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	99.12 241	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 94	99.70 108	99.17 216	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 65

h-mvs33		98.61 325	98.34 341	99.44 255	99.60 243	98.67 329	99.27 178	99.44 331	99.68 129	99.32 327	99.49 327	92.50 418	100.00 1	99.24 137	96.51 486	99.65 156

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		99.48 129	99.65 73	98.95 363	99.71 191	97.27 422	99.50 102	99.82 103	99.59 167	99.41 304	99.85 68	99.62 40	100.00 1	99.53 89	99.89 173	99.59 211

HyFIR lowres test		98.91 293	98.64 308	99.73 113	99.85 72	99.47 183	98.07 417	99.83 97	98.64 331	99.89 72	99.60 278	92.57 415	100.00 1	99.33 125	99.97 73	99.72 97

NormalMVS		99.09 257	98.91 283	99.62 180	99.78 137	99.11 278	99.36 144	99.77 147	99.82 85	99.68 194	99.53 314	93.30 404	99.99 7	99.24 137	99.76 269	99.74 89

SymmetryMVS		99.01 277	98.82 293	99.58 196	99.65 233	99.11 278	99.36 144	99.20 397	99.82 85	99.68 194	99.53 314	93.30 404	99.99 7	99.24 137	99.63 328	99.64 168

Elysia		99.69 59	99.65 73	99.81 54	99.86 59	99.72 95	99.34 148	99.77 147	99.94 36	99.91 62	99.76 149	98.55 214	99.99 7	99.70 61	99.98 50	99.72 97

StellarMVS		99.69 59	99.65 73	99.81 54	99.86 59	99.72 95	99.34 148	99.77 147	99.94 36	99.91 62	99.76 149	98.55 214	99.99 7	99.70 61	99.98 50	99.72 97

fmvsm_s_conf0.5_n_5		99.78 37	99.76 49	99.85 32	99.79 129	99.72 95	98.84 324	99.96 28	99.96 28	99.96 34	99.72 175	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	99.08 257	99.97 20	99.98 18	99.96 34	99.79 118	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	99.64 132	99.12 241	99.91 51	99.98 18	99.95 45	99.67 220	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	99.11 246	99.91 51	99.98 18	99.96 34	99.64 236	99.60 43	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	99.01 281	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		99.52 119	99.42 143	99.83 41	99.86 59	99.65 126	99.52 94	99.81 116	99.87 62	99.81 115	99.79 118	96.78 343	99.99 7	99.83 46	99.51 364	99.86 46

test_fmvsmconf_n		99.85 12	99.84 20	99.88 19	99.91 31	99.73 90	98.97 299	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	99.55 169	99.17 216	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 86	99.80 115	99.65 126	99.63 64	99.86 75	99.97 25	99.89 72	99.89 41	99.52 59	99.99 7	99.42 110	99.96 87	99.65 156

sd_testset		99.78 37	99.78 39	99.80 64	99.80 115	99.76 70	99.80 14	99.79 130	99.97 25	99.89 72	99.89 41	99.53 57	99.99 7	99.36 118	99.96 87	99.65 156

test_vis1_n_1920		99.72 53	99.88 7	99.27 318	99.93 24	97.84 397	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	99.53 225	99.96 7	98.62 339	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 95	99.64 78	99.53 225	99.79 129	98.82 316	99.58 82	99.97 20	99.95 32	99.96 34	99.76 149	98.44 235	99.99 7	99.34 122	99.96 87	99.78 75

IterMVS-SCA-FT		99.00 280	99.16 205	98.51 409	99.75 170	95.90 455	98.07 417	99.84 88	99.84 75	99.89 72	99.73 167	96.01 370	99.99 7	99.33 125	100.00 1	99.63 174

IterMVS		98.97 284	99.16 205	98.42 414	99.74 178	95.64 459	98.06 419	99.83 97	99.83 81	99.85 98	99.74 162	96.10 369	99.99 7	99.27 136	100.00 1	99.63 174
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	99.81 106	99.53 172	99.15 225	99.89 60	99.99 3	99.98 14	99.86 63	99.13 116	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	99.81 106	99.75 79	99.06 263	99.85 81	99.99 3	99.97 24	99.84 76	99.12 119	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	98.94 308	99.96 28	99.98 18	99.96 34	99.78 131	99.88 11	99.98 26	99.96 9	99.99 16	99.90 29

GDP-MVS		98.81 308	98.57 317	99.50 233	99.53 289	99.12 277	99.28 174	99.86 75	99.53 176	99.57 247	99.32 373	90.88 439	99.98 26	99.46 100	99.74 280	99.42 310

WB-MVS		99.44 149	99.32 172	99.80 64	99.81 106	99.61 150	99.47 112	99.81 116	99.82 85	99.71 182	99.72 175	96.60 348	99.98 26	99.75 56	99.23 405	99.82 63

test_fmvs1_n		99.68 64	99.81 28	99.28 313	99.95 15	97.93 393	99.49 107	100.00 1	99.82 85	99.99 7	99.89 41	99.21 102	99.98 26	99.97 4	99.98 50	99.93 20

test_fmvs2		99.72 53	99.85 17	99.34 293	99.91 31	98.08 384	99.48 109	100.00 1	99.90 49	99.99 7	99.91 31	99.50 61	99.98 26	99.98 1	99.99 16	99.96 13

patch_mono-2		99.51 120	99.46 133	99.64 164	99.70 206	99.11 278	99.04 269	99.87 69	99.71 118	99.47 285	99.79 118	98.24 258	99.98 26	99.38 114	99.96 87	99.83 56

CHOSEN 280x420		98.41 350	98.41 333	98.40 415	99.34 362	95.89 456	96.94 481	99.44 331	98.80 311	99.25 343	99.52 318	93.51 403	99.98 26	98.94 199	99.98 50	99.32 338

Fast-Effi-MVS+-dtu		99.20 226	99.12 216	99.43 259	99.25 384	99.69 112	99.05 264	99.82 103	99.50 181	98.97 377	99.05 418	98.98 151	99.98 26	98.20 276	99.24 403	98.62 450

Effi-MVS+-dtu		99.07 261	98.92 279	99.52 227	98.89 440	99.78 57	99.15 225	99.66 213	99.34 221	98.92 384	99.24 394	97.69 304	99.98 26	98.11 286	99.28 396	98.81 439

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 63	99.68 48	99.85 81	99.95 32	99.98 14	99.92 27	99.28 91	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 75	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		99.41 162	99.44 139	99.31 305	99.57 266	98.40 358	99.77 19	99.80 121	99.73 108	99.63 220	99.30 378	98.02 280	99.98 26	99.43 105	99.69 307	99.55 229

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 26	99.77 19	99.80 121	99.73 108	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 71	99.88 45	99.66 120	99.69 45	99.92 42	99.67 137	99.77 144	99.75 157	99.61 41	99.98 26	99.35 121	99.98 50	99.72 97
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSM_04072		99.55 109	99.55 109	99.55 215	99.71 191	99.24 253	99.27 178	99.79 130	99.72 112	99.78 132	99.64 236	99.36 79	99.97 43	98.74 225	99.90 159	99.45 284

KinetiMVS		99.66 76	99.63 81	99.76 86	99.89 39	99.57 164	99.37 140	99.82 103	99.95 32	99.90 67	99.63 251	98.57 210	99.97 43	99.65 70	99.94 127	99.74 89

LuminaMVS		99.39 168	99.28 187	99.73 113	99.83 85	99.49 179	99.00 287	99.05 411	99.81 91	99.89 72	99.79 118	96.54 352	99.97 43	99.64 73	99.98 50	99.73 93

fmvsm_s_conf0.5_n_8		99.76 46	99.72 55	99.88 19	99.82 94	99.75 79	99.02 276	99.87 69	99.98 18	99.98 14	99.81 97	99.07 130	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	99.42 204	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	99.45 251	99.93 24	98.40 358	99.30 165	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		99.48 129	99.65 73	98.97 360	99.54 282	97.16 425	99.11 246	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 73

Anonymous20240521		99.44 149	99.42 143	99.49 237	99.89 39	98.96 300	99.62 67	99.76 155	99.85 71	99.82 108	99.88 50	96.39 359	99.97 43	99.59 78	99.98 50	99.55 229

xiu_mvs_v1_base_debu		99.23 210	99.34 166	98.91 373	99.59 249	98.23 367	98.47 381	99.66 213	99.61 159	99.68 194	98.94 436	99.39 70	99.97 43	99.18 150	99.55 353	98.51 460

xiu_mvs_v2_base		99.02 271	99.11 219	98.77 394	99.37 346	98.09 381	98.13 409	99.51 310	99.47 191	99.42 298	98.54 460	99.38 74	99.97 43	98.83 207	99.33 389	98.24 472

xiu_mvs_v1_base		99.23 210	99.34 166	98.91 373	99.59 249	98.23 367	98.47 381	99.66 213	99.61 159	99.68 194	98.94 436	99.39 70	99.97 43	99.18 150	99.55 353	98.51 460

xiu_mvs_v1_base_debi		99.23 210	99.34 166	98.91 373	99.59 249	98.23 367	98.47 381	99.66 213	99.61 159	99.68 194	98.94 436	99.39 70	99.97 43	99.18 150	99.55 353	98.51 460

anonymousdsp		99.80 30	99.77 45	99.90 8	99.96 7	99.88 12	99.73 30	99.85 81	99.70 124	99.92 59	99.93 22	99.45 62	99.97 43	99.36 118	100.00 1	99.85 49

UA-Net		99.78 37	99.76 49	99.86 30	99.72 187	99.71 100	99.91 4	99.95 36	99.96 28	99.71 182	99.91 31	99.15 111	99.97 43	99.50 94	100.00 1	99.90 29

PS-MVSNAJ		99.00 280	99.08 231	98.76 395	99.37 346	98.10 380	98.00 425	99.51 310	99.47 191	99.41 304	98.50 462	99.28 91	99.97 43	98.83 207	99.34 388	98.20 476

pmmvs3		98.08 374	97.80 383	98.91 373	99.41 339	97.69 405	97.87 438	99.66 213	95.87 461	99.50 280	99.51 320	90.35 448	99.97 43	98.55 248	99.47 371	99.08 400

DTE-MVSNet		99.68 64	99.61 87	99.88 19	99.80 115	99.87 15	99.67 53	99.71 183	99.72 112	99.84 101	99.78 131	98.67 197	99.97 43	99.30 130	99.95 111	99.80 65

jason		99.16 239	99.11 219	99.32 301	99.75 170	98.44 355	98.26 398	99.39 347	98.70 324	99.74 167	99.30 378	98.54 218	99.97 43	98.48 251	99.82 232	99.55 229
jason: jason.
lupinMVS		98.96 287	98.87 286	99.24 326	99.57 266	98.40 358	98.12 410	99.18 399	98.28 374	99.63 220	99.13 406	98.02 280	99.97 43	98.22 274	99.69 307	99.35 328

K. test v3		98.87 300	98.60 311	99.69 137	99.93 24	99.46 189	99.74 27	94.97 489	99.78 102	99.88 82	99.88 50	93.66 401	99.97 43	99.61 76	99.95 111	99.64 168

lessismore_v0				99.64 164	99.86 59	99.38 217		90.66 499		99.89 72	99.83 83	94.56 391	99.97 43	99.56 83	99.92 145	99.57 222

EPNet		98.13 371	97.77 386	99.18 333	94.57 503	97.99 387	99.24 190	97.96 461	99.74 107	97.29 473	99.62 260	93.13 408	99.97 43	98.59 245	99.83 222	99.58 216
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		99.40 164	99.38 151	99.44 255	99.90 37	98.66 332	98.94 308	99.91 51	97.97 392	99.79 128	99.73 167	99.05 138	99.97 43	99.15 156	99.99 16	99.68 124

IterMVS-LS		99.41 162	99.47 128	99.25 324	99.81 106	98.09 381	98.85 322	99.76 155	99.62 154	99.83 107	99.64 236	98.54 218	99.97 43	99.15 156	99.99 16	99.68 124
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 52

usedtu_dtu_shiyan2		99.44 149	99.33 171	99.78 75	99.86 59	99.76 70	99.54 90	99.79 130	99.66 141	99.66 208	99.79 118	96.76 344	99.96 68	99.15 156	99.72 293	99.62 186

fmvsm_s_conf0.5_n_7		99.73 52	99.78 39	99.60 190	99.74 178	98.93 305	98.85 322	99.96 28	99.96 28	99.97 24	99.76 149	99.82 18	99.96 68	99.95 14	99.98 50	99.90 29

BP-MVS1		98.72 317	98.46 327	99.50 233	99.53 289	99.00 292	99.34 148	98.53 438	99.65 145	99.73 172	99.38 356	90.62 444	99.96 68	99.50 94	99.86 204	99.55 229

MVSMamba_PlusPlus		99.55 109	99.58 97	99.47 244	99.68 220	99.40 212	99.52 94	99.70 192	99.92 45	99.77 144	99.86 63	98.28 254	99.96 68	99.54 86	99.90 159	99.05 407

test_vis1_n		99.68 64	99.79 34	99.36 288	99.94 18	98.18 373	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 52

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 26	99.82 10	99.82 103	99.84 75	99.94 48	99.91 31	99.13 116	99.96 68	99.83 46	99.99 16	99.83 56

PS-CasMVS		99.66 76	99.58 97	99.89 11	99.80 115	99.85 21	99.66 57	99.73 170	99.62 154	99.84 101	99.71 185	98.62 203	99.96 68	99.30 130	99.96 87	99.86 46

PEN-MVS		99.66 76	99.59 93	99.89 11	99.83 85	99.87 15	99.66 57	99.73 170	99.70 124	99.84 101	99.73 167	98.56 213	99.96 68	99.29 133	99.94 127	99.83 56

TranMVSNet+NR-MVSNet		99.54 113	99.47 128	99.76 86	99.58 256	99.64 132	99.30 165	99.63 235	99.61 159	99.71 182	99.56 302	98.76 183	99.96 68	99.14 163	99.92 145	99.68 124

IB-MVS	95.41 20	95.30 455	94.46 459	97.84 439	98.76 458	95.33 464	97.33 465	96.07 481	96.02 460	95.37 492	97.41 482	76.17 494	99.96 68	97.54 345	95.44 493	98.22 473
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	98.23 365	97.89 381	99.26 321	99.19 396	99.26 245	99.65 62	99.69 200	91.33 489	98.14 448	99.77 141	98.28 254	99.96 68	95.41 455	99.55 353	98.58 455

