High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 4	99.98 3	99.76 71	99.12 246	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

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 4	99.97 6	99.74 88	99.01 287	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_fmvsmvis_n_1920		99.84 18	99.86 13	99.81 55	99.88 47	99.55 174	99.17 221	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

fmvsm_l_mol_unc0.5_1		99.85 12	99.82 25	99.94 2	99.93 24	99.86 18	98.72 358	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_fmvsm_n_1920		99.84 18	99.85 17	99.83 42	99.82 100	99.70 110	99.17 221	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

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

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

test_fmvsmconf_n		99.85 12	99.84 20	99.88 20	99.91 32	99.73 91	98.97 306	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

fmvsm_s_conf0.5_n_6		99.80 31	99.78 40	99.85 33	99.78 147	99.78 58	99.00 293	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

fmvsm_s_conf0.5_n_9		99.82 25	99.82 25	99.82 47	99.83 91	99.59 161	98.97 306	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_l_conf0.5_n_3		99.85 12	99.83 21	99.92 3	99.88 47	99.86 18	99.08 263	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

fmvsm_l_conf0.5_n_9		99.83 22	99.81 29	99.89 12	99.86 61	99.80 52	98.94 315	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_conf0.1_n		99.86 10	99.85 17	99.89 12	99.93 24	99.78 58	99.07 268	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_vis1_n_1920		99.72 54	99.88 7	99.27 337	99.93 24	97.84 440	99.34 150	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_fmvs3		99.83 22	99.93 2	99.53 233	99.96 7	98.62 378	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

mvsany_test3		99.85 12	99.88 7	99.75 99	99.95 15	99.37 232	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

fmvsm_s_conf0.5_n_4		99.78 38	99.78 40	99.79 73	99.75 183	99.56 170	98.98 304	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

wuyk23d		97.58 438	99.13 227	92.93 533	99.69 233	99.49 185	99.52 95	99.77 171	97.97 434	99.96 34	99.79 121	99.84 17	99.94 99	95.85 492	99.82 257	79.36 554

fmvsm_s_conf0.5_n_7		99.73 53	99.78 40	99.60 196	99.74 194	98.93 330	98.85 330	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

cdsmvs_eth3d_5k		24.88 525	33.17 527	0.00 543	0.00 567	0.00 570	0.00 555	99.62 266	0.00 562	0.00 563	99.13 446	99.82 19	0.00 564	0.00 562	0.00 562	0.00 559

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_cas_vis1_n_1920		99.76 47	99.86 13	99.45 260	99.93 24	98.40 400	99.30 168	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_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	99.88 243	99.98 1	100.00 1	99.98 5

fmvsm_s_conf0.5_n		99.83 22	99.81 29	99.87 27	99.85 76	99.78 58	99.03 278	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

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

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

mvsany_test1		99.44 156	99.45 142	99.40 284	99.37 385	98.64 375	97.90 467	99.59 292	99.27 248	99.92 60	99.82 92	99.74 27	99.93 121	99.55 86	99.87 218	99.63 178

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

fmvsm_s_conf0.5_n_5		99.78 38	99.76 50	99.85 33	99.79 138	99.72 96	98.84 333	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

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

XVG-OURS		99.21 238	99.06 253	99.65 161	99.82 100	99.62 145	97.87 468	99.74 191	98.36 393	99.66 224	99.68 229	99.71 29	99.90 205	96.84 437	99.88 204	99.43 321

XVG-OURS-SEG-HR		99.16 255	98.99 286	99.66 154	99.84 82	99.64 137	98.25 424	99.73 196	98.39 389	99.63 239	99.43 367	99.70 32	99.90 205	97.34 393	98.64 494	99.44 314

DeepC-MVS	98.90 4	99.62 95	99.61 90	99.67 146	99.72 203	99.44 206	99.24 194	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
fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 4	99.95 15	99.82 42	99.10 255	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

fmvsm_l_conf0.5_n_a		99.80 31	99.79 35	99.84 39	99.88 47	99.64 137	99.12 246	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

mmtdpeth		99.78 38	99.83 21	99.66 154	99.85 76	99.05 309	99.79 15	99.97 22	100.00 1	99.43 319	99.94 20	99.64 36	99.94 99	99.83 47	99.99 19	99.98 5

ACMH	98.42 6	99.59 102	99.54 117	99.72 123	99.86 61	99.62 145	99.56 88	99.79 153	98.77 342	99.80 127	99.85 69	99.64 36	99.85 299	98.70 253	99.89 193	99.70 108
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs5depth		99.88 6	99.91 3	99.80 65	99.92 30	99.42 213	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

GeoE		99.69 60	99.66 73	99.78 77	99.76 165	99.76 71	99.60 79	99.82 123	99.46 207	99.75 166	99.56 321	99.63 38	99.95 82	99.43 107	99.88 204	99.62 190

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	99.87 260	99.54 88	99.92 159	99.63 178

DSMNet-mixed		99.48 136	99.65 75	98.95 387	99.71 209	97.27 468	99.50 103	99.82 123	99.59 181	99.41 328	99.85 69	99.62 41	100.00 1	99.53 91	99.89 193	99.59 217

casdiffseed414692147		99.68 65	99.68 64	99.67 146	99.86 61	99.65 130	99.32 159	99.87 81	99.75 111	99.77 152	99.80 109	99.61 42	99.68 469	99.21 147	99.95 117	99.67 137

Vis-MVSNet		99.75 50	99.74 54	99.79 73	99.88 47	99.66 124	99.69 45	99.92 48	99.67 145	99.77 152	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
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_l_conf0.5_n		99.80 31	99.78 40	99.85 33	99.88 47	99.66 124	99.11 251	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

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	99.87 260	99.59 79	99.74 312	99.71 105

E5new		99.68 65	99.67 66	99.70 134	99.87 56	99.62 145	99.41 123	99.84 106	99.68 137	99.77 152	99.81 99	99.59 47	99.78 398	99.13 175	99.96 92	99.70 108

E6new		99.68 65	99.67 66	99.70 134	99.86 61	99.62 145	99.41 123	99.84 106	99.68 137	99.77 152	99.81 99	99.59 47	99.78 398	99.13 175	99.96 92	99.70 108

E6		99.68 65	99.67 66	99.70 134	99.86 61	99.62 145	99.41 123	99.84 106	99.68 137	99.77 152	99.81 99	99.59 47	99.78 398	99.13 175	99.96 92	99.70 108

E5		99.68 65	99.67 66	99.70 134	99.87 56	99.62 145	99.41 123	99.84 106	99.68 137	99.77 152	99.81 99	99.59 47	99.78 398	99.13 175	99.96 92	99.70 108

fmvsm_s_conf0.5_n_a		99.82 25	99.79 35	99.89 12	99.85 76	99.82 42	99.03 278	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_f		99.75 50	99.88 7	99.37 296	99.96 7	98.21 413	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

SPE-MVS-test		99.68 65	99.70 58	99.64 168	99.57 298	99.83 34	99.78 17	99.97 22	99.92 46	99.50 301	99.38 385	99.57 53	99.95 82	99.69 65	99.90 177	99.15 398

PMMVS2		99.48 136	99.45 142	99.57 211	99.76 165	98.99 316	98.09 443	99.90 65	98.95 306	99.78 140	99.58 309	99.57 53	99.93 121	99.48 98	99.95 117	99.79 76

EC-MVSNet		99.69 60	99.69 61	99.68 142	99.71 209	99.91 4	99.76 23	99.96 31	99.86 66	99.51 298	99.39 382	99.57 53	99.93 121	99.64 74	99.86 226	99.20 386

viewmacassd2359aftdt		99.63 87	99.61 90	99.68 142	99.84 82	99.61 155	99.14 234	99.87 81	99.71 123	99.75 166	99.77 146	99.54 56	99.72 441	98.91 217	99.96 92	99.70 108

SD-MVS		99.01 298	99.30 189	98.15 461	99.50 342	99.40 221	98.94 315	99.61 274	99.22 261	99.75 166	99.82 92	99.54 56	95.51 554	97.48 384	99.87 218	99.54 250
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
casdiffmvs_mvg		99.68 65	99.68 64	99.69 140	99.81 113	99.59 161	99.29 176	99.90 65	99.71 123	99.79 134	99.73 177	99.54 56	99.84 317	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
fmvsm_s_conf0.5_n_3		99.79 35	99.77 46	99.85 33	99.81 113	99.71 102	98.97 306	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

sd_testset		99.78 38	99.78 40	99.80 65	99.80 124	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

SDMVSNet		99.77 45	99.77 46	99.76 88	99.80 124	99.65 130	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

CS-MVS		99.67 77	99.70 58	99.58 203	99.53 327	99.84 27	99.79 15	99.96 31	99.90 50	99.61 256	99.41 371	99.51 62	99.95 82	99.66 70	99.89 193	98.96 447

test_fmvs2		99.72 54	99.85 17	99.34 310	99.91 32	98.08 427	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

E4		99.61 99	99.59 97	99.66 154	99.84 82	99.53 177	99.08 263	99.84 106	99.65 158	99.74 177	99.80 109	99.45 64	99.77 411	98.93 214	99.95 117	99.69 121

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

SSM_0407		99.56 107	99.56 111	99.54 228	99.71 209	99.24 265	99.15 230	99.84 106	99.80 96	99.78 140	99.70 207	99.44 66	99.93 121	98.74 242	99.90 177	99.45 299

SSM_0404		99.57 103	99.58 101	99.54 228	99.76 165	99.28 251	99.19 212	99.84 106	99.80 96	99.78 140	99.70 207	99.44 66	99.93 121	98.74 242	99.95 117	99.41 327

fmvsm_s_conf0.1_n_2		99.81 29	99.78 40	99.89 12	99.93 24	99.76 71	98.92 319	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

tt0805		99.63 87	99.57 106	99.81 55	99.87 56	99.88 12	99.58 83	98.70 471	99.72 117	99.91 63	99.60 296	99.43 68	99.81 380	99.81 52	99.53 398	99.73 96

fmvsm_s_conf0.5_n_2		99.78 38	99.75 52	99.88 20	99.82 100	99.76 71	98.88 324	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

