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.

test_vis1_n		97.92 221	97.44 255	99.34 126	99.53 156	98.08 224	99.74 43	99.49 134	99.15 14	100.00 1	99.94 4	79.51 369	99.98 10	99.88 5	99.76 100	99.97 3

test_vis1_n_1920		98.63 150	98.40 157	99.31 133	99.86 20	97.94 235	99.67 62	99.62 36	99.43 2	99.99 2	99.91 13	87.29 350	100.00 1	99.92 4	99.92 16	99.98 2

test_fmvs1_n		98.41 162	98.14 173	99.21 152	99.82 38	97.71 247	99.74 43	99.49 134	99.32 8	99.99 2	99.95 2	85.32 357	99.97 17	99.82 6	99.84 67	99.96 4

test_fmvsm_n_1920		99.69 1	99.66 1	99.78 43	99.84 31	99.44 85	99.58 107	99.69 18	99.43 2	99.98 4	99.91 13	98.62 68	100.00 1	99.97 1	99.95 9	99.90 7

test_fmvs1		98.88 114	98.79 116	99.16 157	99.69 100	97.61 249	99.55 130	99.49 134	99.32 8	99.98 4	99.91 13	91.41 306	99.96 25	99.82 6	99.92 16	99.90 7

dcpmvs_2		99.23 66	99.58 4	98.16 278	99.83 36	94.68 337	99.76 37	99.52 93	99.07 27	99.98 4	99.88 29	98.56 71	99.93 74	99.67 11	99.98 2	99.87 21

test_cas_vis1_n_1920		99.16 73	99.01 85	99.61 74	99.81 42	98.86 165	99.65 73	99.64 34	99.39 5	99.97 7	99.94 4	93.20 259	99.98 10	99.55 19	99.91 21	99.99 1

mvsany_test1		99.50 14	99.46 16	99.62 73	99.61 134	99.09 126	98.94 316	99.48 146	99.10 20	99.96 8	99.91 13	98.85 39	99.96 25	99.72 8	99.58 127	99.82 44

SED-MVS		99.61 4	99.52 8	99.88 5	99.84 31	99.90 2	99.60 93	99.48 146	99.08 25	99.91 9	99.81 81	99.20 7	99.96 25	98.91 89	99.85 59	99.79 64

test_241102_ONE					99.84 31	99.90 2		99.48 146	99.07 27	99.91 9	99.74 133	99.20 7	99.76 183

EI-MVSNet-UG-set		99.58 6	99.57 5	99.64 68	99.78 51	99.14 121	99.60 93	99.45 184	99.01 32	99.90 11	99.83 61	98.98 23	99.93 74	99.59 15	99.95 9	99.86 23

EI-MVSNet-Vis-set		99.58 6	99.56 7	99.64 68	99.78 51	99.15 120	99.61 92	99.45 184	99.01 32	99.89 12	99.82 68	99.01 18	99.92 85	99.56 18	99.95 9	99.85 26

DVP-MVS++		99.59 5	99.50 10	99.88 5	99.51 162	99.88 8	99.87 9	99.51 107	98.99 37	99.88 13	99.81 81	99.27 5	99.96 25	98.85 102	99.80 87	99.81 51

test_241102_TWO								99.48 146	99.08 25	99.88 13	99.81 81	98.94 29	99.96 25	98.91 89	99.84 67	99.88 16

DPE-MVS		99.46 25	99.32 34	99.91 2	99.78 51	99.88 8	99.36 217	99.51 107	98.73 67	99.88 13	99.84 57	98.72 59	99.96 25	98.16 182	99.87 44	99.88 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SD-MVS		99.41 41	99.52 8	99.05 168	99.74 75	99.68 48	99.46 175	99.52 93	99.11 19	99.88 13	99.91 13	99.43 1	97.70 365	98.72 120	99.93 14	99.77 72
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
APDe-MVS		99.66 2	99.57 5	99.92 1	99.77 57	99.89 4	99.75 40	99.56 61	99.02 30	99.88 13	99.85 47	99.18 10	99.96 25	99.22 59	99.92 16	99.90 7

test_fmvsmvis_n_1920		99.65 3	99.61 3	99.77 46	99.38 203	99.37 91	99.58 107	99.62 36	99.41 4	99.87 18	99.92 11	98.81 44	100.00 1	99.97 1	99.93 14	99.94 5

test0726					99.85 25	99.89 4	99.62 86	99.50 126	99.10 20	99.86 19	99.82 68	98.94 29

Vis-MVSNet		99.12 85	98.97 91	99.56 84	99.78 51	99.10 125	99.68 59	99.66 27	98.49 83	99.86 19	99.87 37	94.77 209	99.84 141	99.19 61	99.41 138	99.74 82
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PC_three_1452									98.18 121	99.84 21	99.70 148	99.31 3	98.52 348	98.30 173	99.80 87	99.81 51

IU-MVS					99.84 31	99.88 8		99.32 255	98.30 102	99.84 21				98.86 100	99.85 59	99.89 10

xiu_mvs_v1_base_debu		99.29 56	99.27 51	99.34 126	99.63 124	98.97 143	99.12 274	99.51 107	98.86 52	99.84 21	99.47 245	98.18 93	99.99 4	99.50 26	99.31 147	99.08 208

xiu_mvs_v1_base		99.29 56	99.27 51	99.34 126	99.63 124	98.97 143	99.12 274	99.51 107	98.86 52	99.84 21	99.47 245	98.18 93	99.99 4	99.50 26	99.31 147	99.08 208

xiu_mvs_v1_base_debi		99.29 56	99.27 51	99.34 126	99.63 124	98.97 143	99.12 274	99.51 107	98.86 52	99.84 21	99.47 245	98.18 93	99.99 4	99.50 26	99.31 147	99.08 208

DeepPCF-MVS	98.18 3	98.81 129	99.37 24	97.12 324	99.60 139	91.75 362	98.61 346	99.44 192	99.35 6	99.83 26	99.85 47	98.70 61	99.81 163	99.02 77	99.91 21	99.81 51

MVS_0304		99.42 36	99.32 34	99.72 55	99.70 96	99.27 103	99.52 141	97.57 366	99.51 1	99.82 27	99.78 111	98.09 97	99.96 25	99.97 1	99.97 5	99.94 5

TSAR-MVS + GP.		99.36 48	99.36 26	99.36 125	99.67 105	98.61 188	99.07 284	99.33 245	99.00 35	99.82 27	99.81 81	99.06 16	99.84 141	99.09 70	99.42 137	99.65 119

FOURS1					99.91 1	99.93 1	99.87 9	99.56 61	99.10 20	99.81 29

DVP-MVS		99.57 9	99.47 14	99.88 5	99.85 25	99.89 4	99.57 114	99.37 228	99.10 20	99.81 29	99.80 94	98.94 29	99.96 25	98.93 86	99.86 52	99.81 51
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
test_0728_THIRD									98.99 37	99.81 29	99.80 94	99.09 14	99.96 25	98.85 102	99.90 29	99.88 16

MVSFormer		99.17 71	99.12 67	99.29 141	99.51 162	98.94 155	99.88 4	99.46 173	97.55 191	99.80 32	99.65 176	97.39 113	99.28 282	99.03 75	99.85 59	99.65 119

lupinMVS		99.13 79	99.01 85	99.46 112	99.51 162	98.94 155	99.05 289	99.16 287	97.86 157	99.80 32	99.56 213	97.39 113	99.86 129	98.94 84	99.85 59	99.58 144

tttt0517		98.42 160	98.14 173	99.28 144	99.66 113	98.38 211	99.74 43	96.85 370	97.68 179	99.79 34	99.74 133	91.39 307	99.89 116	98.83 108	99.56 128	99.57 145

APD-MVS_3200maxsize		99.48 20	99.35 28	99.85 25	99.76 60	99.83 16	99.63 80	99.54 77	98.36 96	99.79 34	99.82 68	98.86 38	99.95 52	98.62 133	99.81 83	99.78 70

jason		99.13 79	99.03 78	99.45 113	99.46 183	98.87 162	99.12 274	99.26 272	98.03 146	99.79 34	99.65 176	97.02 127	99.85 135	99.02 77	99.90 29	99.65 119
jason: jason.
SteuartSystems-ACMMP		99.54 10	99.42 17	99.87 11	99.82 38	99.81 25	99.59 99	99.51 107	98.62 73	99.79 34	99.83 61	99.28 4	99.97 17	98.48 155	99.90 29	99.84 30
Skip Steuart: Steuart Systems R&D Blog.
DeepC-MVS_fast	98.69 1	99.49 16	99.39 21	99.77 46	99.63 124	99.59 62	99.36 217	99.46 173	99.07 27	99.79 34	99.82 68	98.85 39	99.92 85	98.68 127	99.87 44	99.82 44
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CS-MVS		99.50 14	99.48 12	99.54 87	99.76 60	99.42 87	99.90 1	99.55 69	98.56 77	99.78 39	99.70 148	98.65 66	99.79 172	99.65 13	99.78 94	99.41 182

SMA-MVS		99.44 31	99.30 43	99.85 25	99.73 82	99.83 16	99.56 120	99.47 164	97.45 203	99.78 39	99.82 68	99.18 10	99.91 95	98.79 113	99.89 38	99.81 51
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
TSAR-MVS + MP.		99.58 6	99.50 10	99.81 36	99.91 1	99.66 53	99.63 80	99.39 214	98.91 50	99.78 39	99.85 47	99.36 2	99.94 61	98.84 105	99.88 41	99.82 44
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test2506		96.81 294	96.65 292	97.29 320	99.74 75	92.21 361	99.60 93	85.06 389	99.13 16	99.77 42	99.93 7	87.82 348	99.85 135	99.38 38	99.38 139	99.80 60

test_part2					99.81 42	99.83 16				99.77 42

MSP-MVS		99.42 36	99.27 51	99.88 5	99.89 8	99.80 27	99.67 62	99.50 126	98.70 69	99.77 42	99.49 237	98.21 91	99.95 52	98.46 159	99.77 97	99.88 16
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 36	99.29 47	99.80 38	99.62 130	99.55 69	99.50 153	99.70 15	98.79 62	99.77 42	99.96 1	97.45 112	99.96 25	98.92 88	99.90 29	99.89 10

APD-MVS		99.27 59	99.08 72	99.84 31	99.75 68	99.79 30	99.50 153	99.50 126	97.16 229	99.77 42	99.82 68	98.78 48	99.94 61	97.56 236	99.86 52	99.80 60
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SR-MVS-dyc-post		99.45 27	99.31 41	99.85 25	99.76 60	99.82 22	99.63 80	99.52 93	98.38 92	99.76 47	99.82 68	98.53 73	99.95 52	98.61 136	99.81 83	99.77 72

RE-MVS-def			99.34 30		99.76 60	99.82 22	99.63 80	99.52 93	98.38 92	99.76 47	99.82 68	98.75 55		98.61 136	99.81 83	99.77 72

ACMMP_NAP		99.47 23	99.34 30	99.88 5	99.87 15	99.86 13	99.47 172	99.48 146	98.05 143	99.76 47	99.86 42	98.82 43	99.93 74	98.82 112	99.91 21	99.84 30

HPM-MVS_fast		99.51 13	99.40 20	99.85 25	99.91 1	99.79 30	99.76 37	99.56 61	97.72 175	99.76 47	99.75 128	99.13 12	99.92 85	99.07 73	99.92 16	99.85 26

VNet		99.11 89	98.90 100	99.73 54	99.52 160	99.56 67	99.41 194	99.39 214	99.01 32	99.74 51	99.78 111	95.56 177	99.92 85	99.52 24	98.18 218	99.72 93

patch_mono-2		99.26 61	99.62 2	98.16 278	99.81 42	94.59 339	99.52 141	99.64 34	99.33 7	99.73 52	99.90 19	99.00 22	99.99 4	99.69 9	99.98 2	99.89 10

