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	99.73 111	100.00 1	99.89 41	99.79 22	99.88 239	99.98 1	100.00 1	99.98 5

test_fmvs2		99.72 53	99.85 17	99.34 304	99.91 31	98.08 417	99.48 109	100.00 1	99.90 49	99.99 7	99.91 31	99.50 62	99.98 26	99.98 1	99.99 19	99.96 13

test_fmvs3		99.83 21	99.93 2	99.53 230	99.96 7	98.62 369	99.67 53	100.00 1	99.95 32	100.00 1	99.95 16	99.85 14	99.99 7	99.98 1	99.99 19	99.98 5

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 70	99.12 244	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 53	99.88 7	99.27 329	99.93 24	97.84 430	99.34 149	100.00 1	99.99 3	99.99 7	99.82 91	99.87 13	99.99 7	99.97 4	99.99 19	99.97 10

test_vis1_n		99.68 64	99.79 34	99.36 297	99.94 18	98.18 406	99.52 94	100.00 1	99.86 65	100.00 1	99.88 50	98.99 151	99.96 69	99.97 4	99.96 91	99.95 15

test_fmvs1_n		99.68 64	99.81 28	99.28 324	99.95 15	97.93 426	99.49 107	100.00 1	99.82 85	99.99 7	99.89 41	99.21 105	99.98 26	99.97 4	99.98 54	99.93 21

test_f		99.75 49	99.88 7	99.37 291	99.96 7	98.21 403	99.51 101	100.00 1	99.94 36	100.00 1	99.93 22	99.58 50	99.94 98	99.97 4	99.99 19	99.97 10

fmvsm_l_conf0.5_n_9		99.83 21	99.81 28	99.89 11	99.86 60	99.80 51	98.94 312	99.96 30	99.98 18	99.96 34	99.78 133	99.88 11	99.98 26	99.96 9	99.99 19	99.90 30

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 46	99.86 18	99.08 260	99.97 21	99.98 18	99.96 34	99.79 120	99.90 9	99.99 7	99.96 9	99.99 19	99.90 30

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 87	99.01 284	99.99 12	99.99 3	99.98 14	99.88 50	99.97 2	99.99 7	99.96 9	100.00 1	99.98 5

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 54	99.88 46	99.55 172	99.17 219	99.98 13	99.99 3	99.96 34	99.84 76	99.96 3	99.99 7	99.96 9	99.99 19	99.88 41

test_cas_vis1_n_1920		99.76 46	99.86 13	99.45 257	99.93 24	98.40 391	99.30 167	99.98 13	99.94 36	99.99 7	99.89 41	99.80 21	99.97 44	99.96 9	99.97 77	99.97 10

fmvsm_s_conf0.5_n_10		99.77 44	99.73 54	99.88 19	99.81 111	99.75 79	99.06 266	99.85 94	99.99 3	99.97 24	99.84 76	99.12 123	99.98 26	99.95 14	99.99 19	99.90 30

fmvsm_s_conf0.5_n_7		99.73 52	99.78 39	99.60 193	99.74 189	98.93 324	98.85 327	99.96 30	99.96 28	99.97 24	99.76 155	99.82 18	99.96 69	99.95 14	99.98 54	99.90 30

fmvsm_l_conf0.5_n		99.80 30	99.78 39	99.85 32	99.88 46	99.66 122	99.11 249	99.91 56	99.98 18	99.96 34	99.64 246	99.60 44	99.99 7	99.95 14	99.99 19	99.88 41

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 41	99.82 99	99.70 109	99.17 219	99.97 21	99.99 3	99.96 34	99.82 91	99.94 4	100.00 1	99.95 14	100.00 1	99.80 67

test_fmvs1		99.48 134	99.65 74	98.97 375	99.54 309	97.16 461	99.11 249	99.98 13	99.78 102	99.96 34	99.81 98	98.72 194	99.97 44	99.95 14	99.97 77	99.79 75

mvsany_test3		99.85 12	99.88 7	99.75 98	99.95 15	99.37 228	99.53 92	99.98 13	99.77 106	99.99 7	99.95 16	99.85 14	99.94 98	99.95 14	99.98 54	99.94 18

fmvsm_s_conf0.5_n_9		99.82 24	99.82 25	99.82 46	99.83 90	99.59 159	98.97 303	99.92 46	99.99 3	99.97 24	99.84 76	99.90 9	99.94 98	99.94 20	99.99 19	99.92 25

fmvsm_s_conf0.1_n_2		99.81 28	99.78 39	99.89 11	99.93 24	99.76 70	98.92 316	99.98 13	99.99 3	99.99 7	99.88 50	99.43 67	99.94 98	99.94 20	99.99 19	99.99 2

fmvsm_l_conf0.5_n_a		99.80 30	99.79 34	99.84 38	99.88 46	99.64 135	99.12 244	99.91 56	99.98 18	99.95 45	99.67 232	99.67 34	99.99 7	99.94 20	99.99 19	99.88 41

MM		99.18 243	99.05 255	99.55 219	99.35 383	98.81 342	99.05 267	97.79 505	99.99 3	99.48 300	99.59 302	96.29 387	99.95 81	99.94 20	99.98 54	99.88 41

test_fmvsmconf_n		99.85 12	99.84 20	99.88 19	99.91 31	99.73 90	98.97 303	99.98 13	99.99 3	99.96 34	99.85 68	99.93 7	99.99 7	99.94 20	99.99 19	99.93 21

fmvsm_s_conf0.5_n_11		99.76 46	99.75 51	99.81 54	99.81 111	99.53 175	99.15 228	99.89 67	99.99 3	99.98 14	99.86 63	99.13 120	99.98 26	99.93 25	99.99 19	99.92 25

fmvsm_s_conf0.5_n_5		99.78 37	99.76 49	99.85 32	99.79 134	99.72 95	98.84 329	99.96 30	99.96 28	99.96 34	99.72 185	99.71 28	99.99 7	99.93 25	99.98 54	99.85 50

fmvsm_s_conf0.5_n_2		99.78 37	99.75 51	99.88 19	99.82 99	99.76 70	98.88 321	99.92 46	99.98 18	99.98 14	99.85 68	99.42 69	99.94 98	99.93 25	99.98 54	99.94 18

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 41	99.10 252	99.98 13	99.99 3	99.98 14	99.91 31	99.68 33	99.93 120	99.93 25	99.99 19	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 57	99.07 265	99.98 13	99.99 3	99.98 14	99.90 36	99.88 11	99.92 153	99.93 25	99.99 19	99.98 5

fmvsm_s_conf0.5_n_a		99.82 24	99.79 34	99.89 11	99.85 75	99.82 41	99.03 275	99.96 30	99.99 3	99.97 24	99.84 76	99.58 50	99.93 120	99.92 30	99.98 54	99.93 21

fmvsm_s_conf0.5_n		99.83 21	99.81 28	99.87 26	99.85 75	99.78 57	99.03 275	99.96 30	99.99 3	99.97 24	99.84 76	99.78 23	99.92 153	99.92 30	99.99 19	99.92 25

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 21	99.99 3	100.00 1	99.98 13	99.78 23	100.00 1	99.92 30	100.00 1	99.87 45

fmvsm_s_conf0.5_n_8		99.76 46	99.72 55	99.88 19	99.82 99	99.75 79	99.02 279	99.87 79	99.98 18	99.98 14	99.81 98	99.07 134	99.97 44	99.91 33	99.99 19	99.92 25

fmvsm_s_conf0.5_n_6		99.80 30	99.78 39	99.85 32	99.78 143	99.78 57	99.00 290	99.97 21	99.96 28	99.97 24	99.56 316	99.92 8	99.93 120	99.91 33	99.99 19	99.83 59

fmvsm_s_conf0.5_n_4		99.78 37	99.78 39	99.79 72	99.75 179	99.56 168	98.98 301	99.94 41	99.92 45	99.97 24	99.72 185	99.84 16	99.92 153	99.91 33	99.98 54	99.89 38

MVStest1		98.22 391	98.09 393	98.62 422	99.04 456	96.23 486	99.20 204	99.92 46	99.44 207	99.98 14	99.87 56	85.87 513	99.67 463	99.91 33	99.57 377	99.95 15

v1921920		99.56 106	99.57 105	99.55 219	99.75 179	99.11 291	99.05 267	99.61 266	99.15 272	99.88 82	99.71 195	99.08 131	99.87 255	99.90 37	99.97 77	99.66 149

v1240		99.56 106	99.58 100	99.51 236	99.80 120	99.00 308	99.00 290	99.65 243	99.15 272	99.90 67	99.75 163	99.09 127	99.88 239	99.90 37	99.96 91	99.67 135

v10		99.69 59	99.69 60	99.66 153	99.81 111	99.39 221	99.66 57	99.75 177	99.60 174	99.92 59	99.87 56	98.75 189	99.86 274	99.90 37	99.99 19	99.73 95

v1192		99.57 102	99.57 105	99.57 208	99.77 156	99.22 267	99.04 272	99.60 278	99.18 259	99.87 92	99.72 185	99.08 131	99.85 293	99.89 40	99.98 54	99.66 149

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 32	99.81 111	99.71 101	98.97 303	99.92 46	99.98 18	99.97 24	99.86 63	99.53 58	99.95 81	99.88 41	99.99 19	99.89 38

v144192		99.55 111	99.54 116	99.58 200	99.78 143	99.20 273	99.11 249	99.62 258	99.18 259	99.89 72	99.72 185	98.66 203	99.87 255	99.88 41	99.97 77	99.66 149

v8		99.68 64	99.69 60	99.65 160	99.80 120	99.40 217	99.66 57	99.76 172	99.64 157	99.93 53	99.85 68	98.66 203	99.84 310	99.88 41	99.99 19	99.71 104

mvs5depth		99.88 6	99.91 3	99.80 64	99.92 29	99.42 209	99.94 3	100.00 1	99.97 25	99.89 72	99.99 12	99.63 37	99.97 44	99.87 44	99.99 19	100.00 1

v1144		99.54 116	99.53 120	99.59 196	99.79 134	99.28 247	99.10 252	99.61 266	99.20 256	99.84 104	99.73 176	98.67 201	99.84 310	99.86 45	99.98 54	99.64 170

mmtdpeth		99.78 37	99.83 21	99.66 153	99.85 75	99.05 304	99.79 15	99.97 21	100.00 1	99.43 313	99.94 19	99.64 35	99.94 98	99.83 46	99.99 19	99.98 5

SSC-MVS		99.52 122	99.42 150	99.83 41	99.86 60	99.65 128	99.52 94	99.81 132	99.87 62	99.81 119	99.79 120	96.78 363	99.99 7	99.83 46	99.51 393	99.86 47

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 26	99.82 10	99.82 119	99.84 75	99.94 48	99.91 31	99.13 120	99.96 69	99.83 46	99.99 19	99.83 59

v2v482		99.50 127	99.47 131	99.58 200	99.78 143	99.25 256	99.14 232	99.58 293	99.25 247	99.81 119	99.62 272	98.24 268	99.84 310	99.83 46	99.97 77	99.64 170

test_vis1_rt		99.45 150	99.46 137	99.41 276	99.71 203	98.63 368	98.99 298	99.96 30	99.03 287	99.95 45	99.12 442	98.75 189	99.84 310	99.82 50	99.82 253	99.77 81

tt0805		99.63 86	99.57 105	99.81 54	99.87 55	99.88 12	99.58 82	98.70 460	99.72 115	99.91 62	99.60 292	99.43 67	99.81 369	99.81 51	99.53 389	99.73 95

VortexMVS		99.13 258	99.24 205	98.79 408	99.67 242	96.60 478	99.24 193	99.80 138	99.85 71	99.93 53	99.84 76	95.06 417	99.89 224	99.80 52	99.98 54	99.89 38

V42		99.56 106	99.54 116	99.63 174	99.79 134	99.46 194	99.39 129	99.59 284	99.24 249	99.86 96	99.70 205	98.55 218	99.82 353	99.79 53	99.95 116	99.60 208

SSC-MVS3.2		99.64 85	99.67 65	99.56 212	99.75 179	98.98 312	98.96 307	99.87 79	99.88 60	99.84 104	99.64 246	99.32 88	99.91 183	99.78 54	99.96 91	99.80 67

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 54	99.72 33	99.88 73	99.92 45	99.98 14	99.93 22	99.94 4	99.98 26	99.77 55	100.00 1	99.92 25

WB-MVS		99.44 153	99.32 179	99.80 64	99.81 111	99.61 153	99.47 112	99.81 132	99.82 85	99.71 192	99.72 185	96.60 369	99.98 26	99.75 56	99.23 437	99.82 66

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 63	99.68 48	99.85 94	99.95 32	99.98 14	99.92 27	99.28 93	99.98 26	99.75 56	100.00 1	99.94 18

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 57	99.70 38	99.86 88	99.89 55	99.98 14	99.90 36	99.94 4	99.98 26	99.75 56	100.00 1	99.90 30

ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 62	100.00 1	99.90 49	100.00 1	99.97 14	99.61 41	99.97 44	99.75 56	100.00 1	99.84 55

AstraMVS		99.15 254	99.06 248	99.42 268	99.85 75	98.59 372	99.13 239	97.26 514	99.84 75	99.87 92	99.77 145	96.11 393	99.93 120	99.71 60	99.96 91	99.74 91

Elysia		99.69 59	99.65 74	99.81 54	99.86 60	99.72 95	99.34 149	99.77 164	99.94 36	99.91 62	99.76 155	98.55 218	99.99 7	99.70 61	99.98 54	99.72 99

StellarMVS		99.69 59	99.65 74	99.81 54	99.86 60	99.72 95	99.34 149	99.77 164	99.94 36	99.91 62	99.76 155	98.55 218	99.99 7	99.70 61	99.98 54	99.72 99

tt0320-xc		99.82 24	99.82 25	99.82 46	99.82 99	99.84 26	99.82 10	99.92 46	99.94 36	99.94 48	99.93 22	99.34 85	99.92 153	99.70 61	99.96 91	99.70 107

reproduce_monomvs		97.40 440	97.46 428	97.20 492	99.05 453	91.91 530	99.20 204	99.18 427	99.84 75	99.86 96	99.75 163	80.67 521	99.83 332	99.69 64	99.95 116	99.85 50

SPE-MVS-test		99.68 64	99.70 57	99.64 167	99.57 289	99.83 33	99.78 17	99.97 21	99.92 45	99.50 296	99.38 379	99.57 52	99.95 81	99.69 64	99.90 173	99.15 391

guyue		99.12 261	99.02 264	99.41 276	99.84 81	98.56 375	99.19 210	98.30 488	99.82 85	99.84 104	99.75 163	94.84 420	99.92 153	99.68 66	99.94 134	99.74 91

tt0320		99.79 34	99.79 34	99.81 54	99.82 99	99.84 26	99.82 10	99.90 63	99.94 36	99.94 48	99.94 19	99.07 134	99.92 153	99.68 66	99.97 77	99.67 135

MGCNet		98.61 344	98.30 374	99.52 232	97.88 525	98.95 319	98.76 346	94.11 537	99.84 75	99.32 346	99.57 312	95.57 406	99.95 81	99.68 66	99.98 54	99.68 126

CS-MVS		99.67 76	99.70 57	99.58 200	99.53 318	99.84 26	99.79 15	99.96 30	99.90 49	99.61 252	99.41 365	99.51 61	99.95 81	99.66 69	99.89 189	98.96 437

KinetiMVS		99.66 77	99.63 82	99.76 87	99.89 40	99.57 167	99.37 140	99.82 119	99.95 32	99.90 67	99.63 262	98.57 214	99.97 44	99.65 70	99.94 134	99.74 91

pmmvs6		99.86 10	99.86 13	99.83 41	99.94 18	99.90 7	99.83 7	99.91 56	99.85 71	99.94 48	99.95 16	99.73 27	99.90 202	99.65 70	99.97 77	99.69 119

MIMVSNet1		99.66 77	99.62 85	99.80 64	99.94 18	99.87 15	99.69 45	99.77 164	99.78 102	99.93 53	99.89 41	97.94 299	99.92 153	99.65 70	99.98 54	99.62 188

