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 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 13	100.00 1	99.85 26

Gipuma		99.03 67	99.16 52	98.64 189	99.94 2	98.51 104	99.32 23	99.75 37	99.58 29	98.60 222	99.62 37	98.22 84	99.51 348	97.70 154	99.73 150	97.89 380
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 26	99.31 36	99.53 37	99.91 3	98.98 69	99.63 7	99.58 63	99.44 42	99.78 31	99.76 12	96.39 208	99.92 54	99.44 41	99.92 58	99.68 61

pmmvs6		99.67 3	99.70 3	99.60 14	99.90 4	99.27 26	99.53 8	99.76 34	99.64 19	99.84 23	99.83 4	99.50 9	99.87 113	99.36 43	99.92 58	99.64 71

PS-MVSNAJss		99.46 14	99.49 13	99.35 72	99.90 4	98.15 131	99.20 45	99.65 53	99.48 34	99.92 8	99.71 19	98.07 97	99.96 12	99.53 35	100.00 1	99.93 11

testf1		99.25 37	99.16 52	99.51 46	99.89 6	99.63 4	98.71 99	99.69 44	98.90 111	99.43 84	99.35 93	98.86 30	99.67 280	97.81 145	99.81 104	99.24 234

APD_test2		99.25 37	99.16 52	99.51 46	99.89 6	99.63 4	98.71 99	99.69 44	98.90 111	99.43 84	99.35 93	98.86 30	99.67 280	97.81 145	99.81 104	99.24 234

ANet_high		99.57 7	99.67 5	99.28 88	99.89 6	98.09 138	99.14 54	99.93 5	99.82 5	99.93 6	99.81 6	99.17 19	99.94 38	99.31 46	100.00 1	99.82 31

anonymousdsp		99.51 11	99.47 18	99.62 9	99.88 9	99.08 67	99.34 20	99.69 44	98.93 109	99.65 50	99.72 18	98.93 28	99.95 24	99.11 60	100.00 1	99.82 31

v7n		99.53 9	99.57 10	99.41 62	99.88 9	98.54 102	99.45 11	99.61 59	99.66 17	99.68 44	99.66 29	98.44 65	99.95 24	99.73 22	99.96 27	99.75 50

mvs_tets		99.63 5	99.67 5	99.49 51	99.88 9	98.61 94	99.34 20	99.71 40	99.27 63	99.90 13	99.74 15	99.68 4	99.97 5	99.55 34	99.99 5	99.88 19

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 66	99.87 12	98.13 134	98.08 170	99.95 1	99.45 40	99.98 2	99.75 13	99.80 1	99.97 5	99.82 9	99.99 5	99.99 2

jajsoiax		99.58 6	99.61 8	99.48 53	99.87 12	98.61 94	99.28 37	99.66 52	99.09 91	99.89 16	99.68 22	99.53 7	99.97 5	99.50 38	99.99 5	99.87 20

test_djsdf		99.52 10	99.51 12	99.53 37	99.86 14	98.74 84	99.39 17	99.56 77	99.11 81	99.70 40	99.73 17	99.00 23	99.97 5	99.26 50	99.98 12	99.89 16

MIMVSNet1		99.38 25	99.32 34	99.55 27	99.86 14	99.19 41	99.41 14	99.59 61	99.59 27	99.71 38	99.57 46	97.12 168	99.90 69	99.21 55	99.87 81	99.54 118

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 25	99.85 16	99.11 63	99.90 1	99.78 32	99.63 21	99.78 31	99.67 27	99.48 10	99.81 192	99.30 47	99.97 20	99.77 41
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 19	99.69 5	99.58 63	99.90 3	99.86 20	99.78 10	99.58 6	99.95 24	99.00 69	99.95 34	99.78 39

SixPastTwentyTwo		98.75 104	98.62 115	99.16 108	99.83 18	97.96 158	99.28 37	98.20 331	99.37 50	99.70 40	99.65 33	92.65 311	99.93 45	99.04 66	99.84 90	99.60 84

Baseline_NR-MVSNet		98.98 73	98.86 83	99.36 66	99.82 19	98.55 99	97.47 258	99.57 70	99.37 50	99.21 128	99.61 40	96.76 192	99.83 168	98.06 129	99.83 97	99.71 53

pm-mvs1		99.44 16	99.48 15	99.33 81	99.80 20	98.63 91	99.29 33	99.63 55	99.30 60	99.65 50	99.60 42	99.16 21	99.82 178	99.07 63	99.83 97	99.56 107

TransMVSNet (Re)		99.44 16	99.47 18	99.36 66	99.80 20	98.58 97	99.27 39	99.57 70	99.39 48	99.75 35	99.62 37	99.17 19	99.83 168	99.06 64	99.62 198	99.66 65

K. test v3		98.00 202	97.66 226	99.03 133	99.79 22	97.56 190	99.19 49	92.47 413	99.62 24	99.52 67	99.66 29	89.61 337	99.96 12	99.25 52	99.81 104	99.56 107

test_fmvsmconf0.1_n		99.49 12	99.54 11	99.34 75	99.78 23	98.11 135	97.77 217	99.90 11	99.33 55	99.97 3	99.66 29	99.71 3	99.96 12	99.79 15	99.99 5	99.96 8

APD_test1		98.83 91	98.66 109	99.34 75	99.78 23	99.47 9	98.42 136	99.45 118	98.28 156	98.98 158	99.19 128	97.76 121	99.58 323	96.57 237	99.55 225	98.97 282

test_vis3_rt		99.14 52	99.17 50	99.07 123	99.78 23	98.38 111	98.92 79	99.94 2	97.80 193	99.91 12	99.67 27	97.15 167	98.91 406	99.76 18	99.56 221	99.92 12

EGC-MVSNET		85.24 393	80.54 396	99.34 75	99.77 26	99.20 38	99.08 58	99.29 190	12.08 431	20.84 432	99.42 80	97.55 139	99.85 133	97.08 189	99.72 158	98.96 284

Anonymous20240521		98.69 115	98.87 80	98.16 252	99.77 26	95.11 294	99.08 58	99.44 122	99.34 54	99.33 104	99.55 54	94.10 287	99.94 38	99.25 52	99.96 27	99.42 173

FC-MVSNet-test		99.27 34	99.25 45	99.34 75	99.77 26	98.37 113	99.30 32	99.57 70	99.61 26	99.40 92	99.50 64	97.12 168	99.85 133	99.02 68	99.94 42	99.80 35

test_vis1_n		98.31 174	98.50 131	97.73 285	99.76 29	94.17 319	98.68 102	99.91 9	96.31 299	99.79 30	99.57 46	92.85 307	99.42 367	99.79 15	99.84 90	99.60 84

test_fmvs3		99.12 58	99.41 22	98.25 244	99.76 29	95.07 295	99.05 64	99.94 2	97.78 195	99.82 25	99.84 3	98.56 56	99.71 260	99.96 1	99.96 27	99.97 4

XXY-MVS		99.14 52	99.15 57	99.10 117	99.76 29	97.74 179	98.85 87	99.62 56	98.48 141	99.37 97	99.49 70	98.75 38	99.86 121	98.20 119	99.80 115	99.71 53

TDRefinement		99.42 21	99.38 25	99.55 27	99.76 29	99.33 20	99.68 6	99.71 40	99.38 49	99.53 65	99.61 40	98.64 46	99.80 199	98.24 116	99.84 90	99.52 129

fmvsm_s_conf0.1_n_a		99.17 47	99.30 39	98.80 164	99.75 33	96.59 243	97.97 192	99.86 16	98.22 159	99.88 18	99.71 19	98.59 52	99.84 151	99.73 22	99.98 12	99.98 3

tt0805		98.69 115	98.62 115	98.90 154	99.75 33	99.30 21	99.15 53	96.97 366	98.86 114	98.87 187	97.62 342	98.63 48	98.96 403	99.41 42	98.29 355	98.45 346

test_vis1_n_1920		98.40 161	98.92 75	96.81 341	99.74 35	90.76 392	98.15 160	99.91 9	98.33 147	99.89 16	99.55 54	95.07 258	99.88 96	99.76 18	99.93 47	99.79 36

FOURS1					99.73 36	99.67 3	99.43 12	99.54 85	99.43 44	99.26 120

PEN-MVS		99.41 22	99.34 31	99.62 9	99.73 36	99.14 56	99.29 33	99.54 85	99.62 24	99.56 57	99.42 80	98.16 92	99.96 12	98.78 83	99.93 47	99.77 41

lessismore_v0				98.97 141	99.73 36	97.53 192		86.71 428		99.37 97	99.52 63	89.93 335	99.92 54	98.99 70	99.72 158	99.44 166

SteuartSystems-ACMMP		98.79 97	98.54 126	99.54 30	99.73 36	99.16 47	98.23 150	99.31 174	97.92 184	98.90 178	98.90 201	98.00 103	99.88 96	96.15 269	99.72 158	99.58 96
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 192	98.15 183	98.22 247	99.73 36	95.15 291	97.36 265	99.68 49	94.45 354	98.99 157	99.27 110	96.87 182	99.94 38	97.13 186	99.91 66	99.57 101

Vis-MVSNet		99.34 27	99.36 28	99.27 91	99.73 36	98.26 120	99.17 50	99.78 32	99.11 81	99.27 116	99.48 71	98.82 33	99.95 24	98.94 73	99.93 47	99.59 90
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSC-MVS		98.71 108	98.74 93	98.62 195	99.72 42	96.08 260	98.74 92	98.64 311	99.74 10	99.67 46	99.24 119	94.57 273	99.95 24	99.11 60	99.24 279	99.82 31

test_f		98.67 123	98.87 80	98.05 261	99.72 42	95.59 272	98.51 123	99.81 27	96.30 301	99.78 31	99.82 5	96.14 218	98.63 413	99.82 9	99.93 47	99.95 9

ACMH	96.65 7	99.25 37	99.24 46	99.26 93	99.72 42	98.38 111	99.07 61	99.55 81	98.30 151	99.65 50	99.45 77	99.22 16	99.76 235	98.44 107	99.77 131	99.64 71
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n		99.16 50	99.33 32	98.64 189	99.71 45	96.10 255	97.87 204	99.85 18	98.56 137	99.90 13	99.68 22	98.69 43	99.85 133	99.72 24	99.98 12	99.97 4

PS-CasMVS		99.40 23	99.33 32	99.62 9	99.71 45	99.10 64	99.29 33	99.53 88	99.53 31	99.46 79	99.41 84	98.23 81	99.95 24	98.89 77	99.95 34	99.81 34

DTE-MVSNet		99.43 20	99.35 29	99.66 7	99.71 45	99.30 21	99.31 27	99.51 92	99.64 19	99.56 57	99.46 73	98.23 81	99.97 5	98.78 83	99.93 47	99.72 52

WR-MVS_H		99.33 28	99.22 47	99.65 8	99.71 45	99.24 29	99.32 23	99.55 81	99.46 39	99.50 73	99.34 97	97.30 157	99.93 45	98.90 75	99.93 47	99.77 41

HPM-MVS_fast		99.01 68	98.82 86	99.57 20	99.71 45	99.35 16	99.00 69	99.50 94	97.33 237	98.94 173	98.86 211	98.75 38	99.82 178	97.53 164	99.71 163	99.56 107

ACMH+	96.62 9	99.08 65	99.00 68	99.33 81	99.71 45	98.83 79	98.60 109	99.58 63	99.11 81	99.53 65	99.18 132	98.81 34	99.67 280	96.71 226	99.77 131	99.50 135

PMVS	91.26 20	97.86 215	97.94 205	97.65 289	99.71 45	97.94 160	98.52 118	98.68 307	98.99 102	97.52 312	99.35 93	97.41 152	98.18 419	91.59 383	99.67 184	96.82 408
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 52	99.09 61	99.29 87	99.70 52	98.28 119	99.13 55	99.52 91	99.48 34	99.24 125	99.41 84	96.79 189	99.82 178	98.69 93	99.88 78	99.76 46

VPNet		98.87 86	98.83 85	99.01 136	99.70 52	97.62 188	98.43 134	99.35 155	99.47 37	99.28 114	99.05 162	96.72 195	99.82 178	98.09 126	99.36 259	99.59 90

fmvsm_s_conf0.1_n_2		99.20 45	99.38 25	98.65 187	99.69 54	96.08 260	97.49 255	99.90 11	99.53 31	99.88 18	99.64 34	98.51 59	99.90 69	99.83 8	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 171	98.68 106	97.27 318	99.69 54	92.29 367	98.03 178	99.85 18	97.62 204	99.96 4	99.62 37	93.98 288	99.74 247	99.52 37	99.86 85	99.79 36

