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.

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 10	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 10	100.00 1	99.85 20

Gipuma		99.03 58	99.16 47	98.64 180	99.94 2	98.51 101	99.32 22	99.75 32	99.58 28	98.60 213	99.62 34	98.22 76	99.51 335	97.70 145	99.73 143	97.89 365
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 25	99.31 31	99.53 34	99.91 3	98.98 66	99.63 6	99.58 56	99.44 38	99.78 28	99.76 10	96.39 198	99.92 51	99.44 35	99.92 52	99.68 53

pmmvs6		99.67 3	99.70 3	99.60 11	99.90 4	99.27 23	99.53 8	99.76 29	99.64 18	99.84 20	99.83 3	99.50 8	99.87 101	99.36 37	99.92 52	99.64 62

PS-MVSNAJss		99.46 14	99.49 12	99.35 69	99.90 4	98.15 127	99.20 44	99.65 47	99.48 32	99.92 8	99.71 17	98.07 88	99.96 12	99.53 29	100.00 1	99.93 8

testf1		99.25 34	99.16 47	99.51 43	99.89 6	99.63 4	98.71 97	99.69 38	98.90 101	99.43 78	99.35 86	98.86 28	99.67 269	97.81 136	99.81 98	99.24 222

APD_test2		99.25 34	99.16 47	99.51 43	99.89 6	99.63 4	98.71 97	99.69 38	98.90 101	99.43 78	99.35 86	98.86 28	99.67 269	97.81 136	99.81 98	99.24 222

ANet_high		99.57 7	99.67 5	99.28 84	99.89 6	98.09 134	99.14 53	99.93 4	99.82 3	99.93 6	99.81 5	99.17 18	99.94 35	99.31 40	100.00 1	99.82 25

anonymousdsp		99.51 11	99.47 16	99.62 6	99.88 9	99.08 64	99.34 19	99.69 38	98.93 99	99.65 47	99.72 16	98.93 26	99.95 23	99.11 54	100.00 1	99.82 25

v7n		99.53 9	99.57 9	99.41 59	99.88 9	98.54 99	99.45 10	99.61 52	99.66 16	99.68 41	99.66 27	98.44 61	99.95 23	99.73 18	99.96 23	99.75 43

mvs_tets		99.63 5	99.67 5	99.49 48	99.88 9	98.61 91	99.34 19	99.71 34	99.27 57	99.90 12	99.74 13	99.68 4	99.97 5	99.55 28	99.99 5	99.88 15

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 63	99.87 12	98.13 130	98.08 165	99.95 1	99.45 36	99.98 2	99.75 11	99.80 1	99.97 5	99.82 7	99.99 5	99.99 1

jajsoiax		99.58 6	99.61 8	99.48 50	99.87 12	98.61 91	99.28 36	99.66 46	99.09 83	99.89 15	99.68 20	99.53 7	99.97 5	99.50 32	99.99 5	99.87 16

test_djsdf		99.52 10	99.51 11	99.53 34	99.86 14	98.74 81	99.39 16	99.56 70	99.11 73	99.70 37	99.73 15	99.00 22	99.97 5	99.26 45	99.98 12	99.89 12

MIMVSNet1		99.38 24	99.32 29	99.55 24	99.86 14	99.19 38	99.41 13	99.59 54	99.59 26	99.71 35	99.57 43	97.12 158	99.90 65	99.21 50	99.87 74	99.54 107

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 22	99.85 16	99.11 60	99.90 1	99.78 27	99.63 20	99.78 28	99.67 25	99.48 9	99.81 181	99.30 41	99.97 19	99.77 35
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
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 16	99.69 4	99.58 56	99.90 2	99.86 18	99.78 8	99.58 6	99.95 23	99.00 63	99.95 29	99.78 33

SixPastTwentyTwo		98.75 96	98.62 106	99.16 104	99.83 18	97.96 154	99.28 36	98.20 320	99.37 45	99.70 37	99.65 31	92.65 303	99.93 42	99.04 60	99.84 84	99.60 73

Baseline_NR-MVSNet		98.98 65	98.86 75	99.36 63	99.82 19	98.55 96	97.47 246	99.57 63	99.37 45	99.21 120	99.61 37	96.76 182	99.83 157	98.06 120	99.83 91	99.71 46

pm-mvs1		99.44 15	99.48 14	99.33 77	99.80 20	98.63 88	99.29 32	99.63 48	99.30 54	99.65 47	99.60 39	99.16 20	99.82 167	99.07 57	99.83 91	99.56 96

TransMVSNet (Re)		99.44 15	99.47 16	99.36 63	99.80 20	98.58 94	99.27 38	99.57 63	99.39 43	99.75 32	99.62 34	99.17 18	99.83 157	99.06 58	99.62 188	99.66 57

K. test v3		98.00 194	97.66 217	99.03 129	99.79 22	97.56 186	99.19 48	92.47 398	99.62 23	99.52 64	99.66 27	89.61 327	99.96 12	99.25 47	99.81 98	99.56 96

test_fmvsmconf0.1_n		99.49 12	99.54 10	99.34 72	99.78 23	98.11 131	97.77 208	99.90 9	99.33 50	99.97 3	99.66 27	99.71 3	99.96 12	99.79 12	99.99 5	99.96 5

APD_test1		98.83 83	98.66 100	99.34 72	99.78 23	99.47 7	98.42 134	99.45 110	98.28 141	98.98 150	99.19 118	97.76 111	99.58 311	96.57 224	99.55 214	98.97 268

test_vis3_rt		99.14 46	99.17 45	99.07 119	99.78 23	98.38 108	98.92 77	99.94 2	97.80 178	99.91 11	99.67 25	97.15 157	98.91 393	99.76 15	99.56 211	99.92 9

EGC-MVSNET		85.24 377	80.54 380	99.34 72	99.77 26	99.20 35	99.08 57	99.29 180	12.08 415	20.84 416	99.42 76	97.55 129	99.85 122	97.08 177	99.72 150	98.96 270

Anonymous20240521		98.69 107	98.87 72	98.16 243	99.77 26	95.11 285	99.08 57	99.44 114	99.34 49	99.33 97	99.55 50	94.10 279	99.94 35	99.25 47	99.96 23	99.42 162

FC-MVSNet-test		99.27 31	99.25 39	99.34 72	99.77 26	98.37 110	99.30 31	99.57 63	99.61 25	99.40 85	99.50 60	97.12 158	99.85 122	99.02 62	99.94 36	99.80 29

test_vis1_n		98.31 166	98.50 122	97.73 275	99.76 29	94.17 310	98.68 100	99.91 7	96.31 284	99.79 27	99.57 43	92.85 299	99.42 354	99.79 12	99.84 84	99.60 73

test_fmvs3		99.12 51	99.41 19	98.25 235	99.76 29	95.07 286	99.05 63	99.94 2	97.78 180	99.82 21	99.84 2	98.56 54	99.71 249	99.96 1	99.96 23	99.97 3

XXY-MVS		99.14 46	99.15 52	99.10 113	99.76 29	97.74 175	98.85 86	99.62 49	98.48 127	99.37 90	99.49 66	98.75 36	99.86 109	98.20 110	99.80 108	99.71 46

TDRefinement		99.42 20	99.38 22	99.55 24	99.76 29	99.33 17	99.68 5	99.71 34	99.38 44	99.53 62	99.61 37	98.64 44	99.80 188	98.24 107	99.84 84	99.52 118

fmvsm_s_conf0.1_n_a		99.17 42	99.30 33	98.80 159	99.75 33	96.59 236	97.97 185	99.86 13	98.22 144	99.88 17	99.71 17	98.59 50	99.84 140	99.73 18	99.98 12	99.98 2

tt0805		98.69 107	98.62 106	98.90 149	99.75 33	99.30 18	99.15 52	96.97 353	98.86 104	98.87 178	97.62 329	98.63 46	98.96 390	99.41 36	98.29 342	98.45 333

test_vis1_n_1920		98.40 152	98.92 69	96.81 330	99.74 35	90.76 380	98.15 156	99.91 7	98.33 133	99.89 15	99.55 50	95.07 250	99.88 84	99.76 15	99.93 41	99.79 30

FOURS1					99.73 36	99.67 3	99.43 11	99.54 78	99.43 40	99.26 112

PEN-MVS		99.41 21	99.34 26	99.62 6	99.73 36	99.14 53	99.29 32	99.54 78	99.62 23	99.56 54	99.42 76	98.16 84	99.96 12	98.78 74	99.93 41	99.77 35

lessismore_v0				98.97 137	99.73 36	97.53 188		86.71 412		99.37 90	99.52 59	89.93 325	99.92 51	98.99 64	99.72 150	99.44 155

SteuartSystems-ACMMP		98.79 89	98.54 117	99.54 27	99.73 36	99.16 44	98.23 147	99.31 164	97.92 169	98.90 169	98.90 191	98.00 94	99.88 84	96.15 256	99.72 150	99.58 85
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 184	98.15 175	98.22 238	99.73 36	95.15 282	97.36 252	99.68 43	94.45 338	98.99 149	99.27 101	96.87 172	99.94 35	97.13 174	99.91 59	99.57 90

Vis-MVSNet		99.34 26	99.36 23	99.27 87	99.73 36	98.26 117	99.17 49	99.78 27	99.11 73	99.27 108	99.48 67	98.82 31	99.95 23	98.94 66	99.93 41	99.59 79
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSC-MVS		98.71 100	98.74 84	98.62 185	99.72 42	96.08 254	98.74 90	98.64 301	99.74 9	99.67 43	99.24 108	94.57 265	99.95 23	99.11 54	99.24 268	99.82 25

test_f		98.67 115	98.87 72	98.05 252	99.72 42	95.59 264	98.51 121	99.81 23	96.30 286	99.78 28	99.82 4	96.14 209	98.63 399	99.82 7	99.93 41	99.95 6

ACMH	96.65 7	99.25 34	99.24 40	99.26 89	99.72 42	98.38 108	99.07 60	99.55 74	98.30 136	99.65 47	99.45 73	99.22 15	99.76 224	98.44 98	99.77 124	99.64 62
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n		99.16 45	99.33 27	98.64 180	99.71 45	96.10 249	97.87 197	99.85 15	98.56 124	99.90 12	99.68 20	98.69 41	99.85 122	99.72 20	99.98 12	99.97 3

PS-CasMVS		99.40 22	99.33 27	99.62 6	99.71 45	99.10 61	99.29 32	99.53 81	99.53 30	99.46 73	99.41 79	98.23 73	99.95 23	98.89 70	99.95 29	99.81 28

DTE-MVSNet		99.43 19	99.35 24	99.66 4	99.71 45	99.30 18	99.31 26	99.51 85	99.64 18	99.56 54	99.46 69	98.23 73	99.97 5	98.78 74	99.93 41	99.72 45

WR-MVS_H		99.33 27	99.22 41	99.65 5	99.71 45	99.24 26	99.32 22	99.55 74	99.46 35	99.50 69	99.34 90	97.30 147	99.93 42	98.90 68	99.93 41	99.77 35

HPM-MVS_fast		99.01 60	98.82 78	99.57 17	99.71 45	99.35 13	99.00 68	99.50 87	97.33 223	98.94 165	98.86 201	98.75 36	99.82 167	97.53 152	99.71 155	99.56 96

ACMH+	96.62 9	99.08 56	99.00 63	99.33 77	99.71 45	98.83 76	98.60 107	99.58 56	99.11 73	99.53 62	99.18 122	98.81 32	99.67 269	96.71 214	99.77 124	99.50 124

PMVS	91.26 20	97.86 206	97.94 196	97.65 279	99.71 45	97.94 156	98.52 116	98.68 297	98.99 92	97.52 299	99.35 86	97.41 142	98.18 404	91.59 368	99.67 174	96.82 392
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 46	99.09 56	99.29 83	99.70 52	98.28 116	99.13 54	99.52 84	99.48 32	99.24 117	99.41 79	96.79 179	99.82 167	98.69 84	99.88 71	99.76 39

VPNet		98.87 78	98.83 77	99.01 132	99.70 52	97.62 184	98.43 132	99.35 146	99.47 34	99.28 106	99.05 152	96.72 185	99.82 167	98.09 117	99.36 248	99.59 79

test_cas_vis1_n_1920		98.33 163	98.68 97	97.27 307	99.69 54	92.29 356	98.03 173	99.85 15	97.62 189	99.96 4	99.62 34	93.98 280	99.74 236	99.52 31	99.86 78	99.79 30