SR-MVS		99.43 34	99.29 47	99.86 20	99.75 68	99.83 16	99.59 99	99.62 36	98.21 114	99.73 52	99.79 105	98.68 62	99.96 25	98.44 160	99.77 97	99.79 64

thisisatest0530		98.35 168	98.03 188	99.31 133	99.63 124	98.56 191	99.54 134	96.75 372	97.53 195	99.73 52	99.65 176	91.25 310	99.89 116	98.62 133	99.56 128	99.48 167

CS-MVS-test		99.49 16	99.48 12	99.54 87	99.78 51	99.30 99	99.89 2	99.58 53	98.56 77	99.73 52	99.69 158	98.55 72	99.82 158	99.69 9	99.85 59	99.48 167

EC-MVSNet		99.44 31	99.39 21	99.58 80	99.56 149	99.49 79	99.88 4	99.58 53	98.38 92	99.73 52	99.69 158	98.20 92	99.70 208	99.64 14	99.82 80	99.54 150

diffmvs		99.14 77	99.02 81	99.51 103	99.61 134	98.96 147	99.28 238	99.49 134	98.46 85	99.72 57	99.71 144	96.50 144	99.88 121	99.31 48	99.11 161	99.67 112
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SF-MVS		99.38 46	99.24 56	99.79 41	99.79 49	99.68 48	99.57 114	99.54 77	97.82 166	99.71 58	99.80 94	98.95 27	99.93 74	98.19 178	99.84 67	99.74 82

xiu_mvs_v2_base		99.26 61	99.25 55	99.29 141	99.53 156	98.91 159	99.02 297	99.45 184	98.80 61	99.71 58	99.26 299	98.94 29	99.98 10	99.34 45	99.23 151	98.98 222

PS-MVSNAJ		99.32 52	99.32 34	99.30 138	99.57 145	98.94 155	98.97 310	99.46 173	98.92 49	99.71 58	99.24 301	99.01 18	99.98 10	99.35 41	99.66 118	98.97 223

PGM-MVS		99.45 27	99.31 41	99.86 20	99.87 15	99.78 36	99.58 107	99.65 32	97.84 161	99.71 58	99.80 94	99.12 13	99.97 17	98.33 169	99.87 44	99.83 39

114514_t		98.93 110	98.67 126	99.72 55	99.85 25	99.53 74	99.62 86	99.59 49	92.65 355	99.71 58	99.78 111	98.06 99	99.90 106	98.84 105	99.91 21	99.74 82

PVSNet_Blended_VisFu		99.36 48	99.28 49	99.61 74	99.86 20	99.07 131	99.47 172	99.93 2	97.66 182	99.71 58	99.86 42	97.73 107	99.96 25	99.47 33	99.82 80	99.79 64

MTAPA		99.52 12	99.39 21	99.89 4	99.90 4	99.86 13	99.66 67	99.47 164	98.79 62	99.68 64	99.81 81	98.43 80	99.97 17	98.88 92	99.90 29	99.83 39

HFP-MVS		99.49 16	99.37 24	99.86 20	99.87 15	99.80 27	99.66 67	99.67 23	98.15 123	99.68 64	99.69 158	99.06 16	99.96 25	98.69 125	99.87 44	99.84 30

VDDNet		97.55 270	97.02 287	99.16 157	99.49 173	98.12 223	99.38 211	99.30 263	95.35 323	99.68 64	99.90 19	82.62 365	99.93 74	99.31 48	98.13 222	99.42 180

HPM-MVS		99.42 36	99.28 49	99.83 32	99.90 4	99.72 42	99.81 20	99.54 77	97.59 186	99.68 64	99.63 188	98.91 34	99.94 61	98.58 142	99.91 21	99.84 30
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
VDD-MVS		97.73 252	97.35 267	98.88 199	99.47 182	97.12 263	99.34 225	98.85 325	98.19 117	99.67 68	99.85 47	82.98 363	99.92 85	99.49 30	98.32 209	99.60 136

ACMMPR		99.49 16	99.36 26	99.86 20	99.87 15	99.79 30	99.66 67	99.67 23	98.15 123	99.67 68	99.69 158	98.95 27	99.96 25	98.69 125	99.87 44	99.84 30

PVSNet_BlendedMVS		98.86 118	98.80 113	99.03 170	99.76 60	98.79 174	99.28 238	99.91 3	97.42 208	99.67 68	99.37 270	97.53 110	99.88 121	98.98 80	97.29 263	98.42 323

PVSNet_Blended		99.08 95	98.97 91	99.42 118	99.76 60	98.79 174	98.78 332	99.91 3	96.74 260	99.67 68	99.49 237	97.53 110	99.88 121	98.98 80	99.85 59	99.60 136

sss		99.17 71	99.05 74	99.53 95	99.62 130	98.97 143	99.36 217	99.62 36	97.83 162	99.67 68	99.65 176	97.37 116	99.95 52	99.19 61	99.19 154	99.68 109

ECVR-MVS		98.04 201	98.05 186	98.00 290	99.74 75	94.37 342	99.59 99	94.98 379	99.13 16	99.66 73	99.93 7	90.67 316	99.84 141	99.40 37	99.38 139	99.80 60

h-mvs33		97.70 258	97.28 277	98.97 180	99.70 96	97.27 257	99.36 217	99.45 184	98.94 46	99.66 73	99.64 182	94.93 196	99.99 4	99.48 31	84.36 368	99.65 119

hse-mvs2		97.50 275	97.14 283	98.59 231	99.49 173	97.05 270	99.28 238	99.22 278	98.94 46	99.66 73	99.42 255	94.93 196	99.65 223	99.48 31	83.80 370	99.08 208

region2R		99.48 20	99.35 28	99.87 11	99.88 11	99.80 27	99.65 73	99.66 27	98.13 127	99.66 73	99.68 164	98.96 24	99.96 25	98.62 133	99.87 44	99.84 30

RPSCF		98.22 176	98.62 137	96.99 326	99.82 38	91.58 363	99.72 47	99.44 192	96.61 272	99.66 73	99.89 23	95.92 164	99.82 158	97.46 246	99.10 164	99.57 145

OMC-MVS		99.08 95	99.04 76	99.20 153	99.67 105	98.22 217	99.28 238	99.52 93	98.07 138	99.66 73	99.81 81	97.79 105	99.78 177	97.79 210	99.81 83	99.60 136

test1111		98.04 201	98.11 177	97.83 301	99.74 75	93.82 347	99.58 107	95.40 378	99.12 18	99.65 79	99.93 7	90.73 315	99.84 141	99.43 36	99.38 139	99.82 44

test_one_0601					99.81 42	99.88 8		99.49 134	98.97 43	99.65 79	99.81 81	99.09 14

LFMVS		97.90 224	97.35 267	99.54 87	99.52 160	99.01 138	99.39 206	98.24 354	97.10 237	99.65 79	99.79 105	84.79 359	99.91 95	99.28 53	98.38 204	99.69 105

MVS_111021_LR		99.41 41	99.33 32	99.65 63	99.77 57	99.51 78	98.94 316	99.85 6	98.82 57	99.65 79	99.74 133	98.51 75	99.80 169	98.83 108	99.89 38	99.64 126

SDMVSNet		99.11 89	98.90 100	99.75 49	99.81 42	99.59 62	99.81 20	99.65 32	98.78 65	99.64 83	99.88 29	94.56 220	99.93 74	99.67 11	98.26 211	99.72 93

sd_testset		98.75 136	98.57 146	99.29 141	99.81 42	98.26 215	99.56 120	99.62 36	98.78 65	99.64 83	99.88 29	92.02 290	99.88 121	99.54 20	98.26 211	99.72 93

9.14			99.10 69		99.72 86		99.40 202	99.51 107	97.53 195	99.64 83	99.78 111	98.84 41	99.91 95	97.63 227	99.82 80

GST-MVS		99.40 44	99.24 56	99.85 25	99.86 20	99.79 30	99.60 93	99.67 23	97.97 149	99.63 86	99.68 164	98.52 74	99.95 52	98.38 163	99.86 52	99.81 51

CPTT-MVS		99.11 89	98.90 100	99.74 52	99.80 48	99.46 83	99.59 99	99.49 134	97.03 243	99.63 86	99.69 158	97.27 119	99.96 25	97.82 208	99.84 67	99.81 51

ACMMP		99.45 27	99.32 34	99.82 33	99.89 8	99.67 51	99.62 86	99.69 18	98.12 128	99.63 86	99.84 57	98.73 58	99.96 25	98.55 151	99.83 76	99.81 51
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
DeepC-MVS	98.35 2	99.30 54	99.19 61	99.64 68	99.82 38	99.23 108	99.62 86	99.55 69	98.94 46	99.63 86	99.95 2	95.82 169	99.94 61	99.37 40	99.97 5	99.73 87
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FE-MVS		98.48 155	98.17 169	99.40 120	99.54 155	98.96 147	99.68 59	98.81 329	95.54 321	99.62 90	99.70 148	93.82 246	99.93 74	97.35 252	99.46 134	99.32 192

CHOSEN 280x420		99.12 85	99.13 66	99.08 163	99.66 113	97.89 236	98.43 356	99.71 13	98.88 51	99.62 90	99.76 125	96.63 140	99.70 208	99.46 34	99.99 1	99.66 115

PHI-MVS		99.30 54	99.17 63	99.70 57	99.56 149	99.52 77	99.58 107	99.80 8	97.12 233	99.62 90	99.73 139	98.58 69	99.90 106	98.61 136	99.91 21	99.68 109

test_yl		98.86 118	98.63 132	99.54 87	99.49 173	99.18 112	99.50 153	99.07 299	98.22 112	99.61 93	99.51 231	95.37 183	99.84 141	98.60 139	98.33 205	99.59 140

DCV-MVSNet		98.86 118	98.63 132	99.54 87	99.49 173	99.18 112	99.50 153	99.07 299	98.22 112	99.61 93	99.51 231	95.37 183	99.84 141	98.60 139	98.33 205	99.59 140

MG-MVS		99.13 79	99.02 81	99.45 113	99.57 145	98.63 185	99.07 284	99.34 238	98.99 37	99.61 93	99.82 68	97.98 101	99.87 126	97.00 271	99.80 87	99.85 26

MP-MVS-pluss		99.37 47	99.20 60	99.88 5	99.90 4	99.87 12	99.30 232	99.52 93	97.18 227	99.60 96	99.79 105	98.79 47	99.95 52	98.83 108	99.91 21	99.83 39
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CDPH-MVS		99.13 79	98.91 99	99.80 38	99.75 68	99.71 44	99.15 269	99.41 203	96.60 274	99.60 96	99.55 216	98.83 42	99.90 106	97.48 243	99.83 76	99.78 70

EPP-MVSNet		99.13 79	98.99 87	99.53 95	99.65 119	99.06 132	99.81 20	99.33 245	97.43 206	99.60 96	99.88 29	97.14 121	99.84 141	99.13 66	98.94 175	99.69 105

HyFIR lowres test		99.11 89	98.92 97	99.65 63	99.90 4	99.37 91	99.02 297	99.91 3	97.67 181	99.59 99	99.75 128	95.90 166	99.73 192	99.53 22	99.02 172	99.86 23

FA-MVS(test-final)		98.75 136	98.53 150	99.41 119	99.55 153	99.05 134	99.80 25	99.01 304	96.59 276	99.58 100	99.59 202	95.39 182	99.90 106	97.78 211	99.49 133	99.28 195

MVS_Test		99.10 93	98.97 91	99.48 107	99.49 173	99.14 121	99.67 62	99.34 238	97.31 216	99.58 100	99.76 125	97.65 109	99.82 158	98.87 95	99.07 167	99.46 175

