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 36	99.86 20	99.61 77	99.56 133	99.63 42	99.48 3	99.98 10	99.83 83	98.75 58	99.99 4	99.97 1	99.96 14	99.94 14

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 36	99.84 32	99.63 74	99.56 133	99.63 42	99.47 4	99.98 10	99.82 92	98.75 58	99.99 4	99.97 1	99.97 8	99.94 14

test_fmvsmconf_n		99.70 3	99.64 4	99.87 17	99.80 54	99.66 63	99.48 196	99.64 38	99.45 10	99.92 25	99.92 17	98.62 73	99.99 4	99.96 10	99.99 1	99.96 7

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 62	99.84 32	99.44 107	99.58 119	99.69 18	99.43 13	99.98 10	99.91 23	98.62 73	100.00 1	99.97 1	99.95 19	99.90 22

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 68	99.89 4	99.75 42	99.56 80	99.02 51	99.88 35	99.85 67	99.18 10	99.96 36	99.22 86	99.92 34	99.90 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 65	99.38 237	99.37 113	99.58 119	99.62 45	99.41 17	99.87 40	99.92 17	98.81 47	100.00 1	99.97 1	99.93 29	99.94 14

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 60	99.88 8	99.56 133	99.55 88	99.15 30	99.90 29	99.90 30	99.00 22	99.97 24	99.11 96	99.91 41	99.86 38

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 32	99.82 25	99.54 152	99.66 28	99.46 7	99.98 10	99.89 36	97.27 129	99.99 4	99.97 1	99.95 19	99.95 10

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 72	99.88 8	99.52 162	99.54 97	99.13 33	99.89 32	99.89 36	98.96 25	99.96 36	99.04 104	99.90 50	99.85 42

our_new_method		99.61 8	99.52 12	99.90 5	99.76 72	99.88 8	99.52 162	99.54 97	99.13 33	99.89 32	99.89 36	98.96 25	99.96 36	99.04 104	99.90 50	99.85 42

SED-MVS		99.61 8	99.52 12	99.88 11	99.84 32	99.90 2	99.60 102	99.48 172	99.08 46	99.91 26	99.81 106	99.20 7	99.96 36	98.91 122	99.85 83	99.79 84

DVP-MVS++		99.59 12	99.50 17	99.88 11	99.51 188	99.88 8	99.87 8	99.51 130	98.99 58	99.88 35	99.81 106	99.27 5	99.96 36	98.85 135	99.80 112	99.81 71

TSAR-MVS + MP.		99.58 13	99.50 17	99.81 53	99.91 1	99.66 63	99.63 90	99.39 243	98.91 71	99.78 65	99.85 67	99.36 2	99.94 81	98.84 138	99.88 65	99.82 64
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 13	99.57 8	99.64 91	99.78 60	99.14 147	99.60 102	99.45 213	99.01 53	99.90 29	99.83 83	98.98 24	99.93 99	99.59 40	99.95 19	99.86 38

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 91	99.78 60	99.15 146	99.61 101	99.45 213	99.01 53	99.89 32	99.82 92	99.01 18	99.92 111	99.56 44	99.95 19	99.85 42

DVP-MVS		99.57 16	99.47 21	99.88 11	99.85 26	99.89 4	99.57 126	99.37 259	99.10 40	99.81 54	99.80 119	98.94 32	99.96 36	98.93 119	99.86 76	99.81 71
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
fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 36	99.83 40	99.64 73	99.52 162	99.65 35	99.10 40	99.98 10	99.92 17	97.35 125	99.96 36	99.94 17	99.92 34	99.95 10

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 28	99.44 219	99.65 67	99.50 179	99.61 53	99.45 10	99.87 40	99.92 17	97.31 126	99.97 24	99.95 12	99.99 1	99.97 4

fmvsm_s_conf0.5_n_8		99.54 19	99.42 27	99.89 8	99.83 40	99.74 47	99.51 171	99.62 45	99.46 7	99.99 2	99.90 30	96.60 154	99.98 15	99.95 12	99.95 19	99.96 7

fmvsm_s_conf0.5_n_6		99.54 19	99.44 26	99.85 36	99.51 188	99.67 60	99.50 179	99.64 38	99.43 13	99.98 10	99.78 138	97.26 131	99.95 68	99.95 12	99.93 29	99.92 20

SteuartSystems-ACMMP		99.54 19	99.42 27	99.87 17	99.82 44	99.81 29	99.59 109	99.51 130	98.62 100	99.79 60	99.83 83	99.28 4	99.97 24	98.48 189	99.90 50	99.84 49
Skip Steuart: Steuart Systems R&D Blog.
XVS		99.53 22	99.42 27	99.87 17	99.85 26	99.83 19	99.69 60	99.68 20	98.98 61	99.37 181	99.74 159	98.81 47	99.94 81	98.79 146	99.86 76	99.84 49

MTAPA		99.52 23	99.39 35	99.89 8	99.90 4	99.86 16	99.66 75	99.47 193	98.79 84	99.68 94	99.81 106	98.43 86	99.97 24	98.88 125	99.90 50	99.83 59

fmvsm_s_conf0.5_n		99.51 24	99.40 33	99.85 36	99.84 32	99.65 67	99.51 171	99.67 23	99.13 33	99.98 10	99.92 17	96.60 154	99.96 36	99.95 12	99.96 14	99.95 10

HPM-MVS_fast		99.51 24	99.40 33	99.85 36	99.91 1	99.79 34	99.76 37	99.56 80	97.72 214	99.76 75	99.75 154	99.13 12	99.92 111	99.07 102	99.92 34	99.85 42

mvsany_test1		99.50 26	99.46 24	99.62 98	99.61 156	99.09 152	98.94 371	99.48 172	99.10 40	99.96 23	99.91 23	98.85 42	99.96 36	99.72 28	99.58 156	99.82 64

CS-MVS		99.50 26	99.48 19	99.54 112	99.76 72	99.42 109	99.90 1	99.55 88	98.56 105	99.78 65	99.70 176	98.65 71	99.79 211	99.65 36	99.78 121	99.41 222

SPE-MVS-test		99.49 28	99.48 19	99.54 112	99.78 60	99.30 125	99.89 2	99.58 70	98.56 105	99.73 81	99.69 187	98.55 78	99.82 196	99.69 31	99.85 83	99.48 201

HFP-MVS		99.49 28	99.37 39	99.86 28	99.87 15	99.80 31	99.66 75	99.67 23	98.15 154	99.68 94	99.69 187	99.06 16	99.96 36	98.69 158	99.87 68	99.84 49

ACMMPR		99.49 28	99.36 41	99.86 28	99.87 15	99.79 34	99.66 75	99.67 23	98.15 154	99.67 98	99.69 187	98.95 30	99.96 36	98.69 158	99.87 68	99.84 49

DeepC-MVS_fast	98.69 1	99.49 28	99.39 35	99.77 65	99.63 145	99.59 80	99.36 256	99.46 202	99.07 48	99.79 60	99.82 92	98.85 42	99.92 111	98.68 160	99.87 68	99.82 64
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 32	99.35 43	99.87 17	99.88 11	99.80 31	99.65 81	99.66 28	98.13 159	99.66 103	99.68 194	98.96 25	99.96 36	98.62 167	99.87 68	99.84 49

APD-MVS_3200maxsize		99.48 32	99.35 43	99.85 36	99.76 72	99.83 19	99.63 90	99.54 97	98.36 127	99.79 60	99.82 92	98.86 41	99.95 68	98.62 167	99.81 107	99.78 90

DELS-MVS		99.48 32	99.42 27	99.65 85	99.72 101	99.40 112	99.05 343	99.66 28	99.14 32	99.57 135	99.80 119	98.46 84	99.94 81	99.57 43	99.84 91	99.60 163
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 35	99.33 47	99.87 17	99.87 15	99.81 29	99.64 84	99.67 23	98.08 170	99.55 140	99.64 213	98.91 37	99.96 36	98.72 153	99.90 50	99.82 64

ACMMP_NAP		99.47 35	99.34 45	99.88 11	99.87 15	99.86 16	99.47 204	99.48 172	98.05 177	99.76 75	99.86 60	98.82 46	99.93 99	98.82 145	99.91 41	99.84 49

MVSMamba_PlusPlus		99.46 37	99.41 32	99.64 91	99.68 121	99.50 99	99.75 42	99.50 150	98.27 137	99.87 40	99.92 17	98.09 104	99.94 81	99.65 36	99.95 19	99.47 207

balanced_conf03		99.46 37	99.39 35	99.67 80	99.55 175	99.58 85	99.74 46	99.51 130	98.42 120	99.87 40	99.84 78	98.05 107	99.91 123	99.58 42	99.94 27	99.52 187

DPE-MVS		99.46 37	99.32 49	99.91 3	99.78 60	99.88 8	99.36 256	99.51 130	98.73 91	99.88 35	99.84 78	98.72 64	99.96 36	98.16 221	99.87 68	99.88 31
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSLP-MVS++		99.46 37	99.47 21	99.44 146	99.60 161	99.16 142	99.41 232	99.71 13	98.98 61	99.45 156	99.78 138	99.19 9	99.54 283	99.28 80	99.84 91	99.63 156

SR-MVS-dyc-post		99.45 41	99.31 55	99.85 36	99.76 72	99.82 25	99.63 90	99.52 115	98.38 123	99.76 75	99.82 92	98.53 79	99.95 68	98.61 170	99.81 107	99.77 92

PGM-MVS		99.45 41	99.31 55	99.86 28	99.87 15	99.78 40	99.58 119	99.65 35	97.84 200	99.71 88	99.80 119	99.12 13	99.97 24	98.33 206	99.87 68	99.83 59

CP-MVS		99.45 41	99.32 49	99.85 36	99.83 40	99.75 44	99.69 60	99.52 115	98.07 171	99.53 143	99.63 219	98.93 36	99.97 24	98.74 150	99.91 41	99.83 59

ACMMP		99.45 41	99.32 49	99.82 50	99.89 8	99.67 60	99.62 95	99.69 18	98.12 161	99.63 118	99.84 78	98.73 63	99.96 36	98.55 185	99.83 100	99.81 71
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 45	99.30 57	99.85 36	99.73 97	99.83 19	99.56 133	99.47 193	97.45 248	99.78 65	99.82 92	99.18 10	99.91 123	98.79 146	99.89 61	99.81 71
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 45	99.30 57	99.86 28	99.88 11	99.79 34	99.69 60	99.48 172	98.12 161	99.50 148	99.75 154	98.78 51	99.97 24	98.57 179	99.89 61	99.83 59

EC-MVSNet		99.44 45	99.39 35	99.58 105	99.56 171	99.49 100	99.88 4	99.58 70	98.38 123	99.73 81	99.69 187	98.20 99	99.70 249	99.64 38	99.82 104	99.54 180

SR-MVS		99.43 48	99.29 61	99.86 28	99.75 82	99.83 19	99.59 109	99.62 45	98.21 147	99.73 81	99.79 131	98.68 67	99.96 36	98.44 195	99.77 124	99.79 84

MCST-MVS		99.43 48	99.30 57	99.82 50	99.79 58	99.74 47	99.29 278	99.40 240	98.79 84	99.52 145	99.62 224	98.91 37	99.90 135	98.64 164	99.75 129	99.82 64

MSP-MVS		99.42 50	99.27 67	99.88 11	99.89 8	99.80 31	99.67 69	99.50 150	98.70 94	99.77 69	99.49 271	98.21 98	99.95 68	98.46 193	99.77 124	99.88 31
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 50	99.29 61	99.80 56	99.62 151	99.55 88	99.50 179	99.70 15	98.79 84	99.77 69	99.96 1	97.45 120	99.96 36	98.92 121	99.90 50	99.89 25

HPM-MVS		99.42 50	99.28 64	99.83 49	99.90 4	99.72 49	99.81 20	99.54 97	97.59 229	99.68 94	99.63 219	98.91 37	99.94 81	98.58 176	99.91 41	99.84 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CNVR-MVS		99.42 50	99.30 57	99.78 62	99.62 151	99.71 51	99.26 297	99.52 115	98.82 78	99.39 177	99.71 172	98.96 25	99.85 168	98.59 175	99.80 112	99.77 92

SD-MVS		99.41 54	99.52 12	99.05 202	99.74 90	99.68 56	99.46 207	99.52 115	99.11 39	99.88 35	99.91 23	99.43 1	97.70 419	98.72 153	99.93 29	99.77 92
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 54	99.33 47	99.65 85	99.77 68	99.51 98	98.94 371	99.85 6	98.82 78	99.65 110	99.74 159	98.51 81	99.80 208	98.83 141	99.89 61	99.64 151

MVS_111021_HR		99.41 54	99.32 49	99.66 81	99.72 101	99.47 104	98.95 369	99.85 6	98.82 78	99.54 141	99.73 165	98.51 81	99.74 227	98.91 122	99.88 65	99.77 92

MM		99.40 57	99.28 64	99.74 71	99.67 123	99.31 123	99.52 162	98.87 368	99.55 1	99.74 79	99.80 119	96.47 161	99.98 15	99.97 1	99.97 8	99.94 14

GST-MVS		99.40 57	99.24 72	99.85 36	99.86 20	99.79 34	99.60 102	99.67 23	97.97 185	99.63 118	99.68 194	98.52 80	99.95 68	98.38 199	99.86 76	99.81 71

