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 80	99.70 38	100.00 1	99.73 109	100.00 1	99.89 41	99.79 22	99.88 235	99.98 1	100.00 1	99.98 5

test_fmvs2		99.72 54	99.85 17	99.34 291	99.91 31	98.08 382	99.48 109	100.00 1	99.90 50	99.99 7	99.91 31	99.50 61	99.98 27	99.98 1	99.99 16	99.96 13

test_fmvs3		99.83 21	99.93 2	99.53 226	99.96 7	98.62 337	99.67 53	100.00 1	99.95 32	100.00 1	99.95 16	99.85 14	99.99 8	99.98 1	99.99 16	99.98 5

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 71	99.12 241	100.00 1	100.00 1	99.99 7	99.91 31	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_vis1_n_1920		99.72 54	99.88 7	99.27 316	99.93 24	97.84 395	99.34 148	100.00 1	99.99 3	99.99 7	99.82 91	99.87 13	99.99 8	99.97 4	99.99 16	99.97 10

test_vis1_n		99.68 65	99.79 34	99.36 287	99.94 18	98.18 371	99.52 94	100.00 1	99.86 66	100.00 1	99.88 50	98.99 148	99.96 69	99.97 4	99.96 87	99.95 14

test_fmvs1_n		99.68 65	99.81 28	99.28 311	99.95 15	97.93 391	99.49 107	100.00 1	99.82 86	99.99 7	99.89 41	99.21 102	99.98 27	99.97 4	99.98 50	99.93 20

test_f		99.75 49	99.88 7	99.37 282	99.96 7	98.21 368	99.51 101	100.00 1	99.94 36	100.00 1	99.93 22	99.58 49	99.94 98	99.97 4	99.99 16	99.97 10

fmvsm_l_conf0.5_n_9		99.83 21	99.81 28	99.89 11	99.86 59	99.80 52	98.94 308	99.96 28	99.98 18	99.96 34	99.78 132	99.88 11	99.98 27	99.96 9	99.99 16	99.90 29

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 45	99.86 19	99.08 257	99.97 20	99.98 18	99.96 34	99.79 119	99.90 9	99.99 8	99.96 9	99.99 16	99.90 29

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 88	99.01 281	99.99 11	99.99 3	99.98 14	99.88 50	99.97 2	99.99 8	99.96 9	100.00 1	99.98 5

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 54	99.88 45	99.55 170	99.17 216	99.98 12	99.99 3	99.96 34	99.84 77	99.96 3	99.99 8	99.96 9	99.99 16	99.88 40

test_cas_vis1_n_1920		99.76 46	99.86 13	99.45 252	99.93 24	98.40 356	99.30 165	99.98 12	99.94 36	99.99 7	99.89 41	99.80 21	99.97 44	99.96 9	99.97 73	99.97 10

fmvsm_s_conf0.5_n_10		99.77 44	99.73 55	99.88 19	99.81 106	99.75 80	99.06 263	99.85 82	99.99 3	99.97 24	99.84 77	99.12 119	99.98 27	99.95 14	99.99 16	99.90 29

fmvsm_s_conf0.5_n_7		99.73 52	99.78 39	99.60 191	99.74 178	98.93 304	98.85 322	99.96 28	99.96 28	99.97 24	99.76 149	99.82 18	99.96 69	99.95 14	99.98 50	99.90 29

fmvsm_l_conf0.5_n		99.80 30	99.78 39	99.85 32	99.88 45	99.66 121	99.11 246	99.91 52	99.98 18	99.96 34	99.64 236	99.60 43	99.99 8	99.95 14	99.99 16	99.88 40

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 41	99.82 94	99.70 109	99.17 216	99.97 20	99.99 3	99.96 34	99.82 91	99.94 4	100.00 1	99.95 14	100.00 1	99.80 65

test_fmvs1		99.48 130	99.65 74	98.97 358	99.54 282	97.16 422	99.11 246	99.98 12	99.78 103	99.96 34	99.81 98	98.72 191	99.97 44	99.95 14	99.97 73	99.79 73

mvsany_test3		99.85 12	99.88 7	99.75 97	99.95 15	99.37 222	99.53 92	99.98 12	99.77 107	99.99 7	99.95 16	99.85 14	99.94 98	99.95 14	99.98 50	99.94 17

fmvsm_s_conf0.5_n_9		99.82 24	99.82 25	99.82 46	99.83 85	99.59 157	98.97 299	99.92 43	99.99 3	99.97 24	99.84 77	99.90 9	99.94 98	99.94 20	99.99 16	99.92 24

fmvsm_s_conf0.1_n_2		99.81 28	99.78 39	99.89 11	99.93 24	99.76 71	98.92 312	99.98 12	99.99 3	99.99 7	99.88 50	99.43 66	99.94 98	99.94 20	99.99 16	99.99 2

fmvsm_l_conf0.5_n_a		99.80 30	99.79 34	99.84 38	99.88 45	99.64 133	99.12 241	99.91 52	99.98 18	99.95 45	99.67 220	99.67 34	99.99 8	99.94 20	99.99 16	99.88 40

MM		99.18 233	99.05 242	99.55 216	99.35 353	98.81 315	99.05 264	97.79 463	99.99 3	99.48 283	99.59 288	96.29 363	99.95 81	99.94 20	99.98 50	99.88 40

test_fmvsmconf_n		99.85 12	99.84 20	99.88 19	99.91 31	99.73 91	98.97 299	99.98 12	99.99 3	99.96 34	99.85 69	99.93 7	99.99 8	99.94 20	99.99 16	99.93 20

fmvsm_s_conf0.5_n_11		99.76 46	99.75 51	99.81 54	99.81 106	99.53 173	99.15 225	99.89 61	99.99 3	99.98 14	99.86 63	99.13 116	99.98 27	99.93 25	99.99 16	99.92 24

fmvsm_s_conf0.5_n_5		99.78 37	99.76 49	99.85 32	99.79 129	99.72 96	98.84 324	99.96 28	99.96 28	99.96 34	99.72 175	99.71 28	99.99 8	99.93 25	99.98 50	99.85 49

fmvsm_s_conf0.5_n_2		99.78 37	99.75 51	99.88 19	99.82 94	99.76 71	98.88 316	99.92 43	99.98 18	99.98 14	99.85 69	99.42 68	99.94 98	99.93 25	99.98 50	99.94 17

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 43	99.10 249	99.98 12	99.99 3	99.98 14	99.91 31	99.68 33	99.93 119	99.93 25	99.99 16	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 58	99.07 262	99.98 12	99.99 3	99.98 14	99.90 36	99.88 11	99.92 150	99.93 25	99.99 16	99.98 5

fmvsm_s_conf0.5_n_a		99.82 24	99.79 34	99.89 11	99.85 72	99.82 43	99.03 272	99.96 28	99.99 3	99.97 24	99.84 77	99.58 49	99.93 119	99.92 30	99.98 50	99.93 20

fmvsm_s_conf0.5_n		99.83 21	99.81 28	99.87 26	99.85 72	99.78 58	99.03 272	99.96 28	99.99 3	99.97 24	99.84 77	99.78 23	99.92 150	99.92 30	99.99 16	99.92 24

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

fmvsm_s_conf0.5_n_8		99.76 46	99.72 56	99.88 19	99.82 94	99.75 80	99.02 276	99.87 70	99.98 18	99.98 14	99.81 98	99.07 130	99.97 44	99.91 33	99.99 16	99.92 24

fmvsm_s_conf0.5_n_6		99.80 30	99.78 39	99.85 32	99.78 137	99.78 58	99.00 287	99.97 20	99.96 28	99.97 24	99.56 302	99.92 8	99.93 119	99.91 33	99.99 16	99.83 56

fmvsm_s_conf0.5_n_4		99.78 37	99.78 39	99.79 71	99.75 170	99.56 166	98.98 297	99.94 38	99.92 46	99.97 24	99.72 175	99.84 16	99.92 150	99.91 33	99.98 50	99.89 37

MVStest1		98.22 366	98.09 361	98.62 399	99.04 423	96.23 445	99.20 201	99.92 43	99.44 199	99.98 14	99.87 56	85.87 466	99.67 436	99.91 33	99.57 347	99.95 14

v1921920		99.56 105	99.57 103	99.55 216	99.75 170	99.11 277	99.05 264	99.61 244	99.15 261	99.88 83	99.71 185	99.08 127	99.87 250	99.90 37	99.97 73	99.66 147

v1240		99.56 105	99.58 98	99.51 232	99.80 115	99.00 291	99.00 287	99.65 223	99.15 261	99.90 68	99.75 157	99.09 123	99.88 235	99.90 37	99.96 87	99.67 133

v10		99.69 60	99.69 61	99.66 151	99.81 106	99.39 216	99.66 57	99.75 161	99.60 165	99.92 60	99.87 56	98.75 186	99.86 269	99.90 37	99.99 16	99.73 93

v1192		99.57 101	99.57 103	99.57 205	99.77 150	99.22 258	99.04 269	99.60 255	99.18 250	99.87 93	99.72 175	99.08 127	99.85 288	99.89 40	99.98 50	99.66 147

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 32	99.81 106	99.71 101	98.97 299	99.92 43	99.98 18	99.97 24	99.86 63	99.53 57	99.95 81	99.88 41	99.99 16	99.89 37

v144192		99.55 110	99.54 113	99.58 197	99.78 137	99.20 264	99.11 246	99.62 237	99.18 250	99.89 73	99.72 175	98.66 200	99.87 250	99.88 41	99.97 73	99.66 147

v8		99.68 65	99.69 61	99.65 158	99.80 115	99.40 213	99.66 57	99.76 156	99.64 149	99.93 53	99.85 69	98.66 200	99.84 304	99.88 41	99.99 16	99.71 102

mvs5depth		99.88 6	99.91 3	99.80 64	99.92 29	99.42 205	99.94 3	100.00 1	99.97 25	99.89 73	99.99 12	99.63 37	99.97 44	99.87 44	99.99 16	100.00 1

v1144		99.54 114	99.53 117	99.59 194	99.79 129	99.28 240	99.10 249	99.61 244	99.20 247	99.84 102	99.73 167	98.67 198	99.84 304	99.86 45	99.98 50	99.64 168

mmtdpeth		99.78 37	99.83 21	99.66 151	99.85 72	99.05 290	99.79 15	99.97 20	100.00 1	99.43 295	99.94 19	99.64 35	99.94 98	99.83 46	99.99 16	99.98 5

SSC-MVS		99.52 120	99.42 144	99.83 41	99.86 59	99.65 127	99.52 94	99.81 117	99.87 63	99.81 116	99.79 119	96.78 342	99.99 8	99.83 46	99.51 363	99.86 46

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 27	99.82 10	99.82 104	99.84 76	99.94 48	99.91 31	99.13 116	99.96 69	99.83 46	99.99 16	99.83 56

v2v482		99.50 123	99.47 129	99.58 197	99.78 137	99.25 248	99.14 229	99.58 270	99.25 238	99.81 116	99.62 260	98.24 259	99.84 304	99.83 46	99.97 73	99.64 168

test_vis1_rt		99.45 146	99.46 134	99.41 270	99.71 191	98.63 336	98.99 294	99.96 28	99.03 274	99.95 45	99.12 408	98.75 186	99.84 304	99.82 50	99.82 232	99.77 79

tt0805		99.63 85	99.57 103	99.81 54	99.87 54	99.88 12	99.58 82	98.70 424	99.72 113	99.91 63	99.60 278	99.43 66	99.81 355	99.81 51	99.53 359	99.73 93

VortexMVS		99.13 246	99.24 196	98.79 389	99.67 227	96.60 437	99.24 190	99.80 122	99.85 72	99.93 53	99.84 77	95.06 381	99.89 220	99.80 52	99.98 50	99.89 37

V42		99.56 105	99.54 113	99.63 172	99.79 129	99.46 190	99.39 129	99.59 261	99.24 240	99.86 96	99.70 195	98.55 215	99.82 339	99.79 53	99.95 111	99.60 204

SSC-MVS3.2		99.64 84	99.67 65	99.56 209	99.75 170	98.98 294	98.96 303	99.87 70	99.88 61	99.84 102	99.64 236	99.32 86	99.91 179	99.78 54	99.96 87	99.80 65

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

WB-MVS		99.44 150	99.32 172	99.80 64	99.81 106	99.61 151	99.47 112	99.81 117	99.82 86	99.71 183	99.72 175	96.60 347	99.98 27	99.75 56	99.23 404	99.82 63

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 64	99.68 49	99.85 82	99.95 32	99.98 14	99.92 27	99.28 91	99.98 27	99.75 56	100.00 1	99.94 17

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

ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 62	100.00 1	99.90 50	100.00 1	99.97 14	99.61 41	99.97 44	99.75 56	100.00 1	99.84 52

AstraMVS		99.15 243	99.06 237	99.42 262	99.85 72	98.59 340	99.13 236	97.26 471	99.84 76	99.87 93	99.77 142	96.11 366	99.93 119	99.71 60	99.96 87	99.74 89

Elysia		99.69 60	99.65 74	99.81 54	99.86 59	99.72 96	99.34 148	99.77 148	99.94 36	99.91 63	99.76 149	98.55 215	99.99 8	99.70 61	99.98 50	99.72 97

StellarMVS		99.69 60	99.65 74	99.81 54	99.86 59	99.72 96	99.34 148	99.77 148	99.94 36	99.91 63	99.76 149	98.55 215	99.99 8	99.70 61	99.98 50	99.72 97

tt0320-xc		99.82 24	99.82 25	99.82 46	99.82 94	99.84 27	99.82 10	99.92 43	99.94 36	99.94 48	99.93 22	99.34 83	99.92 150	99.70 61	99.96 87	99.70 105

reproduce_monomvs		97.40 403	97.46 393	97.20 453	99.05 420	91.91 481	99.20 201	99.18 396	99.84 76	99.86 96	99.75 157	80.67 474	99.83 323	99.69 64	99.95 111	99.85 49

SPE-MVS-test		99.68 65	99.70 58	99.64 165	99.57 266	99.83 35	99.78 17	99.97 20	99.92 46	99.50 280	99.38 355	99.57 51	99.95 81	99.69 64	99.90 159	99.15 375

guyue		99.12 249	99.02 251	99.41 270	99.84 77	98.56 341	99.19 207	98.30 449	99.82 86	99.84 102	99.75 157	94.84 384	99.92 150	99.68 66	99.94 127	99.74 89

tt0320		99.79 34	99.79 34	99.81 54	99.82 94	99.84 27	99.82 10	99.90 58	99.94 36	99.94 48	99.94 19	99.07 130	99.92 150	99.68 66	99.97 73	99.67 133