LuminaMVS		99.39 174	99.28 194	99.73 113	99.83 90	99.49 183	99.00 290	99.05 440	99.81 91	99.89 72	99.79 120	96.54 373	99.97 44	99.64 73	99.98 54	99.73 95

sc_t1		99.81 28	99.80 32	99.82 46	99.88 46	99.88 12	99.83 7	99.79 147	99.94 36	99.93 53	99.92 27	99.35 84	99.92 153	99.64 73	99.94 134	99.68 126

EC-MVSNet		99.69 59	99.69 60	99.68 141	99.71 203	99.91 4	99.76 23	99.96 30	99.86 65	99.51 293	99.39 376	99.57 52	99.93 120	99.64 73	99.86 222	99.20 379

K. test v3		98.87 316	98.60 329	99.69 139	99.93 24	99.46 194	99.74 27	94.97 532	99.78 102	99.88 82	99.88 50	93.66 439	99.97 44	99.61 76	99.95 116	99.64 170

KD-MVS_self_test		99.63 86	99.59 96	99.76 87	99.84 81	99.90 7	99.37 140	99.79 147	99.83 81	99.88 82	99.85 68	98.42 246	99.90 202	99.60 77	99.73 312	99.49 278

Anonymous20240521		99.44 153	99.42 150	99.49 242	99.89 40	98.96 318	99.62 67	99.76 172	99.85 71	99.82 112	99.88 50	96.39 380	99.97 44	99.59 78	99.98 54	99.55 235

TransMVSNet (Re)		99.78 37	99.77 45	99.81 54	99.91 31	99.85 21	99.75 25	99.86 88	99.70 128	99.91 62	99.89 41	99.60 44	99.87 255	99.59 78	99.74 305	99.71 104

OurMVSNet-221017-0		99.75 49	99.71 56	99.84 38	99.96 7	99.83 33	99.83 7	99.85 94	99.80 95	99.93 53	99.93 22	98.54 223	99.93 120	99.59 78	99.98 54	99.76 86

EU-MVSNet		99.39 174	99.62 85	98.72 415	99.88 46	96.44 480	99.56 87	99.85 94	99.90 49	99.90 67	99.85 68	98.09 287	99.83 332	99.58 81	99.95 116	99.90 30

mvs_anonymous		99.28 205	99.39 156	98.94 379	99.19 427	97.81 432	99.02 279	99.55 307	99.78 102	99.85 101	99.80 108	98.24 268	99.86 274	99.57 82	99.50 396	99.15 391

test1111		97.74 421	98.16 388	96.49 511	99.60 263	89.86 545	99.71 37	91.21 541	99.89 55	99.88 82	99.87 56	93.73 438	99.90 202	99.56 83	99.99 19	99.70 107

lessismore_v0				99.64 167	99.86 60	99.38 223		90.66 542		99.89 72	99.83 83	94.56 426	99.97 44	99.56 83	99.92 156	99.57 227

dtuonlycased		99.24 217	99.47 131	98.56 429	99.90 37	96.17 488	97.62 473	99.85 94	99.66 148	99.86 96	99.50 340	99.39 71	99.93 120	99.55 85	99.85 229	99.59 215

mvsany_test1		99.44 153	99.45 139	99.40 279	99.37 376	98.64 366	97.90 456	99.59 284	99.27 242	99.92 59	99.82 91	99.74 26	99.93 120	99.55 85	99.87 214	99.63 176

MVSMamba_PlusPlus		99.55 111	99.58 100	99.47 250	99.68 235	99.40 217	99.52 94	99.70 210	99.92 45	99.77 151	99.86 63	98.28 264	99.96 69	99.54 87	99.90 173	99.05 422

pm-mvs1		99.79 34	99.79 34	99.78 76	99.91 31	99.83 33	99.76 23	99.87 79	99.73 111	99.89 72	99.87 56	99.63 37	99.87 255	99.54 87	99.92 156	99.63 176

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 46	99.90 49	99.97 24	99.87 56	99.81 20	99.95 81	99.54 87	99.99 19	99.80 67
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		99.48 134	99.65 74	98.95 378	99.71 203	97.27 458	99.50 102	99.82 119	99.59 176	99.41 322	99.85 68	99.62 40	100.00 1	99.53 90	99.89 189	99.59 215

test2506		94.73 499	94.59 499	95.15 519	99.59 269	85.90 547	99.75 25	74.01 549	99.89 55	99.71 192	99.86 63	79.00 531	99.90 202	99.52 91	99.99 19	99.65 158

balanced_ft_v1		99.37 181	99.36 167	99.38 286	99.10 446	99.38 223	99.68 48	99.72 197	99.72 115	99.36 333	99.77 145	97.66 323	99.94 98	99.52 91	99.73 312	98.83 455

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 40	99.91 4	99.89 5	99.71 201	99.93 43	99.95 45	99.89 41	99.71 28	99.96 69	99.51 93	99.97 77	99.84 55

FC-MVSNet-test		99.70 57	99.65 74	99.86 30	99.88 46	99.86 18	99.72 33	99.78 159	99.90 49	99.82 112	99.83 83	98.45 242	99.87 255	99.51 93	99.97 77	99.86 47

BP-MVS1		98.72 334	98.46 350	99.50 238	99.53 318	99.00 308	99.34 149	98.53 471	99.65 153	99.73 182	99.38 379	90.62 485	99.96 69	99.50 95	99.86 222	99.55 235

UA-Net		99.78 37	99.76 49	99.86 30	99.72 198	99.71 101	99.91 4	99.95 38	99.96 28	99.71 192	99.91 31	99.15 115	99.97 44	99.50 95	100.00 1	99.90 30

viewdifsd2359ckpt11		99.62 94	99.64 79	99.56 212	99.86 60	99.19 276	99.02 279	99.93 42	99.83 81	99.88 82	99.81 98	98.99 151	99.83 332	99.48 97	99.96 91	99.65 158

viewmsd2359difaftdt		99.62 94	99.64 79	99.56 212	99.86 60	99.19 276	99.02 279	99.93 42	99.83 81	99.88 82	99.81 98	98.99 151	99.83 332	99.48 97	99.96 91	99.65 158

PMMVS2		99.48 134	99.45 139	99.57 208	99.76 161	98.99 310	98.09 432	99.90 63	98.95 298	99.78 139	99.58 305	99.57 52	99.93 120	99.48 97	99.95 116	99.79 75

VPA-MVSNet		99.66 77	99.62 85	99.79 72	99.68 235	99.75 79	99.62 67	99.69 219	99.85 71	99.80 126	99.81 98	98.81 177	99.91 183	99.47 100	99.88 200	99.70 107

GDP-MVS		98.81 324	98.57 335	99.50 238	99.53 318	99.12 290	99.28 177	99.86 88	99.53 184	99.57 263	99.32 398	90.88 480	99.98 26	99.46 101	99.74 305	99.42 319

ECVR-MVS		97.73 422	98.04 396	96.78 503	99.59 269	90.81 539	99.72 33	90.43 543	99.89 55	99.86 96	99.86 63	93.60 440	99.89 224	99.46 101	99.99 19	99.65 158

nrg030		99.70 57	99.66 72	99.82 46	99.76 161	99.84 26	99.61 73	99.70 210	99.93 43	99.78 139	99.68 226	99.10 125	99.78 387	99.45 103	99.96 91	99.83 59

FE-MVSNET2		99.68 64	99.67 65	99.72 122	99.86 60	99.68 116	99.46 116	99.88 73	99.62 162	99.87 92	99.85 68	99.06 141	99.85 293	99.44 104	99.98 54	99.63 176

TAMVS		99.49 132	99.45 139	99.63 174	99.48 343	99.42 209	99.45 117	99.57 295	99.66 148	99.78 139	99.83 83	97.85 306	99.86 274	99.44 104	99.96 91	99.61 203

GeoE		99.69 59	99.66 72	99.78 76	99.76 161	99.76 70	99.60 79	99.82 119	99.46 202	99.75 165	99.56 316	99.63 37	99.95 81	99.43 106	99.88 200	99.62 188

new-patchmatchnet		99.35 188	99.57 105	98.71 419	99.82 99	96.62 476	98.55 380	99.75 177	99.50 189	99.88 82	99.87 56	99.31 89	99.88 239	99.43 106	100.00 1	99.62 188

test20.03		99.55 111	99.54 116	99.58 200	99.79 134	99.37 228	99.02 279	99.89 67	99.60 174	99.82 112	99.62 272	98.81 177	99.89 224	99.43 106	99.86 222	99.47 286

MVSFormer		99.41 168	99.44 144	99.31 316	99.57 289	98.40 391	99.77 19	99.80 138	99.73 111	99.63 235	99.30 404	98.02 292	99.98 26	99.43 106	99.69 335	99.55 235

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 26	99.77 19	99.80 138	99.73 111	99.97 24	99.92 27	99.77 25	99.98 26	99.43 106	100.00 1	99.90 30

SDMVSNet		99.77 44	99.77 45	99.76 87	99.80 120	99.65 128	99.63 64	99.86 88	99.97 25	99.89 72	99.89 41	99.52 60	99.99 7	99.42 111	99.96 91	99.65 158

Anonymous20231211		99.62 94	99.57 105	99.76 87	99.61 260	99.60 157	99.81 13	99.73 188	99.82 85	99.90 67	99.90 36	97.97 298	99.86 274	99.42 111	99.96 91	99.80 67

SixPastTwentyTwo		99.42 161	99.30 186	99.76 87	99.92 29	99.67 119	99.70 38	99.14 433	99.65 153	99.89 72	99.90 36	96.20 391	99.94 98	99.42 111	99.92 156	99.67 135

BridgeMVS		99.50 127	99.50 124	99.50 238	99.42 366	99.49 183	99.52 94	99.75 177	99.86 65	99.78 139	99.71 195	98.20 276	99.90 202	99.39 114	99.88 200	99.10 403

patch_mono-2		99.51 124	99.46 137	99.64 167	99.70 219	99.11 291	99.04 272	99.87 79	99.71 121	99.47 302	99.79 120	98.24 268	99.98 26	99.38 115	99.96 91	99.83 59

UGNet		99.38 177	99.34 173	99.49 242	98.90 469	98.90 329	99.70 38	99.35 383	99.86 65	98.57 451	99.81 98	98.50 235	99.93 120	99.38 115	99.98 54	99.66 149
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 56	99.67 65	99.81 54	99.89 40	99.72 95	99.59 80	99.82 119	99.39 223	99.82 112	99.84 76	99.38 76	99.91 183	99.38 115	99.93 148	99.80 67

FIs		99.65 83	99.58 100	99.84 38	99.84 81	99.85 21	99.66 57	99.75 177	99.86 65	99.74 176	99.79 120	98.27 266	99.85 293	99.37 118	99.93 148	99.83 59

sd_testset		99.78 37	99.78 39	99.80 64	99.80 120	99.76 70	99.80 14	99.79 147	99.97 25	99.89 72	99.89 41	99.53 58	99.99 7	99.36 119	99.96 91	99.65 158

anonymousdsp		99.80 30	99.77 45	99.90 8	99.96 7	99.88 12	99.73 30	99.85 94	99.70 128	99.92 59	99.93 22	99.45 63	99.97 44	99.36 119	100.00 1	99.85 50

casdiffmvs_mvg		99.68 64	99.68 63	99.69 139	99.81 111	99.59 159	99.29 175	99.90 63	99.71 121	99.79 133	99.73 176	99.54 55	99.84 310	99.36 119	99.96 91	99.65 158
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 72	99.88 46	99.66 122	99.69 45	99.92 46	99.67 141	99.77 151	99.75 163	99.61 41	99.98 26	99.35 122	99.98 54	99.72 99
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 98	99.64 79	99.53 230	99.79 134	98.82 341	99.58 82	99.97 21	99.95 32	99.96 34	99.76 155	98.44 243	99.99 7	99.34 123	99.96 91	99.78 77

CHOSEN 1792x2688		99.39 174	99.30 186	99.65 160	99.88 46	99.25 256	98.78 344	99.88 73	98.66 346	99.96 34	99.79 120	97.45 331	99.93 120	99.34 123	99.99 19	99.78 77

CDS-MVSNet		99.22 229	99.13 222	99.50 238	99.35 383	99.11 291	98.96 307	99.54 313	99.46 202	99.61 252	99.70 205	96.31 384	99.83 332	99.34 123	99.88 200	99.55 235
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 294	99.16 215	98.51 430	99.75 179	95.90 494	98.07 435	99.84 103	99.84 75	99.89 72	99.73 176	96.01 396	99.99 7	99.33 126	100.00 1	99.63 176

HyFIR lowres test		98.91 308	98.64 325	99.73 113	99.85 75	99.47 188	98.07 435	99.83 113	98.64 349	99.89 72	99.60 292	92.57 453	100.00 1	99.33 126	99.97 77	99.72 99

pmmvs5		99.19 239	99.11 229	99.42 268	99.76 161	98.88 333	98.55 380	99.73 188	98.82 323	99.72 187	99.62 272	96.56 370	99.82 353	99.32 128	99.95 116	99.56 231

v148		99.40 170	99.41 154	99.39 282	99.76 161	98.94 321	99.09 257	99.59 284	99.17 266	99.81 119	99.61 282	98.41 247	99.69 445	99.32 128	99.94 134	99.53 254

baseline		99.63 86	99.62 85	99.66 153	99.80 120	99.62 143	99.44 119	99.80 138	99.71 121	99.72 187	99.69 214	99.15 115	99.83 332	99.32 128	99.94 134	99.53 254

CVMVSNet		98.61 344	98.88 300	97.80 465	99.58 279	93.60 522	99.26 186	99.64 251	99.66 148	99.72 187	99.67 232	93.26 444	99.93 120	99.30 131	99.81 263	99.87 45

PS-CasMVS		99.66 77	99.58 100	99.89 11	99.80 120	99.85 21	99.66 57	99.73 188	99.62 162	99.84 104	99.71 195	98.62 207	99.96 69	99.30 131	99.96 91	99.86 47

DTE-MVSNet		99.68 64	99.61 89	99.88 19	99.80 120	99.87 15	99.67 53	99.71 201	99.72 115	99.84 104	99.78 133	98.67 201	99.97 44	99.30 131	99.95 116	99.80 67

tmp_tt		95.75 489	95.42 484	96.76 505	89.90 548	94.42 514	98.86 325	97.87 503	78.01 539	99.30 356	99.69 214	97.70 315	95.89 538	99.29 134	98.14 504	99.95 15

PEN-MVS		99.66 77	99.59 96	99.89 11	99.83 90	99.87 15	99.66 57	99.73 188	99.70 128	99.84 104	99.73 176	98.56 217	99.96 69	99.29 134	99.94 134	99.83 59

WR-MVS_H		99.61 98	99.53 120	99.87 26	99.80 120	99.83 33	99.67 53	99.75 177	99.58 178	99.85 101	99.69 214	98.18 279	99.94 98	99.28 136	99.95 116	99.83 59

IterMVS		98.97 298	99.16 215	98.42 435	99.74 189	95.64 499	98.06 437	99.83 113	99.83 81	99.85 101	99.74 171	96.10 395	99.99 7	99.27 137	100.00 1	99.63 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
hybridcas		99.65 83	99.63 82	99.70 133	99.85 75	99.67 119	99.30 167	99.87 79	99.67 141	99.81 119	99.77 145	99.21 105	99.81 369	99.24 138	99.94 134	99.61 203

NormalMVS		99.09 270	98.91 298	99.62 183	99.78 143	99.11 291	99.36 144	99.77 164	99.82 85	99.68 206	99.53 329	93.30 442	99.99 7	99.24 138	99.76 293	99.74 91

SymmetryMVS		99.01 291	98.82 308	99.58 200	99.65 249	99.11 291	99.36 144	99.20 425	99.82 85	99.68 206	99.53 329	93.30 442	99.99 7	99.24 138	99.63 356	99.64 170

WBMVS		97.50 436	97.18 442	98.48 432	98.85 477	95.89 495	98.44 399	99.52 329	99.53 184	99.52 286	99.42 363	80.10 524	99.86 274	99.24 138	99.95 116	99.68 126

h-mvs33		98.61 344	98.34 369	99.44 261	99.60 263	98.67 356	99.27 181	99.44 355	99.68 133	99.32 346	99.49 345	92.50 457	100.00 1	99.24 138	96.51 529	99.65 158

hse-mvs2		98.52 358	98.30 374	99.16 347	99.29 406	98.60 370	98.77 345	99.02 442	99.68 133	99.32 346	99.04 453	92.50 457	99.85 293	99.24 138	97.87 512	99.03 427

