High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 70	99.12 242	100.00 1	100.00 1	99.99 7	99.91 31	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 41	99.82 95	99.70 108	99.17 217	99.97 20	99.99 3	99.96 34	99.82 90	99.94 4	100.00 1	99.95 14	100.00 1	99.80 66

h-mvs33		98.61 326	98.34 342	99.44 256	99.60 244	98.67 330	99.27 179	99.44 332	99.68 132	99.32 328	99.49 328	92.50 419	100.00 1	99.24 137	96.51 487	99.65 157

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 20	99.99 3	100.00 1	99.98 13	99.78 23	100.00 1	99.92 30	100.00 1	99.87 44

DSMNet-mixed		99.48 131	99.65 74	98.95 364	99.71 192	97.27 423	99.50 102	99.82 104	99.59 170	99.41 305	99.85 68	99.62 40	100.00 1	99.53 89	99.89 174	99.59 212

HyFIR lowres test		98.91 294	98.64 309	99.73 113	99.85 73	99.47 184	98.07 418	99.83 98	98.64 332	99.89 72	99.60 279	92.57 416	100.00 1	99.33 125	99.97 73	99.72 98

NormalMVS		99.09 258	98.91 284	99.62 181	99.78 138	99.11 279	99.36 144	99.77 147	99.82 85	99.68 195	99.53 315	93.30 405	99.99 7	99.24 137	99.76 270	99.74 90

SymmetryMVS		99.01 278	98.82 294	99.58 197	99.65 234	99.11 279	99.36 144	99.20 398	99.82 85	99.68 195	99.53 315	93.30 405	99.99 7	99.24 137	99.63 329	99.64 169

Elysia		99.69 59	99.65 74	99.81 54	99.86 59	99.72 95	99.34 148	99.77 147	99.94 36	99.91 62	99.76 152	98.55 214	99.99 7	99.70 61	99.98 50	99.72 98

StellarMVS		99.69 59	99.65 74	99.81 54	99.86 59	99.72 95	99.34 148	99.77 147	99.94 36	99.91 62	99.76 152	98.55 214	99.99 7	99.70 61	99.98 50	99.72 98

fmvsm_s_conf0.5_n_5		99.78 37	99.76 49	99.85 32	99.79 130	99.72 95	98.84 325	99.96 28	99.96 28	99.96 34	99.72 178	99.71 28	99.99 7	99.93 25	99.98 50	99.85 49

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 45	99.86 18	99.08 258	99.97 20	99.98 18	99.96 34	99.79 119	99.90 9	99.99 7	99.96 9	99.99 16	99.90 29

fmvsm_l_conf0.5_n_a		99.80 30	99.79 34	99.84 38	99.88 45	99.64 133	99.12 242	99.91 51	99.98 18	99.95 45	99.67 223	99.67 34	99.99 7	99.94 20	99.99 16	99.88 40

fmvsm_l_conf0.5_n		99.80 30	99.78 39	99.85 32	99.88 45	99.66 120	99.11 247	99.91 51	99.98 18	99.96 34	99.64 237	99.60 44	99.99 7	99.95 14	99.99 16	99.88 40

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 87	99.01 282	99.99 11	99.99 3	99.98 14	99.88 50	99.97 2	99.99 7	99.96 9	100.00 1	99.98 5

SSC-MVS		99.52 120	99.42 144	99.83 41	99.86 59	99.65 126	99.52 94	99.81 117	99.87 62	99.81 116	99.79 119	96.78 344	99.99 7	99.83 46	99.51 365	99.86 46

test_fmvsmconf_n		99.85 12	99.84 20	99.88 19	99.91 31	99.73 90	98.97 300	99.98 12	99.99 3	99.96 34	99.85 68	99.93 7	99.99 7	99.94 20	99.99 16	99.93 20

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 54	99.88 45	99.55 170	99.17 217	99.98 12	99.99 3	99.96 34	99.84 76	99.96 3	99.99 7	99.96 9	99.99 16	99.88 40

SDMVSNet		99.77 44	99.77 45	99.76 87	99.80 116	99.65 126	99.63 64	99.86 76	99.97 25	99.89 72	99.89 41	99.52 60	99.99 7	99.42 110	99.96 87	99.65 157

sd_testset		99.78 37	99.78 39	99.80 64	99.80 116	99.76 70	99.80 14	99.79 131	99.97 25	99.89 72	99.89 41	99.53 58	99.99 7	99.36 118	99.96 87	99.65 157

test_vis1_n_1920		99.72 53	99.88 7	99.27 319	99.93 24	97.84 398	99.34 148	100.00 1	99.99 3	99.99 7	99.82 90	99.87 13	99.99 7	99.97 4	99.99 16	99.97 10

test_fmvs3		99.83 21	99.93 2	99.53 226	99.96 7	98.62 340	99.67 53	100.00 1	99.95 32	100.00 1	99.95 16	99.85 14	99.99 7	99.98 1	99.99 16	99.98 5

dcpmvs_2		99.61 96	99.64 79	99.53 226	99.79 130	98.82 317	99.58 82	99.97 20	99.95 32	99.96 34	99.76 152	98.44 235	99.99 7	99.34 122	99.96 87	99.78 76

IterMVS-SCA-FT		99.00 281	99.16 206	98.51 410	99.75 171	95.90 456	98.07 418	99.84 89	99.84 75	99.89 72	99.73 170	96.01 371	99.99 7	99.33 125	100.00 1	99.63 175

IterMVS		98.97 285	99.16 206	98.42 415	99.74 179	95.64 460	98.06 420	99.83 98	99.83 81	99.85 99	99.74 165	96.10 370	99.99 7	99.27 136	100.00 1	99.63 175
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_11		99.76 46	99.75 51	99.81 54	99.81 107	99.53 173	99.15 226	99.89 60	99.99 3	99.98 14	99.86 63	99.13 117	99.98 26	99.93 25	99.99 16	99.92 24

fmvsm_s_conf0.5_n_10		99.77 44	99.73 54	99.88 19	99.81 107	99.75 79	99.06 264	99.85 82	99.99 3	99.97 24	99.84 76	99.12 120	99.98 26	99.95 14	99.99 16	99.90 29

fmvsm_l_conf0.5_n_9		99.83 21	99.81 28	99.89 11	99.86 59	99.80 51	98.94 309	99.96 28	99.98 18	99.96 34	99.78 132	99.88 11	99.98 26	99.96 9	99.99 16	99.90 29

GDP-MVS		98.81 309	98.57 318	99.50 234	99.53 290	99.12 278	99.28 175	99.86 76	99.53 178	99.57 248	99.32 374	90.88 440	99.98 26	99.46 100	99.74 281	99.42 311

WB-MVS		99.44 150	99.32 173	99.80 64	99.81 107	99.61 151	99.47 112	99.81 117	99.82 85	99.71 183	99.72 178	96.60 349	99.98 26	99.75 56	99.23 406	99.82 65

test_fmvs1_n		99.68 64	99.81 28	99.28 314	99.95 15	97.93 394	99.49 107	100.00 1	99.82 85	99.99 7	99.89 41	99.21 103	99.98 26	99.97 4	99.98 50	99.93 20

test_fmvs2		99.72 53	99.85 17	99.34 294	99.91 31	98.08 385	99.48 109	100.00 1	99.90 49	99.99 7	99.91 31	99.50 62	99.98 26	99.98 1	99.99 16	99.96 13

patch_mono-2		99.51 121	99.46 133	99.64 165	99.70 207	99.11 279	99.04 270	99.87 69	99.71 121	99.47 286	99.79 119	98.24 258	99.98 26	99.38 114	99.96 87	99.83 58

CHOSEN 280x420		98.41 351	98.41 334	98.40 416	99.34 363	95.89 457	96.94 482	99.44 332	98.80 312	99.25 344	99.52 319	93.51 404	99.98 26	98.94 200	99.98 50	99.32 339

Fast-Effi-MVS+-dtu		99.20 227	99.12 217	99.43 260	99.25 385	99.69 112	99.05 265	99.82 104	99.50 183	98.97 378	99.05 419	98.98 151	99.98 26	98.20 277	99.24 404	98.62 451

Effi-MVS+-dtu		99.07 262	98.92 280	99.52 228	98.89 441	99.78 57	99.15 226	99.66 213	99.34 223	98.92 385	99.24 395	97.69 305	99.98 26	98.11 287	99.28 397	98.81 440

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 63	99.68 48	99.85 82	99.95 32	99.98 14	99.92 27	99.28 92	99.98 26	99.75 56	100.00 1	99.94 17

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 57	99.70 38	99.86 76	99.89 55	99.98 14	99.90 36	99.94 4	99.98 26	99.75 56	100.00 1	99.90 29

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 54	99.72 33	99.88 65	99.92 45	99.98 14	99.93 22	99.94 4	99.98 26	99.77 55	100.00 1	99.92 24

MVSFormer		99.41 163	99.44 140	99.31 306	99.57 267	98.40 359	99.77 19	99.80 122	99.73 111	99.63 221	99.30 379	98.02 281	99.98 26	99.43 105	99.69 308	99.55 230

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 26	99.77 19	99.80 122	99.73 111	99.97 24	99.92 27	99.77 25	99.98 26	99.43 105	100.00 1	99.90 29

Vis-MVSNet		99.75 49	99.74 53	99.79 72	99.88 45	99.66 120	99.69 45	99.92 42	99.67 140	99.77 144	99.75 160	99.61 41	99.98 26	99.35 121	99.98 50	99.72 98
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSM_04072		99.55 109	99.55 110	99.55 216	99.71 192	99.24 254	99.27 179	99.79 131	99.72 115	99.78 132	99.64 237	99.36 80	99.97 43	98.74 226	99.90 160	99.45 285

KinetiMVS		99.66 77	99.63 82	99.76 87	99.89 39	99.57 165	99.37 140	99.82 104	99.95 32	99.90 67	99.63 252	98.57 210	99.97 43	99.65 70	99.94 128	99.74 90

LuminaMVS		99.39 169	99.28 188	99.73 113	99.83 86	99.49 180	99.00 288	99.05 412	99.81 91	99.89 72	99.79 119	96.54 353	99.97 43	99.64 73	99.98 50	99.73 94

fmvsm_s_conf0.5_n_8		99.76 46	99.72 55	99.88 19	99.82 95	99.75 79	99.02 277	99.87 69	99.98 18	99.98 14	99.81 97	99.07 131	99.97 43	99.91 33	99.99 16	99.92 24

mvs5depth		99.88 6	99.91 3	99.80 64	99.92 29	99.42 205	99.94 3	100.00 1	99.97 25	99.89 72	99.99 12	99.63 37	99.97 43	99.87 44	99.99 16	100.00 1

test_cas_vis1_n_1920		99.76 46	99.86 13	99.45 252	99.93 24	98.40 359	99.30 166	99.98 12	99.94 36	99.99 7	99.89 41	99.80 21	99.97 43	99.96 9	99.97 73	99.97 10

test_fmvs1		99.48 131	99.65 74	98.97 361	99.54 283	97.16 426	99.11 247	99.98 12	99.78 102	99.96 34	99.81 97	98.72 190	99.97 43	99.95 14	99.97 73	99.79 74

Anonymous20240521		99.44 150	99.42 144	99.49 238	99.89 39	98.96 301	99.62 67	99.76 155	99.85 71	99.82 109	99.88 50	96.39 360	99.97 43	99.59 78	99.98 50	99.55 230

xiu_mvs_v1_base_debu		99.23 211	99.34 167	98.91 374	99.59 250	98.23 368	98.47 382	99.66 213	99.61 162	99.68 195	98.94 437	99.39 71	99.97 43	99.18 151	99.55 354	98.51 461

xiu_mvs_v2_base		99.02 272	99.11 220	98.77 395	99.37 347	98.09 382	98.13 410	99.51 311	99.47 193	99.42 299	98.54 461	99.38 75	99.97 43	98.83 208	99.33 390	98.24 473

xiu_mvs_v1_base		99.23 211	99.34 167	98.91 374	99.59 250	98.23 368	98.47 382	99.66 213	99.61 162	99.68 195	98.94 437	99.39 71	99.97 43	99.18 151	99.55 354	98.51 461

xiu_mvs_v1_base_debi		99.23 211	99.34 167	98.91 374	99.59 250	98.23 368	98.47 382	99.66 213	99.61 162	99.68 195	98.94 437	99.39 71	99.97 43	99.18 151	99.55 354	98.51 461

anonymousdsp		99.80 30	99.77 45	99.90 8	99.96 7	99.88 12	99.73 30	99.85 82	99.70 127	99.92 59	99.93 22	99.45 63	99.97 43	99.36 118	100.00 1	99.85 49

UA-Net		99.78 37	99.76 49	99.86 30	99.72 188	99.71 100	99.91 4	99.95 36	99.96 28	99.71 183	99.91 31	99.15 112	99.97 43	99.50 94	100.00 1	99.90 29

PS-MVSNAJ		99.00 281	99.08 232	98.76 396	99.37 347	98.10 381	98.00 426	99.51 311	99.47 193	99.41 305	98.50 463	99.28 92	99.97 43	98.83 208	99.34 389	98.20 477

pmmvs3		98.08 375	97.80 384	98.91 374	99.41 340	97.69 406	97.87 439	99.66 213	95.87 462	99.50 281	99.51 321	90.35 449	99.97 43	98.55 249	99.47 372	99.08 401

DTE-MVSNet		99.68 64	99.61 88	99.88 19	99.80 116	99.87 15	99.67 53	99.71 183	99.72 115	99.84 102	99.78 132	98.67 197	99.97 43	99.30 130	99.95 111	99.80 66

jason		99.16 240	99.11 220	99.32 302	99.75 171	98.44 356	98.26 399	99.39 348	98.70 325	99.74 168	99.30 379	98.54 218	99.97 43	98.48 252	99.82 233	99.55 230
jason: jason.
lupinMVS		98.96 288	98.87 287	99.24 327	99.57 267	98.40 359	98.12 411	99.18 400	98.28 375	99.63 221	99.13 407	98.02 281	99.97 43	98.22 275	99.69 308	99.35 329

K. test v3		98.87 301	98.60 312	99.69 137	99.93 24	99.46 190	99.74 27	94.97 490	99.78 102	99.88 82	99.88 50	93.66 402	99.97 43	99.61 76	99.95 111	99.64 169

lessismore_v0				99.64 165	99.86 59	99.38 218		90.66 500		99.89 72	99.83 83	94.56 392	99.97 43	99.56 83	99.92 146	99.57 223

EPNet		98.13 372	97.77 387	99.18 334	94.57 504	97.99 388	99.24 191	97.96 462	99.74 110	97.29 474	99.62 261	93.13 409	99.97 43	98.59 246	99.83 223	99.58 217
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		99.40 165	99.38 153	99.44 256	99.90 37	98.66 333	98.94 309	99.91 51	97.97 393	99.79 128	99.73 170	99.05 139	99.97 43	99.15 157	99.99 16	99.68 125

