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	99.34 286	99.91 31	98.08 377	99.48 107	100.00 1	99.90 50	99.99 7	99.91 31	99.50 57	99.98 27	99.98 1	99.99 16	99.96 13

test_fmvs3		99.83 21	99.93 2	99.53 221	99.96 7	98.62 332	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	99.12 235	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	99.27 311	99.93 24	97.84 390	99.34 142	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	99.36 282	99.94 18	98.18 366	99.52 92	100.00 1	99.86 66	100.00 1	99.88 50	98.99 144	99.96 69	99.97 4	99.96 87	99.95 14

test_fmvs1_n		99.68 65	99.81 28	99.28 306	99.95 15	97.93 386	99.49 105	100.00 1	99.82 86	99.99 7	99.89 41	99.21 98	99.98 27	99.97 4	99.98 50	99.93 20

test_f		99.75 49	99.88 7	99.37 277	99.96 7	98.21 363	99.51 99	100.00 1	99.94 36	100.00 1	99.93 22	99.58 45	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 57	99.80 52	98.94 302	99.96 28	99.98 18	99.96 34	99.78 127	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	99.08 251	99.97 20	99.98 18	99.96 34	99.79 115	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	99.01 275	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	99.55 165	99.17 210	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	99.45 247	99.93 24	98.40 351	99.30 159	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	99.81 101	99.75 79	99.06 257	99.85 82	99.99 3	99.97 24	99.84 77	99.12 115	99.98 27	99.95 14	99.99 16	99.90 29

fmvsm_s_conf0.5_n_7		99.73 52	99.78 39	99.60 186	99.74 173	98.93 299	98.85 316	99.96 28	99.96 28	99.97 24	99.76 144	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	99.11 240	99.91 52	99.98 18	99.96 34	99.64 231	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 89	99.70 108	99.17 210	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		99.48 126	99.65 70	98.97 353	99.54 277	97.16 413	99.11 240	99.98 12	99.78 103	99.96 34	99.81 98	98.72 187	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	99.37 217	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 80	99.59 152	98.97 293	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	98.92 306	99.98 12	99.99 3	99.99 7	99.88 50	99.43 62	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	99.12 235	99.91 52	99.98 18	99.95 45	99.67 215	99.67 34	99.99 8	99.94 20	99.99 16	99.88 40

MM		99.18 228	99.05 237	99.55 211	99.35 348	98.81 310	99.05 258	97.79 453	99.99 3	99.48 278	99.59 283	96.29 358	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	98.97 293	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	99.81 101	99.53 168	99.15 219	99.89 61	99.99 3	99.98 14	99.86 63	99.13 112	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	99.79 124	99.72 95	98.84 318	99.96 28	99.96 28	99.96 34	99.72 170	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 89	99.76 71	98.88 310	99.92 43	99.98 18	99.98 14	99.85 69	99.42 64	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	99.10 243	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	99.07 256	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 67	99.82 43	99.03 266	99.96 28	99.99 3	99.97 24	99.84 77	99.58 45	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 67	99.78 58	99.03 266	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 89	99.75 79	99.02 270	99.87 70	99.98 18	99.98 14	99.81 98	99.07 126	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	99.78 132	99.78 58	99.00 281	99.97 20	99.96 28	99.97 24	99.56 297	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	99.75 165	99.56 161	98.98 291	99.94 38	99.92 46	99.97 24	99.72 170	99.84 16	99.92 149	99.91 33	99.98 50	99.89 37

MVStest1		98.22 361	98.09 356	98.62 389	99.04 418	96.23 435	99.20 195	99.92 43	99.44 193	99.98 14	99.87 56	85.87 457	99.67 426	99.91 33	99.57 342	99.95 14

v1921920		99.56 101	99.57 99	99.55 211	99.75 165	99.11 272	99.05 258	99.61 238	99.15 255	99.88 83	99.71 180	99.08 123	99.87 249	99.90 37	99.97 73	99.66 143

v1240		99.56 101	99.58 94	99.51 227	99.80 110	99.00 286	99.00 281	99.65 217	99.15 255	99.90 68	99.75 152	99.09 119	99.88 234	99.90 37	99.96 87	99.67 129

v10		99.69 60	99.69 61	99.66 146	99.81 101	99.39 211	99.66 57	99.75 155	99.60 160	99.92 60	99.87 56	98.75 182	99.86 268	99.90 37	99.99 16	99.73 93

v1192		99.57 97	99.57 99	99.57 200	99.77 145	99.22 253	99.04 263	99.60 249	99.18 244	99.87 93	99.72 170	99.08 123	99.85 287	99.89 40	99.98 50	99.66 143

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 32	99.81 101	99.71 100	98.97 293	99.92 43	99.98 18	99.97 24	99.86 63	99.53 53	99.95 80	99.88 41	99.99 16	99.89 37

v144192		99.55 106	99.54 109	99.58 192	99.78 132	99.20 259	99.11 240	99.62 231	99.18 244	99.89 73	99.72 170	98.66 196	99.87 249	99.88 41	99.97 73	99.66 143

v8		99.68 65	99.69 61	99.65 153	99.80 110	99.40 208	99.66 57	99.76 150	99.64 144	99.93 53	99.85 69	98.66 196	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	99.42 200	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		99.54 110	99.53 113	99.59 189	99.79 124	99.28 235	99.10 243	99.61 238	99.20 241	99.84 102	99.73 162	98.67 194	99.84 303	99.86 45	99.98 50	99.64 164

mmtdpeth		99.78 37	99.83 21	99.66 146	99.85 67	99.05 285	99.79 15	99.97 20	100.00 1	99.43 290	99.94 19	99.64 35	99.94 97	99.83 46	99.99 16	99.98 5

SSC-MVS		99.52 116	99.42 140	99.83 41	99.86 57	99.65 126	99.52 92	99.81 113	99.87 63	99.81 116	99.79 115	96.78 338	99.99 8	99.83 46	99.51 358	99.86 46

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 27	99.82 10	99.82 100	99.84 76	99.94 48	99.91 31	99.13 112	99.96 69	99.83 46	99.99 16	99.83 56

v2v482		99.50 119	99.47 125	99.58 192	99.78 132	99.25 243	99.14 223	99.58 264	99.25 232	99.81 116	99.62 255	98.24 255	99.84 303	99.83 46	99.97 73	99.64 164

test_vis1_rt		99.45 142	99.46 130	99.41 265	99.71 186	98.63 331	98.99 288	99.96 28	99.03 268	99.95 45	99.12 403	98.75 182	99.84 303	99.82 50	99.82 228	99.77 79

tt0805		99.63 81	99.57 99	99.81 54	99.87 54	99.88 12	99.58 82	98.70 414	99.72 113	99.91 63	99.60 273	99.43 62	99.81 349	99.81 51	99.53 354	99.73 93

VortexMVS		99.13 241	99.24 191	98.79 380	99.67 222	96.60 427	99.24 184	99.80 117	99.85 72	99.93 53	99.84 77	95.06 376	99.89 219	99.80 52	99.98 50	99.89 37

V42		99.56 101	99.54 109	99.63 167	99.79 124	99.46 185	99.39 123	99.59 255	99.24 234	99.86 96	99.70 190	98.55 211	99.82 333	99.79 53	99.95 107	99.60 199

SSC-MVS3.2		99.64 80	99.67 65	99.56 204	99.75 165	98.98 289	98.96 297	99.87 70	99.88 61	99.84 102	99.64 231	99.32 82	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		99.44 146	99.32 167	99.80 64	99.81 101	99.61 146	99.47 110	99.81 113	99.82 86	99.71 179	99.72 170	96.60 342	99.98 27	99.75 56	99.23 399	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 87	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		99.15 238	99.06 232	99.42 257	99.85 67	98.59 335	99.13 230	97.26 461	99.84 76	99.87 93	99.77 137	96.11 361	99.93 118	99.71 60	99.96 87	99.74 89

Elysia		99.69 60	99.65 70	99.81 54	99.86 57	99.72 95	99.34 142	99.77 142	99.94 36	99.91 63	99.76 144	98.55 211	99.99 8	99.70 61	99.98 50	99.72 97

StellarMVS		99.69 60	99.65 70	99.81 54	99.86 57	99.72 95	99.34 142	99.77 142	99.94 36	99.91 63	99.76 144	98.55 211	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 89	99.84 27	99.82 10	99.92 43	99.94 36	99.94 48	99.93 22	99.34 79	99.92 149	99.70 61	99.96 87	99.70 105

reproduce_monomvs		97.40 394	97.46 387	97.20 443	99.05 415	91.91 471	99.20 195	99.18 386	99.84 76	99.86 96	99.75 152	80.67 465	99.83 319	99.69 64	99.95 107	99.85 49

SPE-MVS-test		99.68 65	99.70 58	99.64 160	99.57 261	99.83 35	99.78 17	99.97 20	99.92 46	99.50 275	99.38 350	99.57 47	99.95 80	99.69 64	99.90 155	99.15 365

guyue		99.12 244	99.02 246	99.41 265	99.84 72	98.56 336	99.19 201	98.30 439	99.82 86	99.84 102	99.75 152	94.84 379	99.92 149	99.68 66	99.94 123	99.74 89

tt0320		99.79 34	99.79 34	99.81 54	99.82 89	99.84 27	99.82 10	99.90 58	99.94 36	99.94 48	99.94 19	99.07 126	99.92 149	99.68 66	99.97 73	99.67 129

MGCNet		98.61 319	98.30 340	99.52 223	97.88 478	98.95 295	98.76 335	94.11 477	99.84 76	99.32 321	99.57 293	95.57 370	99.95 80	99.68 66	99.98 50	99.68 120

CS-MVS		99.67 72	99.70 58	99.58 192	99.53 284	99.84 27	99.79 15	99.96 28	99.90 50	99.61 231	99.41 340	99.51 56	99.95 80	99.66 69	99.89 169	98.96 407

mamv4		99.73 52	99.74 53	99.70 131	99.66 224	99.87 15	99.69 45	99.93 39	99.93 43	99.93 53	99.86 63	99.07 126	100.00 1	99.66 69	99.92 141	99.24 340

KinetiMVS		99.66 73	99.63 78	99.76 85	99.89 39	99.57 160	99.37 134	99.82 100	99.95 32	99.90 68	99.63 246	98.57 207	99.97 44	99.65 71	99.94 123	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	99.69 113

MIMVSNet1		99.66 73	99.62 80	99.80 64	99.94 18	99.87 15	99.69 45	99.77 142	99.78 103	99.93 53	99.89 41	97.94 283	99.92 149	99.65 71	99.98 50	99.62 182

LuminaMVS		99.39 164	99.28 182	99.73 112	99.83 80	99.49 175	99.00 281	99.05 398	99.81 92	99.89 73	99.79 115	96.54 346	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	99.79 126	99.94 36	99.93 53	99.92 27	99.35 78	99.92 149	99.64 74	99.94 123	99.68 120

EC-MVSNet		99.69 60	99.69 61	99.68 135	99.71 186	99.91 4	99.76 23	99.96 28	99.86 66	99.51 272	99.39 348	99.57 47	99.93 118	99.64 74	99.86 200	99.20 353

K. test v3		98.87 295	98.60 305	99.69 133	99.93 24	99.46 185	99.74 27	94.97 472	99.78 103	99.88 83	99.88 50	93.66 394	99.97 44	99.61 77	99.95 107	99.64 164

KD-MVS_self_test		99.63 81	99.59 90	99.76 85	99.84 72	99.90 7	99.37 134	99.79 126	99.83 82	99.88 83	99.85 69	98.42 235	99.90 197	99.60 78	99.73 282	99.49 264

Anonymous20240521		99.44 146	99.42 140	99.49 233	99.89 39	98.96 294	99.62 67	99.76 150	99.85 72	99.82 109	99.88 50	96.39 353	99.97 44	99.59 79	99.98 50	99.55 224

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	99.74 276	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	98.54 215	99.93 118	99.59 79	99.98 50	99.76 84

EU-MVSNet		99.39 164	99.62 80	98.72 385	99.88 45	96.44 429	99.56 87	99.85 82	99.90 50	99.90 68	99.85 69	98.09 271	99.83 319	99.58 82	99.95 107	99.90 29

mvs_anonymous		99.28 192	99.39 145	98.94 357	99.19 391	97.81 392	99.02 270	99.55 277	99.78 103	99.85 99	99.80 104	98.24 255	99.86 268	99.57 83	99.50 361	99.15 365

test1111		97.74 379	98.16 352	96.49 454	99.60 239	89.86 485	99.71 37	91.21 481	99.89 56	99.88 83	99.87 56	93.73 393	99.90 197	99.56 84	99.99 16	99.70 105

lessismore_v0				99.64 160	99.86 57	99.38 213		90.66 482		99.89 73	99.83 84	94.56 384	99.97 44	99.56 84	99.92 141	99.57 217

mvsany_test1		99.44 146	99.45 132	99.40 268	99.37 341	98.64 330	97.90 431	99.59 255	99.27 228	99.92 60	99.82 91	99.74 26	99.93 118	99.55 86	99.87 192	99.63 170

MVSMamba_PlusPlus		99.55 106	99.58 94	99.47 240	99.68 215	99.40 208	99.52 92	99.70 186	99.92 46	99.77 145	99.86 63	98.28 251	99.96 69	99.54 87	99.90 155	99.05 394