IMVS_0404		99.23 210	99.20 200	99.32 301	99.71 191	98.55 345	98.57 366	99.71 183	99.41 211	99.52 270	99.60 278	98.12 273	99.95 80	98.45 254	99.70 299	99.45 284

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 32	99.81 106	99.71 100	98.97 299	99.92 42	99.98 18	99.97 24	99.86 63	99.53 57	99.95 80	99.88 41	99.99 16	99.89 37

MM		99.18 233	99.05 242	99.55 215	99.35 353	98.81 317	99.05 264	97.79 467	99.99 3	99.48 283	99.59 288	96.29 364	99.95 80	99.94 20	99.98 50	99.88 40

GeoE		99.69 59	99.66 71	99.78 75	99.76 154	99.76 70	99.60 79	99.82 103	99.46 194	99.75 157	99.56 302	99.63 37	99.95 80	99.43 105	99.88 183	99.62 186

CS-MVS		99.67 75	99.70 57	99.58 196	99.53 289	99.84 26	99.79 15	99.96 28	99.90 49	99.61 236	99.41 346	99.51 60	99.95 80	99.66 69	99.89 173	98.96 420

CANet_DTU		98.91 293	98.85 288	99.09 345	98.79 453	98.13 376	98.18 402	99.31 370	99.48 186	98.86 392	99.51 320	96.56 349	99.95 80	99.05 178	99.95 111	99.19 369

MGCNet		98.61 325	98.30 346	99.52 227	97.88 488	98.95 301	98.76 341	94.11 494	99.84 75	99.32 327	99.57 298	95.57 376	99.95 80	99.68 66	99.98 50	99.68 124

SPE-MVS-test		99.68 64	99.70 57	99.64 164	99.57 266	99.83 34	99.78 17	99.97 20	99.92 45	99.50 280	99.38 356	99.57 51	99.95 80	99.69 64	99.90 159	99.15 378

Fast-Effi-MVS+		99.02 271	98.87 286	99.46 248	99.38 344	99.50 178	99.04 269	99.79 130	97.17 440	98.62 415	98.74 450	99.34 83	99.95 80	98.32 266	99.41 379	98.92 427

MTAPA		99.35 182	99.20 200	99.80 64	99.81 106	99.81 47	99.33 154	99.53 300	99.27 234	99.42 298	99.63 251	98.21 264	99.95 80	97.83 315	99.79 254	99.65 156

UniMVSNet_NR-MVSNet		99.37 175	99.25 194	99.72 121	99.47 320	99.56 165	98.97 299	99.61 245	99.43 206	99.67 202	99.28 382	97.85 294	99.95 80	99.17 153	99.81 242	99.65 156

DU-MVS		99.33 190	99.21 199	99.71 127	99.43 332	99.56 165	98.83 327	99.53 300	99.38 216	99.67 202	99.36 364	97.67 306	99.95 80	99.17 153	99.81 242	99.63 174

CP-MVSNet		99.54 113	99.43 141	99.87 26	99.76 154	99.82 42	99.57 85	99.61 245	99.54 174	99.80 122	99.64 236	97.79 298	99.95 80	99.21 143	99.94 127	99.84 52

Patchmtry		98.78 310	98.54 322	99.49 237	98.89 440	99.19 266	99.32 157	99.67 208	99.65 145	99.72 177	99.79 118	91.87 426	99.95 80	98.00 295	99.97 73	99.33 334

QAPM		98.40 352	97.99 368	99.65 157	99.39 341	99.47 183	99.67 53	99.52 305	91.70 488	98.78 403	99.80 107	98.55 214	99.95 80	94.71 466	99.75 273	99.53 245

3Dnovator	99.15 2	99.43 153	99.36 159	99.65 157	99.39 341	99.42 204	99.70 38	99.56 278	99.23 242	99.35 318	99.80 107	99.17 107	99.95 80	98.21 275	99.84 214	99.59 211

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 65
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 85	99.59 156	98.97 299	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 94	99.76 70	98.88 316	99.92 42	99.98 18	99.98 14	99.85 68	99.42 68	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	98.92 312	99.98 12	99.99 3	99.99 7	99.88 50	99.43 66	99.94 97	99.94 20	99.99 16	99.99 2

mmtdpeth		99.78 37	99.83 21	99.66 150	99.85 72	99.05 291	99.79 15	99.97 20	100.00 1	99.43 295	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 97	99.95 15	99.37 222	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	99.37 283	99.96 7	98.21 370	99.51 101	100.00 1	99.94 36	100.00 1	99.93 22	99.58 49	99.94 97	99.97 4	99.99 16	99.97 10

test_method		91.72 461	92.32 461	89.91 481	93.49 504	70.18 507	90.28 495	99.56 278	61.71 499	95.39 491	99.52 318	93.90 395	99.94 97	98.76 223	98.27 457	99.62 186

tttt0517		97.62 394	97.20 404	98.90 379	99.76 154	97.40 418	99.48 109	94.36 491	99.06 272	99.70 186	99.49 327	84.55 473	99.94 97	98.73 230	99.65 323	99.36 325

CANet		99.11 253	99.05 242	99.28 313	98.83 447	98.56 343	98.71 348	99.41 337	99.25 238	99.23 347	99.22 396	97.66 310	99.94 97	99.19 148	99.97 73	99.33 334

patchmatchnet-post											99.62 260	90.58 445	99.94 97

SCA		98.11 372	98.36 338	97.36 454	99.20 394	92.99 483	98.17 404	98.49 442	98.24 376	99.10 368	99.57 298	96.01 370	99.94 97	96.86 392	99.62 330	99.14 383

balanced_ft_v1		99.37 175	99.36 159	99.38 278	99.10 415	99.38 217	99.68 48	99.72 179	99.72 112	99.36 315	99.77 141	97.66 310	99.94 97	99.52 90	99.73 286	98.83 437

ADS-MVSNet2		97.78 387	97.66 391	98.12 429	99.14 404	95.36 463	99.22 198	98.75 426	96.97 445	98.25 437	99.64 236	90.90 437	99.94 97	96.51 414	99.56 349	99.08 400

WR-MVS_H		99.61 95	99.53 116	99.87 26	99.80 115	99.83 34	99.67 53	99.75 160	99.58 169	99.85 98	99.69 204	98.18 269	99.94 97	99.28 135	99.95 111	99.83 56

mvsmamba		99.08 258	98.95 273	99.45 251	99.36 349	99.18 271	99.39 129	98.81 423	99.37 217	99.35 318	99.70 195	96.36 361	99.94 97	98.66 239	99.59 344	99.22 359

SixPastTwentyTwo		99.42 156	99.30 179	99.76 86	99.92 29	99.67 118	99.70 38	99.14 404	99.65 145	99.89 72	99.90 36	96.20 366	99.94 97	99.42 110	99.92 145	99.67 133

CP-MVS		99.23 210	99.05 242	99.75 97	99.66 229	99.66 120	99.38 132	99.62 238	98.38 359	99.06 373	99.27 384	98.79 178	99.94 97	97.51 348	99.82 232	99.66 147

SteuartSystems-ACMMP		99.30 194	99.14 210	99.76 86	99.87 54	99.66 120	99.18 211	99.60 256	98.55 340	99.57 247	99.67 220	99.03 141	99.94 97	97.01 383	99.80 249	99.69 117
Skip Steuart: Steuart Systems R&D Blog.
PatchT		98.45 347	98.32 343	98.83 388	98.94 435	98.29 365	99.24 190	98.82 421	99.84 75	99.08 369	99.76 149	91.37 429	99.94 97	98.82 209	99.00 418	98.26 471

new_pmnet		98.88 299	98.89 284	98.84 386	99.70 206	97.62 406	98.15 406	99.50 314	97.98 391	99.62 230	99.54 312	98.15 270	99.94 97	97.55 344	99.84 214	98.95 422

wuyk23d		97.58 396	99.13 212	92.93 479	99.69 212	99.49 179	99.52 94	99.77 147	97.97 392	99.96 34	99.79 118	99.84 16	99.94 97	95.85 445	99.82 232	79.36 497

3Dnovator+	98.92 3	99.35 182	99.24 196	99.67 143	99.35 353	99.47 183	99.62 67	99.50 314	99.44 199	99.12 365	99.78 131	98.77 182	99.94 97	97.87 308	99.72 293	99.62 186

mamba_0408		99.54 113	99.55 109	99.54 221	99.71 191	99.24 253	99.27 178	99.79 130	99.72 112	99.78 132	99.64 236	99.36 79	99.93 119	98.74 225	99.90 159	99.45 284

SSM_0407		99.56 104	99.56 107	99.54 221	99.71 191	99.24 253	99.15 225	99.84 88	99.80 95	99.78 132	99.70 195	99.44 64	99.93 119	98.74 225	99.90 159	99.45 284

SSM_0404		99.57 100	99.58 97	99.54 221	99.76 154	99.28 240	99.19 207	99.84 88	99.80 95	99.78 132	99.70 195	99.44 64	99.93 119	98.74 225	99.95 111	99.41 311

AstraMVS		99.15 243	99.06 237	99.42 261	99.85 72	98.59 342	99.13 236	97.26 475	99.84 75	99.87 92	99.77 141	96.11 367	99.93 119	99.71 60	99.96 87	99.74 89

fmvsm_s_conf0.5_n_6		99.80 30	99.78 39	99.85 32	99.78 137	99.78 57	99.00 287	99.97 20	99.96 28	99.97 24	99.56 302	99.92 8	99.93 119	99.91 33	99.99 16	99.83 56

reproduce_model		99.50 122	99.40 147	99.83 41	99.60 243	99.83 34	99.12 241	99.68 203	99.49 183	99.80 122	99.79 118	99.01 144	99.93 119	98.24 272	99.82 232	99.73 93

reproduce-ours		99.46 141	99.35 164	99.82 46	99.56 277	99.83 34	99.05 264	99.65 223	99.45 197	99.78 132	99.78 131	98.93 157	99.93 119	98.11 286	99.81 242	99.70 105

our_new_method		99.46 141	99.35 164	99.82 46	99.56 277	99.83 34	99.05 264	99.65 223	99.45 197	99.78 132	99.78 131	98.93 157	99.93 119	98.11 286	99.81 242	99.70 105

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 42	99.10 249	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 72	99.82 42	99.03 272	99.96 28	99.99 3	99.97 24	99.84 76	99.58 49	99.93 119	99.92 30	99.98 50	99.93 20

mvsany_test1		99.44 149	99.45 135	99.40 272	99.37 346	98.64 337	97.90 437	99.59 262	99.27 234	99.92 59	99.82 90	99.74 26	99.93 119	99.55 85	99.87 196	99.63 174

ETV-MVS		99.18 233	99.18 203	99.16 334	99.34 362	99.28 240	99.12 241	99.79 130	99.48 186	98.93 381	98.55 459	99.40 69	99.93 119	98.51 250	99.52 363	98.28 470

thisisatest0530		97.45 403	96.95 414	98.94 364	99.68 220	97.73 403	99.09 254	94.19 493	98.61 336	99.56 255	99.30 378	84.30 475	99.93 119	98.27 269	99.54 358	99.16 376

our_test_3		98.85 304	99.09 229	98.13 428	99.66 229	94.90 471	97.72 445	99.58 271	99.07 270	99.64 215	99.62 260	98.19 267	99.93 119	98.41 259	99.95 111	99.55 229

MSP-MVS		99.04 268	98.79 298	99.81 54	99.78 137	99.73 90	99.35 147	99.57 273	98.54 343	99.54 263	98.99 427	96.81 342	99.93 119	96.97 386	99.53 360	99.77 79
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		99.23 210	99.05 242	99.77 79	99.76 154	99.70 108	99.31 162	99.59 262	98.41 355	99.32 327	99.36 364	98.73 189	99.93 119	97.29 361	99.74 280	99.67 133

RRT-MVS		99.08 258	99.00 259	99.33 296	99.27 380	98.65 335	99.62 67	99.93 39	99.66 141	99.67 202	99.82 90	95.27 382	99.93 119	98.64 242	99.09 411	99.41 311

APDe-MVS		99.48 129	99.36 159	99.85 32	99.55 280	99.81 47	99.50 102	99.69 200	98.99 277	99.75 157	99.71 185	98.79 178	99.93 119	98.46 253	99.85 209	99.80 65
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CVMVSNet		98.61 325	98.88 285	97.80 440	99.58 256	93.60 481	99.26 183	99.64 231	99.66 141	99.72 177	99.67 220	93.26 406	99.93 119	99.30 130	99.81 242	99.87 44

ACMMPR		99.23 210	99.06 237	99.76 86	99.74 178	99.69 112	99.31 162	99.59 262	98.36 361	99.35 318	99.38 356	98.61 205	99.93 119	97.43 352	99.75 273	99.67 133

PGM-MVS		99.20 226	99.01 255	99.77 79	99.75 170	99.71 100	99.16 222	99.72 179	97.99 390	99.42 298	99.60 278	98.81 173	99.93 119	96.91 389	99.74 280	99.66 147

LCM-MVSNet-Re		99.28 197	99.15 209	99.67 143	99.33 367	99.76 70	99.34 148	99.97 20	98.93 290	99.91 62	99.79 118	98.68 194	99.93 119	96.80 397	99.56 349	99.30 345

PMMVS2		99.48 129	99.45 135	99.57 204	99.76 154	98.99 294	98.09 414	99.90 57	98.95 284	99.78 132	99.58 291	99.57 51	99.93 119	99.48 96	99.95 111	99.79 73

mPP-MVS		99.19 229	99.00 259	99.76 86	99.76 154	99.68 115	99.38 132	99.54 290	98.34 370	99.01 375	99.50 323	98.53 223	99.93 119	97.18 377	99.78 263	99.66 147

OurMVSNet-221017-0		99.75 49	99.71 56	99.84 38	99.96 7	99.83 34	99.83 7	99.85 81	99.80 95	99.93 53	99.93 22	98.54 218	99.93 119	99.59 78	99.98 50	99.76 84

