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_vis3_rt		99.89 3	99.90 4	99.87 26	99.98 3	99.75 79	99.70 38	100.00 1	99.73 109	100.00 1	99.89 41	99.79 22	99.88 234	99.98 1	100.00 1	99.98 5

test_fmvs2		99.72 54	99.85 17	99.34 289	99.91 31	98.08 380	99.48 108	100.00 1	99.90 50	99.99 7	99.91 31	99.50 60	99.98 27	99.98 1	99.99 16	99.96 13

test_fmvs3		99.83 21	99.93 2	99.53 224	99.96 7	98.62 335	99.67 53	100.00 1	99.95 32	100.00 1	99.95 16	99.85 14	99.99 8	99.98 1	99.99 16	99.98 5

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 71	99.12 239	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_vis1_n_1920		99.72 54	99.88 7	99.27 314	99.93 24	97.84 393	99.34 146	100.00 1	99.99 3	99.99 7	99.82 91	99.87 13	99.99 8	99.97 4	99.99 16	99.97 10

test_vis1_n		99.68 65	99.79 34	99.36 285	99.94 18	98.18 369	99.52 93	100.00 1	99.86 66	100.00 1	99.88 50	98.99 147	99.96 69	99.97 4	99.96 87	99.95 14

test_fmvs1_n		99.68 65	99.81 28	99.28 309	99.95 15	97.93 389	99.49 106	100.00 1	99.82 86	99.99 7	99.89 41	99.21 101	99.98 27	99.97 4	99.98 50	99.93 20

test_f		99.75 49	99.88 7	99.37 280	99.96 7	98.21 366	99.51 100	100.00 1	99.94 36	100.00 1	99.93 22	99.58 48	99.94 97	99.97 4	99.99 16	99.97 10

fmvsm_l_conf0.5_n_9		99.83 21	99.81 28	99.89 11	99.86 58	99.80 52	98.94 306	99.96 28	99.98 18	99.96 34	99.78 130	99.88 11	99.98 27	99.96 9	99.99 16	99.90 29

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 45	99.86 19	99.08 255	99.97 20	99.98 18	99.96 34	99.79 118	99.90 9	99.99 8	99.96 9	99.99 16	99.90 29

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 87	99.01 279	99.99 11	99.99 3	99.98 14	99.88 50	99.97 2	99.99 8	99.96 9	100.00 1	99.98 5

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 54	99.88 45	99.55 168	99.17 214	99.98 12	99.99 3	99.96 34	99.84 77	99.96 3	99.99 8	99.96 9	99.99 16	99.88 40

test_cas_vis1_n_1920		99.76 46	99.86 13	99.45 250	99.93 24	98.40 354	99.30 163	99.98 12	99.94 36	99.99 7	99.89 41	99.80 21	99.97 44	99.96 9	99.97 73	99.97 10

fmvsm_s_conf0.5_n_10		99.77 44	99.73 55	99.88 19	99.81 104	99.75 79	99.06 261	99.85 82	99.99 3	99.97 24	99.84 77	99.12 118	99.98 27	99.95 14	99.99 16	99.90 29

fmvsm_s_conf0.5_n_7		99.73 52	99.78 39	99.60 189	99.74 176	98.93 302	98.85 320	99.96 28	99.96 28	99.97 24	99.76 147	99.82 18	99.96 69	99.95 14	99.98 50	99.90 29

fmvsm_l_conf0.5_n		99.80 30	99.78 39	99.85 32	99.88 45	99.66 120	99.11 244	99.91 52	99.98 18	99.96 34	99.64 234	99.60 43	99.99 8	99.95 14	99.99 16	99.88 40

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 41	99.82 92	99.70 108	99.17 214	99.97 20	99.99 3	99.96 34	99.82 91	99.94 4	100.00 1	99.95 14	100.00 1	99.80 65

test_fmvs1		99.48 129	99.65 73	98.97 356	99.54 280	97.16 418	99.11 244	99.98 12	99.78 103	99.96 34	99.81 98	98.72 190	99.97 44	99.95 14	99.97 73	99.79 73

mvsany_test3		99.85 12	99.88 7	99.75 96	99.95 15	99.37 220	99.53 91	99.98 12	99.77 107	99.99 7	99.95 16	99.85 14	99.94 97	99.95 14	99.98 50	99.94 17

fmvsm_s_conf0.5_n_9		99.82 24	99.82 25	99.82 46	99.83 83	99.59 155	98.97 297	99.92 43	99.99 3	99.97 24	99.84 77	99.90 9	99.94 97	99.94 20	99.99 16	99.92 24

fmvsm_s_conf0.1_n_2		99.81 28	99.78 39	99.89 11	99.93 24	99.76 71	98.92 310	99.98 12	99.99 3	99.99 7	99.88 50	99.43 65	99.94 97	99.94 20	99.99 16	99.99 2

fmvsm_l_conf0.5_n_a		99.80 30	99.79 34	99.84 38	99.88 45	99.64 132	99.12 239	99.91 52	99.98 18	99.95 45	99.67 218	99.67 34	99.99 8	99.94 20	99.99 16	99.88 40

MM		99.18 231	99.05 240	99.55 214	99.35 351	98.81 313	99.05 262	97.79 458	99.99 3	99.48 281	99.59 286	96.29 361	99.95 80	99.94 20	99.98 50	99.88 40

test_fmvsmconf_n		99.85 12	99.84 20	99.88 19	99.91 31	99.73 90	98.97 297	99.98 12	99.99 3	99.96 34	99.85 69	99.93 7	99.99 8	99.94 20	99.99 16	99.93 20

fmvsm_s_conf0.5_n_11		99.76 46	99.75 51	99.81 54	99.81 104	99.53 171	99.15 223	99.89 61	99.99 3	99.98 14	99.86 63	99.13 115	99.98 27	99.93 25	99.99 16	99.92 24

fmvsm_s_conf0.5_n_5		99.78 37	99.76 49	99.85 32	99.79 127	99.72 95	98.84 322	99.96 28	99.96 28	99.96 34	99.72 173	99.71 28	99.99 8	99.93 25	99.98 50	99.85 49

fmvsm_s_conf0.5_n_2		99.78 37	99.75 51	99.88 19	99.82 92	99.76 71	98.88 314	99.92 43	99.98 18	99.98 14	99.85 69	99.42 67	99.94 97	99.93 25	99.98 50	99.94 17

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 43	99.10 247	99.98 12	99.99 3	99.98 14	99.91 31	99.68 33	99.93 118	99.93 25	99.99 16	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 58	99.07 260	99.98 12	99.99 3	99.98 14	99.90 36	99.88 11	99.92 149	99.93 25	99.99 16	99.98 5

fmvsm_s_conf0.5_n_a		99.82 24	99.79 34	99.89 11	99.85 70	99.82 43	99.03 270	99.96 28	99.99 3	99.97 24	99.84 77	99.58 48	99.93 118	99.92 30	99.98 50	99.93 20

fmvsm_s_conf0.5_n		99.83 21	99.81 28	99.87 26	99.85 70	99.78 58	99.03 270	99.96 28	99.99 3	99.97 24	99.84 77	99.78 23	99.92 149	99.92 30	99.99 16	99.92 24

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

fmvsm_s_conf0.5_n_8		99.76 46	99.72 56	99.88 19	99.82 92	99.75 79	99.02 274	99.87 70	99.98 18	99.98 14	99.81 98	99.07 129	99.97 44	99.91 33	99.99 16	99.92 24

fmvsm_s_conf0.5_n_6		99.80 30	99.78 39	99.85 32	99.78 135	99.78 58	99.00 285	99.97 20	99.96 28	99.97 24	99.56 300	99.92 8	99.93 118	99.91 33	99.99 16	99.83 56

fmvsm_s_conf0.5_n_4		99.78 37	99.78 39	99.79 71	99.75 168	99.56 164	98.98 295	99.94 38	99.92 46	99.97 24	99.72 173	99.84 16	99.92 149	99.91 33	99.98 50	99.89 37

MVStest1		98.22 364	98.09 359	98.62 394	99.04 421	96.23 440	99.20 199	99.92 43	99.44 197	99.98 14	99.87 56	85.87 461	99.67 431	99.91 33	99.57 345	99.95 14

v1921920		99.56 104	99.57 102	99.55 214	99.75 168	99.11 275	99.05 262	99.61 242	99.15 259	99.88 83	99.71 183	99.08 126	99.87 249	99.90 37	99.97 73	99.66 146

v1240		99.56 104	99.58 97	99.51 230	99.80 113	99.00 289	99.00 285	99.65 221	99.15 259	99.90 68	99.75 155	99.09 122	99.88 234	99.90 37	99.96 87	99.67 132

v10		99.69 60	99.69 61	99.66 149	99.81 104	99.39 214	99.66 57	99.75 159	99.60 163	99.92 60	99.87 56	98.75 185	99.86 268	99.90 37	99.99 16	99.73 93

v1192		99.57 100	99.57 102	99.57 203	99.77 148	99.22 256	99.04 267	99.60 253	99.18 248	99.87 93	99.72 173	99.08 126	99.85 287	99.89 40	99.98 50	99.66 146

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 32	99.81 104	99.71 100	98.97 297	99.92 43	99.98 18	99.97 24	99.86 63	99.53 56	99.95 80	99.88 41	99.99 16	99.89 37

v144192		99.55 109	99.54 112	99.58 195	99.78 135	99.20 262	99.11 244	99.62 235	99.18 248	99.89 73	99.72 173	98.66 199	99.87 249	99.88 41	99.97 73	99.66 146

v8		99.68 65	99.69 61	99.65 156	99.80 113	99.40 211	99.66 57	99.76 154	99.64 147	99.93 53	99.85 69	98.66 199	99.84 303	99.88 41	99.99 16	99.71 102

mvs5depth		99.88 6	99.91 3	99.80 64	99.92 29	99.42 203	99.94 3	100.00 1	99.97 25	99.89 73	99.99 12	99.63 37	99.97 44	99.87 44	99.99 16	100.00 1

v1144		99.54 113	99.53 116	99.59 192	99.79 127	99.28 238	99.10 247	99.61 242	99.20 245	99.84 102	99.73 165	98.67 197	99.84 303	99.86 45	99.98 50	99.64 167

mmtdpeth		99.78 37	99.83 21	99.66 149	99.85 70	99.05 288	99.79 15	99.97 20	100.00 1	99.43 293	99.94 19	99.64 35	99.94 97	99.83 46	99.99 16	99.98 5

SSC-MVS		99.52 119	99.42 143	99.83 41	99.86 58	99.65 126	99.52 93	99.81 116	99.87 63	99.81 116	99.79 118	96.78 341	99.99 8	99.83 46	99.51 361	99.86 46

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 27	99.82 10	99.82 103	99.84 76	99.94 48	99.91 31	99.13 115	99.96 69	99.83 46	99.99 16	99.83 56

v2v482		99.50 122	99.47 128	99.58 195	99.78 135	99.25 246	99.14 227	99.58 268	99.25 236	99.81 116	99.62 258	98.24 258	99.84 303	99.83 46	99.97 73	99.64 167

test_vis1_rt		99.45 145	99.46 133	99.41 268	99.71 189	98.63 334	98.99 292	99.96 28	99.03 272	99.95 45	99.12 406	98.75 185	99.84 303	99.82 50	99.82 231	99.77 79

tt0805		99.63 84	99.57 102	99.81 54	99.87 54	99.88 12	99.58 82	98.70 419	99.72 113	99.91 63	99.60 276	99.43 65	99.81 351	99.81 51	99.53 357	99.73 93

VortexMVS		99.13 244	99.24 194	98.79 385	99.67 225	96.60 432	99.24 188	99.80 121	99.85 72	99.93 53	99.84 77	95.06 379	99.89 219	99.80 52	99.98 50	99.89 37

V42		99.56 104	99.54 112	99.63 170	99.79 127	99.46 188	99.39 127	99.59 259	99.24 238	99.86 96	99.70 193	98.55 214	99.82 335	99.79 53	99.95 110	99.60 202

SSC-MVS3.2		99.64 83	99.67 65	99.56 207	99.75 168	98.98 292	98.96 301	99.87 70	99.88 61	99.84 102	99.64 234	99.32 85	99.91 178	99.78 54	99.96 87	99.80 65

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 55	99.72 33	99.88 66	99.92 46	99.98 14	99.93 22	99.94 4	99.98 27	99.77 55	100.00 1	99.92 24

WB-MVS		99.44 149	99.32 170	99.80 64	99.81 104	99.61 149	99.47 111	99.81 116	99.82 86	99.71 182	99.72 173	96.60 345	99.98 27	99.75 56	99.23 402	99.82 63

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 64	99.68 49	99.85 82	99.95 32	99.98 14	99.92 27	99.28 90	99.98 27	99.75 56	100.00 1	99.94 17

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 58	99.70 38	99.86 76	99.89 56	99.98 14	99.90 36	99.94 4	99.98 27	99.75 56	100.00 1	99.90 29

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 50	100.00 1	99.97 14	99.61 41	99.97 44	99.75 56	100.00 1	99.84 52

AstraMVS		99.15 241	99.06 235	99.42 260	99.85 70	98.59 338	99.13 234	97.26 466	99.84 76	99.87 93	99.77 140	96.11 364	99.93 118	99.71 60	99.96 87	99.74 89

Elysia		99.69 60	99.65 73	99.81 54	99.86 58	99.72 95	99.34 146	99.77 146	99.94 36	99.91 63	99.76 147	98.55 214	99.99 8	99.70 61	99.98 50	99.72 97

StellarMVS		99.69 60	99.65 73	99.81 54	99.86 58	99.72 95	99.34 146	99.77 146	99.94 36	99.91 63	99.76 147	98.55 214	99.99 8	99.70 61	99.98 50	99.72 97

tt0320-xc		99.82 24	99.82 25	99.82 46	99.82 92	99.84 27	99.82 10	99.92 43	99.94 36	99.94 48	99.93 22	99.34 82	99.92 149	99.70 61	99.96 87	99.70 105

reproduce_monomvs		97.40 398	97.46 391	97.20 448	99.05 418	91.91 476	99.20 199	99.18 391	99.84 76	99.86 96	99.75 155	80.67 469	99.83 319	99.69 64	99.95 110	99.85 49