HPM-MVS++		99.39 59	99.23 75	99.87 17	99.75 82	99.84 18	99.43 220	99.51 130	98.68 97	99.27 206	99.53 257	98.64 72	99.96 36	98.44 195	99.80 112	99.79 84

SF-MVS		99.38 60	99.24 72	99.79 59	99.79 58	99.68 56	99.57 126	99.54 97	97.82 205	99.71 88	99.80 119	98.95 30	99.93 99	98.19 217	99.84 91	99.74 102

fmvsm_s_conf0.5_n_5		99.37 61	99.21 77	99.86 28	99.80 54	99.68 56	99.42 227	99.61 53	99.37 20	99.97 21	99.86 60	94.96 220	99.99 4	99.97 1	99.93 29	99.92 20

fmvsm_s_conf0.5_n_3		99.37 61	99.20 79	99.87 17	99.75 82	99.70 53	99.48 196	99.66 28	99.45 10	99.99 2	99.93 10	94.64 247	99.97 24	99.94 17	99.97 8	99.95 10

fmvsm_s_conf0.1_n_2		99.37 61	99.22 76	99.81 53	99.77 68	99.75 44	99.46 207	99.60 60	99.47 4	99.98 10	99.94 6	94.98 219	99.95 68	99.97 1	99.79 119	99.73 109

MP-MVS-pluss		99.37 61	99.20 79	99.88 11	99.90 4	99.87 15	99.30 273	99.52 115	97.18 274	99.60 128	99.79 131	98.79 50	99.95 68	98.83 141	99.91 41	99.83 59
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_4		99.36 65	99.24 72	99.73 74	99.78 60	99.53 93	99.49 191	99.60 60	99.42 16	99.99 2	99.86 60	95.15 215	99.95 68	99.95 12	99.89 61	99.73 109

TSAR-MVS + GP.		99.36 65	99.36 41	99.36 155	99.67 123	98.61 216	99.07 338	99.33 279	99.00 56	99.82 53	99.81 106	99.06 16	99.84 175	99.09 100	99.42 167	99.65 144

PVSNet_Blended_VisFu		99.36 65	99.28 64	99.61 99	99.86 20	99.07 157	99.47 204	99.93 2	97.66 223	99.71 88	99.86 60	97.73 115	99.96 36	99.47 59	99.82 104	99.79 84

fmvsm_s_conf0.5_n_7		99.34 68	99.29 61	99.48 135	99.70 111	98.63 212	99.42 227	99.63 42	99.46 7	99.98 10	99.88 44	95.59 196	99.96 36	99.97 1	99.98 4	99.85 42

NCCC		99.34 68	99.19 81	99.79 59	99.61 156	99.65 67	99.30 273	99.48 172	98.86 73	99.21 221	99.63 219	98.72 64	99.90 135	98.25 213	99.63 151	99.80 80

mamv4		99.33 70	99.42 27	99.07 198	99.67 123	97.73 274	99.42 227	99.60 60	98.15 154	99.94 24	99.91 23	98.42 88	99.94 81	99.72 28	99.96 14	99.54 180

MP-MVS		99.33 70	99.15 84	99.87 17	99.88 11	99.82 25	99.66 75	99.46 202	98.09 166	99.48 152	99.74 159	98.29 95	99.96 36	97.93 239	99.87 68	99.82 64
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_s_conf0.5_n_2		99.32 72	99.13 86	99.89 8	99.80 54	99.77 41	99.44 215	99.58 70	99.47 4	99.99 2	99.93 10	94.04 271	99.96 36	99.96 10	99.93 29	99.93 19

PS-MVSNAJ		99.32 72	99.32 49	99.30 169	99.57 167	98.94 179	98.97 365	99.46 202	98.92 70	99.71 88	99.24 340	99.01 18	99.98 15	99.35 67	99.66 146	98.97 273

CSCG		99.32 72	99.32 49	99.32 163	99.85 26	98.29 241	99.71 55	99.66 28	98.11 163	99.41 170	99.80 119	98.37 92	99.96 36	98.99 110	99.96 14	99.72 117

PHI-MVS		99.30 75	99.17 83	99.70 78	99.56 171	99.52 97	99.58 119	99.80 8	97.12 280	99.62 122	99.73 165	98.58 75	99.90 135	98.61 170	99.91 41	99.68 134

DeepC-MVS	98.35 2	99.30 75	99.19 81	99.64 91	99.82 44	99.23 135	99.62 95	99.55 88	98.94 67	99.63 118	99.95 3	95.82 187	99.94 81	99.37 66	99.97 8	99.73 109
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 77	99.10 90	99.86 28	99.70 111	99.65 67	99.53 161	99.62 45	98.74 90	99.99 2	99.95 3	94.53 254	99.94 81	99.89 21	99.96 14	99.97 4

xiu_mvs_v1_base_debu		99.29 77	99.27 67	99.34 157	99.63 145	98.97 169	99.12 328	99.51 130	98.86 73	99.84 46	99.47 280	98.18 100	99.99 4	99.50 52	99.31 177	99.08 258

xiu_mvs_v1_base		99.29 77	99.27 67	99.34 157	99.63 145	98.97 169	99.12 328	99.51 130	98.86 73	99.84 46	99.47 280	98.18 100	99.99 4	99.50 52	99.31 177	99.08 258

xiu_mvs_v1_base_debi		99.29 77	99.27 67	99.34 157	99.63 145	98.97 169	99.12 328	99.51 130	98.86 73	99.84 46	99.47 280	98.18 100	99.99 4	99.50 52	99.31 177	99.08 258

APD-MVS		99.27 81	99.08 94	99.84 48	99.75 82	99.79 34	99.50 179	99.50 150	97.16 276	99.77 69	99.82 92	98.78 51	99.94 81	97.56 278	99.86 76	99.80 80
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
LS3D		99.27 81	99.12 88	99.74 71	99.18 291	99.75 44	99.56 133	99.57 75	98.45 116	99.49 151	99.85 67	97.77 114	99.94 81	98.33 206	99.84 91	99.52 187

fmvsm_s_conf0.1_n_a		99.26 83	99.06 96	99.85 36	99.52 185	99.62 75	99.54 152	99.62 45	98.69 95	99.99 2	99.96 1	94.47 256	99.94 81	99.88 22	99.92 34	99.98 2

patch_mono-2		99.26 83	99.62 5	98.16 320	99.81 48	94.59 392	99.52 162	99.64 38	99.33 22	99.73 81	99.90 30	99.00 22	99.99 4	99.69 31	99.98 4	99.89 25

ETV-MVS		99.26 83	99.21 77	99.40 149	99.46 212	99.30 125	99.56 133	99.52 115	98.52 109	99.44 161	99.27 336	98.41 90	99.86 162	99.10 99	99.59 155	99.04 265

xiu_mvs_v2_base		99.26 83	99.25 71	99.29 172	99.53 179	98.91 184	99.02 351	99.45 213	98.80 83	99.71 88	99.26 338	98.94 32	99.98 15	99.34 72	99.23 182	98.98 272

CANet		99.25 87	99.14 85	99.59 102	99.41 227	99.16 142	99.35 261	99.57 75	98.82 78	99.51 147	99.61 228	96.46 162	99.95 68	99.59 40	99.98 4	99.65 144

3Dnovator	97.25 9	99.24 88	99.05 97	99.81 53	99.12 307	99.66 63	99.84 12	99.74 10	99.09 45	98.92 276	99.90 30	95.94 181	99.98 15	98.95 115	99.92 34	99.79 84

dcpmvs_2		99.23 89	99.58 7	98.16 320	99.83 40	94.68 389	99.76 37	99.52 115	99.07 48	99.98 10	99.88 44	98.56 77	99.93 99	99.67 33	99.98 4	99.87 36

test_fmvsmconf0.01_n		99.22 90	99.03 102	99.79 59	98.42 398	99.48 102	99.55 147	99.51 130	99.39 18	99.78 65	99.93 10	94.80 231	99.95 68	99.93 19	99.95 19	99.94 14

CHOSEN 1792x2688		99.19 91	99.10 90	99.45 142	99.89 8	98.52 226	99.39 244	99.94 1	98.73 91	99.11 240	99.89 36	95.50 199	99.94 81	99.50 52	99.97 8	99.89 25

F-COLMAP		99.19 91	99.04 99	99.64 91	99.78 60	99.27 130	99.42 227	99.54 97	97.29 265	99.41 170	99.59 233	98.42 88	99.93 99	98.19 217	99.69 140	99.73 109

EIA-MVS		99.18 93	99.09 93	99.45 142	99.49 202	99.18 139	99.67 69	99.53 110	97.66 223	99.40 175	99.44 287	98.10 103	99.81 201	98.94 116	99.62 152	99.35 231

3Dnovator+	97.12 13	99.18 93	98.97 117	99.82 50	99.17 299	99.68 56	99.81 20	99.51 130	99.20 27	98.72 304	99.89 36	95.68 193	99.97 24	98.86 133	99.86 76	99.81 71

MVSFormer		99.17 95	99.12 88	99.29 172	99.51 188	98.94 179	99.88 4	99.46 202	97.55 235	99.80 58	99.65 207	97.39 121	99.28 326	99.03 106	99.85 83	99.65 144

sss		99.17 95	99.05 97	99.53 120	99.62 151	98.97 169	99.36 256	99.62 45	97.83 201	99.67 98	99.65 207	97.37 124	99.95 68	99.19 88	99.19 185	99.68 134

guyue		99.16 97	99.04 99	99.52 126	99.69 116	98.92 183	99.59 109	98.81 375	98.73 91	99.90 29	99.87 55	95.34 206	99.88 153	99.66 35	99.81 107	99.74 102

test_cas_vis1_n_1920		99.16 97	99.01 111	99.61 99	99.81 48	98.86 190	99.65 81	99.64 38	99.39 18	99.97 21	99.94 6	93.20 293	99.98 15	99.55 45	99.91 41	99.99 1

DP-MVS		99.16 97	98.95 123	99.78 62	99.77 68	99.53 93	99.41 232	99.50 150	97.03 292	99.04 257	99.88 44	97.39 121	99.92 111	98.66 162	99.90 50	99.87 36

MVS_0304		99.15 100	98.96 121	99.73 74	98.92 344	99.37 113	99.37 251	96.92 424	99.51 2	99.66 103	99.78 138	96.69 151	99.97 24	99.84 24	99.97 8	99.84 49

casdiffmvs_mvg		99.15 100	99.02 107	99.55 111	99.66 133	99.09 152	99.64 84	99.56 80	98.26 139	99.45 156	99.87 55	96.03 176	99.81 201	99.54 46	99.15 189	99.73 109
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		99.15 100	99.02 107	99.53 120	99.66 133	99.14 147	99.72 52	99.48 172	98.35 128	99.42 166	99.84 78	96.07 174	99.79 211	99.51 51	99.14 190	99.67 137

diffmvs		99.14 103	99.02 107	99.51 129	99.61 156	98.96 173	99.28 283	99.49 160	98.46 114	99.72 86	99.71 172	96.50 160	99.88 153	99.31 76	99.11 192	99.67 137
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		99.14 103	98.99 113	99.59 102	99.58 165	99.41 111	99.16 319	99.44 222	98.45 116	99.19 227	99.49 271	98.08 105	99.89 148	97.73 261	99.75 129	99.48 201

CDPH-MVS		99.13 105	98.91 128	99.80 56	99.75 82	99.71 51	99.15 322	99.41 233	96.60 324	99.60 128	99.55 248	98.83 45	99.90 135	97.48 285	99.83 100	99.78 90

casdiffmvs		99.13 105	98.98 116	99.56 109	99.65 140	99.16 142	99.56 133	99.50 150	98.33 131	99.41 170	99.86 60	95.92 182	99.83 188	99.45 61	99.16 186	99.70 128
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jason		99.13 105	99.03 102	99.45 142	99.46 212	98.87 187	99.12 328	99.26 308	98.03 180	99.79 60	99.65 207	97.02 140	99.85 168	99.02 108	99.90 50	99.65 144
jason: jason.
lupinMVS		99.13 105	99.01 111	99.46 141	99.51 188	98.94 179	99.05 343	99.16 325	97.86 195	99.80 58	99.56 245	97.39 121	99.86 162	98.94 116	99.85 83	99.58 171

EPP-MVSNet		99.13 105	98.99 113	99.53 120	99.65 140	99.06 158	99.81 20	99.33 279	97.43 252	99.60 128	99.88 44	97.14 133	99.84 175	99.13 94	98.94 206	99.69 130

MG-MVS		99.13 105	99.02 107	99.45 142	99.57 167	98.63 212	99.07 338	99.34 272	98.99 58	99.61 125	99.82 92	97.98 109	99.87 159	97.00 316	99.80 112	99.85 42

BP-MVS1		99.12 111	98.94 125	99.65 85	99.51 188	99.30 125	99.67 69	98.92 356	98.48 112	99.84 46	99.69 187	94.96 220	99.92 111	99.62 39	99.79 119	99.71 126

CHOSEN 280x420		99.12 111	99.13 86	99.08 197	99.66 133	97.89 267	98.43 412	99.71 13	98.88 72	99.62 122	99.76 151	96.63 153	99.70 249	99.46 60	99.99 1	99.66 140

DP-MVS Recon		99.12 111	98.95 123	99.65 85	99.74 90	99.70 53	99.27 288	99.57 75	96.40 340	99.42 166	99.68 194	98.75 58	99.80 208	97.98 236	99.72 135	99.44 217