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	99.92 141	99.63 170

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		99.48 126	99.65 70	98.95 356	99.71 186	97.27 410	99.50 100	99.82 100	99.59 162	99.41 299	99.85 69	99.62 40	100.00 1	99.53 90	99.89 169	99.59 206

test2506		94.73 444	94.59 445	95.15 461	99.59 245	85.90 487	99.75 25	74.01 489	99.89 56	99.71 179	99.86 63	79.00 475	99.90 197	99.52 91	99.99 16	99.65 152

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 177	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 70	99.86 30	99.88 45	99.86 19	99.72 33	99.78 136	99.90 50	99.82 109	99.83 84	98.45 231	99.87 249	99.51 92	99.97 73	99.86 46

BP-MVS1		98.72 311	98.46 321	99.50 229	99.53 284	99.00 286	99.34 142	98.53 424	99.65 140	99.73 169	99.38 350	90.62 431	99.96 69	99.50 94	99.86 200	99.55 224

UA-Net		99.78 37	99.76 49	99.86 30	99.72 182	99.71 100	99.91 4	99.95 36	99.96 28	99.71 179	99.91 31	99.15 107	99.97 44	99.50 94	100.00 1	99.90 29

viewdifsd2359ckpt11		99.62 88	99.64 75	99.56 204	99.86 57	99.19 260	99.02 270	99.93 39	99.83 82	99.88 83	99.81 98	98.99 144	99.83 319	99.48 96	99.96 87	99.65 152

viewmsd2359difaftdt		99.62 88	99.64 75	99.56 204	99.86 57	99.19 260	99.02 270	99.93 39	99.83 82	99.88 83	99.81 98	98.99 144	99.83 319	99.48 96	99.96 87	99.65 152

PMMVS2		99.48 126	99.45 132	99.57 200	99.76 149	98.99 288	98.09 408	99.90 58	98.95 278	99.78 133	99.58 286	99.57 47	99.93 118	99.48 96	99.95 107	99.79 73

VPA-MVSNet		99.66 73	99.62 80	99.79 71	99.68 215	99.75 79	99.62 67	99.69 194	99.85 72	99.80 123	99.81 98	98.81 170	99.91 178	99.47 99	99.88 179	99.70 105

GDP-MVS		98.81 302	98.57 311	99.50 229	99.53 284	99.12 271	99.28 168	99.86 76	99.53 171	99.57 242	99.32 367	90.88 427	99.98 27	99.46 100	99.74 276	99.42 299

ECVR-MVS		97.73 380	98.04 359	96.78 447	99.59 245	90.81 480	99.72 33	90.43 483	99.89 56	99.86 96	99.86 63	93.60 395	99.89 219	99.46 100	99.99 16	99.65 152

nrg030		99.70 58	99.66 68	99.82 46	99.76 149	99.84 27	99.61 73	99.70 186	99.93 43	99.78 133	99.68 211	99.10 117	99.78 363	99.45 102	99.96 87	99.83 56

FE-MVSNET2		99.68 65	99.67 65	99.72 120	99.86 57	99.68 115	99.46 114	99.88 66	99.62 149	99.87 93	99.85 69	99.06 133	99.85 287	99.44 103	99.98 50	99.63 170

TAMVS		99.49 124	99.45 132	99.63 167	99.48 309	99.42 200	99.45 115	99.57 266	99.66 137	99.78 133	99.83 84	97.85 290	99.86 268	99.44 103	99.96 87	99.61 195

GeoE		99.69 60	99.66 68	99.78 75	99.76 149	99.76 71	99.60 79	99.82 100	99.46 188	99.75 154	99.56 297	99.63 37	99.95 80	99.43 105	99.88 179	99.62 182

new-patchmatchnet		99.35 177	99.57 99	98.71 387	99.82 89	96.62 425	98.55 363	99.75 155	99.50 175	99.88 83	99.87 56	99.31 83	99.88 234	99.43 105	100.00 1	99.62 182

test20.03		99.55 106	99.54 109	99.58 192	99.79 124	99.37 217	99.02 270	99.89 61	99.60 160	99.82 109	99.62 255	98.81 170	99.89 219	99.43 105	99.86 200	99.47 272

MVSFormer		99.41 158	99.44 136	99.31 298	99.57 261	98.40 351	99.77 19	99.80 117	99.73 109	99.63 215	99.30 372	98.02 276	99.98 27	99.43 105	99.69 301	99.55 224

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 27	99.77 19	99.80 117	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	99.80 110	99.65 126	99.63 64	99.86 76	99.97 25	99.89 73	99.89 41	99.52 55	99.99 8	99.42 110	99.96 87	99.65 152

Anonymous20231211		99.62 88	99.57 99	99.76 85	99.61 237	99.60 150	99.81 13	99.73 165	99.82 86	99.90 68	99.90 36	97.97 282	99.86 268	99.42 110	99.96 87	99.80 65

SixPastTwentyTwo		99.42 152	99.30 174	99.76 85	99.92 29	99.67 118	99.70 38	99.14 391	99.65 140	99.89 73	99.90 36	96.20 360	99.94 97	99.42 110	99.92 141	99.67 129

balanced_conf03		99.50 119	99.50 118	99.50 229	99.42 332	99.49 175	99.52 92	99.75 155	99.86 66	99.78 133	99.71 180	98.20 263	99.90 197	99.39 113	99.88 179	99.10 376

patch_mono-2		99.51 117	99.46 130	99.64 160	99.70 201	99.11 272	99.04 263	99.87 70	99.71 118	99.47 280	99.79 115	98.24 255	99.98 27	99.38 114	99.96 87	99.83 56

UGNet		99.38 167	99.34 162	99.49 233	98.90 430	98.90 303	99.70 38	99.35 349	99.86 66	98.57 414	99.81 98	98.50 226	99.93 118	99.38 114	99.98 50	99.66 143
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	99.82 100	99.39 209	99.82 109	99.84 77	99.38 70	99.91 178	99.38 114	99.93 135	99.80 65

FIs		99.65 79	99.58 94	99.84 38	99.84 72	99.85 22	99.66 57	99.75 155	99.86 66	99.74 164	99.79 115	98.27 253	99.85 287	99.37 117	99.93 135	99.83 56

sd_testset		99.78 37	99.78 39	99.80 64	99.80 110	99.76 71	99.80 14	99.79 126	99.97 25	99.89 73	99.89 41	99.53 53	99.99 8	99.36 118	99.96 87	99.65 152

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 58	99.97 44	99.36 118	100.00 1	99.85 49

casdiffmvs_mvg		99.68 65	99.68 64	99.69 133	99.81 101	99.59 152	99.29 166	99.90 58	99.71 118	99.79 129	99.73 162	99.54 50	99.84 303	99.36 118	99.96 87	99.65 152
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	99.67 133	99.77 145	99.75 152	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 92	99.64 75	99.53 221	99.79 124	98.82 309	99.58 82	99.97 20	99.95 32	99.96 34	99.76 144	98.44 232	99.99 8	99.34 122	99.96 87	99.78 75

CHOSEN 1792x2688		99.39 164	99.30 174	99.65 153	99.88 45	99.25 243	98.78 333	99.88 66	98.66 320	99.96 34	99.79 115	97.45 312	99.93 118	99.34 122	99.99 16	99.78 75

CDS-MVSNet		99.22 214	99.13 207	99.50 229	99.35 348	99.11 272	98.96 297	99.54 283	99.46 188	99.61 231	99.70 190	96.31 356	99.83 319	99.34 122	99.88 179	99.55 224
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 275	99.16 200	98.51 395	99.75 165	95.90 441	98.07 411	99.84 89	99.84 76	99.89 73	99.73 162	96.01 364	99.99 8	99.33 125	100.00 1	99.63 170

HyFIR lowres test		98.91 288	98.64 302	99.73 112	99.85 67	99.47 179	98.07 411	99.83 94	98.64 323	99.89 73	99.60 273	92.57 406	100.00 1	99.33 125	99.97 73	99.72 97

pmmvs5		99.19 224	99.11 214	99.42 257	99.76 149	98.88 305	98.55 363	99.73 165	98.82 299	99.72 174	99.62 255	96.56 343	99.82 333	99.32 127	99.95 107	99.56 220

v148		99.40 160	99.41 143	99.39 271	99.76 149	98.94 296	99.09 248	99.59 255	99.17 249	99.81 116	99.61 265	98.41 236	99.69 409	99.32 127	99.94 123	99.53 240

baseline		99.63 81	99.62 80	99.66 146	99.80 110	99.62 140	99.44 117	99.80 117	99.71 118	99.72 174	99.69 199	99.15 107	99.83 319	99.32 127	99.94 123	99.53 240

CVMVSNet		98.61 319	98.88 280	97.80 426	99.58 251	93.60 464	99.26 177	99.64 225	99.66 137	99.72 174	99.67 215	93.26 399	99.93 118	99.30 130	99.81 238	99.87 44

PS-CasMVS		99.66 73	99.58 94	99.89 11	99.80 110	99.85 22	99.66 57	99.73 165	99.62 149	99.84 102	99.71 180	98.62 200	99.96 69	99.30 130	99.96 87	99.86 46

DTE-MVSNet		99.68 65	99.61 84	99.88 19	99.80 110	99.87 15	99.67 53	99.71 177	99.72 113	99.84 102	99.78 127	98.67 194	99.97 44	99.30 130	99.95 107	99.80 65

tmp_tt		95.75 437	95.42 432	96.76 448	89.90 488	94.42 458	98.86 314	97.87 451	78.01 479	99.30 331	99.69 199	97.70 298	95.89 481	99.29 133	98.14 457	99.95 14

PEN-MVS		99.66 73	99.59 90	99.89 11	99.83 80	99.87 15	99.66 57	99.73 165	99.70 124	99.84 102	99.73 162	98.56 210	99.96 69	99.29 133	99.94 123	99.83 56

WR-MVS_H		99.61 92	99.53 113	99.87 26	99.80 110	99.83 35	99.67 53	99.75 155	99.58 164	99.85 99	99.69 199	98.18 266	99.94 97	99.28 135	99.95 107	99.83 56

IterMVS		98.97 279	99.16 200	98.42 400	99.74 173	95.64 445	98.06 413	99.83 94	99.83 82	99.85 99	99.74 157	96.10 363	99.99 8	99.27 136	100.00 1	99.63 170
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
NormalMVS		99.09 252	98.91 278	99.62 176	99.78 132	99.11 272	99.36 138	99.77 142	99.82 86	99.68 191	99.53 309	93.30 397	99.99 8	99.24 137	99.76 265	99.74 89

SymmetryMVS		99.01 272	98.82 288	99.58 192	99.65 229	99.11 272	99.36 138	99.20 384	99.82 86	99.68 191	99.53 309	93.30 397	99.99 8	99.24 137	99.63 322	99.64 164

WBMVS		97.50 390	97.18 396	98.48 397	98.85 438	95.89 442	98.44 380	99.52 298	99.53 171	99.52 265	99.42 339	80.10 468	99.86 268	99.24 137	99.95 107	99.68 120

h-mvs33		98.61 319	98.34 335	99.44 251	99.60 239	98.67 322	99.27 172	99.44 324	99.68 129	99.32 321	99.49 322	92.50 409	100.00 1	99.24 137	96.51 474	99.65 152

hse-mvs2		98.52 332	98.30 340	99.16 327	99.29 370	98.60 333	98.77 334	99.02 400	99.68 129	99.32 321	99.04 413	92.50 409	99.85 287	99.24 137	97.87 464	99.03 398

FMVSNet1		99.66 73	99.63 78	99.73 112	99.78 132	99.77 64	99.68 49	99.70 186	99.67 133	99.82 109	99.83 84	98.98 148	99.90 197	99.24 137	99.97 73	99.53 240

casdiffmvs		99.63 81	99.61 84	99.67 139	99.79 124	99.59 152	99.13 230	99.85 82	99.79 100	99.76 149	99.72 170	99.33 81	99.82 333	99.21 143	99.94 123	99.59 206
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		99.54 110	99.43 138	99.87 26	99.76 149	99.82 43	99.57 85	99.61 238	99.54 169	99.80 123	99.64 231	97.79 294	99.95 80	99.21 143	99.94 123	99.84 52

DELS-MVS		99.34 182	99.30 174	99.48 238	99.51 293	99.36 221	98.12 404	99.53 293	99.36 214	99.41 299	99.61 265	99.22 97	99.87 249	99.21 143	99.68 306	99.20 353
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		99.47 136	99.50 118	99.37 277	99.70 201	98.80 313	98.67 344	99.92 43	99.49 177	99.77 145	99.71 180	99.08 123	99.78 363	99.20 146	99.94 123	99.54 234

UniMVSNet (Re)		99.37 171	99.26 187	99.68 135	99.51 293	99.58 157	98.98 291	99.60 249	99.43 200	99.70 183	99.36 358	97.70 298	99.88 234	99.20 146	99.87 192	99.59 206

CANet		99.11 248	99.05 237	99.28 306	98.83 440	98.56 336	98.71 342	99.41 330	99.25 232	99.23 340	99.22 390	97.66 306	99.94 97	99.19 148	99.97 73	99.33 322