ETV-MVS		99.18 247	99.18 217	99.16 356	99.34 401	99.28 251	99.12 246	99.79 153	99.48 199	98.93 419	98.55 507	99.40 71	99.93 121	98.51 275	99.52 401	98.28 500

dtuonlycased		99.24 221	99.47 133	98.56 438	99.90 38	96.17 498	97.62 485	99.85 96	99.66 152	99.86 97	99.50 346	99.39 72	99.93 121	99.55 86	99.85 233	99.59 217

xiu_mvs_v1_base_debu		99.23 224	99.34 176	98.91 398	99.59 278	98.23 410	98.47 402	99.66 241	99.61 172	99.68 209	98.94 479	99.39 72	99.97 45	99.18 156	99.55 391	98.51 490

xiu_mvs_v1_base		99.23 224	99.34 176	98.91 398	99.59 278	98.23 410	98.47 402	99.66 241	99.61 172	99.68 209	98.94 479	99.39 72	99.97 45	99.18 156	99.55 391	98.51 490

xiu_mvs_v1_base_debi		99.23 224	99.34 176	98.91 398	99.59 278	98.23 410	98.47 402	99.66 241	99.61 172	99.68 209	98.94 479	99.39 72	99.97 45	99.18 156	99.55 391	98.51 490

ACMM	98.09 11	99.46 148	99.38 162	99.72 123	99.80 124	99.69 115	99.13 241	99.65 251	98.99 299	99.64 234	99.72 187	99.39 72	99.86 280	98.23 300	99.81 267	99.60 210
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v2_base		99.02 292	99.11 234	98.77 420	99.37 385	98.09 424	98.13 437	99.51 343	99.47 204	99.42 322	98.54 508	99.38 77	99.97 45	98.83 223	99.33 431	98.24 504

XXY-MVS		99.71 57	99.67 66	99.81 55	99.89 41	99.72 96	99.59 80	99.82 123	99.39 229	99.82 113	99.84 77	99.38 77	99.91 186	99.38 116	99.93 150	99.80 68

LPG-MVS_test		99.22 233	99.05 260	99.74 104	99.82 100	99.63 143	99.16 227	99.73 196	97.56 461	99.64 234	99.69 216	99.37 79	99.89 227	96.66 447	99.87 218	99.69 121

LGP-MVS_train				99.74 104	99.82 100	99.63 143		99.73 196	97.56 461	99.64 234	99.69 216	99.37 79	99.89 227	96.66 447	99.87 218	99.69 121

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	99.78 140	99.92 28	99.37 79	99.88 243	98.93 214	99.95 117	99.60 210

mamba_0408		99.54 117	99.55 113	99.54 228	99.71 209	99.24 265	99.27 182	99.79 153	99.72 117	99.78 140	99.64 250	99.36 82	99.93 121	98.74 242	99.90 177	99.45 299

SSM_04072		99.55 112	99.55 113	99.55 222	99.71 209	99.24 265	99.27 182	99.79 153	99.72 117	99.78 140	99.64 250	99.36 82	99.97 45	98.74 242	99.90 177	99.45 299

testgi		99.29 207	99.26 203	99.37 296	99.75 183	98.81 351	98.84 333	99.89 69	98.38 391	99.75 166	99.04 462	99.36 82	99.86 280	99.08 185	99.25 444	99.45 299

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

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

Fast-Effi-MVS+		99.02 292	98.87 308	99.46 257	99.38 382	99.50 184	99.04 275	99.79 153	97.17 485	98.62 454	98.74 494	99.34 86	99.95 82	98.32 292	99.41 421	98.92 455

casdiffmvs		99.63 87	99.61 90	99.67 146	99.79 138	99.59 161	99.13 241	99.85 96	99.79 100	99.76 161	99.72 187	99.33 88	99.82 363	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
SSC-MVS3.2		99.64 86	99.67 66	99.56 215	99.75 183	98.98 318	98.96 310	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

new-patchmatchnet		99.35 192	99.57 106	98.71 428	99.82 100	96.62 486	98.55 388	99.75 185	99.50 194	99.88 83	99.87 57	99.31 90	99.88 243	99.43 107	100.00 1	99.62 190

HPM-MVS_fast		99.43 160	99.30 189	99.80 65	99.83 91	99.81 48	99.52 95	99.70 218	98.35 399	99.51 298	99.50 346	99.31 90	99.88 243	98.18 307	99.84 239	99.69 121

EG-PatchMatch MVS		99.57 103	99.56 111	99.62 185	99.77 160	99.33 242	99.26 187	99.76 179	99.32 240	99.80 127	99.78 134	99.29 92	99.87 260	99.15 165	99.91 173	99.66 151

DeepPCF-MVS	98.42 6	99.18 247	99.02 269	99.67 146	99.22 429	99.75 80	97.25 504	99.47 355	98.72 347	99.66 224	99.70 207	99.29 92	99.63 491	98.07 318	99.81 267	99.62 190

pcd_1.5k_mvsjas		16.61 526	22.14 529	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	99.28 94	0.00 564	0.00 562	0.00 562	0.00 559

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

PS-MVSNAJ		99.00 301	99.08 247	98.76 421	99.37 385	98.10 423	98.00 455	99.51 343	99.47 204	99.41 328	98.50 510	99.28 94	99.97 45	98.83 223	99.34 430	98.20 508

TSAR-MVS + MP.		99.34 197	99.24 209	99.63 176	99.82 100	99.37 232	99.26 187	99.35 393	98.77 342	99.57 267	99.70 207	99.27 97	99.88 243	97.71 356	99.75 305	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
E2		99.54 117	99.51 123	99.62 185	99.78 147	99.47 190	99.01 287	99.82 123	99.55 185	99.69 202	99.77 146	99.26 98	99.76 418	98.82 226	99.93 150	99.62 190

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

ACMH+	98.40 8	99.50 128	99.43 150	99.71 129	99.86 61	99.76 71	99.32 159	99.77 171	99.53 189	99.77 152	99.76 156	99.26 98	99.78 398	97.77 347	99.88 204	99.60 210

dtuplus		99.52 123	99.55 113	99.43 268	99.76 165	98.90 336	98.71 362	99.89 69	99.67 145	99.79 134	99.77 146	99.25 102	99.81 380	99.18 156	99.96 92	99.57 230

E3		99.54 117	99.51 123	99.62 185	99.78 147	99.47 190	99.01 287	99.82 123	99.55 185	99.69 202	99.77 146	99.25 102	99.76 418	98.82 226	99.93 150	99.62 190

HPM-MVS		99.25 217	99.07 251	99.78 77	99.81 113	99.75 80	99.61 73	99.67 236	97.72 456	99.35 344	99.25 424	99.23 104	99.92 155	97.21 411	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
DELS-MVS		99.34 197	99.30 189	99.48 251	99.51 336	99.36 236	98.12 439	99.53 333	99.36 235	99.41 328	99.61 286	99.22 105	99.87 260	99.21 147	99.68 348	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
hybridcas		99.65 84	99.63 83	99.70 134	99.85 76	99.67 121	99.30 168	99.87 81	99.67 145	99.81 120	99.77 146	99.21 106	99.81 380	99.24 140	99.94 136	99.61 205

test_fmvs1_n		99.68 65	99.81 29	99.28 331	99.95 15	97.93 436	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

pmmvs-eth3d		99.48 136	99.47 133	99.51 239	99.77 160	99.41 220	98.81 341	99.66 241	99.42 223	99.75 166	99.66 241	99.20 108	99.76 418	98.98 200	99.99 19	99.36 343

COLMAP_ROB	98.06 12	99.45 152	99.37 165	99.70 134	99.83 91	99.70 110	99.38 133	99.78 166	99.53 189	99.67 217	99.78 134	99.19 109	99.86 280	97.32 395	99.87 218	99.55 238
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
viewmanbaseed2359cas		99.50 128	99.47 133	99.61 192	99.73 198	99.52 182	99.03 278	99.83 116	99.49 196	99.65 228	99.64 250	99.18 110	99.71 446	98.73 247	99.92 159	99.58 223

TSAR-MVS + GP.		99.12 266	99.04 266	99.38 291	99.34 401	99.16 288	98.15 434	99.29 412	98.18 417	99.63 239	99.62 276	99.18 110	99.68 469	98.20 303	99.74 312	99.30 364

icg_test_0407_2		99.30 205	99.29 195	99.31 323	99.71 209	98.55 386	98.17 431	99.71 209	99.41 224	99.73 183	99.60 296	99.17 112	99.92 155	98.45 279	99.70 334	99.45 299

IMVS_0407		99.38 180	99.42 153	99.28 331	99.71 209	98.55 386	99.27 182	99.71 209	99.41 224	99.73 183	99.60 296	99.17 112	99.83 340	98.45 279	99.70 334	99.45 299

MVS_111021_HR		99.12 266	99.02 269	99.40 284	99.50 342	99.11 296	97.92 464	99.71 209	98.76 345	99.08 402	99.47 359	99.17 112	99.54 506	97.85 340	99.76 297	99.54 250

3Dnovator	99.15 2	99.43 160	99.36 170	99.65 161	99.39 379	99.42 213	99.70 38	99.56 309	99.23 257	99.35 344	99.80 109	99.17 112	99.95 82	98.21 302	99.84 239	99.59 217

EGC-MVSNET		89.05 517	85.52 520	99.64 168	99.89 41	99.78 58	99.56 88	99.52 338	24.19 557	49.96 560	99.83 84	99.15 116	99.92 155	97.71 356	99.85 233	99.21 381

UA-Net		99.78 38	99.76 50	99.86 31	99.72 203	99.71 102	99.91 4	99.95 39	99.96 29	99.71 194	99.91 32	99.15 116	99.97 45	99.50 96	100.00 1	99.90 31

baseline		99.63 87	99.62 86	99.66 154	99.80 124	99.62 145	99.44 120	99.80 144	99.71 123	99.72 189	99.69 216	99.15 116	99.83 340	99.32 129	99.94 136	99.53 259

OPM-MVS		99.26 215	99.13 227	99.63 176	99.70 225	99.61 155	98.58 380	99.48 352	98.50 378	99.52 291	99.63 266	99.14 119	99.76 418	97.89 332	99.77 292	99.51 273
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Effi-MVS+		99.06 281	98.97 291	99.34 310	99.31 409	98.98 318	98.31 419	99.91 58	98.81 333	98.79 439	98.94 479	99.14 119	99.84 317	98.79 233	98.74 487	99.20 386

fmvsm_s_conf0.5_n_11		99.76 47	99.75 52	99.81 55	99.81 113	99.53 177	99.15 230	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

ttmdpeth		99.48 136	99.55 113	99.29 328	99.76 165	98.16 418	99.33 156	99.95 39	99.79 100	99.36 340	99.89 42	99.13 121	99.77 411	99.09 183	99.64 361	99.93 22

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

fmvsm_s_conf0.5_n_10		99.77 45	99.73 55	99.88 20	99.81 113	99.75 80	99.06 269	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