SPE-MVS-test		99.68 65	99.70 58	99.64 163	99.57 264	99.83 35	99.78 17	99.97 20	99.92 46	99.50 278	99.38 353	99.57 50	99.95 80	99.69 64	99.90 158	99.15 370

guyue		99.12 247	99.02 249	99.41 268	99.84 75	98.56 339	99.19 205	98.30 444	99.82 86	99.84 102	99.75 155	94.84 382	99.92 149	99.68 66	99.94 126	99.74 89

tt0320		99.79 34	99.79 34	99.81 54	99.82 92	99.84 27	99.82 10	99.90 58	99.94 36	99.94 48	99.94 19	99.07 129	99.92 149	99.68 66	99.97 73	99.67 132

MGCNet		98.61 322	98.30 343	99.52 226	97.88 482	98.95 298	98.76 339	94.11 482	99.84 76	99.32 324	99.57 296	95.57 373	99.95 80	99.68 66	99.98 50	99.68 123

CS-MVS		99.67 75	99.70 58	99.58 195	99.53 287	99.84 27	99.79 15	99.96 28	99.90 50	99.61 234	99.41 343	99.51 59	99.95 80	99.66 69	99.89 172	98.96 412

mamv4		99.73 52	99.74 53	99.70 131	99.66 227	99.87 15	99.69 45	99.93 39	99.93 43	99.93 53	99.86 63	99.07 129	100.00 1	99.66 69	99.92 144	99.24 345

KinetiMVS		99.66 76	99.63 81	99.76 85	99.89 39	99.57 163	99.37 138	99.82 103	99.95 32	99.90 68	99.63 249	98.57 210	99.97 44	99.65 71	99.94 126	99.74 89

pmmvs6		99.86 10	99.86 13	99.83 41	99.94 18	99.90 7	99.83 7	99.91 52	99.85 72	99.94 48	99.95 16	99.73 27	99.90 197	99.65 71	99.97 73	99.69 116

MIMVSNet1		99.66 76	99.62 83	99.80 64	99.94 18	99.87 15	99.69 45	99.77 146	99.78 103	99.93 53	99.89 41	97.94 286	99.92 149	99.65 71	99.98 50	99.62 185

LuminaMVS		99.39 167	99.28 185	99.73 112	99.83 83	99.49 178	99.00 285	99.05 403	99.81 92	99.89 73	99.79 118	96.54 349	99.97 44	99.64 74	99.98 50	99.73 93

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 81	99.92 149	99.64 74	99.94 126	99.68 123

EC-MVSNet		99.69 60	99.69 61	99.68 138	99.71 189	99.91 4	99.76 23	99.96 28	99.86 66	99.51 275	99.39 351	99.57 50	99.93 118	99.64 74	99.86 203	99.20 358

K. test v3		98.87 298	98.60 308	99.69 136	99.93 24	99.46 188	99.74 27	94.97 477	99.78 103	99.88 83	99.88 50	93.66 397	99.97 44	99.61 77	99.95 110	99.64 167

KD-MVS_self_test		99.63 84	99.59 93	99.76 85	99.84 75	99.90 7	99.37 138	99.79 130	99.83 82	99.88 83	99.85 69	98.42 238	99.90 197	99.60 78	99.73 285	99.49 267

Anonymous20240521		99.44 149	99.42 143	99.49 236	99.89 39	98.96 297	99.62 67	99.76 154	99.85 72	99.82 109	99.88 50	96.39 356	99.97 44	99.59 79	99.98 50	99.55 227

TransMVSNet (Re)		99.78 37	99.77 45	99.81 54	99.91 31	99.85 22	99.75 25	99.86 76	99.70 124	99.91 63	99.89 41	99.60 43	99.87 249	99.59 79	99.74 279	99.71 102

OurMVSNet-221017-0		99.75 49	99.71 57	99.84 38	99.96 7	99.83 35	99.83 7	99.85 82	99.80 96	99.93 53	99.93 22	98.54 218	99.93 118	99.59 79	99.98 50	99.76 84

EU-MVSNet		99.39 167	99.62 83	98.72 390	99.88 45	96.44 434	99.56 87	99.85 82	99.90 50	99.90 68	99.85 69	98.09 274	99.83 319	99.58 82	99.95 110	99.90 29

mvs_anonymous		99.28 195	99.39 148	98.94 360	99.19 394	97.81 395	99.02 274	99.55 281	99.78 103	99.85 99	99.80 107	98.24 258	99.86 268	99.57 83	99.50 364	99.15 370

test1111		97.74 383	98.16 355	96.49 459	99.60 242	89.86 490	99.71 37	91.21 486	99.89 56	99.88 83	99.87 56	93.73 396	99.90 197	99.56 84	99.99 16	99.70 105

lessismore_v0				99.64 163	99.86 58	99.38 216		90.66 487		99.89 73	99.83 84	94.56 387	99.97 44	99.56 84	99.92 144	99.57 220

mvsany_test1		99.44 149	99.45 135	99.40 271	99.37 344	98.64 333	97.90 435	99.59 259	99.27 232	99.92 60	99.82 91	99.74 26	99.93 118	99.55 86	99.87 195	99.63 173

MVSMamba_PlusPlus		99.55 109	99.58 97	99.47 243	99.68 218	99.40 211	99.52 93	99.70 190	99.92 46	99.77 145	99.86 63	98.28 254	99.96 69	99.54 87	99.90 158	99.05 399

pm-mvs1		99.79 34	99.79 34	99.78 75	99.91 31	99.83 35	99.76 23	99.87 70	99.73 109	99.89 73	99.87 56	99.63 37	99.87 249	99.54 87	99.92 144	99.63 173

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 43	99.90 50	99.97 24	99.87 56	99.81 20	99.95 80	99.54 87	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
DSMNet-mixed		99.48 129	99.65 73	98.95 359	99.71 189	97.27 415	99.50 101	99.82 103	99.59 165	99.41 302	99.85 69	99.62 40	100.00 1	99.53 90	99.89 172	99.59 209

test2506		94.73 449	94.59 449	95.15 466	99.59 248	85.90 492	99.75 25	74.01 494	99.89 56	99.71 182	99.86 63	79.00 479	99.90 197	99.52 91	99.99 16	99.65 155

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 181	99.93 43	99.95 45	99.89 41	99.71 28	99.96 69	99.51 92	99.97 73	99.84 52

FC-MVSNet-test		99.70 58	99.65 73	99.86 30	99.88 45	99.86 19	99.72 33	99.78 140	99.90 50	99.82 109	99.83 84	98.45 234	99.87 249	99.51 92	99.97 73	99.86 46

BP-MVS1		98.72 314	98.46 324	99.50 232	99.53 287	99.00 289	99.34 146	98.53 429	99.65 143	99.73 172	99.38 353	90.62 435	99.96 69	99.50 94	99.86 203	99.55 227

UA-Net		99.78 37	99.76 49	99.86 30	99.72 185	99.71 100	99.91 4	99.95 36	99.96 28	99.71 182	99.91 31	99.15 110	99.97 44	99.50 94	100.00 1	99.90 29

viewdifsd2359ckpt11		99.62 91	99.64 78	99.56 207	99.86 58	99.19 263	99.02 274	99.93 39	99.83 82	99.88 83	99.81 98	98.99 147	99.83 319	99.48 96	99.96 87	99.65 155

viewmsd2359difaftdt		99.62 91	99.64 78	99.56 207	99.86 58	99.19 263	99.02 274	99.93 39	99.83 82	99.88 83	99.81 98	98.99 147	99.83 319	99.48 96	99.96 87	99.65 155

PMMVS2		99.48 129	99.45 135	99.57 203	99.76 152	98.99 291	98.09 412	99.90 58	98.95 282	99.78 133	99.58 289	99.57 50	99.93 118	99.48 96	99.95 110	99.79 73

VPA-MVSNet		99.66 76	99.62 83	99.79 71	99.68 218	99.75 79	99.62 67	99.69 198	99.85 72	99.80 123	99.81 98	98.81 173	99.91 178	99.47 99	99.88 182	99.70 105

GDP-MVS		98.81 305	98.57 314	99.50 232	99.53 287	99.12 274	99.28 172	99.86 76	99.53 174	99.57 245	99.32 370	90.88 431	99.98 27	99.46 100	99.74 279	99.42 303

ECVR-MVS		97.73 384	98.04 362	96.78 452	99.59 248	90.81 485	99.72 33	90.43 488	99.89 56	99.86 96	99.86 63	93.60 398	99.89 219	99.46 100	99.99 16	99.65 155

nrg030		99.70 58	99.66 71	99.82 46	99.76 152	99.84 27	99.61 73	99.70 190	99.93 43	99.78 133	99.68 214	99.10 120	99.78 365	99.45 102	99.96 87	99.83 56

FE-MVSNET2		99.68 65	99.67 65	99.72 120	99.86 58	99.68 115	99.46 115	99.88 66	99.62 152	99.87 93	99.85 69	99.06 136	99.85 287	99.44 103	99.98 50	99.63 173

TAMVS		99.49 127	99.45 135	99.63 170	99.48 312	99.42 203	99.45 116	99.57 270	99.66 140	99.78 133	99.83 84	97.85 293	99.86 268	99.44 103	99.96 87	99.61 198

GeoE		99.69 60	99.66 71	99.78 75	99.76 152	99.76 71	99.60 79	99.82 103	99.46 192	99.75 157	99.56 300	99.63 37	99.95 80	99.43 105	99.88 182	99.62 185

new-patchmatchnet		99.35 180	99.57 102	98.71 392	99.82 92	96.62 430	98.55 367	99.75 159	99.50 179	99.88 83	99.87 56	99.31 86	99.88 234	99.43 105	100.00 1	99.62 185

test20.03		99.55 109	99.54 112	99.58 195	99.79 127	99.37 220	99.02 274	99.89 61	99.60 163	99.82 109	99.62 258	98.81 173	99.89 219	99.43 105	99.86 203	99.47 275

MVSFormer		99.41 161	99.44 139	99.31 301	99.57 264	98.40 354	99.77 19	99.80 121	99.73 109	99.63 218	99.30 375	98.02 279	99.98 27	99.43 105	99.69 304	99.55 227

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 27	99.77 19	99.80 121	99.73 109	99.97 24	99.92 27	99.77 25	99.98 27	99.43 105	100.00 1	99.90 29

SDMVSNet		99.77 44	99.77 45	99.76 85	99.80 113	99.65 126	99.63 64	99.86 76	99.97 25	99.89 73	99.89 41	99.52 58	99.99 8	99.42 110	99.96 87	99.65 155

Anonymous20231211		99.62 91	99.57 102	99.76 85	99.61 240	99.60 153	99.81 13	99.73 169	99.82 86	99.90 68	99.90 36	97.97 285	99.86 268	99.42 110	99.96 87	99.80 65

SixPastTwentyTwo		99.42 155	99.30 177	99.76 85	99.92 29	99.67 118	99.70 38	99.14 396	99.65 143	99.89 73	99.90 36	96.20 363	99.94 97	99.42 110	99.92 144	99.67 132

balanced_conf03		99.50 122	99.50 121	99.50 232	99.42 335	99.49 178	99.52 93	99.75 159	99.86 66	99.78 133	99.71 183	98.20 266	99.90 197	99.39 113	99.88 182	99.10 381

patch_mono-2		99.51 120	99.46 133	99.64 163	99.70 204	99.11 275	99.04 267	99.87 70	99.71 118	99.47 283	99.79 118	98.24 258	99.98 27	99.38 114	99.96 87	99.83 56

UGNet		99.38 170	99.34 165	99.49 236	98.90 433	98.90 306	99.70 38	99.35 353	99.86 66	98.57 417	99.81 98	98.50 229	99.93 118	99.38 114	99.98 50	99.66 146
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
XXY-MVS		99.71 57	99.67 65	99.81 54	99.89 39	99.72 95	99.59 80	99.82 103	99.39 213	99.82 109	99.84 77	99.38 73	99.91 178	99.38 114	99.93 138	99.80 65

FIs		99.65 82	99.58 97	99.84 38	99.84 75	99.85 22	99.66 57	99.75 159	99.86 66	99.74 167	99.79 118	98.27 256	99.85 287	99.37 117	99.93 138	99.83 56

sd_testset		99.78 37	99.78 39	99.80 64	99.80 113	99.76 71	99.80 14	99.79 130	99.97 25	99.89 73	99.89 41	99.53 56	99.99 8	99.36 118	99.96 87	99.65 155

anonymousdsp		99.80 30	99.77 45	99.90 8	99.96 7	99.88 12	99.73 30	99.85 82	99.70 124	99.92 60	99.93 22	99.45 61	99.97 44	99.36 118	100.00 1	99.85 49

casdiffmvs_mvg		99.68 65	99.68 64	99.69 136	99.81 104	99.59 155	99.29 170	99.90 58	99.71 118	99.79 129	99.73 165	99.54 53	99.84 303	99.36 118	99.96 87	99.65 155
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		99.75 49	99.74 53	99.79 71	99.88 45	99.66 120	99.69 45	99.92 43	99.67 136	99.77 145	99.75 155	99.61 41	99.98 27	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
dcpmvs_2		99.61 95	99.64 78	99.53 224	99.79 127	98.82 312	99.58 82	99.97 20	99.95 32	99.96 34	99.76 147	98.44 235	99.99 8	99.34 122	99.96 87	99.78 75

CHOSEN 1792x2688		99.39 167	99.30 177	99.65 156	99.88 45	99.25 246	98.78 337	99.88 66	98.66 324	99.96 34	99.79 118	97.45 315	99.93 118	99.34 122	99.99 16	99.78 75

CDS-MVSNet		99.22 217	99.13 210	99.50 232	99.35 351	99.11 275	98.96 301	99.54 287	99.46 192	99.61 234	99.70 193	96.31 359	99.83 319	99.34 122	99.88 182	99.55 227
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 278	99.16 203	98.51 400	99.75 168	95.90 446	98.07 415	99.84 89	99.84 76	99.89 73	99.73 165	96.01 367	99.99 8	99.33 125	100.00 1	99.63 173

HyFIR lowres test		98.91 291	98.64 305	99.73 112	99.85 70	99.47 182	98.07 415	99.83 97	98.64 327	99.89 73	99.60 276	92.57 409	100.00 1	99.33 125	99.97 73	99.72 97

pmmvs5		99.19 227	99.11 217	99.42 260	99.76 152	98.88 308	98.55 367	99.73 169	98.82 303	99.72 177	99.62 258	96.56 346	99.82 335	99.32 127	99.95 110	99.56 223

v148		99.40 163	99.41 146	99.39 274	99.76 152	98.94 299	99.09 252	99.59 259	99.17 253	99.81 116	99.61 268	98.41 239	99.69 414	99.32 127	99.94 126	99.53 243

baseline		99.63 84	99.62 83	99.66 149	99.80 113	99.62 140	99.44 118	99.80 121	99.71 118	99.72 177	99.69 202	99.15 110	99.83 319	99.32 127	99.94 126	99.53 243