EI-MVSNet-UG-set		99.48 126	99.50 118	99.42 257	99.57 261	98.65 328	99.24 184	99.46 318	99.68 129	99.80 123	99.66 220	98.99 144	99.89 219	99.19 148	99.90 155	99.72 97

xiu_mvs_v1_base_debu		99.23 205	99.34 162	98.91 363	99.59 245	98.23 360	98.47 375	99.66 207	99.61 154	99.68 191	98.94 429	99.39 66	99.97 44	99.18 150	99.55 347	98.51 446

xiu_mvs_v1_base		99.23 205	99.34 162	98.91 363	99.59 245	98.23 360	98.47 375	99.66 207	99.61 154	99.68 191	98.94 429	99.39 66	99.97 44	99.18 150	99.55 347	98.51 446

xiu_mvs_v1_base_debi		99.23 205	99.34 162	98.91 363	99.59 245	98.23 360	98.47 375	99.66 207	99.61 154	99.68 191	98.94 429	99.39 66	99.97 44	99.18 150	99.55 347	98.51 446

VPNet		99.46 138	99.37 151	99.71 126	99.82 89	99.59 152	99.48 107	99.70 186	99.81 92	99.69 186	99.58 286	97.66 306	99.86 268	99.17 153	99.44 368	99.67 129

UniMVSNet_NR-MVSNet		99.37 171	99.25 189	99.72 120	99.47 315	99.56 161	98.97 293	99.61 238	99.43 200	99.67 198	99.28 376	97.85 290	99.95 80	99.17 153	99.81 238	99.65 152

DU-MVS		99.33 185	99.21 194	99.71 126	99.43 327	99.56 161	98.83 321	99.53 293	99.38 210	99.67 198	99.36 358	97.67 302	99.95 80	99.17 153	99.81 238	99.63 170

EI-MVSNet-Vis-set		99.47 136	99.49 122	99.42 257	99.57 261	98.66 325	99.24 184	99.46 318	99.67 133	99.79 129	99.65 229	98.97 150	99.89 219	99.15 156	99.89 169	99.71 102

EI-MVSNet		99.38 167	99.44 136	99.21 321	99.58 251	98.09 374	99.26 177	99.46 318	99.62 149	99.75 154	99.67 215	98.54 215	99.85 287	99.15 156	99.92 141	99.68 120

VNet		99.18 228	99.06 232	99.56 204	99.24 381	99.36 221	99.33 148	99.31 358	99.67 133	99.47 280	99.57 293	96.48 347	99.84 303	99.15 156	99.30 387	99.47 272

EG-PatchMatch MVS		99.57 97	99.56 104	99.62 176	99.77 145	99.33 227	99.26 177	99.76 150	99.32 219	99.80 123	99.78 127	99.29 85	99.87 249	99.15 156	99.91 153	99.66 143

PVSNet_Blended_VisFu		99.40 160	99.38 148	99.44 251	99.90 37	98.66 325	98.94 302	99.91 52	97.97 384	99.79 129	99.73 162	99.05 135	99.97 44	99.15 156	99.99 16	99.68 120

IterMVS-LS		99.41 158	99.47 125	99.25 317	99.81 101	98.09 374	98.85 316	99.76 150	99.62 149	99.83 108	99.64 231	98.54 215	99.97 44	99.15 156	99.99 16	99.68 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 110	99.47 125	99.76 85	99.58 251	99.64 132	99.30 159	99.63 228	99.61 154	99.71 179	99.56 297	98.76 180	99.96 69	99.14 162	99.92 141	99.68 120

MVSTER		98.47 339	98.22 345	99.24 319	99.06 414	98.35 357	99.08 251	99.46 318	99.27 228	99.75 154	99.66 220	88.61 444	99.85 287	99.14 162	99.92 141	99.52 251

diffmvs_AUTHOR		99.48 126	99.48 123	99.47 240	99.80 110	98.89 304	98.71 342	99.82 100	99.79 100	99.66 204	99.63 246	98.87 166	99.88 234	99.13 164	99.95 107	99.62 182

Anonymous20231206		99.35 177	99.31 169	99.47 240	99.74 173	99.06 284	99.28 168	99.74 161	99.23 236	99.72 174	99.53 309	97.63 308	99.88 234	99.11 165	99.84 210	99.48 268

Syy-MVS		98.17 364	97.85 376	99.15 329	98.50 463	98.79 314	98.60 351	99.21 381	97.89 390	96.76 466	96.37 489	95.47 373	99.57 452	99.10 166	98.73 433	99.09 381

ttmdpeth		99.48 126	99.55 106	99.29 303	99.76 149	98.16 368	99.33 148	99.95 36	99.79 100	99.36 310	99.89 41	99.13 112	99.77 372	99.09 167	99.64 319	99.93 20

MVS_Test		99.28 192	99.31 169	99.19 324	99.35 348	98.79 314	99.36 138	99.49 311	99.17 249	99.21 345	99.67 215	98.78 177	99.66 431	99.09 167	99.66 315	99.10 376

FE-MVSNET3		98.87 295	98.71 297	99.35 284	99.59 245	98.88 305	97.17 462	99.64 225	98.94 279	99.27 333	99.22 390	95.57 370	99.83 319	99.08 169	99.92 141	99.35 317

testgi		99.29 191	99.26 187	99.37 277	99.75 165	98.81 310	98.84 318	99.89 61	98.38 351	99.75 154	99.04 413	99.36 75	99.86 268	99.08 169	99.25 395	99.45 277

1112_ss		99.05 260	98.84 285	99.67 139	99.66 224	99.29 233	98.52 369	99.82 100	97.65 402	99.43 290	99.16 397	96.42 350	99.91 178	99.07 171	99.84 210	99.80 65

CANet_DTU		98.91 288	98.85 283	99.09 338	98.79 446	98.13 369	98.18 396	99.31 358	99.48 180	98.86 385	99.51 315	96.56 343	99.95 80	99.05 172	99.95 107	99.19 356

Baseline_NR-MVSNet		99.49 124	99.37 151	99.82 46	99.91 31	99.84 27	98.83 321	99.86 76	99.68 129	99.65 207	99.88 50	97.67 302	99.87 249	99.03 173	99.86 200	99.76 84

FMVSNet2		99.35 177	99.28 182	99.55 211	99.49 304	99.35 224	99.45 115	99.57 266	99.44 193	99.70 183	99.74 157	97.21 323	99.87 249	99.03 173	99.94 123	99.44 289

Test_1112_low_res		98.95 285	98.73 295	99.63 167	99.68 215	99.15 268	98.09 408	99.80 117	97.14 428	99.46 284	99.40 344	96.11 361	99.89 219	99.01 175	99.84 210	99.84 52

VDD-MVS		99.20 221	99.11 214	99.44 251	99.43 327	98.98 289	99.50 100	98.32 438	99.80 96	99.56 250	99.69 199	96.99 333	99.85 287	98.99 176	99.73 282	99.50 259

DeepC-MVS	98.90 4	99.62 88	99.61 84	99.67 139	99.72 182	99.44 193	99.24 184	99.71 177	99.27 228	99.93 53	99.90 36	99.70 31	99.93 118	98.99 176	99.99 16	99.64 164
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
pmmvs-eth3d		99.48 126	99.47 125	99.51 227	99.77 145	99.41 207	98.81 326	99.66 207	99.42 204	99.75 154	99.66 220	99.20 99	99.76 376	98.98 178	99.99 16	99.36 314

EPNet_dtu		97.62 385	97.79 379	97.11 446	96.67 483	92.31 469	98.51 370	98.04 445	99.24 234	95.77 475	99.47 329	93.78 392	99.66 431	98.98 178	99.62 324	99.37 311
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 182	99.32 167	99.39 271	99.67 222	98.77 316	98.57 360	99.81 113	99.61 154	99.48 278	99.41 340	98.47 227	99.86 268	98.97 180	99.90 155	99.53 240
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		99.40 160	99.31 169	99.68 135	99.43 327	99.55 165	99.73 30	99.50 307	99.46 188	99.88 83	99.36 358	97.54 309	99.87 249	98.97 180	99.87 192	99.63 170

TestfortrainingZip a		99.61 92	99.53 113	99.85 32	99.76 149	99.84 27	99.38 126	99.78 136	99.58 164	99.81 116	99.66 220	99.02 139	99.90 197	98.96 182	99.79 250	99.81 64

viewdifsd2359ckpt07		99.51 117	99.50 118	99.52 223	99.80 110	99.19 260	98.92 306	99.88 66	99.72 113	99.64 210	99.62 255	99.06 133	99.81 349	98.96 182	99.94 123	99.56 220

GBi-Net		99.42 152	99.31 169	99.73 112	99.49 304	99.77 64	99.68 49	99.70 186	99.44 193	99.62 225	99.83 84	97.21 323	99.90 197	98.96 182	99.90 155	99.53 240

FMVSNet5		97.80 377	97.25 394	99.42 257	98.83 440	98.97 292	99.38 126	99.80 117	98.87 291	99.25 336	99.69 199	80.60 467	99.91 178	98.96 182	99.90 155	99.38 308

test1		99.42 152	99.31 169	99.73 112	99.49 304	99.77 64	99.68 49	99.70 186	99.44 193	99.62 225	99.83 84	97.21 323	99.90 197	98.96 182	99.90 155	99.53 240

FMVSNet3		98.80 303	98.63 304	99.32 294	99.13 400	98.72 319	99.10 243	99.48 312	99.23 236	99.62 225	99.64 231	92.57 406	99.86 268	98.96 182	99.90 155	99.39 306

UnsupCasMVSNet_eth		98.83 299	98.57 311	99.59 189	99.68 215	99.45 191	98.99 288	99.67 202	99.48 180	99.55 255	99.36 358	94.92 377	99.86 268	98.95 188	96.57 473	99.45 277

CHOSEN 280x420		98.41 344	98.41 327	98.40 401	99.34 357	95.89 442	96.94 468	99.44 324	98.80 303	99.25 336	99.52 313	93.51 396	99.98 27	98.94 189	99.98 50	99.32 325

E4		99.61 92	99.59 90	99.66 146	99.84 72	99.53 168	99.08 251	99.84 89	99.65 140	99.74 164	99.80 104	99.45 58	99.77 372	98.93 190	99.95 107	99.69 113

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 72	99.88 234	98.93 190	99.95 107	99.60 199

viewmacassd2359aftdt		99.63 81	99.61 84	99.68 135	99.84 72	99.61 146	99.14 223	99.87 70	99.71 118	99.75 154	99.77 137	99.54 50	99.72 393	98.91 192	99.96 87	99.70 105

alignmvs		98.28 354	97.96 365	99.25 317	99.12 402	98.93 299	99.03 266	98.42 431	99.64 144	98.72 400	97.85 468	90.86 428	99.62 443	98.88 193	99.13 401	99.19 356

testing3-2		96.51 416	96.43 411	96.74 450	99.36 344	91.38 477	99.10 243	97.87 451	99.48 180	98.57 414	98.71 444	76.65 477	99.66 431	98.87 194	99.26 394	99.18 358

MGCFI-Net		99.02 266	99.01 250	99.06 345	99.11 407	98.60 333	99.63 64	99.67 202	99.63 146	98.58 412	97.65 471	99.07 126	99.57 452	98.85 195	98.92 417	99.03 398

sss		98.90 290	98.77 294	99.27 311	99.48 309	98.44 348	98.72 340	99.32 354	97.94 388	99.37 309	99.35 363	96.31 356	99.91 178	98.85 195	99.63 322	99.47 272

xiu_mvs_v2_base		99.02 266	99.11 214	98.77 382	99.37 341	98.09 374	98.13 403	99.51 303	99.47 185	99.42 293	98.54 453	99.38 70	99.97 44	98.83 197	99.33 383	98.24 458

PS-MVSNAJ		99.00 275	99.08 226	98.76 383	99.37 341	98.10 373	98.00 419	99.51 303	99.47 185	99.41 299	98.50 455	99.28 87	99.97 44	98.83 197	99.34 382	98.20 462

E2		99.54 110	99.51 116	99.62 176	99.78 132	99.47 179	99.01 275	99.82 100	99.55 167	99.69 186	99.77 137	99.26 91	99.76 376	98.82 199	99.93 135	99.62 182

E3		99.54 110	99.51 116	99.62 176	99.78 132	99.47 179	99.01 275	99.82 100	99.55 167	99.69 186	99.77 137	99.25 95	99.76 376	98.82 199	99.93 135	99.62 182

D2MVS		99.22 214	99.19 197	99.29 303	99.69 207	98.74 318	98.81 326	99.41 330	98.55 332	99.68 191	99.69 199	98.13 268	99.87 249	98.82 199	99.98 50	99.24 340

PatchT		98.45 341	98.32 337	98.83 376	98.94 428	98.29 358	99.24 184	98.82 408	99.84 76	99.08 362	99.76 144	91.37 417	99.94 97	98.82 199	99.00 412	98.26 457

testf1		99.63 81	99.60 88	99.72 120	99.94 18	99.95 2	99.47 110	99.89 61	99.43 200	99.88 83	99.80 104	99.26 91	99.90 197	98.81 203	99.88 179	99.32 325

APD_test2		99.63 81	99.60 88	99.72 120	99.94 18	99.95 2	99.47 110	99.89 61	99.43 200	99.88 83	99.80 104	99.26 91	99.90 197	98.81 203	99.88 179	99.32 325

sasdasda		99.02 266	99.00 254	99.09 338	99.10 409	98.70 320	99.61 73	99.66 207	99.63 146	98.64 406	97.65 471	99.04 136	99.54 456	98.79 205	98.92 417	99.04 396