CHOSEN 1792x2688		99.39 168	99.30 179	99.65 157	99.88 45	99.25 248	98.78 339	99.88 65	98.66 328	99.96 34	99.79 118	97.45 317	99.93 119	99.34 122	99.99 16	99.78 75

N_pmnet		98.73 316	98.53 323	99.35 290	99.72 187	98.67 329	98.34 391	94.65 490	98.35 366	99.79 128	99.68 216	98.03 279	99.93 119	98.28 268	99.92 145	99.44 299

UGNet		99.38 171	99.34 166	99.49 237	98.90 437	98.90 309	99.70 38	99.35 356	99.86 65	98.57 421	99.81 97	98.50 229	99.93 119	99.38 114	99.98 50	99.66 147
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	99.71 191	99.91 4	99.76 23	99.96 28	99.86 65	99.51 277	99.39 354	99.57 51	99.93 119	99.64 73	99.86 204	99.20 366

EPP-MVSNet		99.17 238	99.00 259	99.66 150	99.80 115	99.43 201	99.70 38	99.24 387	99.48 186	99.56 255	99.77 141	94.89 385	99.93 119	98.72 232	99.89 173	99.63 174

DeepC-MVS	98.90 4	99.62 91	99.61 87	99.67 143	99.72 187	99.44 197	99.24 190	99.71 183	99.27 234	99.93 53	99.90 36	99.70 31	99.93 119	98.99 186	99.99 16	99.64 168
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		99.30 194	99.29 184	99.31 305	99.71 191	98.55 345	98.17 404	99.71 183	99.41 211	99.73 172	99.60 278	99.17 107	99.92 150	98.45 254	99.70 299	99.45 284

lecture		99.56 104	99.48 126	99.81 54	99.78 137	99.86 18	99.50 102	99.70 192	99.59 167	99.75 157	99.71 185	98.94 156	99.92 150	98.59 245	99.76 269	99.66 147

guyue		99.12 249	99.02 251	99.41 269	99.84 77	98.56 343	99.19 207	98.30 453	99.82 85	99.84 101	99.75 157	94.84 386	99.92 150	99.68 66	99.94 127	99.74 89

sc_t1		99.81 28	99.80 32	99.82 46	99.88 45	99.88 12	99.83 7	99.79 130	99.94 36	99.93 53	99.92 27	99.35 82	99.92 150	99.64 73	99.94 127	99.68 124

tt0320-xc		99.82 24	99.82 25	99.82 46	99.82 94	99.84 26	99.82 10	99.92 42	99.94 36	99.94 48	99.93 22	99.34 83	99.92 150	99.70 61	99.96 87	99.70 105

tt0320		99.79 34	99.79 34	99.81 54	99.82 94	99.84 26	99.82 10	99.90 57	99.94 36	99.94 48	99.94 19	99.07 130	99.92 150	99.68 66	99.97 73	99.67 133

fmvsm_s_conf0.5_n_4		99.78 37	99.78 39	99.79 71	99.75 170	99.56 165	98.98 297	99.94 38	99.92 45	99.97 24	99.72 175	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	99.07 262	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 72	99.78 57	99.03 272	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		89.05 463	85.52 466	99.64 164	99.89 39	99.78 57	99.56 87	99.52 305	24.19 500	49.96 501	99.83 83	99.15 111	99.92 150	97.71 324	99.85 209	99.21 362

DVP-MVS++		99.38 171	99.25 194	99.77 79	99.03 426	99.77 63	99.74 27	99.61 245	99.18 250	99.76 152	99.61 270	99.00 145	99.92 150	97.72 322	99.60 340	99.62 186

MSC_two_6792asdad				99.74 102	99.03 426	99.53 172		99.23 388					99.92 150	97.77 316	99.69 307	99.78 75

No_MVS				99.74 102	99.03 426	99.53 172		99.23 388					99.92 150	97.77 316	99.69 307	99.78 75

ZD-MVS					99.43 332	99.61 150		99.43 334	96.38 455	99.11 366	99.07 416	97.86 292	99.92 150	94.04 474	99.49 369

SED-MVS		99.40 164	99.28 187	99.77 79	99.69 212	99.82 42	99.20 201	99.54 290	99.13 263	99.82 108	99.63 251	98.91 163	99.92 150	97.85 311	99.70 299	99.58 216

test_241102_TWO								99.54 290	99.13 263	99.76 152	99.63 251	98.32 252	99.92 150	97.85 311	99.69 307	99.75 87

ZNCC-MVS		99.22 219	99.04 248	99.77 79	99.76 154	99.73 90	99.28 174	99.56 278	98.19 380	99.14 362	99.29 381	98.84 172	99.92 150	97.53 347	99.80 249	99.64 168

test_0728_SECOND				99.83 41	99.70 206	99.79 54	99.14 229	99.61 245					99.92 150	97.88 305	99.72 293	99.77 79

SR-MVS		99.19 229	99.00 259	99.74 102	99.51 298	99.72 95	99.18 211	99.60 256	98.85 302	99.47 285	99.58 291	98.38 244	99.92 150	96.92 388	99.54 358	99.57 222

DPE-MVS		99.14 244	98.92 279	99.82 46	99.57 266	99.77 63	98.74 344	99.60 256	98.55 340	99.76 152	99.69 204	98.23 262	99.92 150	96.39 422	99.75 273	99.76 84
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS		99.06 262	98.83 292	99.76 86	99.76 154	99.71 100	99.32 157	99.50 314	98.35 366	98.97 377	99.48 331	98.37 245	99.92 150	95.95 442	99.75 273	99.63 174
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PM-MVS		99.36 180	99.29 184	99.58 196	99.83 85	99.66 120	98.95 306	99.86 75	98.85 302	99.81 115	99.73 167	98.40 243	99.92 150	98.36 262	99.83 222	99.17 374

HPM-MVS		99.25 205	99.07 235	99.78 75	99.81 106	99.75 79	99.61 73	99.67 208	97.72 413	99.35 318	99.25 389	99.23 100	99.92 150	97.21 373	99.82 232	99.67 133
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
tpm		97.15 412	96.95 414	97.75 442	98.91 436	94.24 475	99.32 157	97.96 461	97.71 414	98.29 435	99.32 373	86.72 467	99.92 150	98.10 289	96.24 489	99.09 394

RPMNet		98.60 328	98.53 323	98.83 388	99.05 422	98.12 377	99.30 165	99.62 238	99.86 65	99.16 358	99.74 162	92.53 417	99.92 150	98.75 224	98.77 432	98.44 465

CPTT-MVS		98.74 314	98.44 330	99.64 164	99.61 241	99.38 217	99.18 211	99.55 284	96.49 453	99.27 339	99.37 359	97.11 334	99.92 150	95.74 449	99.67 318	99.62 186

MIMVSNet1		99.66 76	99.62 83	99.80 64	99.94 18	99.87 15	99.69 45	99.77 147	99.78 102	99.93 53	99.89 41	97.94 287	99.92 150	99.65 70	99.98 50	99.62 186

CSCG		99.37 175	99.29 184	99.60 190	99.71 191	99.46 189	99.43 121	99.85 81	98.79 312	99.41 304	99.60 278	98.92 160	99.92 150	98.02 291	99.92 145	99.43 305

ACMMP		99.25 205	99.08 231	99.74 102	99.79 129	99.68 115	99.50 102	99.65 223	98.07 386	99.52 270	99.69 204	98.57 210	99.92 150	97.18 377	99.79 254	99.63 174
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 83	99.67 64	99.56 208	99.75 170	98.98 295	98.96 303	99.87 69	99.88 60	99.84 101	99.64 236	99.32 86	99.91 179	99.78 54	99.96 87	99.80 65

SR-MVS-dyc-post		99.27 201	99.11 219	99.73 113	99.54 282	99.74 87	99.26 183	99.62 238	99.16 257	99.52 270	99.64 236	98.41 239	99.91 179	97.27 364	99.61 337	99.54 239

DVP-MVS		99.32 192	99.17 204	99.77 79	99.69 212	99.80 51	99.14 229	99.31 370	99.16 257	99.62 230	99.61 270	98.35 247	99.91 179	97.88 305	99.72 293	99.61 200
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									99.18 250	99.62 230	99.61 270	98.58 209	99.91 179	97.72 322	99.80 249	99.77 79

GST-MVS		99.16 239	98.96 272	99.75 97	99.73 182	99.73 90	99.20 201	99.55 284	98.22 377	99.32 327	99.35 369	98.65 201	99.91 179	96.86 392	99.74 280	99.62 186

MP-MVS-pluss		99.14 244	98.92 279	99.80 64	99.83 85	99.83 34	98.61 355	99.63 235	96.84 449	99.44 291	99.58 291	98.81 173	99.91 179	97.70 327	99.82 232	99.67 133
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		99.25 205	99.08 231	99.76 86	99.73 182	99.70 108	99.31 162	99.59 262	98.36 361	99.36 315	99.37 359	98.80 177	99.91 179	97.43 352	99.75 273	99.68 124

HPM-MVS++		98.96 287	98.70 306	99.74 102	99.52 296	99.71 100	98.86 320	99.19 398	98.47 351	98.59 418	99.06 417	98.08 277	99.91 179	96.94 387	99.60 340	99.60 204

test-LLR		97.15 412	96.95 414	97.74 443	98.18 479	95.02 469	97.38 462	96.10 479	98.00 388	97.81 463	98.58 455	90.04 451	99.91 179	97.69 333	98.78 430	98.31 468

test-mter		96.23 436	95.73 439	97.74 443	98.18 479	95.02 469	97.38 462	96.10 479	97.90 400	97.81 463	98.58 455	79.12 487	99.91 179	97.69 333	98.78 430	98.31 468

VPA-MVSNet		99.66 76	99.62 83	99.79 71	99.68 220	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	99.88 183	99.70 105

XVG-ACMP-BASELINE		99.23 210	99.10 227	99.63 171	99.82 94	99.58 161	98.83 327	99.72 179	98.36 361	99.60 239	99.71 185	98.92 160	99.91 179	97.08 381	99.84 214	99.40 314

APD-MVS		98.87 300	98.59 313	99.71 127	99.50 304	99.62 140	99.01 281	99.57 273	96.80 451	99.54 263	99.63 251	98.29 253	99.91 179	95.24 458	99.71 297	99.61 200
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CR-MVSNet		98.35 357	98.20 353	98.83 388	99.05 422	98.12 377	99.30 165	99.67 208	97.39 430	99.16 358	99.79 118	91.87 426	99.91 179	98.78 222	98.77 432	98.44 465

FMVSNet5		97.80 386	97.25 403	99.42 261	98.83 447	98.97 298	99.38 132	99.80 121	98.87 299	99.25 343	99.69 204	80.60 480	99.91 179	98.96 192	99.90 159	99.38 319

XXY-MVS		99.71 56	99.67 64	99.81 54	99.89 39	99.72 95	99.59 80	99.82 103	99.39 215	99.82 108	99.84 76	99.38 74	99.91 179	99.38 114	99.93 139	99.80 65

sss		98.90 295	98.77 299	99.27 318	99.48 314	98.44 355	98.72 346	99.32 366	97.94 398	99.37 314	99.35 369	96.31 362	99.91 179	98.85 205	99.63 328	99.47 277

1112_ss		99.05 265	98.84 290	99.67 143	99.66 229	99.29 238	98.52 375	99.82 103	97.65 416	99.43 295	99.16 404	96.42 356	99.91 179	99.07 177	99.84 214	99.80 65

LS3D		99.24 208	99.11 219	99.61 186	98.38 473	99.79 54	99.57 85	99.68 203	99.61 159	99.15 360	99.71 185	98.70 192	99.91 179	97.54 345	99.68 312	99.13 386

MED-MVS test				99.74 102	99.76 154	99.65 126	99.38 132	99.78 141	99.58 169	99.81 115	99.66 225		99.90 198	97.69 333	99.79 254	99.67 133

MED-MVS		99.45 145	99.36 159	99.74 102	99.76 154	99.65 126	99.38 132	99.78 141	99.31 227	99.81 115	99.66 225	99.02 142	99.90 198	97.69 333	99.79 254	99.67 133

TestfortrainingZip a		99.61 95	99.53 116	99.85 32	99.76 154	99.84 26	99.38 132	99.78 141	99.58 169	99.81 115	99.66 225	99.02 142	99.90 198	98.96 192	99.79 254	99.81 64

WB-MVSnew		98.34 359	98.14 359	98.96 361	98.14 482	97.90 395	98.27 396	97.26 475	98.63 332	98.80 399	98.00 473	97.77 299	99.90 198	97.37 356	98.98 419	99.09 394

testf1		99.63 84	99.60 91	99.72 121	99.94 18	99.95 2	99.47 112	99.89 60	99.43 206	99.88 82	99.80 107	99.26 95	99.90 198	98.81 213	99.88 183	99.32 338

APD_test2		99.63 84	99.60 91	99.72 121	99.94 18	99.95 2	99.47 112	99.89 60	99.43 206	99.88 82	99.80 107	99.26 95	99.90 198	98.81 213	99.88 183	99.32 338

balanced_conf03		99.50 122	99.50 121	99.50 233	99.42 337	99.49 179	99.52 94	99.75 160	99.86 65	99.78 132	99.71 185	98.20 266	99.90 198	99.39 113	99.88 183	99.10 389

test2506		94.73 457	94.59 457	95.15 478	99.59 249	85.90 504	99.75 25	74.01 506	99.89 55	99.71 182	99.86 63	79.00 488	99.90 198	99.52 90	99.99 16	99.65 156

test1111		97.74 388	98.16 358	96.49 471	99.60 243	89.86 502	99.71 37	91.21 498	99.89 55	99.88 82	99.87 56	93.73 400	99.90 198	99.56 83	99.99 16	99.70 105

KD-MVS_self_test		99.63 84	99.59 93	99.76 86	99.84 77	99.90 7	99.37 140	99.79 130	99.83 81	99.88 82	99.85 68	98.42 238	99.90 198	99.60 77	99.73 286	99.49 269

ET-MVSNet_ETH3D		96.78 420	96.07 430	98.91 373	99.26 383	97.92 394	97.70 448	96.05 482	97.96 395	92.37 495	98.43 463	87.06 461	99.90 198	98.27 269	97.56 474	98.91 428

tfpnnormal		99.43 153	99.38 151	99.60 190	99.87 54	99.75 79	99.59 80	99.78 141	99.71 118	99.90 67	99.69 204	98.85 171	99.90 198	97.25 370	99.78 263	99.15 378