MGCNet		98.61 324	98.30 345	99.52 228	97.88 486	98.95 300	98.76 341	94.11 487	99.84 76	99.32 326	99.57 298	95.57 375	99.95 81	99.68 66	99.98 50	99.68 124

CS-MVS		99.67 76	99.70 58	99.58 197	99.53 289	99.84 27	99.79 15	99.96 28	99.90 50	99.61 236	99.41 345	99.51 60	99.95 81	99.66 69	99.89 173	98.96 417

mamv4		99.73 52	99.74 53	99.70 132	99.66 229	99.87 15	99.69 45	99.93 39	99.93 43	99.93 53	99.86 63	99.07 130	100.00 1	99.66 69	99.92 145	99.24 350

KinetiMVS		99.66 77	99.63 82	99.76 86	99.89 39	99.57 165	99.37 140	99.82 104	99.95 32	99.90 68	99.63 251	98.57 211	99.97 44	99.65 71	99.94 127	99.74 89

pmmvs6		99.86 10	99.86 13	99.83 41	99.94 18	99.90 7	99.83 7	99.91 52	99.85 72	99.94 48	99.95 16	99.73 27	99.90 198	99.65 71	99.97 73	99.69 117

MIMVSNet1		99.66 77	99.62 84	99.80 64	99.94 18	99.87 15	99.69 45	99.77 148	99.78 103	99.93 53	99.89 41	97.94 287	99.92 150	99.65 71	99.98 50	99.62 186

LuminaMVS		99.39 169	99.28 187	99.73 113	99.83 85	99.49 180	99.00 287	99.05 408	99.81 92	99.89 73	99.79 119	96.54 351	99.97 44	99.64 74	99.98 50	99.73 93

sc_t1		99.81 28	99.80 32	99.82 46	99.88 45	99.88 12	99.83 7	99.79 131	99.94 36	99.93 53	99.92 27	99.35 82	99.92 150	99.64 74	99.94 127	99.68 124

EC-MVSNet		99.69 60	99.69 61	99.68 140	99.71 191	99.91 4	99.76 23	99.96 28	99.86 66	99.51 277	99.39 353	99.57 51	99.93 119	99.64 74	99.86 204	99.20 363

K. test v3		98.87 300	98.60 310	99.69 138	99.93 24	99.46 190	99.74 27	94.97 482	99.78 103	99.88 83	99.88 50	93.66 399	99.97 44	99.61 77	99.95 111	99.64 168

KD-MVS_self_test		99.63 85	99.59 94	99.76 86	99.84 77	99.90 7	99.37 140	99.79 131	99.83 82	99.88 83	99.85 69	98.42 239	99.90 198	99.60 78	99.73 286	99.49 269

Anonymous20240521		99.44 150	99.42 144	99.49 238	99.89 39	98.96 299	99.62 67	99.76 156	99.85 72	99.82 109	99.88 50	96.39 358	99.97 44	99.59 79	99.98 50	99.55 229

TransMVSNet (Re)		99.78 37	99.77 45	99.81 54	99.91 31	99.85 22	99.75 25	99.86 76	99.70 124	99.91 63	99.89 41	99.60 43	99.87 250	99.59 79	99.74 280	99.71 102

OurMVSNet-221017-0		99.75 49	99.71 57	99.84 38	99.96 7	99.83 35	99.83 7	99.85 82	99.80 96	99.93 53	99.93 22	98.54 219	99.93 119	99.59 79	99.98 50	99.76 84

EU-MVSNet		99.39 169	99.62 84	98.72 394	99.88 45	96.44 439	99.56 87	99.85 82	99.90 50	99.90 68	99.85 69	98.09 275	99.83 323	99.58 82	99.95 111	99.90 29

mvs_anonymous		99.28 197	99.39 149	98.94 362	99.19 396	97.81 397	99.02 276	99.55 283	99.78 103	99.85 99	99.80 108	98.24 259	99.86 269	99.57 83	99.50 366	99.15 375

test1111		97.74 387	98.16 357	96.49 464	99.60 244	89.86 495	99.71 37	91.21 491	99.89 56	99.88 83	99.87 56	93.73 398	99.90 198	99.56 84	99.99 16	99.70 105

lessismore_v0				99.64 165	99.86 59	99.38 218		90.66 492		99.89 73	99.83 84	94.56 389	99.97 44	99.56 84	99.92 145	99.57 222

mvsany_test1		99.44 150	99.45 136	99.40 273	99.37 346	98.64 335	97.90 437	99.59 261	99.27 234	99.92 60	99.82 91	99.74 26	99.93 119	99.55 86	99.87 196	99.63 174

MVSMamba_PlusPlus		99.55 110	99.58 98	99.47 245	99.68 220	99.40 213	99.52 94	99.70 192	99.92 46	99.77 145	99.86 63	98.28 255	99.96 69	99.54 87	99.90 159	99.05 404

pm-mvs1		99.79 34	99.79 34	99.78 75	99.91 31	99.83 35	99.76 23	99.87 70	99.73 109	99.89 73	99.87 56	99.63 37	99.87 250	99.54 87	99.92 145	99.63 174

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 19	99.91 31	99.90 7	99.96 1	99.92 43	99.90 50	99.97 24	99.87 56	99.81 20	99.95 81	99.54 87	99.99 16	99.80 65
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
DSMNet-mixed		99.48 130	99.65 74	98.95 361	99.71 191	97.27 419	99.50 102	99.82 104	99.59 167	99.41 304	99.85 69	99.62 40	100.00 1	99.53 90	99.89 173	99.59 211

test2506		94.73 454	94.59 454	95.15 471	99.59 250	85.90 497	99.75 25	74.01 499	99.89 56	99.71 183	99.86 63	79.00 484	99.90 198	99.52 91	99.99 16	99.65 156

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 183	99.93 43	99.95 45	99.89 41	99.71 28	99.96 69	99.51 92	99.97 73	99.84 52

FC-MVSNet-test		99.70 58	99.65 74	99.86 30	99.88 45	99.86 19	99.72 33	99.78 142	99.90 50	99.82 109	99.83 84	98.45 235	99.87 250	99.51 92	99.97 73	99.86 46

BP-MVS1		98.72 316	98.46 326	99.50 234	99.53 289	99.00 291	99.34 148	98.53 434	99.65 145	99.73 173	99.38 355	90.62 440	99.96 69	99.50 94	99.86 204	99.55 229

UA-Net		99.78 37	99.76 49	99.86 30	99.72 187	99.71 101	99.91 4	99.95 36	99.96 28	99.71 183	99.91 31	99.15 111	99.97 44	99.50 94	100.00 1	99.90 29

viewdifsd2359ckpt11		99.62 92	99.64 79	99.56 209	99.86 59	99.19 265	99.02 276	99.93 39	99.83 82	99.88 83	99.81 98	98.99 148	99.83 323	99.48 96	99.96 87	99.65 156

viewmsd2359difaftdt		99.62 92	99.64 79	99.56 209	99.86 59	99.19 265	99.02 276	99.93 39	99.83 82	99.88 83	99.81 98	98.99 148	99.83 323	99.48 96	99.96 87	99.65 156

PMMVS2		99.48 130	99.45 136	99.57 205	99.76 154	98.99 293	98.09 414	99.90 58	98.95 284	99.78 133	99.58 291	99.57 51	99.93 119	99.48 96	99.95 111	99.79 73

VPA-MVSNet		99.66 77	99.62 84	99.79 71	99.68 220	99.75 80	99.62 67	99.69 200	99.85 72	99.80 123	99.81 98	98.81 174	99.91 179	99.47 99	99.88 183	99.70 105

GDP-MVS		98.81 307	98.57 316	99.50 234	99.53 289	99.12 276	99.28 174	99.86 76	99.53 176	99.57 247	99.32 372	90.88 436	99.98 27	99.46 100	99.74 280	99.42 308

ECVR-MVS		97.73 388	98.04 364	96.78 457	99.59 250	90.81 490	99.72 33	90.43 493	99.89 56	99.86 96	99.86 63	93.60 400	99.89 220	99.46 100	99.99 16	99.65 156

nrg030		99.70 58	99.66 72	99.82 46	99.76 154	99.84 27	99.61 73	99.70 192	99.93 43	99.78 133	99.68 216	99.10 121	99.78 369	99.45 102	99.96 87	99.83 56

FE-MVSNET2		99.68 65	99.67 65	99.72 121	99.86 59	99.68 116	99.46 116	99.88 66	99.62 154	99.87 93	99.85 69	99.06 137	99.85 288	99.44 103	99.98 50	99.63 174

TAMVS		99.49 128	99.45 136	99.63 172	99.48 314	99.42 205	99.45 117	99.57 272	99.66 141	99.78 133	99.83 84	97.85 294	99.86 269	99.44 103	99.96 87	99.61 200

GeoE		99.69 60	99.66 72	99.78 75	99.76 154	99.76 71	99.60 79	99.82 104	99.46 194	99.75 158	99.56 302	99.63 37	99.95 81	99.43 105	99.88 183	99.62 186

new-patchmatchnet		99.35 182	99.57 103	98.71 397	99.82 94	96.62 435	98.55 369	99.75 161	99.50 181	99.88 83	99.87 56	99.31 87	99.88 235	99.43 105	100.00 1	99.62 186

test20.03		99.55 110	99.54 113	99.58 197	99.79 129	99.37 222	99.02 276	99.89 61	99.60 165	99.82 109	99.62 260	98.81 174	99.89 220	99.43 105	99.86 204	99.47 277

MVSFormer		99.41 163	99.44 140	99.31 303	99.57 266	98.40 356	99.77 19	99.80 122	99.73 109	99.63 220	99.30 377	98.02 280	99.98 27	99.43 105	99.69 306	99.55 229

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 27	99.77 19	99.80 122	99.73 109	99.97 24	99.92 27	99.77 25	99.98 27	99.43 105	100.00 1	99.90 29

SDMVSNet		99.77 44	99.77 45	99.76 86	99.80 115	99.65 127	99.63 64	99.86 76	99.97 25	99.89 73	99.89 41	99.52 59	99.99 8	99.42 110	99.96 87	99.65 156

Anonymous20231211		99.62 92	99.57 103	99.76 86	99.61 242	99.60 155	99.81 13	99.73 171	99.82 86	99.90 68	99.90 36	97.97 286	99.86 269	99.42 110	99.96 87	99.80 65

SixPastTwentyTwo		99.42 157	99.30 179	99.76 86	99.92 29	99.67 119	99.70 38	99.14 401	99.65 145	99.89 73	99.90 36	96.20 365	99.94 98	99.42 110	99.92 145	99.67 133

balanced_conf03		99.50 123	99.50 122	99.50 234	99.42 337	99.49 180	99.52 94	99.75 161	99.86 66	99.78 133	99.71 185	98.20 267	99.90 198	99.39 113	99.88 183	99.10 386

patch_mono-2		99.51 121	99.46 134	99.64 165	99.70 206	99.11 277	99.04 269	99.87 70	99.71 118	99.47 285	99.79 119	98.24 259	99.98 27	99.38 114	99.96 87	99.83 56

UGNet		99.38 172	99.34 166	99.49 238	98.90 435	98.90 308	99.70 38	99.35 355	99.86 66	98.57 419	99.81 98	98.50 230	99.93 119	99.38 114	99.98 50	99.66 147
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
XXY-MVS		99.71 57	99.67 65	99.81 54	99.89 39	99.72 96	99.59 80	99.82 104	99.39 215	99.82 109	99.84 77	99.38 74	99.91 179	99.38 114	99.93 139	99.80 65

FIs		99.65 83	99.58 98	99.84 38	99.84 77	99.85 22	99.66 57	99.75 161	99.86 66	99.74 168	99.79 119	98.27 257	99.85 288	99.37 117	99.93 139	99.83 56

sd_testset		99.78 37	99.78 39	99.80 64	99.80 115	99.76 71	99.80 14	99.79 131	99.97 25	99.89 73	99.89 41	99.53 57	99.99 8	99.36 118	99.96 87	99.65 156

anonymousdsp		99.80 30	99.77 45	99.90 8	99.96 7	99.88 12	99.73 30	99.85 82	99.70 124	99.92 60	99.93 22	99.45 62	99.97 44	99.36 118	100.00 1	99.85 49

casdiffmvs_mvg		99.68 65	99.68 64	99.69 138	99.81 106	99.59 157	99.29 172	99.90 58	99.71 118	99.79 129	99.73 167	99.54 54	99.84 304	99.36 118	99.96 87	99.65 156
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		99.75 49	99.74 53	99.79 71	99.88 45	99.66 121	99.69 45	99.92 43	99.67 137	99.77 145	99.75 157	99.61 41	99.98 27	99.35 121	99.98 50	99.72 97
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 96	99.64 79	99.53 226	99.79 129	98.82 314	99.58 82	99.97 20	99.95 32	99.96 34	99.76 149	98.44 236	99.99 8	99.34 122	99.96 87	99.78 75

CHOSEN 1792x2688		99.39 169	99.30 179	99.65 158	99.88 45	99.25 248	98.78 339	99.88 66	98.66 326	99.96 34	99.79 119	97.45 316	99.93 119	99.34 122	99.99 16	99.78 75

CDS-MVSNet		99.22 219	99.13 212	99.50 234	99.35 353	99.11 277	98.96 303	99.54 289	99.46 194	99.61 236	99.70 195	96.31 361	99.83 323	99.34 122	99.88 183	99.55 229
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 280	99.16 205	98.51 405	99.75 170	95.90 451	98.07 417	99.84 89	99.84 76	99.89 73	99.73 167	96.01 369	99.99 8	99.33 125	100.00 1	99.63 174

HyFIR lowres test		98.91 293	98.64 307	99.73 113	99.85 72	99.47 184	98.07 417	99.83 98	98.64 329	99.89 73	99.60 278	92.57 413	100.00 1	99.33 125	99.97 73	99.72 97

pmmvs5		99.19 229	99.11 219	99.42 262	99.76 154	98.88 310	98.55 369	99.73 171	98.82 305	99.72 178	99.62 260	96.56 348	99.82 339	99.32 127	99.95 111	99.56 225

v148		99.40 165	99.41 147	99.39 276	99.76 154	98.94 301	99.09 254	99.59 261	99.17 255	99.81 116	99.61 270	98.41 240	99.69 419	99.32 127	99.94 127	99.53 245

baseline		99.63 85	99.62 84	99.66 151	99.80 115	99.62 141	99.44 119	99.80 122	99.71 118	99.72 178	99.69 204	99.15 111	99.83 323	99.32 127	99.94 127	99.53 245

CVMVSNet		98.61 324	98.88 285	97.80 436	99.58 256	93.60 474	99.26 183	99.64 231	99.66 141	99.72 178	99.67 220	93.26 404	99.93 119	99.30 130	99.81 242	99.87 44