IMVS_0403		99.37 185	99.39 159	99.28 331	99.71 209	98.55 386	99.19 212	99.71 209	99.41 224	99.67 217	99.60 296	99.12 124	99.84 317	98.45 279	99.70 334	99.45 299

nrg030		99.70 58	99.66 73	99.82 47	99.76 165	99.84 27	99.61 73	99.70 218	99.93 44	99.78 140	99.68 229	99.10 126	99.78 398	99.45 104	99.96 92	99.83 60

MSDG		99.08 276	98.98 289	99.37 296	99.60 272	99.13 293	97.54 488	99.74 191	98.84 328	99.53 289	99.55 330	99.10 126	99.79 394	97.07 422	99.86 226	99.18 391

viewcassd2359sk11		99.48 136	99.45 142	99.58 203	99.73 198	99.42 213	98.96 310	99.80 144	99.44 212	99.63 239	99.74 172	99.09 128	99.76 418	98.72 249	99.91 173	99.57 230

PC_three_1452									97.56 461	99.68 209	99.41 371	99.09 128	97.09 550	96.66 447	99.60 377	99.62 190

v1240		99.56 107	99.58 101	99.51 239	99.80 124	99.00 314	99.00 293	99.65 251	99.15 279	99.90 68	99.75 164	99.09 128	99.88 243	99.90 38	99.96 92	99.67 137

MVS_111021_LR		99.13 263	99.03 268	99.42 271	99.58 288	99.32 245	97.91 466	99.73 196	98.68 352	99.31 358	99.48 355	99.09 128	99.66 480	97.70 359	99.77 292	99.29 367

viewmambaseed2359dif		99.47 146	99.50 126	99.37 296	99.70 225	98.80 354	98.67 366	99.92 48	99.49 196	99.77 152	99.71 197	99.08 132	99.78 398	99.20 151	99.94 136	99.54 250

v1921920		99.56 107	99.57 106	99.55 222	99.75 183	99.11 296	99.05 270	99.61 274	99.15 279	99.88 83	99.71 197	99.08 132	99.87 260	99.90 38	99.97 78	99.66 151

v1192		99.57 103	99.57 106	99.57 211	99.77 160	99.22 271	99.04 275	99.60 286	99.18 265	99.87 93	99.72 187	99.08 132	99.85 299	99.89 41	99.98 55	99.66 151

Casviewmamba		99.63 87	99.60 94	99.73 114	99.84 82	99.72 96	99.36 145	99.87 81	99.67 145	99.74 177	99.73 177	99.07 135	99.83 340	99.14 172	99.93 150	99.62 190

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	99.07 135	99.92 155	99.68 67	99.97 78	99.67 137

fmvsm_s_conf0.5_n_8		99.76 47	99.72 56	99.88 20	99.82 100	99.75 80	99.02 282	99.87 81	99.98 19	99.98 14	99.81 99	99.07 135	99.97 45	99.91 34	99.99 19	99.92 26

MGCFI-Net		99.02 292	99.01 275	99.06 376	99.11 453	98.60 379	99.63 64	99.67 236	99.63 164	98.58 458	97.65 530	99.07 135	99.57 501	98.85 221	98.92 472	99.03 437

test_0402		99.22 233	99.14 224	99.45 260	99.79 138	99.43 210	99.28 178	99.68 231	99.54 187	99.40 334	99.56 321	99.07 135	99.82 363	96.01 482	99.96 92	99.11 407

ACMP	97.51 14	99.05 285	98.84 312	99.67 146	99.78 147	99.55 174	98.88 324	99.66 241	97.11 489	99.47 308	99.60 296	99.07 135	99.89 227	96.18 477	99.85 233	99.58 223
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CLD-MVS		98.76 337	98.57 343	99.33 313	99.57 298	98.97 321	97.53 490	99.55 316	96.41 504	99.27 365	99.13 446	99.07 135	99.78 398	96.73 443	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
FE-MVSNET2		99.68 65	99.67 66	99.72 123	99.86 61	99.68 118	99.46 117	99.88 75	99.62 167	99.87 93	99.85 69	99.06 142	99.85 299	99.44 105	99.98 55	99.63 178

viewdifsd2359ckpt07		99.51 125	99.50 126	99.52 235	99.80 124	99.19 281	98.92 319	99.88 75	99.72 117	99.64 234	99.62 276	99.06 142	99.81 380	98.96 205	99.94 136	99.56 234

PVSNet_Blended_VisFu		99.40 173	99.38 162	99.44 264	99.90 38	98.66 368	98.94 315	99.91 58	97.97 434	99.79 134	99.73 177	99.05 144	99.97 45	99.15 165	99.99 19	99.68 128

sasdasda		99.02 292	99.00 279	99.09 368	99.10 455	98.70 363	99.61 73	99.66 241	99.63 164	98.64 451	97.65 530	99.04 145	99.54 506	98.79 233	98.92 472	99.04 434

canonicalmvs		99.02 292	99.00 279	99.09 368	99.10 455	98.70 363	99.61 73	99.66 241	99.63 164	98.64 451	97.65 530	99.04 145	99.54 506	98.79 233	98.92 472	99.04 434

SteuartSystems-ACMMP		99.30 205	99.14 224	99.76 88	99.87 56	99.66 124	99.18 216	99.60 286	98.55 369	99.57 267	99.67 235	99.03 147	99.94 99	97.01 423	99.80 274	99.69 121
Skip Steuart: Steuart Systems R&D Blog.
MED-MVS		99.51 125	99.42 153	99.80 65	99.76 165	99.65 130	99.38 133	99.78 166	99.77 108	99.81 120	99.78 134	99.02 148	99.90 205	97.69 365	99.76 297	99.85 51

reproduce_model		99.50 128	99.40 158	99.83 42	99.60 272	99.83 34	99.12 246	99.68 231	99.49 196	99.80 127	99.79 121	99.01 149	99.93 121	98.24 299	99.82 257	99.73 96

DVP-MVS++		99.38 180	99.25 207	99.77 81	99.03 468	99.77 64	99.74 27	99.61 274	99.18 265	99.76 161	99.61 286	99.00 150	99.92 155	97.72 354	99.60 377	99.62 190

OPU-MVS				99.29 328	99.12 448	99.44 206	99.20 206				99.40 377	99.00 150	98.84 540	96.54 455	99.60 377	99.58 223

viewdifsd2359ckpt11		99.62 95	99.64 80	99.56 215	99.86 61	99.19 281	99.02 282	99.93 44	99.83 82	99.88 83	99.81 99	98.99 152	99.83 340	99.48 98	99.96 92	99.65 160

viewmsd2359difaftdt		99.62 95	99.64 80	99.56 215	99.86 61	99.19 281	99.02 282	99.93 44	99.83 82	99.88 83	99.81 99	98.99 152	99.83 340	99.48 98	99.96 92	99.65 160

test_vis1_n		99.68 65	99.79 35	99.36 302	99.94 18	98.18 416	99.52 95	100.00 1	99.86 66	100.00 1	99.88 51	98.99 152	99.96 70	99.97 4	99.96 92	99.95 16

EI-MVSNet-UG-set		99.48 136	99.50 126	99.42 271	99.57 298	98.65 372	99.24 194	99.46 358	99.68 137	99.80 127	99.66 241	98.99 152	99.89 227	99.19 153	99.90 177	99.72 100

Fast-Effi-MVS+-dtu		99.20 240	99.12 231	99.43 268	99.25 424	99.69 115	99.05 270	99.82 123	99.50 194	98.97 414	99.05 460	98.98 156	99.98 27	98.20 303	99.24 446	98.62 480

FMVSNet1		99.66 78	99.63 83	99.73 114	99.78 147	99.77 64	99.68 48	99.70 218	99.67 145	99.82 113	99.83 84	98.98 156	99.90 205	99.24 140	99.97 78	99.53 259

EI-MVSNet-Vis-set		99.47 146	99.49 130	99.42 271	99.57 298	98.66 368	99.24 194	99.46 358	99.67 145	99.79 134	99.65 248	98.97 158	99.89 227	99.15 165	99.89 193	99.71 105

PHI-MVS		99.11 271	98.95 295	99.59 199	99.13 446	99.59 161	99.17 221	99.65 251	97.88 446	99.25 371	99.46 362	98.97 158	99.80 390	97.26 404	99.82 257	99.37 340

TinyColmap		98.97 305	98.93 297	99.07 374	99.46 362	98.19 414	97.75 473	99.75 185	98.79 337	99.54 284	99.70 207	98.97 158	99.62 492	96.63 451	99.83 247	99.41 327

lecture		99.56 107	99.48 131	99.81 55	99.78 147	99.86 18	99.50 103	99.70 218	99.59 181	99.75 166	99.71 197	98.94 161	99.92 155	98.59 266	99.76 297	99.66 151

reproduce-ours		99.46 148	99.35 174	99.82 47	99.56 312	99.83 34	99.05 270	99.65 251	99.45 210	99.78 140	99.78 134	98.93 162	99.93 121	98.11 313	99.81 267	99.70 108

our_new_method		99.46 148	99.35 174	99.82 47	99.56 312	99.83 34	99.05 270	99.65 251	99.45 210	99.78 140	99.78 134	98.93 162	99.93 121	98.11 313	99.81 267	99.70 108

SMA-MVS		99.19 243	99.00 279	99.73 114	99.46 362	99.73 91	99.13 241	99.52 338	97.40 473	99.57 267	99.64 250	98.93 162	99.83 340	97.61 375	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
viewdifsd2359ckpt13		99.42 164	99.37 165	99.57 211	99.72 203	99.46 198	99.01 287	99.80 144	99.20 262	99.51 298	99.60 296	98.92 165	99.70 450	98.65 262	99.90 177	99.55 238

XVG-ACMP-BASELINE		99.23 224	99.10 243	99.63 176	99.82 100	99.58 166	98.83 336	99.72 205	98.36 393	99.60 259	99.71 197	98.92 165	99.91 186	97.08 421	99.84 239	99.40 330

CSCG		99.37 185	99.29 195	99.60 196	99.71 209	99.46 198	99.43 122	99.85 96	98.79 337	99.41 328	99.60 296	98.92 165	99.92 155	98.02 319	99.92 159	99.43 321

SED-MVS		99.40 173	99.28 198	99.77 81	99.69 233	99.82 42	99.20 206	99.54 322	99.13 281	99.82 113	99.63 266	98.91 168	99.92 155	97.85 340	99.70 334	99.58 223

test_241102_ONE					99.69 233	99.82 42		99.54 322	99.12 284	99.82 113	99.49 351	98.91 168	99.52 512