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	99.69 117

APD-MVS_3200maxsize		99.31 193	99.16 205	99.74 102	99.53 289	99.75 79	99.27 178	99.61 245	99.19 249	99.57 247	99.64 236	98.76 183	99.90 198	97.29 361	99.62 330	99.56 225

baseline2		96.83 419	96.28 426	98.46 413	99.09 419	96.91 432	98.83 327	93.87 496	97.23 437	96.23 488	98.36 464	88.12 458	99.90 198	96.68 403	98.14 464	98.57 457

XVG-OURS-SEG-HR		99.16 239	98.99 266	99.66 150	99.84 77	99.64 132	98.25 399	99.73 170	98.39 358	99.63 220	99.43 343	99.70 31	99.90 198	97.34 357	98.64 443	99.44 299

XVG-OURS		99.21 224	99.06 237	99.65 157	99.82 94	99.62 140	97.87 438	99.74 166	98.36 361	99.66 208	99.68 216	99.71 28	99.90 198	96.84 395	99.88 183	99.43 305

JIA-IIPM		98.06 375	97.92 378	98.50 410	98.59 466	97.02 429	98.80 335	98.51 440	99.88 60	97.89 457	99.87 56	91.89 425	99.90 198	98.16 283	97.68 473	98.59 453

GBi-Net		99.42 156	99.31 174	99.73 113	99.49 309	99.77 63	99.68 48	99.70 192	99.44 199	99.62 230	99.83 83	97.21 328	99.90 198	98.96 192	99.90 159	99.53 245

test1		99.42 156	99.31 174	99.73 113	99.49 309	99.77 63	99.68 48	99.70 192	99.44 199	99.62 230	99.83 83	97.21 328	99.90 198	98.96 192	99.90 159	99.53 245

FMVSNet1		99.66 76	99.63 81	99.73 113	99.78 137	99.77 63	99.68 48	99.70 192	99.67 137	99.82 108	99.83 83	98.98 151	99.90 198	99.24 137	99.97 73	99.53 245

WTY-MVS		98.59 331	98.37 337	99.26 321	99.43 332	98.40 358	98.74 344	99.13 406	98.10 383	99.21 352	99.24 394	94.82 387	99.90 198	97.86 309	98.77 432	99.49 269

VortexMVS		99.13 246	99.24 196	98.79 392	99.67 227	96.60 441	99.24 190	99.80 121	99.85 71	99.93 53	99.84 76	95.06 383	99.89 220	99.80 52	99.98 50	99.89 37

ECVR-MVS		97.73 389	98.04 365	96.78 464	99.59 249	90.81 497	99.72 33	90.43 500	99.89 55	99.86 95	99.86 63	93.60 402	99.89 220	99.46 100	99.99 16	99.65 156

EI-MVSNet-UG-set		99.48 129	99.50 121	99.42 261	99.57 266	98.65 335	99.24 190	99.46 325	99.68 129	99.80 122	99.66 225	98.99 147	99.89 220	99.19 148	99.90 159	99.72 97

EI-MVSNet-Vis-set		99.47 139	99.49 125	99.42 261	99.57 266	98.66 332	99.24 190	99.46 325	99.67 137	99.79 128	99.65 234	98.97 153	99.89 220	99.15 156	99.89 173	99.71 102

新几何1				99.52 227	99.50 304	99.22 259		99.26 380	95.66 466	98.60 417	99.28 382	97.67 306	99.89 220	95.95 442	99.32 391	99.45 284

testdata2													99.89 220	95.99 439

testdata				99.42 261	99.51 298	98.93 305		99.30 373	96.20 458	98.87 391	99.40 350	98.33 251	99.89 220	96.29 426	99.28 396	99.44 299

TESTMET0.1,1		96.24 435	95.84 436	97.41 452	98.24 477	93.84 478	97.38 462	95.84 486	98.43 352	97.81 463	98.56 458	79.77 484	99.89 220	97.77 316	98.77 432	98.52 459

test20.03		99.55 109	99.54 112	99.58 196	99.79 129	99.37 222	99.02 276	99.89 60	99.60 165	99.82 108	99.62 260	98.81 173	99.89 220	99.43 105	99.86 204	99.47 277

MDA-MVSNet-bldmvs		99.06 262	99.05 242	99.07 350	99.80 115	97.83 398	98.89 315	99.72 179	99.29 230	99.63 220	99.70 195	96.47 354	99.89 220	98.17 282	99.82 232	99.50 264

LPG-MVS_test		99.22 219	99.05 242	99.74 102	99.82 94	99.63 138	99.16 222	99.73 170	97.56 418	99.64 215	99.69 204	99.37 76	99.89 220	96.66 405	99.87 196	99.69 117

LGP-MVS_train				99.74 102	99.82 94	99.63 138		99.73 170	97.56 418	99.64 215	99.69 204	99.37 76	99.89 220	96.66 405	99.87 196	99.69 117

Test_1112_low_res		98.95 290	98.73 300	99.63 171	99.68 220	99.15 274	98.09 414	99.80 121	97.14 442	99.46 289	99.40 350	96.11 367	99.89 220	99.01 185	99.84 214	99.84 52

PatchmatchNet		97.65 393	97.80 383	97.18 460	98.82 450	92.49 485	99.17 216	98.39 448	98.12 382	98.79 401	99.58 291	90.71 443	99.89 220	97.23 371	99.41 379	99.16 376
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMP	97.51 14	99.05 265	98.84 290	99.67 143	99.78 137	99.55 169	98.88 316	99.66 213	97.11 444	99.47 285	99.60 278	99.07 130	99.89 220	96.18 431	99.85 209	99.58 216
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
diffmvs_AUTHOR		99.48 129	99.48 126	99.47 244	99.80 115	98.89 310	98.71 348	99.82 103	99.79 99	99.66 208	99.63 251	98.87 169	99.88 235	99.13 165	99.95 111	99.62 186

test_vis3_rt		99.89 3	99.90 4	99.87 26	99.98 3	99.75 79	99.70 38	100.00 1	99.73 108	100.00 1	99.89 41	99.79 22	99.88 235	99.98 1	100.00 1	99.98 5

FE-MVS		97.85 382	97.42 398	99.15 336	99.44 329	98.75 324	99.77 19	98.20 456	95.85 462	99.33 324	99.80 107	88.86 456	99.88 235	96.40 421	99.12 408	98.81 439

ppachtmachnet_test		98.89 298	99.12 216	98.20 426	99.66 229	95.24 467	97.63 450	99.68 203	99.08 268	99.78 132	99.62 260	98.65 201	99.88 235	98.02 291	99.96 87	99.48 273

TSAR-MVS + MP.		99.34 187	99.24 196	99.63 171	99.82 94	99.37 222	99.26 183	99.35 356	98.77 316	99.57 247	99.70 195	99.27 94	99.88 235	97.71 324	99.75 273	99.65 156
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
new-patchmatchnet		99.35 182	99.57 102	98.71 401	99.82 94	96.62 439	98.55 369	99.75 160	99.50 181	99.88 82	99.87 56	99.31 87	99.88 235	99.43 105	100.00 1	99.62 186

Anonymous20231206		99.35 182	99.31 174	99.47 244	99.74 178	99.06 290	99.28 174	99.74 166	99.23 242	99.72 177	99.53 314	97.63 313	99.88 235	99.11 170	99.84 214	99.48 273

XVS		99.27 201	99.11 219	99.75 97	99.71 191	99.71 100	99.37 140	99.61 245	99.29 230	98.76 404	99.47 335	98.47 230	99.88 235	97.62 339	99.73 286	99.67 133

v1240		99.56 104	99.58 97	99.51 231	99.80 115	99.00 292	99.00 287	99.65 223	99.15 261	99.90 67	99.75 157	99.09 123	99.88 235	99.90 37	99.96 87	99.67 133

X-MVStestdata		96.09 440	94.87 453	99.75 97	99.71 191	99.71 100	99.37 140	99.61 245	99.29 230	98.76 404	61.30 509	98.47 230	99.88 235	97.62 339	99.73 286	99.67 133

旧先验2							97.94 432		95.33 469	98.94 380			99.88 235	96.75 399

UniMVSNet (Re)		99.37 175	99.26 192	99.68 139	99.51 298	99.58 161	98.98 297	99.60 256	99.43 206	99.70 186	99.36 364	97.70 302	99.88 235	99.20 146	99.87 196	99.59 211

HPM-MVS_fast		99.43 153	99.30 179	99.80 64	99.83 85	99.81 47	99.52 94	99.70 192	98.35 366	99.51 277	99.50 323	99.31 87	99.88 235	98.18 280	99.84 214	99.69 117

TDRefinement		99.72 53	99.70 57	99.77 79	99.90 37	99.85 21	99.86 6	99.92 42	99.69 127	99.78 132	99.92 27	99.37 76	99.88 235	98.93 200	99.95 111	99.60 204

PCF-MVS	96.03 18	96.73 422	95.86 435	99.33 296	99.44 329	99.16 272	96.87 482	99.44 331	86.58 493	98.95 379	99.40 350	94.38 392	99.88 235	87.93 489	99.80 249	98.95 422
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		96.21 438	95.78 437	97.49 448	98.53 468	93.83 479	98.04 420	93.94 495	98.96 281	98.46 428	98.17 469	79.86 482	99.87 250	96.99 384	99.06 412	98.78 442

SF-MVS		99.10 256	98.93 275	99.62 180	99.58 256	99.51 177	99.13 236	99.65 223	97.97 392	99.42 298	99.61 270	98.86 170	99.87 250	96.45 420	99.68 312	99.49 269

D2MVS		99.22 219	99.19 202	99.29 310	99.69 212	98.74 325	98.81 332	99.41 337	98.55 340	99.68 194	99.69 204	98.13 271	99.87 250	98.82 209	99.98 50	99.24 354

thisisatest0515		96.98 416	96.42 424	98.66 402	99.42 337	97.47 412	97.27 467	94.30 492	97.24 436	99.15 360	98.86 442	85.01 471	99.87 250	97.10 379	99.39 381	98.63 449

ACMMP_NAP		99.28 197	99.11 219	99.79 71	99.75 170	99.81 47	98.95 306	99.53 300	98.27 375	99.53 268	99.73 167	98.75 185	99.87 250	97.70 327	99.83 222	99.68 124

Patchmatch-test		98.10 373	97.98 370	98.48 411	99.27 380	96.48 442	99.40 127	99.07 408	98.81 309	99.23 347	99.57 298	90.11 450	99.87 250	96.69 402	99.64 325	99.09 394

v144192		99.55 109	99.54 112	99.58 196	99.78 137	99.20 265	99.11 246	99.62 238	99.18 250	99.89 72	99.72 175	98.66 199	99.87 250	99.88 41	99.97 73	99.66 147

v1921920		99.56 104	99.57 102	99.55 215	99.75 170	99.11 278	99.05 264	99.61 245	99.15 261	99.88 82	99.71 185	99.08 127	99.87 250	99.90 37	99.97 73	99.66 147

FC-MVSNet-test		99.70 57	99.65 73	99.86 30	99.88 45	99.86 18	99.72 33	99.78 141	99.90 49	99.82 108	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 75	99.91 31	99.83 34	99.76 23	99.87 69	99.73 108	99.89 72	99.87 56	99.63 37	99.87 250	99.54 86	99.92 145	99.63 174

TransMVSNet (Re)		99.78 37	99.77 45	99.81 54	99.91 31	99.85 21	99.75 25	99.86 75	99.70 124	99.91 62	99.89 41	99.60 43	99.87 250	99.59 78	99.74 280	99.71 102

NR-MVSNet		99.40 164	99.31 174	99.68 139	99.43 332	99.55 169	99.73 30	99.50 314	99.46 194	99.88 82	99.36 364	97.54 314	99.87 250	98.97 190	99.87 196	99.63 174

Baseline_NR-MVSNet		99.49 127	99.37 154	99.82 46	99.91 31	99.84 26	98.83 327	99.86 75	99.68 129	99.65 212	99.88 50	97.67 306	99.87 250	99.03 181	99.86 204	99.76 84

EG-PatchMatch MVS		99.57 100	99.56 107	99.62 180	99.77 150	99.33 232	99.26 183	99.76 155	99.32 225	99.80 122	99.78 131	99.29 89	99.87 250	99.15 156	99.91 157	99.66 147

DELS-MVS		99.34 187	99.30 179	99.48 242	99.51 298	99.36 226	98.12 410	99.53 300	99.36 220	99.41 304	99.61 270	99.22 101	99.87 250	99.21 143	99.68 312	99.20 366
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		99.35 182	99.28 187	99.55 215	99.49 309	99.35 229	99.45 117	99.57 273	99.44 199	99.70 186	99.74 162	97.21 328	99.87 250	99.03 181	99.94 127	99.44 299

ab-mvs		99.33 190	99.28 187	99.47 244	99.57 266	99.39 215	99.78 17	99.43 334	98.87 299	99.57 247	99.82 90	98.06 278	99.87 250	98.69 237	99.73 286	99.15 378

DP-MVS		99.48 129	99.39 148	99.74 102	99.57 266	99.62 140	99.29 172	99.61 245	99.87 62	99.74 167	99.76 149	98.69 193	99.87 250	98.20 276	99.80 249	99.75 87

F-COLMAP		98.74 314	98.45 329	99.62 180	99.57 266	99.47 183	98.84 324	99.65 223	96.31 457	98.93 381	99.19 403	97.68 305	99.87 250	96.52 413	99.37 384	99.53 245

ME-MVS		99.26 203	99.10 227	99.73 113	99.60 243	99.65 126	98.75 343	99.45 330	99.31 227	99.65 212	99.66 225	98.00 285	99.86 269	97.69 333	99.79 254	99.67 133

WBMVS		97.50 402	97.18 405	98.48 411	98.85 445	95.89 456	98.44 386	99.52 305	99.53 176	99.52 270	99.42 345	80.10 481	99.86 269	99.24 137	99.95 111	99.68 124