Effi-MVS+		99.06 257	98.97 265	99.34 286	99.31 364	98.98 289	98.31 388	99.91 52	98.81 301	98.79 394	98.94 429	99.14 110	99.84 303	98.79 205	98.74 430	99.20 353

canonicalmvs		99.02 266	99.00 254	99.09 338	99.10 409	98.70 320	99.61 73	99.66 207	99.63 146	98.64 406	97.65 471	99.04 136	99.54 456	98.79 205	98.92 417	99.04 396

VDDNet		98.97 279	98.82 288	99.42 257	99.71 186	98.81 310	99.62 67	98.68 415	99.81 92	99.38 307	99.80 104	94.25 386	99.85 287	98.79 205	99.32 385	99.59 206

CR-MVSNet		98.35 351	98.20 347	98.83 376	99.05 415	98.12 370	99.30 159	99.67 202	97.39 416	99.16 351	99.79 115	91.87 414	99.91 178	98.78 209	98.77 426	98.44 451

test_method		91.72 445	92.32 448	89.91 464	93.49 487	70.18 490	90.28 479	99.56 271	61.71 482	95.39 477	99.52 313	93.90 388	99.94 97	98.76 210	98.27 450	99.62 182

RPMNet		98.60 322	98.53 317	98.83 376	99.05 415	98.12 370	99.30 159	99.62 231	99.86 66	99.16 351	99.74 157	92.53 408	99.92 149	98.75 211	98.77 426	98.44 451

mamba_0408		99.54 110	99.55 106	99.54 217	99.71 186	99.24 247	99.27 172	99.79 126	99.72 113	99.78 133	99.64 231	99.36 75	99.93 118	98.74 212	99.90 155	99.45 277

SSM_04072		99.55 106	99.55 106	99.55 211	99.71 186	99.24 247	99.27 172	99.79 126	99.72 113	99.78 133	99.64 231	99.36 75	99.97 44	98.74 212	99.90 155	99.45 277

SSM_0407		99.56 101	99.56 104	99.54 217	99.71 186	99.24 247	99.15 219	99.84 89	99.80 96	99.78 133	99.70 190	99.44 60	99.93 118	98.74 212	99.90 155	99.45 277

SSM_0404		99.57 97	99.58 94	99.54 217	99.76 149	99.28 235	99.19 201	99.84 89	99.80 96	99.78 133	99.70 190	99.44 60	99.93 118	98.74 212	99.95 107	99.41 300

pmmvs4		99.13 241	99.06 232	99.36 282	99.57 261	99.10 279	98.01 417	99.25 371	98.78 306	99.58 239	99.44 336	98.24 255	99.76 376	98.74 212	99.93 135	99.22 346

viewmanbaseed2359cas		99.50 119	99.47 125	99.61 182	99.73 177	99.52 172	99.03 266	99.83 94	99.49 177	99.65 207	99.64 231	99.18 101	99.71 398	98.73 217	99.92 141	99.58 211

tttt0517		97.62 385	97.20 395	98.90 369	99.76 149	97.40 407	99.48 107	94.36 474	99.06 266	99.70 183	99.49 322	84.55 460	99.94 97	98.73 217	99.65 317	99.36 314

viewcassd2359sk11		99.48 126	99.45 132	99.58 192	99.73 177	99.42 200	98.96 297	99.80 117	99.44 193	99.63 215	99.74 157	99.09 119	99.76 376	98.72 219	99.91 153	99.57 217

EPP-MVSNet		99.17 233	99.00 254	99.66 146	99.80 110	99.43 197	99.70 38	99.24 374	99.48 180	99.56 250	99.77 137	94.89 378	99.93 118	98.72 219	99.89 169	99.63 170

FE-MVSNET		99.45 142	99.36 156	99.71 126	99.84 72	99.64 132	99.16 216	99.91 52	98.65 321	99.73 169	99.73 162	98.54 215	99.82 333	98.71 221	99.96 87	99.67 129

Anonymous20240529		99.42 152	99.34 162	99.65 153	99.53 284	99.60 150	99.63 64	99.39 340	99.47 185	99.76 149	99.78 127	98.13 268	99.86 268	98.70 222	99.68 306	99.49 264

ACMH	98.42 6	99.59 96	99.54 109	99.72 120	99.86 57	99.62 140	99.56 87	99.79 126	98.77 308	99.80 123	99.85 69	99.64 35	99.85 287	98.70 222	99.89 169	99.70 105
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 185	99.28 182	99.47 240	99.57 261	99.39 211	99.78 17	99.43 327	98.87 291	99.57 242	99.82 91	98.06 274	99.87 249	98.69 224	99.73 282	99.15 365

LFMVS		98.46 340	98.19 350	99.26 314	99.24 381	98.52 344	99.62 67	96.94 463	99.87 63	99.31 326	99.58 286	91.04 422	99.81 349	98.68 225	99.42 372	99.45 277

WR-MVS		99.11 248	98.93 270	99.66 146	99.30 368	99.42 200	98.42 381	99.37 345	99.04 267	99.57 242	99.20 395	96.89 335	99.86 268	98.66 226	99.87 192	99.70 105

mvsmamba		99.08 253	98.95 268	99.45 247	99.36 344	99.18 265	99.39 123	98.81 409	99.37 211	99.35 312	99.70 190	96.36 355	99.94 97	98.66 226	99.59 338	99.22 346

viewdifsd2359ckpt13		99.42 152	99.37 151	99.57 200	99.72 182	99.46 185	99.01 275	99.80 117	99.20 241	99.51 272	99.60 273	98.92 157	99.70 402	98.65 228	99.90 155	99.55 224

RRT-MVS		99.08 253	99.00 254	99.33 289	99.27 375	98.65 328	99.62 67	99.93 39	99.66 137	99.67 198	99.82 91	95.27 375	99.93 118	98.64 229	99.09 405	99.41 300

E3new		99.42 152	99.37 151	99.56 204	99.68 215	99.38 213	98.93 305	99.79 126	99.30 223	99.55 255	99.69 199	98.88 164	99.76 376	98.63 230	99.89 169	99.53 240

Anonymous202405211		98.75 307	98.46 321	99.63 167	99.34 357	99.66 120	99.47 110	97.65 454	99.28 227	99.56 250	99.50 318	93.15 400	99.84 303	98.62 231	99.58 340	99.40 303

lecture		99.56 101	99.48 123	99.81 54	99.78 132	99.86 19	99.50 100	99.70 186	99.59 162	99.75 154	99.71 180	98.94 153	99.92 149	98.59 232	99.76 265	99.66 143

EPNet		98.13 365	97.77 380	99.18 326	94.57 486	97.99 380	99.24 184	97.96 447	99.74 108	97.29 459	99.62 255	93.13 401	99.97 44	98.59 232	99.83 218	99.58 211
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 260	99.09 224	98.91 363	99.21 386	98.36 356	98.82 325	99.47 315	98.85 294	98.90 380	99.56 297	98.78 177	99.09 472	98.57 234	99.68 306	99.26 337

Patchmatch-RL test		98.60 322	98.36 332	99.33 289	99.77 145	99.07 282	98.27 390	99.87 70	98.91 286	99.74 164	99.72 170	90.57 433	99.79 360	98.55 235	99.85 205	99.11 374

pmmvs3		98.08 368	97.80 377	98.91 363	99.41 334	97.69 398	97.87 432	99.66 207	95.87 447	99.50 275	99.51 315	90.35 435	99.97 44	98.55 235	99.47 365	99.08 387

ETV-MVS		99.18 228	99.18 198	99.16 327	99.34 357	99.28 235	99.12 235	99.79 126	99.48 180	98.93 374	98.55 452	99.40 65	99.93 118	98.51 237	99.52 357	98.28 456

viewdifsd2359ckpt09		99.24 203	99.16 200	99.49 233	99.70 201	99.22 253	98.88 310	99.81 113	98.70 316	99.38 307	99.37 353	98.22 260	99.76 376	98.48 238	99.88 179	99.51 253

jason		99.16 234	99.11 214	99.32 294	99.75 165	98.44 348	98.26 392	99.39 340	98.70 316	99.74 164	99.30 372	98.54 215	99.97 44	98.48 238	99.82 228	99.55 224
jason: jason.
APDe-MVS		99.48 126	99.36 156	99.85 32	99.55 275	99.81 48	99.50 100	99.69 194	98.99 271	99.75 154	99.71 180	98.79 175	99.93 118	98.46 240	99.85 205	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		99.30 189	99.29 179	99.31 298	99.71 186	98.55 338	98.17 398	99.71 177	99.41 205	99.73 169	99.60 273	99.17 103	99.92 149	98.45 241	99.70 293	99.45 277

IMVS_0407		99.38 167	99.42 140	99.28 306	99.71 186	98.55 338	99.27 172	99.71 177	99.41 205	99.73 169	99.60 273	99.17 103	99.83 319	98.45 241	99.70 293	99.45 277

IMVS_0404		99.23 205	99.20 195	99.32 294	99.71 186	98.55 338	98.57 360	99.71 177	99.41 205	99.52 265	99.60 273	98.12 270	99.95 80	98.45 241	99.70 293	99.45 277

IMVS_0403		99.37 171	99.39 145	99.28 306	99.71 186	98.55 338	99.19 201	99.71 177	99.41 205	99.67 198	99.60 273	99.12 115	99.84 303	98.45 241	99.70 293	99.45 277

CL-MVSNet_self_test		98.71 313	98.56 315	99.15 329	99.22 384	98.66 325	97.14 463	99.51 303	98.09 377	99.54 258	99.27 378	96.87 336	99.74 388	98.43 245	98.96 414	99.03 398

our_test_3		98.85 298	99.09 224	98.13 414	99.66 224	94.90 456	97.72 437	99.58 264	99.07 264	99.64 210	99.62 255	98.19 264	99.93 118	98.41 246	99.95 107	99.55 224

Gipuma		99.57 97	99.59 90	99.49 233	99.98 3	99.71 100	99.72 33	99.84 89	99.81 92	99.94 48	99.78 127	98.91 160	99.71 398	98.41 246	99.95 107	99.05 394
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 396	96.91 405	98.74 384	97.72 479	97.57 400	97.60 443	97.36 460	98.00 380	99.21 345	98.02 464	90.04 438	99.79 360	98.37 248	95.89 478	98.86 421

PM-MVS		99.36 175	99.29 179	99.58 192	99.83 80	99.66 120	98.95 300	99.86 76	98.85 294	99.81 116	99.73 162	98.40 240	99.92 149	98.36 249	99.83 218	99.17 361

baseline1		97.73 380	97.33 391	98.96 354	99.30 368	97.73 396	99.40 121	98.42 431	99.33 218	99.46 284	99.21 393	91.18 420	99.82 333	98.35 250	91.26 481	99.32 325

MVS-HIRNet		97.86 374	98.22 345	96.76 448	99.28 373	91.53 475	98.38 383	92.60 480	99.13 257	99.31 326	99.96 15	97.18 327	99.68 421	98.34 251	99.83 218	99.07 392

GA-MVS		97.99 373	97.68 383	98.93 360	99.52 291	98.04 378	97.19 461	99.05 398	98.32 364	98.81 390	98.97 425	89.89 440	99.41 467	98.33 252	99.05 408	99.34 321

Fast-Effi-MVS+		99.02 266	98.87 281	99.46 244	99.38 339	99.50 174	99.04 263	99.79 126	97.17 426	98.62 408	98.74 443	99.34 79	99.95 80	98.32 253	99.41 373	98.92 414

MDA-MVSNet_test_wron		98.95 285	98.99 261	98.85 372	99.64 230	97.16 413	98.23 394	99.33 352	98.93 283	99.56 250	99.66 220	97.39 316	99.83 319	98.29 254	99.88 179	99.55 224

N_pmnet		98.73 310	98.53 317	99.35 284	99.72 182	98.67 322	98.34 385	94.65 473	98.35 358	99.79 129	99.68 211	98.03 275	99.93 118	98.28 255	99.92 141	99.44 289

ET-MVSNet_ETH3D		96.78 408	96.07 418	98.91 363	99.26 378	97.92 387	97.70 439	96.05 468	97.96 387	92.37 481	98.43 456	87.06 448	99.90 197	98.27 256	97.56 467	98.91 415

thisisatest0530		97.45 391	96.95 402	98.94 357	99.68 215	97.73 396	99.09 248	94.19 476	98.61 328	99.56 250	99.30 372	84.30 462	99.93 118	98.27 256	99.54 352	99.16 363

YYNet1		98.95 285	98.99 261	98.84 374	99.64 230	97.14 415	98.22 395	99.32 354	98.92 285	99.59 237	99.66 220	97.40 314	99.83 319	98.27 256	99.90 155	99.55 224

reproduce_model		99.50 119	99.40 144	99.83 41	99.60 239	99.83 35	99.12 235	99.68 197	99.49 177	99.80 123	99.79 115	99.01 141	99.93 118	98.24 259	99.82 228	99.73 93

ACMM	98.09 11	99.46 138	99.38 148	99.72 120	99.80 110	99.69 112	99.13 230	99.65 217	98.99 271	99.64 210	99.72 170	99.39 66	99.86 268	98.23 260	99.81 238	99.60 199
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 282	98.87 281	99.24 319	99.57 261	98.40 351	98.12 404	99.18 386	98.28 366	99.63 215	99.13 399	98.02 276	99.97 44	98.22 261	99.69 301	99.35 317

3Dnovator	99.15 2	99.43 149	99.36 156	99.65 153	99.39 336	99.42 200	99.70 38	99.56 271	99.23 236	99.35 312	99.80 104	99.17 103	99.95 80	98.21 262	99.84 210	99.59 206

