99.76 82	98.79 237	99.28 330	99.91 3	97.42 303	99.67 127	99.37 359	97.53 122	99.88 168	98.98 144	97.29 360	98.42 437

ab-mvs		98.86 189	98.63 208	99.54 127	99.64 167	99.19 152	99.44 256	99.54 108	97.77 256	99.30 242	99.81 139	94.20 311	99.93 108	99.17 119	98.82 263	99.49 246

MAR-MVS		98.86 189	98.63 208	99.54 127	99.37 287	99.66 71	99.45 249	99.54 108	96.61 373	99.01 307	99.40 349	97.09 143	99.86 182	97.68 318	99.53 173	99.10 303
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	98.86 189	98.75 190	99.17 230	99.88 13	98.53 264	99.34 308	99.59 72	97.55 284	98.70 361	99.89 45	95.83 220	99.90 148	98.10 270	99.90 56	99.08 308
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 198	98.62 213	99.53 135	99.61 192	99.08 171	99.80 25	99.51 159	97.10 334	99.31 238	99.78 181	95.23 251	99.77 261	98.21 258	99.03 242	99.75 113

HY-MVS	97.30 7	98.85 198	98.64 207	99.47 170	99.42 268	99.08 171	99.62 109	99.36 310	97.39 306	99.28 246	99.68 241	96.44 183	99.92 123	98.37 244	98.22 302	99.40 273

PVSNet	96.02 17	98.85 198	98.84 180	98.89 272	99.73 107	97.28 336	98.32 485	99.60 67	97.86 240	99.50 186	99.57 290	96.75 165	99.86 182	98.56 221	99.70 152	99.54 226

PatchMatch-RL		98.84 201	98.62 213	99.52 142	99.71 117	99.28 142	99.06 393	99.77 12	97.74 262	99.50 186	99.53 305	95.41 239	99.84 200	97.17 367	99.64 162	99.44 265

Effi-MVS+		98.81 202	98.59 219	99.48 164	99.46 258	99.12 166	98.08 496	99.50 184	97.50 292	99.38 219	99.41 345	96.37 187	99.81 236	99.11 127	98.54 281	99.51 241

alignmvs		98.81 202	98.56 222	99.58 118	99.43 266	99.42 119	99.51 195	98.96 411	98.61 114	99.35 231	98.92 432	94.78 274	99.77 261	99.35 80	98.11 312	99.54 226

DeepPCF-MVS	98.18 3	98.81 202	99.37 43	97.12 438	99.60 198	91.75 480	98.61 463	99.44 264	99.35 27	99.83 64	99.85 91	98.70 70	99.81 236	99.02 141	99.91 45	99.81 79

PMMVS		98.80 205	98.62 213	99.34 197	99.27 315	98.70 246	98.76 448	99.31 344	97.34 309	99.21 267	99.07 408	97.20 137	99.82 231	98.56 221	98.87 258	99.52 232

icg_test_0407_2		98.79 206	98.86 175	98.57 320	99.55 217	96.93 366	99.07 389	99.44 264	98.05 213	99.66 132	99.80 157	97.13 139	99.18 402	98.15 266	98.92 251	99.60 201

viewdifsd2359ckpt11		98.78 207	98.74 192	98.89 272	99.67 138	97.04 355	99.50 206	99.58 77	98.26 158	99.56 172	99.90 36	94.36 304	99.87 175	99.49 61	98.32 295	99.77 100

viewmsd2359difaftdt		98.78 207	98.74 192	98.90 268	99.67 138	97.04 355	99.50 206	99.58 77	98.26 158	99.56 172	99.90 36	94.36 304	99.87 175	99.49 61	98.32 295	99.77 100

Effi-MVS+-dtu		98.78 207	98.89 168	98.47 338	99.33 297	96.91 371	99.57 146	99.30 349	98.47 128	99.41 210	98.99 422	96.78 163	99.74 271	98.73 191	99.38 183	98.74 350

FIs		98.78 207	98.63 208	99.23 225	99.18 339	99.54 99	99.83 15	99.59 72	98.28 153	98.79 348	99.81 139	96.75 165	99.37 359	99.08 133	96.38 380	98.78 338

Fast-Effi-MVS+-dtu		98.77 211	98.83 182	98.60 315	99.41 273	96.99 361	99.52 185	99.49 197	98.11 197	99.24 259	99.34 369	96.96 152	99.79 249	97.95 285	99.45 179	99.02 319

sd_testset		98.75 212	98.57 220	99.29 213	99.81 57	98.26 286	99.56 154	99.62 51	98.78 99	99.64 147	99.88 58	92.02 375	99.88 168	99.54 51	98.26 299	99.72 138

FA-MVS(test-final)		98.75 212	98.53 224	99.41 184	99.55 217	99.05 176	99.80 25	99.01 405	96.59 378	99.58 167	99.59 281	95.39 240	99.90 148	97.78 302	99.49 177	99.28 288

FC-MVSNet-test		98.75 212	98.62 213	99.15 235	99.08 366	99.45 116	99.86 11	99.60 67	98.23 168	98.70 361	99.82 124	96.80 162	99.22 394	99.07 134	96.38 380	98.79 336

XVG-OURS		98.73 215	98.68 199	98.88 277	99.70 122	97.73 318	98.92 426	99.55 99	98.52 123	99.45 194	99.84 106	95.27 246	99.91 135	98.08 275	98.84 261	99.00 320

Fast-Effi-MVS+		98.70 216	98.43 229	99.51 147	99.51 234	99.28 142	99.52 185	99.47 231	96.11 412	99.01 307	99.34 369	96.20 197	99.84 200	97.88 289	98.82 263	99.39 274

XVG-OURS-SEG-HR		98.69 217	98.62 213	98.89 272	99.71 117	97.74 317	99.12 379	99.54 108	98.44 134	99.42 205	99.71 218	94.20 311	99.92 123	98.54 225	98.90 257	99.00 320

1314		98.68 218	98.54 223	99.11 238	98.89 399	98.65 250	99.27 335	99.49 197	96.89 352	97.99 420	99.56 293	97.72 120	99.83 222	97.74 309	99.27 194	98.84 334

VortexMVS		98.67 219	98.66 203	98.68 310	99.62 181	97.96 305	99.59 128	99.41 280	98.13 187	99.31 238	99.70 222	95.48 238	99.27 379	99.40 72	97.32 359	98.79 336

EI-MVSNet		98.67 219	98.67 200	98.68 310	99.35 291	97.97 303	99.50 206	99.38 298	96.93 351	99.20 271	99.83 113	97.87 114	99.36 363	98.38 242	97.56 338	98.71 354

test_djsdf		98.67 219	98.57 220	98.98 251	98.70 430	98.91 208	99.88 4	99.46 244	97.55 284	99.22 264	99.88 58	95.73 228	99.28 376	99.03 139	97.62 333	98.75 346

QAPM		98.67 219	98.30 239	99.80 64	99.20 333	99.67 68	99.77 35	99.72 14	94.74 440	98.73 353	99.90 36	95.78 225	99.98 20	96.96 379	99.88 74	99.76 107

nrg030		98.64 223	98.42 230	99.28 217	99.05 375	99.69 63	99.81 20	99.46 244	98.04 220	99.01 307	99.82 124	96.69 167	99.38 356	99.34 85	94.59 425	98.78 338

test_vis1_n_1920		98.63 224	98.40 232	99.31 205	99.86 25	97.94 310	99.67 77	99.62 51	99.43 19	99.99 2	99.91 26	87.29 449	100.00 1	99.92 24	99.92 38	99.98 2

PAPR		98.63 224	98.34 235	99.51 147	99.40 278	99.03 178	98.80 443	99.36 310	96.33 393	99.00 311	99.12 406	98.46 88	99.84 200	95.23 432	99.37 190	99.66 174

CVMVSNet		98.57 226	98.67 200	98.30 358	99.35 291	95.59 423	99.50 206	99.55 99	98.60 116	99.39 217	99.83 113	94.48 300	99.45 341	98.75 188	98.56 279	99.85 47

IMVS_0404		98.53 227	98.52 225	98.55 326	99.55 217	96.93 366	99.20 363	99.44 264	98.05 213	98.96 318	99.80 157	94.66 289	99.13 410	98.15 266	98.92 251	99.60 201

MVSTER		98.49 228	98.32 237	99.00 249	99.35 291	99.02 179	99.54 174	99.38 298	97.41 304	99.20 271	99.73 211	93.86 328	99.36 363	98.87 164	97.56 338	98.62 398

FE-MVS		98.48 229	98.17 245	99.40 186	99.54 224	98.96 191	99.68 73	98.81 437	95.54 423	99.62 154	99.70 222	93.82 329	99.93 108	97.35 350	99.46 178	99.32 285

OpenMVS	96.50 16	98.47 230	98.12 252	99.52 142	99.04 377	99.53 102	99.82 16	99.72 14	94.56 443	98.08 415	99.88 58	94.73 282	99.98 20	97.47 339	99.76 140	99.06 314

IterMVS-LS		98.46 231	98.42 230	98.58 319	99.59 201	98.00 301	99.37 292	99.43 275	96.94 350	99.07 296	99.59 281	97.87 114	99.03 429	98.32 251	95.62 403	98.71 354
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 232	98.28 240	98.94 258	98.50 451	98.96 191	99.77 35	99.50 184	97.07 336	98.87 333	99.77 190	94.76 278	99.28 376	98.66 201	97.60 334	98.57 419

jajsoiax		98.43 233	98.28 240	98.88 277	98.60 444	98.43 279	99.82 16	99.53 124	98.19 175	98.63 373	99.80 157	93.22 342	99.44 346	99.22 109	97.50 345	98.77 342

tttt0517		98.42 234	98.14 249	99.28 217	99.66 150	98.38 282	99.74 48	96.85 498	97.68 269	99.79 77	99.74 205	91.39 394	99.89 163	98.83 177	99.56 170	99.57 219

BH-untuned		98.42 234	98.36 233	98.59 316	99.49 248	96.70 380	99.27 335	99.13 387	97.24 319	98.80 346	99.38 356	95.75 227	99.74 271	97.07 372	99.16 206	99.33 284

test_fmvs1_n		98.41 236	98.14 249	99.21 226	99.82 53	97.71 322	99.74 48	99.49 197	99.32 30	99.99 2	99.95 3	85.32 468	99.97 29	99.82 29	99.84 101	99.96 7

D2MVS		98.41 236	98.50 226	98.15 374	99.26 318	96.62 386	99.40 281	99.61 60	97.71 264	98.98 314	99.36 362	96.04 205	99.67 304	98.70 194	97.41 355	98.15 455