CVMVSNet		98.61 322	98.88 283	97.80 431	99.58 254	93.60 469	99.26 181	99.64 229	99.66 140	99.72 177	99.67 218	93.26 402	99.93 118	99.30 130	99.81 241	99.87 44

PS-CasMVS		99.66 76	99.58 97	99.89 11	99.80 113	99.85 22	99.66 57	99.73 169	99.62 152	99.84 102	99.71 183	98.62 203	99.96 69	99.30 130	99.96 87	99.86 46

DTE-MVSNet		99.68 65	99.61 87	99.88 19	99.80 113	99.87 15	99.67 53	99.71 181	99.72 113	99.84 102	99.78 130	98.67 197	99.97 44	99.30 130	99.95 110	99.80 65

tmp_tt		95.75 441	95.42 436	96.76 453	89.90 493	94.42 463	98.86 318	97.87 456	78.01 484	99.30 334	99.69 202	97.70 301	95.89 486	99.29 133	98.14 460	99.95 14

PEN-MVS		99.66 76	99.59 93	99.89 11	99.83 83	99.87 15	99.66 57	99.73 169	99.70 124	99.84 102	99.73 165	98.56 213	99.96 69	99.29 133	99.94 126	99.83 56

WR-MVS_H		99.61 95	99.53 116	99.87 26	99.80 113	99.83 35	99.67 53	99.75 159	99.58 167	99.85 99	99.69 202	98.18 269	99.94 97	99.28 135	99.95 110	99.83 56

IterMVS		98.97 282	99.16 203	98.42 405	99.74 176	95.64 450	98.06 417	99.83 97	99.83 82	99.85 99	99.74 160	96.10 366	99.99 8	99.27 136	100.00 1	99.63 173
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
NormalMVS		99.09 255	98.91 281	99.62 179	99.78 135	99.11 275	99.36 142	99.77 146	99.82 86	99.68 194	99.53 312	93.30 400	99.99 8	99.24 137	99.76 268	99.74 89

SymmetryMVS		99.01 275	98.82 291	99.58 195	99.65 232	99.11 275	99.36 142	99.20 389	99.82 86	99.68 194	99.53 312	93.30 400	99.99 8	99.24 137	99.63 325	99.64 167

WBMVS		97.50 394	97.18 400	98.48 402	98.85 441	95.89 447	98.44 384	99.52 302	99.53 174	99.52 268	99.42 342	80.10 472	99.86 268	99.24 137	99.95 110	99.68 123

h-mvs33		98.61 322	98.34 338	99.44 254	99.60 242	98.67 325	99.27 176	99.44 328	99.68 129	99.32 324	99.49 325	92.50 412	100.00 1	99.24 137	96.51 478	99.65 155

hse-mvs2		98.52 335	98.30 343	99.16 330	99.29 373	98.60 336	98.77 338	99.02 405	99.68 129	99.32 324	99.04 416	92.50 412	99.85 287	99.24 137	97.87 467	99.03 403

FMVSNet1		99.66 76	99.63 81	99.73 112	99.78 135	99.77 64	99.68 49	99.70 190	99.67 136	99.82 109	99.83 84	98.98 151	99.90 197	99.24 137	99.97 73	99.53 243

casdiffmvs		99.63 84	99.61 87	99.67 142	99.79 127	99.59 155	99.13 234	99.85 82	99.79 100	99.76 152	99.72 173	99.33 84	99.82 335	99.21 143	99.94 126	99.59 209
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CP-MVSNet		99.54 113	99.43 141	99.87 26	99.76 152	99.82 43	99.57 85	99.61 242	99.54 172	99.80 123	99.64 234	97.79 297	99.95 80	99.21 143	99.94 126	99.84 52

DELS-MVS		99.34 185	99.30 177	99.48 241	99.51 296	99.36 224	98.12 408	99.53 297	99.36 218	99.41 302	99.61 268	99.22 100	99.87 249	99.21 143	99.68 309	99.20 358
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
viewmambaseed2359dif		99.47 139	99.50 121	99.37 280	99.70 204	98.80 316	98.67 348	99.92 43	99.49 181	99.77 145	99.71 183	99.08 126	99.78 365	99.20 146	99.94 126	99.54 237

UniMVSNet (Re)		99.37 174	99.26 190	99.68 138	99.51 296	99.58 160	98.98 295	99.60 253	99.43 204	99.70 186	99.36 361	97.70 301	99.88 234	99.20 146	99.87 195	99.59 209

CANet		99.11 251	99.05 240	99.28 309	98.83 443	98.56 339	98.71 346	99.41 334	99.25 236	99.23 343	99.22 393	97.66 309	99.94 97	99.19 148	99.97 73	99.33 326

EI-MVSNet-UG-set		99.48 129	99.50 121	99.42 260	99.57 264	98.65 331	99.24 188	99.46 322	99.68 129	99.80 123	99.66 223	98.99 147	99.89 219	99.19 148	99.90 158	99.72 97

xiu_mvs_v1_base_debu		99.23 208	99.34 165	98.91 367	99.59 248	98.23 363	98.47 379	99.66 211	99.61 157	99.68 194	98.94 432	99.39 69	99.97 44	99.18 150	99.55 350	98.51 451

xiu_mvs_v1_base		99.23 208	99.34 165	98.91 367	99.59 248	98.23 363	98.47 379	99.66 211	99.61 157	99.68 194	98.94 432	99.39 69	99.97 44	99.18 150	99.55 350	98.51 451

xiu_mvs_v1_base_debi		99.23 208	99.34 165	98.91 367	99.59 248	98.23 363	98.47 379	99.66 211	99.61 157	99.68 194	98.94 432	99.39 69	99.97 44	99.18 150	99.55 350	98.51 451

VPNet		99.46 141	99.37 154	99.71 126	99.82 92	99.59 155	99.48 108	99.70 190	99.81 92	99.69 189	99.58 289	97.66 309	99.86 268	99.17 153	99.44 371	99.67 132

UniMVSNet_NR-MVSNet		99.37 174	99.25 192	99.72 120	99.47 318	99.56 164	98.97 297	99.61 242	99.43 204	99.67 201	99.28 379	97.85 293	99.95 80	99.17 153	99.81 241	99.65 155

DU-MVS		99.33 188	99.21 197	99.71 126	99.43 330	99.56 164	98.83 325	99.53 297	99.38 214	99.67 201	99.36 361	97.67 305	99.95 80	99.17 153	99.81 241	99.63 173

EI-MVSNet-Vis-set		99.47 139	99.49 125	99.42 260	99.57 264	98.66 328	99.24 188	99.46 322	99.67 136	99.79 129	99.65 232	98.97 153	99.89 219	99.15 156	99.89 172	99.71 102

EI-MVSNet		99.38 170	99.44 139	99.21 324	99.58 254	98.09 377	99.26 181	99.46 322	99.62 152	99.75 157	99.67 218	98.54 218	99.85 287	99.15 156	99.92 144	99.68 123

VNet		99.18 231	99.06 235	99.56 207	99.24 384	99.36 224	99.33 152	99.31 363	99.67 136	99.47 283	99.57 296	96.48 350	99.84 303	99.15 156	99.30 390	99.47 275

EG-PatchMatch MVS		99.57 100	99.56 107	99.62 179	99.77 148	99.33 230	99.26 181	99.76 154	99.32 223	99.80 123	99.78 130	99.29 88	99.87 249	99.15 156	99.91 156	99.66 146

PVSNet_Blended_VisFu		99.40 163	99.38 151	99.44 254	99.90 37	98.66 328	98.94 306	99.91 52	97.97 388	99.79 129	99.73 165	99.05 138	99.97 44	99.15 156	99.99 16	99.68 123

IterMVS-LS		99.41 161	99.47 128	99.25 320	99.81 104	98.09 377	98.85 320	99.76 154	99.62 152	99.83 108	99.64 234	98.54 218	99.97 44	99.15 156	99.99 16	99.68 123
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 113	99.47 128	99.76 85	99.58 254	99.64 132	99.30 163	99.63 232	99.61 157	99.71 182	99.56 300	98.76 183	99.96 69	99.14 162	99.92 144	99.68 123

MVSTER		98.47 342	98.22 348	99.24 322	99.06 417	98.35 360	99.08 255	99.46 322	99.27 232	99.75 157	99.66 223	88.61 448	99.85 287	99.14 162	99.92 144	99.52 254

E6new		99.68 65	99.67 65	99.70 131	99.86 58	99.62 140	99.41 121	99.84 89	99.68 129	99.77 145	99.81 98	99.59 45	99.78 365	99.13 164	99.96 87	99.70 105

E6		99.68 65	99.67 65	99.70 131	99.86 58	99.62 140	99.41 121	99.84 89	99.68 129	99.77 145	99.81 98	99.59 45	99.78 365	99.13 164	99.96 87	99.70 105

E5		99.68 65	99.67 65	99.70 131	99.87 54	99.62 140	99.41 121	99.84 89	99.68 129	99.77 145	99.81 98	99.59 45	99.78 365	99.13 164	99.96 87	99.70 105

diffmvs_AUTHOR		99.48 129	99.48 126	99.47 243	99.80 113	98.89 307	98.71 346	99.82 103	99.79 100	99.66 207	99.63 249	98.87 169	99.88 234	99.13 164	99.95 110	99.62 185

Anonymous20231206		99.35 180	99.31 172	99.47 243	99.74 176	99.06 287	99.28 172	99.74 165	99.23 240	99.72 177	99.53 312	97.63 311	99.88 234	99.11 168	99.84 213	99.48 271

Syy-MVS		98.17 367	97.85 379	99.15 332	98.50 466	98.79 317	98.60 355	99.21 386	97.89 395	96.76 471	96.37 494	95.47 376	99.57 457	99.10 169	98.73 436	99.09 386

ttmdpeth		99.48 129	99.55 109	99.29 306	99.76 152	98.16 371	99.33 152	99.95 36	99.79 100	99.36 313	99.89 41	99.13 115	99.77 377	99.09 170	99.64 322	99.93 20

MVS_Test		99.28 195	99.31 172	99.19 327	99.35 351	98.79 317	99.36 142	99.49 315	99.17 253	99.21 348	99.67 218	98.78 180	99.66 436	99.09 170	99.66 318	99.10 381

FE-MVSNET3		98.87 298	98.71 300	99.35 287	99.59 248	98.88 308	97.17 467	99.64 229	98.94 283	99.27 336	99.22 393	95.57 373	99.83 319	99.08 172	99.92 144	99.35 321

testgi		99.29 194	99.26 190	99.37 280	99.75 168	98.81 313	98.84 322	99.89 61	98.38 355	99.75 157	99.04 416	99.36 78	99.86 268	99.08 172	99.25 398	99.45 280

1112_ss		99.05 263	98.84 288	99.67 142	99.66 227	99.29 236	98.52 373	99.82 103	97.65 407	99.43 293	99.16 400	96.42 353	99.91 178	99.07 174	99.84 213	99.80 65

CANet_DTU		98.91 291	98.85 286	99.09 341	98.79 449	98.13 372	98.18 400	99.31 363	99.48 184	98.86 388	99.51 318	96.56 346	99.95 80	99.05 175	99.95 110	99.19 361

Baseline_NR-MVSNet		99.49 127	99.37 154	99.82 46	99.91 31	99.84 27	98.83 325	99.86 76	99.68 129	99.65 210	99.88 50	97.67 305	99.87 249	99.03 176	99.86 203	99.76 84

FMVSNet2		99.35 180	99.28 185	99.55 214	99.49 307	99.35 227	99.45 116	99.57 270	99.44 197	99.70 186	99.74 160	97.21 326	99.87 249	99.03 176	99.94 126	99.44 293

Test_1112_low_res		98.95 288	98.73 298	99.63 170	99.68 218	99.15 271	98.09 412	99.80 121	97.14 433	99.46 287	99.40 347	96.11 364	99.89 219	99.01 178	99.84 213	99.84 52

VDD-MVS		99.20 224	99.11 217	99.44 254	99.43 330	98.98 292	99.50 101	98.32 443	99.80 96	99.56 253	99.69 202	96.99 336	99.85 287	98.99 179	99.73 285	99.50 262

DeepC-MVS	98.90 4	99.62 91	99.61 87	99.67 142	99.72 185	99.44 196	99.24 188	99.71 181	99.27 232	99.93 53	99.90 36	99.70 31	99.93 118	98.99 179	99.99 16	99.64 167
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
pmmvs-eth3d		99.48 129	99.47 128	99.51 230	99.77 148	99.41 210	98.81 330	99.66 211	99.42 208	99.75 157	99.66 223	99.20 102	99.76 381	98.98 181	99.99 16	99.36 318

EPNet_dtu		97.62 389	97.79 382	97.11 451	96.67 488	92.31 474	98.51 374	98.04 450	99.24 238	95.77 480	99.47 332	93.78 395	99.66 436	98.98 181	99.62 327	99.37 315
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 185	99.32 170	99.39 274	99.67 225	98.77 319	98.57 364	99.81 116	99.61 157	99.48 281	99.41 343	98.47 230	99.86 268	98.97 183	99.90 158	99.53 243
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NR-MVSNet		99.40 163	99.31 172	99.68 138	99.43 330	99.55 168	99.73 30	99.50 311	99.46 192	99.88 83	99.36 361	97.54 312	99.87 249	98.97 183	99.87 195	99.63 173

TestfortrainingZip a		99.61 95	99.53 116	99.85 32	99.76 152	99.84 27	99.38 130	99.78 140	99.58 167	99.81 116	99.66 223	99.02 142	99.90 197	98.96 185	99.79 253	99.81 64

viewdifsd2359ckpt07		99.51 120	99.50 121	99.52 226	99.80 113	99.19 263	98.92 310	99.88 66	99.72 113	99.64 213	99.62 258	99.06 136	99.81 351	98.96 185	99.94 126	99.56 223

GBi-Net		99.42 155	99.31 172	99.73 112	99.49 307	99.77 64	99.68 49	99.70 190	99.44 197	99.62 228	99.83 84	97.21 326	99.90 197	98.96 185	99.90 158	99.53 243

FMVSNet5		97.80 381	97.25 398	99.42 260	98.83 443	98.97 295	99.38 130	99.80 121	98.87 295	99.25 339	99.69 202	80.60 471	99.91 178	98.96 185	99.90 158	99.38 312

test1		99.42 155	99.31 172	99.73 112	99.49 307	99.77 64	99.68 49	99.70 190	99.44 197	99.62 228	99.83 84	97.21 326	99.90 197	98.96 185	99.90 158	99.53 243