MDTV_nov1_ep13_2view						95.18 330	99.35 222		96.84 256	99.58 100		95.19 192		97.82 208		99.46 175

DELS-MVS		99.48 20	99.42 17	99.65 63	99.72 86	99.40 90	99.05 289	99.66 27	99.14 15	99.57 103	99.80 94	98.46 78	99.94 61	99.57 17	99.84 67	99.60 136
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
ZD-MVS					99.71 91	99.79 30		99.61 41	96.84 256	99.56 104	99.54 221	98.58 69	99.96 25	96.93 278	99.75 102

CR-MVSNet		98.17 183	97.93 200	98.87 203	99.18 251	98.49 202	99.22 260	99.33 245	96.96 247	99.56 104	99.38 267	94.33 228	99.00 326	94.83 327	98.58 195	99.14 200

RPMNet		96.72 295	95.90 307	99.19 154	99.18 251	98.49 202	99.22 260	99.52 93	88.72 368	99.56 104	97.38 362	94.08 238	99.95 52	86.87 373	98.58 195	99.14 200

IS-MVSNet		99.05 98	98.87 105	99.57 82	99.73 82	99.32 95	99.75 40	99.20 282	98.02 147	99.56 104	99.86 42	96.54 143	99.67 215	98.09 185	99.13 160	99.73 87

ZNCC-MVS		99.47 23	99.33 32	99.87 11	99.87 15	99.81 25	99.64 76	99.67 23	98.08 137	99.55 108	99.64 182	98.91 34	99.96 25	98.72 120	99.90 29	99.82 44

thisisatest0515		98.14 186	97.79 211	99.19 154	99.50 171	98.50 201	98.61 346	96.82 371	96.95 249	99.54 109	99.43 253	91.66 302	99.86 129	98.08 189	99.51 132	99.22 198

MVS_111021_HR		99.41 41	99.32 34	99.66 59	99.72 86	99.47 82	98.95 314	99.85 6	98.82 57	99.54 109	99.73 139	98.51 75	99.74 186	98.91 89	99.88 41	99.77 72

CP-MVS		99.45 27	99.32 34	99.85 25	99.83 36	99.75 39	99.69 53	99.52 93	98.07 138	99.53 111	99.63 188	98.93 33	99.97 17	98.74 117	99.91 21	99.83 39

WTY-MVS		99.06 97	98.88 104	99.61 74	99.62 130	99.16 115	99.37 213	99.56 61	98.04 144	99.53 111	99.62 193	96.84 133	99.94 61	98.85 102	98.49 202	99.72 93

MCST-MVS		99.43 34	99.30 43	99.82 33	99.79 49	99.74 41	99.29 236	99.40 211	98.79 62	99.52 113	99.62 193	98.91 34	99.90 106	98.64 131	99.75 102	99.82 44

PatchT		97.03 291	96.44 296	98.79 219	98.99 287	98.34 212	99.16 266	99.07 299	92.13 356	99.52 113	97.31 365	94.54 223	98.98 328	88.54 366	98.73 191	99.03 216

CANet		99.25 64	99.14 65	99.59 77	99.41 194	99.16 115	99.35 222	99.57 56	98.82 57	99.51 115	99.61 197	96.46 145	99.95 52	99.59 15	99.98 2	99.65 119

mPP-MVS		99.44 31	99.30 43	99.86 20	99.88 11	99.79 30	99.69 53	99.48 146	98.12 128	99.50 116	99.75 128	98.78 48	99.97 17	98.57 145	99.89 38	99.83 39

PatchMatch-RL		98.84 128	98.62 137	99.52 101	99.71 91	99.28 101	99.06 287	99.77 9	97.74 174	99.50 116	99.53 225	95.41 181	99.84 141	97.17 265	99.64 121	99.44 178

PVSNet	96.02 17	98.85 125	98.84 110	98.89 197	99.73 82	97.28 256	98.32 362	99.60 46	97.86 157	99.50 116	99.57 210	96.75 137	99.86 129	98.56 148	99.70 112	99.54 150

LS3D		99.27 59	99.12 67	99.74 52	99.18 251	99.75 39	99.56 120	99.57 56	98.45 86	99.49 119	99.85 47	97.77 106	99.94 61	98.33 169	99.84 67	99.52 156

MP-MVS		99.33 51	99.15 64	99.87 11	99.88 11	99.82 22	99.66 67	99.46 173	98.09 133	99.48 120	99.74 133	98.29 88	99.96 25	97.93 198	99.87 44	99.82 44
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
旧先验2							98.96 311		96.70 263	99.47 121			99.94 61	98.19 178

MSDG		98.98 106	98.80 113	99.53 95	99.76 60	99.19 110	98.75 335	99.55 69	97.25 221	99.47 121	99.77 119	97.82 104	99.87 126	96.93 278	99.90 29	99.54 150

CDS-MVSNet		99.09 94	99.03 78	99.25 147	99.42 191	98.73 177	99.45 176	99.46 173	98.11 130	99.46 123	99.77 119	98.01 100	99.37 263	98.70 122	98.92 178	99.66 115
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MSLP-MVS++		99.46 25	99.47 14	99.44 117	99.60 139	99.16 115	99.41 194	99.71 13	98.98 40	99.45 124	99.78 111	99.19 9	99.54 240	99.28 53	99.84 67	99.63 130

XVG-OURS		98.73 139	98.68 125	98.88 199	99.70 96	97.73 243	98.92 318	99.55 69	98.52 81	99.45 124	99.84 57	95.27 187	99.91 95	98.08 189	98.84 184	99.00 219

casdiffmvs_mvg		99.15 75	99.02 81	99.55 86	99.66 113	99.09 126	99.64 76	99.56 61	98.26 106	99.45 124	99.87 37	96.03 158	99.81 163	99.54 20	99.15 158	99.73 87
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tpmrst		98.33 169	98.48 152	97.90 296	99.16 259	94.78 335	99.31 230	99.11 292	97.27 219	99.45 124	99.59 202	95.33 185	99.84 141	98.48 155	98.61 192	99.09 207

TAMVS		99.12 85	99.08 72	99.24 149	99.46 183	98.55 192	99.51 147	99.46 173	98.09 133	99.45 124	99.82 68	98.34 86	99.51 241	98.70 122	98.93 176	99.67 112

ETV-MVS		99.26 61	99.21 59	99.40 120	99.46 183	99.30 99	99.56 120	99.52 93	98.52 81	99.44 129	99.27 297	98.41 83	99.86 129	99.10 69	99.59 126	99.04 215

CANet_DTU		98.97 108	98.87 105	99.25 147	99.33 215	98.42 210	99.08 283	99.30 263	99.16 13	99.43 130	99.75 128	95.27 187	99.97 17	98.56 148	99.95 9	99.36 187

SCA		98.19 180	98.16 170	98.27 273	99.30 223	95.55 318	99.07 284	98.97 308	97.57 189	99.43 130	99.57 210	92.72 270	99.74 186	97.58 231	99.20 153	99.52 156

testdata				99.54 87	99.75 68	98.95 152		99.51 107	97.07 239	99.43 130	99.70 148	98.87 37	99.94 61	97.76 215	99.64 121	99.72 93

DPM-MVS		98.95 109	98.71 122	99.66 59	99.63 124	99.55 69	98.64 345	99.10 293	97.93 152	99.42 133	99.55 216	98.67 64	99.80 169	95.80 308	99.68 116	99.61 134

XVG-OURS-SEG-HR		98.69 143	98.62 137	98.89 197	99.71 91	97.74 242	99.12 274	99.54 77	98.44 89	99.42 133	99.71 144	94.20 232	99.92 85	98.54 152	98.90 180	99.00 219

baseline		99.15 75	99.02 81	99.53 95	99.66 113	99.14 121	99.72 47	99.48 146	98.35 97	99.42 133	99.84 57	96.07 156	99.79 172	99.51 25	99.14 159	99.67 112

DP-MVS Recon		99.12 85	98.95 95	99.65 63	99.74 75	99.70 46	99.27 243	99.57 56	96.40 290	99.42 133	99.68 164	98.75 55	99.80 169	97.98 195	99.72 108	99.44 178

Effi-MVS+-dtu		98.78 133	98.89 103	98.47 250	99.33 215	96.91 283	99.57 114	99.30 263	98.47 84	99.41 137	98.99 327	96.78 135	99.74 186	98.73 119	99.38 139	98.74 245

casdiffmvs		99.13 79	98.98 90	99.56 84	99.65 119	99.16 115	99.56 120	99.50 126	98.33 100	99.41 137	99.86 42	95.92 164	99.83 152	99.45 35	99.16 155	99.70 103
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MIMVSNet		97.73 252	97.45 250	98.57 235	99.45 188	97.50 251	99.02 297	98.98 307	96.11 310	99.41 137	99.14 312	90.28 318	98.74 345	95.74 309	98.93 176	99.47 173

CSCG		99.32 52	99.32 34	99.32 132	99.85 25	98.29 213	99.71 49	99.66 27	98.11 130	99.41 137	99.80 94	98.37 85	99.96 25	98.99 79	99.96 8	99.72 93

F-COLMAP		99.19 67	99.04 76	99.64 68	99.78 51	99.27 103	99.42 192	99.54 77	97.29 218	99.41 137	99.59 202	98.42 82	99.93 74	98.19 178	99.69 113	99.73 87

EIA-MVS		99.18 69	99.09 71	99.45 113	99.49 173	99.18 112	99.67 62	99.53 88	97.66 182	99.40 142	99.44 251	98.10 96	99.81 163	98.94 84	99.62 124	99.35 188

mvsmamba		98.92 111	98.87 105	99.08 163	99.07 275	99.16 115	99.88 4	99.51 107	98.15 123	99.40 142	99.89 23	97.12 122	99.33 273	99.38 38	97.40 259	98.73 247

MDTV_nov1_ep13			98.32 162		99.11 266	94.44 341	99.27 243	98.74 336	97.51 197	99.40 142	99.62 193	94.78 206	99.76 183	97.59 230	98.81 188

iter_conf_final		98.71 140	98.61 143	98.99 176	99.49 173	98.96 147	99.63 80	99.41 203	98.19 117	99.39 145	99.77 119	94.82 202	99.38 258	99.30 51	97.52 243	98.64 283

CVMVSNet		98.57 152	98.67 126	98.30 268	99.35 209	95.59 317	99.50 153	99.55 69	98.60 75	99.39 145	99.83 61	94.48 224	99.45 245	98.75 116	98.56 198	99.85 26

CNVR-MVS		99.42 36	99.30 43	99.78 43	99.62 130	99.71 44	99.26 251	99.52 93	98.82 57	99.39 145	99.71 144	98.96 24	99.85 135	98.59 141	99.80 87	99.77 72

Effi-MVS+		98.81 129	98.59 144	99.48 107	99.46 183	99.12 124	98.08 368	99.50 126	97.50 198	99.38 148	99.41 259	96.37 149	99.81 163	99.11 68	98.54 199	99.51 162

mvs_anonymous		99.03 101	98.99 87	99.16 157	99.38 203	98.52 198	99.51 147	99.38 220	97.79 167	99.38 148	99.81 81	97.30 117	99.45 245	99.35 41	98.99 173	99.51 162

iter_conf05		98.55 153	98.44 153	98.87 203	99.34 213	98.60 189	99.55 130	99.42 200	98.21 114	99.37 150	99.77 119	93.55 252	99.38 258	99.30 51	97.48 251	98.63 291

XVS		99.53 11	99.42 17	99.87 11	99.85 25	99.83 16	99.69 53	99.68 20	98.98 40	99.37 150	99.74 133	98.81 44	99.94 61	98.79 113	99.86 52	99.84 30

X-MVStestdata		96.55 297	95.45 315	99.87 11	99.85 25	99.83 16	99.69 53	99.68 20	98.98 40	99.37 150	64.01 385	98.81 44	99.94 61	98.79 113	99.86 52	99.84 30