BH-RMVSNet		98.41 236	98.08 258	99.40 186	99.41 273	98.83 231	99.30 319	98.77 443	97.70 267	98.94 322	99.65 255	92.91 349	99.74 271	96.52 399	99.55 172	99.64 188

mvs_tets		98.40 239	98.23 243	98.91 266	98.67 435	98.51 270	99.66 84	99.53 124	98.19 175	98.65 370	99.81 139	92.75 351	99.44 346	99.31 90	97.48 349	98.77 342

MonoMVSNet		98.38 240	98.47 228	98.12 376	98.59 446	96.19 403	99.72 54	98.79 441	97.89 237	99.44 199	99.52 309	96.13 200	98.90 456	98.64 203	97.54 340	99.28 288

XXY-MVS		98.38 240	98.09 257	99.24 223	99.26 318	99.32 132	99.56 154	99.55 99	97.45 297	98.71 355	99.83 113	93.23 340	99.63 322	98.88 161	96.32 382	98.76 344

dtuonly		98.37 242	98.26 242	98.69 308	99.07 368	96.81 377	98.51 473	98.75 444	97.77 256	99.57 170	99.68 241	96.12 201	99.71 287	95.76 417	99.11 222	99.57 219

ACMM	97.58 5	98.37 242	98.34 235	98.48 333	99.41 273	97.10 346	99.56 154	99.45 255	98.53 122	99.04 304	99.85 91	93.00 345	99.71 287	98.74 189	97.45 350	98.64 389
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 244	98.03 264	99.31 205	99.63 172	98.56 261	99.54 174	96.75 500	97.53 288	99.73 99	99.65 255	91.25 398	99.89 163	98.62 206	99.56 170	99.48 249

tpmrst		98.33 245	98.48 227	97.90 395	99.16 349	94.78 447	99.31 317	99.11 389	97.27 315	99.45 194	99.59 281	95.33 244	99.84 200	98.48 228	98.61 273	99.09 307

baseline1		98.31 246	97.95 273	99.38 192	99.50 246	98.74 242	99.59 128	98.93 413	98.41 136	99.14 282	99.60 279	94.59 292	99.79 249	98.48 228	93.29 448	99.61 198

PatchmatchNet		98.31 246	98.36 233	98.19 369	99.16 349	95.32 435	99.27 335	98.92 416	97.37 307	99.37 222	99.58 285	94.90 265	99.70 295	97.43 345	99.21 201	99.54 226
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 248	97.98 269	99.26 219	99.57 209	98.16 290	99.41 273	98.55 465	96.03 417	99.19 274	99.74 205	91.87 378	99.92 123	99.16 122	98.29 298	99.70 154

VPA-MVSNet		98.29 249	97.95 273	99.30 210	99.16 349	99.54 99	99.50 206	99.58 77	98.27 155	99.35 231	99.37 359	92.53 363	99.65 312	99.35 80	94.46 426	98.72 352

UniMVSNet (Re)		98.29 249	98.00 267	99.13 237	99.00 382	99.36 127	99.49 223	99.51 159	97.95 231	98.97 316	99.13 403	96.30 192	99.38 356	98.36 246	93.34 447	98.66 385

HQP_MVS		98.27 251	98.22 244	98.44 344	99.29 310	96.97 363	99.39 285	99.47 231	98.97 76	99.11 287	99.61 276	92.71 356	99.69 301	97.78 302	97.63 331	98.67 376

UniMVSNet_NR-MVSNet		98.22 252	97.97 270	98.96 254	98.92 395	98.98 184	99.48 231	99.53 124	97.76 258	98.71 355	99.46 334	96.43 184	99.22 394	98.57 218	92.87 458	98.69 363

LPG-MVS_test		98.22 252	98.13 251	98.49 331	99.33 297	97.05 352	99.58 138	99.55 99	97.46 294	99.24 259	99.83 113	92.58 361	99.72 281	98.09 271	97.51 343	98.68 368

RPSCF		98.22 252	98.62 213	96.99 441	99.82 53	91.58 481	99.72 54	99.44 264	96.61 373	99.66 132	99.89 45	95.92 215	99.82 231	97.46 340	99.10 230	99.57 219

ADS-MVSNet		98.20 255	98.08 258	98.56 324	99.33 297	96.48 391	99.23 354	99.15 384	96.24 400	99.10 290	99.67 248	94.11 316	99.71 287	96.81 387	99.05 239	99.48 249

OPM-MVS		98.19 256	98.10 254	98.45 341	98.88 400	97.07 350	99.28 330	99.38 298	98.57 118	99.22 264	99.81 139	92.12 373	99.66 307	98.08 275	97.54 340	98.61 407
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 256	98.16 246	98.27 364	99.30 306	95.55 424	99.07 389	98.97 409	97.57 281	99.43 202	99.57 290	92.72 354	99.74 271	97.58 323	99.20 203	99.52 232

miper_ehance_all_eth		98.18 258	98.10 254	98.41 347	99.23 326	97.72 319	98.72 453	99.31 344	96.60 376	98.88 330	99.29 382	97.29 132	99.13 410	97.60 321	95.99 391	98.38 442

CR-MVSNet		98.17 259	97.93 276	98.87 281	99.18 339	98.49 273	99.22 358	99.33 330	96.96 346	99.56 172	99.38 356	94.33 307	99.00 438	94.83 439	98.58 276	99.14 299

miper_enhance_ethall		98.16 260	98.08 258	98.41 347	98.96 391	97.72 319	98.45 478	99.32 340	96.95 348	98.97 316	99.17 398	97.06 146	99.22 394	97.86 292	95.99 391	98.29 446

CLD-MVS		98.16 260	98.10 254	98.33 354	99.29 310	96.82 376	98.75 449	99.44 264	97.83 247	99.13 283	99.55 296	92.92 347	99.67 304	98.32 251	97.69 329	98.48 429
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 262	97.79 290	99.19 228	99.50 246	98.50 272	98.61 463	96.82 499	96.95 348	99.54 179	99.43 339	91.66 387	99.86 182	98.08 275	99.51 174	99.22 296

pmmvs4		98.13 263	97.90 278	98.81 293	98.61 442	98.87 222	98.99 412	99.21 377	96.44 388	99.06 301	99.58 285	95.90 217	99.11 416	97.18 366	96.11 387	98.46 434

WR-MVS_H		98.13 263	97.87 283	98.90 268	99.02 379	98.84 228	99.70 59	99.59 72	97.27 315	98.40 393	99.19 397	95.53 235	99.23 387	98.34 248	93.78 443	98.61 407

c3_l		98.12 265	98.04 263	98.38 351	99.30 306	97.69 323	98.81 442	99.33 330	96.67 366	98.83 341	99.34 369	97.11 142	98.99 440	97.58 323	95.34 410	98.48 429

ACMH	97.28 8	98.10 266	97.99 268	98.44 344	99.41 273	96.96 365	99.60 117	99.56 89	98.09 201	98.15 413	99.91 26	90.87 405	99.70 295	98.88 161	97.45 350	98.67 376
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
usedtu_dtu_shiyan1		98.09 267	97.82 287	98.89 272	98.70 430	98.90 213	98.57 466	99.47 231	96.78 358	98.87 333	99.05 412	94.75 279	99.23 387	97.45 342	96.74 370	98.53 423

FE-MVSNET3		98.09 267	97.82 287	98.89 272	98.70 430	98.90 213	98.57 466	99.47 231	96.78 358	98.87 333	99.05 412	94.75 279	99.23 387	97.45 342	96.74 370	98.53 423

Anonymous20240529		98.09 267	97.68 307	99.34 197	99.66 150	98.44 278	99.40 281	99.43 275	93.67 451	99.22 264	99.89 45	90.23 413	99.93 108	99.26 107	98.33 291	99.66 174

CP-MVSNet		98.09 267	97.78 293	99.01 247	98.97 390	99.24 148	99.67 77	99.46 244	97.25 317	98.48 387	99.64 261	93.79 330	99.06 425	98.63 205	94.10 437	98.74 350

dmvs_re		98.08 271	98.16 246	97.85 401	99.55 217	94.67 452	99.70 59	98.92 416	98.15 180	99.06 301	99.35 365	93.67 334	99.25 384	97.77 305	97.25 361	99.64 188

DU-MVS		98.08 271	97.79 290	98.96 254	98.87 403	98.98 184	99.41 273	99.45 255	97.87 239	98.71 355	99.50 316	94.82 269	99.22 394	98.57 218	92.87 458	98.68 368

v2v482		98.06 273	97.77 295	98.92 262	98.90 398	98.82 234	99.57 146	99.36 310	96.65 368	99.19 274	99.35 365	94.20 311	99.25 384	97.72 312	94.97 418	98.69 363

V42		98.06 273	97.79 290	98.86 284	98.98 388	98.84 228	99.69 63	99.34 322	96.53 380	99.30 242	99.37 359	94.67 287	99.32 371	97.57 327	94.66 423	98.42 437

test-LLR		98.06 273	97.90 278	98.55 326	98.79 413	97.10 346	98.67 456	97.75 483	97.34 309	98.61 377	98.85 434	94.45 302	99.45 341	97.25 358	99.38 183	99.10 303

WR-MVS		98.06 273	97.73 302	99.06 241	98.86 406	99.25 147	99.19 365	99.35 317	97.30 313	98.66 364	99.43 339	93.94 323	99.21 399	98.58 215	94.28 432	98.71 354

ACMP	97.20 11	98.06 273	97.94 275	98.45 341	99.37 287	97.01 359	99.44 256	99.49 197	97.54 287	98.45 390	99.79 174	91.95 377	99.72 281	97.91 287	97.49 348	98.62 398
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 278	97.96 271	98.33 354	99.26 318	97.38 333	98.56 470	99.31 344	96.65 368	98.88 330	99.52 309	96.58 174	99.12 415	97.39 347	95.53 407	98.47 431

test1111		98.04 279	98.11 253	97.83 407	99.74 100	93.82 463	99.58 138	95.40 509	99.12 46	99.65 142	99.93 10	90.73 406	99.84 200	99.43 69	99.38 183	99.82 72

ECVR-MVS		98.04 279	98.05 262	98.00 385	99.74 100	94.37 458	99.59 128	94.98 510	99.13 41	99.66 132	99.93 10	90.67 407	99.84 200	99.40 72	99.38 183	99.80 88