FMVSNet1		99.66 77	99.63 82	99.73 113	99.78 143	99.77 63	99.68 48	99.70 210	99.67 141	99.82 112	99.83 83	98.98 155	99.90 202	99.24 138	99.97 77	99.53 254

casdiffseed414692147		99.68 64	99.68 63	99.67 145	99.86 60	99.65 128	99.32 158	99.87 79	99.75 109	99.77 151	99.80 108	99.61 41	99.68 457	99.21 145	99.95 116	99.67 135

casdiffmvs		99.63 86	99.61 89	99.67 145	99.79 134	99.59 159	99.13 239	99.85 94	99.79 99	99.76 160	99.72 185	99.33 87	99.82 353	99.21 145	99.94 134	99.59 215
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		99.54 116	99.43 147	99.87 26	99.76 161	99.82 41	99.57 85	99.61 266	99.54 182	99.80 126	99.64 246	97.79 310	99.95 81	99.21 145	99.94 134	99.84 55

DELS-MVS		99.34 193	99.30 186	99.48 248	99.51 327	99.36 232	98.12 428	99.53 324	99.36 229	99.41 322	99.61 282	99.22 104	99.87 255	99.21 145	99.68 340	99.20 379
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		99.47 144	99.50 124	99.37 291	99.70 219	98.80 345	98.67 359	99.92 46	99.49 191	99.77 151	99.71 195	99.08 131	99.78 387	99.20 149	99.94 134	99.54 247

UniMVSNet (Re)		99.37 181	99.26 199	99.68 141	99.51 327	99.58 164	98.98 301	99.60 278	99.43 214	99.70 196	99.36 388	97.70 315	99.88 239	99.20 149	99.87 214	99.59 215

CANet		99.11 266	99.05 255	99.28 324	98.83 480	98.56 375	98.71 356	99.41 362	99.25 247	99.23 367	99.22 426	97.66 323	99.94 98	99.19 151	99.97 77	99.33 346

EI-MVSNet-UG-set		99.48 134	99.50 124	99.42 268	99.57 289	98.65 363	99.24 193	99.46 349	99.68 133	99.80 126	99.66 237	98.99 151	99.89 224	99.19 151	99.90 173	99.72 99

dtuplus		99.52 122	99.55 112	99.43 265	99.76 161	98.90 329	98.71 356	99.89 67	99.67 141	99.79 133	99.77 145	99.25 101	99.81 369	99.18 153	99.96 91	99.57 227

xiu_mvs_v1_base_debu		99.23 220	99.34 173	98.91 389	99.59 269	98.23 400	98.47 393	99.66 233	99.61 167	99.68 206	98.94 470	99.39 71	99.97 44	99.18 153	99.55 382	98.51 478

xiu_mvs_v1_base		99.23 220	99.34 173	98.91 389	99.59 269	98.23 400	98.47 393	99.66 233	99.61 167	99.68 206	98.94 470	99.39 71	99.97 44	99.18 153	99.55 382	98.51 478

xiu_mvs_v1_base_debi		99.23 220	99.34 173	98.91 389	99.59 269	98.23 400	98.47 393	99.66 233	99.61 167	99.68 206	98.94 470	99.39 71	99.97 44	99.18 153	99.55 382	98.51 478

VPNet		99.46 146	99.37 162	99.71 128	99.82 99	99.59 159	99.48 109	99.70 210	99.81 91	99.69 200	99.58 305	97.66 323	99.86 274	99.17 157	99.44 405	99.67 135

UniMVSNet_NR-MVSNet		99.37 181	99.25 203	99.72 122	99.47 349	99.56 168	98.97 303	99.61 266	99.43 214	99.67 214	99.28 409	97.85 306	99.95 81	99.17 157	99.81 263	99.65 158

DU-MVS		99.33 196	99.21 209	99.71 128	99.43 361	99.56 168	98.83 332	99.53 324	99.38 224	99.67 214	99.36 388	97.67 319	99.95 81	99.17 157	99.81 263	99.63 176

hybrid		99.42 161	99.43 147	99.37 291	99.75 179	98.77 348	98.72 353	99.84 103	99.61 167	99.65 224	99.68 226	98.53 228	99.79 383	99.16 160	99.94 134	99.54 247

usedtu_dtu_shiyan2		99.44 153	99.33 178	99.78 76	99.86 60	99.76 70	99.54 90	99.79 147	99.66 148	99.66 220	99.79 120	96.76 364	99.96 69	99.15 161	99.72 320	99.62 188

EI-MVSNet-Vis-set		99.47 144	99.49 128	99.42 268	99.57 289	98.66 359	99.24 193	99.46 349	99.67 141	99.79 133	99.65 244	98.97 157	99.89 224	99.15 161	99.89 189	99.71 104

EI-MVSNet		99.38 177	99.44 144	99.21 340	99.58 279	98.09 414	99.26 186	99.46 349	99.62 162	99.75 165	99.67 232	98.54 223	99.85 293	99.15 161	99.92 156	99.68 126

VNet		99.18 243	99.06 248	99.56 212	99.24 417	99.36 232	99.33 155	99.31 398	99.67 141	99.47 302	99.57 312	96.48 374	99.84 310	99.15 161	99.30 424	99.47 286

EG-PatchMatch MVS		99.57 102	99.56 110	99.62 183	99.77 156	99.33 238	99.26 186	99.76 172	99.32 234	99.80 126	99.78 133	99.29 91	99.87 255	99.15 161	99.91 169	99.66 149

PVSNet_Blended_VisFu		99.40 170	99.38 159	99.44 261	99.90 37	98.66 359	98.94 312	99.91 56	97.97 422	99.79 133	99.73 176	99.05 143	99.97 44	99.15 161	99.99 19	99.68 126

IterMVS-LS		99.41 168	99.47 131	99.25 335	99.81 111	98.09 414	98.85 327	99.76 172	99.62 162	99.83 110	99.64 246	98.54 223	99.97 44	99.15 161	99.99 19	99.68 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cashybrid2		99.63 86	99.60 93	99.73 113	99.84 81	99.72 95	99.36 144	99.87 79	99.67 141	99.74 176	99.73 176	99.07 134	99.83 332	99.14 168	99.93 148	99.62 188

TranMVSNet+NR-MVSNet		99.54 116	99.47 131	99.76 87	99.58 279	99.64 135	99.30 167	99.63 255	99.61 167	99.71 192	99.56 316	98.76 187	99.96 69	99.14 168	99.92 156	99.68 126

MVSTER		98.47 365	98.22 381	99.24 337	99.06 452	98.35 397	99.08 260	99.46 349	99.27 242	99.75 165	99.66 237	88.61 499	99.85 293	99.14 168	99.92 156	99.52 265

hybridnocas07		99.43 157	99.44 144	99.39 282	99.75 179	98.85 338	98.76 346	99.85 94	99.71 121	99.70 196	99.68 226	98.47 237	99.77 400	99.13 171	99.95 116	99.55 235

E5new		99.68 64	99.67 65	99.70 133	99.87 55	99.62 143	99.41 122	99.84 103	99.68 133	99.77 151	99.81 98	99.59 46	99.78 387	99.13 171	99.96 91	99.70 107

E6new		99.68 64	99.67 65	99.70 133	99.86 60	99.62 143	99.41 122	99.84 103	99.68 133	99.77 151	99.81 98	99.59 46	99.78 387	99.13 171	99.96 91	99.70 107

E6		99.68 64	99.67 65	99.70 133	99.86 60	99.62 143	99.41 122	99.84 103	99.68 133	99.77 151	99.81 98	99.59 46	99.78 387	99.13 171	99.96 91	99.70 107

E5		99.68 64	99.67 65	99.70 133	99.87 55	99.62 143	99.41 122	99.84 103	99.68 133	99.77 151	99.81 98	99.59 46	99.78 387	99.13 171	99.96 91	99.70 107

diffmvs_AUTHOR		99.48 134	99.48 129	99.47 250	99.80 120	98.89 331	98.71 356	99.82 119	99.79 99	99.66 220	99.63 262	98.87 173	99.88 239	99.13 171	99.95 116	99.62 188

Anonymous20231206		99.35 188	99.31 181	99.47 250	99.74 189	99.06 303	99.28 177	99.74 183	99.23 251	99.72 187	99.53 329	97.63 326	99.88 239	99.11 177	99.84 235	99.48 282

Syy-MVS		98.17 397	97.85 413	99.15 349	98.50 504	98.79 346	98.60 367	99.21 422	97.89 432	96.76 518	96.37 546	95.47 411	99.57 489	99.10 178	98.73 478	99.09 409

ttmdpeth		99.48 134	99.55 112	99.29 321	99.76 161	98.16 408	99.33 155	99.95 38	99.79 99	99.36 333	99.89 41	99.13 120	99.77 400	99.09 179	99.64 353	99.93 21

MVS_Test		99.28 205	99.31 181	99.19 344	99.35 383	98.79 346	99.36 144	99.49 342	99.17 266	99.21 373	99.67 232	98.78 184	99.66 468	99.09 179	99.66 349	99.10 403

usedtu_dtu_shiyan1		98.87 316	98.71 318	99.35 301	99.59 269	98.88 333	97.17 495	99.64 251	98.94 299	99.27 358	99.22 426	95.57 406	99.83 332	99.08 181	99.92 156	99.35 339

FE-MVSNET3		98.87 316	98.71 318	99.35 301	99.59 269	98.88 333	97.17 495	99.64 251	98.94 299	99.27 358	99.22 426	95.57 406	99.83 332	99.08 181	99.92 156	99.35 339

testgi		99.29 203	99.26 199	99.37 291	99.75 179	98.81 342	98.84 329	99.89 67	98.38 381	99.75 165	99.04 453	99.36 81	99.86 274	99.08 181	99.25 433	99.45 293

1112_ss		99.05 278	98.84 305	99.67 145	99.66 245	99.29 245	98.52 387	99.82 119	97.65 447	99.43 313	99.16 435	96.42 377	99.91 183	99.07 184	99.84 235	99.80 67

CANet_DTU		98.91 308	98.85 303	99.09 359	98.79 486	98.13 409	98.18 418	99.31 398	99.48 194	98.86 421	99.51 337	96.56 370	99.95 81	99.05 185	99.95 116	99.19 382

blended_shiyan8		97.82 416	97.45 430	98.92 384	98.06 521	97.45 449	97.73 463	99.35 383	97.96 425	98.35 463	97.34 525	92.76 452	99.84 310	99.04 186	96.49 531	99.47 286

blended_shiyan6		97.82 416	97.46 428	98.92 384	98.08 520	97.46 447	97.73 463	99.34 387	97.96 425	98.33 464	97.35 524	92.78 450	99.84 310	99.04 186	96.53 525	99.46 291

ELoFTR		99.25 213	99.26 199	99.21 340	99.86 60	98.66 359	99.00 290	99.93 42	98.56 358	99.83 110	99.83 83	97.34 337	99.92 153	99.03 188	100.00 1	99.04 424

Baseline_NR-MVSNet		99.49 132	99.37 162	99.82 46	99.91 31	99.84 26	98.83 332	99.86 88	99.68 133	99.65 224	99.88 50	97.67 319	99.87 255	99.03 188	99.86 222	99.76 86

FMVSNet2		99.35 188	99.28 194	99.55 219	99.49 338	99.35 235	99.45 117	99.57 295	99.44 207	99.70 196	99.74 171	97.21 343	99.87 255	99.03 188	99.94 134	99.44 308

wanda-best-256-512		97.53 433	97.14 444	98.72 415	97.71 527	96.86 471	97.00 504	99.34 387	97.73 442	98.18 471	96.82 537	91.92 461	99.84 310	99.02 191	96.53 525	99.45 293

FE-blended-shiyan7		97.53 433	97.14 444	98.72 415	97.71 527	96.86 471	97.00 504	99.34 387	97.73 442	98.18 471	96.82 537	91.92 461	99.84 310	99.02 191	96.53 525	99.45 293

Test_1112_low_res		98.95 304	98.73 316	99.63 174	99.68 235	99.15 285	98.09 432	99.80 138	97.14 475	99.46 306	99.40 371	96.11 393	99.89 224	99.01 193	99.84 235	99.84 55

VDD-MVS		99.20 236	99.11 229	99.44 261	99.43 361	98.98 312	99.50 102	98.32 487	99.80 95	99.56 271	99.69 214	96.99 356	99.85 293	98.99 194	99.73 312	99.50 273

DeepC-MVS	98.90 4	99.62 94	99.61 89	99.67 145	99.72 198	99.44 202	99.24 193	99.71 201	99.27 242	99.93 53	99.90 36	99.70 31	99.93 120	98.99 194	99.99 19	99.64 170
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
pmmvs-eth3d		99.48 134	99.47 131	99.51 236	99.77 156	99.41 216	98.81 337	99.66 233	99.42 218	99.75 165	99.66 237	99.20 107	99.76 407	98.98 196	99.99 19	99.36 336

EPNet_dtu		97.62 427	97.79 417	97.11 498	96.67 538	92.31 528	98.51 388	98.04 495	99.24 249	95.77 528	99.47 353	93.78 437	99.66 468	98.98 196	99.62 358	99.37 333
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dtuonly		98.93 307	99.11 229	98.38 438	99.72 198	95.75 497	97.07 502	99.91 56	99.04 285	99.65 224	99.41 365	98.32 261	99.83 332	98.97 198	99.90 173	99.55 235

diffmvs		99.34 193	99.32 179	99.39 282	99.67 242	98.77 348	98.57 376	99.81 132	99.61 167	99.48 300	99.41 365	98.47 237	99.86 274	98.97 198	99.90 173	99.53 254
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		99.40 170	99.31 181	99.68 141	99.43 361	99.55 172	99.73 30	99.50 338	99.46 202	99.88 82	99.36 388	97.54 327	99.87 255	98.97 198	99.87 214	99.63 176

RoMa-SfM		99.32 198	99.23 208	99.59 196	99.77 156	99.53 175	98.89 319	99.88 73	98.78 330	99.65 224	99.52 333	97.78 311	99.90 202	98.96 201	99.86 222	99.35 339

TestfortrainingZip a		99.55 111	99.45 139	99.85 32	99.76 161	99.82 41	99.38 132	99.62 258	99.77 106	99.87 92	99.78 133	98.12 284	99.88 239	98.96 201	99.77 289	99.85 50

viewdifsd2359ckpt07		99.51 124	99.50 124	99.52 232	99.80 120	99.19 276	98.92 316	99.88 73	99.72 115	99.64 230	99.62 272	99.06 141	99.81 369	98.96 201	99.94 134	99.56 231

GBi-Net		99.42 161	99.31 181	99.73 113	99.49 338	99.77 63	99.68 48	99.70 210	99.44 207	99.62 245	99.83 83	97.21 343	99.90 202	98.96 201	99.90 173	99.53 254

FMVSNet5		97.80 419	97.25 439	99.42 268	98.83 480	98.97 315	99.38 132	99.80 138	98.87 313	99.25 363	99.69 214	80.60 523	99.91 183	98.96 201	99.90 173	99.38 329

test1		99.42 161	99.31 181	99.73 113	99.49 338	99.77 63	99.68 48	99.70 210	99.44 207	99.62 245	99.83 83	97.21 343	99.90 202	98.96 201	99.90 173	99.53 254

FMVSNet3		98.80 325	98.63 327	99.32 312	99.13 437	98.72 352	99.10 252	99.48 343	99.23 251	99.62 245	99.64 246	92.57 453	99.86 274	98.96 201	99.90 173	99.39 327

UnsupCasMVSNet_eth		98.83 321	98.57 335	99.59 196	99.68 235	99.45 200	98.99 298	99.67 228	99.48 194	99.55 276	99.36 388	94.92 418	99.86 274	98.95 208	96.57 524	99.45 293

