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 14	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 17	100.00 1	99.85 31

Gipuma		99.03 89	99.16 63	98.64 237	99.94 2	98.51 114	99.32 26	99.75 44	99.58 39	98.60 301	99.62 41	98.22 114	99.51 436	97.70 209	99.73 200	97.89 474
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 28	99.31 42	99.53 38	99.91 3	98.98 72	99.63 7	99.58 104	99.44 53	99.78 40	99.76 16	96.39 266	99.92 66	99.44 55	99.92 72	99.68 74

pmmvs6		99.67 3	99.70 3	99.60 16	99.90 4	99.27 26	99.53 9	99.76 40	99.64 26	99.84 31	99.83 4	99.50 9	99.87 136	99.36 58	99.92 72	99.64 87

PS-MVSNAJss		99.46 17	99.49 16	99.35 80	99.90 4	98.15 149	99.20 49	99.65 78	99.48 45	99.92 8	99.71 23	98.07 129	99.96 13	99.53 49	100.00 1	99.93 12

testf1		99.25 41	99.16 63	99.51 49	99.89 6	99.63 3	98.71 106	99.69 58	98.90 137	99.43 109	99.35 112	98.86 35	99.67 350	97.81 192	99.81 141	99.24 304

APD_test2		99.25 41	99.16 63	99.51 49	99.89 6	99.63 3	98.71 106	99.69 58	98.90 137	99.43 109	99.35 112	98.86 35	99.67 350	97.81 192	99.81 141	99.24 304

ANet_high		99.57 10	99.67 6	99.28 96	99.89 6	98.09 158	99.14 58	99.93 6	99.82 8	99.93 6	99.81 8	99.17 20	99.94 42	99.31 62	100.00 1	99.82 37

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 58	98.93 133	99.65 64	99.72 22	98.93 33	99.95 26	99.11 78	100.00 1	99.82 37

v7n		99.53 12	99.57 13	99.41 69	99.88 9	98.54 112	99.45 14	99.61 93	99.66 23	99.68 58	99.66 33	98.44 85	99.95 26	99.73 29	99.96 29	99.75 63

mvs_tets		99.63 6	99.67 6	99.49 55	99.88 9	98.61 104	99.34 23	99.71 49	99.27 75	99.90 14	99.74 19	99.68 4	99.97 6	99.55 44	99.99 5	99.88 21

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 74	99.87 12	98.13 152	98.08 197	99.95 2	99.45 51	99.98 2	99.75 17	99.80 1	99.97 6	99.82 13	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 57	99.87 12	98.61 104	99.28 40	99.66 72	99.09 111	99.89 18	99.68 26	99.53 7	99.97 6	99.50 51	99.99 5	99.87 23

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 92	99.39 20	99.56 122	99.11 101	99.70 52	99.73 21	99.00 27	99.97 6	99.26 66	99.98 12	99.89 17

MIMVSNet1		99.38 27	99.32 40	99.55 28	99.86 14	99.19 41	99.41 17	99.59 101	99.59 37	99.71 50	99.57 50	97.12 215	99.90 82	99.21 71	99.87 101	99.54 144

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 37	99.63 29	99.78 40	99.67 31	99.48 10	99.81 227	99.30 63	99.97 21	99.77 54
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	99.58 104	99.90 3	99.86 24	99.78 14	99.58 6	99.95 26	99.00 88	99.95 40	99.78 51

SixPastTwentyTwo		98.75 139	98.62 155	99.16 119	99.83 18	97.96 181	99.28 40	98.20 427	99.37 61	99.70 52	99.65 37	92.65 401	99.93 54	99.04 85	99.84 115	99.60 103

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 83	99.88 4	99.86 24	99.80 12	99.03 24	99.89 98	99.48 53	99.93 58	99.60 103

Baseline_NR-MVSNet		98.98 99	98.86 116	99.36 74	99.82 19	98.55 109	97.47 309	99.57 112	99.37 61	99.21 175	99.61 44	96.76 243	99.83 198	98.06 165	99.83 127	99.71 66

pm-mvs1		99.44 19	99.48 18	99.33 89	99.80 21	98.63 101	99.29 36	99.63 83	99.30 72	99.65 64	99.60 46	99.16 22	99.82 210	99.07 81	99.83 127	99.56 131

TransMVSNet (Re)		99.44 19	99.47 21	99.36 74	99.80 21	98.58 107	99.27 42	99.57 112	99.39 59	99.75 45	99.62 41	99.17 20	99.83 198	99.06 83	99.62 268	99.66 81

K. test v3		98.00 269	97.66 299	99.03 149	99.79 23	97.56 229	99.19 53	92.47 535	99.62 33	99.52 88	99.66 33	89.61 442	99.96 13	99.25 68	99.81 141	99.56 131

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 83	99.78 24	98.11 154	97.77 256	99.90 12	99.33 67	99.97 3	99.66 33	99.71 3	99.96 13	99.79 20	99.99 5	99.96 9

APD_test1		98.83 123	98.66 147	99.34 83	99.78 24	99.47 8	98.42 152	99.45 181	98.28 201	98.98 215	99.19 160	97.76 159	99.58 407	96.57 324	99.55 299	98.97 366

test_vis3_rt		99.14 63	99.17 61	99.07 139	99.78 24	98.38 124	98.92 83	99.94 3	97.80 249	99.91 12	99.67 31	97.15 213	98.91 506	99.76 24	99.56 294	99.92 13

EGC-MVSNET		85.24 514	80.54 517	99.34 83	99.77 27	99.20 38	99.08 62	99.29 264	12.08 557	20.84 560	99.42 90	97.55 179	99.85 159	97.08 266	99.72 209	98.96 369

Anonymous20240521		98.69 152	98.87 112	98.16 319	99.77 27	95.11 391	99.08 62	99.44 189	99.34 66	99.33 139	99.55 57	94.10 368	99.94 42	99.25 68	99.96 29	99.42 220

FC-MVSNet-test		99.27 38	99.25 53	99.34 83	99.77 27	98.37 126	99.30 35	99.57 112	99.61 35	99.40 118	99.50 69	97.12 215	99.85 159	99.02 87	99.94 52	99.80 46

test_vis1_n		98.31 228	98.50 176	97.73 368	99.76 30	94.17 425	98.68 109	99.91 10	96.31 378	99.79 39	99.57 50	92.85 397	99.42 461	99.79 20	99.84 115	99.60 103

test_fmvs3		99.12 70	99.41 26	98.25 306	99.76 30	95.07 392	99.05 68	99.94 3	97.78 253	99.82 35	99.84 3	98.56 74	99.71 313	99.96 1	99.96 29	99.97 4

XXY-MVS		99.14 63	99.15 68	99.10 131	99.76 30	97.74 213	98.85 93	99.62 90	98.48 182	99.37 126	99.49 75	98.75 48	99.86 145	98.20 153	99.80 153	99.71 66

TDRefinement		99.42 23	99.38 28	99.55 28	99.76 30	99.33 20	99.68 6	99.71 49	99.38 60	99.53 84	99.61 44	98.64 62	99.80 236	98.24 148	99.84 115	99.52 162

dtuonlycased		97.70 304	98.19 237	96.24 460	99.75 34	89.51 522	94.69 488	99.64 80	98.23 203	99.46 102	98.57 341	98.25 108	99.85 159	95.65 385	99.44 336	99.36 254

fmvsm_s_conf0.1_n_a		99.17 53	99.30 45	98.80 198	99.75 34	96.59 309	97.97 229	99.86 17	98.22 205	99.88 21	99.71 23	98.59 68	99.84 180	99.73 29	99.98 12	99.98 3

tt0805		98.69 152	98.62 155	98.90 179	99.75 34	99.30 21	99.15 57	96.97 472	98.86 143	98.87 250	97.62 440	98.63 64	98.96 502	99.41 57	98.29 463	98.45 438

test_vis1_n_1920		98.40 208	98.92 103	96.81 438	99.74 37	90.76 511	98.15 185	99.91 10	98.33 192	99.89 18	99.55 57	95.07 330	99.88 116	99.76 24	99.93 58	99.79 48

usedtu_dtu_shiyan2		98.99 95	98.86 116	99.39 72	99.73 38	98.71 98	99.05 68	99.47 172	99.16 95	99.49 95	99.12 187	96.34 272	99.93 54	98.05 167	99.36 348	99.54 144

FOURS1					99.73 38	99.67 2	99.43 15	99.54 133	99.43 55	99.26 158

PEN-MVS		99.41 24	99.34 36	99.62 9	99.73 38	99.14 57	99.29 36	99.54 133	99.62 33	99.56 75	99.42 90	98.16 123	99.96 13	98.78 103	99.93 58	99.77 54

lessismore_v0				98.97 163	99.73 38	97.53 232		86.71 553		99.37 126	99.52 68	89.93 437	99.92 66	98.99 89	99.72 209	99.44 211

SteuartSystems-ACMMP		98.79 132	98.54 168	99.54 31	99.73 38	99.16 48	98.23 174	99.31 248	97.92 239	98.90 238	98.90 258	98.00 135	99.88 116	96.15 360	99.72 209	99.58 118
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 252	98.15 244	98.22 312	99.73 38	95.15 388	97.36 323	99.68 65	94.45 460	98.99 214	99.27 132	96.87 232	99.94 42	97.13 263	99.91 81	99.57 125

Vis-MVSNet		99.34 30	99.36 33	99.27 99	99.73 38	98.26 138	99.17 54	99.78 37	99.11 101	99.27 154	99.48 76	98.82 39	99.95 26	98.94 92	99.93 58	99.59 110
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
fmvsm_l_mol_unc0.5_1		99.35 29	99.38 28	99.25 104	99.72 45	97.83 197	96.88 365	99.84 23	99.64 26	99.86 24	99.81 8	98.84 37	99.96 13	99.86 4	99.97 21	99.97 4

tt0320-xc		99.64 5	99.68 5	99.50 54	99.72 45	98.98 72	99.51 10	99.85 19	99.86 6	99.88 21	99.82 5	99.02 26	99.90 82	99.54 45	99.95 40	99.61 101

SSC-MVS		98.71 143	98.74 129	98.62 243	99.72 45	96.08 337	98.74 99	98.64 398	99.74 12	99.67 60	99.24 145	94.57 347	99.95 26	99.11 78	99.24 375	99.82 37

test_f		98.67 162	98.87 112	98.05 335	99.72 45	95.59 356	98.51 136	99.81 33	96.30 380	99.78 40	99.82 5	96.14 281	98.63 514	99.82 13	99.93 58	99.95 10

ACMH	96.65 7	99.25 41	99.24 54	99.26 101	99.72 45	98.38 124	99.07 65	99.55 127	98.30 196	99.65 64	99.45 85	99.22 17	99.76 274	98.44 132	99.77 173	99.64 87
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 57	99.71 50	98.94 79	99.54 8	99.83 27	99.87 5	99.89 18	99.82 5	98.75 48	99.90 82	99.54 45	99.95 40	99.59 110

fmvsm_s_conf0.1_n		99.16 57	99.33 38	98.64 237	99.71 50	96.10 332	97.87 242	99.85 19	98.56 178	99.90 14	99.68 26	98.69 58	99.85 159	99.72 31	99.98 12	99.97 4

PS-CasMVS		99.40 25	99.33 38	99.62 9	99.71 50	99.10 65	99.29 36	99.53 137	99.53 42	99.46 102	99.41 95	98.23 111	99.95 26	98.89 97	99.95 40	99.81 42

DTE-MVSNet		99.43 22	99.35 34	99.66 7	99.71 50	99.30 21	99.31 30	99.51 145	99.64 26	99.56 75	99.46 81	98.23 111	99.97 6	98.78 103	99.93 58	99.72 65

WR-MVS_H		99.33 31	99.22 55	99.65 8	99.71 50	99.24 29	99.32 26	99.55 127	99.46 50	99.50 94	99.34 116	97.30 202	99.93 54	98.90 95	99.93 58	99.77 54

HPM-MVS_fast		99.01 91	98.82 122	99.57 21	99.71 50	99.35 16	99.00 73	99.50 150	97.33 303	98.94 233	98.86 269	98.75 48	99.82 210	97.53 225	99.71 218	99.56 131

ACMH+	96.62 9	99.08 80	99.00 95	99.33 89	99.71 50	98.83 87	98.60 121	99.58 104	99.11 101	99.53 84	99.18 164	98.81 40	99.67 350	96.71 307	99.77 173	99.50 170

PMVS	91.26 20	97.86 286	97.94 269	97.65 377	99.71 50	97.94 184	98.52 131	98.68 393	98.99 125	97.52 405	99.35 112	97.41 195	98.18 521	91.59 497	99.67 247	96.82 511
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		99.15 58	99.22 55	98.94 168	99.70 58	97.49 233	98.62 118	99.67 71	98.85 146	99.34 136	99.54 63	98.47 78	99.81 227	98.93 93	99.91 81	99.51 166

KinetiMVS		99.03 89	99.02 91	99.03 149	99.70 58	97.48 236	98.43 149	99.29 264	99.70 15	99.60 72	99.07 200	96.13 283	99.94 42	99.42 56	99.87 101	99.68 74

FIs		99.14 63	99.09 83	99.29 95	99.70 58	98.28 136	99.13 59	99.52 143	99.48 45	99.24 168	99.41 95	96.79 240	99.82 210	98.69 113	99.88 96	99.76 59

VPNet		98.87 113	98.83 121	99.01 154	99.70 58	97.62 226	98.43 149	99.35 229	99.47 48	99.28 152	99.05 208	96.72 247	99.82 210	98.09 162	99.36 348	99.59 110

fmvsm_s_conf0.1_n_2		99.20 51	99.38 28	98.65 235	99.69 62	96.08 337	97.49 304	99.90 12	99.53 42	99.88 21	99.64 38	98.51 77	99.90 82	99.83 11	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 223	98.68 142	97.27 410	99.69 62	92.29 482	98.03 208	99.85 19	97.62 265	99.96 4	99.62 41	93.98 369	99.74 293	99.52 50	99.86 108	99.79 48

MP-MVS-pluss		98.57 179	98.23 231	99.60 16	99.69 62	99.35 16	97.16 346	99.38 215	94.87 446	98.97 219	98.99 232	98.01 134	99.88 116	97.29 246	99.70 229	99.58 118
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 40	98.96 165	99.68 65	97.35 246	98.84 95	99.48 160	99.69 17	99.63 67	99.68 26	99.03 24	99.96 13	97.97 178	99.92 72	99.57 125

sd_testset		99.28 37	99.31 42	99.19 113	99.68 65	98.06 168	99.41 17	99.30 256	99.69 17	99.63 67	99.68 26	99.25 16	99.96 13	97.25 249	99.92 72	99.57 125

test_fmvs1_n		98.09 260	98.28 220	97.52 395	99.68 65	93.47 458	98.63 116	99.93 6	95.41 431	99.68 58	99.64 38	91.88 416	99.48 445	99.82 13	99.87 101	99.62 93

CHOSEN 1792x2688		97.49 320	97.14 337	98.54 266	99.68 65	96.09 335	96.50 396	99.62 90	91.58 508	98.84 255	98.97 239	92.36 404	99.88 116	96.76 299	99.95 40	99.67 79

tfpnnormal		98.90 109	98.90 106	98.91 176	99.67 69	97.82 203	99.00 73	99.44 189	99.45 51	99.51 93	99.24 145	98.20 118	99.86 145	95.92 370	99.69 235	99.04 352

MTAPA		98.88 112	98.64 151	99.61 13	99.67 69	99.36 15	98.43 149	99.20 291	98.83 150	98.89 241	98.90 258	96.98 226	99.92 66	97.16 256	99.70 229	99.56 131

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 266	99.66 71	96.97 286	98.00 216	99.85 19	99.24 78	99.92 8	99.50 69	99.39 12	99.95 26	99.89 3	99.98 12	98.71 411

mvs5depth		99.30 34	99.59 12	98.44 282	99.65 72	95.35 375	99.82 3	99.94 3	99.83 7	99.42 113	99.94 2	98.13 126	99.96 13	99.63 37	99.96 29	100.00 1

fmvsm_l_conf0.5_n_a		99.19 52	99.27 48	98.94 168	99.65 72	97.05 281	97.80 251	99.76 40	98.70 160	99.78 40	99.11 189	98.79 44	99.95 26	99.85 7	99.96 29	99.83 34

WB-MVS		98.52 194	98.55 166	98.43 283	99.65 72	95.59 356	98.52 131	98.77 381	99.65 25	99.52 88	99.00 230	94.34 357	99.93 54	98.65 115	98.83 426	99.76 59

CP-MVSNet		99.21 48	99.09 83	99.56 26	99.65 72	98.96 78	99.13 59	99.34 235	99.42 56	99.33 139	99.26 138	97.01 224	99.94 42	98.74 108	99.93 58	99.79 48