PatchmatchNet		98.31 170	98.36 158	98.19 276	99.16 259	95.32 326	99.27 243	98.92 314	97.37 212	99.37 150	99.58 206	94.90 199	99.70 208	97.43 249	99.21 152	99.54 150
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
AllTest		98.87 115	98.72 120	99.31 133	99.86 20	98.48 204	99.56 120	99.61 41	97.85 159	99.36 154	99.85 47	95.95 161	99.85 135	96.66 291	99.83 76	99.59 140

TestCases				99.31 133	99.86 20	98.48 204		99.61 41	97.85 159	99.36 154	99.85 47	95.95 161	99.85 135	96.66 291	99.83 76	99.59 140

Vis-MVSNet (Re-imp)		98.87 115	98.72 120	99.31 133	99.71 91	98.88 161	99.80 25	99.44 192	97.91 154	99.36 154	99.78 111	95.49 180	99.43 254	97.91 199	99.11 161	99.62 132

alignmvs		98.81 129	98.56 148	99.58 80	99.43 189	99.42 87	99.51 147	98.96 310	98.61 74	99.35 157	98.92 334	94.78 206	99.77 179	99.35 41	98.11 223	99.54 150

VPA-MVSNet		98.29 173	97.95 197	99.30 138	99.16 259	99.54 71	99.50 153	99.58 53	98.27 105	99.35 157	99.37 270	92.53 279	99.65 223	99.35 41	94.46 324	98.72 248

AdaColmap		99.01 105	98.80 113	99.66 59	99.56 149	99.54 71	99.18 264	99.70 15	98.18 121	99.35 157	99.63 188	96.32 150	99.90 106	97.48 243	99.77 97	99.55 148

test222					99.75 68	99.49 79	98.91 320	99.49 134	96.42 288	99.34 160	99.65 176	98.28 89			99.69 113	99.72 93

API-MVS		99.04 99	99.03 78	99.06 166	99.40 199	99.31 98	99.55 130	99.56 61	98.54 79	99.33 161	99.39 266	98.76 52	99.78 177	96.98 273	99.78 94	98.07 342

bld_raw_dy_0_64		98.69 143	98.58 145	98.99 176	98.88 300	98.96 147	99.80 25	99.41 203	97.91 154	99.32 162	99.87 37	95.70 174	99.31 279	99.09 70	97.27 264	98.71 250

v144192		97.92 221	97.60 235	98.87 203	98.83 310	98.65 183	99.55 130	99.34 238	96.20 301	99.32 162	99.40 262	94.36 227	99.26 286	96.37 299	95.03 315	98.70 255

GeoE		98.85 125	98.62 137	99.53 95	99.61 134	99.08 129	99.80 25	99.51 107	97.10 237	99.31 164	99.78 111	95.23 191	99.77 179	98.21 176	99.03 170	99.75 78

canonicalmvs		99.02 102	98.86 108	99.51 103	99.42 191	99.32 95	99.80 25	99.48 146	98.63 72	99.31 164	98.81 338	97.09 124	99.75 185	99.27 56	97.90 227	99.47 173

V42		98.06 195	97.79 211	98.86 207	98.98 290	98.84 167	99.69 53	99.34 238	96.53 278	99.30 166	99.37 270	94.67 215	99.32 276	97.57 235	94.66 321	98.42 323

ab-mvs		98.86 118	98.63 132	99.54 87	99.64 121	99.19 110	99.44 181	99.54 77	97.77 169	99.30 166	99.81 81	94.20 232	99.93 74	99.17 64	98.82 186	99.49 166

TAPA-MVS	97.07 15	97.74 251	97.34 270	98.94 184	99.70 96	97.53 250	99.25 253	99.51 107	91.90 357	99.30 166	99.63 188	98.78 48	99.64 226	88.09 368	99.87 44	99.65 119
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
新几何1				99.75 49	99.75 68	99.59 62		99.54 77	96.76 259	99.29 169	99.64 182	98.43 80	99.94 61	96.92 280	99.66 118	99.72 93

test_fmvs2		97.25 285	97.30 275	97.09 325	99.43 189	93.31 355	99.73 46	98.87 324	98.83 56	99.28 170	99.80 94	84.45 360	99.66 218	97.88 201	97.45 253	98.30 331

VPNet		97.84 233	97.44 255	99.01 172	99.21 244	98.94 155	99.48 167	99.57 56	98.38 92	99.28 170	99.73 139	88.89 333	99.39 257	99.19 61	93.27 340	98.71 250

HY-MVS	97.30 7	98.85 125	98.64 131	99.47 110	99.42 191	99.08 129	99.62 86	99.36 229	97.39 211	99.28 170	99.68 164	96.44 147	99.92 85	98.37 165	98.22 213	99.40 184

PAPM_NR		99.04 99	98.84 110	99.66 59	99.74 75	99.44 85	99.39 206	99.38 220	97.70 177	99.28 170	99.28 294	98.34 86	99.85 135	96.96 275	99.45 135	99.69 105

HPM-MVS++		99.39 45	99.23 58	99.87 11	99.75 68	99.84 15	99.43 185	99.51 107	98.68 71	99.27 174	99.53 225	98.64 67	99.96 25	98.44 160	99.80 87	99.79 64

v1240		97.69 259	97.32 273	98.79 219	98.85 308	98.43 208	99.48 167	99.36 229	96.11 310	99.27 174	99.36 273	93.76 249	99.24 290	94.46 330	95.23 310	98.70 255

thres600view7		97.86 229	97.51 243	98.92 188	99.72 86	97.95 233	99.59 99	98.74 336	97.94 151	99.27 174	98.62 344	91.75 296	99.86 129	93.73 339	98.19 217	98.96 225

PLC	97.94 4	99.02 102	98.85 109	99.53 95	99.66 113	99.01 138	99.24 255	99.52 93	96.85 255	99.27 174	99.48 242	98.25 90	99.91 95	97.76 215	99.62 124	99.65 119
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thres100view900		97.76 245	97.45 250	98.69 226	99.72 86	97.86 239	99.59 99	98.74 336	97.93 152	99.26 178	98.62 344	91.75 296	99.83 152	93.22 344	98.18 218	98.37 329

EPMVS		97.82 238	97.65 230	98.35 263	98.88 300	95.98 310	99.49 163	94.71 381	97.57 189	99.26 178	99.48 242	92.46 284	99.71 202	97.87 203	99.08 166	99.35 188

Fast-Effi-MVS+-dtu		98.77 135	98.83 112	98.60 230	99.41 194	96.99 277	99.52 141	99.49 134	98.11 130	99.24 180	99.34 280	96.96 131	99.79 172	97.95 197	99.45 135	99.02 218

v1921920		97.80 242	97.45 250	98.84 211	98.80 311	98.53 194	99.52 141	99.34 238	96.15 307	99.24 180	99.47 245	93.98 241	99.29 281	95.40 318	95.13 313	98.69 259

LPG-MVS_test		98.22 176	98.13 175	98.49 244	99.33 215	97.05 270	99.58 107	99.55 69	97.46 200	99.24 180	99.83 61	92.58 277	99.72 196	98.09 185	97.51 245	98.68 264

LGP-MVS_train				98.49 244	99.33 215	97.05 270		99.55 69	97.46 200	99.24 180	99.83 61	92.58 277	99.72 196	98.09 185	97.51 245	98.68 264

v1144		97.98 212	97.69 226	98.85 210	98.87 304	98.66 182	99.54 134	99.35 234	96.27 296	99.23 184	99.35 276	94.67 215	99.23 291	96.73 286	95.16 312	98.68 264

Anonymous20240529		98.09 191	97.68 227	99.34 126	99.66 113	98.44 207	99.40 202	99.43 198	93.67 345	99.22 185	99.89 23	90.23 322	99.93 74	99.26 57	98.33 205	99.66 115

OPM-MVS		98.19 180	98.10 178	98.45 252	98.88 300	97.07 268	99.28 238	99.38 220	98.57 76	99.22 185	99.81 81	92.12 288	99.66 218	98.08 189	97.54 242	98.61 303
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test_djsdf		98.67 146	98.57 146	98.98 178	98.70 326	98.91 159	99.88 4	99.46 173	97.55 191	99.22 185	99.88 29	95.73 172	99.28 282	99.03 75	97.62 235	98.75 242

test12				99.75 49	99.64 121	99.61 60		99.29 267		99.21 188		98.38 84	99.89 116		99.74 105	99.74 82

NCCC		99.34 50	99.19 61	99.79 41	99.61 134	99.65 56	99.30 232	99.48 146	98.86 52	99.21 188	99.63 188	98.72 59	99.90 106	98.25 174	99.63 123	99.80 60

PMMVS		98.80 132	98.62 137	99.34 126	99.27 232	98.70 179	98.76 334	99.31 259	97.34 213	99.21 188	99.07 318	97.20 120	99.82 158	98.56 148	98.87 181	99.52 156

v1192		97.81 240	97.44 255	98.91 192	98.88 300	98.68 180	99.51 147	99.34 238	96.18 303	99.20 191	99.34 280	94.03 239	99.36 267	95.32 320	95.18 311	98.69 259

EI-MVSNet		98.67 146	98.67 126	98.68 227	99.35 209	97.97 229	99.50 153	99.38 220	96.93 252	99.20 191	99.83 61	97.87 102	99.36 267	98.38 163	97.56 240	98.71 250

MVSTER		98.49 154	98.32 162	99.00 174	99.35 209	99.02 136	99.54 134	99.38 220	97.41 209	99.20 191	99.73 139	93.86 245	99.36 267	98.87 95	97.56 240	98.62 294

Anonymous202405211		98.30 172	97.98 193	99.26 146	99.57 145	98.16 219	99.41 194	98.55 348	96.03 315	99.19 194	99.74 133	91.87 293	99.92 85	99.16 65	98.29 210	99.70 103

v2v482		98.06 195	97.77 216	98.92 188	98.90 297	98.82 171	99.57 114	99.36 229	96.65 267	99.19 194	99.35 276	94.20 232	99.25 287	97.72 221	94.97 316	98.69 259

CNLPA		99.14 77	98.99 87	99.59 77	99.58 143	99.41 89	99.16 266	99.44 192	98.45 86	99.19 194	99.49 237	98.08 98	99.89 116	97.73 219	99.75 102	99.48 167

UGNet		98.87 115	98.69 124	99.40 120	99.22 243	98.72 178	99.44 181	99.68 20	99.24 11	99.18 197	99.42 255	92.74 269	99.96 25	99.34 45	99.94 13	99.53 155
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
tfpn200view9		97.72 254	97.38 263	98.72 224	99.69 100	97.96 231	99.50 153	98.73 341	97.83 162	99.17 198	98.45 349	91.67 300	99.83 152	93.22 344	98.18 218	98.37 329

thres400		97.77 244	97.38 263	98.92 188	99.69 100	97.96 231	99.50 153	98.73 341	97.83 162	99.17 198	98.45 349	91.67 300	99.83 152	93.22 344	98.18 218	98.96 225

Test_1112_low_res		98.89 113	98.66 129	99.57 82	99.69 100	98.95 152	99.03 294	99.47 164	96.98 245	99.15 200	99.23 302	96.77 136	99.89 116	98.83 108	98.78 189	99.86 23

baseline1		98.31 170	97.95 197	99.38 124	99.50 171	98.74 176	99.59 99	98.93 312	98.41 90	99.14 201	99.60 200	94.59 218	99.79 172	98.48 155	93.29 339	99.61 134

1112_ss		98.98 106	98.77 117	99.59 77	99.68 104	99.02 136	99.25 253	99.48 146	97.23 224	99.13 202	99.58 206	96.93 132	99.90 106	98.87 95	98.78 189	99.84 30