CHOSEN 280x420		98.41 372	98.41 359	98.40 436	99.34 392	95.89 495	96.94 509	99.44 355	98.80 327	99.25 363	99.52 333	93.51 441	99.98 26	98.94 209	99.98 54	99.32 350

E4		99.61 98	99.59 96	99.66 153	99.84 81	99.53 175	99.08 260	99.84 103	99.65 153	99.74 176	99.80 108	99.45 63	99.77 400	98.93 210	99.95 116	99.69 119

TDRefinement		99.72 53	99.70 57	99.77 80	99.90 37	99.85 21	99.86 6	99.92 46	99.69 131	99.78 139	99.92 27	99.37 78	99.88 239	98.93 210	99.95 116	99.60 208

PDCNetPlus		98.55 354	98.50 346	98.69 420	99.64 251	96.12 489	97.67 470	100.00 1	98.34 393	99.79 133	99.75 163	92.45 459	99.98 26	98.92 212	99.99 19	99.96 13

viewmacassd2359aftdt		99.63 86	99.61 89	99.68 141	99.84 81	99.61 153	99.14 232	99.87 79	99.71 121	99.75 165	99.77 145	99.54 55	99.72 429	98.91 213	99.96 91	99.70 107

alignmvs		98.28 382	97.96 402	99.25 335	99.12 439	98.93 324	99.03 275	98.42 479	99.64 157	98.72 436	97.85 515	90.86 481	99.62 480	98.88 214	99.13 442	99.19 382

testing3-2		96.51 467	96.43 461	96.74 507	99.36 379	91.38 536	99.10 252	97.87 503	99.48 194	98.57 451	98.71 487	76.65 536	99.66 468	98.87 215	99.26 431	99.18 384

MGCFI-Net		99.02 285	99.01 269	99.06 367	99.11 444	98.60 370	99.63 64	99.67 228	99.63 159	98.58 449	97.65 519	99.07 134	99.57 489	98.85 216	98.92 461	99.03 427

sss		98.90 311	98.77 315	99.27 329	99.48 343	98.44 388	98.72 353	99.32 394	97.94 428	99.37 332	99.35 393	96.31 384	99.91 183	98.85 216	99.63 356	99.47 286

xiu_mvs_v2_base		99.02 285	99.11 229	98.77 411	99.37 376	98.09 414	98.13 427	99.51 334	99.47 199	99.42 316	98.54 499	99.38 76	99.97 44	98.83 218	99.33 420	98.24 492

PS-MVSNAJ		99.00 294	99.08 242	98.76 412	99.37 376	98.10 413	98.00 444	99.51 334	99.47 199	99.41 322	98.50 501	99.28 93	99.97 44	98.83 218	99.34 419	98.20 496

E2		99.54 116	99.51 122	99.62 183	99.78 143	99.47 188	99.01 284	99.82 119	99.55 180	99.69 200	99.77 145	99.26 97	99.76 407	98.82 220	99.93 148	99.62 188

E3		99.54 116	99.51 122	99.62 183	99.78 143	99.47 188	99.01 284	99.82 119	99.55 180	99.69 200	99.77 145	99.25 101	99.76 407	98.82 220	99.93 148	99.62 188

D2MVS		99.22 229	99.19 212	99.29 321	99.69 227	98.74 351	98.81 337	99.41 362	98.55 360	99.68 206	99.69 214	98.13 282	99.87 255	98.82 220	99.98 54	99.24 366

PatchT		98.45 368	98.32 371	98.83 404	98.94 467	98.29 398	99.24 193	98.82 453	99.84 75	99.08 394	99.76 155	91.37 470	99.94 98	98.82 220	99.00 455	98.26 490

testf1		99.63 86	99.60 93	99.72 122	99.94 18	99.95 2	99.47 112	99.89 67	99.43 214	99.88 82	99.80 108	99.26 97	99.90 202	98.81 224	99.88 200	99.32 350

APD_test2		99.63 86	99.60 93	99.72 122	99.94 18	99.95 2	99.47 112	99.89 67	99.43 214	99.88 82	99.80 108	99.26 97	99.90 202	98.81 224	99.88 200	99.32 350

gbinet_0.2-2-1-0.02		97.52 435	97.07 446	98.88 398	97.35 535	97.35 455	97.17 495	99.25 411	97.86 437	98.41 461	96.54 543	90.74 483	99.85 293	98.80 226	97.51 516	99.43 314

usedtu_blend_shiyan5		97.97 410	97.65 426	98.92 384	97.71 527	97.49 444	99.53 92	99.81 132	99.52 188	98.18 471	96.82 537	91.92 461	99.83 332	98.79 227	96.53 525	99.45 293

blend_shiyan4		95.04 497	93.76 503	98.88 398	97.92 523	97.49 444	97.72 465	99.34 387	97.93 429	97.65 503	97.11 530	77.69 534	99.83 332	98.79 227	79.72 542	99.33 346

sasdasda		99.02 285	99.00 273	99.09 359	99.10 446	98.70 354	99.61 73	99.66 233	99.63 159	98.64 442	97.65 519	99.04 144	99.54 494	98.79 227	98.92 461	99.04 424

Effi-MVS+		99.06 275	98.97 285	99.34 304	99.31 400	98.98 312	98.31 409	99.91 56	98.81 325	98.79 430	98.94 470	99.14 118	99.84 310	98.79 227	98.74 475	99.20 379

canonicalmvs		99.02 285	99.00 273	99.09 359	99.10 446	98.70 354	99.61 73	99.66 233	99.63 159	98.64 442	97.65 519	99.04 144	99.54 494	98.79 227	98.92 461	99.04 424

VDDNet		98.97 298	98.82 308	99.42 268	99.71 203	98.81 342	99.62 67	98.68 461	99.81 91	99.38 330	99.80 108	94.25 430	99.85 293	98.79 227	99.32 422	99.59 215

CR-MVSNet		98.35 379	98.20 383	98.83 404	99.05 453	98.12 410	99.30 167	99.67 228	97.39 462	99.16 381	99.79 120	91.87 466	99.91 183	98.78 233	98.77 470	98.44 483

test_method		91.72 504	92.32 504	89.91 524	93.49 547	70.18 550	90.28 537	99.56 300	61.71 542	95.39 530	99.52 333	93.90 433	99.94 98	98.76 234	98.27 497	99.62 188

RPMNet		98.60 347	98.53 341	98.83 404	99.05 453	98.12 410	99.30 167	99.62 258	99.86 65	99.16 381	99.74 171	92.53 455	99.92 153	98.75 235	98.77 470	98.44 483

mamba_0408		99.54 116	99.55 112	99.54 225	99.71 203	99.24 261	99.27 181	99.79 147	99.72 115	99.78 139	99.64 246	99.36 81	99.93 120	98.74 236	99.90 173	99.45 293

SSM_04072		99.55 111	99.55 112	99.55 219	99.71 203	99.24 261	99.27 181	99.79 147	99.72 115	99.78 139	99.64 246	99.36 81	99.97 44	98.74 236	99.90 173	99.45 293

SSM_0407		99.56 106	99.56 110	99.54 225	99.71 203	99.24 261	99.15 228	99.84 103	99.80 95	99.78 139	99.70 205	99.44 65	99.93 120	98.74 236	99.90 173	99.45 293

SSM_0404		99.57 102	99.58 100	99.54 225	99.76 161	99.28 247	99.19 210	99.84 103	99.80 95	99.78 139	99.70 205	99.44 65	99.93 120	98.74 236	99.95 116	99.41 320

pmmvs4		99.13 258	99.06 248	99.36 297	99.57 289	99.10 298	98.01 441	99.25 411	98.78 330	99.58 260	99.44 360	98.24 268	99.76 407	98.74 236	99.93 148	99.22 371

viewmanbaseed2359cas		99.50 127	99.47 131	99.61 189	99.73 193	99.52 180	99.03 275	99.83 113	99.49 191	99.65 224	99.64 246	99.18 109	99.71 434	98.73 241	99.92 156	99.58 221

tttt0517		97.62 427	97.20 441	98.90 395	99.76 161	97.40 453	99.48 109	94.36 534	99.06 284	99.70 196	99.49 345	84.55 516	99.94 98	98.73 241	99.65 351	99.36 336

viewcassd2359sk11		99.48 134	99.45 139	99.58 200	99.73 193	99.42 209	98.96 307	99.80 138	99.44 207	99.63 235	99.74 171	99.09 127	99.76 407	98.72 243	99.91 169	99.57 227

EPP-MVSNet		99.17 248	99.00 273	99.66 153	99.80 120	99.43 206	99.70 38	99.24 415	99.48 194	99.56 271	99.77 145	94.89 419	99.93 120	98.72 243	99.89 189	99.63 176

PMatch-SfM		98.91 308	98.81 310	99.22 339	99.79 134	98.89 331	98.18 418	99.61 266	99.18 259	99.03 401	99.61 282	96.13 392	99.80 379	98.71 245	99.04 452	98.99 435

FE-MVSNET		99.45 150	99.36 167	99.71 128	99.84 81	99.64 135	99.16 225	99.91 56	98.65 347	99.73 182	99.73 176	98.54 223	99.82 353	98.71 245	99.96 91	99.67 135

Anonymous20240529		99.42 161	99.34 173	99.65 160	99.53 318	99.60 157	99.63 64	99.39 372	99.47 199	99.76 160	99.78 133	98.13 282	99.86 274	98.70 247	99.68 340	99.49 278

ACMH	98.42 6	99.59 101	99.54 116	99.72 122	99.86 60	99.62 143	99.56 87	99.79 147	98.77 333	99.80 126	99.85 68	99.64 35	99.85 293	98.70 247	99.89 189	99.70 107
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 196	99.28 194	99.47 250	99.57 289	99.39 221	99.78 17	99.43 359	98.87 313	99.57 263	99.82 91	98.06 290	99.87 255	98.69 249	99.73 312	99.15 391

LFMVS		98.46 367	98.19 386	99.26 332	99.24 417	98.52 383	99.62 67	96.94 517	99.87 62	99.31 351	99.58 305	91.04 475	99.81 369	98.68 250	99.42 409	99.45 293

DKM		99.12 261	98.98 283	99.54 225	99.71 203	99.48 187	98.53 385	99.88 73	99.18 259	98.99 405	99.64 246	96.25 388	99.75 418	98.66 251	99.93 148	99.40 323

WR-MVS		99.11 266	98.93 290	99.66 153	99.30 404	99.42 209	98.42 401	99.37 378	99.04 285	99.57 263	99.20 432	96.89 359	99.86 274	98.66 251	99.87 214	99.70 107

mvsmamba		99.08 271	98.95 288	99.45 257	99.36 379	99.18 282	99.39 129	98.81 455	99.37 225	99.35 337	99.70 205	96.36 382	99.94 98	98.66 251	99.59 373	99.22 371

viewdifsd2359ckpt13		99.42 161	99.37 162	99.57 208	99.72 198	99.46 194	99.01 284	99.80 138	99.20 256	99.51 293	99.60 292	98.92 164	99.70 438	98.65 254	99.90 173	99.55 235

RRT-MVS		99.08 271	99.00 273	99.33 307	99.27 411	98.65 363	99.62 67	99.93 42	99.66 148	99.67 214	99.82 91	95.27 415	99.93 120	98.64 255	99.09 447	99.41 320

E3new		99.42 161	99.37 162	99.56 212	99.68 235	99.38 223	98.93 315	99.79 147	99.30 237	99.55 276	99.69 214	98.88 171	99.76 407	98.63 256	99.89 189	99.53 254

Anonymous202405211		98.75 330	98.46 350	99.63 174	99.34 392	99.66 122	99.47 112	97.65 506	99.28 241	99.56 271	99.50 340	93.15 445	99.84 310	98.62 257	99.58 375	99.40 323

SP-SuperGlue		98.66 341	98.63 327	98.73 414	98.44 506	99.02 306	98.22 416	99.44 355	99.37 225	98.17 475	99.30 404	96.95 357	99.12 517	98.59 258	99.20 440	98.06 500

lecture		99.56 106	99.48 129	99.81 54	99.78 143	99.86 18	99.50 102	99.70 210	99.59 176	99.75 165	99.71 195	98.94 160	99.92 153	98.59 258	99.76 293	99.66 149

EPNet		98.13 399	97.77 419	99.18 346	94.57 546	97.99 420	99.24 193	97.96 498	99.74 110	97.29 510	99.62 272	93.13 446	99.97 44	98.59 258	99.83 243	99.58 221
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 278	99.09 240	98.91 389	99.21 422	98.36 396	98.82 336	99.47 346	98.85 316	98.90 416	99.56 316	98.78 184	99.09 520	98.57 261	99.68 340	99.26 363

DenseAffine		99.17 248	99.06 248	99.49 242	99.76 161	99.33 238	98.43 400	99.97 21	99.11 278	99.17 380	99.61 282	97.05 352	99.76 407	98.56 262	99.88 200	99.38 329

Patchmatch-RL test		98.60 347	98.36 366	99.33 307	99.77 156	99.07 301	98.27 411	99.87 79	98.91 308	99.74 176	99.72 185	90.57 487	99.79 383	98.55 263	99.85 229	99.11 400

pmmvs3		98.08 402	97.80 415	98.91 389	99.41 368	97.69 438	97.87 457	99.66 233	95.87 499	99.50 296	99.51 337	90.35 489	99.97 44	98.55 263	99.47 401	99.08 415

LoFTR		99.29 203	99.26 199	99.36 297	99.70 219	99.05 304	98.66 361	99.95 38	98.85 316	99.86 96	99.75 163	98.14 281	99.93 120	98.54 265	99.91 169	99.10 403

SP-LightGlue		98.62 343	98.51 343	98.94 379	98.69 497	99.01 307	98.34 405	99.54 313	99.27 242	97.72 501	99.15 437	95.88 400	99.54 494	98.53 266	99.47 401	98.27 489

ETV-MVS		99.18 243	99.18 213	99.16 347	99.34 392	99.28 247	99.12 244	99.79 147	99.48 194	98.93 410	98.55 498	99.40 70	99.93 120	98.51 267	99.52 392	98.28 488

viewdifsd2359ckpt09		99.24 217	99.16 215	99.49 242	99.70 219	99.22 267	98.88 321	99.81 132	98.70 341	99.38 330	99.37 383	98.22 273	99.76 407	98.48 268	99.88 200	99.51 267

jason		99.16 250	99.11 229	99.32 312	99.75 179	98.44 388	98.26 413	99.39 372	98.70 341	99.74 176	99.30 404	98.54 223	99.97 44	98.48 268	99.82 253	99.55 235
jason: jason.
APDe-MVS		99.48 134	99.36 167	99.85 32	99.55 307	99.81 47	99.50 102	99.69 219	98.99 291	99.75 165	99.71 195	98.79 182	99.93 120	98.46 270	99.85 229	99.80 67
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
icg_test_0407_2		99.30 201	99.29 191	99.31 316	99.71 203	98.55 377	98.17 421	99.71 201	99.41 219	99.73 182	99.60 292	99.17 111	99.92 153	98.45 271	99.70 326	99.45 293

IMVS_0407		99.38 177	99.42 150	99.28 324	99.71 203	98.55 377	99.27 181	99.71 201	99.41 219	99.73 182	99.60 292	99.17 111	99.83 332	98.45 271	99.70 326	99.45 293

IMVS_0404		99.23 220	99.20 210	99.32 312	99.71 203	98.55 377	98.57 376	99.71 201	99.41 219	99.52 286	99.60 292	98.12 284	99.95 81	98.45 271	99.70 326	99.45 293

IMVS_0403		99.37 181	99.39 156	99.28 324	99.71 203	98.55 377	99.19 210	99.71 201	99.41 219	99.67 214	99.60 292	99.12 123	99.84 310	98.45 271	99.70 326	99.45 293

CL-MVSNet_self_test		98.71 336	98.56 339	99.15 349	99.22 420	98.66 359	97.14 498	99.51 334	98.09 413	99.54 279	99.27 411	96.87 360	99.74 424	98.43 275	98.96 457	99.03 427

our_test_3		98.85 320	99.09 240	98.13 452	99.66 245	94.90 512	97.72 465	99.58 293	99.07 282	99.64 230	99.62 272	98.19 277	99.93 120	98.41 276	99.95 116	99.55 235