HPM-MVS		98.79 132	98.53 170	99.59 20	99.65 72	99.29 23	99.16 55	99.43 195	96.74 356	98.61 298	98.38 367	98.62 65	99.87 136	96.47 336	99.67 247	99.59 110
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 171	98.36 205	99.42 67	99.65 72	99.42 10	98.55 127	99.57 112	97.72 258	98.90 238	99.26 138	96.12 285	99.52 430	95.72 381	99.71 218	99.32 275

NormalMVS		98.26 236	97.97 265	99.15 124	99.64 78	97.83 197	98.28 168	99.43 195	99.24 78	98.80 264	98.85 272	89.76 440	99.94 42	98.04 168	99.67 247	99.68 74

lecture		99.25 41	99.12 72	99.62 9	99.64 78	99.40 11	98.89 88	99.51 145	99.19 90	99.37 126	99.25 143	98.36 91	99.88 116	98.23 150	99.67 247	99.59 110

fmvsm_l_conf0.5_n		99.21 48	99.28 47	99.02 152	99.64 78	97.28 258	97.82 247	99.76 40	98.73 152	99.82 35	99.09 198	98.81 40	99.95 26	99.86 4	99.96 29	99.83 34

test_fmvsmconf_n		99.44 19	99.48 18	99.31 94	99.64 78	98.10 157	97.68 271	99.84 23	99.29 73	99.92 8	99.57 50	99.60 5	99.96 13	99.74 28	99.98 12	99.89 17

TSAR-MVS + MP.		98.63 168	98.49 181	99.06 145	99.64 78	97.90 190	98.51 136	98.94 345	96.96 336	99.24 168	98.89 264	97.83 152	99.81 227	96.88 289	99.49 324	99.48 189
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 126	98.72 133	99.12 127	99.64 78	98.54 112	97.98 225	99.68 65	97.62 265	99.34 136	99.18 164	97.54 181	99.77 268	97.79 194	99.74 196	99.04 352

Elysia		99.15 58	99.14 69	99.18 114	99.63 84	97.92 186	98.50 138	99.43 195	99.67 20	99.70 52	99.13 183	96.66 250	99.98 4	99.54 45	99.96 29	99.64 87

StellarMVS		99.15 58	99.14 69	99.18 114	99.63 84	97.92 186	98.50 138	99.43 195	99.67 20	99.70 52	99.13 183	96.66 250	99.98 4	99.54 45	99.96 29	99.64 87

KD-MVS_self_test		99.25 41	99.18 60	99.44 65	99.63 84	99.06 70	98.69 108	99.54 133	99.31 70	99.62 70	99.53 65	97.36 199	99.86 145	99.24 70	99.71 218	99.39 234

EU-MVSNet		97.66 308	98.50 176	95.13 501	99.63 84	85.84 537	98.35 162	98.21 426	98.23 203	99.54 80	99.46 81	95.02 331	99.68 345	98.24 148	99.87 101	99.87 23

HyFIR lowres test		97.19 350	96.60 381	98.96 165	99.62 88	97.28 258	95.17 472	99.50 150	94.21 466	99.01 209	98.32 377	86.61 463	99.99 2	97.10 265	99.84 115	99.60 103

E5new		99.05 84	99.11 75	98.85 183	99.60 89	97.30 252	98.42 152	99.63 83	98.73 152	99.26 158	99.39 101	98.71 52	99.70 322	98.43 134	99.84 115	99.54 144

E6new		99.05 84	99.11 75	98.85 183	99.60 89	97.30 252	98.42 152	99.63 83	98.73 152	99.26 158	99.39 101	98.71 52	99.70 322	98.43 134	99.84 115	99.54 144

E6		99.05 84	99.11 75	98.85 183	99.60 89	97.30 252	98.42 152	99.63 83	98.73 152	99.26 158	99.39 101	98.71 52	99.70 322	98.43 134	99.84 115	99.54 144

E5		99.05 84	99.11 75	98.85 183	99.60 89	97.30 252	98.42 152	99.63 83	98.73 152	99.26 158	99.39 101	98.71 52	99.70 322	98.43 134	99.84 115	99.54 144

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 161	99.59 93	97.18 272	97.44 313	99.83 27	99.56 40	99.91 12	99.34 116	99.36 13	99.93 54	99.83 11	99.98 12	99.85 31

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 83	99.59 93	98.21 146	97.82 247	99.84 23	99.41 58	99.92 8	99.41 95	99.51 8	99.95 26	99.84 10	99.97 21	99.87 23

aaatest				99.45 64	99.58 95	98.93 80	98.68 109	99.60 95	96.46 372	99.53 84	98.77 292		99.83 198	96.67 313	99.64 259	99.58 118

MED-MVS		99.01 91	98.84 120	99.52 44	99.58 95	98.93 80	98.68 109	99.60 95	98.85 146	99.53 84	99.16 171	97.87 150	99.83 198	96.67 313	99.62 268	99.81 42

TestfortrainingZip a		99.09 74	98.92 103	99.61 13	99.58 95	99.17 43	98.68 109	99.27 271	98.85 146	99.61 71	99.16 171	97.14 214	99.86 145	98.39 139	99.57 290	99.81 42

FE-MVSNET		98.59 176	98.50 176	98.87 180	99.58 95	97.30 252	98.08 197	99.74 45	96.94 338	98.97 219	99.10 192	96.94 228	99.74 293	97.33 242	99.86 108	99.55 138

mmtdpeth		99.30 34	99.42 25	98.92 174	99.58 95	96.89 294	99.48 13	99.92 8	99.92 2	98.26 343	99.80 12	98.33 97	99.91 75	99.56 42	99.95 40	99.97 4

ACMMP_NAP		98.75 139	98.48 182	99.57 21	99.58 95	99.29 23	97.82 247	99.25 279	96.94 338	98.78 266	99.12 187	98.02 133	99.84 180	97.13 263	99.67 247	99.59 110

nrg030		99.40 25	99.35 34	99.54 31	99.58 95	99.13 60	98.98 76	99.48 160	99.68 19	99.46 102	99.26 138	98.62 65	99.73 300	99.17 75	99.92 72	99.76 59

VDDNet		98.21 244	97.95 266	99.01 154	99.58 95	97.74 213	99.01 71	97.29 459	99.67 20	98.97 219	99.50 69	90.45 434	99.80 236	97.88 185	99.20 384	99.48 189

COLMAP_ROB	96.50 10	98.99 95	98.85 119	99.41 69	99.58 95	99.10 65	98.74 99	99.56 122	99.09 111	99.33 139	99.19 160	98.40 87	99.72 311	95.98 368	99.76 189	99.42 220
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	98.99 157	99.57 104	97.73 215	97.93 231	99.83 27	99.22 81	99.93 6	99.30 126	99.42 11	99.96 13	99.85 7	99.99 5	99.29 286

ZNCC-MVS		98.68 158	98.40 194	99.54 31	99.57 104	99.21 32	98.46 146	99.29 264	97.28 310	98.11 355	98.39 365	98.00 135	99.87 136	96.86 292	99.64 259	99.55 138

MSP-MVS		98.40 208	98.00 260	99.61 13	99.57 104	99.25 28	98.57 125	99.35 229	97.55 276	99.31 148	97.71 433	94.61 346	99.88 116	96.14 361	99.19 387	99.70 71
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		98.32 224	98.39 197	98.13 321	99.57 104	95.54 359	97.78 253	99.49 158	97.37 300	99.19 177	97.65 437	98.96 30	99.49 441	96.50 335	98.99 414	99.34 264

MP-MVS		98.46 200	98.09 249	99.54 31	99.57 104	99.22 31	98.50 138	99.19 295	97.61 268	97.58 399	98.66 322	97.40 196	99.88 116	94.72 412	99.60 277	99.54 144
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 143	98.46 186	99.47 61	99.57 104	98.97 74	98.23 174	99.48 160	96.60 363	99.10 190	99.06 201	98.71 52	99.83 198	95.58 390	99.78 165	99.62 93

LGP-MVS_train				99.47 61	99.57 104	98.97 74		99.48 160	96.60 363	99.10 190	99.06 201	98.71 52	99.83 198	95.58 390	99.78 165	99.62 93

IS-MVSNet		98.19 247	97.90 275	99.08 137	99.57 104	97.97 178	99.31 30	98.32 420	99.01 124	98.98 215	99.03 213	91.59 418	99.79 250	95.49 393	99.80 153	99.48 189

viewdifsd2359ckpt11		98.84 120	99.04 88	98.24 308	99.56 112	95.51 361	97.38 318	99.70 55	99.16 95	99.57 73	99.40 98	98.26 106	99.71 313	98.55 126	99.82 134	99.50 170

viewmsd2359difaftdt		98.84 120	99.04 88	98.24 308	99.56 112	95.51 361	97.38 318	99.70 55	99.16 95	99.57 73	99.40 98	98.26 106	99.71 313	98.55 126	99.82 134	99.50 170

dcpmvs_2		98.78 134	99.11 75	97.78 358	99.56 112	93.67 453	99.06 66	99.86 17	99.50 44	99.66 61	99.26 138	97.21 210	99.99 2	98.00 173	99.91 81	99.68 74

test_0402		98.76 138	98.71 136	98.93 171	99.56 112	98.14 151	98.45 148	99.34 235	99.28 74	98.95 225	98.91 255	98.34 96	99.79 250	95.63 386	99.91 81	98.86 387

EPP-MVSNet		98.30 229	98.04 256	99.07 139	99.56 112	97.83 197	99.29 36	98.07 434	99.03 122	98.59 303	99.13 183	92.16 409	99.90 82	96.87 290	99.68 241	99.49 178

ACMMP		98.75 139	98.50 176	99.52 44	99.56 112	99.16 48	98.87 89	99.37 219	97.16 326	98.82 260	99.01 226	97.71 162	99.87 136	96.29 352	99.69 235	99.54 144
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
casdiffseed414692147		99.09 74	99.12 72	99.01 154	99.55 118	97.91 188	98.30 166	99.68 65	99.04 120	99.19 177	99.37 105	98.98 28	99.61 391	98.13 157	99.83 127	99.50 170

fmvsm_s_conf0.5_n_a		99.10 73	99.20 59	98.78 205	99.55 118	96.59 309	97.79 252	99.82 32	98.21 207	99.81 37	99.53 65	98.46 83	99.84 180	99.70 34	99.97 21	99.90 16

fmvsm_s_conf0.5_n		99.09 74	99.26 51	98.61 247	99.55 118	96.09 335	97.74 264	99.81 33	98.55 179	99.85 28	99.55 57	98.60 67	99.84 180	99.69 36	99.98 12	99.89 17

FMVSNet1		99.17 53	99.17 61	99.17 116	99.55 118	98.24 140	99.20 49	99.44 189	99.21 83	99.43 109	99.55 57	97.82 155	99.86 145	98.42 138	99.89 95	99.41 224

Vis-MVSNet (Re-imp)		97.46 322	97.16 334	98.34 296	99.55 118	96.10 332	98.94 81	98.44 413	98.32 194	98.16 349	98.62 334	88.76 447	99.73 300	93.88 439	99.79 160	99.18 326

ACMM	96.08 12	98.91 107	98.73 131	99.48 57	99.55 118	99.14 57	98.07 201	99.37 219	97.62 265	99.04 204	98.96 243	98.84 37	99.79 250	97.43 236	99.65 257	99.49 178
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
hybridcas		99.08 80	99.13 71	98.92 174	99.54 124	97.61 227	98.22 178	99.66 72	99.27 75	99.40 118	99.24 145	98.47 78	99.70 322	98.59 119	99.80 153	99.46 201

test_fmvs2		98.70 148	98.97 99	97.89 348	99.54 124	94.05 430	98.55 127	99.92 8	96.78 354	99.72 48	99.78 14	96.60 255	99.67 350	99.91 2	99.90 89	99.94 11

mPP-MVS		98.64 166	98.34 209	99.54 31	99.54 124	99.17 43	98.63 116	99.24 285	97.47 285	98.09 357	98.68 316	97.62 171	99.89 98	96.22 355	99.62 268	99.57 125

XVG-ACMP-BASELINE		98.56 181	98.34 209	99.22 110	99.54 124	98.59 106	97.71 267	99.46 177	97.25 314	98.98 215	98.99 232	97.54 181	99.84 180	95.88 371	99.74 196	99.23 306

Casviewmamba		99.12 70	99.12 72	99.09 135	99.53 128	98.08 162	98.34 164	99.66 72	99.35 65	99.35 131	99.23 151	98.39 89	99.72 311	98.46 130	99.81 141	99.47 198

viewmacassd2359aftdt		98.86 117	98.87 112	98.83 191	99.53 128	97.32 251	97.70 269	99.64 80	98.22 205	99.25 166	99.27 132	98.40 87	99.61 391	97.98 177	99.87 101	99.55 138

region2R		98.69 152	98.40 194	99.54 31	99.53 128	99.17 43	98.52 131	99.31 248	97.46 290	98.44 325	98.51 349	97.83 152	99.88 116	96.46 337	99.58 286	99.58 118

PGM-MVS		98.66 163	98.37 203	99.55 28	99.53 128	99.18 42	98.23 174	99.49 158	97.01 335	98.69 281	98.88 266	98.00 135	99.89 98	95.87 374	99.59 281	99.58 118

E4		98.87 113	98.88 109	98.81 195	99.52 132	97.23 262	97.62 282	99.61 93	98.58 173	99.18 182	99.33 119	98.29 100	99.69 332	97.99 176	99.83 127	99.52 162

Patchmatch-RL test		97.26 342	97.02 344	97.99 341	99.52 132	95.53 360	96.13 425	99.71 49	97.47 285	99.27 154	99.16 171	84.30 489	99.62 383	97.89 182	99.77 173	98.81 396

ACMMPR		98.70 148	98.42 192	99.54 31	99.52 132	99.14 57	98.52 131	99.31 248	97.47 285	98.56 309	98.54 344	97.75 160	99.88 116	96.57 324	99.59 281	99.58 118

DKM-HiRes		98.14 255	97.80 283	99.16 119	99.51 135	98.40 121	96.70 377	99.63 83	97.55 276	97.45 413	98.74 299	93.27 383	99.54 423	97.78 195	99.55 299	99.53 158

fmvsm_s_conf0.5_n_9		99.17 53	99.38 28	98.53 268	99.51 135	95.82 350	97.62 282	99.78 37	99.72 14	99.90 14	99.48 76	98.66 60	99.89 98	99.85 7	99.93 58	99.89 17

AstraMVS		98.16 254	98.07 254	98.41 286	99.51 135	95.86 347	98.00 216	95.14 513	98.97 128	99.43 109	99.24 145	93.25 384	99.84 180	99.21 71	99.87 101	99.54 144

fmvsm_s_conf0.5_n_8		99.13 67	99.26 51	98.74 218	99.51 135	96.44 322	97.65 277	99.65 78	99.66 23	99.78 40	99.48 76	97.92 143	99.93 54	99.72 31	99.95 40	99.87 23

GST-MVS		98.61 172	98.30 217	99.52 44	99.51 135	99.20 38	98.26 172	99.25 279	97.44 293	98.67 285	98.39 365	97.68 163	99.85 159	96.00 366	99.51 312	99.52 162

Anonymous20231206		98.21 244	98.21 232	98.20 313	99.51 135	95.43 371	98.13 187	99.32 243	96.16 387	98.93 234	98.82 282	96.00 290	99.83 198	97.32 244	99.73 200	99.36 254

ACMP	95.32 15	98.41 205	98.09 249	99.36 74	99.51 135	98.79 90	97.68 271	99.38 215	95.76 412	98.81 262	98.82 282	98.36 91	99.82 210	94.75 409	99.77 173	99.48 189
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
RoMa-HiRes		98.68 158	98.52 171	99.16 119	99.50 142	98.35 130	98.01 214	99.71 49	96.94 338	99.35 131	98.66 322	96.38 268	99.63 378	98.39 139	99.71 218	99.48 189

LuminaMVS		98.39 215	98.20 233	98.98 161	99.50 142	97.49 233	97.78 253	97.69 443	98.75 151	99.49 95	99.25 143	92.30 407	99.94 42	99.14 76	99.88 96	99.50 170

DVP-MVS		98.77 137	98.52 171	99.52 44	99.50 142	99.21 32	98.02 211	98.84 370	97.97 233	99.08 192	99.02 214	97.61 173	99.88 116	96.99 274	99.63 264	99.48 189
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 16	99.50 142	99.23 30	98.02 211	99.32 243					99.88 116	96.99 274	99.63 264	99.68 74

test0726					99.50 142	99.21 32	98.17 183	99.35 229	97.97 233	99.26 158	99.06 201	97.61 173