PS-CasMVS		99.66 77	99.58 98	99.89 11	99.80 115	99.85 22	99.66 57	99.73 171	99.62 154	99.84 102	99.71 185	98.62 204	99.96 69	99.30 130	99.96 87	99.86 46

DTE-MVSNet		99.68 65	99.61 88	99.88 19	99.80 115	99.87 15	99.67 53	99.71 183	99.72 113	99.84 102	99.78 132	98.67 198	99.97 44	99.30 130	99.95 111	99.80 65

tmp_tt		95.75 446	95.42 441	96.76 458	89.90 498	94.42 468	98.86 320	97.87 461	78.01 489	99.30 336	99.69 204	97.70 302	95.89 491	99.29 133	98.14 462	99.95 14

PEN-MVS		99.66 77	99.59 94	99.89 11	99.83 85	99.87 15	99.66 57	99.73 171	99.70 124	99.84 102	99.73 167	98.56 214	99.96 69	99.29 133	99.94 127	99.83 56

WR-MVS_H		99.61 96	99.53 117	99.87 26	99.80 115	99.83 35	99.67 53	99.75 161	99.58 169	99.85 99	99.69 204	98.18 270	99.94 98	99.28 135	99.95 111	99.83 56

IterMVS		98.97 284	99.16 205	98.42 410	99.74 178	95.64 455	98.06 419	99.83 98	99.83 82	99.85 99	99.74 162	96.10 368	99.99 8	99.27 136	100.00 1	99.63 174
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
NormalMVS		99.09 257	98.91 283	99.62 181	99.78 137	99.11 277	99.36 144	99.77 148	99.82 86	99.68 195	99.53 314	93.30 402	99.99 8	99.24 137	99.76 269	99.74 89

SymmetryMVS		99.01 277	98.82 293	99.58 197	99.65 234	99.11 277	99.36 144	99.20 394	99.82 86	99.68 195	99.53 314	93.30 402	99.99 8	99.24 137	99.63 327	99.64 168

WBMVS		97.50 399	97.18 404	98.48 407	98.85 443	95.89 452	98.44 386	99.52 304	99.53 176	99.52 270	99.42 344	80.10 477	99.86 269	99.24 137	99.95 111	99.68 124

h-mvs33		98.61 324	98.34 340	99.44 256	99.60 244	98.67 327	99.27 178	99.44 330	99.68 129	99.32 326	99.49 327	92.50 416	100.00 1	99.24 137	96.51 482	99.65 156

hse-mvs2		98.52 337	98.30 345	99.16 332	99.29 375	98.60 338	98.77 340	99.02 410	99.68 129	99.32 326	99.04 418	92.50 416	99.85 288	99.24 137	97.87 469	99.03 408

FMVSNet1		99.66 77	99.63 82	99.73 113	99.78 137	99.77 64	99.68 49	99.70 192	99.67 137	99.82 109	99.83 84	98.98 152	99.90 198	99.24 137	99.97 73	99.53 245

casdiffmvs		99.63 85	99.61 88	99.67 144	99.79 129	99.59 157	99.13 236	99.85 82	99.79 100	99.76 153	99.72 175	99.33 85	99.82 339	99.21 143	99.94 127	99.59 211
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CP-MVSNet		99.54 114	99.43 142	99.87 26	99.76 154	99.82 43	99.57 85	99.61 244	99.54 174	99.80 123	99.64 236	97.79 298	99.95 81	99.21 143	99.94 127	99.84 52

DELS-MVS		99.34 187	99.30 179	99.48 243	99.51 298	99.36 226	98.12 410	99.53 299	99.36 220	99.41 304	99.61 270	99.22 101	99.87 250	99.21 143	99.68 311	99.20 363
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		99.47 140	99.50 122	99.37 282	99.70 206	98.80 318	98.67 350	99.92 43	99.49 183	99.77 145	99.71 185	99.08 127	99.78 369	99.20 146	99.94 127	99.54 239

UniMVSNet (Re)		99.37 176	99.26 192	99.68 140	99.51 298	99.58 162	98.98 297	99.60 255	99.43 206	99.70 187	99.36 363	97.70 302	99.88 235	99.20 146	99.87 196	99.59 211

CANet		99.11 253	99.05 242	99.28 311	98.83 445	98.56 341	98.71 348	99.41 336	99.25 238	99.23 345	99.22 395	97.66 310	99.94 98	99.19 148	99.97 73	99.33 331

EI-MVSNet-UG-set		99.48 130	99.50 122	99.42 262	99.57 266	98.65 333	99.24 190	99.46 324	99.68 129	99.80 123	99.66 225	98.99 148	99.89 220	99.19 148	99.90 159	99.72 97

xiu_mvs_v1_base_debu		99.23 210	99.34 166	98.91 371	99.59 250	98.23 365	98.47 381	99.66 213	99.61 159	99.68 195	98.94 434	99.39 70	99.97 44	99.18 150	99.55 352	98.51 456

xiu_mvs_v1_base		99.23 210	99.34 166	98.91 371	99.59 250	98.23 365	98.47 381	99.66 213	99.61 159	99.68 195	98.94 434	99.39 70	99.97 44	99.18 150	99.55 352	98.51 456

xiu_mvs_v1_base_debi		99.23 210	99.34 166	98.91 371	99.59 250	98.23 365	98.47 381	99.66 213	99.61 159	99.68 195	98.94 434	99.39 70	99.97 44	99.18 150	99.55 352	98.51 456

VPNet		99.46 142	99.37 155	99.71 127	99.82 94	99.59 157	99.48 109	99.70 192	99.81 92	99.69 190	99.58 291	97.66 310	99.86 269	99.17 153	99.44 373	99.67 133

UniMVSNet_NR-MVSNet		99.37 176	99.25 194	99.72 121	99.47 320	99.56 166	98.97 299	99.61 244	99.43 206	99.67 202	99.28 381	97.85 294	99.95 81	99.17 153	99.81 242	99.65 156

DU-MVS		99.33 190	99.21 199	99.71 127	99.43 332	99.56 166	98.83 327	99.53 299	99.38 216	99.67 202	99.36 363	97.67 306	99.95 81	99.17 153	99.81 242	99.63 174

usedtu_dtu_shiyan2		99.44 150	99.33 171	99.78 75	99.86 59	99.76 71	99.54 90	99.79 131	99.66 141	99.66 208	99.79 119	96.76 343	99.96 69	99.15 156	99.72 292	99.62 186

EI-MVSNet-Vis-set		99.47 140	99.49 126	99.42 262	99.57 266	98.66 330	99.24 190	99.46 324	99.67 137	99.79 129	99.65 234	98.97 154	99.89 220	99.15 156	99.89 173	99.71 102

EI-MVSNet		99.38 172	99.44 140	99.21 326	99.58 256	98.09 379	99.26 183	99.46 324	99.62 154	99.75 158	99.67 220	98.54 219	99.85 288	99.15 156	99.92 145	99.68 124

VNet		99.18 233	99.06 237	99.56 209	99.24 386	99.36 226	99.33 154	99.31 368	99.67 137	99.47 285	99.57 298	96.48 352	99.84 304	99.15 156	99.30 392	99.47 277

EG-PatchMatch MVS		99.57 101	99.56 108	99.62 181	99.77 150	99.33 232	99.26 183	99.76 156	99.32 225	99.80 123	99.78 132	99.29 89	99.87 250	99.15 156	99.91 157	99.66 147

PVSNet_Blended_VisFu		99.40 165	99.38 152	99.44 256	99.90 37	98.66 330	98.94 308	99.91 52	97.97 390	99.79 129	99.73 167	99.05 139	99.97 44	99.15 156	99.99 16	99.68 124

IterMVS-LS		99.41 163	99.47 129	99.25 322	99.81 106	98.09 379	98.85 322	99.76 156	99.62 154	99.83 108	99.64 236	98.54 219	99.97 44	99.15 156	99.99 16	99.68 124
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 114	99.47 129	99.76 86	99.58 256	99.64 133	99.30 165	99.63 234	99.61 159	99.71 183	99.56 302	98.76 184	99.96 69	99.14 163	99.92 145	99.68 124

MVSTER		98.47 344	98.22 350	99.24 324	99.06 419	98.35 362	99.08 257	99.46 324	99.27 234	99.75 158	99.66 225	88.61 453	99.85 288	99.14 163	99.92 145	99.52 256

E5new		99.68 65	99.67 65	99.70 132	99.87 54	99.62 141	99.41 122	99.84 89	99.68 129	99.77 145	99.81 98	99.59 45	99.78 369	99.13 165	99.96 87	99.70 105

E6new		99.68 65	99.67 65	99.70 132	99.86 59	99.62 141	99.41 122	99.84 89	99.68 129	99.77 145	99.81 98	99.59 45	99.78 369	99.13 165	99.96 87	99.70 105

E6		99.68 65	99.67 65	99.70 132	99.86 59	99.62 141	99.41 122	99.84 89	99.68 129	99.77 145	99.81 98	99.59 45	99.78 369	99.13 165	99.96 87	99.70 105

E5		99.68 65	99.67 65	99.70 132	99.87 54	99.62 141	99.41 122	99.84 89	99.68 129	99.77 145	99.81 98	99.59 45	99.78 369	99.13 165	99.96 87	99.70 105

diffmvs_AUTHOR		99.48 130	99.48 127	99.47 245	99.80 115	98.89 309	98.71 348	99.82 104	99.79 100	99.66 208	99.63 251	98.87 170	99.88 235	99.13 165	99.95 111	99.62 186

Anonymous20231206		99.35 182	99.31 174	99.47 245	99.74 178	99.06 289	99.28 174	99.74 167	99.23 242	99.72 178	99.53 314	97.63 312	99.88 235	99.11 170	99.84 214	99.48 273

Syy-MVS		98.17 369	97.85 381	99.15 334	98.50 468	98.79 319	98.60 357	99.21 391	97.89 399	96.76 476	96.37 499	95.47 378	99.57 462	99.10 171	98.73 438	99.09 391

ttmdpeth		99.48 130	99.55 110	99.29 308	99.76 154	98.16 373	99.33 154	99.95 36	99.79 100	99.36 315	99.89 41	99.13 116	99.77 382	99.09 172	99.64 324	99.93 20

MVS_Test		99.28 197	99.31 174	99.19 329	99.35 353	98.79 319	99.36 144	99.49 317	99.17 255	99.21 350	99.67 220	98.78 181	99.66 441	99.09 172	99.66 320	99.10 386

FE-MVSNET3		98.87 300	98.71 302	99.35 289	99.59 250	98.88 310	97.17 471	99.64 231	98.94 285	99.27 338	99.22 395	95.57 375	99.83 323	99.08 174	99.92 145	99.35 326

testgi		99.29 196	99.26 192	99.37 282	99.75 170	98.81 315	98.84 324	99.89 61	98.38 357	99.75 158	99.04 418	99.36 79	99.86 269	99.08 174	99.25 400	99.45 284

1112_ss		99.05 265	98.84 290	99.67 144	99.66 229	99.29 238	98.52 375	99.82 104	97.65 412	99.43 295	99.16 402	96.42 355	99.91 179	99.07 176	99.84 214	99.80 65

CANet_DTU		98.91 293	98.85 288	99.09 343	98.79 451	98.13 374	98.18 402	99.31 368	99.48 186	98.86 390	99.51 320	96.56 348	99.95 81	99.05 177	99.95 111	99.19 366

blended_shiyan8		97.82 382	97.45 395	98.92 366	98.06 482	97.45 413	97.73 443	99.35 355	97.96 393	98.35 430	97.34 482	92.76 412	99.84 304	99.04 178	96.49 484	99.47 277

blended_shiyan6		97.82 382	97.46 393	98.92 366	98.08 481	97.46 411	97.73 443	99.34 358	97.96 393	98.33 431	97.35 481	92.78 410	99.84 304	99.04 178	96.53 479	99.46 282

Baseline_NR-MVSNet		99.49 128	99.37 155	99.82 46	99.91 31	99.84 27	98.83 327	99.86 76	99.68 129	99.65 212	99.88 50	97.67 306	99.87 250	99.03 180	99.86 204	99.76 84

FMVSNet2		99.35 182	99.28 187	99.55 216	99.49 309	99.35 229	99.45 117	99.57 272	99.44 199	99.70 187	99.74 162	97.21 327	99.87 250	99.03 180	99.94 127	99.44 298

FE-blended-shiyan7		97.53 398	97.14 406	98.72 394	97.71 488	96.86 431	97.00 476	99.34 358	97.73 408	98.18 438	96.82 492	91.92 419	99.84 304	99.02 182	96.53 479	99.45 284

Test_1112_low_res		98.95 290	98.73 300	99.63 172	99.68 220	99.15 273	98.09 414	99.80 122	97.14 438	99.46 289	99.40 349	96.11 366	99.89 220	99.01 183	99.84 214	99.84 52

VDD-MVS		99.20 226	99.11 219	99.44 256	99.43 332	98.98 294	99.50 102	98.32 448	99.80 96	99.56 255	99.69 204	96.99 337	99.85 288	98.99 184	99.73 286	99.50 264

DeepC-MVS	98.90 4	99.62 92	99.61 88	99.67 144	99.72 187	99.44 198	99.24 190	99.71 183	99.27 234	99.93 53	99.90 36	99.70 31	99.93 119	98.99 184	99.99 16	99.64 168
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
pmmvs-eth3d		99.48 130	99.47 129	99.51 232	99.77 150	99.41 212	98.81 332	99.66 213	99.42 210	99.75 158	99.66 225	99.20 103	99.76 386	98.98 186	99.99 16	99.36 323

EPNet_dtu		97.62 393	97.79 384	97.11 456	96.67 493	92.31 479	98.51 376	98.04 455	99.24 240	95.77 485	99.47 334	93.78 397	99.66 441	98.98 186	99.62 329	99.37 320
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 187	99.32 172	99.39 276	99.67 227	98.77 321	98.57 366	99.81 117	99.61 159	99.48 283	99.41 345	98.47 231	99.86 269	98.97 188	99.90 159	99.53 245
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NR-MVSNet		99.40 165	99.31 174	99.68 140	99.43 332	99.55 170	99.73 30	99.50 313	99.46 194	99.88 83	99.36 363	97.54 313	99.87 250	98.97 188	99.87 196	99.63 174

TestfortrainingZip a		99.61 96	99.53 117	99.85 32	99.76 154	99.84 27	99.38 132	99.78 142	99.58 169	99.81 116	99.66 225	99.02 143	99.90 198	98.96 190	99.79 254	99.81 64

viewdifsd2359ckpt07		99.51 121	99.50 122	99.52 228	99.80 115	99.19 265	98.92 312	99.88 66	99.72 113	99.64 215	99.62 260	99.06 137	99.81 355	98.96 190	99.94 127	99.56 225