MP-MVS-pluss		98.57 129	98.23 165	99.60 11	99.69 54	99.35 13	97.16 270	99.38 133	94.87 328	98.97 154	98.99 170	98.01 93	99.88 84	97.29 162	99.70 160	99.58 85
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 38	99.32 29	98.96 138	99.68 56	97.35 197	98.84 88	99.48 96	99.69 12	99.63 50	99.68 20	99.03 21	99.96 12	97.97 127	99.92 52	99.57 90

sd_testset		99.28 30	99.31 31	99.19 100	99.68 56	98.06 143	99.41 13	99.30 172	99.69 12	99.63 50	99.68 20	99.25 14	99.96 12	97.25 165	99.92 52	99.57 90

test_fmvs1_n		98.09 188	98.28 157	97.52 293	99.68 56	93.47 335	98.63 103	99.93 4	95.41 317	99.68 41	99.64 32	91.88 312	99.48 342	99.82 7	99.87 74	99.62 66

CHOSEN 1792x2688		97.49 234	97.14 250	98.54 203	99.68 56	96.09 252	96.50 302	99.62 49	91.58 376	98.84 181	98.97 176	92.36 305	99.88 84	96.76 207	99.95 29	99.67 56

tfpnnormal		98.90 75	98.90 71	98.91 146	99.67 60	97.82 167	99.00 68	99.44 114	99.45 36	99.51 68	99.24 108	98.20 79	99.86 109	95.92 265	99.69 163	99.04 255

MTAPA		98.88 77	98.64 103	99.61 9	99.67 60	99.36 12	98.43 132	99.20 203	98.83 108	98.89 171	98.90 191	96.98 168	99.92 51	97.16 169	99.70 160	99.56 96

test_fmvsmvis_n_1920		99.26 33	99.49 12	98.54 203	99.66 62	96.97 219	98.00 179	99.85 15	99.24 59	99.92 8	99.50 60	99.39 11	99.95 23	99.89 3	99.98 12	98.71 309

fmvsm_l_conf0.5_n_a		99.19 41	99.27 36	98.94 141	99.65 63	97.05 215	97.80 204	99.76 29	98.70 112	99.78 28	99.11 138	98.79 34	99.95 23	99.85 5	99.96 23	99.83 22

WB-MVS		98.52 141	98.55 115	98.43 217	99.65 63	95.59 264	98.52 116	98.77 287	99.65 17	99.52 64	99.00 169	94.34 271	99.93 42	98.65 86	98.83 315	99.76 39

CP-MVSNet		99.21 39	99.09 56	99.56 22	99.65 63	98.96 71	99.13 54	99.34 152	99.42 41	99.33 97	99.26 103	97.01 166	99.94 35	98.74 79	99.93 41	99.79 30

HPM-MVS		98.79 89	98.53 118	99.59 15	99.65 63	99.29 20	99.16 50	99.43 120	96.74 266	98.61 211	98.38 275	98.62 47	99.87 101	96.47 236	99.67 174	99.59 79
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 124	98.36 147	99.42 57	99.65 63	99.42 8	98.55 112	99.57 63	97.72 183	98.90 169	99.26 103	96.12 211	99.52 330	95.72 276	99.71 155	99.32 203

fmvsm_l_conf0.5_n		99.21 39	99.28 35	99.02 131	99.64 68	97.28 201	97.82 201	99.76 29	98.73 109	99.82 21	99.09 144	98.81 32	99.95 23	99.86 4	99.96 23	99.83 22

test_fmvsmconf_n		99.44 15	99.48 14	99.31 82	99.64 68	98.10 133	97.68 219	99.84 18	99.29 55	99.92 8	99.57 43	99.60 5	99.96 12	99.74 17	99.98 12	99.89 12

TSAR-MVS + MP.		98.63 121	98.49 126	99.06 125	99.64 68	97.90 158	98.51 121	98.94 252	96.96 253	99.24 117	98.89 197	97.83 104	99.81 181	96.88 197	99.49 233	99.48 138
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 85	98.72 88	99.12 109	99.64 68	98.54 99	97.98 182	99.68 43	97.62 189	99.34 96	99.18 122	97.54 130	99.77 218	97.79 138	99.74 140	99.04 255

KD-MVS_self_test		99.25 34	99.18 44	99.44 56	99.63 72	99.06 65	98.69 99	99.54 78	99.31 52	99.62 53	99.53 56	97.36 145	99.86 109	99.24 49	99.71 155	99.39 175

EU-MVSNet		97.66 223	98.50 122	95.13 371	99.63 72	85.84 401	98.35 140	98.21 319	98.23 143	99.54 58	99.46 69	95.02 251	99.68 266	98.24 107	99.87 74	99.87 16

HyFIR lowres test		97.19 259	96.60 283	98.96 138	99.62 74	97.28 201	95.17 364	99.50 87	94.21 343	99.01 147	98.32 283	86.61 345	99.99 2	97.10 176	99.84 84	99.60 73

ACMMP_NAP		98.75 96	98.48 127	99.57 17	99.58 75	99.29 20	97.82 201	99.25 192	96.94 255	98.78 188	99.12 137	98.02 92	99.84 140	97.13 174	99.67 174	99.59 79

nrg030		99.40 22	99.35 24	99.54 27	99.58 75	99.13 56	98.98 71	99.48 96	99.68 14	99.46 73	99.26 103	98.62 47	99.73 241	99.17 53	99.92 52	99.76 39

VDDNet		98.21 179	97.95 194	99.01 132	99.58 75	97.74 175	99.01 66	97.29 345	99.67 15	98.97 154	99.50 60	90.45 322	99.80 188	97.88 133	99.20 276	99.48 138

COLMAP_ROB	96.50 10	98.99 62	98.85 76	99.41 59	99.58 75	99.10 61	98.74 90	99.56 70	99.09 83	99.33 97	99.19 118	98.40 63	99.72 248	95.98 263	99.76 136	99.42 162
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 27	99.45 18	98.99 134	99.57 79	97.73 177	97.93 186	99.83 20	99.22 60	99.93 6	99.30 97	99.42 10	99.96 12	99.85 5	99.99 5	99.29 212

ZNCC-MVS		98.68 112	98.40 139	99.54 27	99.57 79	99.21 29	98.46 129	99.29 180	97.28 229	98.11 257	98.39 273	98.00 94	99.87 101	96.86 200	99.64 182	99.55 103

MSP-MVS		98.40 152	98.00 190	99.61 9	99.57 79	99.25 25	98.57 110	99.35 146	97.55 200	99.31 105	97.71 322	94.61 264	99.88 84	96.14 257	99.19 279	99.70 51
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
testgi		98.32 164	98.39 142	98.13 244	99.57 79	95.54 267	97.78 206	99.49 94	97.37 220	99.19 122	97.65 326	98.96 24	99.49 339	96.50 235	98.99 304	99.34 196

MP-MVS		98.46 146	98.09 180	99.54 27	99.57 79	99.22 28	98.50 123	99.19 207	97.61 192	97.58 293	98.66 238	97.40 143	99.88 84	94.72 301	99.60 195	99.54 107
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 100	98.46 131	99.47 53	99.57 79	98.97 67	98.23 147	99.48 96	96.60 271	99.10 132	99.06 145	98.71 39	99.83 157	95.58 283	99.78 118	99.62 66

LGP-MVS_train				99.47 53	99.57 79	98.97 67		99.48 96	96.60 271	99.10 132	99.06 145	98.71 39	99.83 157	95.58 283	99.78 118	99.62 66

IS-MVSNet		98.19 181	97.90 200	99.08 117	99.57 79	97.97 151	99.31 26	98.32 315	99.01 91	98.98 150	99.03 156	91.59 313	99.79 201	95.49 285	99.80 108	99.48 138

dcpmvs_2		98.78 91	99.11 53	97.78 266	99.56 87	93.67 331	99.06 61	99.86 13	99.50 31	99.66 44	99.26 103	97.21 155	99.99 2	98.00 125	99.91 59	99.68 53

test_0402		98.76 95	98.71 91	98.93 143	99.56 87	98.14 129	98.45 131	99.34 152	99.28 56	98.95 158	98.91 188	98.34 69	99.79 201	95.63 280	99.91 59	98.86 288

EPP-MVSNet		98.30 167	98.04 186	99.07 119	99.56 87	97.83 164	99.29 32	98.07 326	99.03 89	98.59 215	99.13 136	92.16 308	99.90 65	96.87 198	99.68 168	99.49 128

ACMMP		98.75 96	98.50 122	99.52 39	99.56 87	99.16 44	98.87 83	99.37 137	97.16 244	98.82 185	99.01 166	97.71 114	99.87 101	96.29 248	99.69 163	99.54 107
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
fmvsm_s_conf0.5_n_a		99.10 53	99.20 43	98.78 165	99.55 91	96.59 236	97.79 205	99.82 22	98.21 145	99.81 25	99.53 56	98.46 60	99.84 140	99.70 21	99.97 19	99.90 11

fmvsm_s_conf0.5_n		99.09 54	99.26 38	98.61 188	99.55 91	96.09 252	97.74 213	99.81 23	98.55 125	99.85 19	99.55 50	98.60 49	99.84 140	99.69 23	99.98 12	99.89 12

FMVSNet1		99.17 42	99.17 45	99.17 101	99.55 91	98.24 119	99.20 44	99.44 114	99.21 62	99.43 78	99.55 50	97.82 107	99.86 109	98.42 100	99.89 69	99.41 165

Vis-MVSNet (Re-imp)		97.46 236	97.16 247	98.34 227	99.55 91	96.10 249	98.94 75	98.44 310	98.32 135	98.16 251	98.62 247	88.76 332	99.73 241	93.88 327	99.79 113	99.18 236

ACMM	96.08 12	98.91 73	98.73 86	99.48 50	99.55 91	99.14 53	98.07 167	99.37 137	97.62 189	99.04 143	98.96 179	98.84 30	99.79 201	97.43 156	99.65 180	99.49 128
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 104	98.97 67	97.89 259	99.54 96	94.05 313	98.55 112	99.92 6	96.78 264	99.72 33	99.78 8	96.60 190	99.67 269	99.91 2	99.90 65	99.94 7

mPP-MVS		98.64 119	98.34 150	99.54 27	99.54 96	99.17 40	98.63 103	99.24 197	97.47 207	98.09 259	98.68 233	97.62 123	99.89 75	96.22 251	99.62 188	99.57 90

XVG-ACMP-BASELINE		98.56 130	98.34 150	99.22 97	99.54 96	98.59 93	97.71 216	99.46 106	97.25 232	98.98 150	98.99 170	97.54 130	99.84 140	95.88 266	99.74 140	99.23 224

region2R		98.69 107	98.40 139	99.54 27	99.53 99	99.17 40	98.52 116	99.31 164	97.46 212	98.44 232	98.51 259	97.83 104	99.88 84	96.46 237	99.58 204	99.58 85

PGM-MVS		98.66 116	98.37 146	99.55 24	99.53 99	99.18 39	98.23 147	99.49 94	97.01 252	98.69 200	98.88 198	98.00 94	99.89 75	95.87 269	99.59 199	99.58 85

Patchmatch-RL test		97.26 252	97.02 254	97.99 256	99.52 101	95.53 268	96.13 325	99.71 34	97.47 207	99.27 108	99.16 128	84.30 366	99.62 294	97.89 130	99.77 124	98.81 295

ACMMPR		98.70 104	98.42 137	99.54 27	99.52 101	99.14 53	98.52 116	99.31 164	97.47 207	98.56 220	98.54 255	97.75 112	99.88 84	96.57 224	99.59 199	99.58 85

GST-MVS		98.61 125	98.30 155	99.52 39	99.51 103	99.20 35	98.26 145	99.25 192	97.44 215	98.67 202	98.39 273	97.68 115	99.85 122	96.00 261	99.51 225	99.52 118

Anonymous20231206		98.21 179	98.21 166	98.20 239	99.51 103	95.43 273	98.13 157	99.32 159	96.16 289	98.93 166	98.82 210	96.00 216	99.83 157	97.32 161	99.73 143	99.36 190

ACMP	95.32 15	98.41 150	98.09 180	99.36 63	99.51 103	98.79 79	97.68 219	99.38 133	95.76 304	98.81 187	98.82 210	98.36 65	99.82 167	94.75 298	99.77 124	99.48 138
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 94	98.52 119	99.52 39	99.50 106	99.21 29	98.02 175	98.84 276	97.97 163	99.08 134	99.02 157	97.61 124	99.88 84	96.99 184	99.63 185	99.48 138
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_SECOND				99.60 11	99.50 106	99.23 27	98.02 175	99.32 159					99.88 84	96.99 184	99.63 185	99.68 53

test0726					99.50 106	99.21 29	98.17 155	99.35 146	97.97 163	99.26 112	99.06 145	97.61 124