MP-MVS-pluss		98.57 137	98.23 173	99.60 14	99.69 54	99.35 16	97.16 283	99.38 142	94.87 344	98.97 162	98.99 180	98.01 102	99.88 96	97.29 174	99.70 170	99.58 96
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 41	99.32 34	98.96 142	99.68 57	97.35 201	98.84 89	99.48 103	99.69 13	99.63 53	99.68 22	99.03 22	99.96 12	97.97 136	99.92 58	99.57 101

sd_testset		99.28 33	99.31 36	99.19 104	99.68 57	98.06 147	99.41 14	99.30 182	99.69 13	99.63 53	99.68 22	99.25 15	99.96 12	97.25 177	99.92 58	99.57 101

test_fmvs1_n		98.09 196	98.28 165	97.52 304	99.68 57	93.47 346	98.63 105	99.93 5	95.41 332	99.68 44	99.64 34	91.88 320	99.48 355	99.82 9	99.87 81	99.62 75

CHOSEN 1792x2688		97.49 244	97.14 259	98.54 213	99.68 57	96.09 258	96.50 316	99.62 56	91.58 392	98.84 190	98.97 186	92.36 313	99.88 96	96.76 219	99.95 34	99.67 64

tfpnnormal		98.90 83	98.90 77	98.91 151	99.67 61	97.82 171	99.00 69	99.44 122	99.45 40	99.51 72	99.24 119	98.20 87	99.86 121	95.92 278	99.69 173	99.04 269

MTAPA		98.88 85	98.64 112	99.61 12	99.67 61	99.36 15	98.43 134	99.20 213	98.83 118	98.89 180	98.90 201	96.98 178	99.92 54	97.16 181	99.70 170	99.56 107

test_fmvsmvis_n_1920		99.26 36	99.49 13	98.54 213	99.66 63	96.97 223	98.00 184	99.85 18	99.24 65	99.92 8	99.50 64	99.39 12	99.95 24	99.89 3	99.98 12	98.71 323

mvs5depth		99.30 30	99.59 9	98.44 226	99.65 64	95.35 283	99.82 3	99.94 2	99.83 4	99.42 87	99.94 2	98.13 95	99.96 12	99.63 28	99.96 27	100.00 1

fmvsm_l_conf0.5_n_a		99.19 46	99.27 42	98.94 145	99.65 64	97.05 219	97.80 213	99.76 34	98.70 122	99.78 31	99.11 148	98.79 36	99.95 24	99.85 5	99.96 27	99.83 28

WB-MVS		98.52 150	98.55 124	98.43 227	99.65 64	95.59 272	98.52 118	98.77 297	99.65 18	99.52 67	99.00 179	94.34 279	99.93 45	98.65 95	98.83 327	99.76 46

CP-MVSNet		99.21 43	99.09 61	99.56 25	99.65 64	98.96 74	99.13 55	99.34 161	99.42 45	99.33 104	99.26 114	97.01 176	99.94 38	98.74 88	99.93 47	99.79 36

HPM-MVS		98.79 97	98.53 127	99.59 18	99.65 64	99.29 23	99.16 51	99.43 128	96.74 281	98.61 220	98.38 288	98.62 49	99.87 113	96.47 249	99.67 184	99.59 90
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 132	98.36 155	99.42 60	99.65 64	99.42 11	98.55 114	99.57 70	97.72 198	98.90 178	99.26 114	96.12 220	99.52 343	95.72 289	99.71 163	99.32 215

fmvsm_l_conf0.5_n		99.21 43	99.28 41	99.02 135	99.64 70	97.28 205	97.82 209	99.76 34	98.73 119	99.82 25	99.09 154	98.81 34	99.95 24	99.86 4	99.96 27	99.83 28

test_fmvsmconf_n		99.44 16	99.48 15	99.31 86	99.64 70	98.10 137	97.68 229	99.84 21	99.29 61	99.92 8	99.57 46	99.60 5	99.96 12	99.74 21	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 129	98.49 135	99.06 129	99.64 70	97.90 162	98.51 123	98.94 262	96.96 268	99.24 125	98.89 207	97.83 114	99.81 192	96.88 209	99.49 244	99.48 149
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 93	98.72 97	99.12 113	99.64 70	98.54 102	97.98 189	99.68 49	97.62 204	99.34 103	99.18 132	97.54 140	99.77 229	97.79 147	99.74 147	99.04 269

KD-MVS_self_test		99.25 37	99.18 49	99.44 59	99.63 74	99.06 68	98.69 101	99.54 85	99.31 58	99.62 56	99.53 60	97.36 155	99.86 121	99.24 54	99.71 163	99.39 186

EU-MVSNet		97.66 232	98.50 131	95.13 383	99.63 74	85.84 414	98.35 142	98.21 330	98.23 158	99.54 61	99.46 73	95.02 259	99.68 277	98.24 116	99.87 81	99.87 20

HyFIR lowres test		97.19 270	96.60 294	98.96 142	99.62 76	97.28 205	95.17 380	99.50 94	94.21 359	99.01 155	98.32 296	86.61 355	99.99 2	97.10 188	99.84 90	99.60 84

fmvsm_l_conf0.5_n_3		99.45 15	99.48 15	99.34 75	99.59 77	98.21 128	97.82 209	99.84 21	99.41 47	99.92 8	99.41 84	99.51 8	99.95 24	99.84 7	99.97 20	99.87 20

mmtdpeth		99.30 30	99.42 21	98.92 150	99.58 78	96.89 230	99.48 10	99.92 7	99.92 2	98.26 257	99.80 9	98.33 74	99.91 63	99.56 33	99.95 34	99.97 4

ACMMP_NAP		98.75 104	98.48 136	99.57 20	99.58 78	99.29 23	97.82 209	99.25 202	96.94 270	98.78 197	99.12 147	98.02 101	99.84 151	97.13 186	99.67 184	99.59 90

nrg030		99.40 23	99.35 29	99.54 30	99.58 78	99.13 59	98.98 72	99.48 103	99.68 15	99.46 79	99.26 114	98.62 49	99.73 252	99.17 58	99.92 58	99.76 46

VDDNet		98.21 187	97.95 203	99.01 136	99.58 78	97.74 179	99.01 67	97.29 357	99.67 16	98.97 162	99.50 64	90.45 332	99.80 199	97.88 142	99.20 287	99.48 149

COLMAP_ROB	96.50 10	98.99 70	98.85 84	99.41 62	99.58 78	99.10 64	98.74 92	99.56 77	99.09 91	99.33 104	99.19 128	98.40 67	99.72 259	95.98 276	99.76 143	99.42 173
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 28	99.45 20	98.99 138	99.57 83	97.73 181	97.93 193	99.83 24	99.22 66	99.93 6	99.30 105	99.42 11	99.96 12	99.85 5	99.99 5	99.29 224

ZNCC-MVS		98.68 120	98.40 148	99.54 30	99.57 83	99.21 32	98.46 131	99.29 190	97.28 243	98.11 269	98.39 286	98.00 103	99.87 113	96.86 212	99.64 192	99.55 114

MSP-MVS		98.40 161	98.00 198	99.61 12	99.57 83	99.25 28	98.57 112	99.35 155	97.55 214	99.31 112	97.71 335	94.61 272	99.88 96	96.14 270	99.19 290	99.70 58
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		98.32 172	98.39 151	98.13 253	99.57 83	95.54 275	97.78 215	99.49 101	97.37 234	99.19 130	97.65 339	98.96 25	99.49 352	96.50 248	98.99 315	99.34 208

MP-MVS		98.46 155	98.09 188	99.54 30	99.57 83	99.22 31	98.50 125	99.19 217	97.61 207	97.58 306	98.66 249	97.40 153	99.88 96	94.72 315	99.60 205	99.54 118
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 108	98.46 140	99.47 56	99.57 83	98.97 70	98.23 150	99.48 103	96.60 286	99.10 140	99.06 155	98.71 41	99.83 168	95.58 296	99.78 125	99.62 75

LGP-MVS_train				99.47 56	99.57 83	98.97 70		99.48 103	96.60 286	99.10 140	99.06 155	98.71 41	99.83 168	95.58 296	99.78 125	99.62 75

IS-MVSNet		98.19 189	97.90 209	99.08 121	99.57 83	97.97 155	99.31 27	98.32 326	99.01 101	98.98 158	99.03 166	91.59 322	99.79 212	95.49 298	99.80 115	99.48 149

dcpmvs_2		98.78 99	99.11 58	97.78 275	99.56 91	93.67 341	99.06 62	99.86 16	99.50 33	99.66 47	99.26 114	97.21 165	99.99 2	98.00 134	99.91 66	99.68 61

test_0402		98.76 103	98.71 100	98.93 147	99.56 91	98.14 133	98.45 133	99.34 161	99.28 62	98.95 166	98.91 198	98.34 73	99.79 212	95.63 293	99.91 66	98.86 301

EPP-MVSNet		98.30 175	98.04 194	99.07 123	99.56 91	97.83 168	99.29 33	98.07 337	99.03 99	98.59 224	99.13 146	92.16 316	99.90 69	96.87 210	99.68 178	99.49 139

ACMMP		98.75 104	98.50 131	99.52 42	99.56 91	99.16 47	98.87 84	99.37 146	97.16 258	98.82 194	99.01 176	97.71 124	99.87 113	96.29 261	99.69 173	99.54 118
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 60	99.20 48	98.78 170	99.55 95	96.59 243	97.79 214	99.82 26	98.21 160	99.81 28	99.53 60	98.46 63	99.84 151	99.70 25	99.97 20	99.90 15

fmvsm_s_conf0.5_n		99.09 61	99.26 44	98.61 198	99.55 95	96.09 258	97.74 223	99.81 27	98.55 138	99.85 22	99.55 54	98.60 51	99.84 151	99.69 27	99.98 12	99.89 16

FMVSNet1		99.17 47	99.17 50	99.17 105	99.55 95	98.24 122	99.20 45	99.44 122	99.21 68	99.43 84	99.55 54	97.82 117	99.86 121	98.42 109	99.89 76	99.41 176

Vis-MVSNet (Re-imp)		97.46 246	97.16 256	98.34 237	99.55 95	96.10 255	98.94 77	98.44 320	98.32 149	98.16 263	98.62 258	88.76 342	99.73 252	93.88 341	99.79 120	99.18 249

ACMM	96.08 12	98.91 81	98.73 95	99.48 53	99.55 95	99.14 56	98.07 172	99.37 146	97.62 204	99.04 151	98.96 189	98.84 32	99.79 212	97.43 168	99.65 190	99.49 139
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 112	98.97 72	97.89 268	99.54 100	94.05 322	98.55 114	99.92 7	96.78 279	99.72 36	99.78 10	96.60 200	99.67 280	99.91 2	99.90 72	99.94 10

mPP-MVS		98.64 127	98.34 158	99.54 30	99.54 100	99.17 43	98.63 105	99.24 207	97.47 221	98.09 271	98.68 244	97.62 133	99.89 82	96.22 264	99.62 198	99.57 101

XVG-ACMP-BASELINE		98.56 138	98.34 158	99.22 101	99.54 100	98.59 96	97.71 226	99.46 114	97.25 246	98.98 158	98.99 180	97.54 140	99.84 151	95.88 279	99.74 147	99.23 236

region2R		98.69 115	98.40 148	99.54 30	99.53 103	99.17 43	98.52 118	99.31 174	97.46 226	98.44 242	98.51 272	97.83 114	99.88 96	96.46 250	99.58 214	99.58 96

PGM-MVS		98.66 124	98.37 154	99.55 27	99.53 103	99.18 42	98.23 150	99.49 101	97.01 267	98.69 208	98.88 208	98.00 103	99.89 82	95.87 282	99.59 209	99.58 96

Patchmatch-RL test		97.26 263	97.02 264	97.99 265	99.52 105	95.53 276	96.13 341	99.71 40	97.47 221	99.27 116	99.16 138	84.30 376	99.62 305	97.89 139	99.77 131	98.81 309

ACMMPR		98.70 112	98.42 146	99.54 30	99.52 105	99.14 56	98.52 118	99.31 174	97.47 221	98.56 229	98.54 267	97.75 122	99.88 96	96.57 237	99.59 209	99.58 96

GST-MVS		98.61 133	98.30 163	99.52 42	99.51 107	99.20 38	98.26 148	99.25 202	97.44 229	98.67 211	98.39 286	97.68 125	99.85 133	96.00 274	99.51 236	99.52 129

Anonymous20231206		98.21 187	98.21 174	98.20 248	99.51 107	95.43 281	98.13 162	99.32 169	96.16 304	98.93 174	98.82 220	96.00 225	99.83 168	97.32 173	99.73 150	99.36 202

ACMP	95.32 15	98.41 159	98.09 188	99.36 66	99.51 107	98.79 82	97.68 229	99.38 142	95.76 319	98.81 196	98.82 220	98.36 69	99.82 178	94.75 312	99.77 131	99.48 149
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 102	98.52 128	99.52 42	99.50 110	99.21 32	98.02 180	98.84 286	97.97 178	99.08 142	99.02 167	97.61 134	99.88 96	96.99 196	99.63 195	99.48 149
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 14	99.50 110	99.23 30	98.02 180	99.32 169					99.88 96	96.99 196	99.63 195	99.68 61

test0726					99.50 110	99.21 32	98.17 158	99.35 155	97.97 178	99.26 120	99.06 155	97.61 134