GBi-Net		99.42 157	99.31 174	99.73 113	99.49 309	99.77 64	99.68 49	99.70 192	99.44 199	99.62 230	99.83 84	97.21 327	99.90 198	98.96 190	99.90 159	99.53 245

FMVSNet5		97.80 385	97.25 402	99.42 262	98.83 445	98.97 297	99.38 132	99.80 122	98.87 297	99.25 341	99.69 204	80.60 476	99.91 179	98.96 190	99.90 159	99.38 317

test1		99.42 157	99.31 174	99.73 113	99.49 309	99.77 64	99.68 49	99.70 192	99.44 199	99.62 230	99.83 84	97.21 327	99.90 198	98.96 190	99.90 159	99.53 245

FMVSNet3		98.80 308	98.63 309	99.32 299	99.13 405	98.72 324	99.10 249	99.48 318	99.23 242	99.62 230	99.64 236	92.57 413	99.86 269	98.96 190	99.90 159	99.39 315

UnsupCasMVSNet_eth		98.83 304	98.57 316	99.59 194	99.68 220	99.45 196	98.99 294	99.67 208	99.48 186	99.55 260	99.36 363	94.92 382	99.86 269	98.95 196	96.57 478	99.45 284

CHOSEN 280x420		98.41 349	98.41 332	98.40 411	99.34 362	95.89 452	96.94 478	99.44 330	98.80 309	99.25 341	99.52 318	93.51 401	99.98 27	98.94 197	99.98 50	99.32 335

E4		99.61 96	99.59 94	99.66 151	99.84 77	99.53 173	99.08 257	99.84 89	99.65 145	99.74 168	99.80 108	99.45 62	99.77 382	98.93 198	99.95 111	99.69 117

TDRefinement		99.72 54	99.70 58	99.77 79	99.90 37	99.85 22	99.86 6	99.92 43	99.69 127	99.78 133	99.92 27	99.37 76	99.88 235	98.93 198	99.95 111	99.60 204

viewmacassd2359aftdt		99.63 85	99.61 88	99.68 140	99.84 77	99.61 151	99.14 229	99.87 70	99.71 118	99.75 158	99.77 142	99.54 54	99.72 403	98.91 200	99.96 87	99.70 105

alignmvs		98.28 359	97.96 370	99.25 322	99.12 407	98.93 304	99.03 272	98.42 441	99.64 149	98.72 405	97.85 473	90.86 437	99.62 453	98.88 201	99.13 406	99.19 366

testing3-2		96.51 425	96.43 420	96.74 460	99.36 349	91.38 487	99.10 249	97.87 461	99.48 186	98.57 419	98.71 449	76.65 487	99.66 441	98.87 202	99.26 399	99.18 368

MGCFI-Net		99.02 271	99.01 255	99.06 350	99.11 412	98.60 338	99.63 64	99.67 208	99.63 151	98.58 417	97.65 476	99.07 130	99.57 462	98.85 203	98.92 422	99.03 408

sss		98.90 295	98.77 299	99.27 316	99.48 314	98.44 353	98.72 346	99.32 364	97.94 396	99.37 314	99.35 368	96.31 361	99.91 179	98.85 203	99.63 327	99.47 277

xiu_mvs_v2_base		99.02 271	99.11 219	98.77 391	99.37 346	98.09 379	98.13 409	99.51 309	99.47 191	99.42 298	98.54 458	99.38 74	99.97 44	98.83 205	99.33 388	98.24 468

PS-MVSNAJ		99.00 280	99.08 231	98.76 392	99.37 346	98.10 378	98.00 425	99.51 309	99.47 191	99.41 304	98.50 460	99.28 91	99.97 44	98.83 205	99.34 387	98.20 472

E2		99.54 114	99.51 120	99.62 181	99.78 137	99.47 184	99.01 281	99.82 104	99.55 172	99.69 190	99.77 142	99.26 95	99.76 386	98.82 207	99.93 139	99.62 186

E3		99.54 114	99.51 120	99.62 181	99.78 137	99.47 184	99.01 281	99.82 104	99.55 172	99.69 190	99.77 142	99.25 99	99.76 386	98.82 207	99.93 139	99.62 186

D2MVS		99.22 219	99.19 202	99.29 308	99.69 212	98.74 323	98.81 332	99.41 336	98.55 338	99.68 195	99.69 204	98.13 272	99.87 250	98.82 207	99.98 50	99.24 350

PatchT		98.45 346	98.32 342	98.83 385	98.94 433	98.29 363	99.24 190	98.82 418	99.84 76	99.08 367	99.76 149	91.37 426	99.94 98	98.82 207	99.00 417	98.26 467

testf1		99.63 85	99.60 92	99.72 121	99.94 18	99.95 2	99.47 112	99.89 61	99.43 206	99.88 83	99.80 108	99.26 95	99.90 198	98.81 211	99.88 183	99.32 335

APD_test2		99.63 85	99.60 92	99.72 121	99.94 18	99.95 2	99.47 112	99.89 61	99.43 206	99.88 83	99.80 108	99.26 95	99.90 198	98.81 211	99.88 183	99.32 335

usedtu_blend_shiyan5		97.97 379	97.65 391	98.92 366	97.71 488	97.49 408	99.53 92	99.81 117	99.52 180	98.18 438	96.82 492	91.92 419	99.83 323	98.79 213	96.53 479	99.45 284

blend_shiyan4		95.04 453	93.76 457	98.88 380	97.92 484	97.49 408	97.72 445	99.34 358	97.93 397	97.65 465	97.11 486	77.69 485	99.83 323	98.79 213	79.72 492	99.33 331

sasdasda		99.02 271	99.00 259	99.09 343	99.10 414	98.70 325	99.61 73	99.66 213	99.63 151	98.64 411	97.65 476	99.04 140	99.54 466	98.79 213	98.92 422	99.04 406

Effi-MVS+		99.06 262	98.97 270	99.34 291	99.31 369	98.98 294	98.31 394	99.91 52	98.81 307	98.79 399	98.94 434	99.14 114	99.84 304	98.79 213	98.74 435	99.20 363

canonicalmvs		99.02 271	99.00 259	99.09 343	99.10 414	98.70 325	99.61 73	99.66 213	99.63 151	98.64 411	97.65 476	99.04 140	99.54 466	98.79 213	98.92 422	99.04 406

VDDNet		98.97 284	98.82 293	99.42 262	99.71 191	98.81 315	99.62 67	98.68 425	99.81 92	99.38 312	99.80 108	94.25 391	99.85 288	98.79 213	99.32 390	99.59 211

CR-MVSNet		98.35 356	98.20 352	98.83 385	99.05 420	98.12 375	99.30 165	99.67 208	97.39 426	99.16 356	99.79 119	91.87 423	99.91 179	98.78 219	98.77 431	98.44 461

test_method		91.72 455	92.32 458	89.91 474	93.49 497	70.18 500	90.28 489	99.56 277	61.71 492	95.39 487	99.52 318	93.90 393	99.94 98	98.76 220	98.27 455	99.62 186

RPMNet		98.60 327	98.53 322	98.83 385	99.05 420	98.12 375	99.30 165	99.62 237	99.86 66	99.16 356	99.74 162	92.53 415	99.92 150	98.75 221	98.77 431	98.44 461

mamba_0408		99.54 114	99.55 110	99.54 222	99.71 191	99.24 252	99.27 178	99.79 131	99.72 113	99.78 133	99.64 236	99.36 79	99.93 119	98.74 222	99.90 159	99.45 284

SSM_04072		99.55 110	99.55 110	99.55 216	99.71 191	99.24 252	99.27 178	99.79 131	99.72 113	99.78 133	99.64 236	99.36 79	99.97 44	98.74 222	99.90 159	99.45 284

SSM_0407		99.56 105	99.56 108	99.54 222	99.71 191	99.24 252	99.15 225	99.84 89	99.80 96	99.78 133	99.70 195	99.44 64	99.93 119	98.74 222	99.90 159	99.45 284

SSM_0404		99.57 101	99.58 98	99.54 222	99.76 154	99.28 240	99.19 207	99.84 89	99.80 96	99.78 133	99.70 195	99.44 64	99.93 119	98.74 222	99.95 111	99.41 309

pmmvs4		99.13 246	99.06 237	99.36 287	99.57 266	99.10 284	98.01 423	99.25 381	98.78 312	99.58 244	99.44 341	98.24 259	99.76 386	98.74 222	99.93 139	99.22 356

viewmanbaseed2359cas		99.50 123	99.47 129	99.61 187	99.73 182	99.52 177	99.03 272	99.83 98	99.49 183	99.65 212	99.64 236	99.18 105	99.71 408	98.73 227	99.92 145	99.58 216

tttt0517		97.62 393	97.20 403	98.90 377	99.76 154	97.40 416	99.48 109	94.36 484	99.06 272	99.70 187	99.49 327	84.55 469	99.94 98	98.73 227	99.65 322	99.36 323

viewcassd2359sk11		99.48 130	99.45 136	99.58 197	99.73 182	99.42 205	98.96 303	99.80 122	99.44 199	99.63 220	99.74 162	99.09 123	99.76 386	98.72 229	99.91 157	99.57 222

EPP-MVSNet		99.17 238	99.00 259	99.66 151	99.80 115	99.43 202	99.70 38	99.24 384	99.48 186	99.56 255	99.77 142	94.89 383	99.93 119	98.72 229	99.89 173	99.63 174

FE-MVSNET		99.45 146	99.36 160	99.71 127	99.84 77	99.64 133	99.16 222	99.91 52	98.65 327	99.73 173	99.73 167	98.54 219	99.82 339	98.71 231	99.96 87	99.67 133

Anonymous20240529		99.42 157	99.34 166	99.65 158	99.53 289	99.60 155	99.63 64	99.39 346	99.47 191	99.76 153	99.78 132	98.13 272	99.86 269	98.70 232	99.68 311	99.49 269

ACMH	98.42 6	99.59 100	99.54 113	99.72 121	99.86 59	99.62 141	99.56 87	99.79 131	98.77 314	99.80 123	99.85 69	99.64 35	99.85 288	98.70 232	99.89 173	99.70 105
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 190	99.28 187	99.47 245	99.57 266	99.39 216	99.78 17	99.43 333	98.87 297	99.57 247	99.82 91	98.06 278	99.87 250	98.69 234	99.73 286	99.15 375

LFMVS		98.46 345	98.19 355	99.26 319	99.24 386	98.52 349	99.62 67	96.94 473	99.87 63	99.31 331	99.58 291	91.04 431	99.81 355	98.68 235	99.42 377	99.45 284

WR-MVS		99.11 253	98.93 275	99.66 151	99.30 373	99.42 205	98.42 387	99.37 351	99.04 273	99.57 247	99.20 400	96.89 339	99.86 269	98.66 236	99.87 196	99.70 105

mvsmamba		99.08 258	98.95 273	99.45 252	99.36 349	99.18 270	99.39 129	98.81 419	99.37 217	99.35 317	99.70 195	96.36 360	99.94 98	98.66 236	99.59 343	99.22 356

viewdifsd2359ckpt13		99.42 157	99.37 155	99.57 205	99.72 187	99.46 190	99.01 281	99.80 122	99.20 247	99.51 277	99.60 278	98.92 161	99.70 412	98.65 238	99.90 159	99.55 229

RRT-MVS		99.08 258	99.00 259	99.33 294	99.27 380	98.65 333	99.62 67	99.93 39	99.66 141	99.67 202	99.82 91	95.27 380	99.93 119	98.64 239	99.09 410	99.41 309

E3new		99.42 157	99.37 155	99.56 209	99.68 220	99.38 218	98.93 311	99.79 131	99.30 229	99.55 260	99.69 204	98.88 168	99.76 386	98.63 240	99.89 173	99.53 245

Anonymous202405211		98.75 312	98.46 326	99.63 172	99.34 362	99.66 121	99.47 112	97.65 464	99.28 233	99.56 255	99.50 323	93.15 405	99.84 304	98.62 241	99.58 345	99.40 312

lecture		99.56 105	99.48 127	99.81 54	99.78 137	99.86 19	99.50 102	99.70 192	99.59 167	99.75 158	99.71 185	98.94 157	99.92 150	98.59 242	99.76 269	99.66 147

EPNet		98.13 370	97.77 385	99.18 331	94.57 496	97.99 385	99.24 190	97.96 457	99.74 108	97.29 469	99.62 260	93.13 406	99.97 44	98.59 242	99.83 222	99.58 216
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 265	99.09 229	98.91 371	99.21 391	98.36 361	98.82 331	99.47 321	98.85 300	98.90 385	99.56 302	98.78 181	99.09 482	98.57 244	99.68 311	99.26 347

Patchmatch-RL test		98.60 327	98.36 337	99.33 294	99.77 150	99.07 287	98.27 396	99.87 70	98.91 292	99.74 168	99.72 175	90.57 442	99.79 366	98.55 245	99.85 209	99.11 384

pmmvs3		98.08 373	97.80 382	98.91 371	99.41 339	97.69 403	97.87 438	99.66 213	95.87 457	99.50 280	99.51 320	90.35 444	99.97 44	98.55 245	99.47 370	99.08 397

ETV-MVS		99.18 233	99.18 203	99.16 332	99.34 362	99.28 240	99.12 241	99.79 131	99.48 186	98.93 379	98.55 457	99.40 69	99.93 119	98.51 247	99.52 362	98.28 466

viewdifsd2359ckpt09		99.24 208	99.16 205	99.49 238	99.70 206	99.22 258	98.88 316	99.81 117	98.70 322	99.38 312	99.37 358	98.22 264	99.76 386	98.48 248	99.88 183	99.51 258

jason		99.16 239	99.11 219	99.32 299	99.75 170	98.44 353	98.26 398	99.39 346	98.70 322	99.74 168	99.30 377	98.54 219	99.97 44	98.48 248	99.82 232	99.55 229
jason: jason.
APDe-MVS		99.48 130	99.36 160	99.85 32	99.55 280	99.81 48	99.50 102	99.69 200	98.99 277	99.75 158	99.71 185	98.79 179	99.93 119	98.46 250	99.85 209	99.80 65
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
icg_test_0407_2		99.30 194	99.29 184	99.31 303	99.71 191	98.55 343	98.17 404	99.71 183	99.41 211	99.73 173	99.60 278	99.17 107	99.92 150	98.45 251	99.70 298	99.45 284

IMVS_0407		99.38 172	99.42 144	99.28 311	99.71 191	98.55 343	99.27 178	99.71 183	99.41 211	99.73 173	99.60 278	99.17 107	99.83 323	98.45 251	99.70 298	99.45 284

