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.

mvs5depth		99.88 6	99.91 3	99.80 65	99.92 30	99.42 214	99.94 3	100.00 1	99.97 26	99.89 73	99.99 12	99.63 38	99.97 45	99.87 45	99.99 19	100.00 1

fmvsm_s_conf0.1_n_2		99.81 29	99.78 40	99.89 12	99.93 24	99.76 71	98.92 320	99.98 14	99.99 4	99.99 7	99.88 51	99.43 68	99.94 99	99.94 21	99.99 19	99.99 2

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 4	99.95 15	99.82 42	99.10 256	99.98 14	99.99 4	99.98 14	99.91 32	99.68 34	99.93 121	99.93 26	99.99 19	99.99 2

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 4	99.98 3	99.76 71	99.12 247	100.00 1	100.00 1	99.99 7	99.91 32	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

mmtdpeth		99.78 38	99.83 21	99.66 154	99.85 76	99.05 310	99.79 15	99.97 22	100.00 1	99.43 320	99.94 20	99.64 36	99.94 99	99.83 47	99.99 19	99.98 5

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 12	99.93 24	99.78 58	99.07 269	99.98 14	99.99 4	99.98 14	99.90 37	99.88 12	99.92 155	99.93 26	99.99 19	99.98 5

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 4	99.97 6	99.74 88	99.01 288	99.99 12	99.99 4	99.98 14	99.88 51	99.97 2	99.99 7	99.96 9	100.00 1	99.98 5

test_vis3_rt		99.89 3	99.90 4	99.87 27	99.98 3	99.75 80	99.70 38	100.00 1	99.73 113	100.00 1	99.89 42	99.79 23	99.88 244	99.98 1	100.00 1	99.98 5

test_fmvs3		99.83 22	99.93 2	99.53 233	99.96 7	98.62 379	99.67 53	100.00 1	99.95 33	100.00 1	99.95 16	99.85 15	99.99 7	99.98 1	99.99 19	99.98 5

fmvsm_l_mol_unc0.5_1		99.85 12	99.82 25	99.94 2	99.93 24	99.86 18	98.72 359	99.99 12	100.00 1	99.93 53	99.95 16	99.94 4	99.99 7	99.96 9	99.99 19	99.97 10

test_cas_vis1_n_1920		99.76 47	99.86 13	99.45 260	99.93 24	98.40 401	99.30 169	99.98 14	99.94 37	99.99 7	99.89 42	99.80 22	99.97 45	99.96 9	99.97 78	99.97 10

test_vis1_n_1920		99.72 54	99.88 7	99.27 337	99.93 24	97.84 441	99.34 151	100.00 1	99.99 4	99.99 7	99.82 92	99.87 14	99.99 7	99.97 4	99.99 19	99.97 10

test_f		99.75 50	99.88 7	99.37 296	99.96 7	98.21 414	99.51 102	100.00 1	99.94 37	100.00 1	99.93 23	99.58 51	99.94 99	99.97 4	99.99 19	99.97 10

PDCNetPlus		98.55 362	98.50 355	98.69 429	99.64 259	96.12 500	97.67 482	100.00 1	98.34 404	99.79 135	99.74 171	92.45 469	99.98 27	98.92 216	99.99 19	99.96 14

test_fmvs2		99.72 54	99.85 17	99.34 310	99.91 32	98.08 428	99.48 110	100.00 1	99.90 50	99.99 7	99.91 32	99.50 63	99.98 27	99.98 1	99.99 19	99.96 14

MVStest1		98.22 400	98.09 403	98.62 431	99.04 467	96.23 497	99.20 207	99.92 48	99.44 212	99.98 14	99.87 57	85.87 524	99.67 476	99.91 34	99.57 386	99.95 16

test_vis1_n		99.68 65	99.79 35	99.36 302	99.94 18	98.18 417	99.52 95	100.00 1	99.86 66	100.00 1	99.88 51	98.99 153	99.96 70	99.97 4	99.96 92	99.95 16

tmp_tt		95.75 500	95.42 495	96.76 516	89.90 561	94.42 528	98.86 329	97.87 516	78.01 552	99.30 364	99.69 216	97.70 322	95.89 552	99.29 135	98.14 518	99.95 16

fmvsm_s_conf0.5_n_2		99.78 38	99.75 52	99.88 20	99.82 100	99.76 71	98.88 325	99.92 48	99.98 19	99.98 14	99.85 69	99.42 70	99.94 99	99.93 26	99.98 55	99.94 19

mvsany_test3		99.85 12	99.88 7	99.75 99	99.95 15	99.37 233	99.53 93	99.98 14	99.77 108	99.99 7	99.95 16	99.85 15	99.94 99	99.95 15	99.98 55	99.94 19

PS-MVSNAJss		99.84 18	99.82 25	99.89 12	99.96 7	99.77 64	99.68 48	99.85 96	99.95 33	99.98 14	99.92 28	99.28 94	99.98 27	99.75 57	100.00 1	99.94 19

ttmdpeth		99.48 136	99.55 113	99.29 328	99.76 166	98.16 419	99.33 157	99.95 39	99.79 100	99.36 341	99.89 42	99.13 121	99.77 412	99.09 183	99.64 362	99.93 22

fmvsm_s_conf0.5_n_a		99.82 25	99.79 35	99.89 12	99.85 76	99.82 42	99.03 279	99.96 31	99.99 4	99.97 24	99.84 77	99.58 51	99.93 121	99.92 31	99.98 55	99.93 22

test_fmvsmconf_n		99.85 12	99.84 20	99.88 20	99.91 32	99.73 92	98.97 307	99.98 14	99.99 4	99.96 34	99.85 69	99.93 8	99.99 7	99.94 21	99.99 19	99.93 22

test_fmvs1_n		99.68 65	99.81 29	99.28 331	99.95 15	97.93 437	99.49 108	100.00 1	99.82 86	99.99 7	99.89 42	99.21 106	99.98 27	99.97 4	99.98 55	99.93 22

fmvsm_s_conf0.5_n_11		99.76 47	99.75 52	99.81 55	99.81 114	99.53 178	99.15 231	99.89 69	99.99 4	99.98 14	99.86 64	99.13 121	99.98 27	99.93 26	99.99 19	99.92 26

fmvsm_s_conf0.5_n_9		99.82 25	99.82 25	99.82 47	99.83 91	99.59 162	98.97 307	99.92 48	99.99 4	99.97 24	99.84 77	99.90 10	99.94 99	99.94 21	99.99 19	99.92 26

fmvsm_s_conf0.5_n_8		99.76 47	99.72 56	99.88 20	99.82 100	99.75 80	99.02 283	99.87 81	99.98 19	99.98 14	99.81 99	99.07 136	99.97 45	99.91 34	99.99 19	99.92 26

fmvsm_s_conf0.5_n		99.83 22	99.81 29	99.87 27	99.85 76	99.78 58	99.03 279	99.96 31	99.99 4	99.97 24	99.84 77	99.78 24	99.92 155	99.92 31	99.99 19	99.92 26

mvs_tets		99.90 2	99.90 4	99.90 9	99.96 7	99.79 55	99.72 33	99.88 75	99.92 46	99.98 14	99.93 23	99.94 4	99.98 27	99.77 56	100.00 1	99.92 26

fmvsm_s_conf0.5_n_10		99.77 45	99.73 55	99.88 20	99.81 114	99.75 80	99.06 270	99.85 96	99.99 4	99.97 24	99.84 77	99.12 124	99.98 27	99.95 15	99.99 19	99.90 31

fmvsm_l_conf0.5_n_9		99.83 22	99.81 29	99.89 12	99.86 61	99.80 52	98.94 316	99.96 31	99.98 19	99.96 34	99.78 134	99.88 12	99.98 27	99.96 9	99.99 19	99.90 31

fmvsm_s_conf0.5_n_7		99.73 53	99.78 40	99.60 196	99.74 195	98.93 331	98.85 331	99.96 31	99.96 29	99.97 24	99.76 156	99.82 19	99.96 70	99.95 15	99.98 55	99.90 31

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 3	99.88 47	99.86 18	99.08 264	99.97 22	99.98 19	99.96 34	99.79 121	99.90 10	99.99 7	99.96 9	99.99 19	99.90 31

UA-Net		99.78 38	99.76 50	99.86 31	99.72 204	99.71 103	99.91 4	99.95 39	99.96 29	99.71 195	99.91 32	99.15 116	99.97 45	99.50 96	100.00 1	99.90 31

jajsoiax		99.89 3	99.89 6	99.89 12	99.96 7	99.78 58	99.70 38	99.86 90	99.89 56	99.98 14	99.90 37	99.94 4	99.98 27	99.75 57	100.00 1	99.90 31

EU-MVSNet		99.39 177	99.62 86	98.72 424	99.88 47	96.44 491	99.56 88	99.85 96	99.90 50	99.90 68	99.85 69	98.09 292	99.83 341	99.58 82	99.95 117	99.90 31

test_djsdf		99.84 18	99.81 29	99.91 4	99.94 18	99.84 27	99.77 19	99.80 144	99.73 113	99.97 24	99.92 28	99.77 26	99.98 27	99.43 107	100.00 1	99.90 31

VortexMVS		99.13 263	99.24 210	98.79 417	99.67 250	96.60 489	99.24 195	99.80 144	99.85 72	99.93 53	99.84 77	95.06 426	99.89 228	99.80 53	99.98 55	99.89 39

fmvsm_s_conf0.5_n_4		99.78 38	99.78 40	99.79 73	99.75 184	99.56 171	98.98 305	99.94 42	99.92 46	99.97 24	99.72 187	99.84 17	99.92 155	99.91 34	99.98 55	99.89 39

fmvsm_s_conf0.5_n_3		99.79 35	99.77 46	99.85 33	99.81 114	99.71 103	98.97 307	99.92 48	99.98 19	99.97 24	99.86 64	99.53 59	99.95 82	99.88 42	99.99 19	99.89 39

fmvsm_l_conf0.5_n_a		99.80 31	99.79 35	99.84 39	99.88 47	99.64 138	99.12 247	99.91 58	99.98 19	99.95 45	99.67 235	99.67 35	99.99 7	99.94 21	99.99 19	99.88 42

fmvsm_l_conf0.5_n		99.80 31	99.78 40	99.85 33	99.88 47	99.66 125	99.11 252	99.91 58	99.98 19	99.96 34	99.64 250	99.60 45	99.99 7	99.95 15	99.99 19	99.88 42

MM		99.18 247	99.05 261	99.55 222	99.35 393	98.81 352	99.05 271	97.79 518	99.99 4	99.48 307	99.59 306	96.29 396	99.95 82	99.94 21	99.98 55	99.88 42

test_fmvsmvis_n_1920		99.84 18	99.86 13	99.81 55	99.88 47	99.55 175	99.17 222	99.98 14	99.99 4	99.96 34	99.84 77	99.96 3	99.99 7	99.96 9	99.99 19	99.88 42

CVMVSNet		98.61 352	98.88 308	97.80 476	99.58 289	93.60 536	99.26 188	99.63 263	99.66 152	99.72 190	99.67 235	93.26 454	99.93 121	99.30 132	99.81 267	99.87 46

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 22	99.99 4	100.00 1	99.98 13	99.78 24	100.00 1	99.92 31	100.00 1	99.87 46

SSC-MVS		99.52 123	99.42 154	99.83 42	99.86 61	99.65 131	99.52 95	99.81 136	99.87 63	99.81 121	99.79 121	96.78 372	99.99 7	99.83 47	99.51 403	99.86 48

FC-MVSNet-test		99.70 58	99.65 75	99.86 31	99.88 47	99.86 18	99.72 33	99.78 166	99.90 50	99.82 114	99.83 84	98.45 246	99.87 261	99.51 94	99.97 78	99.86 48

PS-CasMVS		99.66 78	99.58 101	99.89 12	99.80 125	99.85 22	99.66 57	99.73 196	99.62 167	99.84 105	99.71 197	98.62 210	99.96 70	99.30 132	99.96 92	99.86 48

MED-MVS		99.51 125	99.42 154	99.80 65	99.76 166	99.65 131	99.38 134	99.78 166	99.77 108	99.81 121	99.78 134	99.02 149	99.90 205	97.69 366	99.76 298	99.85 51

TestfortrainingZip a		99.55 112	99.45 143	99.85 33	99.76 166	99.82 42	99.38 134	99.62 267	99.77 108	99.87 93	99.78 134	98.12 289	99.88 244	98.96 205	99.77 293	99.85 51

fmvsm_s_conf0.5_n_5		99.78 38	99.76 50	99.85 33	99.79 139	99.72 97	98.84 334	99.96 31	99.96 29	99.96 34	99.72 187	99.71 29	99.99 7	99.93 26	99.98 55	99.85 51

reproduce_monomvs		97.40 449	97.46 438	97.20 503	99.05 464	91.91 544	99.20 207	99.18 439	99.84 76	99.86 97	99.75 164	80.67 532	99.83 341	99.69 65	99.95 117	99.85 51

anonymousdsp		99.80 31	99.77 46	99.90 9	99.96 7	99.88 12	99.73 30	99.85 96	99.70 130	99.92 60	99.93 23	99.45 64	99.97 45	99.36 120	100.00 1	99.85 51

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 9	99.89 41	99.91 4	99.89 5	99.71 209	99.93 44	99.95 45	99.89 42	99.71 29	99.96 70	99.51 94	99.97 78	99.84 56

CP-MVSNet		99.54 117	99.43 151	99.87 27	99.76 166	99.82 42	99.57 86	99.61 275	99.54 187	99.80 128	99.64 250	97.79 316	99.95 82	99.21 147	99.94 136	99.84 56

Test_1112_low_res		98.95 311	98.73 324	99.63 176	99.68 243	99.15 291	98.09 444	99.80 144	97.14 488	99.46 313	99.40 378	96.11 402	99.89 228	99.01 197	99.84 239	99.84 56

ANet_high		99.88 6	99.87 11	99.91 4	99.99 1	99.91 4	99.65 62	100.00 1	99.90 50	100.00 1	99.97 14	99.61 42	99.97 45	99.75 57	100.00 1	99.84 56

fmvsm_s_conf0.5_n_6		99.80 31	99.78 40	99.85 33	99.78 148	99.78 58	99.00 294	99.97 22	99.96 29	99.97 24	99.56 321	99.92 9	99.93 121	99.91 34	99.99 19	99.83 60

patch_mono-2		99.51 125	99.46 139	99.64 168	99.70 226	99.11 297	99.04 276	99.87 81	99.71 123	99.47 309	99.79 121	98.24 273	99.98 27	99.38 116	99.96 92	99.83 60

nrg030		99.70 58	99.66 73	99.82 47	99.76 166	99.84 27	99.61 73	99.70 218	99.93 44	99.78 141	99.68 229	99.10 126	99.78 399	99.45 104	99.96 92	99.83 60

FIs		99.65 84	99.58 101	99.84 39	99.84 82	99.85 22	99.66 57	99.75 185	99.86 66	99.74 178	99.79 121	98.27 271	99.85 300	99.37 119	99.93 150	99.83 60

v7n		99.82 25	99.80 33	99.88 20	99.96 7	99.84 27	99.82 10	99.82 123	99.84 76	99.94 48	99.91 32	99.13 121	99.96 70	99.83 47	99.99 19	99.83 60

PEN-MVS		99.66 78	99.59 97	99.89 12	99.83 91	99.87 15	99.66 57	99.73 196	99.70 130	99.84 105	99.73 177	98.56 221	99.96 70	99.29 135	99.94 136	99.83 60

WR-MVS_H		99.61 99	99.53 121	99.87 27	99.80 125	99.83 34	99.67 53	99.75 185	99.58 183	99.85 102	99.69 216	98.18 284	99.94 99	99.28 137	99.95 117	99.83 60

WB-MVS		99.44 156	99.32 183	99.80 65	99.81 114	99.61 156	99.47 113	99.81 136	99.82 86	99.71 195	99.72 187	96.60 378	99.98 27	99.75 57	99.23 449	99.82 67

SSC-MVS3.2		99.64 86	99.67 66	99.56 215	99.75 184	98.98 319	98.96 311	99.87 81	99.88 61	99.84 105	99.64 250	99.32 89	99.91 186	99.78 55	99.96 92	99.80 68

test_fmvsm_n_1920		99.84 18	99.85 17	99.83 42	99.82 100	99.70 111	99.17 222	99.97 22	99.99 4	99.96 34	99.82 92	99.94 4	100.00 1	99.95 15	100.00 1	99.80 68

Anonymous20231211		99.62 95	99.57 106	99.76 88	99.61 270	99.60 160	99.81 13	99.73 196	99.82 86	99.90 68	99.90 37	97.97 304	99.86 281	99.42 112	99.96 92	99.80 68

APDe-MVS		99.48 136	99.36 171	99.85 33	99.55 317	99.81 48	99.50 103	99.69 228	98.99 300	99.75 167	99.71 197	98.79 184	99.93 121	98.46 279	99.85 233	99.80 68
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DTE-MVSNet		99.68 65	99.61 90	99.88 20	99.80 125	99.87 15	99.67 53	99.71 209	99.72 117	99.84 105	99.78 134	98.67 204	99.97 45	99.30 132	99.95 117	99.80 68