AllTest		98.44 157	98.20 175	99.16 108	99.50 110	98.55 99	98.25 149	99.58 63	96.80 277	98.88 183	99.06 155	97.65 128	99.57 325	94.45 322	99.61 203	99.37 195

TestCases				99.16 108	99.50 110	98.55 99		99.58 63	96.80 277	98.88 183	99.06 155	97.65 128	99.57 325	94.45 322	99.61 203	99.37 195

XVG-OURS		98.53 146	98.34 158	99.11 115	99.50 110	98.82 81	95.97 347	99.50 94	97.30 241	99.05 149	98.98 184	99.35 13	99.32 381	95.72 289	99.68 178	99.18 249

EG-PatchMatch MVS		98.99 70	99.01 67	98.94 145	99.50 110	97.47 194	98.04 177	99.59 61	98.15 171	99.40 92	99.36 92	98.58 55	99.76 235	98.78 83	99.68 178	99.59 90

fmvsm_s_conf0.5_n_2		99.14 52	99.31 36	98.63 193	99.49 117	96.08 260	97.38 262	99.81 27	99.48 34	99.84 23	99.57 46	98.46 63	99.89 82	99.82 9	99.97 20	99.91 13

SED-MVS		98.91 81	98.72 97	99.49 51	99.49 117	99.17 43	98.10 168	99.31 174	98.03 174	99.66 47	99.02 167	98.36 69	99.88 96	96.91 202	99.62 198	99.41 176

IU-MVS					99.49 117	99.15 51		98.87 277	92.97 377	99.41 89				96.76 219	99.62 198	99.66 65

test_241102_ONE					99.49 117	99.17 43		99.31 174	97.98 177	99.66 47	98.90 201	98.36 69	99.48 355

UA-Net		99.47 13	99.40 23	99.70 2	99.49 117	99.29 23	99.80 4	99.72 38	99.82 5	99.04 151	99.81 6	98.05 100	99.96 12	98.85 79	99.99 5	99.86 24

HFP-MVS		98.71 108	98.44 143	99.51 46	99.49 117	99.16 47	98.52 118	99.31 174	97.47 221	98.58 226	98.50 276	97.97 107	99.85 133	96.57 237	99.59 209	99.53 126

VPA-MVSNet		99.30 30	99.30 39	99.28 88	99.49 117	98.36 116	99.00 69	99.45 118	99.63 21	99.52 67	99.44 78	98.25 79	99.88 96	99.09 62	99.84 90	99.62 75

XVG-OURS-SEG-HR		98.49 152	98.28 165	99.14 111	99.49 117	98.83 79	96.54 312	99.48 103	97.32 239	99.11 137	98.61 260	99.33 14	99.30 384	96.23 263	98.38 351	99.28 226

114514_t		96.50 303	95.77 311	98.69 184	99.48 125	97.43 198	97.84 208	99.55 81	81.42 424	96.51 364	98.58 264	95.53 245	99.67 280	93.41 354	99.58 214	98.98 279

IterMVS-LS		98.55 142	98.70 103	98.09 254	99.48 125	94.73 303	97.22 278	99.39 140	98.97 105	99.38 95	99.31 104	96.00 225	99.93 45	98.58 98	99.97 20	99.60 84
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v8		99.01 68	99.16 52	98.57 205	99.47 127	96.31 252	98.90 80	99.47 111	99.03 99	99.52 67	99.57 46	96.93 179	99.81 192	99.60 29	99.98 12	99.60 84

SSC-MVS3.2		98.53 146	98.79 89	97.74 282	99.46 128	93.62 344	96.45 318	99.34 161	99.33 55	98.93 174	98.70 240	97.90 110	99.90 69	99.12 59	99.92 58	99.69 60

fmvsm_s_conf0.5_n_3		99.22 42	99.37 27	98.78 170	99.46 128	96.58 245	97.65 235	99.72 38	99.47 37	99.86 20	99.50 64	98.94 26	99.89 82	99.75 20	99.97 20	99.86 24

XVS		98.72 107	98.45 141	99.53 37	99.46 128	99.21 32	98.65 103	99.34 161	98.62 127	97.54 310	98.63 256	97.50 146	99.83 168	96.79 215	99.53 231	99.56 107

X-MVStestdata		94.32 351	92.59 370	99.53 37	99.46 128	99.21 32	98.65 103	99.34 161	98.62 127	97.54 310	45.85 429	97.50 146	99.83 168	96.79 215	99.53 231	99.56 107

test20.03		98.78 99	98.77 92	98.78 170	99.46 128	97.20 212	97.78 215	99.24 207	99.04 98	99.41 89	98.90 201	97.65 128	99.76 235	97.70 154	99.79 120	99.39 186

CSCG		98.68 120	98.50 131	99.20 102	99.45 133	98.63 91	98.56 113	99.57 70	97.87 188	98.85 188	98.04 317	97.66 127	99.84 151	96.72 224	99.81 104	99.13 258

GeoE		99.05 66	98.99 70	99.25 96	99.44 134	98.35 117	98.73 96	99.56 77	98.42 143	98.91 177	98.81 222	98.94 26	99.91 63	98.35 111	99.73 150	99.49 139

v148		98.45 156	98.60 120	98.00 264	99.44 134	94.98 296	97.44 260	99.06 243	98.30 151	99.32 110	98.97 186	96.65 198	99.62 305	98.37 110	99.85 86	99.39 186

v10		98.97 74	99.11 58	98.55 210	99.44 134	96.21 254	98.90 80	99.55 81	98.73 119	99.48 74	99.60 42	96.63 199	99.83 168	99.70 25	99.99 5	99.61 83

V42		98.78 99	98.78 91	98.76 175	99.44 134	97.04 220	98.27 147	99.19 217	97.87 188	99.25 124	99.16 138	96.84 183	99.78 223	99.21 55	99.84 90	99.46 158

MDA-MVSNet-bldmvs		97.94 206	97.91 208	98.06 259	99.44 134	94.96 297	96.63 310	99.15 233	98.35 145	98.83 191	99.11 148	94.31 280	99.85 133	96.60 234	98.72 333	99.37 195

casdiffmvs_mvg		99.12 58	99.16 52	98.99 138	99.43 139	97.73 181	98.00 184	99.62 56	99.22 66	99.55 60	99.22 124	98.93 28	99.75 242	98.66 94	99.81 104	99.50 135
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		96.49 304	96.82 278	95.52 376	99.42 140	87.08 411	99.22 42	87.14 427	99.11 81	99.46 79	99.58 44	88.69 343	99.86 121	98.80 81	99.95 34	99.62 75

v2v482		98.56 138	98.62 115	98.37 234	99.42 140	95.81 269	97.58 245	99.16 228	97.90 186	99.28 114	99.01 176	95.98 230	99.79 212	99.33 45	99.90 72	99.51 132

OPM-MVS		98.56 138	98.32 162	99.25 96	99.41 142	98.73 87	97.13 285	99.18 221	97.10 261	98.75 203	98.92 197	98.18 88	99.65 296	96.68 228	99.56 221	99.37 195
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 198	98.08 191	98.04 262	99.41 142	94.59 309	94.59 398	99.40 138	97.50 218	98.82 194	98.83 217	96.83 185	99.84 151	97.50 166	99.81 104	99.71 53

test_one_0601					99.39 144	99.20 38		99.31 174	98.49 140	98.66 213	99.02 167	97.64 131

mvsany_test3		98.87 86	98.92 75	98.74 181	99.38 145	96.94 227	98.58 111	99.10 238	96.49 291	99.96 4	99.81 6	98.18 88	99.45 362	98.97 71	99.79 120	99.83 28

patch_mono-2		98.51 151	98.63 113	98.17 250	99.38 145	94.78 300	97.36 265	99.69 44	98.16 170	98.49 238	99.29 107	97.06 171	99.97 5	98.29 115	99.91 66	99.76 46

test2506		92.39 382	91.89 384	93.89 397	99.38 145	82.28 428	99.32 23	66.03 435	99.08 93	98.77 200	99.57 46	66.26 423	99.84 151	98.71 91	99.95 34	99.54 118

ECVR-MVS		96.42 306	96.61 292	95.85 368	99.38 145	88.18 406	99.22 42	86.00 429	99.08 93	99.36 99	99.57 46	88.47 348	99.82 178	98.52 104	99.95 34	99.54 118

casdiffmvs		98.95 77	99.00 68	98.81 162	99.38 145	97.33 202	97.82 209	99.57 70	99.17 77	99.35 101	99.17 136	98.35 72	99.69 268	98.46 106	99.73 150	99.41 176
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 76	99.02 66	98.76 175	99.38 145	97.26 207	98.49 126	99.50 94	98.86 114	99.19 130	99.06 155	98.23 81	99.69 268	98.71 91	99.76 143	99.33 213

TranMVSNet+NR-MVSNet		99.17 47	99.07 64	99.46 58	99.37 151	98.87 77	98.39 138	99.42 131	99.42 45	99.36 99	99.06 155	98.38 68	99.95 24	98.34 112	99.90 72	99.57 101

tttt0517		95.64 330	94.98 340	97.64 291	99.36 152	93.81 336	98.72 97	90.47 421	98.08 173	98.67 211	98.34 293	73.88 409	99.92 54	97.77 149	99.51 236	99.20 241

test_part2					99.36 152	99.10 64				99.05 149

v1144		98.60 134	98.66 109	98.41 229	99.36 152	95.90 265	97.58 245	99.34 161	97.51 217	99.27 116	99.15 142	96.34 213	99.80 199	99.47 40	99.93 47	99.51 132

CP-MVS		98.70 112	98.42 146	99.52 42	99.36 152	99.12 61	98.72 97	99.36 150	97.54 215	98.30 251	98.40 285	97.86 113	99.89 82	96.53 246	99.72 158	99.56 107

Test_1112_low_res		96.99 285	96.55 296	98.31 240	99.35 156	95.47 279	95.84 359	99.53 88	91.51 394	96.80 352	98.48 279	91.36 324	99.83 168	96.58 235	99.53 231	99.62 75

DeepC-MVS	97.60 4	98.97 74	98.93 74	99.10 117	99.35 156	97.98 154	98.01 183	99.46 114	97.56 212	99.54 61	99.50 64	98.97 24	99.84 151	98.06 129	99.92 58	99.49 139
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 262	96.86 274	98.58 202	99.34 158	96.32 251	96.75 304	99.58 63	93.14 375	96.89 347	97.48 349	92.11 317	99.86 121	96.91 202	99.54 227	99.57 101

reproduce_model		99.15 51	98.97 72	99.67 4	99.33 159	99.44 10	98.15 160	99.47 111	99.12 80	99.52 67	99.32 103	98.31 75	99.90 69	97.78 148	99.73 150	99.66 65

MVSMamba_PlusPlus		98.83 91	98.98 71	98.36 235	99.32 160	96.58 245	98.90 80	99.41 135	99.75 8	98.72 206	99.50 64	96.17 217	99.94 38	99.27 49	99.78 125	98.57 339

SF-MVS		98.53 146	98.27 168	99.32 83	99.31 161	98.75 83	98.19 154	99.41 135	96.77 280	98.83 191	98.90 201	97.80 119	99.82 178	95.68 292	99.52 234	99.38 193

CPTT-MVS		97.84 221	97.36 245	99.27 91	99.31 161	98.46 107	98.29 145	99.27 196	94.90 343	97.83 290	98.37 289	94.90 261	99.84 151	93.85 343	99.54 227	99.51 132

UnsupCasMVSNet_eth		97.89 210	97.60 231	98.75 177	99.31 161	97.17 215	97.62 239	99.35 155	98.72 121	98.76 202	98.68 244	92.57 312	99.74 247	97.76 153	95.60 413	99.34 208

pmmvs-eth3d		98.47 154	98.34 158	98.86 156	99.30 164	97.76 177	97.16 283	99.28 193	95.54 325	99.42 87	99.19 128	97.27 160	99.63 302	97.89 139	99.97 20	99.20 241

mamv4		99.44 16	99.39 24	99.58 19	99.30 164	99.74 2	99.04 65	99.81 27	99.77 7	99.82 25	99.57 46	97.82 117	99.98 4	99.53 35	99.89 76	99.01 273

Anonymous20231211		99.27 34	99.27 42	99.26 93	99.29 166	98.18 129	99.49 9	99.51 92	99.70 12	99.80 29	99.68 22	96.84 183	99.83 168	99.21 55	99.91 66	99.77 41

UnsupCasMVSNet_bld		97.30 260	96.92 270	98.45 224	99.28 167	96.78 237	96.20 335	99.27 196	95.42 329	98.28 255	98.30 297	93.16 298	99.71 260	94.99 306	97.37 389	98.87 300