IMVS_0404		99.23 210	99.20 200	99.32 299	99.71 191	98.55 343	98.57 366	99.71 183	99.41 211	99.52 270	99.60 278	98.12 274	99.95 81	98.45 251	99.70 298	99.45 284

IMVS_0403		99.37 176	99.39 149	99.28 311	99.71 191	98.55 343	99.19 207	99.71 183	99.41 211	99.67 202	99.60 278	99.12 119	99.84 304	98.45 251	99.70 298	99.45 284

CL-MVSNet_self_test		98.71 318	98.56 320	99.15 334	99.22 389	98.66 330	97.14 472	99.51 309	98.09 383	99.54 263	99.27 383	96.87 340	99.74 398	98.43 255	98.96 419	99.03 408

our_test_3		98.85 303	99.09 229	98.13 424	99.66 229	94.90 466	97.72 445	99.58 270	99.07 270	99.64 215	99.62 260	98.19 268	99.93 119	98.41 256	99.95 111	99.55 229

Gipuma		99.57 101	99.59 94	99.49 238	99.98 3	99.71 101	99.72 33	99.84 89	99.81 92	99.94 48	99.78 132	98.91 164	99.71 408	98.41 256	99.95 111	99.05 404
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 405	96.91 414	98.74 393	97.72 487	97.57 405	97.60 452	97.36 470	98.00 386	99.21 350	98.02 469	90.04 447	99.79 366	98.37 258	95.89 487	98.86 431

PM-MVS		99.36 180	99.29 184	99.58 197	99.83 85	99.66 121	98.95 306	99.86 76	98.85 300	99.81 116	99.73 167	98.40 244	99.92 150	98.36 259	99.83 222	99.17 371

baseline1		97.73 388	97.33 399	98.96 359	99.30 373	97.73 401	99.40 127	98.42 441	99.33 224	99.46 289	99.21 398	91.18 429	99.82 339	98.35 260	91.26 490	99.32 335

MVS-HIRNet		97.86 380	98.22 350	96.76 458	99.28 378	91.53 485	98.38 389	92.60 490	99.13 263	99.31 331	99.96 15	97.18 331	99.68 431	98.34 261	99.83 222	99.07 402

GA-MVS		97.99 378	97.68 388	98.93 365	99.52 296	98.04 383	97.19 470	99.05 408	98.32 370	98.81 395	98.97 430	89.89 449	99.41 477	98.33 262	99.05 413	99.34 330

Fast-Effi-MVS+		99.02 271	98.87 286	99.46 249	99.38 344	99.50 179	99.04 269	99.79 131	97.17 436	98.62 413	98.74 448	99.34 83	99.95 81	98.32 263	99.41 378	98.92 424

MDA-MVSNet_test_wron		98.95 290	98.99 266	98.85 381	99.64 235	97.16 422	98.23 400	99.33 362	98.93 289	99.56 255	99.66 225	97.39 320	99.83 323	98.29 264	99.88 183	99.55 229

N_pmnet		98.73 315	98.53 322	99.35 289	99.72 187	98.67 327	98.34 391	94.65 483	98.35 364	99.79 129	99.68 216	98.03 279	99.93 119	98.28 265	99.92 145	99.44 298

ET-MVSNet_ETH3D		96.78 417	96.07 427	98.91 371	99.26 383	97.92 392	97.70 448	96.05 478	97.96 393	92.37 491	98.43 461	87.06 457	99.90 198	98.27 266	97.56 472	98.91 425

thisisatest0530		97.45 400	96.95 411	98.94 362	99.68 220	97.73 401	99.09 254	94.19 486	98.61 334	99.56 255	99.30 377	84.30 471	99.93 119	98.27 266	99.54 357	99.16 373

YYNet1		98.95 290	98.99 266	98.84 383	99.64 235	97.14 424	98.22 401	99.32 364	98.92 291	99.59 242	99.66 225	97.40 318	99.83 323	98.27 266	99.90 159	99.55 229

reproduce_model		99.50 123	99.40 148	99.83 41	99.60 244	99.83 35	99.12 241	99.68 203	99.49 183	99.80 123	99.79 119	99.01 145	99.93 119	98.24 269	99.82 232	99.73 93

ACMM	98.09 11	99.46 142	99.38 152	99.72 121	99.80 115	99.69 113	99.13 236	99.65 223	98.99 277	99.64 215	99.72 175	99.39 70	99.86 269	98.23 270	99.81 242	99.60 204
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 287	98.87 286	99.24 324	99.57 266	98.40 356	98.12 410	99.18 396	98.28 372	99.63 220	99.13 404	98.02 280	99.97 44	98.22 271	99.69 306	99.35 326

3Dnovator	99.15 2	99.43 154	99.36 160	99.65 158	99.39 341	99.42 205	99.70 38	99.56 277	99.23 242	99.35 317	99.80 108	99.17 107	99.95 81	98.21 272	99.84 214	99.59 211

Fast-Effi-MVS+-dtu		99.20 226	99.12 216	99.43 260	99.25 384	99.69 113	99.05 264	99.82 104	99.50 181	98.97 375	99.05 416	98.98 152	99.98 27	98.20 273	99.24 402	98.62 446

MS-PatchMatch		99.00 280	98.97 270	99.09 343	99.11 412	98.19 369	98.76 341	99.33 362	98.49 347	99.44 291	99.58 291	98.21 265	99.69 419	98.20 273	99.62 329	99.39 315

TSAR-MVS + GP.		99.12 249	99.04 248	99.38 279	99.34 362	99.16 271	98.15 406	99.29 372	98.18 379	99.63 220	99.62 260	99.18 105	99.68 431	98.20 273	99.74 280	99.30 341

DP-MVS		99.48 130	99.39 149	99.74 102	99.57 266	99.62 141	99.29 172	99.61 244	99.87 63	99.74 168	99.76 149	98.69 194	99.87 250	98.20 273	99.80 249	99.75 87

MVP-Stereo		99.16 239	99.08 231	99.43 260	99.48 314	99.07 287	99.08 257	99.55 283	98.63 330	99.31 331	99.68 216	98.19 268	99.78 369	98.18 277	99.58 345	99.45 284
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 154	99.30 179	99.80 64	99.83 85	99.81 48	99.52 94	99.70 192	98.35 364	99.51 277	99.50 323	99.31 87	99.88 235	98.18 277	99.84 214	99.69 117

MDA-MVSNet-bldmvs		99.06 262	99.05 242	99.07 348	99.80 115	97.83 396	98.89 315	99.72 180	99.29 230	99.63 220	99.70 195	96.47 353	99.89 220	98.17 279	99.82 232	99.50 264

JIA-IIPM		98.06 374	97.92 377	98.50 406	98.59 464	97.02 426	98.80 335	98.51 436	99.88 61	97.89 453	99.87 56	91.89 422	99.90 198	98.16 280	97.68 471	98.59 449

EIA-MVS		99.12 249	99.01 255	99.45 252	99.36 349	99.62 141	99.34 148	99.79 131	98.41 353	98.84 392	98.89 438	98.75 186	99.84 304	98.15 281	99.51 363	98.89 428

miper_lstm_enhance		98.65 323	98.60 310	98.82 388	99.20 394	97.33 418	97.78 441	99.66 213	99.01 276	99.59 242	99.50 323	94.62 388	99.85 288	98.12 282	99.90 159	99.26 347

reproduce-ours		99.46 142	99.35 164	99.82 46	99.56 277	99.83 35	99.05 264	99.65 223	99.45 197	99.78 133	99.78 132	98.93 158	99.93 119	98.11 283	99.81 242	99.70 105

our_new_method		99.46 142	99.35 164	99.82 46	99.56 277	99.83 35	99.05 264	99.65 223	99.45 197	99.78 133	99.78 132	98.93 158	99.93 119	98.11 283	99.81 242	99.70 105

Effi-MVS+-dtu		99.07 261	98.92 279	99.52 228	98.89 438	99.78 58	99.15 225	99.66 213	99.34 221	98.92 382	99.24 393	97.69 304	99.98 27	98.11 283	99.28 395	98.81 435

tpm		97.15 409	96.95 411	97.75 438	98.91 434	94.24 469	99.32 157	97.96 457	97.71 410	98.29 432	99.32 372	86.72 463	99.92 150	98.10 286	96.24 485	99.09 391

DeepPCF-MVS	98.42 6	99.18 233	99.02 251	99.67 144	99.22 389	99.75 80	97.25 468	99.47 321	98.72 319	99.66 208	99.70 195	99.29 89	99.63 452	98.07 287	99.81 242	99.62 186

ppachtmachnet_test		98.89 298	99.12 216	98.20 422	99.66 229	95.24 462	97.63 450	99.68 203	99.08 268	99.78 133	99.62 260	98.65 202	99.88 235	98.02 288	99.96 87	99.48 273

tpmrst		97.73 388	98.07 363	96.73 461	98.71 460	92.00 480	99.10 249	98.86 415	98.52 343	98.92 382	99.54 312	91.90 421	99.82 339	98.02 288	99.03 415	98.37 463

CSCG		99.37 176	99.29 184	99.60 191	99.71 191	99.46 190	99.43 121	99.85 82	98.79 310	99.41 304	99.60 278	98.92 161	99.92 150	98.02 288	99.92 145	99.43 304

eth_miper_zixun_eth		98.68 321	98.71 302	98.60 401	99.10 414	96.84 432	97.52 458	99.54 289	98.94 285	99.58 244	99.48 330	96.25 364	99.76 386	98.01 291	99.93 139	99.21 359

Patchmtry		98.78 309	98.54 321	99.49 238	98.89 438	99.19 265	99.32 157	99.67 208	99.65 145	99.72 178	99.79 119	91.87 423	99.95 81	98.00 292	99.97 73	99.33 331

PVSNet_BlendedMVS		99.03 269	99.01 255	99.09 343	99.54 282	97.99 385	98.58 362	99.82 104	97.62 413	99.34 321	99.71 185	98.52 227	99.77 382	97.98 293	99.97 73	99.52 256

PVSNet_Blended		98.70 319	98.59 312	99.02 353	99.54 282	97.99 385	97.58 453	99.82 104	95.70 461	99.34 321	98.98 428	98.52 227	99.77 382	97.98 293	99.83 222	99.30 341

cl____		98.54 335	98.41 332	98.92 366	99.03 424	97.80 399	97.46 460	99.59 261	98.90 293	99.60 239	99.46 337	93.85 395	99.78 369	97.97 295	99.89 173	99.17 371

DIV-MVS_self_test		98.54 335	98.42 331	98.92 366	99.03 424	97.80 399	97.46 460	99.59 261	98.90 293	99.60 239	99.46 337	93.87 394	99.78 369	97.97 295	99.89 173	99.18 368

AUN-MVS		97.82 382	97.38 398	99.14 337	99.27 380	98.53 347	98.72 346	99.02 410	98.10 381	97.18 472	99.03 422	89.26 451	99.85 288	97.94 297	97.91 467	99.03 408

FA-MVS(test-final)		98.52 337	98.32 342	99.10 342	99.48 314	98.67 327	99.77 19	98.60 432	97.35 428	99.63 220	99.80 108	93.07 407	99.84 304	97.92 298	99.30 392	98.78 438

ambc				99.20 328	99.35 353	98.53 347	99.17 216	99.46 324		99.67 202	99.80 108	98.46 234	99.70 412	97.92 298	99.70 298	99.38 317

USDC		98.96 287	98.93 275	99.05 351	99.54 282	97.99 385	97.07 475	99.80 122	98.21 376	99.75 158	99.77 142	98.43 237	99.64 450	97.90 300	99.88 183	99.51 258

OPM-MVS		99.26 203	99.13 212	99.63 172	99.70 206	99.61 151	98.58 362	99.48 318	98.50 345	99.52 270	99.63 251	99.14 114	99.76 386	97.89 301	99.77 267	99.51 258
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 192	99.17 204	99.77 79	99.69 212	99.80 52	99.14 229	99.31 368	99.16 257	99.62 230	99.61 270	98.35 248	99.91 179	97.88 302	99.72 292	99.61 200
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.83 41	99.70 206	99.79 55	99.14 229	99.61 244					99.92 150	97.88 302	99.72 292	99.77 79

c3_l		98.72 316	98.71 302	98.72 394	99.12 407	97.22 421	97.68 449	99.56 277	98.90 293	99.54 263	99.48 330	96.37 359	99.73 401	97.88 302	99.88 183	99.21 359

3Dnovator+	98.92 3	99.35 182	99.24 196	99.67 144	99.35 353	99.47 184	99.62 67	99.50 313	99.44 199	99.12 363	99.78 132	98.77 183	99.94 98	97.87 305	99.72 292	99.62 186

miper_ehance_all_eth		98.59 330	98.59 312	98.59 402	98.98 430	97.07 425	97.49 459	99.52 304	98.50 345	99.52 270	99.37 358	96.41 357	99.71 408	97.86 306	99.62 329	99.00 415

WTY-MVS		98.59 330	98.37 336	99.26 319	99.43 332	98.40 356	98.74 344	99.13 403	98.10 381	99.21 350	99.24 393	94.82 385	99.90 198	97.86 306	98.77 431	99.49 269

APD_test1		99.36 180	99.28 187	99.61 187	99.89 39	99.89 10	99.32 157	99.74 167	99.18 250	99.69 190	99.75 157	98.41 240	99.84 304	97.85 308	99.70 298	99.10 386

SED-MVS		99.40 165	99.28 187	99.77 79	99.69 212	99.82 43	99.20 201	99.54 289	99.13 263	99.82 109	99.63 251	98.91 164	99.92 150	97.85 308	99.70 298	99.58 216

test_241102_TWO								99.54 289	99.13 263	99.76 153	99.63 251	98.32 253	99.92 150	97.85 308	99.69 306	99.75 87

MVS_111021_HR		99.12 249	99.02 251	99.40 273	99.50 304	99.11 277	97.92 434	99.71 183	98.76 317	99.08 367	99.47 334	99.17 107	99.54 466	97.85 308	99.76 269	99.54 239

MTAPA		99.35 182	99.20 200	99.80 64	99.81 106	99.81 48	99.33 154	99.53 299	99.27 234	99.42 298	99.63 251	98.21 265	99.95 81	97.83 312	99.79 254	99.65 156

MSC_two_6792asdad				99.74 102	99.03 424	99.53 173		99.23 385					99.92 150	97.77 313	99.69 306	99.78 75

No_MVS				99.74 102	99.03 424	99.53 173		99.23 385					99.92 150	97.77 313	99.69 306	99.78 75