AllTest		98.44 203	98.20 233	99.16 119	99.50 142	98.55 109	98.25 173	99.58 104	96.80 352	98.88 245	99.06 201	97.65 166	99.57 409	94.45 419	99.61 275	99.37 246

TestCases				99.16 119	99.50 142	98.55 109		99.58 104	96.80 352	98.88 245	99.06 201	97.65 166	99.57 409	94.45 419	99.61 275	99.37 246

XVG-OURS		98.53 190	98.34 209	99.11 129	99.50 142	98.82 89	95.97 435	99.50 150	97.30 308	99.05 202	98.98 237	99.35 14	99.32 476	95.72 381	99.68 241	99.18 326

EG-PatchMatch MVS		98.99 95	99.01 93	98.94 168	99.50 142	97.47 237	98.04 206	99.59 101	98.15 223	99.40 118	99.36 111	98.58 73	99.76 274	98.78 103	99.68 241	99.59 110

fmvsm_s_conf0.5_n_2		99.14 63	99.31 42	98.63 241	99.49 151	96.08 337	97.38 318	99.81 33	99.48 45	99.84 31	99.57 50	98.46 83	99.89 98	99.82 13	99.97 21	99.91 14

SED-MVS		98.91 107	98.72 133	99.49 55	99.49 151	99.17 43	98.10 194	99.31 248	98.03 229	99.66 61	99.02 214	98.36 91	99.88 116	96.91 282	99.62 268	99.41 224

IU-MVS					99.49 151	99.15 52		98.87 361	92.97 491	99.41 115				96.76 299	99.62 268	99.66 81

test_241102_ONE					99.49 151	99.17 43		99.31 248	97.98 232	99.66 61	98.90 258	98.36 91	99.48 445

UA-Net		99.47 16	99.40 27	99.70 2	99.49 151	99.29 23	99.80 4	99.72 47	99.82 8	99.04 204	99.81 8	98.05 132	99.96 13	98.85 99	99.99 5	99.86 29

HFP-MVS		98.71 143	98.44 189	99.51 49	99.49 151	99.16 48	98.52 131	99.31 248	97.47 285	98.58 305	98.50 353	97.97 139	99.85 159	96.57 324	99.59 281	99.53 158

VPA-MVSNet		99.30 34	99.30 45	99.28 96	99.49 151	98.36 129	99.00 73	99.45 181	99.63 29	99.52 88	99.44 86	98.25 108	99.88 116	99.09 80	99.84 115	99.62 93

XVG-OURS-SEG-HR		98.49 197	98.28 220	99.14 125	99.49 151	98.83 87	96.54 392	99.48 160	97.32 305	99.11 187	98.61 336	99.33 15	99.30 479	96.23 354	98.38 457	99.28 289

fmvsm_s_conf0.5_n_11		99.21 48	99.34 36	98.80 198	99.48 159	96.56 314	97.97 229	99.69 58	99.63 29	99.84 31	99.54 63	98.21 116	99.94 42	99.76 24	99.95 40	99.88 21

114514_t		96.50 389	95.77 409	98.69 228	99.48 159	97.43 243	97.84 246	99.55 127	81.42 547	96.51 471	98.58 340	95.53 313	99.67 350	93.41 456	99.58 286	98.98 362

IterMVS-LS		98.55 185	98.70 139	98.09 326	99.48 159	94.73 408	97.22 340	99.39 213	98.97 128	99.38 122	99.31 125	96.00 290	99.93 54	98.58 120	99.97 21	99.60 103
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_10		99.15 58	99.27 48	98.78 205	99.47 162	96.56 314	97.75 262	99.71 49	99.60 36	99.74 47	99.44 86	97.96 140	99.95 26	99.86 4	99.94 52	99.82 37

fmvsm_s_conf0.5_n_5		99.07 83	99.10 81	98.99 157	99.47 162	97.22 265	97.40 315	99.83 27	97.61 268	99.85 28	99.30 126	98.80 42	99.95 26	99.71 33	99.90 89	99.78 51

v8		99.01 91	99.16 63	98.57 254	99.47 162	96.31 327	98.90 84	99.47 172	99.03 122	99.52 88	99.57 50	96.93 229	99.81 227	99.60 38	99.98 12	99.60 103

SSC-MVS3.2		98.53 190	98.79 125	97.74 365	99.46 165	93.62 456	96.45 399	99.34 235	99.33 67	98.93 234	98.70 312	97.90 144	99.90 82	99.12 77	99.92 72	99.69 73

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 205	99.46 165	96.58 312	97.65 277	99.72 47	99.47 48	99.86 24	99.50 69	98.94 31	99.89 98	99.75 27	99.97 21	99.86 29

XVS		98.72 142	98.45 187	99.53 38	99.46 165	99.21 32	98.65 114	99.34 235	98.62 167	97.54 403	98.63 331	97.50 187	99.83 198	96.79 295	99.53 306	99.56 131

X-MVStestdata		94.32 461	92.59 484	99.53 38	99.46 165	99.21 32	98.65 114	99.34 235	98.62 167	97.54 403	45.85 556	97.50 187	99.83 198	96.79 295	99.53 306	99.56 131

test20.03		98.78 134	98.77 128	98.78 205	99.46 165	97.20 268	97.78 253	99.24 285	99.04 120	99.41 115	98.90 258	97.65 166	99.76 274	97.70 209	99.79 160	99.39 234

guyue		98.01 268	97.93 271	98.26 304	99.45 170	95.48 366	98.08 197	96.24 491	98.89 139	99.34 136	99.14 181	91.32 425	99.82 210	99.07 81	99.83 127	99.48 189

CSCG		98.68 158	98.50 176	99.20 111	99.45 170	98.63 101	98.56 126	99.57 112	97.87 243	98.85 252	98.04 406	97.66 165	99.84 180	96.72 305	99.81 141	99.13 341

GeoE		99.05 84	98.99 97	99.25 104	99.44 172	98.35 130	98.73 103	99.56 122	98.42 185	98.91 237	98.81 285	98.94 31	99.91 75	98.35 142	99.73 200	99.49 178

v148		98.45 202	98.60 160	98.00 339	99.44 172	94.98 394	97.44 313	99.06 323	98.30 196	99.32 145	98.97 239	96.65 252	99.62 383	98.37 141	99.85 110	99.39 234

v10		98.97 100	99.11 75	98.55 261	99.44 172	96.21 331	98.90 84	99.55 127	98.73 152	99.48 97	99.60 46	96.63 254	99.83 198	99.70 34	99.99 5	99.61 101

V42		98.78 134	98.78 127	98.76 212	99.44 172	97.04 282	98.27 171	99.19 295	97.87 243	99.25 166	99.16 171	96.84 233	99.78 262	99.21 71	99.84 115	99.46 201

MDA-MVSNet-bldmvs		97.94 276	97.91 274	98.06 333	99.44 172	94.96 395	96.63 386	99.15 311	98.35 189	98.83 257	99.11 189	94.31 359	99.85 159	96.60 321	98.72 435	99.37 246

viewdifsd2359ckpt07		98.71 143	98.86 116	98.26 304	99.43 177	95.65 355	97.20 341	99.66 72	99.20 85	99.29 150	99.01 226	98.29 100	99.73 300	97.92 181	99.75 193	99.39 234

casdiffmvs_mvg		99.12 70	99.16 63	98.99 157	99.43 177	97.73 215	98.00 216	99.62 90	99.22 81	99.55 78	99.22 153	98.93 33	99.75 286	98.66 114	99.81 141	99.50 170
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_0404		98.90 109	99.01 93	98.57 254	99.42 179	96.59 309	98.13 187	99.66 72	99.09 111	99.30 149	99.02 214	98.79 44	99.89 98	97.87 187	99.80 153	99.23 306

test1111		96.49 390	96.82 360	95.52 492	99.42 179	87.08 534	99.22 46	87.14 552	99.11 101	99.46 102	99.58 48	88.69 448	99.86 145	98.80 101	99.95 40	99.62 93

v2v482		98.56 181	98.62 155	98.37 293	99.42 179	95.81 351	97.58 291	99.16 306	97.90 241	99.28 152	99.01 226	95.98 295	99.79 250	99.33 60	99.90 89	99.51 166

OPM-MVS		98.56 181	98.32 215	99.25 104	99.41 182	98.73 95	97.13 348	99.18 299	97.10 329	98.75 272	98.92 252	98.18 119	99.65 370	96.68 311	99.56 294	99.37 246
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 262	98.08 252	98.04 336	99.41 182	94.59 414	94.59 493	99.40 211	97.50 282	98.82 260	98.83 279	96.83 235	99.84 180	97.50 228	99.81 141	99.71 66

E2		98.70 148	98.68 142	98.73 220	99.40 184	97.10 279	97.48 305	99.57 112	98.09 226	99.00 210	99.20 157	97.90 144	99.67 350	97.73 206	99.77 173	99.43 215

E3		98.69 152	98.68 142	98.73 220	99.40 184	97.10 279	97.48 305	99.57 112	98.09 226	99.00 210	99.20 157	97.90 144	99.67 350	97.73 206	99.77 173	99.43 215

ELoFTR		97.81 297	97.74 288	98.04 336	99.39 186	95.79 352	97.28 334	99.58 104	94.13 469	99.38 122	99.37 105	93.31 382	99.60 395	97.23 250	99.96 29	98.74 409

test_one_0601					99.39 186	99.20 38		99.31 248	98.49 181	98.66 287	99.02 214	97.64 169

mvsany_test3		98.87 113	98.92 103	98.74 218	99.38 188	96.94 290	98.58 124	99.10 317	96.49 369	99.96 4	99.81 8	98.18 119	99.45 455	98.97 90	99.79 160	99.83 34

patch_mono-2		98.51 195	98.63 153	98.17 316	99.38 188	94.78 405	97.36 323	99.69 58	98.16 218	98.49 318	99.29 129	97.06 218	99.97 6	98.29 146	99.91 81	99.76 59

test2506		92.39 497	91.89 499	93.89 517	99.38 188	82.28 553	99.32 26	66.03 561	99.08 115	98.77 269	99.57 50	66.26 541	99.84 180	98.71 111	99.95 40	99.54 144

ECVR-MVS		96.42 396	96.61 379	95.85 481	99.38 188	88.18 529	99.22 46	86.00 554	99.08 115	99.36 129	99.57 50	88.47 453	99.82 210	98.52 128	99.95 40	99.54 144

casdiffmvs		98.95 103	99.00 95	98.81 195	99.38 188	97.33 248	97.82 247	99.57 112	99.17 94	99.35 131	99.17 169	98.35 95	99.69 332	98.46 130	99.73 200	99.41 224
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		98.96 102	99.02 91	98.76 212	99.38 188	97.26 260	98.49 141	99.50 150	98.86 143	99.19 177	99.06 201	98.23 111	99.69 332	98.71 111	99.76 189	99.33 270

TranMVSNet+NR-MVSNet		99.17 53	99.07 86	99.46 63	99.37 194	98.87 85	98.39 158	99.42 202	99.42 56	99.36 129	99.06 201	98.38 90	99.95 26	98.34 143	99.90 89	99.57 125

fmvsm_s_conf0.5_n_6		99.08 80	99.21 58	98.69 228	99.36 195	96.51 316	97.62 282	99.68 65	98.43 184	99.85 28	99.10 192	99.12 23	99.88 116	99.77 23	99.92 72	99.67 79

tttt0517		95.64 432	94.98 445	97.64 380	99.36 195	93.81 448	98.72 104	90.47 546	98.08 228	98.67 285	98.34 372	73.88 526	99.92 66	97.77 198	99.51 312	99.20 316

test_part2					99.36 195	99.10 65				99.05 202

v1144		98.60 174	98.66 147	98.41 286	99.36 195	95.90 344	97.58 291	99.34 235	97.51 281	99.27 154	99.15 177	96.34 272	99.80 236	99.47 54	99.93 58	99.51 166

CP-MVS		98.70 148	98.42 192	99.52 44	99.36 195	99.12 62	98.72 104	99.36 223	97.54 279	98.30 337	98.40 364	97.86 151	99.89 98	96.53 333	99.72 209	99.56 131

testing915		96.85 373	96.43 391	98.09 326	99.35 200	95.18 387	98.60 121	97.22 463	98.37 186	97.41 417	97.98 411	83.29 496	99.69 332	96.35 346	99.29 366	99.42 220

RoMa-SfM		98.46 200	98.27 223	99.02 152	99.35 200	98.32 133	97.56 293	99.70 55	95.88 402	99.38 122	98.65 325	96.41 264	99.46 452	97.78 195	99.71 218	99.28 289

DKM		98.18 249	97.95 266	98.85 183	99.35 200	98.31 134	96.68 379	99.69 58	96.90 344	98.61 298	98.77 292	94.41 352	98.93 504	97.32 244	99.84 115	99.32 275

diffmvs_AUTHOR		98.50 196	98.59 162	98.23 311	99.35 200	95.48 366	96.61 388	99.60 95	98.37 186	98.90 238	99.00 230	97.37 198	99.76 274	98.22 151	99.85 110	99.46 201

Test_1112_low_res		96.99 367	96.55 383	98.31 299	99.35 200	95.47 369	95.84 447	99.53 137	91.51 510	96.80 453	98.48 356	91.36 424	99.83 198	96.58 322	99.53 306	99.62 93

DeepC-MVS	97.60 4	98.97 100	98.93 102	99.10 131	99.35 200	97.98 177	98.01 214	99.46 177	97.56 274	99.54 80	99.50 69	98.97 29	99.84 180	98.06 165	99.92 72	99.49 178
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 341	96.86 356	98.58 251	99.34 206	96.32 326	96.75 373	99.58 104	93.14 487	96.89 447	97.48 450	92.11 412	99.86 145	96.91 282	99.54 302	99.57 125

test-260524					99.33 207	99.02 71		99.25 279		99.23 170		96.59 256	99.85 159	98.10 161	99.62 268

reproduce_model		99.15 58	98.97 99	99.67 4	99.33 207	99.44 9	98.15 185	99.47 172	99.12 100	99.52 88	99.32 124	98.31 98	99.90 82	97.78 195	99.73 200	99.66 81

DenseAffine		98.10 257	97.86 279	98.84 189	99.32 209	97.93 185	96.62 387	99.76 40	96.68 361	98.65 288	98.72 303	94.46 350	99.33 474	96.76 299	99.75 193	99.25 300

MVSMamba_PlusPlus		98.83 123	98.98 98	98.36 294	99.32 209	96.58 312	98.90 84	99.41 206	99.75 10	98.72 276	99.50 69	96.17 280	99.94 42	99.27 65	99.78 165	98.57 431

fmvsm_s_conf0.5_n_4		99.01 91	99.22 55	98.38 290	99.31 211	95.48 366	97.56 293	99.73 46	98.87 141	99.75 45	99.27 132	98.80 42	99.86 145	99.80 18	99.90 89	99.81 42

SF-MVS		98.53 190	98.27 223	99.32 91	99.31 211	98.75 91	98.19 179	99.41 206	96.77 355	98.83 257	98.90 258	97.80 156	99.82 210	95.68 384	99.52 309	99.38 243

CPTT-MVS		97.84 293	97.36 321	99.27 99	99.31 211	98.46 117	98.29 167	99.27 271	94.90 445	97.83 381	98.37 368	94.90 333	99.84 180	93.85 441	99.54 302	99.51 166

UnsupCasMVSNet_eth		97.89 280	97.60 305	98.75 214	99.31 211	97.17 274	97.62 282	99.35 229	98.72 158	98.76 271	98.68 316	92.57 402	99.74 293	97.76 202	95.60 534	99.34 264

fmvsm_s_conf0.5_n_7		98.83 123	99.04 88	98.20 313	99.30 215	94.83 403	97.23 336	99.36 223	98.64 162	99.84 31	99.43 89	98.10 128	99.91 75	99.56 42	99.96 29	99.87 23

pmmvs-eth3d		98.47 199	98.34 209	98.86 182	99.30 215	97.76 211	97.16 346	99.28 268	95.54 422	99.42 113	99.19 160	97.27 205	99.63 378	97.89 182	99.97 21	99.20 316

viewcassd2359sk11		98.55 185	98.51 173	98.67 231	99.29 217	96.99 285	97.39 316	99.54 133	97.73 256	98.81 262	99.08 199	97.55 179	99.66 363	97.52 227	99.67 247	99.36 254

SymmetryMVS		98.05 264	97.71 294	99.09 135	99.29 217	97.83 197	98.28 168	97.64 448	99.24 78	98.80 264	98.85 272	89.76 440	99.94 42	98.04 168	99.50 320	99.49 178