EC-MVSNet		99.09 61	99.05 65	99.20 102	99.28 167	98.93 75	99.24 41	99.84 21	99.08 93	98.12 268	98.37 289	98.72 40	99.90 69	99.05 65	99.77 131	98.77 317

reproduce-ours		99.09 61	98.90 77	99.67 4	99.27 169	99.49 6	98.00 184	99.42 131	99.05 96	99.48 74	99.27 110	98.29 77	99.89 82	97.61 158	99.71 163	99.62 75

our_new_method		99.09 61	98.90 77	99.67 4	99.27 169	99.49 6	98.00 184	99.42 131	99.05 96	99.48 74	99.27 110	98.29 77	99.89 82	97.61 158	99.71 163	99.62 75

DPE-MVS		98.59 136	98.26 169	99.57 20	99.27 169	99.15 51	97.01 288	99.39 140	97.67 200	99.44 83	98.99 180	97.53 142	99.89 82	95.40 300	99.68 178	99.66 65
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 220	98.18 178	96.87 337	99.27 169	91.16 386	95.53 368	99.25 202	99.10 88	99.41 89	99.35 93	93.10 300	99.96 12	98.65 95	99.94 42	99.49 139

v1192		98.60 134	98.66 109	98.41 229	99.27 169	95.88 266	97.52 251	99.36 150	97.41 230	99.33 104	99.20 127	96.37 211	99.82 178	99.57 31	99.92 58	99.55 114

N_pmnet		97.63 234	97.17 255	98.99 138	99.27 169	97.86 165	95.98 346	93.41 410	95.25 334	99.47 78	98.90 201	95.63 242	99.85 133	96.91 202	99.73 150	99.27 227

FPMVS		93.44 368	92.23 375	97.08 326	99.25 175	97.86 165	95.61 365	97.16 361	92.90 379	93.76 412	98.65 251	75.94 407	95.66 426	79.30 425	97.49 382	97.73 390

new-patchmatchnet		98.35 167	98.74 93	97.18 321	99.24 176	92.23 369	96.42 322	99.48 103	98.30 151	99.69 42	99.53 60	97.44 151	99.82 178	98.84 80	99.77 131	99.49 139

MCST-MVS		98.00 202	97.63 229	99.10 117	99.24 176	98.17 130	96.89 297	98.73 304	95.66 320	97.92 281	97.70 337	97.17 166	99.66 291	96.18 268	99.23 282	99.47 156

UniMVSNet (Re)		98.87 86	98.71 100	99.35 72	99.24 176	98.73 87	97.73 225	99.38 142	98.93 109	99.12 136	98.73 234	96.77 190	99.86 121	98.63 97	99.80 115	99.46 158

jason		97.45 248	97.35 246	97.76 279	99.24 176	93.93 330	95.86 356	98.42 322	94.24 358	98.50 237	98.13 307	94.82 265	99.91 63	97.22 178	99.73 150	99.43 170
jason: jason.
IterMVS		97.73 226	98.11 187	96.57 347	99.24 176	90.28 395	95.52 370	99.21 211	98.86 114	99.33 104	99.33 99	93.11 299	99.94 38	98.49 105	99.94 42	99.48 149
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 142	98.62 115	98.32 238	99.22 181	95.58 274	97.51 253	99.45 118	97.16 258	99.45 82	99.24 119	96.12 220	99.85 133	99.60 29	99.88 78	99.55 114

ITE_SJBPF				98.87 155	99.22 181	98.48 106		99.35 155	97.50 218	98.28 255	98.60 262	97.64 131	99.35 377	93.86 342	99.27 274	98.79 315

h-mvs33		97.77 224	97.33 248	99.10 117	99.21 183	97.84 167	98.35 142	98.57 314	99.11 81	98.58 226	99.02 167	88.65 346	99.96 12	98.11 124	96.34 405	99.49 139

v144192		98.54 144	98.57 123	98.45 224	99.21 183	95.98 263	97.63 238	99.36 150	97.15 260	99.32 110	99.18 132	95.84 237	99.84 151	99.50 38	99.91 66	99.54 118

APDe-MVS		98.99 70	98.79 89	99.60 14	99.21 183	99.15 51	98.87 84	99.48 103	97.57 210	99.35 101	99.24 119	97.83 114	99.89 82	97.88 142	99.70 170	99.75 50
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 79	98.81 88	99.28 88	99.21 183	98.45 108	98.46 131	99.33 167	99.63 21	99.48 74	99.15 142	97.23 163	99.75 242	97.17 180	99.66 189	99.63 74

SR-MVS-dyc-post		98.81 95	98.55 124	99.57 20	99.20 187	99.38 12	98.48 129	99.30 182	98.64 123	98.95 166	98.96 189	97.49 149	99.86 121	96.56 241	99.39 255	99.45 162

RE-MVS-def			98.58 122		99.20 187	99.38 12	98.48 129	99.30 182	98.64 123	98.95 166	98.96 189	97.75 122		96.56 241	99.39 255	99.45 162

v1921920		98.54 144	98.60 120	98.38 232	99.20 187	95.76 271	97.56 247	99.36 150	97.23 252	99.38 95	99.17 136	96.02 223	99.84 151	99.57 31	99.90 72	99.54 118

thisisatest0530		95.27 337	94.45 348	97.74 282	99.19 190	94.37 313	97.86 205	90.20 422	97.17 257	98.22 258	97.65 339	73.53 410	99.90 69	96.90 207	99.35 261	98.95 285

Anonymous20240529		98.93 79	98.87 80	99.12 113	99.19 190	98.22 127	99.01 67	98.99 260	99.25 64	99.54 61	99.37 88	97.04 172	99.80 199	97.89 139	99.52 234	99.35 206

APD-MVS_3200maxsize		98.84 90	98.61 119	99.53 37	99.19 190	99.27 26	98.49 126	99.33 167	98.64 123	99.03 154	98.98 184	97.89 111	99.85 133	96.54 245	99.42 252	99.46 158

HQP_MVS		97.99 205	97.67 223	98.93 147	99.19 190	97.65 185	97.77 217	99.27 196	98.20 164	97.79 293	97.98 320	94.90 261	99.70 264	94.42 324	99.51 236	99.45 162

plane_prior7					99.19 190	97.87 164

ab-mvs		98.41 159	98.36 155	98.59 201	99.19 190	97.23 208	99.32 23	98.81 291	97.66 201	98.62 218	99.40 87	96.82 186	99.80 199	95.88 279	99.51 236	98.75 320

F-COLMAP		97.30 260	96.68 287	99.14 111	99.19 190	98.39 110	97.27 274	99.30 182	92.93 378	96.62 358	98.00 318	95.73 240	99.68 277	92.62 370	98.46 350	99.35 206

SR-MVS		98.71 108	98.43 144	99.57 20	99.18 197	99.35 16	98.36 141	99.29 190	98.29 154	98.88 183	98.85 214	97.53 142	99.87 113	96.14 270	99.31 267	99.48 149

UniMVSNet_NR-MVSNet		98.86 89	98.68 106	99.40 64	99.17 198	98.74 84	97.68 229	99.40 138	99.14 79	99.06 144	98.59 263	96.71 196	99.93 45	98.57 100	99.77 131	99.53 126

LF4IMVS		97.90 208	97.69 222	98.52 215	99.17 198	97.66 184	97.19 282	99.47 111	96.31 299	97.85 289	98.20 304	96.71 196	99.52 343	94.62 316	99.72 158	98.38 356

SMA-MVS		98.40 161	98.03 195	99.51 46	99.16 200	99.21 32	98.05 175	99.22 210	94.16 360	98.98 158	99.10 151	97.52 144	99.79 212	96.45 251	99.64 192	99.53 126
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 93	98.63 113	99.39 65	99.16 200	98.74 84	97.54 249	99.25 202	98.84 117	99.06 144	98.76 231	96.76 192	99.93 45	98.57 100	99.77 131	99.50 135

NR-MVSNet		98.95 77	98.82 86	99.36 66	99.16 200	98.72 89	99.22 42	99.20 213	99.10 88	99.72 36	98.76 231	96.38 210	99.86 121	98.00 134	99.82 100	99.50 135

MVS_111021_LR		98.30 175	98.12 186	98.83 159	99.16 200	98.03 149	96.09 343	99.30 182	97.58 209	98.10 270	98.24 300	98.25 79	99.34 378	96.69 227	99.65 190	99.12 259

DSMNet-mixed		97.42 251	97.60 231	96.87 337	99.15 204	91.46 376	98.54 116	99.12 235	92.87 380	97.58 306	99.63 36	96.21 216	99.90 69	95.74 288	99.54 227	99.27 227

D2MVS		97.84 221	97.84 213	97.83 271	99.14 205	94.74 302	96.94 292	98.88 275	95.84 317	98.89 180	98.96 189	94.40 277	99.69 268	97.55 161	99.95 34	99.05 265

pmmvs5		97.64 233	97.49 237	98.08 257	99.14 205	95.12 293	96.70 307	99.05 246	93.77 367	98.62 218	98.83 217	93.23 296	99.75 242	98.33 114	99.76 143	99.36 202

SPE-MVS-test		99.13 56	99.09 61	99.26 93	99.13 207	98.97 70	99.31 27	99.88 14	99.44 42	98.16 263	98.51 272	98.64 46	99.93 45	98.91 74	99.85 86	98.88 299

VDD-MVS		98.56 138	98.39 151	99.07 123	99.13 207	98.07 144	98.59 110	97.01 364	99.59 27	99.11 137	99.27 110	94.82 265	99.79 212	98.34 112	99.63 195	99.34 208

save fliter					99.11 209	97.97 155	96.53 314	99.02 254	98.24 157

APD-MVS		98.10 194	97.67 223	99.42 60	99.11 209	98.93 75	97.76 220	99.28 193	94.97 341	98.72 206	98.77 229	97.04 172	99.85 133	93.79 344	99.54 227	99.49 139
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 115	98.71 100	98.62 195	99.10 211	96.37 249	97.23 275	98.87 277	99.20 70	99.19 130	98.99 180	97.30 157	99.85 133	98.77 86	99.79 120	99.65 70

EI-MVSNet		98.40 161	98.51 129	98.04 262	99.10 211	94.73 303	97.20 279	98.87 277	98.97 105	99.06 144	99.02 167	96.00 225	99.80 199	98.58 98	99.82 100	99.60 84

CVMVSNet		96.25 311	97.21 254	93.38 404	99.10 211	80.56 432	97.20 279	98.19 333	96.94 270	99.00 156	99.02 167	89.50 339	99.80 199	96.36 257	99.59 209	99.78 39

EI-MVSNet-Vis-set		98.68 120	98.70 103	98.63 193	99.09 214	96.40 248	97.23 275	98.86 282	99.20 70	99.18 134	98.97 186	97.29 159	99.85 133	98.72 90	99.78 125	99.64 71

HPM-MVS++		98.10 194	97.64 228	99.48 53	99.09 214	99.13 59	97.52 251	98.75 301	97.46 226	96.90 346	97.83 330	96.01 224	99.84 151	95.82 286	99.35 261	99.46 158

DP-MVS Recon		97.33 258	96.92 270	98.57 205	99.09 214	97.99 151	96.79 300	99.35 155	93.18 374	97.71 297	98.07 315	95.00 260	99.31 382	93.97 337	99.13 298	98.42 353

MVS_111021_HR		98.25 183	98.08 191	98.75 177	99.09 214	97.46 195	95.97 347	99.27 196	97.60 208	97.99 279	98.25 299	98.15 94	99.38 373	96.87 210	99.57 218	99.42 173

BP-MVS1		97.40 253	96.97 266	98.71 183	99.07 218	96.81 233	98.34 144	97.18 359	98.58 133	98.17 260	98.61 260	84.01 378	99.94 38	98.97 71	99.78 125	99.37 195

9.14			97.78 215		99.07 218		97.53 250	99.32 169	95.53 326	98.54 233	98.70 240	97.58 136	99.76 235	94.32 329	99.46 246

PAPM_NR		96.82 292	96.32 303	98.30 241	99.07 218	96.69 241	97.48 256	98.76 298	95.81 318	96.61 359	96.47 375	94.12 286	99.17 395	90.82 397	97.78 376	99.06 264

TAMVS		98.24 184	98.05 193	98.80 164	99.07 218	97.18 214	97.88 201	98.81 291	96.66 285	99.17 135	99.21 125	94.81 267	99.77 229	96.96 200	99.88 78	99.44 166

CLD-MVS		97.49 244	97.16 256	98.48 221	99.07 218	97.03 221	94.71 391	99.21 211	94.46 352	98.06 273	97.16 361	97.57 137	99.48 355	94.46 321	99.78 125	98.95 285
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 56	99.10 60	99.24 98	99.06 223	99.15 51	99.36 19	99.88 14	99.36 53	98.21 259	98.46 280	98.68 44	99.93 45	99.03 67	99.85 86	98.64 332

thres100view900		94.19 354	93.67 359	95.75 371	99.06 223	91.35 379	98.03 178	94.24 405	98.33 147	97.40 322	94.98 405	79.84 394	99.62 305	83.05 418	98.08 367	96.29 412

thres600view7		94.45 349	93.83 356	96.29 355	99.06 223	91.53 375	97.99 188	94.24 405	98.34 146	97.44 320	95.01 403	79.84 394	99.67 280	84.33 416	98.23 356	97.66 393

plane_prior1					99.05 226

YYNet1		97.60 235	97.67 223	97.39 314	99.04 227	93.04 353	95.27 377	98.38 325	97.25 246	98.92 176	98.95 193	95.48 249	99.73 252	96.99 196	98.74 331	99.41 176