Anonymous20240529		99.42 156	99.34 166	99.65 157	99.53 289	99.60 154	99.63 64	99.39 347	99.47 191	99.76 152	99.78 131	98.13 271	99.86 269	98.70 235	99.68 312	99.49 269

test_post											52.41 510	90.25 449	99.86 269

Anonymous20231211		99.62 91	99.57 102	99.76 86	99.61 241	99.60 154	99.81 13	99.73 170	99.82 85	99.90 67	99.90 36	97.97 286	99.86 269	99.42 110	99.96 87	99.80 65

v10		99.69 59	99.69 60	99.66 150	99.81 106	99.39 215	99.66 57	99.75 160	99.60 165	99.92 59	99.87 56	98.75 185	99.86 269	99.90 37	99.99 16	99.73 93

VPNet		99.46 141	99.37 154	99.71 127	99.82 94	99.59 156	99.48 109	99.70 192	99.81 91	99.69 189	99.58 291	97.66 310	99.86 269	99.17 153	99.44 374	99.67 133

testgi		99.29 196	99.26 192	99.37 283	99.75 170	98.81 317	98.84 324	99.89 60	98.38 359	99.75 157	99.04 420	99.36 79	99.86 269	99.08 174	99.25 401	99.45 284

mvs_anonymous		99.28 197	99.39 148	98.94 364	99.19 396	97.81 399	99.02 276	99.55 284	99.78 102	99.85 98	99.80 107	98.24 258	99.86 269	99.57 82	99.50 367	99.15 378

diffmvs		99.34 187	99.32 172	99.39 275	99.67 227	98.77 323	98.57 366	99.81 116	99.61 159	99.48 283	99.41 346	98.47 230	99.86 269	98.97 190	99.90 159	99.53 245
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		99.11 253	98.93 275	99.66 150	99.30 373	99.42 204	98.42 387	99.37 352	99.04 273	99.57 247	99.20 402	96.89 340	99.86 269	98.66 239	99.87 196	99.70 105

114514_t		98.49 343	98.11 361	99.64 164	99.73 182	99.58 161	99.24 190	99.76 155	89.94 491	99.42 298	99.56 302	97.76 301	99.86 269	97.74 321	99.82 232	99.47 277

UnsupCasMVSNet_eth		98.83 305	98.57 317	99.59 193	99.68 220	99.45 195	98.99 294	99.67 208	99.48 186	99.55 260	99.36 364	94.92 384	99.86 269	98.95 198	96.57 481	99.45 284

FMVSNet3		98.80 309	98.63 310	99.32 301	99.13 406	98.72 326	99.10 249	99.48 319	99.23 242	99.62 230	99.64 236	92.57 415	99.86 269	98.96 192	99.90 159	99.39 317

HY-MVS	98.23 9	98.21 369	97.95 372	98.99 357	99.03 426	98.24 366	99.61 73	98.72 427	96.81 450	98.73 406	99.51 320	94.06 394	99.86 269	96.91 389	98.20 459	98.86 434

TAMVS		99.49 127	99.45 135	99.63 171	99.48 314	99.42 204	99.45 117	99.57 273	99.66 141	99.78 132	99.83 83	97.85 294	99.86 269	99.44 103	99.96 87	99.61 200

ACMM	98.09 11	99.46 141	99.38 151	99.72 121	99.80 115	99.69 112	99.13 236	99.65 223	98.99 277	99.64 215	99.72 175	99.39 70	99.86 269	98.23 273	99.81 242	99.60 204
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS_ROB	97.31 17	97.36 409	96.84 419	98.89 380	99.29 375	99.45 195	98.87 319	99.48 319	86.54 494	99.44 291	99.74 162	97.34 323	99.86 269	91.61 481	99.28 396	97.37 490

COLMAP_ROB	98.06 12	99.45 145	99.37 154	99.70 132	99.83 85	99.70 108	99.38 132	99.78 141	99.53 176	99.67 202	99.78 131	99.19 104	99.86 269	97.32 358	99.87 196	99.55 229
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		97.52 401	97.07 409	98.88 382	97.35 496	97.35 420	97.17 471	99.25 383	97.86 406	98.41 431	96.54 500	90.74 442	99.85 288	98.80 215	97.51 475	99.43 305

FE-MVSNET2		99.68 64	99.67 64	99.72 121	99.86 59	99.68 115	99.46 116	99.88 65	99.62 154	99.87 92	99.85 68	99.06 136	99.85 288	99.44 103	99.98 50	99.63 174

testing3		96.48 429	95.63 441	99.01 356	99.23 388	97.81 399	98.90 314	99.10 407	98.72 321	97.84 462	97.92 474	72.44 500	99.85 288	97.21 373	99.33 389	99.35 328

hse-mvs2		98.52 338	98.30 346	99.16 334	99.29 375	98.60 340	98.77 340	99.02 413	99.68 129	99.32 327	99.04 420	92.50 418	99.85 288	99.24 137	97.87 471	99.03 411

AUN-MVS		97.82 383	97.38 399	99.14 339	99.27 380	98.53 349	98.72 346	99.02 413	98.10 383	97.18 476	99.03 424	89.26 455	99.85 288	97.94 300	97.91 469	99.03 411

miper_lstm_enhance		98.65 324	98.60 311	98.82 391	99.20 394	97.33 421	97.78 441	99.66 213	99.01 276	99.59 242	99.50 323	94.62 390	99.85 288	98.12 285	99.90 159	99.26 351

TEST9					99.35 353	99.35 229	98.11 412	99.41 337	94.83 477	97.92 455	98.99 427	98.02 280	99.85 288

train_agg		98.35 357	97.95 372	99.57 204	99.35 353	99.35 229	98.11 412	99.41 337	94.90 474	97.92 455	98.99 427	98.02 280	99.85 288	95.38 456	99.44 374	99.50 264

agg_prior					99.35 353	99.36 226		99.39 347		97.76 466			99.85 288

FIs		99.65 82	99.58 97	99.84 38	99.84 77	99.85 21	99.66 57	99.75 160	99.86 65	99.74 167	99.79 118	98.27 256	99.85 288	99.37 117	99.93 139	99.83 56

v1192		99.57 100	99.57 102	99.57 204	99.77 150	99.22 259	99.04 269	99.60 256	99.18 250	99.87 92	99.72 175	99.08 127	99.85 288	99.89 40	99.98 50	99.66 147

无先验							98.01 423	99.23 388	95.83 463				99.85 288	95.79 448		99.44 299

VDD-MVS		99.20 226	99.11 219	99.44 255	99.43 332	98.98 295	99.50 102	98.32 452	99.80 95	99.56 255	99.69 204	96.99 338	99.85 288	98.99 186	99.73 286	99.50 264

VDDNet		98.97 284	98.82 293	99.42 261	99.71 191	98.81 317	99.62 67	98.68 429	99.81 91	99.38 312	99.80 107	94.25 393	99.85 288	98.79 216	99.32 391	99.59 211

EI-MVSNet		99.38 171	99.44 139	99.21 328	99.58 256	98.09 381	99.26 183	99.46 325	99.62 154	99.75 157	99.67 220	98.54 218	99.85 288	99.15 156	99.92 145	99.68 124

MVSTER		98.47 345	98.22 351	99.24 326	99.06 421	98.35 364	99.08 257	99.46 325	99.27 234	99.75 157	99.66 225	88.61 457	99.85 288	99.14 163	99.92 145	99.52 256

ACMH	98.42 6	99.59 99	99.54 112	99.72 121	99.86 59	99.62 140	99.56 87	99.79 130	98.77 316	99.80 122	99.85 68	99.64 35	99.85 288	98.70 235	99.89 173	99.70 105
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
wanda-best-256-512		97.53 399	97.14 407	98.72 397	97.71 490	96.86 434	97.00 478	99.34 359	97.73 411	98.18 441	96.82 494	91.92 421	99.84 305	99.02 183	96.53 482	99.45 284

blended_shiyan8		97.82 383	97.45 396	98.92 368	98.06 484	97.45 415	97.73 443	99.35 356	97.96 395	98.35 433	97.34 484	92.76 414	99.84 305	99.04 179	96.49 488	99.47 277

FE-blended-shiyan7		97.53 399	97.14 407	98.72 397	97.71 490	96.86 434	97.00 478	99.34 359	97.73 411	98.18 441	96.82 494	91.92 421	99.84 305	99.02 183	96.53 482	99.45 284

blended_shiyan6		97.82 383	97.46 394	98.92 368	98.08 483	97.46 413	97.73 443	99.34 359	97.96 395	98.33 434	97.35 483	92.78 412	99.84 305	99.04 179	96.53 482	99.46 282

IMVS_0403		99.37 175	99.39 148	99.28 313	99.71 191	98.55 345	99.19 207	99.71 183	99.41 211	99.67 202	99.60 278	99.12 119	99.84 305	98.45 254	99.70 299	99.45 284

APD_test1		99.36 180	99.28 187	99.61 186	99.89 39	99.89 10	99.32 157	99.74 166	99.18 250	99.69 189	99.75 157	98.41 239	99.84 305	97.85 311	99.70 299	99.10 389

test_vis1_rt		99.45 145	99.46 133	99.41 269	99.71 191	98.63 338	98.99 294	99.96 28	99.03 274	99.95 45	99.12 410	98.75 185	99.84 305	99.82 50	99.82 232	99.77 79

FA-MVS(test-final)		98.52 338	98.32 343	99.10 344	99.48 314	98.67 329	99.77 19	98.60 436	97.35 432	99.63 220	99.80 107	93.07 409	99.84 305	97.92 301	99.30 393	98.78 442

EIA-MVS		99.12 249	99.01 255	99.45 251	99.36 349	99.62 140	99.34 148	99.79 130	98.41 355	98.84 394	98.89 440	98.75 185	99.84 305	98.15 284	99.51 364	98.89 431

Anonymous202405211		98.75 313	98.46 327	99.63 171	99.34 362	99.66 120	99.47 112	97.65 468	99.28 233	99.56 255	99.50 323	93.15 407	99.84 305	98.62 244	99.58 346	99.40 314

Effi-MVS+		99.06 262	98.97 270	99.34 293	99.31 369	98.98 295	98.31 394	99.91 51	98.81 309	98.79 401	98.94 436	99.14 114	99.84 305	98.79 216	98.74 436	99.20 366

gm-plane-assit					97.59 493	89.02 503			93.47 481		98.30 465		99.84 305	96.38 423

test_8					99.34 362	99.31 235	98.08 416	99.40 344	94.90 474	97.87 459	98.97 432	98.02 280	99.84 305

v1144		99.54 113	99.53 116	99.59 193	99.79 129	99.28 240	99.10 249	99.61 245	99.20 247	99.84 101	99.73 167	98.67 197	99.84 305	99.86 45	99.98 50	99.64 168

v8		99.68 64	99.69 60	99.65 157	99.80 115	99.40 212	99.66 57	99.76 155	99.64 149	99.93 53	99.85 68	98.66 199	99.84 305	99.88 41	99.99 16	99.71 102

v2v482		99.50 122	99.47 128	99.58 196	99.78 137	99.25 248	99.14 229	99.58 271	99.25 238	99.81 115	99.62 260	98.24 258	99.84 305	99.83 46	99.97 73	99.64 168

VNet		99.18 233	99.06 237	99.56 208	99.24 386	99.36 226	99.33 154	99.31 370	99.67 137	99.47 285	99.57 298	96.48 353	99.84 305	99.15 156	99.30 393	99.47 277

ADS-MVSNet		97.72 392	97.67 390	97.86 438	99.14 404	94.65 472	99.22 198	98.86 418	96.97 445	98.25 437	99.64 236	90.90 437	99.84 305	96.51 414	99.56 349	99.08 400

casdiffmvs_mvg		99.68 64	99.68 63	99.69 137	99.81 106	99.59 156	99.29 172	99.90 57	99.71 118	99.79 128	99.73 167	99.54 54	99.84 305	99.36 118	99.96 87	99.65 156
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		99.01 277	98.92 279	99.27 318	99.71 191	99.28 240	98.59 360	99.77 147	98.32 372	99.39 311	99.41 346	98.62 203	99.84 305	96.62 410	99.84 214	98.69 448

usedtu_dtu_shiyan1		98.87 300	98.71 302	99.35 290	99.59 249	98.88 311	97.17 471	99.64 231	98.94 285	99.27 339	99.22 396	95.57 376	99.83 325	99.08 174	99.92 145	99.35 328

usedtu_blend_shiyan5		97.97 380	97.65 392	98.92 368	97.71 490	97.49 410	99.53 92	99.81 116	99.52 180	98.18 441	96.82 494	91.92 421	99.83 325	98.79 216	96.53 482	99.45 284

blend_shiyan4		95.04 456	93.76 460	98.88 382	97.92 486	97.49 410	97.72 445	99.34 359	97.93 399	97.65 469	97.11 488	77.69 491	99.83 325	98.79 216	79.72 499	99.33 334

FE-MVSNET3		98.87 300	98.71 302	99.35 290	99.59 249	98.88 311	97.17 471	99.64 231	98.94 285	99.27 339	99.22 396	95.57 376	99.83 325	99.08 174	99.92 145	99.35 328

viewdifsd2359ckpt11		99.62 91	99.64 78	99.56 208	99.86 59	99.19 266	99.02 276	99.93 39	99.83 81	99.88 82	99.81 97	98.99 147	99.83 325	99.48 96	99.96 87	99.65 156

viewmsd2359difaftdt		99.62 91	99.64 78	99.56 208	99.86 59	99.19 266	99.02 276	99.93 39	99.83 81	99.88 82	99.81 97	98.99 147	99.83 325	99.48 96	99.96 87	99.65 156

IMVS_0407		99.38 171	99.42 143	99.28 313	99.71 191	98.55 345	99.27 178	99.71 183	99.41 211	99.73 172	99.60 278	99.17 107	99.83 325	98.45 254	99.70 299	99.45 284

reproduce_monomvs		97.40 406	97.46 394	97.20 459	99.05 422	91.91 488	99.20 201	99.18 399	99.84 75	99.86 95	99.75 157	80.67 478	99.83 325	99.69 64	99.95 111	99.85 49

9.14			98.64 308		99.45 328		98.81 332	99.60 256	97.52 423	99.28 338	99.56 302	98.53 223	99.83 325	95.36 457	99.64 325