Anonymous20231211		99.27 38	99.27 48	99.26 101	99.29 217	98.18 147	99.49 12	99.51 145	99.70 15	99.80 38	99.68 26	96.84 233	99.83 198	99.21 71	99.91 81	99.77 54

viewmanbaseed2359cas		98.58 178	98.54 168	98.70 226	99.28 220	97.13 278	97.47 309	99.55 127	97.55 276	98.96 224	98.92 252	97.77 158	99.59 400	97.59 219	99.77 173	99.39 234

UnsupCasMVSNet_bld		97.30 339	96.92 351	98.45 280	99.28 220	96.78 303	96.20 419	99.27 271	95.42 428	98.28 341	98.30 379	93.16 387	99.71 313	94.99 403	97.37 501	98.87 386

EC-MVSNet		99.09 74	99.05 87	99.20 111	99.28 220	98.93 80	99.24 44	99.84 23	99.08 115	98.12 354	98.37 368	98.72 51	99.90 82	99.05 84	99.77 173	98.77 404

mamba_0408		98.80 130	98.88 109	98.55 261	99.27 223	96.50 317	98.00 216	99.60 95	98.93 133	99.22 172	98.84 277	98.59 68	99.89 98	97.74 204	99.72 209	99.27 293

SSM_04072		98.80 130	98.88 109	98.56 259	99.27 223	96.50 317	98.00 216	99.60 95	98.93 133	99.22 172	98.84 277	98.59 68	99.90 82	97.74 204	99.72 209	99.27 293

SSM_0407		98.86 117	98.96 101	98.55 261	99.27 223	96.50 317	98.04 206	99.66 72	99.09 111	99.22 172	99.02 214	98.79 44	99.87 136	97.87 187	99.72 209	99.27 293

reproduce-ours		99.09 74	98.90 106	99.67 4	99.27 223	99.49 5	98.00 216	99.42 202	99.05 118	99.48 97	99.27 132	98.29 100	99.89 98	97.61 216	99.71 218	99.62 93

our_new_method		99.09 74	98.90 106	99.67 4	99.27 223	99.49 5	98.00 216	99.42 202	99.05 118	99.48 97	99.27 132	98.29 100	99.89 98	97.61 216	99.71 218	99.62 93

DPE-MVS		98.59 176	98.26 226	99.57 21	99.27 223	99.15 52	97.01 352	99.39 213	97.67 261	99.44 108	98.99 232	97.53 183	99.89 98	95.40 395	99.68 241	99.66 81
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 292	98.18 239	96.87 434	99.27 223	91.16 503	95.53 457	99.25 279	99.10 108	99.41 115	99.35 112	93.10 390	99.96 13	98.65 115	99.94 52	99.49 178

v1192		98.60 174	98.66 147	98.41 286	99.27 223	95.88 346	97.52 299	99.36 223	97.41 295	99.33 139	99.20 157	96.37 270	99.82 210	99.57 40	99.92 72	99.55 138

N_pmnet		97.63 310	97.17 333	98.99 157	99.27 223	97.86 194	95.98 434	93.41 532	95.25 435	99.47 101	98.90 258	95.63 309	99.85 159	96.91 282	99.73 200	99.27 293

PMatch-SfM		97.89 280	97.64 301	98.66 233	99.26 232	97.44 242	96.08 429	99.51 145	96.72 357	98.47 321	99.13 183	93.62 379	99.70 322	97.14 260	98.80 429	98.83 389

viewdifsd2359ckpt13		98.39 215	98.29 219	98.70 226	99.26 232	97.19 269	97.51 301	99.48 160	96.94 338	98.58 305	98.82 282	97.47 193	99.55 417	97.21 252	99.33 355	99.34 264

FPMVS		93.44 480	92.23 489	97.08 420	99.25 234	97.86 194	95.61 454	97.16 466	92.90 494	93.76 529	98.65 325	75.94 523	95.66 547	79.30 547	97.49 494	97.73 486

aaEdge-Enhanced		98.61 172	98.33 214	99.44 65	99.24 235	98.93 80	97.45 311	99.06 323	98.14 224	99.06 194	98.77 292	96.97 227	99.82 210	96.67 313	99.64 259	99.58 118

new-patchmatchnet		98.35 218	98.74 129	97.18 414	99.24 235	92.23 484	96.42 403	99.48 160	98.30 196	99.69 56	99.53 65	97.44 194	99.82 210	98.84 100	99.77 173	99.49 178

MCST-MVS		98.00 269	97.63 303	99.10 131	99.24 235	98.17 148	96.89 364	98.73 390	95.66 414	97.92 371	97.70 435	97.17 212	99.66 363	96.18 359	99.23 378	99.47 198

UniMVSNet (Re)		98.87 113	98.71 136	99.35 80	99.24 235	98.73 95	97.73 266	99.38 215	98.93 133	99.12 186	98.73 301	96.77 241	99.86 145	98.63 117	99.80 153	99.46 201

jason		97.45 324	97.35 322	97.76 362	99.24 235	93.93 442	95.86 444	98.42 416	94.24 465	98.50 317	98.13 396	94.82 337	99.91 75	97.22 251	99.73 200	99.43 215
jason: jason.
IterMVS		97.73 301	98.11 248	96.57 447	99.24 235	90.28 514	95.52 459	99.21 289	98.86 143	99.33 139	99.33 119	93.11 389	99.94 42	98.49 129	99.94 52	99.48 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 185	98.62 155	98.32 297	99.22 241	95.58 358	97.51 301	99.45 181	97.16 326	99.45 107	99.24 145	96.12 285	99.85 159	99.60 38	99.88 96	99.55 138

ITE_SJBPF				98.87 180	99.22 241	98.48 116		99.35 229	97.50 282	98.28 341	98.60 338	97.64 169	99.35 471	93.86 440	99.27 369	98.79 402

h-mvs33		97.77 299	97.33 324	99.10 131	99.21 243	97.84 196	98.35 162	98.57 404	99.11 101	98.58 305	99.02 214	88.65 451	99.96 13	98.11 159	96.34 520	99.49 178

v144192		98.54 188	98.57 164	98.45 280	99.21 243	95.98 340	97.63 281	99.36 223	97.15 328	99.32 145	99.18 164	95.84 302	99.84 180	99.50 51	99.91 81	99.54 144

APDe-MVS		98.99 95	98.79 125	99.60 16	99.21 243	99.15 52	98.87 89	99.48 160	97.57 272	99.35 131	99.24 145	97.83 152	99.89 98	97.88 185	99.70 229	99.75 63
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 105	98.81 124	99.28 96	99.21 243	98.45 118	98.46 146	99.33 241	99.63 29	99.48 97	99.15 177	97.23 208	99.75 286	97.17 255	99.66 255	99.63 92

viewmamba		98.57 179	98.66 147	98.31 299	99.20 247	95.89 345	96.92 362	99.57 112	98.71 159	99.02 208	99.04 210	97.48 191	99.71 313	98.28 147	99.70 229	99.35 260

SR-MVS-dyc-post		98.81 128	98.55 166	99.57 21	99.20 247	99.38 12	98.48 144	99.30 256	98.64 162	98.95 225	98.96 243	97.49 190	99.86 145	96.56 328	99.39 344	99.45 207

RE-MVS-def			98.58 163		99.20 247	99.38 12	98.48 144	99.30 256	98.64 162	98.95 225	98.96 243	97.75 160		96.56 328	99.39 344	99.45 207

v1921920		98.54 188	98.60 160	98.38 290	99.20 247	95.76 354	97.56 293	99.36 223	97.23 320	99.38 122	99.17 169	96.02 288	99.84 180	99.57 40	99.90 89	99.54 144

E3new		98.41 205	98.34 209	98.62 243	99.19 251	96.90 293	97.32 326	99.50 150	97.40 297	98.63 292	98.92 252	97.21 210	99.65 370	97.34 240	99.52 309	99.31 280

thisisatest0530		95.27 445	94.45 457	97.74 365	99.19 251	94.37 418	97.86 243	90.20 547	97.17 325	98.22 344	97.65 437	73.53 527	99.90 82	96.90 287	99.35 351	98.95 370

Anonymous20240529		98.93 105	98.87 112	99.12 127	99.19 251	98.22 145	99.01 71	98.99 341	99.25 77	99.54 80	99.37 105	97.04 219	99.80 236	97.89 182	99.52 309	99.35 260

APD-MVS_3200maxsize		98.84 120	98.61 159	99.53 38	99.19 251	99.27 26	98.49 141	99.33 241	98.64 162	99.03 207	98.98 237	97.89 148	99.85 159	96.54 332	99.42 340	99.46 201

HQP_MVS		97.99 272	97.67 296	98.93 171	99.19 251	97.65 222	97.77 256	99.27 271	98.20 211	97.79 385	97.98 411	94.90 333	99.70 322	94.42 422	99.51 312	99.45 207

plane_prior7					99.19 251	97.87 193

ab-mvs		98.41 205	98.36 205	98.59 250	99.19 251	97.23 262	99.32 26	98.81 375	97.66 262	98.62 296	99.40 98	96.82 236	99.80 236	95.88 371	99.51 312	98.75 407

F-COLMAP		97.30 339	96.68 370	99.14 125	99.19 251	98.39 123	97.27 335	99.30 256	92.93 492	96.62 462	98.00 409	95.73 305	99.68 345	92.62 478	98.46 455	99.35 260

viewdifsd2359ckpt09		98.13 256	97.92 272	98.77 210	99.18 259	97.35 246	97.29 330	99.53 137	95.81 409	98.09 357	98.47 357	96.34 272	99.66 363	97.02 270	99.51 312	99.29 286

SR-MVS		98.71 143	98.43 190	99.57 21	99.18 259	99.35 16	98.36 161	99.29 264	98.29 199	98.88 245	98.85 272	97.53 183	99.87 136	96.14 361	99.31 360	99.48 189

UniMVSNet_NR-MVSNet		98.86 117	98.68 142	99.40 71	99.17 261	98.74 92	97.68 271	99.40 211	99.14 99	99.06 194	98.59 339	96.71 248	99.93 54	98.57 122	99.77 173	99.53 158

LF4IMVS		97.90 278	97.69 295	98.52 270	99.17 261	97.66 220	97.19 345	99.47 172	96.31 378	97.85 380	98.20 391	96.71 248	99.52 430	94.62 413	99.72 209	98.38 448

SMA-MVS		98.40 208	98.03 257	99.51 49	99.16 263	99.21 32	98.05 204	99.22 288	94.16 468	98.98 215	99.10 192	97.52 185	99.79 250	96.45 338	99.64 259	99.53 158
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		98.82 126	98.63 153	99.39 72	99.16 263	98.74 92	97.54 297	99.25 279	98.84 149	99.06 194	98.76 297	96.76 243	99.93 54	98.57 122	99.77 173	99.50 170

NR-MVSNet		98.95 103	98.82 122	99.36 74	99.16 263	98.72 97	99.22 46	99.20 291	99.10 108	99.72 48	98.76 297	96.38 268	99.86 145	98.00 173	99.82 134	99.50 170

MVS_111021_LR		98.30 229	98.12 247	98.83 191	99.16 263	98.03 170	96.09 428	99.30 256	97.58 271	98.10 356	98.24 387	98.25 108	99.34 472	96.69 310	99.65 257	99.12 342

dtuplus		98.32 224	98.39 197	98.10 324	99.15 267	95.29 379	96.68 379	99.51 145	97.32 305	99.18 182	99.15 177	97.61 173	99.62 383	97.19 253	99.74 196	99.38 243

DSMNet-mixed		97.42 327	97.60 305	96.87 434	99.15 267	91.46 492	98.54 129	99.12 314	92.87 495	97.58 399	99.63 40	96.21 279	99.90 82	95.74 380	99.54 302	99.27 293

hybridnocas07		98.32 224	98.37 203	98.17 316	99.14 269	95.51 361	96.67 381	99.56 122	97.85 245	98.75 272	98.95 247	96.65 252	99.63 378	98.00 173	99.78 165	99.37 246

D2MVS		97.84 293	97.84 281	97.83 353	99.14 269	94.74 407	96.94 358	98.88 359	95.84 404	98.89 241	98.96 243	94.40 354	99.69 332	97.55 222	99.95 40	99.05 348

pmmvs5		97.64 309	97.49 312	98.08 330	99.14 269	95.12 390	96.70 377	99.05 327	93.77 478	98.62 296	98.83 279	93.23 385	99.75 286	98.33 145	99.76 189	99.36 254

hybrid		98.22 241	98.27 223	98.08 330	99.13 272	95.24 381	96.61 388	99.53 137	97.43 294	98.46 322	98.97 239	96.75 246	99.65 370	97.84 190	99.69 235	99.35 260

SPE-MVS-test		99.13 67	99.09 83	99.26 101	99.13 272	98.97 74	99.31 30	99.88 15	99.44 53	98.16 349	98.51 349	98.64 62	99.93 54	98.91 94	99.85 110	98.88 385

VDD-MVS		98.56 181	98.39 197	99.07 139	99.13 272	98.07 165	98.59 123	97.01 469	99.59 37	99.11 187	99.27 132	94.82 337	99.79 250	98.34 143	99.63 264	99.34 264

save fliter					99.11 275	97.97 178	96.53 394	99.02 335	98.24 202

APD-MVS		98.10 257	97.67 296	99.42 67	99.11 275	98.93 80	97.76 259	99.28 268	94.97 443	98.72 276	98.77 292	97.04 219	99.85 159	93.79 442	99.54 302	99.49 178
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 152	98.71 136	98.62 243	99.10 277	96.37 324	97.23 336	98.87 361	99.20 85	99.19 177	98.99 232	97.30 202	99.85 159	98.77 106	99.79 160	99.65 86

EI-MVSNet		98.40 208	98.51 173	98.04 336	99.10 277	94.73 408	97.20 341	98.87 361	98.97 128	99.06 194	99.02 214	96.00 290	99.80 236	98.58 120	99.82 134	99.60 103

CVMVSNet		96.25 406	97.21 332	93.38 525	99.10 277	80.56 557	97.20 341	98.19 429	96.94 338	99.00 210	99.02 214	89.50 444	99.80 236	96.36 345	99.59 281	99.78 51

EI-MVSNet-Vis-set		98.68 158	98.70 139	98.63 241	99.09 280	96.40 323	97.23 336	98.86 366	99.20 85	99.18 182	98.97 239	97.29 204	99.85 159	98.72 110	99.78 165	99.64 87

HPM-MVS++		98.10 257	97.64 301	99.48 57	99.09 280	99.13 60	97.52 299	98.75 387	97.46 290	96.90 446	97.83 425	96.01 289	99.84 180	95.82 378	99.35 351	99.46 201

DP-MVS Recon		97.33 336	96.92 351	98.57 254	99.09 280	97.99 174	96.79 368	99.35 229	93.18 486	97.71 389	98.07 404	95.00 332	99.31 477	93.97 435	99.13 395	98.42 445

MVS_111021_HR		98.25 239	98.08 252	98.75 214	99.09 280	97.46 239	95.97 435	99.27 271	97.60 270	97.99 367	98.25 385	98.15 125	99.38 467	96.87 290	99.57 290	99.42 220

BP-MVS1		97.40 329	96.97 347	98.71 224	99.07 284	96.81 299	98.34 164	97.18 464	98.58 173	98.17 346	98.61 336	84.01 491	99.94 42	98.97 90	99.78 165	99.37 246

9.14			97.78 285		99.07 284		97.53 298	99.32 243	95.53 423	98.54 313	98.70 312	97.58 176	99.76 274	94.32 427	99.46 327

PAPM_NR		96.82 376	96.32 395	98.30 301	99.07 284	96.69 307	97.48 305	98.76 383	95.81 409	96.61 463	96.47 481	94.12 367	99.17 491	90.82 514	97.78 486	99.06 347

TAMVS		98.24 240	98.05 255	98.80 198	99.07 284	97.18 272	97.88 239	98.81 375	96.66 362	99.17 185	99.21 155	94.81 339	99.77 268	96.96 279	99.88 96	99.44 211

CLD-MVS		97.49 320	97.16 334	98.48 277	99.07 284	97.03 283	94.71 484	99.21 289	94.46 457	98.06 360	97.16 465	97.57 177	99.48 445	94.46 418	99.78 165	98.95 370
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 67	99.10 81	99.24 107	99.06 289	99.15 52	99.36 22	99.88 15	99.36 64	98.21 345	98.46 358	98.68 59	99.93 54	99.03 86	99.85 110	98.64 423

thres100view900		94.19 465	93.67 469	95.75 484	99.06 289	91.35 496	98.03 208	94.24 525	98.33 192	97.40 418	94.98 514	79.84 508	99.62 383	83.05 540	98.08 475	96.29 519

thres600view7		94.45 459	93.83 466	96.29 457	99.06 289	91.53 491	97.99 223	94.24 525	98.34 190	97.44 415	95.01 512	79.84 508	99.67 350	84.33 537	98.23 464	97.66 489

onestephybrid01		98.40 208	98.39 197	98.42 284	99.05 292	96.23 329	96.73 375	99.41 206	98.18 214	98.65 288	99.02 214	97.02 222	99.69 332	97.73 206	99.70 229	99.33 270

plane_prior1					99.05 292

YYNet1		97.60 311	97.67 296	97.39 406	99.04 294	93.04 465	95.27 468	98.38 419	97.25 314	98.92 236	98.95 247	95.48 317	99.73 300	96.99 274	98.74 433	99.41 224