Gipuma		99.57 102	99.59 96	99.49 242	99.98 3	99.71 101	99.72 33	99.84 103	99.81 91	99.94 48	99.78 133	98.91 167	99.71 434	98.41 276	99.95 116	99.05 422
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 442	96.91 454	98.74 413	97.72 526	97.57 441	97.60 474	97.36 512	98.00 418	99.21 373	98.02 511	90.04 493	99.79 383	98.37 278	95.89 534	98.86 452

PM-MVS		99.36 186	99.29 191	99.58 200	99.83 90	99.66 122	98.95 310	99.86 88	98.85 316	99.81 119	99.73 176	98.40 251	99.92 153	98.36 279	99.83 243	99.17 387

baseline1		97.73 422	97.33 435	98.96 376	99.30 404	97.73 436	99.40 127	98.42 479	99.33 233	99.46 306	99.21 430	91.18 473	99.82 353	98.35 280	91.26 537	99.32 350

MVS-HIRNet		97.86 414	98.22 381	96.76 505	99.28 409	91.53 534	98.38 403	92.60 540	99.13 274	99.31 351	99.96 15	97.18 347	99.68 457	98.34 281	99.83 243	99.07 420

GA-MVS		97.99 409	97.68 423	98.93 383	99.52 325	98.04 418	97.19 494	99.05 440	98.32 396	98.81 426	98.97 465	89.89 495	99.41 507	98.33 282	99.05 450	99.34 345

Fast-Effi-MVS+		99.02 285	98.87 301	99.46 254	99.38 373	99.50 182	99.04 272	99.79 147	97.17 473	98.62 445	98.74 485	99.34 85	99.95 81	98.32 283	99.41 410	98.92 444

MDA-MVSNet_test_wron		98.95 304	98.99 280	98.85 400	99.64 251	97.16 461	98.23 415	99.33 392	98.93 304	99.56 271	99.66 237	97.39 335	99.83 332	98.29 284	99.88 200	99.55 235

N_pmnet		98.73 333	98.53 341	99.35 301	99.72 198	98.67 356	98.34 405	94.65 533	98.35 389	99.79 133	99.68 226	98.03 291	99.93 120	98.28 285	99.92 156	99.44 308

ET-MVSNet_ETH3D		96.78 457	96.07 470	98.91 389	99.26 414	97.92 427	97.70 468	96.05 522	97.96 425	92.37 538	98.43 502	87.06 504	99.90 202	98.27 286	97.56 515	98.91 446

thisisatest0530		97.45 437	96.95 451	98.94 379	99.68 235	97.73 436	99.09 257	94.19 536	98.61 355	99.56 271	99.30 404	84.30 518	99.93 120	98.27 286	99.54 387	99.16 389

YYNet1		98.95 304	98.99 280	98.84 402	99.64 251	97.14 463	98.22 416	99.32 394	98.92 307	99.59 258	99.66 237	97.40 333	99.83 332	98.27 286	99.90 173	99.55 235

reproduce_model		99.50 127	99.40 155	99.83 41	99.60 263	99.83 33	99.12 244	99.68 223	99.49 191	99.80 126	99.79 120	99.01 148	99.93 120	98.24 289	99.82 253	99.73 95

ACMM	98.09 11	99.46 146	99.38 159	99.72 122	99.80 120	99.69 113	99.13 239	99.65 243	98.99 291	99.64 230	99.72 185	99.39 71	99.86 274	98.23 290	99.81 263	99.60 208
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 301	98.87 301	99.24 337	99.57 289	98.40 391	98.12 428	99.18 427	98.28 399	99.63 235	99.13 438	98.02 292	99.97 44	98.22 291	99.69 335	99.35 339

3Dnovator	99.15 2	99.43 157	99.36 167	99.65 160	99.39 370	99.42 209	99.70 38	99.56 300	99.23 251	99.35 337	99.80 108	99.17 111	99.95 81	98.21 292	99.84 235	99.59 215

Fast-Effi-MVS+-dtu		99.20 236	99.12 226	99.43 265	99.25 415	99.69 113	99.05 267	99.82 119	99.50 189	98.97 406	99.05 451	98.98 155	99.98 26	98.20 293	99.24 435	98.62 468

MS-PatchMatch		99.00 294	98.97 285	99.09 359	99.11 444	98.19 404	98.76 346	99.33 392	98.49 370	99.44 309	99.58 305	98.21 274	99.69 445	98.20 293	99.62 358	99.39 327

TSAR-MVS + GP.		99.12 261	99.04 261	99.38 286	99.34 392	99.16 283	98.15 424	99.29 402	98.18 406	99.63 235	99.62 272	99.18 109	99.68 457	98.20 293	99.74 305	99.30 357

DP-MVS		99.48 134	99.39 156	99.74 103	99.57 289	99.62 143	99.29 175	99.61 266	99.87 62	99.74 176	99.76 155	98.69 197	99.87 255	98.20 293	99.80 270	99.75 89

MVP-Stereo		99.16 250	99.08 242	99.43 265	99.48 343	99.07 301	99.08 260	99.55 307	98.63 350	99.31 351	99.68 226	98.19 277	99.78 387	98.18 297	99.58 375	99.45 293
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 157	99.30 186	99.80 64	99.83 90	99.81 47	99.52 94	99.70 210	98.35 389	99.51 293	99.50 340	99.31 89	99.88 239	98.18 297	99.84 235	99.69 119

MDA-MVSNet-bldmvs		99.06 275	99.05 255	99.07 365	99.80 120	97.83 431	98.89 319	99.72 197	99.29 238	99.63 235	99.70 205	96.47 375	99.89 224	98.17 299	99.82 253	99.50 273

JIA-IIPM		98.06 404	97.92 409	98.50 431	98.59 500	97.02 465	98.80 340	98.51 473	99.88 60	97.89 490	99.87 56	91.89 465	99.90 202	98.16 300	97.68 514	98.59 471

EIA-MVS		99.12 261	99.01 269	99.45 257	99.36 379	99.62 143	99.34 149	99.79 147	98.41 376	98.84 423	98.89 474	98.75 189	99.84 310	98.15 301	99.51 393	98.89 449

miper_lstm_enhance		98.65 342	98.60 329	98.82 407	99.20 425	97.33 456	97.78 461	99.66 233	99.01 289	99.59 258	99.50 340	94.62 425	99.85 293	98.12 302	99.90 173	99.26 363

reproduce-ours		99.46 146	99.35 171	99.82 46	99.56 303	99.83 33	99.05 267	99.65 243	99.45 205	99.78 139	99.78 133	98.93 161	99.93 120	98.11 303	99.81 263	99.70 107

our_new_method		99.46 146	99.35 171	99.82 46	99.56 303	99.83 33	99.05 267	99.65 243	99.45 205	99.78 139	99.78 133	98.93 161	99.93 120	98.11 303	99.81 263	99.70 107

Effi-MVS+-dtu		99.07 274	98.92 294	99.52 232	98.89 472	99.78 57	99.15 228	99.66 233	99.34 230	98.92 413	99.24 423	97.69 317	99.98 26	98.11 303	99.28 427	98.81 457

tpm		97.15 449	96.95 451	97.75 467	98.91 468	94.24 516	99.32 158	97.96 498	97.71 445	98.29 465	99.32 398	86.72 510	99.92 153	98.10 306	96.24 532	99.09 409

DeepPCF-MVS	98.42 6	99.18 243	99.02 264	99.67 145	99.22 420	99.75 79	97.25 492	99.47 346	98.72 338	99.66 220	99.70 205	99.29 91	99.63 479	98.07 307	99.81 263	99.62 188

ppachtmachnet_test		98.89 314	99.12 226	98.20 450	99.66 245	95.24 508	97.63 471	99.68 223	99.08 280	99.78 139	99.62 272	98.65 205	99.88 239	98.02 308	99.96 91	99.48 282

tpmrst		97.73 422	98.07 395	96.73 508	98.71 495	92.00 529	99.10 252	98.86 450	98.52 366	98.92 413	99.54 326	91.90 464	99.82 353	98.02 308	99.03 453	98.37 485

CSCG		99.37 181	99.29 191	99.60 193	99.71 203	99.46 194	99.43 121	99.85 94	98.79 328	99.41 322	99.60 292	98.92 164	99.92 153	98.02 308	99.92 156	99.43 314

eth_miper_zixun_eth		98.68 339	98.71 318	98.60 424	99.10 446	96.84 473	97.52 480	99.54 313	98.94 299	99.58 260	99.48 349	96.25 388	99.76 407	98.01 311	99.93 148	99.21 374

Patchmtry		98.78 326	98.54 340	99.49 242	98.89 472	99.19 276	99.32 158	99.67 228	99.65 153	99.72 187	99.79 120	91.87 466	99.95 81	98.00 312	99.97 77	99.33 346

PVSNet_BlendedMVS		99.03 282	99.01 269	99.09 359	99.54 309	97.99 420	98.58 372	99.82 119	97.62 448	99.34 341	99.71 195	98.52 232	99.77 400	97.98 313	99.97 77	99.52 265

PVSNet_Blended		98.70 337	98.59 331	99.02 370	99.54 309	97.99 420	97.58 475	99.82 119	95.70 504	99.34 341	98.98 463	98.52 232	99.77 400	97.98 313	99.83 243	99.30 357

cl____		98.54 356	98.41 359	98.92 384	99.03 457	97.80 434	97.46 482	99.59 284	98.90 309	99.60 255	99.46 356	93.85 435	99.78 387	97.97 315	99.89 189	99.17 387

DIV-MVS_self_test		98.54 356	98.42 358	98.92 384	99.03 457	97.80 434	97.46 482	99.59 284	98.90 309	99.60 255	99.46 356	93.87 434	99.78 387	97.97 315	99.89 189	99.18 384

AUN-MVS		97.82 416	97.38 433	99.14 352	99.27 411	98.53 381	98.72 353	99.02 442	98.10 411	97.18 513	99.03 457	89.26 497	99.85 293	97.94 317	97.91 510	99.03 427

FA-MVS(test-final)		98.52 358	98.32 371	99.10 358	99.48 343	98.67 356	99.77 19	98.60 469	97.35 464	99.63 235	99.80 108	93.07 447	99.84 310	97.92 318	99.30 424	98.78 460

ambc				99.20 343	99.35 383	98.53 381	99.17 219	99.46 349		99.67 214	99.80 108	98.46 241	99.70 438	97.92 318	99.70 326	99.38 329

USDC		98.96 301	98.93 290	99.05 368	99.54 309	97.99 420	97.07 502	99.80 138	98.21 403	99.75 165	99.77 145	98.43 244	99.64 477	97.90 320	99.88 200	99.51 267

OPM-MVS		99.26 211	99.13 222	99.63 174	99.70 219	99.61 153	98.58 372	99.48 343	98.50 368	99.52 286	99.63 262	99.14 118	99.76 407	97.89 321	99.77 289	99.51 267
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 198	99.17 214	99.77 80	99.69 227	99.80 51	99.14 232	99.31 398	99.16 268	99.62 245	99.61 282	98.35 255	99.91 183	97.88 322	99.72 320	99.61 203
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	99.70 219	99.79 54	99.14 232	99.61 266					99.92 153	97.88 322	99.72 320	99.77 81

c3_l		98.72 334	98.71 318	98.72 415	99.12 439	97.22 460	97.68 469	99.56 300	98.90 309	99.54 279	99.48 349	96.37 381	99.73 427	97.88 322	99.88 200	99.21 374

SIFT-ConvMatch		98.16 398	98.37 364	97.52 474	99.54 309	99.20 273	96.97 507	98.47 476	98.09 413	99.14 386	99.40 371	95.93 399	99.05 522	97.87 325	99.92 156	94.31 527

3Dnovator+	98.92 3	99.35 188	99.24 205	99.67 145	99.35 383	99.47 188	99.62 67	99.50 338	99.44 207	99.12 390	99.78 133	98.77 186	99.94 98	97.87 325	99.72 320	99.62 188

miper_ehance_all_eth		98.59 350	98.59 331	98.59 425	98.98 464	97.07 464	97.49 481	99.52 329	98.50 368	99.52 286	99.37 383	96.41 379	99.71 434	97.86 327	99.62 358	99.00 434

WTY-MVS		98.59 350	98.37 364	99.26 332	99.43 361	98.40 391	98.74 350	99.13 435	98.10 411	99.21 373	99.24 423	94.82 421	99.90 202	97.86 327	98.77 470	99.49 278

ArgMatch-SfM		99.14 255	99.06 248	99.36 297	99.59 269	99.14 287	98.45 398	99.81 132	98.67 345	99.50 296	99.42 363	98.55 218	99.84 310	97.85 329	99.73 312	99.11 400

APD_test1		99.36 186	99.28 194	99.61 189	99.89 40	99.89 10	99.32 158	99.74 183	99.18 259	99.69 200	99.75 163	98.41 247	99.84 310	97.85 329	99.70 326	99.10 403

SED-MVS		99.40 170	99.28 194	99.77 80	99.69 227	99.82 41	99.20 204	99.54 313	99.13 274	99.82 112	99.63 262	98.91 167	99.92 153	97.85 329	99.70 326	99.58 221

test_241102_TWO								99.54 313	99.13 274	99.76 160	99.63 262	98.32 261	99.92 153	97.85 329	99.69 335	99.75 89

MVS_111021_HR		99.12 261	99.02 264	99.40 279	99.50 333	99.11 291	97.92 453	99.71 201	98.76 336	99.08 394	99.47 353	99.17 111	99.54 494	97.85 329	99.76 293	99.54 247

SIFT-PointCN		98.28 382	98.47 348	97.71 471	99.70 219	98.91 328	96.98 506	99.70 210	97.90 430	99.36 333	99.35 393	95.51 409	99.83 332	97.84 334	99.89 189	94.39 526

MTAPA		99.35 188	99.20 210	99.80 64	99.81 111	99.81 47	99.33 155	99.53 324	99.27 242	99.42 316	99.63 262	98.21 274	99.95 81	97.83 335	99.79 276	99.65 158

MSC_two_6792asdad				99.74 103	99.03 457	99.53 175		99.23 416					99.92 153	97.77 336	99.69 335	99.78 77

No_MVS				99.74 103	99.03 457	99.53 175		99.23 416					99.92 153	97.77 336	99.69 335	99.78 77

TESTMET0.1,1		96.24 475	95.84 476	97.41 482	98.24 513	93.84 519	97.38 485	95.84 527	98.43 373	97.81 496	98.56 497	79.77 527	99.89 224	97.77 336	98.77 470	98.52 477

ACMH+	98.40 8	99.50 127	99.43 147	99.71 128	99.86 60	99.76 70	99.32 158	99.77 164	99.53 184	99.77 151	99.76 155	99.26 97	99.78 387	97.77 336	99.88 200	99.60 208

IU-MVS					99.69 227	99.77 63		99.22 419	97.50 455	99.69 200				97.75 340	99.70 326	99.77 81

114514_t		98.49 363	98.11 392	99.64 167	99.73 193	99.58 164	99.24 193	99.76 172	89.94 534	99.42 316	99.56 316	97.76 314	99.86 274	97.74 341	99.82 253	99.47 286

MASt3R-SfM		98.45 368	98.51 343	98.26 449	99.32 398	97.43 452	97.43 484	99.69 219	94.97 514	99.75 165	99.41 365	98.49 236	99.75 418	97.73 342	99.79 276	97.61 512

DVP-MVS++		99.38 177	99.25 203	99.77 80	99.03 457	99.77 63	99.74 27	99.61 266	99.18 259	99.76 160	99.61 282	99.00 149	99.92 153	97.72 343	99.60 369	99.62 188

test_0728_THIRD									99.18 259	99.62 245	99.61 282	98.58 213	99.91 183	97.72 343	99.80 270	99.77 81

EGC-MVSNET		89.05 506	85.52 509	99.64 167	99.89 40	99.78 57	99.56 87	99.52 329	24.19 543	49.96 544	99.83 83	99.15 115	99.92 153	97.71 345	99.85 229	99.21 374

miper_enhance_ethall		98.03 405	97.94 407	98.32 442	98.27 512	96.43 481	96.95 508	99.41 362	96.37 494	99.43 313	98.96 467	94.74 422	99.69 445	97.71 345	99.62 358	98.83 455