XXY-MVS		99.71 57	99.67 66	99.81 55	99.89 41	99.72 97	99.59 80	99.82 123	99.39 229	99.82 114	99.84 77	99.38 77	99.91 186	99.38 116	99.93 150	99.80 68

1112_ss		99.05 285	98.84 313	99.67 146	99.66 253	99.29 250	98.52 396	99.82 123	97.65 460	99.43 320	99.16 444	96.42 386	99.91 186	99.07 188	99.84 239	99.80 68

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 20	99.91 32	99.90 7	99.96 1	99.92 48	99.90 50	99.97 24	99.87 57	99.81 21	99.95 82	99.54 88	99.99 19	99.80 68
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
test_fmvs1		99.48 136	99.65 75	98.97 384	99.54 319	97.16 472	99.11 252	99.98 14	99.78 103	99.96 34	99.81 99	98.72 197	99.97 45	99.95 15	99.97 78	99.79 76

PMMVS2		99.48 136	99.45 143	99.57 211	99.76 166	98.99 317	98.09 444	99.90 65	98.95 307	99.78 141	99.58 309	99.57 53	99.93 121	99.48 98	99.95 117	99.79 76

MSC_two_6792asdad				99.74 104	99.03 469	99.53 178		99.23 427					99.92 155	97.77 348	99.69 344	99.78 78

No_MVS				99.74 104	99.03 469	99.53 178		99.23 427					99.92 155	97.77 348	99.69 344	99.78 78

dcpmvs_2		99.61 99	99.64 80	99.53 233	99.79 139	98.82 351	99.58 83	99.97 22	99.95 33	99.96 34	99.76 156	98.44 247	99.99 7	99.34 124	99.96 92	99.78 78

CHOSEN 1792x2688		99.39 177	99.30 190	99.65 161	99.88 47	99.25 261	98.78 349	99.88 75	98.66 356	99.96 34	99.79 121	97.45 339	99.93 121	99.34 124	99.99 19	99.78 78

test_vis1_rt		99.45 152	99.46 139	99.41 281	99.71 210	98.63 378	98.99 302	99.96 31	99.03 295	99.95 45	99.12 451	98.75 192	99.84 318	99.82 51	99.82 257	99.77 82

IU-MVS					99.69 234	99.77 64		99.22 430	97.50 468	99.69 203				97.75 352	99.70 335	99.77 82

test_0728_THIRD									99.18 265	99.62 250	99.61 286	98.58 217	99.91 186	97.72 355	99.80 274	99.77 82

test_0728_SECOND				99.83 42	99.70 226	99.79 55	99.14 235	99.61 275					99.92 155	97.88 334	99.72 328	99.77 82

MSP-MVS		99.04 288	98.79 322	99.81 55	99.78 148	99.73 92	99.35 150	99.57 305	98.54 373	99.54 285	98.99 470	96.81 371	99.93 121	96.97 427	99.53 399	99.77 82
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
DPE-MVS		99.14 260	98.92 302	99.82 47	99.57 299	99.77 64	98.74 356	99.60 287	98.55 370	99.76 162	99.69 216	98.23 277	99.92 155	96.39 467	99.75 306	99.76 87
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
Baseline_NR-MVSNet		99.49 133	99.37 166	99.82 47	99.91 32	99.84 27	98.83 337	99.86 90	99.68 137	99.65 229	99.88 51	97.67 326	99.87 261	99.02 194	99.86 226	99.76 87

OurMVSNet-221017-0		99.75 50	99.71 57	99.84 39	99.96 7	99.83 34	99.83 7	99.85 96	99.80 96	99.93 53	99.93 23	98.54 227	99.93 121	99.59 79	99.98 55	99.76 87

test_241102_TWO								99.54 323	99.13 282	99.76 162	99.63 266	98.32 265	99.92 155	97.85 341	99.69 344	99.75 90

DP-MVS		99.48 136	99.39 160	99.74 104	99.57 299	99.62 146	99.29 177	99.61 275	99.87 63	99.74 178	99.76 156	98.69 200	99.87 261	98.20 304	99.80 274	99.75 90

NormalMVS		99.09 275	98.91 306	99.62 185	99.78 148	99.11 297	99.36 146	99.77 171	99.82 86	99.68 210	99.53 336	93.30 452	99.99 7	99.24 140	99.76 298	99.74 92

KinetiMVS		99.66 78	99.63 83	99.76 88	99.89 41	99.57 170	99.37 142	99.82 123	99.95 33	99.90 68	99.63 266	98.57 218	99.97 45	99.65 71	99.94 136	99.74 92

AstraMVS		99.15 259	99.06 254	99.42 271	99.85 76	98.59 382	99.13 242	97.26 528	99.84 76	99.87 93	99.77 146	96.11 402	99.93 121	99.71 61	99.96 92	99.74 92

guyue		99.12 266	99.02 270	99.41 281	99.84 82	98.56 385	99.19 213	98.30 500	99.82 86	99.84 105	99.75 164	94.84 430	99.92 155	99.68 67	99.94 136	99.74 92

LuminaMVS		99.39 177	99.28 199	99.73 114	99.83 91	99.49 186	99.00 294	99.05 452	99.81 92	99.89 73	99.79 121	96.54 382	99.97 45	99.64 74	99.98 55	99.73 96

reproduce_model		99.50 128	99.40 159	99.83 42	99.60 273	99.83 34	99.12 247	99.68 232	99.49 196	99.80 128	99.79 121	99.01 150	99.93 121	98.24 300	99.82 257	99.73 96

tt0805		99.63 87	99.57 106	99.81 55	99.87 56	99.88 12	99.58 83	98.70 472	99.72 117	99.91 63	99.60 296	99.43 68	99.81 381	99.81 52	99.52 401	99.73 96

v10		99.69 60	99.69 61	99.66 154	99.81 114	99.39 226	99.66 57	99.75 185	99.60 179	99.92 60	99.87 57	98.75 192	99.86 281	99.90 38	99.99 19	99.73 96

Elysia		99.69 60	99.65 75	99.81 55	99.86 61	99.72 97	99.34 151	99.77 171	99.94 37	99.91 63	99.76 156	98.55 222	99.99 7	99.70 62	99.98 55	99.72 100

StellarMVS		99.69 60	99.65 75	99.81 55	99.86 61	99.72 97	99.34 151	99.77 171	99.94 37	99.91 63	99.76 156	98.55 222	99.99 7	99.70 62	99.98 55	99.72 100

EI-MVSNet-UG-set		99.48 136	99.50 126	99.42 271	99.57 299	98.65 373	99.24 195	99.46 359	99.68 137	99.80 128	99.66 241	98.99 153	99.89 228	99.19 153	99.90 177	99.72 100

Vis-MVSNet		99.75 50	99.74 54	99.79 73	99.88 47	99.66 125	99.69 45	99.92 48	99.67 145	99.77 153	99.75 164	99.61 42	99.98 27	99.35 123	99.98 55	99.72 100
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
HyFIR lowres test		98.91 316	98.64 334	99.73 114	99.85 76	99.47 191	98.07 447	99.83 116	98.64 359	99.89 73	99.60 296	92.57 463	100.00 1	99.33 127	99.97 78	99.72 100

EI-MVSNet-Vis-set		99.47 146	99.49 130	99.42 271	99.57 299	98.66 369	99.24 195	99.46 359	99.67 145	99.79 135	99.65 248	98.97 159	99.89 228	99.15 165	99.89 193	99.71 105

v8		99.68 65	99.69 61	99.65 161	99.80 125	99.40 222	99.66 57	99.76 179	99.64 162	99.93 53	99.85 69	98.66 206	99.84 318	99.88 42	99.99 19	99.71 105

TransMVSNet (Re)		99.78 38	99.77 46	99.81 55	99.91 32	99.85 22	99.75 25	99.86 90	99.70 130	99.91 63	99.89 42	99.60 45	99.87 261	99.59 79	99.74 313	99.71 105

testing915		98.42 379	98.12 401	99.32 318	99.72 204	98.35 407	99.59 80	99.36 392	99.66 152	98.94 418	99.07 458	88.34 511	99.89 228	98.83 223	99.56 387	99.70 108

E5new		99.68 65	99.67 66	99.70 134	99.87 56	99.62 146	99.41 123	99.84 106	99.68 137	99.77 153	99.81 99	99.59 47	99.78 399	99.13 175	99.96 92	99.70 108

E6new		99.68 65	99.67 66	99.70 134	99.86 61	99.62 146	99.41 123	99.84 106	99.68 137	99.77 153	99.81 99	99.59 47	99.78 399	99.13 175	99.96 92	99.70 108

E6		99.68 65	99.67 66	99.70 134	99.86 61	99.62 146	99.41 123	99.84 106	99.68 137	99.77 153	99.81 99	99.59 47	99.78 399	99.13 175	99.96 92	99.70 108

E5		99.68 65	99.67 66	99.70 134	99.87 56	99.62 146	99.41 123	99.84 106	99.68 137	99.77 153	99.81 99	99.59 47	99.78 399	99.13 175	99.96 92	99.70 108

viewmacassd2359aftdt		99.63 87	99.61 90	99.68 142	99.84 82	99.61 156	99.14 235	99.87 81	99.71 123	99.75 167	99.77 146	99.54 56	99.72 442	98.91 217	99.96 92	99.70 108

tt0320-xc		99.82 25	99.82 25	99.82 47	99.82 100	99.84 27	99.82 10	99.92 48	99.94 37	99.94 48	99.93 23	99.34 86	99.92 155	99.70 62	99.96 92	99.70 108

reproduce-ours		99.46 148	99.35 175	99.82 47	99.56 313	99.83 34	99.05 271	99.65 252	99.45 210	99.78 141	99.78 134	98.93 163	99.93 121	98.11 314	99.81 267	99.70 108

our_new_method		99.46 148	99.35 175	99.82 47	99.56 313	99.83 34	99.05 271	99.65 252	99.45 210	99.78 141	99.78 134	98.93 163	99.93 121	98.11 314	99.81 267	99.70 108

test1111		97.74 430	98.16 397	96.49 522	99.60 273	89.86 559	99.71 37	91.21 556	99.89 56	99.88 83	99.87 57	93.73 448	99.90 205	99.56 84	99.99 19	99.70 108

VPA-MVSNet		99.66 78	99.62 86	99.79 73	99.68 243	99.75 80	99.62 67	99.69 228	99.85 72	99.80 128	99.81 99	98.81 179	99.91 186	99.47 101	99.88 204	99.70 108

WR-MVS		99.11 271	98.93 298	99.66 154	99.30 414	99.42 214	98.42 411	99.37 388	99.04 293	99.57 268	99.20 440	96.89 368	99.86 281	98.66 260	99.87 218	99.70 108

ACMH	98.42 6	99.59 102	99.54 117	99.72 123	99.86 61	99.62 146	99.56 88	99.79 153	98.77 343	99.80 128	99.85 69	99.64 36	99.85 300	98.70 254	99.89 193	99.70 108
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E4		99.61 99	99.59 97	99.66 154	99.84 82	99.53 178	99.08 264	99.84 106	99.65 158	99.74 178	99.80 109	99.45 64	99.77 412	98.93 214	99.95 117	99.69 121

pmmvs6		99.86 10	99.86 13	99.83 42	99.94 18	99.90 7	99.83 7	99.91 58	99.85 72	99.94 48	99.95 16	99.73 28	99.90 205	99.65 71	99.97 78	99.69 121

HPM-MVS_fast		99.43 160	99.30 190	99.80 65	99.83 91	99.81 48	99.52 95	99.70 218	98.35 400	99.51 299	99.50 347	99.31 90	99.88 244	98.18 308	99.84 239	99.69 121

LPG-MVS_test		99.22 233	99.05 261	99.74 104	99.82 100	99.63 144	99.16 228	99.73 196	97.56 462	99.64 235	99.69 216	99.37 79	99.89 228	96.66 448	99.87 218	99.69 121

LGP-MVS_train				99.74 104	99.82 100	99.63 144		99.73 196	97.56 462	99.64 235	99.69 216	99.37 79	99.89 228	96.66 448	99.87 218	99.69 121

SteuartSystems-ACMMP		99.30 205	99.14 225	99.76 88	99.87 56	99.66 125	99.18 217	99.60 287	98.55 370	99.57 268	99.67 235	99.03 148	99.94 99	97.01 424	99.80 274	99.69 121
Skip Steuart: Steuart Systems R&D Blog.
MG-MVS		98.52 366	98.39 371	98.94 388	99.15 444	97.39 465	98.18 429	99.21 433	98.89 321	99.23 376	99.63 266	97.37 344	99.74 437	94.22 522	99.61 375	99.69 121

sc_t1		99.81 29	99.80 33	99.82 47	99.88 47	99.88 12	99.83 7	99.79 153	99.94 37	99.93 53	99.92 28	99.35 85	99.92 155	99.64 74	99.94 136	99.68 128

WBMVS		97.50 445	97.18 452	98.48 441	98.85 490	95.89 506	98.44 409	99.52 339	99.53 189	99.52 292	99.42 370	80.10 535	99.86 281	99.24 140	99.95 117	99.68 128

MGCNet		98.61 352	98.30 383	99.52 235	97.88 538	98.95 326	98.76 351	94.11 551	99.84 76	99.32 354	99.57 317	95.57 415	99.95 82	99.68 67	99.98 55	99.68 128

ACMMP_NAP		99.28 209	99.11 235	99.79 73	99.75 184	99.81 48	98.95 314	99.53 334	98.27 412	99.53 290	99.73 177	98.75 192	99.87 261	97.70 360	99.83 247	99.68 128

HFP-MVS		99.25 217	99.08 248	99.76 88	99.73 199	99.70 111	99.31 166	99.59 293	98.36 394	99.36 341	99.37 390	98.80 183	99.91 186	97.43 389	99.75 306	99.68 128

EI-MVSNet		99.38 180	99.44 148	99.21 349	99.58 289	98.09 425	99.26 188	99.46 359	99.62 167	99.75 167	99.67 235	98.54 227	99.85 300	99.15 165	99.92 159	99.68 128

TranMVSNet+NR-MVSNet		99.54 117	99.47 133	99.76 88	99.58 289	99.64 138	99.30 169	99.63 263	99.61 172	99.71 195	99.56 321	98.76 190	99.96 70	99.14 172	99.92 159	99.68 128

PVSNet_Blended_VisFu		99.40 173	99.38 163	99.44 264	99.90 38	98.66 369	98.94 316	99.91 58	97.97 435	99.79 135	99.73 177	99.05 145	99.97 45	99.15 165	99.99 19	99.68 128

IterMVS-LS		99.41 171	99.47 133	99.25 344	99.81 114	98.09 425	98.85 331	99.76 179	99.62 167	99.83 111	99.64 250	98.54 227	99.97 45	99.15 165	99.99 19	99.68 128
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
casdiffseed414692147		99.68 65	99.68 64	99.67 146	99.86 61	99.65 131	99.32 160	99.87 81	99.75 111	99.77 153	99.80 109	99.61 42	99.68 470	99.21 147	99.95 117	99.67 137

aaatest				99.74 104	99.76 166	99.65 131	99.38 134	99.78 166	99.58 183	99.81 121	99.66 241		99.90 205	97.69 366	99.79 280	99.67 137

FE-MVSNET		99.45 152	99.36 171	99.71 129	99.84 82	99.64 138	99.16 228	99.91 58	98.65 357	99.73 184	99.73 177	98.54 227	99.82 364	98.71 252	99.96 92	99.67 137

aaEdge-Enhanced		99.26 215	99.10 244	99.73 114	99.60 273	99.65 131	98.75 355	99.45 364	99.31 242	99.65 229	99.66 241	98.00 303	99.86 281	97.69 366	99.79 280	99.67 137

tt0320		99.79 35	99.79 35	99.81 55	99.82 100	99.84 27	99.82 10	99.90 65	99.94 37	99.94 48	99.94 20	99.07 136	99.92 155	99.68 67	99.97 78	99.67 137

MP-MVS-pluss		99.14 260	98.92 302	99.80 65	99.83 91	99.83 34	98.61 374	99.63 263	96.84 499	99.44 316	99.58 309	98.81 179	99.91 186	97.70 360	99.82 257	99.67 137
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R		99.23 224	99.05 261	99.77 81	99.76 166	99.70 111	99.31 166	99.59 293	98.41 387	99.32 354	99.36 395	98.73 196	99.93 121	97.29 400	99.74 313	99.67 137

XVS		99.27 213	99.11 235	99.75 99	99.71 210	99.71 103	99.37 142	99.61 275	99.29 244	98.76 443	99.47 360	98.47 241	99.88 244	97.62 374	99.73 320	99.67 137

v1240		99.56 107	99.58 101	99.51 239	99.80 125	99.00 315	99.00 294	99.65 252	99.15 280	99.90 68	99.75 164	99.09 128	99.88 244	99.90 38	99.96 92	99.67 137