MDA-MVSNet_test_wron		97.60 311	97.66 299	97.41 405	99.04 294	93.09 461	95.27 468	98.42 416	97.26 313	98.88 245	98.95 247	95.43 319	99.73 300	97.02 270	98.72 435	99.41 224

MIMVSNet		96.62 383	96.25 400	97.71 369	99.04 294	94.66 411	99.16 55	96.92 477	97.23 320	97.87 376	99.10 192	86.11 469	99.65 370	91.65 495	99.21 382	98.82 391

PMatch-Up-SfM		97.79 298	97.48 315	98.72 222	99.03 297	97.78 208	96.05 431	99.48 160	96.90 344	98.72 276	99.18 164	92.00 414	99.71 313	97.15 259	98.77 430	98.69 415

usedtu_dtu_shiyan1		97.37 331	97.13 338	98.11 322	99.03 297	95.40 372	94.47 496	98.99 341	96.87 347	97.97 368	97.81 426	92.12 410	99.75 286	97.49 233	99.43 338	99.16 336

FE-MVSNET3		97.37 331	97.13 338	98.11 322	99.03 297	95.40 372	94.47 496	98.99 341	96.87 347	97.97 368	97.81 426	92.12 410	99.75 286	97.49 233	99.43 338	99.16 336

icg_test_0407_2		98.20 246	98.38 201	97.65 377	99.03 297	94.03 433	95.78 449	99.45 181	98.16 218	99.06 194	98.71 305	98.27 104	99.68 345	97.50 228	99.45 329	99.22 311

IMVS_0407		98.39 215	98.64 151	97.66 375	99.03 297	94.03 433	98.10 194	99.45 181	98.16 218	99.06 194	98.71 305	98.27 104	99.71 313	97.50 228	99.45 329	99.22 311

IMVS_0404		98.07 262	98.20 233	97.69 370	99.03 297	94.03 433	96.67 381	99.45 181	98.16 218	98.03 364	98.71 305	96.80 239	99.82 210	97.50 228	99.45 329	99.22 311

IMVS_0403		98.34 219	98.56 165	97.66 375	99.03 297	94.03 433	97.98 225	99.45 181	98.16 218	98.89 241	98.71 305	97.90 144	99.74 293	97.50 228	99.45 329	99.22 311

PatchMatch-RL		97.24 345	96.78 363	98.61 247	99.03 297	97.83 197	96.36 407	99.06 323	93.49 483	97.36 422	97.78 428	95.75 304	99.49 441	93.44 455	98.77 430	98.52 433

ArgMatch-SfM		97.96 275	97.72 292	98.66 233	99.02 305	97.33 248	96.49 397	99.52 143	95.46 426	98.71 280	98.29 382	96.14 281	99.69 332	96.30 350	99.56 294	98.97 366

viewmambaseed2359dif		98.19 247	98.26 226	97.99 341	99.02 305	95.03 393	96.59 391	99.53 137	96.21 382	99.00 210	98.99 232	97.62 171	99.61 391	97.62 215	99.72 209	99.33 270

GDP-MVS		97.50 317	97.11 340	98.67 231	99.02 305	96.85 297	98.16 184	99.71 49	98.32 194	98.52 316	98.54 344	83.39 495	99.95 26	98.79 102	99.56 294	99.19 322

ZD-MVS					99.01 308	98.84 86		99.07 322	94.10 471	98.05 362	98.12 398	96.36 271	99.86 145	92.70 477	99.19 387

CDPH-MVS		97.26 342	96.66 374	99.07 139	99.00 309	98.15 149	96.03 432	99.01 338	91.21 514	97.79 385	97.85 423	96.89 231	99.69 332	92.75 475	99.38 347	99.39 234

diffmvs		98.22 241	98.24 230	98.17 316	99.00 309	95.44 370	96.38 405	99.58 104	97.79 252	98.53 314	98.50 353	96.76 243	99.74 293	97.95 180	99.64 259	99.34 264
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		98.40 208	98.19 237	99.03 149	99.00 309	97.65 222	96.85 366	98.94 345	98.57 175	98.89 241	98.50 353	95.60 311	99.85 159	97.54 224	99.85 110	99.59 110

plane_prior6					98.99 312	97.70 218						94.90 333

ArgMatch-Sym		97.83 295	97.54 307	98.71 224	98.98 313	97.65 222	96.25 417	99.43 195	95.60 417	98.85 252	97.98 411	95.72 306	99.56 412	95.54 392	99.50 320	98.92 376

xiu_mvs_v1_base_debu		97.86 286	98.17 240	96.92 431	98.98 313	93.91 443	96.45 399	99.17 303	97.85 245	98.41 328	97.14 467	98.47 78	99.92 66	98.02 170	99.05 402	96.92 507

xiu_mvs_v1_base		97.86 286	98.17 240	96.92 431	98.98 313	93.91 443	96.45 399	99.17 303	97.85 245	98.41 328	97.14 467	98.47 78	99.92 66	98.02 170	99.05 402	96.92 507

xiu_mvs_v1_base_debi		97.86 286	98.17 240	96.92 431	98.98 313	93.91 443	96.45 399	99.17 303	97.85 245	98.41 328	97.14 467	98.47 78	99.92 66	98.02 170	99.05 402	96.92 507

MVP-Stereo		98.08 261	97.92 272	98.57 254	98.96 317	96.79 300	97.90 237	99.18 299	96.41 374	98.46 322	98.95 247	95.93 299	99.60 395	96.51 334	98.98 417	99.31 280
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 208	98.68 142	97.54 393	98.96 317	97.99 174	97.88 239	99.36 223	98.20 211	99.63 67	99.04 210	98.76 47	95.33 549	96.56 328	99.74 196	99.31 280
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				98.91 176	98.94 319	97.76 211		98.76 383	87.58 538	96.75 455	98.10 400	94.80 340	99.78 262	92.73 476	99.00 412	99.20 316

USDC		97.41 328	97.40 317	97.44 403	98.94 319	93.67 453	95.17 472	99.53 137	94.03 474	98.97 219	99.10 192	95.29 322	99.34 472	95.84 377	99.73 200	99.30 284

tfpn200view9		94.03 469	93.44 471	95.78 483	98.93 321	91.44 494	97.60 288	94.29 522	97.94 237	97.10 430	94.31 523	79.67 510	99.62 383	83.05 540	98.08 475	96.29 519

testdata				98.09 326	98.93 321	95.40 372		98.80 377	90.08 523	97.45 413	98.37 368	95.26 323	99.70 322	93.58 449	98.95 420	99.17 330

thres400		94.14 467	93.44 471	96.24 460	98.93 321	91.44 494	97.60 288	94.29 522	97.94 237	97.10 430	94.31 523	79.67 510	99.62 383	83.05 540	98.08 475	97.66 489

TAPA-MVS	96.21 11	96.63 382	95.95 405	98.65 235	98.93 321	98.09 158	96.93 360	99.28 268	83.58 544	98.13 353	97.78 428	96.13 283	99.40 463	93.52 451	99.29 366	98.45 438
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 325	96.93 291	95.54 456	98.78 380	85.72 541	96.86 450	98.11 399	94.43 351			99.10 400	99.23 306

PVSNet_BlendedMVS		97.55 316	97.53 309	97.60 384	98.92 325	93.77 450	96.64 385	99.43 195	94.49 455	97.62 395	99.18 164	96.82 236	99.67 350	94.73 410	99.93 58	99.36 254

PVSNet_Blended		96.88 370	96.68 370	97.47 401	98.92 325	93.77 450	94.71 484	99.43 195	90.98 517	97.62 395	97.36 459	96.82 236	99.67 350	94.73 410	99.56 294	98.98 362

MSDG		97.71 303	97.52 310	98.28 303	98.91 328	96.82 298	94.42 498	99.37 219	97.65 263	98.37 334	98.29 382	97.40 196	99.33 474	94.09 433	99.22 379	98.68 420

Anonymous202405211		97.90 278	97.50 311	99.08 137	98.90 329	98.25 139	98.53 130	96.16 492	98.87 141	99.11 187	98.86 269	90.40 435	99.78 262	97.36 239	99.31 360	99.19 322

原ACMM1				98.35 295	98.90 329	96.25 328		98.83 374	92.48 499	96.07 482	98.10 400	95.39 320	99.71 313	92.61 479	98.99 414	99.08 344

GBi-Net		98.65 164	98.47 184	99.17 116	98.90 329	98.24 140	99.20 49	99.44 189	98.59 170	98.95 225	99.55 57	94.14 364	99.86 145	97.77 198	99.69 235	99.41 224

test1		98.65 164	98.47 184	99.17 116	98.90 329	98.24 140	99.20 49	99.44 189	98.59 170	98.95 225	99.55 57	94.14 364	99.86 145	97.77 198	99.69 235	99.41 224

FMVSNet2		98.49 197	98.40 194	98.75 214	98.90 329	97.14 277	98.61 120	99.13 313	98.59 170	99.19 177	99.28 130	94.14 364	99.82 210	97.97 178	99.80 153	99.29 286

OMC-MVS		97.88 283	97.49 312	99.04 148	98.89 334	98.63 101	96.94 358	99.25 279	95.02 441	98.53 314	98.51 349	97.27 205	99.47 448	93.50 453	99.51 312	99.01 357

VortexMVS		97.98 273	98.31 216	97.02 424	98.88 335	91.45 493	98.03 208	99.47 172	98.65 161	99.55 78	99.47 79	91.49 422	99.81 227	99.32 61	99.91 81	99.80 46

MVSFormer		98.26 236	98.43 190	97.77 359	98.88 335	93.89 446	99.39 20	99.56 122	99.11 101	98.16 349	98.13 396	93.81 373	99.97 6	99.26 66	99.57 290	99.43 215

lupinMVS		97.06 360	96.86 356	97.65 377	98.88 335	93.89 446	95.48 460	97.97 436	93.53 481	98.16 349	97.58 441	93.81 373	99.91 75	96.77 298	99.57 290	99.17 330

dmvs_re		95.98 418	95.39 429	97.74 365	98.86 338	97.45 240	98.37 160	95.69 507	97.95 235	96.56 465	95.95 491	90.70 432	97.68 529	88.32 525	96.13 524	98.11 462

DELS-MVS		98.27 234	98.20 233	98.48 277	98.86 338	96.70 306	95.60 455	99.20 291	97.73 256	98.45 324	98.71 305	97.50 187	99.82 210	98.21 152	99.59 281	98.93 375
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		97.89 280	97.98 262	97.60 384	98.86 338	94.35 419	96.21 418	99.44 189	97.45 292	99.06 194	98.88 266	97.99 138	99.28 483	94.38 426	99.58 286	99.18 326

LCM-MVSNet-Re		98.64 166	98.48 182	99.11 129	98.85 341	98.51 114	98.49 141	99.83 27	98.37 186	99.69 56	99.46 81	98.21 116	99.92 66	94.13 432	99.30 364	98.91 380

pmmvs4		97.58 314	97.28 325	98.51 271	98.84 342	96.93 291	95.40 464	98.52 410	93.60 480	98.61 298	98.65 325	95.10 329	99.60 395	96.97 278	99.79 160	98.99 361

NP-MVS					98.84 342	97.39 245					96.84 471

sss		97.21 348	96.93 349	98.06 333	98.83 344	95.22 385	96.75 373	98.48 412	94.49 455	97.27 424	97.90 419	92.77 398	99.80 236	96.57 324	99.32 358	99.16 336

PVSNet	93.40 17	95.67 430	95.70 412	95.57 490	98.83 344	88.57 525	92.50 534	97.72 441	92.69 497	96.49 474	96.44 482	93.72 376	99.43 459	93.61 446	99.28 368	98.71 411

MVE	83.40 22	92.50 496	91.92 497	94.25 510	98.83 344	91.64 489	92.71 532	83.52 556	95.92 400	86.46 550	95.46 505	95.20 324	95.40 548	80.51 545	98.64 444	95.73 527
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 474	93.91 464	93.39 524	98.82 347	81.72 555	97.76 259	95.28 511	98.60 169	96.54 466	96.66 476	65.85 544	99.62 383	96.65 317	98.99 414	98.82 391

ambc				98.24 308	98.82 347	95.97 342	98.62 118	99.00 340		99.27 154	99.21 155	96.99 225	99.50 437	96.55 331	99.50 320	99.26 299

旧先验1					98.82 347	97.45 240		98.76 383			98.34 372	95.50 316			99.01 411	99.23 306

test_vis1_rt		97.75 300	97.72 292	97.83 353	98.81 350	96.35 325	97.30 329	99.69 58	94.61 453	97.87 376	98.05 405	96.26 277	98.32 518	98.74 108	98.18 467	98.82 391

WTY-MVS		96.67 380	96.27 399	97.87 351	98.81 350	94.61 413	96.77 371	97.92 438	94.94 444	97.12 429	97.74 432	91.11 427	99.82 210	93.89 438	98.15 471	99.18 326

3Dnovator+	97.89 3	98.69 152	98.51 173	99.24 107	98.81 350	98.40 121	99.02 70	99.19 295	98.99 125	98.07 359	99.28 130	97.11 217	99.84 180	96.84 293	99.32 358	99.47 198

dtuonly		96.49 390	97.28 325	94.10 513	98.80 353	83.27 549	93.66 521	99.48 160	95.10 439	97.87 376	98.30 379	95.61 310	99.68 345	96.98 277	99.75 193	99.33 270

LoFTR		97.97 274	97.79 284	98.53 268	98.80 353	97.47 237	97.01 352	99.55 127	95.55 420	99.46 102	99.22 153	94.22 362	99.44 457	96.45 338	99.82 134	98.68 420

QAPM		97.31 337	96.81 362	98.82 193	98.80 353	97.49 233	99.06 66	99.19 295	90.22 521	97.69 391	99.16 171	96.91 230	99.90 82	90.89 512	99.41 341	99.07 346

VNet		98.42 204	98.30 217	98.79 202	98.79 356	97.29 257	98.23 174	98.66 395	99.31 70	98.85 252	98.80 286	94.80 340	99.78 262	98.13 157	99.13 395	99.31 280

DPM-MVS		96.32 400	95.59 419	98.51 271	98.76 357	97.21 267	94.54 495	98.26 423	91.94 505	96.37 475	97.25 463	93.06 392	99.43 459	91.42 500	98.74 433	98.89 382

3Dnovator	98.27 2	98.81 128	98.73 131	99.05 146	98.76 357	97.81 206	99.25 43	99.30 256	98.57 175	98.55 311	99.33 119	97.95 141	99.90 82	97.16 256	99.67 247	99.44 211

PLC	94.65 16	96.51 387	95.73 411	98.85 183	98.75 359	97.91 188	96.42 403	99.06 323	90.94 518	95.59 491	97.38 457	94.41 352	99.59 400	90.93 510	98.04 480	99.05 348
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 374	96.75 366	97.08 420	98.74 360	93.33 459	96.71 376	98.26 423	96.72 357	98.44 325	97.37 458	95.20 324	99.47 448	91.89 490	97.43 498	98.44 441

hse-mvs2		97.46 322	97.07 341	98.64 237	98.73 361	97.33 248	97.45 311	97.64 448	99.11 101	98.58 305	97.98 411	88.65 451	99.79 250	98.11 159	97.39 500	98.81 396

CDS-MVSNet		97.69 305	97.35 322	98.69 228	98.73 361	97.02 284	96.92 362	98.75 387	95.89 401	98.59 303	98.67 318	92.08 413	99.74 293	96.72 305	99.81 141	99.32 275
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 403	95.83 407	97.64 380	98.72 363	94.30 420	98.87 89	98.77 381	97.80 249	96.53 467	98.02 408	97.34 200	99.47 448	76.93 549	99.48 325	99.16 336

EIA-MVS		98.00 269	97.74 288	98.80 198	98.72 363	98.09 158	98.05 204	99.60 95	97.39 298	96.63 461	95.55 500	97.68 163	99.80 236	96.73 304	99.27 369	98.52 433