TSAR-MVS + MP.		99.34 193	99.24 205	99.63 174	99.82 99	99.37 228	99.26 186	99.35 383	98.77 333	99.57 263	99.70 205	99.27 96	99.88 239	97.71 345	99.75 298	99.65 158
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 430	97.28 436	98.40 436	98.37 509	96.75 474	97.24 493	99.37 378	97.31 466	99.41 322	99.22 426	87.30 502	99.37 509	97.70 348	99.62 358	99.08 415

MP-MVS-pluss		99.14 255	98.92 294	99.80 64	99.83 90	99.83 33	98.61 365	99.63 255	96.84 486	99.44 309	99.58 305	98.81 177	99.91 183	97.70 348	99.82 253	99.67 135
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 205	99.11 229	99.79 72	99.75 179	99.81 47	98.95 310	99.53 324	98.27 400	99.53 284	99.73 176	98.75 189	99.87 255	97.70 348	99.83 243	99.68 126

UnsupCasMVSNet_bld		98.55 354	98.27 377	99.40 279	99.56 303	99.37 228	97.97 449	99.68 223	97.49 456	99.08 394	99.35 393	95.41 413	99.82 353	97.70 348	98.19 501	99.01 433

MVS_111021_LR		99.13 258	99.03 263	99.42 268	99.58 279	99.32 241	97.91 455	99.73 188	98.68 343	99.31 351	99.48 349	99.09 127	99.66 468	97.70 348	99.77 289	99.29 360

IS-MVSNet		99.03 282	98.85 303	99.55 219	99.80 120	99.25 256	99.73 30	99.15 431	99.37 225	99.61 252	99.71 195	94.73 423	99.81 369	97.70 348	99.88 200	99.58 221

MED-MVS test				99.74 103	99.76 161	99.65 128	99.38 132	99.78 159	99.58 178	99.81 119	99.66 237		99.90 202	97.69 354	99.79 276	99.67 135

MED-MVS		99.51 124	99.42 150	99.80 64	99.76 161	99.65 128	99.38 132	99.78 159	99.77 106	99.81 119	99.78 133	99.02 147	99.90 202	97.69 354	99.79 276	99.85 50

ME-MVS		99.26 211	99.10 238	99.73 113	99.60 263	99.65 128	98.75 349	99.45 354	99.31 236	99.65 224	99.66 237	98.00 297	99.86 274	97.69 354	99.79 276	99.67 135

test-LLR		97.15 449	96.95 451	97.74 468	98.18 516	95.02 510	97.38 485	96.10 519	98.00 418	97.81 496	98.58 494	90.04 493	99.91 183	97.69 354	98.78 468	98.31 486

test-mter		96.23 476	95.73 479	97.74 468	98.18 516	95.02 510	97.38 485	96.10 519	97.90 430	97.81 496	98.58 494	79.12 530	99.91 183	97.69 354	98.78 468	98.31 486

MonoMVSNet		98.23 389	98.32 371	97.99 455	98.97 465	96.62 476	99.49 107	98.42 479	99.62 162	99.40 327	99.79 120	95.51 409	98.58 531	97.68 359	95.98 533	98.76 463

SP-DiffGlue		98.47 365	98.43 357	98.59 425	97.44 534	98.59 372	98.01 441	99.36 382	99.00 290	99.06 398	99.20 432	97.01 354	99.25 513	97.64 360	99.15 441	97.92 508

SIFT-NCMNet		98.18 394	98.46 350	97.36 486	99.67 242	99.19 276	96.33 524	98.99 446	98.83 321	99.62 245	99.63 262	95.41 413	99.33 510	97.64 360	100.00 1	93.54 538

XVS		99.27 209	99.11 229	99.75 98	99.71 203	99.71 101	99.37 140	99.61 266	99.29 238	98.76 433	99.47 353	98.47 237	99.88 239	97.62 362	99.73 312	99.67 135

X-MVStestdata		96.09 480	94.87 495	99.75 98	99.71 203	99.71 101	99.37 140	99.61 266	99.29 238	98.76 433	61.30 552	98.47 237	99.88 239	97.62 362	99.73 312	99.67 135

SMA-MVS		99.19 239	99.00 273	99.73 113	99.46 353	99.73 90	99.13 239	99.52 329	97.40 461	99.57 263	99.64 246	98.93 161	99.83 332	97.61 364	99.79 276	99.63 176
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		96.71 460	96.79 459	96.46 512	98.90 469	90.71 540	99.41 122	98.68 461	94.69 519	98.14 480	99.34 397	86.32 512	99.80 379	97.60 365	98.07 508	98.88 450

PVSNet	97.47 15	98.42 371	98.44 355	98.35 439	99.46 353	96.26 485	96.70 518	99.34 387	97.68 446	99.00 404	99.13 438	97.40 333	99.72 429	97.59 366	99.68 340	99.08 415

SIFT-PCN-Cal		98.24 387	98.51 343	97.43 481	99.65 249	98.64 366	97.09 499	99.35 383	98.16 407	99.69 200	99.52 333	95.59 404	99.83 332	97.57 367	100.00 1	93.81 534

new_pmnet		98.88 315	98.89 299	98.84 402	99.70 219	97.62 440	98.15 424	99.50 338	97.98 421	99.62 245	99.54 326	98.15 280	99.94 98	97.55 368	99.84 235	98.95 439

IB-MVS	95.41 20	95.30 495	94.46 501	97.84 464	98.76 491	95.33 505	97.33 488	96.07 521	96.02 498	95.37 531	97.41 523	76.17 537	99.96 69	97.54 369	95.44 536	98.22 493
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		99.24 217	99.11 229	99.61 189	98.38 508	99.79 54	99.57 85	99.68 223	99.61 167	99.15 384	99.71 195	98.70 196	99.91 183	97.54 369	99.68 340	99.13 399

ZNCC-MVS		99.22 229	99.04 261	99.77 80	99.76 161	99.73 90	99.28 177	99.56 300	98.19 405	99.14 386	99.29 408	98.84 176	99.92 153	97.53 371	99.80 270	99.64 170

CP-MVS		99.23 220	99.05 255	99.75 98	99.66 245	99.66 122	99.38 132	99.62 258	98.38 381	99.06 398	99.27 411	98.79 182	99.94 98	97.51 372	99.82 253	99.66 149

SD-MVS		99.01 291	99.30 186	98.15 451	99.50 333	99.40 217	98.94 312	99.61 266	99.22 255	99.75 165	99.82 91	99.54 55	95.51 541	97.48 373	99.87 214	99.54 247
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
SIFT-NN-PointCN		97.97 410	98.24 379	97.14 497	99.59 269	98.71 353	96.75 515	99.56 300	97.02 480	97.91 489	99.27 411	96.85 361	98.39 532	97.47 374	99.76 293	94.31 527

PMMVS		98.49 363	98.29 376	99.11 356	98.96 466	98.42 390	97.54 476	99.32 394	97.53 453	98.47 457	98.15 510	97.88 303	99.82 353	97.46 375	99.24 435	99.09 409

DeepC-MVS_fast	98.47 5	99.23 220	99.12 226	99.56 212	99.28 409	99.22 267	98.99 298	99.40 369	99.08 280	99.58 260	99.64 246	98.90 170	99.83 332	97.44 376	99.75 298	99.63 176
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 213	99.08 242	99.76 87	99.73 193	99.70 109	99.31 164	99.59 284	98.36 383	99.36 333	99.37 383	98.80 181	99.91 183	97.43 377	99.75 298	99.68 126

ACMMPR		99.23 220	99.06 248	99.76 87	99.74 189	99.69 113	99.31 164	99.59 284	98.36 383	99.35 337	99.38 379	98.61 209	99.93 120	97.43 377	99.75 298	99.67 135

Vis-MVSNet (Re-imp)		98.77 328	98.58 334	99.34 304	99.78 143	98.88 333	99.61 73	99.56 300	99.11 278	99.24 366	99.56 316	93.00 449	99.78 387	97.43 377	99.89 189	99.35 339

MIMVSNet		98.43 370	98.20 383	99.11 356	99.53 318	98.38 395	99.58 82	98.61 466	98.96 295	99.33 343	99.76 155	90.92 477	99.81 369	97.38 380	99.76 293	99.15 391

WB-MVSnew		98.34 381	98.14 390	98.96 376	98.14 519	97.90 428	98.27 411	97.26 514	98.63 350	98.80 428	98.00 513	97.77 312	99.90 202	97.37 381	98.98 456	99.09 409

SP-MNN		97.94 413	97.82 414	98.31 444	98.30 511	97.67 439	97.81 460	97.93 500	98.14 408	97.16 515	98.64 493	96.31 384	99.21 515	97.34 382	98.75 474	98.05 502

XVG-OURS-SEG-HR		99.16 250	98.99 280	99.66 153	99.84 81	99.64 135	98.25 414	99.73 188	98.39 379	99.63 235	99.43 361	99.70 31	99.90 202	97.34 382	98.64 482	99.44 308

COLMAP_ROB	98.06 12	99.45 150	99.37 162	99.70 133	99.83 90	99.70 109	99.38 132	99.78 159	99.53 184	99.67 214	99.78 133	99.19 108	99.86 274	97.32 384	99.87 214	99.55 235
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
0.4-1-1-0.1		93.18 501	91.66 505	97.73 470	95.83 539	95.29 506	95.30 530	95.90 525	93.59 522	90.58 540	94.40 549	77.87 532	99.77 400	97.31 385	84.20 538	98.15 498

MCST-MVS		99.02 285	98.81 310	99.65 160	99.58 279	99.49 183	98.58 372	99.07 437	98.40 378	99.04 400	99.25 417	98.51 234	99.80 379	97.31 385	99.51 393	99.65 158

region2R		99.23 220	99.05 255	99.77 80	99.76 161	99.70 109	99.31 164	99.59 284	98.41 376	99.32 346	99.36 388	98.73 193	99.93 120	97.29 387	99.74 305	99.67 135

APD-MVS_3200maxsize		99.31 200	99.16 215	99.74 103	99.53 318	99.75 79	99.27 181	99.61 266	99.19 258	99.57 263	99.64 246	98.76 187	99.90 202	97.29 387	99.62 358	99.56 231

TAPA-MVS	97.92 13	98.03 405	97.55 427	99.46 254	99.47 349	99.44 202	98.50 389	99.62 258	86.79 535	99.07 397	99.26 415	98.26 267	99.62 480	97.28 389	99.73 312	99.31 355
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 209	99.11 229	99.73 113	99.54 309	99.74 87	99.26 186	99.62 258	99.16 268	99.52 286	99.64 246	98.41 247	99.91 183	97.27 390	99.61 366	99.54 247

RE-MVS-def			99.13 222		99.54 309	99.74 87	99.26 186	99.62 258	99.16 268	99.52 286	99.64 246	98.57 214		97.27 390	99.61 366	99.54 247

testing11		96.05 482	95.41 485	97.97 457	98.78 488	95.27 507	98.59 370	98.23 490	98.86 315	96.56 522	96.91 535	75.20 539	99.69 445	97.26 392	98.29 496	98.93 442

test_yl		98.25 385	97.95 403	99.13 354	99.17 431	98.47 384	99.00 290	98.67 463	98.97 293	99.22 371	99.02 458	91.31 471	99.69 445	97.26 392	98.93 459	99.24 366

DCV-MVSNet		98.25 385	97.95 403	99.13 354	99.17 431	98.47 384	99.00 290	98.67 463	98.97 293	99.22 371	99.02 458	91.31 471	99.69 445	97.26 392	98.93 459	99.24 366

PHI-MVS		99.11 266	98.95 288	99.59 196	99.13 437	99.59 159	99.17 219	99.65 243	97.88 434	99.25 363	99.46 356	98.97 157	99.80 379	97.26 392	99.82 253	99.37 333

tfpnnormal		99.43 157	99.38 159	99.60 193	99.87 55	99.75 79	99.59 80	99.78 159	99.71 121	99.90 67	99.69 214	98.85 175	99.90 202	97.25 396	99.78 285	99.15 391

PatchmatchNet		97.65 426	97.80 415	97.18 493	98.82 483	92.49 527	99.17 219	98.39 483	98.12 410	98.79 430	99.58 305	90.71 484	99.89 224	97.23 397	99.41 410	99.16 389
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 297	98.80 313	99.56 212	99.25 415	99.43 206	98.54 383	99.27 406	98.58 357	98.80 428	99.43 361	98.53 228	99.70 438	97.22 398	99.59 373	99.54 247

SIFT-UM-Cal		98.18 394	98.45 353	97.37 485	99.59 269	98.95 319	96.76 514	99.39 372	98.39 379	99.46 306	99.31 401	96.23 390	99.24 514	97.21 399	99.70 326	93.90 533

testing3		96.48 468	95.63 481	99.01 371	99.23 419	97.81 432	98.90 318	99.10 436	98.72 338	97.84 495	97.92 514	72.44 543	99.85 293	97.21 399	99.33 420	99.35 339

HPM-MVS		99.25 213	99.07 246	99.78 76	99.81 111	99.75 79	99.61 73	99.67 228	97.72 444	99.35 337	99.25 417	99.23 103	99.92 153	97.21 399	99.82 253	99.67 135
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
0.3-1-1-0.015		92.36 503	90.68 507	97.39 483	94.94 543	94.41 515	94.21 534	95.89 526	92.87 525	88.87 542	93.49 551	75.30 538	99.76 407	97.19 402	83.41 540	98.02 503

0.4-1-1-0.2		92.59 502	91.07 506	97.15 496	94.73 545	93.68 521	93.50 535	95.91 523	92.68 526	90.48 541	93.52 550	77.77 533	99.75 418	97.19 402	83.88 539	98.01 504

MatchFormer		99.03 282	99.02 264	99.08 364	99.56 303	98.47 384	98.57 376	99.90 63	98.13 409	99.80 126	99.75 163	98.34 257	99.84 310	97.18 404	99.90 173	98.92 444

mPP-MVS		99.19 239	99.00 273	99.76 87	99.76 161	99.68 116	99.38 132	99.54 313	98.34 393	99.01 403	99.50 340	98.53 228	99.93 120	97.18 404	99.78 285	99.66 149

ACMMP		99.25 213	99.08 242	99.74 103	99.79 134	99.68 116	99.50 102	99.65 243	98.07 415	99.52 286	99.69 214	98.57 214	99.92 153	97.18 404	99.79 276	99.63 176
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		96.23 476	95.74 478	97.70 472	98.86 476	95.59 502	98.66 361	98.14 492	98.96 295	97.67 502	97.06 531	76.78 535	98.92 525	97.10 407	98.41 493	98.58 473

thisisatest0515		96.98 453	96.42 462	98.66 421	99.42 366	97.47 446	97.27 490	94.30 535	97.24 469	99.15 384	98.86 476	85.01 514	99.87 255	97.10 407	99.39 412	98.63 467

XVG-ACMP-BASELINE		99.23 220	99.10 238	99.63 174	99.82 99	99.58 164	98.83 332	99.72 197	98.36 383	99.60 255	99.71 195	98.92 164	99.91 183	97.08 409	99.84 235	99.40 323

MSDG		99.08 271	98.98 283	99.37 291	99.60 263	99.13 288	97.54 476	99.74 183	98.84 320	99.53 284	99.55 324	99.10 125	99.79 383	97.07 410	99.86 222	99.18 384

SteuartSystems-ACMMP		99.30 201	99.14 220	99.76 87	99.87 55	99.66 122	99.18 214	99.60 278	98.55 360	99.57 263	99.67 232	99.03 146	99.94 98	97.01 411	99.80 270	99.69 119
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 478	95.78 477	97.49 475	98.53 502	93.83 520	98.04 438	93.94 538	98.96 295	98.46 458	98.17 509	79.86 525	99.87 255	96.99 412	99.06 448	98.78 460

EPMVS		96.53 465	96.32 463	97.17 495	98.18 516	92.97 525	99.39 129	89.95 544	98.21 403	98.61 446	99.59 302	86.69 511	99.72 429	96.99 412	99.23 437	98.81 457

SIFT-CM-Cal		97.96 412	98.15 389	97.39 483	99.61 260	99.15 285	96.75 515	98.41 482	98.04 417	99.03 401	99.54 326	95.24 416	99.41 507	96.97 414	99.80 270	93.61 537

