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 14	100.00 1	99.85 29

Gipuma		99.03 77	99.16 59	98.64 202	99.94 2	98.51 108	99.32 26	99.75 41	99.58 37	98.60 249	99.62 40	98.22 98	99.51 376	97.70 177	99.73 167	97.89 409
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 40	99.53 38	99.91 3	98.98 71	99.63 7	99.58 75	99.44 50	99.78 38	99.76 15	96.39 230	99.92 62	99.44 52	99.92 66	99.68 67

pmmvs6		99.67 3	99.70 3	99.60 15	99.90 4	99.27 27	99.53 9	99.76 38	99.64 27	99.84 29	99.83 4	99.50 9	99.87 131	99.36 55	99.92 66	99.64 80

PS-MVSNAJss		99.46 17	99.49 16	99.35 76	99.90 4	98.15 135	99.20 48	99.65 61	99.48 42	99.92 8	99.71 22	98.07 112	99.96 14	99.53 45	100.00 1	99.93 11

testf1		99.25 40	99.16 59	99.51 48	99.89 6	99.63 4	98.71 104	99.69 49	98.90 127	99.43 98	99.35 100	98.86 33	99.67 307	97.81 166	99.81 120	99.24 257

APD_test2		99.25 40	99.16 59	99.51 48	99.89 6	99.63 4	98.71 104	99.69 49	98.90 127	99.43 98	99.35 100	98.86 33	99.67 307	97.81 166	99.81 120	99.24 257

ANet_high		99.57 10	99.67 6	99.28 92	99.89 6	98.09 142	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 19	99.94 41	99.31 59	100.00 1	99.82 34

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 49	98.93 123	99.65 61	99.72 21	98.93 31	99.95 26	99.11 75	100.00 1	99.82 34

v7n		99.53 12	99.57 13	99.41 66	99.88 9	98.54 106	99.45 14	99.61 69	99.66 24	99.68 55	99.66 32	98.44 76	99.95 26	99.73 25	99.96 27	99.75 56

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 98	99.34 23	99.71 45	99.27 71	99.90 13	99.74 18	99.68 4	99.97 7	99.55 40	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 70	99.87 12	98.13 138	98.08 182	99.95 1	99.45 48	99.98 2	99.75 16	99.80 1	99.97 7	99.82 10	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 56	99.87 12	98.61 98	99.28 40	99.66 58	99.09 102	99.89 17	99.68 25	99.53 7	99.97 7	99.50 48	99.99 5	99.87 21

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 88	99.39 20	99.56 89	99.11 92	99.70 49	99.73 20	99.00 26	99.97 7	99.26 63	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 38	99.55 28	99.86 14	99.19 42	99.41 17	99.59 73	99.59 35	99.71 47	99.57 49	97.12 187	99.90 78	99.21 68	99.87 94	99.54 133

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 35	99.63 29	99.78 38	99.67 30	99.48 10	99.81 215	99.30 60	99.97 20	99.77 47
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 20	99.69 5	99.58 75	99.90 3	99.86 23	99.78 13	99.58 6	99.95 26	99.00 85	99.95 37	99.78 44

SixPastTwentyTwo		98.75 121	98.62 133	99.16 114	99.83 18	97.96 162	99.28 40	98.20 356	99.37 58	99.70 49	99.65 36	92.65 335	99.93 52	99.04 82	99.84 105	99.60 96

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 64	99.88 4	99.86 23	99.80 11	99.03 23	99.89 94	99.48 50	99.93 53	99.60 96

Baseline_NR-MVSNet		98.98 85	98.86 100	99.36 70	99.82 19	98.55 103	97.47 282	99.57 82	99.37 58	99.21 149	99.61 43	96.76 212	99.83 189	98.06 146	99.83 112	99.71 59

pm-mvs1		99.44 19	99.48 18	99.33 85	99.80 21	98.63 95	99.29 36	99.63 64	99.30 68	99.65 61	99.60 45	99.16 21	99.82 199	99.07 78	99.83 112	99.56 122

TransMVSNet (Re)		99.44 19	99.47 21	99.36 70	99.80 21	98.58 101	99.27 42	99.57 82	99.39 56	99.75 43	99.62 40	99.17 19	99.83 189	99.06 80	99.62 221	99.66 74

K. test v3		98.00 229	97.66 254	99.03 141	99.79 23	97.56 198	99.19 52	92.47 442	99.62 32	99.52 80	99.66 32	89.61 366	99.96 14	99.25 65	99.81 120	99.56 122

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 79	99.78 24	98.11 139	97.77 237	99.90 11	99.33 63	99.97 3	99.66 32	99.71 3	99.96 14	99.79 17	99.99 5	99.96 8

APD_test1		98.83 105	98.66 126	99.34 79	99.78 24	99.47 9	98.42 144	99.45 133	98.28 178	98.98 182	99.19 140	97.76 138	99.58 351	96.57 265	99.55 248	98.97 311

test_vis3_rt		99.14 59	99.17 57	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 219	99.91 12	99.67 30	97.15 186	98.91 435	99.76 21	99.56 244	99.92 12

EGC-MVSNET		85.24 422	80.54 425	99.34 79	99.77 27	99.20 39	99.08 61	99.29 213	12.08 460	20.84 461	99.42 87	97.55 157	99.85 153	97.08 217	99.72 175	98.96 313

Anonymous20240521		98.69 132	98.87 97	98.16 274	99.77 27	95.11 315	99.08 61	99.44 141	99.34 62	99.33 121	99.55 57	94.10 310	99.94 41	99.25 65	99.96 27	99.42 192

FC-MVSNet-test		99.27 37	99.25 50	99.34 79	99.77 27	98.37 117	99.30 35	99.57 82	99.61 34	99.40 107	99.50 67	97.12 187	99.85 153	99.02 84	99.94 48	99.80 39

test_vis1_n		98.31 194	98.50 150	97.73 308	99.76 30	94.17 343	98.68 107	99.91 9	96.31 327	99.79 37	99.57 49	92.85 331	99.42 396	99.79 17	99.84 105	99.60 96

test_fmvs3		99.12 66	99.41 25	98.25 265	99.76 30	95.07 316	99.05 67	99.94 2	97.78 222	99.82 32	99.84 3	98.56 67	99.71 285	99.96 1	99.96 27	99.97 4

XXY-MVS		99.14 59	99.15 64	99.10 124	99.76 30	97.74 187	98.85 92	99.62 66	98.48 162	99.37 112	99.49 73	98.75 45	99.86 140	98.20 136	99.80 131	99.71 59

TDRefinement		99.42 24	99.38 28	99.55 28	99.76 30	99.33 21	99.68 6	99.71 45	99.38 57	99.53 78	99.61 43	98.64 55	99.80 223	98.24 132	99.84 105	99.52 145

fmvsm_s_conf0.1_n_a		99.17 51	99.30 43	98.80 175	99.75 34	96.59 254	97.97 211	99.86 16	98.22 181	99.88 20	99.71 22	98.59 61	99.84 171	99.73 25	99.98 12	99.98 3

tt0805		98.69 132	98.62 133	98.90 165	99.75 34	99.30 22	99.15 56	96.97 393	98.86 132	98.87 212	97.62 371	98.63 57	98.96 432	99.41 54	98.29 384	98.45 375

test_vis1_n_1920		98.40 178	98.92 90	96.81 370	99.74 36	90.76 421	98.15 170	99.91 9	98.33 169	99.89 17	99.55 57	95.07 281	99.88 112	99.76 21	99.93 53	99.79 41

FOURS1					99.73 37	99.67 3	99.43 15	99.54 97	99.43 52	99.26 138

PEN-MVS		99.41 25	99.34 35	99.62 9	99.73 37	99.14 57	99.29 36	99.54 97	99.62 32	99.56 69	99.42 87	98.16 106	99.96 14	98.78 99	99.93 53	99.77 47

lessismore_v0				98.97 152	99.73 37	97.53 200		86.71 457		99.37 112	99.52 66	89.93 362	99.92 62	98.99 86	99.72 175	99.44 185

SteuartSystems-ACMMP		98.79 114	98.54 145	99.54 31	99.73 37	99.16 48	98.23 160	99.31 197	97.92 210	98.90 202	98.90 221	98.00 118	99.88 112	96.15 297	99.72 175	99.58 111
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 215	98.15 207	98.22 268	99.73 37	95.15 312	97.36 290	99.68 54	94.45 383	98.99 181	99.27 118	96.87 201	99.94 41	97.13 214	99.91 75	99.57 116

Vis-MVSNet		99.34 30	99.36 32	99.27 95	99.73 37	98.26 124	99.17 53	99.78 35	99.11 92	99.27 134	99.48 74	98.82 36	99.95 26	98.94 89	99.93 53	99.59 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc		99.64 5	99.68 5	99.50 53	99.72 43	98.98 71	99.51 10	99.85 18	99.86 6	99.88 20	99.82 5	99.02 25	99.90 78	99.54 41	99.95 37	99.61 94

SSC-MVS		98.71 125	98.74 110	98.62 208	99.72 43	96.08 277	98.74 97	98.64 336	99.74 13	99.67 57	99.24 130	94.57 296	99.95 26	99.11 75	99.24 308	99.82 34

test_f		98.67 140	98.87 97	98.05 283	99.72 43	95.59 291	98.51 128	99.81 30	96.30 329	99.78 38	99.82 5	96.14 240	98.63 442	99.82 10	99.93 53	99.95 9

ACMH	96.65 7	99.25 40	99.24 51	99.26 97	99.72 43	98.38 115	99.07 64	99.55 93	98.30 173	99.65 61	99.45 83	99.22 16	99.76 259	98.44 123	99.77 148	99.64 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 56	99.71 47	98.94 78	99.54 8	99.83 25	99.87 5	99.89 17	99.82 5	98.75 45	99.90 78	99.54 41	99.95 37	99.59 103

fmvsm_s_conf0.1_n		99.16 55	99.33 36	98.64 202	99.71 47	96.10 272	97.87 223	99.85 18	98.56 158	99.90 13	99.68 25	98.69 51	99.85 153	99.72 27	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 36	99.62 9	99.71 47	99.10 65	99.29 36	99.53 100	99.53 39	99.46 93	99.41 91	98.23 95	99.95 26	98.89 93	99.95 37	99.81 37

DTE-MVSNet		99.43 23	99.35 33	99.66 7	99.71 47	99.30 22	99.31 30	99.51 105	99.64 27	99.56 69	99.46 79	98.23 95	99.97 7	98.78 99	99.93 53	99.72 58

WR-MVS_H		99.33 31	99.22 52	99.65 8	99.71 47	99.24 30	99.32 26	99.55 93	99.46 47	99.50 86	99.34 104	97.30 176	99.93 52	98.90 91	99.93 53	99.77 47

HPM-MVS_fast		99.01 79	98.82 103	99.57 21	99.71 47	99.35 17	99.00 72	99.50 108	97.33 265	98.94 197	98.86 231	98.75 45	99.82 199	97.53 188	99.71 184	99.56 122

ACMH+	96.62 9	99.08 73	99.00 82	99.33 85	99.71 47	98.83 83	98.60 114	99.58 75	99.11 92	99.53 78	99.18 144	98.81 37	99.67 307	96.71 254	99.77 148	99.50 151

PMVS	91.26 20	97.86 243	97.94 231	97.65 315	99.71 47	97.94 164	98.52 123	98.68 332	98.99 115	97.52 340	99.35 100	97.41 170	98.18 448	91.59 411	99.67 205	96.82 437
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 77	99.02 78	99.03 141	99.70 55	97.48 203	98.43 141	99.29 213	99.70 16	99.60 68	99.07 171	96.13 241	99.94 41	99.42 53	99.87 94	99.68 67

FIs		99.14 59	99.09 72	99.29 91	99.70 55	98.28 123	99.13 58	99.52 104	99.48 42	99.24 143	99.41 91	96.79 209	99.82 199	98.69 109	99.88 90	99.76 52

VPNet		98.87 99	98.83 102	99.01 145	99.70 55	97.62 196	98.43 141	99.35 178	99.47 45	99.28 132	99.05 179	96.72 215	99.82 199	98.09 143	99.36 288	99.59 103

fmvsm_s_conf0.1_n_2		99.20 49	99.38 28	98.65 200	99.69 58	96.08 277	97.49 279	99.90 11	99.53 39	99.88 20	99.64 37	98.51 70	99.90 78	99.83 9	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 191	98.68 123	97.27 346	99.69 58	92.29 395	98.03 192	99.85 18	97.62 231	99.96 4	99.62 40	93.98 311	99.74 271	99.52 47	99.86 100	99.79 41

MP-MVS-pluss		98.57 154	98.23 195	99.60 15	99.69 58	99.35 17	97.16 309	99.38 164	94.87 373	98.97 186	98.99 199	98.01 117	99.88 112	97.29 202	99.70 191	99.58 111
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 45	99.32 38	98.96 153	99.68 61	97.35 211	98.84 94	99.48 117	99.69 18	99.63 64	99.68 25	99.03 23	99.96 14	97.97 155	99.92 66	99.57 116

sd_testset		99.28 36	99.31 40	99.19 108	99.68 61	98.06 151	99.41 17	99.30 205	99.69 18	99.63 64	99.68 25	99.25 15	99.96 14	97.25 205	99.92 66	99.57 116

test_fmvs1_n		98.09 220	98.28 186	97.52 332	99.68 61	93.47 374	98.63 110	99.93 5	95.41 361	99.68 55	99.64 37	91.88 345	99.48 383	99.82 10	99.87 94	99.62 86