LFMVS		97.20 349	96.72 367	98.64 237	98.72 363	96.95 289	98.93 82	94.14 527	99.74 12	98.78 266	99.01 226	84.45 486	99.73 300	97.44 235	99.27 369	99.25 300

new_pmnet		96.99 367	96.76 364	97.67 373	98.72 363	94.89 400	95.95 439	98.20 427	92.62 498	98.55 311	98.54 344	94.88 336	99.52 430	93.96 436	99.44 336	98.59 430

Fast-Effi-MVS+		97.67 307	97.38 319	98.57 254	98.71 367	97.43 243	97.23 336	99.45 181	94.82 448	96.13 479	96.51 478	98.52 76	99.91 75	96.19 357	98.83 426	98.37 450

TEST9					98.71 367	98.08 162	95.96 437	99.03 332	91.40 511	95.85 487	97.53 444	96.52 259	99.76 274

train_agg		97.10 355	96.45 390	99.07 139	98.71 367	98.08 162	95.96 437	99.03 332	91.64 506	95.85 487	97.53 444	96.47 261	99.76 274	93.67 445	99.16 390	99.36 254

TSAR-MVS + GP.		98.18 249	97.98 262	98.77 210	98.71 367	97.88 192	96.32 410	98.66 395	96.33 376	99.23 170	98.51 349	97.48 191	99.40 463	97.16 256	99.46 327	99.02 355

FA-MVS(test-final)		96.99 367	96.82 360	97.50 397	98.70 371	94.78 405	99.34 23	96.99 470	95.07 440	98.48 320	99.33 119	88.41 454	99.65 370	96.13 363	98.92 423	98.07 465

AUN-MVS		96.24 408	95.45 425	98.60 249	98.70 371	97.22 265	97.38 318	97.65 446	95.95 399	95.53 498	97.96 417	82.11 504	99.79 250	96.31 348	97.44 497	98.80 401

our_test_3		97.39 330	97.73 291	96.34 455	98.70 371	89.78 520	94.61 492	98.97 344	96.50 368	99.04 204	98.85 272	95.98 295	99.84 180	97.26 248	99.67 247	99.41 224

ppachtmachnet_test		97.50 317	97.74 288	96.78 441	98.70 371	91.23 502	94.55 494	99.05 327	96.36 375	99.21 175	98.79 288	96.39 266	99.78 262	96.74 302	99.82 134	99.34 264

PCF-MVS	92.86 18	94.36 460	93.00 480	98.42 284	98.70 371	97.56 229	93.16 531	99.11 316	79.59 548	97.55 402	97.43 454	92.19 408	99.73 300	79.85 546	99.45 329	97.97 471
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 277	98.02 258	97.58 386	98.69 376	94.10 429	98.13 187	98.90 355	97.95 235	97.32 423	99.58 48	95.95 298	98.75 511	96.41 341	99.22 379	99.87 23

ETV-MVS		98.03 265	97.86 279	98.56 259	98.69 376	98.07 165	97.51 301	99.50 150	98.10 225	97.50 407	95.51 501	98.41 86	99.88 116	96.27 353	99.24 375	97.71 488

test_prior				98.95 167	98.69 376	97.95 182		99.03 332					99.59 400			99.30 284

mvsmamba		97.57 315	97.26 327	98.51 271	98.69 376	96.73 305	98.74 99	97.25 460	97.03 334	97.88 375	99.23 151	90.95 428	99.87 136	96.61 320	99.00 412	98.91 380

agg_prior					98.68 380	97.99 174		99.01 338		95.59 491			99.77 268

test_8					98.67 381	98.01 171	95.91 443	99.02 335	91.64 506	95.79 490	97.50 448	96.47 261	99.76 274

HQP-NCC					98.67 381		96.29 412		96.05 391	95.55 494

ACMP_Plane					98.67 381		96.29 412		96.05 391	95.55 494

CNVR-MVS		98.17 252	97.87 278	99.07 139	98.67 381	98.24 140	97.01 352	98.93 348	97.25 314	97.62 395	98.34 372	97.27 205	99.57 409	96.42 340	99.33 355	99.39 234

HQP-MVS		97.00 366	96.49 386	98.55 261	98.67 381	96.79 300	96.29 412	99.04 330	96.05 391	95.55 494	96.84 471	93.84 371	99.54 423	92.82 471	99.26 373	99.32 275

MM		98.22 241	97.99 261	98.91 176	98.66 386	96.97 286	97.89 238	94.44 519	99.54 41	98.95 225	99.14 181	93.50 380	99.92 66	99.80 18	99.96 29	99.85 31

test_fmvs1		97.72 302	97.94 269	97.07 422	98.66 386	92.39 479	97.68 271	99.81 33	95.20 438	99.54 80	99.44 86	91.56 420	99.41 462	99.78 22	99.77 173	99.40 233

BridgeMVS		98.63 168	98.72 133	98.38 290	98.66 386	96.68 308	98.90 84	99.42 202	98.99 125	98.97 219	99.19 160	95.81 303	99.85 159	98.77 106	99.77 173	98.60 427

thres200		93.72 476	93.14 477	95.46 495	98.66 386	91.29 498	96.61 388	94.63 517	97.39 298	96.83 451	93.71 526	79.88 507	99.56 412	82.40 543	98.13 472	95.54 528

wuyk23d		96.06 411	97.62 304	91.38 529	98.65 390	98.57 108	98.85 93	96.95 474	96.86 350	99.90 14	99.16 171	99.18 19	98.40 517	89.23 523	99.77 173	77.18 552

NCCC		97.86 286	97.47 316	99.05 146	98.61 391	98.07 165	96.98 355	98.90 355	97.63 264	97.04 436	97.93 418	95.99 294	99.66 363	95.31 396	98.82 428	99.43 215

DeepC-MVS_fast	96.85 6	98.30 229	98.15 244	98.75 214	98.61 391	97.23 262	97.76 259	99.09 319	97.31 307	98.75 272	98.66 322	97.56 178	99.64 375	96.10 365	99.55 299	99.39 234
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 478	92.09 491	97.75 363	98.60 393	94.40 417	97.32 326	95.26 512	97.56 274	96.79 454	95.50 502	53.57 557	99.77 268	95.26 398	98.97 418	99.08 344

thisisatest0515		94.12 468	93.16 476	96.97 428	98.60 393	92.90 468	93.77 519	90.61 545	94.10 471	96.91 443	95.87 494	74.99 524	99.80 236	94.52 416	99.12 398	98.20 457

GA-MVS		95.86 424	95.32 434	97.49 398	98.60 393	94.15 426	93.83 518	97.93 437	95.49 424	96.68 459	97.42 455	83.21 497	99.30 479	96.22 355	98.55 452	99.01 357

dmvs_testset		92.94 491	92.21 490	95.13 501	98.59 396	90.99 506	97.65 277	92.09 538	96.95 337	94.00 525	93.55 527	92.34 406	96.97 539	72.20 550	92.52 544	97.43 498

OPU-MVS				98.82 193	98.59 396	98.30 135	98.10 194				98.52 348	98.18 119	98.75 511	94.62 413	99.48 325	99.41 224

MSLP-MVS++		98.02 266	98.14 246	97.64 380	98.58 398	95.19 386	97.48 305	99.23 287	97.47 285	97.90 373	98.62 334	97.04 219	98.81 509	97.55 222	99.41 341	98.94 374

test12				98.93 171	98.58 398	97.83 197		98.66 395		96.53 467		95.51 315	99.69 332		99.13 395	99.27 293

CL-MVSNet_self_test		97.44 325	97.22 331	98.08 330	98.57 400	95.78 353	94.30 502	98.79 378	96.58 365	98.60 301	98.19 392	94.74 343	99.64 375	96.41 341	98.84 425	98.82 391

PS-MVSNAJ		97.08 358	97.39 318	96.16 468	98.56 401	92.46 477	95.24 470	98.85 369	97.25 314	97.49 408	95.99 490	98.07 129	99.90 82	96.37 343	98.67 443	96.12 524

CNLPA		97.17 352	96.71 368	98.55 261	98.56 401	98.05 169	96.33 409	98.93 348	96.91 343	97.06 434	97.39 456	94.38 355	99.45 455	91.66 494	99.18 389	98.14 461

xiu_mvs_v2_base		97.16 353	97.49 312	96.17 466	98.54 403	92.46 477	95.45 461	98.84 370	97.25 314	97.48 409	96.49 479	98.31 98	99.90 82	96.34 347	98.68 442	96.15 523

alignmvs		97.35 334	96.88 355	98.78 205	98.54 403	98.09 158	97.71 267	97.69 443	99.20 85	97.59 398	95.90 493	88.12 457	99.55 417	98.18 154	98.96 419	98.70 414

FE-MVS		95.66 431	94.95 447	97.77 359	98.53 405	95.28 380	99.40 19	96.09 496	93.11 488	97.96 370	99.26 138	79.10 514	99.77 268	92.40 484	98.71 437	98.27 455

Effi-MVS+		98.02 266	97.82 282	98.62 243	98.53 405	97.19 269	97.33 325	99.68 65	97.30 308	96.68 459	97.46 453	98.56 74	99.80 236	96.63 318	98.20 466	98.86 387

baseline1		95.96 421	95.44 426	97.52 395	98.51 407	93.99 440	98.39 158	96.09 496	98.21 207	98.40 333	97.76 430	86.88 461	99.63 378	95.42 394	89.27 547	98.95 370

MVS_Test		98.18 249	98.36 205	97.67 373	98.48 408	94.73 408	98.18 180	99.02 335	97.69 259	98.04 363	99.11 189	97.22 209	99.56 412	98.57 122	98.90 424	98.71 411

MGCFI-Net		98.34 219	98.28 220	98.51 271	98.47 409	97.59 228	98.96 78	99.48 160	99.18 93	97.40 418	95.50 502	98.66 60	99.50 437	98.18 154	98.71 437	98.44 441

BH-RMVSNet		96.83 374	96.58 382	97.58 386	98.47 409	94.05 430	96.67 381	97.36 453	96.70 360	97.87 376	97.98 411	95.14 328	99.44 457	90.47 516	98.58 450	99.25 300

sasdasda		98.34 219	98.26 226	98.58 251	98.46 411	97.82 203	98.96 78	99.46 177	99.19 90	97.46 410	95.46 505	98.59 68	99.46 452	98.08 163	98.71 437	98.46 435

canonicalmvs		98.34 219	98.26 226	98.58 251	98.46 411	97.82 203	98.96 78	99.46 177	99.19 90	97.46 410	95.46 505	98.59 68	99.46 452	98.08 163	98.71 437	98.46 435

MVS-HIRNet		94.32 461	95.62 415	90.42 532	98.46 411	75.36 558	96.29 412	89.13 549	95.25 435	95.38 500	99.75 17	92.88 395	99.19 489	94.07 434	99.39 344	96.72 514

MatchFormer		97.07 359	96.92 351	97.49 398	98.44 414	95.92 343	96.79 368	99.14 312	93.08 489	99.32 145	99.10 192	93.89 370	99.03 497	92.78 474	99.78 165	97.52 494

PHI-MVS		98.29 232	97.95 266	99.34 83	98.44 414	99.16 48	98.12 191	99.38 215	96.01 395	98.06 360	98.43 361	97.80 156	99.67 350	95.69 383	99.58 286	99.20 316

DVP-MVS++		98.90 109	98.70 139	99.51 49	98.43 416	99.15 52	99.43 15	99.32 243	98.17 215	99.26 158	99.02 214	98.18 119	99.88 116	97.07 267	99.45 329	99.49 178

MSC_two_6792asdad				99.32 91	98.43 416	98.37 126		98.86 366					99.89 98	97.14 260	99.60 277	99.71 66

No_MVS				99.32 91	98.43 416	98.37 126		98.86 366					99.89 98	97.14 260	99.60 277	99.71 66

Fast-Effi-MVS+-dtu		98.27 234	98.09 249	98.81 195	98.43 416	98.11 154	97.61 287	99.50 150	98.64 162	97.39 420	97.52 447	98.12 127	99.95 26	96.90 287	98.71 437	98.38 448

OpenMVS_ROB	95.38 14	95.84 426	95.18 442	97.81 355	98.41 420	97.15 276	97.37 322	98.62 399	83.86 543	98.65 288	98.37 368	94.29 360	99.68 345	88.41 524	98.62 448	96.60 515

SIFT-CM-Cal		96.28 403	96.31 396	96.16 468	98.39 421	98.11 154	93.46 526	96.47 488	94.81 449	98.49 318	98.43 361	94.48 349	97.34 535	92.60 480	99.70 229	93.02 542

DeepPCF-MVS	96.93 5	98.32 224	98.01 259	99.23 109	98.39 421	98.97 74	95.03 476	99.18 299	96.88 346	99.33 139	98.78 290	98.16 123	99.28 483	96.74 302	99.62 268	99.44 211

Patchmatch-test		96.55 386	96.34 394	97.17 416	98.35 423	93.06 462	98.40 157	97.79 439	97.33 303	98.41 328	98.67 318	83.68 494	99.69 332	95.16 401	99.31 360	98.77 404

AdaColmap		97.14 354	96.71 368	98.46 279	98.34 424	97.80 207	96.95 357	98.93 348	95.58 419	96.92 441	97.66 436	95.87 301	99.53 426	90.97 508	99.14 393	98.04 466

OpenMVS	96.65 7	97.09 357	96.68 370	98.32 297	98.32 425	97.16 275	98.86 92	99.37 219	89.48 526	96.29 477	99.15 177	96.56 257	99.90 82	92.90 468	99.20 384	97.89 474

MG-MVS		96.77 377	96.61 379	97.26 411	98.31 426	93.06 462	95.93 440	98.12 432	96.45 373	97.92 371	98.73 301	93.77 375	99.39 465	91.19 505	99.04 405	99.33 270

TestfortrainingZip				98.97 163	98.30 427	98.43 120	98.68 109	98.26 423	97.76 254	98.86 251	98.16 395	95.15 327	99.47 448		97.55 491	99.02 355

SIFT-NN-NCMNet		95.39 442	95.22 439	95.92 477	98.29 428	98.34 132	93.58 523	94.60 518	94.07 473	94.84 510	97.53 444	94.37 356	96.62 542	91.01 507	98.64 444	92.80 545

SIFT-UMatch		96.33 399	96.47 387	95.89 479	98.29 428	97.95 182	93.84 517	97.24 461	95.78 411	98.72 276	98.04 406	93.45 381	96.81 540	93.14 463	99.73 200	92.91 544

test_yl		96.69 378	96.29 397	97.90 346	98.28 430	95.24 381	97.29 330	97.36 453	98.21 207	98.17 346	97.86 421	86.27 465	99.55 417	94.87 407	98.32 459	98.89 382

DCV-MVSNet		96.69 378	96.29 397	97.90 346	98.28 430	95.24 381	97.29 330	97.36 453	98.21 207	98.17 346	97.86 421	86.27 465	99.55 417	94.87 407	98.32 459	98.89 382

SIFT-NCM-Cal		96.56 385	96.68 370	96.20 464	98.27 432	98.44 119	94.40 499	96.67 482	95.29 433	97.63 394	98.17 393	96.40 265	96.59 544	93.61 446	99.66 255	93.57 535

SIFT-NN-UMatch		95.38 443	95.26 436	95.75 484	98.25 433	97.78 208	93.24 530	95.66 509	94.01 475	95.10 505	97.47 452	93.12 388	96.78 541	92.42 483	98.04 480	92.69 547

CHOSEN 280x420		95.51 437	95.47 423	95.65 489	98.25 433	88.27 528	93.25 529	98.88 359	93.53 481	94.65 514	97.15 466	86.17 467	99.93 54	97.41 237	99.93 58	98.73 410

SIFT-NN-CMatch		95.63 433	95.48 422	96.08 472	98.24 435	98.00 172	92.71 532	94.29 522	94.20 467	95.85 487	97.26 462	95.72 306	97.01 537	91.99 488	99.02 409	93.23 539

SCA		96.41 397	96.66 374	95.67 487	98.24 435	88.35 527	95.85 446	96.88 478	96.11 389	97.67 392	98.67 318	93.10 390	99.85 159	94.16 428	99.22 379	98.81 396

DeepMVS_CX				93.44 523	98.24 435	94.21 423		94.34 521	64.28 552	91.34 541	94.87 518	89.45 445	92.77 552	77.54 548	93.14 543	93.35 538

MS-PatchMatch		97.68 306	97.75 287	97.45 402	98.23 438	93.78 449	97.29 330	98.84 370	96.10 390	98.64 291	98.65 325	96.04 287	99.36 468	96.84 293	99.14 393	99.20 316

SIFT-ConvMatch		96.57 384	96.62 377	96.43 451	98.20 439	98.27 137	93.88 516	96.88 478	95.29 433	98.88 245	98.25 385	95.18 326	97.43 533	93.22 461	99.83 127	93.59 534