FMVSNet3		98.80 306	98.63 307	99.32 297	99.13 403	98.72 322	99.10 247	99.48 316	99.23 240	99.62 228	99.64 234	92.57 409	99.86 268	98.96 185	99.90 158	99.39 310

UnsupCasMVSNet_eth		98.83 302	98.57 314	99.59 192	99.68 218	99.45 194	98.99 292	99.67 206	99.48 184	99.55 258	99.36 361	94.92 380	99.86 268	98.95 191	96.57 476	99.45 280

CHOSEN 280x420		98.41 347	98.41 330	98.40 406	99.34 360	95.89 447	96.94 473	99.44 328	98.80 307	99.25 339	99.52 316	93.51 399	99.98 27	98.94 192	99.98 50	99.32 330

E4		99.61 95	99.59 93	99.66 149	99.84 75	99.53 171	99.08 255	99.84 89	99.65 143	99.74 167	99.80 107	99.45 61	99.77 377	98.93 193	99.95 110	99.69 116

TDRefinement		99.72 54	99.70 58	99.77 78	99.90 37	99.85 22	99.86 6	99.92 43	99.69 127	99.78 133	99.92 27	99.37 75	99.88 234	98.93 193	99.95 110	99.60 202

viewmacassd2359aftdt		99.63 84	99.61 87	99.68 138	99.84 75	99.61 149	99.14 227	99.87 70	99.71 118	99.75 157	99.77 140	99.54 53	99.72 398	98.91 195	99.96 87	99.70 105

alignmvs		98.28 357	97.96 368	99.25 320	99.12 405	98.93 302	99.03 270	98.42 436	99.64 147	98.72 403	97.85 471	90.86 432	99.62 448	98.88 196	99.13 404	99.19 361

testing3-2		96.51 420	96.43 415	96.74 455	99.36 347	91.38 482	99.10 247	97.87 456	99.48 184	98.57 417	98.71 447	76.65 482	99.66 436	98.87 197	99.26 397	99.18 363

MGCFI-Net		99.02 269	99.01 253	99.06 348	99.11 410	98.60 336	99.63 64	99.67 206	99.63 149	98.58 415	97.65 474	99.07 129	99.57 457	98.85 198	98.92 420	99.03 403

sss		98.90 293	98.77 297	99.27 314	99.48 312	98.44 351	98.72 344	99.32 359	97.94 392	99.37 312	99.35 366	96.31 359	99.91 178	98.85 198	99.63 325	99.47 275

xiu_mvs_v2_base		99.02 269	99.11 217	98.77 387	99.37 344	98.09 377	98.13 407	99.51 307	99.47 189	99.42 296	98.54 456	99.38 73	99.97 44	98.83 200	99.33 386	98.24 463

PS-MVSNAJ		99.00 278	99.08 229	98.76 388	99.37 344	98.10 376	98.00 423	99.51 307	99.47 189	99.41 302	98.50 458	99.28 90	99.97 44	98.83 200	99.34 385	98.20 467

E2		99.54 113	99.51 119	99.62 179	99.78 135	99.47 182	99.01 279	99.82 103	99.55 170	99.69 189	99.77 140	99.26 94	99.76 381	98.82 202	99.93 138	99.62 185

E3		99.54 113	99.51 119	99.62 179	99.78 135	99.47 182	99.01 279	99.82 103	99.55 170	99.69 189	99.77 140	99.25 98	99.76 381	98.82 202	99.93 138	99.62 185

D2MVS		99.22 217	99.19 200	99.29 306	99.69 210	98.74 321	98.81 330	99.41 334	98.55 336	99.68 194	99.69 202	98.13 271	99.87 249	98.82 202	99.98 50	99.24 345

PatchT		98.45 344	98.32 340	98.83 381	98.94 431	98.29 361	99.24 188	98.82 413	99.84 76	99.08 365	99.76 147	91.37 421	99.94 97	98.82 202	99.00 415	98.26 462

testf1		99.63 84	99.60 91	99.72 120	99.94 18	99.95 2	99.47 111	99.89 61	99.43 204	99.88 83	99.80 107	99.26 94	99.90 197	98.81 206	99.88 182	99.32 330

APD_test2		99.63 84	99.60 91	99.72 120	99.94 18	99.95 2	99.47 111	99.89 61	99.43 204	99.88 83	99.80 107	99.26 94	99.90 197	98.81 206	99.88 182	99.32 330

usedtu_blend_shiyan5		97.97 377	97.65 389	98.92 364	97.71 484	97.49 406	99.53 91	99.81 116	99.52 178	98.18 434	96.82 488	91.92 415	99.83 319	98.79 208	96.53 477	99.45 280

blend_shiyan4		95.04 448	93.76 452	98.88 376	97.92 480	97.49 406	97.72 441	99.34 355	97.93 393	97.65 460	97.11 482	77.69 480	99.83 319	98.79 208	79.72 487	99.33 326

sasdasda		99.02 269	99.00 257	99.09 341	99.10 412	98.70 323	99.61 73	99.66 211	99.63 149	98.64 409	97.65 474	99.04 139	99.54 461	98.79 208	98.92 420	99.04 401

Effi-MVS+		99.06 260	98.97 268	99.34 289	99.31 367	98.98 292	98.31 392	99.91 52	98.81 305	98.79 397	98.94 432	99.14 113	99.84 303	98.79 208	98.74 433	99.20 358

canonicalmvs		99.02 269	99.00 257	99.09 341	99.10 412	98.70 323	99.61 73	99.66 211	99.63 149	98.64 409	97.65 474	99.04 139	99.54 461	98.79 208	98.92 420	99.04 401

VDDNet		98.97 282	98.82 291	99.42 260	99.71 189	98.81 313	99.62 67	98.68 420	99.81 92	99.38 310	99.80 107	94.25 389	99.85 287	98.79 208	99.32 388	99.59 209

CR-MVSNet		98.35 354	98.20 350	98.83 381	99.05 418	98.12 373	99.30 163	99.67 206	97.39 421	99.16 354	99.79 118	91.87 418	99.91 178	98.78 214	98.77 429	98.44 456

test_method		91.72 450	92.32 453	89.91 469	93.49 492	70.18 495	90.28 484	99.56 275	61.71 487	95.39 482	99.52 316	93.90 391	99.94 97	98.76 215	98.27 453	99.62 185

RPMNet		98.60 325	98.53 320	98.83 381	99.05 418	98.12 373	99.30 163	99.62 235	99.86 66	99.16 354	99.74 160	92.53 411	99.92 149	98.75 216	98.77 429	98.44 456

mamba_0408		99.54 113	99.55 109	99.54 220	99.71 189	99.24 250	99.27 176	99.79 130	99.72 113	99.78 133	99.64 234	99.36 78	99.93 118	98.74 217	99.90 158	99.45 280

SSM_04072		99.55 109	99.55 109	99.55 214	99.71 189	99.24 250	99.27 176	99.79 130	99.72 113	99.78 133	99.64 234	99.36 78	99.97 44	98.74 217	99.90 158	99.45 280

SSM_0407		99.56 104	99.56 107	99.54 220	99.71 189	99.24 250	99.15 223	99.84 89	99.80 96	99.78 133	99.70 193	99.44 63	99.93 118	98.74 217	99.90 158	99.45 280

SSM_0404		99.57 100	99.58 97	99.54 220	99.76 152	99.28 238	99.19 205	99.84 89	99.80 96	99.78 133	99.70 193	99.44 63	99.93 118	98.74 217	99.95 110	99.41 304

pmmvs4		99.13 244	99.06 235	99.36 285	99.57 264	99.10 282	98.01 421	99.25 376	98.78 310	99.58 242	99.44 339	98.24 258	99.76 381	98.74 217	99.93 138	99.22 351

viewmanbaseed2359cas		99.50 122	99.47 128	99.61 185	99.73 180	99.52 175	99.03 270	99.83 97	99.49 181	99.65 210	99.64 234	99.18 104	99.71 403	98.73 222	99.92 144	99.58 214

tttt0517		97.62 389	97.20 399	98.90 373	99.76 152	97.40 412	99.48 108	94.36 479	99.06 270	99.70 186	99.49 325	84.55 464	99.94 97	98.73 222	99.65 320	99.36 318

viewcassd2359sk11		99.48 129	99.45 135	99.58 195	99.73 180	99.42 203	98.96 301	99.80 121	99.44 197	99.63 218	99.74 160	99.09 122	99.76 381	98.72 224	99.91 156	99.57 220

EPP-MVSNet		99.17 236	99.00 257	99.66 149	99.80 113	99.43 200	99.70 38	99.24 379	99.48 184	99.56 253	99.77 140	94.89 381	99.93 118	98.72 224	99.89 172	99.63 173

FE-MVSNET		99.45 145	99.36 159	99.71 126	99.84 75	99.64 132	99.16 220	99.91 52	98.65 325	99.73 172	99.73 165	98.54 218	99.82 335	98.71 226	99.96 87	99.67 132

Anonymous20240529		99.42 155	99.34 165	99.65 156	99.53 287	99.60 153	99.63 64	99.39 344	99.47 189	99.76 152	99.78 130	98.13 271	99.86 268	98.70 227	99.68 309	99.49 267

ACMH	98.42 6	99.59 99	99.54 112	99.72 120	99.86 58	99.62 140	99.56 87	99.79 130	98.77 312	99.80 123	99.85 69	99.64 35	99.85 287	98.70 227	99.89 172	99.70 105
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 188	99.28 185	99.47 243	99.57 264	99.39 214	99.78 17	99.43 331	98.87 295	99.57 245	99.82 91	98.06 277	99.87 249	98.69 229	99.73 285	99.15 370

LFMVS		98.46 343	98.19 353	99.26 317	99.24 384	98.52 347	99.62 67	96.94 468	99.87 63	99.31 329	99.58 289	91.04 426	99.81 351	98.68 230	99.42 375	99.45 280

WR-MVS		99.11 251	98.93 273	99.66 149	99.30 371	99.42 203	98.42 385	99.37 349	99.04 271	99.57 245	99.20 398	96.89 338	99.86 268	98.66 231	99.87 195	99.70 105

mvsmamba		99.08 256	98.95 271	99.45 250	99.36 347	99.18 268	99.39 127	98.81 414	99.37 215	99.35 315	99.70 193	96.36 358	99.94 97	98.66 231	99.59 341	99.22 351

viewdifsd2359ckpt13		99.42 155	99.37 154	99.57 203	99.72 185	99.46 188	99.01 279	99.80 121	99.20 245	99.51 275	99.60 276	98.92 160	99.70 407	98.65 233	99.90 158	99.55 227

RRT-MVS		99.08 256	99.00 257	99.33 292	99.27 378	98.65 331	99.62 67	99.93 39	99.66 140	99.67 201	99.82 91	95.27 378	99.93 118	98.64 234	99.09 408	99.41 304

E3new		99.42 155	99.37 154	99.56 207	99.68 218	99.38 216	98.93 309	99.79 130	99.30 227	99.55 258	99.69 202	98.88 167	99.76 381	98.63 235	99.89 172	99.53 243

Anonymous202405211		98.75 310	98.46 324	99.63 170	99.34 360	99.66 120	99.47 111	97.65 459	99.28 231	99.56 253	99.50 321	93.15 403	99.84 303	98.62 236	99.58 343	99.40 307

lecture		99.56 104	99.48 126	99.81 54	99.78 135	99.86 19	99.50 101	99.70 190	99.59 165	99.75 157	99.71 183	98.94 156	99.92 149	98.59 237	99.76 268	99.66 146

EPNet		98.13 368	97.77 383	99.18 329	94.57 491	97.99 383	99.24 188	97.96 452	99.74 108	97.29 464	99.62 258	93.13 404	99.97 44	98.59 237	99.83 221	99.58 214
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 263	99.09 227	98.91 367	99.21 389	98.36 359	98.82 329	99.47 319	98.85 298	98.90 383	99.56 300	98.78 180	99.09 477	98.57 239	99.68 309	99.26 342

Patchmatch-RL test		98.60 325	98.36 335	99.33 292	99.77 148	99.07 285	98.27 394	99.87 70	98.91 290	99.74 167	99.72 173	90.57 437	99.79 362	98.55 240	99.85 208	99.11 379

pmmvs3		98.08 371	97.80 380	98.91 367	99.41 337	97.69 401	97.87 436	99.66 211	95.87 452	99.50 278	99.51 318	90.35 439	99.97 44	98.55 240	99.47 368	99.08 392

ETV-MVS		99.18 231	99.18 201	99.16 330	99.34 360	99.28 238	99.12 239	99.79 130	99.48 184	98.93 377	98.55 455	99.40 68	99.93 118	98.51 242	99.52 360	98.28 461

viewdifsd2359ckpt09		99.24 206	99.16 203	99.49 236	99.70 204	99.22 256	98.88 314	99.81 116	98.70 320	99.38 310	99.37 356	98.22 263	99.76 381	98.48 243	99.88 182	99.51 256

jason		99.16 237	99.11 217	99.32 297	99.75 168	98.44 351	98.26 396	99.39 344	98.70 320	99.74 167	99.30 375	98.54 218	99.97 44	98.48 243	99.82 231	99.55 227
jason: jason.
APDe-MVS		99.48 129	99.36 159	99.85 32	99.55 278	99.81 48	99.50 101	99.69 198	98.99 275	99.75 157	99.71 183	98.79 178	99.93 118	98.46 245	99.85 208	99.80 65
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
icg_test_0407_2		99.30 192	99.29 182	99.31 301	99.71 189	98.55 341	98.17 402	99.71 181	99.41 209	99.73 172	99.60 276	99.17 106	99.92 149	98.45 246	99.70 296	99.45 280

IMVS_0407		99.38 170	99.42 143	99.28 309	99.71 189	98.55 341	99.27 176	99.71 181	99.41 209	99.73 172	99.60 276	99.17 106	99.83 319	98.45 246	99.70 296	99.45 280

IMVS_0404		99.23 208	99.20 198	99.32 297	99.71 189	98.55 341	98.57 364	99.71 181	99.41 209	99.52 268	99.60 276	98.12 273	99.95 80	98.45 246	99.70 296	99.45 280

IMVS_0403		99.37 174	99.39 148	99.28 309	99.71 189	98.55 341	99.19 205	99.71 181	99.41 209	99.67 201	99.60 276	99.12 118	99.84 303	98.45 246	99.70 296	99.45 280