Fast-Effi-MVS+-dtu		99.20 221	99.12 211	99.43 255	99.25 379	99.69 112	99.05 258	99.82 100	99.50 175	98.97 370	99.05 411	98.98 148	99.98 27	98.20 263	99.24 397	98.62 436

MS-PatchMatch		99.00 275	98.97 265	99.09 338	99.11 407	98.19 364	98.76 335	99.33 352	98.49 341	99.44 286	99.58 286	98.21 261	99.69 409	98.20 263	99.62 324	99.39 306

TSAR-MVS + GP.		99.12 244	99.04 243	99.38 274	99.34 357	99.16 266	98.15 400	99.29 362	98.18 373	99.63 215	99.62 255	99.18 101	99.68 421	98.20 263	99.74 276	99.30 331

DP-MVS		99.48 126	99.39 145	99.74 101	99.57 261	99.62 140	99.29 166	99.61 238	99.87 63	99.74 164	99.76 144	98.69 190	99.87 249	98.20 263	99.80 245	99.75 87

MVP-Stereo		99.16 234	99.08 226	99.43 255	99.48 309	99.07 282	99.08 251	99.55 277	98.63 324	99.31 326	99.68 211	98.19 264	99.78 363	98.18 267	99.58 340	99.45 277
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 149	99.30 174	99.80 64	99.83 80	99.81 48	99.52 92	99.70 186	98.35 358	99.51 272	99.50 318	99.31 83	99.88 234	98.18 267	99.84 210	99.69 113

MDA-MVSNet-bldmvs		99.06 257	99.05 237	99.07 343	99.80 110	97.83 391	98.89 309	99.72 174	99.29 224	99.63 215	99.70 190	96.47 348	99.89 219	98.17 269	99.82 228	99.50 259

JIA-IIPM		98.06 369	97.92 372	98.50 396	98.59 459	97.02 417	98.80 329	98.51 426	99.88 61	97.89 444	99.87 56	91.89 413	99.90 197	98.16 270	97.68 466	98.59 439

EIA-MVS		99.12 244	99.01 250	99.45 247	99.36 344	99.62 140	99.34 142	99.79 126	98.41 347	98.84 387	98.89 433	98.75 182	99.84 303	98.15 271	99.51 358	98.89 418

miper_lstm_enhance		98.65 318	98.60 305	98.82 379	99.20 389	97.33 409	97.78 435	99.66 207	99.01 270	99.59 237	99.50 318	94.62 383	99.85 287	98.12 272	99.90 155	99.26 337

reproduce-ours		99.46 138	99.35 160	99.82 46	99.56 272	99.83 35	99.05 258	99.65 217	99.45 191	99.78 133	99.78 127	98.93 154	99.93 118	98.11 273	99.81 238	99.70 105

our_new_method		99.46 138	99.35 160	99.82 46	99.56 272	99.83 35	99.05 258	99.65 217	99.45 191	99.78 133	99.78 127	98.93 154	99.93 118	98.11 273	99.81 238	99.70 105

Effi-MVS+-dtu		99.07 256	98.92 274	99.52 223	98.89 433	99.78 58	99.15 219	99.66 207	99.34 215	98.92 377	99.24 388	97.69 300	99.98 27	98.11 273	99.28 390	98.81 425

tpm		97.15 400	96.95 402	97.75 428	98.91 429	94.24 459	99.32 151	97.96 447	97.71 400	98.29 425	99.32 367	86.72 454	99.92 149	98.10 276	96.24 476	99.09 381

DeepPCF-MVS	98.42 6	99.18 228	99.02 246	99.67 139	99.22 384	99.75 79	97.25 459	99.47 315	98.72 313	99.66 204	99.70 190	99.29 85	99.63 442	98.07 277	99.81 238	99.62 182

ppachtmachnet_test		98.89 293	99.12 211	98.20 412	99.66 224	95.24 452	97.63 441	99.68 197	99.08 262	99.78 133	99.62 255	98.65 198	99.88 234	98.02 278	99.96 87	99.48 268

tpmrst		97.73 380	98.07 358	96.73 451	98.71 455	92.00 470	99.10 243	98.86 405	98.52 337	98.92 377	99.54 307	91.90 412	99.82 333	98.02 278	99.03 410	98.37 453

CSCG		99.37 171	99.29 179	99.60 186	99.71 186	99.46 185	99.43 119	99.85 82	98.79 304	99.41 299	99.60 273	98.92 157	99.92 149	98.02 278	99.92 141	99.43 295

eth_miper_zixun_eth		98.68 316	98.71 297	98.60 391	99.10 409	96.84 422	97.52 449	99.54 283	98.94 279	99.58 239	99.48 325	96.25 359	99.76 376	98.01 281	99.93 135	99.21 349

Patchmtry		98.78 304	98.54 316	99.49 233	98.89 433	99.19 260	99.32 151	99.67 202	99.65 140	99.72 174	99.79 115	91.87 414	99.95 80	98.00 282	99.97 73	99.33 322

PVSNet_BlendedMVS		99.03 264	99.01 250	99.09 338	99.54 277	97.99 380	98.58 356	99.82 100	97.62 403	99.34 316	99.71 180	98.52 223	99.77 372	97.98 283	99.97 73	99.52 251

PVSNet_Blended		98.70 314	98.59 307	99.02 348	99.54 277	97.99 380	97.58 444	99.82 100	95.70 451	99.34 316	98.98 423	98.52 223	99.77 372	97.98 283	99.83 218	99.30 331

cl____		98.54 330	98.41 327	98.92 361	99.03 419	97.80 394	97.46 451	99.59 255	98.90 287	99.60 234	99.46 332	93.85 390	99.78 363	97.97 285	99.89 169	99.17 361

DIV-MVS_self_test		98.54 330	98.42 326	98.92 361	99.03 419	97.80 394	97.46 451	99.59 255	98.90 287	99.60 234	99.46 332	93.87 389	99.78 363	97.97 285	99.89 169	99.18 358

AUN-MVS		97.82 376	97.38 390	99.14 332	99.27 375	98.53 342	98.72 340	99.02 400	98.10 375	97.18 462	99.03 417	89.26 442	99.85 287	97.94 287	97.91 462	99.03 398

FA-MVS(test-final)		98.52 332	98.32 337	99.10 337	99.48 309	98.67 322	99.77 19	98.60 422	97.35 418	99.63 215	99.80 104	93.07 402	99.84 303	97.92 288	99.30 387	98.78 428

ambc				99.20 323	99.35 348	98.53 342	99.17 210	99.46 318		99.67 198	99.80 104	98.46 230	99.70 402	97.92 288	99.70 293	99.38 308

USDC		98.96 282	98.93 270	99.05 346	99.54 277	97.99 380	97.07 466	99.80 117	98.21 370	99.75 154	99.77 137	98.43 233	99.64 440	97.90 290	99.88 179	99.51 253

OPM-MVS		99.26 198	99.13 207	99.63 167	99.70 201	99.61 146	98.58 356	99.48 312	98.50 339	99.52 265	99.63 246	99.14 110	99.76 376	97.89 291	99.77 263	99.51 253
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 187	99.17 199	99.77 78	99.69 207	99.80 52	99.14 223	99.31 358	99.16 251	99.62 225	99.61 265	98.35 244	99.91 178	97.88 292	99.72 288	99.61 195
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	99.70 201	99.79 55	99.14 223	99.61 238					99.92 149	97.88 292	99.72 288	99.77 79

c3_l		98.72 311	98.71 297	98.72 385	99.12 402	97.22 412	97.68 440	99.56 271	98.90 287	99.54 258	99.48 325	96.37 354	99.73 391	97.88 292	99.88 179	99.21 349

3Dnovator+	98.92 3	99.35 177	99.24 191	99.67 139	99.35 348	99.47 179	99.62 67	99.50 307	99.44 193	99.12 358	99.78 127	98.77 179	99.94 97	97.87 295	99.72 288	99.62 182

miper_ehance_all_eth		98.59 325	98.59 307	98.59 392	98.98 425	97.07 416	97.49 450	99.52 298	98.50 339	99.52 265	99.37 353	96.41 352	99.71 398	97.86 296	99.62 324	99.00 405

WTY-MVS		98.59 325	98.37 331	99.26 314	99.43 327	98.40 351	98.74 338	99.13 393	98.10 375	99.21 345	99.24 388	94.82 380	99.90 197	97.86 296	98.77 426	99.49 264

APD_test1		99.36 175	99.28 182	99.61 182	99.89 39	99.89 10	99.32 151	99.74 161	99.18 244	99.69 186	99.75 152	98.41 236	99.84 303	97.85 298	99.70 293	99.10 376

SED-MVS		99.40 160	99.28 182	99.77 78	99.69 207	99.82 43	99.20 195	99.54 283	99.13 257	99.82 109	99.63 246	98.91 160	99.92 149	97.85 298	99.70 293	99.58 211

test_241102_TWO								99.54 283	99.13 257	99.76 149	99.63 246	98.32 249	99.92 149	97.85 298	99.69 301	99.75 87

MVS_111021_HR		99.12 244	99.02 246	99.40 268	99.50 299	99.11 272	97.92 428	99.71 177	98.76 311	99.08 362	99.47 329	99.17 103	99.54 456	97.85 298	99.76 265	99.54 234

MTAPA		99.35 177	99.20 195	99.80 64	99.81 101	99.81 48	99.33 148	99.53 293	99.27 228	99.42 293	99.63 246	98.21 261	99.95 80	97.83 302	99.79 250	99.65 152

MSC_two_6792asdad				99.74 101	99.03 419	99.53 168		99.23 375					99.92 149	97.77 303	99.69 301	99.78 75

No_MVS				99.74 101	99.03 419	99.53 168		99.23 375					99.92 149	97.77 303	99.69 301	99.78 75

TESTMET0.1,1		96.24 423	95.84 424	97.41 437	98.24 470	93.84 462	97.38 453	95.84 469	98.43 344	97.81 450	98.56 451	79.77 471	99.89 219	97.77 303	98.77 426	98.52 445

ACMH+	98.40 8	99.50 119	99.43 138	99.71 126	99.86 57	99.76 71	99.32 151	99.77 142	99.53 171	99.77 145	99.76 144	99.26 91	99.78 363	97.77 303	99.88 179	99.60 199

IU-MVS					99.69 207	99.77 64		99.22 378	97.50 410	99.69 186				97.75 307	99.70 293	99.77 79

114514_t		98.49 337	98.11 355	99.64 160	99.73 177	99.58 157	99.24 184	99.76 150	89.94 474	99.42 293	99.56 297	97.76 297	99.86 268	97.74 308	99.82 228	99.47 272

DVP-MVS++		99.38 167	99.25 189	99.77 78	99.03 419	99.77 64	99.74 27	99.61 238	99.18 244	99.76 149	99.61 265	99.00 142	99.92 149	97.72 309	99.60 334	99.62 182

test_0728_THIRD									99.18 244	99.62 225	99.61 265	98.58 206	99.91 178	97.72 309	99.80 245	99.77 79

EGC-MVSNET		89.05 447	85.52 450	99.64 160	99.89 39	99.78 58	99.56 87	99.52 298	24.19 483	49.96 484	99.83 84	99.15 107	99.92 149	97.71 311	99.85 205	99.21 349

miper_enhance_ethall		98.03 370	97.94 370	98.32 406	98.27 469	96.43 430	96.95 467	99.41 330	96.37 442	99.43 290	98.96 427	94.74 381	99.69 409	97.71 311	99.62 324	98.83 424

TSAR-MVS + MP.		99.34 182	99.24 191	99.63 167	99.82 89	99.37 217	99.26 177	99.35 349	98.77 308	99.57 242	99.70 190	99.27 90	99.88 234	97.71 311	99.75 269	99.65 152
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 388	97.28 392	98.40 401	98.37 467	96.75 423	97.24 460	99.37 345	97.31 420	99.41 299	99.22 390	87.30 446	99.37 468	97.70 314	99.62 324	99.08 387

MP-MVS-pluss		99.14 239	98.92 274	99.80 64	99.83 80	99.83 35	98.61 349	99.63 228	96.84 435	99.44 286	99.58 286	98.81 170	99.91 178	97.70 314	99.82 228	99.67 129
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 192	99.11 214	99.79 71	99.75 165	99.81 48	98.95 300	99.53 293	98.27 367	99.53 263	99.73 162	98.75 182	99.87 249	97.70 314	99.83 218	99.68 120

UnsupCasMVSNet_bld		98.55 329	98.27 343	99.40 268	99.56 272	99.37 217	97.97 424	99.68 197	97.49 411	99.08 362	99.35 363	95.41 374	99.82 333	97.70 314	98.19 454	99.01 404

MVS_111021_LR		99.13 241	99.03 245	99.42 257	99.58 251	99.32 229	97.91 430	99.73 165	98.68 318	99.31 326	99.48 325	99.09 119	99.66 431	97.70 314	99.77 263	99.29 334

IS-MVSNet		99.03 264	98.85 283	99.55 211	99.80 110	99.25 243	99.73 30	99.15 390	99.37 211	99.61 231	99.71 180	94.73 382	99.81 349	97.70 314	99.88 179	99.58 211

MED-MVS test				99.74 101	99.76 149	99.65 126	99.38 126	99.78 136	99.58 164	99.81 116	99.66 220		99.90 197	97.69 320	99.79 250	99.67 129