MDA-MVSNet_test_wron		97.60 235	97.66 226	97.41 313	99.04 227	93.09 349	95.27 377	98.42 322	97.26 245	98.88 183	98.95 193	95.43 250	99.73 252	97.02 193	98.72 333	99.41 176

MIMVSNet		96.62 299	96.25 307	97.71 286	99.04 227	94.66 306	99.16 51	96.92 370	97.23 252	97.87 286	99.10 151	86.11 361	99.65 296	91.65 381	99.21 286	98.82 304

PatchMatch-RL		97.24 266	96.78 281	98.61 198	99.03 230	97.83 168	96.36 325	99.06 243	93.49 372	97.36 326	97.78 331	95.75 239	99.49 352	93.44 353	98.77 330	98.52 341

GDP-MVS		97.50 241	97.11 260	98.67 186	99.02 231	96.85 231	98.16 159	99.71 40	98.32 149	98.52 236	98.54 267	83.39 382	99.95 24	98.79 82	99.56 221	99.19 246

ZD-MVS					99.01 232	98.84 78		99.07 242	94.10 362	98.05 275	98.12 309	96.36 212	99.86 121	92.70 369	99.19 290

CDPH-MVS		97.26 263	96.66 290	99.07 123	99.00 233	98.15 131	96.03 345	99.01 257	91.21 398	97.79 293	97.85 329	96.89 181	99.69 268	92.75 367	99.38 258	99.39 186

diffmvs		98.22 185	98.24 172	98.17 250	99.00 233	95.44 280	96.38 324	99.58 63	97.79 194	98.53 234	98.50 276	96.76 192	99.74 247	97.95 138	99.64 192	99.34 208
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		98.40 161	98.19 177	99.03 133	99.00 233	97.65 185	96.85 298	98.94 262	98.57 134	98.89 180	98.50 276	95.60 243	99.85 133	97.54 163	99.85 86	99.59 90

plane_prior6					98.99 236	97.70 183						94.90 261

xiu_mvs_v1_base_debu		97.86 215	98.17 179	96.92 334	98.98 237	93.91 331	96.45 318	99.17 225	97.85 190	98.41 245	97.14 363	98.47 60	99.92 54	98.02 131	99.05 304	96.92 405

xiu_mvs_v1_base		97.86 215	98.17 179	96.92 334	98.98 237	93.91 331	96.45 318	99.17 225	97.85 190	98.41 245	97.14 363	98.47 60	99.92 54	98.02 131	99.05 304	96.92 405

xiu_mvs_v1_base_debi		97.86 215	98.17 179	96.92 334	98.98 237	93.91 331	96.45 318	99.17 225	97.85 190	98.41 245	97.14 363	98.47 60	99.92 54	98.02 131	99.05 304	96.92 405

MVP-Stereo		98.08 197	97.92 207	98.57 205	98.96 240	96.79 234	97.90 199	99.18 221	96.41 295	98.46 240	98.95 193	95.93 234	99.60 313	96.51 247	98.98 318	99.31 219
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 161	98.68 106	97.54 302	98.96 240	97.99 151	97.88 201	99.36 150	98.20 164	99.63 53	99.04 164	98.76 37	95.33 428	96.56 241	99.74 147	99.31 219
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				98.91 151	98.94 242	97.76 177		98.76 298	87.58 415	96.75 354	98.10 311	94.80 268	99.78 223	92.73 368	99.00 313	99.20 241

USDC		97.41 252	97.40 241	97.44 311	98.94 242	93.67 341	95.17 380	99.53 88	94.03 364	98.97 162	99.10 151	95.29 252	99.34 378	95.84 285	99.73 150	99.30 222

tfpn200view9		94.03 358	93.44 361	95.78 370	98.93 244	91.44 377	97.60 242	94.29 403	97.94 182	97.10 332	94.31 412	79.67 396	99.62 305	83.05 418	98.08 367	96.29 412

testdata				98.09 254	98.93 244	95.40 282		98.80 293	90.08 406	97.45 319	98.37 289	95.26 253	99.70 264	93.58 349	98.95 321	99.17 253

thres400		94.14 356	93.44 361	96.24 358	98.93 244	91.44 377	97.60 242	94.29 403	97.94 182	97.10 332	94.31 412	79.67 396	99.62 305	83.05 418	98.08 367	97.66 393

TAPA-MVS	96.21 11	96.63 298	95.95 309	98.65 187	98.93 244	98.09 138	96.93 294	99.28 193	83.58 421	98.13 267	97.78 331	96.13 219	99.40 369	93.52 350	99.29 272	98.45 346
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 248	96.93 228	95.54 367	98.78 296	85.72 418	96.86 349	98.11 310	94.43 275			99.10 303	99.23 236

PVSNet_BlendedMVS		97.55 240	97.53 234	97.60 294	98.92 248	93.77 338	96.64 309	99.43 128	94.49 350	97.62 302	99.18 132	96.82 186	99.67 280	94.73 313	99.93 47	99.36 202

PVSNet_Blended		96.88 288	96.68 287	97.47 309	98.92 248	93.77 338	94.71 391	99.43 128	90.98 400	97.62 302	97.36 357	96.82 186	99.67 280	94.73 313	99.56 221	98.98 279

MSDG		97.71 228	97.52 235	98.28 243	98.91 251	96.82 232	94.42 401	99.37 146	97.65 202	98.37 250	98.29 298	97.40 153	99.33 380	94.09 335	99.22 283	98.68 330

Anonymous202405211		97.90 208	97.50 236	99.08 121	98.90 252	98.25 121	98.53 117	96.16 381	98.87 113	99.11 137	98.86 211	90.40 333	99.78 223	97.36 171	99.31 267	99.19 246

原ACMM1				98.35 236	98.90 252	96.25 253		98.83 290	92.48 384	96.07 375	98.10 311	95.39 251	99.71 260	92.61 371	98.99 315	99.08 261

GBi-Net		98.65 125	98.47 138	99.17 105	98.90 252	98.24 122	99.20 45	99.44 122	98.59 130	98.95 166	99.55 54	94.14 283	99.86 121	97.77 149	99.69 173	99.41 176

test1		98.65 125	98.47 138	99.17 105	98.90 252	98.24 122	99.20 45	99.44 122	98.59 130	98.95 166	99.55 54	94.14 283	99.86 121	97.77 149	99.69 173	99.41 176

FMVSNet2		98.49 152	98.40 148	98.75 177	98.90 252	97.14 218	98.61 108	99.13 234	98.59 130	99.19 130	99.28 108	94.14 283	99.82 178	97.97 136	99.80 115	99.29 224

OMC-MVS		97.88 212	97.49 237	99.04 132	98.89 257	98.63 91	96.94 292	99.25 202	95.02 339	98.53 234	98.51 272	97.27 160	99.47 358	93.50 352	99.51 236	99.01 273

MVSFormer		98.26 181	98.43 144	97.77 276	98.88 258	93.89 334	99.39 17	99.56 77	99.11 81	98.16 263	98.13 307	93.81 291	99.97 5	99.26 50	99.57 218	99.43 170

lupinMVS		97.06 278	96.86 274	97.65 289	98.88 258	93.89 334	95.48 371	97.97 339	93.53 370	98.16 263	97.58 343	93.81 291	99.91 63	96.77 218	99.57 218	99.17 253

dmvs_re		95.98 319	95.39 329	97.74 282	98.86 260	97.45 196	98.37 140	95.69 393	97.95 180	96.56 360	95.95 384	90.70 330	97.68 422	88.32 406	96.13 409	98.11 368

DELS-MVS		98.27 179	98.20 175	98.48 221	98.86 260	96.70 240	95.60 366	99.20 213	97.73 197	98.45 241	98.71 237	97.50 146	99.82 178	98.21 118	99.59 209	98.93 290
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		97.89 210	97.98 200	97.60 294	98.86 260	94.35 314	96.21 334	99.44 122	97.45 228	99.06 144	98.88 208	97.99 106	99.28 388	94.38 328	99.58 214	99.18 249

LCM-MVSNet-Re		98.64 127	98.48 136	99.11 115	98.85 263	98.51 104	98.49 126	99.83 24	98.37 144	99.69 42	99.46 73	98.21 86	99.92 54	94.13 334	99.30 270	98.91 294

pmmvs4		97.58 238	97.28 249	98.51 216	98.84 264	96.93 228	95.40 375	98.52 317	93.60 369	98.61 220	98.65 251	95.10 257	99.60 313	96.97 199	99.79 120	98.99 278

NP-MVS					98.84 264	97.39 200					96.84 366

sss		97.21 268	96.93 268	98.06 259	98.83 266	95.22 289	96.75 304	98.48 319	94.49 350	97.27 328	97.90 326	92.77 308	99.80 199	96.57 237	99.32 265	99.16 256

PVSNet	93.40 17	95.67 328	95.70 314	95.57 375	98.83 266	88.57 402	92.50 418	97.72 344	92.69 382	96.49 367	96.44 376	93.72 294	99.43 365	93.61 347	99.28 273	98.71 323

MVE	83.40 22	92.50 381	91.92 383	94.25 391	98.83 266	91.64 374	92.71 417	83.52 431	95.92 315	86.46 429	95.46 397	95.20 254	95.40 427	80.51 423	98.64 342	95.73 420
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 362	93.91 354	93.39 403	98.82 269	81.72 430	97.76 220	95.28 395	98.60 129	96.54 361	96.66 370	65.85 426	99.62 305	96.65 230	98.99 315	98.82 304

ambc				98.24 246	98.82 269	95.97 264	98.62 107	99.00 259		99.27 116	99.21 125	96.99 177	99.50 349	96.55 244	99.50 243	99.26 230

旧先验1					98.82 269	97.45 196		98.76 298			98.34 293	95.50 248			99.01 312	99.23 236

test_vis1_rt		97.75 225	97.72 221	97.83 271	98.81 272	96.35 250	97.30 270	99.69 44	94.61 348	97.87 286	98.05 316	96.26 215	98.32 416	98.74 88	98.18 359	98.82 304

WTY-MVS		96.67 296	96.27 306	97.87 269	98.81 272	94.61 308	96.77 302	97.92 341	94.94 342	97.12 331	97.74 334	91.11 326	99.82 178	93.89 340	98.15 363	99.18 249

3Dnovator+	97.89 3	98.69 115	98.51 129	99.24 98	98.81 272	98.40 109	99.02 66	99.19 217	98.99 102	98.07 272	99.28 108	97.11 170	99.84 151	96.84 213	99.32 265	99.47 156

QAPM		97.31 259	96.81 280	98.82 160	98.80 275	97.49 193	99.06 62	99.19 217	90.22 404	97.69 299	99.16 138	96.91 180	99.90 69	90.89 396	99.41 253	99.07 263

VNet		98.42 158	98.30 163	98.79 167	98.79 276	97.29 204	98.23 150	98.66 308	99.31 58	98.85 188	98.80 223	94.80 268	99.78 223	98.13 123	99.13 298	99.31 219

DPM-MVS		96.32 308	95.59 320	98.51 216	98.76 277	97.21 211	94.54 400	98.26 328	91.94 389	96.37 368	97.25 359	93.06 302	99.43 365	91.42 386	98.74 331	98.89 296

3Dnovator	98.27 2	98.81 95	98.73 95	99.05 130	98.76 277	97.81 174	99.25 40	99.30 182	98.57 134	98.55 231	99.33 99	97.95 108	99.90 69	97.16 181	99.67 184	99.44 166

PLC	94.65 16	96.51 301	95.73 313	98.85 157	98.75 279	97.91 161	96.42 322	99.06 243	90.94 401	95.59 381	97.38 355	94.41 276	99.59 317	90.93 394	98.04 372	99.05 265
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 290	96.75 283	97.08 326	98.74 280	93.33 347	96.71 306	98.26 328	96.72 282	98.44 242	97.37 356	95.20 254	99.47 358	91.89 376	97.43 386	98.44 349

hse-mvs2		97.46 246	97.07 261	98.64 189	98.73 281	97.33 202	97.45 259	97.64 350	99.11 81	98.58 226	97.98 320	88.65 346	99.79 212	98.11 124	97.39 388	98.81 309

CDS-MVSNet		97.69 229	97.35 246	98.69 184	98.73 281	97.02 222	96.92 296	98.75 301	95.89 316	98.59 224	98.67 246	92.08 318	99.74 247	96.72 224	99.81 104	99.32 215
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 202	97.74 218	98.80 164	98.72 283	98.09 138	98.05 175	99.60 60	97.39 232	96.63 357	95.55 392	97.68 125	99.80 199	96.73 223	99.27 274	98.52 341