MSP-MVS		99.04 281	98.79 314	99.81 54	99.78 143	99.73 90	99.35 148	99.57 295	98.54 363	99.54 279	98.99 460	96.81 362	99.93 120	96.97 414	99.53 389	99.77 81
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++		98.96 301	98.70 322	99.74 103	99.52 325	99.71 101	98.86 325	99.19 426	98.47 372	98.59 448	99.06 450	98.08 289	99.91 183	96.94 416	99.60 369	99.60 208

SR-MVS		99.19 239	99.00 273	99.74 103	99.51 327	99.72 95	99.18 214	99.60 278	98.85 316	99.47 302	99.58 305	98.38 252	99.92 153	96.92 417	99.54 387	99.57 227

PGM-MVS		99.20 236	99.01 269	99.77 80	99.75 179	99.71 101	99.16 225	99.72 197	97.99 420	99.42 316	99.60 292	98.81 177	99.93 120	96.91 418	99.74 305	99.66 149

HY-MVS	98.23 9	98.21 393	97.95 403	98.99 372	99.03 457	98.24 399	99.61 73	98.72 459	96.81 487	98.73 435	99.51 337	94.06 432	99.86 274	96.91 418	98.20 499	98.86 452

MDTV_nov1_ep13			97.73 421		98.70 496	90.83 538	99.15 228	98.02 496	98.51 367	98.82 425	99.61 282	90.98 476	99.66 468	96.89 420	98.92 461

SIFT-NCM-Cal		98.18 394	98.41 359	97.48 476	99.57 289	99.28 247	97.26 491	98.08 493	98.30 398	99.23 367	99.39 376	97.13 348	99.04 523	96.86 421	99.86 222	94.12 530

GST-MVS		99.16 250	98.96 287	99.75 98	99.73 193	99.73 90	99.20 204	99.55 307	98.22 402	99.32 346	99.35 393	98.65 205	99.91 183	96.86 421	99.74 305	99.62 188

test_post1							99.14 232				51.63 554	89.54 496	99.82 353	96.86 421

SCA		98.11 400	98.36 366	97.36 486	99.20 425	92.99 524	98.17 421	98.49 475	98.24 401	99.10 393	99.57 312	96.01 396	99.94 98	96.86 421	99.62 358	99.14 396

UBG		96.53 465	95.95 472	98.29 447	98.87 475	96.31 484	98.48 392	98.07 494	98.83 321	97.32 508	96.54 543	79.81 526	99.62 480	96.84 425	98.74 475	98.95 439

XVG-OURS		99.21 234	99.06 248	99.65 160	99.82 99	99.62 143	97.87 457	99.74 183	98.36 383	99.66 220	99.68 226	99.71 28	99.90 202	96.84 425	99.88 200	99.43 314

LCM-MVSNet-Re		99.28 205	99.15 219	99.67 145	99.33 397	99.76 70	99.34 149	99.97 21	98.93 304	99.91 62	99.79 120	98.68 198	99.93 120	96.80 427	99.56 378	99.30 357

RPSCF		99.18 243	99.02 264	99.64 167	99.83 90	99.85 21	99.44 119	99.82 119	98.33 395	99.50 296	99.78 133	97.90 301	99.65 475	96.78 428	99.83 243	99.44 308

旧先验2							97.94 451		95.33 509	98.94 409			99.88 239	96.75 429

MDTV_nov1_ep13_2view						91.44 535	99.14 232		97.37 463	99.21 373		91.78 468		96.75 429		99.03 427

CLD-MVS		98.76 329	98.57 335	99.33 307	99.57 289	98.97 315	97.53 478	99.55 307	96.41 492	99.27 358	99.13 438	99.07 134	99.78 387	96.73 431	99.89 189	99.23 369
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 401	97.98 401	98.48 432	99.27 411	96.48 479	99.40 127	99.07 437	98.81 325	99.23 367	99.57 312	90.11 492	99.87 255	96.69 432	99.64 353	99.09 409

baseline2		96.83 456	96.28 464	98.46 434	99.09 450	96.91 469	98.83 332	93.87 539	97.23 470	96.23 527	98.36 504	88.12 501	99.90 202	96.68 433	98.14 504	98.57 475

cascas		96.99 452	96.82 458	97.48 476	97.57 532	95.64 499	96.43 522	99.56 300	91.75 530	97.13 516	97.61 522	95.58 405	98.63 529	96.68 433	99.11 444	98.18 497

PC_three_1452									97.56 449	99.68 206	99.41 365	99.09 127	97.09 537	96.66 435	99.60 369	99.62 188

LPG-MVS_test		99.22 229	99.05 255	99.74 103	99.82 99	99.63 141	99.16 225	99.73 188	97.56 449	99.64 230	99.69 214	99.37 78	99.89 224	96.66 435	99.87 214	99.69 119

LGP-MVS_train				99.74 103	99.82 99	99.63 141		99.73 188	97.56 449	99.64 230	99.69 214	99.37 78	99.89 224	96.66 435	99.87 214	99.69 119

ETVMVS		96.14 479	95.22 490	98.89 396	98.80 484	98.01 419	98.66 361	98.35 486	98.71 340	97.18 513	96.31 548	74.23 542	99.75 418	96.64 438	98.13 507	98.90 447

SIFT-MNN		97.55 432	97.74 420	96.98 501	99.38 373	98.85 338	96.92 511	98.61 466	98.36 383	98.63 444	99.10 446	92.51 456	97.85 535	96.63 439	99.48 400	94.25 529

TinyColmap		98.97 298	98.93 290	99.07 365	99.46 353	98.19 404	97.75 462	99.75 177	98.79 328	99.54 279	99.70 205	98.97 157	99.62 480	96.63 439	99.83 243	99.41 320

LF4IMVS		99.01 291	98.92 294	99.27 329	99.71 203	99.28 247	98.59 370	99.77 164	98.32 396	99.39 329	99.41 365	98.62 207	99.84 310	96.62 441	99.84 235	98.69 466

NCCC		98.82 322	98.57 335	99.58 200	99.21 422	99.31 242	98.61 365	99.25 411	98.65 347	98.43 459	99.26 415	97.86 304	99.81 369	96.55 442	99.27 430	99.61 203

OPU-MVS				99.29 321	99.12 439	99.44 202	99.20 204				99.40 371	99.00 149	98.84 527	96.54 443	99.60 369	99.58 221

F-COLMAP		98.74 331	98.45 353	99.62 183	99.57 289	99.47 188	98.84 329	99.65 243	96.31 495	98.93 410	99.19 434	97.68 318	99.87 255	96.52 444	99.37 415	99.53 254

SIFT-UMatch		98.07 403	98.27 377	97.46 480	99.57 289	98.99 310	96.93 510	99.02 442	98.53 364	99.26 362	99.23 425	95.43 412	99.31 511	96.51 445	99.91 169	94.09 531

testing99		95.86 487	95.19 491	97.87 462	98.76 491	95.03 509	98.62 364	98.44 478	98.68 343	96.67 520	96.66 542	74.31 541	99.69 445	96.51 445	98.03 509	98.90 447

ADS-MVSNet2		97.78 420	97.66 425	98.12 453	99.14 435	95.36 504	99.22 201	98.75 458	96.97 481	98.25 467	99.64 246	90.90 478	99.94 98	96.51 445	99.56 378	99.08 415

ADS-MVSNet		97.72 425	97.67 424	97.86 463	99.14 435	94.65 513	99.22 201	98.86 450	96.97 481	98.25 467	99.64 246	90.90 478	99.84 310	96.51 445	99.56 378	99.08 415

PatchMatch-RL		98.68 339	98.47 348	99.30 320	99.44 358	99.28 247	98.14 426	99.54 313	97.12 476	99.11 391	99.25 417	97.80 309	99.70 438	96.51 445	99.30 424	98.93 442

CMPMVS	77.52 23	98.50 361	98.19 386	99.41 276	98.33 510	99.56 168	99.01 284	99.59 284	95.44 507	99.57 263	99.80 108	95.64 402	99.46 506	96.47 450	99.92 156	99.21 374
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 483	95.32 488	98.02 454	98.76 491	95.39 503	98.38 403	98.65 465	98.82 323	96.84 517	96.71 541	75.06 540	99.71 434	96.46 451	98.23 498	98.98 436

SF-MVS		99.10 269	98.93 290	99.62 183	99.58 279	99.51 181	99.13 239	99.65 243	97.97 422	99.42 316	99.61 282	98.86 174	99.87 255	96.45 452	99.68 340	99.49 278

FE-MVS		97.85 415	97.42 432	99.15 349	99.44 358	98.75 350	99.77 19	98.20 491	95.85 500	99.33 343	99.80 108	88.86 498	99.88 239	96.40 453	99.12 443	98.81 457

DPE-MVS		99.14 255	98.92 294	99.82 46	99.57 289	99.77 63	98.74 350	99.60 278	98.55 360	99.76 160	99.69 214	98.23 272	99.92 153	96.39 454	99.75 298	99.76 86
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 530	89.02 546			93.47 523		98.30 505		99.84 310	96.38 455

AllTest		99.21 234	99.07 246	99.63 174	99.78 143	99.64 135	99.12 244	99.83 113	98.63 350	99.63 235	99.72 185	98.68 198	99.75 418	96.38 455	99.83 243	99.51 267

TestCases				99.63 174	99.78 143	99.64 135		99.83 113	98.63 350	99.63 235	99.72 185	98.68 198	99.75 418	96.38 455	99.83 243	99.51 267

testdata				99.42 268	99.51 327	98.93 324		99.30 401	96.20 496	98.87 420	99.40 371	98.33 260	99.89 224	96.29 458	99.28 427	99.44 308

dp		96.86 455	97.07 446	96.24 514	98.68 498	90.30 544	99.19 210	98.38 484	97.35 464	98.23 469	99.59 302	87.23 503	99.82 353	96.27 459	98.73 478	98.59 471

SP-NN		96.37 471	96.23 466	96.77 504	96.83 536	96.95 466	96.47 521	97.07 516	96.75 489	93.41 537	97.75 516	94.13 431	95.69 539	96.25 460	97.43 517	97.68 511

tpmvs		97.39 441	97.69 422	96.52 510	98.41 507	91.76 531	99.30 167	98.94 448	97.74 441	97.85 494	99.55 324	92.40 460	99.73 427	96.25 460	98.73 478	98.06 500

KD-MVS_2432*1600		95.89 484	95.41 485	97.31 490	94.96 541	93.89 517	97.09 499	99.22 419	97.23 470	98.88 417	99.04 453	79.23 528	99.54 494	96.24 462	96.81 522	98.50 481

miper_refine_blended		95.89 484	95.41 485	97.31 490	94.96 541	93.89 517	97.09 499	99.22 419	97.23 470	98.88 417	99.04 453	79.23 528	99.54 494	96.24 462	96.81 522	98.50 481

ACMP	97.51 14	99.05 278	98.84 305	99.67 145	99.78 143	99.55 172	98.88 321	99.66 233	97.11 477	99.47 302	99.60 292	99.07 134	99.89 224	96.18 464	99.85 229	99.58 221
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 311	98.72 317	99.44 261	99.39 370	99.42 209	98.58 372	99.64 251	97.31 466	99.44 309	99.62 272	98.59 211	99.69 445	96.17 465	99.79 276	99.22 371

DP-MVS Recon		98.50 361	98.23 380	99.31 316	99.49 338	99.46 194	98.56 379	99.63 255	94.86 517	98.85 422	99.37 383	97.81 308	99.59 487	96.08 466	99.44 405	98.88 450

tpm cat1		96.78 457	96.98 450	96.16 515	98.85 477	90.59 541	99.08 260	99.32 394	92.37 527	97.73 500	99.46 356	91.15 474	99.69 445	96.07 467	98.80 467	98.21 494

tpm2		96.35 472	96.22 467	96.73 508	98.88 474	91.75 532	99.21 203	98.51 473	93.27 524	97.89 490	99.21 430	84.83 515	99.70 438	96.04 468	98.18 502	98.75 464

dmvs_re		98.69 338	98.48 347	99.31 316	99.55 307	99.42 209	99.54 90	98.38 484	99.32 234	98.72 436	98.71 487	96.76 364	99.21 515	96.01 469	99.35 418	99.31 355

test_0402		99.22 229	99.14 220	99.45 257	99.79 134	99.43 206	99.28 177	99.68 223	99.54 182	99.40 327	99.56 316	99.07 134	99.82 353	96.01 469	99.96 91	99.11 400

ITE_SJBPF				99.38 286	99.63 255	99.44 202		99.73 188	98.56 358	99.33 343	99.53 329	98.88 171	99.68 457	96.01 469	99.65 351	99.02 432

test_prior2							97.95 450		97.87 435	98.05 482	99.05 451	97.90 301		95.99 472	99.49 398

testdata2													99.89 224	95.99 472

原ACMM1				99.37 291	99.47 349	98.87 337		99.27 406	96.74 490	98.26 466	99.32 398	97.93 300	99.82 353	95.96 474	99.38 413	99.43 314

新几何1				99.52 232	99.50 333	99.22 267		99.26 408	95.66 505	98.60 447	99.28 409	97.67 319	99.89 224	95.95 475	99.32 422	99.45 293

MP-MVS		99.06 275	98.83 307	99.76 87	99.76 161	99.71 101	99.32 158	99.50 338	98.35 389	98.97 406	99.48 349	98.37 253	99.92 153	95.95 475	99.75 298	99.63 176
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ALIKED-LG		98.78 326	98.66 324	99.14 352	99.02 463	99.40 217	98.74 350	99.79 147	98.62 354	99.18 379	99.38 379	97.54 327	99.77 400	95.94 477	99.74 305	98.25 491

testing222		95.60 494	94.59 499	98.61 423	98.66 499	97.45 449	98.54 383	97.90 502	98.53 364	96.54 523	96.47 545	70.62 546	99.81 369	95.91 478	98.15 503	98.56 476

wuyk23d		97.58 429	99.13 222	92.93 522	99.69 227	99.49 183	99.52 94	99.77 164	97.97 422	99.96 34	99.79 120	99.84 16	99.94 98	95.85 479	99.82 253	79.36 540

HQP_MVS		98.90 311	98.68 323	99.55 219	99.58 279	99.24 261	98.80 340	99.54 313	98.94 299	99.14 386	99.25 417	97.24 341	99.82 353	95.84 480	99.78 285	99.60 208

plane_prior5								99.54 313					99.82 353	95.84 480	99.78 285	99.60 208

SIFT-NN-CMatch		97.30 444	97.34 434	97.18 493	99.54 309	98.85 338	96.02 526	95.77 530	97.05 479	97.55 504	98.70 489	96.35 383	98.75 528	95.82 482	99.26 431	93.95 532

无先验							98.01 441	99.23 416	95.83 501				99.85 293	95.79 483		99.44 308

SIFT-NN-UMatch		97.18 448	97.24 440	97.01 500	99.57 289	98.65 363	96.33 524	97.31 513	97.07 478	97.48 505	98.73 486	94.39 428	98.87 526	95.75 484	98.50 490	93.50 539

CPTT-MVS		98.74 331	98.44 355	99.64 167	99.61 260	99.38 223	99.18 214	99.55 307	96.49 491	99.27 358	99.37 383	97.11 350	99.92 153	95.74 485	99.67 346	99.62 188

PLC	97.35 16	98.36 376	97.99 399	99.48 248	99.32 398	99.24 261	98.50 389	99.51 334	95.19 512	98.58 449	98.96 467	96.95 357	99.83 332	95.63 486	99.25 433	99.37 333
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 352	98.34 369	99.28 324	99.18 430	99.10 298	98.34 405	99.41 362	98.48 371	98.52 454	98.98 463	97.05 352	99.78 387	95.59 487	99.50 396	98.96 437

1314		98.00 408	97.90 411	98.27 448	98.90 469	97.45 449	99.30 167	99.06 439	94.98 513	97.21 512	99.12 442	98.43 244	99.67 463	95.58 488	98.56 485	97.71 510