AllTest		98.44 148	98.20 167	99.16 104	99.50 106	98.55 96	98.25 146	99.58 56	96.80 262	98.88 174	99.06 145	97.65 118	99.57 313	94.45 308	99.61 193	99.37 184

TestCases				99.16 104	99.50 106	98.55 96		99.58 56	96.80 262	98.88 174	99.06 145	97.65 118	99.57 313	94.45 308	99.61 193	99.37 184

XVG-OURS		98.53 138	98.34 150	99.11 111	99.50 106	98.82 78	95.97 331	99.50 87	97.30 227	99.05 141	98.98 174	99.35 12	99.32 368	95.72 276	99.68 168	99.18 236

EG-PatchMatch MVS		98.99 62	99.01 62	98.94 141	99.50 106	97.47 190	98.04 172	99.59 54	98.15 156	99.40 85	99.36 85	98.58 53	99.76 224	98.78 74	99.68 168	99.59 79

SED-MVS		98.91 73	98.72 88	99.49 48	99.49 113	99.17 40	98.10 163	99.31 164	98.03 159	99.66 44	99.02 157	98.36 65	99.88 84	96.91 190	99.62 188	99.41 165

IU-MVS					99.49 113	99.15 48		98.87 267	92.97 361	99.41 82				96.76 207	99.62 188	99.66 57

test_241102_ONE					99.49 113	99.17 40		99.31 164	97.98 162	99.66 44	98.90 191	98.36 65	99.48 342

UA-Net		99.47 13	99.40 20	99.70 2	99.49 113	99.29 20	99.80 3	99.72 33	99.82 3	99.04 143	99.81 5	98.05 91	99.96 12	98.85 71	99.99 5	99.86 19

HFP-MVS		98.71 100	98.44 134	99.51 43	99.49 113	99.16 44	98.52 116	99.31 164	97.47 207	98.58 217	98.50 263	97.97 98	99.85 122	96.57 224	99.59 199	99.53 115

VPA-MVSNet		99.30 29	99.30 33	99.28 84	99.49 113	98.36 113	99.00 68	99.45 110	99.63 20	99.52 64	99.44 74	98.25 71	99.88 84	99.09 56	99.84 84	99.62 66

XVG-OURS-SEG-HR		98.49 143	98.28 157	99.14 107	99.49 113	98.83 76	96.54 299	99.48 96	97.32 225	99.11 129	98.61 249	99.33 13	99.30 371	96.23 250	98.38 338	99.28 214

114514_t		96.50 292	95.77 299	98.69 177	99.48 120	97.43 194	97.84 200	99.55 74	81.42 408	96.51 350	98.58 252	95.53 236	99.67 269	93.41 340	99.58 204	98.98 265

IterMVS-LS		98.55 134	98.70 94	98.09 245	99.48 120	94.73 294	97.22 265	99.39 131	98.97 95	99.38 88	99.31 96	96.00 216	99.93 42	98.58 89	99.97 19	99.60 73
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v8		99.01 60	99.16 47	98.57 195	99.47 122	96.31 246	98.90 78	99.47 104	99.03 89	99.52 64	99.57 43	96.93 169	99.81 181	99.60 24	99.98 12	99.60 73

XVS		98.72 99	98.45 132	99.53 34	99.46 123	99.21 29	98.65 101	99.34 152	98.62 117	97.54 297	98.63 245	97.50 136	99.83 157	96.79 203	99.53 220	99.56 96

X-MVStestdata		94.32 338	92.59 356	99.53 34	99.46 123	99.21 29	98.65 101	99.34 152	98.62 117	97.54 297	45.85 413	97.50 136	99.83 157	96.79 203	99.53 220	99.56 96

test20.03		98.78 91	98.77 83	98.78 165	99.46 123	97.20 208	97.78 206	99.24 197	99.04 88	99.41 82	98.90 191	97.65 118	99.76 224	97.70 145	99.79 113	99.39 175

CSCG		98.68 112	98.50 122	99.20 98	99.45 126	98.63 88	98.56 111	99.57 63	97.87 173	98.85 179	98.04 304	97.66 117	99.84 140	96.72 212	99.81 98	99.13 244

GeoE		99.05 57	98.99 65	99.25 92	99.44 127	98.35 114	98.73 94	99.56 70	98.42 129	98.91 168	98.81 212	98.94 25	99.91 60	98.35 102	99.73 143	99.49 128

v148		98.45 147	98.60 111	98.00 255	99.44 127	94.98 287	97.44 248	99.06 233	98.30 136	99.32 103	98.97 176	96.65 188	99.62 294	98.37 101	99.85 80	99.39 175

v10		98.97 66	99.11 53	98.55 200	99.44 127	96.21 248	98.90 78	99.55 74	98.73 109	99.48 70	99.60 39	96.63 189	99.83 157	99.70 21	99.99 5	99.61 72

V42		98.78 91	98.78 82	98.76 169	99.44 127	97.04 216	98.27 144	99.19 207	97.87 173	99.25 116	99.16 128	96.84 173	99.78 212	99.21 50	99.84 84	99.46 147

MDA-MVSNet-bldmvs		97.94 198	97.91 199	98.06 250	99.44 127	94.96 288	96.63 297	99.15 223	98.35 131	98.83 182	99.11 138	94.31 272	99.85 122	96.60 221	98.72 321	99.37 184

casdiffmvs_mvg		99.12 51	99.16 47	98.99 134	99.43 132	97.73 177	98.00 179	99.62 49	99.22 60	99.55 57	99.22 113	98.93 26	99.75 231	98.66 85	99.81 98	99.50 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		96.49 293	96.82 267	95.52 365	99.42 133	87.08 398	99.22 41	87.14 411	99.11 73	99.46 73	99.58 41	88.69 333	99.86 109	98.80 73	99.95 29	99.62 66

v2v482		98.56 130	98.62 106	98.37 224	99.42 133	95.81 261	97.58 234	99.16 218	97.90 171	99.28 106	99.01 166	95.98 221	99.79 201	99.33 39	99.90 65	99.51 121

OPM-MVS		98.56 130	98.32 154	99.25 92	99.41 135	98.73 84	97.13 272	99.18 211	97.10 247	98.75 194	98.92 187	98.18 80	99.65 285	96.68 216	99.56 211	99.37 184
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 190	98.08 183	98.04 253	99.41 135	94.59 300	94.59 382	99.40 129	97.50 204	98.82 185	98.83 207	96.83 175	99.84 140	97.50 154	99.81 98	99.71 46

test_one_0601					99.39 137	99.20 35		99.31 164	98.49 126	98.66 204	99.02 157	97.64 121

mvsany_test3		98.87 78	98.92 69	98.74 175	99.38 138	96.94 223	98.58 109	99.10 228	96.49 276	99.96 4	99.81 5	98.18 80	99.45 349	98.97 65	99.79 113	99.83 22

patch_mono-2		98.51 142	98.63 104	98.17 241	99.38 138	94.78 291	97.36 252	99.69 38	98.16 155	98.49 228	99.29 98	97.06 161	99.97 5	98.29 106	99.91 59	99.76 39

test2506		92.39 367	91.89 369	93.89 383	99.38 138	82.28 413	99.32 22	66.03 419	99.08 85	98.77 191	99.57 43	66.26 409	99.84 140	98.71 82	99.95 29	99.54 107

ECVR-MVS		96.42 295	96.61 281	95.85 357	99.38 138	88.18 394	99.22 41	86.00 413	99.08 85	99.36 92	99.57 43	88.47 338	99.82 167	98.52 95	99.95 29	99.54 107

casdiffmvs		98.95 69	99.00 63	98.81 157	99.38 138	97.33 198	97.82 201	99.57 63	99.17 71	99.35 94	99.17 126	98.35 68	99.69 257	98.46 97	99.73 143	99.41 165
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		98.96 68	99.02 61	98.76 169	99.38 138	97.26 203	98.49 124	99.50 87	98.86 104	99.19 122	99.06 145	98.23 73	99.69 257	98.71 82	99.76 136	99.33 201

TranMVSNet+NR-MVSNet		99.17 42	99.07 59	99.46 55	99.37 144	98.87 74	98.39 136	99.42 123	99.42 41	99.36 92	99.06 145	98.38 64	99.95 23	98.34 103	99.90 65	99.57 90

tttt0517		95.64 318	94.98 327	97.64 281	99.36 145	93.81 327	98.72 95	90.47 406	98.08 158	98.67 202	98.34 280	73.88 397	99.92 51	97.77 139	99.51 225	99.20 229

test_part2					99.36 145	99.10 61				99.05 141

v1144		98.60 126	98.66 100	98.41 219	99.36 145	95.90 257	97.58 234	99.34 152	97.51 203	99.27 108	99.15 132	96.34 203	99.80 188	99.47 34	99.93 41	99.51 121

CP-MVS		98.70 104	98.42 137	99.52 39	99.36 145	99.12 58	98.72 95	99.36 141	97.54 201	98.30 241	98.40 272	97.86 103	99.89 75	96.53 233	99.72 150	99.56 96

Test_1112_low_res		96.99 274	96.55 285	98.31 231	99.35 149	95.47 271	95.84 343	99.53 81	91.51 378	96.80 339	98.48 266	91.36 315	99.83 157	96.58 222	99.53 220	99.62 66

DeepC-MVS	97.60 4	98.97 66	98.93 68	99.10 113	99.35 149	97.98 150	98.01 178	99.46 106	97.56 198	99.54 58	99.50 60	98.97 23	99.84 140	98.06 120	99.92 52	99.49 128
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 251	96.86 263	98.58 192	99.34 151	96.32 245	96.75 291	99.58 56	93.14 359	96.89 334	97.48 336	92.11 309	99.86 109	96.91 190	99.54 216	99.57 90

MVSMamba_PlusPlus		98.83 83	98.98 66	98.36 225	99.32 152	96.58 238	98.90 78	99.41 125	99.75 6	98.72 197	99.50 60	96.17 207	99.94 35	99.27 43	99.78 118	98.57 325

iter_conf05		99.03 58	99.22 41	98.46 213	99.32 152	96.55 240	99.55 7	99.70 37	99.75 6	99.82 21	99.50 60	96.17 207	99.94 35	99.27 43	99.86 78	98.88 285

SF-MVS		98.53 138	98.27 160	99.32 79	99.31 154	98.75 80	98.19 151	99.41 125	96.77 265	98.83 182	98.90 191	97.80 109	99.82 167	95.68 279	99.52 223	99.38 182

CPTT-MVS		97.84 212	97.36 236	99.27 87	99.31 154	98.46 104	98.29 142	99.27 186	94.90 327	97.83 277	98.37 276	94.90 253	99.84 140	93.85 329	99.54 216	99.51 121

UnsupCasMVSNet_eth		97.89 202	97.60 222	98.75 171	99.31 154	97.17 211	97.62 228	99.35 146	98.72 111	98.76 193	98.68 233	92.57 304	99.74 236	97.76 143	95.60 398	99.34 196

pmmvs-eth3d		98.47 145	98.34 150	98.86 151	99.30 157	97.76 173	97.16 270	99.28 183	95.54 310	99.42 81	99.19 118	97.27 150	99.63 291	97.89 130	99.97 19	99.20 229

mamv4		99.44 15	99.39 21	99.58 16	99.30 157	99.74 2	99.04 64	99.81 23	99.77 5	99.82 21	99.57 43	97.82 107	99.98 4	99.53 29	99.89 69	99.01 259

Anonymous20231211		99.27 31	99.27 36	99.26 89	99.29 159	98.18 125	99.49 9	99.51 85	99.70 11	99.80 26	99.68 20	96.84 173	99.83 157	99.21 50	99.91 59	99.77 35

UnsupCasMVSNet_bld		97.30 249	96.92 259	98.45 215	99.28 160	96.78 230	96.20 320	99.27 186	95.42 314	98.28 245	98.30 284	93.16 290	99.71 249	94.99 293	97.37 374	98.87 287

EC-MVSNet		99.09 54	99.05 60	99.20 98	99.28 160	98.93 72	99.24 40	99.84 18	99.08 85	98.12 256	98.37 276	98.72 38	99.90 65	99.05 59	99.77 124	98.77 303