Vis-MVSNet		99.12 111	98.97 117	99.56 109	99.78 60	99.10 151	99.68 66	99.66 28	98.49 111	99.86 44	99.87 55	94.77 236	99.84 175	99.19 88	99.41 168	99.74 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAMVS		99.12 111	99.08 94	99.24 182	99.46 212	98.55 220	99.51 171	99.46 202	98.09 166	99.45 156	99.82 92	98.34 93	99.51 285	98.70 155	98.93 207	99.67 137

SDMVSNet		99.11 116	98.90 129	99.75 68	99.81 48	99.59 80	99.81 20	99.65 35	98.78 87	99.64 115	99.88 44	94.56 250	99.93 99	99.67 33	98.26 250	99.72 117

VNet		99.11 116	98.90 129	99.73 74	99.52 185	99.56 86	99.41 232	99.39 243	99.01 53	99.74 79	99.78 138	95.56 197	99.92 111	99.52 50	98.18 258	99.72 117

CPTT-MVS		99.11 116	98.90 129	99.74 71	99.80 54	99.46 105	99.59 109	99.49 160	97.03 292	99.63 118	99.69 187	97.27 129	99.96 36	97.82 250	99.84 91	99.81 71

HyFIR lowres test		99.11 116	98.92 126	99.65 85	99.90 4	99.37 113	99.02 351	99.91 3	97.67 222	99.59 131	99.75 154	95.90 184	99.73 233	99.53 48	99.02 203	99.86 38

MVS_Test		99.10 120	98.97 117	99.48 135	99.49 202	99.14 147	99.67 69	99.34 272	97.31 263	99.58 132	99.76 151	97.65 117	99.82 196	98.87 128	99.07 198	99.46 212

AstraMVS		99.09 121	99.03 102	99.25 179	99.66 133	98.13 250	99.57 126	98.24 407	98.82 78	99.91 26	99.88 44	95.81 188	99.90 135	99.72 28	99.67 145	99.74 102

CDS-MVSNet		99.09 121	99.03 102	99.25 179	99.42 222	98.73 203	99.45 209	99.46 202	98.11 163	99.46 155	99.77 147	98.01 108	99.37 309	98.70 155	98.92 209	99.66 140
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
GDP-MVS		99.08 123	98.89 132	99.64 91	99.53 179	99.34 117	99.64 84	99.48 172	98.32 132	99.77 69	99.66 205	95.14 216	99.93 99	98.97 114	99.50 162	99.64 151

PVSNet_Blended		99.08 123	98.97 117	99.42 147	99.76 72	98.79 199	98.78 387	99.91 3	96.74 309	99.67 98	99.49 271	97.53 118	99.88 153	98.98 111	99.85 83	99.60 163

OMC-MVS		99.08 123	99.04 99	99.20 186	99.67 123	98.22 245	99.28 283	99.52 115	98.07 171	99.66 103	99.81 106	97.79 113	99.78 216	97.79 252	99.81 107	99.60 163

mvsmamba		99.06 126	98.96 121	99.36 155	99.47 210	98.64 211	99.70 56	99.05 340	97.61 228	99.65 110	99.83 83	96.54 158	99.92 111	99.19 88	99.62 152	99.51 195

WTY-MVS		99.06 126	98.88 134	99.61 99	99.62 151	99.16 142	99.37 251	99.56 80	98.04 178	99.53 143	99.62 224	96.84 145	99.94 81	98.85 135	98.49 237	99.72 117

IS-MVSNet		99.05 128	98.87 135	99.57 107	99.73 97	99.32 119	99.75 42	99.20 320	98.02 182	99.56 136	99.86 60	96.54 158	99.67 257	98.09 224	99.13 191	99.73 109

PAPM_NR		99.04 129	98.84 141	99.66 81	99.74 90	99.44 107	99.39 244	99.38 251	97.70 218	99.28 201	99.28 333	98.34 93	99.85 168	96.96 320	99.45 165	99.69 130

API-MVS		99.04 129	99.03 102	99.06 200	99.40 232	99.31 123	99.55 147	99.56 80	98.54 107	99.33 191	99.39 303	98.76 55	99.78 216	96.98 318	99.78 121	98.07 396

mvs_anonymous		99.03 131	98.99 113	99.16 190	99.38 237	98.52 226	99.51 171	99.38 251	97.79 206	99.38 179	99.81 106	97.30 127	99.45 291	99.35 67	98.99 204	99.51 195

sasdasda		99.02 132	98.86 137	99.51 129	99.42 222	99.32 119	99.80 25	99.48 172	98.63 98	99.31 193	98.81 383	97.09 135	99.75 225	99.27 82	97.90 269	99.47 207

train_agg		99.02 132	98.77 148	99.77 65	99.67 123	99.65 67	99.05 343	99.41 233	96.28 344	98.95 272	99.49 271	98.76 55	99.91 123	97.63 269	99.72 135	99.75 98

canonicalmvs		99.02 132	98.86 137	99.51 129	99.42 222	99.32 119	99.80 25	99.48 172	98.63 98	99.31 193	98.81 383	97.09 135	99.75 225	99.27 82	97.90 269	99.47 207

PLC	97.94 4	99.02 132	98.85 139	99.53 120	99.66 133	99.01 164	99.24 302	99.52 115	96.85 304	99.27 206	99.48 277	98.25 97	99.91 123	97.76 257	99.62 152	99.65 144
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MGCFI-Net		99.01 136	98.85 139	99.50 134	99.42 222	99.26 131	99.82 16	99.48 172	98.60 102	99.28 201	98.81 383	97.04 139	99.76 222	99.29 79	97.87 272	99.47 207

AdaColmap		99.01 136	98.80 144	99.66 81	99.56 171	99.54 90	99.18 317	99.70 15	98.18 152	99.35 187	99.63 219	96.32 167	99.90 135	97.48 285	99.77 124	99.55 178

1112_ss		98.98 138	98.77 148	99.59 102	99.68 121	99.02 162	99.25 299	99.48 172	97.23 271	99.13 236	99.58 237	96.93 144	99.90 135	98.87 128	98.78 220	99.84 49

MSDG		98.98 138	98.80 144	99.53 120	99.76 72	99.19 137	98.75 390	99.55 88	97.25 268	99.47 153	99.77 147	97.82 112	99.87 159	96.93 323	99.90 50	99.54 180

CANet_DTU		98.97 140	98.87 135	99.25 179	99.33 249	98.42 238	99.08 337	99.30 298	99.16 29	99.43 163	99.75 154	95.27 209	99.97 24	98.56 182	99.95 19	99.36 230

DPM-MVS		98.95 141	98.71 154	99.66 81	99.63 145	99.55 88	98.64 401	99.10 331	97.93 188	99.42 166	99.55 248	98.67 69	99.80 208	95.80 357	99.68 143	99.61 160

114514_t		98.93 142	98.67 158	99.72 77	99.85 26	99.53 93	99.62 95	99.59 66	92.65 409	99.71 88	99.78 138	98.06 106	99.90 135	98.84 138	99.91 41	99.74 102

PS-MVSNAJss		98.92 143	98.92 126	98.90 227	98.78 365	98.53 222	99.78 32	99.54 97	98.07 171	99.00 264	99.76 151	99.01 18	99.37 309	99.13 94	97.23 312	98.81 282

RRT-MVS		98.91 144	98.75 150	99.39 153	99.46 212	98.61 216	99.76 37	99.50 150	98.06 175	99.81 54	99.88 44	93.91 278	99.94 81	99.11 96	99.27 180	99.61 160

Test_1112_low_res		98.89 145	98.66 161	99.57 107	99.69 116	98.95 176	99.03 348	99.47 193	96.98 294	99.15 234	99.23 341	96.77 148	99.89 148	98.83 141	98.78 220	99.86 38

test_fmvs1		98.88 146	98.79 147	99.16 190	99.69 116	97.61 283	99.55 147	99.49 160	99.32 23	99.98 10	99.91 23	91.41 341	99.96 36	99.82 25	99.92 34	99.90 22

AllTest		98.87 147	98.72 152	99.31 164	99.86 20	98.48 232	99.56 133	99.61 53	97.85 198	99.36 184	99.85 67	95.95 179	99.85 168	96.66 336	99.83 100	99.59 167

UGNet		98.87 147	98.69 156	99.40 149	99.22 282	98.72 204	99.44 215	99.68 20	99.24 26	99.18 231	99.42 291	92.74 303	99.96 36	99.34 72	99.94 27	99.53 186
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)		98.87 147	98.72 152	99.31 164	99.71 106	98.88 186	99.80 25	99.44 222	97.91 190	99.36 184	99.78 138	95.49 200	99.43 300	97.91 240	99.11 192	99.62 158

test_yl		98.86 150	98.63 164	99.54 112	99.49 202	99.18 139	99.50 179	99.07 337	98.22 145	99.61 125	99.51 265	95.37 204	99.84 175	98.60 173	98.33 244	99.59 167

DCV-MVSNet		98.86 150	98.63 164	99.54 112	99.49 202	99.18 139	99.50 179	99.07 337	98.22 145	99.61 125	99.51 265	95.37 204	99.84 175	98.60 173	98.33 244	99.59 167

EPNet		98.86 150	98.71 154	99.30 169	97.20 418	98.18 246	99.62 95	98.91 361	99.28 25	98.63 323	99.81 106	95.96 178	99.99 4	99.24 85	99.72 135	99.73 109
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		98.86 150	98.80 144	99.03 204	99.76 72	98.79 199	99.28 283	99.91 3	97.42 254	99.67 98	99.37 308	97.53 118	99.88 153	98.98 111	97.29 310	98.42 374

ab-mvs		98.86 150	98.63 164	99.54 112	99.64 142	99.19 137	99.44 215	99.54 97	97.77 209	99.30 197	99.81 106	94.20 264	99.93 99	99.17 92	98.82 217	99.49 200

MAR-MVS		98.86 150	98.63 164	99.54 112	99.37 240	99.66 63	99.45 209	99.54 97	96.61 321	99.01 260	99.40 299	97.09 135	99.86 162	97.68 268	99.53 160	99.10 253
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	98.86 150	98.75 150	99.17 189	99.88 11	98.53 222	99.34 264	99.59 66	97.55 235	98.70 311	99.89 36	95.83 186	99.90 135	98.10 223	99.90 50	99.08 258
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GeoE		98.85 157	98.62 169	99.53 120	99.61 156	99.08 155	99.80 25	99.51 130	97.10 284	99.31 193	99.78 138	95.23 213	99.77 218	98.21 215	99.03 201	99.75 98

HY-MVS	97.30 7	98.85 157	98.64 163	99.47 139	99.42 222	99.08 155	99.62 95	99.36 260	97.39 257	99.28 201	99.68 194	96.44 164	99.92 111	98.37 201	98.22 253	99.40 224

PVSNet	96.02 17	98.85 157	98.84 141	98.89 230	99.73 97	97.28 293	98.32 418	99.60 60	97.86 195	99.50 148	99.57 242	96.75 149	99.86 162	98.56 182	99.70 139	99.54 180

PatchMatch-RL		98.84 160	98.62 169	99.52 126	99.71 106	99.28 128	99.06 341	99.77 9	97.74 213	99.50 148	99.53 257	95.41 202	99.84 175	97.17 309	99.64 149	99.44 217

Effi-MVS+		98.81 161	98.59 175	99.48 135	99.46 212	99.12 150	98.08 425	99.50 150	97.50 243	99.38 179	99.41 295	96.37 166	99.81 201	99.11 96	98.54 234	99.51 195

alignmvs		98.81 161	98.56 178	99.58 105	99.43 220	99.42 109	99.51 171	98.96 351	98.61 101	99.35 187	98.92 378	94.78 233	99.77 218	99.35 67	98.11 263	99.54 180

DeepPCF-MVS	98.18 3	98.81 161	99.37 39	97.12 377	99.60 161	91.75 417	98.61 402	99.44 222	99.35 21	99.83 52	99.85 67	98.70 66	99.81 201	99.02 108	99.91 41	99.81 71

PMMVS		98.80 164	98.62 169	99.34 157	99.27 267	98.70 205	98.76 389	99.31 293	97.34 260	99.21 221	99.07 357	97.20 132	99.82 196	98.56 182	98.87 212	99.52 187

Effi-MVS+-dtu		98.78 165	98.89 132	98.47 288	99.33 249	96.91 322	99.57 126	99.30 298	98.47 113	99.41 170	98.99 368	96.78 147	99.74 227	98.73 152	99.38 169	98.74 297

FIs		98.78 165	98.63 164	99.23 184	99.18 291	99.54 90	99.83 15	99.59 66	98.28 135	98.79 298	99.81 106	96.75 149	99.37 309	99.08 101	96.38 328	98.78 285

Fast-Effi-MVS+-dtu		98.77 167	98.83 143	98.60 267	99.41 227	96.99 316	99.52 162	99.49 160	98.11 163	99.24 213	99.34 318	96.96 143	99.79 211	97.95 238	99.45 165	99.02 268

sd_testset		98.75 168	98.57 176	99.29 172	99.81 48	98.26 243	99.56 133	99.62 45	98.78 87	99.64 115	99.88 44	92.02 325	99.88 153	99.54 46	98.26 250	99.72 117

FA-MVS(test-final)		98.75 168	98.53 180	99.41 148	99.55 175	99.05 160	99.80 25	99.01 345	96.59 326	99.58 132	99.59 233	95.39 203	99.90 135	97.78 253	99.49 163	99.28 239