LFMVS		97.20 269	96.72 284	98.64 189	98.72 283	96.95 226	98.93 78	94.14 407	99.74 10	98.78 197	99.01 176	84.45 373	99.73 252	97.44 167	99.27 274	99.25 231

new_pmnet		96.99 285	96.76 282	97.67 287	98.72 283	94.89 298	95.95 351	98.20 331	92.62 383	98.55 231	98.54 267	94.88 264	99.52 343	93.96 338	99.44 251	98.59 338

Fast-Effi-MVS+		97.67 231	97.38 243	98.57 205	98.71 286	97.43 198	97.23 275	99.45 118	94.82 345	96.13 372	96.51 372	98.52 58	99.91 63	96.19 266	98.83 327	98.37 358

TEST9					98.71 286	98.08 142	95.96 349	99.03 251	91.40 395	95.85 378	97.53 345	96.52 203	99.76 235

train_agg		97.10 275	96.45 300	99.07 123	98.71 286	98.08 142	95.96 349	99.03 251	91.64 390	95.85 378	97.53 345	96.47 205	99.76 235	93.67 346	99.16 293	99.36 202

TSAR-MVS + GP.		98.18 190	97.98 200	98.77 174	98.71 286	97.88 163	96.32 328	98.66 308	96.33 297	99.23 127	98.51 272	97.48 150	99.40 369	97.16 181	99.46 246	99.02 272

FA-MVS(test-final)		96.99 285	96.82 278	97.50 306	98.70 290	94.78 300	99.34 20	96.99 365	95.07 338	98.48 239	99.33 99	88.41 349	99.65 296	96.13 272	98.92 324	98.07 371

AUN-MVS		96.24 313	95.45 325	98.60 200	98.70 290	97.22 210	97.38 262	97.65 348	95.95 314	95.53 388	97.96 324	82.11 390	99.79 212	96.31 259	97.44 385	98.80 314

our_test_3		97.39 254	97.73 220	96.34 353	98.70 290	89.78 398	94.61 397	98.97 261	96.50 290	99.04 151	98.85 214	95.98 230	99.84 151	97.26 176	99.67 184	99.41 176

ppachtmachnet_test		97.50 241	97.74 218	96.78 343	98.70 290	91.23 385	94.55 399	99.05 246	96.36 296	99.21 128	98.79 225	96.39 208	99.78 223	96.74 221	99.82 100	99.34 208

PCF-MVS	92.86 18	94.36 350	93.00 368	98.42 228	98.70 290	97.56 190	93.16 416	99.11 237	79.59 425	97.55 309	97.43 352	92.19 315	99.73 252	79.85 424	99.45 248	97.97 377
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 207	98.02 196	97.58 296	98.69 295	94.10 321	98.13 162	98.90 271	97.95 180	97.32 327	99.58 44	95.95 233	98.75 411	96.41 253	99.22 283	99.87 20

ETV-MVS		98.03 199	97.86 212	98.56 209	98.69 295	98.07 144	97.51 253	99.50 94	98.10 172	97.50 314	95.51 393	98.41 66	99.88 96	96.27 262	99.24 279	97.71 392

test_prior				98.95 144	98.69 295	97.95 159		99.03 251					99.59 317			99.30 222

mvsmamba		97.57 239	97.26 250	98.51 216	98.69 295	96.73 239	98.74 92	97.25 358	97.03 266	97.88 285	99.23 123	90.95 327	99.87 113	96.61 233	99.00 313	98.91 294

agg_prior					98.68 299	97.99 151		99.01 257		95.59 381			99.77 229

test_8					98.67 300	98.01 150	95.91 355	99.02 254	91.64 390	95.79 380	97.50 348	96.47 205	99.76 235

HQP-NCC					98.67 300		96.29 330		96.05 307	95.55 384

ACMP_Plane					98.67 300		96.29 330		96.05 307	95.55 384

CNVR-MVS		98.17 192	97.87 211	99.07 123	98.67 300	98.24 122	97.01 288	98.93 265	97.25 246	97.62 302	98.34 293	97.27 160	99.57 325	96.42 252	99.33 264	99.39 186

HQP-MVS		97.00 284	96.49 299	98.55 210	98.67 300	96.79 234	96.29 330	99.04 249	96.05 307	95.55 384	96.84 366	93.84 289	99.54 337	92.82 364	99.26 277	99.32 215

MM		98.22 185	97.99 199	98.91 151	98.66 305	96.97 223	97.89 200	94.44 401	99.54 30	98.95 166	99.14 145	93.50 295	99.92 54	99.80 14	99.96 27	99.85 26

test_fmvs1		97.72 227	97.94 205	97.07 328	98.66 305	92.39 364	97.68 229	99.81 27	95.20 337	99.54 61	99.44 78	91.56 323	99.41 368	99.78 17	99.77 131	99.40 185

balanced_conf03		98.63 129	98.72 97	98.38 232	98.66 305	96.68 242	98.90 80	99.42 131	98.99 102	98.97 162	99.19 128	95.81 238	99.85 133	98.77 86	99.77 131	98.60 335

thres200		93.72 364	93.14 366	95.46 379	98.66 305	91.29 381	96.61 311	94.63 400	97.39 232	96.83 350	93.71 415	79.88 393	99.56 328	82.40 421	98.13 364	95.54 421

wuyk23d		96.06 315	97.62 230	91.38 408	98.65 309	98.57 98	98.85 87	96.95 368	96.86 275	99.90 13	99.16 138	99.18 18	98.40 415	89.23 404	99.77 131	77.18 428

NCCC		97.86 215	97.47 240	99.05 130	98.61 310	98.07 144	96.98 290	98.90 271	97.63 203	97.04 336	97.93 325	95.99 229	99.66 291	95.31 301	98.82 329	99.43 170

DeepC-MVS_fast	96.85 6	98.30 175	98.15 183	98.75 177	98.61 310	97.23 208	97.76 220	99.09 240	97.31 240	98.75 203	98.66 249	97.56 138	99.64 299	96.10 273	99.55 225	99.39 186
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 366	92.09 377	97.75 280	98.60 312	94.40 312	97.32 268	95.26 396	97.56 212	96.79 353	95.50 394	53.57 434	99.77 229	95.26 302	98.97 319	99.08 261

thisisatest0515		94.12 357	93.16 365	96.97 332	98.60 312	92.90 354	93.77 412	90.61 420	94.10 362	96.91 343	95.87 387	74.99 408	99.80 199	94.52 319	99.12 301	98.20 364

GA-MVS		95.86 322	95.32 332	97.49 307	98.60 312	94.15 320	93.83 411	97.93 340	95.49 327	96.68 355	97.42 353	83.21 383	99.30 384	96.22 264	98.55 348	99.01 273

dmvs_testset		92.94 376	92.21 376	95.13 383	98.59 315	90.99 388	97.65 235	92.09 416	96.95 269	94.00 408	93.55 416	92.34 314	96.97 425	72.20 427	92.52 423	97.43 400

OPU-MVS				98.82 160	98.59 315	98.30 118	98.10 168				98.52 271	98.18 88	98.75 411	94.62 316	99.48 245	99.41 176

MSLP-MVS++		98.02 200	98.14 185	97.64 291	98.58 317	95.19 290	97.48 256	99.23 209	97.47 221	97.90 283	98.62 258	97.04 172	98.81 409	97.55 161	99.41 253	98.94 289

test12				98.93 147	98.58 317	97.83 168		98.66 308		96.53 362		95.51 247	99.69 268		99.13 298	99.27 227

CL-MVSNet_self_test		97.44 249	97.22 253	98.08 257	98.57 319	95.78 270	94.30 404	98.79 294	96.58 288	98.60 222	98.19 305	94.74 271	99.64 299	96.41 253	98.84 326	98.82 304

PS-MVSNAJ		97.08 277	97.39 242	96.16 364	98.56 320	92.46 362	95.24 379	98.85 285	97.25 246	97.49 315	95.99 383	98.07 97	99.90 69	96.37 255	98.67 341	96.12 417

CNLPA		97.17 272	96.71 285	98.55 210	98.56 320	98.05 148	96.33 327	98.93 265	96.91 272	97.06 335	97.39 354	94.38 278	99.45 362	91.66 380	99.18 292	98.14 367

xiu_mvs_v2_base		97.16 273	97.49 237	96.17 362	98.54 322	92.46 362	95.45 372	98.84 286	97.25 246	97.48 316	96.49 373	98.31 75	99.90 69	96.34 258	98.68 340	96.15 416

alignmvs		97.35 256	96.88 273	98.78 170	98.54 322	98.09 138	97.71 226	97.69 346	99.20 70	97.59 305	95.90 386	88.12 351	99.55 332	98.18 120	98.96 320	98.70 326

FE-MVS		95.66 329	94.95 342	97.77 276	98.53 324	95.28 286	99.40 16	96.09 384	93.11 376	97.96 280	99.26 114	79.10 400	99.77 229	92.40 373	98.71 335	98.27 362

Effi-MVS+		98.02 200	97.82 214	98.62 195	98.53 324	97.19 213	97.33 267	99.68 49	97.30 241	96.68 355	97.46 351	98.56 56	99.80 199	96.63 231	98.20 358	98.86 301

baseline1		95.96 320	95.44 326	97.52 304	98.51 326	93.99 328	98.39 138	96.09 384	98.21 160	98.40 249	97.76 333	86.88 353	99.63 302	95.42 299	89.27 426	98.95 285

MVS_Test		98.18 190	98.36 155	97.67 287	98.48 327	94.73 303	98.18 155	99.02 254	97.69 199	98.04 276	99.11 148	97.22 164	99.56 328	98.57 100	98.90 325	98.71 323

MGCFI-Net		98.34 168	98.28 165	98.51 216	98.47 328	97.59 189	98.96 74	99.48 103	99.18 76	97.40 322	95.50 394	98.66 45	99.50 349	98.18 120	98.71 335	98.44 349

BH-RMVSNet		96.83 290	96.58 295	97.58 296	98.47 328	94.05 322	96.67 308	97.36 353	96.70 284	97.87 286	97.98 320	95.14 256	99.44 364	90.47 399	98.58 347	99.25 231

sasdasda		98.34 168	98.26 169	98.58 202	98.46 330	97.82 171	98.96 74	99.46 114	99.19 74	97.46 317	95.46 397	98.59 52	99.46 360	98.08 127	98.71 335	98.46 343

canonicalmvs		98.34 168	98.26 169	98.58 202	98.46 330	97.82 171	98.96 74	99.46 114	99.19 74	97.46 317	95.46 397	98.59 52	99.46 360	98.08 127	98.71 335	98.46 343

MVS-HIRNet		94.32 351	95.62 317	90.42 409	98.46 330	75.36 433	96.29 330	89.13 424	95.25 334	95.38 390	99.75 13	92.88 305	99.19 394	94.07 336	99.39 255	96.72 410

PHI-MVS		98.29 178	97.95 203	99.34 75	98.44 333	99.16 47	98.12 165	99.38 142	96.01 311	98.06 273	98.43 283	97.80 119	99.67 280	95.69 291	99.58 214	99.20 241

DVP-MVS++		98.90 83	98.70 103	99.51 46	98.43 334	99.15 51	99.43 12	99.32 169	98.17 167	99.26 120	99.02 167	98.18 88	99.88 96	97.07 190	99.45 248	99.49 139

MSC_two_6792asdad				99.32 83	98.43 334	98.37 113		98.86 282					99.89 82	97.14 184	99.60 205	99.71 53

No_MVS				99.32 83	98.43 334	98.37 113		98.86 282					99.89 82	97.14 184	99.60 205	99.71 53

Fast-Effi-MVS+-dtu		98.27 179	98.09 188	98.81 162	98.43 334	98.11 135	97.61 241	99.50 94	98.64 123	97.39 324	97.52 347	98.12 96	99.95 24	96.90 207	98.71 335	98.38 356

OpenMVS_ROB	95.38 14	95.84 324	95.18 337	97.81 273	98.41 338	97.15 217	97.37 264	98.62 312	83.86 420	98.65 214	98.37 289	94.29 281	99.68 277	88.41 405	98.62 345	96.60 411

DeepPCF-MVS	96.93 5	98.32 172	98.01 197	99.23 100	98.39 339	98.97 70	95.03 384	99.18 221	96.88 273	99.33 104	98.78 227	98.16 92	99.28 388	96.74 221	99.62 198	99.44 166

Patchmatch-test		96.55 300	96.34 302	97.17 323	98.35 340	93.06 350	98.40 137	97.79 342	97.33 237	98.41 245	98.67 246	83.68 381	99.69 268	95.16 304	99.31 267	98.77 317

AdaColmap		97.14 274	96.71 285	98.46 223	98.34 341	97.80 175	96.95 291	98.93 265	95.58 324	96.92 341	97.66 338	95.87 236	99.53 339	90.97 393	99.14 296	98.04 372