X-MVStestdata		96.09 490	94.87 507	99.75 99	99.71 210	99.71 103	99.37 142	99.61 275	99.29 244	98.76 443	61.30 568	98.47 241	99.88 244	97.62 374	99.73 320	99.67 137

VPNet		99.46 148	99.37 166	99.71 129	99.82 100	99.59 162	99.48 110	99.70 218	99.81 92	99.69 203	99.58 309	97.66 330	99.86 281	99.17 160	99.44 416	99.67 137

ACMMPR		99.23 224	99.06 254	99.76 88	99.74 195	99.69 116	99.31 166	99.59 293	98.36 394	99.35 345	99.38 386	98.61 212	99.93 121	97.43 389	99.75 306	99.67 137

SixPastTwentyTwo		99.42 164	99.30 190	99.76 88	99.92 30	99.67 122	99.70 38	99.14 445	99.65 158	99.89 73	99.90 37	96.20 400	99.94 99	99.42 112	99.92 159	99.67 137

HPM-MVS		99.25 217	99.07 252	99.78 77	99.81 114	99.75 80	99.61 73	99.67 237	97.72 457	99.35 345	99.25 425	99.23 104	99.92 155	97.21 412	99.82 257	99.67 137
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
lecture		99.56 107	99.48 131	99.81 55	99.78 148	99.86 18	99.50 103	99.70 218	99.59 181	99.75 167	99.71 197	98.94 162	99.92 155	98.59 267	99.76 298	99.66 151

v144192		99.55 112	99.54 117	99.58 203	99.78 148	99.20 279	99.11 252	99.62 267	99.18 265	99.89 73	99.72 187	98.66 206	99.87 261	99.88 42	99.97 78	99.66 151

v1921920		99.56 107	99.57 106	99.55 222	99.75 184	99.11 297	99.05 271	99.61 275	99.15 280	99.88 83	99.71 197	99.08 133	99.87 261	99.90 38	99.97 78	99.66 151

v1192		99.57 103	99.57 106	99.57 211	99.77 161	99.22 272	99.04 276	99.60 287	99.18 265	99.87 93	99.72 187	99.08 133	99.85 300	99.89 41	99.98 55	99.66 151

PGM-MVS		99.20 240	99.01 276	99.77 81	99.75 184	99.71 103	99.16 228	99.72 205	97.99 433	99.42 323	99.60 296	98.81 179	99.93 121	96.91 431	99.74 313	99.66 151

mPP-MVS		99.19 243	99.00 280	99.76 88	99.76 166	99.68 119	99.38 134	99.54 323	98.34 404	99.01 412	99.50 347	98.53 232	99.93 121	97.18 417	99.78 288	99.66 151

CP-MVS		99.23 224	99.05 261	99.75 99	99.66 253	99.66 125	99.38 134	99.62 267	98.38 392	99.06 407	99.27 419	98.79 184	99.94 99	97.51 384	99.82 257	99.66 151

EG-PatchMatch MVS		99.57 103	99.56 111	99.62 185	99.77 161	99.33 243	99.26 188	99.76 179	99.32 240	99.80 128	99.78 134	99.29 92	99.87 261	99.15 165	99.91 173	99.66 151

UGNet		99.38 180	99.34 177	99.49 245	98.90 481	98.90 337	99.70 38	99.35 394	99.86 66	98.57 461	99.81 99	98.50 239	99.93 121	99.38 116	99.98 55	99.66 151
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
viewdifsd2359ckpt11		99.62 95	99.64 80	99.56 215	99.86 61	99.19 282	99.02 283	99.93 44	99.83 82	99.88 83	99.81 99	98.99 153	99.83 341	99.48 98	99.96 92	99.65 160

viewmsd2359difaftdt		99.62 95	99.64 80	99.56 215	99.86 61	99.19 282	99.02 283	99.93 44	99.83 82	99.88 83	99.81 99	98.99 153	99.83 341	99.48 98	99.96 92	99.65 160

SDMVSNet		99.77 45	99.77 46	99.76 88	99.80 125	99.65 131	99.63 64	99.86 90	99.97 26	99.89 73	99.89 42	99.52 61	99.99 7	99.42 112	99.96 92	99.65 160

sd_testset		99.78 38	99.78 40	99.80 65	99.80 125	99.76 71	99.80 14	99.79 153	99.97 26	99.89 73	99.89 42	99.53 59	99.99 7	99.36 120	99.96 92	99.65 160

test2506		94.73 510	94.59 511	95.15 530	99.59 279	85.90 561	99.75 25	74.01 564	99.89 56	99.71 195	99.86 64	79.00 543	99.90 205	99.52 92	99.99 19	99.65 160

ECVR-MVS		97.73 431	98.04 406	96.78 514	99.59 279	90.81 553	99.72 33	90.43 558	99.89 56	99.86 97	99.86 64	93.60 450	99.89 228	99.46 102	99.99 19	99.65 160

h-mvs33		98.61 352	98.34 378	99.44 264	99.60 273	98.67 366	99.27 183	99.44 365	99.68 137	99.32 354	99.49 352	92.50 467	100.00 1	99.24 140	96.51 543	99.65 160

TSAR-MVS + MP.		99.34 197	99.24 210	99.63 176	99.82 100	99.37 233	99.26 188	99.35 394	98.77 343	99.57 268	99.70 207	99.27 97	99.88 244	97.71 357	99.75 306	99.65 160
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MTAPA		99.35 192	99.20 215	99.80 65	99.81 114	99.81 48	99.33 157	99.53 334	99.27 248	99.42 323	99.63 266	98.21 279	99.95 82	97.82 347	99.79 280	99.65 160

MCST-MVS		99.02 292	98.81 318	99.65 161	99.58 289	99.49 186	98.58 381	99.07 449	98.40 389	99.04 409	99.25 425	98.51 238	99.80 391	97.31 397	99.51 403	99.65 160

UniMVSNet_NR-MVSNet		99.37 185	99.25 208	99.72 123	99.47 359	99.56 171	98.97 307	99.61 275	99.43 219	99.67 218	99.28 417	97.85 312	99.95 82	99.17 160	99.81 267	99.65 160

casdiffmvs_mvg		99.68 65	99.68 64	99.69 140	99.81 114	99.59 162	99.29 177	99.90 65	99.71 123	99.79 135	99.73 177	99.54 56	99.84 318	99.36 120	99.96 92	99.65 160
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SymmetryMVS		99.01 298	98.82 316	99.58 203	99.65 257	99.11 297	99.36 146	99.20 436	99.82 86	99.68 210	99.53 336	93.30 452	99.99 7	99.24 140	99.63 365	99.64 172

ZNCC-MVS		99.22 233	99.04 267	99.77 81	99.76 166	99.73 92	99.28 179	99.56 310	98.19 417	99.14 395	99.29 415	98.84 178	99.92 155	97.53 383	99.80 274	99.64 172

v1144		99.54 117	99.53 121	99.59 199	99.79 139	99.28 252	99.10 256	99.61 275	99.20 262	99.84 105	99.73 177	98.67 204	99.84 318	99.86 46	99.98 55	99.64 172

v2v482		99.50 128	99.47 133	99.58 203	99.78 148	99.25 261	99.14 235	99.58 302	99.25 253	99.81 121	99.62 276	98.24 273	99.84 318	99.83 47	99.97 78	99.64 172

K. test v3		98.87 324	98.60 338	99.69 140	99.93 24	99.46 199	99.74 27	94.97 546	99.78 103	99.88 83	99.88 51	93.66 449	99.97 45	99.61 77	99.95 117	99.64 172

DeepC-MVS	98.90 4	99.62 95	99.61 90	99.67 146	99.72 204	99.44 207	99.24 195	99.71 209	99.27 248	99.93 53	99.90 37	99.70 32	99.93 121	98.99 198	99.99 19	99.64 172
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FE-MVSNET2		99.68 65	99.67 66	99.72 123	99.86 61	99.68 119	99.46 117	99.88 75	99.62 167	99.87 93	99.85 69	99.06 143	99.85 300	99.44 105	99.98 55	99.63 178

mvsany_test1		99.44 156	99.45 143	99.40 284	99.37 386	98.64 376	97.90 468	99.59 293	99.27 248	99.92 60	99.82 92	99.74 27	99.93 121	99.55 86	99.87 218	99.63 178

SMA-MVS		99.19 243	99.00 280	99.73 114	99.46 363	99.73 92	99.13 242	99.52 339	97.40 474	99.57 268	99.64 250	98.93 163	99.83 341	97.61 376	99.79 280	99.63 178
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
IterMVS-SCA-FT		99.00 301	99.16 220	98.51 439	99.75 184	95.90 505	98.07 447	99.84 106	99.84 76	99.89 73	99.73 177	96.01 405	99.99 7	99.33 127	100.00 1	99.63 178

pm-mvs1		99.79 35	99.79 35	99.78 77	99.91 32	99.83 34	99.76 23	99.87 81	99.73 113	99.89 73	99.87 57	99.63 38	99.87 261	99.54 88	99.92 159	99.63 178

MP-MVS		99.06 281	98.83 315	99.76 88	99.76 166	99.71 103	99.32 160	99.50 348	98.35 400	98.97 415	99.48 356	98.37 257	99.92 155	95.95 489	99.75 306	99.63 178
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DU-MVS		99.33 200	99.21 214	99.71 129	99.43 371	99.56 171	98.83 337	99.53 334	99.38 230	99.67 218	99.36 395	97.67 326	99.95 82	99.17 160	99.81 267	99.63 178

NR-MVSNet		99.40 173	99.31 185	99.68 142	99.43 371	99.55 175	99.73 30	99.50 348	99.46 207	99.88 83	99.36 395	97.54 335	99.87 261	98.97 202	99.87 218	99.63 178

IterMVS		98.97 305	99.16 220	98.42 444	99.74 195	95.64 512	98.06 449	99.83 116	99.83 82	99.85 102	99.74 171	96.10 404	99.99 7	99.27 139	100.00 1	99.63 178
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EPP-MVSNet		99.17 252	99.00 280	99.66 154	99.80 125	99.43 211	99.70 38	99.24 426	99.48 199	99.56 276	99.77 146	94.89 429	99.93 121	98.72 250	99.89 193	99.63 178

ACMMP		99.25 217	99.08 248	99.74 104	99.79 139	99.68 119	99.50 103	99.65 252	98.07 428	99.52 292	99.69 216	98.57 218	99.92 155	97.18 417	99.79 280	99.63 178
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
DeepC-MVS_fast	98.47 5	99.23 224	99.12 232	99.56 215	99.28 419	99.22 272	98.99 302	99.40 379	99.08 288	99.58 265	99.64 250	98.90 172	99.83 341	97.44 388	99.75 306	99.63 178
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
Casviewmamba		99.63 87	99.60 94	99.73 114	99.84 82	99.72 97	99.36 146	99.87 81	99.67 145	99.74 178	99.73 177	99.07 136	99.83 341	99.14 172	99.93 150	99.62 190

usedtu_dtu_shiyan2		99.44 156	99.33 182	99.78 77	99.86 61	99.76 71	99.54 91	99.79 153	99.66 152	99.66 225	99.79 121	96.76 373	99.96 70	99.15 165	99.72 328	99.62 190

E2		99.54 117	99.51 123	99.62 185	99.78 148	99.47 191	99.01 288	99.82 123	99.55 185	99.69 203	99.77 146	99.26 98	99.76 419	98.82 226	99.93 150	99.62 190

E3		99.54 117	99.51 123	99.62 185	99.78 148	99.47 191	99.01 288	99.82 123	99.55 185	99.69 203	99.77 146	99.25 102	99.76 419	98.82 226	99.93 150	99.62 190

diffmvs_AUTHOR		99.48 136	99.48 131	99.47 253	99.80 125	98.89 340	98.71 363	99.82 123	99.79 100	99.66 225	99.63 266	98.87 175	99.88 244	99.13 175	99.95 117	99.62 190

DVP-MVS++		99.38 180	99.25 208	99.77 81	99.03 469	99.77 64	99.74 27	99.61 275	99.18 265	99.76 162	99.61 286	99.00 151	99.92 155	97.72 355	99.60 378	99.62 190

PC_three_1452									97.56 462	99.68 210	99.41 372	99.09 128	97.09 551	96.66 448	99.60 378	99.62 190

GeoE		99.69 60	99.66 73	99.78 77	99.76 166	99.76 71	99.60 79	99.82 123	99.46 207	99.75 167	99.56 321	99.63 38	99.95 82	99.43 107	99.88 204	99.62 190

test_method		91.72 515	92.32 516	89.91 535	93.49 560	70.18 564	90.28 550	99.56 310	61.71 556	95.39 543	99.52 340	93.90 443	99.94 99	98.76 241	98.27 511	99.62 190

GST-MVS		99.16 255	98.96 294	99.75 99	99.73 199	99.73 92	99.20 207	99.55 317	98.22 414	99.32 354	99.35 400	98.65 208	99.91 186	96.86 434	99.74 313	99.62 190

new-patchmatchnet		99.35 192	99.57 106	98.71 428	99.82 100	96.62 487	98.55 389	99.75 185	99.50 194	99.88 83	99.87 57	99.31 90	99.88 244	99.43 107	100.00 1	99.62 190

CPTT-MVS		98.74 339	98.44 364	99.64 168	99.61 270	99.38 228	99.18 217	99.55 317	96.49 504	99.27 366	99.37 390	97.11 359	99.92 155	95.74 499	99.67 355	99.62 190

MIMVSNet1		99.66 78	99.62 86	99.80 65	99.94 18	99.87 15	99.69 45	99.77 171	99.78 103	99.93 53	99.89 42	97.94 305	99.92 155	99.65 71	99.98 55	99.62 190

DeepPCF-MVS	98.42 6	99.18 247	99.02 270	99.67 146	99.22 430	99.75 80	97.25 505	99.47 356	98.72 348	99.66 225	99.70 207	99.29 92	99.63 492	98.07 319	99.81 267	99.62 190

3Dnovator+	98.92 3	99.35 192	99.24 210	99.67 146	99.35 393	99.47 191	99.62 67	99.50 348	99.44 212	99.12 399	99.78 134	98.77 189	99.94 99	97.87 337	99.72 328	99.62 190

hybridcas		99.65 84	99.63 83	99.70 134	99.85 76	99.67 122	99.30 169	99.87 81	99.67 145	99.81 121	99.77 146	99.21 106	99.81 381	99.24 140	99.94 136	99.61 205

DVP-MVS		99.32 202	99.17 219	99.77 81	99.69 234	99.80 52	99.14 235	99.31 409	99.16 274	99.62 250	99.61 286	98.35 259	99.91 186	97.88 334	99.72 328	99.61 205
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
APD-MVS		98.87 324	98.59 340	99.71 129	99.50 343	99.62 146	99.01 288	99.57 305	96.80 501	99.54 285	99.63 266	98.29 268	99.91 186	95.24 508	99.71 332	99.61 205
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		98.82 330	98.57 344	99.58 203	99.21 432	99.31 247	98.61 374	99.25 422	98.65 357	98.43 469	99.26 423	97.86 310	99.81 381	96.55 455	99.27 442	99.61 205

TAMVS		99.49 133	99.45 143	99.63 176	99.48 353	99.42 214	99.45 118	99.57 305	99.66 152	99.78 141	99.83 84	97.85 312	99.86 281	99.44 105	99.96 92	99.61 205

HPM-MVS++		98.96 308	98.70 331	99.74 104	99.52 335	99.71 103	98.86 329	99.19 437	98.47 383	98.59 458	99.06 460	98.08 294	99.91 186	96.94 429	99.60 378	99.60 210

V42		99.56 107	99.54 117	99.63 176	99.79 139	99.46 199	99.39 131	99.59 293	99.24 255	99.86 97	99.70 207	98.55 222	99.82 364	99.79 54	99.95 117	99.60 210

HQP_MVS		98.90 319	98.68 332	99.55 222	99.58 289	99.24 266	98.80 345	99.54 323	98.94 308	99.14 395	99.25 425	97.24 349	99.82 364	95.84 494	99.78 288	99.60 210

plane_prior5								99.54 323					99.82 364	95.84 494	99.78 288	99.60 210

TDRefinement		99.72 54	99.70 58	99.77 81	99.90 38	99.85 22	99.86 6	99.92 48	99.69 133	99.78 141	99.92 28	99.37 79	99.88 244	98.93 214	99.95 117	99.60 210

ACMH+	98.40 8	99.50 128	99.43 151	99.71 129	99.86 61	99.76 71	99.32 160	99.77 171	99.53 189	99.77 153	99.76 156	99.26 98	99.78 399	97.77 348	99.88 204	99.60 210

ACMM	98.09 11	99.46 148	99.38 163	99.72 123	99.80 125	99.69 116	99.13 242	99.65 252	98.99 300	99.64 235	99.72 187	99.39 72	99.86 281	98.23 301	99.81 267	99.60 210
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
dtuonlycased		99.24 221	99.47 133	98.56 438	99.90 38	96.17 499	97.62 486	99.85 96	99.66 152	99.86 97	99.50 347	99.39 72	99.93 121	99.55 86	99.85 233	99.59 217