CHOSEN 1792x2688		97.49 272	97.14 287	98.54 230	99.68 61	96.09 275	96.50 344	99.62 66	91.58 421	98.84 215	98.97 206	92.36 337	99.88 112	96.76 247	99.95 37	99.67 72

tfpnnormal		98.90 95	98.90 92	98.91 162	99.67 65	97.82 179	99.00 72	99.44 141	99.45 48	99.51 85	99.24 130	98.20 101	99.86 140	95.92 306	99.69 194	99.04 298

MTAPA		98.88 98	98.64 129	99.61 13	99.67 65	99.36 16	98.43 141	99.20 237	98.83 136	98.89 204	98.90 221	96.98 197	99.92 62	97.16 209	99.70 191	99.56 122

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 230	99.66 67	96.97 234	98.00 199	99.85 18	99.24 73	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 352

mvs5depth		99.30 33	99.59 12	98.44 244	99.65 68	95.35 304	99.82 3	99.94 2	99.83 7	99.42 102	99.94 2	98.13 109	99.96 14	99.63 33	99.96 27	100.00 1

fmvsm_l_conf0.5_n_a		99.19 50	99.27 46	98.94 156	99.65 68	97.05 230	97.80 232	99.76 38	98.70 141	99.78 38	99.11 163	98.79 41	99.95 26	99.85 5	99.96 27	99.83 31

WB-MVS		98.52 167	98.55 143	98.43 245	99.65 68	95.59 291	98.52 123	98.77 321	99.65 26	99.52 80	99.00 198	94.34 302	99.93 52	98.65 111	98.83 356	99.76 52

CP-MVSNet		99.21 47	99.09 72	99.56 26	99.65 68	98.96 77	99.13 58	99.34 184	99.42 53	99.33 121	99.26 123	97.01 195	99.94 41	98.74 104	99.93 53	99.79 41

HPM-MVS		98.79 114	98.53 146	99.59 19	99.65 68	99.29 24	99.16 54	99.43 147	96.74 309	98.61 247	98.38 316	98.62 58	99.87 131	96.47 277	99.67 205	99.59 103
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 149	98.36 175	99.42 64	99.65 68	99.42 11	98.55 119	99.57 82	97.72 225	98.90 202	99.26 123	96.12 243	99.52 371	95.72 317	99.71 184	99.32 235

NormalMVS		98.26 201	97.97 228	99.15 117	99.64 74	97.83 174	98.28 154	99.43 147	99.24 73	98.80 222	98.85 234	89.76 364	99.94 41	98.04 148	99.67 205	99.68 67

lecture		99.25 40	99.12 67	99.62 9	99.64 74	99.40 12	98.89 87	99.51 105	99.19 84	99.37 112	99.25 128	98.36 80	99.88 112	98.23 134	99.67 205	99.59 103

fmvsm_l_conf0.5_n		99.21 47	99.28 45	99.02 144	99.64 74	97.28 215	97.82 228	99.76 38	98.73 138	99.82 32	99.09 170	98.81 37	99.95 26	99.86 4	99.96 27	99.83 31

test_fmvsmconf_n		99.44 19	99.48 18	99.31 90	99.64 74	98.10 141	97.68 249	99.84 22	99.29 69	99.92 8	99.57 49	99.60 5	99.96 14	99.74 24	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 146	98.49 154	99.06 137	99.64 74	97.90 168	98.51 128	98.94 286	96.96 296	99.24 143	98.89 227	97.83 131	99.81 215	96.88 237	99.49 268	99.48 167
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 108	98.72 114	99.12 120	99.64 74	98.54 106	97.98 207	99.68 54	97.62 231	99.34 119	99.18 144	97.54 158	99.77 253	97.79 168	99.74 164	99.04 298

Elysia		99.15 56	99.14 65	99.18 109	99.63 80	97.92 165	98.50 130	99.43 147	99.67 21	99.70 49	99.13 159	96.66 218	99.98 4	99.54 41	99.96 27	99.64 80

StellarMVS		99.15 56	99.14 65	99.18 109	99.63 80	97.92 165	98.50 130	99.43 147	99.67 21	99.70 49	99.13 159	96.66 218	99.98 4	99.54 41	99.96 27	99.64 80

KD-MVS_self_test		99.25 40	99.18 56	99.44 63	99.63 80	99.06 70	98.69 106	99.54 97	99.31 66	99.62 67	99.53 63	97.36 173	99.86 140	99.24 67	99.71 184	99.39 205

EU-MVSNet		97.66 260	98.50 150	95.13 412	99.63 80	85.84 443	98.35 150	98.21 355	98.23 180	99.54 74	99.46 79	95.02 282	99.68 303	98.24 132	99.87 94	99.87 21

HyFIR lowres test		97.19 298	96.60 322	98.96 153	99.62 84	97.28 215	95.17 409	99.50 108	94.21 388	99.01 178	98.32 324	86.61 384	99.99 2	97.10 216	99.84 105	99.60 96

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 79	99.59 85	98.21 132	97.82 228	99.84 22	99.41 55	99.92 8	99.41 91	99.51 8	99.95 26	99.84 8	99.97 20	99.87 21

mmtdpeth		99.30 33	99.42 24	98.92 161	99.58 86	96.89 241	99.48 13	99.92 7	99.92 2	98.26 284	99.80 11	98.33 86	99.91 71	99.56 38	99.95 37	99.97 4

ACMMP_NAP		98.75 121	98.48 155	99.57 21	99.58 86	99.29 24	97.82 228	99.25 226	96.94 298	98.78 224	99.12 162	98.02 116	99.84 171	97.13 214	99.67 205	99.59 103

nrg030		99.40 26	99.35 33	99.54 31	99.58 86	99.13 60	98.98 75	99.48 117	99.68 20	99.46 93	99.26 123	98.62 58	99.73 277	99.17 72	99.92 66	99.76 52

VDDNet		98.21 208	97.95 229	99.01 145	99.58 86	97.74 187	99.01 70	97.29 384	99.67 21	98.97 186	99.50 67	90.45 359	99.80 223	97.88 161	99.20 316	99.48 167

COLMAP_ROB	96.50 10	98.99 82	98.85 101	99.41 66	99.58 86	99.10 65	98.74 97	99.56 89	99.09 102	99.33 121	99.19 140	98.40 78	99.72 284	95.98 304	99.76 160	99.42 192
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 31	99.45 23	98.99 147	99.57 91	97.73 189	97.93 212	99.83 25	99.22 76	99.93 6	99.30 112	99.42 11	99.96 14	99.85 5	99.99 5	99.29 244

ZNCC-MVS		98.68 137	98.40 167	99.54 31	99.57 91	99.21 33	98.46 138	99.29 213	97.28 271	98.11 296	98.39 314	98.00 118	99.87 131	96.86 240	99.64 215	99.55 129

MSP-MVS		98.40 178	98.00 223	99.61 13	99.57 91	99.25 29	98.57 117	99.35 178	97.55 242	99.31 129	97.71 364	94.61 295	99.88 112	96.14 298	99.19 319	99.70 64
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		98.32 192	98.39 170	98.13 275	99.57 91	95.54 294	97.78 234	99.49 115	97.37 262	99.19 151	97.65 368	98.96 28	99.49 380	96.50 276	98.99 344	99.34 227

MP-MVS		98.46 172	98.09 212	99.54 31	99.57 91	99.22 32	98.50 130	99.19 241	97.61 234	97.58 334	98.66 277	97.40 171	99.88 112	94.72 343	99.60 228	99.54 133
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 125	98.46 159	99.47 60	99.57 91	98.97 73	98.23 160	99.48 117	96.60 314	99.10 161	99.06 172	98.71 49	99.83 189	95.58 324	99.78 142	99.62 86

LGP-MVS_train				99.47 60	99.57 91	98.97 73		99.48 117	96.60 314	99.10 161	99.06 172	98.71 49	99.83 189	95.58 324	99.78 142	99.62 86

IS-MVSNet		98.19 211	97.90 236	99.08 129	99.57 91	97.97 159	99.31 30	98.32 351	99.01 114	98.98 182	99.03 183	91.59 347	99.79 236	95.49 326	99.80 131	99.48 167

dcpmvs_2		98.78 116	99.11 68	97.78 298	99.56 99	93.67 369	99.06 65	99.86 16	99.50 41	99.66 58	99.26 123	97.21 184	99.99 2	98.00 153	99.91 75	99.68 67

test_0402		98.76 120	98.71 117	98.93 158	99.56 99	98.14 137	98.45 140	99.34 184	99.28 70	98.95 190	98.91 218	98.34 85	99.79 236	95.63 321	99.91 75	98.86 330

EPP-MVSNet		98.30 195	98.04 219	99.07 131	99.56 99	97.83 174	99.29 36	98.07 362	99.03 112	98.59 251	99.13 159	92.16 341	99.90 78	96.87 238	99.68 199	99.49 156

ACMMP		98.75 121	98.50 150	99.52 44	99.56 99	99.16 48	98.87 88	99.37 168	97.16 286	98.82 219	99.01 195	97.71 141	99.87 131	96.29 289	99.69 194	99.54 133
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 68	99.20 55	98.78 181	99.55 103	96.59 254	97.79 233	99.82 29	98.21 182	99.81 35	99.53 63	98.46 74	99.84 171	99.70 30	99.97 20	99.90 15

fmvsm_s_conf0.5_n		99.09 69	99.26 48	98.61 211	99.55 103	96.09 275	97.74 243	99.81 30	98.55 159	99.85 26	99.55 57	98.60 60	99.84 171	99.69 32	99.98 12	99.89 16

FMVSNet1		99.17 51	99.17 57	99.17 111	99.55 103	98.24 126	99.20 48	99.44 141	99.21 78	99.43 98	99.55 57	97.82 134	99.86 140	98.42 125	99.89 88	99.41 195

Vis-MVSNet (Re-imp)		97.46 274	97.16 284	98.34 257	99.55 103	96.10 272	98.94 80	98.44 345	98.32 171	98.16 290	98.62 286	88.76 371	99.73 277	93.88 369	99.79 137	99.18 277

ACMM	96.08 12	98.91 93	98.73 112	99.48 56	99.55 103	99.14 57	98.07 185	99.37 168	97.62 231	99.04 174	98.96 209	98.84 35	99.79 236	97.43 196	99.65 213	99.49 156
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 129	98.97 86	97.89 291	99.54 108	94.05 346	98.55 119	99.92 7	96.78 307	99.72 45	99.78 13	96.60 222	99.67 307	99.91 2	99.90 82	99.94 10

mPP-MVS		98.64 144	98.34 178	99.54 31	99.54 108	99.17 44	98.63 110	99.24 231	97.47 249	98.09 298	98.68 272	97.62 150	99.89 94	96.22 292	99.62 221	99.57 116

XVG-ACMP-BASELINE		98.56 155	98.34 178	99.22 105	99.54 108	98.59 100	97.71 246	99.46 129	97.25 274	98.98 182	98.99 199	97.54 158	99.84 171	95.88 307	99.74 164	99.23 259

region2R		98.69 132	98.40 167	99.54 31	99.53 111	99.17 44	98.52 123	99.31 197	97.46 254	98.44 269	98.51 300	97.83 131	99.88 112	96.46 278	99.58 237	99.58 111

PGM-MVS		98.66 141	98.37 174	99.55 28	99.53 111	99.18 43	98.23 160	99.49 115	97.01 295	98.69 235	98.88 228	98.00 118	99.89 94	95.87 310	99.59 232	99.58 111

Patchmatch-RL test		97.26 291	97.02 292	97.99 287	99.52 113	95.53 295	96.13 369	99.71 45	97.47 249	99.27 134	99.16 150	84.30 405	99.62 332	97.89 158	99.77 148	98.81 338

ACMMPR		98.70 129	98.42 165	99.54 31	99.52 113	99.14 57	98.52 123	99.31 197	97.47 249	98.56 256	98.54 295	97.75 139	99.88 112	96.57 265	99.59 232	99.58 111

fmvsm_s_conf0.5_n_9		99.17 51	99.38 28	98.53 232	99.51 115	95.82 287	97.62 260	99.78 35	99.72 15	99.90 13	99.48 74	98.66 53	99.89 94	99.85 5	99.93 53	99.89 16

AstraMVS		98.16 217	98.07 217	98.41 247	99.51 115	95.86 284	98.00 199	95.14 425	98.97 118	99.43 98	99.24 130	93.25 319	99.84 171	99.21 68	99.87 94	99.54 133

fmvsm_s_conf0.5_n_8		99.13 63	99.26 48	98.74 192	99.51 115	96.44 264	97.65 255	99.65 61	99.66 24	99.78 38	99.48 74	97.92 125	99.93 52	99.72 27	99.95 37	99.87 21

GST-MVS		98.61 150	98.30 184	99.52 44	99.51 115	99.20 39	98.26 158	99.25 226	97.44 257	98.67 238	98.39 314	97.68 142	99.85 153	96.00 302	99.51 259	99.52 145

Anonymous20231206		98.21 208	98.21 196	98.20 269	99.51 115	95.43 302	98.13 172	99.32 192	96.16 333	98.93 198	98.82 244	96.00 248	99.83 189	97.32 201	99.73 167	99.36 221

ACMP	95.32 15	98.41 176	98.09 212	99.36 70	99.51 115	98.79 86	97.68 249	99.38 164	95.76 348	98.81 221	98.82 244	98.36 80	99.82 199	94.75 340	99.77 148	99.48 167
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 184	98.20 197	98.98 151	99.50 121	97.49 201	97.78 234	97.69 371	98.75 137	99.49 87	99.25 128	92.30 339	99.94 41	99.14 73	99.88 90	99.50 151