FC-MVSNet-test		98.75 168	98.62 169	99.15 194	99.08 318	99.45 106	99.86 11	99.60 60	98.23 144	98.70 311	99.82 92	96.80 146	99.22 340	99.07 102	96.38 328	98.79 283

XVG-OURS		98.73 171	98.68 157	98.88 232	99.70 111	97.73 274	98.92 373	99.55 88	98.52 109	99.45 156	99.84 78	95.27 209	99.91 123	98.08 228	98.84 215	99.00 269

Fast-Effi-MVS+		98.70 172	98.43 184	99.51 129	99.51 188	99.28 128	99.52 162	99.47 193	96.11 360	99.01 260	99.34 318	96.20 171	99.84 175	97.88 242	98.82 217	99.39 225

XVG-OURS-SEG-HR		98.69 173	98.62 169	98.89 230	99.71 106	97.74 273	99.12 328	99.54 97	98.44 119	99.42 166	99.71 172	94.20 264	99.92 111	98.54 186	98.90 211	99.00 269

1314		98.68 174	98.54 179	99.11 196	98.89 348	98.65 209	99.27 288	99.49 160	96.89 302	97.99 362	99.56 245	97.72 116	99.83 188	97.74 260	99.27 180	98.84 281

VortexMVS		98.67 175	98.66 161	98.68 262	99.62 151	97.96 261	99.59 109	99.41 233	98.13 159	99.31 193	99.70 176	95.48 201	99.27 329	99.40 63	97.32 309	98.79 283

EI-MVSNet		98.67 175	98.67 158	98.68 262	99.35 244	97.97 259	99.50 179	99.38 251	96.93 301	99.20 224	99.83 83	97.87 110	99.36 313	98.38 199	97.56 288	98.71 301

test_djsdf		98.67 175	98.57 176	98.98 210	98.70 379	98.91 184	99.88 4	99.46 202	97.55 235	99.22 218	99.88 44	95.73 191	99.28 326	99.03 106	97.62 283	98.75 293

QAPM		98.67 175	98.30 194	99.80 56	99.20 285	99.67 60	99.77 34	99.72 11	94.74 387	98.73 303	99.90 30	95.78 189	99.98 15	96.96 320	99.88 65	99.76 97

nrg030		98.64 179	98.42 185	99.28 176	99.05 324	99.69 55	99.81 20	99.46 202	98.04 178	99.01 260	99.82 92	96.69 151	99.38 306	99.34 72	94.59 373	98.78 285

test_vis1_n_1920		98.63 180	98.40 187	99.31 164	99.86 20	97.94 266	99.67 69	99.62 45	99.43 13	99.99 2	99.91 23	87.29 392	100.00 1	99.92 20	99.92 34	99.98 2

PAPR		98.63 180	98.34 190	99.51 129	99.40 232	99.03 161	98.80 385	99.36 260	96.33 341	99.00 264	99.12 355	98.46 84	99.84 175	95.23 372	99.37 176	99.66 140

CVMVSNet		98.57 182	98.67 158	98.30 308	99.35 244	95.59 364	99.50 179	99.55 88	98.60 102	99.39 177	99.83 83	94.48 255	99.45 291	98.75 149	98.56 232	99.85 42

MVSTER		98.49 183	98.32 192	99.00 208	99.35 244	99.02 162	99.54 152	99.38 251	97.41 255	99.20 224	99.73 165	93.86 280	99.36 313	98.87 128	97.56 288	98.62 345

FE-MVS		98.48 184	98.17 199	99.40 149	99.54 178	98.96 173	99.68 66	98.81 375	95.54 371	99.62 122	99.70 176	93.82 281	99.93 99	97.35 296	99.46 164	99.32 236

OpenMVS	96.50 16	98.47 185	98.12 206	99.52 126	99.04 326	99.53 93	99.82 16	99.72 11	94.56 390	98.08 357	99.88 44	94.73 239	99.98 15	97.47 287	99.76 127	99.06 264

IterMVS-LS		98.46 186	98.42 185	98.58 271	99.59 163	98.00 257	99.37 251	99.43 228	96.94 300	99.07 249	99.59 233	97.87 110	99.03 369	98.32 208	95.62 351	98.71 301
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		98.44 187	98.28 195	98.94 217	98.50 395	98.96 173	99.77 34	99.50 150	97.07 286	98.87 285	99.77 147	94.76 237	99.28 326	98.66 162	97.60 284	98.57 360

jajsoiax		98.43 188	98.28 195	98.88 232	98.60 389	98.43 236	99.82 16	99.53 110	98.19 149	98.63 323	99.80 119	93.22 292	99.44 296	99.22 86	97.50 295	98.77 289

tttt0517		98.42 189	98.14 203	99.28 176	99.66 133	98.38 239	99.74 46	96.85 425	97.68 220	99.79 60	99.74 159	91.39 342	99.89 148	98.83 141	99.56 157	99.57 174

BH-untuned		98.42 189	98.36 188	98.59 268	99.49 202	96.70 330	99.27 288	99.13 329	97.24 270	98.80 296	99.38 305	95.75 190	99.74 227	97.07 314	99.16 186	99.33 235

test_fmvs1_n		98.41 191	98.14 203	99.21 185	99.82 44	97.71 279	99.74 46	99.49 160	99.32 23	99.99 2	99.95 3	85.32 405	99.97 24	99.82 25	99.84 91	99.96 7

D2MVS		98.41 191	98.50 181	98.15 323	99.26 270	96.62 336	99.40 240	99.61 53	97.71 215	98.98 267	99.36 311	96.04 175	99.67 257	98.70 155	97.41 305	98.15 392

BH-RMVSNet		98.41 191	98.08 212	99.40 149	99.41 227	98.83 195	99.30 273	98.77 381	97.70 218	98.94 274	99.65 207	92.91 299	99.74 227	96.52 340	99.55 159	99.64 151

mvs_tets		98.40 194	98.23 197	98.91 225	98.67 382	98.51 228	99.66 75	99.53 110	98.19 149	98.65 320	99.81 106	92.75 301	99.44 296	99.31 76	97.48 299	98.77 289

MonoMVSNet		98.38 195	98.47 183	98.12 325	98.59 391	96.19 353	99.72 52	98.79 379	97.89 192	99.44 161	99.52 261	96.13 172	98.90 391	98.64 164	97.54 290	99.28 239

XXY-MVS		98.38 195	98.09 211	99.24 182	99.26 270	99.32 119	99.56 133	99.55 88	97.45 248	98.71 305	99.83 83	93.23 290	99.63 274	98.88 125	96.32 330	98.76 291

ACMM	97.58 5	98.37 197	98.34 190	98.48 283	99.41 227	97.10 303	99.56 133	99.45 213	98.53 108	99.04 257	99.85 67	93.00 295	99.71 243	98.74 150	97.45 300	98.64 336
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thisisatest0530		98.35 198	98.03 218	99.31 164	99.63 145	98.56 219	99.54 152	96.75 427	97.53 239	99.73 81	99.65 207	91.25 346	99.89 148	98.62 167	99.56 157	99.48 201

tpmrst		98.33 199	98.48 182	97.90 342	99.16 301	94.78 386	99.31 271	99.11 330	97.27 266	99.45 156	99.59 233	95.33 207	99.84 175	98.48 189	98.61 226	99.09 257

baseline1		98.31 200	97.95 227	99.38 154	99.50 200	98.74 202	99.59 109	98.93 353	98.41 121	99.14 235	99.60 231	94.59 248	99.79 211	98.48 189	93.29 393	99.61 160

PatchmatchNet		98.31 200	98.36 188	98.19 318	99.16 301	95.32 375	99.27 288	98.92 356	97.37 258	99.37 181	99.58 237	94.90 226	99.70 249	97.43 291	99.21 183	99.54 180
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous202405211		98.30 202	97.98 223	99.26 178	99.57 167	98.16 247	99.41 232	98.55 400	96.03 365	99.19 227	99.74 159	91.87 328	99.92 111	99.16 93	98.29 249	99.70 128

VPA-MVSNet		98.29 203	97.95 227	99.30 169	99.16 301	99.54 90	99.50 179	99.58 70	98.27 137	99.35 187	99.37 308	92.53 313	99.65 265	99.35 67	94.46 374	98.72 299

UniMVSNet (Re)		98.29 203	98.00 221	99.13 195	99.00 331	99.36 116	99.49 191	99.51 130	97.95 186	98.97 269	99.13 352	96.30 168	99.38 306	98.36 203	93.34 392	98.66 332

HQP_MVS		98.27 205	98.22 198	98.44 294	99.29 262	96.97 318	99.39 244	99.47 193	98.97 64	99.11 240	99.61 228	92.71 306	99.69 254	97.78 253	97.63 281	98.67 323

UniMVSNet_NR-MVSNet		98.22 206	97.97 224	98.96 213	98.92 344	98.98 166	99.48 196	99.53 110	97.76 210	98.71 305	99.46 284	96.43 165	99.22 340	98.57 179	92.87 400	98.69 310

LPG-MVS_test		98.22 206	98.13 205	98.49 281	99.33 249	97.05 309	99.58 119	99.55 88	97.46 245	99.24 213	99.83 83	92.58 311	99.72 237	98.09 224	97.51 293	98.68 315

RPSCF		98.22 206	98.62 169	96.99 379	99.82 44	91.58 418	99.72 52	99.44 222	96.61 321	99.66 103	99.89 36	95.92 182	99.82 196	97.46 288	99.10 195	99.57 174

ADS-MVSNet		98.20 209	98.08 212	98.56 275	99.33 249	96.48 341	99.23 305	99.15 326	96.24 348	99.10 243	99.67 200	94.11 268	99.71 243	96.81 328	99.05 199	99.48 201

OPM-MVS		98.19 210	98.10 208	98.45 291	98.88 349	97.07 307	99.28 283	99.38 251	98.57 104	99.22 218	99.81 106	92.12 323	99.66 260	98.08 228	97.54 290	98.61 354
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SCA		98.19 210	98.16 200	98.27 314	99.30 258	95.55 365	99.07 338	98.97 349	97.57 232	99.43 163	99.57 242	92.72 304	99.74 227	97.58 273	99.20 184	99.52 187

miper_ehance_all_eth		98.18 212	98.10 208	98.41 297	99.23 278	97.72 276	98.72 393	99.31 293	96.60 324	98.88 282	99.29 331	97.29 128	99.13 355	97.60 271	95.99 339	98.38 379

CR-MVSNet		98.17 213	97.93 230	98.87 236	99.18 291	98.49 230	99.22 309	99.33 279	96.96 296	99.56 136	99.38 305	94.33 260	99.00 374	94.83 379	98.58 229	99.14 250

miper_enhance_ethall		98.16 214	98.08 212	98.41 297	98.96 340	97.72 276	98.45 411	99.32 289	96.95 298	98.97 269	99.17 347	97.06 138	99.22 340	97.86 245	95.99 339	98.29 383

CLD-MVS		98.16 214	98.10 208	98.33 304	99.29 262	96.82 327	98.75 390	99.44 222	97.83 201	99.13 236	99.55 248	92.92 297	99.67 257	98.32 208	97.69 279	98.48 366
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		98.14 216	97.79 242	99.19 187	99.50 200	98.50 229	98.61 402	96.82 426	96.95 298	99.54 141	99.43 289	91.66 337	99.86 162	98.08 228	99.51 161	99.22 247

pmmvs4		98.13 217	97.90 232	98.81 248	98.61 388	98.87 187	98.99 359	99.21 319	96.44 336	99.06 254	99.58 237	95.90 184	99.11 360	97.18 308	96.11 335	98.46 371

WR-MVS_H		98.13 217	97.87 237	98.90 227	99.02 328	98.84 192	99.70 56	99.59 66	97.27 266	98.40 339	99.19 346	95.53 198	99.23 336	98.34 205	93.78 388	98.61 354

c3_l		98.12 219	98.04 217	98.38 301	99.30 258	97.69 280	98.81 384	99.33 279	96.67 314	98.83 291	99.34 318	97.11 134	98.99 375	97.58 273	95.34 358	98.48 366

ACMH	97.28 8	98.10 220	97.99 222	98.44 294	99.41 227	96.96 320	99.60 102	99.56 80	98.09 166	98.15 355	99.91 23	90.87 350	99.70 249	98.88 125	97.45 300	98.67 323
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		98.09 221	97.68 259	99.34 157	99.66 133	98.44 235	99.40 240	99.43 228	93.67 397	99.22 218	99.89 36	90.23 358	99.93 99	99.26 84	98.33 244	99.66 140

CP-MVSNet		98.09 221	97.78 245	99.01 206	98.97 339	99.24 134	99.67 69	99.46 202	97.25 268	98.48 336	99.64 213	93.79 282	99.06 365	98.63 166	94.10 382	98.74 297

dmvs_re		98.08 223	98.16 200	97.85 346	99.55 175	94.67 390	99.70 56	98.92 356	98.15 154	99.06 254	99.35 314	93.67 286	99.25 333	97.77 256	97.25 311	99.64 151

DU-MVS		98.08 223	97.79 242	98.96 213	98.87 352	98.98 166	99.41 232	99.45 213	97.87 194	98.71 305	99.50 268	94.82 229	99.22 340	98.57 179	92.87 400	98.68 315

v2v482		98.06 225	97.77 247	98.92 221	98.90 347	98.82 196	99.57 126	99.36 260	96.65 316	99.19 227	99.35 314	94.20 264	99.25 333	97.72 263	94.97 366	98.69 310