Gipuma		99.57 103	99.59 97	99.49 245	99.98 3	99.71 102	99.72 33	99.84 106	99.81 92	99.94 48	99.78 134	98.91 168	99.71 446	98.41 284	99.95 117	99.05 431
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepC-MVS_fast	98.47 5	99.23 224	99.12 231	99.56 215	99.28 418	99.22 271	98.99 301	99.40 378	99.08 287	99.58 264	99.64 250	98.90 171	99.83 340	97.44 387	99.75 305	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
E3new		99.42 164	99.37 165	99.56 215	99.68 242	99.38 227	98.93 318	99.79 153	99.30 243	99.55 280	99.69 216	98.88 172	99.76 418	98.63 264	99.89 193	99.53 259

ITE_SJBPF				99.38 291	99.63 263	99.44 206		99.73 196	98.56 367	99.33 350	99.53 335	98.88 172	99.68 469	96.01 482	99.65 359	99.02 442

diffmvs_AUTHOR		99.48 136	99.48 131	99.47 253	99.80 124	98.89 339	98.71 362	99.82 123	99.79 100	99.66 224	99.63 266	98.87 174	99.88 243	99.13 175	99.95 117	99.62 190

SF-MVS		99.10 274	98.93 297	99.62 185	99.58 288	99.51 183	99.13 241	99.65 251	97.97 434	99.42 322	99.61 286	98.86 175	99.87 260	96.45 464	99.68 348	99.49 284

tfpnnormal		99.43 160	99.38 162	99.60 196	99.87 56	99.75 80	99.59 80	99.78 166	99.71 123	99.90 68	99.69 216	98.85 176	99.90 205	97.25 408	99.78 288	99.15 398

ZNCC-MVS		99.22 233	99.04 266	99.77 81	99.76 165	99.73 91	99.28 178	99.56 309	98.19 416	99.14 394	99.29 414	98.84 177	99.92 155	97.53 382	99.80 274	99.64 172

MP-MVS-pluss		99.14 260	98.92 301	99.80 65	99.83 91	99.83 34	98.61 373	99.63 263	96.84 498	99.44 315	99.58 309	98.81 178	99.91 186	97.70 359	99.82 257	99.67 137
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VPA-MVSNet		99.66 78	99.62 86	99.79 73	99.68 242	99.75 80	99.62 67	99.69 227	99.85 72	99.80 127	99.81 99	98.81 178	99.91 186	99.47 101	99.88 204	99.70 108

test20.03		99.55 112	99.54 117	99.58 203	99.79 138	99.37 232	99.02 282	99.89 69	99.60 179	99.82 113	99.62 276	98.81 178	99.89 227	99.43 107	99.86 226	99.47 292

PGM-MVS		99.20 240	99.01 275	99.77 81	99.75 183	99.71 102	99.16 227	99.72 205	97.99 432	99.42 322	99.60 296	98.81 178	99.93 121	96.91 430	99.74 312	99.66 151

HFP-MVS		99.25 217	99.08 247	99.76 88	99.73 198	99.70 110	99.31 165	99.59 292	98.36 393	99.36 340	99.37 389	98.80 182	99.91 186	97.43 388	99.75 305	99.68 128

viewmamba		99.49 133	99.51 123	99.42 271	99.75 183	98.90 336	98.85 330	99.85 96	99.69 133	99.73 183	99.67 235	98.79 183	99.82 363	99.28 137	99.95 117	99.54 250

APDe-MVS		99.48 136	99.36 170	99.85 33	99.55 316	99.81 48	99.50 103	99.69 227	98.99 299	99.75 166	99.71 197	98.79 183	99.93 121	98.46 278	99.85 233	99.80 68
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CP-MVS		99.23 224	99.05 260	99.75 99	99.66 252	99.66 124	99.38 133	99.62 266	98.38 391	99.06 406	99.27 418	98.79 183	99.94 99	97.51 383	99.82 257	99.66 151

MSLP-MVS++		99.05 285	99.09 245	98.91 398	99.21 431	98.36 405	98.82 340	99.47 355	98.85 324	98.90 425	99.56 321	98.78 186	99.09 533	98.57 269	99.68 348	99.26 370

MVS_Test		99.28 209	99.31 184	99.19 353	99.35 392	98.79 355	99.36 145	99.49 351	99.17 272	99.21 381	99.67 235	98.78 186	99.66 480	99.09 183	99.66 357	99.10 410

3Dnovator+	98.92 3	99.35 192	99.24 209	99.67 146	99.35 392	99.47 190	99.62 67	99.50 347	99.44 212	99.12 398	99.78 134	98.77 188	99.94 99	97.87 336	99.72 327	99.62 190

APD-MVS_3200maxsize		99.31 204	99.16 219	99.74 104	99.53 327	99.75 80	99.27 182	99.61 274	99.19 264	99.57 267	99.64 250	98.76 189	99.90 205	97.29 399	99.62 366	99.56 234

TranMVSNet+NR-MVSNet		99.54 117	99.47 133	99.76 88	99.58 288	99.64 137	99.30 168	99.63 263	99.61 172	99.71 194	99.56 321	98.76 189	99.96 70	99.14 172	99.92 159	99.68 128

test_vis1_rt		99.45 152	99.46 139	99.41 281	99.71 209	98.63 377	98.99 301	99.96 31	99.03 294	99.95 45	99.12 450	98.75 191	99.84 317	99.82 51	99.82 257	99.77 82

EIA-MVS		99.12 266	99.01 275	99.45 260	99.36 388	99.62 145	99.34 150	99.79 153	98.41 386	98.84 432	98.89 483	98.75 191	99.84 317	98.15 311	99.51 402	98.89 460

ACMMP_NAP		99.28 209	99.11 234	99.79 73	99.75 183	99.81 48	98.95 313	99.53 333	98.27 411	99.53 289	99.73 177	98.75 191	99.87 260	97.70 359	99.83 247	99.68 128

v10		99.69 60	99.69 61	99.66 154	99.81 113	99.39 225	99.66 57	99.75 185	99.60 179	99.92 60	99.87 57	98.75 191	99.86 280	99.90 38	99.99 19	99.73 96

region2R		99.23 224	99.05 260	99.77 81	99.76 165	99.70 110	99.31 165	99.59 292	98.41 386	99.32 353	99.36 394	98.73 195	99.93 121	97.29 399	99.74 312	99.67 137

SD_0403		97.42 448	96.90 464	98.98 383	99.54 318	97.90 438	99.52 95	99.54 322	99.34 236	97.87 502	98.85 486	98.72 196	99.64 489	78.93 555	99.83 247	99.40 330

test_fmvs1		99.48 136	99.65 75	98.97 384	99.54 318	97.16 471	99.11 251	99.98 14	99.78 103	99.96 34	99.81 99	98.72 196	99.97 45	99.95 15	99.97 78	99.79 76

LS3D		99.24 221	99.11 234	99.61 192	98.38 520	99.79 55	99.57 86	99.68 231	99.61 172	99.15 392	99.71 197	98.70 198	99.91 186	97.54 380	99.68 348	99.13 406

DP-MVS		99.48 136	99.39 159	99.74 104	99.57 298	99.62 145	99.29 176	99.61 274	99.87 63	99.74 177	99.76 156	98.69 199	99.87 260	98.20 303	99.80 274	99.75 90

AllTest		99.21 238	99.07 251	99.63 176	99.78 147	99.64 137	99.12 246	99.83 116	98.63 359	99.63 239	99.72 187	98.68 200	99.75 429	96.38 467	99.83 247	99.51 273

TestCases				99.63 176	99.78 147	99.64 137		99.83 116	98.63 359	99.63 239	99.72 187	98.68 200	99.75 429	96.38 467	99.83 247	99.51 273

LCM-MVSNet-Re		99.28 209	99.15 223	99.67 146	99.33 406	99.76 71	99.34 150	99.97 22	98.93 312	99.91 63	99.79 121	98.68 200	99.93 121	96.80 439	99.56 386	99.30 364

v1144		99.54 117	99.53 121	99.59 199	99.79 138	99.28 251	99.10 255	99.61 274	99.20 262	99.84 105	99.73 177	98.67 203	99.84 317	99.86 46	99.98 55	99.64 172

DTE-MVSNet		99.68 65	99.61 90	99.88 20	99.80 124	99.87 15	99.67 53	99.71 209	99.72 117	99.84 105	99.78 134	98.67 203	99.97 45	99.30 132	99.95 117	99.80 68

v144192		99.55 112	99.54 117	99.58 203	99.78 147	99.20 278	99.11 251	99.62 266	99.18 265	99.89 73	99.72 187	98.66 205	99.87 260	99.88 42	99.97 78	99.66 151

v8		99.68 65	99.69 61	99.65 161	99.80 124	99.40 221	99.66 57	99.76 179	99.64 162	99.93 53	99.85 69	98.66 205	99.84 317	99.88 42	99.99 19	99.71 105

GST-MVS		99.16 255	98.96 293	99.75 99	99.73 198	99.73 91	99.20 206	99.55 316	98.22 413	99.32 353	99.35 399	98.65 207	99.91 186	96.86 433	99.74 312	99.62 190

ppachtmachnet_test		98.89 322	99.12 231	98.20 460	99.66 252	95.24 520	97.63 483	99.68 231	99.08 287	99.78 140	99.62 276	98.65 207	99.88 243	98.02 319	99.96 92	99.48 288

PS-CasMVS		99.66 78	99.58 101	99.89 12	99.80 124	99.85 22	99.66 57	99.73 196	99.62 167	99.84 105	99.71 197	98.62 209	99.96 70	99.30 132	99.96 92	99.86 48

LF4IMVS		99.01 298	98.92 301	99.27 337	99.71 209	99.28 251	98.59 378	99.77 171	98.32 407	99.39 336	99.41 371	98.62 209	99.84 317	96.62 453	99.84 239	98.69 478

onestephybrid01		99.45 152	99.46 139	99.42 271	99.69 233	98.88 341	98.76 350	99.81 136	99.78 103	99.67 217	99.73 177	98.61 211	99.84 317	99.17 160	99.93 150	99.52 270

ACMMPR		99.23 224	99.06 253	99.76 88	99.74 194	99.69 115	99.31 165	99.59 292	98.36 393	99.35 344	99.38 385	98.61 211	99.93 121	97.43 388	99.75 305	99.67 137

API-MVS		98.38 384	98.39 370	98.35 448	98.83 492	99.26 257	99.14 234	99.18 438	98.59 365	98.66 450	98.78 492	98.61 211	99.57 501	94.14 523	99.56 386	96.21 533

test_one_0601					99.63 263	99.76 71		99.55 316	99.23 257	99.31 358	99.61 286	98.59 214