CLD-MVS		98.16 184	98.10 178	98.33 264	99.29 227	96.82 286	98.75 335	99.44 192	97.83 162	99.13 202	99.55 216	92.92 263	99.67 215	98.32 171	97.69 232	98.48 315
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
原ACMM1				99.65 63	99.73 82	99.33 94		99.47 164	97.46 200	99.12 204	99.66 175	98.67 64	99.91 95	97.70 224	99.69 113	99.71 102

tpm		97.67 264	97.55 237	98.03 285	99.02 284	95.01 332	99.43 185	98.54 349	96.44 286	99.12 204	99.34 280	91.83 295	99.60 234	97.75 217	96.46 280	99.48 167

HQP_MVS		98.27 175	98.22 168	98.44 255	99.29 227	96.97 279	99.39 206	99.47 164	98.97 43	99.11 206	99.61 197	92.71 272	99.69 213	97.78 211	97.63 233	98.67 271

plane_prior3						97.00 276			98.69 70	99.11 206

CHOSEN 1792x2688		99.19 67	99.10 69	99.45 113	99.89 8	98.52 198	99.39 206	99.94 1	98.73 67	99.11 206	99.89 23	95.50 179	99.94 61	99.50 26	99.97 5	99.89 10

v8		97.95 217	97.63 233	98.93 186	98.95 294	98.81 173	99.80 25	99.41 203	96.03 315	99.10 209	99.42 255	94.92 198	99.30 280	96.94 277	94.08 332	98.66 279

ADS-MVSNet2		98.02 205	98.07 185	97.87 297	99.33 215	95.19 329	99.23 256	99.08 296	96.24 298	99.10 209	99.67 170	94.11 236	98.93 338	96.81 283	99.05 168	99.48 167

ADS-MVSNet		98.20 179	98.08 182	98.56 238	99.33 215	96.48 298	99.23 256	99.15 288	96.24 298	99.10 209	99.67 170	94.11 236	99.71 202	96.81 283	99.05 168	99.48 167

thres200		97.61 268	97.28 277	98.62 229	99.64 121	98.03 225	99.26 251	98.74 336	97.68 179	99.09 212	98.32 353	91.66 302	99.81 163	92.88 348	98.22 213	98.03 345

dp		97.75 249	97.80 210	97.59 312	99.10 269	93.71 350	99.32 228	98.88 322	96.48 283	99.08 213	99.55 216	92.67 275	99.82 158	96.52 294	98.58 195	99.24 197

GBi-Net		97.68 261	97.48 245	98.29 269	99.51 162	97.26 259	99.43 185	99.48 146	96.49 280	99.07 214	99.32 287	90.26 319	98.98 328	97.10 266	96.65 275	98.62 294

test1		97.68 261	97.48 245	98.29 269	99.51 162	97.26 259	99.43 185	99.48 146	96.49 280	99.07 214	99.32 287	90.26 319	98.98 328	97.10 266	96.65 275	98.62 294

FMVSNet3		98.03 203	97.76 220	98.84 211	99.39 202	98.98 140	99.40 202	99.38 220	96.67 265	99.07 214	99.28 294	92.93 262	98.98 328	97.10 266	96.65 275	98.56 310

IterMVS-LS		98.46 157	98.42 155	98.58 234	99.59 141	98.00 227	99.37 213	99.43 198	96.94 251	99.07 214	99.59 202	97.87 102	99.03 321	98.32 171	95.62 302	98.71 250
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		98.08 193	98.16 170	97.85 298	99.55 153	94.67 338	99.70 50	98.92 314	98.15 123	99.06 218	99.35 276	93.67 251	99.25 287	97.77 214	97.25 265	99.64 126

pmmvs4		98.13 187	97.90 202	98.81 216	98.61 335	98.87 162	98.99 304	99.21 281	96.44 286	99.06 218	99.58 206	95.90 166	99.11 312	97.18 264	96.11 288	98.46 320

XVG-ACMP-BASELINE		97.83 235	97.71 225	98.20 275	99.11 266	96.33 303	99.41 194	99.52 93	98.06 142	99.05 220	99.50 234	89.64 328	99.73 192	97.73 219	97.38 261	98.53 311

CostFormer		97.72 254	97.73 223	97.71 308	99.15 262	94.02 346	99.54 134	99.02 303	94.67 336	99.04 221	99.35 276	92.35 287	99.77 179	98.50 154	97.94 226	99.34 190

DP-MVS		99.16 73	98.95 95	99.78 43	99.77 57	99.53 74	99.41 194	99.50 126	97.03 243	99.04 221	99.88 29	97.39 113	99.92 85	98.66 129	99.90 29	99.87 21

ACMM	97.58 5	98.37 167	98.34 160	98.48 246	99.41 194	97.10 264	99.56 120	99.45 184	98.53 80	99.04 221	99.85 47	93.00 261	99.71 202	98.74 117	97.45 253	98.64 283
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Fast-Effi-MVS+		98.70 141	98.43 154	99.51 103	99.51 162	99.28 101	99.52 141	99.47 164	96.11 310	99.01 224	99.34 280	96.20 154	99.84 141	97.88 201	98.82 186	99.39 185

nrg030		98.64 149	98.42 155	99.28 144	99.05 281	99.69 47	99.81 20	99.46 173	98.04 144	99.01 224	99.82 68	96.69 139	99.38 258	99.34 45	94.59 323	98.78 235

test_prior2							98.96 311		98.34 98	99.01 224	99.52 228	98.68 62		97.96 196	99.74 105

MAR-MVS		98.86 118	98.63 132	99.54 87	99.37 206	99.66 53	99.45 176	99.54 77	96.61 272	99.01 224	99.40 262	97.09 124	99.86 129	97.68 226	99.53 131	99.10 203
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
PS-MVSNAJss		98.92 111	98.92 97	98.90 194	98.78 315	98.53 194	99.78 32	99.54 77	98.07 138	99.00 228	99.76 125	99.01 18	99.37 263	99.13 66	97.23 266	98.81 232

PAPR		98.63 150	98.34 160	99.51 103	99.40 199	99.03 135	98.80 330	99.36 229	96.33 291	99.00 228	99.12 316	98.46 78	99.84 141	95.23 321	99.37 146	99.66 115

D2MVS		98.41 162	98.50 151	98.15 281	99.26 234	96.62 293	99.40 202	99.61 41	97.71 176	98.98 230	99.36 273	96.04 157	99.67 215	98.70 122	97.41 258	98.15 339

v10		97.85 230	97.52 241	98.86 207	98.99 287	98.67 181	99.75 40	99.41 203	95.70 319	98.98 230	99.41 259	94.75 211	99.23 291	96.01 304	94.63 322	98.67 271

miper_enhance_ethall		98.16 184	98.08 182	98.41 257	98.96 293	97.72 244	98.45 355	99.32 255	96.95 249	98.97 232	99.17 308	97.06 126	99.22 294	97.86 204	95.99 291	98.29 332

UniMVSNet (Re)		98.29 173	98.00 191	99.13 161	99.00 286	99.36 93	99.49 163	99.51 107	97.95 150	98.97 232	99.13 313	96.30 151	99.38 258	98.36 167	93.34 338	98.66 279

TEST9					99.67 105	99.65 56	99.05 289	99.41 203	96.22 300	98.95 234	99.49 237	98.77 51	99.91 95

train_agg		99.02 102	98.77 117	99.77 46	99.67 105	99.65 56	99.05 289	99.41 203	96.28 294	98.95 234	99.49 237	98.76 52	99.91 95	97.63 227	99.72 108	99.75 78

RRT_MVS		98.70 141	98.66 129	98.83 213	98.90 297	98.45 206	99.89 2	99.28 269	97.76 170	98.94 236	99.92 11	96.98 129	99.25 287	99.28 53	97.00 272	98.80 233

BH-RMVSNet		98.41 162	98.08 182	99.40 120	99.41 194	98.83 170	99.30 232	98.77 332	97.70 177	98.94 236	99.65 176	92.91 265	99.74 186	96.52 294	99.55 130	99.64 126

test_8					99.67 105	99.61 60	99.03 294	99.41 203	96.28 294	98.93 238	99.48 242	98.76 52	99.91 95

3Dnovator	97.25 9	99.24 65	99.05 74	99.81 36	99.12 264	99.66 53	99.84 13	99.74 10	99.09 24	98.92 239	99.90 19	95.94 163	99.98 10	98.95 83	99.92 16	99.79 64

v7n		97.87 227	97.52 241	98.92 188	98.76 319	98.58 190	99.84 13	99.46 173	96.20 301	98.91 240	99.70 148	94.89 200	99.44 250	96.03 303	93.89 334	98.75 242

JIA-IIPM		97.50 275	97.02 287	98.93 186	98.73 321	97.80 241	99.30 232	98.97 308	91.73 358	98.91 240	94.86 372	95.10 193	99.71 202	97.58 231	97.98 225	99.28 195

v148		97.79 243	97.55 237	98.50 243	98.74 320	97.72 244	99.54 134	99.33 245	96.26 297	98.90 242	99.51 231	94.68 214	99.14 304	97.83 207	93.15 342	98.63 291

GA-MVS		97.85 230	97.47 247	99.00 174	99.38 203	97.99 228	98.57 349	99.15 288	97.04 242	98.90 242	99.30 290	89.83 325	99.38 258	96.70 288	98.33 205	99.62 132

tpm2		97.44 280	97.34 270	97.74 307	99.15 262	94.36 343	99.45 176	98.94 311	93.45 350	98.90 242	99.44 251	91.35 308	99.59 235	97.31 253	98.07 224	99.29 194

tt0805		97.97 215	97.77 216	98.57 235	99.59 141	96.61 294	99.45 176	99.08 296	98.21 114	98.88 245	99.80 94	88.66 336	99.70 208	98.58 142	97.72 231	99.39 185

miper_ehance_all_eth		98.18 182	98.10 178	98.41 257	99.23 240	97.72 244	98.72 338	99.31 259	96.60 274	98.88 245	99.29 292	97.29 118	99.13 307	97.60 229	95.99 291	98.38 328

eth_miper_zixun_eth		98.05 200	97.96 195	98.33 264	99.26 234	97.38 254	98.56 351	99.31 259	96.65 267	98.88 245	99.52 228	96.58 141	99.12 311	97.39 251	95.53 305	98.47 317

cl22		97.85 230	97.64 232	98.48 246	99.09 272	97.87 237	98.60 348	99.33 245	97.11 236	98.87 248	99.22 303	92.38 286	99.17 303	98.21 176	95.99 291	98.42 323

agg_prior					99.67 105	99.62 59		99.40 211		98.87 248			99.91 95

anonymousdsp		98.44 158	98.28 165	98.94 184	98.50 341	98.96 147	99.77 34	99.50 126	97.07 239	98.87 248	99.77 119	94.76 210	99.28 282	98.66 129	97.60 236	98.57 309

DSMNet-mixed		97.25 285	97.35 267	96.95 329	97.84 351	93.61 353	99.57 114	96.63 374	96.13 309	98.87 248	98.61 346	94.59 218	97.70 365	95.08 323	98.86 182	99.55 148

FMVSNet2		97.72 254	97.36 265	98.80 218	99.51 162	98.84 167	99.45 176	99.42 200	96.49 280	98.86 252	99.29 292	90.26 319	98.98 328	96.44 296	96.56 278	98.58 308

c3_l		98.12 189	98.04 187	98.38 261	99.30 223	97.69 248	98.81 329	99.33 245	96.67 265	98.83 253	99.34 280	97.11 123	98.99 327	97.58 231	95.34 308	98.48 315

ITE_SJBPF				98.08 283	99.29 227	96.37 301		98.92 314	98.34 98	98.83 253	99.75 128	91.09 311	99.62 232	95.82 306	97.40 259	98.25 335