VDDNet		98.97 305	98.82 316	99.42 271	99.71 210	98.81 352	99.62 67	98.68 473	99.81 92	99.38 338	99.80 109	94.25 440	99.85 300	98.79 233	99.32 434	99.59 217

casdiffmvs		99.63 87	99.61 90	99.67 146	99.79 139	99.59 162	99.13 242	99.85 96	99.79 100	99.76 162	99.72 187	99.33 88	99.82 364	99.21 147	99.94 136	99.59 217
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UniMVSNet (Re)		99.37 185	99.26 204	99.68 142	99.51 337	99.58 167	98.98 305	99.60 287	99.43 219	99.70 199	99.36 395	97.70 322	99.88 244	99.20 151	99.87 218	99.59 217

DSMNet-mixed		99.48 136	99.65 75	98.95 387	99.71 210	97.27 469	99.50 103	99.82 123	99.59 181	99.41 329	99.85 69	99.62 41	100.00 1	99.53 91	99.89 193	99.59 217

3Dnovator	99.15 2	99.43 160	99.36 171	99.65 161	99.39 380	99.42 214	99.70 38	99.56 310	99.23 257	99.35 345	99.80 109	99.17 112	99.95 82	98.21 303	99.84 239	99.59 217

DKM-HiRes		98.95 311	98.73 324	99.62 185	99.82 100	99.47 191	98.50 398	99.81 136	99.41 224	97.76 511	99.58 309	95.04 427	99.83 341	98.89 218	99.76 298	99.58 223

viewmanbaseed2359cas		99.50 128	99.47 133	99.61 192	99.73 199	99.52 183	99.03 279	99.83 116	99.49 196	99.65 229	99.64 250	99.18 110	99.71 447	98.73 248	99.92 159	99.58 223

SED-MVS		99.40 173	99.28 199	99.77 81	99.69 234	99.82 42	99.20 207	99.54 323	99.13 282	99.82 114	99.63 266	98.91 169	99.92 155	97.85 341	99.70 335	99.58 223

OPU-MVS				99.29 328	99.12 449	99.44 207	99.20 207				99.40 378	99.00 151	98.84 541	96.54 456	99.60 378	99.58 223

EPNet		98.13 408	97.77 429	99.18 355	94.57 559	97.99 431	99.24 195	97.96 511	99.74 112	97.29 523	99.62 276	93.13 456	99.97 45	98.59 267	99.83 247	99.58 223
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IS-MVSNet		99.03 289	98.85 311	99.55 222	99.80 125	99.25 261	99.73 30	99.15 443	99.37 231	99.61 257	99.71 197	94.73 433	99.81 381	97.70 360	99.88 204	99.58 223

ACMP	97.51 14	99.05 285	98.84 313	99.67 146	99.78 148	99.55 175	98.88 325	99.66 242	97.11 490	99.47 309	99.60 296	99.07 136	99.89 228	96.18 478	99.85 233	99.58 223
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
dtuplus		99.52 123	99.55 113	99.43 268	99.76 166	98.90 337	98.71 363	99.89 69	99.67 145	99.79 135	99.77 146	99.25 102	99.81 381	99.18 156	99.96 92	99.57 230

viewcassd2359sk11		99.48 136	99.45 143	99.58 203	99.73 199	99.42 214	98.96 311	99.80 144	99.44 212	99.63 240	99.74 171	99.09 128	99.76 419	98.72 250	99.91 173	99.57 230

SR-MVS		99.19 243	99.00 280	99.74 104	99.51 337	99.72 97	99.18 217	99.60 287	98.85 325	99.47 309	99.58 309	98.38 256	99.92 155	96.92 430	99.54 397	99.57 230

lessismore_v0				99.64 168	99.86 61	99.38 228		90.66 557		99.89 73	99.83 84	94.56 436	99.97 45	99.56 84	99.92 159	99.57 230

viewdifsd2359ckpt07		99.51 125	99.50 126	99.52 235	99.80 125	99.19 282	98.92 320	99.88 75	99.72 117	99.64 235	99.62 276	99.06 143	99.81 381	98.96 205	99.94 136	99.56 234

pmmvs5		99.19 243	99.11 235	99.42 271	99.76 166	98.88 342	98.55 389	99.73 196	98.82 332	99.72 190	99.62 276	96.56 379	99.82 364	99.32 129	99.95 117	99.56 234

APD-MVS_3200maxsize		99.31 204	99.16 220	99.74 104	99.53 328	99.75 80	99.27 183	99.61 275	99.19 264	99.57 268	99.64 250	98.76 190	99.90 205	97.29 400	99.62 367	99.56 234

CDPH-MVS		98.56 361	98.20 392	99.61 192	99.50 343	99.46 199	98.32 419	99.41 372	95.22 523	99.21 382	99.10 455	98.34 261	99.82 364	95.09 512	99.66 358	99.56 234

dtuonly		98.93 315	99.11 235	98.38 447	99.72 204	95.75 509	97.07 515	99.91 58	99.04 293	99.65 229	99.41 372	98.32 265	99.83 341	98.97 202	99.90 177	99.55 238

viewdifsd2359ckpt13		99.42 164	99.37 166	99.57 211	99.72 204	99.46 199	99.01 288	99.80 144	99.20 262	99.51 299	99.60 296	98.92 166	99.70 451	98.65 263	99.90 177	99.55 238

BP-MVS1		98.72 342	98.46 359	99.50 241	99.53 328	99.00 315	99.34 151	98.52 483	99.65 158	99.73 184	99.38 386	90.62 495	99.96 70	99.50 96	99.86 226	99.55 238

Anonymous20240521		99.44 156	99.42 154	99.49 245	99.89 41	98.96 325	99.62 67	99.76 179	99.85 72	99.82 114	99.88 51	96.39 389	99.97 45	99.59 79	99.98 55	99.55 238

our_test_3		98.85 328	99.09 246	98.13 462	99.66 253	94.90 526	97.72 477	99.58 302	99.07 290	99.64 235	99.62 276	98.19 282	99.93 121	98.41 285	99.95 117	99.55 238

YYNet1		98.95 311	98.99 287	98.84 411	99.64 259	97.14 474	98.22 427	99.32 405	98.92 316	99.59 263	99.66 241	97.40 341	99.83 341	98.27 297	99.90 177	99.55 238

MDA-MVSNet_test_wron		98.95 311	98.99 287	98.85 409	99.64 259	97.16 472	98.23 426	99.33 403	98.93 313	99.56 276	99.66 241	97.39 343	99.83 341	98.29 294	99.88 204	99.55 238

MVSFormer		99.41 171	99.44 148	99.31 323	99.57 299	98.40 401	99.77 19	99.80 144	99.73 113	99.63 240	99.30 411	98.02 298	99.98 27	99.43 107	99.69 344	99.55 238

jason		99.16 255	99.11 235	99.32 318	99.75 184	98.44 398	98.26 424	99.39 382	98.70 351	99.74 178	99.30 411	98.54 227	99.97 45	98.48 277	99.82 257	99.55 238
jason: jason.
CDS-MVSNet		99.22 233	99.13 228	99.50 241	99.35 393	99.11 297	98.96 311	99.54 323	99.46 207	99.61 257	99.70 207	96.31 393	99.83 341	99.34 124	99.88 204	99.55 238
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RoMa-HiRes		99.38 180	99.30 190	99.64 168	99.81 114	99.47 191	99.11 252	99.94 42	99.03 295	99.55 281	99.56 321	97.71 321	99.92 155	99.19 153	99.77 293	99.54 248

viewmamba		99.49 133	99.51 123	99.42 271	99.75 184	98.90 337	98.85 331	99.85 96	99.69 133	99.73 184	99.67 235	98.79 184	99.82 364	99.28 137	99.95 117	99.54 248

hybridnocas07		99.43 160	99.44 148	99.39 287	99.75 184	98.85 348	98.76 351	99.85 96	99.71 123	99.70 199	99.68 229	98.47 241	99.77 412	99.13 175	99.95 117	99.54 248

hybrid		99.42 164	99.43 151	99.37 296	99.75 184	98.77 358	98.72 359	99.84 106	99.61 172	99.65 229	99.68 229	98.53 232	99.79 395	99.16 164	99.94 136	99.54 248

viewmambaseed2359dif		99.47 146	99.50 126	99.37 296	99.70 226	98.80 355	98.67 367	99.92 48	99.49 196	99.77 153	99.71 197	99.08 133	99.78 399	99.20 151	99.94 136	99.54 248

SR-MVS-dyc-post		99.27 213	99.11 235	99.73 114	99.54 319	99.74 88	99.26 188	99.62 267	99.16 274	99.52 292	99.64 250	98.41 251	99.91 186	97.27 403	99.61 375	99.54 248

RE-MVS-def			99.13 228		99.54 319	99.74 88	99.26 188	99.62 267	99.16 274	99.52 292	99.64 250	98.57 218		97.27 403	99.61 375	99.54 248

SD-MVS		99.01 298	99.30 190	98.15 461	99.50 343	99.40 222	98.94 316	99.61 275	99.22 261	99.75 167	99.82 92	99.54 56	95.51 555	97.48 385	99.87 218	99.54 248
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
CNVR-MVS		98.99 304	98.80 321	99.56 215	99.25 425	99.43 211	98.54 392	99.27 417	98.58 367	98.80 438	99.43 368	98.53 232	99.70 451	97.22 411	99.59 382	99.54 248

MVS_111021_HR		99.12 266	99.02 270	99.40 284	99.50 343	99.11 297	97.92 465	99.71 209	98.76 346	99.08 403	99.47 360	99.17 112	99.54 507	97.85 341	99.76 298	99.54 248

COLMAP_ROB	98.06 12	99.45 152	99.37 166	99.70 134	99.83 91	99.70 111	99.38 134	99.78 166	99.53 189	99.67 218	99.78 134	99.19 109	99.86 281	97.32 396	99.87 218	99.54 248
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
E3new		99.42 164	99.37 166	99.56 215	99.68 243	99.38 228	98.93 319	99.79 153	99.30 243	99.55 281	99.69 216	98.88 173	99.76 419	98.63 265	99.89 193	99.53 259

v148		99.40 173	99.41 158	99.39 287	99.76 166	98.94 328	99.09 261	99.59 293	99.17 272	99.81 121	99.61 286	98.41 251	99.69 458	99.32 129	99.94 136	99.53 259

diffmvs		99.34 197	99.32 183	99.39 287	99.67 250	98.77 358	98.57 385	99.81 136	99.61 172	99.48 307	99.41 372	98.47 241	99.86 281	98.97 202	99.90 177	99.53 259
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.63 87	99.62 86	99.66 154	99.80 125	99.62 146	99.44 120	99.80 144	99.71 123	99.72 190	99.69 216	99.15 116	99.83 341	99.32 129	99.94 136	99.53 259

HQP4-MVS										98.15 486			99.70 451			99.53 259

GBi-Net		99.42 164	99.31 185	99.73 114	99.49 348	99.77 64	99.68 48	99.70 218	99.44 212	99.62 250	99.83 84	97.21 352	99.90 205	98.96 205	99.90 177	99.53 259

test1		99.42 164	99.31 185	99.73 114	99.49 348	99.77 64	99.68 48	99.70 218	99.44 212	99.62 250	99.83 84	97.21 352	99.90 205	98.96 205	99.90 177	99.53 259

FMVSNet1		99.66 78	99.63 83	99.73 114	99.78 148	99.77 64	99.68 48	99.70 218	99.67 145	99.82 114	99.83 84	98.98 157	99.90 205	99.24 140	99.97 78	99.53 259

HQP-MVS		98.36 385	98.02 408	99.39 287	99.31 410	98.94 328	97.98 458	99.37 388	97.45 470	98.15 486	98.83 489	96.67 375	99.70 451	94.73 515	99.67 355	99.53 259

QAPM		98.40 383	97.99 409	99.65 161	99.39 380	99.47 191	99.67 53	99.52 339	91.70 544	98.78 442	99.80 109	98.55 222	99.95 82	94.71 517	99.75 306	99.53 259

F-COLMAP		98.74 339	98.45 362	99.62 185	99.57 299	99.47 191	98.84 334	99.65 252	96.31 508	98.93 420	99.19 442	97.68 325	99.87 261	96.52 457	99.37 427	99.53 259

onestephybrid01		99.45 152	99.46 139	99.42 271	99.69 234	98.88 342	98.76 351	99.81 136	99.78 103	99.67 218	99.73 177	98.61 212	99.84 318	99.17 160	99.93 150	99.52 270

MVSTER		98.47 373	98.22 390	99.24 346	99.06 462	98.35 407	99.08 264	99.46 359	99.27 248	99.75 167	99.66 241	88.61 509	99.85 300	99.14 172	99.92 159	99.52 270

PVSNet_BlendedMVS		99.03 289	99.01 276	99.09 368	99.54 319	97.99 431	98.58 381	99.82 123	97.62 461	99.34 349	99.71 197	98.52 236	99.77 412	97.98 325	99.97 78	99.52 270

viewdifsd2359ckpt09		99.24 221	99.16 220	99.49 245	99.70 226	99.22 272	98.88 325	99.81 136	98.70 351	99.38 338	99.37 390	98.22 278	99.76 419	98.48 277	99.88 204	99.51 273

OPM-MVS		99.26 215	99.13 228	99.63 176	99.70 226	99.61 156	98.58 381	99.48 353	98.50 379	99.52 292	99.63 266	99.14 119	99.76 419	97.89 333	99.77 293	99.51 273
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
AllTest		99.21 238	99.07 252	99.63 176	99.78 148	99.64 138	99.12 247	99.83 116	98.63 360	99.63 240	99.72 187	98.68 201	99.75 430	96.38 468	99.83 247	99.51 273

TestCases				99.63 176	99.78 148	99.64 138		99.83 116	98.63 360	99.63 240	99.72 187	98.68 201	99.75 430	96.38 468	99.83 247	99.51 273

BH-RMVSNet		98.41 381	98.14 399	99.21 349	99.21 432	98.47 394	98.60 376	98.26 501	98.35 400	98.93 420	99.31 408	97.20 355	99.66 481	94.32 520	99.10 457	99.51 273

USDC		98.96 308	98.93 298	99.05 377	99.54 319	97.99 431	97.07 515	99.80 144	98.21 415	99.75 167	99.77 146	98.43 248	99.64 490	97.90 332	99.88 204	99.51 273

test9_res														95.10 511	99.44 416	99.50 279

train_agg		98.35 388	97.95 413	99.57 211	99.35 393	99.35 240	98.11 442	99.41 372	94.90 528	97.92 498	98.99 470	98.02 298	99.85 300	95.38 506	99.44 416	99.50 279

agg_prior2														94.58 518	99.46 415	99.50 279

VDD-MVS		99.20 240	99.11 235	99.44 264	99.43 371	98.98 319	99.50 103	98.32 499	99.80 96	99.56 276	99.69 216	96.99 365	99.85 300	98.99 198	99.73 320	99.50 279

MDA-MVSNet-bldmvs		99.06 281	99.05 261	99.07 374	99.80 125	97.83 442	98.89 323	99.72 205	99.29 244	99.63 240	99.70 207	96.47 384	99.89 228	98.17 310	99.82 257	99.50 279

KD-MVS_self_test		99.63 87	99.59 97	99.76 88	99.84 82	99.90 7	99.37 142	99.79 153	99.83 82	99.88 83	99.85 69	98.42 250	99.90 205	99.60 78	99.73 320	99.49 284

SF-MVS		99.10 274	98.93 298	99.62 185	99.58 289	99.51 184	99.13 242	99.65 252	97.97 435	99.42 323	99.61 286	98.86 176	99.87 261	96.45 465	99.68 349	99.49 284

Anonymous20240529		99.42 164	99.34 177	99.65 161	99.53 328	99.60 160	99.63 64	99.39 382	99.47 204	99.76 162	99.78 134	98.13 287	99.86 281	98.70 254	99.68 349	99.49 284

WTY-MVS		98.59 358	98.37 373	99.26 341	99.43 371	98.40 401	98.74 356	99.13 447	98.10 423	99.21 382	99.24 431	94.82 431	99.90 205	97.86 339	98.77 483	99.49 284

ppachtmachnet_test		98.89 322	99.12 232	98.20 460	99.66 253	95.24 521	97.63 484	99.68 232	99.08 288	99.78 141	99.62 276	98.65 208	99.88 244	98.02 320	99.96 92	99.48 288

Anonymous20231206		99.35 192	99.31 185	99.47 253	99.74 195	99.06 309	99.28 179	99.74 191	99.23 257	99.72 190	99.53 336	97.63 334	99.88 244	99.11 181	99.84 239	99.48 288

test_prior				99.46 257	99.35 393	99.22 272		99.39 382					99.69 458			99.48 288

test12				99.54 228	99.29 416	99.33 243		99.16 442		98.43 469		97.54 335	99.82 364		99.47 411	99.48 288

blended_shiyan8		97.82 425	97.45 440	98.92 393	98.06 534	97.45 460	97.73 475	99.35 394	97.96 438	98.35 473	97.34 537	92.76 462	99.84 318	99.04 190	96.49 545	99.47 292