SMA-MVS		99.19 229	99.00 259	99.73 113	99.46 324	99.73 90	99.13 236	99.52 305	97.40 429	99.57 247	99.64 236	98.93 157	99.83 325	97.61 341	99.79 254	99.63 174
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		99.39 168	99.62 83	98.72 397	99.88 45	96.44 443	99.56 87	99.85 81	99.90 49	99.90 67	99.85 68	98.09 275	99.83 325	99.58 81	99.95 111	99.90 29

YYNet1		98.95 290	98.99 266	98.84 386	99.64 234	97.14 427	98.22 401	99.32 366	98.92 293	99.59 242	99.66 225	97.40 319	99.83 325	98.27 269	99.90 159	99.55 229

MDA-MVSNet_test_wron		98.95 290	98.99 266	98.85 384	99.64 234	97.16 425	98.23 400	99.33 364	98.93 290	99.56 255	99.66 225	97.39 321	99.83 325	98.29 267	99.88 183	99.55 229

baseline		99.63 84	99.62 83	99.66 150	99.80 115	99.62 140	99.44 119	99.80 121	99.71 118	99.72 177	99.69 204	99.15 111	99.83 325	99.32 127	99.94 127	99.53 245

CDS-MVSNet		99.22 219	99.13 212	99.50 233	99.35 353	99.11 278	98.96 303	99.54 290	99.46 194	99.61 236	99.70 195	96.31 362	99.83 325	99.34 122	99.88 183	99.55 229
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DeepC-MVS_fast	98.47 5	99.23 210	99.12 216	99.56 208	99.28 378	99.22 259	98.99 294	99.40 344	99.08 268	99.58 244	99.64 236	98.90 166	99.83 325	97.44 351	99.75 273	99.63 174
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	98.36 354	97.99 368	99.48 242	99.32 368	99.24 253	98.50 377	99.51 310	95.19 472	98.58 419	98.96 434	96.95 339	99.83 325	95.63 450	99.25 401	99.37 322
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
FE-MVSNET		99.45 145	99.36 159	99.71 127	99.84 77	99.64 132	99.16 222	99.91 51	98.65 329	99.73 172	99.73 167	98.54 218	99.82 342	98.71 234	99.96 87	99.67 133

pmmvs5		99.19 229	99.11 219	99.42 261	99.76 154	98.88 311	98.55 369	99.73 170	98.82 307	99.72 177	99.62 260	96.56 349	99.82 342	99.32 127	99.95 111	99.56 225

test_post1							99.14 229				51.63 511	89.54 454	99.82 342	96.86 392

原ACMM1				99.37 283	99.47 320	98.87 315		99.27 378	96.74 452	98.26 436	99.32 373	97.93 288	99.82 342	95.96 441	99.38 382	99.43 305

V42		99.56 104	99.54 112	99.63 171	99.79 129	99.46 189	99.39 129	99.59 262	99.24 240	99.86 95	99.70 195	98.55 214	99.82 342	99.79 53	99.95 111	99.60 204

CDPH-MVS		98.56 334	98.20 353	99.61 186	99.50 304	99.46 189	98.32 393	99.41 337	95.22 470	99.21 352	99.10 414	98.34 249	99.82 342	95.09 462	99.66 321	99.56 225

test12				99.54 221	99.29 375	99.33 232		99.16 402		98.43 429		97.54 314	99.82 342		99.47 371	99.48 273

casdiffmvs		99.63 84	99.61 87	99.67 143	99.79 129	99.59 156	99.13 236	99.85 81	99.79 99	99.76 152	99.72 175	99.33 85	99.82 342	99.21 143	99.94 127	99.59 211
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		97.73 389	97.33 400	98.96 361	99.30 373	97.73 403	99.40 127	98.42 445	99.33 224	99.46 289	99.21 400	91.18 432	99.82 342	98.35 263	91.26 494	99.32 338

HQP_MVS		98.90 295	98.68 307	99.55 215	99.58 256	99.24 253	98.80 335	99.54 290	98.94 285	99.14 362	99.25 389	97.24 326	99.82 342	95.84 446	99.78 263	99.60 204

plane_prior5								99.54 290					99.82 342	95.84 446	99.78 263	99.60 204

tpmrst		97.73 389	98.07 364	96.73 468	98.71 462	92.00 487	99.10 249	98.86 418	98.52 345	98.92 384	99.54 312	91.90 424	99.82 342	98.02 291	99.03 416	98.37 467

UnsupCasMVSNet_bld		98.55 335	98.27 349	99.40 272	99.56 277	99.37 222	97.97 430	99.68 203	97.49 425	99.08 369	99.35 369	95.41 381	99.82 342	97.70 327	98.19 461	99.01 417

dp		96.86 418	97.07 409	96.24 474	98.68 464	90.30 501	99.19 207	98.38 449	97.35 432	98.23 439	99.59 288	87.23 460	99.82 342	96.27 427	98.73 439	98.59 453

test_0402		99.22 219	99.14 210	99.45 251	99.79 129	99.43 201	99.28 174	99.68 203	99.54 174	99.40 309	99.56 302	99.07 130	99.82 342	96.01 436	99.96 87	99.11 387

PMMVS		98.49 343	98.29 348	99.11 342	98.96 434	98.42 357	97.54 454	99.32 366	97.53 422	98.47 427	98.15 470	97.88 291	99.82 342	97.46 350	99.24 403	99.09 394

viewdifsd2359ckpt07		99.51 120	99.50 121	99.52 227	99.80 115	99.19 266	98.92 312	99.88 65	99.72 112	99.64 215	99.62 260	99.06 136	99.81 358	98.96 192	99.94 127	99.56 225

testing222		95.60 454	94.59 457	98.61 404	98.66 465	97.45 415	98.54 372	97.90 464	98.53 344	96.54 484	96.47 502	70.62 503	99.81 358	95.91 444	98.15 463	98.56 458

tt0805		99.63 84	99.57 102	99.81 54	99.87 54	99.88 12	99.58 82	98.70 428	99.72 112	99.91 62	99.60 278	99.43 66	99.81 358	99.81 51	99.53 360	99.73 93

LFMVS		98.46 346	98.19 356	99.26 321	99.24 386	98.52 351	99.62 67	96.94 477	99.87 62	99.31 332	99.58 291	91.04 434	99.81 358	98.68 238	99.42 378	99.45 284

NCCC		98.82 306	98.57 317	99.58 196	99.21 391	99.31 235	98.61 355	99.25 383	98.65 329	98.43 429	99.26 387	97.86 292	99.81 358	96.55 411	99.27 399	99.61 200

MIMVSNet		98.43 348	98.20 353	99.11 342	99.53 289	98.38 362	99.58 82	98.61 434	98.96 281	99.33 324	99.76 149	90.92 436	99.81 358	97.38 355	99.76 269	99.15 378

IS-MVSNet		99.03 269	98.85 288	99.55 215	99.80 115	99.25 248	99.73 30	99.15 403	99.37 217	99.61 236	99.71 185	94.73 389	99.81 358	97.70 327	99.88 183	99.58 216

AdaColmap		98.60 328	98.35 340	99.38 278	99.12 408	99.22 259	98.67 350	99.42 336	97.84 408	98.81 397	99.27 384	97.32 324	99.81 358	95.14 460	99.53 360	99.10 389

MCST-MVS		99.02 271	98.81 295	99.65 157	99.58 256	99.49 179	98.58 362	99.07 408	98.40 357	99.04 374	99.25 389	98.51 228	99.80 366	97.31 359	99.51 364	99.65 156

CostFormer		96.71 423	96.79 422	96.46 472	98.90 437	90.71 498	99.41 122	98.68 429	94.69 478	98.14 448	99.34 372	86.32 469	99.80 366	97.60 342	98.07 467	98.88 432

PHI-MVS		99.11 253	98.95 273	99.59 193	99.13 406	99.59 156	99.17 216	99.65 223	97.88 403	99.25 343	99.46 338	98.97 153	99.80 366	97.26 366	99.82 232	99.37 322

Patchmatch-RL test		98.60 328	98.36 338	99.33 296	99.77 150	99.07 288	98.27 396	99.87 69	98.91 294	99.74 167	99.72 175	90.57 446	99.79 369	98.55 248	99.85 209	99.11 387

test0.0.03 1		97.37 408	96.91 417	98.74 396	97.72 489	97.57 407	97.60 452	97.36 474	98.00 388	99.21 352	98.02 471	90.04 451	99.79 369	98.37 261	95.89 491	98.86 434

MSDG		99.08 258	98.98 269	99.37 283	99.60 243	99.13 275	97.54 454	99.74 166	98.84 305	99.53 268	99.55 310	99.10 121	99.79 369	97.07 382	99.86 204	99.18 371

E5new		99.68 64	99.67 64	99.70 132	99.87 54	99.62 140	99.41 122	99.84 88	99.68 129	99.77 144	99.81 97	99.59 45	99.78 372	99.13 165	99.96 87	99.70 105

E6new		99.68 64	99.67 64	99.70 132	99.86 59	99.62 140	99.41 122	99.84 88	99.68 129	99.77 144	99.81 97	99.59 45	99.78 372	99.13 165	99.96 87	99.70 105

E6		99.68 64	99.67 64	99.70 132	99.86 59	99.62 140	99.41 122	99.84 88	99.68 129	99.77 144	99.81 97	99.59 45	99.78 372	99.13 165	99.96 87	99.70 105

E5		99.68 64	99.67 64	99.70 132	99.87 54	99.62 140	99.41 122	99.84 88	99.68 129	99.77 144	99.81 97	99.59 45	99.78 372	99.13 165	99.96 87	99.70 105

viewmambaseed2359dif		99.47 139	99.50 121	99.37 283	99.70 206	98.80 320	98.67 350	99.92 42	99.49 183	99.77 144	99.71 185	99.08 127	99.78 372	99.20 146	99.94 127	99.54 239

cl____		98.54 336	98.41 333	98.92 368	99.03 426	97.80 401	97.46 460	99.59 262	98.90 295	99.60 239	99.46 338	93.85 397	99.78 372	97.97 298	99.89 173	99.17 374

DIV-MVS_self_test		98.54 336	98.42 332	98.92 368	99.03 426	97.80 401	97.46 460	99.59 262	98.90 295	99.60 239	99.46 338	93.87 396	99.78 372	97.97 298	99.89 173	99.18 371

MVP-Stereo		99.16 239	99.08 231	99.43 259	99.48 314	99.07 288	99.08 257	99.55 284	98.63 332	99.31 332	99.68 216	98.19 267	99.78 372	98.18 280	99.58 346	99.45 284
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
nrg030		99.70 57	99.66 71	99.82 46	99.76 154	99.84 26	99.61 73	99.70 192	99.93 43	99.78 132	99.68 216	99.10 121	99.78 372	99.45 102	99.96 87	99.83 56

Vis-MVSNet (Re-imp)		98.77 311	98.58 316	99.34 293	99.78 137	98.88 311	99.61 73	99.56 278	99.11 267	99.24 346	99.56 302	93.00 411	99.78 372	97.43 352	99.89 173	99.35 328

CNLPA		98.57 333	98.34 341	99.28 313	99.18 399	99.10 285	98.34 391	99.41 337	98.48 350	98.52 424	98.98 430	97.05 336	99.78 372	95.59 451	99.50 367	98.96 420

ACMH+	98.40 8	99.50 122	99.43 141	99.71 127	99.86 59	99.76 70	99.32 157	99.77 147	99.53 176	99.77 144	99.76 149	99.26 95	99.78 372	97.77 316	99.88 183	99.60 204

CLD-MVS		98.76 312	98.57 317	99.33 296	99.57 266	98.97 298	97.53 456	99.55 284	96.41 454	99.27 339	99.13 406	99.07 130	99.78 372	96.73 401	99.89 173	99.23 357
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		93.18 458	91.66 462	97.73 445	95.83 498	95.29 465	95.30 491	95.90 484	93.59 480	90.58 497	94.40 506	77.87 489	99.77 385	97.31 359	84.20 495	98.15 478

E4		99.61 95	99.59 93	99.66 150	99.84 77	99.53 172	99.08 257	99.84 88	99.65 145	99.74 167	99.80 107	99.45 62	99.77 385	98.93 200	99.95 111	99.69 117

ttmdpeth		99.48 129	99.55 109	99.29 310	99.76 154	98.16 375	99.33 154	99.95 36	99.79 99	99.36 315	99.89 41	99.13 116	99.77 385	99.09 172	99.64 325	99.93 20

PVSNet_BlendedMVS		99.03 269	99.01 255	99.09 345	99.54 282	97.99 387	98.58 362	99.82 103	97.62 417	99.34 322	99.71 185	98.52 226	99.77 385	97.98 296	99.97 73	99.52 256

PVSNet_Blended		98.70 320	98.59 313	99.02 355	99.54 282	97.99 387	97.58 453	99.82 103	95.70 465	99.34 322	98.98 430	98.52 226	99.77 385	97.98 296	99.83 222	99.30 345

0.3-1-1-0.015		92.36 460	90.68 464	97.39 453	94.94 501	94.41 474	94.21 493	95.89 485	92.87 483	88.87 499	93.49 508	75.30 495	99.76 390	97.19 375	83.41 497	98.02 481

E3new		99.42 156	99.37 154	99.56 208	99.68 220	99.38 217	98.93 311	99.79 130	99.30 229	99.55 260	99.69 204	98.88 167	99.76 390	98.63 243	99.89 173	99.53 245

E2		99.54 113	99.51 119	99.62 180	99.78 137	99.47 183	99.01 281	99.82 103	99.55 172	99.69 189	99.77 141	99.26 95	99.76 390	98.82 209	99.93 139	99.62 186

E3		99.54 113	99.51 119	99.62 180	99.78 137	99.47 183	99.01 281	99.82 103	99.55 172	99.69 189	99.77 141	99.25 99	99.76 390	98.82 209	99.93 139	99.62 186

viewdifsd2359ckpt09		99.24 208	99.16 205	99.49 237	99.70 206	99.22 259	98.88 316	99.81 116	98.70 324	99.38 312	99.37 359	98.22 263	99.76 390	98.48 251	99.88 183	99.51 258

viewcassd2359sk11		99.48 129	99.45 135	99.58 196	99.73 182	99.42 204	98.96 303	99.80 121	99.44 199	99.63 220	99.74 162	99.09 123	99.76 390	98.72 232	99.91 157	99.57 222

eth_miper_zixun_eth		98.68 322	98.71 302	98.60 405	99.10 415	96.84 436	97.52 458	99.54 290	98.94 285	99.58 244	99.48 331	96.25 365	99.76 390	98.01 294	99.93 139	99.21 362