OMC-MVS		98.90 319	98.72 325	99.44 264	99.39 379	99.42 213	98.58 380	99.64 259	97.31 478	99.44 315	99.62 276	98.59 214	99.69 457	96.17 478	99.79 280	99.22 378

test_0728_THIRD									99.18 265	99.62 249	99.61 286	98.58 216	99.91 186	97.72 354	99.80 274	99.77 82

KinetiMVS		99.66 78	99.63 83	99.76 88	99.89 41	99.57 169	99.37 141	99.82 123	99.95 33	99.90 68	99.63 266	98.57 217	99.97 45	99.65 71	99.94 136	99.74 92

RE-MVS-def			99.13 227		99.54 318	99.74 88	99.26 187	99.62 266	99.16 274	99.52 291	99.64 250	98.57 217		97.27 402	99.61 374	99.54 250

ACMMP		99.25 217	99.08 247	99.74 104	99.79 138	99.68 118	99.50 103	99.65 251	98.07 427	99.52 291	99.69 216	98.57 217	99.92 155	97.18 416	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
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	98.56 220	99.96 70	99.29 135	99.94 136	99.83 60

ArgMatch-SfM		99.14 260	99.06 253	99.36 302	99.59 278	99.14 292	98.45 407	99.81 136	98.67 354	99.50 301	99.42 369	98.55 221	99.84 317	97.85 340	99.73 319	99.11 407

Elysia		99.69 60	99.65 75	99.81 55	99.86 61	99.72 96	99.34 150	99.77 171	99.94 37	99.91 63	99.76 156	98.55 221	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 96	99.34 150	99.77 171	99.94 37	99.91 63	99.76 156	98.55 221	99.99 7	99.70 62	99.98 55	99.72 100

V42		99.56 107	99.54 117	99.63 176	99.79 138	99.46 198	99.39 130	99.59 292	99.24 255	99.86 97	99.70 207	98.55 221	99.82 363	99.79 54	99.95 117	99.60 210

QAPM		98.40 383	97.99 408	99.65 161	99.39 379	99.47 190	99.67 53	99.52 338	91.70 543	98.78 441	99.80 109	98.55 221	99.95 82	94.71 516	99.75 305	99.53 259

FE-MVSNET		99.45 152	99.36 170	99.71 129	99.84 82	99.64 137	99.16 227	99.91 58	98.65 356	99.73 183	99.73 177	98.54 226	99.82 363	98.71 251	99.96 92	99.67 137

EI-MVSNet		99.38 180	99.44 147	99.21 349	99.58 288	98.09 424	99.26 187	99.46 358	99.62 167	99.75 166	99.67 235	98.54 226	99.85 299	99.15 165	99.92 159	99.68 128

jason		99.16 255	99.11 234	99.32 318	99.75 183	98.44 397	98.26 423	99.39 381	98.70 350	99.74 177	99.30 410	98.54 226	99.97 45	98.48 276	99.82 257	99.55 238
jason: jason.
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	98.54 226	99.93 121	99.59 79	99.98 55	99.76 87

IterMVS-LS		99.41 171	99.47 133	99.25 344	99.81 113	98.09 424	98.85 330	99.76 179	99.62 167	99.83 111	99.64 250	98.54 226	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.
hybrid		99.42 164	99.43 150	99.37 296	99.75 183	98.77 357	98.72 358	99.84 106	99.61 172	99.65 228	99.68 229	98.53 231	99.79 394	99.16 164	99.94 136	99.54 250

9.14			98.64 333		99.45 366		98.81 341	99.60 286	97.52 466	99.28 364	99.56 321	98.53 231	99.83 340	95.36 506	99.64 361

mPP-MVS		99.19 243	99.00 279	99.76 88	99.76 165	99.68 118	99.38 133	99.54 322	98.34 403	99.01 411	99.50 346	98.53 231	99.93 121	97.18 416	99.78 288	99.66 151

CNVR-MVS		98.99 304	98.80 320	99.56 215	99.25 424	99.43 210	98.54 391	99.27 416	98.58 366	98.80 437	99.43 367	98.53 231	99.70 450	97.22 410	99.59 381	99.54 250

PVSNet_BlendedMVS		99.03 289	99.01 275	99.09 368	99.54 318	97.99 430	98.58 380	99.82 123	97.62 460	99.34 348	99.71 197	98.52 235	99.77 411	97.98 324	99.97 78	99.52 270

PVSNet_Blended		98.70 345	98.59 339	99.02 379	99.54 318	97.99 430	97.58 487	99.82 123	95.70 516	99.34 348	98.98 472	98.52 235	99.77 411	97.98 324	99.83 247	99.30 364

MCST-MVS		99.02 292	98.81 317	99.65 161	99.58 288	99.49 185	98.58 380	99.07 448	98.40 388	99.04 408	99.25 424	98.51 237	99.80 390	97.31 396	99.51 402	99.65 160

UGNet		99.38 180	99.34 176	99.49 245	98.90 480	98.90 336	99.70 38	99.35 393	99.86 66	98.57 460	99.81 99	98.50 238	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
MASt3R-SfM		98.45 376	98.51 351	98.26 458	99.32 407	97.43 462	97.43 496	99.69 227	94.97 526	99.75 166	99.41 371	98.49 239	99.75 429	97.73 353	99.79 280	97.61 524

hybridnocas07		99.43 160	99.44 147	99.39 287	99.75 183	98.85 347	98.76 350	99.85 96	99.71 123	99.70 198	99.68 229	98.47 240	99.77 411	99.13 175	99.95 117	99.55 238

XVS		99.27 213	99.11 234	99.75 99	99.71 209	99.71 102	99.37 141	99.61 274	99.29 244	98.76 442	99.47 359	98.47 240	99.88 243	97.62 373	99.73 319	99.67 137

X-MVStestdata		96.09 490	94.87 506	99.75 99	99.71 209	99.71 102	99.37 141	99.61 274	99.29 244	98.76 442	61.30 567	98.47 240	99.88 243	97.62 373	99.73 319	99.67 137

diffmvs		99.34 197	99.32 182	99.39 287	99.67 249	98.77 357	98.57 384	99.81 136	99.61 172	99.48 306	99.41 371	98.47 240	99.86 280	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
ambc				99.20 352	99.35 392	98.53 390	99.17 221	99.46 358		99.67 217	99.80 109	98.46 244	99.70 450	97.92 329	99.70 334	99.38 336

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	99.82 113	99.83 84	98.45 245	99.87 260	99.51 94	99.97 78	99.86 48

dcpmvs_2		99.61 99	99.64 80	99.53 233	99.79 138	98.82 350	99.58 83	99.97 22	99.95 33	99.96 34	99.76 156	98.44 246	99.99 7	99.34 124	99.96 92	99.78 78

1314		98.00 417	97.90 420	98.27 457	98.90 480	97.45 459	99.30 168	99.06 450	94.98 525	97.21 524	99.12 450	98.43 247	99.67 475	95.58 501	98.56 497	97.71 522

USDC		98.96 308	98.93 297	99.05 377	99.54 318	97.99 430	97.07 514	99.80 144	98.21 414	99.75 166	99.77 146	98.43 247	99.64 489	97.90 331	99.88 204	99.51 273

KD-MVS_self_test		99.63 87	99.59 97	99.76 88	99.84 82	99.90 7	99.37 141	99.79 153	99.83 82	99.88 83	99.85 69	98.42 249	99.90 205	99.60 78	99.73 319	99.49 284

APD_test1		99.36 190	99.28 198	99.61 192	99.89 41	99.89 10	99.32 159	99.74 191	99.18 265	99.69 202	99.75 164	98.41 250	99.84 317	97.85 340	99.70 334	99.10 410

SR-MVS-dyc-post		99.27 213	99.11 234	99.73 114	99.54 318	99.74 88	99.26 187	99.62 266	99.16 274	99.52 291	99.64 250	98.41 250	99.91 186	97.27 402	99.61 374	99.54 250

v148		99.40 173	99.41 157	99.39 287	99.76 165	98.94 327	99.09 260	99.59 292	99.17 272	99.81 120	99.61 286	98.41 250	99.69 457	99.32 129	99.94 136	99.53 259

Test By Simon												98.41 250

PM-MVS		99.36 190	99.29 195	99.58 203	99.83 91	99.66 124	98.95 313	99.86 90	98.85 324	99.81 120	99.73 177	98.40 254	99.92 155	98.36 288	99.83 247	99.17 394

SR-MVS		99.19 243	99.00 279	99.74 104	99.51 336	99.72 96	99.18 216	99.60 286	98.85 324	99.47 308	99.58 309	98.38 255	99.92 155	96.92 429	99.54 396	99.57 230

segment_acmp												98.37 256

MP-MVS		99.06 281	98.83 314	99.76 88	99.76 165	99.71 102	99.32 159	99.50 347	98.35 399	98.97 414	99.48 355	98.37 256	99.92 155	95.95 488	99.75 305	99.63 178
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DVP-MVS		99.32 202	99.17 218	99.77 81	99.69 233	99.80 52	99.14 234	99.31 408	99.16 274	99.62 249	99.61 286	98.35 258	99.91 186	97.88 333	99.72 327	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
test0726					99.69 233	99.80 52	99.24 194	99.57 304	99.16 274	99.73 183	99.65 248	98.35 258

MatchFormer		99.03 289	99.02 269	99.08 373	99.56 312	98.47 393	98.57 384	99.90 65	98.13 420	99.80 127	99.75 164	98.34 260	99.84 317	97.18 416	99.90 177	98.92 455

MVS		95.72 501	94.63 509	98.99 381	98.56 513	97.98 435	99.30 168	98.86 461	72.71 553	97.30 521	99.08 456	98.34 260	99.74 436	89.21 538	98.33 507	99.26 370

CDPH-MVS		98.56 361	98.20 391	99.61 192	99.50 342	99.46 198	98.32 418	99.41 371	95.22 522	99.21 381	99.10 454	98.34 260	99.82 363	95.09 511	99.66 357	99.56 234

testdata				99.42 271	99.51 336	98.93 330		99.30 411	96.20 508	98.87 429	99.40 377	98.33 263	99.89 227	96.29 470	99.28 438	99.44 314

dtuonly		98.93 315	99.11 234	98.38 447	99.72 203	95.75 508	97.07 514	99.91 58	99.04 292	99.65 228	99.41 371	98.32 264	99.83 340	98.97 202	99.90 177	99.55 238

test_241102_TWO								99.54 322	99.13 281	99.76 161	99.63 266	98.32 264	99.92 155	97.85 340	99.69 343	99.75 90