EPNet_dtu		98.03 281	97.96 271	98.23 367	98.27 458	95.54 426	99.23 354	98.75 444	99.02 62	97.82 429	99.71 218	96.11 202	99.48 336	93.04 462	99.65 161	99.69 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 281	97.76 299	98.84 288	99.39 281	98.98 184	99.40 281	99.38 298	96.67 366	99.07 296	99.28 384	92.93 346	98.98 441	97.10 368	96.65 373	98.56 420

ADS-MVSNet2		98.02 283	98.07 261	97.87 397	99.33 297	95.19 438	99.23 354	99.08 393	96.24 400	99.10 290	99.67 248	94.11 316	98.93 453	96.81 387	99.05 239	99.48 249

HQP-MVS		98.02 283	97.90 278	98.37 352	99.19 336	96.83 374	98.98 415	99.39 290	98.24 165	98.66 364	99.40 349	92.47 365	99.64 316	97.19 364	97.58 336	98.64 389

LTVRE_ROB	97.16 12	98.02 283	97.90 278	98.40 349	99.23 326	96.80 378	99.70 59	99.60 67	97.12 330	98.18 411	99.70 222	91.73 383	99.72 281	98.39 241	97.45 350	98.68 368
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____		98.01 286	97.84 286	98.55 326	99.25 322	97.97 303	98.71 454	99.34 322	96.47 387	98.59 380	99.54 301	95.65 231	99.21 399	97.21 360	95.77 397	98.46 434

DIV-MVS_self_test		98.01 286	97.85 285	98.48 333	99.24 324	97.95 308	98.71 454	99.35 317	96.50 381	98.60 379	99.54 301	95.72 229	99.03 429	97.21 360	95.77 397	98.46 434

miper_lstm_enhance		98.00 288	97.91 277	98.28 363	99.34 296	97.43 331	98.88 431	99.36 310	96.48 385	98.80 346	99.55 296	95.98 209	98.91 454	97.27 356	95.50 408	98.51 427

BH-w/o		98.00 288	97.89 282	98.32 356	99.35 291	96.20 402	99.01 409	98.90 423	96.42 390	98.38 394	99.00 420	95.26 248	99.72 281	96.06 409	98.61 273	99.03 317

v1144		97.98 290	97.69 306	98.85 287	98.87 403	98.66 249	99.54 174	99.35 317	96.27 398	99.23 263	99.35 365	94.67 287	99.23 387	96.73 390	95.16 414	98.68 368

EU-MVSNet		97.98 290	98.03 264	97.81 410	98.72 427	96.65 385	99.66 84	99.66 32	98.09 201	98.35 399	99.82 124	95.25 249	98.01 478	97.41 346	95.30 411	98.78 338

tpmvs		97.98 290	98.02 266	97.84 404	99.04 377	94.73 448	99.31 317	99.20 378	96.10 416	98.76 351	99.42 341	94.94 260	99.81 236	96.97 378	98.45 285	98.97 326

tt0805		97.97 293	97.77 295	98.57 320	99.59 201	96.61 387	99.45 249	99.08 393	98.21 171	98.88 330	99.80 157	88.66 433	99.70 295	98.58 215	97.72 328	99.39 274

NR-MVSNet		97.97 293	97.61 316	99.02 246	98.87 403	99.26 145	99.47 241	99.42 277	97.63 274	97.08 448	99.50 316	95.07 256	99.13 410	97.86 292	93.59 444	98.68 368

v8		97.95 295	97.63 314	98.93 260	98.95 392	98.81 236	99.80 25	99.41 280	96.03 417	99.10 290	99.42 341	94.92 263	99.30 374	96.94 381	94.08 438	98.66 385

Patchmatch-test		97.93 296	97.65 310	98.77 299	99.18 339	97.07 350	99.03 401	99.14 386	96.16 407	98.74 352	99.57 290	94.56 294	99.72 281	93.36 457	99.11 222	99.52 232

PS-CasMVS		97.93 296	97.59 318	98.95 256	98.99 385	99.06 174	99.68 73	99.52 133	97.13 328	98.31 401	99.68 241	92.44 369	99.05 426	98.51 226	94.08 438	98.75 346

TranMVSNet+NR-MVSNet		97.93 296	97.66 309	98.76 300	98.78 416	98.62 255	99.65 90	99.49 197	97.76 258	98.49 386	99.60 279	94.23 310	98.97 448	98.00 282	92.90 456	98.70 359

test_vis1_n		97.92 299	97.44 340	99.34 197	99.53 225	98.08 297	99.74 48	99.49 197	99.15 38	100.00 1	99.94 6	79.51 490	99.98 20	99.88 26	99.76 140	99.97 4

v144192		97.92 299	97.60 317	98.87 281	98.83 410	98.65 250	99.55 169	99.34 322	96.20 403	99.32 237	99.40 349	94.36 304	99.26 382	96.37 406	95.03 417	98.70 359

ACMH+	97.24 10	97.92 299	97.78 293	98.32 356	99.46 258	96.68 384	99.56 154	99.54 108	98.41 136	97.79 431	99.87 74	90.18 416	99.66 307	98.05 279	97.18 365	98.62 398

LFMVS		97.90 302	97.35 352	99.54 127	99.52 231	99.01 181	99.39 285	98.24 474	97.10 334	99.65 142	99.79 174	84.79 471	99.91 135	99.28 101	98.38 288	99.69 157

reproduce_monomvs		97.89 303	97.87 283	97.96 390	99.51 234	95.45 430	99.60 117	99.25 367	99.17 36	98.85 340	99.49 319	89.29 425	99.64 316	99.35 80	96.31 383	98.78 338

Anonymous20231211		97.88 304	97.54 322	98.90 268	99.71 117	98.53 264	99.48 231	99.57 84	94.16 446	98.81 344	99.68 241	93.23 340	99.42 352	98.84 174	94.42 429	98.76 344

OurMVSNet-221017-0		97.88 304	97.77 295	98.19 369	98.71 429	96.53 389	99.88 4	99.00 406	97.79 253	98.78 349	99.94 6	91.68 384	99.35 366	97.21 360	96.99 369	98.69 363

v7n		97.87 306	97.52 324	98.92 262	98.76 423	98.58 260	99.84 12	99.46 244	96.20 403	98.91 325	99.70 222	94.89 266	99.44 346	96.03 410	93.89 441	98.75 346

baseline2		97.87 306	97.55 319	98.82 290	99.18 339	98.02 300	99.41 273	96.58 504	96.97 345	96.51 456	99.17 398	93.43 335	99.57 328	97.71 313	99.03 242	98.86 332

thres600view7		97.86 308	97.51 326	98.92 262	99.72 111	97.95 308	99.59 128	98.74 448	97.94 232	99.27 252	98.62 445	91.75 381	99.86 182	93.73 452	98.19 306	98.96 328

UBG		97.85 309	97.48 329	98.95 256	99.25 322	97.64 324	99.24 351	98.74 448	97.90 236	98.64 371	98.20 463	88.65 434	99.81 236	98.27 254	98.40 286	99.42 267

cl22		97.85 309	97.64 313	98.48 333	99.09 363	97.87 312	98.60 465	99.33 330	97.11 333	98.87 333	99.22 393	92.38 370	99.17 404	98.21 258	95.99 391	98.42 437

v10		97.85 309	97.52 324	98.86 284	98.99 385	98.67 248	99.75 43	99.41 280	95.70 421	98.98 314	99.41 345	94.75 279	99.23 387	96.01 412	94.63 424	98.67 376

GA-MVS		97.85 309	97.47 332	99.00 249	99.38 284	97.99 302	98.57 466	99.15 384	97.04 341	98.90 327	99.30 380	89.83 419	99.38 356	96.70 392	98.33 291	99.62 196

testing3-2		97.84 313	97.70 305	98.24 366	99.53 225	95.37 434	99.55 169	98.67 459	98.46 129	99.27 252	99.34 369	86.58 456	99.83 222	99.32 88	98.63 272	99.52 232

tfpnnormal		97.84 313	97.47 332	98.98 251	99.20 333	99.22 150	99.64 98	99.61 60	96.32 394	98.27 405	99.70 222	93.35 339	99.44 346	95.69 420	95.40 409	98.27 447

VPNet		97.84 313	97.44 340	99.01 247	99.21 331	98.94 201	99.48 231	99.57 84	98.38 138	99.28 246	99.73 211	88.89 428	99.39 354	99.19 113	93.27 449	98.71 354

LCM-MVSNet-Re		97.83 316	98.15 248	96.87 447	99.30 306	92.25 478	99.59 128	98.26 472	97.43 301	96.20 460	99.13 403	96.27 193	98.73 464	98.17 263	98.99 246	99.64 188

XVG-ACMP-BASELINE		97.83 316	97.71 304	98.20 368	99.11 357	96.33 396	99.41 273	99.52 133	98.06 210	99.05 303	99.50 316	89.64 422	99.73 277	97.73 310	97.38 357	98.53 423

IterMVS		97.83 316	97.77 295	98.02 382	99.58 203	96.27 399	99.02 404	99.48 209	97.22 321	98.71 355	99.70 222	92.75 351	99.13 410	97.46 340	96.00 390	98.67 376
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 319	97.75 300	98.06 379	99.57 209	96.36 395	99.02 404	99.49 197	97.18 324	98.71 355	99.72 215	92.72 354	99.14 407	97.44 344	95.86 396	98.67 376

EPMVS		97.82 319	97.65 310	98.35 353	98.88 400	95.98 406	99.49 223	94.71 514	97.57 281	99.26 257	99.48 327	92.46 368	99.71 287	97.87 291	99.08 236	99.35 280

MVP-Stereo		97.81 321	97.75 300	97.99 386	97.53 474	96.60 388	98.96 419	98.85 432	97.22 321	97.23 442	99.36 362	95.28 245	99.46 339	95.51 424	99.78 134	97.92 472
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 321	97.44 340	98.91 266	98.88 400	98.68 247	99.51 195	99.34 322	96.18 405	99.20 271	99.34 369	94.03 320	99.36 363	95.32 430	95.18 413	98.69 363

ttmdpeth		97.80 323	97.63 314	98.29 359	98.77 421	97.38 333	99.64 98	99.36 310	98.78 99	96.30 459	99.58 285	92.34 372	99.39 354	98.36 246	95.58 404	98.10 457

v1921920		97.80 323	97.45 335	98.84 288	98.80 412	98.53 264	99.52 185	99.34 322	96.15 409	99.24 259	99.47 330	93.98 322	99.29 375	95.40 428	95.13 415	98.69 363

v148		97.79 325	97.55 319	98.50 330	98.74 424	97.72 319	99.54 174	99.33 330	96.26 399	98.90 327	99.51 313	94.68 286	99.14 407	97.83 296	93.15 453	98.63 396

thres400		97.77 326	97.38 348	98.92 262	99.69 128	97.96 305	99.50 206	98.73 454	97.83 247	99.17 279	98.45 452	91.67 385	99.83 222	93.22 459	98.18 307	98.96 328

thres100view900		97.76 327	97.45 335	98.69 308	99.72 111	97.86 314	99.59 128	98.74 448	97.93 233	99.26 257	98.62 445	91.75 381	99.83 222	93.22 459	98.18 307	98.37 443