OPM-MVS		99.26 203	99.13 212	99.63 171	99.70 206	99.61 150	98.58 362	99.48 319	98.50 347	99.52 270	99.63 251	99.14 114	99.76 390	97.89 304	99.77 267	99.51 258
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
pmmvs-eth3d		99.48 129	99.47 128	99.51 231	99.77 150	99.41 211	98.81 332	99.66 213	99.42 210	99.75 157	99.66 225	99.20 103	99.76 390	98.98 188	99.99 16	99.36 325

pmmvs4		99.13 246	99.06 237	99.36 288	99.57 266	99.10 285	98.01 423	99.25 383	98.78 314	99.58 244	99.44 342	98.24 258	99.76 390	98.74 225	99.93 139	99.22 359

0.4-1-1-0.2		92.59 459	91.07 463	97.15 462	94.73 502	93.68 480	93.50 494	95.91 483	92.68 484	90.48 498	93.52 507	77.77 490	99.75 400	97.19 375	83.88 496	98.01 482

ETVMVS		96.14 439	95.22 450	98.89 380	98.80 451	98.01 386	98.66 352	98.35 451	98.71 323	97.18 476	96.31 505	74.23 499	99.75 400	96.64 408	98.13 466	98.90 429

AllTest		99.21 224	99.07 235	99.63 171	99.78 137	99.64 132	99.12 241	99.83 97	98.63 332	99.63 220	99.72 175	98.68 194	99.75 400	96.38 423	99.83 222	99.51 258

TestCases				99.63 171	99.78 137	99.64 132		99.83 97	98.63 332	99.63 220	99.72 175	98.68 194	99.75 400	96.38 423	99.83 222	99.51 258

CL-MVSNet_self_test		98.71 319	98.56 321	99.15 336	99.22 389	98.66 332	97.14 474	99.51 310	98.09 385	99.54 263	99.27 384	96.87 341	99.74 404	98.43 258	98.96 420	99.03 411

MVS		95.72 450	94.63 456	98.99 357	98.56 467	97.98 392	99.30 165	98.86 418	72.71 498	97.30 472	99.08 415	98.34 249	99.74 404	89.21 485	98.33 454	99.26 351

MG-MVS		98.52 338	98.39 335	98.94 364	99.15 403	97.39 419	98.18 402	99.21 394	98.89 298	99.23 347	99.63 251	97.37 322	99.74 404	94.22 471	99.61 337	99.69 117

c3_l		98.72 317	98.71 302	98.72 397	99.12 408	97.22 424	97.68 449	99.56 278	98.90 295	99.54 263	99.48 331	96.37 360	99.73 407	97.88 305	99.88 183	99.21 362

tpmvs		97.39 407	97.69 388	96.52 470	98.41 472	91.76 489	99.30 165	98.94 417	97.74 410	97.85 461	99.55 310	92.40 420	99.73 407	96.25 428	98.73 439	98.06 480

viewmacassd2359aftdt		99.63 84	99.61 87	99.68 139	99.84 77	99.61 150	99.14 229	99.87 69	99.71 118	99.75 157	99.77 141	99.54 54	99.72 409	98.91 202	99.96 87	99.70 105

thres600view7		96.60 425	96.16 428	97.93 435	99.63 236	96.09 453	99.18 211	97.57 469	98.77 316	98.72 407	97.32 485	87.04 462	99.72 409	88.57 487	98.62 444	97.98 483

EPMVS		96.53 426	96.32 425	97.17 461	98.18 479	92.97 484	99.39 129	89.95 501	98.21 378	98.61 416	99.59 288	86.69 468	99.72 409	96.99 384	99.23 405	98.81 439

PVSNet	97.47 15	98.42 349	98.44 330	98.35 417	99.46 324	96.26 448	96.70 484	99.34 359	97.68 415	99.00 376	99.13 406	97.40 319	99.72 409	97.59 343	99.68 312	99.08 400

MAR-MVS		98.24 364	97.92 378	99.19 331	98.78 455	99.65 126	99.17 216	99.14 404	95.36 468	98.04 451	98.81 447	97.47 316	99.72 409	95.47 454	99.06 412	98.21 474
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		99.50 122	99.47 128	99.61 186	99.73 182	99.52 176	99.03 272	99.83 97	99.49 183	99.65 212	99.64 236	99.18 105	99.71 414	98.73 230	99.92 145	99.58 216

testing91		96.00 443	95.32 448	98.02 430	98.76 458	95.39 462	98.38 389	98.65 433	98.82 307	96.84 479	96.71 498	75.06 497	99.71 414	96.46 419	98.23 458	98.98 419

miper_ehance_all_eth		98.59 331	98.59 313	98.59 406	98.98 432	97.07 428	97.49 459	99.52 305	98.50 347	99.52 270	99.37 359	96.41 358	99.71 414	97.86 309	99.62 330	99.00 418

Gipuma		99.57 100	99.59 93	99.49 237	99.98 3	99.71 100	99.72 33	99.84 88	99.81 91	99.94 48	99.78 131	98.91 163	99.71 414	98.41 259	99.95 111	99.05 407
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
viewdifsd2359ckpt13		99.42 156	99.37 154	99.57 204	99.72 187	99.46 189	99.01 281	99.80 121	99.20 247	99.51 277	99.60 278	98.92 160	99.70 418	98.65 241	99.90 159	99.55 229

ambc				99.20 330	99.35 353	98.53 349	99.17 216	99.46 325		99.67 202	99.80 107	98.46 233	99.70 418	97.92 301	99.70 299	99.38 319

HQP4-MVS										98.15 444			99.70 418			99.53 245

CNVR-MVS		98.99 283	98.80 297	99.56 208	99.25 384	99.43 201	98.54 372	99.27 378	98.58 338	98.80 399	99.43 343	98.53 223	99.70 418	97.22 372	99.59 344	99.54 239

tpm2		96.35 432	96.22 427	96.73 468	98.88 442	91.75 490	99.21 200	98.51 440	93.27 482	97.89 457	99.21 400	84.83 472	99.70 418	96.04 435	98.18 462	98.75 446

HQP-MVS		98.36 354	98.02 367	99.39 275	99.31 369	98.94 302	97.98 427	99.37 352	97.45 426	98.15 444	98.83 444	96.67 346	99.70 418	94.73 464	99.67 318	99.53 245

PatchMatch-RL		98.68 322	98.47 326	99.30 309	99.44 329	99.28 240	98.14 408	99.54 290	97.12 443	99.11 366	99.25 389	97.80 297	99.70 418	96.51 414	99.30 393	98.93 425

testing11		96.05 442	95.41 445	97.97 433	98.78 455	95.27 466	98.59 360	98.23 455	98.86 301	96.56 483	96.91 492	75.20 496	99.69 425	97.26 366	98.29 456	98.93 425

testing99		95.86 447	95.19 451	97.87 437	98.76 458	95.03 468	98.62 354	98.44 444	98.68 326	96.67 482	96.66 499	74.31 498	99.69 425	96.51 414	98.03 468	98.90 429

miper_enhance_ethall		98.03 376	97.94 376	98.32 420	98.27 476	96.43 444	96.95 480	99.41 337	96.37 456	99.43 295	98.96 434	94.74 388	99.69 425	97.71 324	99.62 330	98.83 437

test_yl		98.25 362	97.95 372	99.13 340	99.17 400	98.47 352	99.00 287	98.67 431	98.97 279	99.22 350	99.02 425	91.31 430	99.69 425	97.26 366	98.93 421	99.24 354

DCV-MVSNet		98.25 362	97.95 372	99.13 340	99.17 400	98.47 352	99.00 287	98.67 431	98.97 279	99.22 350	99.02 425	91.31 430	99.69 425	97.26 366	98.93 421	99.24 354

MS-PatchMatch		99.00 280	98.97 270	99.09 345	99.11 413	98.19 371	98.76 341	99.33 364	98.49 349	99.44 291	99.58 291	98.21 264	99.69 425	98.20 276	99.62 330	99.39 317

v148		99.40 164	99.41 146	99.39 275	99.76 154	98.94 302	99.09 254	99.59 262	99.17 255	99.81 115	99.61 270	98.41 239	99.69 425	99.32 127	99.94 127	99.53 245

test_prior				99.46 248	99.35 353	99.22 259		99.39 347					99.69 425			99.48 273

tpm cat1		96.78 420	96.98 413	96.16 475	98.85 445	90.59 499	99.08 257	99.32 366	92.37 485	97.73 467	99.46 338	91.15 433	99.69 425	96.07 434	98.80 429	98.21 474

PAPM_NR		98.36 354	98.04 365	99.33 296	99.48 314	98.93 305	98.79 338	99.28 377	97.54 421	98.56 423	98.57 457	97.12 333	99.69 425	94.09 473	98.90 427	99.38 319

PAPM		95.61 453	94.71 455	98.31 422	99.12 408	96.63 438	96.66 485	98.46 443	90.77 490	96.25 486	98.68 454	93.01 410	99.69 425	81.60 496	97.86 472	98.62 450

OMC-MVS		98.90 295	98.72 301	99.44 255	99.39 341	99.42 204	98.58 362	99.64 231	97.31 434	99.44 291	99.62 260	98.59 207	99.69 425	96.17 432	99.79 254	99.22 359

E-PMN		97.14 414	97.43 397	96.27 473	98.79 453	91.62 491	95.54 489	99.01 415	99.44 199	98.88 388	99.12 410	92.78 412	99.68 437	94.30 470	99.03 416	97.50 487

TSAR-MVS + GP.		99.12 249	99.04 248	99.38 278	99.34 362	99.16 272	98.15 406	99.29 374	98.18 381	99.63 220	99.62 260	99.18 105	99.68 437	98.20 276	99.74 280	99.30 345

MVS-HIRNet		97.86 381	98.22 351	96.76 465	99.28 378	91.53 492	98.38 389	92.60 497	99.13 263	99.31 332	99.96 15	97.18 332	99.68 437	98.34 264	99.83 222	99.07 405

PAPR		97.56 397	97.07 409	99.04 354	98.80 451	98.11 379	97.63 450	99.25 383	94.56 479	98.02 453	98.25 467	97.43 318	99.68 437	90.90 484	98.74 436	99.33 334

ITE_SJBPF				99.38 278	99.63 236	99.44 197		99.73 170	98.56 339	99.33 324	99.53 314	98.88 167	99.68 437	96.01 436	99.65 323	99.02 416

MVStest1		98.22 367	98.09 362	98.62 403	99.04 425	96.23 449	99.20 201	99.92 42	99.44 199	99.98 14	99.87 56	85.87 470	99.67 442	99.91 33	99.57 348	99.95 14

thres100view900		96.39 431	96.03 431	97.47 450	99.63 236	95.93 454	99.18 211	97.57 469	98.75 320	98.70 410	97.31 486	87.04 462	99.67 442	87.62 490	98.51 448	96.81 492

tfpn200view9		96.30 434	95.89 433	97.53 447	99.58 256	96.11 451	99.00 287	97.54 472	98.43 352	98.52 424	96.98 490	86.85 464	99.67 442	87.62 490	98.51 448	96.81 492

1314		98.00 378	97.90 380	98.27 425	98.90 437	97.45 415	99.30 165	99.06 410	94.98 473	97.21 475	99.12 410	98.43 236	99.67 442	95.58 452	98.56 446	97.71 486

thres400		96.40 430	95.89 433	97.92 436	99.58 256	96.11 451	99.00 287	97.54 472	98.43 352	98.52 424	96.98 490	86.85 464	99.67 442	87.62 490	98.51 448	97.98 483

testing3-2		96.51 428	96.43 423	96.74 467	99.36 349	91.38 494	99.10 249	97.87 465	99.48 186	98.57 421	98.71 451	76.65 493	99.66 447	98.87 204	99.26 400	99.18 371

EMVS		96.96 417	97.28 401	95.99 477	98.76 458	91.03 495	95.26 492	98.61 434	99.34 221	98.92 384	98.88 441	93.79 398	99.66 447	92.87 478	99.05 414	97.30 491

MVS_Test		99.28 197	99.31 174	99.19 331	99.35 353	98.79 321	99.36 144	99.49 318	99.17 255	99.21 352	99.67 220	98.78 180	99.66 447	99.09 172	99.66 321	99.10 389

EPNet_dtu		97.62 394	97.79 385	97.11 463	96.67 497	92.31 486	98.51 376	98.04 459	99.24 240	95.77 489	99.47 335	93.78 399	99.66 447	98.98 188	99.62 330	99.37 322
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
BH-RMVSNet		98.41 350	98.14 359	99.21 328	99.21 391	98.47 352	98.60 357	98.26 454	98.35 366	98.93 381	99.31 376	97.20 331	99.66 447	94.32 469	99.10 410	99.51 258

MDTV_nov1_ep13			97.73 387		98.70 463	90.83 496	99.15 225	98.02 460	98.51 346	98.82 396	99.61 270	90.98 435	99.66 447	96.89 391	98.92 423

MVS_111021_LR		99.13 246	99.03 250	99.42 261	99.58 256	99.32 234	97.91 436	99.73 170	98.68 326	99.31 332	99.48 331	99.09 123	99.66 447	97.70 327	99.77 267	99.29 348

BH-untuned		98.22 367	98.09 362	98.58 408	99.38 344	97.24 423	98.55 369	98.98 416	97.81 409	99.20 357	98.76 449	97.01 337	99.65 454	94.83 463	98.33 454	98.86 434

RPSCF		99.18 233	99.02 251	99.64 164	99.83 85	99.85 21	99.44 119	99.82 103	98.33 371	99.50 280	99.78 131	97.90 289	99.65 454	96.78 398	99.83 222	99.44 299

SD_0403		97.42 405	96.90 418	98.98 359	99.54 282	97.90 395	99.52 94	99.54 290	99.34 221	97.87 459	98.85 443	98.72 190	99.64 456	78.93 497	99.83 222	99.40 314

USDC		98.96 287	98.93 275	99.05 353	99.54 282	97.99 387	97.07 477	99.80 121	98.21 378	99.75 157	99.77 141	98.43 236	99.64 456	97.90 303	99.88 183	99.51 258