ArgMatch-Sym		99.06 281	98.96 293	99.35 306	99.62 267	99.22 271	98.34 414	99.79 153	98.80 335	99.50 301	99.29 414	98.30 266	99.75 429	97.30 398	99.71 331	99.08 422

APD-MVS		98.87 324	98.59 339	99.71 129	99.50 342	99.62 145	99.01 287	99.57 304	96.80 500	99.54 284	99.63 266	98.29 267	99.91 186	95.24 507	99.71 331	99.61 205
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVSMamba_PlusPlus		99.55 112	99.58 101	99.47 253	99.68 242	99.40 221	99.52 95	99.70 218	99.92 46	99.77 152	99.86 64	98.28 268	99.96 70	99.54 88	99.90 177	99.05 431

OpenMVS	98.12 10	98.23 398	97.89 421	99.26 341	99.19 436	99.26 257	99.65 62	99.69 227	91.33 544	98.14 489	99.77 146	98.28 268	99.96 70	95.41 504	99.55 391	98.58 485

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	99.74 177	99.79 121	98.27 270	99.85 299	99.37 119	99.93 150	99.83 60

TAPA-MVS	97.92 13	98.03 414	97.55 436	99.46 257	99.47 358	99.44 206	98.50 397	99.62 266	86.79 547	99.07 405	99.26 422	98.26 271	99.62 492	97.28 401	99.73 319	99.31 362
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
patch_mono-2		99.51 125	99.46 139	99.64 168	99.70 225	99.11 296	99.04 275	99.87 81	99.71 123	99.47 308	99.79 121	98.24 272	99.98 27	99.38 116	99.96 92	99.83 60

v2v482		99.50 128	99.47 133	99.58 203	99.78 147	99.25 260	99.14 234	99.58 301	99.25 253	99.81 120	99.62 276	98.24 272	99.84 317	99.83 47	99.97 78	99.64 172

pmmvs4		99.13 263	99.06 253	99.36 302	99.57 298	99.10 303	98.01 452	99.25 421	98.78 339	99.58 264	99.44 366	98.24 272	99.76 418	98.74 242	99.93 150	99.22 378

mvs_anonymous		99.28 209	99.39 159	98.94 388	99.19 436	97.81 442	99.02 282	99.55 316	99.78 103	99.85 102	99.80 109	98.24 272	99.86 280	99.57 83	99.50 405	99.15 398

DPE-MVS		99.14 260	98.92 301	99.82 47	99.57 298	99.77 64	98.74 355	99.60 286	98.55 369	99.76 161	99.69 216	98.23 276	99.92 155	96.39 466	99.75 305	99.76 87
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
viewdifsd2359ckpt09		99.24 221	99.16 219	99.49 245	99.70 225	99.22 271	98.88 324	99.81 136	98.70 350	99.38 337	99.37 389	98.22 277	99.76 418	98.48 276	99.88 204	99.51 273

MTAPA		99.35 192	99.20 214	99.80 65	99.81 113	99.81 48	99.33 156	99.53 333	99.27 248	99.42 322	99.63 266	98.21 278	99.95 82	97.83 346	99.79 280	99.65 160

MS-PatchMatch		99.00 301	98.97 291	99.09 368	99.11 453	98.19 414	98.76 350	99.33 402	98.49 380	99.44 315	99.58 309	98.21 278	99.69 457	98.20 303	99.62 366	99.39 334

BridgeMVS		99.50 128	99.50 126	99.50 241	99.42 375	99.49 185	99.52 95	99.75 185	99.86 66	99.78 140	99.71 197	98.20 280	99.90 205	99.39 115	99.88 204	99.10 410

our_test_3		98.85 328	99.09 245	98.13 462	99.66 252	94.90 525	97.72 476	99.58 301	99.07 289	99.64 234	99.62 276	98.19 281	99.93 121	98.41 284	99.95 117	99.55 238

MVP-Stereo		99.16 255	99.08 247	99.43 268	99.48 352	99.07 306	99.08 263	99.55 316	98.63 359	99.31 358	99.68 229	98.19 281	99.78 398	98.18 307	99.58 383	99.45 299
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WR-MVS_H		99.61 99	99.53 121	99.87 27	99.80 124	99.83 34	99.67 53	99.75 185	99.58 183	99.85 102	99.69 216	98.18 283	99.94 99	99.28 137	99.95 117	99.83 60

new_pmnet		98.88 323	98.89 306	98.84 411	99.70 225	97.62 450	98.15 434	99.50 347	97.98 433	99.62 249	99.54 332	98.15 284	99.94 99	97.55 379	99.84 239	98.95 449

LoFTR		99.29 207	99.26 203	99.36 302	99.70 225	99.05 309	98.66 368	99.95 39	98.85 324	99.86 97	99.75 164	98.14 285	99.93 121	98.54 273	99.91 173	99.10 410

D2MVS		99.22 233	99.19 216	99.29 328	99.69 233	98.74 360	98.81 341	99.41 371	98.55 369	99.68 209	99.69 216	98.13 286	99.87 260	98.82 226	99.98 55	99.24 373

Anonymous20240529		99.42 164	99.34 176	99.65 161	99.53 327	99.60 159	99.63 64	99.39 381	99.47 204	99.76 161	99.78 134	98.13 286	99.86 280	98.70 253	99.68 348	99.49 284

TestfortrainingZip a		99.55 112	99.45 142	99.85 33	99.76 165	99.82 42	99.38 133	99.62 266	99.77 108	99.87 93	99.78 134	98.12 288	99.88 243	98.96 205	99.77 292	99.85 51

IMVS_0404		99.23 224	99.20 214	99.32 318	99.71 209	98.55 386	98.57 384	99.71 209	99.41 224	99.52 291	99.60 296	98.12 288	99.95 82	98.45 279	99.70 334	99.45 299

TestfortrainingZip				99.38 291	99.17 440	99.25 260	99.38 133	98.82 464	98.93 312	99.68 209	99.49 351	98.11 290	99.56 505		98.44 504	99.32 357

EU-MVSNet		99.39 177	99.62 86	98.72 424	99.88 47	96.44 490	99.56 88	99.85 96	99.90 50	99.90 68	99.85 69	98.09 291	99.83 340	99.58 82	99.95 117	99.90 31

PMVS	92.94 21	98.82 330	98.81 317	98.85 409	99.84 82	97.99 430	99.20 206	99.47 355	99.71 123	99.42 322	99.82 92	98.09 291	99.47 516	93.88 528	99.85 233	99.07 428
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
HPM-MVS++		98.96 308	98.70 330	99.74 104	99.52 334	99.71 102	98.86 328	99.19 436	98.47 382	98.59 457	99.06 459	98.08 293	99.91 186	96.94 428	99.60 377	99.60 210

PRO-TEST		99.17 252	99.14 224	99.28 331	99.04 466	98.92 334	99.24 194	99.76 179	99.69 133	99.41 328	99.17 442	98.06 294	99.85 299	98.39 286	99.47 410	99.06 430

ab-mvs		99.33 200	99.28 198	99.47 253	99.57 298	99.39 225	99.78 17	99.43 368	98.87 321	99.57 267	99.82 92	98.06 294	99.87 260	98.69 255	99.73 319	99.15 398

N_pmnet		98.73 341	98.53 349	99.35 306	99.72 203	98.67 365	98.34 414	94.65 546	98.35 399	99.79 134	99.68 229	98.03 296	99.93 121	98.28 294	99.92 159	99.44 314

TEST9					99.35 392	99.35 239	98.11 441	99.41 371	94.83 530	97.92 497	98.99 469	98.02 297	99.85 299

train_agg		98.35 388	97.95 412	99.57 211	99.35 392	99.35 239	98.11 441	99.41 371	94.90 527	97.92 497	98.99 469	98.02 297	99.85 299	95.38 505	99.44 415	99.50 279

test_8					99.34 401	99.31 246	98.08 445	99.40 378	94.90 527	97.87 502	98.97 474	98.02 297	99.84 317

MVSFormer		99.41 171	99.44 147	99.31 323	99.57 298	98.40 400	99.77 19	99.80 144	99.73 113	99.63 239	99.30 410	98.02 297	99.98 27	99.43 107	99.69 343	99.55 238

lupinMVS		98.96 308	98.87 308	99.24 346	99.57 298	98.40 400	98.12 439	99.18 438	98.28 410	99.63 239	99.13 446	98.02 297	99.97 45	98.22 301	99.69 343	99.35 346

aaEdge-Enhanced		99.26 215	99.10 243	99.73 114	99.60 272	99.65 130	98.75 354	99.45 363	99.31 242	99.65 228	99.66 241	98.00 302	99.86 280	97.69 365	99.79 280	99.67 137

Anonymous20231211		99.62 95	99.57 106	99.76 88	99.61 269	99.60 159	99.81 13	99.73 196	99.82 86	99.90 68	99.90 37	97.97 303	99.86 280	99.42 112	99.96 92	99.80 68

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	97.94 304	99.92 155	99.65 71	99.98 55	99.62 190

原ACMM1				99.37 296	99.47 358	98.87 346		99.27 416	96.74 502	98.26 475	99.32 404	97.93 305	99.82 363	95.96 487	99.38 424	99.43 321

test_prior2							97.95 461		97.87 447	98.05 491	99.05 460	97.90 306		95.99 485	99.49 407

RPSCF		99.18 247	99.02 269	99.64 168	99.83 91	99.85 22	99.44 120	99.82 123	98.33 406	99.50 301	99.78 134	97.90 306	99.65 487	96.78 440	99.83 247	99.44 314

PMMVS		98.49 371	98.29 384	99.11 365	98.96 477	98.42 399	97.54 488	99.32 404	97.53 465	98.47 466	98.15 519	97.88 308	99.82 363	97.46 386	99.24 446	99.09 416

ZD-MVS					99.43 370	99.61 155		99.43 368	96.38 505	99.11 399	99.07 457	97.86 309	99.92 155	94.04 525	99.49 407

NCCC		98.82 330	98.57 343	99.58 203	99.21 431	99.31 246	98.61 373	99.25 421	98.65 356	98.43 468	99.26 422	97.86 309	99.81 380	96.55 454	99.27 441	99.61 205

UniMVSNet_NR-MVSNet		99.37 185	99.25 207	99.72 123	99.47 358	99.56 170	98.97 306	99.61 274	99.43 219	99.67 217	99.28 416	97.85 311	99.95 82	99.17 160	99.81 267	99.65 160

TAMVS		99.49 133	99.45 142	99.63 176	99.48 352	99.42 213	99.45 118	99.57 304	99.66 152	99.78 140	99.83 84	97.85 311	99.86 280	99.44 105	99.96 92	99.61 205