CL-MVSNet_self_test		98.71 316	98.56 318	99.15 332	99.22 387	98.66 328	97.14 468	99.51 307	98.09 381	99.54 261	99.27 381	96.87 339	99.74 393	98.43 250	98.96 417	99.03 403

our_test_3		98.85 301	99.09 227	98.13 419	99.66 227	94.90 461	97.72 441	99.58 268	99.07 268	99.64 213	99.62 258	98.19 267	99.93 118	98.41 251	99.95 110	99.55 227

Gipuma		99.57 100	99.59 93	99.49 236	99.98 3	99.71 100	99.72 33	99.84 89	99.81 92	99.94 48	99.78 130	98.91 163	99.71 403	98.41 251	99.95 110	99.05 399
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 400	96.91 409	98.74 389	97.72 483	97.57 403	97.60 448	97.36 465	98.00 384	99.21 348	98.02 467	90.04 442	99.79 362	98.37 253	95.89 482	98.86 426

PM-MVS		99.36 178	99.29 182	99.58 195	99.83 83	99.66 120	98.95 304	99.86 76	98.85 298	99.81 116	99.73 165	98.40 243	99.92 149	98.36 254	99.83 221	99.17 366

baseline1		97.73 384	97.33 395	98.96 357	99.30 371	97.73 399	99.40 125	98.42 436	99.33 222	99.46 287	99.21 396	91.18 424	99.82 335	98.35 255	91.26 485	99.32 330

MVS-HIRNet		97.86 378	98.22 348	96.76 453	99.28 376	91.53 480	98.38 387	92.60 485	99.13 261	99.31 329	99.96 15	97.18 330	99.68 426	98.34 256	99.83 221	99.07 397

GA-MVS		97.99 376	97.68 386	98.93 363	99.52 294	98.04 381	97.19 466	99.05 403	98.32 368	98.81 393	98.97 428	89.89 444	99.41 472	98.33 257	99.05 411	99.34 325

Fast-Effi-MVS+		99.02 269	98.87 284	99.46 247	99.38 342	99.50 177	99.04 267	99.79 130	97.17 431	98.62 411	98.74 446	99.34 82	99.95 80	98.32 258	99.41 376	98.92 419

MDA-MVSNet_test_wron		98.95 288	98.99 264	98.85 377	99.64 233	97.16 418	98.23 398	99.33 357	98.93 287	99.56 253	99.66 223	97.39 319	99.83 319	98.29 259	99.88 182	99.55 227

N_pmnet		98.73 313	98.53 320	99.35 287	99.72 185	98.67 325	98.34 389	94.65 478	98.35 362	99.79 129	99.68 214	98.03 278	99.93 118	98.28 260	99.92 144	99.44 293

ET-MVSNet_ETH3D		96.78 412	96.07 422	98.91 367	99.26 381	97.92 390	97.70 444	96.05 473	97.96 391	92.37 486	98.43 459	87.06 452	99.90 197	98.27 261	97.56 470	98.91 420

thisisatest0530		97.45 395	96.95 406	98.94 360	99.68 218	97.73 399	99.09 252	94.19 481	98.61 332	99.56 253	99.30 375	84.30 466	99.93 118	98.27 261	99.54 355	99.16 368

YYNet1		98.95 288	98.99 264	98.84 379	99.64 233	97.14 420	98.22 399	99.32 359	98.92 289	99.59 240	99.66 223	97.40 317	99.83 319	98.27 261	99.90 158	99.55 227

reproduce_model		99.50 122	99.40 147	99.83 41	99.60 242	99.83 35	99.12 239	99.68 201	99.49 181	99.80 123	99.79 118	99.01 144	99.93 118	98.24 264	99.82 231	99.73 93

ACMM	98.09 11	99.46 141	99.38 151	99.72 120	99.80 113	99.69 112	99.13 234	99.65 221	98.99 275	99.64 213	99.72 173	99.39 69	99.86 268	98.23 265	99.81 241	99.60 202
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 285	98.87 284	99.24 322	99.57 264	98.40 354	98.12 408	99.18 391	98.28 370	99.63 218	99.13 402	98.02 279	99.97 44	98.22 266	99.69 304	99.35 321

3Dnovator	99.15 2	99.43 152	99.36 159	99.65 156	99.39 339	99.42 203	99.70 38	99.56 275	99.23 240	99.35 315	99.80 107	99.17 106	99.95 80	98.21 267	99.84 213	99.59 209

Fast-Effi-MVS+-dtu		99.20 224	99.12 214	99.43 258	99.25 382	99.69 112	99.05 262	99.82 103	99.50 179	98.97 373	99.05 414	98.98 151	99.98 27	98.20 268	99.24 400	98.62 441

MS-PatchMatch		99.00 278	98.97 268	99.09 341	99.11 410	98.19 367	98.76 339	99.33 357	98.49 345	99.44 289	99.58 289	98.21 264	99.69 414	98.20 268	99.62 327	99.39 310

TSAR-MVS + GP.		99.12 247	99.04 246	99.38 277	99.34 360	99.16 269	98.15 404	99.29 367	98.18 377	99.63 218	99.62 258	99.18 104	99.68 426	98.20 268	99.74 279	99.30 336

DP-MVS		99.48 129	99.39 148	99.74 101	99.57 264	99.62 140	99.29 170	99.61 242	99.87 63	99.74 167	99.76 147	98.69 193	99.87 249	98.20 268	99.80 248	99.75 87

MVP-Stereo		99.16 237	99.08 229	99.43 258	99.48 312	99.07 285	99.08 255	99.55 281	98.63 328	99.31 329	99.68 214	98.19 267	99.78 365	98.18 272	99.58 343	99.45 280
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 152	99.30 177	99.80 64	99.83 83	99.81 48	99.52 93	99.70 190	98.35 362	99.51 275	99.50 321	99.31 86	99.88 234	98.18 272	99.84 213	99.69 116

MDA-MVSNet-bldmvs		99.06 260	99.05 240	99.07 346	99.80 113	97.83 394	98.89 313	99.72 178	99.29 228	99.63 218	99.70 193	96.47 351	99.89 219	98.17 274	99.82 231	99.50 262

JIA-IIPM		98.06 372	97.92 375	98.50 401	98.59 462	97.02 422	98.80 333	98.51 431	99.88 61	97.89 448	99.87 56	91.89 417	99.90 197	98.16 275	97.68 469	98.59 444

EIA-MVS		99.12 247	99.01 253	99.45 250	99.36 347	99.62 140	99.34 146	99.79 130	98.41 351	98.84 390	98.89 436	98.75 185	99.84 303	98.15 276	99.51 361	98.89 423

miper_lstm_enhance		98.65 321	98.60 308	98.82 384	99.20 392	97.33 414	97.78 439	99.66 211	99.01 274	99.59 240	99.50 321	94.62 386	99.85 287	98.12 277	99.90 158	99.26 342

reproduce-ours		99.46 141	99.35 163	99.82 46	99.56 275	99.83 35	99.05 262	99.65 221	99.45 195	99.78 133	99.78 130	98.93 157	99.93 118	98.11 278	99.81 241	99.70 105

our_new_method		99.46 141	99.35 163	99.82 46	99.56 275	99.83 35	99.05 262	99.65 221	99.45 195	99.78 133	99.78 130	98.93 157	99.93 118	98.11 278	99.81 241	99.70 105

Effi-MVS+-dtu		99.07 259	98.92 277	99.52 226	98.89 436	99.78 58	99.15 223	99.66 211	99.34 219	98.92 380	99.24 391	97.69 303	99.98 27	98.11 278	99.28 393	98.81 430

tpm		97.15 404	96.95 406	97.75 433	98.91 432	94.24 464	99.32 155	97.96 452	97.71 405	98.29 428	99.32 370	86.72 458	99.92 149	98.10 281	96.24 480	99.09 386

DeepPCF-MVS	98.42 6	99.18 231	99.02 249	99.67 142	99.22 387	99.75 79	97.25 464	99.47 319	98.72 317	99.66 207	99.70 193	99.29 88	99.63 447	98.07 282	99.81 241	99.62 185

ppachtmachnet_test		98.89 296	99.12 214	98.20 417	99.66 227	95.24 457	97.63 446	99.68 201	99.08 266	99.78 133	99.62 258	98.65 201	99.88 234	98.02 283	99.96 87	99.48 271

tpmrst		97.73 384	98.07 361	96.73 456	98.71 458	92.00 475	99.10 247	98.86 410	98.52 341	98.92 380	99.54 310	91.90 416	99.82 335	98.02 283	99.03 413	98.37 458

CSCG		99.37 174	99.29 182	99.60 189	99.71 189	99.46 188	99.43 120	99.85 82	98.79 308	99.41 302	99.60 276	98.92 160	99.92 149	98.02 283	99.92 144	99.43 299

eth_miper_zixun_eth		98.68 319	98.71 300	98.60 396	99.10 412	96.84 427	97.52 454	99.54 287	98.94 283	99.58 242	99.48 328	96.25 362	99.76 381	98.01 286	99.93 138	99.21 354

Patchmtry		98.78 307	98.54 319	99.49 236	98.89 436	99.19 263	99.32 155	99.67 206	99.65 143	99.72 177	99.79 118	91.87 418	99.95 80	98.00 287	99.97 73	99.33 326

PVSNet_BlendedMVS		99.03 267	99.01 253	99.09 341	99.54 280	97.99 383	98.58 360	99.82 103	97.62 408	99.34 319	99.71 183	98.52 226	99.77 377	97.98 288	99.97 73	99.52 254

PVSNet_Blended		98.70 317	98.59 310	99.02 351	99.54 280	97.99 383	97.58 449	99.82 103	95.70 456	99.34 319	98.98 426	98.52 226	99.77 377	97.98 288	99.83 221	99.30 336

cl____		98.54 333	98.41 330	98.92 364	99.03 422	97.80 397	97.46 456	99.59 259	98.90 291	99.60 237	99.46 335	93.85 393	99.78 365	97.97 290	99.89 172	99.17 366

DIV-MVS_self_test		98.54 333	98.42 329	98.92 364	99.03 422	97.80 397	97.46 456	99.59 259	98.90 291	99.60 237	99.46 335	93.87 392	99.78 365	97.97 290	99.89 172	99.18 363

AUN-MVS		97.82 380	97.38 394	99.14 335	99.27 378	98.53 345	98.72 344	99.02 405	98.10 379	97.18 467	99.03 420	89.26 446	99.85 287	97.94 292	97.91 465	99.03 403

FA-MVS(test-final)		98.52 335	98.32 340	99.10 340	99.48 312	98.67 325	99.77 19	98.60 427	97.35 423	99.63 218	99.80 107	93.07 405	99.84 303	97.92 293	99.30 390	98.78 433

ambc				99.20 326	99.35 351	98.53 345	99.17 214	99.46 322		99.67 201	99.80 107	98.46 233	99.70 407	97.92 293	99.70 296	99.38 312

USDC		98.96 285	98.93 273	99.05 349	99.54 280	97.99 383	97.07 471	99.80 121	98.21 374	99.75 157	99.77 140	98.43 236	99.64 445	97.90 295	99.88 182	99.51 256

OPM-MVS		99.26 201	99.13 210	99.63 170	99.70 204	99.61 149	98.58 360	99.48 316	98.50 343	99.52 268	99.63 249	99.14 113	99.76 381	97.89 296	99.77 266	99.51 256
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 190	99.17 202	99.77 78	99.69 210	99.80 52	99.14 227	99.31 363	99.16 255	99.62 228	99.61 268	98.35 247	99.91 178	97.88 297	99.72 291	99.61 198
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.83 41	99.70 204	99.79 55	99.14 227	99.61 242					99.92 149	97.88 297	99.72 291	99.77 79

c3_l		98.72 314	98.71 300	98.72 390	99.12 405	97.22 417	97.68 445	99.56 275	98.90 291	99.54 261	99.48 328	96.37 357	99.73 396	97.88 297	99.88 182	99.21 354

3Dnovator+	98.92 3	99.35 180	99.24 194	99.67 142	99.35 351	99.47 182	99.62 67	99.50 311	99.44 197	99.12 361	99.78 130	98.77 182	99.94 97	97.87 300	99.72 291	99.62 185

miper_ehance_all_eth		98.59 328	98.59 310	98.59 397	98.98 428	97.07 421	97.49 455	99.52 302	98.50 343	99.52 268	99.37 356	96.41 355	99.71 403	97.86 301	99.62 327	99.00 410

WTY-MVS		98.59 328	98.37 334	99.26 317	99.43 330	98.40 354	98.74 342	99.13 398	98.10 379	99.21 348	99.24 391	94.82 383	99.90 197	97.86 301	98.77 429	99.49 267

APD_test1		99.36 178	99.28 185	99.61 185	99.89 39	99.89 10	99.32 155	99.74 165	99.18 248	99.69 189	99.75 155	98.41 239	99.84 303	97.85 303	99.70 296	99.10 381

SED-MVS		99.40 163	99.28 185	99.77 78	99.69 210	99.82 43	99.20 199	99.54 287	99.13 261	99.82 109	99.63 249	98.91 163	99.92 149	97.85 303	99.70 296	99.58 214

test_241102_TWO								99.54 287	99.13 261	99.76 152	99.63 249	98.32 252	99.92 149	97.85 303	99.69 304	99.75 87

MVS_111021_HR		99.12 247	99.02 249	99.40 271	99.50 302	99.11 275	97.92 432	99.71 181	98.76 315	99.08 365	99.47 332	99.17 106	99.54 461	97.85 303	99.76 268	99.54 237

MTAPA		99.35 180	99.20 198	99.80 64	99.81 104	99.81 48	99.33 152	99.53 297	99.27 232	99.42 296	99.63 249	98.21 264	99.95 80	97.83 307	99.79 253	99.65 155

MSC_two_6792asdad				99.74 101	99.03 422	99.53 171		99.23 380					99.92 149	97.77 308	99.69 304	99.78 75

No_MVS				99.74 101	99.03 422	99.53 171		99.23 380					99.92 149	97.77 308	99.69 304	99.78 75

TESTMET0.1,1		96.24 427	95.84 428	97.41 442	98.24 473	93.84 467	97.38 458	95.84 474	98.43 348	97.81 454	98.56 454	79.77 475	99.89 219	97.77 308	98.77 429	98.52 450

ACMH+	98.40 8	99.50 122	99.43 141	99.71 126	99.86 58	99.76 71	99.32 155	99.77 146	99.53 174	99.77 145	99.76 147	99.26 94	99.78 365	97.77 308	99.88 182	99.60 202