DPE-MVS		98.59 128	98.26 161	99.57 17	99.27 162	99.15 48	97.01 275	99.39 131	97.67 185	99.44 77	98.99 170	97.53 132	99.89 75	95.40 287	99.68 168	99.66 57
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 211	98.18 170	96.87 326	99.27 162	91.16 375	95.53 352	99.25 192	99.10 80	99.41 82	99.35 86	93.10 292	99.96 12	98.65 86	99.94 36	99.49 128

v1192		98.60 126	98.66 100	98.41 219	99.27 162	95.88 258	97.52 240	99.36 141	97.41 216	99.33 97	99.20 116	96.37 201	99.82 167	99.57 26	99.92 52	99.55 103

N_pmnet		97.63 225	97.17 246	98.99 134	99.27 162	97.86 161	95.98 330	93.41 395	95.25 319	99.47 72	98.90 191	95.63 233	99.85 122	96.91 190	99.73 143	99.27 215

FPMVS		93.44 354	92.23 360	97.08 315	99.25 166	97.86 161	95.61 349	97.16 348	92.90 363	93.76 397	98.65 240	75.94 395	95.66 410	79.30 410	97.49 367	97.73 375

new-patchmatchnet		98.35 159	98.74 84	97.18 310	99.24 167	92.23 358	96.42 307	99.48 96	98.30 136	99.69 39	99.53 56	97.44 141	99.82 167	98.84 72	99.77 124	99.49 128

MCST-MVS		98.00 194	97.63 220	99.10 113	99.24 167	98.17 126	96.89 284	98.73 294	95.66 305	97.92 268	97.70 324	97.17 156	99.66 280	96.18 255	99.23 271	99.47 145

UniMVSNet (Re)		98.87 78	98.71 91	99.35 69	99.24 167	98.73 84	97.73 215	99.38 133	98.93 99	99.12 128	98.73 224	96.77 180	99.86 109	98.63 88	99.80 108	99.46 147

jason		97.45 238	97.35 237	97.76 270	99.24 167	93.93 321	95.86 340	98.42 311	94.24 342	98.50 227	98.13 294	94.82 257	99.91 60	97.22 166	99.73 143	99.43 159
jason: jason.
IterMVS		97.73 217	98.11 179	96.57 336	99.24 167	90.28 383	95.52 354	99.21 201	98.86 104	99.33 97	99.33 92	93.11 291	99.94 35	98.49 96	99.94 36	99.48 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 134	98.62 106	98.32 229	99.22 172	95.58 266	97.51 242	99.45 110	97.16 244	99.45 76	99.24 108	96.12 211	99.85 122	99.60 24	99.88 71	99.55 103

ITE_SJBPF				98.87 150	99.22 172	98.48 103		99.35 146	97.50 204	98.28 245	98.60 250	97.64 121	99.35 364	93.86 328	99.27 263	98.79 301

h-mvs33		97.77 215	97.33 239	99.10 113	99.21 174	97.84 163	98.35 140	98.57 304	99.11 73	98.58 217	99.02 157	88.65 336	99.96 12	98.11 115	96.34 390	99.49 128

v144192		98.54 136	98.57 114	98.45 215	99.21 174	95.98 255	97.63 227	99.36 141	97.15 246	99.32 103	99.18 122	95.84 228	99.84 140	99.50 32	99.91 59	99.54 107

APDe-MVS		98.99 62	98.79 81	99.60 11	99.21 174	99.15 48	98.87 83	99.48 96	97.57 195	99.35 94	99.24 108	97.83 104	99.89 75	97.88 133	99.70 160	99.75 43
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 71	98.81 80	99.28 84	99.21 174	98.45 105	98.46 129	99.33 157	99.63 20	99.48 70	99.15 132	97.23 153	99.75 231	97.17 168	99.66 179	99.63 65

SR-MVS-dyc-post		98.81 87	98.55 115	99.57 17	99.20 178	99.38 9	98.48 127	99.30 172	98.64 113	98.95 158	98.96 179	97.49 139	99.86 109	96.56 228	99.39 244	99.45 151

RE-MVS-def			98.58 113		99.20 178	99.38 9	98.48 127	99.30 172	98.64 113	98.95 158	98.96 179	97.75 112		96.56 228	99.39 244	99.45 151

v1921920		98.54 136	98.60 111	98.38 222	99.20 178	95.76 263	97.56 236	99.36 141	97.23 238	99.38 88	99.17 126	96.02 214	99.84 140	99.57 26	99.90 65	99.54 107

thisisatest0530		95.27 325	94.45 335	97.74 273	99.19 181	94.37 304	97.86 198	90.20 407	97.17 243	98.22 247	97.65 326	73.53 398	99.90 65	96.90 195	99.35 250	98.95 271

Anonymous20240529		98.93 71	98.87 72	99.12 109	99.19 181	98.22 124	99.01 66	98.99 250	99.25 58	99.54 58	99.37 82	97.04 162	99.80 188	97.89 130	99.52 223	99.35 194

APD-MVS_3200maxsize		98.84 82	98.61 110	99.53 34	99.19 181	99.27 23	98.49 124	99.33 157	98.64 113	99.03 146	98.98 174	97.89 101	99.85 122	96.54 232	99.42 241	99.46 147

HQP_MVS		97.99 197	97.67 214	98.93 143	99.19 181	97.65 181	97.77 208	99.27 186	98.20 149	97.79 280	97.98 307	94.90 253	99.70 253	94.42 310	99.51 225	99.45 151

plane_prior7					99.19 181	97.87 160

ab-mvs		98.41 150	98.36 147	98.59 191	99.19 181	97.23 204	99.32 22	98.81 281	97.66 186	98.62 209	99.40 81	96.82 176	99.80 188	95.88 266	99.51 225	98.75 306

F-COLMAP		97.30 249	96.68 276	99.14 107	99.19 181	98.39 107	97.27 261	99.30 172	92.93 362	96.62 345	98.00 305	95.73 231	99.68 266	92.62 356	98.46 337	99.35 194

SR-MVS		98.71 100	98.43 135	99.57 17	99.18 188	99.35 13	98.36 139	99.29 180	98.29 139	98.88 174	98.85 204	97.53 132	99.87 101	96.14 257	99.31 256	99.48 138

UniMVSNet_NR-MVSNet		98.86 81	98.68 97	99.40 61	99.17 189	98.74 81	97.68 219	99.40 129	99.14 72	99.06 136	98.59 251	96.71 186	99.93 42	98.57 91	99.77 124	99.53 115

LF4IMVS		97.90 200	97.69 213	98.52 205	99.17 189	97.66 180	97.19 269	99.47 104	96.31 284	97.85 276	98.20 291	96.71 186	99.52 330	94.62 302	99.72 150	98.38 343

SMA-MVS		98.40 152	98.03 187	99.51 43	99.16 191	99.21 29	98.05 170	99.22 200	94.16 344	98.98 150	99.10 141	97.52 134	99.79 201	96.45 238	99.64 182	99.53 115
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
DU-MVS		98.82 85	98.63 104	99.39 62	99.16 191	98.74 81	97.54 238	99.25 192	98.84 107	99.06 136	98.76 221	96.76 182	99.93 42	98.57 91	99.77 124	99.50 124

NR-MVSNet		98.95 69	98.82 78	99.36 63	99.16 191	98.72 86	99.22 41	99.20 203	99.10 80	99.72 33	98.76 221	96.38 200	99.86 109	98.00 125	99.82 94	99.50 124

MVS_111021_LR		98.30 167	98.12 178	98.83 154	99.16 191	98.03 145	96.09 327	99.30 172	97.58 194	98.10 258	98.24 287	98.25 71	99.34 365	96.69 215	99.65 180	99.12 245

DSMNet-mixed		97.42 241	97.60 222	96.87 326	99.15 195	91.46 365	98.54 114	99.12 225	92.87 364	97.58 293	99.63 33	96.21 206	99.90 65	95.74 275	99.54 216	99.27 215

D2MVS		97.84 212	97.84 204	97.83 262	99.14 196	94.74 293	96.94 279	98.88 265	95.84 302	98.89 171	98.96 179	94.40 269	99.69 257	97.55 149	99.95 29	99.05 251

pmmvs5		97.64 224	97.49 228	98.08 248	99.14 196	95.12 284	96.70 294	99.05 236	93.77 351	98.62 209	98.83 207	93.23 288	99.75 231	98.33 105	99.76 136	99.36 190

CS-MVS-test		99.13 49	99.09 56	99.26 89	99.13 198	98.97 67	99.31 26	99.88 11	99.44 38	98.16 251	98.51 259	98.64 44	99.93 42	98.91 67	99.85 80	98.88 285

VDD-MVS		98.56 130	98.39 142	99.07 119	99.13 198	98.07 140	98.59 108	97.01 351	99.59 26	99.11 129	99.27 101	94.82 257	99.79 201	98.34 103	99.63 185	99.34 196

save fliter					99.11 200	97.97 151	96.53 301	99.02 244	98.24 142

APD-MVS		98.10 186	97.67 214	99.42 57	99.11 200	98.93 72	97.76 211	99.28 183	94.97 325	98.72 197	98.77 219	97.04 162	99.85 122	93.79 330	99.54 216	99.49 128
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 107	98.71 91	98.62 185	99.10 202	96.37 243	97.23 262	98.87 267	99.20 64	99.19 122	98.99 170	97.30 147	99.85 122	98.77 77	99.79 113	99.65 61

EI-MVSNet		98.40 152	98.51 120	98.04 253	99.10 202	94.73 294	97.20 266	98.87 267	98.97 95	99.06 136	99.02 157	96.00 216	99.80 188	98.58 89	99.82 94	99.60 73

CVMVSNet		96.25 300	97.21 245	93.38 389	99.10 202	80.56 416	97.20 266	98.19 322	96.94 255	99.00 148	99.02 157	89.50 329	99.80 188	96.36 244	99.59 199	99.78 33

EI-MVSNet-Vis-set		98.68 112	98.70 94	98.63 184	99.09 205	96.40 242	97.23 262	98.86 272	99.20 64	99.18 126	98.97 176	97.29 149	99.85 122	98.72 81	99.78 118	99.64 62

HPM-MVS++		98.10 186	97.64 219	99.48 50	99.09 205	99.13 56	97.52 240	98.75 291	97.46 212	96.90 333	97.83 317	96.01 215	99.84 140	95.82 273	99.35 250	99.46 147

DP-MVS Recon		97.33 247	96.92 259	98.57 195	99.09 205	97.99 147	96.79 287	99.35 146	93.18 358	97.71 284	98.07 302	95.00 252	99.31 369	93.97 323	99.13 287	98.42 340

MVS_111021_HR		98.25 175	98.08 183	98.75 171	99.09 205	97.46 191	95.97 331	99.27 186	97.60 193	97.99 266	98.25 286	98.15 86	99.38 360	96.87 198	99.57 208	99.42 162

9.14			97.78 206		99.07 209		97.53 239	99.32 159	95.53 311	98.54 224	98.70 230	97.58 126	99.76 224	94.32 315	99.46 235

PAPM_NR		96.82 281	96.32 291	98.30 232	99.07 209	96.69 234	97.48 244	98.76 288	95.81 303	96.61 346	96.47 361	94.12 278	99.17 382	90.82 382	97.78 362	99.06 250

TAMVS		98.24 176	98.05 185	98.80 159	99.07 209	97.18 210	97.88 194	98.81 281	96.66 270	99.17 127	99.21 114	94.81 259	99.77 218	96.96 188	99.88 71	99.44 155

CLD-MVS		97.49 234	97.16 247	98.48 211	99.07 209	97.03 217	94.71 375	99.21 201	94.46 336	98.06 261	97.16 348	97.57 127	99.48 342	94.46 307	99.78 118	98.95 271
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		99.13 49	99.10 55	99.24 94	99.06 213	99.15 48	99.36 18	99.88 11	99.36 48	98.21 248	98.46 267	98.68 42	99.93 42	99.03 61	99.85 80	98.64 318

thres100view900		94.19 341	93.67 345	95.75 360	99.06 213	91.35 368	98.03 173	94.24 390	98.33 133	97.40 309	94.98 390	79.84 382	99.62 294	83.05 403	98.08 354	96.29 396

thres600view7		94.45 336	93.83 342	96.29 344	99.06 213	91.53 364	97.99 181	94.24 390	98.34 132	97.44 307	95.01 388	79.84 382	99.67 269	84.33 401	98.23 343	97.66 378

plane_prior1					99.05 216

YYNet1		97.60 226	97.67 214	97.39 303	99.04 217	93.04 342	95.27 361	98.38 314	97.25 232	98.92 167	98.95 183	95.48 240	99.73 241	96.99 184	98.74 319	99.41 165

MDA-MVSNet_test_wron		97.60 226	97.66 217	97.41 302	99.04 217	93.09 338	95.27 361	98.42 311	97.26 231	98.88 174	98.95 183	95.43 242	99.73 241	97.02 181	98.72 321	99.41 165