DeepPCF-MVS	98.42 6	99.18 233	99.02 251	99.67 143	99.22 389	99.75 79	97.25 468	99.47 322	98.72 321	99.66 208	99.70 195	99.29 89	99.63 458	98.07 290	99.81 242	99.62 186

UBG		96.53 426	95.95 432	98.29 424	98.87 443	96.31 447	98.48 380	98.07 458	98.83 306	97.32 471	96.54 500	79.81 483	99.62 459	96.84 395	98.74 436	98.95 422

alignmvs		98.28 360	97.96 371	99.25 324	99.12 408	98.93 305	99.03 272	98.42 445	99.64 149	98.72 407	97.85 475	90.86 440	99.62 459	98.88 203	99.13 407	99.19 369

DeepMVS_CX				97.98 432	99.69 212	96.95 430		99.26 380	75.51 497	95.74 490	98.28 466	96.47 354	99.62 459	91.23 483	97.89 470	97.38 489

TinyColmap		98.97 284	98.93 275	99.07 350	99.46 324	98.19 371	97.75 442	99.75 160	98.79 312	99.54 263	99.70 195	98.97 153	99.62 459	96.63 409	99.83 222	99.41 311

TAPA-MVS	97.92 13	98.03 376	97.55 393	99.46 248	99.47 320	99.44 197	98.50 377	99.62 238	86.79 492	99.07 372	99.26 387	98.26 257	99.62 459	97.28 363	99.73 286	99.31 343
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DPM-MVS		98.28 360	97.94 376	99.32 301	99.36 349	99.11 278	97.31 466	98.78 425	96.88 447	98.84 394	99.11 413	97.77 299	99.61 464	94.03 475	99.36 385	99.23 357

thres200		96.09 440	95.68 440	97.33 456	99.48 314	96.22 450	98.53 374	97.57 469	98.06 387	98.37 432	96.73 497	86.84 466	99.61 464	86.99 493	98.57 445	96.16 495

DP-MVS Recon		98.50 341	98.23 350	99.31 305	99.49 309	99.46 189	98.56 368	99.63 235	94.86 476	98.85 393	99.37 359	97.81 296	99.59 466	96.08 433	99.44 374	98.88 432

PVSNet_0	95.53 19	95.85 448	95.31 449	97.47 450	98.78 455	93.48 482	95.72 488	99.40 344	96.18 459	97.37 470	97.73 476	95.73 372	99.58 467	95.49 453	81.40 498	99.36 325

MGCFI-Net		99.02 271	99.01 255	99.06 352	99.11 413	98.60 340	99.63 64	99.67 208	99.63 151	98.58 419	97.65 478	99.07 130	99.57 468	98.85 205	98.92 423	99.03 411

Syy-MVS		98.17 370	97.85 382	99.15 336	98.50 470	98.79 321	98.60 357	99.21 394	97.89 401	96.76 480	96.37 503	95.47 380	99.57 468	99.10 171	98.73 439	99.09 394

myMVS_eth3d		95.63 452	94.73 454	98.34 419	98.50 470	96.36 445	98.60 357	99.21 394	97.89 401	96.76 480	96.37 503	72.10 501	99.57 468	94.38 468	98.73 439	99.09 394

API-MVS		98.38 353	98.39 335	98.35 417	98.83 447	99.26 245	99.14 229	99.18 399	98.59 337	98.66 412	98.78 448	98.61 205	99.57 468	94.14 472	99.56 349	96.21 494

TestfortrainingZip				99.38 278	99.17 400	99.25 248	99.38 132	98.82 421	98.93 290	99.68 194	99.49 327	98.11 274	99.56 472		98.44 452	99.32 338

sasdasda		99.02 271	99.00 259	99.09 345	99.10 415	98.70 327	99.61 73	99.66 213	99.63 151	98.64 413	97.65 478	99.04 139	99.54 473	98.79 216	98.92 423	99.04 409

KD-MVS_2432*1600		95.89 444	95.41 445	97.31 457	94.96 499	93.89 476	97.09 475	99.22 391	97.23 437	98.88 388	99.04 420	79.23 485	99.54 473	96.24 429	96.81 479	98.50 463

miper_refine_blended		95.89 444	95.41 445	97.31 457	94.96 499	93.89 476	97.09 475	99.22 391	97.23 437	98.88 388	99.04 420	79.23 485	99.54 473	96.24 429	96.81 479	98.50 463

canonicalmvs		99.02 271	99.00 259	99.09 345	99.10 415	98.70 327	99.61 73	99.66 213	99.63 151	98.64 413	97.65 478	99.04 139	99.54 473	98.79 216	98.92 423	99.04 409

MVS_111021_HR		99.12 249	99.02 251	99.40 272	99.50 304	99.11 278	97.92 434	99.71 183	98.76 319	99.08 369	99.47 335	99.17 107	99.54 473	97.85 311	99.76 269	99.54 239

test_241102_ONE					99.69 212	99.82 42		99.54 290	99.12 266	99.82 108	99.49 327	98.91 163	99.52 478

gg-mvs-nofinetune		95.87 446	95.17 452	97.97 433	98.19 478	96.95 430	99.69 45	89.23 502	99.89 55	96.24 487	99.94 19	81.19 477	99.51 479	93.99 476	98.20 459	97.44 488

TR-MVS		97.44 404	97.15 406	98.32 420	98.53 468	97.46 413	98.47 381	97.91 463	96.85 448	98.21 440	98.51 461	96.42 356	99.51 479	92.16 480	97.29 477	97.98 483

BH-w/o		97.20 411	97.01 412	97.76 441	99.08 420	95.69 458	98.03 422	98.52 439	95.76 464	97.96 454	98.02 471	95.62 374	99.47 481	92.82 479	97.25 478	98.12 479

PMVS	92.94 21	98.82 306	98.81 295	98.85 384	99.84 77	97.99 387	99.20 201	99.47 322	99.71 118	99.42 298	99.82 90	98.09 275	99.47 481	93.88 477	99.85 209	99.07 405
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CMPMVS	77.52 23	98.50 341	98.19 356	99.41 269	98.33 475	99.56 165	99.01 281	99.59 262	95.44 467	99.57 247	99.80 107	95.64 373	99.46 483	96.47 418	99.92 145	99.21 362
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GA-MVS		97.99 379	97.68 389	98.93 367	99.52 296	98.04 385	97.19 470	99.05 411	98.32 372	98.81 397	98.97 432	89.89 453	99.41 484	98.33 265	99.05 414	99.34 333

cl22		97.56 397	97.28 401	98.40 415	98.37 474	96.75 437	97.24 469	99.37 352	97.31 434	99.41 304	99.22 396	87.30 459	99.37 485	97.70 327	99.62 330	99.08 400

UWE-MVS-28		95.64 451	95.47 443	96.14 476	97.98 485	90.39 500	98.49 379	95.81 487	99.02 275	98.03 452	98.19 468	84.49 474	99.28 486	88.75 486	98.47 451	98.75 446

dmvs_re		98.69 321	98.48 325	99.31 305	99.55 280	99.42 204	99.54 90	98.38 449	99.32 225	98.72 407	98.71 451	96.76 344	99.21 487	96.01 436	99.35 387	99.31 343

GG-mvs-BLEND				97.36 454	97.59 493	96.87 433	99.70 38	88.49 503		94.64 493	97.26 487	80.66 479	99.12 488	91.50 482	96.50 487	96.08 496

MSLP-MVS++		99.05 265	99.09 229	98.91 373	99.21 391	98.36 363	98.82 331	99.47 322	98.85 302	98.90 387	99.56 302	98.78 180	99.09 489	98.57 247	99.68 312	99.26 351

FPMVS		96.32 433	95.50 442	98.79 392	99.60 243	98.17 374	98.46 385	98.80 424	97.16 441	96.28 485	99.63 251	82.19 476	99.09 489	88.45 488	98.89 428	99.10 389

dmvs_testset		97.27 410	96.83 420	98.59 406	99.46 324	97.55 408	99.25 189	96.84 478	98.78 314	97.24 474	97.67 477	97.11 334	98.97 491	86.59 495	98.54 447	99.27 349

myMVS_eth3d28		96.23 436	95.74 438	97.70 446	98.86 444	95.59 461	98.66 352	98.14 457	98.96 281	97.67 468	97.06 489	76.78 492	98.92 492	97.10 379	98.41 453	98.58 455

OPU-MVS				99.29 310	99.12 408	99.44 197	99.20 201				99.40 350	99.00 145	98.84 493	96.54 412	99.60 340	99.58 216

cascas		96.99 415	96.82 421	97.48 449	97.57 495	95.64 459	96.43 486	99.56 278	91.75 487	97.13 478	97.61 481	95.58 375	98.63 494	96.68 403	99.11 409	98.18 477

MVE	92.54 22	96.66 424	96.11 429	98.31 422	99.68 220	97.55 408	97.94 432	95.60 488	99.37 217	90.68 496	98.70 453	96.56 349	98.61 495	86.94 494	99.55 353	98.77 444
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MonoMVSNet		98.23 365	98.32 343	97.99 431	98.97 433	96.62 439	99.49 107	98.42 445	99.62 154	99.40 309	99.79 118	95.51 379	98.58 496	97.68 338	95.98 490	98.76 445

PC_three_1452									97.56 418	99.68 194	99.41 346	99.09 123	97.09 497	96.66 405	99.60 340	99.62 186

tmp_tt		95.75 449	95.42 444	96.76 465	89.90 505	94.42 473	98.86 320	97.87 465	78.01 496	99.30 337	99.69 204	97.70 302	95.89 498	99.29 133	98.14 464	99.95 14

dongtai		89.37 462	88.91 465	90.76 480	99.19 396	77.46 505	95.47 490	87.82 504	92.28 486	94.17 494	98.82 446	71.22 502	95.54 499	63.85 498	97.34 476	99.27 349

SD-MVS		99.01 277	99.30 179	98.15 427	99.50 304	99.40 212	98.94 308	99.61 245	99.22 246	99.75 157	99.82 90	99.54 54	95.51 500	97.48 349	99.87 196	99.54 239
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
kuosan		85.65 464	84.57 467	88.90 482	97.91 487	77.11 506	96.37 487	87.62 505	85.24 495	85.45 500	96.83 493	69.94 504	90.98 501	45.90 499	95.83 492	98.62 450

test123		29.31 465	33.05 470	18.08 483	25.93 507	12.24 508	97.53 456	10.93 508	11.78 501	24.21 502	50.08 513	21.04 505	8.60 502	23.51 500	32.43 501	33.39 498

testmvs		28.94 466	33.33 468	15.79 484	26.03 506	9.81 509	96.77 483	15.67 507	11.55 502	23.87 503	50.74 512	19.03 506	8.53 503	23.21 501	33.07 500	29.03 499

mmdepth		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

monomultidepth		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

test_blank		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uanet_test		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

DCPMVS		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

cdsmvs_eth3d_5k		24.88 467	33.17 469	0.00 485	0.00 508	0.00 510	0.00 496	99.62 238	0.00 503	0.00 504	99.13 406	99.82 18	0.00 504	0.00 502	0.00 502	0.00 500

pcd_1.5k_mvsjas		16.61 468	22.14 471	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	99.28 91	0.00 504	0.00 502	0.00 502	0.00 500

sosnet-low-res		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

sosnet		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uncertanet		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

Regformer		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

ab-mvs-re		8.26 479	11.02 482	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	99.16 404	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uanet		8.33 469	11.11 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	100.00 1	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

WAC-MVS						96.36 445								95.20 459

FOURS1					99.83 85	99.89 10	99.74 27	99.71 183	99.69 127	99.63 220

test_one_0601					99.63 236	99.76 70		99.55 284	99.23 242	99.31 332	99.61 270	98.59 207

eth-test2					0.00 508

eth-test					0.00 508

RE-MVS-def			99.13 212		99.54 282	99.74 87	99.26 183	99.62 238	99.16 257	99.52 270	99.64 236	98.57 210		97.27 364	99.61 337	99.54 239

IU-MVS					99.69 212	99.77 63		99.22 391	97.50 424	99.69 189				97.75 320	99.70 299	99.77 79

save fliter					99.53 289	99.25 248	98.29 395	99.38 351	99.07 270

test0726					99.69 212	99.80 51	99.24 190	99.57 273	99.16 257	99.73 172	99.65 234	98.35 247

GSMVS																99.14 383

test_part2					99.62 240	99.67 118				99.55 260

sam_mvs1												90.81 441				99.14 383

sam_mvs												90.52 447

MTGPA								99.53 300

MTMP							99.09 254	98.59 437

test9_res														95.10 461	99.44 374	99.50 264

agg_prior2														94.58 467	99.46 373	99.50 264

test_prior4						99.19 266	98.00 425

test_prior2							97.95 431		97.87 404	98.05 450	99.05 418	97.90 289		95.99 439	99.49 369

新几何2							98.04 420

旧先验1					99.49 309	99.29 238		99.26 380			99.39 354	97.67 306			99.36 385	99.46 282

原ACMM2							97.92 434

test222					99.51 298	99.08 287	97.83 440	99.29 374	95.21 471	98.68 411	99.31 376	97.28 325			99.38 382	99.43 305

segment_acmp												98.37 245

testdata1							97.72 445		97.86 406

plane_prior7					99.58 256	99.38 217

plane_prior6					99.47 320	99.26 245						97.24 326

plane_prior4											99.25 389

plane_prior3						99.31 235			98.36 361	99.14 362

plane_prior2							98.80 335		98.94 285

plane_prior1					99.51 298

plane_prior						99.24 253	98.42 387		97.87 404						99.71 297

n2								0.00 509

nn								0.00 509

door-mid								99.83 97

test11								99.29 374

door								99.77 147

HQP5-MVS						98.94 302

HQP-NCC					99.31 369		97.98 427		97.45 426	98.15 444

ACMP_Plane					99.31 369		97.98 427		97.45 426	98.15 444

BP-MVS														94.73 464

HQP3-MVS								99.37 352							99.67 318

HQP2-MVS												96.67 346

NP-MVS					99.40 340	99.13 275					98.83 444

MDTV_nov1_ep13_2view						91.44 493	99.14 229		97.37 431	99.21 352		91.78 428		96.75 399		99.03 411

ACMMP++_ref															99.94 127

ACMMP++															99.79 254

Test By Simon												98.41 239

High-resolution multi-view benchmark