OpenMVS	96.65 7	97.09 276	96.68 287	98.32 238	98.32 342	97.16 216	98.86 86	99.37 146	89.48 408	96.29 370	99.15 142	96.56 201	99.90 69	92.90 361	99.20 287	97.89 380

MG-MVS		96.77 293	96.61 292	97.26 319	98.31 343	93.06 350	95.93 352	98.12 336	96.45 294	97.92 281	98.73 234	93.77 293	99.39 371	91.19 391	99.04 307	99.33 213

test_yl		96.69 294	96.29 304	97.90 266	98.28 344	95.24 287	97.29 271	97.36 353	98.21 160	98.17 260	97.86 327	86.27 357	99.55 332	94.87 310	98.32 352	98.89 296

DCV-MVSNet		96.69 294	96.29 304	97.90 266	98.28 344	95.24 287	97.29 271	97.36 353	98.21 160	98.17 260	97.86 327	86.27 357	99.55 332	94.87 310	98.32 352	98.89 296

CHOSEN 280x420		95.51 334	95.47 323	95.65 374	98.25 346	88.27 405	93.25 415	98.88 275	93.53 370	94.65 399	97.15 362	86.17 359	99.93 45	97.41 169	99.93 47	98.73 322

SCA		96.41 307	96.66 290	95.67 372	98.24 347	88.35 404	95.85 358	96.88 371	96.11 305	97.67 300	98.67 246	93.10 300	99.85 133	94.16 330	99.22 283	98.81 309

DeepMVS_CX				93.44 402	98.24 347	94.21 317		94.34 402	64.28 428	91.34 422	94.87 409	89.45 340	92.77 429	77.54 426	93.14 422	93.35 424

MS-PatchMatch		97.68 230	97.75 217	97.45 310	98.23 349	93.78 337	97.29 271	98.84 286	96.10 306	98.64 215	98.65 251	96.04 222	99.36 374	96.84 213	99.14 296	99.20 241

BH-w/o		95.13 340	94.89 344	95.86 367	98.20 350	91.31 380	95.65 364	97.37 352	93.64 368	96.52 363	95.70 390	93.04 303	99.02 400	88.10 407	95.82 412	97.24 403

mvs_anonymous		97.83 223	98.16 182	96.87 337	98.18 351	91.89 371	97.31 269	98.90 271	97.37 234	98.83 191	99.46 73	96.28 214	99.79 212	98.90 75	98.16 362	98.95 285

miper_lstm_enhance		97.18 271	97.16 256	97.25 320	98.16 352	92.85 355	95.15 382	99.31 174	97.25 246	98.74 205	98.78 227	90.07 334	99.78 223	97.19 179	99.80 115	99.11 260

RRT-MVS		97.88 212	97.98 200	97.61 293	98.15 353	93.77 338	98.97 73	99.64 54	99.16 78	98.69 208	99.42 80	91.60 321	99.89 82	97.63 157	98.52 349	99.16 256

ET-MVSNet_ETH3D		94.30 353	93.21 364	97.58 296	98.14 354	94.47 311	94.78 390	93.24 412	94.72 346	89.56 424	95.87 387	78.57 403	99.81 192	96.91 202	97.11 397	98.46 343

ADS-MVSNet2		95.43 335	94.98 340	96.76 344	98.14 354	91.74 372	97.92 196	97.76 343	90.23 402	96.51 364	98.91 198	85.61 364	99.85 133	92.88 362	96.90 398	98.69 327

ADS-MVSNet		95.24 338	94.93 343	96.18 361	98.14 354	90.10 397	97.92 196	97.32 356	90.23 402	96.51 364	98.91 198	85.61 364	99.74 247	92.88 362	96.90 398	98.69 327

c3_l		97.36 255	97.37 244	97.31 315	98.09 357	93.25 348	95.01 385	99.16 228	97.05 263	98.77 200	98.72 236	92.88 305	99.64 299	96.93 201	99.76 143	99.05 265

FMVSNet3		97.50 241	97.24 252	98.29 242	98.08 358	95.83 268	97.86 205	98.91 270	97.89 187	98.95 166	98.95 193	87.06 352	99.81 192	97.77 149	99.69 173	99.23 236

PAPM		91.88 390	90.34 393	96.51 348	98.06 359	92.56 360	92.44 419	97.17 360	86.35 416	90.38 423	96.01 382	86.61 355	99.21 393	70.65 429	95.43 414	97.75 389

Effi-MVS+-dtu		98.26 181	97.90 209	99.35 72	98.02 360	99.49 6	98.02 180	99.16 228	98.29 154	97.64 301	97.99 319	96.44 207	99.95 24	96.66 229	98.93 323	98.60 335

eth_miper_zixun_eth		97.23 267	97.25 251	97.17 323	98.00 361	92.77 357	94.71 391	99.18 221	97.27 244	98.56 229	98.74 233	91.89 319	99.69 268	97.06 192	99.81 104	99.05 265

HY-MVS	95.94 13	95.90 321	95.35 331	97.55 301	97.95 362	94.79 299	98.81 91	96.94 369	92.28 387	95.17 392	98.57 265	89.90 336	99.75 242	91.20 390	97.33 393	98.10 369

UGNet		98.53 146	98.45 141	98.79 167	97.94 363	96.96 225	99.08 58	98.54 315	99.10 88	96.82 351	99.47 72	96.55 202	99.84 151	98.56 103	99.94 42	99.55 114
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		96.47 305	95.70 314	98.79 167	97.92 364	99.12 61	98.28 146	98.60 313	92.16 388	95.54 387	96.17 380	94.77 270	99.52 343	89.62 402	98.23 356	97.72 391
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		96.86 289	96.55 296	97.79 274	97.91 365	94.21 317	97.56 247	98.87 277	97.49 220	99.06 144	99.05 162	80.72 391	99.80 199	98.44 107	99.82 100	99.37 195

API-MVS		97.04 280	96.91 272	97.42 312	97.88 366	98.23 126	98.18 155	98.50 318	97.57 210	97.39 324	96.75 368	96.77 190	99.15 397	90.16 400	99.02 311	94.88 422

myMVS_eth3d28		92.92 377	92.31 373	94.77 386	97.84 367	87.59 409	96.19 336	96.11 383	97.08 262	94.27 402	93.49 418	66.07 425	98.78 410	91.78 378	97.93 375	97.92 379

miper_ehance_all_eth		97.06 278	97.03 263	97.16 325	97.83 368	93.06 350	94.66 394	99.09 240	95.99 312	98.69 208	98.45 281	92.73 310	99.61 312	96.79 215	99.03 308	98.82 304

cl____		97.02 281	96.83 277	97.58 296	97.82 369	94.04 324	94.66 394	99.16 228	97.04 264	98.63 216	98.71 237	88.68 345	99.69 268	97.00 194	99.81 104	99.00 277

DIV-MVS_self_test		97.02 281	96.84 276	97.58 296	97.82 369	94.03 325	94.66 394	99.16 228	97.04 264	98.63 216	98.71 237	88.69 343	99.69 268	97.00 194	99.81 104	99.01 273

CANet		97.87 214	97.76 216	98.19 249	97.75 371	95.51 277	96.76 303	99.05 246	97.74 196	96.93 340	98.21 303	95.59 244	99.89 82	97.86 144	99.93 47	99.19 246

UBG		93.25 371	92.32 372	96.04 366	97.72 372	90.16 396	95.92 354	95.91 388	96.03 310	93.95 410	93.04 421	69.60 415	99.52 343	90.72 398	97.98 373	98.45 346

mvsany_test1		97.60 235	97.54 233	97.77 276	97.72 372	95.35 283	95.36 376	97.13 362	94.13 361	99.71 38	99.33 99	97.93 109	99.30 384	97.60 160	98.94 322	98.67 331

PVSNet_0	89.98 21	91.15 391	90.30 394	93.70 399	97.72 372	84.34 423	90.24 422	97.42 351	90.20 405	93.79 411	93.09 420	90.90 329	98.89 408	86.57 413	72.76 429	97.87 382

CR-MVSNet		96.28 310	95.95 309	97.28 317	97.71 375	94.22 315	98.11 166	98.92 268	92.31 386	96.91 343	99.37 88	85.44 367	99.81 192	97.39 170	97.36 391	97.81 385

RPMNet		97.02 281	96.93 268	97.30 316	97.71 375	94.22 315	98.11 166	99.30 182	99.37 50	96.91 343	99.34 97	86.72 354	99.87 113	97.53 164	97.36 391	97.81 385

ETVMVS		92.60 380	91.08 389	97.18 321	97.70 377	93.65 343	96.54 312	95.70 391	96.51 289	94.68 398	92.39 424	61.80 431	99.50 349	86.97 410	97.41 387	98.40 354

pmmvs3		95.03 342	94.40 349	96.93 333	97.70 377	92.53 361	95.08 383	97.71 345	88.57 412	97.71 297	98.08 314	79.39 398	99.82 178	96.19 266	99.11 302	98.43 351

baseline2		93.73 363	92.83 369	96.42 351	97.70 377	91.28 382	96.84 299	89.77 423	93.96 366	92.44 418	95.93 385	79.14 399	99.77 229	92.94 360	96.76 402	98.21 363

WBMVS		95.18 339	94.78 345	96.37 352	97.68 380	89.74 399	95.80 360	98.73 304	97.54 215	98.30 251	98.44 282	70.06 413	99.82 178	96.62 232	99.87 81	99.54 118

tpm		94.67 347	94.34 351	95.66 373	97.68 380	88.42 403	97.88 201	94.90 397	94.46 352	96.03 377	98.56 266	78.66 401	99.79 212	95.88 279	95.01 416	98.78 316

CANet_DTU		97.26 263	97.06 262	97.84 270	97.57 382	94.65 307	96.19 336	98.79 294	97.23 252	95.14 393	98.24 300	93.22 297	99.84 151	97.34 172	99.84 90	99.04 269

testing11		93.08 374	92.02 379	96.26 357	97.56 383	90.83 391	96.32 328	95.70 391	96.47 293	92.66 417	93.73 414	64.36 429	99.59 317	93.77 345	97.57 380	98.37 358

tpm2		93.09 373	92.58 371	94.62 388	97.56 383	86.53 412	97.66 233	95.79 390	86.15 417	94.07 407	98.23 302	75.95 406	99.53 339	90.91 395	96.86 401	97.81 385

testing91		93.32 369	92.27 374	96.47 350	97.54 385	91.25 383	96.17 340	96.76 373	97.18 256	93.65 413	93.50 417	65.11 428	99.63 302	93.04 359	97.45 384	98.53 340

TR-MVS		95.55 332	95.12 338	96.86 340	97.54 385	93.94 329	96.49 317	96.53 378	94.36 357	97.03 338	96.61 371	94.26 282	99.16 396	86.91 412	96.31 406	97.47 399

testing99		93.04 375	91.98 382	96.23 359	97.53 387	90.70 393	96.35 326	95.94 387	96.87 274	93.41 414	93.43 419	63.84 430	99.59 317	93.24 357	97.19 394	98.40 354

1314		95.74 326	95.60 318	96.17 362	97.53 387	92.75 358	98.07 172	98.31 327	91.22 397	94.25 403	96.68 369	95.53 245	99.03 399	91.64 382	97.18 395	96.74 409

CostFormer		93.97 359	93.78 357	94.51 389	97.53 387	85.83 415	97.98 189	95.96 386	89.29 410	94.99 395	98.63 256	78.63 402	99.62 305	94.54 318	96.50 403	98.09 370

FMVSNet5		96.01 317	95.20 336	98.41 229	97.53 387	96.10 255	98.74 92	99.50 94	97.22 255	98.03 277	99.04 164	69.80 414	99.88 96	97.27 175	99.71 163	99.25 231

PMMVS		96.51 301	95.98 308	98.09 254	97.53 387	95.84 267	94.92 387	98.84 286	91.58 392	96.05 376	95.58 391	95.68 241	99.66 291	95.59 295	98.09 366	98.76 319

reproduce_monomvs		95.00 344	95.25 333	94.22 392	97.51 392	83.34 424	97.86 205	98.44 320	98.51 139	99.29 113	99.30 105	67.68 419	99.56 328	98.89 77	99.81 104	99.77 41

PAPR		95.29 336	94.47 347	97.75 280	97.50 393	95.14 292	94.89 388	98.71 306	91.39 396	95.35 391	95.48 396	94.57 273	99.14 398	84.95 415	97.37 389	98.97 282

testing222		91.96 388	90.37 392	96.72 345	97.47 394	92.59 359	96.11 342	94.76 398	96.83 276	92.90 416	92.87 422	57.92 432	99.55 332	86.93 411	97.52 381	98.00 376

PatchT		96.65 297	96.35 301	97.54 302	97.40 395	95.32 285	97.98 189	96.64 375	99.33 55	96.89 347	99.42 80	84.32 375	99.81 192	97.69 156	97.49 382	97.48 398

tpm cat1		93.29 370	93.13 367	93.75 398	97.39 396	84.74 418	97.39 261	97.65 348	83.39 422	94.16 404	98.41 284	82.86 386	99.39 371	91.56 384	95.35 415	97.14 404