MIMVSNet		96.62 288	96.25 295	97.71 276	99.04 217	94.66 297	99.16 50	96.92 357	97.23 238	97.87 273	99.10 141	86.11 351	99.65 285	91.65 366	99.21 275	98.82 291

PatchMatch-RL		97.24 255	96.78 270	98.61 188	99.03 220	97.83 164	96.36 310	99.06 233	93.49 356	97.36 313	97.78 318	95.75 230	99.49 339	93.44 339	98.77 318	98.52 328

ZD-MVS					99.01 221	98.84 75		99.07 232	94.10 346	98.05 263	98.12 296	96.36 202	99.86 109	92.70 355	99.19 279

CDPH-MVS		97.26 252	96.66 279	99.07 119	99.00 222	98.15 127	96.03 329	99.01 247	91.21 382	97.79 280	97.85 316	96.89 171	99.69 257	92.75 353	99.38 247	99.39 175

diffmvs		98.22 177	98.24 164	98.17 241	99.00 222	95.44 272	96.38 309	99.58 56	97.79 179	98.53 225	98.50 263	96.76 182	99.74 236	97.95 129	99.64 182	99.34 196
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 152	98.19 169	99.03 129	99.00 222	97.65 181	96.85 285	98.94 252	98.57 122	98.89 171	98.50 263	95.60 234	99.85 122	97.54 151	99.85 80	99.59 79

plane_prior6					98.99 225	97.70 179						94.90 253

xiu_mvs_v1_base_debu		97.86 206	98.17 171	96.92 323	98.98 226	93.91 322	96.45 304	99.17 215	97.85 175	98.41 235	97.14 350	98.47 57	99.92 51	98.02 122	99.05 293	96.92 389

xiu_mvs_v1_base		97.86 206	98.17 171	96.92 323	98.98 226	93.91 322	96.45 304	99.17 215	97.85 175	98.41 235	97.14 350	98.47 57	99.92 51	98.02 122	99.05 293	96.92 389

xiu_mvs_v1_base_debi		97.86 206	98.17 171	96.92 323	98.98 226	93.91 322	96.45 304	99.17 215	97.85 175	98.41 235	97.14 350	98.47 57	99.92 51	98.02 122	99.05 293	96.92 389

MVP-Stereo		98.08 189	97.92 198	98.57 195	98.96 229	96.79 227	97.90 192	99.18 211	96.41 280	98.46 230	98.95 183	95.93 225	99.60 301	96.51 234	98.98 306	99.31 207
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 152	98.68 97	97.54 291	98.96 229	97.99 147	97.88 194	99.36 141	98.20 149	99.63 50	99.04 154	98.76 35	95.33 412	96.56 228	99.74 140	99.31 207
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
新几何1				98.91 146	98.94 231	97.76 173		98.76 288	87.58 399	96.75 341	98.10 298	94.80 260	99.78 212	92.73 354	99.00 302	99.20 229

USDC		97.41 242	97.40 232	97.44 300	98.94 231	93.67 331	95.17 364	99.53 81	94.03 348	98.97 154	99.10 141	95.29 244	99.34 365	95.84 272	99.73 143	99.30 210

tfpn200view9		94.03 345	93.44 347	95.78 359	98.93 233	91.44 366	97.60 231	94.29 388	97.94 167	97.10 319	94.31 397	79.67 384	99.62 294	83.05 403	98.08 354	96.29 396

testdata				98.09 245	98.93 233	95.40 274		98.80 283	90.08 390	97.45 306	98.37 276	95.26 245	99.70 253	93.58 335	98.95 309	99.17 240

thres400		94.14 343	93.44 347	96.24 347	98.93 233	91.44 366	97.60 231	94.29 388	97.94 167	97.10 319	94.31 397	79.67 384	99.62 294	83.05 403	98.08 354	97.66 378

TAPA-MVS	96.21 11	96.63 287	95.95 297	98.65 179	98.93 233	98.09 134	96.93 281	99.28 183	83.58 405	98.13 255	97.78 318	96.13 210	99.40 356	93.52 336	99.29 261	98.45 333
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 237	96.93 224	95.54 351	98.78 286	85.72 402	96.86 336	98.11 297	94.43 267			99.10 292	99.23 224

PVSNet_BlendedMVS		97.55 231	97.53 225	97.60 283	98.92 237	93.77 329	96.64 296	99.43 120	94.49 334	97.62 289	99.18 122	96.82 176	99.67 269	94.73 299	99.93 41	99.36 190

PVSNet_Blended		96.88 277	96.68 276	97.47 298	98.92 237	93.77 329	94.71 375	99.43 120	90.98 384	97.62 289	97.36 344	96.82 176	99.67 269	94.73 299	99.56 211	98.98 265

MSDG		97.71 219	97.52 226	98.28 234	98.91 240	96.82 226	94.42 385	99.37 137	97.65 187	98.37 240	98.29 285	97.40 143	99.33 367	94.09 321	99.22 272	98.68 316

Anonymous202405211		97.90 200	97.50 227	99.08 117	98.90 241	98.25 118	98.53 115	96.16 368	98.87 103	99.11 129	98.86 201	90.40 323	99.78 212	97.36 159	99.31 256	99.19 234

原ACMM1				98.35 226	98.90 241	96.25 247		98.83 280	92.48 368	96.07 361	98.10 298	95.39 243	99.71 249	92.61 357	98.99 304	99.08 247

GBi-Net		98.65 117	98.47 129	99.17 101	98.90 241	98.24 119	99.20 44	99.44 114	98.59 119	98.95 158	99.55 50	94.14 275	99.86 109	97.77 139	99.69 163	99.41 165

test1		98.65 117	98.47 129	99.17 101	98.90 241	98.24 119	99.20 44	99.44 114	98.59 119	98.95 158	99.55 50	94.14 275	99.86 109	97.77 139	99.69 163	99.41 165

FMVSNet2		98.49 143	98.40 139	98.75 171	98.90 241	97.14 214	98.61 106	99.13 224	98.59 119	99.19 122	99.28 99	94.14 275	99.82 167	97.97 127	99.80 108	99.29 212

OMC-MVS		97.88 204	97.49 228	99.04 128	98.89 246	98.63 88	96.94 279	99.25 192	95.02 323	98.53 225	98.51 259	97.27 150	99.47 345	93.50 338	99.51 225	99.01 259

MVSFormer		98.26 173	98.43 135	97.77 267	98.88 247	93.89 325	99.39 16	99.56 70	99.11 73	98.16 251	98.13 294	93.81 283	99.97 5	99.26 45	99.57 208	99.43 159

lupinMVS		97.06 267	96.86 263	97.65 279	98.88 247	93.89 325	95.48 355	97.97 328	93.53 354	98.16 251	97.58 330	93.81 283	99.91 60	96.77 206	99.57 208	99.17 240

dmvs_re		95.98 307	95.39 317	97.74 273	98.86 249	97.45 192	98.37 138	95.69 379	97.95 165	96.56 347	95.95 369	90.70 320	97.68 406	88.32 391	96.13 394	98.11 355

DELS-MVS		98.27 171	98.20 167	98.48 211	98.86 249	96.70 233	95.60 350	99.20 203	97.73 182	98.45 231	98.71 227	97.50 136	99.82 167	98.21 109	99.59 199	98.93 276
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
TinyColmap		97.89 202	97.98 192	97.60 283	98.86 249	94.35 305	96.21 319	99.44 114	97.45 214	99.06 136	98.88 198	97.99 97	99.28 375	94.38 314	99.58 204	99.18 236

LCM-MVSNet-Re		98.64 119	98.48 127	99.11 111	98.85 252	98.51 101	98.49 124	99.83 20	98.37 130	99.69 39	99.46 69	98.21 78	99.92 51	94.13 320	99.30 259	98.91 280

pmmvs4		97.58 229	97.28 240	98.51 206	98.84 253	96.93 224	95.40 359	98.52 307	93.60 353	98.61 211	98.65 240	95.10 249	99.60 301	96.97 187	99.79 113	98.99 264

NP-MVS					98.84 253	97.39 196					96.84 353

sss		97.21 257	96.93 257	98.06 250	98.83 255	95.22 280	96.75 291	98.48 309	94.49 334	97.27 315	97.90 313	92.77 300	99.80 188	96.57 224	99.32 254	99.16 243

PVSNet	93.40 17	95.67 316	95.70 302	95.57 364	98.83 255	88.57 390	92.50 402	97.72 333	92.69 366	96.49 353	96.44 362	93.72 286	99.43 352	93.61 333	99.28 262	98.71 309

MVE	83.40 22	92.50 366	91.92 368	94.25 378	98.83 255	91.64 363	92.71 401	83.52 415	95.92 300	86.46 413	95.46 382	95.20 246	95.40 411	80.51 408	98.64 330	95.73 404
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ambc				98.24 237	98.82 258	95.97 256	98.62 105	99.00 249		99.27 108	99.21 114	96.99 167	99.50 336	96.55 231	99.50 232	99.26 218

旧先验1					98.82 258	97.45 192		98.76 288			98.34 280	95.50 239			99.01 301	99.23 224

test_vis1_rt		97.75 216	97.72 212	97.83 262	98.81 260	96.35 244	97.30 257	99.69 38	94.61 332	97.87 273	98.05 303	96.26 205	98.32 402	98.74 79	98.18 346	98.82 291

WTY-MVS		96.67 285	96.27 294	97.87 260	98.81 260	94.61 299	96.77 289	97.92 330	94.94 326	97.12 318	97.74 321	91.11 317	99.82 167	93.89 326	98.15 350	99.18 236

3Dnovator+	97.89 3	98.69 107	98.51 120	99.24 94	98.81 260	98.40 106	99.02 65	99.19 207	98.99 92	98.07 260	99.28 99	97.11 160	99.84 140	96.84 201	99.32 254	99.47 145

QAPM		97.31 248	96.81 269	98.82 155	98.80 263	97.49 189	99.06 61	99.19 207	90.22 388	97.69 286	99.16 128	96.91 170	99.90 65	90.89 381	99.41 242	99.07 249

VNet		98.42 149	98.30 155	98.79 162	98.79 264	97.29 200	98.23 147	98.66 298	99.31 52	98.85 179	98.80 213	94.80 260	99.78 212	98.13 114	99.13 287	99.31 207

DPM-MVS		96.32 297	95.59 308	98.51 206	98.76 265	97.21 207	94.54 384	98.26 317	91.94 373	96.37 354	97.25 346	93.06 294	99.43 352	91.42 371	98.74 319	98.89 282

3Dnovator	98.27 2	98.81 87	98.73 86	99.05 126	98.76 265	97.81 170	99.25 39	99.30 172	98.57 122	98.55 222	99.33 92	97.95 99	99.90 65	97.16 169	99.67 174	99.44 155

PLC	94.65 16	96.51 290	95.73 301	98.85 152	98.75 267	97.91 157	96.42 307	99.06 233	90.94 385	95.59 367	97.38 342	94.41 268	99.59 305	90.93 379	98.04 359	99.05 251
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 279	96.75 272	97.08 315	98.74 268	93.33 336	96.71 293	98.26 317	96.72 267	98.44 232	97.37 343	95.20 246	99.47 345	91.89 362	97.43 371	98.44 336

hse-mvs2		97.46 236	97.07 251	98.64 180	98.73 269	97.33 198	97.45 247	97.64 338	99.11 73	98.58 217	97.98 307	88.65 336	99.79 201	98.11 115	97.39 373	98.81 295

CDS-MVSNet		97.69 220	97.35 237	98.69 177	98.73 269	97.02 218	96.92 283	98.75 291	95.89 301	98.59 215	98.67 235	92.08 310	99.74 236	96.72 212	99.81 98	99.32 203
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 194	97.74 209	98.80 159	98.72 271	98.09 134	98.05 170	99.60 53	97.39 218	96.63 344	95.55 377	97.68 115	99.80 188	96.73 211	99.27 263	98.52 328

LFMVS		97.20 258	96.72 273	98.64 180	98.72 271	96.95 222	98.93 76	94.14 392	99.74 9	98.78 188	99.01 166	84.45 363	99.73 241	97.44 155	99.27 263	99.25 219

new_pmnet		96.99 274	96.76 271	97.67 277	98.72 271	94.89 289	95.95 335	98.20 320	92.62 367	98.55 222	98.54 255	94.88 256	99.52 330	93.96 324	99.44 240	98.59 324

Fast-Effi-MVS+		97.67 222	97.38 234	98.57 195	98.71 274	97.43 194	97.23 262	99.45 110	94.82 329	96.13 358	96.51 358	98.52 56	99.91 60	96.19 253	98.83 315	98.37 345