DVP-MVS		98.77 119	98.52 147	99.52 44	99.50 121	99.21 33	98.02 195	98.84 310	97.97 204	99.08 163	99.02 184	97.61 152	99.88 112	96.99 224	99.63 218	99.48 167
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 15	99.50 121	99.23 31	98.02 195	99.32 192					99.88 112	96.99 224	99.63 218	99.68 67

test0726					99.50 121	99.21 33	98.17 168	99.35 178	97.97 204	99.26 138	99.06 172	97.61 152

AllTest		98.44 174	98.20 197	99.16 114	99.50 121	98.55 103	98.25 159	99.58 75	96.80 305	98.88 208	99.06 172	97.65 145	99.57 353	94.45 350	99.61 226	99.37 214

TestCases				99.16 114	99.50 121	98.55 103		99.58 75	96.80 305	98.88 208	99.06 172	97.65 145	99.57 353	94.45 350	99.61 226	99.37 214

XVG-OURS		98.53 163	98.34 178	99.11 122	99.50 121	98.82 85	95.97 375	99.50 108	97.30 269	99.05 172	98.98 204	99.35 13	99.32 410	95.72 317	99.68 199	99.18 277

EG-PatchMatch MVS		98.99 82	99.01 80	98.94 156	99.50 121	97.47 204	98.04 190	99.59 73	98.15 197	99.40 107	99.36 99	98.58 66	99.76 259	98.78 99	99.68 199	99.59 103

fmvsm_s_conf0.5_n_2		99.14 59	99.31 40	98.63 206	99.49 129	96.08 277	97.38 287	99.81 30	99.48 42	99.84 29	99.57 49	98.46 74	99.89 94	99.82 10	99.97 20	99.91 13

SED-MVS		98.91 93	98.72 114	99.49 54	99.49 129	99.17 44	98.10 179	99.31 197	98.03 200	99.66 58	99.02 184	98.36 80	99.88 112	96.91 230	99.62 221	99.41 195

IU-MVS					99.49 129	99.15 52		98.87 301	92.97 406	99.41 104				96.76 247	99.62 221	99.66 74

test_241102_ONE					99.49 129	99.17 44		99.31 197	97.98 203	99.66 58	98.90 221	98.36 80	99.48 383

UA-Net		99.47 16	99.40 26	99.70 2	99.49 129	99.29 24	99.80 4	99.72 43	99.82 8	99.04 174	99.81 8	98.05 115	99.96 14	98.85 95	99.99 5	99.86 27

HFP-MVS		98.71 125	98.44 162	99.51 48	99.49 129	99.16 48	98.52 123	99.31 197	97.47 249	98.58 253	98.50 304	97.97 122	99.85 153	96.57 265	99.59 232	99.53 142

VPA-MVSNet		99.30 33	99.30 43	99.28 92	99.49 129	98.36 120	99.00 72	99.45 133	99.63 29	99.52 80	99.44 84	98.25 93	99.88 112	99.09 77	99.84 105	99.62 86

XVG-OURS-SEG-HR		98.49 169	98.28 186	99.14 118	99.49 129	98.83 83	96.54 340	99.48 117	97.32 267	99.11 158	98.61 288	99.33 14	99.30 413	96.23 291	98.38 380	99.28 246

114514_t		96.50 331	95.77 340	98.69 196	99.48 137	97.43 208	97.84 227	99.55 93	81.42 453	96.51 393	98.58 292	95.53 268	99.67 307	93.41 382	99.58 237	98.98 308

IterMVS-LS		98.55 159	98.70 120	98.09 276	99.48 137	94.73 326	97.22 304	99.39 162	98.97 118	99.38 110	99.31 111	96.00 248	99.93 52	98.58 114	99.97 20	99.60 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_5		99.07 75	99.10 70	98.99 147	99.47 139	97.22 220	97.40 285	99.83 25	97.61 234	99.85 26	99.30 112	98.80 39	99.95 26	99.71 29	99.90 82	99.78 44

v8		99.01 79	99.16 59	98.57 218	99.47 139	96.31 269	98.90 83	99.47 125	99.03 112	99.52 80	99.57 49	96.93 198	99.81 215	99.60 34	99.98 12	99.60 96

SSC-MVS3.2		98.53 163	98.79 106	97.74 305	99.46 141	93.62 372	96.45 346	99.34 184	99.33 63	98.93 198	98.70 268	97.90 126	99.90 78	99.12 74	99.92 66	99.69 66

fmvsm_s_conf0.5_n_3		99.22 46	99.37 31	98.78 181	99.46 141	96.58 257	97.65 255	99.72 43	99.47 45	99.86 23	99.50 67	98.94 29	99.89 94	99.75 23	99.97 20	99.86 27

XVS		98.72 124	98.45 160	99.53 38	99.46 141	99.21 33	98.65 108	99.34 184	98.62 148	97.54 338	98.63 284	97.50 164	99.83 189	96.79 243	99.53 254	99.56 122

X-MVStestdata		94.32 380	92.59 399	99.53 38	99.46 141	99.21 33	98.65 108	99.34 184	98.62 148	97.54 338	45.85 458	97.50 164	99.83 189	96.79 243	99.53 254	99.56 122

test20.03		98.78 116	98.77 109	98.78 181	99.46 141	97.20 223	97.78 234	99.24 231	99.04 111	99.41 104	98.90 221	97.65 145	99.76 259	97.70 177	99.79 137	99.39 205

guyue		98.01 228	97.93 233	98.26 264	99.45 146	95.48 298	98.08 182	96.24 408	98.89 129	99.34 119	99.14 157	91.32 351	99.82 199	99.07 78	99.83 112	99.48 167

CSCG		98.68 137	98.50 150	99.20 106	99.45 146	98.63 95	98.56 118	99.57 82	97.87 214	98.85 213	98.04 345	97.66 144	99.84 171	96.72 252	99.81 120	99.13 287

GeoE		99.05 76	98.99 84	99.25 100	99.44 148	98.35 121	98.73 101	99.56 89	98.42 165	98.91 201	98.81 246	98.94 29	99.91 71	98.35 127	99.73 167	99.49 156

v148		98.45 173	98.60 138	98.00 286	99.44 148	94.98 318	97.44 284	99.06 267	98.30 173	99.32 127	98.97 206	96.65 220	99.62 332	98.37 126	99.85 101	99.39 205

v10		98.97 86	99.11 68	98.55 225	99.44 148	96.21 271	98.90 83	99.55 93	98.73 138	99.48 88	99.60 45	96.63 221	99.83 189	99.70 30	99.99 5	99.61 94

V42		98.78 116	98.78 108	98.76 186	99.44 148	97.04 231	98.27 157	99.19 241	97.87 214	99.25 142	99.16 150	96.84 202	99.78 247	99.21 68	99.84 105	99.46 177

MDA-MVSNet-bldmvs		97.94 234	97.91 235	98.06 281	99.44 148	94.96 319	96.63 337	99.15 257	98.35 167	98.83 216	99.11 163	94.31 303	99.85 153	96.60 262	98.72 362	99.37 214

casdiffmvs_mvg		99.12 66	99.16 59	98.99 147	99.43 153	97.73 189	98.00 199	99.62 66	99.22 76	99.55 72	99.22 136	98.93 31	99.75 266	98.66 110	99.81 120	99.50 151
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
mamba_0404		98.90 95	99.01 80	98.57 218	99.42 154	96.59 254	98.13 172	99.66 58	99.09 102	99.30 130	99.02 184	98.79 41	99.89 94	97.87 163	99.80 131	99.23 259

test1111		96.49 332	96.82 306	95.52 405	99.42 154	87.08 440	99.22 45	87.14 456	99.11 92	99.46 93	99.58 47	88.69 372	99.86 140	98.80 97	99.95 37	99.62 86

v2v482		98.56 155	98.62 133	98.37 254	99.42 154	95.81 288	97.58 268	99.16 252	97.90 212	99.28 132	99.01 195	95.98 253	99.79 236	99.33 57	99.90 82	99.51 148

OPM-MVS		98.56 155	98.32 182	99.25 100	99.41 157	98.73 91	97.13 311	99.18 245	97.10 289	98.75 230	98.92 217	98.18 102	99.65 323	96.68 256	99.56 244	99.37 214
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 222	98.08 215	98.04 284	99.41 157	94.59 332	94.59 427	99.40 160	97.50 246	98.82 219	98.83 241	96.83 204	99.84 171	97.50 190	99.81 120	99.71 59

test_one_0601					99.39 159	99.20 39		99.31 197	98.49 161	98.66 240	99.02 184	97.64 148

mvsany_test3		98.87 99	98.92 90	98.74 192	99.38 160	96.94 238	98.58 116	99.10 262	96.49 319	99.96 4	99.81 8	98.18 102	99.45 391	98.97 87	99.79 137	99.83 31

patch_mono-2		98.51 168	98.63 131	98.17 272	99.38 160	94.78 323	97.36 290	99.69 49	98.16 192	98.49 265	99.29 115	97.06 190	99.97 7	98.29 131	99.91 75	99.76 52

test2506		92.39 411	91.89 413	93.89 426	99.38 160	82.28 457	99.32 26	66.03 464	99.08 106	98.77 227	99.57 49	66.26 452	99.84 171	98.71 107	99.95 37	99.54 133

ECVR-MVS		96.42 334	96.61 320	95.85 397	99.38 160	88.18 435	99.22 45	86.00 458	99.08 106	99.36 115	99.57 49	88.47 377	99.82 199	98.52 120	99.95 37	99.54 133

casdiffmvs		98.95 89	99.00 82	98.81 173	99.38 160	97.33 212	97.82 228	99.57 82	99.17 88	99.35 117	99.17 148	98.35 84	99.69 294	98.46 122	99.73 167	99.41 195
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 88	99.02 78	98.76 186	99.38 160	97.26 217	98.49 133	99.50 108	98.86 132	99.19 151	99.06 172	98.23 95	99.69 294	98.71 107	99.76 160	99.33 232

TranMVSNet+NR-MVSNet		99.17 51	99.07 75	99.46 62	99.37 166	98.87 81	98.39 146	99.42 153	99.42 53	99.36 115	99.06 172	98.38 79	99.95 26	98.34 128	99.90 82	99.57 116

fmvsm_s_conf0.5_n_6		99.08 73	99.21 54	98.69 196	99.36 167	96.51 259	97.62 260	99.68 54	98.43 164	99.85 26	99.10 166	99.12 22	99.88 112	99.77 20	99.92 66	99.67 72

tttt0517		95.64 359	94.98 369	97.64 318	99.36 167	93.81 364	98.72 102	90.47 450	98.08 199	98.67 238	98.34 321	73.88 438	99.92 62	97.77 170	99.51 259	99.20 269

test_part2					99.36 167	99.10 65				99.05 172

v1144		98.60 151	98.66 126	98.41 247	99.36 167	95.90 282	97.58 268	99.34 184	97.51 245	99.27 134	99.15 154	96.34 235	99.80 223	99.47 51	99.93 53	99.51 148

CP-MVS		98.70 129	98.42 165	99.52 44	99.36 167	99.12 62	98.72 102	99.36 172	97.54 243	98.30 278	98.40 313	97.86 130	99.89 94	96.53 274	99.72 175	99.56 122

Test_1112_low_res		96.99 313	96.55 324	98.31 260	99.35 172	95.47 300	95.84 387	99.53 100	91.51 423	96.80 380	98.48 307	91.36 350	99.83 189	96.58 263	99.53 254	99.62 86

DeepC-MVS	97.60 4	98.97 86	98.93 89	99.10 124	99.35 172	97.98 158	98.01 198	99.46 129	97.56 240	99.54 74	99.50 67	98.97 27	99.84 171	98.06 146	99.92 66	99.49 156
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 290	96.86 302	98.58 215	99.34 174	96.32 268	96.75 330	99.58 75	93.14 404	96.89 375	97.48 378	92.11 342	99.86 140	96.91 230	99.54 250	99.57 116

reproduce_model		99.15 56	98.97 86	99.67 4	99.33 175	99.44 10	98.15 170	99.47 125	99.12 91	99.52 80	99.32 110	98.31 87	99.90 78	97.78 169	99.73 167	99.66 74

MVSMamba_PlusPlus		98.83 105	98.98 85	98.36 255	99.32 176	96.58 257	98.90 83	99.41 157	99.75 11	98.72 233	99.50 67	96.17 239	99.94 41	99.27 62	99.78 142	98.57 368

fmvsm_s_conf0.5_n_4		99.01 79	99.22 52	98.38 251	99.31 177	95.48 298	97.56 270	99.73 42	98.87 130	99.75 43	99.27 118	98.80 39	99.86 140	99.80 15	99.90 82	99.81 37

SF-MVS		98.53 163	98.27 189	99.32 87	99.31 177	98.75 87	98.19 164	99.41 157	96.77 308	98.83 216	98.90 221	97.80 136	99.82 199	95.68 320	99.52 257	99.38 212

CPTT-MVS		97.84 249	97.36 273	99.27 95	99.31 177	98.46 111	98.29 153	99.27 220	94.90 372	97.83 318	98.37 317	94.90 284	99.84 171	93.85 371	99.54 250	99.51 148

UnsupCasMVSNet_eth		97.89 238	97.60 259	98.75 188	99.31 177	97.17 226	97.62 260	99.35 178	98.72 140	98.76 229	98.68 272	92.57 336	99.74 271	97.76 174	95.60 442	99.34 227

fmvsm_s_conf0.5_n_7		98.83 105	99.04 77	98.20 269	99.30 181	94.83 321	97.23 300	99.36 172	98.64 143	99.84 29	99.43 86	98.10 111	99.91 71	99.56 38	99.96 27	99.87 21

pmmvs-eth3d		98.47 171	98.34 178	98.86 167	99.30 181	97.76 185	97.16 309	99.28 217	95.54 354	99.42 102	99.19 140	97.27 179	99.63 329	97.89 158	99.97 20	99.20 269

mamv4		99.44 19	99.39 27	99.58 20	99.30 181	99.74 2	99.04 68	99.81 30	99.77 10	99.82 32	99.57 49	97.82 134	99.98 4	99.53 45	99.89 88	99.01 302