PEN-MVS		97.76 327	97.44 340	98.72 303	98.77 421	98.54 263	99.78 33	99.51 159	97.06 338	98.29 404	99.64 261	92.63 360	98.89 457	98.09 271	93.16 452	98.72 352

Baseline_NR-MVSNet		97.76 327	97.45 335	98.68 310	99.09 363	98.29 284	99.41 273	98.85 432	95.65 422	98.63 373	99.67 248	94.82 269	99.10 419	98.07 278	92.89 457	98.64 389

TR-MVS		97.76 327	97.41 346	98.82 290	99.06 371	97.87 312	98.87 433	98.56 463	96.63 372	98.68 363	99.22 393	92.49 364	99.65 312	95.40 428	97.79 326	98.95 330

Patchmtry		97.75 331	97.40 347	98.81 293	99.10 360	98.87 222	99.11 385	99.33 330	94.83 438	98.81 344	99.38 356	94.33 307	99.02 433	96.10 408	95.57 405	98.53 423

dp		97.75 331	97.80 289	97.59 425	99.10 360	93.71 466	99.32 313	98.88 427	96.48 385	99.08 295	99.55 296	92.67 359	99.82 231	96.52 399	98.58 276	99.24 294

WBMVS		97.74 333	97.50 327	98.46 339	99.24 324	97.43 331	99.21 360	99.42 277	97.45 297	98.96 318	99.41 345	88.83 429	99.23 387	98.94 152	96.02 388	98.71 354

TAPA-MVS	97.07 15	97.74 333	97.34 355	98.94 258	99.70 122	97.53 327	99.25 346	99.51 159	91.90 476	99.30 242	99.63 267	98.78 53	99.64 316	88.09 488	99.87 78	99.65 181
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 335	97.35 352	98.88 277	99.47 256	97.12 345	99.34 308	98.85 432	98.19 175	99.67 127	99.85 91	82.98 479	99.92 123	99.49 61	98.32 295	99.60 201

MIMVSNet		97.73 335	97.45 335	98.57 320	99.45 264	97.50 329	99.02 404	98.98 408	96.11 412	99.41 210	99.14 402	90.28 409	98.74 463	95.74 418	98.93 249	99.47 255

tfpn200view9		97.72 337	97.38 348	98.72 303	99.69 128	97.96 305	99.50 206	98.73 454	97.83 247	99.17 279	98.45 452	91.67 385	99.83 222	93.22 459	98.18 307	98.37 443

CostFormer		97.72 337	97.73 302	97.71 417	99.15 353	94.02 462	99.54 174	99.02 404	94.67 441	99.04 304	99.35 365	92.35 371	99.77 261	98.50 227	97.94 317	99.34 283

FMVSNet2		97.72 337	97.36 350	98.80 295	99.51 234	98.84 228	99.45 249	99.42 277	96.49 382	98.86 339	99.29 382	90.26 410	98.98 441	96.44 401	96.56 376	98.58 417

test0.0.03 1		97.71 340	97.42 345	98.56 324	98.41 456	97.82 315	98.78 446	98.63 461	97.34 309	98.05 419	98.98 424	94.45 302	98.98 441	95.04 435	97.15 366	98.89 331

h-mvs33		97.70 341	97.28 365	98.97 253	99.70 122	97.27 337	99.36 298	99.45 255	98.94 79	99.66 132	99.64 261	94.93 261	99.99 4	99.48 64	84.36 493	99.65 181

myMVS_eth3d28		97.69 342	97.34 355	98.73 301	99.27 315	97.52 328	99.33 310	98.78 442	98.03 222	98.82 343	98.49 450	86.64 455	99.46 339	98.44 235	98.24 301	99.23 295

v1240		97.69 342	97.32 360	98.79 296	98.85 407	98.43 279	99.48 231	99.36 310	96.11 412	99.27 252	99.36 362	93.76 332	99.24 386	94.46 442	95.23 412	98.70 359

cascas		97.69 342	97.43 344	98.48 333	98.60 444	97.30 335	98.18 491	99.39 290	92.96 463	98.41 392	98.78 441	93.77 331	99.27 379	98.16 264	98.61 273	98.86 332

pm-mvs1		97.68 345	97.28 365	98.88 277	99.06 371	98.62 255	99.50 206	99.45 255	96.32 394	97.87 427	99.79 174	92.47 365	99.35 366	97.54 330	93.54 445	98.67 376

GBi-Net		97.68 345	97.48 329	98.29 359	99.51 234	97.26 339	99.43 262	99.48 209	96.49 382	99.07 296	99.32 377	90.26 410	98.98 441	97.10 368	96.65 373	98.62 398

test1		97.68 345	97.48 329	98.29 359	99.51 234	97.26 339	99.43 262	99.48 209	96.49 382	99.07 296	99.32 377	90.26 410	98.98 441	97.10 368	96.65 373	98.62 398

tpm		97.67 348	97.55 319	98.03 380	99.02 379	95.01 443	99.43 262	98.54 466	96.44 388	99.12 285	99.34 369	91.83 380	99.60 325	97.75 308	96.46 378	99.48 249

PCF-MVS	97.08 14	97.66 349	97.06 378	99.47 170	99.61 192	99.09 168	98.04 497	99.25 367	91.24 480	98.51 384	99.70 222	94.55 296	99.91 135	92.76 467	99.85 93	99.42 267
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 350	97.65 310	97.63 420	98.78 416	97.62 325	99.13 376	98.33 470	97.36 308	99.07 296	98.94 428	95.64 232	99.15 405	92.95 463	98.68 271	96.12 503

our_test_3		97.65 350	97.68 307	97.55 426	98.62 440	94.97 444	98.84 438	99.30 349	96.83 357	98.19 410	99.34 369	97.01 150	99.02 433	95.00 436	96.01 389	98.64 389

testgi		97.65 350	97.50 327	98.13 375	99.36 290	96.45 392	99.42 269	99.48 209	97.76 258	97.87 427	99.45 336	91.09 402	98.81 459	94.53 441	98.52 282	99.13 302

thres200		97.61 353	97.28 365	98.62 314	99.64 167	98.03 299	99.26 344	98.74 448	97.68 269	99.09 293	98.32 458	91.66 387	99.81 236	92.88 464	98.22 302	98.03 462

PAPM		97.59 354	97.09 377	99.07 240	99.06 371	98.26 286	98.30 486	99.10 390	94.88 436	98.08 415	99.34 369	96.27 193	99.64 316	89.87 480	98.92 251	99.31 286

UWE-MVS		97.58 355	97.29 364	98.48 333	99.09 363	96.25 400	99.01 409	96.61 503	97.86 240	99.19 274	99.01 419	88.72 430	99.90 148	97.38 348	98.69 270	99.28 288

SD_0403		97.55 356	97.53 323	97.62 421	99.61 192	93.64 469	99.72 54	99.44 264	98.03 222	98.62 376	99.39 353	96.06 204	99.57 328	87.88 490	99.01 245	99.66 174

VDDNet		97.55 356	97.02 379	99.16 231	99.49 248	98.12 295	99.38 290	99.30 349	95.35 425	99.68 121	99.90 36	82.62 481	99.93 108	99.31 90	98.13 311	99.42 267

TESTMET0.1,1		97.55 356	97.27 368	98.40 349	98.93 393	96.53 389	98.67 456	97.61 488	96.96 346	98.64 371	99.28 384	88.63 436	99.45 341	97.30 354	99.38 183	99.21 297

pmmvs5		97.52 359	97.30 362	98.16 371	98.57 447	96.73 379	99.27 335	98.90 423	96.14 410	98.37 395	99.53 305	91.54 390	99.14 407	97.51 334	95.87 395	98.63 396

LF4IMVS		97.52 359	97.46 334	97.70 418	98.98 388	95.55 424	99.29 324	98.82 435	98.07 206	98.66 364	99.64 261	89.97 417	99.61 324	97.01 374	96.68 372	97.94 470

DTE-MVSNet		97.51 361	97.19 371	98.46 339	98.63 439	98.13 293	99.84 12	99.48 209	96.68 365	97.97 422	99.67 248	92.92 347	98.56 467	96.88 386	92.60 462	98.70 359

testing11		97.50 362	97.10 376	98.71 306	99.20 333	96.91 371	99.29 324	98.82 435	97.89 237	98.21 409	98.40 454	85.63 464	99.83 222	98.45 234	98.04 314	99.37 278

ETVMVS		97.50 362	96.90 383	99.29 213	99.23 326	98.78 240	99.32 313	98.90 423	97.52 290	98.56 381	98.09 470	84.72 472	99.69 301	97.86 292	97.88 321	99.39 274

hse-mvs2		97.50 362	97.14 373	98.59 316	99.49 248	97.05 352	99.28 330	99.22 373	98.94 79	99.66 132	99.42 341	94.93 261	99.65 312	99.48 64	83.80 497	99.08 308

SixPastTwentyTwo		97.50 362	97.33 358	98.03 380	98.65 437	96.23 401	99.77 35	98.68 457	97.14 327	97.90 425	99.93 10	90.45 408	99.18 402	97.00 375	96.43 379	98.67 376

JIA-IIPM		97.50 362	97.02 379	98.93 260	98.73 425	97.80 316	99.30 319	98.97 409	91.73 477	98.91 325	94.86 505	95.10 255	99.71 287	97.58 323	97.98 315	99.28 288

ppachtmachnet_test		97.49 367	97.45 335	97.61 424	98.62 440	95.24 436	98.80 443	99.46 244	96.11 412	98.22 408	99.62 272	96.45 182	98.97 448	93.77 450	95.97 394	98.61 407

test-mter		97.49 367	97.13 375	98.55 326	98.79 413	97.10 346	98.67 456	97.75 483	96.65 368	98.61 377	98.85 434	88.23 440	99.45 341	97.25 358	99.38 183	99.10 303

testing91		97.44 369	97.02 379	98.71 306	99.18 339	96.89 373	99.19 365	99.04 400	97.78 255	98.31 401	98.29 459	85.41 467	99.85 190	98.01 281	97.95 316	99.39 274

tpm2		97.44 369	97.34 355	97.74 416	99.15 353	94.36 459	99.45 249	98.94 412	93.45 457	98.90 327	99.44 337	91.35 395	99.59 326	97.31 351	98.07 313	99.29 287

tpm cat1		97.39 371	97.36 350	97.50 428	99.17 347	93.73 465	99.43 262	99.31 344	91.27 479	98.71 355	99.08 407	94.31 309	99.77 261	96.41 404	98.50 283	99.00 320