IU-MVS					99.69 210	99.77 64		99.22 383	97.50 415	99.69 189				97.75 312	99.70 296	99.77 79

114514_t		98.49 340	98.11 358	99.64 163	99.73 180	99.58 160	99.24 188	99.76 154	89.94 479	99.42 296	99.56 300	97.76 300	99.86 268	97.74 313	99.82 231	99.47 275

DVP-MVS++		99.38 170	99.25 192	99.77 78	99.03 422	99.77 64	99.74 27	99.61 242	99.18 248	99.76 152	99.61 268	99.00 145	99.92 149	97.72 314	99.60 337	99.62 185

test_0728_THIRD									99.18 248	99.62 228	99.61 268	98.58 209	99.91 178	97.72 314	99.80 248	99.77 79

EGC-MVSNET		89.05 452	85.52 455	99.64 163	99.89 39	99.78 58	99.56 87	99.52 302	24.19 488	49.96 489	99.83 84	99.15 110	99.92 149	97.71 316	99.85 208	99.21 354

miper_enhance_ethall		98.03 373	97.94 373	98.32 411	98.27 472	96.43 435	96.95 472	99.41 334	96.37 447	99.43 293	98.96 430	94.74 384	99.69 414	97.71 316	99.62 327	98.83 429

TSAR-MVS + MP.		99.34 185	99.24 194	99.63 170	99.82 92	99.37 220	99.26 181	99.35 353	98.77 312	99.57 245	99.70 193	99.27 93	99.88 234	97.71 316	99.75 272	99.65 155
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 392	97.28 396	98.40 406	98.37 470	96.75 428	97.24 465	99.37 349	97.31 425	99.41 302	99.22 393	87.30 450	99.37 473	97.70 319	99.62 327	99.08 392

MP-MVS-pluss		99.14 242	98.92 277	99.80 64	99.83 83	99.83 35	98.61 353	99.63 232	96.84 440	99.44 289	99.58 289	98.81 173	99.91 178	97.70 319	99.82 231	99.67 132
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 195	99.11 217	99.79 71	99.75 168	99.81 48	98.95 304	99.53 297	98.27 371	99.53 266	99.73 165	98.75 185	99.87 249	97.70 319	99.83 221	99.68 123

UnsupCasMVSNet_bld		98.55 332	98.27 346	99.40 271	99.56 275	99.37 220	97.97 428	99.68 201	97.49 416	99.08 365	99.35 366	95.41 377	99.82 335	97.70 319	98.19 457	99.01 409

MVS_111021_LR		99.13 244	99.03 248	99.42 260	99.58 254	99.32 232	97.91 434	99.73 169	98.68 322	99.31 329	99.48 328	99.09 122	99.66 436	97.70 319	99.77 266	99.29 339

IS-MVSNet		99.03 267	98.85 286	99.55 214	99.80 113	99.25 246	99.73 30	99.15 395	99.37 215	99.61 234	99.71 183	94.73 385	99.81 351	97.70 319	99.88 182	99.58 214

MED-MVS test				99.74 101	99.76 152	99.65 126	99.38 130	99.78 140	99.58 167	99.81 116	99.66 223		99.90 197	97.69 325	99.79 253	99.67 132

MED-MVS		99.45 145	99.36 159	99.74 101	99.76 152	99.65 126	99.38 130	99.78 140	99.31 225	99.81 116	99.66 223	99.02 142	99.90 197	97.69 325	99.79 253	99.67 132

ME-MVS		99.26 201	99.10 225	99.73 112	99.60 242	99.65 126	98.75 341	99.45 327	99.31 225	99.65 210	99.66 223	98.00 284	99.86 268	97.69 325	99.79 253	99.67 132

test-LLR		97.15 404	96.95 406	97.74 434	98.18 475	95.02 459	97.38 458	96.10 470	98.00 384	97.81 454	98.58 451	90.04 442	99.91 178	97.69 325	98.78 427	98.31 459

test-mter		96.23 428	95.73 431	97.74 434	98.18 475	95.02 459	97.38 458	96.10 470	97.90 394	97.81 454	98.58 451	79.12 478	99.91 178	97.69 325	98.78 427	98.31 459

MonoMVSNet		98.23 362	98.32 340	97.99 422	98.97 429	96.62 430	99.49 106	98.42 436	99.62 152	99.40 307	99.79 118	95.51 375	98.58 484	97.68 330	95.98 481	98.76 436

XVS		99.27 199	99.11 217	99.75 96	99.71 189	99.71 100	99.37 138	99.61 242	99.29 228	98.76 400	99.47 332	98.47 230	99.88 234	97.62 331	99.73 285	99.67 132

X-MVStestdata		96.09 432	94.87 445	99.75 96	99.71 189	99.71 100	99.37 138	99.61 242	99.29 228	98.76 400	61.30 497	98.47 230	99.88 234	97.62 331	99.73 285	99.67 132

SMA-MVS		99.19 227	99.00 257	99.73 112	99.46 322	99.73 90	99.13 234	99.52 302	97.40 420	99.57 245	99.64 234	98.93 157	99.83 319	97.61 333	99.79 253	99.63 173
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
CostFormer		96.71 415	96.79 414	96.46 460	98.90 433	90.71 486	99.41 121	98.68 420	94.69 469	98.14 439	99.34 369	86.32 460	99.80 359	97.60 334	98.07 463	98.88 424

PVSNet	97.47 15	98.42 346	98.44 327	98.35 408	99.46 322	96.26 439	96.70 476	99.34 355	97.68 406	99.00 372	99.13 402	97.40 317	99.72 398	97.59 335	99.68 309	99.08 392

new_pmnet		98.88 297	98.89 282	98.84 379	99.70 204	97.62 402	98.15 404	99.50 311	97.98 387	99.62 228	99.54 310	98.15 270	99.94 97	97.55 336	99.84 213	98.95 414

IB-MVS	95.41 20	95.30 447	94.46 451	97.84 430	98.76 454	95.33 455	97.33 461	96.07 472	96.02 451	95.37 483	97.41 478	76.17 483	99.96 69	97.54 337	95.44 484	98.22 464
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
LS3D		99.24 206	99.11 217	99.61 185	98.38 469	99.79 55	99.57 85	99.68 201	99.61 157	99.15 356	99.71 183	98.70 192	99.91 178	97.54 337	99.68 309	99.13 378

ZNCC-MVS		99.22 217	99.04 246	99.77 78	99.76 152	99.73 90	99.28 172	99.56 275	98.19 376	99.14 358	99.29 378	98.84 172	99.92 149	97.53 339	99.80 248	99.64 167

CP-MVS		99.23 208	99.05 240	99.75 96	99.66 227	99.66 120	99.38 130	99.62 235	98.38 355	99.06 369	99.27 381	98.79 178	99.94 97	97.51 340	99.82 231	99.66 146

SD-MVS		99.01 275	99.30 177	98.15 418	99.50 302	99.40 211	98.94 306	99.61 242	99.22 244	99.75 157	99.82 91	99.54 53	95.51 488	97.48 341	99.87 195	99.54 237
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
PMMVS		98.49 340	98.29 345	99.11 338	98.96 430	98.42 353	97.54 450	99.32 359	97.53 413	98.47 423	98.15 466	97.88 290	99.82 335	97.46 342	99.24 400	99.09 386

DeepC-MVS_fast	98.47 5	99.23 208	99.12 214	99.56 207	99.28 376	99.22 256	98.99 292	99.40 341	99.08 266	99.58 242	99.64 234	98.90 166	99.83 319	97.44 343	99.75 272	99.63 173
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 203	99.08 229	99.76 85	99.73 180	99.70 108	99.31 160	99.59 259	98.36 357	99.36 313	99.37 356	98.80 177	99.91 178	97.43 344	99.75 272	99.68 123

ACMMPR		99.23 208	99.06 235	99.76 85	99.74 176	99.69 112	99.31 160	99.59 259	98.36 357	99.35 315	99.38 353	98.61 205	99.93 118	97.43 344	99.75 272	99.67 132

Vis-MVSNet (Re-imp)		98.77 308	98.58 313	99.34 289	99.78 135	98.88 308	99.61 73	99.56 275	99.11 265	99.24 342	99.56 300	93.00 407	99.78 365	97.43 344	99.89 172	99.35 321

MIMVSNet		98.43 345	98.20 350	99.11 338	99.53 287	98.38 358	99.58 82	98.61 425	98.96 279	99.33 321	99.76 147	90.92 428	99.81 351	97.38 347	99.76 268	99.15 370

WB-MVSnew		98.34 356	98.14 356	98.96 357	98.14 478	97.90 391	98.27 394	97.26 466	98.63 328	98.80 395	98.00 469	97.77 298	99.90 197	97.37 348	98.98 416	99.09 386

XVG-OURS-SEG-HR		99.16 237	98.99 264	99.66 149	99.84 75	99.64 132	98.25 397	99.73 169	98.39 354	99.63 218	99.43 340	99.70 31	99.90 197	97.34 349	98.64 440	99.44 293

COLMAP_ROB	98.06 12	99.45 145	99.37 154	99.70 131	99.83 83	99.70 108	99.38 130	99.78 140	99.53 174	99.67 201	99.78 130	99.19 103	99.86 268	97.32 350	99.87 195	99.55 227
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 269	98.81 293	99.65 156	99.58 254	99.49 178	98.58 360	99.07 400	98.40 353	99.04 370	99.25 386	98.51 228	99.80 359	97.31 351	99.51 361	99.65 155

region2R		99.23 208	99.05 240	99.77 78	99.76 152	99.70 108	99.31 160	99.59 259	98.41 351	99.32 324	99.36 361	98.73 189	99.93 118	97.29 352	99.74 279	99.67 132

APD-MVS_3200maxsize		99.31 191	99.16 203	99.74 101	99.53 287	99.75 79	99.27 176	99.61 242	99.19 247	99.57 245	99.64 234	98.76 183	99.90 197	97.29 352	99.62 327	99.56 223

TAPA-MVS	97.92 13	98.03 373	97.55 390	99.46 247	99.47 318	99.44 196	98.50 375	99.62 235	86.79 480	99.07 368	99.26 384	98.26 257	99.62 448	97.28 354	99.73 285	99.31 334
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 199	99.11 217	99.73 112	99.54 280	99.74 87	99.26 181	99.62 235	99.16 255	99.52 268	99.64 234	98.41 239	99.91 178	97.27 355	99.61 334	99.54 237

RE-MVS-def			99.13 210		99.54 280	99.74 87	99.26 181	99.62 235	99.16 255	99.52 268	99.64 234	98.57 210		97.27 355	99.61 334	99.54 237

testing11		96.05 434	95.41 437	97.97 424	98.78 451	95.27 456	98.59 358	98.23 446	98.86 297	96.56 474	96.91 486	75.20 484	99.69 414	97.26 357	98.29 452	98.93 417

test_yl		98.25 359	97.95 369	99.13 336	99.17 398	98.47 348	99.00 285	98.67 422	98.97 277	99.22 346	99.02 421	91.31 422	99.69 414	97.26 357	98.93 418	99.24 345

DCV-MVSNet		98.25 359	97.95 369	99.13 336	99.17 398	98.47 348	99.00 285	98.67 422	98.97 277	99.22 346	99.02 421	91.31 422	99.69 414	97.26 357	98.93 418	99.24 345

PHI-MVS		99.11 251	98.95 271	99.59 192	99.13 403	99.59 155	99.17 214	99.65 221	97.88 397	99.25 339	99.46 335	98.97 153	99.80 359	97.26 357	99.82 231	99.37 315

tfpnnormal		99.43 152	99.38 151	99.60 189	99.87 54	99.75 79	99.59 80	99.78 140	99.71 118	99.90 68	99.69 202	98.85 171	99.90 197	97.25 361	99.78 262	99.15 370

PatchmatchNet		97.65 388	97.80 380	97.18 449	98.82 446	92.49 473	99.17 214	98.39 439	98.12 378	98.79 397	99.58 289	90.71 434	99.89 219	97.23 362	99.41 376	99.16 368
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 281	98.80 295	99.56 207	99.25 382	99.43 200	98.54 370	99.27 371	98.58 334	98.80 395	99.43 340	98.53 223	99.70 407	97.22 363	99.59 341	99.54 237

testing3		96.48 421	95.63 433	99.01 352	99.23 386	97.81 395	98.90 312	99.10 399	98.72 317	97.84 453	97.92 470	72.44 488	99.85 287	97.21 364	99.33 386	99.35 321

HPM-MVS		99.25 203	99.07 233	99.78 75	99.81 104	99.75 79	99.61 73	99.67 206	97.72 404	99.35 315	99.25 386	99.23 99	99.92 149	97.21 364	99.82 231	99.67 132
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 227	99.00 257	99.76 85	99.76 152	99.68 115	99.38 130	99.54 287	98.34 366	99.01 371	99.50 321	98.53 223	99.93 118	97.18 366	99.78 262	99.66 146

ACMMP		99.25 203	99.08 229	99.74 101	99.79 127	99.68 115	99.50 101	99.65 221	98.07 382	99.52 268	99.69 202	98.57 210	99.92 149	97.18 366	99.79 253	99.63 173
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
myMVS_eth3d28		96.23 428	95.74 430	97.70 436	98.86 440	95.59 452	98.66 350	98.14 448	98.96 279	97.67 459	97.06 483	76.78 481	98.92 480	97.10 368	98.41 449	98.58 446

thisisatest0515		96.98 408	96.42 416	98.66 393	99.42 335	97.47 408	97.27 463	94.30 480	97.24 427	99.15 356	98.86 438	85.01 462	99.87 249	97.10 368	99.39 378	98.63 440

XVG-ACMP-BASELINE		99.23 208	99.10 225	99.63 170	99.82 92	99.58 160	98.83 325	99.72 178	98.36 357	99.60 237	99.71 183	98.92 160	99.91 178	97.08 370	99.84 213	99.40 307

MSDG		99.08 256	98.98 267	99.37 280	99.60 242	99.13 272	97.54 450	99.74 165	98.84 301	99.53 266	99.55 308	99.10 120	99.79 362	97.07 371	99.86 203	99.18 363

SteuartSystems-ACMMP		99.30 192	99.14 208	99.76 85	99.87 54	99.66 120	99.18 209	99.60 253	98.55 336	99.57 245	99.67 218	99.03 141	99.94 97	97.01 372	99.80 248	99.69 116
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 430	95.78 429	97.49 438	98.53 464	93.83 468	98.04 418	93.94 483	98.96 279	98.46 424	98.17 465	79.86 473	99.87 249	96.99 373	99.06 409	98.78 433