IterMVS-LS		99.41 163	99.47 128	99.25 325	99.81 107	98.09 382	98.85 323	99.76 155	99.62 157	99.83 108	99.64 237	98.54 218	99.97 43	99.15 157	99.99 16	99.68 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 62	100.00 1	99.90 49	100.00 1	99.97 14	99.61 41	99.97 43	99.75 56	100.00 1	99.84 54

usedtu_dtu_shiyan2		99.44 150	99.33 172	99.78 76	99.86 59	99.76 70	99.54 90	99.79 131	99.66 144	99.66 209	99.79 119	96.76 345	99.96 68	99.15 157	99.72 294	99.62 187

fmvsm_s_conf0.5_n_7		99.73 52	99.78 39	99.60 191	99.74 179	98.93 306	98.85 323	99.96 28	99.96 28	99.97 24	99.76 152	99.82 18	99.96 68	99.95 14	99.98 50	99.90 29

BP-MVS1		98.72 318	98.46 328	99.50 234	99.53 290	99.00 293	99.34 148	98.53 439	99.65 148	99.73 173	99.38 357	90.62 445	99.96 68	99.50 94	99.86 205	99.55 230

MVSMamba_PlusPlus		99.55 109	99.58 98	99.47 245	99.68 221	99.40 213	99.52 94	99.70 192	99.92 45	99.77 144	99.86 63	98.28 254	99.96 68	99.54 86	99.90 160	99.05 408

test_vis1_n		99.68 64	99.79 34	99.36 289	99.94 18	98.18 374	99.52 94	100.00 1	99.86 65	100.00 1	99.88 50	98.99 147	99.96 68	99.97 4	99.96 87	99.95 14

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 183	99.93 43	99.95 45	99.89 41	99.71 28	99.96 68	99.51 92	99.97 73	99.84 54

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 26	99.82 10	99.82 104	99.84 75	99.94 48	99.91 31	99.13 117	99.96 68	99.83 46	99.99 16	99.83 58

PS-CasMVS		99.66 77	99.58 98	99.89 11	99.80 116	99.85 21	99.66 57	99.73 170	99.62 157	99.84 102	99.71 188	98.62 203	99.96 68	99.30 130	99.96 87	99.86 46

PEN-MVS		99.66 77	99.59 94	99.89 11	99.83 86	99.87 15	99.66 57	99.73 170	99.70 127	99.84 102	99.73 170	98.56 213	99.96 68	99.29 133	99.94 128	99.83 58

TranMVSNet+NR-MVSNet		99.54 114	99.47 128	99.76 87	99.58 257	99.64 133	99.30 166	99.63 235	99.61 162	99.71 183	99.56 303	98.76 183	99.96 68	99.14 164	99.92 146	99.68 125

IB-MVS	95.41 20	95.30 456	94.46 460	97.84 440	98.76 459	95.33 465	97.33 466	96.07 482	96.02 461	95.37 493	97.41 483	76.17 495	99.96 68	97.54 346	95.44 494	98.22 474
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
OpenMVS	98.12 10	98.23 366	97.89 382	99.26 322	99.19 397	99.26 246	99.65 62	99.69 200	91.33 490	98.14 449	99.77 144	98.28 254	99.96 68	95.41 456	99.55 354	98.58 456

IMVS_0404		99.23 211	99.20 201	99.32 302	99.71 192	98.55 346	98.57 367	99.71 183	99.41 213	99.52 271	99.60 279	98.12 273	99.95 80	98.45 255	99.70 300	99.45 285

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 32	99.81 107	99.71 100	98.97 300	99.92 42	99.98 18	99.97 24	99.86 63	99.53 58	99.95 80	99.88 41	99.99 16	99.89 37

MM		99.18 234	99.05 243	99.55 216	99.35 354	98.81 318	99.05 265	97.79 468	99.99 3	99.48 284	99.59 289	96.29 365	99.95 80	99.94 20	99.98 50	99.88 40

GeoE		99.69 59	99.66 72	99.78 76	99.76 155	99.76 70	99.60 79	99.82 104	99.46 196	99.75 158	99.56 303	99.63 37	99.95 80	99.43 105	99.88 184	99.62 187

CS-MVS		99.67 76	99.70 57	99.58 197	99.53 290	99.84 26	99.79 15	99.96 28	99.90 49	99.61 237	99.41 347	99.51 61	99.95 80	99.66 69	99.89 174	98.96 421

CANet_DTU		98.91 294	98.85 289	99.09 346	98.79 454	98.13 377	98.18 403	99.31 371	99.48 188	98.86 393	99.51 321	96.56 350	99.95 80	99.05 179	99.95 111	99.19 370

MGCNet		98.61 326	98.30 347	99.52 228	97.88 489	98.95 302	98.76 342	94.11 495	99.84 75	99.32 328	99.57 299	95.57 377	99.95 80	99.68 66	99.98 50	99.68 125

SPE-MVS-test		99.68 64	99.70 57	99.64 165	99.57 267	99.83 33	99.78 17	99.97 20	99.92 45	99.50 281	99.38 357	99.57 52	99.95 80	99.69 64	99.90 160	99.15 379

Fast-Effi-MVS+		99.02 272	98.87 287	99.46 249	99.38 345	99.50 179	99.04 270	99.79 131	97.17 441	98.62 416	98.74 451	99.34 84	99.95 80	98.32 267	99.41 380	98.92 428

MTAPA		99.35 183	99.20 201	99.80 64	99.81 107	99.81 47	99.33 154	99.53 301	99.27 235	99.42 299	99.63 252	98.21 264	99.95 80	97.83 316	99.79 255	99.65 157

UniMVSNet_NR-MVSNet		99.37 176	99.25 195	99.72 121	99.47 321	99.56 166	98.97 300	99.61 246	99.43 208	99.67 203	99.28 383	97.85 295	99.95 80	99.17 154	99.81 243	99.65 157

DU-MVS		99.33 191	99.21 200	99.71 127	99.43 333	99.56 166	98.83 328	99.53 301	99.38 218	99.67 203	99.36 365	97.67 307	99.95 80	99.17 154	99.81 243	99.63 175

CP-MVSNet		99.54 114	99.43 142	99.87 26	99.76 155	99.82 41	99.57 85	99.61 246	99.54 176	99.80 122	99.64 237	97.79 299	99.95 80	99.21 143	99.94 128	99.84 54

Patchmtry		98.78 311	98.54 323	99.49 238	98.89 441	99.19 267	99.32 157	99.67 208	99.65 148	99.72 178	99.79 119	91.87 427	99.95 80	98.00 296	99.97 73	99.33 335

QAPM		98.40 353	97.99 369	99.65 158	99.39 342	99.47 184	99.67 53	99.52 306	91.70 489	98.78 404	99.80 107	98.55 214	99.95 80	94.71 467	99.75 274	99.53 246

3Dnovator	99.15 2	99.43 154	99.36 161	99.65 158	99.39 342	99.42 205	99.70 38	99.56 279	99.23 243	99.35 319	99.80 107	99.17 108	99.95 80	98.21 276	99.84 215	99.59 212

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 19	99.91 31	99.90 7	99.96 1	99.92 42	99.90 49	99.97 24	99.87 56	99.81 20	99.95 80	99.54 86	99.99 16	99.80 66
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
fmvsm_s_conf0.5_n_9		99.82 24	99.82 25	99.82 46	99.83 86	99.59 157	98.97 300	99.92 42	99.99 3	99.97 24	99.84 76	99.90 9	99.94 97	99.94 20	99.99 16	99.92 24

fmvsm_s_conf0.5_n_2		99.78 37	99.75 51	99.88 19	99.82 95	99.76 70	98.88 317	99.92 42	99.98 18	99.98 14	99.85 68	99.42 69	99.94 97	99.93 25	99.98 50	99.94 17

fmvsm_s_conf0.1_n_2		99.81 28	99.78 39	99.89 11	99.93 24	99.76 70	98.92 313	99.98 12	99.99 3	99.99 7	99.88 50	99.43 67	99.94 97	99.94 20	99.99 16	99.99 2

mmtdpeth		99.78 37	99.83 21	99.66 151	99.85 73	99.05 292	99.79 15	99.97 20	100.00 1	99.43 296	99.94 19	99.64 35	99.94 97	99.83 46	99.99 16	99.98 5

mvsany_test3		99.85 12	99.88 7	99.75 98	99.95 15	99.37 223	99.53 92	99.98 12	99.77 106	99.99 7	99.95 16	99.85 14	99.94 97	99.95 14	99.98 50	99.94 17

test_f		99.75 49	99.88 7	99.37 284	99.96 7	98.21 371	99.51 101	100.00 1	99.94 36	100.00 1	99.93 22	99.58 50	99.94 97	99.97 4	99.99 16	99.97 10

test_method		91.72 462	92.32 462	89.91 482	93.49 505	70.18 508	90.28 496	99.56 279	61.71 500	95.39 492	99.52 319	93.90 396	99.94 97	98.76 224	98.27 458	99.62 187

tttt0517		97.62 395	97.20 405	98.90 380	99.76 155	97.40 419	99.48 109	94.36 492	99.06 273	99.70 187	99.49 328	84.55 474	99.94 97	98.73 231	99.65 324	99.36 326

CANet		99.11 254	99.05 243	99.28 314	98.83 448	98.56 344	98.71 349	99.41 338	99.25 239	99.23 348	99.22 397	97.66 311	99.94 97	99.19 149	99.97 73	99.33 335

patchmatchnet-post											99.62 261	90.58 446	99.94 97

SCA		98.11 373	98.36 339	97.36 455	99.20 395	92.99 484	98.17 405	98.49 443	98.24 377	99.10 369	99.57 299	96.01 371	99.94 97	96.86 393	99.62 331	99.14 384

balanced_ft_v1		99.37 176	99.36 161	99.38 279	99.10 416	99.38 218	99.68 48	99.72 179	99.72 115	99.36 316	99.77 144	97.66 311	99.94 97	99.52 90	99.73 287	98.83 438

ADS-MVSNet2		97.78 388	97.66 392	98.12 430	99.14 405	95.36 464	99.22 199	98.75 427	96.97 446	98.25 438	99.64 237	90.90 438	99.94 97	96.51 415	99.56 350	99.08 401

WR-MVS_H		99.61 96	99.53 117	99.87 26	99.80 116	99.83 33	99.67 53	99.75 160	99.58 172	99.85 99	99.69 207	98.18 269	99.94 97	99.28 135	99.95 111	99.83 58

mvsmamba		99.08 259	98.95 274	99.45 252	99.36 350	99.18 272	99.39 129	98.81 424	99.37 219	99.35 319	99.70 198	96.36 362	99.94 97	98.66 240	99.59 345	99.22 360

SixPastTwentyTwo		99.42 157	99.30 180	99.76 87	99.92 29	99.67 118	99.70 38	99.14 405	99.65 148	99.89 72	99.90 36	96.20 367	99.94 97	99.42 110	99.92 146	99.67 134

CP-MVS		99.23 211	99.05 243	99.75 98	99.66 230	99.66 120	99.38 132	99.62 238	98.38 360	99.06 374	99.27 385	98.79 178	99.94 97	97.51 349	99.82 233	99.66 148

SteuartSystems-ACMMP		99.30 195	99.14 211	99.76 87	99.87 54	99.66 120	99.18 212	99.60 257	98.55 341	99.57 248	99.67 223	99.03 142	99.94 97	97.01 384	99.80 250	99.69 118
Skip Steuart: Steuart Systems R&D Blog.
PatchT		98.45 348	98.32 344	98.83 389	98.94 436	98.29 366	99.24 191	98.82 422	99.84 75	99.08 370	99.76 152	91.37 430	99.94 97	98.82 210	99.00 419	98.26 472

new_pmnet		98.88 300	98.89 285	98.84 387	99.70 207	97.62 407	98.15 407	99.50 315	97.98 392	99.62 231	99.54 313	98.15 270	99.94 97	97.55 345	99.84 215	98.95 423

wuyk23d		97.58 397	99.13 213	92.93 480	99.69 213	99.49 180	99.52 94	99.77 147	97.97 393	99.96 34	99.79 119	99.84 16	99.94 97	95.85 446	99.82 233	79.36 498

3Dnovator+	98.92 3	99.35 183	99.24 197	99.67 143	99.35 354	99.47 184	99.62 67	99.50 315	99.44 201	99.12 366	99.78 132	98.77 182	99.94 97	97.87 309	99.72 294	99.62 187

mamba_0408		99.54 114	99.55 110	99.54 222	99.71 192	99.24 254	99.27 179	99.79 131	99.72 115	99.78 132	99.64 237	99.36 80	99.93 119	98.74 226	99.90 160	99.45 285

SSM_0407		99.56 104	99.56 108	99.54 222	99.71 192	99.24 254	99.15 226	99.84 89	99.80 95	99.78 132	99.70 198	99.44 65	99.93 119	98.74 226	99.90 160	99.45 285

SSM_0404		99.57 100	99.58 98	99.54 222	99.76 155	99.28 241	99.19 208	99.84 89	99.80 95	99.78 132	99.70 198	99.44 65	99.93 119	98.74 226	99.95 111	99.41 312

AstraMVS		99.15 244	99.06 238	99.42 262	99.85 73	98.59 343	99.13 237	97.26 476	99.84 75	99.87 92	99.77 144	96.11 368	99.93 119	99.71 60	99.96 87	99.74 90

fmvsm_s_conf0.5_n_6		99.80 30	99.78 39	99.85 32	99.78 138	99.78 57	99.00 288	99.97 20	99.96 28	99.97 24	99.56 303	99.92 8	99.93 119	99.91 33	99.99 16	99.83 58

reproduce_model		99.50 124	99.40 149	99.83 41	99.60 244	99.83 33	99.12 242	99.68 203	99.49 185	99.80 122	99.79 119	99.01 144	99.93 119	98.24 273	99.82 233	99.73 94

reproduce-ours		99.46 143	99.35 165	99.82 46	99.56 278	99.83 33	99.05 265	99.65 223	99.45 199	99.78 132	99.78 132	98.93 157	99.93 119	98.11 287	99.81 243	99.70 106

our_new_method		99.46 143	99.35 165	99.82 46	99.56 278	99.83 33	99.05 265	99.65 223	99.45 199	99.78 132	99.78 132	98.93 157	99.93 119	98.11 287	99.81 243	99.70 106

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 41	99.10 250	99.98 12	99.99 3	99.98 14	99.91 31	99.68 33	99.93 119	99.93 25	99.99 16	99.99 2

fmvsm_s_conf0.5_n_a		99.82 24	99.79 34	99.89 11	99.85 73	99.82 41	99.03 273	99.96 28	99.99 3	99.97 24	99.84 76	99.58 50	99.93 119	99.92 30	99.98 50	99.93 20

mvsany_test1		99.44 150	99.45 135	99.40 273	99.37 347	98.64 338	97.90 438	99.59 263	99.27 235	99.92 59	99.82 90	99.74 26	99.93 119	99.55 85	99.87 197	99.63 175