V42		98.06 225	97.79 242	98.86 239	98.98 337	98.84 192	99.69 60	99.34 272	96.53 328	99.30 197	99.37 308	94.67 244	99.32 321	97.57 277	94.66 371	98.42 374

test-LLR		98.06 225	97.90 232	98.55 277	98.79 362	97.10 303	98.67 396	97.75 416	97.34 260	98.61 326	98.85 380	94.45 257	99.45 291	97.25 300	99.38 169	99.10 253

WR-MVS		98.06 225	97.73 254	99.06 200	98.86 355	99.25 133	99.19 315	99.35 267	97.30 264	98.66 314	99.43 289	93.94 275	99.21 345	98.58 176	94.28 378	98.71 301

ACMP	97.20 11	98.06 225	97.94 229	98.45 291	99.37 240	97.01 314	99.44 215	99.49 160	97.54 238	98.45 337	99.79 131	91.95 327	99.72 237	97.91 240	97.49 298	98.62 345
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
eth_miper_zixun_eth		98.05 230	97.96 225	98.33 304	99.26 270	97.38 290	98.56 407	99.31 293	96.65 316	98.88 282	99.52 261	96.58 156	99.12 359	97.39 293	95.53 355	98.47 368

test1111		98.04 231	98.11 207	97.83 349	99.74 90	93.82 401	99.58 119	95.40 434	99.12 38	99.65 110	99.93 10	90.73 351	99.84 175	99.43 62	99.38 169	99.82 64

ECVR-MVS		98.04 231	98.05 216	98.00 333	99.74 90	94.37 396	99.59 109	94.98 435	99.13 33	99.66 103	99.93 10	90.67 352	99.84 175	99.40 63	99.38 169	99.80 80

EPNet_dtu		98.03 233	97.96 225	98.23 316	98.27 400	95.54 367	99.23 305	98.75 382	99.02 51	97.82 371	99.71 172	96.11 173	99.48 286	93.04 400	99.65 148	99.69 130
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet3		98.03 233	97.76 251	98.84 243	99.39 235	98.98 166	99.40 240	99.38 251	96.67 314	99.07 249	99.28 333	92.93 296	98.98 376	97.10 310	96.65 321	98.56 361

ADS-MVSNet2		98.02 235	98.07 215	97.87 344	99.33 249	95.19 378	99.23 305	99.08 334	96.24 348	99.10 243	99.67 200	94.11 268	98.93 388	96.81 328	99.05 199	99.48 201

HQP-MVS		98.02 235	97.90 232	98.37 302	99.19 288	96.83 325	98.98 362	99.39 243	98.24 141	98.66 314	99.40 299	92.47 315	99.64 268	97.19 306	97.58 286	98.64 336

LTVRE_ROB	97.16 12	98.02 235	97.90 232	98.40 299	99.23 278	96.80 328	99.70 56	99.60 60	97.12 280	98.18 354	99.70 176	91.73 333	99.72 237	98.39 198	97.45 300	98.68 315
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____		98.01 238	97.84 240	98.55 277	99.25 274	97.97 259	98.71 394	99.34 272	96.47 335	98.59 329	99.54 253	95.65 194	99.21 345	97.21 302	95.77 345	98.46 371

DIV-MVS_self_test		98.01 238	97.85 239	98.48 283	99.24 276	97.95 264	98.71 394	99.35 267	96.50 329	98.60 328	99.54 253	95.72 192	99.03 369	97.21 302	95.77 345	98.46 371

miper_lstm_enhance		98.00 240	97.91 231	98.28 313	99.34 248	97.43 288	98.88 377	99.36 260	96.48 333	98.80 296	99.55 248	95.98 177	98.91 389	97.27 299	95.50 356	98.51 364

BH-w/o		98.00 240	97.89 236	98.32 306	99.35 244	96.20 352	99.01 356	98.90 363	96.42 338	98.38 340	99.00 366	95.26 211	99.72 237	96.06 350	98.61 226	99.03 266

v1144		97.98 242	97.69 258	98.85 242	98.87 352	98.66 208	99.54 152	99.35 267	96.27 346	99.23 217	99.35 314	94.67 244	99.23 336	96.73 331	95.16 362	98.68 315

EU-MVSNet		97.98 242	98.03 218	97.81 352	98.72 376	96.65 335	99.66 75	99.66 28	98.09 166	98.35 342	99.82 92	95.25 212	98.01 412	97.41 292	95.30 359	98.78 285

tpmvs		97.98 242	98.02 220	97.84 348	99.04 326	94.73 387	99.31 271	99.20 320	96.10 364	98.76 301	99.42 291	94.94 222	99.81 201	96.97 319	98.45 238	98.97 273

tt0805		97.97 245	97.77 247	98.57 272	99.59 163	96.61 337	99.45 209	99.08 334	98.21 147	98.88 282	99.80 119	88.66 376	99.70 249	98.58 176	97.72 278	99.39 225

NR-MVSNet		97.97 245	97.61 268	99.02 205	98.87 352	99.26 131	99.47 204	99.42 230	97.63 225	97.08 390	99.50 268	95.07 218	99.13 355	97.86 245	93.59 389	98.68 315

v8		97.95 247	97.63 266	98.93 219	98.95 341	98.81 198	99.80 25	99.41 233	96.03 365	99.10 243	99.42 291	94.92 225	99.30 324	96.94 322	94.08 383	98.66 332

Patchmatch-test		97.93 248	97.65 262	98.77 253	99.18 291	97.07 307	99.03 348	99.14 328	96.16 355	98.74 302	99.57 242	94.56 250	99.72 237	93.36 396	99.11 192	99.52 187

PS-CasMVS		97.93 248	97.59 270	98.95 215	98.99 334	99.06 158	99.68 66	99.52 115	97.13 278	98.31 344	99.68 194	92.44 319	99.05 366	98.51 187	94.08 383	98.75 293

TranMVSNet+NR-MVSNet		97.93 248	97.66 261	98.76 254	98.78 365	98.62 214	99.65 81	99.49 160	97.76 210	98.49 335	99.60 231	94.23 263	98.97 383	98.00 235	92.90 398	98.70 306

test_vis1_n		97.92 251	97.44 291	99.34 157	99.53 179	98.08 253	99.74 46	99.49 160	99.15 30	100.00 1	99.94 6	79.51 427	99.98 15	99.88 22	99.76 127	99.97 4

v144192		97.92 251	97.60 269	98.87 236	98.83 359	98.65 209	99.55 147	99.34 272	96.20 351	99.32 192	99.40 299	94.36 259	99.26 332	96.37 347	95.03 365	98.70 306

ACMH+	97.24 10	97.92 251	97.78 245	98.32 306	99.46 212	96.68 334	99.56 133	99.54 97	98.41 121	97.79 373	99.87 55	90.18 359	99.66 260	98.05 232	97.18 315	98.62 345

LFMVS		97.90 254	97.35 303	99.54 112	99.52 185	99.01 164	99.39 244	98.24 407	97.10 284	99.65 110	99.79 131	84.79 408	99.91 123	99.28 80	98.38 241	99.69 130

reproduce_monomvs		97.89 255	97.87 237	97.96 337	99.51 188	95.45 370	99.60 102	99.25 310	99.17 28	98.85 290	99.49 271	89.29 368	99.64 268	99.35 67	96.31 331	98.78 285

Anonymous20231211		97.88 256	97.54 274	98.90 227	99.71 106	98.53 222	99.48 196	99.57 75	94.16 393	98.81 294	99.68 194	93.23 290	99.42 302	98.84 138	94.42 376	98.76 291

OurMVSNet-221017-0		97.88 256	97.77 247	98.19 318	98.71 378	96.53 339	99.88 4	99.00 346	97.79 206	98.78 299	99.94 6	91.68 334	99.35 316	97.21 302	96.99 319	98.69 310

v7n		97.87 258	97.52 275	98.92 221	98.76 372	98.58 218	99.84 12	99.46 202	96.20 351	98.91 277	99.70 176	94.89 227	99.44 296	96.03 351	93.89 386	98.75 293

baseline2		97.87 258	97.55 271	98.82 245	99.18 291	98.02 256	99.41 232	96.58 431	96.97 295	96.51 397	99.17 347	93.43 287	99.57 279	97.71 264	99.03 201	98.86 279

thres600view7		97.86 260	97.51 277	98.92 221	99.72 101	97.95 264	99.59 109	98.74 385	97.94 187	99.27 206	98.62 391	91.75 331	99.86 162	93.73 392	98.19 257	98.96 275

UBG		97.85 261	97.48 280	98.95 215	99.25 274	97.64 281	99.24 302	98.74 385	97.90 191	98.64 321	98.20 408	88.65 377	99.81 201	98.27 211	98.40 239	99.42 219

cl22		97.85 261	97.64 265	98.48 283	99.09 315	97.87 268	98.60 404	99.33 279	97.11 283	98.87 285	99.22 342	92.38 320	99.17 349	98.21 215	95.99 339	98.42 374

v10		97.85 261	97.52 275	98.86 239	98.99 334	98.67 207	99.75 42	99.41 233	95.70 369	98.98 267	99.41 295	94.75 238	99.23 336	96.01 353	94.63 372	98.67 323

GA-MVS		97.85 261	97.47 283	99.00 208	99.38 237	97.99 258	98.57 405	99.15 326	97.04 291	98.90 279	99.30 329	89.83 362	99.38 306	96.70 333	98.33 244	99.62 158

testing3-2		97.84 265	97.70 257	98.24 315	99.53 179	95.37 374	99.55 147	98.67 395	98.46 114	99.27 206	99.34 318	86.58 396	99.83 188	99.32 75	98.63 225	99.52 187

tfpnnormal		97.84 265	97.47 283	98.98 210	99.20 285	99.22 136	99.64 84	99.61 53	96.32 342	98.27 348	99.70 176	93.35 289	99.44 296	95.69 360	95.40 357	98.27 384

VPNet		97.84 265	97.44 291	99.01 206	99.21 283	98.94 179	99.48 196	99.57 75	98.38 123	99.28 201	99.73 165	88.89 371	99.39 304	99.19 88	93.27 394	98.71 301

LCM-MVSNet-Re		97.83 268	98.15 202	96.87 385	99.30 258	92.25 415	99.59 109	98.26 405	97.43 252	96.20 401	99.13 352	96.27 169	98.73 398	98.17 220	98.99 204	99.64 151

XVG-ACMP-BASELINE		97.83 268	97.71 256	98.20 317	99.11 309	96.33 346	99.41 232	99.52 115	98.06 175	99.05 256	99.50 268	89.64 365	99.73 233	97.73 261	97.38 307	98.53 362

IterMVS		97.83 268	97.77 247	98.02 330	99.58 165	96.27 349	99.02 351	99.48 172	97.22 272	98.71 305	99.70 176	92.75 301	99.13 355	97.46 288	96.00 338	98.67 323
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.82 271	97.75 252	98.06 327	99.57 167	96.36 345	99.02 351	99.49 160	97.18 274	98.71 305	99.72 169	92.72 304	99.14 352	97.44 290	95.86 344	98.67 323

EPMVS		97.82 271	97.65 262	98.35 303	98.88 349	95.98 356	99.49 191	94.71 437	97.57 232	99.26 211	99.48 277	92.46 318	99.71 243	97.87 244	99.08 197	99.35 231

MVP-Stereo		97.81 273	97.75 252	97.99 334	97.53 411	96.60 338	98.96 366	98.85 370	97.22 272	97.23 384	99.36 311	95.28 208	99.46 289	95.51 364	99.78 121	97.92 409
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		97.81 273	97.44 291	98.91 225	98.88 349	98.68 206	99.51 171	99.34 272	96.18 353	99.20 224	99.34 318	94.03 272	99.36 313	95.32 370	95.18 361	98.69 310

ttmdpeth		97.80 275	97.63 266	98.29 309	98.77 370	97.38 290	99.64 84	99.36 260	98.78 87	96.30 400	99.58 237	92.34 322	99.39 304	98.36 203	95.58 352	98.10 394

v1921920		97.80 275	97.45 286	98.84 243	98.80 361	98.53 222	99.52 162	99.34 272	96.15 357	99.24 213	99.47 280	93.98 274	99.29 325	95.40 368	95.13 363	98.69 310

v148		97.79 277	97.55 271	98.50 280	98.74 373	97.72 276	99.54 152	99.33 279	96.26 347	98.90 279	99.51 265	94.68 243	99.14 352	97.83 249	93.15 397	98.63 343

thres400		97.77 278	97.38 299	98.92 221	99.69 116	97.96 261	99.50 179	98.73 391	97.83 201	99.17 232	98.45 398	91.67 335	99.83 188	93.22 397	98.18 258	98.96 275

thres100view900		97.76 279	97.45 286	98.69 261	99.72 101	97.86 270	99.59 109	98.74 385	97.93 188	99.26 211	98.62 391	91.75 331	99.83 188	93.22 397	98.18 258	98.37 380

PEN-MVS		97.76 279	97.44 291	98.72 257	98.77 370	98.54 221	99.78 32	99.51 130	97.06 288	98.29 347	99.64 213	92.63 310	98.89 392	98.09 224	93.16 396	98.72 299