Anonymous20231211		97.88 225	97.54 240	98.90 194	99.71 91	98.53 194	99.48 167	99.57 56	94.16 341	98.81 255	99.68 164	93.23 256	99.42 255	98.84 105	94.42 326	98.76 240

Patchmtry		97.75 249	97.40 262	98.81 216	99.10 269	98.87 162	99.11 280	99.33 245	94.83 333	98.81 255	99.38 267	94.33 228	99.02 323	96.10 301	95.57 303	98.53 311

miper_lstm_enhance		98.00 210	97.91 201	98.28 272	99.34 213	97.43 253	98.88 322	99.36 229	96.48 283	98.80 257	99.55 216	95.98 159	98.91 339	97.27 255	95.50 306	98.51 313

BH-untuned		98.42 160	98.36 158	98.59 231	99.49 173	96.70 289	99.27 243	99.13 291	97.24 223	98.80 257	99.38 267	95.75 171	99.74 186	97.07 269	99.16 155	99.33 191

FIs		98.78 133	98.63 132	99.23 151	99.18 251	99.54 71	99.83 16	99.59 49	98.28 103	98.79 259	99.81 81	96.75 137	99.37 263	99.08 72	96.38 282	98.78 235

OurMVSNet-221017-0		97.88 225	97.77 216	98.19 276	98.71 325	96.53 296	99.88 4	99.00 305	97.79 167	98.78 260	99.94 4	91.68 299	99.35 270	97.21 258	96.99 273	98.69 259

MVS-HIRNet		95.75 313	95.16 318	97.51 314	99.30 223	93.69 351	98.88 322	95.78 376	85.09 371	98.78 260	92.65 374	91.29 309	99.37 263	94.85 326	99.85 59	99.46 175

tpmvs		97.98 212	98.02 190	97.84 300	99.04 282	94.73 336	99.31 230	99.20 282	96.10 314	98.76 262	99.42 255	94.94 195	99.81 163	96.97 274	98.45 203	98.97 223

Patchmatch-test		97.93 218	97.65 230	98.77 221	99.18 251	97.07 268	99.03 294	99.14 290	96.16 305	98.74 263	99.57 210	94.56 220	99.72 196	93.36 343	99.11 161	99.52 156

QAPM		98.67 146	98.30 164	99.80 38	99.20 246	99.67 51	99.77 34	99.72 11	94.74 335	98.73 264	99.90 19	95.78 170	99.98 10	96.96 275	99.88 41	99.76 77

3Dnovator+	97.12 13	99.18 69	98.97 91	99.82 33	99.17 257	99.68 48	99.81 20	99.51 107	99.20 12	98.72 265	99.89 23	95.68 175	99.97 17	98.86 100	99.86 52	99.81 51

IterMVS-SCA-FT		97.82 238	97.75 221	98.06 284	99.57 145	96.36 302	99.02 297	99.49 134	97.18 227	98.71 266	99.72 143	92.72 270	99.14 304	97.44 248	95.86 296	98.67 271

UniMVSNet_NR-MVSNet		98.22 176	97.97 194	98.96 181	98.92 296	98.98 140	99.48 167	99.53 88	97.76 170	98.71 266	99.46 249	96.43 148	99.22 294	98.57 145	92.87 345	98.69 259

DU-MVS		98.08 193	97.79 211	98.96 181	98.87 304	98.98 140	99.41 194	99.45 184	97.87 156	98.71 266	99.50 234	94.82 202	99.22 294	98.57 145	92.87 345	98.68 264

tpm cat1		97.39 281	97.36 265	97.50 315	99.17 257	93.73 349	99.43 185	99.31 259	91.27 359	98.71 266	99.08 317	94.31 230	99.77 179	96.41 298	98.50 201	99.00 219

XXY-MVS		98.38 166	98.09 181	99.24 149	99.26 234	99.32 95	99.56 120	99.55 69	97.45 203	98.71 266	99.83 61	93.23 256	99.63 231	98.88 92	96.32 284	98.76 240

IterMVS		97.83 235	97.77 216	98.02 287	99.58 143	96.27 305	99.02 297	99.48 146	97.22 225	98.71 266	99.70 148	92.75 267	99.13 307	97.46 246	96.00 290	98.67 271
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		98.75 136	98.62 137	99.15 160	99.08 274	99.45 84	99.86 12	99.60 46	98.23 111	98.70 272	99.82 68	96.80 134	99.22 294	99.07 73	96.38 282	98.79 234

COLMAP_ROB	97.56 6	98.86 118	98.75 119	99.17 156	99.88 11	98.53 194	99.34 225	99.59 49	97.55 191	98.70 272	99.89 23	95.83 168	99.90 106	98.10 184	99.90 29	99.08 208
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TR-MVS		97.76 245	97.41 261	98.82 214	99.06 278	97.87 237	98.87 324	98.56 347	96.63 271	98.68 274	99.22 303	92.49 280	99.65 223	95.40 318	97.79 229	98.95 227

WR-MVS		98.06 195	97.73 223	99.06 166	98.86 307	99.25 106	99.19 263	99.35 234	97.30 217	98.66 275	99.43 253	93.94 242	99.21 299	98.58 142	94.28 328	98.71 250

HQP-NCC					99.19 248		98.98 307		98.24 108	98.66 275

ACMP_Plane					99.19 248		98.98 307		98.24 108	98.66 275

HQP4-MVS										98.66 275			99.64 226			98.64 283

HQP-MVS		98.02 205	97.90 202	98.37 262	99.19 248	96.83 284	98.98 307	99.39 214	98.24 108	98.66 275	99.40 262	92.47 281	99.64 226	97.19 262	97.58 238	98.64 283

LF4IMVS		97.52 272	97.46 249	97.70 309	98.98 290	95.55 318	99.29 236	98.82 328	98.07 138	98.66 275	99.64 182	89.97 324	99.61 233	97.01 270	96.68 274	97.94 352

mvs_tets		98.40 165	98.23 167	98.91 192	98.67 329	98.51 200	99.66 67	99.53 88	98.19 117	98.65 281	99.81 81	92.75 267	99.44 250	99.31 48	97.48 251	98.77 238

TESTMET0.1,1		97.55 270	97.27 280	98.40 259	98.93 295	96.53 296	98.67 341	97.61 365	96.96 247	98.64 282	99.28 294	88.63 338	99.45 245	97.30 254	99.38 139	99.21 199

jajsoiax		98.43 159	98.28 165	98.88 199	98.60 336	98.43 208	99.82 17	99.53 88	98.19 117	98.63 283	99.80 94	93.22 258	99.44 250	99.22 59	97.50 247	98.77 238

Baseline_NR-MVSNet		97.76 245	97.45 250	98.68 227	99.09 272	98.29 213	99.41 194	98.85 325	95.65 320	98.63 283	99.67 170	94.82 202	99.10 314	98.07 192	92.89 344	98.64 283

EPNet		98.86 118	98.71 122	99.30 138	97.20 363	98.18 218	99.62 86	98.91 318	99.28 10	98.63 283	99.81 81	95.96 160	99.99 4	99.24 58	99.72 108	99.73 87
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test-LLR		98.06 195	97.90 202	98.55 240	98.79 312	97.10 264	98.67 341	97.75 362	97.34 213	98.61 286	98.85 335	94.45 225	99.45 245	97.25 256	99.38 139	99.10 203

test-mter		97.49 278	97.13 284	98.55 240	98.79 312	97.10 264	98.67 341	97.75 362	96.65 267	98.61 286	98.85 335	88.23 342	99.45 245	97.25 256	99.38 139	99.10 203

DIV-MVS_self_test		98.01 208	97.85 208	98.48 246	99.24 239	97.95 233	98.71 339	99.35 234	96.50 279	98.60 288	99.54 221	95.72 173	99.03 321	97.21 258	95.77 297	98.46 320

cl____		98.01 208	97.84 209	98.55 240	99.25 238	97.97 229	98.71 339	99.34 238	96.47 285	98.59 289	99.54 221	95.65 176	99.21 299	97.21 258	95.77 297	98.46 320

FMVSNet1		96.84 293	96.36 297	98.29 269	99.32 221	97.26 259	99.43 185	99.48 146	95.11 327	98.55 290	99.32 287	83.95 362	98.98 328	95.81 307	96.26 285	98.62 294

UniMVSNet_ETH3D		97.32 283	96.81 290	98.87 203	99.40 199	97.46 252	99.51 147	99.53 88	95.86 318	98.54 291	99.77 119	82.44 366	99.66 218	98.68 127	97.52 243	99.50 165

AUN-MVS		96.88 292	96.31 298	98.59 231	99.48 181	97.04 273	99.27 243	99.22 278	97.44 205	98.51 292	99.41 259	91.97 291	99.66 218	97.71 222	83.83 369	99.07 213

PCF-MVS	97.08 14	97.66 265	97.06 286	99.47 110	99.61 134	99.09 126	98.04 369	99.25 274	91.24 360	98.51 292	99.70 148	94.55 222	99.91 95	92.76 351	99.85 59	99.42 180
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TranMVSNet+NR-MVSNet		97.93 218	97.66 229	98.76 222	98.78 315	98.62 186	99.65 73	99.49 134	97.76 170	98.49 294	99.60 200	94.23 231	98.97 335	98.00 194	92.90 343	98.70 255

CP-MVSNet		98.09 191	97.78 214	99.01 172	98.97 292	99.24 107	99.67 62	99.46 173	97.25 221	98.48 295	99.64 182	93.79 247	99.06 317	98.63 132	94.10 331	98.74 245

ACMP	97.20 11	98.06 195	97.94 199	98.45 252	99.37 206	97.01 275	99.44 181	99.49 134	97.54 194	98.45 296	99.79 105	91.95 292	99.72 196	97.91 199	97.49 250	98.62 294
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
cascas		97.69 259	97.43 259	98.48 246	98.60 336	97.30 255	98.18 367	99.39 214	92.96 353	98.41 297	98.78 340	93.77 248	99.27 285	98.16 182	98.61 192	98.86 229

WR-MVS_H		98.13 187	97.87 207	98.90 194	99.02 284	98.84 167	99.70 50	99.59 49	97.27 219	98.40 298	99.19 307	95.53 178	99.23 291	98.34 168	93.78 335	98.61 303

BH-w/o		98.00 210	97.89 206	98.32 266	99.35 209	96.20 307	99.01 302	98.90 320	96.42 288	98.38 299	99.00 326	95.26 189	99.72 196	96.06 302	98.61 192	99.03 216

pmmvs5		97.52 272	97.30 275	98.16 278	98.57 338	96.73 288	99.27 243	98.90 320	96.14 308	98.37 300	99.53 225	91.54 305	99.14 304	97.51 240	95.87 295	98.63 291

EU-MVSNet		97.98 212	98.03 188	97.81 304	98.72 323	96.65 292	99.66 67	99.66 27	98.09 133	98.35 301	99.82 68	95.25 190	98.01 358	97.41 250	95.30 309	98.78 235

FMVSNet5		96.43 301	96.19 300	97.15 321	99.11 266	95.89 312	99.32 228	99.52 93	94.47 340	98.34 302	99.07 318	87.54 349	97.07 369	92.61 352	95.72 300	98.47 317

PS-CasMVS		97.93 218	97.59 236	98.95 183	98.99 287	99.06 132	99.68 59	99.52 93	97.13 231	98.31 303	99.68 164	92.44 285	99.05 318	98.51 153	94.08 332	98.75 242

USDC		97.34 282	97.20 281	97.75 306	99.07 275	95.20 328	98.51 353	99.04 302	97.99 148	98.31 303	99.86 42	89.02 331	99.55 239	95.67 313	97.36 262	98.49 314