UWE-MVS-28		97.36 372	97.24 369	97.75 414	98.84 409	94.44 456	99.24 351	97.58 490	97.98 229	99.00 311	99.00 420	91.35 395	99.53 334	93.75 451	98.39 287	99.27 292

testing99		97.36 372	96.94 382	98.63 313	99.18 339	96.70 380	99.30 319	98.93 413	97.71 264	98.23 406	98.26 461	84.92 470	99.84 200	98.04 280	97.85 324	99.35 280

SSC-MVS3.2		97.34 374	97.15 372	97.93 392	99.02 379	95.76 418	99.48 231	99.58 77	97.62 276	99.09 293	99.53 305	87.95 443	99.27 379	96.42 402	95.66 402	98.75 346

USDC		97.34 374	97.20 370	97.75 414	99.07 368	95.20 437	98.51 473	99.04 400	97.99 227	98.31 401	99.86 84	89.02 426	99.55 332	95.67 422	97.36 358	98.49 428

UniMVSNet_ETH3D		97.32 376	96.81 385	98.87 281	99.40 278	97.46 330	99.51 195	99.53 124	95.86 420	98.54 383	99.77 190	82.44 482	99.66 307	98.68 199	97.52 342	99.50 245

testing3		97.28 377	96.76 387	98.82 290	99.37 287	98.07 298	99.45 249	99.36 310	97.56 283	97.89 426	98.95 427	83.70 476	98.82 458	96.03 410	98.56 279	99.58 216

MVS		97.28 377	96.55 391	99.48 164	98.78 416	98.95 197	99.27 335	99.39 290	83.53 500	98.08 415	99.54 301	96.97 151	99.87 175	94.23 446	99.16 206	99.63 193

test_fmvs2		97.25 379	97.30 362	97.09 439	99.43 266	93.31 472	99.73 52	98.87 429	98.83 89	99.28 246	99.80 157	84.45 473	99.66 307	97.88 289	97.45 350	98.30 445

DSMNet-mixed		97.25 379	97.35 352	96.95 444	97.84 468	93.61 470	99.57 146	96.63 502	96.13 411	98.87 333	98.61 447	94.59 292	97.70 486	95.08 434	98.86 259	99.55 224

MS-PatchMatch		97.24 381	97.32 360	96.99 441	98.45 454	93.51 471	98.82 441	99.32 340	97.41 304	98.13 414	99.30 380	88.99 427	99.56 330	95.68 421	99.80 125	97.90 474

testing222		97.16 382	96.50 392	99.16 231	99.16 349	98.47 277	99.27 335	98.66 460	97.71 264	98.23 406	98.15 465	82.28 484	99.84 200	97.36 349	97.66 330	99.18 298

TransMVSNet (Re)		97.15 383	96.58 390	98.86 284	99.12 355	98.85 226	99.49 223	98.91 421	95.48 424	97.16 446	99.80 157	93.38 336	99.11 416	94.16 448	91.73 466	98.62 398

TinyColmap		97.12 384	96.89 384	97.83 407	99.07 368	95.52 427	98.57 466	98.74 448	97.58 280	97.81 430	99.79 174	88.16 441	99.56 330	95.10 433	97.21 363	98.39 441

K. test v3		97.10 385	96.79 386	98.01 383	98.72 427	96.33 396	99.87 8	97.05 495	97.59 278	96.16 461	99.80 157	88.71 431	99.04 427	96.69 393	96.55 377	98.65 387

Syy-MVS		97.09 386	97.14 373	96.95 444	99.00 382	92.73 476	99.29 324	99.39 290	97.06 338	97.41 436	98.15 465	93.92 325	98.68 465	91.71 473	98.34 289	99.45 263

dtuonlycased		97.04 387	97.33 358	96.16 456	99.08 366	90.59 486	98.79 445	99.38 298	97.19 323	96.91 453	99.49 319	90.22 415	98.75 462	97.04 373	97.89 320	99.14 299

PatchT		97.03 388	96.44 394	98.79 296	98.99 385	98.34 283	99.16 369	99.07 396	92.13 474	99.52 183	97.31 491	94.54 297	98.98 441	88.54 486	98.73 268	99.03 317

mmtdpeth		96.95 389	96.71 388	97.67 419	99.33 297	94.90 446	99.89 2	99.28 355	98.15 180	99.72 104	98.57 448	86.56 457	99.90 148	99.82 29	89.02 484	98.20 452

myMVS_eth3d		96.89 390	96.37 395	98.43 346	99.00 382	97.16 343	99.29 324	99.39 290	97.06 338	97.41 436	98.15 465	83.46 478	98.68 465	95.27 431	98.34 289	99.45 263

AUN-MVS		96.88 391	96.31 397	98.59 316	99.48 255	97.04 355	99.27 335	99.22 373	97.44 300	98.51 384	99.41 345	91.97 376	99.66 307	97.71 313	83.83 496	99.07 313

FMVSNet1		96.84 392	96.36 396	98.29 359	99.32 304	97.26 339	99.43 262	99.48 209	95.11 429	98.55 382	99.32 377	83.95 475	98.98 441	95.81 415	96.26 384	98.62 398

test2506		96.81 393	96.65 389	97.29 434	99.74 100	92.21 479	99.60 117	85.06 531	99.13 41	99.77 86	99.93 10	87.82 447	99.85 190	99.38 77	99.38 183	99.80 88

RPMNet		96.72 394	95.90 407	99.19 228	99.18 339	98.49 273	99.22 358	99.52 133	88.72 490	99.56 172	97.38 487	94.08 318	99.95 76	86.87 497	98.58 276	99.14 299

mvs5depth		96.66 395	96.22 399	97.97 388	97.00 487	96.28 398	98.66 459	99.03 403	96.61 373	96.93 452	99.79 174	87.20 450	99.47 337	96.65 397	94.13 435	98.16 454

test_0402		96.64 396	96.24 398	97.85 401	98.85 407	96.43 393	99.44 256	99.26 364	93.52 454	96.98 450	99.52 309	88.52 437	99.20 401	92.58 470	97.50 345	97.93 471

X-MVStestdata		96.55 397	95.45 416	99.87 22	99.85 31	99.83 22	99.69 63	99.68 24	98.98 72	99.37 222	64.01 539	98.81 49	99.94 91	98.79 185	99.86 86	99.84 54

pmmvs6		96.53 398	96.09 403	97.82 409	98.69 433	95.47 428	99.37 292	99.47 231	93.46 456	97.41 436	99.78 181	87.06 454	99.33 369	96.92 384	92.70 460	98.65 387

ET-MVSNet_ETH3D		96.49 399	95.64 413	99.05 243	99.53 225	98.82 234	98.84 438	97.51 491	97.63 274	84.77 508	99.21 396	92.09 374	98.91 454	98.98 144	92.21 464	99.41 270

UnsupCasMVSNet_eth		96.44 400	96.12 401	97.40 431	98.65 437	95.65 421	99.36 298	99.51 159	97.13 328	96.04 463	98.99 422	88.40 438	98.17 474	96.71 391	90.27 477	98.40 440

FMVSNet5		96.43 401	96.19 400	97.15 435	99.11 357	95.89 413	99.32 313	99.52 133	94.47 445	98.34 400	99.07 408	87.54 448	97.07 492	92.61 469	95.72 400	98.47 431

new_pmnet		96.38 402	96.03 404	97.41 430	98.13 463	95.16 440	99.05 396	99.20 378	93.94 447	97.39 439	98.79 440	91.61 389	99.04 427	90.43 478	95.77 397	98.05 461

Anonymous20231206		96.22 403	96.03 404	96.79 449	97.31 480	94.14 461	99.63 104	99.08 393	96.17 406	97.04 449	99.06 410	93.94 323	97.76 484	86.96 496	95.06 416	98.47 431

IB-MVS	95.67 18	96.22 403	95.44 417	98.57 320	99.21 331	96.70 380	98.65 460	97.74 485	96.71 363	97.27 441	98.54 449	86.03 461	99.92 123	98.47 231	86.30 490	99.10 303
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		96.20 405	95.89 408	97.13 437	97.72 473	94.96 445	99.79 31	99.29 353	93.01 461	97.20 445	99.03 416	89.69 421	98.36 471	91.16 476	96.13 386	98.07 459

gg-mvs-nofinetune		96.17 406	95.32 418	98.73 301	98.79 413	98.14 292	99.38 290	94.09 516	91.07 482	98.07 418	91.04 518	89.62 423	99.35 366	96.75 389	99.09 235	98.68 368

test20.03		96.12 407	95.96 406	96.63 450	97.44 475	95.45 430	99.51 195	99.38 298	96.55 379	96.16 461	99.25 390	93.76 332	96.17 501	87.35 493	94.22 433	98.27 447

PVSNet_0	94.43 19	96.09 408	95.47 415	97.94 391	99.31 305	94.34 460	97.81 501	99.70 18	97.12 330	97.46 435	98.75 442	89.71 420	99.79 249	97.69 317	81.69 505	99.68 163

MVStest1		96.08 409	95.48 414	97.89 396	98.93 393	96.70 380	99.56 154	99.35 317	92.69 466	91.81 493	99.46 334	89.90 418	98.96 450	95.00 436	92.61 461	98.00 466

EG-PatchMatch MVS		95.97 410	95.69 411	96.81 448	97.78 470	92.79 475	99.16 369	98.93 413	96.16 407	94.08 479	99.22 393	82.72 480	99.47 337	95.67 422	97.50 345	98.17 453

APD_test1		95.87 411	96.49 393	94.00 468	99.53 225	84.01 498	99.54 174	99.32 340	95.91 419	97.99 420	99.85 91	85.49 466	99.88 168	91.96 471	98.84 261	98.12 456