ETV-MVS		99.18 234	99.18 204	99.16 335	99.34 363	99.28 241	99.12 242	99.79 131	99.48 188	98.93 382	98.55 460	99.40 70	99.93 119	98.51 251	99.52 364	98.28 471

thisisatest0530		97.45 404	96.95 415	98.94 365	99.68 221	97.73 404	99.09 255	94.19 494	98.61 337	99.56 256	99.30 379	84.30 476	99.93 119	98.27 270	99.54 359	99.16 377

our_test_3		98.85 305	99.09 230	98.13 429	99.66 230	94.90 472	97.72 446	99.58 272	99.07 271	99.64 216	99.62 261	98.19 267	99.93 119	98.41 260	99.95 111	99.55 230

MSP-MVS		99.04 269	98.79 299	99.81 54	99.78 138	99.73 90	99.35 147	99.57 274	98.54 344	99.54 264	98.99 428	96.81 343	99.93 119	96.97 387	99.53 361	99.77 80
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
region2R		99.23 211	99.05 243	99.77 80	99.76 155	99.70 108	99.31 163	99.59 263	98.41 356	99.32 328	99.36 365	98.73 189	99.93 119	97.29 362	99.74 281	99.67 134

RRT-MVS		99.08 259	99.00 260	99.33 297	99.27 381	98.65 336	99.62 67	99.93 39	99.66 144	99.67 203	99.82 90	95.27 383	99.93 119	98.64 243	99.09 412	99.41 312

APDe-MVS		99.48 131	99.36 161	99.85 32	99.55 281	99.81 47	99.50 102	99.69 200	98.99 278	99.75 158	99.71 188	98.79 178	99.93 119	98.46 254	99.85 210	99.80 66
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CVMVSNet		98.61 326	98.88 286	97.80 441	99.58 257	93.60 482	99.26 184	99.64 231	99.66 144	99.72 178	99.67 223	93.26 407	99.93 119	99.30 130	99.81 243	99.87 44

ACMMPR		99.23 211	99.06 238	99.76 87	99.74 179	99.69 112	99.31 163	99.59 263	98.36 362	99.35 319	99.38 357	98.61 205	99.93 119	97.43 353	99.75 274	99.67 134

PGM-MVS		99.20 227	99.01 256	99.77 80	99.75 171	99.71 100	99.16 223	99.72 179	97.99 391	99.42 299	99.60 279	98.81 173	99.93 119	96.91 390	99.74 281	99.66 148

LCM-MVSNet-Re		99.28 198	99.15 210	99.67 143	99.33 368	99.76 70	99.34 148	99.97 20	98.93 291	99.91 62	99.79 119	98.68 194	99.93 119	96.80 398	99.56 350	99.30 346

PMMVS2		99.48 131	99.45 135	99.57 205	99.76 155	98.99 295	98.09 415	99.90 57	98.95 285	99.78 132	99.58 292	99.57 52	99.93 119	99.48 96	99.95 111	99.79 74

mPP-MVS		99.19 230	99.00 260	99.76 87	99.76 155	99.68 115	99.38 132	99.54 291	98.34 371	99.01 376	99.50 324	98.53 223	99.93 119	97.18 378	99.78 263	99.66 148

OurMVSNet-221017-0		99.75 49	99.71 56	99.84 38	99.96 7	99.83 33	99.83 7	99.85 82	99.80 95	99.93 53	99.93 22	98.54 218	99.93 119	99.59 78	99.98 50	99.76 85

CHOSEN 1792x2688		99.39 169	99.30 180	99.65 158	99.88 45	99.25 249	98.78 340	99.88 65	98.66 329	99.96 34	99.79 119	97.45 318	99.93 119	99.34 122	99.99 16	99.78 76

N_pmnet		98.73 317	98.53 324	99.35 291	99.72 188	98.67 330	98.34 392	94.65 491	98.35 367	99.79 128	99.68 219	98.03 280	99.93 119	98.28 269	99.92 146	99.44 300

UGNet		99.38 172	99.34 167	99.49 238	98.90 438	98.90 310	99.70 38	99.35 357	99.86 65	98.57 422	99.81 97	98.50 229	99.93 119	99.38 114	99.98 50	99.66 148
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
EC-MVSNet		99.69 59	99.69 60	99.68 139	99.71 192	99.91 4	99.76 23	99.96 28	99.86 65	99.51 278	99.39 355	99.57 52	99.93 119	99.64 73	99.86 205	99.20 367

EPP-MVSNet		99.17 239	99.00 260	99.66 151	99.80 116	99.43 202	99.70 38	99.24 388	99.48 188	99.56 256	99.77 144	94.89 386	99.93 119	98.72 233	99.89 174	99.63 175

DeepC-MVS	98.90 4	99.62 92	99.61 88	99.67 143	99.72 188	99.44 198	99.24 191	99.71 183	99.27 235	99.93 53	99.90 36	99.70 31	99.93 119	98.99 187	99.99 16	99.64 169
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
icg_test_0407_2		99.30 195	99.29 185	99.31 306	99.71 192	98.55 346	98.17 405	99.71 183	99.41 213	99.73 173	99.60 279	99.17 108	99.92 150	98.45 255	99.70 300	99.45 285

lecture		99.56 104	99.48 126	99.81 54	99.78 138	99.86 18	99.50 102	99.70 192	99.59 170	99.75 158	99.71 188	98.94 156	99.92 150	98.59 246	99.76 270	99.66 148

guyue		99.12 250	99.02 252	99.41 270	99.84 78	98.56 344	99.19 208	98.30 454	99.82 85	99.84 102	99.75 160	94.84 387	99.92 150	99.68 66	99.94 128	99.74 90

sc_t1		99.81 28	99.80 32	99.82 46	99.88 45	99.88 12	99.83 7	99.79 131	99.94 36	99.93 53	99.92 27	99.35 83	99.92 150	99.64 73	99.94 128	99.68 125

tt0320-xc		99.82 24	99.82 25	99.82 46	99.82 95	99.84 26	99.82 10	99.92 42	99.94 36	99.94 48	99.93 22	99.34 84	99.92 150	99.70 61	99.96 87	99.70 106

tt0320		99.79 34	99.79 34	99.81 54	99.82 95	99.84 26	99.82 10	99.90 57	99.94 36	99.94 48	99.94 19	99.07 131	99.92 150	99.68 66	99.97 73	99.67 134

fmvsm_s_conf0.5_n_4		99.78 37	99.78 39	99.79 72	99.75 171	99.56 166	98.98 298	99.94 38	99.92 45	99.97 24	99.72 178	99.84 16	99.92 150	99.91 33	99.98 50	99.89 37

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 57	99.07 263	99.98 12	99.99 3	99.98 14	99.90 36	99.88 11	99.92 150	99.93 25	99.99 16	99.98 5

fmvsm_s_conf0.5_n		99.83 21	99.81 28	99.87 26	99.85 73	99.78 57	99.03 273	99.96 28	99.99 3	99.97 24	99.84 76	99.78 23	99.92 150	99.92 30	99.99 16	99.92 24

EGC-MVSNET		89.05 464	85.52 467	99.64 165	99.89 39	99.78 57	99.56 87	99.52 306	24.19 501	49.96 502	99.83 83	99.15 112	99.92 150	97.71 325	99.85 210	99.21 363

DVP-MVS++		99.38 172	99.25 195	99.77 80	99.03 427	99.77 63	99.74 27	99.61 246	99.18 251	99.76 153	99.61 271	99.00 145	99.92 150	97.72 323	99.60 341	99.62 187

MSC_two_6792asdad				99.74 103	99.03 427	99.53 173		99.23 389					99.92 150	97.77 317	99.69 308	99.78 76

No_MVS				99.74 103	99.03 427	99.53 173		99.23 389					99.92 150	97.77 317	99.69 308	99.78 76

ZD-MVS					99.43 333	99.61 151		99.43 335	96.38 456	99.11 367	99.07 417	97.86 293	99.92 150	94.04 475	99.49 370

SED-MVS		99.40 165	99.28 188	99.77 80	99.69 213	99.82 41	99.20 202	99.54 291	99.13 264	99.82 109	99.63 252	98.91 163	99.92 150	97.85 312	99.70 300	99.58 217

test_241102_TWO								99.54 291	99.13 264	99.76 153	99.63 252	98.32 252	99.92 150	97.85 312	99.69 308	99.75 88

ZNCC-MVS		99.22 220	99.04 249	99.77 80	99.76 155	99.73 90	99.28 175	99.56 279	98.19 381	99.14 363	99.29 382	98.84 172	99.92 150	97.53 348	99.80 250	99.64 169

test_0728_SECOND				99.83 41	99.70 207	99.79 54	99.14 230	99.61 246					99.92 150	97.88 306	99.72 294	99.77 80

SR-MVS		99.19 230	99.00 260	99.74 103	99.51 299	99.72 95	99.18 212	99.60 257	98.85 303	99.47 286	99.58 292	98.38 244	99.92 150	96.92 389	99.54 359	99.57 223

DPE-MVS		99.14 245	98.92 280	99.82 46	99.57 267	99.77 63	98.74 345	99.60 257	98.55 341	99.76 153	99.69 207	98.23 262	99.92 150	96.39 423	99.75 274	99.76 85
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS		99.06 263	98.83 293	99.76 87	99.76 155	99.71 100	99.32 157	99.50 315	98.35 367	98.97 378	99.48 332	98.37 245	99.92 150	95.95 443	99.75 274	99.63 175
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PM-MVS		99.36 181	99.29 185	99.58 197	99.83 86	99.66 120	98.95 307	99.86 76	98.85 303	99.81 116	99.73 170	98.40 243	99.92 150	98.36 263	99.83 223	99.17 375

HPM-MVS		99.25 206	99.07 236	99.78 76	99.81 107	99.75 79	99.61 73	99.67 208	97.72 414	99.35 319	99.25 390	99.23 101	99.92 150	97.21 374	99.82 233	99.67 134
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
tpm		97.15 413	96.95 415	97.75 443	98.91 437	94.24 476	99.32 157	97.96 462	97.71 415	98.29 436	99.32 374	86.72 468	99.92 150	98.10 290	96.24 490	99.09 395

RPMNet		98.60 329	98.53 324	98.83 389	99.05 423	98.12 378	99.30 166	99.62 238	99.86 65	99.16 359	99.74 165	92.53 418	99.92 150	98.75 225	98.77 433	98.44 466

CPTT-MVS		98.74 315	98.44 331	99.64 165	99.61 242	99.38 218	99.18 212	99.55 285	96.49 454	99.27 340	99.37 360	97.11 335	99.92 150	95.74 450	99.67 319	99.62 187

MIMVSNet1		99.66 77	99.62 84	99.80 64	99.94 18	99.87 15	99.69 45	99.77 147	99.78 102	99.93 53	99.89 41	97.94 288	99.92 150	99.65 70	99.98 50	99.62 187

CSCG		99.37 176	99.29 185	99.60 191	99.71 192	99.46 190	99.43 121	99.85 82	98.79 313	99.41 305	99.60 279	98.92 160	99.92 150	98.02 292	99.92 146	99.43 306

ACMMP		99.25 206	99.08 232	99.74 103	99.79 130	99.68 115	99.50 102	99.65 223	98.07 387	99.52 271	99.69 207	98.57 210	99.92 150	97.18 378	99.79 255	99.63 175
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
SSC-MVS3.2		99.64 84	99.67 65	99.56 209	99.75 171	98.98 296	98.96 304	99.87 69	99.88 60	99.84 102	99.64 237	99.32 87	99.91 179	99.78 54	99.96 87	99.80 66

SR-MVS-dyc-post		99.27 202	99.11 220	99.73 113	99.54 283	99.74 87	99.26 184	99.62 238	99.16 258	99.52 271	99.64 237	98.41 239	99.91 179	97.27 365	99.61 338	99.54 240

DVP-MVS		99.32 193	99.17 205	99.77 80	99.69 213	99.80 51	99.14 230	99.31 371	99.16 258	99.62 231	99.61 271	98.35 247	99.91 179	97.88 306	99.72 294	99.61 201
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									99.18 251	99.62 231	99.61 271	98.58 209	99.91 179	97.72 323	99.80 250	99.77 80

GST-MVS		99.16 240	98.96 273	99.75 98	99.73 183	99.73 90	99.20 202	99.55 285	98.22 378	99.32 328	99.35 370	98.65 201	99.91 179	96.86 393	99.74 281	99.62 187

MP-MVS-pluss		99.14 245	98.92 280	99.80 64	99.83 86	99.83 33	98.61 356	99.63 235	96.84 450	99.44 292	99.58 292	98.81 173	99.91 179	97.70 328	99.82 233	99.67 134
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		99.25 206	99.08 232	99.76 87	99.73 183	99.70 108	99.31 163	99.59 263	98.36 362	99.36 316	99.37 360	98.80 177	99.91 179	97.43 353	99.75 274	99.68 125

HPM-MVS++		98.96 288	98.70 307	99.74 103	99.52 297	99.71 100	98.86 321	99.19 399	98.47 352	98.59 419	99.06 418	98.08 278	99.91 179	96.94 388	99.60 341	99.60 205

test-LLR		97.15 413	96.95 415	97.74 444	98.18 480	95.02 470	97.38 463	96.10 480	98.00 389	97.81 464	98.58 456	90.04 452	99.91 179	97.69 334	98.78 431	98.31 469

test-mter		96.23 437	95.73 440	97.74 444	98.18 480	95.02 470	97.38 463	96.10 480	97.90 401	97.81 464	98.58 456	79.12 488	99.91 179	97.69 334	98.78 431	98.31 469

VPA-MVSNet		99.66 77	99.62 84	99.79 72	99.68 221	99.75 79	99.62 67	99.69 200	99.85 71	99.80 122	99.81 97	98.81 173	99.91 179	99.47 99	99.88 184	99.70 106

XVG-ACMP-BASELINE		99.23 211	99.10 228	99.63 172	99.82 95	99.58 162	98.83 328	99.72 179	98.36 362	99.60 240	99.71 188	98.92 160	99.91 179	97.08 382	99.84 215	99.40 315

APD-MVS		98.87 301	98.59 314	99.71 127	99.50 305	99.62 141	99.01 282	99.57 274	96.80 452	99.54 264	99.63 252	98.29 253	99.91 179	95.24 459	99.71 298	99.61 201
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CR-MVSNet		98.35 358	98.20 354	98.83 389	99.05 423	98.12 378	99.30 166	99.67 208	97.39 431	99.16 359	99.79 119	91.87 427	99.91 179	98.78 223	98.77 433	98.44 466

FMVSNet5		97.80 387	97.25 404	99.42 262	98.83 448	98.97 299	99.38 132	99.80 122	98.87 300	99.25 344	99.69 207	80.60 481	99.91 179	98.96 193	99.90 160	99.38 320

XXY-MVS		99.71 56	99.67 65	99.81 54	99.89 39	99.72 95	99.59 80	99.82 104	99.39 217	99.82 109	99.84 76	99.38 75	99.91 179	99.38 114	99.93 140	99.80 66

sss		98.90 296	98.77 300	99.27 319	99.48 315	98.44 356	98.72 347	99.32 367	97.94 399	99.37 315	99.35 370	96.31 363	99.91 179	98.85 206	99.63 329	99.47 278