PVSNet_0	95.53 19	95.85 488	95.31 489	97.47 478	98.78 488	93.48 523	95.72 527	99.40 369	96.18 497	97.37 507	97.73 517	95.73 401	99.58 488	95.49 489	81.40 541	99.36 336

MAR-MVS		98.24 387	97.92 409	99.19 344	98.78 488	99.65 128	99.17 219	99.14 433	95.36 508	98.04 483	98.81 482	97.47 330	99.72 429	95.47 490	99.06 448	98.21 494
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	98.23 389	97.89 412	99.26 332	99.19 427	99.26 253	99.65 62	99.69 219	91.33 532	98.14 480	99.77 145	98.28 264	99.96 69	95.41 491	99.55 382	98.58 473

train_agg		98.35 379	97.95 403	99.57 208	99.35 383	99.35 235	98.11 430	99.41 362	94.90 515	97.92 487	98.99 460	98.02 292	99.85 293	95.38 492	99.44 405	99.50 273

9.14			98.64 325		99.45 357		98.81 337	99.60 278	97.52 454	99.28 357	99.56 316	98.53 228	99.83 332	95.36 493	99.64 353

APD-MVS		98.87 316	98.59 331	99.71 128	99.50 333	99.62 143	99.01 284	99.57 295	96.80 488	99.54 279	99.63 262	98.29 263	99.91 183	95.24 494	99.71 324	99.61 203
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 482								95.20 495

AdaColmap		98.60 347	98.35 368	99.38 286	99.12 439	99.22 267	98.67 359	99.42 361	97.84 439	98.81 426	99.27 411	97.32 339	99.81 369	95.14 496	99.53 389	99.10 403

test9_res														95.10 497	99.44 405	99.50 273

CDPH-MVS		98.56 353	98.20 383	99.61 189	99.50 333	99.46 194	98.32 408	99.41 362	95.22 510	99.21 373	99.10 446	98.34 257	99.82 353	95.09 498	99.66 349	99.56 231

SIFT-NN-NCMNet		97.22 446	97.27 438	97.07 499	99.64 251	99.20 273	96.53 520	95.91 523	96.91 483	97.38 506	98.95 469	96.01 396	98.29 533	94.87 499	99.21 439	93.73 536

BH-untuned		98.22 391	98.09 393	98.58 428	99.38 373	97.24 459	98.55 380	98.98 447	97.81 440	99.20 378	98.76 484	97.01 354	99.65 475	94.83 500	98.33 494	98.86 452

BP-MVS														94.73 501

HQP-MVS		98.36 376	98.02 398	99.39 282	99.31 400	98.94 321	97.98 446	99.37 378	97.45 457	98.15 476	98.83 479	96.67 366	99.70 438	94.73 501	99.67 346	99.53 254

QAPM		98.40 374	97.99 399	99.65 160	99.39 370	99.47 188	99.67 53	99.52 329	91.70 531	98.78 432	99.80 108	98.55 218	99.95 81	94.71 503	99.75 298	99.53 254

agg_prior2														94.58 504	99.46 404	99.50 273

myMVS_eth3d		95.63 492	94.73 496	98.34 441	98.50 504	96.36 482	98.60 367	99.21 422	97.89 432	96.76 518	96.37 546	72.10 544	99.57 489	94.38 505	98.73 478	99.09 409

BH-RMVSNet		98.41 372	98.14 390	99.21 340	99.21 422	98.47 384	98.60 367	98.26 489	98.35 389	98.93 410	99.31 401	97.20 346	99.66 468	94.32 506	99.10 445	99.51 267

E-PMN		97.14 451	97.43 431	96.27 513	98.79 486	91.62 533	95.54 528	99.01 445	99.44 207	98.88 417	99.12 442	92.78 450	99.68 457	94.30 507	99.03 453	97.50 513

MG-MVS		98.52 358	98.39 362	98.94 379	99.15 434	97.39 454	98.18 418	99.21 422	98.89 312	99.23 367	99.63 262	97.37 336	99.74 424	94.22 508	99.61 366	99.69 119

ALIKED-MNN		98.03 405	97.78 418	98.78 410	98.84 479	98.97 315	98.16 423	99.74 183	97.31 466	96.60 521	98.85 477	96.61 368	99.48 503	94.16 509	99.77 289	97.91 509

API-MVS		98.38 375	98.39 362	98.35 439	98.83 480	99.26 253	99.14 232	99.18 427	98.59 356	98.66 441	98.78 483	98.61 209	99.57 489	94.14 510	99.56 378	96.21 521

PAPM_NR		98.36 376	98.04 396	99.33 307	99.48 343	98.93 324	98.79 343	99.28 405	97.54 452	98.56 453	98.57 496	97.12 349	99.69 445	94.09 511	98.90 465	99.38 329

ZD-MVS					99.43 361	99.61 153		99.43 359	96.38 493	99.11 391	99.07 449	97.86 304	99.92 153	94.04 512	99.49 398

DPM-MVS		98.28 382	97.94 407	99.32 312	99.36 379	99.11 291	97.31 489	98.78 457	96.88 484	98.84 423	99.11 445	97.77 312	99.61 485	94.03 513	99.36 416	99.23 369

gg-mvs-nofinetune		95.87 486	95.17 492	97.97 457	98.19 515	96.95 466	99.69 45	89.23 545	99.89 55	96.24 526	99.94 19	81.19 520	99.51 501	93.99 514	98.20 499	97.44 514

XFeat-MNN		96.67 461	96.56 460	96.98 501	96.73 537	95.62 501	94.54 533	98.93 449	97.42 460	98.18 471	98.67 492	91.60 469	99.12 517	93.88 515	99.10 445	96.21 521

PMVS	92.94 21	98.82 322	98.81 310	98.85 400	99.84 81	97.99 420	99.20 204	99.47 346	99.71 121	99.42 316	99.82 91	98.09 287	99.47 504	93.88 515	99.85 229	99.07 420
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 454	97.28 436	95.99 517	98.76 491	91.03 537	95.26 531	98.61 466	99.34 230	98.92 413	98.88 475	93.79 436	99.66 468	92.87 517	99.05 450	97.30 517

BH-w/o		97.20 447	97.01 449	97.76 466	99.08 451	95.69 498	98.03 440	98.52 472	95.76 503	97.96 486	98.02 511	95.62 403	99.47 504	92.82 518	97.25 521	98.12 499

TR-MVS		97.44 438	97.15 443	98.32 442	98.53 502	97.46 447	98.47 393	97.91 501	96.85 485	98.21 470	98.51 500	96.42 377	99.51 501	92.16 519	97.29 520	97.98 505

ALIKED-NN		96.66 462	96.26 465	97.88 461	97.49 533	98.59 372	96.71 517	99.15 431	95.50 506	93.58 536	98.39 503	94.52 427	97.74 536	92.05 520	98.94 458	97.29 518

OpenMVS_ROB	97.31 17	97.36 443	96.84 456	98.89 396	99.29 406	99.45 200	98.87 324	99.48 343	86.54 537	99.44 309	99.74 171	97.34 337	99.86 274	91.61 521	99.28 427	97.37 516

GG-mvs-BLEND				97.36 486	97.59 530	96.87 470	99.70 38	88.49 546		94.64 534	97.26 528	80.66 522	99.12 517	91.50 522	96.50 530	96.08 524

DeepMVS_CX				97.98 456	99.69 227	96.95 466		99.26 408	75.51 540	95.74 529	98.28 506	96.47 375	99.62 480	91.23 523	97.89 511	97.38 515

PAPR		97.56 430	97.07 446	99.04 369	98.80 484	98.11 412	97.63 471	99.25 411	94.56 521	98.02 485	98.25 507	97.43 332	99.68 457	90.90 524	98.74 475	99.33 346

MVS		95.72 490	94.63 498	98.99 372	98.56 501	97.98 425	99.30 167	98.86 450	72.71 541	97.30 509	99.08 448	98.34 257	99.74 424	89.21 525	98.33 494	99.26 363

SIFT-NN		94.78 498	94.89 494	94.45 520	98.23 514	97.29 457	94.93 532	95.84 527	95.82 502	94.78 533	97.12 529	90.26 490	92.28 543	88.91 526	98.14 504	93.77 535

UWE-MVS-28		95.64 491	95.47 483	96.14 516	97.98 522	90.39 542	98.49 391	95.81 529	99.02 288	98.03 484	98.19 508	84.49 517	99.28 512	88.75 527	98.47 491	98.75 464

thres600view7		96.60 464	96.16 468	97.93 459	99.63 255	96.09 492	99.18 214	97.57 507	98.77 333	98.72 436	97.32 526	87.04 505	99.72 429	88.57 528	98.62 483	97.98 505

FPMVS		96.32 473	95.50 482	98.79 408	99.60 263	98.17 407	98.46 397	98.80 456	97.16 474	96.28 524	99.63 262	82.19 519	99.09 520	88.45 529	98.89 466	99.10 403

XFeat-NN		93.89 500	93.91 502	93.83 521	95.49 540	92.69 526	90.85 536	97.98 497	94.69 519	95.08 532	96.98 532	88.36 500	94.23 542	88.42 530	97.34 518	94.57 525

PCF-MVS	96.03 18	96.73 459	95.86 475	99.33 307	99.44 358	99.16 283	96.87 512	99.44 355	86.58 536	98.95 408	99.40 371	94.38 429	99.88 239	87.93 531	99.80 270	98.95 439
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 470	96.03 471	97.47 478	99.63 255	95.93 493	99.18 214	97.57 507	98.75 337	98.70 439	97.31 527	87.04 505	99.67 463	87.62 532	98.51 487	96.81 519

tfpn200view9		96.30 474	95.89 473	97.53 473	99.58 279	96.11 490	99.00 290	97.54 510	98.43 373	98.52 454	96.98 532	86.85 507	99.67 463	87.62 532	98.51 487	96.81 519

thres400		96.40 469	95.89 473	97.92 460	99.58 279	96.11 490	99.00 290	97.54 510	98.43 373	98.52 454	96.98 532	86.85 507	99.67 463	87.62 532	98.51 487	97.98 505

thres200		96.09 480	95.68 480	97.33 489	99.48 343	96.22 487	98.53 385	97.57 507	98.06 416	98.37 462	96.73 540	86.84 509	99.61 485	86.99 535	98.57 484	96.16 523

MVE	92.54 22	96.66 462	96.11 469	98.31 444	99.68 235	97.55 442	97.94 451	95.60 531	99.37 225	90.68 539	98.70 489	96.56 370	98.61 530	86.94 536	99.55 382	98.77 462
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 445	96.83 457	98.59 425	99.46 353	97.55 442	99.25 192	96.84 518	98.78 330	97.24 511	97.67 518	97.11 350	98.97 524	86.59 537	98.54 486	99.27 361

GLUNet-SfM		95.26 496	95.06 493	95.87 518	94.84 544	90.39 542	90.24 538	99.92 46	92.30 528	99.16 381	99.25 417	94.69 424	98.01 534	85.55 538	99.62 358	99.21 374

PAPM		95.61 493	94.71 497	98.31 444	99.12 439	96.63 475	96.66 519	98.46 477	90.77 533	96.25 525	98.68 491	93.01 448	99.69 445	81.60 539	97.86 513	98.62 468

SD_0403		97.42 439	96.90 455	98.98 374	99.54 309	97.90 428	99.52 94	99.54 313	99.34 230	97.87 492	98.85 477	98.72 194	99.64 477	78.93 540	99.83 243	99.40 323

dongtai		89.37 505	88.91 508	90.76 523	99.19 427	77.46 548	95.47 529	87.82 547	92.28 529	94.17 535	98.82 481	71.22 545	95.54 540	63.85 541	97.34 518	99.27 361

kuosan		85.65 507	84.57 510	88.90 525	97.91 524	77.11 549	96.37 523	87.62 548	85.24 538	85.45 543	96.83 536	69.94 547	90.98 544	45.90 542	95.83 535	98.62 468

test123		29.31 508	33.05 513	18.08 526	25.93 550	12.24 551	97.53 478	10.93 551	11.78 544	24.21 545	50.08 556	21.04 548	8.60 545	23.51 543	32.43 544	33.39 541

testmvs		28.94 509	33.33 511	15.79 527	26.03 549	9.81 552	96.77 513	15.67 550	11.55 545	23.87 546	50.74 555	19.03 549	8.53 546	23.21 544	33.07 543	29.03 542

mmdepth		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

monomultidepth		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

test_blank		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet_test		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

DCPMVS		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

cdsmvs_eth3d_5k		24.88 510	33.17 512	0.00 528	0.00 551	0.00 553	0.00 539	99.62 258	0.00 546	0.00 547	99.13 438	99.82 18	0.00 547	0.00 545	0.00 545	0.00 543

pcd_1.5k_mvsjas		16.61 511	22.14 514	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	99.28 93	0.00 547	0.00 545	0.00 545	0.00 543

sosnet-low-res		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

sosnet		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uncertanet		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

Regformer		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

ab-mvs-re		8.26 522	11.02 525	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	99.16 435	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet		8.33 512	11.11 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	100.00 1	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

TestfortrainingZip				99.38 286	99.17 431	99.25 256	99.38 132	98.82 453	98.93 304	99.68 206	99.49 345	98.11 286	99.56 493		98.44 492	99.32 350

FOURS1					99.83 90	99.89 10	99.74 27	99.71 201	99.69 131	99.63 235

test_one_0601					99.63 255	99.76 70		99.55 307	99.23 251	99.31 351	99.61 282	98.59 211

eth-test2					0.00 551

eth-test					0.00 551

test_241102_ONE					99.69 227	99.82 41		99.54 313	99.12 277	99.82 112	99.49 345	98.91 167	99.52 500

save fliter					99.53 318	99.25 256	98.29 410	99.38 377	99.07 282

test0726					99.69 227	99.80 51	99.24 193	99.57 295	99.16 268	99.73 182	99.65 244	98.35 255

GSMVS																99.14 396

test_part2					99.62 259	99.67 119				99.55 276

sam_mvs1												90.81 482				99.14 396

sam_mvs												90.52 488

MTGPA								99.53 324

test_post											52.41 553	90.25 491	99.86 274

patchmatchnet-post											99.62 272	90.58 486	99.94 98

MTMP							99.09 257	98.59 470

TEST9					99.35 383	99.35 235	98.11 430	99.41 362	94.83 518	97.92 487	98.99 460	98.02 292	99.85 293

test_8					99.34 392	99.31 242	98.08 434	99.40 369	94.90 515	97.87 492	98.97 465	98.02 292	99.84 310

agg_prior					99.35 383	99.36 232		99.39 372		97.76 499			99.85 293

test_prior4						99.19 276	98.00 444

test_prior				99.46 254	99.35 383	99.22 267		99.39 372					99.69 445			99.48 282

新几何2							98.04 438

旧先验1					99.49 338	99.29 245		99.26 408			99.39 376	97.67 319			99.36 416	99.46 291

原ACMM2							97.92 453

test222					99.51 327	99.08 300	97.83 459	99.29 402	95.21 511	98.68 440	99.31 401	97.28 340			99.38 413	99.43 314

segment_acmp												98.37 253

testdata1							97.72 465		97.86 437

test12				99.54 225	99.29 406	99.33 238		99.16 430		98.43 459		97.54 327	99.82 353		99.47 401	99.48 282

plane_prior7					99.58 279	99.38 223

plane_prior6					99.47 349	99.26 253						97.24 341

plane_prior4											99.25 417

plane_prior3						99.31 242			98.36 383	99.14 386

plane_prior2							98.80 340		98.94 299

plane_prior1					99.51 327

plane_prior						99.24 261	98.42 401		97.87 435						99.71 324

n2								0.00 552

nn								0.00 552

door-mid								99.83 113

test11								99.29 402

door								99.77 164

HQP5-MVS						98.94 321

HQP-NCC					99.31 400		97.98 446		97.45 457	98.15 476

ACMP_Plane					99.31 400		97.98 446		97.45 457	98.15 476

HQP4-MVS										98.15 476			99.70 438			99.53 254

HQP3-MVS								99.37 378							99.67 346

HQP2-MVS												96.67 366

NP-MVS					99.40 369	99.13 288					98.83 479

ACMMP++_ref															99.94 134

ACMMP++															99.79 276

Test By Simon												98.41 247

High-resolution multi-view benchmark