Patchmatch-RL test		95.84 412	95.81 410	95.95 459	95.61 503	90.57 487	98.24 487	98.39 468	95.10 431	95.20 468	98.67 444	94.78 274	97.77 483	96.28 407	90.02 478	99.51 241

test_vis1_rt		95.81 413	95.65 412	96.32 454	99.67 138	91.35 482	99.49 223	96.74 501	98.25 163	95.24 466	98.10 469	74.96 492	99.90 148	99.53 53	98.85 260	97.70 480

sc_t1		95.75 414	95.05 421	97.87 397	98.83 410	94.61 453	99.21 360	99.45 255	87.45 492	97.97 422	99.85 91	81.19 487	99.43 350	98.27 254	93.20 451	99.57 219

MVS-HIRNet		95.75 414	95.16 419	97.51 427	99.30 306	93.69 467	98.88 431	95.78 506	85.09 499	98.78 349	92.65 514	91.29 397	99.37 359	94.85 438	99.85 93	99.46 260

tt0320		95.71 416	95.07 420	97.62 421	99.05 375	95.02 442	99.25 346	99.52 133	86.81 493	97.97 422	99.72 215	83.58 477	99.15 405	96.38 405	93.35 446	98.68 368

blended_shiyan8		95.56 417	94.79 424	97.87 397	96.60 491	95.90 412	98.85 434	99.27 362	92.19 469	98.47 388	97.94 474	91.43 392	99.11 416	97.26 357	81.09 508	98.60 410

blended_shiyan6		95.54 418	94.78 425	97.84 404	96.60 491	95.89 413	98.85 434	99.28 355	92.17 473	98.43 391	97.95 473	91.44 391	99.02 433	97.30 354	80.97 509	98.60 410

MIMVSNet1		95.51 419	95.04 422	96.92 446	97.38 477	95.60 422	99.52 185	99.50 184	93.65 452	96.97 451	99.17 398	85.28 469	96.56 498	88.36 487	95.55 406	98.60 410

MDA-MVSNet_test_wron		95.45 420	94.60 429	98.01 383	98.16 462	97.21 342	99.11 385	99.24 370	93.49 455	80.73 517	98.98 424	93.02 344	98.18 473	94.22 447	94.45 428	98.64 389

wanda-best-256-512		95.43 421	94.66 427	97.77 412	96.45 493	95.68 419	98.48 475	99.28 355	92.18 471	98.36 396	97.68 479	91.20 399	99.03 429	97.31 351	80.97 509	98.60 410

FE-blended-shiyan7		95.43 421	94.66 427	97.77 412	96.45 493	95.68 419	98.48 475	99.28 355	92.18 471	98.36 396	97.68 479	91.20 399	99.03 429	97.31 351	80.97 509	98.60 410

TDRefinement		95.42 423	94.57 432	97.97 388	89.83 533	96.11 405	99.48 231	98.75 444	96.74 361	96.68 455	99.88 58	88.65 434	99.71 287	98.37 244	82.74 503	98.09 458

gbinet_0.2-2-1-0.02		95.40 424	94.58 431	97.85 401	96.11 498	95.97 407	98.56 470	99.26 364	92.12 475	98.47 388	97.49 485	90.23 413	99.00 438	97.71 313	81.25 506	98.58 417

YYNet1		95.36 425	94.51 433	97.92 393	97.89 466	97.10 346	99.10 387	99.23 371	93.26 459	80.77 516	99.04 415	92.81 350	98.02 477	94.30 443	94.18 434	98.64 389

pmmvs-eth3d		95.34 426	94.73 426	97.15 435	95.53 505	95.94 409	99.35 303	99.10 390	95.13 427	93.55 483	97.54 484	88.15 442	97.91 480	94.58 440	89.69 482	97.61 482

tt0320-xc		95.31 427	94.59 430	97.45 429	98.92 395	94.73 448	99.20 363	99.31 344	86.74 494	97.23 442	99.72 215	81.14 488	98.95 451	97.08 371	91.98 465	98.67 376

blend_shiyan4		95.25 428	94.39 435	97.84 404	96.70 490	95.92 410	98.84 438	99.28 355	92.21 468	98.16 412	97.84 476	87.10 453	99.07 422	97.53 331	81.87 504	98.54 421

0.4-1-1-0.1		95.23 429	94.22 437	98.26 365	97.39 476	95.86 415	97.59 505	97.62 486	93.85 449	94.97 473	97.03 493	87.20 450	99.87 175	98.47 231	83.84 495	99.05 315

FE-MVSNET2		95.10 430	94.44 434	97.08 440	95.08 509	95.97 407	99.51 195	99.37 308	95.02 433	94.10 478	97.57 482	86.18 460	97.66 488	93.28 458	89.86 480	97.61 482

usedtu_blend_shiyan5		95.04 431	94.10 438	97.86 400	96.45 493	95.92 410	99.29 324	99.22 373	86.17 497	98.36 396	97.68 479	91.20 399	99.07 422	97.53 331	80.97 509	98.60 410

dmvs_testset		95.02 432	96.12 401	91.72 478	99.10 360	80.43 511	99.58 138	97.87 482	97.47 293	95.22 467	98.82 436	93.99 321	95.18 506	88.09 488	94.91 421	99.56 223

KD-MVS_self_test		95.00 433	94.34 436	96.96 443	97.07 486	95.39 433	99.56 154	99.44 264	95.11 429	97.13 447	97.32 490	91.86 379	97.27 491	90.35 479	81.23 507	98.23 451

MDA-MVSNet-bldmvs		94.96 434	93.98 441	97.92 393	98.24 459	97.27 337	99.15 372	99.33 330	93.80 450	80.09 518	99.03 416	88.31 439	97.86 482	93.49 455	94.36 430	98.62 398

N_pmnet		94.95 435	95.83 409	92.31 476	98.47 452	79.33 515	99.12 379	92.81 522	93.87 448	97.68 432	99.13 403	93.87 327	99.01 436	91.38 475	96.19 385	98.59 416

0.4-1-1-0.2		94.94 436	93.92 443	97.99 386	96.84 489	95.13 441	96.64 511	97.62 486	93.45 457	94.92 474	96.56 497	87.14 452	99.86 182	98.43 238	83.69 499	98.98 324

0.3-1-1-0.015		94.79 437	93.69 449	98.10 377	96.99 488	95.46 429	97.02 509	97.61 488	93.53 453	94.03 480	96.54 498	85.60 465	99.86 182	98.43 238	83.45 500	98.99 323

KD-MVS_2432*1600		94.62 438	93.72 446	97.31 432	97.19 483	95.82 416	98.34 482	99.20 378	95.00 434	97.57 433	98.35 456	87.95 443	98.10 475	92.87 465	77.00 518	98.01 463

miper_refine_blended		94.62 438	93.72 446	97.31 432	97.19 483	95.82 416	98.34 482	99.20 378	95.00 434	97.57 433	98.35 456	87.95 443	98.10 475	92.87 465	77.00 518	98.01 463

CL-MVSNet_self_test		94.49 440	93.97 442	96.08 457	96.16 497	93.67 468	98.33 484	99.38 298	95.13 427	97.33 440	98.15 465	92.69 358	96.57 497	88.67 485	79.87 516	97.99 467

new-patchmatchnet		94.48 441	94.08 440	95.67 461	95.08 509	92.41 477	99.18 367	99.28 355	94.55 444	93.49 484	97.37 488	87.86 446	97.01 494	91.57 474	88.36 485	97.61 482

OpenMVS_ROB	92.34 20	94.38 442	93.70 448	96.41 453	97.38 477	93.17 473	99.06 393	98.75 444	86.58 495	94.84 475	98.26 461	81.53 485	99.32 371	89.01 484	97.87 322	96.76 494

RoMa-SfM		94.36 443	93.86 444	95.88 460	98.61 442	90.62 485	98.85 434	99.04 400	91.63 478	94.14 477	99.49 319	77.16 491	99.09 421	92.66 468	93.13 454	97.91 473

CMPMVS	69.68 23	94.13 444	94.90 423	91.84 477	97.24 481	80.01 512	98.52 472	99.48 209	89.01 488	91.99 492	99.67 248	85.67 463	99.13 410	95.44 426	97.03 368	96.39 500
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 445	93.25 452	96.60 451	94.76 512	94.49 455	98.92 426	98.18 478	89.66 484	96.48 457	98.06 471	86.28 459	97.33 490	89.68 481	87.20 489	97.97 469

FE-MVSNET		94.07 446	93.36 451	96.22 455	94.05 516	94.71 450	99.56 154	98.36 469	93.15 460	93.76 482	97.55 483	86.47 458	96.49 499	87.48 491	89.83 481	97.48 487

mvsany_test3		93.77 447	93.45 450	94.74 466	95.78 501	88.01 492	99.64 98	98.25 473	98.28 153	94.31 476	97.97 472	68.89 507	98.51 469	97.50 335	90.37 475	97.71 477

UnsupCasMVSNet_bld		93.53 448	92.51 454	96.58 452	97.38 477	93.82 463	98.24 487	99.48 209	91.10 481	93.10 485	96.66 496	74.89 494	98.37 470	94.03 449	87.71 488	97.56 485

dongtai		93.26 449	92.93 453	94.25 467	99.39 281	85.68 496	97.68 503	93.27 518	92.87 464	96.85 454	99.39 353	82.33 483	97.48 489	76.78 510	97.80 325	99.58 216

LoFTR		93.25 450	92.33 456	95.99 458	97.91 464	90.83 483	99.06 393	98.56 463	92.19 469	90.24 497	98.18 464	72.97 495	99.26 382	89.37 482	92.52 463	97.89 475

DKM		93.17 451	92.50 455	95.21 464	98.53 450	90.26 488	98.74 452	98.90 423	93.00 462	92.61 488	99.06 410	70.06 504	97.74 485	91.92 472	89.65 483	97.62 481

WB-MVS		93.10 452	94.10 438	90.12 489	95.51 507	81.88 504	99.73 52	99.27 362	95.05 432	93.09 486	98.91 433	94.70 285	91.89 517	76.62 511	94.02 440	96.58 498

PM-MVS		92.96 453	92.23 457	95.14 465	95.61 503	89.98 490	99.37 292	98.21 476	94.80 439	95.04 472	97.69 478	65.06 510	97.90 481	94.30 443	89.98 479	97.54 486

SSC-MVS		92.73 454	93.73 445	89.72 492	95.02 511	81.38 506	99.76 38	99.23 371	94.87 437	92.80 487	98.93 429	94.71 284	91.37 519	74.49 516	93.80 442	96.42 499

test_fmvs3		92.10 455	91.77 458	93.08 474	96.19 496	86.25 493	99.82 16	98.62 462	96.65 368	95.19 469	96.90 494	55.05 519	95.93 503	96.63 398	90.92 474	97.06 493