1112_ss		99.05 266	98.84 291	99.67 143	99.66 230	99.29 239	98.52 376	99.82 104	97.65 417	99.43 296	99.16 405	96.42 357	99.91 179	99.07 178	99.84 215	99.80 66

LS3D		99.24 209	99.11 220	99.61 187	98.38 474	99.79 54	99.57 85	99.68 203	99.61 162	99.15 361	99.71 188	98.70 192	99.91 179	97.54 346	99.68 313	99.13 387

MED-MVS test				99.74 103	99.76 155	99.65 126	99.38 132	99.78 142	99.58 172	99.81 116	99.66 228		99.90 198	97.69 334	99.79 255	99.67 134

MED-MVS		99.51 121	99.42 144	99.80 64	99.76 155	99.65 126	99.38 132	99.78 142	99.77 106	99.81 116	99.78 132	99.02 143	99.90 198	97.69 334	99.79 255	99.85 49

WB-MVSnew		98.34 360	98.14 360	98.96 362	98.14 483	97.90 396	98.27 397	97.26 476	98.63 333	98.80 400	98.00 474	97.77 300	99.90 198	97.37 357	98.98 420	99.09 395

testf1		99.63 85	99.60 92	99.72 121	99.94 18	99.95 2	99.47 112	99.89 60	99.43 208	99.88 82	99.80 107	99.26 96	99.90 198	98.81 214	99.88 184	99.32 339

APD_test2		99.63 85	99.60 92	99.72 121	99.94 18	99.95 2	99.47 112	99.89 60	99.43 208	99.88 82	99.80 107	99.26 96	99.90 198	98.81 214	99.88 184	99.32 339

BridgeMVS		99.50 124	99.50 121	99.50 234	99.42 338	99.49 180	99.52 94	99.75 160	99.86 65	99.78 132	99.71 188	98.20 266	99.90 198	99.39 113	99.88 184	99.10 390

test2506		94.73 458	94.59 458	95.15 479	99.59 250	85.90 505	99.75 25	74.01 507	99.89 55	99.71 183	99.86 63	79.00 489	99.90 198	99.52 90	99.99 16	99.65 157

test1111		97.74 389	98.16 359	96.49 472	99.60 244	89.86 503	99.71 37	91.21 499	99.89 55	99.88 82	99.87 56	93.73 401	99.90 198	99.56 83	99.99 16	99.70 106

KD-MVS_self_test		99.63 85	99.59 94	99.76 87	99.84 78	99.90 7	99.37 140	99.79 131	99.83 81	99.88 82	99.85 68	98.42 238	99.90 198	99.60 77	99.73 287	99.49 270

ET-MVSNet_ETH3D		96.78 421	96.07 431	98.91 374	99.26 384	97.92 395	97.70 449	96.05 483	97.96 396	92.37 496	98.43 464	87.06 462	99.90 198	98.27 270	97.56 475	98.91 429

tfpnnormal		99.43 154	99.38 153	99.60 191	99.87 54	99.75 79	99.59 80	99.78 142	99.71 121	99.90 67	99.69 207	98.85 171	99.90 198	97.25 371	99.78 263	99.15 379

pmmvs6		99.86 10	99.86 13	99.83 41	99.94 18	99.90 7	99.83 7	99.91 51	99.85 71	99.94 48	99.95 16	99.73 27	99.90 198	99.65 70	99.97 73	99.69 118

APD-MVS_3200maxsize		99.31 194	99.16 206	99.74 103	99.53 290	99.75 79	99.27 179	99.61 246	99.19 250	99.57 248	99.64 237	98.76 183	99.90 198	97.29 362	99.62 331	99.56 226

baseline2		96.83 420	96.28 427	98.46 414	99.09 420	96.91 433	98.83 328	93.87 497	97.23 438	96.23 489	98.36 465	88.12 459	99.90 198	96.68 404	98.14 465	98.57 458

XVG-OURS-SEG-HR		99.16 240	98.99 267	99.66 151	99.84 78	99.64 133	98.25 400	99.73 170	98.39 359	99.63 221	99.43 344	99.70 31	99.90 198	97.34 358	98.64 444	99.44 300

XVG-OURS		99.21 225	99.06 238	99.65 158	99.82 95	99.62 141	97.87 439	99.74 166	98.36 362	99.66 209	99.68 219	99.71 28	99.90 198	96.84 396	99.88 184	99.43 306

JIA-IIPM		98.06 376	97.92 379	98.50 411	98.59 467	97.02 430	98.80 336	98.51 441	99.88 60	97.89 458	99.87 56	91.89 426	99.90 198	98.16 284	97.68 474	98.59 454

GBi-Net		99.42 157	99.31 175	99.73 113	99.49 310	99.77 63	99.68 48	99.70 192	99.44 201	99.62 231	99.83 83	97.21 329	99.90 198	98.96 193	99.90 160	99.53 246

test1		99.42 157	99.31 175	99.73 113	99.49 310	99.77 63	99.68 48	99.70 192	99.44 201	99.62 231	99.83 83	97.21 329	99.90 198	98.96 193	99.90 160	99.53 246

FMVSNet1		99.66 77	99.63 82	99.73 113	99.78 138	99.77 63	99.68 48	99.70 192	99.67 140	99.82 109	99.83 83	98.98 151	99.90 198	99.24 137	99.97 73	99.53 246

WTY-MVS		98.59 332	98.37 338	99.26 322	99.43 333	98.40 359	98.74 345	99.13 407	98.10 384	99.21 353	99.24 395	94.82 388	99.90 198	97.86 310	98.77 433	99.49 270

VortexMVS		99.13 247	99.24 197	98.79 393	99.67 228	96.60 442	99.24 191	99.80 122	99.85 71	99.93 53	99.84 76	95.06 384	99.89 219	99.80 52	99.98 50	99.89 37

ECVR-MVS		97.73 390	98.04 366	96.78 465	99.59 250	90.81 498	99.72 33	90.43 501	99.89 55	99.86 96	99.86 63	93.60 403	99.89 219	99.46 100	99.99 16	99.65 157

EI-MVSNet-UG-set		99.48 131	99.50 121	99.42 262	99.57 267	98.65 336	99.24 191	99.46 326	99.68 132	99.80 122	99.66 228	98.99 147	99.89 219	99.19 149	99.90 160	99.72 98

EI-MVSNet-Vis-set		99.47 141	99.49 125	99.42 262	99.57 267	98.66 333	99.24 191	99.46 326	99.67 140	99.79 128	99.65 235	98.97 153	99.89 219	99.15 157	99.89 174	99.71 103

新几何1				99.52 228	99.50 305	99.22 260		99.26 381	95.66 467	98.60 418	99.28 383	97.67 307	99.89 219	95.95 443	99.32 392	99.45 285

testdata2													99.89 219	95.99 440

testdata				99.42 262	99.51 299	98.93 306		99.30 374	96.20 459	98.87 392	99.40 351	98.33 251	99.89 219	96.29 427	99.28 397	99.44 300

TESTMET0.1,1		96.24 436	95.84 437	97.41 453	98.24 478	93.84 479	97.38 463	95.84 487	98.43 353	97.81 464	98.56 459	79.77 485	99.89 219	97.77 317	98.77 433	98.52 460

test20.03		99.55 109	99.54 113	99.58 197	99.79 130	99.37 223	99.02 277	99.89 60	99.60 168	99.82 109	99.62 261	98.81 173	99.89 219	99.43 105	99.86 205	99.47 278

MDA-MVSNet-bldmvs		99.06 263	99.05 243	99.07 351	99.80 116	97.83 399	98.89 316	99.72 179	99.29 231	99.63 221	99.70 198	96.47 355	99.89 219	98.17 283	99.82 233	99.50 265

LPG-MVS_test		99.22 220	99.05 243	99.74 103	99.82 95	99.63 139	99.16 223	99.73 170	97.56 419	99.64 216	99.69 207	99.37 77	99.89 219	96.66 406	99.87 197	99.69 118

LGP-MVS_train				99.74 103	99.82 95	99.63 139		99.73 170	97.56 419	99.64 216	99.69 207	99.37 77	99.89 219	96.66 406	99.87 197	99.69 118

Test_1112_low_res		98.95 291	98.73 301	99.63 172	99.68 221	99.15 275	98.09 415	99.80 122	97.14 443	99.46 290	99.40 351	96.11 368	99.89 219	99.01 186	99.84 215	99.84 54

PatchmatchNet		97.65 394	97.80 384	97.18 461	98.82 451	92.49 486	99.17 217	98.39 449	98.12 383	98.79 402	99.58 292	90.71 444	99.89 219	97.23 372	99.41 380	99.16 377
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMP	97.51 14	99.05 266	98.84 291	99.67 143	99.78 138	99.55 170	98.88 317	99.66 213	97.11 445	99.47 286	99.60 279	99.07 131	99.89 219	96.18 432	99.85 210	99.58 217
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TestfortrainingZip a		99.55 109	99.45 135	99.85 32	99.76 155	99.82 41	99.38 132	99.62 238	99.77 106	99.87 92	99.78 132	98.12 273	99.88 234	98.96 193	99.77 267	99.85 49

diffmvs_AUTHOR		99.48 131	99.48 126	99.47 245	99.80 116	98.89 311	98.71 349	99.82 104	99.79 99	99.66 209	99.63 252	98.87 169	99.88 234	99.13 166	99.95 111	99.62 187

test_vis3_rt		99.89 3	99.90 4	99.87 26	99.98 3	99.75 79	99.70 38	100.00 1	99.73 111	100.00 1	99.89 41	99.79 22	99.88 234	99.98 1	100.00 1	99.98 5

FE-MVS		97.85 383	97.42 399	99.15 337	99.44 330	98.75 325	99.77 19	98.20 457	95.85 463	99.33 325	99.80 107	88.86 457	99.88 234	96.40 422	99.12 409	98.81 440

ppachtmachnet_test		98.89 299	99.12 217	98.20 427	99.66 230	95.24 468	97.63 451	99.68 203	99.08 269	99.78 132	99.62 261	98.65 201	99.88 234	98.02 292	99.96 87	99.48 274

TSAR-MVS + MP.		99.34 188	99.24 197	99.63 172	99.82 95	99.37 223	99.26 184	99.35 357	98.77 317	99.57 248	99.70 198	99.27 95	99.88 234	97.71 325	99.75 274	99.65 157
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
new-patchmatchnet		99.35 183	99.57 103	98.71 402	99.82 95	96.62 440	98.55 370	99.75 160	99.50 183	99.88 82	99.87 56	99.31 88	99.88 234	99.43 105	100.00 1	99.62 187

Anonymous20231206		99.35 183	99.31 175	99.47 245	99.74 179	99.06 291	99.28 175	99.74 166	99.23 243	99.72 178	99.53 315	97.63 314	99.88 234	99.11 171	99.84 215	99.48 274

XVS		99.27 202	99.11 220	99.75 98	99.71 192	99.71 100	99.37 140	99.61 246	99.29 231	98.76 405	99.47 336	98.47 230	99.88 234	97.62 340	99.73 287	99.67 134

v1240		99.56 104	99.58 98	99.51 232	99.80 116	99.00 293	99.00 288	99.65 223	99.15 262	99.90 67	99.75 160	99.09 124	99.88 234	99.90 37	99.96 87	99.67 134

X-MVStestdata		96.09 441	94.87 454	99.75 98	99.71 192	99.71 100	99.37 140	99.61 246	99.29 231	98.76 405	61.30 510	98.47 230	99.88 234	97.62 340	99.73 287	99.67 134

旧先验2							97.94 433		95.33 470	98.94 381			99.88 234	96.75 400

UniMVSNet (Re)		99.37 176	99.26 193	99.68 139	99.51 299	99.58 162	98.98 298	99.60 257	99.43 208	99.70 187	99.36 365	97.70 303	99.88 234	99.20 147	99.87 197	99.59 212

HPM-MVS_fast		99.43 154	99.30 180	99.80 64	99.83 86	99.81 47	99.52 94	99.70 192	98.35 367	99.51 278	99.50 324	99.31 88	99.88 234	98.18 281	99.84 215	99.69 118

TDRefinement		99.72 53	99.70 57	99.77 80	99.90 37	99.85 21	99.86 6	99.92 42	99.69 130	99.78 132	99.92 27	99.37 77	99.88 234	98.93 201	99.95 111	99.60 205

PCF-MVS	96.03 18	96.73 423	95.86 436	99.33 297	99.44 330	99.16 273	96.87 483	99.44 332	86.58 494	98.95 380	99.40 351	94.38 393	99.88 234	87.93 490	99.80 250	98.95 423
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		96.21 439	95.78 438	97.49 449	98.53 469	93.83 480	98.04 421	93.94 496	98.96 282	98.46 429	98.17 470	79.86 483	99.87 250	96.99 385	99.06 413	98.78 443

SF-MVS		99.10 257	98.93 276	99.62 181	99.58 257	99.51 178	99.13 237	99.65 223	97.97 393	99.42 299	99.61 271	98.86 170	99.87 250	96.45 421	99.68 313	99.49 270

D2MVS		99.22 220	99.19 203	99.29 311	99.69 213	98.74 326	98.81 333	99.41 338	98.55 341	99.68 195	99.69 207	98.13 271	99.87 250	98.82 210	99.98 50	99.24 355

thisisatest0515		96.98 417	96.42 425	98.66 403	99.42 338	97.47 413	97.27 468	94.30 493	97.24 437	99.15 361	98.86 443	85.01 472	99.87 250	97.10 380	99.39 382	98.63 450

ACMMP_NAP		99.28 198	99.11 220	99.79 72	99.75 171	99.81 47	98.95 307	99.53 301	98.27 376	99.53 269	99.73 170	98.75 185	99.87 250	97.70 328	99.83 223	99.68 125

Patchmatch-test		98.10 374	97.98 371	98.48 412	99.27 381	96.48 443	99.40 127	99.07 409	98.81 310	99.23 348	99.57 299	90.11 451	99.87 250	96.69 403	99.64 326	99.09 395

v144192		99.55 109	99.54 113	99.58 197	99.78 138	99.20 266	99.11 247	99.62 238	99.18 251	99.89 72	99.72 178	98.66 199	99.87 250	99.88 41	99.97 73	99.66 148

v1921920		99.56 104	99.57 103	99.55 216	99.75 171	99.11 279	99.05 265	99.61 246	99.15 262	99.88 82	99.71 188	99.08 128	99.87 250	99.90 37	99.97 73	99.66 148

FC-MVSNet-test		99.70 57	99.65 74	99.86 30	99.88 45	99.86 18	99.72 33	99.78 142	99.90 49	99.82 109	99.83 83	98.45 234	99.87 250	99.51 92	99.97 73	99.86 46

pm-mvs1		99.79 34	99.79 34	99.78 76	99.91 31	99.83 33	99.76 23	99.87 69	99.73 111	99.89 72	99.87 56	99.63 37	99.87 250	99.54 86	99.92 146	99.63 175