SymmetryMVS		98.05 224	97.71 249	99.09 128	99.29 184	97.83 174	98.28 154	97.64 376	99.24 73	98.80 222	98.85 234	89.76 364	99.94 41	98.04 148	99.50 266	99.49 156

Anonymous20231211		99.27 37	99.27 46	99.26 97	99.29 184	98.18 133	99.49 12	99.51 105	99.70 16	99.80 36	99.68 25	96.84 202	99.83 189	99.21 68	99.91 75	99.77 47

UnsupCasMVSNet_bld		97.30 288	96.92 298	98.45 242	99.28 186	96.78 248	96.20 363	99.27 220	95.42 358	98.28 282	98.30 325	93.16 322	99.71 285	94.99 334	97.37 418	98.87 329

EC-MVSNet		99.09 69	99.05 76	99.20 106	99.28 186	98.93 79	99.24 44	99.84 22	99.08 106	98.12 295	98.37 317	98.72 48	99.90 78	99.05 81	99.77 148	98.77 346

mamba_0408		98.80 112	98.88 95	98.55 225	99.27 188	96.50 260	98.00 199	99.60 70	98.93 123	99.22 146	98.84 239	98.59 61	99.89 94	97.74 175	99.72 175	99.27 247

mamba_test_0407_2		98.80 112	98.88 95	98.56 223	99.27 188	96.50 260	98.00 199	99.60 70	98.93 123	99.22 146	98.84 239	98.59 61	99.90 78	97.74 175	99.72 175	99.27 247

mamba_test_0407		98.86 102	98.96 88	98.55 225	99.27 188	96.50 260	98.04 190	99.66 58	99.09 102	99.22 146	99.02 184	98.79 41	99.87 131	97.87 163	99.72 175	99.27 247

reproduce-ours		99.09 69	98.90 92	99.67 4	99.27 188	99.49 6	98.00 199	99.42 153	99.05 109	99.48 88	99.27 118	98.29 89	99.89 94	97.61 182	99.71 184	99.62 86

our_new_method		99.09 69	98.90 92	99.67 4	99.27 188	99.49 6	98.00 199	99.42 153	99.05 109	99.48 88	99.27 118	98.29 89	99.89 94	97.61 182	99.71 184	99.62 86

DPE-MVS		98.59 153	98.26 190	99.57 21	99.27 188	99.15 52	97.01 314	99.39 162	97.67 227	99.44 97	98.99 199	97.53 160	99.89 94	95.40 328	99.68 199	99.66 74
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 248	98.18 202	96.87 366	99.27 188	91.16 415	95.53 397	99.25 226	99.10 99	99.41 104	99.35 100	93.10 324	99.96 14	98.65 111	99.94 48	99.49 156

v1192		98.60 151	98.66 126	98.41 247	99.27 188	95.88 283	97.52 275	99.36 172	97.41 258	99.33 121	99.20 139	96.37 233	99.82 199	99.57 36	99.92 66	99.55 129

N_pmnet		97.63 262	97.17 283	98.99 147	99.27 188	97.86 171	95.98 374	93.41 439	95.25 363	99.47 92	98.90 221	95.63 265	99.85 153	96.91 230	99.73 167	99.27 247

FPMVS		93.44 397	92.23 404	97.08 354	99.25 197	97.86 171	95.61 394	97.16 388	92.90 408	93.76 441	98.65 279	75.94 436	95.66 455	79.30 453	97.49 411	97.73 419

new-patchmatchnet		98.35 186	98.74 110	97.18 349	99.24 198	92.23 397	96.42 350	99.48 117	98.30 173	99.69 53	99.53 63	97.44 169	99.82 199	98.84 96	99.77 148	99.49 156

MCST-MVS		98.00 229	97.63 257	99.10 124	99.24 198	98.17 134	96.89 323	98.73 329	95.66 349	97.92 309	97.70 366	97.17 185	99.66 318	96.18 296	99.23 311	99.47 175

UniMVSNet (Re)		98.87 99	98.71 117	99.35 76	99.24 198	98.73 91	97.73 245	99.38 164	98.93 123	99.12 157	98.73 258	96.77 210	99.86 140	98.63 113	99.80 131	99.46 177

jason		97.45 276	97.35 274	97.76 302	99.24 198	93.93 358	95.86 384	98.42 347	94.24 387	98.50 264	98.13 335	94.82 288	99.91 71	97.22 206	99.73 167	99.43 189
jason: jason.
IterMVS		97.73 254	98.11 211	96.57 376	99.24 198	90.28 424	95.52 399	99.21 235	98.86 132	99.33 121	99.33 106	93.11 323	99.94 41	98.49 121	99.94 48	99.48 167
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 159	98.62 133	98.32 258	99.22 203	95.58 293	97.51 277	99.45 133	97.16 286	99.45 96	99.24 130	96.12 243	99.85 153	99.60 34	99.88 90	99.55 129

ITE_SJBPF				98.87 166	99.22 203	98.48 110		99.35 178	97.50 246	98.28 282	98.60 290	97.64 148	99.35 406	93.86 370	99.27 303	98.79 344

h-mvs33		97.77 252	97.33 276	99.10 124	99.21 205	97.84 173	98.35 150	98.57 339	99.11 92	98.58 253	99.02 184	88.65 375	99.96 14	98.11 141	96.34 434	99.49 156

v144192		98.54 161	98.57 141	98.45 242	99.21 205	95.98 280	97.63 259	99.36 172	97.15 288	99.32 127	99.18 144	95.84 260	99.84 171	99.50 48	99.91 75	99.54 133

APDe-MVS		98.99 82	98.79 106	99.60 15	99.21 205	99.15 52	98.87 88	99.48 117	97.57 238	99.35 117	99.24 130	97.83 131	99.89 94	97.88 161	99.70 191	99.75 56
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 91	98.81 105	99.28 92	99.21 205	98.45 112	98.46 138	99.33 190	99.63 29	99.48 88	99.15 154	97.23 182	99.75 266	97.17 208	99.66 212	99.63 85

SR-MVS-dyc-post		98.81 110	98.55 143	99.57 21	99.20 209	99.38 13	98.48 136	99.30 205	98.64 143	98.95 190	98.96 209	97.49 167	99.86 140	96.56 269	99.39 284	99.45 181

RE-MVS-def			98.58 140		99.20 209	99.38 13	98.48 136	99.30 205	98.64 143	98.95 190	98.96 209	97.75 139		96.56 269	99.39 284	99.45 181

v1921920		98.54 161	98.60 138	98.38 251	99.20 209	95.76 290	97.56 270	99.36 172	97.23 280	99.38 110	99.17 148	96.02 246	99.84 171	99.57 36	99.90 82	99.54 133

thisisatest0530		95.27 366	94.45 377	97.74 305	99.19 212	94.37 336	97.86 224	90.20 451	97.17 285	98.22 285	97.65 368	73.53 439	99.90 78	96.90 235	99.35 290	98.95 314

Anonymous20240529		98.93 91	98.87 97	99.12 120	99.19 212	98.22 131	99.01 70	98.99 284	99.25 72	99.54 74	99.37 95	97.04 191	99.80 223	97.89 158	99.52 257	99.35 225

APD-MVS_3200maxsize		98.84 104	98.61 137	99.53 38	99.19 212	99.27 27	98.49 133	99.33 190	98.64 143	99.03 177	98.98 204	97.89 128	99.85 153	96.54 273	99.42 281	99.46 177

HQP_MVS		97.99 232	97.67 251	98.93 158	99.19 212	97.65 193	97.77 237	99.27 220	98.20 186	97.79 321	97.98 349	94.90 284	99.70 290	94.42 352	99.51 259	99.45 181

plane_prior7					99.19 212	97.87 170

ab-mvs		98.41 176	98.36 175	98.59 214	99.19 212	97.23 218	99.32 26	98.81 315	97.66 228	98.62 245	99.40 94	96.82 205	99.80 223	95.88 307	99.51 259	98.75 349

F-COLMAP		97.30 288	96.68 315	99.14 118	99.19 212	98.39 114	97.27 299	99.30 205	92.93 407	96.62 386	98.00 347	95.73 263	99.68 303	92.62 398	98.46 379	99.35 225

SR-MVS		98.71 125	98.43 163	99.57 21	99.18 219	99.35 17	98.36 149	99.29 213	98.29 176	98.88 208	98.85 234	97.53 160	99.87 131	96.14 298	99.31 296	99.48 167

UniMVSNet_NR-MVSNet		98.86 102	98.68 123	99.40 68	99.17 220	98.74 88	97.68 249	99.40 160	99.14 90	99.06 165	98.59 291	96.71 216	99.93 52	98.57 116	99.77 148	99.53 142

LF4IMVS		97.90 236	97.69 250	98.52 233	99.17 220	97.66 192	97.19 308	99.47 125	96.31 327	97.85 317	98.20 332	96.71 216	99.52 371	94.62 344	99.72 175	98.38 385

SMA-MVS		98.40 178	98.03 220	99.51 48	99.16 222	99.21 33	98.05 188	99.22 234	94.16 389	98.98 182	99.10 166	97.52 162	99.79 236	96.45 279	99.64 215	99.53 142
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		98.82 108	98.63 131	99.39 69	99.16 222	98.74 88	97.54 273	99.25 226	98.84 135	99.06 165	98.76 255	96.76 212	99.93 52	98.57 116	99.77 148	99.50 151

NR-MVSNet		98.95 89	98.82 103	99.36 70	99.16 222	98.72 93	99.22 45	99.20 237	99.10 99	99.72 45	98.76 255	96.38 232	99.86 140	98.00 153	99.82 116	99.50 151

MVS_111021_LR		98.30 195	98.12 210	98.83 170	99.16 222	98.03 153	96.09 371	99.30 205	97.58 237	98.10 297	98.24 328	98.25 93	99.34 407	96.69 255	99.65 213	99.12 288

DSMNet-mixed		97.42 279	97.60 259	96.87 366	99.15 226	91.46 404	98.54 121	99.12 259	92.87 409	97.58 334	99.63 39	96.21 238	99.90 78	95.74 316	99.54 250	99.27 247

D2MVS		97.84 249	97.84 240	97.83 294	99.14 227	94.74 325	96.94 318	98.88 299	95.84 346	98.89 204	98.96 209	94.40 300	99.69 294	97.55 185	99.95 37	99.05 294

pmmvs5		97.64 261	97.49 265	98.08 279	99.14 227	95.12 314	96.70 333	99.05 270	93.77 396	98.62 245	98.83 241	93.23 320	99.75 266	98.33 130	99.76 160	99.36 221

SPE-MVS-test		99.13 63	99.09 72	99.26 97	99.13 229	98.97 73	99.31 30	99.88 14	99.44 50	98.16 290	98.51 300	98.64 55	99.93 52	98.91 90	99.85 101	98.88 328

VDD-MVS		98.56 155	98.39 170	99.07 131	99.13 229	98.07 148	98.59 115	97.01 391	99.59 35	99.11 158	99.27 118	94.82 288	99.79 236	98.34 128	99.63 218	99.34 227

save fliter					99.11 231	97.97 159	96.53 342	99.02 278	98.24 179

APD-MVS		98.10 218	97.67 251	99.42 64	99.11 231	98.93 79	97.76 240	99.28 217	94.97 370	98.72 233	98.77 253	97.04 191	99.85 153	93.79 372	99.54 250	99.49 156
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 132	98.71 117	98.62 208	99.10 233	96.37 266	97.23 300	98.87 301	99.20 80	99.19 151	98.99 199	97.30 176	99.85 153	98.77 102	99.79 137	99.65 79

EI-MVSNet		98.40 178	98.51 148	98.04 284	99.10 233	94.73 326	97.20 305	98.87 301	98.97 118	99.06 165	99.02 184	96.00 248	99.80 223	98.58 114	99.82 116	99.60 96

CVMVSNet		96.25 340	97.21 282	93.38 433	99.10 233	80.56 461	97.20 305	98.19 358	96.94 298	99.00 179	99.02 184	89.50 368	99.80 223	96.36 285	99.59 232	99.78 44

EI-MVSNet-Vis-set		98.68 137	98.70 120	98.63 206	99.09 236	96.40 265	97.23 300	98.86 306	99.20 80	99.18 155	98.97 206	97.29 178	99.85 153	98.72 106	99.78 142	99.64 80

HPM-MVS++		98.10 218	97.64 256	99.48 56	99.09 236	99.13 60	97.52 275	98.75 326	97.46 254	96.90 374	97.83 359	96.01 247	99.84 171	95.82 314	99.35 290	99.46 177

DP-MVS Recon		97.33 286	96.92 298	98.57 218	99.09 236	97.99 155	96.79 326	99.35 178	93.18 403	97.71 325	98.07 343	95.00 283	99.31 411	93.97 365	99.13 327	98.42 382

MVS_111021_HR		98.25 204	98.08 215	98.75 188	99.09 236	97.46 205	95.97 375	99.27 220	97.60 236	97.99 307	98.25 327	98.15 108	99.38 402	96.87 238	99.57 241	99.42 192

BP-MVS1		97.40 281	96.97 294	98.71 195	99.07 240	96.81 244	98.34 152	97.18 386	98.58 154	98.17 287	98.61 288	84.01 407	99.94 41	98.97 87	99.78 142	99.37 214

9.14			97.78 242		99.07 240		97.53 274	99.32 192	95.53 355	98.54 260	98.70 268	97.58 154	99.76 259	94.32 357	99.46 271