Baseline_NR-MVSNet		97.76 279	97.45 286	98.68 262	99.09 315	98.29 241	99.41 232	98.85 370	95.65 370	98.63 323	99.67 200	94.82 229	99.10 362	98.07 231	92.89 399	98.64 336

TR-MVS		97.76 279	97.41 297	98.82 245	99.06 321	97.87 268	98.87 379	98.56 399	96.63 320	98.68 313	99.22 342	92.49 314	99.65 265	95.40 368	97.79 276	98.95 277

Patchmtry		97.75 283	97.40 298	98.81 248	99.10 312	98.87 187	99.11 334	99.33 279	94.83 385	98.81 294	99.38 305	94.33 260	99.02 371	96.10 349	95.57 353	98.53 362

dp		97.75 283	97.80 241	97.59 364	99.10 312	93.71 404	99.32 268	98.88 366	96.48 333	99.08 248	99.55 248	92.67 309	99.82 196	96.52 340	98.58 229	99.24 245

WBMVS		97.74 285	97.50 278	98.46 289	99.24 276	97.43 288	99.21 311	99.42 230	97.45 248	98.96 271	99.41 295	88.83 372	99.23 336	98.94 116	96.02 336	98.71 301

TAPA-MVS	97.07 15	97.74 285	97.34 306	98.94 217	99.70 111	97.53 284	99.25 299	99.51 130	91.90 411	99.30 197	99.63 219	98.78 51	99.64 268	88.09 423	99.87 68	99.65 144
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.73 287	97.35 303	98.88 232	99.47 210	97.12 302	99.34 264	98.85 370	98.19 149	99.67 98	99.85 67	82.98 416	99.92 111	99.49 56	98.32 248	99.60 163

MIMVSNet		97.73 287	97.45 286	98.57 272	99.45 218	97.50 286	99.02 351	98.98 348	96.11 360	99.41 170	99.14 351	90.28 354	98.74 397	95.74 358	98.93 207	99.47 207

tfpn200view9		97.72 289	97.38 299	98.72 257	99.69 116	97.96 261	99.50 179	98.73 391	97.83 201	99.17 232	98.45 398	91.67 335	99.83 188	93.22 397	98.18 258	98.37 380

CostFormer		97.72 289	97.73 254	97.71 357	99.15 305	94.02 400	99.54 152	99.02 344	94.67 388	99.04 257	99.35 314	92.35 321	99.77 218	98.50 188	97.94 268	99.34 234

FMVSNet2		97.72 289	97.36 301	98.80 250	99.51 188	98.84 192	99.45 209	99.42 230	96.49 330	98.86 289	99.29 331	90.26 355	98.98 376	96.44 342	96.56 324	98.58 359

test0.0.03 1		97.71 292	97.42 296	98.56 275	98.41 399	97.82 271	98.78 387	98.63 397	97.34 260	98.05 361	98.98 370	94.45 257	98.98 376	95.04 375	97.15 316	98.89 278

h-mvs33		97.70 293	97.28 315	98.97 212	99.70 111	97.27 294	99.36 256	99.45 213	98.94 67	99.66 103	99.64 213	94.93 223	99.99 4	99.48 57	84.36 426	99.65 144

myMVS_eth3d28		97.69 294	97.34 306	98.73 255	99.27 267	97.52 285	99.33 266	98.78 380	98.03 180	98.82 293	98.49 396	86.64 395	99.46 289	98.44 195	98.24 252	99.23 246

v1240		97.69 294	97.32 310	98.79 251	98.85 356	98.43 236	99.48 196	99.36 260	96.11 360	99.27 206	99.36 311	93.76 284	99.24 335	94.46 382	95.23 360	98.70 306

cascas		97.69 294	97.43 295	98.48 283	98.60 389	97.30 292	98.18 423	99.39 243	92.96 405	98.41 338	98.78 387	93.77 283	99.27 329	98.16 221	98.61 226	98.86 279

pm-mvs1		97.68 297	97.28 315	98.88 232	99.06 321	98.62 214	99.50 179	99.45 213	96.32 342	97.87 369	99.79 131	92.47 315	99.35 316	97.54 280	93.54 390	98.67 323

GBi-Net		97.68 297	97.48 280	98.29 309	99.51 188	97.26 296	99.43 220	99.48 172	96.49 330	99.07 249	99.32 326	90.26 355	98.98 376	97.10 310	96.65 321	98.62 345

test1		97.68 297	97.48 280	98.29 309	99.51 188	97.26 296	99.43 220	99.48 172	96.49 330	99.07 249	99.32 326	90.26 355	98.98 376	97.10 310	96.65 321	98.62 345

tpm		97.67 300	97.55 271	98.03 328	99.02 328	95.01 382	99.43 220	98.54 401	96.44 336	99.12 238	99.34 318	91.83 330	99.60 277	97.75 259	96.46 326	99.48 201

PCF-MVS	97.08 14	97.66 301	97.06 328	99.47 139	99.61 156	99.09 152	98.04 426	99.25 310	91.24 414	98.51 333	99.70 176	94.55 252	99.91 123	92.76 405	99.85 83	99.42 219
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		97.65 302	97.65 262	97.63 360	98.78 365	97.62 282	99.13 325	98.33 404	97.36 259	99.07 249	98.94 374	95.64 195	99.15 350	92.95 401	98.68 224	96.12 428

our_test_3		97.65 302	97.68 259	97.55 365	98.62 386	94.97 383	98.84 381	99.30 298	96.83 307	98.19 353	99.34 318	97.01 141	99.02 371	95.00 376	96.01 337	98.64 336

testgi		97.65 302	97.50 278	98.13 324	99.36 243	96.45 342	99.42 227	99.48 172	97.76 210	97.87 369	99.45 286	91.09 347	98.81 394	94.53 381	98.52 235	99.13 252

thres200		97.61 305	97.28 315	98.62 266	99.64 142	98.03 255	99.26 297	98.74 385	97.68 220	99.09 246	98.32 404	91.66 337	99.81 201	92.88 402	98.22 253	98.03 399

PAPM		97.59 306	97.09 327	99.07 198	99.06 321	98.26 243	98.30 419	99.10 331	94.88 383	98.08 357	99.34 318	96.27 169	99.64 268	89.87 416	98.92 209	99.31 237

UWE-MVS		97.58 307	97.29 314	98.48 283	99.09 315	96.25 350	99.01 356	96.61 430	97.86 195	99.19 227	99.01 365	88.72 373	99.90 135	97.38 294	98.69 223	99.28 239

VDDNet		97.55 308	97.02 329	99.16 190	99.49 202	98.12 252	99.38 249	99.30 298	95.35 373	99.68 94	99.90 30	82.62 418	99.93 99	99.31 76	98.13 262	99.42 219

TESTMET0.1,1		97.55 308	97.27 318	98.40 299	98.93 342	96.53 339	98.67 396	97.61 419	96.96 296	98.64 321	99.28 333	88.63 379	99.45 291	97.30 298	99.38 169	99.21 248

pmmvs5		97.52 310	97.30 312	98.16 320	98.57 392	96.73 329	99.27 288	98.90 363	96.14 358	98.37 341	99.53 257	91.54 340	99.14 352	97.51 282	95.87 343	98.63 343

LF4IMVS		97.52 310	97.46 285	97.70 358	98.98 337	95.55 365	99.29 278	98.82 373	98.07 171	98.66 314	99.64 213	89.97 360	99.61 276	97.01 315	96.68 320	97.94 407

DTE-MVSNet		97.51 312	97.19 321	98.46 289	98.63 385	98.13 250	99.84 12	99.48 172	96.68 313	97.97 364	99.67 200	92.92 297	98.56 401	96.88 327	92.60 404	98.70 306

testing11		97.50 313	97.10 326	98.71 259	99.20 285	96.91 322	99.29 278	98.82 373	97.89 192	98.21 352	98.40 400	85.63 402	99.83 188	98.45 194	98.04 265	99.37 229

ETVMVS		97.50 313	96.90 333	99.29 172	99.23 278	98.78 201	99.32 268	98.90 363	97.52 241	98.56 330	98.09 414	84.72 409	99.69 254	97.86 245	97.88 271	99.39 225

hse-mvs2		97.50 313	97.14 323	98.59 268	99.49 202	97.05 309	99.28 283	99.22 316	98.94 67	99.66 103	99.42 291	94.93 223	99.65 265	99.48 57	83.80 428	99.08 258

SixPastTwentyTwo		97.50 313	97.33 309	98.03 328	98.65 383	96.23 351	99.77 34	98.68 394	97.14 277	97.90 367	99.93 10	90.45 353	99.18 348	97.00 316	96.43 327	98.67 323

JIA-IIPM		97.50 313	97.02 329	98.93 219	98.73 374	97.80 272	99.30 273	98.97 349	91.73 412	98.91 277	94.86 430	95.10 217	99.71 243	97.58 273	97.98 266	99.28 239

ppachtmachnet_test		97.49 318	97.45 286	97.61 363	98.62 386	95.24 376	98.80 385	99.46 202	96.11 360	98.22 351	99.62 224	96.45 163	98.97 383	93.77 390	95.97 342	98.61 354

test-mter		97.49 318	97.13 325	98.55 277	98.79 362	97.10 303	98.67 396	97.75 416	96.65 316	98.61 326	98.85 380	88.23 383	99.45 291	97.25 300	99.38 169	99.10 253

testing91		97.44 320	97.02 329	98.71 259	99.18 291	96.89 324	99.19 315	99.04 341	97.78 208	98.31 344	98.29 405	85.41 404	99.85 168	98.01 234	97.95 267	99.39 225

tpm2		97.44 320	97.34 306	97.74 356	99.15 305	94.36 397	99.45 209	98.94 352	93.45 402	98.90 279	99.44 287	91.35 343	99.59 278	97.31 297	98.07 264	99.29 238

tpm cat1		97.39 322	97.36 301	97.50 367	99.17 299	93.73 403	99.43 220	99.31 293	91.27 413	98.71 305	99.08 356	94.31 262	99.77 218	96.41 345	98.50 236	99.00 269

UWE-MVS-28		97.36 323	97.24 319	97.75 354	98.84 358	94.44 394	99.24 302	97.58 420	97.98 184	99.00 264	99.00 366	91.35 343	99.53 284	93.75 391	98.39 240	99.27 243

testing99		97.36 323	96.94 332	98.63 265	99.18 291	96.70 330	99.30 273	98.93 353	97.71 215	98.23 349	98.26 406	84.92 407	99.84 175	98.04 233	97.85 274	99.35 231

SSC-MVS3.2		97.34 325	97.15 322	97.93 339	99.02 328	95.76 361	99.48 196	99.58 70	97.62 227	99.09 246	99.53 257	87.95 386	99.27 329	96.42 343	95.66 350	98.75 293

USDC		97.34 325	97.20 320	97.75 354	99.07 319	95.20 377	98.51 409	99.04 341	97.99 183	98.31 344	99.86 60	89.02 369	99.55 282	95.67 362	97.36 308	98.49 365

UniMVSNet_ETH3D		97.32 327	96.81 335	98.87 236	99.40 232	97.46 287	99.51 171	99.53 110	95.86 368	98.54 332	99.77 147	82.44 419	99.66 260	98.68 160	97.52 292	99.50 199

testing3		97.28 328	96.76 337	98.82 245	99.37 240	98.07 254	99.45 209	99.36 260	97.56 234	97.89 368	98.95 373	83.70 413	98.82 393	96.03 351	98.56 232	99.58 171

MVS		97.28 328	96.55 341	99.48 135	98.78 365	98.95 176	99.27 288	99.39 243	83.53 430	98.08 357	99.54 253	96.97 142	99.87 159	94.23 386	99.16 186	99.63 156

test_fmvs2		97.25 330	97.30 312	97.09 378	99.43 220	93.31 409	99.73 50	98.87 368	98.83 77	99.28 201	99.80 119	84.45 410	99.66 260	97.88 242	97.45 300	98.30 382

DSMNet-mixed		97.25 330	97.35 303	96.95 382	97.84 406	93.61 407	99.57 126	96.63 429	96.13 359	98.87 285	98.61 393	94.59 248	97.70 419	95.08 374	98.86 213	99.55 178

MS-PatchMatch		97.24 332	97.32 310	96.99 379	98.45 397	93.51 408	98.82 383	99.32 289	97.41 255	98.13 356	99.30 329	88.99 370	99.56 280	95.68 361	99.80 112	97.90 410

testing222		97.16 333	96.50 342	99.16 190	99.16 301	98.47 234	99.27 288	98.66 396	97.71 215	98.23 349	98.15 409	82.28 421	99.84 175	97.36 295	97.66 280	99.18 249

TransMVSNet (Re)		97.15 334	96.58 340	98.86 239	99.12 307	98.85 191	99.49 191	98.91 361	95.48 372	97.16 388	99.80 119	93.38 288	99.11 360	94.16 388	91.73 407	98.62 345

TinyColmap		97.12 335	96.89 334	97.83 349	99.07 319	95.52 368	98.57 405	98.74 385	97.58 231	97.81 372	99.79 131	88.16 384	99.56 280	95.10 373	97.21 313	98.39 378

K. test v3		97.10 336	96.79 336	98.01 331	98.72 376	96.33 346	99.87 8	97.05 423	97.59 229	96.16 402	99.80 119	88.71 374	99.04 367	96.69 334	96.55 325	98.65 334