MatchFormer		91.94 456	90.72 461	95.58 462	97.82 469	89.79 491	98.92 426	98.87 429	88.24 491	88.03 502	97.92 475	70.39 502	99.23 387	85.21 502	91.12 470	97.72 476

test_f		91.90 457	91.26 460	93.84 470	95.52 506	85.92 494	99.69 63	98.53 467	95.31 426	93.87 481	96.37 500	55.33 518	98.27 472	95.70 419	90.98 473	97.32 489

usedtu_dtu_shiyan2		91.34 458	89.96 467	95.47 463	93.61 520	90.81 484	99.15 372	98.68 457	86.37 496	95.19 469	98.27 460	72.64 497	97.05 493	85.40 501	80.32 514	98.54 421

test_method		91.10 459	91.36 459	90.31 486	95.85 500	73.72 524	94.89 513	99.25 367	68.39 515	95.82 464	99.02 418	80.50 489	98.95 451	93.64 453	94.89 422	98.25 449

Gipuma		90.99 460	90.15 465	93.51 471	98.73 425	90.12 489	93.98 518	99.45 255	79.32 503	92.28 489	94.91 504	69.61 505	97.98 479	87.42 492	95.67 401	92.45 511
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 461	90.11 466	93.34 472	98.78 416	85.59 497	98.15 494	93.16 520	89.37 487	92.07 491	98.38 455	81.48 486	95.19 505	62.54 522	97.04 367	99.25 293

SP-DiffGlue		90.78 462	90.71 462	90.98 482	95.45 508	81.30 507	97.92 500	97.30 493	75.18 506	92.09 490	95.93 501	74.93 493	94.89 509	93.46 456	94.12 436	96.74 496

testf1		90.42 463	90.68 463	89.65 493	97.78 470	73.97 522	99.13 376	98.81 437	89.62 485	91.80 494	98.93 429	62.23 514	98.80 460	86.61 498	91.17 468	96.19 501

APD_test2		90.42 463	90.68 463	89.65 493	97.78 470	73.97 522	99.13 376	98.81 437	89.62 485	91.80 494	98.93 429	62.23 514	98.80 460	86.61 498	91.17 468	96.19 501

ELoFTR		89.95 465	88.65 470	93.85 469	95.93 499	85.85 495	98.64 461	98.31 471	90.34 483	85.03 507	97.76 477	60.28 516	99.01 436	87.27 494	84.26 494	96.71 497

SP-LightGlue		89.28 466	88.68 468	91.06 481	98.21 461	80.90 509	98.19 490	96.96 496	72.38 509	89.60 500	94.43 507	72.44 498	95.06 507	82.91 504	93.03 455	97.22 490

SP-SuperGlue		89.23 467	88.68 468	90.88 483	98.23 460	80.60 510	98.16 492	97.30 493	73.08 508	89.64 499	94.62 506	71.80 500	94.91 508	82.11 506	93.22 450	97.14 492

SP-NN		88.62 468	88.17 471	89.96 490	97.89 466	78.51 516	97.19 507	96.09 505	71.28 511	88.29 501	94.00 510	71.98 499	93.65 513	82.37 505	94.46 426	97.71 477

SP-MNN		88.33 469	87.78 472	89.95 491	98.28 457	77.92 517	98.01 498	95.69 508	70.61 513	86.18 505	94.36 508	71.09 501	94.76 510	81.51 507	94.32 431	97.17 491

ALIKED-NN		88.27 470	87.61 473	90.24 487	98.46 453	79.97 513	97.04 508	94.61 515	75.25 505	86.99 503	96.90 494	72.78 496	95.78 504	75.45 514	91.01 472	94.97 506

ALIKED-LG		88.17 471	87.32 474	90.75 484	98.67 435	81.68 505	98.16 492	94.72 513	78.63 504	86.08 506	97.07 492	70.16 503	96.62 496	71.97 518	90.37 475	93.95 508

test_vis3_rt		87.04 472	85.81 476	90.73 485	93.99 517	81.96 503	99.76 38	90.23 526	92.81 465	81.35 515	91.56 516	40.06 534	99.07 422	94.27 445	88.23 486	91.15 514

ALIKED-MNN		86.97 473	85.90 475	90.16 488	99.06 371	79.59 514	97.93 499	94.82 511	72.37 510	84.41 509	95.46 502	68.55 508	96.43 500	72.40 517	88.11 487	94.47 507

PMMVS2		86.87 474	85.37 478	91.35 480	90.21 530	83.80 500	98.89 430	97.45 492	83.13 502	91.67 496	95.03 503	48.49 528	94.70 511	85.86 500	77.62 517	95.54 504

LCM-MVSNet		86.80 475	85.22 479	91.53 479	87.81 536	80.96 508	98.23 489	98.99 407	71.05 512	90.13 498	96.51 499	48.45 529	96.88 495	90.51 477	85.30 492	96.76 494

FPMVS		84.93 476	85.65 477	82.75 502	86.77 537	63.39 529	98.35 481	98.92 416	74.11 507	83.39 512	98.98 424	50.85 522	92.40 516	84.54 503	94.97 418	92.46 510

PDCNetPlus		84.77 477	83.24 480	89.36 495	94.33 515	83.93 499	98.13 495	76.80 536	83.26 501	86.31 504	97.33 489	62.90 512	92.65 514	87.20 495	62.90 522	91.50 513

XFeat-NN		82.84 478	83.12 481	82.00 504	94.35 514	67.14 528	93.32 523	89.27 527	62.21 521	84.06 510	93.50 512	69.15 506	89.40 520	78.92 508	83.33 501	89.46 517

EGC-MVSNET		82.80 479	77.86 486	97.62 421	97.91 464	96.12 404	99.33 310	99.28 355	8.40 540	25.05 541	99.27 387	84.11 474	99.33 369	89.20 483	98.22 302	97.42 488

tmp_tt		82.80 479	81.52 483	86.66 497	66.61 543	68.44 527	92.79 526	97.92 480	68.96 514	80.04 519	99.85 91	85.77 462	96.15 502	97.86 292	43.89 531	95.39 505

XFeat-MNN		82.40 481	82.10 482	83.31 500	93.04 522	68.49 526	95.39 512	90.86 524	60.29 522	81.56 514	94.09 509	66.79 509	91.70 518	76.62 511	80.26 515	89.74 516

E-PMN		80.61 482	79.88 484	82.81 501	90.75 528	76.38 520	97.69 502	95.76 507	66.44 517	83.52 511	92.25 515	62.54 513	87.16 528	68.53 520	61.40 523	84.89 520

EMVS		80.02 483	79.22 485	82.43 503	91.19 527	76.40 519	97.55 506	92.49 523	66.36 519	83.01 513	91.27 517	64.63 511	85.79 531	65.82 521	60.65 524	85.08 519

GLUNet-SfM		78.99 484	76.32 488	86.99 496	89.16 535	73.30 525	93.36 522	90.45 525	66.38 518	74.95 524	93.30 513	52.29 521	94.61 512	75.35 515	51.65 529	93.07 509

ANet_high		77.30 485	74.86 492	84.62 499	75.88 541	77.61 518	97.63 504	93.15 521	88.81 489	64.27 527	89.29 529	36.51 537	83.93 532	75.89 513	52.31 527	92.33 512

SIFT-NN		76.99 486	77.37 487	75.84 506	97.10 485	62.39 530	94.15 517	87.21 529	59.41 523	79.90 520	90.73 520	54.60 520	88.56 523	47.22 524	86.03 491	76.57 522

MVE	76.82 21	76.91 487	74.31 493	84.70 498	85.38 540	76.05 521	96.88 510	93.17 519	67.39 516	71.28 525	89.01 531	21.66 544	87.69 526	71.74 519	72.29 520	90.35 515
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 488	74.97 491	79.01 505	70.98 542	55.18 541	93.37 521	98.21 476	65.08 520	61.78 530	93.83 511	21.74 543	92.53 515	78.59 509	91.12 470	89.34 518
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-MNN		75.73 489	75.71 489	75.77 507	95.65 502	60.92 532	94.36 515	87.62 528	58.67 524	75.90 522	90.94 519	49.64 526	89.04 522	44.85 529	83.80 497	77.35 521

SIFT-NN-NCMNet		75.53 490	75.57 490	75.42 508	93.93 518	61.35 531	94.41 514	86.44 530	58.51 525	76.23 521	90.44 522	50.56 523	89.34 521	46.60 525	83.04 502	75.58 524

SIFT-NN-CMatch		72.61 491	71.92 494	74.68 509	92.79 523	60.24 534	93.28 524	81.57 534	58.24 527	75.18 523	90.26 524	49.66 525	87.35 527	46.02 526	60.26 525	76.45 523

SIFT-NCM-Cal		71.65 492	70.76 496	74.34 510	94.61 513	60.18 535	94.16 516	81.72 533	57.21 529	55.36 533	89.56 528	42.48 530	88.45 524	41.31 534	80.41 513	74.39 526

SIFT-NN-UMatch		71.65 492	70.86 495	74.00 511	90.69 529	60.53 533	93.59 519	81.89 532	58.42 526	60.99 531	89.71 527	50.18 524	87.89 525	45.77 527	66.55 521	73.57 528

SIFT-NN-PointCN		70.32 494	69.71 497	72.13 514	90.01 531	58.29 539	93.45 520	76.20 537	56.66 532	70.25 526	89.20 530	48.94 527	83.41 533	45.45 528	57.26 526	74.70 525

SIFT-ConvMatch		69.43 495	68.09 498	73.45 512	93.86 519	60.02 536	92.57 527	77.69 535	57.58 528	62.69 528	90.53 521	42.14 531	86.65 530	43.98 530	51.72 528	73.67 527

SIFT-UMatch		68.14 496	66.40 499	73.38 513	92.20 526	59.42 537	92.84 525	76.01 538	56.87 530	58.37 532	90.35 523	41.97 532	87.16 528	42.64 531	46.35 530	73.55 529

SIFT-CM-Cal		66.94 497	65.48 500	71.33 515	93.05 521	58.77 538	91.46 530	70.45 540	56.64 533	61.97 529	89.98 525	40.72 533	83.32 534	42.57 532	42.47 532	71.90 530

SIFT-UM-Cal		64.60 498	62.65 501	70.42 516	92.22 525	58.07 540	92.29 528	66.92 541	56.70 531	50.16 535	89.97 526	37.90 535	82.95 535	42.33 533	35.40 535	70.24 532

SIFT-PointCN		62.71 499	61.56 502	66.18 517	89.53 534	50.88 542	91.81 529	72.35 539	53.65 534	50.49 534	86.32 533	33.30 538	76.23 537	35.91 538	40.66 533	71.43 531