PAPM_NR		96.82 320	96.32 331	98.30 261	99.07 240	96.69 252	97.48 280	98.76 323	95.81 347	96.61 387	96.47 404	94.12 309	99.17 424	90.82 425	97.78 405	99.06 293

TAMVS		98.24 205	98.05 218	98.80 175	99.07 240	97.18 225	97.88 220	98.81 315	96.66 313	99.17 156	99.21 137	94.81 290	99.77 253	96.96 228	99.88 90	99.44 185

CLD-MVS		97.49 272	97.16 284	98.48 239	99.07 240	97.03 232	94.71 420	99.21 235	94.46 381	98.06 300	97.16 390	97.57 155	99.48 383	94.46 349	99.78 142	98.95 314
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 63	99.10 70	99.24 102	99.06 245	99.15 52	99.36 22	99.88 14	99.36 61	98.21 286	98.46 308	98.68 52	99.93 52	99.03 83	99.85 101	98.64 361

thres100view900		94.19 383	93.67 388	95.75 400	99.06 245	91.35 408	98.03 192	94.24 434	98.33 169	97.40 350	94.98 434	79.84 423	99.62 332	83.05 446	98.08 396	96.29 441

thres600view7		94.45 378	93.83 385	96.29 384	99.06 245	91.53 403	97.99 206	94.24 434	98.34 168	97.44 348	95.01 432	79.84 423	99.67 307	84.33 444	98.23 385	97.66 422

plane_prior1					99.05 248

YYNet1		97.60 263	97.67 251	97.39 342	99.04 249	93.04 381	95.27 406	98.38 350	97.25 274	98.92 200	98.95 213	95.48 272	99.73 277	96.99 224	98.74 360	99.41 195

MDA-MVSNet_test_wron		97.60 263	97.66 254	97.41 341	99.04 249	93.09 377	95.27 406	98.42 347	97.26 273	98.88 208	98.95 213	95.43 273	99.73 277	97.02 221	98.72 362	99.41 195

MIMVSNet		96.62 327	96.25 335	97.71 309	99.04 249	94.66 329	99.16 54	96.92 397	97.23 280	97.87 314	99.10 166	86.11 390	99.65 323	91.65 409	99.21 315	98.82 333

icg_test_0407_2		98.20 210	98.38 172	97.65 315	99.03 252	94.03 349	95.78 389	99.45 133	98.16 192	99.06 165	98.71 261	98.27 91	99.68 303	97.50 190	99.45 273	99.22 264

icg_test_0407		98.39 184	98.64 129	97.66 313	99.03 252	94.03 349	98.10 179	99.45 133	98.16 192	99.06 165	98.71 261	98.27 91	99.71 285	97.50 190	99.45 273	99.22 264

ICG_test_0404		98.07 222	98.20 197	97.69 310	99.03 252	94.03 349	96.67 334	99.45 133	98.16 192	98.03 304	98.71 261	96.80 208	99.82 199	97.50 190	99.45 273	99.22 264

icg_test_0403		98.34 187	98.56 142	97.66 313	99.03 252	94.03 349	97.98 207	99.45 133	98.16 192	98.89 204	98.71 261	97.90 126	99.74 271	97.50 190	99.45 273	99.22 264

PatchMatch-RL		97.24 294	96.78 309	98.61 211	99.03 252	97.83 174	96.36 353	99.06 267	93.49 401	97.36 354	97.78 360	95.75 262	99.49 380	93.44 381	98.77 359	98.52 370

viewmambaseed2359dif		98.19 211	98.26 190	97.99 287	99.02 257	95.03 317	96.59 339	99.53 100	96.21 330	99.00 179	98.99 199	97.62 150	99.61 339	97.62 181	99.72 175	99.33 232

GDP-MVS		97.50 269	97.11 288	98.67 199	99.02 257	96.85 242	98.16 169	99.71 45	98.32 171	98.52 263	98.54 295	83.39 411	99.95 26	98.79 98	99.56 244	99.19 274

ZD-MVS					99.01 259	98.84 82		99.07 266	94.10 391	98.05 302	98.12 337	96.36 234	99.86 140	92.70 397	99.19 319

CDPH-MVS		97.26 291	96.66 318	99.07 131	99.00 260	98.15 135	96.03 373	99.01 281	91.21 427	97.79 321	97.85 358	96.89 200	99.69 294	92.75 395	99.38 287	99.39 205

diffmvs		98.22 206	98.24 194	98.17 272	99.00 260	95.44 301	96.38 352	99.58 75	97.79 221	98.53 261	98.50 304	96.76 212	99.74 271	97.95 157	99.64 215	99.34 227
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		98.40 178	98.19 201	99.03 141	99.00 260	97.65 193	96.85 324	98.94 286	98.57 155	98.89 204	98.50 304	95.60 266	99.85 153	97.54 187	99.85 101	99.59 103

plane_prior6					98.99 263	97.70 191						94.90 284

xiu_mvs_v1_base_debu		97.86 243	98.17 203	96.92 363	98.98 264	93.91 359	96.45 346	99.17 249	97.85 216	98.41 272	97.14 392	98.47 71	99.92 62	98.02 150	99.05 333	96.92 434

xiu_mvs_v1_base		97.86 243	98.17 203	96.92 363	98.98 264	93.91 359	96.45 346	99.17 249	97.85 216	98.41 272	97.14 392	98.47 71	99.92 62	98.02 150	99.05 333	96.92 434

xiu_mvs_v1_base_debi		97.86 243	98.17 203	96.92 363	98.98 264	93.91 359	96.45 346	99.17 249	97.85 216	98.41 272	97.14 392	98.47 71	99.92 62	98.02 150	99.05 333	96.92 434

MVP-Stereo		98.08 221	97.92 234	98.57 218	98.96 267	96.79 245	97.90 218	99.18 245	96.41 323	98.46 267	98.95 213	95.93 257	99.60 341	96.51 275	98.98 347	99.31 239
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 178	98.68 123	97.54 330	98.96 267	97.99 155	97.88 220	99.36 172	98.20 186	99.63 64	99.04 181	98.76 44	95.33 457	96.56 269	99.74 164	99.31 239
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				98.91 162	98.94 269	97.76 185		98.76 323	87.58 444	96.75 382	98.10 339	94.80 291	99.78 247	92.73 396	99.00 342	99.20 269

USDC		97.41 280	97.40 269	97.44 339	98.94 269	93.67 369	95.17 409	99.53 100	94.03 393	98.97 186	99.10 166	95.29 275	99.34 407	95.84 313	99.73 167	99.30 242

tfpn200view9		94.03 387	93.44 390	95.78 399	98.93 271	91.44 406	97.60 265	94.29 432	97.94 208	97.10 360	94.31 441	79.67 425	99.62 332	83.05 446	98.08 396	96.29 441

testdata				98.09 276	98.93 271	95.40 303		98.80 317	90.08 435	97.45 347	98.37 317	95.26 276	99.70 290	93.58 377	98.95 350	99.17 281

thres400		94.14 385	93.44 390	96.24 387	98.93 271	91.44 406	97.60 265	94.29 432	97.94 208	97.10 360	94.31 441	79.67 425	99.62 332	83.05 446	98.08 396	97.66 422

TAPA-MVS	96.21 11	96.63 326	95.95 337	98.65 200	98.93 271	98.09 142	96.93 320	99.28 217	83.58 450	98.13 294	97.78 360	96.13 241	99.40 398	93.52 378	99.29 301	98.45 375
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 275	96.93 239	95.54 396	98.78 320	85.72 447	96.86 377	98.11 338	94.43 298			99.10 332	99.23 259

PVSNet_BlendedMVS		97.55 268	97.53 262	97.60 322	98.92 275	93.77 366	96.64 336	99.43 147	94.49 379	97.62 330	99.18 144	96.82 205	99.67 307	94.73 341	99.93 53	99.36 221

PVSNet_Blended		96.88 316	96.68 315	97.47 337	98.92 275	93.77 366	94.71 420	99.43 147	90.98 429	97.62 330	97.36 386	96.82 205	99.67 307	94.73 341	99.56 244	98.98 308

MSDG		97.71 256	97.52 263	98.28 263	98.91 278	96.82 243	94.42 430	99.37 168	97.65 229	98.37 277	98.29 326	97.40 171	99.33 409	94.09 363	99.22 312	98.68 359

Anonymous202405211		97.90 236	97.50 264	99.08 129	98.90 279	98.25 125	98.53 122	96.16 409	98.87 130	99.11 158	98.86 231	90.40 360	99.78 247	97.36 199	99.31 296	99.19 274

原ACMM1				98.35 256	98.90 279	96.25 270		98.83 314	92.48 413	96.07 404	98.10 339	95.39 274	99.71 285	92.61 399	98.99 344	99.08 290

GBi-Net		98.65 142	98.47 157	99.17 111	98.90 279	98.24 126	99.20 48	99.44 141	98.59 151	98.95 190	99.55 57	94.14 306	99.86 140	97.77 170	99.69 194	99.41 195

test1		98.65 142	98.47 157	99.17 111	98.90 279	98.24 126	99.20 48	99.44 141	98.59 151	98.95 190	99.55 57	94.14 306	99.86 140	97.77 170	99.69 194	99.41 195

FMVSNet2		98.49 169	98.40 167	98.75 188	98.90 279	97.14 229	98.61 113	99.13 258	98.59 151	99.19 151	99.28 116	94.14 306	99.82 199	97.97 155	99.80 131	99.29 244

OMC-MVS		97.88 240	97.49 265	99.04 140	98.89 284	98.63 95	96.94 318	99.25 226	95.02 368	98.53 261	98.51 300	97.27 179	99.47 386	93.50 380	99.51 259	99.01 302

VortexMVS		97.98 233	98.31 183	97.02 357	98.88 285	91.45 405	98.03 192	99.47 125	98.65 142	99.55 72	99.47 77	91.49 349	99.81 215	99.32 58	99.91 75	99.80 39

MVSFormer		98.26 201	98.43 163	97.77 299	98.88 285	93.89 362	99.39 20	99.56 89	99.11 92	98.16 290	98.13 335	93.81 314	99.97 7	99.26 63	99.57 241	99.43 189

lupinMVS		97.06 306	96.86 302	97.65 315	98.88 285	93.89 362	95.48 400	97.97 364	93.53 399	98.16 290	97.58 372	93.81 314	99.91 71	96.77 246	99.57 241	99.17 281

dmvs_re		95.98 348	95.39 358	97.74 305	98.86 288	97.45 206	98.37 148	95.69 421	97.95 206	96.56 388	95.95 413	90.70 357	97.68 451	88.32 434	96.13 438	98.11 397

DELS-MVS		98.27 199	98.20 197	98.48 239	98.86 288	96.70 251	95.60 395	99.20 237	97.73 224	98.45 268	98.71 261	97.50 164	99.82 199	98.21 135	99.59 232	98.93 319
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		97.89 238	97.98 225	97.60 322	98.86 288	94.35 337	96.21 362	99.44 141	97.45 256	99.06 165	98.88 228	97.99 121	99.28 417	94.38 356	99.58 237	99.18 277

LCM-MVSNet-Re		98.64 144	98.48 155	99.11 122	98.85 291	98.51 108	98.49 133	99.83 25	98.37 166	99.69 53	99.46 79	98.21 100	99.92 62	94.13 362	99.30 299	98.91 323

pmmvs4		97.58 266	97.28 277	98.51 234	98.84 292	96.93 239	95.40 404	98.52 342	93.60 398	98.61 247	98.65 279	95.10 280	99.60 341	96.97 227	99.79 137	98.99 307

NP-MVS					98.84 292	97.39 210					96.84 395

sss		97.21 296	96.93 296	98.06 281	98.83 294	95.22 310	96.75 330	98.48 344	94.49 379	97.27 356	97.90 355	92.77 332	99.80 223	96.57 265	99.32 294	99.16 284

PVSNet	93.40 17	95.67 357	95.70 343	95.57 404	98.83 294	88.57 431	92.50 447	97.72 369	92.69 411	96.49 396	96.44 405	93.72 317	99.43 394	93.61 375	99.28 302	98.71 352

MVE	83.40 22	92.50 410	91.92 412	94.25 420	98.83 294	91.64 402	92.71 446	83.52 460	95.92 344	86.46 458	95.46 426	95.20 277	95.40 456	80.51 451	98.64 371	95.73 449
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 391	93.91 383	93.39 432	98.82 297	81.72 459	97.76 240	95.28 423	98.60 150	96.54 389	96.66 399	65.85 455	99.62 332	96.65 258	98.99 344	98.82 333

ambc				98.24 267	98.82 297	95.97 281	98.62 112	99.00 283		99.27 134	99.21 137	96.99 196	99.50 377	96.55 272	99.50 266	99.26 253

旧先验1					98.82 297	97.45 206		98.76 323			98.34 321	95.50 271			99.01 341	99.23 259

test_vis1_rt		97.75 253	97.72 248	97.83 294	98.81 300	96.35 267	97.30 295	99.69 49	94.61 377	97.87 314	98.05 344	96.26 237	98.32 445	98.74 104	98.18 388	98.82 333

WTY-MVS		96.67 324	96.27 334	97.87 292	98.81 300	94.61 331	96.77 328	97.92 366	94.94 371	97.12 359	97.74 363	91.11 353	99.82 199	93.89 368	98.15 392	99.18 277

3Dnovator+	97.89 3	98.69 132	98.51 148	99.24 102	98.81 300	98.40 113	99.02 69	99.19 241	98.99 115	98.07 299	99.28 116	97.11 189	99.84 171	96.84 241	99.32 294	99.47 175

QAPM		97.31 287	96.81 308	98.82 171	98.80 303	97.49 201	99.06 65	99.19 241	90.22 433	97.69 327	99.16 150	96.91 199	99.90 78	90.89 424	99.41 282	99.07 292