MED-MVS		99.45 142	99.36 156	99.74 101	99.76 149	99.65 126	99.38 126	99.78 136	99.31 221	99.81 116	99.66 220	99.02 139	99.90 197	97.69 320	99.79 250	99.67 129

ME-MVS		99.26 198	99.10 222	99.73 112	99.60 239	99.65 126	98.75 337	99.45 323	99.31 221	99.65 207	99.66 220	98.00 281	99.86 268	97.69 320	99.79 250	99.67 129

test-LLR		97.15 400	96.95 402	97.74 429	98.18 472	95.02 454	97.38 453	96.10 465	98.00 380	97.81 450	98.58 448	90.04 438	99.91 178	97.69 320	98.78 424	98.31 454

test-mter		96.23 424	95.73 427	97.74 429	98.18 472	95.02 454	97.38 453	96.10 465	97.90 389	97.81 450	98.58 448	79.12 474	99.91 178	97.69 320	98.78 424	98.31 454

MonoMVSNet		98.23 359	98.32 337	97.99 417	98.97 426	96.62 425	99.49 105	98.42 431	99.62 149	99.40 304	99.79 115	95.51 372	98.58 479	97.68 325	95.98 477	98.76 431

XVS		99.27 196	99.11 214	99.75 96	99.71 186	99.71 100	99.37 134	99.61 238	99.29 224	98.76 397	99.47 329	98.47 227	99.88 234	97.62 326	99.73 282	99.67 129

X-MVStestdata		96.09 428	94.87 441	99.75 96	99.71 186	99.71 100	99.37 134	99.61 238	99.29 224	98.76 397	61.30 492	98.47 227	99.88 234	97.62 326	99.73 282	99.67 129

SMA-MVS		99.19 224	99.00 254	99.73 112	99.46 319	99.73 90	99.13 230	99.52 298	97.40 415	99.57 242	99.64 231	98.93 154	99.83 319	97.61 328	99.79 250	99.63 170
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		96.71 411	96.79 410	96.46 455	98.90 430	90.71 481	99.41 120	98.68 415	94.69 464	98.14 435	99.34 366	86.32 456	99.80 357	97.60 329	98.07 460	98.88 419

PVSNet	97.47 15	98.42 343	98.44 324	98.35 403	99.46 319	96.26 434	96.70 471	99.34 351	97.68 401	99.00 369	99.13 399	97.40 314	99.72 393	97.59 330	99.68 306	99.08 387

new_pmnet		98.88 294	98.89 279	98.84 374	99.70 201	97.62 399	98.15 400	99.50 307	97.98 383	99.62 225	99.54 307	98.15 267	99.94 97	97.55 331	99.84 210	98.95 409

IB-MVS	95.41 20	95.30 443	94.46 447	97.84 425	98.76 451	95.33 450	97.33 456	96.07 467	96.02 446	95.37 478	97.41 475	76.17 478	99.96 69	97.54 332	95.44 480	98.22 459
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		99.24 203	99.11 214	99.61 182	98.38 466	99.79 55	99.57 85	99.68 197	99.61 154	99.15 353	99.71 180	98.70 189	99.91 178	97.54 332	99.68 306	99.13 373

ZNCC-MVS		99.22 214	99.04 243	99.77 78	99.76 149	99.73 90	99.28 168	99.56 271	98.19 372	99.14 355	99.29 375	98.84 169	99.92 149	97.53 334	99.80 245	99.64 164

CP-MVS		99.23 205	99.05 237	99.75 96	99.66 224	99.66 120	99.38 126	99.62 231	98.38 351	99.06 366	99.27 378	98.79 175	99.94 97	97.51 335	99.82 228	99.66 143

SD-MVS		99.01 272	99.30 174	98.15 413	99.50 299	99.40 208	98.94 302	99.61 238	99.22 240	99.75 154	99.82 91	99.54 50	95.51 483	97.48 336	99.87 192	99.54 234
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		98.49 337	98.29 342	99.11 335	98.96 427	98.42 350	97.54 445	99.32 354	97.53 408	98.47 420	98.15 463	97.88 287	99.82 333	97.46 337	99.24 397	99.09 381

DeepC-MVS_fast	98.47 5	99.23 205	99.12 211	99.56 204	99.28 373	99.22 253	98.99 288	99.40 337	99.08 262	99.58 239	99.64 231	98.90 163	99.83 319	97.44 338	99.75 269	99.63 170
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 200	99.08 226	99.76 85	99.73 177	99.70 108	99.31 156	99.59 255	98.36 353	99.36 310	99.37 353	98.80 174	99.91 178	97.43 339	99.75 269	99.68 120

ACMMPR		99.23 205	99.06 232	99.76 85	99.74 173	99.69 112	99.31 156	99.59 255	98.36 353	99.35 312	99.38 350	98.61 202	99.93 118	97.43 339	99.75 269	99.67 129

Vis-MVSNet (Re-imp)		98.77 305	98.58 310	99.34 286	99.78 132	98.88 305	99.61 73	99.56 271	99.11 261	99.24 339	99.56 297	93.00 404	99.78 363	97.43 339	99.89 169	99.35 317

MIMVSNet		98.43 342	98.20 347	99.11 335	99.53 284	98.38 355	99.58 82	98.61 420	98.96 275	99.33 318	99.76 144	90.92 424	99.81 349	97.38 342	99.76 265	99.15 365

WB-MVSnew		98.34 353	98.14 353	98.96 354	98.14 475	97.90 388	98.27 390	97.26 461	98.63 324	98.80 392	98.00 466	97.77 295	99.90 197	97.37 343	98.98 413	99.09 381

XVG-OURS-SEG-HR		99.16 234	98.99 261	99.66 146	99.84 72	99.64 132	98.25 393	99.73 165	98.39 350	99.63 215	99.43 337	99.70 31	99.90 197	97.34 344	98.64 437	99.44 289

COLMAP_ROB	98.06 12	99.45 142	99.37 151	99.70 131	99.83 80	99.70 108	99.38 126	99.78 136	99.53 171	99.67 198	99.78 127	99.19 100	99.86 268	97.32 345	99.87 192	99.55 224
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 266	98.81 290	99.65 153	99.58 251	99.49 175	98.58 356	99.07 395	98.40 349	99.04 367	99.25 383	98.51 225	99.80 357	97.31 346	99.51 358	99.65 152

region2R		99.23 205	99.05 237	99.77 78	99.76 149	99.70 108	99.31 156	99.59 255	98.41 347	99.32 321	99.36 358	98.73 186	99.93 118	97.29 347	99.74 276	99.67 129

APD-MVS_3200maxsize		99.31 188	99.16 200	99.74 101	99.53 284	99.75 79	99.27 172	99.61 238	99.19 243	99.57 242	99.64 231	98.76 180	99.90 197	97.29 347	99.62 324	99.56 220

TAPA-MVS	97.92 13	98.03 370	97.55 386	99.46 244	99.47 315	99.44 193	98.50 371	99.62 231	86.79 475	99.07 365	99.26 381	98.26 254	99.62 443	97.28 349	99.73 282	99.31 329
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 196	99.11 214	99.73 112	99.54 277	99.74 87	99.26 177	99.62 231	99.16 251	99.52 265	99.64 231	98.41 236	99.91 178	97.27 350	99.61 331	99.54 234

RE-MVS-def			99.13 207		99.54 277	99.74 87	99.26 177	99.62 231	99.16 251	99.52 265	99.64 231	98.57 207		97.27 350	99.61 331	99.54 234

testing11		96.05 430	95.41 433	97.97 419	98.78 448	95.27 451	98.59 354	98.23 441	98.86 293	96.56 469	96.91 482	75.20 479	99.69 409	97.26 352	98.29 449	98.93 412

test_yl		98.25 356	97.95 366	99.13 333	99.17 395	98.47 345	99.00 281	98.67 417	98.97 273	99.22 343	99.02 418	91.31 418	99.69 409	97.26 352	98.93 415	99.24 340

DCV-MVSNet		98.25 356	97.95 366	99.13 333	99.17 395	98.47 345	99.00 281	98.67 417	98.97 273	99.22 343	99.02 418	91.31 418	99.69 409	97.26 352	98.93 415	99.24 340

PHI-MVS		99.11 248	98.95 268	99.59 189	99.13 400	99.59 152	99.17 210	99.65 217	97.88 392	99.25 336	99.46 332	98.97 150	99.80 357	97.26 352	99.82 228	99.37 311

tfpnnormal		99.43 149	99.38 148	99.60 186	99.87 54	99.75 79	99.59 80	99.78 136	99.71 118	99.90 68	99.69 199	98.85 168	99.90 197	97.25 356	99.78 259	99.15 365

PatchmatchNet		97.65 384	97.80 377	97.18 444	98.82 443	92.49 468	99.17 210	98.39 434	98.12 374	98.79 394	99.58 286	90.71 430	99.89 219	97.23 357	99.41 373	99.16 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 278	98.80 292	99.56 204	99.25 379	99.43 197	98.54 366	99.27 366	98.58 330	98.80 392	99.43 337	98.53 220	99.70 402	97.22 358	99.59 338	99.54 234

testing3		96.48 417	95.63 429	99.01 349	99.23 383	97.81 392	98.90 308	99.10 394	98.72 313	97.84 449	97.92 467	72.44 483	99.85 287	97.21 359	99.33 383	99.35 317

HPM-MVS		99.25 200	99.07 230	99.78 75	99.81 101	99.75 79	99.61 73	99.67 202	97.72 399	99.35 312	99.25 383	99.23 96	99.92 149	97.21 359	99.82 228	99.67 129
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 224	99.00 254	99.76 85	99.76 149	99.68 115	99.38 126	99.54 283	98.34 362	99.01 368	99.50 318	98.53 220	99.93 118	97.18 361	99.78 259	99.66 143

ACMMP		99.25 200	99.08 226	99.74 101	99.79 124	99.68 115	99.50 100	99.65 217	98.07 378	99.52 265	99.69 199	98.57 207	99.92 149	97.18 361	99.79 250	99.63 170
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		96.23 424	95.74 426	97.70 431	98.86 437	95.59 447	98.66 346	98.14 443	98.96 275	97.67 455	97.06 479	76.78 476	98.92 475	97.10 363	98.41 446	98.58 441

thisisatest0515		96.98 404	96.42 412	98.66 388	99.42 332	97.47 403	97.27 458	94.30 475	97.24 422	99.15 353	98.86 435	85.01 458	99.87 249	97.10 363	99.39 375	98.63 435

XVG-ACMP-BASELINE		99.23 205	99.10 222	99.63 167	99.82 89	99.58 157	98.83 321	99.72 174	98.36 353	99.60 234	99.71 180	98.92 157	99.91 178	97.08 365	99.84 210	99.40 303

MSDG		99.08 253	98.98 264	99.37 277	99.60 239	99.13 269	97.54 445	99.74 161	98.84 297	99.53 263	99.55 305	99.10 117	99.79 360	97.07 366	99.86 200	99.18 358

SteuartSystems-ACMMP		99.30 189	99.14 205	99.76 85	99.87 54	99.66 120	99.18 205	99.60 249	98.55 332	99.57 242	99.67 215	99.03 138	99.94 97	97.01 367	99.80 245	99.69 113
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 426	95.78 425	97.49 433	98.53 461	93.83 463	98.04 414	93.94 478	98.96 275	98.46 421	98.17 462	79.86 469	99.87 249	96.99 368	99.06 406	98.78 428

EPMVS		96.53 414	96.32 413	97.17 445	98.18 472	92.97 467	99.39 123	89.95 484	98.21 370	98.61 409	99.59 283	86.69 455	99.72 393	96.99 368	99.23 399	98.81 425

MSP-MVS		99.04 263	98.79 293	99.81 54	99.78 132	99.73 90	99.35 141	99.57 266	98.54 335	99.54 258	98.99 420	96.81 337	99.93 118	96.97 370	99.53 354	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++		98.96 282	98.70 300	99.74 101	99.52 291	99.71 100	98.86 314	99.19 385	98.47 343	98.59 411	99.06 410	98.08 273	99.91 178	96.94 371	99.60 334	99.60 199

SR-MVS		99.19 224	99.00 254	99.74 101	99.51 293	99.72 95	99.18 205	99.60 249	98.85 294	99.47 280	99.58 286	98.38 241	99.92 149	96.92 372	99.54 352	99.57 217

PGM-MVS		99.20 221	99.01 250	99.77 78	99.75 165	99.71 100	99.16 216	99.72 174	97.99 382	99.42 293	99.60 273	98.81 170	99.93 118	96.91 373	99.74 276	99.66 143

HY-MVS	98.23 9	98.21 363	97.95 366	98.99 350	99.03 419	98.24 359	99.61 73	98.72 413	96.81 436	98.73 399	99.51 315	94.06 387	99.86 268	96.91 373	98.20 452	98.86 421

MDTV_nov1_ep13			97.73 381		98.70 456	90.83 479	99.15 219	98.02 446	98.51 338	98.82 389	99.61 265	90.98 423	99.66 431	96.89 375	98.92 417

GST-MVS		99.16 234	98.96 267	99.75 96	99.73 177	99.73 90	99.20 195	99.55 277	98.22 369	99.32 321	99.35 363	98.65 198	99.91 178	96.86 376	99.74 276	99.62 182

test_post1							99.14 223				51.63 494	89.54 441	99.82 333	96.86 376

SCA		98.11 366	98.36 332	97.36 438	99.20 389	92.99 466	98.17 398	98.49 428	98.24 368	99.10 361	99.57 293	96.01 364	99.94 97	96.86 376	99.62 324	99.14 370