SIFT-PCN-Cal		61.29 500	60.21 503	64.54 518	89.88 532	50.56 543	91.21 531	65.73 542	53.15 535	48.59 536	87.20 532	36.60 536	76.52 536	37.37 537	32.17 536	66.54 533

SIFT-NCMNet		55.02 501	53.54 504	59.46 519	86.55 538	47.35 545	87.85 532	46.22 543	51.77 536	44.11 537	83.50 534	27.88 541	68.75 538	32.81 539	21.14 539	62.27 534

wuyk23d		40.18 502	41.29 507	36.84 520	86.18 539	49.12 544	79.73 533	22.81 545	27.64 537	25.46 540	28.45 540	21.98 542	48.89 539	55.80 523	23.56 538	12.51 537

testmvs		39.17 503	43.78 505	25.37 522	36.04 545	16.84 547	98.36 480	26.56 544	20.06 538	38.51 539	67.32 535	29.64 540	15.30 541	37.59 535	39.90 534	43.98 536

test123		39.01 504	42.50 506	28.53 521	39.17 544	20.91 546	98.75 449	19.17 546	19.83 539	38.57 538	66.67 536	33.16 539	15.42 540	37.50 536	29.66 537	49.26 535

cdsmvs_eth3d_5k		24.64 505	32.85 508	0.00 523	0.00 546	0.00 548	0.00 534	99.51 159	0.00 541	0.00 542	99.56 293	96.58 174	0.00 542	0.00 540	0.00 540	0.00 538

ab-mvs-re		8.30 506	11.06 509	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	99.58 285	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

pcd_1.5k_mvsjas		8.27 507	11.03 510	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	99.01 19	0.00 542	0.00 540	0.00 540	0.00 538

test_blank		0.13 508	0.17 511	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	1.57 541	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

mmdepth		0.02 509	0.03 512	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

monomultidepth		0.02 509	0.03 512	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

uanet_test		0.02 509	0.03 512	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

DCPMVS		0.02 509	0.03 512	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

sosnet-low-res		0.02 509	0.03 512	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

sosnet		0.02 509	0.03 512	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

uncertanet		0.02 509	0.03 512	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

Regformer		0.02 509	0.03 512	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

uanet		0.02 509	0.03 512	0.00 523	0.00 546	0.00 548	0.00 534	0.00 547	0.00 541	0.00 542	0.27 542	0.00 545	0.00 542	0.00 540	0.00 540	0.00 538

MED-MVS test				99.87 22	99.88 13	99.81 33	99.69 63	99.87 6	99.34 28	99.90 34	99.83 113		99.95 76	98.83 177	99.89 67	99.83 64

TestfortrainingZip				99.69 89	99.58 203	99.62 83	99.69 63	99.38 298	98.98 72	99.84 55	99.75 199	98.84 45	99.78 257		99.21 201	99.66 174

WAC-MVS						97.16 343								95.47 425

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

MSC_two_6792asdad				99.87 22	99.51 234	99.76 49		99.33 330					99.96 41	98.87 164	99.84 101	99.89 30

PC_three_1452									98.18 178	99.84 55	99.70 222	99.31 3	98.52 468	98.30 253	99.80 125	99.81 79

No_MVS				99.87 22	99.51 234	99.76 49		99.33 330					99.96 41	98.87 164	99.84 101	99.89 30

test_one_0601					99.81 57	99.88 10		99.49 197	98.97 76	99.65 142	99.81 139	99.09 15

eth-test2					0.00 546

eth-test					0.00 546

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 355	99.56 172	99.54 301	98.58 79	99.96 41	96.93 382	99.75 142

RE-MVS-def			99.34 49		99.76 82	99.82 28	99.63 104	99.52 133	98.38 138	99.76 92	99.82 124	98.75 61		98.61 209	99.81 120	99.77 100

IU-MVS					99.84 38	99.88 10		99.32 340	98.30 152	99.84 55				98.86 169	99.85 93	99.89 30

OPU-MVS				99.64 102	99.56 213	99.72 56	99.60 117				99.70 222	99.27 6	99.42 352	98.24 257	99.80 125	99.79 92

test_241102_TWO								99.48 209	99.08 56	99.88 42	99.81 139	98.94 33	99.96 41	98.91 158	99.84 101	99.88 36

test_241102_ONE					99.84 38	99.90 2		99.48 209	99.07 58	99.91 31	99.74 205	99.20 8	99.76 265

9.14			99.10 98		99.72 111		99.40 281	99.51 159	97.53 288	99.64 147	99.78 181	98.84 45	99.91 135	97.63 319	99.82 117

save fliter					99.76 82	99.59 89	99.14 375	99.40 287	99.00 67

test_0728_THIRD									98.99 69	99.81 69	99.80 157	99.09 15	99.96 41	98.85 171	99.90 56	99.88 36

test_0728_SECOND				99.91 6	99.84 38	99.89 6	99.57 146	99.51 159					99.96 41	98.93 155	99.86 86	99.88 36

test0726					99.85 31	99.89 6	99.62 109	99.50 184	99.10 48	99.86 52	99.82 124	98.94 33

GSMVS																99.52 232

test_part2					99.81 57	99.83 22				99.77 86

sam_mvs1												94.86 267				99.52 232

sam_mvs												94.72 283

ambc				93.06 475	92.68 524	82.36 501	98.47 477	98.73 454		95.09 471	97.41 486	55.55 517	99.10 419	96.42 402	91.32 467	97.71 477

MTGPA								99.47 231

test_post1							99.23 354				65.14 538	94.18 314	99.71 287	97.58 323

test_post											65.99 537	94.65 290	99.73 277

patchmatchnet-post											98.70 443	94.79 273	99.74 271

GG-mvs-BLEND				98.45 341	98.55 448	98.16 290	99.43 262	93.68 517		97.23 442	98.46 451	89.30 424	99.22 394	95.43 427	98.22 302	97.98 468

MTMP							99.54 174	98.88 427

gm-plane-assit					98.54 449	92.96 474			94.65 442		99.15 401		99.64 316	97.56 328

test9_res														97.49 336	99.72 148	99.75 113

TEST9					99.67 138	99.65 75	99.05 396	99.41 280	96.22 402	98.95 320	99.49 319	98.77 57	99.91 135

test_8					99.67 138	99.61 86	99.03 401	99.41 280	96.28 396	98.93 323	99.48 327	98.76 58	99.91 135

agg_prior2														97.21 360	99.73 147	99.75 113

agg_prior					99.67 138	99.62 83		99.40 287		98.87 333			99.91 135

TestCases				99.31 205	99.86 25	98.48 275		99.61 60	97.85 243	99.36 228	99.85 91	95.95 212	99.85 190	96.66 395	99.83 113	99.59 212

test_prior4						99.56 95	98.99 412

test_prior2							98.96 419		98.34 144	99.01 307	99.52 309	98.68 71		97.96 284	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							98.96 419		96.70 364	99.47 191			99.94 91	98.19 260

新几何2							99.01 409

新几何1				99.75 77	99.75 92	99.59 89		99.54 108	96.76 360	99.29 245	99.64 261	98.43 90	99.94 91	96.92 384	99.66 159	99.72 138

旧先验1					99.74 100	99.59 89		99.54 108			99.69 233	98.47 87			99.68 156	99.73 128

无先验							98.99 412	99.51 159	96.89 352				99.93 108	97.53 331		99.72 138

原ACMM2							98.95 422

原ACMM1				99.65 96	99.73 107	99.33 131		99.47 231	97.46 294	99.12 285	99.66 253	98.67 73	99.91 135	97.70 316	99.69 153	99.71 150

test222					99.75 92	99.49 110	98.91 429	99.49 197	96.42 390	99.34 235	99.65 255	98.28 100			99.69 153	99.72 138

testdata2													99.95 76	96.67 394

segment_acmp												98.96 26

testdata				99.54 127	99.75 92	98.95 197		99.51 159	97.07 336	99.43 202	99.70 222	98.87 41	99.94 91	97.76 306	99.64 162	99.72 138

testdata1							98.85 434		98.32 148

test12				99.75 77	99.64 167	99.61 86		99.29 353		99.21 267		98.38 95	99.89 163		99.74 145	99.74 118

plane_prior7					99.29 310	97.03 358

plane_prior6					99.27 315	96.98 362						92.71 356

plane_prior5								99.47 231					99.69 301	97.78 302	97.63 331	98.67 376

plane_prior4											99.61 276

plane_prior3						97.00 360			98.69 108	99.11 287

plane_prior2							99.39 285		98.97 76

plane_prior1					99.26 318

plane_prior						96.97 363	99.21 360		98.45 131						97.60 334

n2								0.00 547

nn								0.00 547

door-mid								98.05 479

lessismore_v0				97.79 411	98.69 433	95.44 432		94.75 512		95.71 465	99.87 74	88.69 432	99.32 371	95.89 413	94.93 420	98.62 398

LGP-MVS_train				98.49 331	99.33 297	97.05 352		99.55 99	97.46 294	99.24 259	99.83 113	92.58 361	99.72 281	98.09 271	97.51 343	98.68 368

test11								99.35 317

door								97.92 480

HQP5-MVS						96.83 374

HQP-NCC					99.19 336		98.98 415		98.24 165	98.66 364

ACMP_Plane					99.19 336		98.98 415		98.24 165	98.66 364

BP-MVS														97.19 364

HQP4-MVS										98.66 364			99.64 316			98.64 389

HQP3-MVS								99.39 290							97.58 336

HQP2-MVS												92.47 365

NP-MVS					99.23 326	96.92 370					99.40 349

MDTV_nov1_ep13_2view						95.18 439	99.35 303		96.84 355	99.58 167		95.19 252		97.82 297		99.46 260

MDTV_nov1_ep13			98.32 237		99.11 357	94.44 456	99.27 335	98.74 448	97.51 291	99.40 215	99.62 272	94.78 274	99.76 265	97.59 322	98.81 265

ACMMP++_ref															97.19 364

ACMMP++															97.43 354

Test By Simon												98.75 61

ITE_SJBPF				98.08 378	99.29 310	96.37 394		98.92 416	98.34 144	98.83 341	99.75 199	91.09 402	99.62 323	95.82 414	97.40 356	98.25 449

DeepMVS_CX				93.34 472	99.29 310	82.27 502		99.22 373	85.15 498	96.33 458	99.05 412	90.97 404	99.73 277	93.57 454	97.77 327	98.01 463

High-resolution multi-view benchmark