PEN-MVS		97.76 245	97.44 255	98.72 224	98.77 318	98.54 193	99.78 32	99.51 107	97.06 241	98.29 305	99.64 182	92.63 276	98.89 341	98.09 185	93.16 341	98.72 248

tfpnnormal		97.84 233	97.47 247	98.98 178	99.20 246	99.22 109	99.64 76	99.61 41	96.32 292	98.27 306	99.70 148	93.35 255	99.44 250	95.69 311	95.40 307	98.27 333

ppachtmachnet_test		97.49 278	97.45 250	97.61 311	98.62 333	95.24 327	98.80 330	99.46 173	96.11 310	98.22 307	99.62 193	96.45 146	98.97 335	93.77 338	95.97 294	98.61 303

our_test_3		97.65 266	97.68 227	97.55 313	98.62 333	94.97 333	98.84 326	99.30 263	96.83 258	98.19 308	99.34 280	97.01 128	99.02 323	95.00 325	96.01 289	98.64 283

LTVRE_ROB	97.16 12	98.02 205	97.90 202	98.40 259	99.23 240	96.80 287	99.70 50	99.60 46	97.12 233	98.18 309	99.70 148	91.73 298	99.72 196	98.39 162	97.45 253	98.68 264
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
ACMH	97.28 8	98.10 190	97.99 192	98.44 255	99.41 194	96.96 281	99.60 93	99.56 61	98.09 133	98.15 310	99.91 13	90.87 314	99.70 208	98.88 92	97.45 253	98.67 271
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MS-PatchMatch		97.24 287	97.32 273	96.99 326	98.45 343	93.51 354	98.82 328	99.32 255	97.41 209	98.13 311	99.30 290	88.99 332	99.56 237	95.68 312	99.80 87	97.90 355

MVS		97.28 284	96.55 294	99.48 107	98.78 315	98.95 152	99.27 243	99.39 214	83.53 372	98.08 312	99.54 221	96.97 130	99.87 126	94.23 334	99.16 155	99.63 130

PAPM		97.59 269	97.09 285	99.07 165	99.06 278	98.26 215	98.30 363	99.10 293	94.88 332	98.08 312	99.34 280	96.27 152	99.64 226	89.87 361	98.92 178	99.31 193

OpenMVS	96.50 16	98.47 156	98.12 176	99.52 101	99.04 282	99.53 74	99.82 17	99.72 11	94.56 338	98.08 312	99.88 29	94.73 212	99.98 10	97.47 245	99.76 100	99.06 214

gg-mvs-nofinetune		96.17 306	95.32 317	98.73 223	98.79 312	98.14 221	99.38 211	94.09 382	91.07 362	98.07 315	91.04 378	89.62 329	99.35 270	96.75 285	99.09 165	98.68 264

test0.0.03 1		97.71 257	97.42 260	98.56 238	98.41 344	97.82 240	98.78 332	98.63 345	97.34 213	98.05 316	98.98 329	94.45 225	98.98 328	95.04 324	97.15 270	98.89 228

APD_test1		95.87 310	96.49 295	94.00 344	99.53 156	84.01 371	99.54 134	99.32 255	95.91 317	97.99 317	99.85 47	85.49 356	99.88 121	91.96 354	98.84 184	98.12 340

1314		98.68 145	98.54 149	99.11 162	98.89 299	98.65 183	99.27 243	99.49 134	96.89 253	97.99 317	99.56 213	97.72 108	99.83 152	97.74 218	99.27 150	98.84 231

DTE-MVSNet		97.51 274	97.19 282	98.46 251	98.63 332	98.13 222	99.84 13	99.48 146	96.68 264	97.97 319	99.67 170	92.92 263	98.56 347	96.88 282	92.60 348	98.70 255

SixPastTwentyTwo		97.50 275	97.33 272	98.03 285	98.65 330	96.23 306	99.77 34	98.68 344	97.14 230	97.90 320	99.93 7	90.45 317	99.18 302	97.00 271	96.43 281	98.67 271

pm-mvs1		97.68 261	97.28 277	98.88 199	99.06 278	98.62 186	99.50 153	99.45 184	96.32 292	97.87 321	99.79 105	92.47 281	99.35 270	97.54 238	93.54 337	98.67 271

testgi		97.65 266	97.50 244	98.13 282	99.36 208	96.45 299	99.42 192	99.48 146	97.76 170	97.87 321	99.45 250	91.09 311	98.81 342	94.53 329	98.52 200	99.13 202

EPNet_dtu		98.03 203	97.96 195	98.23 274	98.27 345	95.54 320	99.23 256	98.75 333	99.02 30	97.82 323	99.71 144	96.11 155	99.48 242	93.04 347	99.65 120	99.69 105
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TinyColmap		97.12 289	96.89 289	97.83 301	99.07 275	95.52 321	98.57 349	98.74 336	97.58 188	97.81 324	99.79 105	88.16 343	99.56 237	95.10 322	97.21 267	98.39 327

ACMH+	97.24 10	97.92 221	97.78 214	98.32 266	99.46 183	96.68 291	99.56 120	99.54 77	98.41 90	97.79 325	99.87 37	90.18 323	99.66 218	98.05 193	97.18 269	98.62 294

N_pmnet		94.95 322	95.83 309	92.31 350	98.47 342	79.33 379	99.12 274	92.81 386	93.87 343	97.68 326	99.13 313	93.87 244	99.01 325	91.38 356	96.19 286	98.59 307

KD-MVS_2432*1600		94.62 323	93.72 329	97.31 318	97.19 364	95.82 313	98.34 359	99.20 282	95.00 330	97.57 327	98.35 351	87.95 345	98.10 355	92.87 349	77.00 376	98.01 346

miper_refine_blended		94.62 323	93.72 329	97.31 318	97.19 364	95.82 313	98.34 359	99.20 282	95.00 330	97.57 327	98.35 351	87.95 345	98.10 355	92.87 349	77.00 376	98.01 346

PVSNet_0	94.43 19	96.09 308	95.47 314	97.94 293	99.31 222	94.34 344	97.81 370	99.70 15	97.12 233	97.46 329	98.75 341	89.71 326	99.79 172	97.69 225	81.69 372	99.68 109

pmmvs6		96.53 298	96.09 303	97.82 303	98.69 327	95.47 322	99.37 213	99.47 164	93.46 349	97.41 330	99.78 111	87.06 351	99.33 273	96.92 280	92.70 347	98.65 281

new_pmnet		96.38 302	96.03 304	97.41 316	98.13 348	95.16 331	99.05 289	99.20 282	93.94 342	97.39 331	98.79 339	91.61 304	99.04 319	90.43 359	95.77 297	98.05 344

CL-MVSNet_self_test		94.49 325	93.97 328	96.08 339	96.16 368	93.67 352	98.33 361	99.38 220	95.13 325	97.33 332	98.15 355	92.69 274	96.57 372	88.67 365	79.87 374	97.99 349

IB-MVS	95.67 18	96.22 303	95.44 316	98.57 235	99.21 244	96.70 289	98.65 344	97.74 364	96.71 262	97.27 333	98.54 347	86.03 353	99.92 85	98.47 158	86.30 366	99.10 203
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
GG-mvs-BLEND				98.45 252	98.55 339	98.16 219	99.43 185	93.68 383		97.23 334	98.46 348	89.30 330	99.22 294	95.43 317	98.22 213	97.98 350

MVP-Stereo		97.81 240	97.75 221	97.99 291	97.53 356	96.60 295	98.96 311	98.85 325	97.22 225	97.23 334	99.36 273	95.28 186	99.46 244	95.51 315	99.78 94	97.92 354
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Anonymous20240521		96.20 305	95.89 308	97.13 323	97.72 355	94.96 334	99.79 31	99.29 267	93.01 352	97.20 336	99.03 323	89.69 327	98.36 351	91.16 357	96.13 287	98.07 342

TransMVSNet (Re)		97.15 288	96.58 293	98.86 207	99.12 264	98.85 166	99.49 163	98.91 318	95.48 322	97.16 337	99.80 94	93.38 254	99.11 312	94.16 336	91.73 350	98.62 294

KD-MVS_self_test		95.00 320	94.34 325	96.96 328	97.07 366	95.39 325	99.56 120	99.44 192	95.11 327	97.13 338	97.32 364	91.86 294	97.27 368	90.35 360	81.23 373	98.23 337

NR-MVSNet		97.97 215	97.61 234	99.02 171	98.87 304	99.26 105	99.47 172	99.42 200	97.63 184	97.08 339	99.50 234	95.07 194	99.13 307	97.86 204	93.59 336	98.68 264

Anonymous20231206		96.22 303	96.03 304	96.79 333	97.31 361	94.14 345	99.63 80	99.08 296	96.17 304	97.04 340	99.06 320	93.94 242	97.76 364	86.96 372	95.06 314	98.47 317

test_0402		96.64 296	96.24 299	97.85 298	98.85 308	96.43 300	99.44 181	99.26 272	93.52 347	96.98 341	99.52 228	88.52 339	99.20 301	92.58 353	97.50 247	97.93 353

MIMVSNet1		95.51 314	95.04 319	96.92 330	97.38 358	95.60 316	99.52 141	99.50 126	93.65 346	96.97 342	99.17 308	85.28 358	96.56 373	88.36 367	95.55 304	98.60 306

TDRefinement		95.42 316	94.57 323	97.97 292	89.83 382	96.11 309	99.48 167	98.75 333	96.74 260	96.68 343	99.88 29	88.65 337	99.71 202	98.37 165	82.74 371	98.09 341

baseline2		97.87 227	97.55 237	98.82 214	99.18 251	98.02 226	99.41 194	96.58 375	96.97 246	96.51 344	99.17 308	93.43 253	99.57 236	97.71 222	99.03 170	98.86 229

pmmvs3		94.09 329	93.25 333	96.60 335	94.76 376	94.49 340	98.92 318	98.18 357	89.66 363	96.48 345	98.06 357	86.28 352	97.33 367	89.68 362	87.20 365	97.97 351

DeepMVS_CX				93.34 347	99.29 227	82.27 374		99.22 278	85.15 370	96.33 346	99.05 321	90.97 313	99.73 192	93.57 341	97.77 230	98.01 346

LCM-MVSNet-Re		97.83 235	98.15 172	96.87 331	99.30 223	92.25 360	99.59 99	98.26 352	97.43 206	96.20 347	99.13 313	96.27 152	98.73 346	98.17 181	98.99 173	99.64 126

test20.03		96.12 307	95.96 306	96.63 334	97.44 357	95.45 323	99.51 147	99.38 220	96.55 277	96.16 348	99.25 300	93.76 249	96.17 374	87.35 371	94.22 329	98.27 333

K. test v3		97.10 290	96.79 291	98.01 288	98.72 323	96.33 303	99.87 9	97.05 369	97.59 186	96.16 348	99.80 94	88.71 334	99.04 319	96.69 289	96.55 279	98.65 281

UnsupCasMVSNet_eth		96.44 300	96.12 301	97.40 317	98.65 330	95.65 315	99.36 217	99.51 107	97.13 231	96.04 350	98.99 327	88.40 340	98.17 354	96.71 287	90.27 358	98.40 326

test_method		91.10 335	91.36 337	90.31 356	95.85 369	73.72 386	94.89 375	99.25 274	68.39 378	95.82 351	99.02 325	80.50 368	98.95 337	93.64 340	94.89 320	98.25 335

lessismore_v0				97.79 305	98.69 327	95.44 324		94.75 380		95.71 352	99.87 37	88.69 335	99.32 276	95.89 305	94.93 318	98.62 294

test_vis1_rt		95.81 312	95.65 312	96.32 338	99.67 105	91.35 364	99.49 163	96.74 373	98.25 107	95.24 353	98.10 356	74.96 370	99.90 106	99.53 22	98.85 183	97.70 358

dmvs_testset		95.02 319	96.12 301	91.72 352	99.10 269	80.43 377	99.58 107	97.87 361	97.47 199	95.22 354	98.82 337	93.99 240	95.18 377	88.09 368	94.91 319	99.56 147