TransMVSNet (Re)		99.78 37	99.77 45	99.81 54	99.91 31	99.85 21	99.75 25	99.86 76	99.70 127	99.91 62	99.89 41	99.60 44	99.87 250	99.59 78	99.74 281	99.71 103

NR-MVSNet		99.40 165	99.31 175	99.68 139	99.43 333	99.55 170	99.73 30	99.50 315	99.46 196	99.88 82	99.36 365	97.54 315	99.87 250	98.97 191	99.87 197	99.63 175

Baseline_NR-MVSNet		99.49 129	99.37 156	99.82 46	99.91 31	99.84 26	98.83 328	99.86 76	99.68 132	99.65 213	99.88 50	97.67 307	99.87 250	99.03 182	99.86 205	99.76 85

EG-PatchMatch MVS		99.57 100	99.56 108	99.62 181	99.77 151	99.33 233	99.26 184	99.76 155	99.32 227	99.80 122	99.78 132	99.29 90	99.87 250	99.15 157	99.91 158	99.66 148

DELS-MVS		99.34 188	99.30 180	99.48 243	99.51 299	99.36 227	98.12 411	99.53 301	99.36 222	99.41 305	99.61 271	99.22 102	99.87 250	99.21 143	99.68 313	99.20 367
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
FMVSNet2		99.35 183	99.28 188	99.55 216	99.49 310	99.35 230	99.45 117	99.57 274	99.44 201	99.70 187	99.74 165	97.21 329	99.87 250	99.03 182	99.94 128	99.44 300

ab-mvs		99.33 191	99.28 188	99.47 245	99.57 267	99.39 216	99.78 17	99.43 335	98.87 300	99.57 248	99.82 90	98.06 279	99.87 250	98.69 238	99.73 287	99.15 379

DP-MVS		99.48 131	99.39 150	99.74 103	99.57 267	99.62 141	99.29 173	99.61 246	99.87 62	99.74 168	99.76 152	98.69 193	99.87 250	98.20 277	99.80 250	99.75 88

F-COLMAP		98.74 315	98.45 330	99.62 181	99.57 267	99.47 184	98.84 325	99.65 223	96.31 458	98.93 382	99.19 404	97.68 306	99.87 250	96.52 414	99.37 385	99.53 246

ME-MVS		99.26 204	99.10 228	99.73 113	99.60 244	99.65 126	98.75 344	99.45 331	99.31 229	99.65 213	99.66 228	98.00 286	99.86 269	97.69 334	99.79 255	99.67 134

WBMVS		97.50 403	97.18 406	98.48 412	98.85 446	95.89 457	98.44 387	99.52 306	99.53 178	99.52 271	99.42 346	80.10 482	99.86 269	99.24 137	99.95 111	99.68 125

Anonymous20240529		99.42 157	99.34 167	99.65 158	99.53 290	99.60 155	99.63 64	99.39 348	99.47 193	99.76 153	99.78 132	98.13 271	99.86 269	98.70 236	99.68 313	99.49 270

test_post											52.41 511	90.25 450	99.86 269

Anonymous20231211		99.62 92	99.57 103	99.76 87	99.61 242	99.60 155	99.81 13	99.73 170	99.82 85	99.90 67	99.90 36	97.97 287	99.86 269	99.42 110	99.96 87	99.80 66

v10		99.69 59	99.69 60	99.66 151	99.81 107	99.39 216	99.66 57	99.75 160	99.60 168	99.92 59	99.87 56	98.75 185	99.86 269	99.90 37	99.99 16	99.73 94

VPNet		99.46 143	99.37 156	99.71 127	99.82 95	99.59 157	99.48 109	99.70 192	99.81 91	99.69 190	99.58 292	97.66 311	99.86 269	99.17 154	99.44 375	99.67 134

testgi		99.29 197	99.26 193	99.37 284	99.75 171	98.81 318	98.84 325	99.89 60	98.38 360	99.75 158	99.04 421	99.36 80	99.86 269	99.08 175	99.25 402	99.45 285

mvs_anonymous		99.28 198	99.39 150	98.94 365	99.19 397	97.81 400	99.02 277	99.55 285	99.78 102	99.85 99	99.80 107	98.24 258	99.86 269	99.57 82	99.50 368	99.15 379

diffmvs		99.34 188	99.32 173	99.39 276	99.67 228	98.77 324	98.57 367	99.81 117	99.61 162	99.48 284	99.41 347	98.47 230	99.86 269	98.97 191	99.90 160	99.53 246
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		99.11 254	98.93 276	99.66 151	99.30 374	99.42 205	98.42 388	99.37 353	99.04 274	99.57 248	99.20 403	96.89 341	99.86 269	98.66 240	99.87 197	99.70 106

114514_t		98.49 344	98.11 362	99.64 165	99.73 183	99.58 162	99.24 191	99.76 155	89.94 492	99.42 299	99.56 303	97.76 302	99.86 269	97.74 322	99.82 233	99.47 278

UnsupCasMVSNet_eth		98.83 306	98.57 318	99.59 194	99.68 221	99.45 196	98.99 295	99.67 208	99.48 188	99.55 261	99.36 365	94.92 385	99.86 269	98.95 199	96.57 482	99.45 285

FMVSNet3		98.80 310	98.63 311	99.32 302	99.13 407	98.72 327	99.10 250	99.48 320	99.23 243	99.62 231	99.64 237	92.57 416	99.86 269	98.96 193	99.90 160	99.39 318

HY-MVS	98.23 9	98.21 370	97.95 373	98.99 358	99.03 427	98.24 367	99.61 73	98.72 428	96.81 451	98.73 407	99.51 321	94.06 395	99.86 269	96.91 390	98.20 460	98.86 435

TAMVS		99.49 129	99.45 135	99.63 172	99.48 315	99.42 205	99.45 117	99.57 274	99.66 144	99.78 132	99.83 83	97.85 295	99.86 269	99.44 103	99.96 87	99.61 201

ACMM	98.09 11	99.46 143	99.38 153	99.72 121	99.80 116	99.69 112	99.13 237	99.65 223	98.99 278	99.64 216	99.72 178	99.39 71	99.86 269	98.23 274	99.81 243	99.60 205
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS_ROB	97.31 17	97.36 410	96.84 420	98.89 381	99.29 376	99.45 196	98.87 320	99.48 320	86.54 495	99.44 292	99.74 165	97.34 324	99.86 269	91.61 482	99.28 397	97.37 491

COLMAP_ROB	98.06 12	99.45 147	99.37 156	99.70 132	99.83 86	99.70 108	99.38 132	99.78 142	99.53 178	99.67 203	99.78 132	99.19 105	99.86 269	97.32 359	99.87 197	99.55 230
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
gbinet_0.2-2-1-0.02		97.52 402	97.07 410	98.88 383	97.35 497	97.35 421	97.17 472	99.25 384	97.86 407	98.41 432	96.54 501	90.74 443	99.85 288	98.80 216	97.51 476	99.43 306

FE-MVSNET2		99.68 64	99.67 65	99.72 121	99.86 59	99.68 115	99.46 116	99.88 65	99.62 157	99.87 92	99.85 68	99.06 137	99.85 288	99.44 103	99.98 50	99.63 175

testing3		96.48 430	95.63 442	99.01 357	99.23 389	97.81 400	98.90 315	99.10 408	98.72 322	97.84 463	97.92 475	72.44 501	99.85 288	97.21 374	99.33 390	99.35 329

hse-mvs2		98.52 339	98.30 347	99.16 335	99.29 376	98.60 341	98.77 341	99.02 414	99.68 132	99.32 328	99.04 421	92.50 419	99.85 288	99.24 137	97.87 472	99.03 412

AUN-MVS		97.82 384	97.38 400	99.14 340	99.27 381	98.53 350	98.72 347	99.02 414	98.10 384	97.18 477	99.03 425	89.26 456	99.85 288	97.94 301	97.91 470	99.03 412

miper_lstm_enhance		98.65 325	98.60 312	98.82 392	99.20 395	97.33 422	97.78 442	99.66 213	99.01 277	99.59 243	99.50 324	94.62 391	99.85 288	98.12 286	99.90 160	99.26 352

TEST9					99.35 354	99.35 230	98.11 413	99.41 338	94.83 478	97.92 456	98.99 428	98.02 281	99.85 288

train_agg		98.35 358	97.95 373	99.57 205	99.35 354	99.35 230	98.11 413	99.41 338	94.90 475	97.92 456	98.99 428	98.02 281	99.85 288	95.38 457	99.44 375	99.50 265

agg_prior					99.35 354	99.36 227		99.39 348		97.76 467			99.85 288

FIs		99.65 83	99.58 98	99.84 38	99.84 78	99.85 21	99.66 57	99.75 160	99.86 65	99.74 168	99.79 119	98.27 256	99.85 288	99.37 117	99.93 140	99.83 58

v1192		99.57 100	99.57 103	99.57 205	99.77 151	99.22 260	99.04 270	99.60 257	99.18 251	99.87 92	99.72 178	99.08 128	99.85 288	99.89 40	99.98 50	99.66 148

无先验							98.01 424	99.23 389	95.83 464				99.85 288	95.79 449		99.44 300

VDD-MVS		99.20 227	99.11 220	99.44 256	99.43 333	98.98 296	99.50 102	98.32 453	99.80 95	99.56 256	99.69 207	96.99 339	99.85 288	98.99 187	99.73 287	99.50 265

VDDNet		98.97 285	98.82 294	99.42 262	99.71 192	98.81 318	99.62 67	98.68 430	99.81 91	99.38 313	99.80 107	94.25 394	99.85 288	98.79 217	99.32 392	99.59 212

EI-MVSNet		99.38 172	99.44 140	99.21 329	99.58 257	98.09 382	99.26 184	99.46 326	99.62 157	99.75 158	99.67 223	98.54 218	99.85 288	99.15 157	99.92 146	99.68 125

MVSTER		98.47 346	98.22 352	99.24 327	99.06 422	98.35 365	99.08 258	99.46 326	99.27 235	99.75 158	99.66 228	88.61 458	99.85 288	99.14 164	99.92 146	99.52 257

ACMH	98.42 6	99.59 99	99.54 113	99.72 121	99.86 59	99.62 141	99.56 87	99.79 131	98.77 317	99.80 122	99.85 68	99.64 35	99.85 288	98.70 236	99.89 174	99.70 106
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
wanda-best-256-512		97.53 400	97.14 408	98.72 398	97.71 491	96.86 435	97.00 479	99.34 360	97.73 412	98.18 442	96.82 495	91.92 422	99.84 305	99.02 184	96.53 483	99.45 285

blended_shiyan8		97.82 384	97.45 397	98.92 369	98.06 485	97.45 416	97.73 444	99.35 357	97.96 396	98.35 434	97.34 485	92.76 415	99.84 305	99.04 180	96.49 489	99.47 278

FE-blended-shiyan7		97.53 400	97.14 408	98.72 398	97.71 491	96.86 435	97.00 479	99.34 360	97.73 412	98.18 442	96.82 495	91.92 422	99.84 305	99.02 184	96.53 483	99.45 285

blended_shiyan6		97.82 384	97.46 395	98.92 369	98.08 484	97.46 414	97.73 444	99.34 360	97.96 396	98.33 435	97.35 484	92.78 413	99.84 305	99.04 180	96.53 483	99.46 283

IMVS_0403		99.37 176	99.39 150	99.28 314	99.71 192	98.55 346	99.19 208	99.71 183	99.41 213	99.67 203	99.60 279	99.12 120	99.84 305	98.45 255	99.70 300	99.45 285

APD_test1		99.36 181	99.28 188	99.61 187	99.89 39	99.89 10	99.32 157	99.74 166	99.18 251	99.69 190	99.75 160	98.41 239	99.84 305	97.85 312	99.70 300	99.10 390

test_vis1_rt		99.45 147	99.46 133	99.41 270	99.71 192	98.63 339	98.99 295	99.96 28	99.03 275	99.95 45	99.12 411	98.75 185	99.84 305	99.82 50	99.82 233	99.77 80

FA-MVS(test-final)		98.52 339	98.32 344	99.10 345	99.48 315	98.67 330	99.77 19	98.60 437	97.35 433	99.63 221	99.80 107	93.07 410	99.84 305	97.92 302	99.30 394	98.78 443

EIA-MVS		99.12 250	99.01 256	99.45 252	99.36 350	99.62 141	99.34 148	99.79 131	98.41 356	98.84 395	98.89 441	98.75 185	99.84 305	98.15 285	99.51 365	98.89 432

Anonymous202405211		98.75 314	98.46 328	99.63 172	99.34 363	99.66 120	99.47 112	97.65 469	99.28 234	99.56 256	99.50 324	93.15 408	99.84 305	98.62 245	99.58 347	99.40 315

Effi-MVS+		99.06 263	98.97 271	99.34 294	99.31 370	98.98 296	98.31 395	99.91 51	98.81 310	98.79 402	98.94 437	99.14 115	99.84 305	98.79 217	98.74 437	99.20 367

gm-plane-assit					97.59 494	89.02 504			93.47 482		98.30 466		99.84 305	96.38 424

test_8					99.34 363	99.31 236	98.08 417	99.40 345	94.90 475	97.87 460	98.97 433	98.02 281	99.84 305

v1144		99.54 114	99.53 117	99.59 194	99.79 130	99.28 241	99.10 250	99.61 246	99.20 248	99.84 102	99.73 170	98.67 197	99.84 305	99.86 45	99.98 50	99.64 169

v8		99.68 64	99.69 60	99.65 158	99.80 116	99.40 213	99.66 57	99.76 155	99.64 152	99.93 53	99.85 68	98.66 199	99.84 305	99.88 41	99.99 16	99.71 103

v2v482		99.50 124	99.47 128	99.58 197	99.78 138	99.25 249	99.14 230	99.58 272	99.25 239	99.81 116	99.62 261	98.24 258	99.84 305	99.83 46	99.97 73	99.64 169

VNet		99.18 234	99.06 238	99.56 209	99.24 387	99.36 227	99.33 154	99.31 371	99.67 140	99.47 286	99.57 299	96.48 354	99.84 305	99.15 157	99.30 394	99.47 278

ADS-MVSNet		97.72 393	97.67 391	97.86 439	99.14 405	94.65 473	99.22 199	98.86 419	96.97 446	98.25 438	99.64 237	90.90 438	99.84 305	96.51 415	99.56 350	99.08 401

casdiffmvs_mvg		99.68 64	99.68 63	99.69 137	99.81 107	99.59 157	99.29 173	99.90 57	99.71 121	99.79 128	99.73 170	99.54 55	99.84 305	99.36 118	99.96 87	99.65 157
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LF4IMVS		99.01 278	98.92 280	99.27 319	99.71 192	99.28 241	98.59 361	99.77 147	98.32 373	99.39 312	99.41 347	98.62 203	99.84 305	96.62 411	99.84 215	98.69 449

usedtu_dtu_shiyan1		98.87 301	98.71 303	99.35 291	99.59 250	98.88 312	97.17 472	99.64 231	98.94 286	99.27 340	99.22 397	95.57 377	99.83 325	99.08 175	99.92 146	99.35 329

usedtu_blend_shiyan5		97.97 381	97.65 393	98.92 369	97.71 491	97.49 411	99.53 92	99.81 117	99.52 182	98.18 442	96.82 495	91.92 422	99.83 325	98.79 217	96.53 483	99.45 285

blend_shiyan4		95.04 457	93.76 461	98.88 383	97.92 487	97.49 411	97.72 446	99.34 360	97.93 400	97.65 470	97.11 489	77.69 492	99.83 325	98.79 217	79.72 500	99.33 335