VNet		98.42 175	98.30 184	98.79 178	98.79 304	97.29 214	98.23 160	98.66 333	99.31 66	98.85 213	98.80 247	94.80 291	99.78 247	98.13 140	99.13 327	99.31 239

DPM-MVS		96.32 336	95.59 349	98.51 234	98.76 305	97.21 222	94.54 429	98.26 353	91.94 418	96.37 397	97.25 388	93.06 326	99.43 394	91.42 414	98.74 360	98.89 325

3Dnovator	98.27 2	98.81 110	98.73 112	99.05 138	98.76 305	97.81 182	99.25 43	99.30 205	98.57 155	98.55 258	99.33 106	97.95 123	99.90 78	97.16 209	99.67 205	99.44 185

PLC	94.65 16	96.51 329	95.73 342	98.85 168	98.75 307	97.91 167	96.42 350	99.06 267	90.94 430	95.59 410	97.38 384	94.41 299	99.59 345	90.93 422	98.04 401	99.05 294
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 318	96.75 311	97.08 354	98.74 308	93.33 375	96.71 332	98.26 353	96.72 310	98.44 269	97.37 385	95.20 277	99.47 386	91.89 404	97.43 415	98.44 378

hse-mvs2		97.46 274	97.07 289	98.64 202	98.73 309	97.33 212	97.45 283	97.64 376	99.11 92	98.58 253	97.98 349	88.65 375	99.79 236	98.11 141	97.39 417	98.81 338

CDS-MVSNet		97.69 257	97.35 274	98.69 196	98.73 309	97.02 233	96.92 322	98.75 326	95.89 345	98.59 251	98.67 274	92.08 343	99.74 271	96.72 252	99.81 120	99.32 235
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 338	95.83 339	97.64 318	98.72 311	94.30 338	98.87 88	98.77 321	97.80 219	96.53 390	98.02 346	97.34 174	99.47 386	76.93 455	99.48 269	99.16 284

EIA-MVS		98.00 229	97.74 245	98.80 175	98.72 311	98.09 142	98.05 188	99.60 70	97.39 260	96.63 385	95.55 421	97.68 142	99.80 223	96.73 251	99.27 303	98.52 370

LFMVS		97.20 297	96.72 312	98.64 202	98.72 311	96.95 237	98.93 81	94.14 436	99.74 13	98.78 224	99.01 195	84.45 402	99.73 277	97.44 195	99.27 303	99.25 254

new_pmnet		96.99 313	96.76 310	97.67 311	98.72 311	94.89 320	95.95 379	98.20 356	92.62 412	98.55 258	98.54 295	94.88 287	99.52 371	93.96 366	99.44 280	98.59 367

Fast-Effi-MVS+		97.67 259	97.38 271	98.57 218	98.71 315	97.43 208	97.23 300	99.45 133	94.82 374	96.13 401	96.51 401	98.52 69	99.91 71	96.19 294	98.83 356	98.37 387

TEST9					98.71 315	98.08 146	95.96 377	99.03 275	91.40 424	95.85 407	97.53 374	96.52 225	99.76 259

train_agg		97.10 303	96.45 328	99.07 131	98.71 315	98.08 146	95.96 377	99.03 275	91.64 419	95.85 407	97.53 374	96.47 227	99.76 259	93.67 374	99.16 322	99.36 221

TSAR-MVS + GP.		98.18 213	97.98 225	98.77 185	98.71 315	97.88 169	96.32 356	98.66 333	96.33 325	99.23 145	98.51 300	97.48 168	99.40 398	97.16 209	99.46 271	99.02 301

FA-MVS(test-final)		96.99 313	96.82 306	97.50 334	98.70 319	94.78 323	99.34 23	96.99 392	95.07 367	98.48 266	99.33 106	88.41 378	99.65 323	96.13 300	98.92 353	98.07 400

AUN-MVS		96.24 342	95.45 354	98.60 213	98.70 319	97.22 220	97.38 287	97.65 374	95.95 343	95.53 417	97.96 353	82.11 419	99.79 236	96.31 287	97.44 414	98.80 343

our_test_3		97.39 282	97.73 247	96.34 382	98.70 319	89.78 427	94.61 426	98.97 285	96.50 318	99.04 174	98.85 234	95.98 253	99.84 171	97.26 204	99.67 205	99.41 195

ppachtmachnet_test		97.50 269	97.74 245	96.78 372	98.70 319	91.23 414	94.55 428	99.05 270	96.36 324	99.21 149	98.79 249	96.39 230	99.78 247	96.74 249	99.82 116	99.34 227

PCF-MVS	92.86 18	94.36 379	93.00 397	98.42 246	98.70 319	97.56 198	93.16 445	99.11 261	79.59 454	97.55 337	97.43 381	92.19 340	99.73 277	79.85 452	99.45 273	97.97 406
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 235	98.02 221	97.58 324	98.69 324	94.10 345	98.13 172	98.90 295	97.95 206	97.32 355	99.58 47	95.95 256	98.75 440	96.41 281	99.22 312	99.87 21

ETV-MVS		98.03 225	97.86 239	98.56 223	98.69 324	98.07 148	97.51 277	99.50 108	98.10 198	97.50 342	95.51 422	98.41 77	99.88 112	96.27 290	99.24 308	97.71 421

test_prior				98.95 155	98.69 324	97.95 163		99.03 275					99.59 345			99.30 242

mvsmamba		97.57 267	97.26 278	98.51 234	98.69 324	96.73 250	98.74 97	97.25 385	97.03 294	97.88 313	99.23 135	90.95 354	99.87 131	96.61 261	99.00 342	98.91 323

agg_prior					98.68 328	97.99 155		99.01 281		95.59 410			99.77 253

test_8					98.67 329	98.01 154	95.91 383	99.02 278	91.64 419	95.79 409	97.50 377	96.47 227	99.76 259

HQP-NCC					98.67 329		96.29 358		96.05 336	95.55 413

ACMP_Plane					98.67 329		96.29 358		96.05 336	95.55 413

CNVR-MVS		98.17 215	97.87 238	99.07 131	98.67 329	98.24 126	97.01 314	98.93 289	97.25 274	97.62 330	98.34 321	97.27 179	99.57 353	96.42 280	99.33 293	99.39 205

HQP-MVS		97.00 312	96.49 327	98.55 225	98.67 329	96.79 245	96.29 358	99.04 273	96.05 336	95.55 413	96.84 395	93.84 312	99.54 365	92.82 392	99.26 306	99.32 235

MM		98.22 206	97.99 224	98.91 162	98.66 334	96.97 234	97.89 219	94.44 430	99.54 38	98.95 190	99.14 157	93.50 318	99.92 62	99.80 15	99.96 27	99.85 29

test_fmvs1		97.72 255	97.94 231	97.07 356	98.66 334	92.39 392	97.68 249	99.81 30	95.20 366	99.54 74	99.44 84	91.56 348	99.41 397	99.78 19	99.77 148	99.40 204

balanced_conf03		98.63 146	98.72 114	98.38 251	98.66 334	96.68 253	98.90 83	99.42 153	98.99 115	98.97 186	99.19 140	95.81 261	99.85 153	98.77 102	99.77 148	98.60 364

thres200		93.72 393	93.14 395	95.46 408	98.66 334	91.29 410	96.61 338	94.63 429	97.39 260	96.83 378	93.71 444	79.88 422	99.56 356	82.40 449	98.13 393	95.54 450

wuyk23d		96.06 344	97.62 258	91.38 437	98.65 338	98.57 102	98.85 92	96.95 395	96.86 303	99.90 13	99.16 150	99.18 18	98.40 444	89.23 432	99.77 148	77.18 457

NCCC		97.86 243	97.47 268	99.05 138	98.61 339	98.07 148	96.98 316	98.90 295	97.63 230	97.04 364	97.93 354	95.99 252	99.66 318	95.31 329	98.82 358	99.43 189

DeepC-MVS_fast	96.85 6	98.30 195	98.15 207	98.75 188	98.61 339	97.23 218	97.76 240	99.09 264	97.31 268	98.75 230	98.66 277	97.56 156	99.64 326	96.10 301	99.55 248	99.39 205
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 395	92.09 406	97.75 303	98.60 341	94.40 335	97.32 293	95.26 424	97.56 240	96.79 381	95.50 423	53.57 463	99.77 253	95.26 330	98.97 348	99.08 290

thisisatest0515		94.12 386	93.16 394	96.97 361	98.60 341	92.90 382	93.77 441	90.61 449	94.10 391	96.91 371	95.87 416	74.99 437	99.80 223	94.52 347	99.12 330	98.20 393

GA-MVS		95.86 351	95.32 361	97.49 335	98.60 341	94.15 344	93.83 440	97.93 365	95.49 356	96.68 383	97.42 382	83.21 412	99.30 413	96.22 292	98.55 377	99.01 302

dmvs_testset		92.94 405	92.21 405	95.13 412	98.59 344	90.99 417	97.65 255	92.09 445	96.95 297	94.00 437	93.55 445	92.34 338	96.97 454	72.20 456	92.52 452	97.43 429

OPU-MVS				98.82 171	98.59 344	98.30 122	98.10 179				98.52 299	98.18 102	98.75 440	94.62 344	99.48 269	99.41 195

MSLP-MVS++		98.02 226	98.14 209	97.64 318	98.58 346	95.19 311	97.48 280	99.23 233	97.47 249	97.90 311	98.62 286	97.04 191	98.81 438	97.55 185	99.41 282	98.94 318

test12				98.93 158	98.58 346	97.83 174		98.66 333		96.53 390		95.51 270	99.69 294		99.13 327	99.27 247

CL-MVSNet_self_test		97.44 277	97.22 281	98.08 279	98.57 348	95.78 289	94.30 433	98.79 318	96.58 316	98.60 249	98.19 333	94.74 294	99.64 326	96.41 281	98.84 355	98.82 333

PS-MVSNAJ		97.08 305	97.39 270	96.16 393	98.56 349	92.46 390	95.24 408	98.85 309	97.25 274	97.49 343	95.99 412	98.07 112	99.90 78	96.37 283	98.67 370	96.12 446

CNLPA		97.17 300	96.71 313	98.55 225	98.56 349	98.05 152	96.33 355	98.93 289	96.91 300	97.06 363	97.39 383	94.38 301	99.45 391	91.66 408	99.18 321	98.14 396

xiu_mvs_v2_base		97.16 301	97.49 265	96.17 391	98.54 351	92.46 390	95.45 401	98.84 310	97.25 274	97.48 344	96.49 402	98.31 87	99.90 78	96.34 286	98.68 369	96.15 445

alignmvs		97.35 284	96.88 301	98.78 181	98.54 351	98.09 142	97.71 246	97.69 371	99.20 80	97.59 333	95.90 415	88.12 380	99.55 360	98.18 137	98.96 349	98.70 355

FE-MVS		95.66 358	94.95 371	97.77 299	98.53 353	95.28 307	99.40 19	96.09 412	93.11 405	97.96 308	99.26 123	79.10 429	99.77 253	92.40 401	98.71 364	98.27 391

Effi-MVS+		98.02 226	97.82 241	98.62 208	98.53 353	97.19 224	97.33 292	99.68 54	97.30 269	96.68 383	97.46 380	98.56 67	99.80 223	96.63 259	98.20 387	98.86 330

baseline1		95.96 349	95.44 355	97.52 332	98.51 355	93.99 356	98.39 146	96.09 412	98.21 182	98.40 276	97.76 362	86.88 382	99.63 329	95.42 327	89.27 455	98.95 314

MVS_Test		98.18 213	98.36 175	97.67 311	98.48 356	94.73 326	98.18 165	99.02 278	97.69 226	98.04 303	99.11 163	97.22 183	99.56 356	98.57 116	98.90 354	98.71 352

MGCFI-Net		98.34 187	98.28 186	98.51 234	98.47 357	97.59 197	98.96 77	99.48 117	99.18 87	97.40 350	95.50 423	98.66 53	99.50 377	98.18 137	98.71 364	98.44 378

BH-RMVSNet		96.83 318	96.58 323	97.58 324	98.47 357	94.05 346	96.67 334	97.36 380	96.70 312	97.87 314	97.98 349	95.14 279	99.44 393	90.47 427	98.58 376	99.25 254

sasdasda		98.34 187	98.26 190	98.58 215	98.46 359	97.82 179	98.96 77	99.46 129	99.19 84	97.46 345	95.46 426	98.59 61	99.46 389	98.08 144	98.71 364	98.46 372

canonicalmvs		98.34 187	98.26 190	98.58 215	98.46 359	97.82 179	98.96 77	99.46 129	99.19 84	97.46 345	95.46 426	98.59 61	99.46 389	98.08 144	98.71 364	98.46 372

MVS-HIRNet		94.32 380	95.62 346	90.42 438	98.46 359	75.36 462	96.29 358	89.13 453	95.25 363	95.38 419	99.75 16	92.88 329	99.19 423	94.07 364	99.39 284	96.72 439

PHI-MVS		98.29 198	97.95 229	99.34 79	98.44 362	99.16 48	98.12 176	99.38 164	96.01 340	98.06 300	98.43 311	97.80 136	99.67 307	95.69 319	99.58 237	99.20 269

DVP-MVS++		98.90 95	98.70 120	99.51 48	98.43 363	99.15 52	99.43 15	99.32 192	98.17 189	99.26 138	99.02 184	98.18 102	99.88 112	97.07 218	99.45 273	99.49 156

MSC_two_6792asdad				99.32 87	98.43 363	98.37 117		98.86 306					99.89 94	97.14 212	99.60 228	99.71 59