Syy-MVS		97.09 337	97.14 323	96.95 382	99.00 331	92.73 413	99.29 278	99.39 243	97.06 288	97.41 378	98.15 409	93.92 277	98.68 399	91.71 409	98.34 242	99.45 215

PatchT		97.03 338	96.44 344	98.79 251	98.99 334	98.34 240	99.16 319	99.07 337	92.13 410	99.52 145	97.31 423	94.54 253	98.98 376	88.54 421	98.73 222	99.03 266

mmtdpeth		96.95 339	96.71 338	97.67 359	99.33 249	94.90 385	99.89 2	99.28 304	98.15 154	99.72 86	98.57 394	86.56 397	99.90 135	99.82 25	89.02 419	98.20 389

myMVS_eth3d		96.89 340	96.37 345	98.43 296	99.00 331	97.16 300	99.29 278	99.39 243	97.06 288	97.41 378	98.15 409	83.46 415	98.68 399	95.27 371	98.34 242	99.45 215

AUN-MVS		96.88 341	96.31 347	98.59 268	99.48 209	97.04 312	99.27 288	99.22 316	97.44 251	98.51 333	99.41 295	91.97 326	99.66 260	97.71 264	83.83 427	99.07 263

FMVSNet1		96.84 342	96.36 346	98.29 309	99.32 256	97.26 296	99.43 220	99.48 172	95.11 377	98.55 331	99.32 326	83.95 412	98.98 376	95.81 356	96.26 332	98.62 345

test2506		96.81 343	96.65 339	97.29 373	99.74 90	92.21 416	99.60 102	85.06 447	99.13 33	99.77 69	99.93 10	87.82 390	99.85 168	99.38 65	99.38 169	99.80 80

RPMNet		96.72 344	95.90 357	99.19 187	99.18 291	98.49 230	99.22 309	99.52 115	88.72 423	99.56 136	97.38 420	94.08 270	99.95 68	86.87 428	98.58 229	99.14 250

mvs5depth		96.66 345	96.22 349	97.97 335	97.00 422	96.28 348	98.66 399	99.03 343	96.61 321	96.93 394	99.79 131	87.20 393	99.47 287	96.65 338	94.13 381	98.16 391

test_0402		96.64 346	96.24 348	97.85 346	98.85 356	96.43 343	99.44 215	99.26 308	93.52 399	96.98 392	99.52 261	88.52 380	99.20 347	92.58 407	97.50 295	97.93 408

X-MVStestdata		96.55 347	95.45 366	99.87 17	99.85 26	99.83 19	99.69 60	99.68 20	98.98 61	99.37 181	64.01 443	98.81 47	99.94 81	98.79 146	99.86 76	99.84 49

pmmvs6		96.53 348	96.09 353	97.82 351	98.69 380	95.47 369	99.37 251	99.47 193	93.46 401	97.41 378	99.78 138	87.06 394	99.33 319	96.92 325	92.70 402	98.65 334

ET-MVSNet_ETH3D		96.49 349	95.64 363	99.05 202	99.53 179	98.82 196	98.84 381	97.51 421	97.63 225	84.77 430	99.21 345	92.09 324	98.91 389	98.98 111	92.21 405	99.41 222

UnsupCasMVSNet_eth		96.44 350	96.12 351	97.40 370	98.65 383	95.65 362	99.36 256	99.51 130	97.13 278	96.04 404	98.99 368	88.40 381	98.17 408	96.71 332	90.27 415	98.40 377

FMVSNet5		96.43 351	96.19 350	97.15 374	99.11 309	95.89 358	99.32 268	99.52 115	94.47 392	98.34 343	99.07 357	87.54 391	97.07 424	92.61 406	95.72 348	98.47 368

new_pmnet		96.38 352	96.03 354	97.41 369	98.13 403	95.16 380	99.05 343	99.20 320	93.94 394	97.39 381	98.79 386	91.61 339	99.04 367	90.43 414	95.77 345	98.05 398

Anonymous20231206		96.22 353	96.03 354	96.79 387	97.31 416	94.14 399	99.63 90	99.08 334	96.17 354	97.04 391	99.06 359	93.94 275	97.76 418	86.96 427	95.06 364	98.47 368

IB-MVS	95.67 18	96.22 353	95.44 367	98.57 272	99.21 283	96.70 330	98.65 400	97.74 418	96.71 311	97.27 383	98.54 395	86.03 399	99.92 111	98.47 192	86.30 424	99.10 253
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		96.20 355	95.89 358	97.13 376	97.72 410	94.96 384	99.79 31	99.29 302	93.01 404	97.20 387	99.03 362	89.69 364	98.36 405	91.16 412	96.13 334	98.07 396

gg-mvs-nofinetune		96.17 356	95.32 368	98.73 255	98.79 362	98.14 249	99.38 249	94.09 438	91.07 416	98.07 360	91.04 436	89.62 366	99.35 316	96.75 330	99.09 196	98.68 315

test20.03		96.12 357	95.96 356	96.63 388	97.44 412	95.45 370	99.51 171	99.38 251	96.55 327	96.16 402	99.25 339	93.76 284	96.17 429	87.35 426	94.22 379	98.27 384

PVSNet_0	94.43 19	96.09 358	95.47 365	97.94 338	99.31 257	94.34 398	97.81 427	99.70 15	97.12 280	97.46 377	98.75 388	89.71 363	99.79 211	97.69 267	81.69 430	99.68 134

MVStest1		96.08 359	95.48 364	97.89 343	98.93 342	96.70 330	99.56 133	99.35 267	92.69 408	91.81 425	99.46 284	89.90 361	98.96 385	95.00 376	92.61 403	98.00 403

EG-PatchMatch MVS		95.97 360	95.69 361	96.81 386	97.78 407	92.79 412	99.16 319	98.93 353	96.16 355	94.08 415	99.22 342	82.72 417	99.47 287	95.67 362	97.50 295	98.17 390

APD_test1		95.87 361	96.49 343	94.00 399	99.53 179	84.01 428	99.54 152	99.32 289	95.91 367	97.99 362	99.85 67	85.49 403	99.88 153	91.96 408	98.84 215	98.12 393

Patchmatch-RL test		95.84 362	95.81 360	95.95 394	95.61 427	90.57 420	98.24 420	98.39 403	95.10 379	95.20 409	98.67 390	94.78 233	97.77 417	96.28 348	90.02 416	99.51 195

test_vis1_rt		95.81 363	95.65 362	96.32 392	99.67 123	91.35 419	99.49 191	96.74 428	98.25 140	95.24 407	98.10 413	74.96 428	99.90 135	99.53 48	98.85 214	97.70 413

sc_t1		95.75 364	95.05 371	97.87 344	98.83 359	94.61 391	99.21 311	99.45 213	87.45 424	97.97 364	99.85 67	81.19 424	99.43 300	98.27 211	93.20 395	99.57 174

MVS-HIRNet		95.75 364	95.16 369	97.51 366	99.30 258	93.69 405	98.88 377	95.78 432	85.09 429	98.78 299	92.65 432	91.29 345	99.37 309	94.85 378	99.85 83	99.46 212

tt0320		95.71 366	95.07 370	97.62 361	99.05 324	95.02 381	99.25 299	99.52 115	86.81 425	97.97 364	99.72 169	83.58 414	99.15 350	96.38 346	93.35 391	98.68 315

MIMVSNet1		95.51 367	95.04 372	96.92 384	97.38 413	95.60 363	99.52 162	99.50 150	93.65 398	96.97 393	99.17 347	85.28 406	96.56 428	88.36 422	95.55 354	98.60 357

MDA-MVSNet_test_wron		95.45 368	94.60 375	98.01 331	98.16 402	97.21 299	99.11 334	99.24 313	93.49 400	80.73 436	98.98 370	93.02 294	98.18 407	94.22 387	94.45 375	98.64 336

TDRefinement		95.42 369	94.57 377	97.97 335	89.83 440	96.11 355	99.48 196	98.75 382	96.74 309	96.68 396	99.88 44	88.65 377	99.71 243	98.37 201	82.74 429	98.09 395

YYNet1		95.36 370	94.51 378	97.92 340	97.89 405	97.10 303	99.10 336	99.23 314	93.26 403	80.77 435	99.04 361	92.81 300	98.02 411	94.30 383	94.18 380	98.64 336

pmmvs-eth3d		95.34 371	94.73 374	97.15 374	95.53 429	95.94 357	99.35 261	99.10 331	95.13 375	93.55 417	97.54 418	88.15 385	97.91 414	94.58 380	89.69 418	97.61 414

tt0320-xc		95.31 372	94.59 376	97.45 368	98.92 344	94.73 387	99.20 314	99.31 293	86.74 426	97.23 384	99.72 169	81.14 425	98.95 386	97.08 313	91.98 406	98.67 323

dmvs_testset		95.02 373	96.12 351	91.72 408	99.10 312	80.43 436	99.58 119	97.87 415	97.47 244	95.22 408	98.82 382	93.99 273	95.18 433	88.09 423	94.91 369	99.56 177

KD-MVS_self_test		95.00 374	94.34 379	96.96 381	97.07 421	95.39 373	99.56 133	99.44 222	95.11 377	97.13 389	97.32 422	91.86 329	97.27 423	90.35 415	81.23 431	98.23 388

MDA-MVSNet-bldmvs		94.96 375	93.98 382	97.92 340	98.24 401	97.27 294	99.15 322	99.33 279	93.80 396	80.09 437	99.03 362	88.31 382	97.86 416	93.49 395	94.36 377	98.62 345

N_pmnet		94.95 376	95.83 359	92.31 406	98.47 396	79.33 438	99.12 328	92.81 444	93.87 395	97.68 374	99.13 352	93.87 279	99.01 373	91.38 411	96.19 333	98.59 358

KD-MVS_2432*1600		94.62 377	93.72 385	97.31 371	97.19 419	95.82 359	98.34 415	99.20 320	95.00 381	97.57 375	98.35 402	87.95 386	98.10 409	92.87 403	77.00 434	98.01 400

miper_refine_blended		94.62 377	93.72 385	97.31 371	97.19 419	95.82 359	98.34 415	99.20 320	95.00 381	97.57 375	98.35 402	87.95 386	98.10 409	92.87 403	77.00 434	98.01 400

CL-MVSNet_self_test		94.49 379	93.97 383	96.08 393	96.16 424	93.67 406	98.33 417	99.38 251	95.13 375	97.33 382	98.15 409	92.69 308	96.57 427	88.67 420	79.87 432	97.99 404

new-patchmatchnet		94.48 380	94.08 381	95.67 395	95.08 432	92.41 414	99.18 317	99.28 304	94.55 391	93.49 418	97.37 421	87.86 389	97.01 425	91.57 410	88.36 420	97.61 414

OpenMVS_ROB	92.34 20	94.38 381	93.70 387	96.41 391	97.38 413	93.17 410	99.06 341	98.75 382	86.58 427	94.84 413	98.26 406	81.53 422	99.32 321	89.01 419	97.87 272	96.76 421

CMPMVS	69.68 23	94.13 382	94.90 373	91.84 407	97.24 417	80.01 437	98.52 408	99.48 172	89.01 421	91.99 424	99.67 200	85.67 401	99.13 355	95.44 366	97.03 318	96.39 425
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		94.09 383	93.25 389	96.60 389	94.76 434	94.49 393	98.92 373	98.18 411	89.66 417	96.48 398	98.06 415	86.28 398	97.33 422	89.68 417	87.20 423	97.97 406

mvsany_test3		93.77 384	93.45 388	94.74 397	95.78 426	88.01 423	99.64 84	98.25 406	98.28 135	94.31 414	97.97 416	68.89 431	98.51 403	97.50 283	90.37 414	97.71 411

UnsupCasMVSNet_bld		93.53 385	92.51 391	96.58 390	97.38 413	93.82 401	98.24 420	99.48 172	91.10 415	93.10 419	96.66 425	74.89 429	98.37 404	94.03 389	87.71 422	97.56 416

dongtai		93.26 386	92.93 390	94.25 398	99.39 235	85.68 426	97.68 429	93.27 440	92.87 406	96.85 395	99.39 303	82.33 420	97.48 421	76.78 434	97.80 275	99.58 171

WB-MVS		93.10 387	94.10 380	90.12 413	95.51 431	81.88 433	99.73 50	99.27 307	95.05 380	93.09 420	98.91 379	94.70 242	91.89 437	76.62 435	94.02 385	96.58 423

PM-MVS		92.96 388	92.23 392	95.14 396	95.61 427	89.98 422	99.37 251	98.21 409	94.80 386	95.04 412	97.69 417	65.06 432	97.90 415	94.30 383	89.98 417	97.54 417

SSC-MVS		92.73 389	93.73 384	89.72 414	95.02 433	81.38 434	99.76 37	99.23 314	94.87 384	92.80 421	98.93 375	94.71 241	91.37 438	74.49 437	93.80 387	96.42 424

test_fmvs3		92.10 390	91.77 393	93.08 404	96.19 423	86.25 424	99.82 16	98.62 398	96.65 316	95.19 410	96.90 424	55.05 439	95.93 431	96.63 339	90.92 413	97.06 420

test_f		91.90 391	91.26 395	93.84 400	95.52 430	85.92 425	99.69 60	98.53 402	95.31 374	93.87 416	96.37 427	55.33 438	98.27 406	95.70 359	90.98 412	97.32 419

test_method		91.10 392	91.36 394	90.31 412	95.85 425	73.72 445	94.89 433	99.25 310	68.39 436	95.82 405	99.02 364	80.50 426	98.95 386	93.64 393	94.89 370	98.25 386