TEST9					98.71 274	98.08 138	95.96 333	99.03 241	91.40 379	95.85 364	97.53 332	96.52 193	99.76 224

train_agg		97.10 264	96.45 288	99.07 119	98.71 274	98.08 138	95.96 333	99.03 241	91.64 374	95.85 364	97.53 332	96.47 195	99.76 224	93.67 332	99.16 282	99.36 190

TSAR-MVS + GP.		98.18 182	97.98 192	98.77 168	98.71 274	97.88 159	96.32 313	98.66 298	96.33 282	99.23 119	98.51 259	97.48 140	99.40 356	97.16 169	99.46 235	99.02 258

FA-MVS(test-final)		96.99 274	96.82 267	97.50 295	98.70 278	94.78 291	99.34 19	96.99 352	95.07 322	98.48 229	99.33 92	88.41 339	99.65 285	96.13 259	98.92 312	98.07 358

AUN-MVS		96.24 301	95.45 313	98.60 190	98.70 278	97.22 206	97.38 250	97.65 336	95.95 299	95.53 374	97.96 311	82.11 378	99.79 201	96.31 246	97.44 370	98.80 300

our_test_3		97.39 243	97.73 211	96.34 342	98.70 278	89.78 386	94.61 381	98.97 251	96.50 275	99.04 143	98.85 204	95.98 221	99.84 140	97.26 164	99.67 174	99.41 165

ppachtmachnet_test		97.50 232	97.74 209	96.78 332	98.70 278	91.23 374	94.55 383	99.05 236	96.36 281	99.21 120	98.79 215	96.39 198	99.78 212	96.74 209	99.82 94	99.34 196

PCF-MVS	92.86 18	94.36 337	93.00 354	98.42 218	98.70 278	97.56 186	93.16 400	99.11 227	79.59 409	97.55 296	97.43 339	92.19 307	99.73 241	79.85 409	99.45 237	97.97 364
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
m2depth		97.91 199	98.02 188	97.58 285	98.69 283	94.10 312	98.13 157	98.90 261	97.95 165	97.32 314	99.58 41	95.95 224	98.75 397	96.41 240	99.22 272	99.87 16

bld_raw_conf03		98.38 158	98.39 142	98.33 228	98.69 283	96.58 238	98.90 78	99.41 125	97.57 195	98.72 197	99.20 116	95.48 240	99.86 109	97.76 143	99.78 118	98.57 325

ETV-MVS		98.03 191	97.86 203	98.56 199	98.69 283	98.07 140	97.51 242	99.50 87	98.10 157	97.50 301	95.51 378	98.41 62	99.88 84	96.27 249	99.24 268	97.71 377

test_prior				98.95 140	98.69 283	97.95 155		99.03 241					99.59 305			99.30 210

mvsmamba		97.57 230	97.26 241	98.51 206	98.69 283	96.73 232	98.74 90	97.25 346	97.03 251	97.88 272	99.23 112	90.95 318	99.87 101	96.61 220	99.00 302	98.91 280

agg_prior					98.68 288	97.99 147		99.01 247		95.59 367			99.77 218

test_8					98.67 289	98.01 146	95.91 339	99.02 244	91.64 374	95.79 366	97.50 335	96.47 195	99.76 224

HQP-NCC					98.67 289		96.29 315		96.05 292	95.55 370

ACMP_Plane					98.67 289		96.29 315		96.05 292	95.55 370

CNVR-MVS		98.17 184	97.87 202	99.07 119	98.67 289	98.24 119	97.01 275	98.93 255	97.25 232	97.62 289	98.34 280	97.27 150	99.57 313	96.42 239	99.33 253	99.39 175

HQP-MVS		97.00 273	96.49 287	98.55 200	98.67 289	96.79 227	96.29 315	99.04 239	96.05 292	95.55 370	96.84 353	93.84 281	99.54 324	92.82 350	99.26 266	99.32 203

MM		98.22 177	97.99 191	98.91 146	98.66 294	96.97 219	97.89 193	94.44 386	99.54 29	98.95 158	99.14 135	93.50 287	99.92 51	99.80 11	99.96 23	99.85 20

test_fmvs1		97.72 218	97.94 196	97.07 317	98.66 294	92.39 353	97.68 219	99.81 23	95.20 321	99.54 58	99.44 74	91.56 314	99.41 355	99.78 14	99.77 124	99.40 174

balanced_conf03		98.63 121	98.72 88	98.38 222	98.66 294	96.68 235	98.90 78	99.42 123	98.99 92	98.97 154	99.19 118	95.81 229	99.85 122	98.77 77	99.77 124	98.60 321

thres200		93.72 350	93.14 352	95.46 368	98.66 294	91.29 370	96.61 298	94.63 385	97.39 218	96.83 337	93.71 400	79.88 381	99.56 316	82.40 406	98.13 351	95.54 405

wuyk23d		96.06 303	97.62 221	91.38 392	98.65 298	98.57 95	98.85 86	96.95 355	96.86 260	99.90 12	99.16 128	99.18 17	98.40 401	89.23 389	99.77 124	77.18 412

NCCC		97.86 206	97.47 231	99.05 126	98.61 299	98.07 140	96.98 277	98.90 261	97.63 188	97.04 323	97.93 312	95.99 220	99.66 280	95.31 288	98.82 317	99.43 159

DeepC-MVS_fast	96.85 6	98.30 167	98.15 175	98.75 171	98.61 299	97.23 204	97.76 211	99.09 230	97.31 226	98.75 194	98.66 238	97.56 128	99.64 288	96.10 260	99.55 214	99.39 175
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 352	92.09 362	97.75 271	98.60 301	94.40 303	97.32 255	95.26 381	97.56 198	96.79 340	95.50 379	53.57 418	99.77 218	95.26 289	98.97 307	99.08 247

thisisatest0515		94.12 344	93.16 351	96.97 321	98.60 301	92.90 343	93.77 396	90.61 405	94.10 346	96.91 330	95.87 372	74.99 396	99.80 188	94.52 305	99.12 290	98.20 351

GA-MVS		95.86 310	95.32 320	97.49 296	98.60 301	94.15 311	93.83 395	97.93 329	95.49 312	96.68 342	97.42 340	83.21 371	99.30 371	96.22 251	98.55 336	99.01 259

dmvs_testset		92.94 362	92.21 361	95.13 371	98.59 304	90.99 376	97.65 225	92.09 401	96.95 254	94.00 393	93.55 401	92.34 306	96.97 409	72.20 412	92.52 407	97.43 385

OPU-MVS				98.82 155	98.59 304	98.30 115	98.10 163				98.52 258	98.18 80	98.75 397	94.62 302	99.48 234	99.41 165

MSLP-MVS++		98.02 192	98.14 177	97.64 281	98.58 306	95.19 281	97.48 244	99.23 199	97.47 207	97.90 270	98.62 247	97.04 162	98.81 396	97.55 149	99.41 242	98.94 275

test12				98.93 143	98.58 306	97.83 164		98.66 298		96.53 348		95.51 238	99.69 257		99.13 287	99.27 215

CL-MVSNet_self_test		97.44 239	97.22 244	98.08 248	98.57 308	95.78 262	94.30 388	98.79 284	96.58 273	98.60 213	98.19 292	94.74 263	99.64 288	96.41 240	98.84 314	98.82 291

PS-MVSNAJ		97.08 266	97.39 233	96.16 353	98.56 309	92.46 351	95.24 363	98.85 275	97.25 232	97.49 302	95.99 368	98.07 88	99.90 65	96.37 242	98.67 329	96.12 401

CNLPA		97.17 261	96.71 274	98.55 200	98.56 309	98.05 144	96.33 312	98.93 255	96.91 257	97.06 322	97.39 341	94.38 270	99.45 349	91.66 365	99.18 281	98.14 354

xiu_mvs_v2_base		97.16 262	97.49 228	96.17 351	98.54 311	92.46 351	95.45 356	98.84 276	97.25 232	97.48 303	96.49 359	98.31 70	99.90 65	96.34 245	98.68 328	96.15 400

alignmvs		97.35 245	96.88 262	98.78 165	98.54 311	98.09 134	97.71 216	97.69 335	99.20 64	97.59 292	95.90 371	88.12 341	99.55 319	98.18 111	98.96 308	98.70 312

FE-MVS		95.66 317	94.95 329	97.77 267	98.53 313	95.28 277	99.40 15	96.09 370	93.11 360	97.96 267	99.26 103	79.10 388	99.77 218	92.40 359	98.71 323	98.27 349

Effi-MVS+		98.02 192	97.82 205	98.62 185	98.53 313	97.19 209	97.33 254	99.68 43	97.30 227	96.68 342	97.46 338	98.56 54	99.80 188	96.63 218	98.20 345	98.86 288

baseline1		95.96 308	95.44 314	97.52 293	98.51 315	93.99 319	98.39 136	96.09 370	98.21 145	98.40 239	97.76 320	86.88 343	99.63 291	95.42 286	89.27 410	98.95 271

MVS_Test		98.18 182	98.36 147	97.67 277	98.48 316	94.73 294	98.18 152	99.02 244	97.69 184	98.04 264	99.11 138	97.22 154	99.56 316	98.57 91	98.90 313	98.71 309

MGCFI-Net		98.34 160	98.28 157	98.51 206	98.47 317	97.59 185	98.96 72	99.48 96	99.18 70	97.40 309	95.50 379	98.66 43	99.50 336	98.18 111	98.71 323	98.44 336

BH-RMVSNet		96.83 279	96.58 284	97.58 285	98.47 317	94.05 313	96.67 295	97.36 341	96.70 269	97.87 273	97.98 307	95.14 248	99.44 351	90.47 384	98.58 335	99.25 219

sasdasda		98.34 160	98.26 161	98.58 192	98.46 319	97.82 167	98.96 72	99.46 106	99.19 68	97.46 304	95.46 382	98.59 50	99.46 347	98.08 118	98.71 323	98.46 330

canonicalmvs		98.34 160	98.26 161	98.58 192	98.46 319	97.82 167	98.96 72	99.46 106	99.19 68	97.46 304	95.46 382	98.59 50	99.46 347	98.08 118	98.71 323	98.46 330

MVS-HIRNet		94.32 338	95.62 305	90.42 393	98.46 319	75.36 417	96.29 315	89.13 409	95.25 319	95.38 376	99.75 11	92.88 297	99.19 381	94.07 322	99.39 244	96.72 394

PHI-MVS		98.29 170	97.95 194	99.34 72	98.44 322	99.16 44	98.12 160	99.38 133	96.01 296	98.06 261	98.43 270	97.80 109	99.67 269	95.69 278	99.58 204	99.20 229

DVP-MVS++		98.90 75	98.70 94	99.51 43	98.43 323	99.15 48	99.43 11	99.32 159	98.17 152	99.26 112	99.02 157	98.18 80	99.88 84	97.07 178	99.45 237	99.49 128

MSC_two_6792asdad				99.32 79	98.43 323	98.37 110		98.86 272					99.89 75	97.14 172	99.60 195	99.71 46

No_MVS				99.32 79	98.43 323	98.37 110		98.86 272					99.89 75	97.14 172	99.60 195	99.71 46

Fast-Effi-MVS+-dtu		98.27 171	98.09 180	98.81 157	98.43 323	98.11 131	97.61 230	99.50 87	98.64 113	97.39 311	97.52 334	98.12 87	99.95 23	96.90 195	98.71 323	98.38 343

OpenMVS_ROB	95.38 14	95.84 312	95.18 324	97.81 264	98.41 327	97.15 213	97.37 251	98.62 302	83.86 404	98.65 205	98.37 276	94.29 273	99.68 266	88.41 390	98.62 333	96.60 395

DeepPCF-MVS	96.93 5	98.32 164	98.01 189	99.23 96	98.39 328	98.97 67	95.03 368	99.18 211	96.88 258	99.33 97	98.78 217	98.16 84	99.28 375	96.74 209	99.62 188	99.44 155

Patchmatch-test		96.55 289	96.34 290	97.17 312	98.35 329	93.06 339	98.40 135	97.79 331	97.33 223	98.41 235	98.67 235	83.68 370	99.69 257	95.16 291	99.31 256	98.77 303

AdaColmap		97.14 263	96.71 274	98.46 213	98.34 330	97.80 171	96.95 278	98.93 255	95.58 309	96.92 328	97.66 325	95.87 227	99.53 326	90.97 378	99.14 285	98.04 359