No_MVS				99.32 87	98.43 363	98.37 117		98.86 306					99.89 94	97.14 212	99.60 228	99.71 59

Fast-Effi-MVS+-dtu		98.27 199	98.09 212	98.81 173	98.43 363	98.11 139	97.61 264	99.50 108	98.64 143	97.39 352	97.52 376	98.12 110	99.95 26	96.90 235	98.71 364	98.38 385

OpenMVS_ROB	95.38 14	95.84 353	95.18 366	97.81 296	98.41 367	97.15 228	97.37 289	98.62 337	83.86 449	98.65 241	98.37 317	94.29 304	99.68 303	88.41 433	98.62 374	96.60 440

DeepPCF-MVS	96.93 5	98.32 192	98.01 222	99.23 104	98.39 368	98.97 73	95.03 413	99.18 245	96.88 301	99.33 121	98.78 251	98.16 106	99.28 417	96.74 249	99.62 221	99.44 185

Patchmatch-test		96.55 328	96.34 330	97.17 351	98.35 369	93.06 378	98.40 145	97.79 367	97.33 265	98.41 272	98.67 274	83.68 410	99.69 294	95.16 332	99.31 296	98.77 346

AdaColmap		97.14 302	96.71 313	98.46 241	98.34 370	97.80 183	96.95 317	98.93 289	95.58 353	96.92 369	97.66 367	95.87 259	99.53 367	90.97 421	99.14 325	98.04 401

OpenMVS	96.65 7	97.09 304	96.68 315	98.32 258	98.32 371	97.16 227	98.86 91	99.37 168	89.48 437	96.29 399	99.15 154	96.56 223	99.90 78	92.90 389	99.20 316	97.89 409

MG-MVS		96.77 321	96.61 320	97.26 347	98.31 372	93.06 378	95.93 380	98.12 361	96.45 322	97.92 309	98.73 258	93.77 316	99.39 400	91.19 419	99.04 336	99.33 232

test_yl		96.69 322	96.29 332	97.90 289	98.28 373	95.24 308	97.29 296	97.36 380	98.21 182	98.17 287	97.86 356	86.27 386	99.55 360	94.87 338	98.32 381	98.89 325

DCV-MVSNet		96.69 322	96.29 332	97.90 289	98.28 373	95.24 308	97.29 296	97.36 380	98.21 182	98.17 287	97.86 356	86.27 386	99.55 360	94.87 338	98.32 381	98.89 325

CHOSEN 280x420		95.51 363	95.47 352	95.65 403	98.25 375	88.27 434	93.25 444	98.88 299	93.53 399	94.65 428	97.15 391	86.17 388	99.93 52	97.41 197	99.93 53	98.73 351

SCA		96.41 335	96.66 318	95.67 401	98.24 376	88.35 433	95.85 386	96.88 398	96.11 334	97.67 328	98.67 274	93.10 324	99.85 153	94.16 358	99.22 312	98.81 338

DeepMVS_CX				93.44 431	98.24 376	94.21 341		94.34 431	64.28 457	91.34 451	94.87 438	89.45 369	92.77 458	77.54 454	93.14 451	93.35 453

MS-PatchMatch		97.68 258	97.75 244	97.45 338	98.23 378	93.78 365	97.29 296	98.84 310	96.10 335	98.64 242	98.65 279	96.04 245	99.36 403	96.84 241	99.14 325	99.20 269

BH-w/o		95.13 369	94.89 373	95.86 396	98.20 379	91.31 409	95.65 393	97.37 379	93.64 397	96.52 392	95.70 419	93.04 327	99.02 429	88.10 435	95.82 441	97.24 432

mvs_anonymous		97.83 251	98.16 206	96.87 366	98.18 380	91.89 399	97.31 294	98.90 295	97.37 262	98.83 216	99.46 79	96.28 236	99.79 236	98.90 91	98.16 391	98.95 314

miper_lstm_enhance		97.18 299	97.16 284	97.25 348	98.16 381	92.85 383	95.15 411	99.31 197	97.25 274	98.74 232	98.78 251	90.07 361	99.78 247	97.19 207	99.80 131	99.11 289

RRT-MVS		97.88 240	97.98 225	97.61 321	98.15 382	93.77 366	98.97 76	99.64 63	99.16 89	98.69 235	99.42 87	91.60 346	99.89 94	97.63 180	98.52 378	99.16 284

ET-MVSNet_ETH3D		94.30 382	93.21 393	97.58 324	98.14 383	94.47 334	94.78 419	93.24 441	94.72 375	89.56 453	95.87 416	78.57 432	99.81 215	96.91 230	97.11 426	98.46 372

ADS-MVSNet2		95.43 364	94.98 369	96.76 373	98.14 383	91.74 400	97.92 215	97.76 368	90.23 431	96.51 393	98.91 218	85.61 393	99.85 153	92.88 390	96.90 427	98.69 356

ADS-MVSNet		95.24 367	94.93 372	96.18 390	98.14 383	90.10 426	97.92 215	97.32 383	90.23 431	96.51 393	98.91 218	85.61 393	99.74 271	92.88 390	96.90 427	98.69 356

c3_l		97.36 283	97.37 272	97.31 343	98.09 386	93.25 376	95.01 414	99.16 252	97.05 291	98.77 227	98.72 260	92.88 329	99.64 326	96.93 229	99.76 160	99.05 294

FMVSNet3		97.50 269	97.24 280	98.29 262	98.08 387	95.83 286	97.86 224	98.91 294	97.89 213	98.95 190	98.95 213	87.06 381	99.81 215	97.77 170	99.69 194	99.23 259

PAPM		91.88 419	90.34 422	96.51 377	98.06 388	92.56 388	92.44 448	97.17 387	86.35 445	90.38 452	96.01 411	86.61 384	99.21 422	70.65 458	95.43 443	97.75 418

Effi-MVS+-dtu		98.26 201	97.90 236	99.35 76	98.02 389	99.49 6	98.02 195	99.16 252	98.29 176	97.64 329	97.99 348	96.44 229	99.95 26	96.66 257	98.93 352	98.60 364

eth_miper_zixun_eth		97.23 295	97.25 279	97.17 351	98.00 390	92.77 385	94.71 420	99.18 245	97.27 272	98.56 256	98.74 257	91.89 344	99.69 294	97.06 220	99.81 120	99.05 294

HY-MVS	95.94 13	95.90 350	95.35 360	97.55 329	97.95 391	94.79 322	98.81 96	96.94 396	92.28 416	95.17 421	98.57 293	89.90 363	99.75 266	91.20 418	97.33 422	98.10 398

UGNet		98.53 163	98.45 160	98.79 178	97.94 392	96.96 236	99.08 61	98.54 340	99.10 99	96.82 379	99.47 77	96.55 224	99.84 171	98.56 119	99.94 48	99.55 129
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		96.47 333	95.70 343	98.79 178	97.92 393	99.12 62	98.28 154	98.60 338	92.16 417	95.54 416	96.17 409	94.77 293	99.52 371	89.62 430	98.23 385	97.72 420
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		96.86 317	96.55 324	97.79 297	97.91 394	94.21 341	97.56 270	98.87 301	97.49 248	99.06 165	99.05 179	80.72 420	99.80 223	98.44 123	99.82 116	99.37 214

API-MVS		97.04 308	96.91 300	97.42 340	97.88 395	98.23 130	98.18 165	98.50 343	97.57 238	97.39 352	96.75 397	96.77 210	99.15 426	90.16 428	99.02 340	94.88 451

myMVS_eth3d28		92.92 406	92.31 402	94.77 415	97.84 396	87.59 438	96.19 364	96.11 411	97.08 290	94.27 431	93.49 447	66.07 454	98.78 439	91.78 406	97.93 404	97.92 408

miper_ehance_all_eth		97.06 306	97.03 291	97.16 353	97.83 397	93.06 378	94.66 423	99.09 264	95.99 341	98.69 235	98.45 309	92.73 334	99.61 339	96.79 243	99.03 337	98.82 333

cl____		97.02 309	96.83 305	97.58 324	97.82 398	94.04 348	94.66 423	99.16 252	97.04 292	98.63 243	98.71 261	88.68 374	99.69 294	97.00 222	99.81 120	99.00 306

DIV-MVS_self_test		97.02 309	96.84 304	97.58 324	97.82 398	94.03 349	94.66 423	99.16 252	97.04 292	98.63 243	98.71 261	88.69 372	99.69 294	97.00 222	99.81 120	99.01 302

CANet		97.87 242	97.76 243	98.19 271	97.75 400	95.51 296	96.76 329	99.05 270	97.74 223	96.93 368	98.21 331	95.59 267	99.89 94	97.86 165	99.93 53	99.19 274

UBG		93.25 400	92.32 401	96.04 395	97.72 401	90.16 425	95.92 382	95.91 416	96.03 339	93.95 439	93.04 450	69.60 444	99.52 371	90.72 426	97.98 402	98.45 375

mvsany_test1		97.60 263	97.54 261	97.77 299	97.72 401	95.35 304	95.36 405	97.13 389	94.13 390	99.71 47	99.33 106	97.93 124	99.30 413	97.60 184	98.94 351	98.67 360

PVSNet_0	89.98 21	91.15 420	90.30 423	93.70 428	97.72 401	84.34 452	90.24 451	97.42 378	90.20 434	93.79 440	93.09 449	90.90 356	98.89 437	86.57 441	72.76 458	97.87 411

CR-MVSNet		96.28 338	95.95 337	97.28 345	97.71 404	94.22 339	98.11 177	98.92 292	92.31 415	96.91 371	99.37 95	85.44 396	99.81 215	97.39 198	97.36 420	97.81 414

RPMNet		97.02 309	96.93 296	97.30 344	97.71 404	94.22 339	98.11 177	99.30 205	99.37 58	96.91 371	99.34 104	86.72 383	99.87 131	97.53 188	97.36 420	97.81 414

ETVMVS		92.60 409	91.08 418	97.18 349	97.70 406	93.65 371	96.54 340	95.70 419	96.51 317	94.68 427	92.39 453	61.80 460	99.50 377	86.97 438	97.41 416	98.40 383

pmmvs3		95.03 371	94.40 378	96.93 362	97.70 406	92.53 389	95.08 412	97.71 370	88.57 441	97.71 325	98.08 342	79.39 427	99.82 199	96.19 294	99.11 331	98.43 380

baseline2		93.73 392	92.83 398	96.42 380	97.70 406	91.28 411	96.84 325	89.77 452	93.96 395	92.44 447	95.93 414	79.14 428	99.77 253	92.94 388	96.76 431	98.21 392

WBMVS		95.18 368	94.78 374	96.37 381	97.68 409	89.74 428	95.80 388	98.73 329	97.54 243	98.30 278	98.44 310	70.06 442	99.82 199	96.62 260	99.87 94	99.54 133

tpm		94.67 376	94.34 380	95.66 402	97.68 409	88.42 432	97.88 220	94.90 426	94.46 381	96.03 406	98.56 294	78.66 430	99.79 236	95.88 307	95.01 445	98.78 345

CANet_DTU		97.26 291	97.06 290	97.84 293	97.57 411	94.65 330	96.19 364	98.79 318	97.23 280	95.14 422	98.24 328	93.22 321	99.84 171	97.34 200	99.84 105	99.04 298

testing11		93.08 403	92.02 408	96.26 386	97.56 412	90.83 420	96.32 356	95.70 419	96.47 321	92.66 446	93.73 443	64.36 458	99.59 345	93.77 373	97.57 409	98.37 387

tpm2		93.09 402	92.58 400	94.62 417	97.56 412	86.53 441	97.66 253	95.79 418	86.15 446	94.07 436	98.23 330	75.95 435	99.53 367	90.91 423	96.86 430	97.81 414

testing91		93.32 398	92.27 403	96.47 379	97.54 414	91.25 412	96.17 368	96.76 400	97.18 284	93.65 442	93.50 446	65.11 457	99.63 329	93.04 387	97.45 413	98.53 369

TR-MVS		95.55 361	95.12 367	96.86 369	97.54 414	93.94 357	96.49 345	96.53 405	94.36 386	97.03 366	96.61 400	94.26 305	99.16 425	86.91 440	96.31 435	97.47 428

testing99		93.04 404	91.98 411	96.23 388	97.53 416	90.70 422	96.35 354	95.94 415	96.87 302	93.41 443	93.43 448	63.84 459	99.59 345	93.24 385	97.19 423	98.40 383

1314		95.74 355	95.60 347	96.17 391	97.53 416	92.75 386	98.07 185	98.31 352	91.22 426	94.25 432	96.68 398	95.53 268	99.03 428	91.64 410	97.18 424	96.74 438

CostFormer		93.97 388	93.78 386	94.51 418	97.53 416	85.83 444	97.98 207	95.96 414	89.29 439	94.99 424	98.63 284	78.63 431	99.62 332	94.54 346	96.50 432	98.09 399

FMVSNet5		96.01 346	95.20 365	98.41 247	97.53 416	96.10 272	98.74 97	99.50 108	97.22 283	98.03 304	99.04 181	69.80 443	99.88 112	97.27 203	99.71 184	99.25 254

PMMVS		96.51 329	95.98 336	98.09 276	97.53 416	95.84 285	94.92 416	98.84 310	91.58 421	96.05 405	95.58 420	95.68 264	99.66 318	95.59 323	98.09 395	98.76 348

reproduce_monomvs		95.00 373	95.25 362	94.22 421	97.51 421	83.34 453	97.86 224	98.44 345	98.51 160	99.29 131	99.30 112	67.68 448	99.56 356	98.89 93	99.81 120	99.77 47