VNet		99.18 247	99.06 254	99.56 215	99.24 427	99.36 237	99.33 157	99.31 409	99.67 145	99.47 309	99.57 317	96.48 383	99.84 318	99.15 165	99.30 436	99.47 292

test20.03		99.55 112	99.54 117	99.58 203	99.79 139	99.37 233	99.02 283	99.89 69	99.60 179	99.82 114	99.62 276	98.81 179	99.89 228	99.43 107	99.86 226	99.47 292

114514_t		98.49 371	98.11 402	99.64 168	99.73 199	99.58 167	99.24 195	99.76 179	89.94 547	99.42 323	99.56 321	97.76 320	99.86 281	97.74 353	99.82 257	99.47 292

sss		98.90 319	98.77 323	99.27 337	99.48 353	98.44 398	98.72 359	99.32 405	97.94 441	99.37 340	99.35 400	96.31 393	99.91 186	98.85 221	99.63 365	99.47 292

blended_shiyan6		97.82 425	97.46 438	98.92 393	98.08 533	97.46 458	97.73 475	99.34 398	97.96 438	98.33 474	97.35 536	92.77 461	99.84 318	99.04 190	96.53 539	99.46 297

旧先验1					99.49 348	99.29 250		99.26 419			99.39 383	97.67 326			99.36 428	99.46 297

wanda-best-256-512		97.53 442	97.14 454	98.72 424	97.71 540	96.86 482	97.00 517	99.34 398	97.73 455	98.18 481	96.82 550	91.92 471	99.84 318	99.02 194	96.53 539	99.45 299

FE-blended-shiyan7		97.53 442	97.14 454	98.72 424	97.71 540	96.86 482	97.00 517	99.34 398	97.73 455	98.18 481	96.82 550	91.92 471	99.84 318	99.02 194	96.53 539	99.45 299

usedtu_blend_shiyan5		97.97 419	97.65 436	98.92 393	97.71 540	97.49 455	99.53 93	99.81 136	99.52 193	98.18 481	96.82 550	91.92 471	99.83 341	98.79 233	96.53 539	99.45 299

mamba_0408		99.54 117	99.55 113	99.54 228	99.71 210	99.24 266	99.27 183	99.79 153	99.72 117	99.78 141	99.64 250	99.36 82	99.93 121	98.74 243	99.90 177	99.45 299

icg_test_0407_2		99.30 205	99.29 196	99.31 323	99.71 210	98.55 387	98.17 432	99.71 209	99.41 224	99.73 184	99.60 296	99.17 112	99.92 155	98.45 280	99.70 335	99.45 299

SSM_04072		99.55 112	99.55 113	99.55 222	99.71 210	99.24 266	99.27 183	99.79 153	99.72 117	99.78 141	99.64 250	99.36 82	99.97 45	98.74 243	99.90 177	99.45 299

SSM_0407		99.56 107	99.56 111	99.54 228	99.71 210	99.24 266	99.15 231	99.84 106	99.80 96	99.78 141	99.70 207	99.44 66	99.93 121	98.74 243	99.90 177	99.45 299

IMVS_0407		99.38 180	99.42 154	99.28 331	99.71 210	98.55 387	99.27 183	99.71 209	99.41 224	99.73 184	99.60 296	99.17 112	99.83 341	98.45 280	99.70 335	99.45 299

IMVS_0404		99.23 224	99.20 215	99.32 318	99.71 210	98.55 387	98.57 385	99.71 209	99.41 224	99.52 292	99.60 296	98.12 289	99.95 82	98.45 280	99.70 335	99.45 299

IMVS_0403		99.37 185	99.39 160	99.28 331	99.71 210	98.55 387	99.19 213	99.71 209	99.41 224	99.67 218	99.60 296	99.12 124	99.84 318	98.45 280	99.70 335	99.45 299

MVP-Stereo		99.16 255	99.08 248	99.43 268	99.48 353	99.07 307	99.08 264	99.55 317	98.63 360	99.31 359	99.68 229	98.19 282	99.78 399	98.18 308	99.58 384	99.45 299
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
新几何1				99.52 235	99.50 343	99.22 272		99.26 419	95.66 518	98.60 457	99.28 417	97.67 326	99.89 228	95.95 489	99.32 434	99.45 299

LFMVS		98.46 375	98.19 395	99.26 341	99.24 427	98.52 393	99.62 67	96.94 531	99.87 63	99.31 359	99.58 309	91.04 485	99.81 381	98.68 257	99.42 421	99.45 299

testgi		99.29 207	99.26 204	99.37 296	99.75 184	98.81 352	98.84 334	99.89 69	98.38 392	99.75 167	99.04 463	99.36 82	99.86 281	99.08 185	99.25 445	99.45 299

UnsupCasMVSNet_eth		98.83 329	98.57 344	99.59 199	99.68 243	99.45 205	98.99 302	99.67 237	99.48 199	99.55 281	99.36 395	94.92 428	99.86 281	98.95 212	96.57 538	99.45 299

PatchmatchNet1														98.28 295	99.92 159	99.44 314
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
无先验							98.01 453	99.23 427	95.83 514				99.85 300	95.79 497		99.44 314

testdata				99.42 271	99.51 337	98.93 331		99.30 412	96.20 509	98.87 430	99.40 378	98.33 264	99.89 228	96.29 471	99.28 439	99.44 314

XVG-OURS-SEG-HR		99.16 255	98.99 287	99.66 154	99.84 82	99.64 138	98.25 425	99.73 196	98.39 390	99.63 240	99.43 368	99.70 32	99.90 205	97.34 394	98.64 495	99.44 314

FMVSNet2		99.35 192	99.28 199	99.55 222	99.49 348	99.35 240	99.45 118	99.57 305	99.44 212	99.70 199	99.74 171	97.21 352	99.87 261	99.03 192	99.94 136	99.44 314

N_pmnet		98.73 341	98.53 350	99.35 306	99.72 204	98.67 366	98.34 415	94.65 547	98.35 400	99.79 135	99.68 229	98.03 297	99.93 121	98.28 295	99.92 159	99.44 314

RPSCF		99.18 247	99.02 270	99.64 168	99.83 91	99.85 22	99.44 120	99.82 123	98.33 407	99.50 302	99.78 134	97.90 307	99.65 488	96.78 441	99.83 247	99.44 314

gbinet_0.2-2-1-0.02		97.52 444	97.07 456	98.88 407	97.35 548	97.35 466	97.17 508	99.25 422	97.86 450	98.41 471	96.54 556	90.74 493	99.85 300	98.80 232	97.51 530	99.43 321

原ACMM1				99.37 296	99.47 359	98.87 347		99.27 417	96.74 503	98.26 476	99.32 405	97.93 306	99.82 364	95.96 488	99.38 425	99.43 321

test222					99.51 337	99.08 306	97.83 471	99.29 413	95.21 524	98.68 450	99.31 408	97.28 348			99.38 425	99.43 321

XVG-OURS		99.21 238	99.06 254	99.65 161	99.82 100	99.62 146	97.87 469	99.74 191	98.36 394	99.66 225	99.68 229	99.71 29	99.90 205	96.84 438	99.88 204	99.43 321

CSCG		99.37 185	99.29 196	99.60 196	99.71 210	99.46 199	99.43 122	99.85 96	98.79 338	99.41 329	99.60 296	98.92 166	99.92 155	98.02 320	99.92 159	99.43 321

GDP-MVS		98.81 332	98.57 344	99.50 241	99.53 328	99.12 296	99.28 179	99.86 90	99.53 189	99.57 268	99.32 405	90.88 490	99.98 27	99.46 102	99.74 313	99.42 326

SSM_0404		99.57 103	99.58 101	99.54 228	99.76 166	99.28 252	99.19 213	99.84 106	99.80 96	99.78 141	99.70 207	99.44 66	99.93 121	98.74 243	99.95 117	99.41 327

RRT-MVS		99.08 276	99.00 280	99.33 313	99.27 421	98.65 373	99.62 67	99.93 44	99.66 152	99.67 218	99.82 92	95.27 424	99.93 121	98.64 264	99.09 459	99.41 327

TinyColmap		98.97 305	98.93 298	99.07 374	99.46 363	98.19 415	97.75 474	99.75 185	98.79 338	99.54 285	99.70 207	98.97 159	99.62 493	96.63 452	99.83 247	99.41 327

DKM		99.12 266	98.98 290	99.54 228	99.71 210	99.48 190	98.53 394	99.88 75	99.18 265	98.99 414	99.64 250	96.25 397	99.75 430	98.66 260	99.93 150	99.40 330

SD_0403		97.42 448	96.90 465	98.98 383	99.54 319	97.90 439	99.52 95	99.54 323	99.34 236	97.87 503	98.85 487	98.72 197	99.64 490	78.93 556	99.83 247	99.40 330

Anonymous202405211		98.75 338	98.46 359	99.63 176	99.34 402	99.66 125	99.47 113	97.65 520	99.28 247	99.56 276	99.50 347	93.15 455	99.84 318	98.62 266	99.58 384	99.40 330

XVG-ACMP-BASELINE		99.23 224	99.10 244	99.63 176	99.82 100	99.58 167	98.83 337	99.72 205	98.36 394	99.60 260	99.71 197	98.92 166	99.91 186	97.08 422	99.84 239	99.40 330

MS-PatchMatch		99.00 301	98.97 292	99.09 368	99.11 454	98.19 415	98.76 351	99.33 403	98.49 381	99.44 316	99.58 309	98.21 279	99.69 458	98.20 304	99.62 367	99.39 334

FMVSNet3		98.80 333	98.63 336	99.32 318	99.13 447	98.72 362	99.10 256	99.48 353	99.23 257	99.62 250	99.64 250	92.57 463	99.86 281	98.96 205	99.90 177	99.39 334

DenseAffine		99.17 252	99.06 254	99.49 245	99.76 166	99.33 243	98.43 410	99.97 22	99.11 286	99.17 389	99.61 286	97.05 361	99.76 419	98.56 271	99.88 204	99.38 336

ambc				99.20 352	99.35 393	98.53 391	99.17 222	99.46 359		99.67 218	99.80 109	98.46 245	99.70 451	97.92 330	99.70 335	99.38 336

FMVSNet5		97.80 428	97.25 449	99.42 271	98.83 493	98.97 322	99.38 134	99.80 144	98.87 322	99.25 372	99.69 216	80.60 534	99.91 186	98.96 205	99.90 177	99.38 336

PAPM_NR		98.36 385	98.04 406	99.33 313	99.48 353	98.93 331	98.79 348	99.28 416	97.54 465	98.56 463	98.57 506	97.12 358	99.69 458	94.09 525	98.90 477	99.38 336

EPNet_dtu		97.62 436	97.79 427	97.11 509	96.67 551	92.31 542	98.51 397	98.04 508	99.24 255	95.77 541	99.47 360	93.78 447	99.66 481	98.98 200	99.62 367	99.37 340
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PHI-MVS		99.11 271	98.95 296	99.59 199	99.13 447	99.59 162	99.17 222	99.65 252	97.88 447	99.25 372	99.46 363	98.97 159	99.80 391	97.26 405	99.82 257	99.37 340

PLC	97.35 16	98.36 385	97.99 409	99.48 251	99.32 408	99.24 266	98.50 398	99.51 344	95.19 525	98.58 459	98.96 477	96.95 366	99.83 341	95.63 500	99.25 445	99.37 340
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tttt0517		97.62 436	97.20 451	98.90 404	99.76 166	97.40 464	99.48 110	94.36 548	99.06 292	99.70 199	99.49 352	84.55 527	99.94 99	98.73 248	99.65 360	99.36 343

pmmvs-eth3d		99.48 136	99.47 133	99.51 239	99.77 161	99.41 221	98.81 342	99.66 242	99.42 223	99.75 167	99.66 241	99.20 108	99.76 419	98.98 200	99.99 19	99.36 343

PVSNet_0	95.53 19	95.85 499	95.31 501	97.47 489	98.78 501	93.48 537	95.72 540	99.40 379	96.18 510	97.37 520	97.73 529	95.73 410	99.58 501	95.49 503	81.40 557	99.36 343

RoMa-SfM		99.32 202	99.23 213	99.59 199	99.77 161	99.53 178	98.89 323	99.88 75	98.78 340	99.65 229	99.52 340	97.78 317	99.90 205	98.96 205	99.86 226	99.35 346

usedtu_dtu_shiyan1		98.87 324	98.71 327	99.35 306	99.59 279	98.88 342	97.17 508	99.64 260	98.94 308	99.27 366	99.22 434	95.57 415	99.83 341	99.08 185	99.92 159	99.35 346

FE-MVSNET3		98.87 324	98.71 327	99.35 306	99.59 279	98.88 342	97.17 508	99.64 260	98.94 308	99.27 366	99.22 434	95.57 415	99.83 341	99.08 185	99.92 159	99.35 346

testing3		96.48 478	95.63 492	99.01 380	99.23 429	97.81 443	98.90 322	99.10 448	98.72 348	97.84 506	97.92 525	72.44 556	99.85 300	97.21 412	99.33 432	99.35 346

lupinMVS		98.96 308	98.87 309	99.24 346	99.57 299	98.40 401	98.12 440	99.18 439	98.28 411	99.63 240	99.13 447	98.02 298	99.97 45	98.22 302	99.69 344	99.35 346

Vis-MVSNet (Re-imp)		98.77 336	98.58 343	99.34 310	99.78 148	98.88 342	99.61 73	99.56 310	99.11 286	99.24 375	99.56 321	93.00 459	99.78 399	97.43 389	99.89 193	99.35 346

GA-MVS		97.99 418	97.68 433	98.93 392	99.52 335	98.04 429	97.19 507	99.05 452	98.32 408	98.81 436	98.97 475	89.89 505	99.41 520	98.33 292	99.05 462	99.34 352

blend_shiyan4		95.04 508	93.76 515	98.88 407	97.92 536	97.49 455	97.72 477	99.34 398	97.93 442	97.65 516	97.11 543	77.69 546	99.83 341	98.79 233	79.72 558	99.33 353

CANet		99.11 271	99.05 261	99.28 331	98.83 493	98.56 385	98.71 363	99.41 372	99.25 253	99.23 376	99.22 434	97.66 330	99.94 99	99.19 153	99.97 78	99.33 353

Patchmtry		98.78 334	98.54 349	99.49 245	98.89 485	99.19 282	99.32 160	99.67 237	99.65 158	99.72 190	99.79 121	91.87 476	99.95 82	98.00 324	99.97 78	99.33 353

PAPR		97.56 439	97.07 456	99.04 378	98.80 497	98.11 423	97.63 484	99.25 422	94.56 534	98.02 495	98.25 517	97.43 340	99.68 470	90.90 538	98.74 488	99.33 353

TestfortrainingZip				99.38 291	99.17 441	99.25 261	99.38 134	98.82 465	98.93 313	99.68 210	99.49 352	98.11 291	99.56 506		98.44 505	99.32 357

testf1		99.63 87	99.60 94	99.72 123	99.94 18	99.95 2	99.47 113	99.89 69	99.43 219	99.88 83	99.80 109	99.26 98	99.90 205	98.81 230	99.88 204	99.32 357

APD_test2		99.63 87	99.60 94	99.72 123	99.94 18	99.95 2	99.47 113	99.89 69	99.43 219	99.88 83	99.80 109	99.26 98	99.90 205	98.81 230	99.88 204	99.32 357

CHOSEN 280x420		98.41 381	98.41 368	98.40 445	99.34 402	95.89 506	96.94 522	99.44 365	98.80 336	99.25 372	99.52 340	93.51 451	99.98 27	98.94 213	99.98 55	99.32 357

baseline1		97.73 431	97.33 445	98.96 385	99.30 414	97.73 447	99.40 129	98.42 491	99.33 239	99.46 313	99.21 438	91.18 483	99.82 364	98.35 290	91.26 551	99.32 357

dmvs_re		98.69 346	98.48 356	99.31 323	99.55 317	99.42 214	99.54 91	98.38 496	99.32 240	98.72 446	98.71 497	96.76 373	99.21 529	96.01 483	99.35 430	99.31 362

TAPA-MVS	97.92 13	98.03 414	97.55 437	99.46 257	99.47 359	99.44 207	98.50 398	99.62 267	86.79 548	99.07 406	99.26 423	98.26 272	99.62 493	97.28 402	99.73 320	99.31 362
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LCM-MVSNet-Re		99.28 209	99.15 224	99.67 146	99.33 407	99.76 71	99.34 151	99.97 22	98.93 313	99.91 63	99.79 121	98.68 201	99.93 121	96.80 440	99.56 387	99.30 364