EPMVS		96.53 418	96.32 417	97.17 450	98.18 475	92.97 472	99.39 127	89.95 489	98.21 374	98.61 412	99.59 286	86.69 459	99.72 398	96.99 373	99.23 402	98.81 430

MSP-MVS		99.04 266	98.79 296	99.81 54	99.78 135	99.73 90	99.35 145	99.57 270	98.54 339	99.54 261	98.99 423	96.81 340	99.93 118	96.97 375	99.53 357	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
HPM-MVS++		98.96 285	98.70 303	99.74 101	99.52 294	99.71 100	98.86 318	99.19 390	98.47 347	98.59 414	99.06 413	98.08 276	99.91 178	96.94 376	99.60 337	99.60 202

SR-MVS		99.19 227	99.00 257	99.74 101	99.51 296	99.72 95	99.18 209	99.60 253	98.85 298	99.47 283	99.58 289	98.38 244	99.92 149	96.92 377	99.54 355	99.57 220

PGM-MVS		99.20 224	99.01 253	99.77 78	99.75 168	99.71 100	99.16 220	99.72 178	97.99 386	99.42 296	99.60 276	98.81 173	99.93 118	96.91 378	99.74 279	99.66 146

HY-MVS	98.23 9	98.21 366	97.95 369	98.99 353	99.03 422	98.24 362	99.61 73	98.72 418	96.81 441	98.73 402	99.51 318	94.06 390	99.86 268	96.91 378	98.20 455	98.86 426

MDTV_nov1_ep13			97.73 384		98.70 459	90.83 484	99.15 223	98.02 451	98.51 342	98.82 392	99.61 268	90.98 427	99.66 436	96.89 380	98.92 420

GST-MVS		99.16 237	98.96 270	99.75 96	99.73 180	99.73 90	99.20 199	99.55 281	98.22 373	99.32 324	99.35 366	98.65 201	99.91 178	96.86 381	99.74 279	99.62 185

test_post1							99.14 227				51.63 499	89.54 445	99.82 335	96.86 381

SCA		98.11 369	98.36 335	97.36 443	99.20 392	92.99 471	98.17 402	98.49 433	98.24 372	99.10 364	99.57 296	96.01 367	99.94 97	96.86 381	99.62 327	99.14 375

UBG		96.53 418	95.95 424	98.29 415	98.87 439	96.31 438	98.48 378	98.07 449	98.83 302	97.32 462	96.54 492	79.81 474	99.62 448	96.84 384	98.74 433	98.95 414

XVG-OURS		99.21 222	99.06 235	99.65 156	99.82 92	99.62 140	97.87 436	99.74 165	98.36 357	99.66 207	99.68 214	99.71 28	99.90 197	96.84 384	99.88 182	99.43 299

LCM-MVSNet-Re		99.28 195	99.15 207	99.67 142	99.33 365	99.76 71	99.34 146	99.97 20	98.93 287	99.91 63	99.79 118	98.68 194	99.93 118	96.80 386	99.56 346	99.30 336

RPSCF		99.18 231	99.02 249	99.64 163	99.83 83	99.85 22	99.44 118	99.82 103	98.33 367	99.50 278	99.78 130	97.90 288	99.65 443	96.78 387	99.83 221	99.44 293

旧先验2							97.94 430		95.33 460	98.94 376			99.88 234	96.75 388

MDTV_nov1_ep13_2view						91.44 481	99.14 227		97.37 422	99.21 348		91.78 420		96.75 388		99.03 403

CLD-MVS		98.76 309	98.57 314	99.33 292	99.57 264	98.97 295	97.53 452	99.55 281	96.41 445	99.27 336	99.13 402	99.07 129	99.78 365	96.73 390	99.89 172	99.23 349
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 370	97.98 367	98.48 402	99.27 378	96.48 433	99.40 125	99.07 400	98.81 305	99.23 343	99.57 296	90.11 441	99.87 249	96.69 391	99.64 322	99.09 386

baseline2		96.83 411	96.28 418	98.46 404	99.09 415	96.91 425	98.83 325	93.87 484	97.23 428	96.23 479	98.36 460	88.12 449	99.90 197	96.68 392	98.14 460	98.57 448

cascas		96.99 407	96.82 413	97.48 439	97.57 487	95.64 450	96.43 478	99.56 275	91.75 475	97.13 469	97.61 477	95.58 372	98.63 482	96.68 392	99.11 406	98.18 468

PC_three_1452									97.56 409	99.68 194	99.41 343	99.09 122	97.09 485	96.66 394	99.60 337	99.62 185

LPG-MVS_test		99.22 217	99.05 240	99.74 101	99.82 92	99.63 138	99.16 220	99.73 169	97.56 409	99.64 213	99.69 202	99.37 75	99.89 219	96.66 394	99.87 195	99.69 116

LGP-MVS_train				99.74 101	99.82 92	99.63 138		99.73 169	97.56 409	99.64 213	99.69 202	99.37 75	99.89 219	96.66 394	99.87 195	99.69 116

ETVMVS		96.14 431	95.22 442	98.89 374	98.80 447	98.01 382	98.66 350	98.35 442	98.71 319	97.18 467	96.31 496	74.23 487	99.75 390	96.64 397	98.13 462	98.90 421

TinyColmap		98.97 282	98.93 273	99.07 346	99.46 322	98.19 367	97.75 440	99.75 159	98.79 308	99.54 261	99.70 193	98.97 153	99.62 448	96.63 398	99.83 221	99.41 304

LF4IMVS		99.01 275	98.92 277	99.27 314	99.71 189	99.28 238	98.59 358	99.77 146	98.32 368	99.39 309	99.41 343	98.62 203	99.84 303	96.62 399	99.84 213	98.69 439

NCCC		98.82 303	98.57 314	99.58 195	99.21 389	99.31 233	98.61 353	99.25 376	98.65 325	98.43 425	99.26 384	97.86 291	99.81 351	96.55 400	99.27 396	99.61 198

OPU-MVS				99.29 306	99.12 405	99.44 196	99.20 199				99.40 347	99.00 145	98.84 481	96.54 401	99.60 337	99.58 214

F-COLMAP		98.74 311	98.45 326	99.62 179	99.57 264	99.47 182	98.84 322	99.65 221	96.31 448	98.93 377	99.19 399	97.68 304	99.87 249	96.52 402	99.37 381	99.53 243

testing99		95.86 439	95.19 443	97.87 428	98.76 454	95.03 458	98.62 352	98.44 435	98.68 322	96.67 473	96.66 491	74.31 486	99.69 414	96.51 403	98.03 464	98.90 421

ADS-MVSNet2		97.78 382	97.66 388	98.12 420	99.14 401	95.36 454	99.22 196	98.75 417	96.97 436	98.25 430	99.64 234	90.90 429	99.94 97	96.51 403	99.56 346	99.08 392

ADS-MVSNet		97.72 387	97.67 387	97.86 429	99.14 401	94.65 462	99.22 196	98.86 410	96.97 436	98.25 430	99.64 234	90.90 429	99.84 303	96.51 403	99.56 346	99.08 392

PatchMatch-RL		98.68 319	98.47 323	99.30 305	99.44 327	99.28 238	98.14 406	99.54 287	97.12 434	99.11 362	99.25 386	97.80 296	99.70 407	96.51 403	99.30 390	98.93 417

CMPMVS	77.52 23	98.50 338	98.19 353	99.41 268	98.33 471	99.56 164	99.01 279	99.59 259	95.44 458	99.57 245	99.80 107	95.64 370	99.46 471	96.47 407	99.92 144	99.21 354
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 435	95.32 440	98.02 421	98.76 454	95.39 453	98.38 387	98.65 424	98.82 303	96.84 470	96.71 490	75.06 485	99.71 403	96.46 408	98.23 454	98.98 411

SF-MVS		99.10 254	98.93 273	99.62 179	99.58 254	99.51 176	99.13 234	99.65 221	97.97 388	99.42 296	99.61 268	98.86 170	99.87 249	96.45 409	99.68 309	99.49 267

FE-MVS		97.85 379	97.42 393	99.15 332	99.44 327	98.75 320	99.77 19	98.20 447	95.85 453	99.33 321	99.80 107	88.86 447	99.88 234	96.40 410	99.12 405	98.81 430

DPE-MVS		99.14 242	98.92 277	99.82 46	99.57 264	99.77 64	98.74 342	99.60 253	98.55 336	99.76 152	99.69 202	98.23 262	99.92 149	96.39 411	99.75 272	99.76 84
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 485	89.02 491			93.47 471		98.30 461		99.84 303	96.38 412

AllTest		99.21 222	99.07 233	99.63 170	99.78 135	99.64 132	99.12 239	99.83 97	98.63 328	99.63 218	99.72 173	98.68 194	99.75 390	96.38 412	99.83 221	99.51 256

TestCases				99.63 170	99.78 135	99.64 132		99.83 97	98.63 328	99.63 218	99.72 173	98.68 194	99.75 390	96.38 412	99.83 221	99.51 256

testdata				99.42 260	99.51 296	98.93 302		99.30 366	96.20 449	98.87 387	99.40 347	98.33 251	99.89 219	96.29 415	99.28 393	99.44 293

dp		96.86 410	97.07 402	96.24 462	98.68 460	90.30 489	99.19 205	98.38 440	97.35 423	98.23 432	99.59 286	87.23 451	99.82 335	96.27 416	98.73 436	98.59 444

tpmvs		97.39 399	97.69 385	96.52 458	98.41 468	91.76 477	99.30 163	98.94 409	97.74 403	97.85 452	99.55 308	92.40 414	99.73 396	96.25 417	98.73 436	98.06 470

KD-MVS_2432*1600		95.89 436	95.41 437	97.31 446	94.96 489	93.89 465	97.09 469	99.22 383	97.23 428	98.88 384	99.04 416	79.23 476	99.54 461	96.24 418	96.81 474	98.50 454

miper_refine_blended		95.89 436	95.41 437	97.31 446	94.96 489	93.89 465	97.09 469	99.22 383	97.23 428	98.88 384	99.04 416	79.23 476	99.54 461	96.24 418	96.81 474	98.50 454

ACMP	97.51 14	99.05 263	98.84 288	99.67 142	99.78 135	99.55 168	98.88 314	99.66 211	97.11 435	99.47 283	99.60 276	99.07 129	99.89 219	96.18 420	99.85 208	99.58 214
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 293	98.72 299	99.44 254	99.39 339	99.42 203	98.58 360	99.64 229	97.31 425	99.44 289	99.62 258	98.59 207	99.69 414	96.17 421	99.79 253	99.22 351

DP-MVS Recon		98.50 338	98.23 347	99.31 301	99.49 307	99.46 188	98.56 366	99.63 232	94.86 467	98.85 389	99.37 356	97.81 295	99.59 455	96.08 422	99.44 371	98.88 424

tpm cat1		96.78 412	96.98 405	96.16 463	98.85 441	90.59 487	99.08 255	99.32 359	92.37 473	97.73 458	99.46 335	91.15 425	99.69 414	96.07 423	98.80 426	98.21 465

tpm2		96.35 424	96.22 419	96.73 456	98.88 438	91.75 478	99.21 198	98.51 431	93.27 472	97.89 448	99.21 396	84.83 463	99.70 407	96.04 424	98.18 458	98.75 437

dmvs_re		98.69 318	98.48 322	99.31 301	99.55 278	99.42 203	99.54 90	98.38 440	99.32 223	98.72 403	98.71 447	96.76 342	99.21 475	96.01 425	99.35 384	99.31 334

test_0402		99.22 217	99.14 208	99.45 250	99.79 127	99.43 200	99.28 172	99.68 201	99.54 172	99.40 307	99.56 300	99.07 129	99.82 335	96.01 425	99.96 87	99.11 379

ITE_SJBPF				99.38 277	99.63 235	99.44 196		99.73 169	98.56 335	99.33 321	99.53 312	98.88 167	99.68 426	96.01 425	99.65 320	99.02 408

test_prior2							97.95 429		97.87 398	98.05 441	99.05 414	97.90 288		95.99 428	99.49 366

testdata2													99.89 219	95.99 428

原ACMM1				99.37 280	99.47 318	98.87 311		99.27 371	96.74 443	98.26 429	99.32 370	97.93 287	99.82 335	95.96 430	99.38 379	99.43 299

新几何1				99.52 226	99.50 302	99.22 256		99.26 373	95.66 457	98.60 413	99.28 379	97.67 305	99.89 219	95.95 431	99.32 388	99.45 280

MP-MVS		99.06 260	98.83 290	99.76 85	99.76 152	99.71 100	99.32 155	99.50 311	98.35 362	98.97 373	99.48 328	98.37 245	99.92 149	95.95 431	99.75 272	99.63 173
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 446	94.59 449	98.61 395	98.66 461	97.45 410	98.54 370	97.90 455	98.53 340	96.54 475	96.47 493	70.62 491	99.81 351	95.91 433	98.15 459	98.56 449

wuyk23d		97.58 391	99.13 210	92.93 467	99.69 210	99.49 178	99.52 93	99.77 146	97.97 388	99.96 34	99.79 118	99.84 16	99.94 97	95.85 434	99.82 231	79.36 485

HQP_MVS		98.90 293	98.68 304	99.55 214	99.58 254	99.24 250	98.80 333	99.54 287	98.94 283	99.14 358	99.25 386	97.24 324	99.82 335	95.84 435	99.78 262	99.60 202

plane_prior5								99.54 287					99.82 335	95.84 435	99.78 262	99.60 202

无先验							98.01 421	99.23 380	95.83 454				99.85 287	95.79 437		99.44 293

CPTT-MVS		98.74 311	98.44 327	99.64 163	99.61 240	99.38 216	99.18 209	99.55 281	96.49 444	99.27 336	99.37 356	97.11 332	99.92 149	95.74 438	99.67 315	99.62 185

PLC	97.35 16	98.36 351	97.99 365	99.48 241	99.32 366	99.24 250	98.50 375	99.51 307	95.19 463	98.58 415	98.96 430	96.95 337	99.83 319	95.63 439	99.25 398	99.37 315
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 330	98.34 338	99.28 309	99.18 397	99.10 282	98.34 389	99.41 334	98.48 346	98.52 420	98.98 426	97.05 334	99.78 365	95.59 440	99.50 364	98.96 412

1314		98.00 375	97.90 377	98.27 416	98.90 433	97.45 410	99.30 163	99.06 402	94.98 464	97.21 466	99.12 406	98.43 236	99.67 431	95.58 441	98.56 443	97.71 474