Gipuma		90.99 393	90.15 398	93.51 401	98.73 374	90.12 421	93.98 434	99.45 213	79.32 432	92.28 422	94.91 429	69.61 430	97.98 413	87.42 425	95.67 349	92.45 432
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
kuosan		90.92 394	90.11 399	93.34 402	98.78 365	85.59 427	98.15 424	93.16 442	89.37 420	92.07 423	98.38 401	81.48 423	95.19 432	62.54 441	97.04 317	99.25 244

testf1		90.42 395	90.68 396	89.65 415	97.78 407	73.97 443	99.13 325	98.81 375	89.62 418	91.80 426	98.93 375	62.23 435	98.80 395	86.61 429	91.17 409	96.19 426

APD_test2		90.42 395	90.68 396	89.65 415	97.78 407	73.97 443	99.13 325	98.81 375	89.62 418	91.80 426	98.93 375	62.23 435	98.80 395	86.61 429	91.17 409	96.19 426

test_vis3_rt		87.04 397	85.81 400	90.73 411	93.99 435	81.96 432	99.76 37	90.23 446	92.81 407	81.35 434	91.56 434	40.06 443	99.07 364	94.27 385	88.23 421	91.15 434

PMMVS2		86.87 398	85.37 402	91.35 410	90.21 439	83.80 429	98.89 376	97.45 422	83.13 431	91.67 428	95.03 428	48.49 441	94.70 434	85.86 431	77.62 433	95.54 429

LCM-MVSNet		86.80 399	85.22 403	91.53 409	87.81 441	80.96 435	98.23 422	98.99 347	71.05 434	90.13 429	96.51 426	48.45 442	96.88 426	90.51 413	85.30 425	96.76 421

FPMVS		84.93 400	85.65 401	82.75 421	86.77 442	63.39 447	98.35 414	98.92 356	74.11 433	83.39 432	98.98 370	50.85 440	92.40 436	84.54 432	94.97 366	92.46 431

EGC-MVSNET		82.80 401	77.86 407	97.62 361	97.91 404	96.12 354	99.33 266	99.28 304	8.40 444	25.05 445	99.27 336	84.11 411	99.33 319	89.20 418	98.22 253	97.42 418

tmp_tt		82.80 401	81.52 404	86.66 417	66.61 447	68.44 446	92.79 436	97.92 413	68.96 435	80.04 438	99.85 67	85.77 400	96.15 430	97.86 245	43.89 440	95.39 430

E-PMN		80.61 403	79.88 405	82.81 420	90.75 438	76.38 441	97.69 428	95.76 433	66.44 438	83.52 431	92.25 433	62.54 434	87.16 440	68.53 439	61.40 437	84.89 438

EMVS		80.02 404	79.22 406	82.43 422	91.19 437	76.40 440	97.55 431	92.49 445	66.36 439	83.01 433	91.27 435	64.63 433	85.79 441	65.82 440	60.65 438	85.08 437

ANet_high		77.30 405	74.86 409	84.62 419	75.88 445	77.61 439	97.63 430	93.15 443	88.81 422	64.27 440	89.29 437	36.51 444	83.93 442	75.89 436	52.31 439	92.33 433

MVE	76.82 21	76.91 406	74.31 410	84.70 418	85.38 444	76.05 442	96.88 432	93.17 441	67.39 437	71.28 439	89.01 438	21.66 449	87.69 439	71.74 438	72.29 436	90.35 435
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 407	74.97 408	79.01 423	70.98 446	55.18 448	93.37 435	98.21 409	65.08 440	61.78 441	93.83 431	21.74 448	92.53 435	78.59 433	91.12 411	89.34 436
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		40.18 408	41.29 413	36.84 424	86.18 443	49.12 449	79.73 437	22.81 449	27.64 441	25.46 444	28.45 444	21.98 447	48.89 443	55.80 442	23.56 443	12.51 441

testmvs		39.17 409	43.78 411	25.37 426	36.04 449	16.84 451	98.36 413	26.56 448	20.06 442	38.51 443	67.32 439	29.64 446	15.30 445	37.59 443	39.90 441	43.98 440

test123		39.01 410	42.50 412	28.53 425	39.17 448	20.91 450	98.75 390	19.17 450	19.83 443	38.57 442	66.67 440	33.16 445	15.42 444	37.50 444	29.66 442	49.26 439

cdsmvs_eth3d_5k		24.64 411	32.85 414	0.00 427	0.00 450	0.00 452	0.00 438	99.51 130	0.00 445	0.00 446	99.56 245	96.58 156	0.00 446	0.00 445	0.00 444	0.00 442

ab-mvs-re		8.30 412	11.06 415	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	99.58 237	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

pcd_1.5k_mvsjas		8.27 413	11.03 416	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	99.01 18	0.00 446	0.00 445	0.00 444	0.00 442

test_blank		0.13 414	0.17 417	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	1.57 445	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

mmdepth		0.02 415	0.03 418	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

monomultidepth		0.02 415	0.03 418	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

uanet_test		0.02 415	0.03 418	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

DCPMVS		0.02 415	0.03 418	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

sosnet-low-res		0.02 415	0.03 418	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

sosnet		0.02 415	0.03 418	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

uncertanet		0.02 415	0.03 418	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

Regformer		0.02 415	0.03 418	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

uanet		0.02 415	0.03 418	0.00 427	0.00 450	0.00 452	0.00 438	0.00 451	0.00 445	0.00 446	0.27 446	0.00 450	0.00 446	0.00 445	0.00 444	0.00 442

WAC-MVS						97.16 300								95.47 365

FOURS1					99.91 1	99.93 1	99.87 8	99.56 80	99.10 40	99.81 54

MSC_two_6792asdad				99.87 17	99.51 188	99.76 42		99.33 279					99.96 36	98.87 128	99.84 91	99.89 25

PC_three_1452									98.18 152	99.84 46	99.70 176	99.31 3	98.52 402	98.30 210	99.80 112	99.81 71

No_MVS				99.87 17	99.51 188	99.76 42		99.33 279					99.96 36	98.87 128	99.84 91	99.89 25

test_one_0601					99.81 48	99.88 8		99.49 160	98.97 64	99.65 110	99.81 106	99.09 14

eth-test2					0.00 450

eth-test					0.00 450

ZD-MVS					99.71 106	99.79 34		99.61 53	96.84 305	99.56 136	99.54 253	98.58 75	99.96 36	96.93 323	99.75 129

RE-MVS-def			99.34 45		99.76 72	99.82 25	99.63 90	99.52 115	98.38 123	99.76 75	99.82 92	98.75 58		98.61 170	99.81 107	99.77 92

IU-MVS					99.84 32	99.88 8		99.32 289	98.30 134	99.84 46				98.86 133	99.85 83	99.89 25

OPU-MVS				99.64 91	99.56 171	99.72 49	99.60 102				99.70 176	99.27 5	99.42 302	98.24 214	99.80 112	99.79 84

test_241102_TWO								99.48 172	99.08 46	99.88 35	99.81 106	98.94 32	99.96 36	98.91 122	99.84 91	99.88 31

test_241102_ONE					99.84 32	99.90 2		99.48 172	99.07 48	99.91 26	99.74 159	99.20 7	99.76 222

9.14			99.10 90		99.72 101		99.40 240	99.51 130	97.53 239	99.64 115	99.78 138	98.84 44	99.91 123	97.63 269	99.82 104

save fliter					99.76 72	99.59 80	99.14 324	99.40 240	99.00 56

test_0728_THIRD									98.99 58	99.81 54	99.80 119	99.09 14	99.96 36	98.85 135	99.90 50	99.88 31

test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 126	99.51 130					99.96 36	98.93 119	99.86 76	99.88 31

test0726					99.85 26	99.89 4	99.62 95	99.50 150	99.10 40	99.86 44	99.82 92	98.94 32

GSMVS																99.52 187

test_part2					99.81 48	99.83 19				99.77 69

sam_mvs1												94.86 228				99.52 187

sam_mvs												94.72 240

ambc				93.06 405	92.68 436	82.36 430	98.47 410	98.73 391		95.09 411	97.41 419	55.55 437	99.10 362	96.42 343	91.32 408	97.71 411

MTGPA								99.47 193

test_post1							99.23 305				65.14 442	94.18 267	99.71 243	97.58 273

test_post											65.99 441	94.65 246	99.73 233

patchmatchnet-post											98.70 389	94.79 232	99.74 227

GG-mvs-BLEND				98.45 291	98.55 393	98.16 247	99.43 220	93.68 439		97.23 384	98.46 397	89.30 367	99.22 340	95.43 367	98.22 253	97.98 405

MTMP							99.54 152	98.88 366

gm-plane-assit					98.54 394	92.96 411			94.65 389		99.15 350		99.64 268	97.56 278

test9_res														97.49 284	99.72 135	99.75 98

TEST9					99.67 123	99.65 67	99.05 343	99.41 233	96.22 350	98.95 272	99.49 271	98.77 54	99.91 123

test_8					99.67 123	99.61 77	99.03 348	99.41 233	96.28 344	98.93 275	99.48 277	98.76 55	99.91 123

agg_prior2														97.21 302	99.73 134	99.75 98

agg_prior					99.67 123	99.62 75		99.40 240		98.87 285			99.91 123

TestCases				99.31 164	99.86 20	98.48 232		99.61 53	97.85 198	99.36 184	99.85 67	95.95 179	99.85 168	96.66 336	99.83 100	99.59 167

test_prior4						99.56 86	98.99 359

test_prior2							98.96 366		98.34 129	99.01 260	99.52 261	98.68 67		97.96 237	99.74 132

test_prior				99.68 79	99.67 123	99.48 102		99.56 80					99.83 188			99.74 102

旧先验2							98.96 366		96.70 312	99.47 153			99.94 81	98.19 217

新几何2							99.01 356

新几何1				99.75 68	99.75 82	99.59 80		99.54 97	96.76 308	99.29 200	99.64 213	98.43 86	99.94 81	96.92 325	99.66 146	99.72 117

旧先验1					99.74 90	99.59 80		99.54 97			99.69 187	98.47 83			99.68 143	99.73 109

无先验							98.99 359	99.51 130	96.89 302				99.93 99	97.53 281		99.72 117

原ACMM2							98.95 369

原ACMM1				99.65 85	99.73 97	99.33 118		99.47 193	97.46 245	99.12 238	99.66 205	98.67 69	99.91 123	97.70 266	99.69 140	99.71 126

test222					99.75 82	99.49 100	98.91 375	99.49 160	96.42 338	99.34 190	99.65 207	98.28 96			99.69 140	99.72 117

testdata2													99.95 68	96.67 335

segment_acmp												98.96 25

testdata				99.54 112	99.75 82	98.95 176		99.51 130	97.07 286	99.43 163	99.70 176	98.87 40	99.94 81	97.76 257	99.64 149	99.72 117

testdata1							98.85 380		98.32 132

test12				99.75 68	99.64 142	99.61 77		99.29 302		99.21 221		98.38 91	99.89 148		99.74 132	99.74 102

plane_prior7					99.29 262	97.03 313

plane_prior6					99.27 267	96.98 317						92.71 306

plane_prior5								99.47 193					99.69 254	97.78 253	97.63 281	98.67 323

plane_prior4											99.61 228

plane_prior3						97.00 315			98.69 95	99.11 240

plane_prior2							99.39 244		98.97 64

plane_prior1					99.26 270

plane_prior						96.97 318	99.21 311		98.45 116						97.60 284

n2								0.00 451

nn								0.00 451

door-mid								98.05 412

lessismore_v0				97.79 353	98.69 380	95.44 372		94.75 436		95.71 406	99.87 55	88.69 375	99.32 321	95.89 354	94.93 368	98.62 345

LGP-MVS_train				98.49 281	99.33 249	97.05 309		99.55 88	97.46 245	99.24 213	99.83 83	92.58 311	99.72 237	98.09 224	97.51 293	98.68 315

test11								99.35 267

door								97.92 413

HQP5-MVS						96.83 325

HQP-NCC					99.19 288		98.98 362		98.24 141	98.66 314

ACMP_Plane					99.19 288		98.98 362		98.24 141	98.66 314

BP-MVS														97.19 306

HQP4-MVS										98.66 314			99.64 268			98.64 336

HQP3-MVS								99.39 243							97.58 286

HQP2-MVS												92.47 315

NP-MVS					99.23 278	96.92 321					99.40 299

MDTV_nov1_ep13_2view						95.18 379	99.35 261		96.84 305	99.58 132		95.19 214		97.82 250		99.46 212

MDTV_nov1_ep13			98.32 192		99.11 309	94.44 394	99.27 288	98.74 385	97.51 242	99.40 175	99.62 224	94.78 233	99.76 222	97.59 272	98.81 219

ACMMP++_ref															97.19 314

ACMMP++															97.43 304

Test By Simon												98.75 58

ITE_SJBPF				98.08 326	99.29 262	96.37 344		98.92 356	98.34 129	98.83 291	99.75 154	91.09 347	99.62 275	95.82 355	97.40 306	98.25 386

DeepMVS_CX				93.34 402	99.29 262	82.27 431		99.22 316	85.15 428	96.33 399	99.05 360	90.97 349	99.73 233	93.57 394	97.77 277	98.01 400

High-resolution multi-view benchmark