TSAR-MVS + GP.		99.12 266	99.04 267	99.38 291	99.34 402	99.16 289	98.15 435	99.29 413	98.18 418	99.63 240	99.62 276	99.18 110	99.68 470	98.20 304	99.74 313	99.30 364

PVSNet_Blended		98.70 345	98.59 340	99.02 379	99.54 319	97.99 431	97.58 488	99.82 123	95.70 517	99.34 349	98.98 473	98.52 236	99.77 412	97.98 325	99.83 247	99.30 364

MVS_111021_LR		99.13 263	99.03 269	99.42 271	99.58 289	99.32 246	97.91 467	99.73 196	98.68 353	99.31 359	99.48 356	99.09 128	99.66 481	97.70 360	99.77 293	99.29 367

dongtai		89.37 516	88.91 520	90.76 534	99.19 437	77.46 562	95.47 542	87.82 562	92.28 542	94.17 548	98.82 491	71.22 558	95.54 554	63.85 557	97.34 532	99.27 368

dmvs_testset		97.27 454	96.83 467	98.59 434	99.46 363	97.55 453	99.25 194	96.84 532	98.78 340	97.24 524	97.67 530	97.11 359	98.97 538	86.59 551	98.54 499	99.27 368

miper_lstm_enhance		98.65 350	98.60 338	98.82 416	99.20 435	97.33 467	97.78 473	99.66 242	99.01 298	99.59 263	99.50 347	94.62 435	99.85 300	98.12 313	99.90 177	99.26 370

MVS		95.72 501	94.63 510	98.99 381	98.56 514	97.98 436	99.30 169	98.86 462	72.71 554	97.30 522	99.08 457	98.34 261	99.74 437	89.21 539	98.33 508	99.26 370

MSLP-MVS++		99.05 285	99.09 246	98.91 398	99.21 432	98.36 406	98.82 341	99.47 356	98.85 325	98.90 426	99.56 321	98.78 187	99.09 534	98.57 270	99.68 349	99.26 370

D2MVS		99.22 233	99.19 217	99.29 328	99.69 234	98.74 361	98.81 342	99.41 372	98.55 370	99.68 210	99.69 216	98.13 287	99.87 261	98.82 226	99.98 55	99.24 373

test_yl		98.25 394	97.95 413	99.13 363	99.17 441	98.47 394	99.00 294	98.67 475	98.97 302	99.22 380	99.02 468	91.31 481	99.69 458	97.26 405	98.93 471	99.24 373

DCV-MVSNet		98.25 394	97.95 413	99.13 363	99.17 441	98.47 394	99.00 294	98.67 475	98.97 302	99.22 380	99.02 468	91.31 481	99.69 458	97.26 405	98.93 471	99.24 373

DPM-MVS		98.28 391	97.94 417	99.32 318	99.36 389	99.11 297	97.31 502	98.78 469	96.88 497	98.84 433	99.11 454	97.77 318	99.61 498	94.03 527	99.36 428	99.23 376

CLD-MVS		98.76 337	98.57 344	99.33 313	99.57 299	98.97 322	97.53 491	99.55 317	96.41 505	99.27 366	99.13 447	99.07 136	99.78 399	96.73 444	99.89 193	99.23 376
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
pmmvs4		99.13 263	99.06 254	99.36 302	99.57 299	99.10 304	98.01 453	99.25 422	98.78 340	99.58 265	99.44 367	98.24 273	99.76 419	98.74 243	99.93 150	99.22 378

mvsmamba		99.08 276	98.95 296	99.45 260	99.36 389	99.18 288	99.39 131	98.81 467	99.37 231	99.35 345	99.70 207	96.36 391	99.94 99	98.66 260	99.59 382	99.22 378

OMC-MVS		98.90 319	98.72 326	99.44 264	99.39 380	99.42 214	98.58 381	99.64 260	97.31 479	99.44 316	99.62 276	98.59 215	99.69 458	96.17 479	99.79 280	99.22 378

GLUNet-SfM		95.26 507	95.06 505	95.87 529	94.84 557	90.39 556	90.24 551	99.92 48	92.30 541	99.16 390	99.25 425	94.69 434	98.01 548	85.55 552	99.62 367	99.21 381

EGC-MVSNET		89.05 517	85.52 521	99.64 168	99.89 41	99.78 58	99.56 88	99.52 339	24.19 558	49.96 561	99.83 84	99.15 116	99.92 155	97.71 357	99.85 233	99.21 381

eth_miper_zixun_eth		98.68 347	98.71 327	98.60 433	99.10 456	96.84 484	97.52 493	99.54 323	98.94 308	99.58 265	99.48 356	96.25 397	99.76 419	98.01 323	99.93 150	99.21 381

c3_l		98.72 342	98.71 327	98.72 424	99.12 449	97.22 471	97.68 481	99.56 310	98.90 318	99.54 285	99.48 356	96.37 390	99.73 440	97.88 334	99.88 204	99.21 381

CMPMVS	77.52 23	98.50 369	98.19 395	99.41 281	98.33 523	99.56 171	99.01 288	99.59 293	95.44 520	99.57 268	99.80 109	95.64 411	99.46 519	96.47 463	99.92 159	99.21 381
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Effi-MVS+		99.06 281	98.97 292	99.34 310	99.31 410	98.98 319	98.31 420	99.91 58	98.81 334	98.79 440	98.94 480	99.14 119	99.84 318	98.79 233	98.74 488	99.20 386

DELS-MVS		99.34 197	99.30 190	99.48 251	99.51 337	99.36 237	98.12 440	99.53 334	99.36 235	99.41 329	99.61 286	99.22 105	99.87 261	99.21 147	99.68 349	99.20 386
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
EC-MVSNet		99.69 60	99.69 61	99.68 142	99.71 210	99.91 4	99.76 23	99.96 31	99.86 66	99.51 299	99.39 383	99.57 53	99.93 121	99.64 74	99.86 226	99.20 386

CANet_DTU		98.91 316	98.85 311	99.09 368	98.79 499	98.13 420	98.18 429	99.31 409	99.48 199	98.86 431	99.51 344	96.56 379	99.95 82	99.05 189	99.95 117	99.19 389

alignmvs		98.28 391	97.96 412	99.25 344	99.12 449	98.93 331	99.03 279	98.42 491	99.64 162	98.72 446	97.85 527	90.86 491	99.62 493	98.88 219	99.13 454	99.19 389

testing3-2		96.51 477	96.43 471	96.74 518	99.36 389	91.38 550	99.10 256	97.87 516	99.48 199	98.57 461	98.71 497	76.65 548	99.66 481	98.87 220	99.26 443	99.18 391

DIV-MVS_self_test		98.54 364	98.42 367	98.92 393	99.03 469	97.80 445	97.46 495	99.59 293	98.90 318	99.60 260	99.46 363	93.87 444	99.78 399	97.97 327	99.89 193	99.18 391

MSDG		99.08 276	98.98 290	99.37 296	99.60 273	99.13 294	97.54 489	99.74 191	98.84 329	99.53 290	99.55 330	99.10 126	99.79 395	97.07 423	99.86 226	99.18 391

cl____		98.54 364	98.41 368	98.92 393	99.03 469	97.80 445	97.46 495	99.59 293	98.90 318	99.60 260	99.46 363	93.85 445	99.78 399	97.97 327	99.89 193	99.17 394

PM-MVS		99.36 190	99.29 196	99.58 203	99.83 91	99.66 125	98.95 314	99.86 90	98.85 325	99.81 121	99.73 177	98.40 255	99.92 155	98.36 289	99.83 247	99.17 394

thisisatest0530		97.45 446	96.95 461	98.94 388	99.68 243	97.73 447	99.09 261	94.19 550	98.61 365	99.56 276	99.30 411	84.30 529	99.93 121	98.27 297	99.54 397	99.16 396

PatchmatchNet		97.65 435	97.80 425	97.18 504	98.82 496	92.49 541	99.17 222	98.39 495	98.12 422	98.79 440	99.58 309	90.71 494	99.89 228	97.23 410	99.41 422	99.16 396
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tfpnnormal		99.43 160	99.38 163	99.60 196	99.87 56	99.75 80	99.59 80	99.78 166	99.71 123	99.90 68	99.69 216	98.85 177	99.90 205	97.25 409	99.78 288	99.15 398

SPE-MVS-test		99.68 65	99.70 58	99.64 168	99.57 299	99.83 34	99.78 17	99.97 22	99.92 46	99.50 302	99.38 386	99.57 53	99.95 82	99.69 65	99.90 177	99.15 398

mvs_anonymous		99.28 209	99.39 160	98.94 388	99.19 437	97.81 443	99.02 283	99.55 317	99.78 103	99.85 102	99.80 109	98.24 273	99.86 281	99.57 83	99.50 406	99.15 398

ab-mvs		99.33 200	99.28 199	99.47 253	99.57 299	99.39 226	99.78 17	99.43 369	98.87 322	99.57 268	99.82 92	98.06 295	99.87 261	98.69 256	99.73 320	99.15 398

MIMVSNet		98.43 378	98.20 392	99.11 365	99.53 328	98.38 405	99.58 83	98.61 478	98.96 304	99.33 351	99.76 156	90.92 487	99.81 381	97.38 392	99.76 298	99.15 398

GSMVS																99.14 403

sam_mvs1												90.81 492				99.14 403

SCA		98.11 409	98.36 375	97.36 497	99.20 435	92.99 538	98.17 432	98.49 487	98.24 413	99.10 402	99.57 317	96.01 405	99.94 99	96.86 434	99.62 367	99.14 403

LS3D		99.24 221	99.11 235	99.61 192	98.38 521	99.79 55	99.57 86	99.68 232	99.61 172	99.15 393	99.71 197	98.70 199	99.91 186	97.54 381	99.68 349	99.13 406

ArgMatch-SfM		99.14 260	99.06 254	99.36 302	99.59 279	99.14 293	98.45 408	99.81 136	98.67 355	99.50 302	99.42 370	98.55 222	99.84 318	97.85 341	99.73 320	99.11 407

Patchmatch-RL test		98.60 355	98.36 375	99.33 313	99.77 161	99.07 307	98.27 422	99.87 81	98.91 317	99.74 178	99.72 187	90.57 497	99.79 395	98.55 272	99.85 233	99.11 407

test_0402		99.22 233	99.14 225	99.45 260	99.79 139	99.43 211	99.28 179	99.68 232	99.54 187	99.40 335	99.56 321	99.07 136	99.82 364	96.01 483	99.96 92	99.11 407

LoFTR		99.29 207	99.26 204	99.36 302	99.70 226	99.05 310	98.66 369	99.95 39	98.85 325	99.86 97	99.75 164	98.14 286	99.93 121	98.54 274	99.91 173	99.10 410

APD_test1		99.36 190	99.28 199	99.61 192	99.89 41	99.89 10	99.32 160	99.74 191	99.18 265	99.69 203	99.75 164	98.41 251	99.84 318	97.85 341	99.70 335	99.10 410

BridgeMVS		99.50 128	99.50 126	99.50 241	99.42 376	99.49 186	99.52 95	99.75 185	99.86 66	99.78 141	99.71 197	98.20 281	99.90 205	99.39 115	99.88 204	99.10 410

MVS_Test		99.28 209	99.31 185	99.19 353	99.35 393	98.79 356	99.36 146	99.49 352	99.17 272	99.21 382	99.67 235	98.78 187	99.66 481	99.09 183	99.66 358	99.10 410

AdaColmap		98.60 355	98.35 377	99.38 291	99.12 449	99.22 272	98.67 367	99.42 371	97.84 452	98.81 436	99.27 419	97.32 347	99.81 381	95.14 510	99.53 399	99.10 410

FPMVS		96.32 483	95.50 493	98.79 417	99.60 273	98.17 418	98.46 407	98.80 468	97.16 487	96.28 537	99.63 266	82.19 530	99.09 534	88.45 543	98.89 478	99.10 410

WB-MVSnew		98.34 390	98.14 399	98.96 385	98.14 532	97.90 439	98.27 422	97.26 528	98.63 360	98.80 438	98.00 523	97.77 318	99.90 205	97.37 393	98.98 468	99.09 416

Syy-MVS		98.17 406	97.85 423	99.15 358	98.50 517	98.79 356	98.60 376	99.21 433	97.89 445	96.76 531	96.37 559	95.47 420	99.57 502	99.10 182	98.73 491	99.09 416

myMVS_eth3d		95.63 503	94.73 508	98.34 450	98.50 517	96.36 493	98.60 376	99.21 433	97.89 445	96.76 531	96.37 559	72.10 557	99.57 502	94.38 519	98.73 491	99.09 416

Patchmatch-test		98.10 410	97.98 411	98.48 441	99.27 421	96.48 490	99.40 129	99.07 449	98.81 334	99.23 376	99.57 317	90.11 502	99.87 261	96.69 445	99.64 362	99.09 416

tpm		97.15 458	96.95 461	97.75 478	98.91 480	94.24 530	99.32 160	97.96 511	97.71 458	98.29 475	99.32 405	86.72 521	99.92 155	98.10 318	96.24 546	99.09 416

PMMVS		98.49 371	98.29 385	99.11 365	98.96 478	98.42 400	97.54 489	99.32 405	97.53 466	98.47 467	98.15 520	97.88 309	99.82 364	97.46 387	99.24 447	99.09 416

ArgMatch-Sym		99.06 281	98.96 294	99.35 306	99.62 268	99.22 272	98.34 415	99.79 153	98.80 336	99.50 302	99.29 415	98.30 267	99.75 430	97.30 399	99.71 332	99.08 422

cl22		97.56 439	97.28 446	98.40 445	98.37 522	96.75 485	97.24 506	99.37 388	97.31 479	99.41 329	99.22 434	87.30 513	99.37 523	97.70 360	99.62 367	99.08 422

ADS-MVSNet2		97.78 429	97.66 435	98.12 463	99.14 445	95.36 517	99.22 204	98.75 470	96.97 494	98.25 477	99.64 250	90.90 488	99.94 99	96.51 458	99.56 387	99.08 422

ADS-MVSNet		97.72 434	97.67 434	97.86 474	99.14 445	94.65 527	99.22 204	98.86 462	96.97 494	98.25 477	99.64 250	90.90 488	99.84 318	96.51 458	99.56 387	99.08 422

pmmvs3		98.08 411	97.80 425	98.91 398	99.41 377	97.69 449	97.87 469	99.66 242	95.87 512	99.50 302	99.51 344	90.35 499	99.97 45	98.55 272	99.47 411	99.08 422

PVSNet	97.47 15	98.42 379	98.44 364	98.35 448	99.46 363	96.26 496	96.70 531	99.34 398	97.68 459	99.00 413	99.13 447	97.40 341	99.72 442	97.59 378	99.68 349	99.08 422

MVS-HIRNet		97.86 423	98.22 390	96.76 516	99.28 419	91.53 548	98.38 413	92.60 554	99.13 282	99.31 359	99.96 15	97.18 356	99.68 470	98.34 291	99.83 247	99.07 428

PMVS	92.94 21	98.82 330	98.81 318	98.85 409	99.84 82	97.99 431	99.20 207	99.47 356	99.71 123	99.42 323	99.82 92	98.09 292	99.47 517	93.88 529	99.85 233	99.07 428
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PRO-TEST		99.17 252	99.14 225	99.28 331	99.04 467	98.92 335	99.24 195	99.76 179	99.69 133	99.41 329	99.17 443	98.06 295	99.85 300	98.39 287	99.47 411	99.06 430

nomal-1		96.75 468	96.26 475	98.21 459	99.06 462	95.71 510	98.65 372	97.76 519	98.51 377	97.96 496	97.91 526	79.57 539	99.88 244	98.11 314	98.84 479	99.05 431

MVSMamba_PlusPlus		99.55 112	99.58 101	99.47 253	99.68 243	99.40 222	99.52 95	99.70 218	99.92 46	99.77 153	99.86 64	98.28 269	99.96 70	99.54 88	99.90 177	99.05 431

Gipuma		99.57 103	99.59 97	99.49 245	99.98 3	99.71 103	99.72 33	99.84 106	99.81 92	99.94 48	99.78 134	98.91 169	99.71 447	98.41 285	99.95 117	99.05 431
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ELoFTR		99.25 217	99.26 204	99.21 349	99.86 61	98.66 369	99.00 294	99.93 44	98.56 368	99.83 111	99.83 84	97.34 345	99.92 155	99.03 192	100.00 1	99.04 434

sasdasda		99.02 292	99.00 280	99.09 368	99.10 456	98.70 364	99.61 73	99.66 242	99.63 164	98.64 452	97.65 531	99.04 146	99.54 507	98.79 233	98.92 473	99.04 434

canonicalmvs		99.02 292	99.00 280	99.09 368	99.10 456	98.70 364	99.61 73	99.66 242	99.63 164	98.64 452	97.65 531	99.04 146	99.54 507	98.79 233	98.92 473	99.04 434