UBG		96.53 414	95.95 420	98.29 410	98.87 436	96.31 433	98.48 374	98.07 444	98.83 298	97.32 457	96.54 487	79.81 470	99.62 443	96.84 379	98.74 430	98.95 409

XVG-OURS		99.21 219	99.06 232	99.65 153	99.82 89	99.62 140	97.87 432	99.74 161	98.36 353	99.66 204	99.68 211	99.71 28	99.90 197	96.84 379	99.88 179	99.43 295

LCM-MVSNet-Re		99.28 192	99.15 204	99.67 139	99.33 362	99.76 71	99.34 142	99.97 20	98.93 283	99.91 63	99.79 115	98.68 191	99.93 118	96.80 381	99.56 343	99.30 331

RPSCF		99.18 228	99.02 246	99.64 160	99.83 80	99.85 22	99.44 117	99.82 100	98.33 363	99.50 275	99.78 127	97.90 285	99.65 438	96.78 382	99.83 218	99.44 289

旧先验2							97.94 426		95.33 455	98.94 373			99.88 234	96.75 383

MDTV_nov1_ep13_2view						91.44 476	99.14 223		97.37 417	99.21 345		91.78 416		96.75 383		99.03 398

CLD-MVS		98.76 306	98.57 311	99.33 289	99.57 261	98.97 292	97.53 447	99.55 277	96.41 440	99.27 333	99.13 399	99.07 126	99.78 363	96.73 385	99.89 169	99.23 344
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 367	97.98 364	98.48 397	99.27 375	96.48 428	99.40 121	99.07 395	98.81 301	99.23 340	99.57 293	90.11 437	99.87 249	96.69 386	99.64 319	99.09 381

baseline2		96.83 407	96.28 414	98.46 399	99.09 412	96.91 420	98.83 321	93.87 479	97.23 423	96.23 474	98.36 457	88.12 445	99.90 197	96.68 387	98.14 457	98.57 443

cascas		96.99 403	96.82 409	97.48 434	97.57 482	95.64 445	96.43 473	99.56 271	91.75 470	97.13 464	97.61 474	95.58 369	98.63 477	96.68 387	99.11 403	98.18 463

PC_three_1452									97.56 404	99.68 191	99.41 340	99.09 119	97.09 480	96.66 389	99.60 334	99.62 182

LPG-MVS_test		99.22 214	99.05 237	99.74 101	99.82 89	99.63 138	99.16 216	99.73 165	97.56 404	99.64 210	99.69 199	99.37 72	99.89 219	96.66 389	99.87 192	99.69 113

LGP-MVS_train				99.74 101	99.82 89	99.63 138		99.73 165	97.56 404	99.64 210	99.69 199	99.37 72	99.89 219	96.66 389	99.87 192	99.69 113

ETVMVS		96.14 427	95.22 438	98.89 370	98.80 444	98.01 379	98.66 346	98.35 437	98.71 315	97.18 462	96.31 491	74.23 482	99.75 385	96.64 392	98.13 459	98.90 416

TinyColmap		98.97 279	98.93 270	99.07 343	99.46 319	98.19 364	97.75 436	99.75 155	98.79 304	99.54 258	99.70 190	98.97 150	99.62 443	96.63 393	99.83 218	99.41 300

LF4IMVS		99.01 272	98.92 274	99.27 311	99.71 186	99.28 235	98.59 354	99.77 142	98.32 364	99.39 306	99.41 340	98.62 200	99.84 303	96.62 394	99.84 210	98.69 434

NCCC		98.82 300	98.57 311	99.58 192	99.21 386	99.31 230	98.61 349	99.25 371	98.65 321	98.43 422	99.26 381	97.86 288	99.81 349	96.55 395	99.27 393	99.61 195

OPU-MVS				99.29 303	99.12 402	99.44 193	99.20 195				99.40 344	99.00 142	98.84 476	96.54 396	99.60 334	99.58 211

F-COLMAP		98.74 308	98.45 323	99.62 176	99.57 261	99.47 179	98.84 318	99.65 217	96.31 443	98.93 374	99.19 396	97.68 301	99.87 249	96.52 397	99.37 378	99.53 240

testing99		95.86 435	95.19 439	97.87 423	98.76 451	95.03 453	98.62 348	98.44 430	98.68 318	96.67 468	96.66 486	74.31 481	99.69 409	96.51 398	98.03 461	98.90 416

ADS-MVSNet2		97.78 378	97.66 385	98.12 415	99.14 398	95.36 449	99.22 192	98.75 412	96.97 431	98.25 427	99.64 231	90.90 425	99.94 97	96.51 398	99.56 343	99.08 387

ADS-MVSNet		97.72 383	97.67 384	97.86 424	99.14 398	94.65 457	99.22 192	98.86 405	96.97 431	98.25 427	99.64 231	90.90 425	99.84 303	96.51 398	99.56 343	99.08 387

PatchMatch-RL		98.68 316	98.47 320	99.30 302	99.44 324	99.28 235	98.14 402	99.54 283	97.12 429	99.11 359	99.25 383	97.80 293	99.70 402	96.51 398	99.30 387	98.93 412

CMPMVS	77.52 23	98.50 335	98.19 350	99.41 265	98.33 468	99.56 161	99.01 275	99.59 255	95.44 453	99.57 242	99.80 104	95.64 367	99.46 466	96.47 402	99.92 141	99.21 349
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 431	95.32 436	98.02 416	98.76 451	95.39 448	98.38 383	98.65 419	98.82 299	96.84 465	96.71 485	75.06 480	99.71 398	96.46 403	98.23 451	98.98 406

SF-MVS		99.10 251	98.93 270	99.62 176	99.58 251	99.51 173	99.13 230	99.65 217	97.97 384	99.42 293	99.61 265	98.86 167	99.87 249	96.45 404	99.68 306	99.49 264

FE-MVS		97.85 375	97.42 389	99.15 329	99.44 324	98.75 317	99.77 19	98.20 442	95.85 448	99.33 318	99.80 104	88.86 443	99.88 234	96.40 405	99.12 402	98.81 425

DPE-MVS		99.14 239	98.92 274	99.82 46	99.57 261	99.77 64	98.74 338	99.60 249	98.55 332	99.76 149	99.69 199	98.23 259	99.92 149	96.39 406	99.75 269	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					97.59 480	89.02 486			93.47 466		98.30 458		99.84 303	96.38 407

AllTest		99.21 219	99.07 230	99.63 167	99.78 132	99.64 132	99.12 235	99.83 94	98.63 324	99.63 215	99.72 170	98.68 191	99.75 385	96.38 407	99.83 218	99.51 253

TestCases				99.63 167	99.78 132	99.64 132		99.83 94	98.63 324	99.63 215	99.72 170	98.68 191	99.75 385	96.38 407	99.83 218	99.51 253

testdata				99.42 257	99.51 293	98.93 299		99.30 361	96.20 444	98.87 384	99.40 344	98.33 248	99.89 219	96.29 410	99.28 390	99.44 289

dp		96.86 406	97.07 398	96.24 457	98.68 457	90.30 484	99.19 201	98.38 435	97.35 418	98.23 429	99.59 283	87.23 447	99.82 333	96.27 411	98.73 433	98.59 439

tpmvs		97.39 395	97.69 382	96.52 453	98.41 465	91.76 472	99.30 159	98.94 404	97.74 398	97.85 448	99.55 305	92.40 411	99.73 391	96.25 412	98.73 433	98.06 465

KD-MVS_2432*1600		95.89 432	95.41 433	97.31 441	94.96 484	93.89 460	97.09 464	99.22 378	97.23 423	98.88 381	99.04 413	79.23 472	99.54 456	96.24 413	96.81 471	98.50 449

miper_refine_blended		95.89 432	95.41 433	97.31 441	94.96 484	93.89 460	97.09 464	99.22 378	97.23 423	98.88 381	99.04 413	79.23 472	99.54 456	96.24 413	96.81 471	98.50 449

ACMP	97.51 14	99.05 260	98.84 285	99.67 139	99.78 132	99.55 165	98.88 310	99.66 207	97.11 430	99.47 280	99.60 273	99.07 126	99.89 219	96.18 415	99.85 205	99.58 211
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 290	98.72 296	99.44 251	99.39 336	99.42 200	98.58 356	99.64 225	97.31 420	99.44 286	99.62 255	98.59 204	99.69 409	96.17 416	99.79 250	99.22 346

DP-MVS Recon		98.50 335	98.23 344	99.31 298	99.49 304	99.46 185	98.56 362	99.63 228	94.86 462	98.85 386	99.37 353	97.81 292	99.59 450	96.08 417	99.44 368	98.88 419

tpm cat1		96.78 408	96.98 401	96.16 458	98.85 438	90.59 482	99.08 251	99.32 354	92.37 468	97.73 454	99.46 332	91.15 421	99.69 409	96.07 418	98.80 423	98.21 460

tpm2		96.35 420	96.22 415	96.73 451	98.88 435	91.75 473	99.21 194	98.51 426	93.27 467	97.89 444	99.21 393	84.83 459	99.70 402	96.04 419	98.18 455	98.75 432

dmvs_re		98.69 315	98.48 319	99.31 298	99.55 275	99.42 200	99.54 90	98.38 435	99.32 219	98.72 400	98.71 444	96.76 339	99.21 470	96.01 420	99.35 381	99.31 329

test_0402		99.22 214	99.14 205	99.45 247	99.79 124	99.43 197	99.28 168	99.68 197	99.54 169	99.40 304	99.56 297	99.07 126	99.82 333	96.01 420	99.96 87	99.11 374

ITE_SJBPF				99.38 274	99.63 232	99.44 193		99.73 165	98.56 331	99.33 318	99.53 309	98.88 164	99.68 421	96.01 420	99.65 317	99.02 403

test_prior2							97.95 425		97.87 393	98.05 437	99.05 411	97.90 285		95.99 423	99.49 363

testdata2													99.89 219	95.99 423

原ACMM1				99.37 277	99.47 315	98.87 308		99.27 366	96.74 438	98.26 426	99.32 367	97.93 284	99.82 333	95.96 425	99.38 376	99.43 295

新几何1				99.52 223	99.50 299	99.22 253		99.26 368	95.66 452	98.60 410	99.28 376	97.67 302	99.89 219	95.95 426	99.32 385	99.45 277

MP-MVS		99.06 257	98.83 287	99.76 85	99.76 149	99.71 100	99.32 151	99.50 307	98.35 358	98.97 370	99.48 325	98.37 242	99.92 149	95.95 426	99.75 269	99.63 170
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 442	94.59 445	98.61 390	98.66 458	97.45 405	98.54 366	97.90 450	98.53 336	96.54 470	96.47 488	70.62 486	99.81 349	95.91 428	98.15 456	98.56 444

wuyk23d		97.58 387	99.13 207	92.93 462	99.69 207	99.49 175	99.52 92	99.77 142	97.97 384	99.96 34	99.79 115	99.84 16	99.94 97	95.85 429	99.82 228	79.36 480

HQP_MVS		98.90 290	98.68 301	99.55 211	99.58 251	99.24 247	98.80 329	99.54 283	98.94 279	99.14 355	99.25 383	97.24 321	99.82 333	95.84 430	99.78 259	99.60 199

plane_prior5								99.54 283					99.82 333	95.84 430	99.78 259	99.60 199

无先验							98.01 417	99.23 375	95.83 449				99.85 287	95.79 432		99.44 289

CPTT-MVS		98.74 308	98.44 324	99.64 160	99.61 237	99.38 213	99.18 205	99.55 277	96.49 439	99.27 333	99.37 353	97.11 329	99.92 149	95.74 433	99.67 312	99.62 182

PLC	97.35 16	98.36 348	97.99 362	99.48 238	99.32 363	99.24 247	98.50 371	99.51 303	95.19 458	98.58 412	98.96 427	96.95 334	99.83 319	95.63 434	99.25 395	99.37 311
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 327	98.34 335	99.28 306	99.18 394	99.10 279	98.34 385	99.41 330	98.48 342	98.52 417	98.98 423	97.05 331	99.78 363	95.59 435	99.50 361	98.96 407

1314		98.00 372	97.90 374	98.27 411	98.90 430	97.45 405	99.30 159	99.06 397	94.98 459	97.21 461	99.12 403	98.43 233	99.67 426	95.58 436	98.56 440	97.71 469

PVSNet_0	95.53 19	95.85 436	95.31 437	97.47 435	98.78 448	93.48 465	95.72 475	99.40 337	96.18 445	97.37 456	97.73 469	95.73 366	99.58 451	95.49 437	81.40 482	99.36 314

MAR-MVS		98.24 358	97.92 372	99.19 324	98.78 448	99.65 126	99.17 210	99.14 391	95.36 454	98.04 438	98.81 440	97.47 311	99.72 393	95.47 438	99.06 406	98.21 460
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	98.23 359	97.89 375	99.26 314	99.19 391	99.26 240	99.65 62	99.69 194	91.33 472	98.14 435	99.77 137	98.28 251	99.96 69	95.41 439	99.55 347	98.58 441

train_agg		98.35 351	97.95 366	99.57 200	99.35 348	99.35 224	98.11 406	99.41 330	94.90 460	97.92 442	98.99 420	98.02 276	99.85 287	95.38 440	99.44 368	99.50 259

9.14			98.64 302		99.45 323		98.81 326	99.60 249	97.52 409	99.28 332	99.56 297	98.53 220	99.83 319	95.36 441	99.64 319