DP-MVS Recon		98.50 369	98.23 388	99.31 323	99.49 347	99.46 198	98.56 387	99.63 263	94.86 529	98.85 431	99.37 389	97.81 313	99.59 499	96.08 479	99.44 415	98.88 461

PatchMatch-RL		98.68 347	98.47 356	99.30 327	99.44 367	99.28 251	98.14 436	99.54 322	97.12 488	99.11 399	99.25 424	97.80 314	99.70 450	96.51 457	99.30 435	98.93 453

CP-MVSNet		99.54 117	99.43 150	99.87 27	99.76 165	99.82 42	99.57 86	99.61 274	99.54 187	99.80 127	99.64 250	97.79 315	99.95 82	99.21 147	99.94 136	99.84 56

RoMa-SfM		99.32 202	99.23 212	99.59 199	99.77 160	99.53 177	98.89 322	99.88 75	98.78 339	99.65 228	99.52 339	97.78 316	99.90 205	98.96 205	99.86 226	99.35 346

WB-MVSnew		98.34 390	98.14 398	98.96 385	98.14 531	97.90 438	98.27 421	97.26 527	98.63 359	98.80 437	98.00 522	97.77 317	99.90 205	97.37 392	98.98 467	99.09 416

DPM-MVS		98.28 391	97.94 416	99.32 318	99.36 388	99.11 296	97.31 501	98.78 468	96.88 496	98.84 432	99.11 453	97.77 317	99.61 497	94.03 526	99.36 427	99.23 376

114514_t		98.49 371	98.11 401	99.64 168	99.73 198	99.58 166	99.24 194	99.76 179	89.94 546	99.42 322	99.56 321	97.76 319	99.86 280	97.74 352	99.82 257	99.47 292

RoMa-HiRes		99.38 180	99.30 189	99.64 168	99.81 113	99.47 190	99.11 251	99.94 42	99.03 294	99.55 280	99.56 321	97.71 320	99.92 155	99.19 153	99.77 292	99.54 250

tmp_tt		95.75 500	95.42 494	96.76 516	89.90 560	94.42 527	98.86 328	97.87 515	78.01 551	99.30 363	99.69 216	97.70 321	95.89 551	99.29 135	98.14 517	99.95 16

UniMVSNet (Re)		99.37 185	99.26 203	99.68 142	99.51 336	99.58 166	98.98 304	99.60 286	99.43 219	99.70 198	99.36 394	97.70 321	99.88 243	99.20 151	99.87 218	99.59 217

Effi-MVS+-dtu		99.07 280	98.92 301	99.52 235	98.89 484	99.78 58	99.15 230	99.66 241	99.34 236	98.92 422	99.24 430	97.69 323	99.98 27	98.11 313	99.28 438	98.81 468

F-COLMAP		98.74 339	98.45 361	99.62 185	99.57 298	99.47 190	98.84 333	99.65 251	96.31 507	98.93 419	99.19 441	97.68 324	99.87 260	96.52 456	99.37 426	99.53 259

新几何1				99.52 235	99.50 342	99.22 271		99.26 418	95.66 517	98.60 456	99.28 416	97.67 325	99.89 227	95.95 488	99.32 433	99.45 299

旧先验1					99.49 347	99.29 249		99.26 418			99.39 382	97.67 325			99.36 427	99.46 297

DU-MVS		99.33 200	99.21 213	99.71 129	99.43 370	99.56 170	98.83 336	99.53 333	99.38 230	99.67 217	99.36 394	97.67 325	99.95 82	99.17 160	99.81 267	99.63 178

Baseline_NR-MVSNet		99.49 133	99.37 165	99.82 47	99.91 32	99.84 27	98.83 336	99.86 90	99.68 137	99.65 228	99.88 51	97.67 325	99.87 260	99.03 192	99.86 226	99.76 87

CANet		99.11 271	99.05 260	99.28 331	98.83 492	98.56 384	98.71 362	99.41 371	99.25 253	99.23 375	99.22 433	97.66 329	99.94 99	99.19 153	99.97 78	99.33 353

balanced_ft_v1		99.37 185	99.36 170	99.38 291	99.10 455	99.38 227	99.68 48	99.72 205	99.72 117	99.36 340	99.77 146	97.66 329	99.94 99	99.52 92	99.73 319	98.83 466

VPNet		99.46 148	99.37 165	99.71 129	99.82 100	99.59 161	99.48 110	99.70 218	99.81 92	99.69 202	99.58 309	97.66 329	99.86 280	99.17 160	99.44 415	99.67 137

test-260524					99.64 258	99.70 110		99.58 301		99.69 202		97.64 332	99.87 260	98.68 256	99.76 297

Anonymous20231206		99.35 192	99.31 184	99.47 253	99.74 194	99.06 308	99.28 178	99.74 191	99.23 257	99.72 189	99.53 335	97.63 333	99.88 243	99.11 181	99.84 239	99.48 288

ALIKED-LG		98.78 334	98.66 332	99.14 361	99.02 474	99.40 221	98.74 355	99.79 153	98.62 363	99.18 387	99.38 385	97.54 334	99.77 411	95.94 490	99.74 312	98.25 503

test12				99.54 228	99.29 415	99.33 242		99.16 441		98.43 468		97.54 334	99.82 363		99.47 410	99.48 288

NR-MVSNet		99.40 173	99.31 184	99.68 142	99.43 370	99.55 174	99.73 30	99.50 347	99.46 207	99.88 83	99.36 394	97.54 334	99.87 260	98.97 202	99.87 218	99.63 178

MAR-MVS		98.24 396	97.92 418	99.19 353	98.78 500	99.65 130	99.17 221	99.14 444	95.36 520	98.04 492	98.81 491	97.47 337	99.72 441	95.47 503	99.06 459	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
CHOSEN 1792x2688		99.39 177	99.30 189	99.65 161	99.88 47	99.25 260	98.78 348	99.88 75	98.66 355	99.96 34	99.79 121	97.45 338	99.93 121	99.34 124	99.99 19	99.78 78

PAPR		97.56 439	97.07 455	99.04 378	98.80 496	98.11 422	97.63 483	99.25 421	94.56 533	98.02 494	98.25 516	97.43 339	99.68 469	90.90 537	98.74 487	99.33 353

YYNet1		98.95 311	98.99 286	98.84 411	99.64 258	97.14 473	98.22 426	99.32 404	98.92 315	99.59 262	99.66 241	97.40 340	99.83 340	98.27 296	99.90 177	99.55 238

PVSNet	97.47 15	98.42 379	98.44 363	98.35 448	99.46 362	96.26 495	96.70 530	99.34 397	97.68 458	99.00 412	99.13 446	97.40 340	99.72 441	97.59 377	99.68 348	99.08 422

MDA-MVSNet_test_wron		98.95 311	98.99 286	98.85 409	99.64 258	97.16 471	98.23 425	99.33 402	98.93 312	99.56 275	99.66 241	97.39 342	99.83 340	98.29 293	99.88 204	99.55 238

MG-MVS		98.52 366	98.39 370	98.94 388	99.15 443	97.39 464	98.18 428	99.21 432	98.89 320	99.23 375	99.63 266	97.37 343	99.74 436	94.22 521	99.61 374	99.69 121

ELoFTR		99.25 217	99.26 203	99.21 349	99.86 61	98.66 368	99.00 293	99.93 44	98.56 367	99.83 111	99.83 84	97.34 344	99.92 155	99.03 192	100.00 1	99.04 434

OpenMVS_ROB	97.31 17	97.36 452	96.84 465	98.89 405	99.29 415	99.45 204	98.87 327	99.48 352	86.54 549	99.44 315	99.74 172	97.34 344	99.86 280	91.61 534	99.28 438	97.37 528

AdaColmap		98.60 355	98.35 376	99.38 291	99.12 448	99.22 271	98.67 366	99.42 370	97.84 451	98.81 435	99.27 418	97.32 346	99.81 380	95.14 509	99.53 398	99.10 410

test222					99.51 336	99.08 305	97.83 470	99.29 412	95.21 523	98.68 449	99.31 407	97.28 347			99.38 424	99.43 321

HQP_MVS		98.90 319	98.68 331	99.55 222	99.58 288	99.24 265	98.80 344	99.54 322	98.94 307	99.14 394	99.25 424	97.24 348	99.82 363	95.84 493	99.78 288	99.60 210

plane_prior6					99.47 358	99.26 257						97.24 348

PMatch-Up-SfM		99.08 276	99.02 269	99.27 337	99.81 113	99.04 311	98.13 437	99.83 116	99.16 274	99.26 369	99.69 216	97.22 350	99.83 340	98.67 258	99.43 419	98.94 452

GBi-Net		99.42 164	99.31 184	99.73 114	99.49 347	99.77 64	99.68 48	99.70 218	99.44 212	99.62 249	99.83 84	97.21 351	99.90 205	98.96 205	99.90 177	99.53 259

test1		99.42 164	99.31 184	99.73 114	99.49 347	99.77 64	99.68 48	99.70 218	99.44 212	99.62 249	99.83 84	97.21 351	99.90 205	98.96 205	99.90 177	99.53 259

FMVSNet2		99.35 192	99.28 198	99.55 222	99.49 347	99.35 239	99.45 118	99.57 304	99.44 212	99.70 198	99.74 172	97.21 351	99.87 260	99.03 192	99.94 136	99.44 314

BH-RMVSNet		98.41 381	98.14 398	99.21 349	99.21 431	98.47 393	98.60 375	98.26 500	98.35 399	98.93 419	99.31 407	97.20 354	99.66 480	94.32 519	99.10 456	99.51 273

MVS-HIRNet		97.86 423	98.22 389	96.76 516	99.28 418	91.53 547	98.38 412	92.60 553	99.13 281	99.31 358	99.96 15	97.18 355	99.68 469	98.34 290	99.83 247	99.07 428

SIFT-NCM-Cal		98.18 403	98.41 367	97.48 487	99.57 298	99.28 251	97.26 503	98.08 505	98.30 409	99.23 375	99.39 382	97.13 356	99.04 536	96.86 433	99.86 226	94.12 542

PAPM_NR		98.36 385	98.04 405	99.33 313	99.48 352	98.93 330	98.79 347	99.28 415	97.54 464	98.56 462	98.57 505	97.12 357	99.69 457	94.09 524	98.90 476	99.38 336

dmvs_testset		97.27 454	96.83 466	98.59 434	99.46 362	97.55 452	99.25 193	96.84 531	98.78 339	97.24 523	97.67 529	97.11 358	98.97 537	86.59 550	98.54 498	99.27 368