FE-MVSNET3		98.87 301	98.71 303	99.35 291	99.59 250	98.88 312	97.17 472	99.64 231	98.94 286	99.27 340	99.22 397	95.57 377	99.83 325	99.08 175	99.92 146	99.35 329

viewdifsd2359ckpt11		99.62 92	99.64 79	99.56 209	99.86 59	99.19 267	99.02 277	99.93 39	99.83 81	99.88 82	99.81 97	98.99 147	99.83 325	99.48 96	99.96 87	99.65 157

viewmsd2359difaftdt		99.62 92	99.64 79	99.56 209	99.86 59	99.19 267	99.02 277	99.93 39	99.83 81	99.88 82	99.81 97	98.99 147	99.83 325	99.48 96	99.96 87	99.65 157

IMVS_0407		99.38 172	99.42 144	99.28 314	99.71 192	98.55 346	99.27 179	99.71 183	99.41 213	99.73 173	99.60 279	99.17 108	99.83 325	98.45 255	99.70 300	99.45 285

reproduce_monomvs		97.40 407	97.46 395	97.20 460	99.05 423	91.91 489	99.20 202	99.18 400	99.84 75	99.86 96	99.75 160	80.67 479	99.83 325	99.69 64	99.95 111	99.85 49

9.14			98.64 309		99.45 329		98.81 333	99.60 257	97.52 424	99.28 339	99.56 303	98.53 223	99.83 325	95.36 458	99.64 326

SMA-MVS		99.19 230	99.00 260	99.73 113	99.46 325	99.73 90	99.13 237	99.52 306	97.40 430	99.57 248	99.64 237	98.93 157	99.83 325	97.61 342	99.79 255	99.63 175
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
EU-MVSNet		99.39 169	99.62 84	98.72 398	99.88 45	96.44 444	99.56 87	99.85 82	99.90 49	99.90 67	99.85 68	98.09 276	99.83 325	99.58 81	99.95 111	99.90 29

YYNet1		98.95 291	98.99 267	98.84 387	99.64 235	97.14 428	98.22 402	99.32 367	98.92 294	99.59 243	99.66 228	97.40 320	99.83 325	98.27 270	99.90 160	99.55 230

MDA-MVSNet_test_wron		98.95 291	98.99 267	98.85 385	99.64 235	97.16 426	98.23 401	99.33 365	98.93 291	99.56 256	99.66 228	97.39 322	99.83 325	98.29 268	99.88 184	99.55 230

baseline		99.63 85	99.62 84	99.66 151	99.80 116	99.62 141	99.44 119	99.80 122	99.71 121	99.72 178	99.69 207	99.15 112	99.83 325	99.32 127	99.94 128	99.53 246

CDS-MVSNet		99.22 220	99.13 213	99.50 234	99.35 354	99.11 279	98.96 304	99.54 291	99.46 196	99.61 237	99.70 198	96.31 363	99.83 325	99.34 122	99.88 184	99.55 230
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DeepC-MVS_fast	98.47 5	99.23 211	99.12 217	99.56 209	99.28 379	99.22 260	98.99 295	99.40 345	99.08 269	99.58 245	99.64 237	98.90 166	99.83 325	97.44 352	99.75 274	99.63 175
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PLC	97.35 16	98.36 355	97.99 369	99.48 243	99.32 369	99.24 254	98.50 378	99.51 311	95.19 473	98.58 420	98.96 435	96.95 340	99.83 325	95.63 451	99.25 402	99.37 323
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
FE-MVSNET		99.45 147	99.36 161	99.71 127	99.84 78	99.64 133	99.16 223	99.91 51	98.65 330	99.73 173	99.73 170	98.54 218	99.82 342	98.71 235	99.96 87	99.67 134

pmmvs5		99.19 230	99.11 220	99.42 262	99.76 155	98.88 312	98.55 370	99.73 170	98.82 308	99.72 178	99.62 261	96.56 350	99.82 342	99.32 127	99.95 111	99.56 226

test_post1							99.14 230				51.63 512	89.54 455	99.82 342	96.86 393

原ACMM1				99.37 284	99.47 321	98.87 316		99.27 379	96.74 453	98.26 437	99.32 374	97.93 289	99.82 342	95.96 442	99.38 383	99.43 306

V42		99.56 104	99.54 113	99.63 172	99.79 130	99.46 190	99.39 129	99.59 263	99.24 241	99.86 96	99.70 198	98.55 214	99.82 342	99.79 53	99.95 111	99.60 205

CDPH-MVS		98.56 335	98.20 354	99.61 187	99.50 305	99.46 190	98.32 394	99.41 338	95.22 471	99.21 353	99.10 415	98.34 249	99.82 342	95.09 463	99.66 322	99.56 226

test12				99.54 222	99.29 376	99.33 233		99.16 403		98.43 430		97.54 315	99.82 342		99.47 372	99.48 274

casdiffmvs		99.63 85	99.61 88	99.67 143	99.79 130	99.59 157	99.13 237	99.85 82	99.79 99	99.76 153	99.72 178	99.33 86	99.82 342	99.21 143	99.94 128	99.59 212
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline1		97.73 390	97.33 401	98.96 362	99.30 374	97.73 404	99.40 127	98.42 446	99.33 226	99.46 290	99.21 401	91.18 433	99.82 342	98.35 264	91.26 495	99.32 339

HQP_MVS		98.90 296	98.68 308	99.55 216	99.58 257	99.24 254	98.80 336	99.54 291	98.94 286	99.14 363	99.25 390	97.24 327	99.82 342	95.84 447	99.78 263	99.60 205

plane_prior5								99.54 291					99.82 342	95.84 447	99.78 263	99.60 205

tpmrst		97.73 390	98.07 365	96.73 469	98.71 463	92.00 488	99.10 250	98.86 419	98.52 346	98.92 385	99.54 313	91.90 425	99.82 342	98.02 292	99.03 417	98.37 468

UnsupCasMVSNet_bld		98.55 336	98.27 350	99.40 273	99.56 278	99.37 223	97.97 431	99.68 203	97.49 426	99.08 370	99.35 370	95.41 382	99.82 342	97.70 328	98.19 462	99.01 418

dp		96.86 419	97.07 410	96.24 475	98.68 465	90.30 502	99.19 208	98.38 450	97.35 433	98.23 440	99.59 289	87.23 461	99.82 342	96.27 428	98.73 440	98.59 454

test_0402		99.22 220	99.14 211	99.45 252	99.79 130	99.43 202	99.28 175	99.68 203	99.54 176	99.40 310	99.56 303	99.07 131	99.82 342	96.01 437	99.96 87	99.11 388

PMMVS		98.49 344	98.29 349	99.11 343	98.96 435	98.42 358	97.54 455	99.32 367	97.53 423	98.47 428	98.15 471	97.88 292	99.82 342	97.46 351	99.24 404	99.09 395

viewdifsd2359ckpt07		99.51 121	99.50 121	99.52 228	99.80 116	99.19 267	98.92 313	99.88 65	99.72 115	99.64 216	99.62 261	99.06 137	99.81 358	98.96 193	99.94 128	99.56 226

testing222		95.60 455	94.59 458	98.61 405	98.66 466	97.45 416	98.54 373	97.90 465	98.53 345	96.54 485	96.47 503	70.62 504	99.81 358	95.91 445	98.15 464	98.56 459

tt0805		99.63 85	99.57 103	99.81 54	99.87 54	99.88 12	99.58 82	98.70 429	99.72 115	99.91 62	99.60 279	99.43 67	99.81 358	99.81 51	99.53 361	99.73 94

LFMVS		98.46 347	98.19 357	99.26 322	99.24 387	98.52 352	99.62 67	96.94 478	99.87 62	99.31 333	99.58 292	91.04 435	99.81 358	98.68 239	99.42 379	99.45 285

NCCC		98.82 307	98.57 318	99.58 197	99.21 392	99.31 236	98.61 356	99.25 384	98.65 330	98.43 430	99.26 388	97.86 293	99.81 358	96.55 412	99.27 400	99.61 201

MIMVSNet		98.43 349	98.20 354	99.11 343	99.53 290	98.38 363	99.58 82	98.61 435	98.96 282	99.33 325	99.76 152	90.92 437	99.81 358	97.38 356	99.76 270	99.15 379

IS-MVSNet		99.03 270	98.85 289	99.55 216	99.80 116	99.25 249	99.73 30	99.15 404	99.37 219	99.61 237	99.71 188	94.73 390	99.81 358	97.70 328	99.88 184	99.58 217

AdaColmap		98.60 329	98.35 341	99.38 279	99.12 409	99.22 260	98.67 351	99.42 337	97.84 409	98.81 398	99.27 385	97.32 325	99.81 358	95.14 461	99.53 361	99.10 390

MCST-MVS		99.02 272	98.81 296	99.65 158	99.58 257	99.49 180	98.58 363	99.07 409	98.40 358	99.04 375	99.25 390	98.51 228	99.80 366	97.31 360	99.51 365	99.65 157

CostFormer		96.71 424	96.79 423	96.46 473	98.90 438	90.71 499	99.41 122	98.68 430	94.69 479	98.14 449	99.34 373	86.32 470	99.80 366	97.60 343	98.07 468	98.88 433

PHI-MVS		99.11 254	98.95 274	99.59 194	99.13 407	99.59 157	99.17 217	99.65 223	97.88 404	99.25 344	99.46 339	98.97 153	99.80 366	97.26 367	99.82 233	99.37 323

Patchmatch-RL test		98.60 329	98.36 339	99.33 297	99.77 151	99.07 289	98.27 397	99.87 69	98.91 295	99.74 168	99.72 178	90.57 447	99.79 369	98.55 249	99.85 210	99.11 388

test0.0.03 1		97.37 409	96.91 418	98.74 397	97.72 490	97.57 408	97.60 453	97.36 475	98.00 389	99.21 353	98.02 472	90.04 452	99.79 369	98.37 262	95.89 492	98.86 435

MSDG		99.08 259	98.98 270	99.37 284	99.60 244	99.13 276	97.54 455	99.74 166	98.84 306	99.53 269	99.55 311	99.10 122	99.79 369	97.07 383	99.86 205	99.18 372

E5new		99.68 64	99.67 65	99.70 132	99.87 54	99.62 141	99.41 122	99.84 89	99.68 132	99.77 144	99.81 97	99.59 46	99.78 372	99.13 166	99.96 87	99.70 106

E6new		99.68 64	99.67 65	99.70 132	99.86 59	99.62 141	99.41 122	99.84 89	99.68 132	99.77 144	99.81 97	99.59 46	99.78 372	99.13 166	99.96 87	99.70 106

E6		99.68 64	99.67 65	99.70 132	99.86 59	99.62 141	99.41 122	99.84 89	99.68 132	99.77 144	99.81 97	99.59 46	99.78 372	99.13 166	99.96 87	99.70 106

E5		99.68 64	99.67 65	99.70 132	99.87 54	99.62 141	99.41 122	99.84 89	99.68 132	99.77 144	99.81 97	99.59 46	99.78 372	99.13 166	99.96 87	99.70 106

viewmambaseed2359dif		99.47 141	99.50 121	99.37 284	99.70 207	98.80 321	98.67 351	99.92 42	99.49 185	99.77 144	99.71 188	99.08 128	99.78 372	99.20 147	99.94 128	99.54 240

cl____		98.54 337	98.41 334	98.92 369	99.03 427	97.80 402	97.46 461	99.59 263	98.90 296	99.60 240	99.46 339	93.85 398	99.78 372	97.97 299	99.89 174	99.17 375

DIV-MVS_self_test		98.54 337	98.42 333	98.92 369	99.03 427	97.80 402	97.46 461	99.59 263	98.90 296	99.60 240	99.46 339	93.87 397	99.78 372	97.97 299	99.89 174	99.18 372

MVP-Stereo		99.16 240	99.08 232	99.43 260	99.48 315	99.07 289	99.08 258	99.55 285	98.63 333	99.31 333	99.68 219	98.19 267	99.78 372	98.18 281	99.58 347	99.45 285
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
nrg030		99.70 57	99.66 72	99.82 46	99.76 155	99.84 26	99.61 73	99.70 192	99.93 43	99.78 132	99.68 219	99.10 122	99.78 372	99.45 102	99.96 87	99.83 58

Vis-MVSNet (Re-imp)		98.77 312	98.58 317	99.34 294	99.78 138	98.88 312	99.61 73	99.56 279	99.11 268	99.24 347	99.56 303	93.00 412	99.78 372	97.43 353	99.89 174	99.35 329

CNLPA		98.57 334	98.34 342	99.28 314	99.18 400	99.10 286	98.34 392	99.41 338	98.48 351	98.52 425	98.98 431	97.05 337	99.78 372	95.59 452	99.50 368	98.96 421

ACMH+	98.40 8	99.50 124	99.43 142	99.71 127	99.86 59	99.76 70	99.32 157	99.77 147	99.53 178	99.77 144	99.76 152	99.26 96	99.78 372	97.77 317	99.88 184	99.60 205

CLD-MVS		98.76 313	98.57 318	99.33 297	99.57 267	98.97 299	97.53 457	99.55 285	96.41 455	99.27 340	99.13 407	99.07 131	99.78 372	96.73 402	99.89 174	99.23 358
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
0.4-1-1-0.1		93.18 459	91.66 463	97.73 446	95.83 499	95.29 466	95.30 492	95.90 485	93.59 481	90.58 498	94.40 507	77.87 490	99.77 385	97.31 360	84.20 496	98.15 479

E4		99.61 96	99.59 94	99.66 151	99.84 78	99.53 173	99.08 258	99.84 89	99.65 148	99.74 168	99.80 107	99.45 63	99.77 385	98.93 201	99.95 111	99.69 118

ttmdpeth		99.48 131	99.55 110	99.29 311	99.76 155	98.16 376	99.33 154	99.95 36	99.79 99	99.36 316	99.89 41	99.13 117	99.77 385	99.09 173	99.64 326	99.93 20

PVSNet_BlendedMVS		99.03 270	99.01 256	99.09 346	99.54 283	97.99 388	98.58 363	99.82 104	97.62 418	99.34 323	99.71 188	98.52 226	99.77 385	97.98 297	99.97 73	99.52 257

PVSNet_Blended		98.70 321	98.59 314	99.02 356	99.54 283	97.99 388	97.58 454	99.82 104	95.70 466	99.34 323	98.98 431	98.52 226	99.77 385	97.98 297	99.83 223	99.30 346