MGCFI-Net		99.02 292	99.01 276	99.06 376	99.11 454	98.60 380	99.63 64	99.67 237	99.63 164	98.58 459	97.65 531	99.07 136	99.57 502	98.85 221	98.92 473	99.03 437

hse-mvs2		98.52 366	98.30 383	99.16 356	99.29 416	98.60 380	98.77 350	99.02 454	99.68 137	99.32 354	99.04 463	92.50 467	99.85 300	99.24 140	97.87 526	99.03 437

CL-MVSNet_self_test		98.71 344	98.56 348	99.15 358	99.22 430	98.66 369	97.14 511	99.51 344	98.09 425	99.54 285	99.27 419	96.87 369	99.74 437	98.43 284	98.96 469	99.03 437

AUN-MVS		97.82 425	97.38 443	99.14 361	99.27 421	98.53 391	98.72 359	99.02 454	98.10 423	97.18 526	99.03 467	89.26 507	99.85 300	97.94 329	97.91 524	99.03 437

MDTV_nov1_ep13_2view						91.44 549	99.14 235		97.37 476	99.21 382		91.78 478		96.75 442		99.03 437

ITE_SJBPF				99.38 291	99.63 264	99.44 207		99.73 196	98.56 368	99.33 351	99.53 336	98.88 173	99.68 470	96.01 483	99.65 360	99.02 442

UnsupCasMVSNet_bld		98.55 362	98.27 386	99.40 284	99.56 313	99.37 233	97.97 461	99.68 232	97.49 469	99.08 403	99.35 400	95.41 422	99.82 364	97.70 360	98.19 515	99.01 443

miper_ehance_all_eth		98.59 358	98.59 340	98.59 434	98.98 476	97.07 475	97.49 494	99.52 339	98.50 379	99.52 292	99.37 390	96.41 388	99.71 447	97.86 339	99.62 367	99.00 444

PMatch-SfM		98.91 316	98.81 318	99.22 348	99.79 139	98.89 340	98.18 429	99.61 275	99.18 265	99.03 410	99.61 286	96.13 401	99.80 391	98.71 252	99.04 464	98.99 445

testing91		96.00 494	95.32 500	98.02 464	98.76 504	95.39 516	98.38 413	98.65 477	98.82 332	96.84 530	96.71 554	75.06 552	99.71 447	96.46 464	98.23 512	98.98 446

CS-MVS		99.67 77	99.70 58	99.58 203	99.53 328	99.84 27	99.79 15	99.96 31	99.90 50	99.61 257	99.41 372	99.51 62	99.95 82	99.66 70	99.89 193	98.96 447

CNLPA		98.57 360	98.34 378	99.28 331	99.18 440	99.10 304	98.34 415	99.41 372	98.48 382	98.52 464	98.98 473	97.05 361	99.78 399	95.59 501	99.50 406	98.96 447

UBG		96.53 475	95.95 483	98.29 456	98.87 488	96.31 495	98.48 402	98.07 507	98.83 330	97.32 521	96.54 556	79.81 537	99.62 493	96.84 438	98.74 488	98.95 449

new_pmnet		98.88 323	98.89 307	98.84 411	99.70 226	97.62 451	98.15 435	99.50 348	97.98 434	99.62 250	99.54 332	98.15 285	99.94 99	97.55 380	99.84 239	98.95 449

PCF-MVS	96.03 18	96.73 469	95.86 486	99.33 313	99.44 368	99.16 289	96.87 525	99.44 365	86.58 549	98.95 417	99.40 378	94.38 439	99.88 244	87.93 545	99.80 274	98.95 449
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PMatch-Up-SfM		99.08 276	99.02 270	99.27 337	99.81 114	99.04 312	98.13 438	99.83 116	99.16 274	99.26 370	99.69 216	97.22 351	99.83 341	98.67 259	99.43 420	98.94 452

testing11		96.05 493	95.41 497	97.97 468	98.78 501	95.27 520	98.59 379	98.23 502	98.86 324	96.56 535	96.91 548	75.20 551	99.69 458	97.26 405	98.29 510	98.93 453

PatchMatch-RL		98.68 347	98.47 357	99.30 327	99.44 368	99.28 252	98.14 437	99.54 323	97.12 489	99.11 400	99.25 425	97.80 315	99.70 451	96.51 458	99.30 436	98.93 453

MatchFormer		99.03 289	99.02 270	99.08 373	99.56 313	98.47 394	98.57 385	99.90 65	98.13 421	99.80 128	99.75 164	98.34 261	99.84 318	97.18 417	99.90 177	98.92 455

Fast-Effi-MVS+		99.02 292	98.87 309	99.46 257	99.38 383	99.50 185	99.04 276	99.79 153	97.17 486	98.62 455	98.74 495	99.34 86	99.95 82	98.32 293	99.41 422	98.92 455

ET-MVSNet_ETH3D		96.78 466	96.07 481	98.91 398	99.26 424	97.92 438	97.70 480	96.05 536	97.96 438	92.37 552	98.43 512	87.06 515	99.90 205	98.27 297	97.56 529	98.91 457

testing99		95.86 498	95.19 503	97.87 473	98.76 504	95.03 523	98.62 373	98.44 490	98.68 353	96.67 533	96.66 555	74.31 554	99.69 458	96.51 458	98.03 523	98.90 458

ETVMVS		96.14 489	95.22 502	98.89 405	98.80 497	98.01 430	98.66 369	98.35 498	98.71 350	97.18 526	96.31 561	74.23 555	99.75 430	96.64 451	98.13 521	98.90 458

EIA-MVS		99.12 266	99.01 276	99.45 260	99.36 389	99.62 146	99.34 151	99.79 153	98.41 387	98.84 433	98.89 484	98.75 192	99.84 318	98.15 312	99.51 403	98.89 460

CostFormer		96.71 470	96.79 469	96.46 523	98.90 481	90.71 554	99.41 123	98.68 473	94.69 532	98.14 490	99.34 404	86.32 523	99.80 391	97.60 377	98.07 522	98.88 461

DP-MVS Recon		98.50 369	98.23 389	99.31 323	99.49 348	99.46 199	98.56 388	99.63 263	94.86 530	98.85 432	99.37 390	97.81 314	99.59 500	96.08 480	99.44 416	98.88 461

test0.0.03 1		97.37 451	96.91 464	98.74 422	97.72 539	97.57 452	97.60 487	97.36 526	98.00 431	99.21 382	98.02 521	90.04 503	99.79 395	98.37 288	95.89 548	98.86 463

BH-untuned		98.22 400	98.09 403	98.58 437	99.38 383	97.24 470	98.55 389	98.98 459	97.81 453	99.20 387	98.76 494	97.01 363	99.65 488	94.83 514	98.33 508	98.86 463

HY-MVS	98.23 9	98.21 402	97.95 413	98.99 381	99.03 469	98.24 410	99.61 73	98.72 471	96.81 500	98.73 445	99.51 344	94.06 442	99.86 281	96.91 431	98.20 513	98.86 463

miper_enhance_ethall		98.03 414	97.94 417	98.32 451	98.27 525	96.43 492	96.95 521	99.41 372	96.37 507	99.43 320	98.96 477	94.74 432	99.69 458	97.71 357	99.62 367	98.83 466

balanced_ft_v1		99.37 185	99.36 171	99.38 291	99.10 456	99.38 228	99.68 48	99.72 205	99.72 117	99.36 341	99.77 146	97.66 330	99.94 99	99.52 92	99.73 320	98.83 466

FE-MVS		97.85 424	97.42 442	99.15 358	99.44 368	98.75 360	99.77 19	98.20 503	95.85 513	99.33 351	99.80 109	88.86 508	99.88 244	96.40 466	99.12 455	98.81 468

Effi-MVS+-dtu		99.07 280	98.92 302	99.52 235	98.89 485	99.78 58	99.15 231	99.66 242	99.34 236	98.92 423	99.24 431	97.69 324	99.98 27	98.11 314	99.28 439	98.81 468

EPMVS		96.53 475	96.32 473	97.17 506	98.18 529	92.97 539	99.39 131	89.95 559	98.21 415	98.61 456	99.59 306	86.69 522	99.72 442	96.99 425	99.23 449	98.81 468

FBQ-MVS		96.06 492	95.42 495	97.98 466	98.90 481	95.77 508	98.71 363	98.20 503	98.34 404	97.83 507	97.34 537	74.90 553	99.39 522	96.20 477	98.40 507	98.78 471

UWE-MVS		96.21 488	95.78 488	97.49 486	98.53 515	93.83 534	98.04 450	93.94 552	98.96 304	98.46 468	98.17 519	79.86 536	99.87 261	96.99 425	99.06 460	98.78 471

FA-MVS(test-final)		98.52 366	98.32 380	99.10 367	99.48 353	98.67 366	99.77 19	98.60 481	97.35 477	99.63 240	99.80 109	93.07 457	99.84 318	97.92 330	99.30 436	98.78 471

MVE	92.54 22	96.66 472	96.11 480	98.31 453	99.68 243	97.55 453	97.94 463	95.60 545	99.37 231	90.68 553	98.70 499	96.56 379	98.61 544	86.94 550	99.55 392	98.77 474
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MonoMVSNet		98.23 398	98.32 380	97.99 465	98.97 477	96.62 487	99.49 108	98.42 491	99.62 167	99.40 335	99.79 121	95.51 418	98.58 545	97.68 371	95.98 547	98.76 475

UWE-MVS-28		95.64 502	95.47 494	96.14 527	97.98 535	90.39 556	98.49 401	95.81 543	99.02 297	98.03 494	98.19 518	84.49 528	99.28 526	88.75 541	98.47 504	98.75 476

tpm2		96.35 482	96.22 478	96.73 519	98.88 487	91.75 546	99.21 206	98.51 485	93.27 537	97.89 501	99.21 438	84.83 526	99.70 451	96.04 482	98.18 516	98.75 476

LF4IMVS		99.01 298	98.92 302	99.27 337	99.71 210	99.28 252	98.59 379	99.77 171	98.32 408	99.39 337	99.41 372	98.62 210	99.84 318	96.62 454	99.84 239	98.69 478

thisisatest0515		96.98 462	96.42 472	98.66 430	99.41 377	97.47 457	97.27 503	94.30 549	97.24 482	99.15 393	98.86 486	85.01 525	99.87 261	97.10 420	99.39 424	98.63 479

kuosan		85.65 518	84.57 522	88.90 536	97.91 537	77.11 563	96.37 536	87.62 563	85.24 551	85.45 557	96.83 549	69.94 560	90.98 558	45.90 559	95.83 549	98.62 480

Fast-Effi-MVS+-dtu		99.20 240	99.12 232	99.43 268	99.25 425	99.69 116	99.05 271	99.82 123	99.50 194	98.97 415	99.05 461	98.98 157	99.98 27	98.20 304	99.24 447	98.62 480

PAPM		95.61 504	94.71 509	98.31 453	99.12 449	96.63 486	96.66 532	98.46 489	90.77 546	96.25 538	98.68 501	93.01 458	99.69 458	81.60 553	97.86 527	98.62 480

JIA-IIPM		98.06 413	97.92 419	98.50 440	98.59 513	97.02 476	98.80 345	98.51 485	99.88 61	97.89 501	99.87 57	91.89 475	99.90 205	98.16 311	97.68 528	98.59 483

dp		96.86 464	97.07 456	96.24 525	98.68 511	90.30 558	99.19 213	98.38 496	97.35 477	98.23 479	99.59 306	87.23 514	99.82 364	96.27 472	98.73 491	98.59 483

myMVS_eth3d28		96.23 486	95.74 489	97.70 483	98.86 489	95.59 515	98.66 369	98.14 505	98.96 304	97.67 515	97.06 544	76.78 547	98.92 539	97.10 420	98.41 506	98.58 485

OpenMVS	98.12 10	98.23 398	97.89 422	99.26 341	99.19 437	99.26 258	99.65 62	99.69 228	91.33 545	98.14 490	99.77 146	98.28 269	99.96 70	95.41 505	99.55 392	98.58 485

baseline2		96.83 465	96.28 474	98.46 443	99.09 460	96.91 480	98.83 337	93.87 553	97.23 483	96.23 540	98.36 514	88.12 512	99.90 205	96.68 446	98.14 518	98.57 487

testing222		95.60 505	94.59 511	98.61 432	98.66 512	97.45 460	98.54 392	97.90 515	98.53 374	96.54 536	96.47 558	70.62 559	99.81 381	95.91 492	98.15 517	98.56 488

TESTMET0.1,1		96.24 485	95.84 487	97.41 493	98.24 526	93.84 533	97.38 498	95.84 541	98.43 384	97.81 508	98.56 507	79.77 538	99.89 228	97.77 348	98.77 483	98.52 489

xiu_mvs_v1_base_debu		99.23 224	99.34 177	98.91 398	99.59 279	98.23 411	98.47 403	99.66 242	99.61 172	99.68 210	98.94 480	99.39 72	99.97 45	99.18 156	99.55 392	98.51 490

xiu_mvs_v1_base		99.23 224	99.34 177	98.91 398	99.59 279	98.23 411	98.47 403	99.66 242	99.61 172	99.68 210	98.94 480	99.39 72	99.97 45	99.18 156	99.55 392	98.51 490

xiu_mvs_v1_base_debi		99.23 224	99.34 177	98.91 398	99.59 279	98.23 411	98.47 403	99.66 242	99.61 172	99.68 210	98.94 480	99.39 72	99.97 45	99.18 156	99.55 392	98.51 490

KD-MVS_2432*1600		95.89 495	95.41 497	97.31 501	94.96 554	93.89 531	97.09 512	99.22 430	97.23 483	98.88 427	99.04 463	79.23 540	99.54 507	96.24 475	96.81 536	98.50 493

miper_refine_blended		95.89 495	95.41 497	97.31 501	94.96 554	93.89 531	97.09 512	99.22 430	97.23 483	98.88 427	99.04 463	79.23 540	99.54 507	96.24 475	96.81 536	98.50 493

CR-MVSNet		98.35 388	98.20 392	98.83 413	99.05 464	98.12 421	99.30 169	99.67 237	97.39 475	99.16 390	99.79 121	91.87 476	99.91 186	98.78 239	98.77 483	98.44 495

RPMNet		98.60 355	98.53 350	98.83 413	99.05 464	98.12 421	99.30 169	99.62 267	99.86 66	99.16 390	99.74 171	92.53 465	99.92 155	98.75 242	98.77 483	98.44 495

tpmrst		97.73 431	98.07 405	96.73 519	98.71 508	92.00 543	99.10 256	98.86 462	98.52 376	98.92 423	99.54 332	91.90 474	99.82 364	98.02 320	99.03 465	98.37 497

test-LLR		97.15 458	96.95 461	97.74 479	98.18 529	95.02 524	97.38 498	96.10 533	98.00 431	97.81 508	98.58 504	90.04 503	99.91 186	97.69 366	98.78 481	98.31 498

test-mter		96.23 486	95.73 490	97.74 479	98.18 529	95.02 524	97.38 498	96.10 533	97.90 443	97.81 508	98.58 504	79.12 542	99.91 186	97.69 366	98.78 481	98.31 498

ETV-MVS		99.18 247	99.18 218	99.16 356	99.34 402	99.28 252	99.12 247	99.79 153	99.48 199	98.93 420	98.55 508	99.40 71	99.93 121	98.51 276	99.52 401	98.28 500

SP-LightGlue		98.62 351	98.51 352	98.94 388	98.69 510	99.01 314	98.34 415	99.54 323	99.27 248	97.72 514	99.15 446	95.88 409	99.54 507	98.53 275	99.47 411	98.27 501

PatchT		98.45 376	98.32 380	98.83 413	98.94 479	98.29 409	99.24 195	98.82 465	99.84 76	99.08 403	99.76 156	91.37 480	99.94 99	98.82 226	99.00 467	98.26 502

ALIKED-LG		98.78 334	98.66 333	99.14 361	99.02 475	99.40 222	98.74 356	99.79 153	98.62 364	99.18 388	99.38 386	97.54 335	99.77 412	95.94 491	99.74 313	98.25 503

xiu_mvs_v2_base		99.02 292	99.11 235	98.77 420	99.37 386	98.09 425	98.13 438	99.51 344	99.47 204	99.42 323	98.54 509	99.38 77	99.97 45	98.83 223	99.33 432	98.24 504

IB-MVS	95.41 20	95.30 506	94.46 513	97.84 475	98.76 504	95.33 518	97.33 501	96.07 535	96.02 511	95.37 544	97.41 535	76.17 549	99.96 70	97.54 381	95.44 550	98.22 505
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
tpm cat1		96.78 466	96.98 460	96.16 526	98.85 490	90.59 555	99.08 264	99.32 405	92.37 540	97.73 513	99.46 363	91.15 484	99.69 458	96.07 481	98.80 480	98.21 506