BH-w/o		95.13 449	94.89 449	95.86 480	98.20 439	91.31 497	95.65 453	97.37 452	93.64 479	96.52 470	95.70 498	93.04 393	99.02 499	88.10 526	95.82 532	97.24 504

SIFT-MNN		95.92 422	95.97 404	95.74 486	98.18 441	98.00 172	94.17 507	96.99 470	95.74 413	97.16 428	97.90 419	90.71 431	95.79 546	93.71 444	99.21 382	93.44 536

mvs_anonymous		97.83 295	98.16 243	96.87 434	98.18 441	91.89 486	97.31 328	98.90 355	97.37 300	98.83 257	99.46 81	96.28 275	99.79 250	98.90 95	98.16 470	98.95 370

SIFT-PCN-Cal		96.34 398	96.46 389	96.01 475	98.17 443	96.89 294	93.48 525	97.35 456	94.84 447	99.35 131	98.30 379	94.70 344	97.92 525	92.03 487	99.88 96	93.21 541

miper_lstm_enhance		97.18 351	97.16 334	97.25 412	98.16 444	92.85 470	95.15 474	99.31 248	97.25 314	98.74 275	98.78 290	90.07 436	99.78 262	97.19 253	99.80 153	99.11 343

RRT-MVS		97.88 283	97.98 262	97.61 383	98.15 445	93.77 450	98.97 77	99.64 80	99.16 95	98.69 281	99.42 90	91.60 417	99.89 98	97.63 214	98.52 454	99.16 336

ET-MVSNet_ETH3D		94.30 463	93.21 475	97.58 386	98.14 446	94.47 416	94.78 483	93.24 534	94.72 450	89.56 545	95.87 494	78.57 518	99.81 227	96.91 282	97.11 510	98.46 435

ADS-MVSNet2		95.43 441	94.98 445	96.76 442	98.14 446	91.74 487	97.92 234	97.76 440	90.23 519	96.51 471	98.91 255	85.61 475	99.85 159	92.88 469	96.90 512	98.69 415

ADS-MVSNet		95.24 446	94.93 448	96.18 465	98.14 446	90.10 517	97.92 234	97.32 458	90.23 519	96.51 471	98.91 255	85.61 475	99.74 293	92.88 469	96.90 512	98.69 415

SIFT-UM-Cal		96.49 390	96.62 377	96.12 471	98.13 449	97.89 191	93.35 527	98.44 413	95.48 425	98.63 292	98.34 372	95.45 318	97.45 532	92.22 486	99.50 320	93.02 542

SIFT-PointCN		96.45 395	96.47 387	96.39 453	98.13 449	97.54 231	93.31 528	97.23 462	94.67 452	98.68 284	98.32 377	94.64 345	97.81 527	93.50 453	99.77 173	93.83 532

c3_l		97.36 333	97.37 320	97.31 407	98.09 451	93.25 460	95.01 477	99.16 306	97.05 331	98.77 269	98.72 303	92.88 395	99.64 375	96.93 281	99.76 189	99.05 348

balanced_ft_v1		98.28 233	98.35 208	98.10 324	98.08 452	96.23 329	99.23 45	99.26 277	98.34 190	97.46 410	99.42 90	95.38 321	99.88 116	98.60 118	99.34 353	98.17 459

FMVSNet3		97.50 317	97.24 329	98.29 302	98.08 452	95.83 349	97.86 243	98.91 354	97.89 242	98.95 225	98.95 247	87.06 460	99.81 227	97.77 198	99.69 235	99.23 306

PAPM		91.88 506	90.34 508	96.51 448	98.06 454	92.56 475	92.44 535	97.17 465	86.35 539	90.38 544	96.01 489	86.61 463	99.21 488	70.65 552	95.43 535	97.75 484

Effi-MVS+-dtu		98.26 236	97.90 275	99.35 80	98.02 455	99.49 5	98.02 211	99.16 306	98.29 199	97.64 393	97.99 410	96.44 263	99.95 26	96.66 316	98.93 422	98.60 427

PRO-TEST		97.86 286	97.88 277	97.81 355	98.01 456	94.96 395	97.99 223	99.48 160	97.80 249	97.83 381	97.76 430	96.27 276	99.80 236	96.68 311	99.07 401	98.69 415

eth_miper_zixun_eth		97.23 346	97.25 328	97.17 416	98.00 457	92.77 472	94.71 484	99.18 299	97.27 312	98.56 309	98.74 299	91.89 415	99.69 332	97.06 269	99.81 141	99.05 348

ALIKED-LG		97.10 355	96.63 376	98.50 275	97.96 458	98.68 100	97.75 262	99.68 65	95.86 403	98.36 336	98.33 376	91.58 419	99.04 496	90.87 513	99.31 360	97.77 483

nomal-1		94.03 469	93.02 479	97.07 422	97.95 459	92.86 469	96.66 384	95.37 510	96.16 387	94.89 509	94.68 520	69.16 533	99.73 300	94.43 421	97.86 485	98.62 426

HY-MVS	95.94 13	95.90 423	95.35 431	97.55 392	97.95 459	94.79 404	98.81 98	96.94 475	92.28 502	95.17 503	98.57 341	89.90 438	99.75 286	91.20 504	97.33 505	98.10 463

UGNet		98.53 190	98.45 187	98.79 202	97.94 461	96.96 288	99.08 62	98.54 407	99.10 108	96.82 452	99.47 79	96.55 258	99.84 180	98.56 125	99.94 52	99.55 138
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		96.47 393	95.70 412	98.79 202	97.92 462	99.12 62	98.28 168	98.60 400	92.16 503	95.54 497	96.17 487	94.77 342	99.52 430	89.62 520	98.23 464	97.72 487
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		96.86 372	96.55 383	97.79 357	97.91 463	94.21 423	97.56 293	98.87 361	97.49 284	99.06 194	99.05 208	80.72 505	99.80 236	98.44 132	99.82 134	99.37 246

SIFT-NN-PointCN		96.06 411	96.11 402	95.91 478	97.88 464	97.73 215	93.49 524	97.51 450	93.22 485	96.57 464	98.26 384	96.23 278	96.60 543	92.54 481	99.27 369	93.40 537

API-MVS		97.04 362	96.91 354	97.42 404	97.88 464	98.23 144	98.18 180	98.50 411	97.57 272	97.39 420	96.75 474	96.77 241	99.15 493	90.16 517	99.02 409	94.88 530

PDCNetPlus		95.22 447	94.73 454	96.70 444	97.85 466	91.14 504	93.94 515	99.97 1	93.06 490	98.95 225	98.89 264	74.32 525	99.14 494	95.63 386	99.93 58	99.82 37

myMVS_eth3d28		92.92 492	92.31 487	94.77 504	97.84 467	87.59 532	96.19 420	96.11 494	97.08 330	94.27 517	93.49 529	66.07 543	98.78 510	91.78 492	97.93 484	97.92 473

miper_ehance_all_eth		97.06 360	97.03 343	97.16 418	97.83 468	93.06 462	94.66 489	99.09 319	95.99 397	98.69 281	98.45 359	92.73 400	99.61 391	96.79 295	99.03 406	98.82 391

cl____		97.02 363	96.83 359	97.58 386	97.82 469	94.04 432	94.66 489	99.16 306	97.04 332	98.63 292	98.71 305	88.68 450	99.69 332	97.00 272	99.81 141	99.00 360

DIV-MVS_self_test		97.02 363	96.84 358	97.58 386	97.82 469	94.03 433	94.66 489	99.16 306	97.04 332	98.63 292	98.71 305	88.69 448	99.69 332	97.00 272	99.81 141	99.01 357

FBQ-MVS		93.12 486	91.90 498	96.81 438	97.80 471	92.96 466	97.12 349	95.93 500	95.83 407	94.07 522	93.03 534	65.21 546	99.18 490	90.94 509	97.13 508	98.28 453

SIFT-NCMNet		96.30 401	96.40 392	96.03 474	97.80 471	97.68 219	92.34 536	96.94 475	95.55 420	98.84 255	98.63 331	94.17 363	97.63 530	93.57 450	99.71 218	92.77 546

CANet		97.87 285	97.76 286	98.19 315	97.75 473	95.51 361	96.76 372	99.05 327	97.74 255	96.93 440	98.21 390	95.59 312	99.89 98	97.86 189	99.93 58	99.19 322

UBG		93.25 484	92.32 486	96.04 473	97.72 474	90.16 515	95.92 442	95.91 501	96.03 394	93.95 527	93.04 533	69.60 532	99.52 430	90.72 515	97.98 482	98.45 438

mvsany_test1		97.60 311	97.54 307	97.77 359	97.72 474	95.35 375	95.36 465	97.13 467	94.13 469	99.71 50	99.33 119	97.93 142	99.30 479	97.60 218	98.94 421	98.67 422

PVSNet_0	89.98 21	91.15 507	90.30 509	93.70 519	97.72 474	84.34 546	90.24 541	97.42 451	90.20 522	93.79 528	93.09 532	90.90 430	98.89 508	86.57 533	72.76 555	97.87 476

CR-MVSNet		96.28 403	95.95 405	97.28 409	97.71 477	94.22 421	98.11 192	98.92 352	92.31 501	96.91 443	99.37 105	85.44 478	99.81 227	97.39 238	97.36 503	97.81 479

RPMNet		97.02 363	96.93 349	97.30 408	97.71 477	94.22 421	98.11 192	99.30 256	99.37 61	96.91 443	99.34 116	86.72 462	99.87 136	97.53 225	97.36 503	97.81 479

ETVMVS		92.60 495	91.08 504	97.18 414	97.70 479	93.65 455	96.54 392	95.70 505	96.51 366	94.68 513	92.39 539	61.80 553	99.50 437	86.97 529	97.41 499	98.40 446

pmmvs3		95.03 451	94.40 459	96.93 430	97.70 479	92.53 476	95.08 475	97.71 442	88.57 533	97.71 389	98.08 403	79.39 512	99.82 210	96.19 357	99.11 399	98.43 443

baseline2		93.73 475	92.83 482	96.42 452	97.70 479	91.28 499	96.84 367	89.77 548	93.96 477	92.44 537	95.93 492	79.14 513	99.77 268	92.94 466	96.76 516	98.21 456

WBMVS		95.18 448	94.78 450	96.37 454	97.68 482	89.74 521	95.80 448	98.73 390	97.54 279	98.30 337	98.44 360	70.06 530	99.82 210	96.62 319	99.87 101	99.54 144

tpm		94.67 456	94.34 461	95.66 488	97.68 482	88.42 526	97.88 239	94.90 514	94.46 457	96.03 486	98.56 343	78.66 516	99.79 250	95.88 371	95.01 537	98.78 403

ALIKED-MNN		95.97 420	95.30 435	98.00 339	97.66 484	98.12 153	96.98 355	99.41 206	91.11 516	94.04 524	97.30 461	91.56 420	98.61 515	89.99 518	99.63 264	97.28 503

CANet_DTU		97.26 342	97.06 342	97.84 352	97.57 485	94.65 412	96.19 420	98.79 378	97.23 320	95.14 504	98.24 387	93.22 386	99.84 180	97.34 240	99.84 115	99.04 352

testing11		93.08 488	92.02 493	96.26 459	97.56 486	90.83 509	96.32 410	95.70 505	96.47 371	92.66 535	93.73 525	64.36 548	99.59 400	93.77 443	97.57 490	98.37 450

tpm2		93.09 487	92.58 485	94.62 507	97.56 486	86.53 535	97.66 275	95.79 504	86.15 540	94.07 522	98.23 389	75.95 522	99.53 426	90.91 511	96.86 515	97.81 479

testing91		93.32 482	92.27 488	96.47 450	97.54 488	91.25 500	96.17 424	96.76 481	97.18 324	93.65 530	93.50 528	65.11 547	99.63 378	93.04 464	97.45 496	98.53 432

TR-MVS		95.55 435	95.12 443	96.86 437	97.54 488	93.94 441	96.49 397	96.53 487	94.36 464	97.03 438	96.61 477	94.26 361	99.16 492	86.91 531	96.31 521	97.47 496

testing99		93.04 489	91.98 496	96.23 462	97.53 490	90.70 512	96.35 408	95.94 499	96.87 347	93.41 531	93.43 530	63.84 549	99.59 400	93.24 460	97.19 506	98.40 446

1314		95.74 428	95.60 417	96.17 466	97.53 490	92.75 473	98.07 201	98.31 421	91.22 513	94.25 518	96.68 475	95.53 313	99.03 497	91.64 496	97.18 507	96.74 513

CostFormer		93.97 471	93.78 467	94.51 508	97.53 490	85.83 538	97.98 225	95.96 498	89.29 528	94.99 507	98.63 331	78.63 517	99.62 383	94.54 415	96.50 518	98.09 464

FMVSNet5		96.01 415	95.20 441	98.41 286	97.53 490	96.10 332	98.74 99	99.50 150	97.22 323	98.03 364	99.04 210	69.80 531	99.88 116	97.27 247	99.71 218	99.25 300

PMMVS		96.51 387	95.98 403	98.09 326	97.53 490	95.84 348	94.92 479	98.84 370	91.58 508	96.05 484	95.58 499	95.68 308	99.66 363	95.59 389	98.09 474	98.76 406

reproduce_monomvs		95.00 453	95.25 437	94.22 511	97.51 495	83.34 548	97.86 243	98.44 413	98.51 180	99.29 150	99.30 126	67.68 537	99.56 412	98.89 97	99.81 141	99.77 54

PAPR		95.29 444	94.47 456	97.75 363	97.50 496	95.14 389	94.89 481	98.71 392	91.39 512	95.35 501	95.48 504	94.57 347	99.14 494	84.95 536	97.37 501	98.97 366

testing222		91.96 504	90.37 507	96.72 443	97.47 497	92.59 474	96.11 427	94.76 515	96.83 351	92.90 533	92.87 535	57.92 555	99.55 417	86.93 530	97.52 492	98.00 470

PatchT		96.65 381	96.35 393	97.54 393	97.40 498	95.32 378	97.98 225	96.64 484	99.33 67	96.89 447	99.42 90	84.32 488	99.81 227	97.69 211	97.49 494	97.48 495

tpm cat1		93.29 483	93.13 478	93.75 518	97.39 499	84.74 541	97.39 316	97.65 446	83.39 545	94.16 519	98.41 363	82.86 500	99.39 465	91.56 498	95.35 536	97.14 505

PatchmatchNet		95.58 434	95.67 414	95.30 500	97.34 500	87.32 533	97.65 277	96.65 483	95.30 432	97.07 433	98.69 314	84.77 483	99.75 286	94.97 405	98.64 444	98.83 389
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SP-LightGlue		97.22 347	97.01 345	97.88 349	97.33 501	97.19 269	96.38 405	99.08 321	97.28 310	96.53 467	97.50 448	92.36 404	98.70 513	97.84 190	98.76 432	97.74 485

Patchmtry		97.35 334	96.97 347	98.50 275	97.31 502	96.47 320	98.18 180	98.92 352	98.95 132	98.78 266	99.37 105	85.44 478	99.85 159	95.96 369	99.83 127	99.17 330

LS3D		98.63 168	98.38 201	99.36 74	97.25 503	99.38 12	99.12 61	99.32 243	99.21 83	98.44 325	98.88 266	97.31 201	99.80 236	96.58 322	99.34 353	98.92 376

IB-MVS	91.63 19	92.24 501	90.90 505	96.27 458	97.22 504	91.24 501	94.36 501	93.33 533	92.37 500	92.24 539	94.58 522	66.20 542	99.89 98	93.16 462	94.63 539	97.66 489
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		92.38 498	91.76 501	94.21 512	97.16 505	84.65 542	95.42 463	88.45 550	95.96 398	96.17 478	95.84 496	66.36 540	99.71 313	91.87 491	98.64 444	98.28 453

tpmrst		95.07 450	95.46 424	93.91 516	97.11 506	84.36 545	97.62 282	96.96 473	94.98 442	96.35 476	98.80 286	85.46 477	99.59 400	95.60 388	96.23 522	97.79 482

Syy-MVS		96.04 413	95.56 421	97.49 398	97.10 507	94.48 415	96.18 422	96.58 485	95.65 415	94.77 511	92.29 541	91.27 426	99.36 468	98.17 156	98.05 478	98.63 424

myMVS_eth3d		91.92 505	90.45 506	96.30 456	97.10 507	90.90 507	96.18 422	96.58 485	95.65 415	94.77 511	92.29 541	53.88 556	99.36 468	89.59 522	98.05 478	98.63 424

blended_shiyan6		95.99 417	95.33 432	97.95 343	97.06 509	94.89 400	95.34 466	98.58 402	96.17 383	97.06 434	92.41 538	87.64 458	99.76 274	97.64 213	96.09 525	99.19 322