0.3-1-1-0.015		92.36 461	90.68 465	97.39 454	94.94 502	94.41 475	94.21 494	95.89 486	92.87 484	88.87 500	93.49 509	75.30 496	99.76 390	97.19 376	83.41 498	98.02 482

E3new		99.42 157	99.37 156	99.56 209	99.68 221	99.38 218	98.93 312	99.79 131	99.30 230	99.55 261	99.69 207	98.88 167	99.76 390	98.63 244	99.89 174	99.53 246

E2		99.54 114	99.51 119	99.62 181	99.78 138	99.47 184	99.01 282	99.82 104	99.55 174	99.69 190	99.77 144	99.26 96	99.76 390	98.82 210	99.93 140	99.62 187

E3		99.54 114	99.51 119	99.62 181	99.78 138	99.47 184	99.01 282	99.82 104	99.55 174	99.69 190	99.77 144	99.25 100	99.76 390	98.82 210	99.93 140	99.62 187

viewdifsd2359ckpt09		99.24 209	99.16 206	99.49 238	99.70 207	99.22 260	98.88 317	99.81 117	98.70 325	99.38 313	99.37 360	98.22 263	99.76 390	98.48 252	99.88 184	99.51 259

viewcassd2359sk11		99.48 131	99.45 135	99.58 197	99.73 183	99.42 205	98.96 304	99.80 122	99.44 201	99.63 221	99.74 165	99.09 124	99.76 390	98.72 233	99.91 158	99.57 223

eth_miper_zixun_eth		98.68 323	98.71 303	98.60 406	99.10 416	96.84 437	97.52 459	99.54 291	98.94 286	99.58 245	99.48 332	96.25 366	99.76 390	98.01 295	99.93 140	99.21 363

OPM-MVS		99.26 204	99.13 213	99.63 172	99.70 207	99.61 151	98.58 363	99.48 320	98.50 348	99.52 271	99.63 252	99.14 115	99.76 390	97.89 305	99.77 267	99.51 259
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
pmmvs-eth3d		99.48 131	99.47 128	99.51 232	99.77 151	99.41 212	98.81 333	99.66 213	99.42 212	99.75 158	99.66 228	99.20 104	99.76 390	98.98 189	99.99 16	99.36 326

pmmvs4		99.13 247	99.06 238	99.36 289	99.57 267	99.10 286	98.01 424	99.25 384	98.78 315	99.58 245	99.44 343	98.24 258	99.76 390	98.74 226	99.93 140	99.22 360

0.4-1-1-0.2		92.59 460	91.07 464	97.15 463	94.73 503	93.68 481	93.50 495	95.91 484	92.68 485	90.48 499	93.52 508	77.77 491	99.75 400	97.19 376	83.88 497	98.01 483

ETVMVS		96.14 440	95.22 451	98.89 381	98.80 452	98.01 387	98.66 353	98.35 452	98.71 324	97.18 477	96.31 506	74.23 500	99.75 400	96.64 409	98.13 467	98.90 430

AllTest		99.21 225	99.07 236	99.63 172	99.78 138	99.64 133	99.12 242	99.83 98	98.63 333	99.63 221	99.72 178	98.68 194	99.75 400	96.38 424	99.83 223	99.51 259

TestCases				99.63 172	99.78 138	99.64 133		99.83 98	98.63 333	99.63 221	99.72 178	98.68 194	99.75 400	96.38 424	99.83 223	99.51 259

CL-MVSNet_self_test		98.71 320	98.56 322	99.15 337	99.22 390	98.66 333	97.14 475	99.51 311	98.09 386	99.54 264	99.27 385	96.87 342	99.74 404	98.43 259	98.96 421	99.03 412

MVS		95.72 451	94.63 457	98.99 358	98.56 468	97.98 393	99.30 166	98.86 419	72.71 499	97.30 473	99.08 416	98.34 249	99.74 404	89.21 486	98.33 455	99.26 352

MG-MVS		98.52 339	98.39 336	98.94 365	99.15 404	97.39 420	98.18 403	99.21 395	98.89 299	99.23 348	99.63 252	97.37 323	99.74 404	94.22 472	99.61 338	99.69 118

c3_l		98.72 318	98.71 303	98.72 398	99.12 409	97.22 425	97.68 450	99.56 279	98.90 296	99.54 264	99.48 332	96.37 361	99.73 407	97.88 306	99.88 184	99.21 363

tpmvs		97.39 408	97.69 389	96.52 471	98.41 473	91.76 490	99.30 166	98.94 418	97.74 411	97.85 462	99.55 311	92.40 421	99.73 407	96.25 429	98.73 440	98.06 481

viewmacassd2359aftdt		99.63 85	99.61 88	99.68 139	99.84 78	99.61 151	99.14 230	99.87 69	99.71 121	99.75 158	99.77 144	99.54 55	99.72 409	98.91 203	99.96 87	99.70 106

thres600view7		96.60 426	96.16 429	97.93 436	99.63 237	96.09 454	99.18 212	97.57 470	98.77 317	98.72 408	97.32 486	87.04 463	99.72 409	88.57 488	98.62 445	97.98 484

EPMVS		96.53 427	96.32 426	97.17 462	98.18 480	92.97 485	99.39 129	89.95 502	98.21 379	98.61 417	99.59 289	86.69 469	99.72 409	96.99 385	99.23 406	98.81 440

PVSNet	97.47 15	98.42 350	98.44 331	98.35 418	99.46 325	96.26 449	96.70 485	99.34 360	97.68 416	99.00 377	99.13 407	97.40 320	99.72 409	97.59 344	99.68 313	99.08 401

MAR-MVS		98.24 365	97.92 379	99.19 332	98.78 456	99.65 126	99.17 217	99.14 405	95.36 469	98.04 452	98.81 448	97.47 317	99.72 409	95.47 455	99.06 413	98.21 475
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
viewmanbaseed2359cas		99.50 124	99.47 128	99.61 187	99.73 183	99.52 177	99.03 273	99.83 98	99.49 185	99.65 213	99.64 237	99.18 106	99.71 414	98.73 231	99.92 146	99.58 217

testing91		96.00 444	95.32 449	98.02 431	98.76 459	95.39 463	98.38 390	98.65 434	98.82 308	96.84 480	96.71 499	75.06 498	99.71 414	96.46 420	98.23 459	98.98 420

miper_ehance_all_eth		98.59 332	98.59 314	98.59 407	98.98 433	97.07 429	97.49 460	99.52 306	98.50 348	99.52 271	99.37 360	96.41 359	99.71 414	97.86 310	99.62 331	99.00 419

Gipuma		99.57 100	99.59 94	99.49 238	99.98 3	99.71 100	99.72 33	99.84 89	99.81 91	99.94 48	99.78 132	98.91 163	99.71 414	98.41 260	99.95 111	99.05 408
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
viewdifsd2359ckpt13		99.42 157	99.37 156	99.57 205	99.72 188	99.46 190	99.01 282	99.80 122	99.20 248	99.51 278	99.60 279	98.92 160	99.70 418	98.65 242	99.90 160	99.55 230

ambc				99.20 331	99.35 354	98.53 350	99.17 217	99.46 326		99.67 203	99.80 107	98.46 233	99.70 418	97.92 302	99.70 300	99.38 320

HQP4-MVS										98.15 445			99.70 418			99.53 246

CNVR-MVS		98.99 284	98.80 298	99.56 209	99.25 385	99.43 202	98.54 373	99.27 379	98.58 339	98.80 400	99.43 344	98.53 223	99.70 418	97.22 373	99.59 345	99.54 240

tpm2		96.35 433	96.22 428	96.73 469	98.88 443	91.75 491	99.21 201	98.51 441	93.27 483	97.89 458	99.21 401	84.83 473	99.70 418	96.04 436	98.18 463	98.75 447

HQP-MVS		98.36 355	98.02 368	99.39 276	99.31 370	98.94 303	97.98 428	99.37 353	97.45 427	98.15 445	98.83 445	96.67 347	99.70 418	94.73 465	99.67 319	99.53 246

PatchMatch-RL		98.68 323	98.47 327	99.30 310	99.44 330	99.28 241	98.14 409	99.54 291	97.12 444	99.11 367	99.25 390	97.80 298	99.70 418	96.51 415	99.30 394	98.93 426

testing11		96.05 443	95.41 446	97.97 434	98.78 456	95.27 467	98.59 361	98.23 456	98.86 302	96.56 484	96.91 493	75.20 497	99.69 425	97.26 367	98.29 457	98.93 426

testing99		95.86 448	95.19 452	97.87 438	98.76 459	95.03 469	98.62 355	98.44 445	98.68 327	96.67 483	96.66 500	74.31 499	99.69 425	96.51 415	98.03 469	98.90 430

miper_enhance_ethall		98.03 377	97.94 377	98.32 421	98.27 477	96.43 445	96.95 481	99.41 338	96.37 457	99.43 296	98.96 435	94.74 389	99.69 425	97.71 325	99.62 331	98.83 438

test_yl		98.25 363	97.95 373	99.13 341	99.17 401	98.47 353	99.00 288	98.67 432	98.97 280	99.22 351	99.02 426	91.31 431	99.69 425	97.26 367	98.93 422	99.24 355

DCV-MVSNet		98.25 363	97.95 373	99.13 341	99.17 401	98.47 353	99.00 288	98.67 432	98.97 280	99.22 351	99.02 426	91.31 431	99.69 425	97.26 367	98.93 422	99.24 355

MS-PatchMatch		99.00 281	98.97 271	99.09 346	99.11 414	98.19 372	98.76 342	99.33 365	98.49 350	99.44 292	99.58 292	98.21 264	99.69 425	98.20 277	99.62 331	99.39 318

v148		99.40 165	99.41 148	99.39 276	99.76 155	98.94 303	99.09 255	99.59 263	99.17 256	99.81 116	99.61 271	98.41 239	99.69 425	99.32 127	99.94 128	99.53 246

test_prior				99.46 249	99.35 354	99.22 260		99.39 348					99.69 425			99.48 274

tpm cat1		96.78 421	96.98 414	96.16 476	98.85 446	90.59 500	99.08 258	99.32 367	92.37 486	97.73 468	99.46 339	91.15 434	99.69 425	96.07 435	98.80 430	98.21 475

PAPM_NR		98.36 355	98.04 366	99.33 297	99.48 315	98.93 306	98.79 339	99.28 378	97.54 422	98.56 424	98.57 458	97.12 334	99.69 425	94.09 474	98.90 428	99.38 320

PAPM		95.61 454	94.71 456	98.31 423	99.12 409	96.63 439	96.66 486	98.46 444	90.77 491	96.25 487	98.68 455	93.01 411	99.69 425	81.60 497	97.86 473	98.62 451

OMC-MVS		98.90 296	98.72 302	99.44 256	99.39 342	99.42 205	98.58 363	99.64 231	97.31 435	99.44 292	99.62 261	98.59 207	99.69 425	96.17 433	99.79 255	99.22 360

casdiffseed414692147		99.68 64	99.68 63	99.67 143	99.86 59	99.65 126	99.32 157	99.87 69	99.75 109	99.77 144	99.80 107	99.61 41	99.68 437	99.21 143	99.95 111	99.67 134

E-PMN		97.14 415	97.43 398	96.27 474	98.79 454	91.62 492	95.54 490	99.01 416	99.44 201	98.88 389	99.12 411	92.78 413	99.68 437	94.30 471	99.03 417	97.50 488

TSAR-MVS + GP.		99.12 250	99.04 249	99.38 279	99.34 363	99.16 273	98.15 407	99.29 375	98.18 382	99.63 221	99.62 261	99.18 106	99.68 437	98.20 277	99.74 281	99.30 346

MVS-HIRNet		97.86 382	98.22 352	96.76 466	99.28 379	91.53 493	98.38 390	92.60 498	99.13 264	99.31 333	99.96 15	97.18 333	99.68 437	98.34 265	99.83 223	99.07 406

PAPR		97.56 398	97.07 410	99.04 355	98.80 452	98.11 380	97.63 451	99.25 384	94.56 480	98.02 454	98.25 468	97.43 319	99.68 437	90.90 485	98.74 437	99.33 335

ITE_SJBPF				99.38 279	99.63 237	99.44 198		99.73 170	98.56 340	99.33 325	99.53 315	98.88 167	99.68 437	96.01 437	99.65 324	99.02 417

MVStest1		98.22 368	98.09 363	98.62 404	99.04 426	96.23 450	99.20 202	99.92 42	99.44 201	99.98 14	99.87 56	85.87 471	99.67 443	99.91 33	99.57 349	99.95 14

thres100view900		96.39 432	96.03 432	97.47 451	99.63 237	95.93 455	99.18 212	97.57 470	98.75 321	98.70 411	97.31 487	87.04 463	99.67 443	87.62 491	98.51 449	96.81 493

tfpn200view9		96.30 435	95.89 434	97.53 448	99.58 257	96.11 452	99.00 288	97.54 473	98.43 353	98.52 425	96.98 491	86.85 465	99.67 443	87.62 491	98.51 449	96.81 493

1314		98.00 379	97.90 381	98.27 426	98.90 438	97.45 416	99.30 166	99.06 411	94.98 474	97.21 476	99.12 411	98.43 236	99.67 443	95.58 453	98.56 447	97.71 487

thres400		96.40 431	95.89 434	97.92 437	99.58 257	96.11 452	99.00 288	97.54 473	98.43 353	98.52 425	96.98 491	86.85 465	99.67 443	87.62 491	98.51 449	97.98 484

testing3-2		96.51 429	96.43 424	96.74 468	99.36 350	91.38 495	99.10 250	97.87 466	99.48 188	98.57 422	98.71 452	76.65 494	99.66 448	98.87 205	99.26 401	99.18 372

EMVS		96.96 418	97.28 402	95.99 478	98.76 459	91.03 496	95.26 493	98.61 435	99.34 223	98.92 385	98.88 442	93.79 399	99.66 448	92.87 479	99.05 415	97.30 492

MVS_Test		99.28 198	99.31 175	99.19 332	99.35 354	98.79 322	99.36 144	99.49 319	99.17 256	99.21 353	99.67 223	98.78 180	99.66 448	99.09 173	99.66 322	99.10 390

EPNet_dtu		97.62 395	97.79 386	97.11 464	96.67 498	92.31 487	98.51 377	98.04 460	99.24 241	95.77 490	99.47 336	93.78 400	99.66 448	98.98 189	99.62 331	99.37 323
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
BH-RMVSNet		98.41 351	98.14 360	99.21 329	99.21 392	98.47 353	98.60 358	98.26 455	98.35 367	98.93 382	99.31 377	97.20 332	99.66 448	94.32 470	99.10 411	99.51 259

MDTV_nov1_ep13			97.73 388		98.70 464	90.83 497	99.15 226	98.02 461	98.51 347	98.82 397	99.61 271	90.98 436	99.66 448	96.89 392	98.92 424

MVS_111021_LR		99.13 247	99.03 251	99.42 262	99.58 257	99.32 235	97.91 437	99.73 170	98.68 327	99.31 333	99.48 332	99.09 124	99.66 448	97.70 328	99.77 267	99.29 349