APD-MVS		98.87 295	98.59 307	99.71 126	99.50 299	99.62 140	99.01 275	99.57 266	96.80 437	99.54 258	99.63 246	98.29 250	99.91 178	95.24 442	99.71 291	99.61 195
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 431								95.20 443

AdaColmap		98.60 322	98.35 334	99.38 274	99.12 402	99.22 253	98.67 344	99.42 329	97.84 396	98.81 390	99.27 378	97.32 319	99.81 349	95.14 444	99.53 354	99.10 376

test9_res														95.10 445	99.44 368	99.50 259

CDPH-MVS		98.56 328	98.20 347	99.61 182	99.50 299	99.46 185	98.32 387	99.41 330	95.22 456	99.21 345	99.10 407	98.34 246	99.82 333	95.09 446	99.66 315	99.56 220

BH-untuned		98.22 361	98.09 356	98.58 394	99.38 339	97.24 411	98.55 363	98.98 403	97.81 397	99.20 350	98.76 442	97.01 332	99.65 438	94.83 447	98.33 447	98.86 421

BP-MVS														94.73 448

HQP-MVS		98.36 348	98.02 361	99.39 271	99.31 364	98.94 296	97.98 421	99.37 345	97.45 412	98.15 431	98.83 437	96.67 340	99.70 402	94.73 448	99.67 312	99.53 240

QAPM		98.40 346	97.99 362	99.65 153	99.39 336	99.47 179	99.67 53	99.52 298	91.70 471	98.78 396	99.80 104	98.55 211	99.95 80	94.71 450	99.75 269	99.53 240

agg_prior2														94.58 451	99.46 367	99.50 259

myMVS_eth3d		95.63 440	94.73 442	98.34 405	98.50 463	96.36 431	98.60 351	99.21 381	97.89 390	96.76 466	96.37 489	72.10 484	99.57 452	94.38 452	98.73 433	99.09 381

BH-RMVSNet		98.41 344	98.14 353	99.21 321	99.21 386	98.47 345	98.60 351	98.26 440	98.35 358	98.93 374	99.31 370	97.20 326	99.66 431	94.32 453	99.10 404	99.51 253

E-PMN		97.14 402	97.43 388	96.27 456	98.79 446	91.62 474	95.54 476	99.01 402	99.44 193	98.88 381	99.12 403	92.78 405	99.68 421	94.30 454	99.03 410	97.50 470

MG-MVS		98.52 332	98.39 329	98.94 357	99.15 397	97.39 408	98.18 396	99.21 381	98.89 290	99.23 340	99.63 246	97.37 317	99.74 388	94.22 455	99.61 331	99.69 113

API-MVS		98.38 347	98.39 329	98.35 403	98.83 440	99.26 240	99.14 223	99.18 386	98.59 329	98.66 405	98.78 441	98.61 202	99.57 452	94.14 456	99.56 343	96.21 477

PAPM_NR		98.36 348	98.04 359	99.33 289	99.48 309	98.93 299	98.79 332	99.28 365	97.54 407	98.56 416	98.57 450	97.12 328	99.69 409	94.09 457	98.90 421	99.38 308

ZD-MVS					99.43 327	99.61 146		99.43 327	96.38 441	99.11 359	99.07 409	97.86 288	99.92 149	94.04 458	99.49 363

DPM-MVS		98.28 354	97.94 370	99.32 294	99.36 344	99.11 272	97.31 457	98.78 411	96.88 433	98.84 387	99.11 406	97.77 295	99.61 448	94.03 459	99.36 379	99.23 344

gg-mvs-nofinetune		95.87 434	95.17 440	97.97 419	98.19 471	96.95 418	99.69 45	89.23 485	99.89 56	96.24 473	99.94 19	81.19 464	99.51 462	93.99 460	98.20 452	97.44 471

PMVS	92.94 21	98.82 300	98.81 290	98.85 372	99.84 72	97.99 380	99.20 195	99.47 315	99.71 118	99.42 293	99.82 91	98.09 271	99.47 464	93.88 461	99.85 205	99.07 392
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 405	97.28 392	95.99 460	98.76 451	91.03 478	95.26 478	98.61 420	99.34 215	98.92 377	98.88 434	93.79 391	99.66 431	92.87 462	99.05 408	97.30 474

BH-w/o		97.20 399	97.01 400	97.76 427	99.08 413	95.69 444	98.03 416	98.52 425	95.76 450	97.96 441	98.02 464	95.62 368	99.47 464	92.82 463	97.25 470	98.12 464

TR-MVS		97.44 392	97.15 397	98.32 406	98.53 461	97.46 404	98.47 375	97.91 449	96.85 434	98.21 430	98.51 454	96.42 350	99.51 462	92.16 464	97.29 469	97.98 466

OpenMVS_ROB	97.31 17	97.36 397	96.84 407	98.89 370	99.29 370	99.45 191	98.87 313	99.48 312	86.54 477	99.44 286	99.74 157	97.34 318	99.86 268	91.61 465	99.28 390	97.37 473

GG-mvs-BLEND				97.36 438	97.59 480	96.87 421	99.70 38	88.49 486		94.64 479	97.26 478	80.66 466	99.12 471	91.50 466	96.50 475	96.08 479

DeepMVS_CX				97.98 418	99.69 207	96.95 418		99.26 368	75.51 480	95.74 476	98.28 459	96.47 348	99.62 443	91.23 467	97.89 463	97.38 472

PAPR		97.56 388	97.07 398	99.04 347	98.80 444	98.11 372	97.63 441	99.25 371	94.56 465	98.02 440	98.25 460	97.43 313	99.68 421	90.90 468	98.74 430	99.33 322

MVS		95.72 438	94.63 444	98.99 350	98.56 460	97.98 385	99.30 159	98.86 405	72.71 481	97.30 458	99.08 408	98.34 246	99.74 388	89.21 469	98.33 447	99.26 337

UWE-MVS-28		95.64 439	95.47 431	96.14 459	97.98 476	90.39 483	98.49 373	95.81 470	99.02 269	98.03 439	98.19 461	84.49 461	99.28 469	88.75 470	98.47 445	98.75 432

thres600view7		96.60 413	96.16 416	97.93 421	99.63 232	96.09 439	99.18 205	97.57 455	98.77 308	98.72 400	97.32 476	87.04 449	99.72 393	88.57 471	98.62 438	97.98 466

FPMVS		96.32 421	95.50 430	98.79 380	99.60 239	98.17 367	98.46 379	98.80 410	97.16 427	96.28 471	99.63 246	82.19 463	99.09 472	88.45 472	98.89 422	99.10 376

PCF-MVS	96.03 18	96.73 410	95.86 423	99.33 289	99.44 324	99.16 266	96.87 469	99.44 324	86.58 476	98.95 372	99.40 344	94.38 385	99.88 234	87.93 473	99.80 245	98.95 409
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 419	96.03 419	97.47 435	99.63 232	95.93 440	99.18 205	97.57 455	98.75 312	98.70 403	97.31 477	87.04 449	99.67 426	87.62 474	98.51 442	96.81 475

tfpn200view9		96.30 422	95.89 421	97.53 432	99.58 251	96.11 437	99.00 281	97.54 458	98.43 344	98.52 417	96.98 480	86.85 451	99.67 426	87.62 474	98.51 442	96.81 475

thres400		96.40 418	95.89 421	97.92 422	99.58 251	96.11 437	99.00 281	97.54 458	98.43 344	98.52 417	96.98 480	86.85 451	99.67 426	87.62 474	98.51 442	97.98 466

thres200		96.09 428	95.68 428	97.33 440	99.48 309	96.22 436	98.53 368	97.57 455	98.06 379	98.37 424	96.73 484	86.84 453	99.61 448	86.99 477	98.57 439	96.16 478

MVE	92.54 22	96.66 412	96.11 417	98.31 408	99.68 215	97.55 401	97.94 426	95.60 471	99.37 211	90.68 482	98.70 446	96.56 343	98.61 478	86.94 478	99.55 347	98.77 430
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 398	96.83 408	98.59 392	99.46 319	97.55 401	99.25 183	96.84 464	98.78 306	97.24 460	97.67 470	97.11 329	98.97 474	86.59 479	98.54 441	99.27 335

PAPM		95.61 441	94.71 443	98.31 408	99.12 402	96.63 424	96.66 472	98.46 429	90.77 473	96.25 472	98.68 447	93.01 403	99.69 409	81.60 480	97.86 465	98.62 436

SD_0403		97.42 393	96.90 406	98.98 352	99.54 277	97.90 388	99.52 92	99.54 283	99.34 215	97.87 446	98.85 436	98.72 187	99.64 440	78.93 481	99.83 218	99.40 303

dongtai		89.37 446	88.91 449	90.76 463	99.19 391	77.46 488	95.47 477	87.82 487	92.28 469	94.17 480	98.82 439	71.22 485	95.54 482	63.85 482	97.34 468	99.27 335

kuosan		85.65 448	84.57 451	88.90 465	97.91 477	77.11 489	96.37 474	87.62 488	85.24 478	85.45 483	96.83 483	69.94 487	90.98 484	45.90 483	95.83 479	98.62 436

test123		29.31 449	33.05 454	18.08 466	25.93 490	12.24 491	97.53 447	10.93 491	11.78 484	24.21 485	50.08 496	21.04 488	8.60 485	23.51 484	32.43 484	33.39 481

testmvs		28.94 450	33.33 452	15.79 467	26.03 489	9.81 492	96.77 470	15.67 490	11.55 485	23.87 486	50.74 495	19.03 489	8.53 486	23.21 485	33.07 483	29.03 482

mmdepth		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

monomultidepth		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

test_blank		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

uanet_test		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

DCPMVS		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

cdsmvs_eth3d_5k		24.88 451	33.17 453	0.00 468	0.00 491	0.00 493	0.00 480	99.62 231	0.00 486	0.00 487	99.13 399	99.82 18	0.00 487	0.00 486	0.00 485	0.00 483

pcd_1.5k_mvsjas		16.61 452	22.14 455	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	99.28 87	0.00 487	0.00 486	0.00 485	0.00 483

sosnet-low-res		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

sosnet		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

uncertanet		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

Regformer		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

ab-mvs-re		8.26 463	11.02 466	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	99.16 397	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

uanet		8.33 453	11.11 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	100.00 1	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

TestfortrainingZip							99.38 126

FOURS1					99.83 80	99.89 10	99.74 27	99.71 177	99.69 127	99.63 215

test_one_0601					99.63 232	99.76 71		99.55 277	99.23 236	99.31 326	99.61 265	98.59 204

eth-test2					0.00 491

eth-test					0.00 491

test_241102_ONE					99.69 207	99.82 43		99.54 283	99.12 260	99.82 109	99.49 322	98.91 160	99.52 461

save fliter					99.53 284	99.25 243	98.29 389	99.38 344	99.07 264

test0726					99.69 207	99.80 52	99.24 184	99.57 266	99.16 251	99.73 169	99.65 229	98.35 244

GSMVS																99.14 370

test_part2					99.62 236	99.67 118				99.55 255

sam_mvs1												90.81 429				99.14 370

sam_mvs												90.52 434

MTGPA								99.53 293

test_post											52.41 493	90.25 436	99.86 268

patchmatchnet-post											99.62 255	90.58 432	99.94 97

MTMP							99.09 248	98.59 423

TEST9					99.35 348	99.35 224	98.11 406	99.41 330	94.83 463	97.92 442	98.99 420	98.02 276	99.85 287

test_8					99.34 357	99.31 230	98.08 410	99.40 337	94.90 460	97.87 446	98.97 425	98.02 276	99.84 303

agg_prior					99.35 348	99.36 221		99.39 340		97.76 453			99.85 287

test_prior4						99.19 260	98.00 419

test_prior				99.46 244	99.35 348	99.22 253		99.39 340					99.69 409			99.48 268

新几何2							98.04 414

旧先验1					99.49 304	99.29 233		99.26 368			99.39 348	97.67 302			99.36 379	99.46 276

原ACMM2							97.92 428

test222					99.51 293	99.08 281	97.83 434	99.29 362	95.21 457	98.68 404	99.31 370	97.28 320			99.38 376	99.43 295

segment_acmp												98.37 242

testdata1							97.72 437		97.86 395

test12				99.54 217	99.29 370	99.33 227		99.16 389		98.43 422		97.54 309	99.82 333		99.47 365	99.48 268

plane_prior7					99.58 251	99.38 213

plane_prior6					99.47 315	99.26 240						97.24 321

plane_prior4											99.25 383

plane_prior3						99.31 230			98.36 353	99.14 355

plane_prior2							98.80 329		98.94 279

plane_prior1					99.51 293

plane_prior						99.24 247	98.42 381		97.87 393						99.71 291

n2								0.00 492

nn								0.00 492

door-mid								99.83 94

test11								99.29 362

door								99.77 142

HQP5-MVS						98.94 296

HQP-NCC					99.31 364		97.98 421		97.45 412	98.15 431

ACMP_Plane					99.31 364		97.98 421		97.45 412	98.15 431

HQP4-MVS										98.15 431			99.70 402			99.53 240

HQP3-MVS								99.37 345							99.67 312

HQP2-MVS												96.67 340

NP-MVS					99.40 335	99.13 269					98.83 437

ACMMP++_ref															99.94 123

ACMMP++															99.79 250

Test By Simon												98.41 236

High-resolution multi-view benchmark