TESTMET0.1,1		96.24 432	95.84 433	97.41 447	98.24 475	93.84 472	97.38 462	95.84 479	98.43 350	97.81 459	98.56 456	79.77 480	99.89 220	97.77 313	98.77 431	98.52 455

ACMH+	98.40 8	99.50 123	99.43 142	99.71 127	99.86 59	99.76 71	99.32 157	99.77 148	99.53 176	99.77 145	99.76 149	99.26 95	99.78 369	97.77 313	99.88 183	99.60 204

IU-MVS					99.69 212	99.77 64		99.22 388	97.50 420	99.69 190				97.75 317	99.70 298	99.77 79

114514_t		98.49 342	98.11 360	99.64 165	99.73 182	99.58 162	99.24 190	99.76 156	89.94 484	99.42 298	99.56 302	97.76 301	99.86 269	97.74 318	99.82 232	99.47 277

DVP-MVS++		99.38 172	99.25 194	99.77 79	99.03 424	99.77 64	99.74 27	99.61 244	99.18 250	99.76 153	99.61 270	99.00 146	99.92 150	97.72 319	99.60 339	99.62 186

test_0728_THIRD									99.18 250	99.62 230	99.61 270	98.58 210	99.91 179	97.72 319	99.80 249	99.77 79

EGC-MVSNET		89.05 457	85.52 460	99.64 165	99.89 39	99.78 58	99.56 87	99.52 304	24.19 493	49.96 494	99.83 84	99.15 111	99.92 150	97.71 321	99.85 209	99.21 359

miper_enhance_ethall		98.03 375	97.94 375	98.32 416	98.27 474	96.43 440	96.95 477	99.41 336	96.37 452	99.43 295	98.96 432	94.74 386	99.69 419	97.71 321	99.62 329	98.83 434

TSAR-MVS + MP.		99.34 187	99.24 196	99.63 172	99.82 94	99.37 222	99.26 183	99.35 355	98.77 314	99.57 247	99.70 195	99.27 94	99.88 235	97.71 321	99.75 273	99.65 156
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 396	97.28 400	98.40 411	98.37 472	96.75 433	97.24 469	99.37 351	97.31 430	99.41 304	99.22 395	87.30 455	99.37 478	97.70 324	99.62 329	99.08 397

MP-MVS-pluss		99.14 244	98.92 279	99.80 64	99.83 85	99.83 35	98.61 355	99.63 234	96.84 445	99.44 291	99.58 291	98.81 174	99.91 179	97.70 324	99.82 232	99.67 133
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 197	99.11 219	99.79 71	99.75 170	99.81 48	98.95 306	99.53 299	98.27 373	99.53 268	99.73 167	98.75 186	99.87 250	97.70 324	99.83 222	99.68 124

UnsupCasMVSNet_bld		98.55 334	98.27 348	99.40 273	99.56 277	99.37 222	97.97 430	99.68 203	97.49 421	99.08 367	99.35 368	95.41 379	99.82 339	97.70 324	98.19 459	99.01 414

MVS_111021_LR		99.13 246	99.03 250	99.42 262	99.58 256	99.32 234	97.91 436	99.73 171	98.68 324	99.31 331	99.48 330	99.09 123	99.66 441	97.70 324	99.77 267	99.29 344

IS-MVSNet		99.03 269	98.85 288	99.55 216	99.80 115	99.25 248	99.73 30	99.15 400	99.37 217	99.61 236	99.71 185	94.73 387	99.81 355	97.70 324	99.88 183	99.58 216

MED-MVS test				99.74 102	99.76 154	99.65 127	99.38 132	99.78 142	99.58 169	99.81 116	99.66 225		99.90 198	97.69 330	99.79 254	99.67 133

MED-MVS		99.45 146	99.36 160	99.74 102	99.76 154	99.65 127	99.38 132	99.78 142	99.31 227	99.81 116	99.66 225	99.02 143	99.90 198	97.69 330	99.79 254	99.67 133

ME-MVS		99.26 203	99.10 227	99.73 113	99.60 244	99.65 127	98.75 343	99.45 329	99.31 227	99.65 212	99.66 225	98.00 285	99.86 269	97.69 330	99.79 254	99.67 133

test-LLR		97.15 409	96.95 411	97.74 439	98.18 477	95.02 464	97.38 462	96.10 475	98.00 386	97.81 459	98.58 453	90.04 447	99.91 179	97.69 330	98.78 429	98.31 464

test-mter		96.23 433	95.73 436	97.74 439	98.18 477	95.02 464	97.38 462	96.10 475	97.90 398	97.81 459	98.58 453	79.12 483	99.91 179	97.69 330	98.78 429	98.31 464

MonoMVSNet		98.23 364	98.32 342	97.99 427	98.97 431	96.62 435	99.49 107	98.42 441	99.62 154	99.40 309	99.79 119	95.51 377	98.58 489	97.68 335	95.98 486	98.76 441

XVS		99.27 201	99.11 219	99.75 97	99.71 191	99.71 101	99.37 140	99.61 244	99.29 230	98.76 402	99.47 334	98.47 231	99.88 235	97.62 336	99.73 286	99.67 133

X-MVStestdata		96.09 437	94.87 450	99.75 97	99.71 191	99.71 101	99.37 140	99.61 244	99.29 230	98.76 402	61.30 502	98.47 231	99.88 235	97.62 336	99.73 286	99.67 133

SMA-MVS		99.19 229	99.00 259	99.73 113	99.46 324	99.73 91	99.13 236	99.52 304	97.40 425	99.57 247	99.64 236	98.93 158	99.83 323	97.61 338	99.79 254	99.63 174
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
CostFormer		96.71 420	96.79 419	96.46 465	98.90 435	90.71 491	99.41 122	98.68 425	94.69 474	98.14 444	99.34 371	86.32 465	99.80 363	97.60 339	98.07 465	98.88 429

PVSNet	97.47 15	98.42 348	98.44 329	98.35 413	99.46 324	96.26 444	96.70 481	99.34 358	97.68 411	99.00 374	99.13 404	97.40 318	99.72 403	97.59 340	99.68 311	99.08 397

new_pmnet		98.88 299	98.89 284	98.84 383	99.70 206	97.62 404	98.15 406	99.50 313	97.98 389	99.62 230	99.54 312	98.15 271	99.94 98	97.55 341	99.84 214	98.95 419

IB-MVS	95.41 20	95.30 452	94.46 456	97.84 435	98.76 456	95.33 460	97.33 465	96.07 477	96.02 456	95.37 488	97.41 480	76.17 488	99.96 69	97.54 342	95.44 489	98.22 469
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		99.24 208	99.11 219	99.61 187	98.38 471	99.79 55	99.57 85	99.68 203	99.61 159	99.15 358	99.71 185	98.70 193	99.91 179	97.54 342	99.68 311	99.13 383

ZNCC-MVS		99.22 219	99.04 248	99.77 79	99.76 154	99.73 91	99.28 174	99.56 277	98.19 378	99.14 360	99.29 380	98.84 173	99.92 150	97.53 344	99.80 249	99.64 168

CP-MVS		99.23 210	99.05 242	99.75 97	99.66 229	99.66 121	99.38 132	99.62 237	98.38 357	99.06 371	99.27 383	98.79 179	99.94 98	97.51 345	99.82 232	99.66 147

SD-MVS		99.01 277	99.30 179	98.15 423	99.50 304	99.40 213	98.94 308	99.61 244	99.22 246	99.75 158	99.82 91	99.54 54	95.51 493	97.48 346	99.87 196	99.54 239
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
PMMVS		98.49 342	98.29 347	99.11 340	98.96 432	98.42 355	97.54 454	99.32 364	97.53 418	98.47 425	98.15 468	97.88 291	99.82 339	97.46 347	99.24 402	99.09 391

DeepC-MVS_fast	98.47 5	99.23 210	99.12 216	99.56 209	99.28 378	99.22 258	98.99 294	99.40 343	99.08 268	99.58 244	99.64 236	98.90 167	99.83 323	97.44 348	99.75 273	99.63 174
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 205	99.08 231	99.76 86	99.73 182	99.70 109	99.31 162	99.59 261	98.36 359	99.36 315	99.37 358	98.80 178	99.91 179	97.43 349	99.75 273	99.68 124

ACMMPR		99.23 210	99.06 237	99.76 86	99.74 178	99.69 113	99.31 162	99.59 261	98.36 359	99.35 317	99.38 355	98.61 206	99.93 119	97.43 349	99.75 273	99.67 133

Vis-MVSNet (Re-imp)		98.77 310	98.58 315	99.34 291	99.78 137	98.88 310	99.61 73	99.56 277	99.11 267	99.24 344	99.56 302	93.00 409	99.78 369	97.43 349	99.89 173	99.35 326

MIMVSNet		98.43 347	98.20 352	99.11 340	99.53 289	98.38 360	99.58 82	98.61 430	98.96 281	99.33 323	99.76 149	90.92 433	99.81 355	97.38 352	99.76 269	99.15 375

WB-MVSnew		98.34 358	98.14 358	98.96 359	98.14 480	97.90 393	98.27 396	97.26 471	98.63 330	98.80 397	98.00 471	97.77 299	99.90 198	97.37 353	98.98 418	99.09 391

XVG-OURS-SEG-HR		99.16 239	98.99 266	99.66 151	99.84 77	99.64 133	98.25 399	99.73 171	98.39 356	99.63 220	99.43 342	99.70 31	99.90 198	97.34 354	98.64 442	99.44 298

COLMAP_ROB	98.06 12	99.45 146	99.37 155	99.70 132	99.83 85	99.70 109	99.38 132	99.78 142	99.53 176	99.67 202	99.78 132	99.19 104	99.86 269	97.32 355	99.87 196	99.55 229
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 271	98.81 295	99.65 158	99.58 256	99.49 180	98.58 362	99.07 405	98.40 355	99.04 372	99.25 388	98.51 229	99.80 363	97.31 356	99.51 363	99.65 156

region2R		99.23 210	99.05 242	99.77 79	99.76 154	99.70 109	99.31 162	99.59 261	98.41 353	99.32 326	99.36 363	98.73 190	99.93 119	97.29 357	99.74 280	99.67 133

APD-MVS_3200maxsize		99.31 193	99.16 205	99.74 102	99.53 289	99.75 80	99.27 178	99.61 244	99.19 249	99.57 247	99.64 236	98.76 184	99.90 198	97.29 357	99.62 329	99.56 225

TAPA-MVS	97.92 13	98.03 375	97.55 392	99.46 249	99.47 320	99.44 198	98.50 377	99.62 237	86.79 485	99.07 370	99.26 386	98.26 258	99.62 453	97.28 359	99.73 286	99.31 339
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 201	99.11 219	99.73 113	99.54 282	99.74 88	99.26 183	99.62 237	99.16 257	99.52 270	99.64 236	98.41 240	99.91 179	97.27 360	99.61 336	99.54 239

RE-MVS-def			99.13 212		99.54 282	99.74 88	99.26 183	99.62 237	99.16 257	99.52 270	99.64 236	98.57 211		97.27 360	99.61 336	99.54 239

testing11		96.05 439	95.41 442	97.97 429	98.78 453	95.27 461	98.59 360	98.23 451	98.86 299	96.56 479	96.91 490	75.20 489	99.69 419	97.26 362	98.29 454	98.93 422

test_yl		98.25 361	97.95 371	99.13 338	99.17 400	98.47 350	99.00 287	98.67 427	98.97 279	99.22 348	99.02 423	91.31 427	99.69 419	97.26 362	98.93 420	99.24 350

DCV-MVSNet		98.25 361	97.95 371	99.13 338	99.17 400	98.47 350	99.00 287	98.67 427	98.97 279	99.22 348	99.02 423	91.31 427	99.69 419	97.26 362	98.93 420	99.24 350

PHI-MVS		99.11 253	98.95 273	99.59 194	99.13 405	99.59 157	99.17 216	99.65 223	97.88 401	99.25 341	99.46 337	98.97 154	99.80 363	97.26 362	99.82 232	99.37 320

tfpnnormal		99.43 154	99.38 152	99.60 191	99.87 54	99.75 80	99.59 80	99.78 142	99.71 118	99.90 68	99.69 204	98.85 172	99.90 198	97.25 366	99.78 263	99.15 375

PatchmatchNet		97.65 392	97.80 382	97.18 454	98.82 448	92.49 478	99.17 216	98.39 444	98.12 380	98.79 399	99.58 291	90.71 439	99.89 220	97.23 367	99.41 378	99.16 373
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 283	98.80 297	99.56 209	99.25 384	99.43 202	98.54 372	99.27 376	98.58 336	98.80 397	99.43 342	98.53 224	99.70 412	97.22 368	99.59 343	99.54 239

testing3		96.48 426	95.63 438	99.01 354	99.23 388	97.81 397	98.90 314	99.10 404	98.72 319	97.84 458	97.92 472	72.44 493	99.85 288	97.21 369	99.33 388	99.35 326

HPM-MVS		99.25 205	99.07 235	99.78 75	99.81 106	99.75 80	99.61 73	99.67 208	97.72 409	99.35 317	99.25 388	99.23 100	99.92 150	97.21 369	99.82 232	99.67 133
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 229	99.00 259	99.76 86	99.76 154	99.68 116	99.38 132	99.54 289	98.34 368	99.01 373	99.50 323	98.53 224	99.93 119	97.18 371	99.78 263	99.66 147

ACMMP		99.25 205	99.08 231	99.74 102	99.79 129	99.68 116	99.50 102	99.65 223	98.07 384	99.52 270	99.69 204	98.57 211	99.92 150	97.18 371	99.79 254	99.63 174
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
myMVS_eth3d28		96.23 433	95.74 435	97.70 441	98.86 442	95.59 457	98.66 352	98.14 453	98.96 281	97.67 464	97.06 487	76.78 486	98.92 485	97.10 373	98.41 451	98.58 451

thisisatest0515		96.98 413	96.42 421	98.66 398	99.42 337	97.47 410	97.27 467	94.30 485	97.24 432	99.15 358	98.86 440	85.01 467	99.87 250	97.10 373	99.39 380	98.63 445

XVG-ACMP-BASELINE		99.23 210	99.10 227	99.63 172	99.82 94	99.58 162	98.83 327	99.72 180	98.36 359	99.60 239	99.71 185	98.92 161	99.91 179	97.08 375	99.84 214	99.40 312

MSDG		99.08 258	98.98 269	99.37 282	99.60 244	99.13 274	97.54 454	99.74 167	98.84 303	99.53 268	99.55 310	99.10 121	99.79 366	97.07 376	99.86 204	99.18 368