PAPR		95.29 365	94.47 376	97.75 303	97.50 422	95.14 313	94.89 417	98.71 331	91.39 425	95.35 420	95.48 425	94.57 296	99.14 427	84.95 443	97.37 418	98.97 311

testing222		91.96 417	90.37 421	96.72 374	97.47 423	92.59 387	96.11 370	94.76 427	96.83 304	92.90 445	92.87 451	57.92 461	99.55 360	86.93 439	97.52 410	98.00 405

PatchT		96.65 325	96.35 329	97.54 330	97.40 424	95.32 306	97.98 207	96.64 402	99.33 63	96.89 375	99.42 87	84.32 404	99.81 215	97.69 179	97.49 411	97.48 427

tpm cat1		93.29 399	93.13 396	93.75 427	97.39 425	84.74 447	97.39 286	97.65 374	83.39 451	94.16 433	98.41 312	82.86 415	99.39 400	91.56 412	95.35 444	97.14 433

PatchmatchNet		95.58 360	95.67 345	95.30 411	97.34 426	87.32 439	97.65 255	96.65 401	95.30 362	97.07 362	98.69 270	84.77 399	99.75 266	94.97 336	98.64 371	98.83 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 284	96.97 294	98.50 238	97.31 427	96.47 263	98.18 165	98.92 292	98.95 122	98.78 224	99.37 95	85.44 396	99.85 153	95.96 305	99.83 112	99.17 281

LS3D		98.63 146	98.38 172	99.36 70	97.25 428	99.38 13	99.12 60	99.32 192	99.21 78	98.44 269	98.88 228	97.31 175	99.80 223	96.58 263	99.34 292	98.92 320

IB-MVS	91.63 19	92.24 415	90.90 419	96.27 385	97.22 429	91.24 413	94.36 432	93.33 440	92.37 414	92.24 449	94.58 440	66.20 453	99.89 94	93.16 386	94.63 447	97.66 422
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		92.38 412	91.76 415	94.21 422	97.16 430	84.65 448	95.42 403	88.45 454	95.96 342	96.17 400	95.84 418	66.36 451	99.71 285	91.87 405	98.64 371	98.28 390

tpmrst		95.07 370	95.46 353	93.91 425	97.11 431	84.36 451	97.62 260	96.96 394	94.98 369	96.35 398	98.80 247	85.46 395	99.59 345	95.60 322	96.23 436	97.79 417

Syy-MVS		96.04 345	95.56 351	97.49 335	97.10 432	94.48 333	96.18 366	96.58 403	95.65 350	94.77 425	92.29 454	91.27 352	99.36 403	98.17 139	98.05 399	98.63 362

myMVS_eth3d		91.92 418	90.45 420	96.30 383	97.10 432	90.90 418	96.18 366	96.58 403	95.65 350	94.77 425	92.29 454	53.88 462	99.36 403	89.59 431	98.05 399	98.63 362

MDTV_nov1_ep13			95.22 364		97.06 434	83.20 454	97.74 243	96.16 409	94.37 385	96.99 367	98.83 241	83.95 408	99.53 367	93.90 367	97.95 403

MVS		93.19 401	92.09 406	96.50 378	96.91 435	94.03 349	98.07 185	98.06 363	68.01 456	94.56 430	96.48 403	95.96 255	99.30 413	83.84 445	96.89 429	96.17 443

E-PMN		94.17 384	94.37 379	93.58 429	96.86 436	85.71 445	90.11 453	97.07 390	98.17 189	97.82 320	97.19 389	84.62 401	98.94 433	89.77 429	97.68 408	96.09 447

JIA-IIPM		95.52 362	95.03 368	97.00 358	96.85 437	94.03 349	96.93 320	95.82 417	99.20 80	94.63 429	99.71 22	83.09 413	99.60 341	94.42 352	94.64 446	97.36 431

EMVS		93.83 390	94.02 382	93.23 434	96.83 438	84.96 446	89.77 454	96.32 407	97.92 210	97.43 349	96.36 408	86.17 388	98.93 434	87.68 436	97.73 407	95.81 448

cl22		95.79 354	95.39 358	96.98 360	96.77 439	92.79 384	94.40 431	98.53 341	94.59 378	97.89 312	98.17 334	82.82 416	99.24 419	96.37 283	99.03 337	98.92 320

WB-MVSnew		95.73 356	95.57 350	96.23 388	96.70 440	90.70 422	96.07 372	93.86 437	95.60 352	97.04 364	95.45 429	96.00 248	99.55 360	91.04 420	98.31 383	98.43 380

dp		93.47 396	93.59 389	93.13 435	96.64 441	81.62 460	97.66 253	96.42 406	92.80 410	96.11 402	98.64 282	78.55 433	99.59 345	93.31 383	92.18 454	98.16 395

MonoMVSNet		96.25 340	96.53 326	95.39 409	96.57 442	91.01 416	98.82 95	97.68 373	98.57 155	98.03 304	99.37 95	90.92 355	97.78 450	94.99 334	93.88 450	97.38 430

test-LLR		93.90 389	93.85 384	94.04 423	96.53 443	84.62 449	94.05 437	92.39 443	96.17 331	94.12 434	95.07 430	82.30 417	99.67 307	95.87 310	98.18 388	97.82 412

test-mter		92.33 414	91.76 415	94.04 423	96.53 443	84.62 449	94.05 437	92.39 443	94.00 394	94.12 434	95.07 430	65.63 456	99.67 307	95.87 310	98.18 388	97.82 412

TESTMET0.1,1		92.19 416	91.77 414	93.46 430	96.48 445	82.80 456	94.05 437	91.52 448	94.45 383	94.00 437	94.88 436	66.65 450	99.56 356	95.78 315	98.11 394	98.02 402

MVS_0304		97.44 277	97.01 293	98.72 194	96.42 446	96.74 249	97.20 305	91.97 446	98.46 163	98.30 278	98.79 249	92.74 333	99.91 71	99.30 60	99.94 48	99.52 145

miper_enhance_ethall		96.01 346	95.74 341	96.81 370	96.41 447	92.27 396	93.69 442	98.89 298	91.14 428	98.30 278	97.35 387	90.58 358	99.58 351	96.31 287	99.03 337	98.60 364

tpmvs		95.02 372	95.25 362	94.33 419	96.39 448	85.87 442	98.08 182	96.83 399	95.46 357	95.51 418	98.69 270	85.91 391	99.53 367	94.16 358	96.23 436	97.58 425

CMPMVS	75.91 23	96.29 337	95.44 355	98.84 169	96.25 449	98.69 94	97.02 313	99.12 259	88.90 440	97.83 318	98.86 231	89.51 367	98.90 436	91.92 403	99.51 259	98.92 320
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 377	93.69 387	96.99 359	96.05 450	93.61 373	94.97 415	93.49 438	96.17 331	97.57 336	94.88 436	82.30 417	99.01 431	93.60 376	94.17 449	98.37 387

EPMVS		93.72 393	93.27 392	95.09 414	96.04 451	87.76 436	98.13 172	85.01 459	94.69 376	96.92 369	98.64 282	78.47 434	99.31 411	95.04 333	96.46 433	98.20 393

cascas		94.79 375	94.33 381	96.15 394	96.02 452	92.36 394	92.34 449	99.26 225	85.34 448	95.08 423	94.96 435	92.96 328	98.53 443	94.41 355	98.59 375	97.56 426

MVStest1		95.86 351	95.60 347	96.63 375	95.87 453	91.70 401	97.93 212	98.94 286	98.03 200	99.56 69	99.66 32	71.83 440	98.26 446	99.35 56	99.24 308	99.91 13

gg-mvs-nofinetune		92.37 413	91.20 417	95.85 397	95.80 454	92.38 393	99.31 30	81.84 461	99.75 11	91.83 450	99.74 18	68.29 445	99.02 429	87.15 437	97.12 425	96.16 444

gm-plane-assit					94.83 455	81.97 458			88.07 443		94.99 433		99.60 341	91.76 407

GG-mvs-BLEND				94.76 416	94.54 456	92.13 398	99.31 30	80.47 462		88.73 456	91.01 456	67.59 449	98.16 449	82.30 450	94.53 448	93.98 452

UWE-MVS-28		90.22 421	89.28 424	93.02 436	94.50 457	82.87 455	96.52 343	87.51 455	95.21 365	92.36 448	96.04 410	71.57 441	98.25 447	72.04 457	97.77 406	97.94 407

EPNet_dtu		94.93 374	94.78 374	95.38 410	93.58 458	87.68 437	96.78 327	95.69 421	97.35 264	89.14 455	98.09 341	88.15 379	99.49 380	94.95 337	99.30 299	98.98 308
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 425	75.95 428	77.12 441	92.39 459	67.91 465	90.16 452	59.44 466	82.04 452	89.42 454	94.67 439	49.68 464	81.74 459	48.06 459	77.66 457	81.72 455

KD-MVS_2432*1600		92.87 407	91.99 409	95.51 406	91.37 460	89.27 429	94.07 435	98.14 359	95.42 358	97.25 357	96.44 405	67.86 446	99.24 419	91.28 416	96.08 439	98.02 402

miper_refine_blended		92.87 407	91.99 409	95.51 406	91.37 460	89.27 429	94.07 435	98.14 359	95.42 358	97.25 357	96.44 405	67.86 446	99.24 419	91.28 416	96.08 439	98.02 402

EPNet		96.14 343	95.44 355	98.25 265	90.76 462	95.50 297	97.92 215	94.65 428	98.97 118	92.98 444	98.85 234	89.12 370	99.87 131	95.99 303	99.68 199	99.39 205
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 426	68.95 429	70.34 442	87.68 463	65.00 466	91.11 450	59.90 465	69.02 455	74.46 460	88.89 457	48.58 465	68.03 461	28.61 460	72.33 459	77.99 456

test_method		79.78 423	79.50 426	80.62 439	80.21 464	45.76 467	70.82 455	98.41 349	31.08 459	80.89 459	97.71 364	84.85 398	97.37 452	91.51 413	80.03 456	98.75 349

tmp_tt		78.77 424	78.73 427	78.90 440	58.45 465	74.76 464	94.20 434	78.26 463	39.16 458	86.71 457	92.82 452	80.50 421	75.19 460	86.16 442	92.29 453	86.74 454

testmvs		17.12 428	20.53 431	6.87 444	12.05 466	4.20 469	93.62 443	6.73 467	4.62 462	10.41 462	24.33 459	8.28 467	3.56 463	9.69 462	15.07 460	12.86 459

test123		17.04 429	20.11 432	7.82 443	10.25 467	4.91 468	94.80 418	4.47 468	4.93 461	10.00 463	24.28 460	9.69 466	3.64 462	10.14 461	12.43 461	14.92 458

mmdepth		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

monomultidepth		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

test_blank		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

eth-test2					0.00 468

eth-test					0.00 468

uanet_test		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

DCPMVS		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

cdsmvs_eth3d_5k		24.66 427	32.88 430	0.00 445	0.00 468	0.00 470	0.00 456	99.10 262	0.00 463	0.00 464	97.58 372	99.21 17	0.00 464	0.00 463	0.00 462	0.00 460

pcd_1.5k_mvsjas		8.17 430	10.90 433	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	98.07 112	0.00 464	0.00 463	0.00 462	0.00 460

sosnet-low-res		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

sosnet		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uncertanet		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

Regformer		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

ab-mvs-re		8.12 431	10.83 434	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	97.48 378	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uanet		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

WAC-MVS						90.90 418								91.37 415

PC_three_1452									93.27 402	99.40 107	98.54 295	98.22 98	97.00 453	95.17 331	99.45 273	99.49 156

test_241102_TWO								99.30 205	98.03 200	99.26 138	99.02 184	97.51 163	99.88 112	96.91 230	99.60 228	99.66 74

test_0728_THIRD									98.17 189	99.08 163	99.02 184	97.89 128	99.88 112	97.07 218	99.71 184	99.70 64

GSMVS																98.81 338

sam_mvs1												84.74 400				98.81 338

sam_mvs												84.29 406

MTGPA								99.20 237

test_post1							97.59 267				20.48 462	83.07 414	99.66 318	94.16 358

test_post											21.25 461	83.86 409	99.70 290

patchmatchnet-post											98.77 253	84.37 403	99.85 153

MTMP							97.93 212	91.91 447

test9_res														93.28 384	99.15 324	99.38 212

agg_prior2														92.50 400	99.16 322	99.37 214

test_prior4						97.97 159	95.86 384

test_prior2							95.74 391		96.48 320	96.11 402	97.63 370	95.92 258		94.16 358	99.20 316

旧先验2							95.76 390		88.56 442	97.52 340			99.66 318	94.48 348

新几何2							95.93 380

无先验							95.74 391	98.74 328	89.38 438				99.73 277	92.38 402		99.22 264

原ACMM2							95.53 397

testdata2													99.79 236	92.80 394

segment_acmp												97.02 194

testdata1							95.44 402		96.32 326

plane_prior5								99.27 220					99.70 290	94.42 352	99.51 259	99.45 181

plane_prior4											97.98 349

plane_prior3						97.78 184			97.41 258	97.79 321

plane_prior2							97.77 237		98.20 186

plane_prior						97.65 193	97.07 312		96.72 310						99.36 288

n2								0.00 469

nn								0.00 469

door-mid								99.57 82

test11								98.87 301

door								99.41 157

HQP5-MVS						96.79 245

BP-MVS														92.82 392

HQP4-MVS										95.56 412			99.54 365			99.32 235

HQP3-MVS								99.04 273							99.26 306

HQP2-MVS												93.84 312

MDTV_nov1_ep13_2view						74.92 463	97.69 248		90.06 436	97.75 324		85.78 392		93.52 378		98.69 356

ACMMP++_ref															99.77 148

ACMMP++															99.68 199

Test By Simon												96.52 225

High-resolution multi-view benchmark