PVSNet_0	95.53 19	95.85 440	95.31 441	97.47 440	98.78 451	93.48 470	95.72 480	99.40 341	96.18 450	97.37 461	97.73 472	95.73 369	99.58 456	95.49 442	81.40 486	99.36 318

MAR-MVS		98.24 361	97.92 375	99.19 327	98.78 451	99.65 126	99.17 214	99.14 396	95.36 459	98.04 442	98.81 443	97.47 314	99.72 398	95.47 443	99.06 409	98.21 465
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
OpenMVS	98.12 10	98.23 362	97.89 378	99.26 317	99.19 394	99.26 243	99.65 62	99.69 198	91.33 477	98.14 439	99.77 140	98.28 254	99.96 69	95.41 444	99.55 350	98.58 446

train_agg		98.35 354	97.95 369	99.57 203	99.35 351	99.35 227	98.11 410	99.41 334	94.90 465	97.92 446	98.99 423	98.02 279	99.85 287	95.38 445	99.44 371	99.50 262

9.14			98.64 305		99.45 326		98.81 330	99.60 253	97.52 414	99.28 335	99.56 300	98.53 223	99.83 319	95.36 446	99.64 322

APD-MVS		98.87 298	98.59 310	99.71 126	99.50 302	99.62 140	99.01 279	99.57 270	96.80 442	99.54 261	99.63 249	98.29 253	99.91 178	95.24 447	99.71 294	99.61 198
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 436								95.20 448

AdaColmap		98.60 325	98.35 337	99.38 277	99.12 405	99.22 256	98.67 348	99.42 333	97.84 401	98.81 393	99.27 381	97.32 322	99.81 351	95.14 449	99.53 357	99.10 381

test9_res														95.10 450	99.44 371	99.50 262

CDPH-MVS		98.56 331	98.20 350	99.61 185	99.50 302	99.46 188	98.32 391	99.41 334	95.22 461	99.21 348	99.10 410	98.34 249	99.82 335	95.09 451	99.66 318	99.56 223

BH-untuned		98.22 364	98.09 359	98.58 399	99.38 342	97.24 416	98.55 367	98.98 408	97.81 402	99.20 353	98.76 445	97.01 335	99.65 443	94.83 452	98.33 450	98.86 426

BP-MVS														94.73 453

HQP-MVS		98.36 351	98.02 364	99.39 274	99.31 367	98.94 299	97.98 425	99.37 349	97.45 417	98.15 435	98.83 440	96.67 343	99.70 407	94.73 453	99.67 315	99.53 243

QAPM		98.40 349	97.99 365	99.65 156	99.39 339	99.47 182	99.67 53	99.52 302	91.70 476	98.78 399	99.80 107	98.55 214	99.95 80	94.71 455	99.75 272	99.53 243

agg_prior2														94.58 456	99.46 370	99.50 262

myMVS_eth3d		95.63 444	94.73 446	98.34 410	98.50 466	96.36 436	98.60 355	99.21 386	97.89 395	96.76 471	96.37 494	72.10 489	99.57 457	94.38 457	98.73 436	99.09 386

BH-RMVSNet		98.41 347	98.14 356	99.21 324	99.21 389	98.47 348	98.60 355	98.26 445	98.35 362	98.93 377	99.31 373	97.20 329	99.66 436	94.32 458	99.10 407	99.51 256

E-PMN		97.14 406	97.43 392	96.27 461	98.79 449	91.62 479	95.54 481	99.01 407	99.44 197	98.88 384	99.12 406	92.78 408	99.68 426	94.30 459	99.03 413	97.50 475

MG-MVS		98.52 335	98.39 332	98.94 360	99.15 400	97.39 413	98.18 400	99.21 386	98.89 294	99.23 343	99.63 249	97.37 320	99.74 393	94.22 460	99.61 334	99.69 116

API-MVS		98.38 350	98.39 332	98.35 408	98.83 443	99.26 243	99.14 227	99.18 391	98.59 333	98.66 408	98.78 444	98.61 205	99.57 457	94.14 461	99.56 346	96.21 482

PAPM_NR		98.36 351	98.04 362	99.33 292	99.48 312	98.93 302	98.79 336	99.28 370	97.54 412	98.56 419	98.57 453	97.12 331	99.69 414	94.09 462	98.90 424	99.38 312

ZD-MVS					99.43 330	99.61 149		99.43 331	96.38 446	99.11 362	99.07 412	97.86 291	99.92 149	94.04 463	99.49 366

DPM-MVS		98.28 357	97.94 373	99.32 297	99.36 347	99.11 275	97.31 462	98.78 416	96.88 438	98.84 390	99.11 409	97.77 298	99.61 453	94.03 464	99.36 382	99.23 349

gg-mvs-nofinetune		95.87 438	95.17 444	97.97 424	98.19 474	96.95 423	99.69 45	89.23 490	99.89 56	96.24 478	99.94 19	81.19 468	99.51 467	93.99 465	98.20 455	97.44 476

PMVS	92.94 21	98.82 303	98.81 293	98.85 377	99.84 75	97.99 383	99.20 199	99.47 319	99.71 118	99.42 296	99.82 91	98.09 274	99.47 469	93.88 466	99.85 208	99.07 397
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 409	97.28 396	95.99 465	98.76 454	91.03 483	95.26 483	98.61 425	99.34 219	98.92 380	98.88 437	93.79 394	99.66 436	92.87 467	99.05 411	97.30 479

BH-w/o		97.20 403	97.01 404	97.76 432	99.08 416	95.69 449	98.03 420	98.52 430	95.76 455	97.96 445	98.02 467	95.62 371	99.47 469	92.82 468	97.25 473	98.12 469

TR-MVS		97.44 396	97.15 401	98.32 411	98.53 464	97.46 409	98.47 379	97.91 454	96.85 439	98.21 433	98.51 457	96.42 353	99.51 467	92.16 469	97.29 472	97.98 471

OpenMVS_ROB	97.31 17	97.36 401	96.84 411	98.89 374	99.29 373	99.45 194	98.87 317	99.48 316	86.54 482	99.44 289	99.74 160	97.34 321	99.86 268	91.61 470	99.28 393	97.37 478

GG-mvs-BLEND				97.36 443	97.59 485	96.87 426	99.70 38	88.49 491		94.64 484	97.26 481	80.66 470	99.12 476	91.50 471	96.50 479	96.08 484

DeepMVS_CX				97.98 423	99.69 210	96.95 423		99.26 373	75.51 485	95.74 481	98.28 462	96.47 351	99.62 448	91.23 472	97.89 466	97.38 477

PAPR		97.56 392	97.07 402	99.04 350	98.80 447	98.11 375	97.63 446	99.25 376	94.56 470	98.02 444	98.25 463	97.43 316	99.68 426	90.90 473	98.74 433	99.33 326

MVS		95.72 442	94.63 448	98.99 353	98.56 463	97.98 388	99.30 163	98.86 410	72.71 486	97.30 463	99.08 411	98.34 249	99.74 393	89.21 474	98.33 450	99.26 342

UWE-MVS-28		95.64 443	95.47 435	96.14 464	97.98 479	90.39 488	98.49 377	95.81 475	99.02 273	98.03 443	98.19 464	84.49 465	99.28 474	88.75 475	98.47 448	98.75 437

thres600view7		96.60 417	96.16 420	97.93 426	99.63 235	96.09 444	99.18 209	97.57 460	98.77 312	98.72 403	97.32 479	87.04 453	99.72 398	88.57 476	98.62 441	97.98 471

FPMVS		96.32 425	95.50 434	98.79 385	99.60 242	98.17 370	98.46 383	98.80 415	97.16 432	96.28 476	99.63 249	82.19 467	99.09 477	88.45 477	98.89 425	99.10 381

PCF-MVS	96.03 18	96.73 414	95.86 427	99.33 292	99.44 327	99.16 269	96.87 474	99.44 328	86.58 481	98.95 375	99.40 347	94.38 388	99.88 234	87.93 478	99.80 248	98.95 414
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 423	96.03 423	97.47 440	99.63 235	95.93 445	99.18 209	97.57 460	98.75 316	98.70 406	97.31 480	87.04 453	99.67 431	87.62 479	98.51 445	96.81 480

tfpn200view9		96.30 426	95.89 425	97.53 437	99.58 254	96.11 442	99.00 285	97.54 463	98.43 348	98.52 420	96.98 484	86.85 455	99.67 431	87.62 479	98.51 445	96.81 480

thres400		96.40 422	95.89 425	97.92 427	99.58 254	96.11 442	99.00 285	97.54 463	98.43 348	98.52 420	96.98 484	86.85 455	99.67 431	87.62 479	98.51 445	97.98 471

thres200		96.09 432	95.68 432	97.33 445	99.48 312	96.22 441	98.53 372	97.57 460	98.06 383	98.37 427	96.73 489	86.84 457	99.61 453	86.99 482	98.57 442	96.16 483

MVE	92.54 22	96.66 416	96.11 421	98.31 413	99.68 218	97.55 404	97.94 430	95.60 476	99.37 215	90.68 487	98.70 449	96.56 346	98.61 483	86.94 483	99.55 350	98.77 435
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 402	96.83 412	98.59 397	99.46 322	97.55 404	99.25 187	96.84 469	98.78 310	97.24 465	97.67 473	97.11 332	98.97 479	86.59 484	98.54 444	99.27 340

PAPM		95.61 445	94.71 447	98.31 413	99.12 405	96.63 429	96.66 477	98.46 434	90.77 478	96.25 477	98.68 450	93.01 406	99.69 414	81.60 485	97.86 468	98.62 441

SD_0403		97.42 397	96.90 410	98.98 355	99.54 280	97.90 391	99.52 93	99.54 287	99.34 219	97.87 450	98.85 439	98.72 190	99.64 445	78.93 486	99.83 221	99.40 307

dongtai		89.37 451	88.91 454	90.76 468	99.19 394	77.46 493	95.47 482	87.82 492	92.28 474	94.17 485	98.82 442	71.22 490	95.54 487	63.85 487	97.34 471	99.27 340

kuosan		85.65 453	84.57 456	88.90 470	97.91 481	77.11 494	96.37 479	87.62 493	85.24 483	85.45 488	96.83 487	69.94 492	90.98 489	45.90 488	95.83 483	98.62 441

test123		29.31 454	33.05 459	18.08 471	25.93 495	12.24 496	97.53 452	10.93 496	11.78 489	24.21 490	50.08 501	21.04 493	8.60 490	23.51 489	32.43 489	33.39 486

testmvs		28.94 455	33.33 457	15.79 472	26.03 494	9.81 497	96.77 475	15.67 495	11.55 490	23.87 491	50.74 500	19.03 494	8.53 491	23.21 490	33.07 488	29.03 487

mmdepth		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

monomultidepth		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

test_blank		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

uanet_test		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

DCPMVS		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

cdsmvs_eth3d_5k		24.88 456	33.17 458	0.00 473	0.00 496	0.00 498	0.00 485	99.62 235	0.00 491	0.00 492	99.13 402	99.82 18	0.00 492	0.00 491	0.00 490	0.00 488

pcd_1.5k_mvsjas		16.61 457	22.14 460	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	99.28 90	0.00 492	0.00 491	0.00 490	0.00 488

sosnet-low-res		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

sosnet		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

uncertanet		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

Regformer		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

ab-mvs-re		8.26 468	11.02 471	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	99.16 400	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

uanet		8.33 458	11.11 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	100.00 1	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

TestfortrainingZip							99.38 130

FOURS1					99.83 83	99.89 10	99.74 27	99.71 181	99.69 127	99.63 218

test_one_0601					99.63 235	99.76 71		99.55 281	99.23 240	99.31 329	99.61 268	98.59 207

eth-test2					0.00 496

eth-test					0.00 496

test_241102_ONE					99.69 210	99.82 43		99.54 287	99.12 264	99.82 109	99.49 325	98.91 163	99.52 466

save fliter					99.53 287	99.25 246	98.29 393	99.38 348	99.07 268

test0726					99.69 210	99.80 52	99.24 188	99.57 270	99.16 255	99.73 172	99.65 232	98.35 247

GSMVS																99.14 375

test_part2					99.62 239	99.67 118				99.55 258

sam_mvs1												90.81 433				99.14 375

sam_mvs												90.52 438

MTGPA								99.53 297

test_post											52.41 498	90.25 440	99.86 268

patchmatchnet-post											99.62 258	90.58 436	99.94 97

MTMP							99.09 252	98.59 428

TEST9					99.35 351	99.35 227	98.11 410	99.41 334	94.83 468	97.92 446	98.99 423	98.02 279	99.85 287

test_8					99.34 360	99.31 233	98.08 414	99.40 341	94.90 465	97.87 450	98.97 428	98.02 279	99.84 303

agg_prior					99.35 351	99.36 224		99.39 344		97.76 457			99.85 287

test_prior4						99.19 263	98.00 423

test_prior				99.46 247	99.35 351	99.22 256		99.39 344					99.69 414			99.48 271

新几何2							98.04 418

旧先验1					99.49 307	99.29 236		99.26 373			99.39 351	97.67 305			99.36 382	99.46 279

原ACMM2							97.92 432

test222					99.51 296	99.08 284	97.83 438	99.29 367	95.21 462	98.68 407	99.31 373	97.28 323			99.38 379	99.43 299

segment_acmp												98.37 245

testdata1							97.72 441		97.86 400

test12				99.54 220	99.29 373	99.33 230		99.16 394		98.43 425		97.54 312	99.82 335		99.47 368	99.48 271

plane_prior7					99.58 254	99.38 216

plane_prior6					99.47 318	99.26 243						97.24 324

plane_prior4											99.25 386

plane_prior3						99.31 233			98.36 357	99.14 358

plane_prior2							98.80 333		98.94 283

plane_prior1					99.51 296

plane_prior						99.24 250	98.42 385		97.87 398						99.71 294

n2								0.00 497

nn								0.00 497

door-mid								99.83 97

test11								99.29 367

door								99.77 146

HQP5-MVS						98.94 299

HQP-NCC					99.31 367		97.98 425		97.45 417	98.15 435

ACMP_Plane					99.31 367		97.98 425		97.45 417	98.15 435

HQP4-MVS										98.15 435			99.70 407			99.53 243

HQP3-MVS								99.37 349							99.67 315

HQP2-MVS												96.67 343

NP-MVS					99.40 338	99.13 272					98.83 440

ACMMP++_ref															99.94 126

ACMMP++															99.79 253

Test By Simon												98.41 239

High-resolution multi-view benchmark