OpenMVS	96.65 7	97.09 265	96.68 276	98.32 229	98.32 331	97.16 212	98.86 85	99.37 137	89.48 392	96.29 356	99.15 132	96.56 191	99.90 65	92.90 347	99.20 276	97.89 365

MG-MVS		96.77 282	96.61 281	97.26 308	98.31 332	93.06 339	95.93 336	98.12 325	96.45 279	97.92 268	98.73 224	93.77 285	99.39 358	91.19 376	99.04 296	99.33 201

test_yl		96.69 283	96.29 292	97.90 257	98.28 333	95.24 278	97.29 258	97.36 341	98.21 145	98.17 249	97.86 314	86.27 347	99.55 319	94.87 296	98.32 339	98.89 282

DCV-MVSNet		96.69 283	96.29 292	97.90 257	98.28 333	95.24 278	97.29 258	97.36 341	98.21 145	98.17 249	97.86 314	86.27 347	99.55 319	94.87 296	98.32 339	98.89 282

CHOSEN 280x420		95.51 322	95.47 311	95.65 363	98.25 335	88.27 393	93.25 399	98.88 265	93.53 354	94.65 385	97.15 349	86.17 349	99.93 42	97.41 157	99.93 41	98.73 308

SCA		96.41 296	96.66 279	95.67 361	98.24 336	88.35 392	95.85 342	96.88 358	96.11 290	97.67 287	98.67 235	93.10 292	99.85 122	94.16 316	99.22 272	98.81 295

DeepMVS_CX				93.44 388	98.24 336	94.21 308		94.34 387	64.28 412	91.34 406	94.87 394	89.45 330	92.77 413	77.54 411	93.14 406	93.35 408

MS-PatchMatch		97.68 221	97.75 208	97.45 299	98.23 338	93.78 328	97.29 258	98.84 276	96.10 291	98.64 206	98.65 240	96.04 213	99.36 361	96.84 201	99.14 285	99.20 229

BH-w/o		95.13 328	94.89 331	95.86 356	98.20 339	91.31 369	95.65 348	97.37 340	93.64 352	96.52 349	95.70 375	93.04 295	99.02 387	88.10 392	95.82 397	97.24 387

mvs_anonymous		97.83 214	98.16 174	96.87 326	98.18 340	91.89 360	97.31 256	98.90 261	97.37 220	98.83 182	99.46 69	96.28 204	99.79 201	98.90 68	98.16 349	98.95 271

miper_lstm_enhance		97.18 260	97.16 247	97.25 309	98.16 341	92.85 344	95.15 366	99.31 164	97.25 232	98.74 196	98.78 217	90.07 324	99.78 212	97.19 167	99.80 108	99.11 246

ET-MVSNet_ETH3D		94.30 340	93.21 350	97.58 285	98.14 342	94.47 302	94.78 374	93.24 397	94.72 330	89.56 408	95.87 372	78.57 391	99.81 181	96.91 190	97.11 382	98.46 330

ADS-MVSNet2		95.43 323	94.98 327	96.76 333	98.14 342	91.74 361	97.92 189	97.76 332	90.23 386	96.51 350	98.91 188	85.61 354	99.85 122	92.88 348	96.90 383	98.69 313

ADS-MVSNet		95.24 326	94.93 330	96.18 350	98.14 342	90.10 385	97.92 189	97.32 344	90.23 386	96.51 350	98.91 188	85.61 354	99.74 236	92.88 348	96.90 383	98.69 313

c3_l		97.36 244	97.37 235	97.31 304	98.09 345	93.25 337	95.01 369	99.16 218	97.05 248	98.77 191	98.72 226	92.88 297	99.64 288	96.93 189	99.76 136	99.05 251

FMVSNet3		97.50 232	97.24 243	98.29 233	98.08 346	95.83 260	97.86 198	98.91 260	97.89 172	98.95 158	98.95 183	87.06 342	99.81 181	97.77 139	99.69 163	99.23 224

PAPM		91.88 375	90.34 378	96.51 337	98.06 347	92.56 349	92.44 403	97.17 347	86.35 400	90.38 407	96.01 367	86.61 345	99.21 380	70.65 413	95.43 399	97.75 374

Effi-MVS+-dtu		98.26 173	97.90 200	99.35 69	98.02 348	99.49 6	98.02 175	99.16 218	98.29 139	97.64 288	97.99 306	96.44 197	99.95 23	96.66 217	98.93 311	98.60 321

eth_miper_zixun_eth		97.23 256	97.25 242	97.17 312	98.00 349	92.77 346	94.71 375	99.18 211	97.27 230	98.56 220	98.74 223	91.89 311	99.69 257	97.06 180	99.81 98	99.05 251

HY-MVS	95.94 13	95.90 309	95.35 319	97.55 290	97.95 350	94.79 290	98.81 89	96.94 356	92.28 371	95.17 378	98.57 253	89.90 326	99.75 231	91.20 375	97.33 378	98.10 356

UGNet		98.53 138	98.45 132	98.79 162	97.94 351	96.96 221	99.08 57	98.54 305	99.10 80	96.82 338	99.47 68	96.55 192	99.84 140	98.56 94	99.94 36	99.55 103
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
MAR-MVS		96.47 294	95.70 302	98.79 162	97.92 352	99.12 58	98.28 143	98.60 303	92.16 372	95.54 373	96.17 366	94.77 262	99.52 330	89.62 387	98.23 343	97.72 376
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
MVSTER		96.86 278	96.55 285	97.79 265	97.91 353	94.21 308	97.56 236	98.87 267	97.49 206	99.06 136	99.05 152	80.72 379	99.80 188	98.44 98	99.82 94	99.37 184

API-MVS		97.04 269	96.91 261	97.42 301	97.88 354	98.23 123	98.18 152	98.50 308	97.57 195	97.39 311	96.75 355	96.77 180	99.15 384	90.16 385	99.02 300	94.88 406

miper_ehance_all_eth		97.06 267	97.03 253	97.16 314	97.83 355	93.06 339	94.66 378	99.09 230	95.99 297	98.69 200	98.45 268	92.73 302	99.61 300	96.79 203	99.03 297	98.82 291

cl____		97.02 270	96.83 266	97.58 285	97.82 356	94.04 315	94.66 378	99.16 218	97.04 249	98.63 207	98.71 227	88.68 335	99.69 257	97.00 182	99.81 98	99.00 263

DIV-MVS_self_test		97.02 270	96.84 265	97.58 285	97.82 356	94.03 316	94.66 378	99.16 218	97.04 249	98.63 207	98.71 227	88.69 333	99.69 257	97.00 182	99.81 98	99.01 259

CANet		97.87 205	97.76 207	98.19 240	97.75 358	95.51 269	96.76 290	99.05 236	97.74 181	96.93 327	98.21 290	95.59 235	99.89 75	97.86 135	99.93 41	99.19 234

UBG		93.25 357	92.32 358	96.04 355	97.72 359	90.16 384	95.92 338	95.91 374	96.03 295	93.95 395	93.04 405	69.60 402	99.52 330	90.72 383	97.98 360	98.45 333

mvsany_test1		97.60 226	97.54 224	97.77 267	97.72 359	95.35 275	95.36 360	97.13 349	94.13 345	99.71 35	99.33 92	97.93 100	99.30 371	97.60 148	98.94 310	98.67 317

PVSNet_0	89.98 21	91.15 376	90.30 379	93.70 385	97.72 359	84.34 410	90.24 406	97.42 339	90.20 389	93.79 396	93.09 404	90.90 319	98.89 395	86.57 398	72.76 413	97.87 367

CR-MVSNet		96.28 299	95.95 297	97.28 306	97.71 362	94.22 306	98.11 161	98.92 258	92.31 370	96.91 330	99.37 82	85.44 357	99.81 181	97.39 158	97.36 376	97.81 370

RPMNet		97.02 270	96.93 257	97.30 305	97.71 362	94.22 306	98.11 161	99.30 172	99.37 45	96.91 330	99.34 90	86.72 344	99.87 101	97.53 152	97.36 376	97.81 370

ETVMVS		92.60 365	91.08 374	97.18 310	97.70 364	93.65 333	96.54 299	95.70 377	96.51 274	94.68 384	92.39 408	61.80 415	99.50 336	86.97 395	97.41 372	98.40 341

pmmvs3		95.03 330	94.40 336	96.93 322	97.70 364	92.53 350	95.08 367	97.71 334	88.57 396	97.71 284	98.08 301	79.39 386	99.82 167	96.19 253	99.11 291	98.43 338

baseline2		93.73 349	92.83 355	96.42 340	97.70 364	91.28 371	96.84 286	89.77 408	93.96 350	92.44 403	95.93 370	79.14 387	99.77 218	92.94 346	96.76 387	98.21 350

WBMVS		95.18 327	94.78 332	96.37 341	97.68 367	89.74 387	95.80 344	98.73 294	97.54 201	98.30 241	98.44 269	70.06 400	99.82 167	96.62 219	99.87 74	99.54 107

tpm		94.67 334	94.34 338	95.66 362	97.68 367	88.42 391	97.88 194	94.90 382	94.46 336	96.03 363	98.56 254	78.66 389	99.79 201	95.88 266	95.01 401	98.78 302

CANet_DTU		97.26 252	97.06 252	97.84 261	97.57 369	94.65 298	96.19 321	98.79 284	97.23 238	95.14 379	98.24 287	93.22 289	99.84 140	97.34 160	99.84 84	99.04 255

testing11		93.08 360	92.02 364	96.26 346	97.56 370	90.83 379	96.32 313	95.70 377	96.47 278	92.66 402	93.73 399	64.36 413	99.59 305	93.77 331	97.57 365	98.37 345

tpm2		93.09 359	92.58 357	94.62 375	97.56 370	86.53 399	97.66 223	95.79 376	86.15 401	94.07 392	98.23 289	75.95 394	99.53 326	90.91 380	96.86 386	97.81 370

testing91		93.32 355	92.27 359	96.47 339	97.54 372	91.25 372	96.17 324	96.76 360	97.18 242	93.65 398	93.50 402	65.11 412	99.63 291	93.04 345	97.45 369	98.53 327

TR-MVS		95.55 320	95.12 325	96.86 329	97.54 372	93.94 320	96.49 303	96.53 365	94.36 341	97.03 325	96.61 357	94.26 274	99.16 383	86.91 397	96.31 391	97.47 384

testing99		93.04 361	91.98 367	96.23 348	97.53 374	90.70 381	96.35 311	95.94 373	96.87 259	93.41 399	93.43 403	63.84 414	99.59 305	93.24 343	97.19 379	98.40 341

1314		95.74 314	95.60 306	96.17 351	97.53 374	92.75 347	98.07 167	98.31 316	91.22 381	94.25 388	96.68 356	95.53 236	99.03 386	91.64 367	97.18 380	96.74 393

CostFormer		93.97 346	93.78 343	94.51 376	97.53 374	85.83 402	97.98 182	95.96 372	89.29 394	94.99 381	98.63 245	78.63 390	99.62 294	94.54 304	96.50 388	98.09 357

FMVSNet5		96.01 305	95.20 323	98.41 219	97.53 374	96.10 249	98.74 90	99.50 87	97.22 241	98.03 265	99.04 154	69.80 401	99.88 84	97.27 163	99.71 155	99.25 219

PMMVS		96.51 290	95.98 296	98.09 245	97.53 374	95.84 259	94.92 371	98.84 276	91.58 376	96.05 362	95.58 376	95.68 232	99.66 280	95.59 282	98.09 353	98.76 305

PAPR		95.29 324	94.47 334	97.75 271	97.50 379	95.14 283	94.89 372	98.71 296	91.39 380	95.35 377	95.48 381	94.57 265	99.14 385	84.95 400	97.37 374	98.97 268

testing222		91.96 373	90.37 377	96.72 334	97.47 380	92.59 348	96.11 326	94.76 383	96.83 261	92.90 401	92.87 406	57.92 416	99.55 319	86.93 396	97.52 366	98.00 363

PatchT		96.65 286	96.35 289	97.54 291	97.40 381	95.32 276	97.98 182	96.64 362	99.33 50	96.89 334	99.42 76	84.32 365	99.81 181	97.69 147	97.49 367	97.48 383

tpm cat1		93.29 356	93.13 353	93.75 384	97.39 382	84.74 405	97.39 249	97.65 336	83.39 406	94.16 389	98.41 271	82.86 374	99.39 358	91.56 369	95.35 400	97.14 388