Patchmatch-RL test		95.84 311	95.81 310	95.95 340	95.61 371	90.57 365	98.24 364	98.39 351	95.10 329	95.20 355	98.67 343	94.78 206	97.77 363	96.28 300	90.02 359	99.51 162

test_fmvs3		92.10 333	91.77 336	93.08 348	96.19 367	86.25 369	99.82 17	98.62 346	96.65 267	95.19 356	96.90 366	55.05 381	95.93 376	96.63 293	90.92 356	97.06 365

ambc				93.06 349	92.68 378	82.36 373	98.47 354	98.73 341		95.09 357	97.41 361	55.55 379	99.10 314	96.42 297	91.32 351	97.71 356

PM-MVS		92.96 332	92.23 335	95.14 342	95.61 371	89.98 367	99.37 213	98.21 355	94.80 334	95.04 358	97.69 359	65.06 374	97.90 361	94.30 331	89.98 360	97.54 362

OpenMVS_ROB	92.34 20	94.38 327	93.70 331	96.41 337	97.38 358	93.17 356	99.06 287	98.75 333	86.58 369	94.84 359	98.26 354	81.53 367	99.32 276	89.01 364	97.87 228	96.76 366

mvsany_test3		93.77 330	93.45 332	94.74 343	95.78 370	88.01 368	99.64 76	98.25 353	98.28 103	94.31 360	97.97 358	68.89 373	98.51 349	97.50 241	90.37 357	97.71 356

EG-PatchMatch MVS		95.97 309	95.69 311	96.81 332	97.78 352	92.79 358	99.16 266	98.93 312	96.16 305	94.08 361	99.22 303	82.72 364	99.47 243	95.67 313	97.50 247	98.17 338

test_f		91.90 334	91.26 338	93.84 345	95.52 374	85.92 370	99.69 53	98.53 350	95.31 324	93.87 362	96.37 369	55.33 380	98.27 352	95.70 310	90.98 355	97.32 364

pmmvs-eth3d		95.34 318	94.73 321	97.15 321	95.53 373	95.94 311	99.35 222	99.10 293	95.13 325	93.55 363	97.54 360	88.15 344	97.91 360	94.58 328	89.69 361	97.61 359

new-patchmatchnet		94.48 326	94.08 326	95.67 341	95.08 375	92.41 359	99.18 264	99.28 269	94.55 339	93.49 364	97.37 363	87.86 347	97.01 370	91.57 355	88.36 362	97.61 359

UnsupCasMVSNet_bld		93.53 331	92.51 334	96.58 336	97.38 358	93.82 347	98.24 364	99.48 146	91.10 361	93.10 365	96.66 367	74.89 371	98.37 350	94.03 337	87.71 364	97.56 361

Gipuma		90.99 336	90.15 341	93.51 346	98.73 321	90.12 366	93.98 376	99.45 184	79.32 374	92.28 366	94.91 371	69.61 372	97.98 359	87.42 370	95.67 301	92.45 374
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CMPMVS	69.68 23	94.13 328	94.90 320	91.84 351	97.24 362	80.01 378	98.52 352	99.48 146	89.01 366	91.99 367	99.67 170	85.67 355	99.13 307	95.44 316	97.03 271	96.39 368
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testf1		90.42 337	90.68 339	89.65 357	97.78 352	73.97 384	99.13 272	98.81 329	89.62 364	91.80 368	98.93 332	62.23 377	98.80 343	86.61 374	91.17 352	96.19 369

APD_test2		90.42 337	90.68 339	89.65 357	97.78 352	73.97 384	99.13 272	98.81 329	89.62 364	91.80 368	98.93 332	62.23 377	98.80 343	86.61 374	91.17 352	96.19 369

PMMVS2		86.87 340	85.37 344	91.35 354	90.21 381	83.80 372	98.89 321	97.45 368	83.13 373	91.67 370	95.03 370	48.49 383	94.70 378	85.86 376	77.62 375	95.54 371

LCM-MVSNet		86.80 341	85.22 345	91.53 353	87.81 383	80.96 376	98.23 366	98.99 306	71.05 376	90.13 371	96.51 368	48.45 384	96.88 371	90.51 358	85.30 367	96.76 366

ET-MVSNet_ETH3D		96.49 299	95.64 313	99.05 168	99.53 156	98.82 171	98.84 326	97.51 367	97.63 184	84.77 372	99.21 306	92.09 289	98.91 339	98.98 80	92.21 349	99.41 182

E-PMN		80.61 345	79.88 347	82.81 362	90.75 380	76.38 382	97.69 371	95.76 377	66.44 380	83.52 373	92.25 375	62.54 376	87.16 382	68.53 381	61.40 379	84.89 380

FPMVS		84.93 342	85.65 343	82.75 363	86.77 384	63.39 388	98.35 358	98.92 314	74.11 375	83.39 374	98.98 329	50.85 382	92.40 380	84.54 377	94.97 316	92.46 373

EMVS		80.02 346	79.22 348	82.43 364	91.19 379	76.40 381	97.55 373	92.49 387	66.36 381	83.01 375	91.27 377	64.63 375	85.79 383	65.82 382	60.65 380	85.08 379

test_vis3_rt		87.04 339	85.81 342	90.73 355	93.99 377	81.96 375	99.76 37	90.23 388	92.81 354	81.35 376	91.56 376	40.06 385	99.07 316	94.27 333	88.23 363	91.15 376

YYNet1		95.36 317	94.51 324	97.92 294	97.89 350	97.10 264	99.10 282	99.23 277	93.26 351	80.77 377	99.04 322	92.81 266	98.02 357	94.30 331	94.18 330	98.64 283

MDA-MVSNet_test_wron		95.45 315	94.60 322	98.01 288	98.16 347	97.21 262	99.11 280	99.24 276	93.49 348	80.73 378	98.98 329	93.02 260	98.18 353	94.22 335	94.45 325	98.64 283

MDA-MVSNet-bldmvs		94.96 321	93.98 327	97.92 294	98.24 346	97.27 257	99.15 269	99.33 245	93.80 344	80.09 379	99.03 323	88.31 341	97.86 362	93.49 342	94.36 327	98.62 294

tmp_tt		82.80 343	81.52 346	86.66 359	66.61 389	68.44 387	92.79 378	97.92 359	68.96 377	80.04 380	99.85 47	85.77 354	96.15 375	97.86 204	43.89 382	95.39 372

MVE	76.82 21	76.91 348	74.31 352	84.70 360	85.38 386	76.05 383	96.88 374	93.17 384	67.39 379	71.28 381	89.01 380	21.66 391	87.69 381	71.74 380	72.29 378	90.35 377
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		77.30 347	74.86 351	84.62 361	75.88 387	77.61 380	97.63 372	93.15 385	88.81 367	64.27 382	89.29 379	36.51 386	83.93 384	75.89 379	52.31 381	92.33 375

PMVS	70.75 22	75.98 349	74.97 350	79.01 365	70.98 388	55.18 389	93.37 377	98.21 355	65.08 382	61.78 383	93.83 373	21.74 390	92.53 379	78.59 378	91.12 354	89.34 378
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		39.01 352	42.50 354	28.53 367	39.17 390	20.91 391	98.75 335	19.17 392	19.83 385	38.57 384	66.67 382	33.16 387	15.42 386	37.50 385	29.66 384	49.26 381

testmvs		39.17 351	43.78 353	25.37 368	36.04 391	16.84 392	98.36 357	26.56 390	20.06 384	38.51 385	67.32 381	29.64 388	15.30 387	37.59 384	39.90 383	43.98 382

wuyk23d		40.18 350	41.29 355	36.84 366	86.18 385	49.12 390	79.73 379	22.81 391	27.64 383	25.46 386	28.45 386	21.98 389	48.89 385	55.80 383	23.56 385	12.51 383

EGC-MVSNET		82.80 343	77.86 349	97.62 310	97.91 349	96.12 308	99.33 227	99.28 269	8.40 386	25.05 387	99.27 297	84.11 361	99.33 273	89.20 363	98.22 213	97.42 363

test_blank		0.13 356	0.17 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	1.57 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet_test		0.02 357	0.03 360	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.27 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

DCPMVS		0.02 357	0.03 360	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.27 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

cdsmvs_eth3d_5k		24.64 353	32.85 356	0.00 369	0.00 392	0.00 393	0.00 380	99.51 107	0.00 387	0.00 388	99.56 213	96.58 141	0.00 388	0.00 386	0.00 386	0.00 384

pcd_1.5k_mvsjas		8.27 355	11.03 358	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.27 388	99.01 18	0.00 388	0.00 386	0.00 386	0.00 384

sosnet-low-res		0.02 357	0.03 360	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.27 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet		0.02 357	0.03 360	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.27 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uncertanet		0.02 357	0.03 360	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.27 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

Regformer		0.02 357	0.03 360	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.27 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

ab-mvs-re		8.30 354	11.06 357	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	99.58 206	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet		0.02 357	0.03 360	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.27 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

MSC_two_6792asdad				99.87 11	99.51 162	99.76 37		99.33 245					99.96 25	98.87 95	99.84 67	99.89 10

No_MVS				99.87 11	99.51 162	99.76 37		99.33 245					99.96 25	98.87 95	99.84 67	99.89 10

eth-test2					0.00 392

eth-test					0.00 392

OPU-MVS				99.64 68	99.56 149	99.72 42	99.60 93				99.70 148	99.27 5	99.42 255	98.24 175	99.80 87	99.79 64

save fliter					99.76 60	99.59 62	99.14 271	99.40 211	99.00 35

test_0728_SECOND				99.91 2	99.84 31	99.89 4	99.57 114	99.51 107					99.96 25	98.93 86	99.86 52	99.88 16

GSMVS																99.52 156

sam_mvs1												94.86 201				99.52 156

sam_mvs												94.72 213

MTGPA								99.47 164

test_post1							99.23 256				65.14 384	94.18 235	99.71 202	97.58 231

test_post											65.99 383	94.65 217	99.73 192

patchmatchnet-post											98.70 342	94.79 205	99.74 186

MTMP							99.54 134	98.88 322

gm-plane-assit					98.54 340	92.96 357			94.65 337		99.15 311		99.64 226	97.56 236

test9_res														97.49 242	99.72 108	99.75 78

agg_prior2														97.21 258	99.73 107	99.75 78

test_prior4						99.56 67	98.99 304

test_prior				99.68 58	99.67 105	99.48 81		99.56 61					99.83 152			99.74 82

新几何2							99.01 302

旧先验1					99.74 75	99.59 62		99.54 77			99.69 158	98.47 77			99.68 116	99.73 87

无先验							98.99 304	99.51 107	96.89 253				99.93 74	97.53 239		99.72 93

原ACMM2							98.95 314

testdata2													99.95 52	96.67 290

segment_acmp												98.96 24

testdata1							98.85 325		98.32 101

plane_prior7					99.29 227	97.03 274

plane_prior6					99.27 232	96.98 278						92.71 272

plane_prior5								99.47 164					99.69 213	97.78 211	97.63 233	98.67 271

plane_prior4											99.61 197

plane_prior2							99.39 206		98.97 43

plane_prior1					99.26 234

plane_prior						96.97 279	99.21 262		98.45 86						97.60 236

n2								0.00 393

nn								0.00 393

door-mid								98.05 358

test11								99.35 234

door								97.92 359

HQP5-MVS						96.83 284

BP-MVS														97.19 262

HQP3-MVS								99.39 214							97.58 238

HQP2-MVS												92.47 281

NP-MVS					99.23 240	96.92 282					99.40 262

ACMMP++_ref															97.19 268

ACMMP++															97.43 257

Test By Simon												98.75 55

High-resolution multi-view benchmark