SteuartSystems-ACMMP		99.30 194	99.14 210	99.76 86	99.87 54	99.66 121	99.18 211	99.60 255	98.55 338	99.57 247	99.67 220	99.03 142	99.94 98	97.01 377	99.80 249	99.69 117
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 435	95.78 434	97.49 443	98.53 466	93.83 473	98.04 420	93.94 488	98.96 281	98.46 426	98.17 467	79.86 478	99.87 250	96.99 378	99.06 411	98.78 438

EPMVS		96.53 423	96.32 422	97.17 455	98.18 477	92.97 477	99.39 129	89.95 494	98.21 376	98.61 414	99.59 288	86.69 464	99.72 403	96.99 378	99.23 404	98.81 435

MSP-MVS		99.04 268	98.79 298	99.81 54	99.78 137	99.73 91	99.35 147	99.57 272	98.54 341	99.54 263	98.99 425	96.81 341	99.93 119	96.97 380	99.53 359	99.77 79
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
HPM-MVS++		98.96 287	98.70 305	99.74 102	99.52 296	99.71 101	98.86 320	99.19 395	98.47 349	98.59 416	99.06 415	98.08 277	99.91 179	96.94 381	99.60 339	99.60 204

SR-MVS		99.19 229	99.00 259	99.74 102	99.51 298	99.72 96	99.18 211	99.60 255	98.85 300	99.47 285	99.58 291	98.38 245	99.92 150	96.92 382	99.54 357	99.57 222

PGM-MVS		99.20 226	99.01 255	99.77 79	99.75 170	99.71 101	99.16 222	99.72 180	97.99 388	99.42 298	99.60 278	98.81 174	99.93 119	96.91 383	99.74 280	99.66 147

HY-MVS	98.23 9	98.21 368	97.95 371	98.99 355	99.03 424	98.24 364	99.61 73	98.72 423	96.81 446	98.73 404	99.51 320	94.06 392	99.86 269	96.91 383	98.20 457	98.86 431

MDTV_nov1_ep13			97.73 386		98.70 461	90.83 489	99.15 225	98.02 456	98.51 344	98.82 394	99.61 270	90.98 432	99.66 441	96.89 385	98.92 422

GST-MVS		99.16 239	98.96 272	99.75 97	99.73 182	99.73 91	99.20 201	99.55 283	98.22 375	99.32 326	99.35 368	98.65 202	99.91 179	96.86 386	99.74 280	99.62 186

test_post1							99.14 229				51.63 504	89.54 450	99.82 339	96.86 386

SCA		98.11 371	98.36 337	97.36 448	99.20 394	92.99 476	98.17 404	98.49 438	98.24 374	99.10 366	99.57 298	96.01 369	99.94 98	96.86 386	99.62 329	99.14 380

UBG		96.53 423	95.95 429	98.29 420	98.87 441	96.31 443	98.48 380	98.07 454	98.83 304	97.32 467	96.54 497	79.81 479	99.62 453	96.84 389	98.74 435	98.95 419

XVG-OURS		99.21 224	99.06 237	99.65 158	99.82 94	99.62 141	97.87 438	99.74 167	98.36 359	99.66 208	99.68 216	99.71 28	99.90 198	96.84 389	99.88 183	99.43 304

LCM-MVSNet-Re		99.28 197	99.15 209	99.67 144	99.33 367	99.76 71	99.34 148	99.97 20	98.93 289	99.91 63	99.79 119	98.68 195	99.93 119	96.80 391	99.56 348	99.30 341

RPSCF		99.18 233	99.02 251	99.64 165	99.83 85	99.85 22	99.44 119	99.82 104	98.33 369	99.50 280	99.78 132	97.90 289	99.65 448	96.78 392	99.83 222	99.44 298

旧先验2							97.94 432		95.33 465	98.94 378			99.88 235	96.75 393

MDTV_nov1_ep13_2view						91.44 486	99.14 229		97.37 427	99.21 350		91.78 425		96.75 393		99.03 408

CLD-MVS		98.76 311	98.57 316	99.33 294	99.57 266	98.97 297	97.53 456	99.55 283	96.41 450	99.27 338	99.13 404	99.07 130	99.78 369	96.73 395	99.89 173	99.23 354
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 372	97.98 369	98.48 407	99.27 380	96.48 438	99.40 127	99.07 405	98.81 307	99.23 345	99.57 298	90.11 446	99.87 250	96.69 396	99.64 324	99.09 391

baseline2		96.83 416	96.28 423	98.46 409	99.09 417	96.91 429	98.83 327	93.87 489	97.23 433	96.23 484	98.36 462	88.12 454	99.90 198	96.68 397	98.14 462	98.57 453

cascas		96.99 412	96.82 418	97.48 444	97.57 492	95.64 455	96.43 483	99.56 277	91.75 480	97.13 474	97.61 479	95.58 374	98.63 487	96.68 397	99.11 408	98.18 473

PC_three_1452									97.56 414	99.68 195	99.41 345	99.09 123	97.09 490	96.66 399	99.60 339	99.62 186

LPG-MVS_test		99.22 219	99.05 242	99.74 102	99.82 94	99.63 139	99.16 222	99.73 171	97.56 414	99.64 215	99.69 204	99.37 76	99.89 220	96.66 399	99.87 196	99.69 117

LGP-MVS_train				99.74 102	99.82 94	99.63 139		99.73 171	97.56 414	99.64 215	99.69 204	99.37 76	99.89 220	96.66 399	99.87 196	99.69 117

ETVMVS		96.14 436	95.22 447	98.89 378	98.80 449	98.01 384	98.66 352	98.35 447	98.71 321	97.18 472	96.31 501	74.23 492	99.75 395	96.64 402	98.13 464	98.90 426

TinyColmap		98.97 284	98.93 275	99.07 348	99.46 324	98.19 369	97.75 442	99.75 161	98.79 310	99.54 263	99.70 195	98.97 154	99.62 453	96.63 403	99.83 222	99.41 309

LF4IMVS		99.01 277	98.92 279	99.27 316	99.71 191	99.28 240	98.59 360	99.77 148	98.32 370	99.39 311	99.41 345	98.62 204	99.84 304	96.62 404	99.84 214	98.69 444

NCCC		98.82 305	98.57 316	99.58 197	99.21 391	99.31 235	98.61 355	99.25 381	98.65 327	98.43 427	99.26 386	97.86 292	99.81 355	96.55 405	99.27 398	99.61 200

OPU-MVS				99.29 308	99.12 407	99.44 198	99.20 201				99.40 349	99.00 146	98.84 486	96.54 406	99.60 339	99.58 216

F-COLMAP		98.74 313	98.45 328	99.62 181	99.57 266	99.47 184	98.84 324	99.65 223	96.31 453	98.93 379	99.19 401	97.68 305	99.87 250	96.52 407	99.37 383	99.53 245

testing99		95.86 444	95.19 448	97.87 433	98.76 456	95.03 463	98.62 354	98.44 440	98.68 324	96.67 478	96.66 496	74.31 491	99.69 419	96.51 408	98.03 466	98.90 426

ADS-MVSNet2		97.78 386	97.66 390	98.12 425	99.14 403	95.36 459	99.22 198	98.75 422	96.97 441	98.25 434	99.64 236	90.90 434	99.94 98	96.51 408	99.56 348	99.08 397

ADS-MVSNet		97.72 391	97.67 389	97.86 434	99.14 403	94.65 467	99.22 198	98.86 415	96.97 441	98.25 434	99.64 236	90.90 434	99.84 304	96.51 408	99.56 348	99.08 397

PatchMatch-RL		98.68 321	98.47 325	99.30 307	99.44 329	99.28 240	98.14 408	99.54 289	97.12 439	99.11 364	99.25 388	97.80 297	99.70 412	96.51 408	99.30 392	98.93 422

CMPMVS	77.52 23	98.50 340	98.19 355	99.41 270	98.33 473	99.56 166	99.01 281	99.59 261	95.44 463	99.57 247	99.80 108	95.64 372	99.46 476	96.47 412	99.92 145	99.21 359
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 440	95.32 445	98.02 426	98.76 456	95.39 458	98.38 389	98.65 429	98.82 305	96.84 475	96.71 495	75.06 490	99.71 408	96.46 413	98.23 456	98.98 416

SF-MVS		99.10 256	98.93 275	99.62 181	99.58 256	99.51 178	99.13 236	99.65 223	97.97 390	99.42 298	99.61 270	98.86 171	99.87 250	96.45 414	99.68 311	99.49 269

FE-MVS		97.85 381	97.42 397	99.15 334	99.44 329	98.75 322	99.77 19	98.20 452	95.85 458	99.33 323	99.80 108	88.86 452	99.88 235	96.40 415	99.12 407	98.81 435

DPE-MVS		99.14 244	98.92 279	99.82 46	99.57 266	99.77 64	98.74 344	99.60 255	98.55 338	99.76 153	99.69 204	98.23 263	99.92 150	96.39 416	99.75 273	99.76 84
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 490	89.02 496			93.47 476		98.30 463		99.84 304	96.38 417

AllTest		99.21 224	99.07 235	99.63 172	99.78 137	99.64 133	99.12 241	99.83 98	98.63 330	99.63 220	99.72 175	98.68 195	99.75 395	96.38 417	99.83 222	99.51 258

TestCases				99.63 172	99.78 137	99.64 133		99.83 98	98.63 330	99.63 220	99.72 175	98.68 195	99.75 395	96.38 417	99.83 222	99.51 258

testdata				99.42 262	99.51 298	98.93 304		99.30 371	96.20 454	98.87 389	99.40 349	98.33 252	99.89 220	96.29 420	99.28 395	99.44 298

dp		96.86 415	97.07 407	96.24 467	98.68 462	90.30 494	99.19 207	98.38 445	97.35 428	98.23 436	99.59 288	87.23 456	99.82 339	96.27 421	98.73 438	98.59 449

tpmvs		97.39 404	97.69 387	96.52 463	98.41 470	91.76 482	99.30 165	98.94 414	97.74 407	97.85 457	99.55 310	92.40 418	99.73 401	96.25 422	98.73 438	98.06 475

KD-MVS_2432*1600		95.89 441	95.41 442	97.31 451	94.96 494	93.89 470	97.09 473	99.22 388	97.23 433	98.88 386	99.04 418	79.23 481	99.54 466	96.24 423	96.81 476	98.50 459

miper_refine_blended		95.89 441	95.41 442	97.31 451	94.96 494	93.89 470	97.09 473	99.22 388	97.23 433	98.88 386	99.04 418	79.23 481	99.54 466	96.24 423	96.81 476	98.50 459

ACMP	97.51 14	99.05 265	98.84 290	99.67 144	99.78 137	99.55 170	98.88 316	99.66 213	97.11 440	99.47 285	99.60 278	99.07 130	99.89 220	96.18 425	99.85 209	99.58 216
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 295	98.72 301	99.44 256	99.39 341	99.42 205	98.58 362	99.64 231	97.31 430	99.44 291	99.62 260	98.59 208	99.69 419	96.17 426	99.79 254	99.22 356

DP-MVS Recon		98.50 340	98.23 349	99.31 303	99.49 309	99.46 190	98.56 368	99.63 234	94.86 472	98.85 391	99.37 358	97.81 296	99.59 460	96.08 427	99.44 373	98.88 429

tpm cat1		96.78 417	96.98 410	96.16 468	98.85 443	90.59 492	99.08 257	99.32 364	92.37 478	97.73 463	99.46 337	91.15 430	99.69 419	96.07 428	98.80 428	98.21 470

tpm2		96.35 429	96.22 424	96.73 461	98.88 440	91.75 483	99.21 200	98.51 436	93.27 477	97.89 453	99.21 398	84.83 468	99.70 412	96.04 429	98.18 460	98.75 442

dmvs_re		98.69 320	98.48 324	99.31 303	99.55 280	99.42 205	99.54 90	98.38 445	99.32 225	98.72 405	98.71 449	96.76 343	99.21 480	96.01 430	99.35 386	99.31 339

test_0402		99.22 219	99.14 210	99.45 252	99.79 129	99.43 202	99.28 174	99.68 203	99.54 174	99.40 309	99.56 302	99.07 130	99.82 339	96.01 430	99.96 87	99.11 384

ITE_SJBPF				99.38 279	99.63 237	99.44 198		99.73 171	98.56 337	99.33 323	99.53 314	98.88 168	99.68 431	96.01 430	99.65 322	99.02 413

test_prior2							97.95 431		97.87 402	98.05 446	99.05 416	97.90 289		95.99 433	99.49 368

testdata2													99.89 220	95.99 433

原ACMM1				99.37 282	99.47 320	98.87 313		99.27 376	96.74 448	98.26 433	99.32 372	97.93 288	99.82 339	95.96 435	99.38 381	99.43 304

新几何1				99.52 228	99.50 304	99.22 258		99.26 378	95.66 462	98.60 415	99.28 381	97.67 306	99.89 220	95.95 436	99.32 390	99.45 284

MP-MVS		99.06 262	98.83 292	99.76 86	99.76 154	99.71 101	99.32 157	99.50 313	98.35 364	98.97 375	99.48 330	98.37 246	99.92 150	95.95 436	99.75 273	99.63 174
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 451	94.59 454	98.61 400	98.66 463	97.45 413	98.54 372	97.90 460	98.53 342	96.54 480	96.47 498	70.62 496	99.81 355	95.91 438	98.15 461	98.56 454

wuyk23d		97.58 395	99.13 212	92.93 472	99.69 212	99.49 180	99.52 94	99.77 148	97.97 390	99.96 34	99.79 119	99.84 16	99.94 98	95.85 439	99.82 232	79.36 490

HQP_MVS		98.90 295	98.68 306	99.55 216	99.58 256	99.24 252	98.80 335	99.54 289	98.94 285	99.14 360	99.25 388	97.24 325	99.82 339	95.84 440	99.78 263	99.60 204

plane_prior5								99.54 289					99.82 339	95.84 440	99.78 263	99.60 204

无先验							98.01 423	99.23 385	95.83 459				99.85 288	95.79 442		99.44 298

CPTT-MVS		98.74 313	98.44 329	99.64 165	99.61 242	99.38 218	99.18 211	99.55 283	96.49 449	99.27 338	99.37 358	97.11 333	99.92 150	95.74 443	99.67 317	99.62 186

PLC	97.35 16	98.36 353	97.99 367	99.48 243	99.32 368	99.24 252	98.50 377	99.51 309	95.19 468	98.58 417	98.96 432	96.95 338	99.83 323	95.63 444	99.25 400	99.37 320
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 332	98.34 340	99.28 311	99.18 399	99.10 284	98.34 391	99.41 336	98.48 348	98.52 422	98.98 428	97.05 335	99.78 369	95.59 445	99.50 366	98.96 417