PatchmatchNet		95.58 331	95.67 316	95.30 382	97.34 397	87.32 410	97.65 235	96.65 374	95.30 333	97.07 334	98.69 242	84.77 370	99.75 242	94.97 308	98.64 342	98.83 303
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 256	96.97 266	98.50 220	97.31 398	96.47 247	98.18 155	98.92 268	98.95 108	98.78 197	99.37 88	85.44 367	99.85 133	95.96 277	99.83 97	99.17 253

LS3D		98.63 129	98.38 153	99.36 66	97.25 399	99.38 12	99.12 57	99.32 169	99.21 68	98.44 242	98.88 208	97.31 156	99.80 199	96.58 235	99.34 263	98.92 291

IB-MVS	91.63 19	92.24 386	90.90 390	96.27 356	97.22 400	91.24 384	94.36 403	93.33 411	92.37 385	92.24 420	94.58 411	66.20 424	99.89 82	93.16 358	94.63 418	97.66 393
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		92.38 383	91.76 386	94.21 393	97.16 401	84.65 419	95.42 374	88.45 425	95.96 313	96.17 371	95.84 389	66.36 422	99.71 260	91.87 377	98.64 342	98.28 361

tpmrst		95.07 341	95.46 324	93.91 396	97.11 402	84.36 422	97.62 239	96.96 367	94.98 340	96.35 369	98.80 223	85.46 366	99.59 317	95.60 294	96.23 407	97.79 388

Syy-MVS		96.04 316	95.56 322	97.49 307	97.10 403	94.48 310	96.18 338	96.58 376	95.65 321	94.77 396	92.29 425	91.27 325	99.36 374	98.17 122	98.05 370	98.63 333

myMVS_eth3d		91.92 389	90.45 391	96.30 354	97.10 403	90.90 389	96.18 338	96.58 376	95.65 321	94.77 396	92.29 425	53.88 433	99.36 374	89.59 403	98.05 370	98.63 333

MDTV_nov1_ep13			95.22 335		97.06 405	83.20 425	97.74 223	96.16 381	94.37 356	96.99 339	98.83 217	83.95 379	99.53 339	93.90 339	97.95 374

MVS		93.19 372	92.09 377	96.50 349	96.91 406	94.03 325	98.07 172	98.06 338	68.01 427	94.56 401	96.48 374	95.96 232	99.30 384	83.84 417	96.89 400	96.17 414

E-PMN		94.17 355	94.37 350	93.58 400	96.86 407	85.71 416	90.11 424	97.07 363	98.17 167	97.82 292	97.19 360	84.62 372	98.94 404	89.77 401	97.68 379	96.09 418

JIA-IIPM		95.52 333	95.03 339	97.00 329	96.85 408	94.03 325	96.93 294	95.82 389	99.20 70	94.63 400	99.71 19	83.09 384	99.60 313	94.42 324	94.64 417	97.36 402

EMVS		93.83 361	94.02 353	93.23 405	96.83 409	84.96 417	89.77 425	96.32 380	97.92 184	97.43 321	96.36 379	86.17 359	98.93 405	87.68 408	97.73 378	95.81 419

cl22		95.79 325	95.39 329	96.98 331	96.77 410	92.79 356	94.40 402	98.53 316	94.59 349	97.89 284	98.17 306	82.82 387	99.24 390	96.37 255	99.03 308	98.92 291

WB-MVSnew		95.73 327	95.57 321	96.23 359	96.70 411	90.70 393	96.07 344	93.86 408	95.60 323	97.04 336	95.45 400	96.00 225	99.55 332	91.04 392	98.31 354	98.43 351

dp		93.47 367	93.59 360	93.13 406	96.64 412	81.62 431	97.66 233	96.42 379	92.80 381	96.11 373	98.64 254	78.55 404	99.59 317	93.31 355	92.18 425	98.16 366

MonoMVSNet		96.25 311	96.53 298	95.39 380	96.57 413	91.01 387	98.82 90	97.68 347	98.57 134	98.03 277	99.37 88	90.92 328	97.78 421	94.99 306	93.88 421	97.38 401

test-LLR		93.90 360	93.85 355	94.04 394	96.53 414	84.62 420	94.05 408	92.39 414	96.17 302	94.12 405	95.07 401	82.30 388	99.67 280	95.87 282	98.18 359	97.82 383

test-mter		92.33 385	91.76 386	94.04 394	96.53 414	84.62 420	94.05 408	92.39 414	94.00 365	94.12 405	95.07 401	65.63 427	99.67 280	95.87 282	98.18 359	97.82 383

TESTMET0.1,1		92.19 387	91.77 385	93.46 401	96.48 416	82.80 427	94.05 408	91.52 419	94.45 354	94.00 408	94.88 407	66.65 421	99.56 328	95.78 287	98.11 365	98.02 373

MVS_0304		97.44 249	97.01 265	98.72 182	96.42 417	96.74 238	97.20 279	91.97 417	98.46 142	98.30 251	98.79 225	92.74 309	99.91 63	99.30 47	99.94 42	99.52 129

miper_enhance_ethall		96.01 317	95.74 312	96.81 341	96.41 418	92.27 368	93.69 413	98.89 274	91.14 399	98.30 251	97.35 358	90.58 331	99.58 323	96.31 259	99.03 308	98.60 335

tpmvs		95.02 343	95.25 333	94.33 390	96.39 419	85.87 413	98.08 170	96.83 372	95.46 328	95.51 389	98.69 242	85.91 362	99.53 339	94.16 330	96.23 407	97.58 396

CMPMVS	75.91 23	96.29 309	95.44 326	98.84 158	96.25 420	98.69 90	97.02 287	99.12 235	88.90 411	97.83 290	98.86 211	89.51 338	98.90 407	91.92 375	99.51 236	98.92 291
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 348	93.69 358	96.99 330	96.05 421	93.61 345	94.97 386	93.49 409	96.17 302	97.57 308	94.88 407	82.30 388	99.01 402	93.60 348	94.17 420	98.37 358

EPMVS		93.72 364	93.27 363	95.09 385	96.04 422	87.76 407	98.13 162	85.01 430	94.69 347	96.92 341	98.64 254	78.47 405	99.31 382	95.04 305	96.46 404	98.20 364

cascas		94.79 346	94.33 352	96.15 365	96.02 423	92.36 366	92.34 420	99.26 201	85.34 419	95.08 394	94.96 406	92.96 304	98.53 414	94.41 327	98.59 346	97.56 397

MVStest1		95.86 322	95.60 318	96.63 346	95.87 424	91.70 373	97.93 193	98.94 262	98.03 174	99.56 57	99.66 29	71.83 411	98.26 417	99.35 44	99.24 279	99.91 13

gg-mvs-nofinetune		92.37 384	91.20 388	95.85 368	95.80 425	92.38 365	99.31 27	81.84 432	99.75 8	91.83 421	99.74 15	68.29 416	99.02 400	87.15 409	97.12 396	96.16 415

gm-plane-assit					94.83 426	81.97 429			88.07 414		94.99 404		99.60 313	91.76 379

GG-mvs-BLEND				94.76 387	94.54 427	92.13 370	99.31 27	80.47 433		88.73 427	91.01 427	67.59 420	98.16 420	82.30 422	94.53 419	93.98 423

UWE-MVS-28		90.22 392	89.28 395	93.02 407	94.50 428	82.87 426	96.52 315	87.51 426	95.21 336	92.36 419	96.04 381	71.57 412	98.25 418	72.04 428	97.77 377	97.94 378

EPNet_dtu		94.93 345	94.78 345	95.38 381	93.58 429	87.68 408	96.78 301	95.69 393	97.35 236	89.14 426	98.09 313	88.15 350	99.49 352	94.95 309	99.30 270	98.98 279
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 396	75.95 399	77.12 412	92.39 430	67.91 436	90.16 423	59.44 437	82.04 423	89.42 425	94.67 410	49.68 435	81.74 430	48.06 430	77.66 428	81.72 426

KD-MVS_2432*1600		92.87 378	91.99 380	95.51 377	91.37 431	89.27 400	94.07 406	98.14 334	95.42 329	97.25 329	96.44 376	67.86 417	99.24 390	91.28 388	96.08 410	98.02 373

miper_refine_blended		92.87 378	91.99 380	95.51 377	91.37 431	89.27 400	94.07 406	98.14 334	95.42 329	97.25 329	96.44 376	67.86 417	99.24 390	91.28 388	96.08 410	98.02 373

EPNet		96.14 314	95.44 326	98.25 244	90.76 433	95.50 278	97.92 196	94.65 399	98.97 105	92.98 415	98.85 214	89.12 341	99.87 113	95.99 275	99.68 178	99.39 186
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 397	68.95 400	70.34 413	87.68 434	65.00 437	91.11 421	59.90 436	69.02 426	74.46 431	88.89 428	48.58 436	68.03 432	28.61 431	72.33 430	77.99 427

test_method		79.78 394	79.50 397	80.62 410	80.21 435	45.76 438	70.82 426	98.41 324	31.08 430	80.89 430	97.71 335	84.85 369	97.37 423	91.51 385	80.03 427	98.75 320

tmp_tt		78.77 395	78.73 398	78.90 411	58.45 436	74.76 435	94.20 405	78.26 434	39.16 429	86.71 428	92.82 423	80.50 392	75.19 431	86.16 414	92.29 424	86.74 425

testmvs		17.12 399	20.53 402	6.87 415	12.05 437	4.20 440	93.62 414	6.73 438	4.62 433	10.41 433	24.33 430	8.28 438	3.56 434	9.69 433	15.07 431	12.86 430

test123		17.04 400	20.11 403	7.82 414	10.25 438	4.91 439	94.80 389	4.47 439	4.93 432	10.00 434	24.28 431	9.69 437	3.64 433	10.14 432	12.43 432	14.92 429

mmdepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

monomultidepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

test_blank		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

eth-test2					0.00 439

eth-test					0.00 439

uanet_test		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

DCPMVS		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

cdsmvs_eth3d_5k		24.66 398	32.88 401	0.00 416	0.00 439	0.00 441	0.00 427	99.10 238	0.00 434	0.00 435	97.58 343	99.21 17	0.00 435	0.00 434	0.00 433	0.00 431

pcd_1.5k_mvsjas		8.17 401	10.90 404	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	98.07 97	0.00 435	0.00 434	0.00 433	0.00 431

sosnet-low-res		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uncertanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

Regformer		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

ab-mvs-re		8.12 402	10.83 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	97.48 349	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

WAC-MVS						90.90 389								91.37 387

PC_three_1452									93.27 373	99.40 92	98.54 267	98.22 84	97.00 424	95.17 303	99.45 248	99.49 139

test_241102_TWO								99.30 182	98.03 174	99.26 120	99.02 167	97.51 145	99.88 96	96.91 202	99.60 205	99.66 65

test_0728_THIRD									98.17 167	99.08 142	99.02 167	97.89 111	99.88 96	97.07 190	99.71 163	99.70 58

GSMVS																98.81 309

sam_mvs1												84.74 371				98.81 309

sam_mvs												84.29 377

MTGPA								99.20 213

test_post1							97.59 244				20.48 433	83.07 385	99.66 291	94.16 330

test_post											21.25 432	83.86 380	99.70 264

patchmatchnet-post											98.77 229	84.37 374	99.85 133

MTMP							97.93 193	91.91 418

test9_res														93.28 356	99.15 295	99.38 193

agg_prior2														92.50 372	99.16 293	99.37 195

test_prior4						97.97 155	95.86 356

test_prior2							95.74 362		96.48 292	96.11 373	97.63 341	95.92 235		94.16 330	99.20 287

旧先验2							95.76 361		88.56 413	97.52 312			99.66 291	94.48 320

新几何2							95.93 352

无先验							95.74 362	98.74 303	89.38 409				99.73 252	92.38 374		99.22 240

原ACMM2							95.53 368

testdata2													99.79 212	92.80 366

segment_acmp												97.02 175

testdata1							95.44 373		96.32 298

plane_prior5								99.27 196					99.70 264	94.42 324	99.51 236	99.45 162

plane_prior4											97.98 320

plane_prior3						97.78 176			97.41 230	97.79 293

plane_prior2							97.77 217		98.20 164

plane_prior						97.65 185	97.07 286		96.72 282						99.36 259

n2								0.00 440

nn								0.00 440

door-mid								99.57 70

test11								98.87 277

door								99.41 135

HQP5-MVS						96.79 234

BP-MVS														92.82 364

HQP4-MVS										95.56 383			99.54 337			99.32 215

HQP3-MVS								99.04 249							99.26 277

HQP2-MVS												93.84 289

MDTV_nov1_ep13_2view						74.92 434	97.69 228		90.06 407	97.75 296		85.78 363		93.52 350		98.69 327

ACMMP++_ref															99.77 131

ACMMP++															99.68 178

Test By Simon												96.52 203

High-resolution multi-view benchmark