PatchmatchNet		95.58 319	95.67 304	95.30 370	97.34 383	87.32 397	97.65 225	96.65 361	95.30 318	97.07 321	98.69 231	84.77 360	99.75 231	94.97 294	98.64 330	98.83 290
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 245	96.97 256	98.50 210	97.31 384	96.47 241	98.18 152	98.92 258	98.95 98	98.78 188	99.37 82	85.44 357	99.85 122	95.96 264	99.83 91	99.17 240

LS3D		98.63 121	98.38 145	99.36 63	97.25 385	99.38 9	99.12 56	99.32 159	99.21 62	98.44 232	98.88 198	97.31 146	99.80 188	96.58 222	99.34 252	98.92 277

IB-MVS	91.63 19	92.24 371	90.90 375	96.27 345	97.22 386	91.24 373	94.36 387	93.33 396	92.37 369	92.24 404	94.58 396	66.20 410	99.89 75	93.16 344	94.63 403	97.66 378
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
UWE-MVS		92.38 368	91.76 371	94.21 379	97.16 387	84.65 406	95.42 358	88.45 410	95.96 298	96.17 357	95.84 374	66.36 408	99.71 249	91.87 363	98.64 330	98.28 348

tpmrst		95.07 329	95.46 312	93.91 382	97.11 388	84.36 409	97.62 228	96.96 354	94.98 324	96.35 355	98.80 213	85.46 356	99.59 305	95.60 281	96.23 392	97.79 373

Syy-MVS		96.04 304	95.56 310	97.49 296	97.10 389	94.48 301	96.18 322	96.58 363	95.65 306	94.77 382	92.29 409	91.27 316	99.36 361	98.17 113	98.05 357	98.63 319

myMVS_eth3d		91.92 374	90.45 376	96.30 343	97.10 389	90.90 377	96.18 322	96.58 363	95.65 306	94.77 382	92.29 409	53.88 417	99.36 361	89.59 388	98.05 357	98.63 319

MDTV_nov1_ep13			95.22 322		97.06 391	83.20 411	97.74 213	96.16 368	94.37 340	96.99 326	98.83 207	83.95 368	99.53 326	93.90 325	97.95 361

MVS		93.19 358	92.09 362	96.50 338	96.91 392	94.03 316	98.07 167	98.06 327	68.01 411	94.56 387	96.48 360	95.96 223	99.30 371	83.84 402	96.89 385	96.17 398

E-PMN		94.17 342	94.37 337	93.58 386	96.86 393	85.71 403	90.11 408	97.07 350	98.17 152	97.82 279	97.19 347	84.62 362	98.94 391	89.77 386	97.68 364	96.09 402

JIA-IIPM		95.52 321	95.03 326	97.00 318	96.85 394	94.03 316	96.93 281	95.82 375	99.20 64	94.63 386	99.71 17	83.09 372	99.60 301	94.42 310	94.64 402	97.36 386

EMVS		93.83 348	94.02 340	93.23 390	96.83 395	84.96 404	89.77 409	96.32 367	97.92 169	97.43 308	96.36 365	86.17 349	98.93 392	87.68 393	97.73 363	95.81 403

cl22		95.79 313	95.39 317	96.98 320	96.77 396	92.79 345	94.40 386	98.53 306	94.59 333	97.89 271	98.17 293	82.82 375	99.24 377	96.37 242	99.03 297	98.92 277

WB-MVSnew		95.73 315	95.57 309	96.23 348	96.70 397	90.70 381	96.07 328	93.86 393	95.60 308	97.04 323	95.45 385	96.00 216	99.55 319	91.04 377	98.31 341	98.43 338

dp		93.47 353	93.59 346	93.13 391	96.64 398	81.62 415	97.66 223	96.42 366	92.80 365	96.11 359	98.64 243	78.55 392	99.59 305	93.31 341	92.18 409	98.16 353

test-LLR		93.90 347	93.85 341	94.04 380	96.53 399	84.62 407	94.05 392	92.39 399	96.17 287	94.12 390	95.07 386	82.30 376	99.67 269	95.87 269	98.18 346	97.82 368

test-mter		92.33 370	91.76 371	94.04 380	96.53 399	84.62 407	94.05 392	92.39 399	94.00 349	94.12 390	95.07 386	65.63 411	99.67 269	95.87 269	98.18 346	97.82 368

TESTMET0.1,1		92.19 372	91.77 370	93.46 387	96.48 401	82.80 412	94.05 392	91.52 404	94.45 338	94.00 393	94.88 392	66.65 407	99.56 316	95.78 274	98.11 352	98.02 360

MVS_0304		97.44 239	97.01 255	98.72 176	96.42 402	96.74 231	97.20 266	91.97 402	98.46 128	98.30 241	98.79 215	92.74 301	99.91 60	99.30 41	99.94 36	99.52 118

miper_enhance_ethall		96.01 305	95.74 300	96.81 330	96.41 403	92.27 357	93.69 397	98.89 264	91.14 383	98.30 241	97.35 345	90.58 321	99.58 311	96.31 246	99.03 297	98.60 321

tpmvs		95.02 331	95.25 321	94.33 377	96.39 404	85.87 400	98.08 165	96.83 359	95.46 313	95.51 375	98.69 231	85.91 352	99.53 326	94.16 316	96.23 392	97.58 381

CMPMVS	75.91 23	96.29 298	95.44 314	98.84 153	96.25 405	98.69 87	97.02 274	99.12 225	88.90 395	97.83 277	98.86 201	89.51 328	98.90 394	91.92 361	99.51 225	98.92 277
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 335	93.69 344	96.99 319	96.05 406	93.61 334	94.97 370	93.49 394	96.17 287	97.57 295	94.88 392	82.30 376	99.01 389	93.60 334	94.17 405	98.37 345

EPMVS		93.72 350	93.27 349	95.09 373	96.04 407	87.76 395	98.13 157	85.01 414	94.69 331	96.92 328	98.64 243	78.47 393	99.31 369	95.04 292	96.46 389	98.20 351

cascas		94.79 333	94.33 339	96.15 354	96.02 408	92.36 355	92.34 404	99.26 191	85.34 403	95.08 380	94.96 391	92.96 296	98.53 400	94.41 313	98.59 334	97.56 382

MVStest1		95.86 310	95.60 306	96.63 335	95.87 409	91.70 362	97.93 186	98.94 252	98.03 159	99.56 54	99.66 27	71.83 399	98.26 403	99.35 38	99.24 268	99.91 10

gg-mvs-nofinetune		92.37 369	91.20 373	95.85 357	95.80 410	92.38 354	99.31 26	81.84 416	99.75 6	91.83 405	99.74 13	68.29 403	99.02 387	87.15 394	97.12 381	96.16 399

gm-plane-assit					94.83 411	81.97 414			88.07 398		94.99 389		99.60 301	91.76 364

GG-mvs-BLEND				94.76 374	94.54 412	92.13 359	99.31 26	80.47 417		88.73 411	91.01 411	67.59 406	98.16 405	82.30 407	94.53 404	93.98 407

EPNet_dtu		94.93 332	94.78 332	95.38 369	93.58 413	87.68 396	96.78 288	95.69 379	97.35 222	89.14 410	98.09 300	88.15 340	99.49 339	94.95 295	99.30 259	98.98 265
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 380	75.95 383	77.12 396	92.39 414	67.91 420	90.16 407	59.44 421	82.04 407	89.42 409	94.67 395	49.68 419	81.74 414	48.06 414	77.66 412	81.72 410

KD-MVS_2432*1600		92.87 363	91.99 365	95.51 366	91.37 415	89.27 388	94.07 390	98.14 323	95.42 314	97.25 316	96.44 362	67.86 404	99.24 377	91.28 373	96.08 395	98.02 360

miper_refine_blended		92.87 363	91.99 365	95.51 366	91.37 415	89.27 388	94.07 390	98.14 323	95.42 314	97.25 316	96.44 362	67.86 404	99.24 377	91.28 373	96.08 395	98.02 360

EPNet		96.14 302	95.44 314	98.25 235	90.76 417	95.50 270	97.92 189	94.65 384	98.97 95	92.98 400	98.85 204	89.12 331	99.87 101	95.99 262	99.68 168	99.39 175
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 381	68.95 384	70.34 397	87.68 418	65.00 421	91.11 405	59.90 420	69.02 410	74.46 415	88.89 412	48.58 420	68.03 416	28.61 415	72.33 414	77.99 411

test_method		79.78 378	79.50 381	80.62 394	80.21 419	45.76 422	70.82 410	98.41 313	31.08 414	80.89 414	97.71 322	84.85 359	97.37 407	91.51 370	80.03 411	98.75 306

tmp_tt		78.77 379	78.73 382	78.90 395	58.45 420	74.76 419	94.20 389	78.26 418	39.16 413	86.71 412	92.82 407	80.50 380	75.19 415	86.16 399	92.29 408	86.74 409

testmvs		17.12 383	20.53 386	6.87 399	12.05 421	4.20 424	93.62 398	6.73 422	4.62 417	10.41 417	24.33 414	8.28 422	3.56 418	9.69 417	15.07 415	12.86 414

test123		17.04 384	20.11 387	7.82 398	10.25 422	4.91 423	94.80 373	4.47 423	4.93 416	10.00 418	24.28 415	9.69 421	3.64 417	10.14 416	12.43 416	14.92 413

test_blank		0.00 387	0.00 390	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.00 418	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

eth-test2					0.00 423

eth-test					0.00 423

uanet_test		0.00 387	0.00 390	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.00 418	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

DCPMVS		0.00 387	0.00 390	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.00 418	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

cdsmvs_eth3d_5k		24.66 382	32.88 385	0.00 400	0.00 423	0.00 425	0.00 411	99.10 228	0.00 418	0.00 419	97.58 330	99.21 16	0.00 419	0.00 418	0.00 417	0.00 415

pcd_1.5k_mvsjas		8.17 385	10.90 388	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.00 418	98.07 88	0.00 419	0.00 418	0.00 417	0.00 415

sosnet-low-res		0.00 387	0.00 390	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.00 418	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

sosnet		0.00 387	0.00 390	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.00 418	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

uncertanet		0.00 387	0.00 390	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.00 418	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

Regformer		0.00 387	0.00 390	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.00 418	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

ab-mvs-re		8.12 386	10.83 389	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	97.48 336	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

uanet		0.00 387	0.00 390	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.00 418	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

WAC-MVS						90.90 377								91.37 372

PC_three_1452									93.27 357	99.40 85	98.54 255	98.22 76	97.00 408	95.17 290	99.45 237	99.49 128

test_241102_TWO								99.30 172	98.03 159	99.26 112	99.02 157	97.51 135	99.88 84	96.91 190	99.60 195	99.66 57

test_0728_THIRD									98.17 152	99.08 134	99.02 157	97.89 101	99.88 84	97.07 178	99.71 155	99.70 51

GSMVS																98.81 295

sam_mvs1												84.74 361				98.81 295

sam_mvs												84.29 367

MTGPA								99.20 203

test_post1							97.59 233				20.48 417	83.07 373	99.66 280	94.16 316

test_post											21.25 416	83.86 369	99.70 253

patchmatchnet-post											98.77 219	84.37 364	99.85 122

MTMP							97.93 186	91.91 403

test9_res														93.28 342	99.15 284	99.38 182

agg_prior2														92.50 358	99.16 282	99.37 184

test_prior4						97.97 151	95.86 340

test_prior2							95.74 346		96.48 277	96.11 359	97.63 328	95.92 226		94.16 316	99.20 276

旧先验2							95.76 345		88.56 397	97.52 299			99.66 280	94.48 306

新几何2							95.93 336

无先验							95.74 346	98.74 293	89.38 393				99.73 241	92.38 360		99.22 228

原ACMM2							95.53 352

testdata2													99.79 201	92.80 352

segment_acmp												97.02 165

testdata1							95.44 357		96.32 283

plane_prior5								99.27 186					99.70 253	94.42 310	99.51 225	99.45 151

plane_prior4											97.98 307

plane_prior3						97.78 172			97.41 216	97.79 280

plane_prior2							97.77 208		98.20 149

plane_prior						97.65 181	97.07 273		96.72 267						99.36 248

n2								0.00 424

nn								0.00 424

door-mid								99.57 63

test11								98.87 267

door								99.41 125

HQP5-MVS						96.79 227

BP-MVS														92.82 350

HQP4-MVS										95.56 369			99.54 324			99.32 203

HQP3-MVS								99.04 239							99.26 266

HQP2-MVS												93.84 281

MDTV_nov1_ep13_2view						74.92 418	97.69 218		90.06 391	97.75 283		85.78 353		93.52 336		98.69 313

ACMMP++_ref															99.77 124

ACMMP++															99.68 168

Test By Simon												96.52 193

High-resolution multi-view benchmark