BH-untuned		98.22 368	98.09 363	98.58 409	99.38 345	97.24 424	98.55 370	98.98 417	97.81 410	99.20 358	98.76 450	97.01 338	99.65 455	94.83 464	98.33 455	98.86 435

RPSCF		99.18 234	99.02 252	99.64 165	99.83 86	99.85 21	99.44 119	99.82 104	98.33 372	99.50 281	99.78 132	97.90 290	99.65 455	96.78 399	99.83 223	99.44 300

SD_0403		97.42 406	96.90 419	98.98 360	99.54 283	97.90 396	99.52 94	99.54 291	99.34 223	97.87 460	98.85 444	98.72 190	99.64 457	78.93 498	99.83 223	99.40 315

USDC		98.96 288	98.93 276	99.05 354	99.54 283	97.99 388	97.07 478	99.80 122	98.21 379	99.75 158	99.77 144	98.43 236	99.64 457	97.90 304	99.88 184	99.51 259

DeepPCF-MVS	98.42 6	99.18 234	99.02 252	99.67 143	99.22 390	99.75 79	97.25 469	99.47 323	98.72 322	99.66 209	99.70 198	99.29 90	99.63 459	98.07 291	99.81 243	99.62 187

UBG		96.53 427	95.95 433	98.29 425	98.87 444	96.31 448	98.48 381	98.07 459	98.83 307	97.32 472	96.54 501	79.81 484	99.62 460	96.84 396	98.74 437	98.95 423

alignmvs		98.28 361	97.96 372	99.25 325	99.12 409	98.93 306	99.03 273	98.42 446	99.64 152	98.72 408	97.85 476	90.86 441	99.62 460	98.88 204	99.13 408	99.19 370

DeepMVS_CX				97.98 433	99.69 213	96.95 431		99.26 381	75.51 498	95.74 491	98.28 467	96.47 355	99.62 460	91.23 484	97.89 471	97.38 490

TinyColmap		98.97 285	98.93 276	99.07 351	99.46 325	98.19 372	97.75 443	99.75 160	98.79 313	99.54 264	99.70 198	98.97 153	99.62 460	96.63 410	99.83 223	99.41 312

TAPA-MVS	97.92 13	98.03 377	97.55 394	99.46 249	99.47 321	99.44 198	98.50 378	99.62 238	86.79 493	99.07 373	99.26 388	98.26 257	99.62 460	97.28 364	99.73 287	99.31 344
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DPM-MVS		98.28 361	97.94 377	99.32 302	99.36 350	99.11 279	97.31 467	98.78 426	96.88 448	98.84 395	99.11 414	97.77 300	99.61 465	94.03 476	99.36 386	99.23 358

thres200		96.09 441	95.68 441	97.33 457	99.48 315	96.22 451	98.53 375	97.57 470	98.06 388	98.37 433	96.73 498	86.84 467	99.61 465	86.99 494	98.57 446	96.16 496

DP-MVS Recon		98.50 342	98.23 351	99.31 306	99.49 310	99.46 190	98.56 369	99.63 235	94.86 477	98.85 394	99.37 360	97.81 297	99.59 467	96.08 434	99.44 375	98.88 433

PVSNet_0	95.53 19	95.85 449	95.31 450	97.47 451	98.78 456	93.48 483	95.72 489	99.40 345	96.18 460	97.37 471	97.73 477	95.73 373	99.58 468	95.49 454	81.40 499	99.36 326

MGCFI-Net		99.02 272	99.01 256	99.06 353	99.11 414	98.60 341	99.63 64	99.67 208	99.63 154	98.58 420	97.65 479	99.07 131	99.57 469	98.85 206	98.92 424	99.03 412

Syy-MVS		98.17 371	97.85 383	99.15 337	98.50 471	98.79 322	98.60 358	99.21 395	97.89 402	96.76 481	96.37 504	95.47 381	99.57 469	99.10 172	98.73 440	99.09 395

myMVS_eth3d		95.63 453	94.73 455	98.34 420	98.50 471	96.36 446	98.60 358	99.21 395	97.89 402	96.76 481	96.37 504	72.10 502	99.57 469	94.38 469	98.73 440	99.09 395

API-MVS		98.38 354	98.39 336	98.35 418	98.83 448	99.26 246	99.14 230	99.18 400	98.59 338	98.66 413	98.78 449	98.61 205	99.57 469	94.14 473	99.56 350	96.21 495

TestfortrainingZip				99.38 279	99.17 401	99.25 249	99.38 132	98.82 422	98.93 291	99.68 195	99.49 328	98.11 275	99.56 473		98.44 453	99.32 339

sasdasda		99.02 272	99.00 260	99.09 346	99.10 416	98.70 328	99.61 73	99.66 213	99.63 154	98.64 414	97.65 479	99.04 140	99.54 474	98.79 217	98.92 424	99.04 410

KD-MVS_2432*1600		95.89 445	95.41 446	97.31 458	94.96 500	93.89 477	97.09 476	99.22 392	97.23 438	98.88 389	99.04 421	79.23 486	99.54 474	96.24 430	96.81 480	98.50 464

miper_refine_blended		95.89 445	95.41 446	97.31 458	94.96 500	93.89 477	97.09 476	99.22 392	97.23 438	98.88 389	99.04 421	79.23 486	99.54 474	96.24 430	96.81 480	98.50 464

canonicalmvs		99.02 272	99.00 260	99.09 346	99.10 416	98.70 328	99.61 73	99.66 213	99.63 154	98.64 414	97.65 479	99.04 140	99.54 474	98.79 217	98.92 424	99.04 410

MVS_111021_HR		99.12 250	99.02 252	99.40 273	99.50 305	99.11 279	97.92 435	99.71 183	98.76 320	99.08 370	99.47 336	99.17 108	99.54 474	97.85 312	99.76 270	99.54 240

test_241102_ONE					99.69 213	99.82 41		99.54 291	99.12 267	99.82 109	99.49 328	98.91 163	99.52 479

gg-mvs-nofinetune		95.87 447	95.17 453	97.97 434	98.19 479	96.95 431	99.69 45	89.23 503	99.89 55	96.24 488	99.94 19	81.19 478	99.51 480	93.99 477	98.20 460	97.44 489

TR-MVS		97.44 405	97.15 407	98.32 421	98.53 469	97.46 414	98.47 382	97.91 464	96.85 449	98.21 441	98.51 462	96.42 357	99.51 480	92.16 481	97.29 478	97.98 484

BH-w/o		97.20 412	97.01 413	97.76 442	99.08 421	95.69 459	98.03 423	98.52 440	95.76 465	97.96 455	98.02 472	95.62 375	99.47 482	92.82 480	97.25 479	98.12 480

PMVS	92.94 21	98.82 307	98.81 296	98.85 385	99.84 78	97.99 388	99.20 202	99.47 323	99.71 121	99.42 299	99.82 90	98.09 276	99.47 482	93.88 478	99.85 210	99.07 406
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CMPMVS	77.52 23	98.50 342	98.19 357	99.41 270	98.33 476	99.56 166	99.01 282	99.59 263	95.44 468	99.57 248	99.80 107	95.64 374	99.46 484	96.47 419	99.92 146	99.21 363
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GA-MVS		97.99 380	97.68 390	98.93 368	99.52 297	98.04 386	97.19 471	99.05 412	98.32 373	98.81 398	98.97 433	89.89 454	99.41 485	98.33 266	99.05 415	99.34 334

cl22		97.56 398	97.28 402	98.40 416	98.37 475	96.75 438	97.24 470	99.37 353	97.31 435	99.41 305	99.22 397	87.30 460	99.37 486	97.70 328	99.62 331	99.08 401

UWE-MVS-28		95.64 452	95.47 444	96.14 477	97.98 486	90.39 501	98.49 380	95.81 488	99.02 276	98.03 453	98.19 469	84.49 475	99.28 487	88.75 487	98.47 452	98.75 447

dmvs_re		98.69 322	98.48 326	99.31 306	99.55 281	99.42 205	99.54 90	98.38 450	99.32 227	98.72 408	98.71 452	96.76 345	99.21 488	96.01 437	99.35 388	99.31 344

GG-mvs-BLEND				97.36 455	97.59 494	96.87 434	99.70 38	88.49 504		94.64 494	97.26 488	80.66 480	99.12 489	91.50 483	96.50 488	96.08 497

MSLP-MVS++		99.05 266	99.09 230	98.91 374	99.21 392	98.36 364	98.82 332	99.47 323	98.85 303	98.90 388	99.56 303	98.78 180	99.09 490	98.57 248	99.68 313	99.26 352

FPMVS		96.32 434	95.50 443	98.79 393	99.60 244	98.17 375	98.46 386	98.80 425	97.16 442	96.28 486	99.63 252	82.19 477	99.09 490	88.45 489	98.89 429	99.10 390

dmvs_testset		97.27 411	96.83 421	98.59 407	99.46 325	97.55 409	99.25 190	96.84 479	98.78 315	97.24 475	97.67 478	97.11 335	98.97 492	86.59 496	98.54 448	99.27 350

myMVS_eth3d28		96.23 437	95.74 439	97.70 447	98.86 445	95.59 462	98.66 353	98.14 458	98.96 282	97.67 469	97.06 490	76.78 493	98.92 493	97.10 380	98.41 454	98.58 456

OPU-MVS				99.29 311	99.12 409	99.44 198	99.20 202				99.40 351	99.00 145	98.84 494	96.54 413	99.60 341	99.58 217

cascas		96.99 416	96.82 422	97.48 450	97.57 496	95.64 460	96.43 487	99.56 279	91.75 488	97.13 479	97.61 482	95.58 376	98.63 495	96.68 404	99.11 410	98.18 478

MVE	92.54 22	96.66 425	96.11 430	98.31 423	99.68 221	97.55 409	97.94 433	95.60 489	99.37 219	90.68 497	98.70 454	96.56 350	98.61 496	86.94 495	99.55 354	98.77 445
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MonoMVSNet		98.23 366	98.32 344	97.99 432	98.97 434	96.62 440	99.49 107	98.42 446	99.62 157	99.40 310	99.79 119	95.51 380	98.58 497	97.68 339	95.98 491	98.76 446

PC_three_1452									97.56 419	99.68 195	99.41 347	99.09 124	97.09 498	96.66 406	99.60 341	99.62 187

tmp_tt		95.75 450	95.42 445	96.76 466	89.90 506	94.42 474	98.86 321	97.87 466	78.01 497	99.30 338	99.69 207	97.70 303	95.89 499	99.29 133	98.14 465	99.95 14

dongtai		89.37 463	88.91 466	90.76 481	99.19 397	77.46 506	95.47 491	87.82 505	92.28 487	94.17 495	98.82 447	71.22 503	95.54 500	63.85 499	97.34 477	99.27 350

SD-MVS		99.01 278	99.30 180	98.15 428	99.50 305	99.40 213	98.94 309	99.61 246	99.22 247	99.75 158	99.82 90	99.54 55	95.51 501	97.48 350	99.87 197	99.54 240
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
kuosan		85.65 465	84.57 468	88.90 483	97.91 488	77.11 507	96.37 488	87.62 506	85.24 496	85.45 501	96.83 494	69.94 505	90.98 502	45.90 500	95.83 493	98.62 451

test123		29.31 466	33.05 471	18.08 484	25.93 508	12.24 509	97.53 457	10.93 509	11.78 502	24.21 503	50.08 514	21.04 506	8.60 503	23.51 501	32.43 502	33.39 499

testmvs		28.94 467	33.33 469	15.79 485	26.03 507	9.81 510	96.77 484	15.67 508	11.55 503	23.87 504	50.74 513	19.03 507	8.53 504	23.21 502	33.07 501	29.03 500

mmdepth		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

test_blank		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet_test		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

cdsmvs_eth3d_5k		24.88 468	33.17 470	0.00 486	0.00 509	0.00 511	0.00 497	99.62 238	0.00 504	0.00 505	99.13 407	99.82 18	0.00 505	0.00 503	0.00 503	0.00 501

pcd_1.5k_mvsjas		16.61 469	22.14 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	99.28 92	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		8.26 480	11.02 483	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	99.16 405	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		8.33 470	11.11 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	100.00 1	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

WAC-MVS						96.36 446								95.20 460

FOURS1					99.83 86	99.89 10	99.74 27	99.71 183	99.69 130	99.63 221

test_one_0601					99.63 237	99.76 70		99.55 285	99.23 243	99.31 333	99.61 271	98.59 207

eth-test2					0.00 509

eth-test					0.00 509

RE-MVS-def			99.13 213		99.54 283	99.74 87	99.26 184	99.62 238	99.16 258	99.52 271	99.64 237	98.57 210		97.27 365	99.61 338	99.54 240

IU-MVS					99.69 213	99.77 63		99.22 392	97.50 425	99.69 190				97.75 321	99.70 300	99.77 80

save fliter					99.53 290	99.25 249	98.29 396	99.38 352	99.07 271

test0726					99.69 213	99.80 51	99.24 191	99.57 274	99.16 258	99.73 173	99.65 235	98.35 247

GSMVS																99.14 384

test_part2					99.62 241	99.67 118				99.55 261

sam_mvs1												90.81 442				99.14 384

sam_mvs												90.52 448

MTGPA								99.53 301

MTMP							99.09 255	98.59 438

test9_res														95.10 462	99.44 375	99.50 265

agg_prior2														94.58 468	99.46 374	99.50 265

test_prior4						99.19 267	98.00 426

test_prior2							97.95 432		97.87 405	98.05 451	99.05 419	97.90 290		95.99 440	99.49 370

新几何2							98.04 421

旧先验1					99.49 310	99.29 239		99.26 381			99.39 355	97.67 307			99.36 386	99.46 283

原ACMM2							97.92 435

test222					99.51 299	99.08 288	97.83 441	99.29 375	95.21 472	98.68 412	99.31 377	97.28 326			99.38 383	99.43 306

segment_acmp												98.37 245

testdata1							97.72 446		97.86 407

plane_prior7					99.58 257	99.38 218

plane_prior6					99.47 321	99.26 246						97.24 327

plane_prior4											99.25 390

plane_prior3						99.31 236			98.36 362	99.14 363

plane_prior2							98.80 336		98.94 286

plane_prior1					99.51 299

plane_prior						99.24 254	98.42 388		97.87 405						99.71 298

n2								0.00 510

nn								0.00 510

door-mid								99.83 98

test11								99.29 375

door								99.77 147

HQP5-MVS						98.94 303

HQP-NCC					99.31 370		97.98 428		97.45 427	98.15 445

ACMP_Plane					99.31 370		97.98 428		97.45 427	98.15 445

BP-MVS														94.73 465

HQP3-MVS								99.37 353							99.67 319

HQP2-MVS												96.67 347

NP-MVS					99.40 341	99.13 276					98.83 445

MDTV_nov1_ep13_2view						91.44 494	99.14 230		97.37 432	99.21 353		91.78 429		96.75 400		99.03 412

ACMMP++_ref															99.94 128

ACMMP++															99.79 255

Test By Simon												98.41 239

High-resolution multi-view benchmark