MDTV_nov1_ep13			95.22 439		97.06 509	83.20 550	97.74 264	96.16 492	94.37 463	96.99 439	98.83 279	83.95 492	99.53 426	93.90 437	97.95 483

blended_shiyan8		95.98 418	95.33 432	97.94 344	97.05 511	94.87 402	95.34 466	98.59 401	96.17 383	97.09 432	92.39 539	87.62 459	99.76 274	97.65 212	96.05 531	99.20 316

MASt3R-SfM		96.02 414	95.82 408	96.60 446	97.03 512	94.90 399	94.26 505	98.53 408	88.40 535	98.41 328	98.67 318	92.39 403	97.62 531	95.31 396	99.41 341	97.29 502

SP-SuperGlue		97.31 337	97.23 330	97.57 391	96.96 513	97.24 261	96.26 416	98.76 383	97.68 260	96.88 449	97.85 423	94.32 358	98.01 523	97.76 202	98.57 451	97.45 497

SIFT-NN		92.96 490	92.79 483	93.46 521	96.92 514	96.45 321	91.89 538	94.39 520	92.91 493	92.54 536	95.46 505	88.26 455	90.71 554	85.22 535	97.52 492	93.22 540

MVS		93.19 485	92.09 491	96.50 449	96.91 515	94.03 433	98.07 201	98.06 435	68.01 551	94.56 516	96.48 480	95.96 297	99.30 479	83.84 538	96.89 514	96.17 521

E-PMN		94.17 466	94.37 460	93.58 520	96.86 516	85.71 539	90.11 543	97.07 468	98.17 215	97.82 384	97.19 464	84.62 485	98.94 503	89.77 519	97.68 489	96.09 525

JIA-IIPM		95.52 436	95.03 444	97.00 425	96.85 517	94.03 433	96.93 360	95.82 502	99.20 85	94.63 515	99.71 23	83.09 498	99.60 395	94.42 422	94.64 538	97.36 500

EMVS		93.83 473	94.02 463	93.23 526	96.83 518	84.96 540	89.77 544	96.32 490	97.92 239	97.43 416	96.36 485	86.17 467	98.93 504	87.68 527	97.73 488	95.81 526

blend_shiyan4		92.09 503	90.16 510	97.88 349	96.78 519	94.93 397	95.24 470	98.58 402	96.22 381	96.07 482	91.42 543	63.46 552	99.73 300	96.70 308	76.98 553	98.98 362

cl22		95.79 427	95.39 429	96.98 427	96.77 520	92.79 471	94.40 499	98.53 408	94.59 454	97.89 374	98.17 393	82.82 501	99.24 485	96.37 343	99.03 406	98.92 376

SP-MNN		96.46 394	96.24 401	97.10 419	96.71 521	95.98 340	96.00 433	97.33 457	95.82 408	94.93 508	97.10 470	93.70 377	98.01 523	96.30 350	98.30 462	97.30 501

WB-MVSnew		95.73 429	95.57 420	96.23 462	96.70 522	90.70 512	96.07 430	93.86 529	95.60 417	97.04 436	95.45 509	96.00 290	99.55 417	91.04 506	98.31 461	98.43 443

dp		93.47 479	93.59 470	93.13 527	96.64 523	81.62 556	97.66 275	96.42 489	92.80 496	96.11 480	98.64 329	78.55 519	99.59 400	93.31 457	92.18 546	98.16 460

MonoMVSNet		96.25 406	96.53 385	95.39 496	96.57 524	91.01 505	98.82 97	97.68 445	98.57 175	98.03 364	99.37 105	90.92 429	97.78 528	94.99 403	93.88 542	97.38 499

wanda-best-256-512		95.48 438	94.74 452	97.68 371	96.53 525	94.12 427	94.17 507	98.57 404	95.84 404	96.71 456	91.16 544	86.05 470	99.76 274	97.57 220	96.09 525	99.17 330

FE-blended-shiyan7		95.48 438	94.74 452	97.68 371	96.53 525	94.12 427	94.17 507	98.57 404	95.84 404	96.71 456	91.16 544	86.05 470	99.76 274	97.57 220	96.09 525	99.17 330

usedtu_blend_shiyan5		96.20 409	95.62 415	97.94 344	96.53 525	94.93 397	98.83 96	99.59 101	98.89 139	96.71 456	91.16 544	86.05 470	99.73 300	96.70 308	96.09 525	99.17 330

test-LLR		93.90 472	93.85 465	94.04 514	96.53 525	84.62 543	94.05 512	92.39 536	96.17 383	94.12 520	95.07 510	82.30 502	99.67 350	95.87 374	98.18 467	97.82 477

test-mter		92.33 500	91.76 501	94.04 514	96.53 525	84.62 543	94.05 512	92.39 536	94.00 476	94.12 520	95.07 510	65.63 545	99.67 350	95.87 374	98.18 467	97.82 477

TESTMET0.1,1		92.19 502	91.77 500	93.46 521	96.48 530	82.80 552	94.05 512	91.52 544	94.45 460	94.00 525	94.88 516	66.65 539	99.56 412	95.78 379	98.11 473	98.02 467

MGCNet		97.44 325	97.01 345	98.72 222	96.42 531	96.74 304	97.20 341	91.97 542	98.46 183	98.30 337	98.79 288	92.74 399	99.91 75	99.30 63	99.94 52	99.52 162

miper_enhance_ethall		96.01 415	95.74 410	96.81 438	96.41 532	92.27 483	93.69 520	98.89 358	91.14 515	98.30 337	97.35 460	90.58 433	99.58 407	96.31 348	99.03 406	98.60 427

tpmvs		95.02 452	95.25 437	94.33 509	96.39 533	85.87 536	98.08 197	96.83 480	95.46 426	95.51 499	98.69 314	85.91 473	99.53 426	94.16 428	96.23 522	97.58 492

CMPMVS	75.91 23	96.29 402	95.44 426	98.84 189	96.25 534	98.69 99	97.02 351	99.12 314	88.90 530	97.83 381	98.86 269	89.51 443	98.90 507	91.92 489	99.51 312	98.92 376
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ALIKED-NN		94.29 464	93.41 473	96.94 429	96.18 535	97.66 220	94.90 480	98.68 393	88.85 531	90.43 543	96.81 473	89.82 439	96.59 544	86.67 532	98.33 458	96.58 516

test0.0.03 1		94.51 458	93.69 468	96.99 426	96.05 536	93.61 457	94.97 478	93.49 531	96.17 383	97.57 401	94.88 516	82.30 502	99.01 501	93.60 448	94.17 541	98.37 450

EPMVS		93.72 476	93.27 474	95.09 503	96.04 537	87.76 530	98.13 187	85.01 555	94.69 451	96.92 441	98.64 329	78.47 520	99.31 477	95.04 402	96.46 519	98.20 457

cascas		94.79 455	94.33 462	96.15 470	96.02 538	92.36 481	92.34 536	99.26 277	85.34 542	95.08 506	94.96 515	92.96 394	98.53 516	94.41 425	98.59 449	97.56 493

gbinet_0.2-2-1-0.02		95.44 440	94.55 455	98.14 320	95.99 539	95.34 377	94.71 484	98.29 422	96.00 396	96.05 484	90.50 548	84.99 480	99.79 250	97.33 242	97.07 511	99.28 289

MVStest1		95.86 424	95.60 417	96.63 445	95.87 540	91.70 488	97.93 231	98.94 345	98.03 229	99.56 75	99.66 33	71.83 528	98.26 519	99.35 59	99.24 375	99.91 14

gg-mvs-nofinetune		92.37 499	91.20 503	95.85 481	95.80 541	92.38 480	99.31 30	81.84 557	99.75 10	91.83 540	99.74 19	68.29 534	99.02 499	87.15 528	97.12 509	96.16 522

SP-DiffGlue		96.87 371	96.76 364	97.21 413	95.17 542	96.88 296	96.12 426	98.93 348	96.51 366	98.37 334	97.55 443	93.65 378	97.83 526	96.11 364	98.45 456	96.92 507

SP-NN		94.67 456	94.44 458	95.36 498	95.12 543	95.23 384	94.27 504	96.10 495	94.46 457	90.91 542	95.76 497	91.47 423	93.87 551	95.23 399	96.62 517	97.00 506

gm-plane-assit					94.83 544	81.97 554			88.07 537		94.99 513		99.60 395	91.76 493

GG-mvs-BLEND				94.76 505	94.54 545	92.13 485	99.31 30	80.47 558		88.73 548	91.01 547	67.59 538	98.16 522	82.30 544	94.53 540	93.98 531

UWE-MVS-28		90.22 508	89.28 511	93.02 528	94.50 546	82.87 551	96.52 395	87.51 551	95.21 437	92.36 538	96.04 488	71.57 529	98.25 520	72.04 551	97.77 487	97.94 472

EPNet_dtu		94.93 454	94.78 450	95.38 497	93.58 547	87.68 531	96.78 370	95.69 507	97.35 302	89.14 547	98.09 402	88.15 456	99.49 441	94.95 406	99.30 364	98.98 362
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
0.4-1-1-0.1		88.42 510	85.91 513	95.94 476	93.08 548	91.54 490	90.99 540	92.04 540	89.96 525	84.83 552	83.25 550	63.75 550	99.52 430	93.25 459	82.07 548	96.75 512

XFeat-MNN		93.41 481	92.98 481	94.68 506	92.63 549	92.92 467	89.72 545	95.81 503	92.10 504	97.23 427	96.29 486	84.95 481	97.31 536	89.60 521	98.54 453	93.81 533

dongtai		76.24 517	75.95 520	77.12 535	92.39 550	67.91 561	90.16 542	59.44 563	82.04 546	89.42 546	94.67 521	49.68 558	81.74 555	48.06 556	77.66 552	81.72 550

0.3-1-1-0.015		87.27 512	84.50 516	95.57 490	91.70 551	90.77 510	89.41 546	92.04 540	88.98 529	82.46 554	81.35 551	60.36 554	99.50 437	92.96 465	81.23 550	96.45 517

KD-MVS_2432*1600		92.87 493	91.99 494	95.51 493	91.37 552	89.27 523	94.07 510	98.14 430	95.42 428	97.25 425	96.44 482	67.86 535	99.24 485	91.28 502	96.08 529	98.02 467

miper_refine_blended		92.87 493	91.99 494	95.51 493	91.37 552	89.27 523	94.07 510	98.14 430	95.42 428	97.25 425	96.44 482	67.86 535	99.24 485	91.28 502	96.08 529	98.02 467

0.4-1-1-0.2		87.49 511	84.89 514	95.31 499	91.33 554	90.08 518	88.47 547	92.07 539	88.70 532	84.06 553	81.08 552	63.62 551	99.49 441	92.93 467	81.71 549	96.37 518

XFeat-NN		89.63 509	89.13 512	91.14 530	90.93 555	90.02 519	84.90 548	94.05 528	88.10 536	92.89 534	93.33 531	78.74 515	90.89 553	83.46 539	95.72 533	92.52 548

EPNet		96.14 410	95.44 426	98.25 306	90.76 556	95.50 365	97.92 234	94.65 516	98.97 128	92.98 532	98.85 272	89.12 446	99.87 136	95.99 367	99.68 241	99.39 234
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 518	68.95 521	70.34 536	87.68 557	65.00 562	91.11 539	59.90 562	69.02 550	74.46 556	88.89 549	48.58 560	68.03 557	28.61 557	72.33 556	77.99 551

GLUNet-SfM		86.26 513	84.68 515	91.01 531	80.58 558	83.56 547	78.04 549	93.59 530	76.70 549	95.29 502	94.72 519	77.51 521	94.26 550	66.39 553	99.33 355	95.20 529

test_method		79.78 515	79.50 518	80.62 533	80.21 559	45.76 564	70.82 550	98.41 418	31.08 555	80.89 555	97.71 433	84.85 482	97.37 534	91.51 499	80.03 551	98.75 407

MVS_clip		56.94 520	60.93 522	44.97 538	71.47 560	51.70 563	61.73 551	21.77 564	28.88 556	86.09 551	92.75 537	48.89 559	27.00 559	61.70 554	75.08 554	56.23 553

tmp_tt		78.77 516	78.73 519	78.90 534	58.45 561	74.76 560	94.20 506	78.26 559	39.16 554	86.71 549	92.82 536	80.50 506	75.19 556	86.16 534	92.29 545	86.74 549

VLMVS_CLIP		57.57 519	58.80 523	53.85 537	47.22 562	42.89 565	60.06 552	76.87 560	39.44 553	65.76 557	80.47 553	36.24 561	64.75 558	58.06 555	65.11 557	53.91 554

VLMVS		32.15 521	34.06 524	26.43 539	35.38 563	29.60 566	32.69 553	19.27 565	3.29 560	44.01 559	60.07 555	35.02 562	20.44 560	22.64 558	54.15 559	29.25 555

MVS_baseline		25.61 522	31.27 526	8.63 540	32.09 564	3.00 569	22.13 554	5.43 567	1.36 561	58.03 558	69.99 554	18.40 563	0.00 563	18.79 559	55.18 558	22.88 556

testmvs		17.12 524	20.53 527	6.87 542	12.05 565	4.20 568	93.62 522	6.73 566	4.62 559	10.41 561	24.33 557	8.28 565	3.56 562	9.69 561	15.07 560	12.86 558

test123		17.04 525	20.11 528	7.82 541	10.25 566	4.91 567	94.80 482	4.47 568	4.93 558	10.00 562	24.28 558	9.69 564	3.64 561	10.14 560	12.43 561	14.92 557

PatchmatchNet2					0.00 567	90.12 516	94.29 503	98.12 432	94.40 462
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
mmdepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

eth-test2					0.00 567

eth-test					0.00 567

uanet_test		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

cdsmvs_eth3d_5k		24.66 523	32.88 525	0.00 543	0.00 567	0.00 570	0.00 555	99.10 317	0.00 562	0.00 563	97.58 441	99.21 18	0.00 563	0.00 562	0.00 562	0.00 559

pcd_1.5k_mvsjas		8.17 526	10.90 529	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	98.07 129	0.00 563	0.00 562	0.00 562	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

ab-mvs-re		8.12 527	10.83 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	97.48 450	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet1														96.95 280	99.71 218	99.28 289
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.85 159
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						90.90 507								91.37 501

PC_three_1452									93.27 484	99.40 118	98.54 344	98.22 114	97.00 538	95.17 400	99.45 329	99.49 178

test_241102_TWO								99.30 256	98.03 229	99.26 158	99.02 214	97.51 186	99.88 116	96.91 282	99.60 277	99.66 81

test_0728_THIRD									98.17 215	99.08 192	99.02 214	97.89 148	99.88 116	97.07 267	99.71 218	99.70 71

GSMVS																98.81 396

sam_mvs1												84.74 484				98.81 396

sam_mvs												84.29 490

MTGPA								99.20 291

test_post1							97.59 290				20.48 560	83.07 499	99.66 363	94.16 428

test_post											21.25 559	83.86 493	99.70 322

patchmatchnet-post											98.77 292	84.37 487	99.85 159

MTMP							97.93 231	91.91 543

test9_res														93.28 458	99.15 392	99.38 243

agg_prior2														92.50 482	99.16 390	99.37 246

test_prior4						97.97 178	95.86 444

test_prior2							95.74 451		96.48 370	96.11 480	97.63 439	95.92 300		94.16 428	99.20 384

旧先验2							95.76 450		88.56 534	97.52 405			99.66 363	94.48 417

新几何2							95.93 440

无先验							95.74 451	98.74 389	89.38 527				99.73 300	92.38 485		99.22 311

原ACMM2							95.53 457

testdata2													99.79 250	92.80 473

segment_acmp												97.02 222

testdata1							95.44 462		96.32 377

plane_prior5								99.27 271					99.70 322	94.42 422	99.51 312	99.45 207

plane_prior4											97.98 411

plane_prior3						97.78 208			97.41 295	97.79 385

plane_prior2							97.77 256		98.20 211

plane_prior						97.65 222	97.07 350		96.72 357						99.36 348

n2								0.00 569

nn								0.00 569

door-mid								99.57 112

test11								98.87 361

door								99.41 206

HQP5-MVS						96.79 300

BP-MVS														92.82 471

HQP4-MVS										95.56 493			99.54 423			99.32 275

HQP3-MVS								99.04 330							99.26 373

HQP2-MVS												93.84 371

MDTV_nov1_ep13_2view						74.92 559	97.69 270		90.06 524	97.75 388		85.78 474		93.52 451		98.69 415

ACMMP++_ref															99.77 173

ACMMP++															99.68 241

Test By Simon												96.52 259

High-resolution multi-view benchmark