1314		98.00 377	97.90 379	98.27 421	98.90 435	97.45 413	99.30 165	99.06 407	94.98 469	97.21 471	99.12 408	98.43 237	99.67 436	95.58 446	98.56 445	97.71 479

PVSNet_0	95.53 19	95.85 445	95.31 446	97.47 445	98.78 453	93.48 475	95.72 485	99.40 343	96.18 455	97.37 466	97.73 474	95.73 371	99.58 461	95.49 447	81.40 491	99.36 323

MAR-MVS		98.24 363	97.92 377	99.19 329	98.78 453	99.65 127	99.17 216	99.14 401	95.36 464	98.04 447	98.81 445	97.47 315	99.72 403	95.47 448	99.06 411	98.21 470
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	98.23 364	97.89 380	99.26 319	99.19 396	99.26 245	99.65 62	99.69 200	91.33 482	98.14 444	99.77 142	98.28 255	99.96 69	95.41 449	99.55 352	98.58 451

train_agg		98.35 356	97.95 371	99.57 205	99.35 353	99.35 229	98.11 412	99.41 336	94.90 470	97.92 451	98.99 425	98.02 280	99.85 288	95.38 450	99.44 373	99.50 264

9.14			98.64 307		99.45 328		98.81 332	99.60 255	97.52 419	99.28 337	99.56 302	98.53 224	99.83 323	95.36 451	99.64 324

APD-MVS		98.87 300	98.59 312	99.71 127	99.50 304	99.62 141	99.01 281	99.57 272	96.80 447	99.54 263	99.63 251	98.29 254	99.91 179	95.24 452	99.71 296	99.61 200
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 441								95.20 453

AdaColmap		98.60 327	98.35 339	99.38 279	99.12 407	99.22 258	98.67 350	99.42 335	97.84 405	98.81 395	99.27 383	97.32 323	99.81 355	95.14 454	99.53 359	99.10 386

test9_res														95.10 455	99.44 373	99.50 264

CDPH-MVS		98.56 333	98.20 352	99.61 187	99.50 304	99.46 190	98.32 393	99.41 336	95.22 466	99.21 350	99.10 412	98.34 250	99.82 339	95.09 456	99.66 320	99.56 225

BH-untuned		98.22 366	98.09 361	98.58 404	99.38 344	97.24 420	98.55 369	98.98 413	97.81 406	99.20 355	98.76 447	97.01 336	99.65 448	94.83 457	98.33 452	98.86 431

BP-MVS														94.73 458

HQP-MVS		98.36 353	98.02 366	99.39 276	99.31 369	98.94 301	97.98 427	99.37 351	97.45 422	98.15 440	98.83 442	96.67 345	99.70 412	94.73 458	99.67 317	99.53 245

QAPM		98.40 351	97.99 367	99.65 158	99.39 341	99.47 184	99.67 53	99.52 304	91.70 481	98.78 401	99.80 108	98.55 215	99.95 81	94.71 460	99.75 273	99.53 245

agg_prior2														94.58 461	99.46 372	99.50 264

myMVS_eth3d		95.63 449	94.73 451	98.34 415	98.50 468	96.36 441	98.60 357	99.21 391	97.89 399	96.76 476	96.37 499	72.10 494	99.57 462	94.38 462	98.73 438	99.09 391

BH-RMVSNet		98.41 349	98.14 358	99.21 326	99.21 391	98.47 350	98.60 357	98.26 450	98.35 364	98.93 379	99.31 375	97.20 330	99.66 441	94.32 463	99.10 409	99.51 258

E-PMN		97.14 411	97.43 396	96.27 466	98.79 451	91.62 484	95.54 486	99.01 412	99.44 199	98.88 386	99.12 408	92.78 410	99.68 431	94.30 464	99.03 415	97.50 480

MG-MVS		98.52 337	98.39 334	98.94 362	99.15 402	97.39 417	98.18 402	99.21 391	98.89 296	99.23 345	99.63 251	97.37 321	99.74 398	94.22 465	99.61 336	99.69 117

API-MVS		98.38 352	98.39 334	98.35 413	98.83 445	99.26 245	99.14 229	99.18 396	98.59 335	98.66 410	98.78 446	98.61 206	99.57 462	94.14 466	99.56 348	96.21 487

PAPM_NR		98.36 353	98.04 364	99.33 294	99.48 314	98.93 304	98.79 338	99.28 375	97.54 417	98.56 421	98.57 455	97.12 332	99.69 419	94.09 467	98.90 426	99.38 317

ZD-MVS					99.43 332	99.61 151		99.43 333	96.38 451	99.11 364	99.07 414	97.86 292	99.92 150	94.04 468	99.49 368

DPM-MVS		98.28 359	97.94 375	99.32 299	99.36 349	99.11 277	97.31 466	98.78 421	96.88 443	98.84 392	99.11 411	97.77 299	99.61 458	94.03 469	99.36 384	99.23 354

gg-mvs-nofinetune		95.87 443	95.17 449	97.97 429	98.19 476	96.95 427	99.69 45	89.23 495	99.89 56	96.24 483	99.94 19	81.19 473	99.51 472	93.99 470	98.20 457	97.44 481

PMVS	92.94 21	98.82 305	98.81 295	98.85 381	99.84 77	97.99 385	99.20 201	99.47 321	99.71 118	99.42 298	99.82 91	98.09 275	99.47 474	93.88 471	99.85 209	99.07 402
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 414	97.28 400	95.99 470	98.76 456	91.03 488	95.26 488	98.61 430	99.34 221	98.92 382	98.88 439	93.79 396	99.66 441	92.87 472	99.05 413	97.30 484

BH-w/o		97.20 408	97.01 409	97.76 437	99.08 418	95.69 454	98.03 422	98.52 435	95.76 460	97.96 450	98.02 469	95.62 373	99.47 474	92.82 473	97.25 475	98.12 474

TR-MVS		97.44 401	97.15 405	98.32 416	98.53 466	97.46 411	98.47 381	97.91 459	96.85 444	98.21 437	98.51 459	96.42 355	99.51 472	92.16 474	97.29 474	97.98 476

OpenMVS_ROB	97.31 17	97.36 406	96.84 416	98.89 378	99.29 375	99.45 196	98.87 319	99.48 318	86.54 487	99.44 291	99.74 162	97.34 322	99.86 269	91.61 475	99.28 395	97.37 483

GG-mvs-BLEND				97.36 448	97.59 490	96.87 430	99.70 38	88.49 496		94.64 489	97.26 485	80.66 475	99.12 481	91.50 476	96.50 483	96.08 489

DeepMVS_CX				97.98 428	99.69 212	96.95 427		99.26 378	75.51 490	95.74 486	98.28 464	96.47 353	99.62 453	91.23 477	97.89 468	97.38 482

PAPR		97.56 396	97.07 407	99.04 352	98.80 449	98.11 377	97.63 450	99.25 381	94.56 475	98.02 449	98.25 465	97.43 317	99.68 431	90.90 478	98.74 435	99.33 331

MVS		95.72 447	94.63 453	98.99 355	98.56 465	97.98 390	99.30 165	98.86 415	72.71 491	97.30 468	99.08 413	98.34 250	99.74 398	89.21 479	98.33 452	99.26 347

UWE-MVS-28		95.64 448	95.47 440	96.14 469	97.98 483	90.39 493	98.49 379	95.81 480	99.02 275	98.03 448	98.19 466	84.49 470	99.28 479	88.75 480	98.47 450	98.75 442

thres600view7		96.60 422	96.16 425	97.93 431	99.63 237	96.09 449	99.18 211	97.57 465	98.77 314	98.72 405	97.32 483	87.04 458	99.72 403	88.57 481	98.62 443	97.98 476

FPMVS		96.32 430	95.50 439	98.79 389	99.60 244	98.17 372	98.46 385	98.80 420	97.16 437	96.28 481	99.63 251	82.19 472	99.09 482	88.45 482	98.89 427	99.10 386

PCF-MVS	96.03 18	96.73 419	95.86 432	99.33 294	99.44 329	99.16 271	96.87 479	99.44 330	86.58 486	98.95 377	99.40 349	94.38 390	99.88 235	87.93 483	99.80 249	98.95 419
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 428	96.03 428	97.47 445	99.63 237	95.93 450	99.18 211	97.57 465	98.75 318	98.70 408	97.31 484	87.04 458	99.67 436	87.62 484	98.51 447	96.81 485

tfpn200view9		96.30 431	95.89 430	97.53 442	99.58 256	96.11 447	99.00 287	97.54 468	98.43 350	98.52 422	96.98 488	86.85 460	99.67 436	87.62 484	98.51 447	96.81 485

thres400		96.40 427	95.89 430	97.92 432	99.58 256	96.11 447	99.00 287	97.54 468	98.43 350	98.52 422	96.98 488	86.85 460	99.67 436	87.62 484	98.51 447	97.98 476

thres200		96.09 437	95.68 437	97.33 450	99.48 314	96.22 446	98.53 374	97.57 465	98.06 385	98.37 429	96.73 494	86.84 462	99.61 458	86.99 487	98.57 444	96.16 488

MVE	92.54 22	96.66 421	96.11 426	98.31 418	99.68 220	97.55 406	97.94 432	95.60 481	99.37 217	90.68 492	98.70 451	96.56 348	98.61 488	86.94 488	99.55 352	98.77 440
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 407	96.83 417	98.59 402	99.46 324	97.55 406	99.25 189	96.84 474	98.78 312	97.24 470	97.67 475	97.11 333	98.97 484	86.59 489	98.54 446	99.27 345

PAPM		95.61 450	94.71 452	98.31 418	99.12 407	96.63 434	96.66 482	98.46 439	90.77 483	96.25 482	98.68 452	93.01 408	99.69 419	81.60 490	97.86 470	98.62 446

SD_0403		97.42 402	96.90 415	98.98 357	99.54 282	97.90 393	99.52 94	99.54 289	99.34 221	97.87 455	98.85 441	98.72 191	99.64 450	78.93 491	99.83 222	99.40 312

dongtai		89.37 456	88.91 459	90.76 473	99.19 396	77.46 498	95.47 487	87.82 497	92.28 479	94.17 490	98.82 444	71.22 495	95.54 492	63.85 492	97.34 473	99.27 345

kuosan		85.65 458	84.57 461	88.90 475	97.91 485	77.11 499	96.37 484	87.62 498	85.24 488	85.45 493	96.83 491	69.94 497	90.98 494	45.90 493	95.83 488	98.62 446

test123		29.31 459	33.05 464	18.08 476	25.93 500	12.24 501	97.53 456	10.93 501	11.78 494	24.21 495	50.08 506	21.04 498	8.60 495	23.51 494	32.43 494	33.39 491

testmvs		28.94 460	33.33 462	15.79 477	26.03 499	9.81 502	96.77 480	15.67 500	11.55 495	23.87 496	50.74 505	19.03 499	8.53 496	23.21 495	33.07 493	29.03 492

mmdepth		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

monomultidepth		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

test_blank		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

uanet_test		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

DCPMVS		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

cdsmvs_eth3d_5k		24.88 461	33.17 463	0.00 478	0.00 501	0.00 503	0.00 490	99.62 237	0.00 496	0.00 497	99.13 404	99.82 18	0.00 497	0.00 496	0.00 495	0.00 493

pcd_1.5k_mvsjas		16.61 462	22.14 465	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	99.28 91	0.00 497	0.00 496	0.00 495	0.00 493

sosnet-low-res		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

sosnet		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

uncertanet		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

Regformer		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

ab-mvs-re		8.26 473	11.02 476	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	99.16 402	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

uanet		8.33 463	11.11 466	0.00 478	0.00 501	0.00 503	0.00 490	0.00 502	0.00 496	0.00 497	100.00 1	0.00 500	0.00 497	0.00 496	0.00 495	0.00 493

TestfortrainingZip							99.38 132

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

test_one_0601					99.63 237	99.76 71		99.55 283	99.23 242	99.31 331	99.61 270	98.59 208

eth-test2					0.00 501

eth-test					0.00 501

test_241102_ONE					99.69 212	99.82 43		99.54 289	99.12 266	99.82 109	99.49 327	98.91 164	99.52 471

save fliter					99.53 289	99.25 248	98.29 395	99.38 350	99.07 270

test0726					99.69 212	99.80 52	99.24 190	99.57 272	99.16 257	99.73 173	99.65 234	98.35 248

GSMVS																99.14 380

test_part2					99.62 241	99.67 119				99.55 260

sam_mvs1												90.81 438				99.14 380

sam_mvs												90.52 443

MTGPA								99.53 299

test_post											52.41 503	90.25 445	99.86 269

patchmatchnet-post											99.62 260	90.58 441	99.94 98

MTMP							99.09 254	98.59 433

TEST9					99.35 353	99.35 229	98.11 412	99.41 336	94.83 473	97.92 451	98.99 425	98.02 280	99.85 288

test_8					99.34 362	99.31 235	98.08 416	99.40 343	94.90 470	97.87 455	98.97 430	98.02 280	99.84 304

agg_prior					99.35 353	99.36 226		99.39 346		97.76 462			99.85 288

test_prior4						99.19 265	98.00 425

test_prior				99.46 249	99.35 353	99.22 258		99.39 346					99.69 419			99.48 273

新几何2							98.04 420

旧先验1					99.49 309	99.29 238		99.26 378			99.39 353	97.67 306			99.36 384	99.46 282

原ACMM2							97.92 434

test222					99.51 298	99.08 286	97.83 440	99.29 372	95.21 467	98.68 409	99.31 375	97.28 324			99.38 381	99.43 304

segment_acmp												98.37 246

testdata1							97.72 445		97.86 404

test12				99.54 222	99.29 375	99.33 232		99.16 399		98.43 427		97.54 313	99.82 339		99.47 370	99.48 273

plane_prior7					99.58 256	99.38 218

plane_prior6					99.47 320	99.26 245						97.24 325

plane_prior4											99.25 388

plane_prior3						99.31 235			98.36 359	99.14 360

plane_prior2							98.80 335		98.94 285

plane_prior1					99.51 298

plane_prior						99.24 252	98.42 387		97.87 402						99.71 296

n2								0.00 502

nn								0.00 502

door-mid								99.83 98

test11								99.29 372

door								99.77 148

HQP5-MVS						98.94 301

HQP-NCC					99.31 369		97.98 427		97.45 422	98.15 440

ACMP_Plane					99.31 369		97.98 427		97.45 422	98.15 440

HQP4-MVS										98.15 440			99.70 412			99.53 245

HQP3-MVS								99.37 351							99.67 317

HQP2-MVS												96.67 345

NP-MVS					99.40 340	99.13 274					98.83 442

ACMMP++_ref															99.94 127

ACMMP++															99.79 254

Test By Simon												98.41 240

High-resolution multi-view benchmark