MAR-MVS		98.24 396	97.92 419	99.19 353	98.78 501	99.65 131	99.17 222	99.14 445	95.36 521	98.04 493	98.81 492	97.47 338	99.72 442	95.47 504	99.06 460	98.21 506
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
PS-MVSNAJ		99.00 301	99.08 248	98.76 421	99.37 386	98.10 424	98.00 456	99.51 344	99.47 204	99.41 329	98.50 511	99.28 94	99.97 45	98.83 223	99.34 431	98.20 508

cascas		96.99 461	96.82 468	97.48 487	97.57 545	95.64 512	96.43 535	99.56 310	91.75 543	97.13 529	97.61 534	95.58 414	98.63 543	96.68 446	99.11 456	98.18 509

0.4-1-1-0.1		93.18 512	91.66 517	97.73 481	95.83 552	95.29 519	95.30 543	95.90 539	93.59 535	90.58 554	94.40 562	77.87 544	99.77 412	97.31 397	84.20 553	98.15 510

BH-w/o		97.20 456	97.01 459	97.76 477	99.08 461	95.69 511	98.03 452	98.52 483	95.76 516	97.96 496	98.02 521	95.62 412	99.47 517	92.82 532	97.25 535	98.12 511

SP-SuperGlue		98.66 349	98.63 336	98.73 423	98.44 519	99.02 313	98.22 427	99.44 365	99.37 231	98.17 485	99.30 411	96.95 366	99.12 531	98.59 267	99.20 452	98.06 512

tpmvs		97.39 450	97.69 432	96.52 521	98.41 520	91.76 545	99.30 169	98.94 460	97.74 454	97.85 505	99.55 330	92.40 470	99.73 440	96.25 473	98.73 491	98.06 512

SP-MNN		97.94 422	97.82 424	98.31 453	98.30 524	97.67 450	97.81 472	97.93 513	98.14 420	97.16 528	98.64 503	96.31 393	99.21 529	97.34 394	98.75 487	98.05 514

0.3-1-1-0.015		92.36 514	90.68 519	97.39 494	94.94 556	94.41 529	94.21 547	95.89 540	92.87 538	88.87 556	93.49 565	75.30 550	99.76 419	97.19 415	83.41 555	98.02 515

0.4-1-1-0.2		92.59 513	91.07 518	97.15 507	94.73 558	93.68 535	93.50 548	95.91 537	92.68 539	90.48 555	93.52 564	77.77 545	99.75 430	97.19 415	83.88 554	98.01 516

thres600view7		96.60 474	96.16 479	97.93 470	99.63 264	96.09 503	99.18 217	97.57 521	98.77 343	98.72 446	97.32 539	87.04 516	99.72 442	88.57 542	98.62 496	97.98 517

thres400		96.40 479	95.89 484	97.92 471	99.58 289	96.11 501	99.00 294	97.54 524	98.43 384	98.52 464	96.98 545	86.85 518	99.67 476	87.62 546	98.51 500	97.98 517

TR-MVS		97.44 447	97.15 453	98.32 451	98.53 515	97.46 458	98.47 403	97.91 514	96.85 498	98.21 480	98.51 510	96.42 386	99.51 514	92.16 533	97.29 534	97.98 517

SP-DiffGlue		98.47 373	98.43 366	98.59 434	97.44 547	98.59 382	98.01 453	99.36 392	99.00 299	99.06 407	99.20 440	97.01 363	99.25 527	97.64 372	99.15 453	97.92 520

ALIKED-MNN		98.03 414	97.78 428	98.78 419	98.84 492	98.97 322	98.16 434	99.74 191	97.31 479	96.60 534	98.85 487	96.61 377	99.48 516	94.16 523	99.77 293	97.91 521

1314		98.00 417	97.90 421	98.27 457	98.90 481	97.45 460	99.30 169	99.06 451	94.98 526	97.21 525	99.12 451	98.43 248	99.67 476	95.58 502	98.56 498	97.71 522

SP-NN		96.37 481	96.23 477	96.77 515	96.83 549	96.95 477	96.47 534	97.07 530	96.75 502	93.41 551	97.75 528	94.13 441	95.69 553	96.25 473	97.43 531	97.68 523

MASt3R-SfM		98.45 376	98.51 352	98.26 458	99.32 408	97.43 463	97.43 497	99.69 228	94.97 527	99.75 167	99.41 372	98.49 240	99.75 430	97.73 354	99.79 280	97.61 524

E-PMN		97.14 460	97.43 441	96.27 524	98.79 499	91.62 547	95.54 541	99.01 457	99.44 212	98.88 427	99.12 451	92.78 460	99.68 470	94.30 521	99.03 465	97.50 525

gg-mvs-nofinetune		95.87 497	95.17 504	97.97 468	98.19 528	96.95 477	99.69 45	89.23 560	99.89 56	96.24 539	99.94 20	81.19 531	99.51 514	93.99 528	98.20 513	97.44 526

DeepMVS_CX				97.98 466	99.69 234	96.95 477		99.26 419	75.51 553	95.74 542	98.28 516	96.47 384	99.62 493	91.23 537	97.89 525	97.38 527

OpenMVS_ROB	97.31 17	97.36 452	96.84 466	98.89 405	99.29 416	99.45 205	98.87 328	99.48 353	86.54 550	99.44 316	99.74 171	97.34 345	99.86 281	91.61 535	99.28 439	97.37 528

EMVS		96.96 463	97.28 446	95.99 528	98.76 504	91.03 551	95.26 544	98.61 478	99.34 236	98.92 423	98.88 485	93.79 446	99.66 481	92.87 531	99.05 462	97.30 529

ALIKED-NN		96.66 472	96.26 475	97.88 472	97.49 546	98.59 382	96.71 530	99.15 443	95.50 519	93.58 550	98.39 513	94.52 437	97.74 550	92.05 534	98.94 470	97.29 530

thres100view900		96.39 480	96.03 482	97.47 489	99.63 264	95.93 504	99.18 217	97.57 521	98.75 347	98.70 449	97.31 540	87.04 516	99.67 476	87.62 546	98.51 500	96.81 531

tfpn200view9		96.30 484	95.89 484	97.53 484	99.58 289	96.11 501	99.00 294	97.54 524	98.43 384	98.52 464	96.98 545	86.85 518	99.67 476	87.62 546	98.51 500	96.81 531

XFeat-MNN		96.67 471	96.56 470	96.98 512	96.73 550	95.62 514	94.54 546	98.93 461	97.42 473	98.18 481	98.67 502	91.60 479	99.12 531	93.88 529	99.10 457	96.21 533

API-MVS		98.38 384	98.39 371	98.35 448	98.83 493	99.26 258	99.14 235	99.18 439	98.59 366	98.66 451	98.78 493	98.61 212	99.57 502	94.14 524	99.56 387	96.21 533

thres200		96.09 490	95.68 491	97.33 500	99.48 353	96.22 498	98.53 394	97.57 521	98.06 429	98.37 472	96.73 553	86.84 520	99.61 498	86.99 549	98.57 497	96.16 535

GG-mvs-BLEND				97.36 497	97.59 543	96.87 481	99.70 38	88.49 561		94.64 547	97.26 541	80.66 533	99.12 531	91.50 536	96.50 544	96.08 536

XFeat-NN		93.89 511	93.91 514	93.83 532	95.49 553	92.69 540	90.85 549	97.98 510	94.69 532	95.08 545	96.98 545	88.36 510	94.23 556	88.42 544	97.34 532	94.57 537

SIFT-PointCN		98.28 391	98.47 357	97.71 482	99.70 226	98.91 336	96.98 519	99.70 218	97.90 443	99.36 341	99.35 400	95.51 418	99.83 341	97.84 346	99.89 193	94.39 538

SIFT-NN-PointCN		97.97 419	98.24 388	97.14 508	99.59 279	98.71 363	96.75 528	99.56 310	97.02 493	97.91 500	99.27 419	96.85 370	98.39 546	97.47 386	99.76 298	94.31 539

SIFT-ConvMatch		98.16 407	98.37 373	97.52 485	99.54 319	99.20 279	96.97 520	98.47 488	98.09 425	99.14 395	99.40 378	95.93 408	99.05 536	97.87 337	99.92 159	94.31 539

SIFT-MNN		97.55 441	97.74 430	96.98 512	99.38 383	98.85 348	96.92 524	98.61 478	98.36 394	98.63 454	99.10 455	92.51 466	97.85 549	96.63 452	99.48 410	94.25 541

SIFT-NCM-Cal		98.18 403	98.41 368	97.48 487	99.57 299	99.28 252	97.26 504	98.08 506	98.30 410	99.23 376	99.39 383	97.13 357	99.04 537	96.86 434	99.86 226	94.12 542

SIFT-UMatch		98.07 412	98.27 386	97.46 491	99.57 299	98.99 317	96.93 523	99.02 454	98.53 374	99.26 370	99.23 433	95.43 421	99.31 525	96.51 458	99.91 173	94.09 543

SIFT-NN-CMatch		97.30 453	97.34 444	97.18 504	99.54 319	98.85 348	96.02 539	95.77 544	97.05 492	97.55 517	98.70 499	96.35 392	98.75 542	95.82 496	99.26 443	93.95 544

SIFT-UM-Cal		98.18 403	98.45 362	97.37 496	99.59 279	98.95 326	96.76 527	99.39 382	98.39 390	99.46 313	99.31 408	96.23 399	99.24 528	97.21 412	99.70 335	93.90 545

SIFT-PCN-Cal		98.24 396	98.51 352	97.43 492	99.65 257	98.64 376	97.09 512	99.35 394	98.16 419	99.69 203	99.52 340	95.59 413	99.83 341	97.57 379	100.00 1	93.81 546

SIFT-NN		94.78 509	94.89 506	94.45 531	98.23 527	97.29 468	94.93 545	95.84 541	95.82 515	94.78 546	97.12 542	90.26 500	92.28 557	88.91 540	98.14 518	93.77 547

SIFT-NN-NCMNet		97.22 455	97.27 448	97.07 510	99.64 259	99.20 279	96.53 533	95.91 537	96.91 496	97.38 519	98.95 479	96.01 405	98.29 547	94.87 513	99.21 451	93.73 548

SIFT-CM-Cal		97.96 421	98.15 398	97.39 494	99.61 270	99.15 291	96.75 528	98.41 494	98.04 430	99.03 410	99.54 332	95.24 425	99.41 520	96.97 427	99.80 274	93.61 549

SIFT-NCMNet		98.18 403	98.46 359	97.36 497	99.67 250	99.19 282	96.33 537	98.99 458	98.83 330	99.62 250	99.63 266	95.41 422	99.33 524	97.64 372	100.00 1	93.54 550

SIFT-NN-UMatch		97.18 457	97.24 450	97.01 511	99.57 299	98.65 373	96.33 537	97.31 527	97.07 491	97.48 518	98.73 496	94.39 438	98.87 540	95.75 498	98.50 503	93.50 551

VLMVS_CLIP		76.68 519	76.70 524	76.61 537	60.81 563	61.63 566	78.48 553	91.77 555	64.66 555	83.93 558	93.59 563	55.35 562	75.94 559	79.82 555	81.86 556	92.28 552

MVS_clip		74.80 520	77.14 523	67.78 538	84.58 562	66.83 565	78.80 552	52.59 566	49.02 557	94.13 549	97.99 524	68.69 561	48.60 561	80.92 554	87.52 552	87.92 553

wuyk23d		97.58 438	99.13 228	92.93 533	99.69 234	99.49 186	99.52 95	99.77 171	97.97 435	99.96 34	99.79 121	99.84 17	99.94 99	95.85 493	99.82 257	79.36 554

VLMVS		62.60 521	63.55 525	59.72 539	60.35 564	58.44 567	68.37 554	54.75 565	23.35 559	80.04 559	90.18 567	54.59 563	52.33 560	63.04 558	77.30 559	68.41 555

MVS_baseline		39.37 522	46.36 526	18.41 540	48.75 565	10.55 569	42.43 555	13.32 568	4.65 562	75.25 560	91.61 566	29.41 564	0.06 564	38.83 560	72.99 560	44.63 556

test123		29.31 523	33.05 529	18.08 541	25.93 567	12.24 568	97.53 491	10.93 569	11.78 560	24.21 562	50.08 572	21.04 565	8.60 562	23.51 561	32.43 562	33.39 557

testmvs		28.94 524	33.33 527	15.79 542	26.03 566	9.81 570	96.77 526	15.67 567	11.55 561	23.87 563	50.74 571	19.03 566	8.53 563	23.21 562	33.07 561	29.03 558

mmdepth		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

monomultidepth		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

test_blank		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

uanet_test		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

DCPMVS		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

cdsmvs_eth3d_5k		24.88 525	33.17 528	0.00 543	0.00 568	0.00 571	0.00 556	99.62 267	0.00 563	0.00 564	99.13 447	99.82 19	0.00 565	0.00 563	0.00 563	0.00 559

pcd_1.5k_mvsjas		16.61 526	22.14 530	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	99.28 94	0.00 565	0.00 563	0.00 563	0.00 559

sosnet-low-res		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

sosnet		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

uncertanet		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

Regformer		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

ab-mvs-re		8.26 537	11.02 541	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	99.16 444	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

uanet		8.33 527	11.11 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	100.00 1	0.00 567	0.00 565	0.00 563	0.00 563	0.00 559

RA-MVS			99.46 139		99.82 100	99.74 88	99.41 123	99.70 218	99.16 274	99.83 111	99.54 332	99.09 128	99.90 205	98.77 240	99.78 288

Meshroom													0.00 565
: In preparation.
AliceVision / Meshro													0.00 565
: In preparation.
AliceVision_Meshroom													0.00 565
: In preparation.
PatchmatchNet2					0.00 568	95.19 522	97.64 483	99.19 437	98.09 425
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.93 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					99.64 259	99.70 111		99.58 302		99.69 203		97.64 333	99.87 261	98.68 257	99.76 298

WAC-MVS						96.36 493								95.20 509

FOURS1					99.83 91	99.89 10	99.74 27	99.71 209	99.69 133	99.63 240

test_one_0601					99.63 264	99.76 71		99.55 317	99.23 257	99.31 359	99.61 286	98.59 215

eth-test2					0.00 568

eth-test					0.00 568

ZD-MVS					99.43 371	99.61 156		99.43 369	96.38 506	99.11 400	99.07 458	97.86 310	99.92 155	94.04 526	99.49 408

test_241102_ONE					99.69 234	99.82 42		99.54 323	99.12 285	99.82 114	99.49 352	98.91 169	99.52 513

9.14			98.64 334		99.45 367		98.81 342	99.60 287	97.52 467	99.28 365	99.56 321	98.53 232	99.83 341	95.36 507	99.64 362

save fliter					99.53 328	99.25 261	98.29 421	99.38 387	99.07 290

test0726					99.69 234	99.80 52	99.24 195	99.57 305	99.16 274	99.73 184	99.65 248	98.35 259

test_part2					99.62 268	99.67 122				99.55 281

sam_mvs												90.52 498

MTGPA								99.53 334

test_post1							99.14 235				51.63 570	89.54 506	99.82 364	96.86 434

test_post											52.41 569	90.25 501	99.86 281

patchmatchnet-post											99.62 276	90.58 496	99.94 99

MTMP							99.09 261	98.59 482

gm-plane-assit					97.59 543	89.02 560			93.47 536		98.30 515		99.84 318	96.38 468

TEST9					99.35 393	99.35 240	98.11 442	99.41 372	94.83 531	97.92 498	98.99 470	98.02 298	99.85 300

test_8					99.34 402	99.31 247	98.08 446	99.40 379	94.90 528	97.87 503	98.97 475	98.02 298	99.84 318

agg_prior					99.35 393	99.36 237		99.39 382		97.76 511			99.85 300

test_prior4						99.19 282	98.00 456

test_prior2							97.95 462		97.87 448	98.05 492	99.05 461	97.90 307		95.99 486	99.49 408

旧先验2							97.94 463		95.33 522	98.94 418			99.88 244	96.75 442

新几何2							98.04 450

原ACMM2							97.92 465

testdata2													99.89 228	95.99 486

segment_acmp												98.37 257

testdata1							97.72 477		97.86 450

plane_prior7					99.58 289	99.38 228

plane_prior6					99.47 359	99.26 258						97.24 349

plane_prior4											99.25 425

plane_prior3						99.31 247			98.36 394	99.14 395

plane_prior2							98.80 345		98.94 308

plane_prior1					99.51 337

plane_prior						99.24 266	98.42 411		97.87 448						99.71 332

n2								0.00 570

nn								0.00 570

door-mid								99.83 116

test11								99.29 413

door								99.77 171

HQP5-MVS						98.94 328

HQP-NCC					99.31 410		97.98 458		97.45 470	98.15 486

ACMP_Plane					99.31 410		97.98 458		97.45 470	98.15 486

BP-MVS														94.73 515

HQP3-MVS								99.37 388							99.67 355

HQP2-MVS												96.67 375

NP-MVS					99.40 379	99.13 294					98.83 489

MDTV_nov1_ep13			97.73 431		98.70 509	90.83 552	99.15 231	98.02 509	98.51 377	98.82 435	99.61 286	90.98 486	99.66 481	96.89 433	98.92 473

ACMMP++_ref															99.94 136

ACMMP++															99.79 280

Test By Simon												98.41 251

High-resolution multi-view benchmark