CPTT-MVS		98.74 339	98.44 363	99.64 168	99.61 269	99.38 227	99.18 216	99.55 316	96.49 503	99.27 365	99.37 389	97.11 358	99.92 155	95.74 498	99.67 354	99.62 190

DenseAffine		99.17 252	99.06 253	99.49 245	99.76 165	99.33 242	98.43 409	99.97 22	99.11 285	99.17 388	99.61 286	97.05 360	99.76 418	98.56 270	99.88 204	99.38 336

CNLPA		98.57 360	98.34 377	99.28 331	99.18 439	99.10 303	98.34 414	99.41 371	98.48 381	98.52 463	98.98 472	97.05 360	99.78 398	95.59 500	99.50 405	98.96 447

SP-DiffGlue		98.47 373	98.43 365	98.59 434	97.44 546	98.59 381	98.01 452	99.36 391	99.00 298	99.06 406	99.20 439	97.01 362	99.25 526	97.64 371	99.15 452	97.92 520

BH-untuned		98.22 400	98.09 402	98.58 437	99.38 382	97.24 469	98.55 388	98.98 458	97.81 452	99.20 386	98.76 493	97.01 362	99.65 487	94.83 513	98.33 507	98.86 463

VDD-MVS		99.20 240	99.11 234	99.44 264	99.43 370	98.98 318	99.50 103	98.32 498	99.80 96	99.56 275	99.69 216	96.99 364	99.85 299	98.99 198	99.73 319	99.50 279

SP-SuperGlue		98.66 349	98.63 335	98.73 423	98.44 518	99.02 312	98.22 426	99.44 364	99.37 231	98.17 484	99.30 410	96.95 365	99.12 530	98.59 266	99.20 451	98.06 512

PLC	97.35 16	98.36 385	97.99 408	99.48 251	99.32 407	99.24 265	98.50 397	99.51 343	95.19 524	98.58 458	98.96 476	96.95 365	99.83 340	95.63 499	99.25 444	99.37 340
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
WR-MVS		99.11 271	98.93 297	99.66 154	99.30 413	99.42 213	98.42 410	99.37 387	99.04 292	99.57 267	99.20 439	96.89 367	99.86 280	98.66 259	99.87 218	99.70 108

CL-MVSNet_self_test		98.71 344	98.56 347	99.15 358	99.22 429	98.66 368	97.14 510	99.51 343	98.09 424	99.54 284	99.27 418	96.87 368	99.74 436	98.43 283	98.96 468	99.03 437

SIFT-NN-PointCN		97.97 419	98.24 387	97.14 508	99.59 278	98.71 362	96.75 527	99.56 309	97.02 492	97.91 499	99.27 418	96.85 369	98.39 545	97.47 385	99.76 297	94.31 539

MSP-MVS		99.04 288	98.79 321	99.81 55	99.78 147	99.73 91	99.35 149	99.57 304	98.54 372	99.54 284	98.99 469	96.81 370	99.93 121	96.97 426	99.53 398	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
SSC-MVS		99.52 123	99.42 153	99.83 42	99.86 61	99.65 130	99.52 95	99.81 136	99.87 63	99.81 120	99.79 121	96.78 371	99.99 7	99.83 47	99.51 402	99.86 48

usedtu_dtu_shiyan2		99.44 156	99.33 181	99.78 77	99.86 61	99.76 71	99.54 91	99.79 153	99.66 152	99.66 224	99.79 121	96.76 372	99.96 70	99.15 165	99.72 327	99.62 190

dmvs_re		98.69 346	98.48 355	99.31 323	99.55 316	99.42 213	99.54 91	98.38 495	99.32 240	98.72 445	98.71 496	96.76 372	99.21 528	96.01 482	99.35 429	99.31 362

HQP2-MVS												96.67 374

HQP-MVS		98.36 385	98.02 407	99.39 287	99.31 409	98.94 327	97.98 457	99.37 387	97.45 469	98.15 485	98.83 488	96.67 374	99.70 450	94.73 514	99.67 354	99.53 259

ALIKED-MNN		98.03 414	97.78 427	98.78 419	98.84 491	98.97 321	98.16 433	99.74 191	97.31 478	96.60 533	98.85 486	96.61 376	99.48 515	94.16 522	99.77 292	97.91 521

WB-MVS		99.44 156	99.32 182	99.80 65	99.81 113	99.61 155	99.47 113	99.81 136	99.82 86	99.71 194	99.72 187	96.60 377	99.98 27	99.75 57	99.23 448	99.82 67

CANet_DTU		98.91 316	98.85 310	99.09 368	98.79 498	98.13 419	98.18 428	99.31 408	99.48 199	98.86 430	99.51 343	96.56 378	99.95 82	99.05 189	99.95 117	99.19 389

pmmvs5		99.19 243	99.11 234	99.42 271	99.76 165	98.88 341	98.55 388	99.73 196	98.82 331	99.72 189	99.62 276	96.56 378	99.82 363	99.32 129	99.95 117	99.56 234

MVE	92.54 22	96.66 472	96.11 479	98.31 453	99.68 242	97.55 452	97.94 462	95.60 544	99.37 231	90.68 552	98.70 498	96.56 378	98.61 543	86.94 549	99.55 391	98.77 474
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
LuminaMVS		99.39 177	99.28 198	99.73 114	99.83 91	99.49 185	99.00 293	99.05 451	99.81 92	99.89 73	99.79 121	96.54 381	99.97 45	99.64 74	99.98 55	99.73 96

VNet		99.18 247	99.06 253	99.56 215	99.24 426	99.36 236	99.33 156	99.31 408	99.67 145	99.47 308	99.57 317	96.48 382	99.84 317	99.15 165	99.30 435	99.47 292

MDA-MVSNet-bldmvs		99.06 281	99.05 260	99.07 374	99.80 124	97.83 441	98.89 322	99.72 205	99.29 244	99.63 239	99.70 207	96.47 383	99.89 227	98.17 309	99.82 257	99.50 279

DeepMVS_CX				97.98 466	99.69 233	96.95 476		99.26 418	75.51 552	95.74 541	98.28 515	96.47 383	99.62 492	91.23 536	97.89 524	97.38 527

1112_ss		99.05 285	98.84 312	99.67 146	99.66 252	99.29 249	98.52 395	99.82 123	97.65 459	99.43 319	99.16 443	96.42 385	99.91 186	99.07 188	99.84 239	99.80 68

TR-MVS		97.44 447	97.15 452	98.32 451	98.53 514	97.46 457	98.47 402	97.91 513	96.85 497	98.21 479	98.51 509	96.42 385	99.51 513	92.16 532	97.29 533	97.98 517

miper_ehance_all_eth		98.59 358	98.59 339	98.59 434	98.98 475	97.07 474	97.49 493	99.52 338	98.50 378	99.52 291	99.37 389	96.41 387	99.71 446	97.86 338	99.62 366	99.00 444

Anonymous20240521		99.44 156	99.42 153	99.49 245	99.89 41	98.96 324	99.62 67	99.76 179	99.85 72	99.82 113	99.88 51	96.39 388	99.97 45	99.59 79	99.98 55	99.55 238

c3_l		98.72 342	98.71 326	98.72 424	99.12 448	97.22 470	97.68 480	99.56 309	98.90 317	99.54 284	99.48 355	96.37 389	99.73 439	97.88 333	99.88 204	99.21 381

mvsmamba		99.08 276	98.95 295	99.45 260	99.36 388	99.18 287	99.39 130	98.81 466	99.37 231	99.35 344	99.70 207	96.36 390	99.94 99	98.66 259	99.59 381	99.22 378

SIFT-NN-CMatch		97.30 453	97.34 443	97.18 504	99.54 318	98.85 347	96.02 538	95.77 543	97.05 491	97.55 516	98.70 498	96.35 391	98.75 541	95.82 495	99.26 442	93.95 544

SP-MNN		97.94 422	97.82 423	98.31 453	98.30 523	97.67 449	97.81 471	97.93 512	98.14 419	97.16 527	98.64 502	96.31 392	99.21 528	97.34 393	98.75 486	98.05 514

sss		98.90 319	98.77 322	99.27 337	99.48 352	98.44 397	98.72 358	99.32 404	97.94 440	99.37 339	99.35 399	96.31 392	99.91 186	98.85 221	99.63 364	99.47 292

CDS-MVSNet		99.22 233	99.13 227	99.50 241	99.35 392	99.11 296	98.96 310	99.54 322	99.46 207	99.61 256	99.70 207	96.31 392	99.83 340	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
MM		99.18 247	99.05 260	99.55 222	99.35 392	98.81 351	99.05 270	97.79 517	99.99 4	99.48 306	99.59 306	96.29 395	99.95 82	99.94 21	99.98 55	99.88 42

DKM		99.12 266	98.98 289	99.54 228	99.71 209	99.48 189	98.53 393	99.88 75	99.18 265	98.99 413	99.64 250	96.25 396	99.75 429	98.66 259	99.93 150	99.40 330

eth_miper_zixun_eth		98.68 347	98.71 326	98.60 433	99.10 455	96.84 483	97.52 492	99.54 322	98.94 307	99.58 264	99.48 355	96.25 396	99.76 418	98.01 322	99.93 150	99.21 381

SIFT-UM-Cal		98.18 403	98.45 361	97.37 496	99.59 278	98.95 325	96.76 526	99.39 381	98.39 389	99.46 312	99.31 407	96.23 398	99.24 527	97.21 411	99.70 334	93.90 545

SixPastTwentyTwo		99.42 164	99.30 189	99.76 88	99.92 30	99.67 121	99.70 38	99.14 444	99.65 158	99.89 73	99.90 37	96.20 399	99.94 99	99.42 112	99.92 159	99.67 137

PMatch-SfM		98.91 316	98.81 317	99.22 348	99.79 138	98.89 339	98.18 428	99.61 274	99.18 265	99.03 409	99.61 286	96.13 400	99.80 390	98.71 251	99.04 463	98.99 445

AstraMVS		99.15 259	99.06 253	99.42 271	99.85 76	98.59 381	99.13 241	97.26 527	99.84 76	99.87 93	99.77 146	96.11 401	99.93 121	99.71 61	99.96 92	99.74 92

Test_1112_low_res		98.95 311	98.73 323	99.63 176	99.68 242	99.15 290	98.09 443	99.80 144	97.14 487	99.46 312	99.40 377	96.11 401	99.89 227	99.01 197	99.84 239	99.84 56

IterMVS		98.97 305	99.16 219	98.42 444	99.74 194	95.64 511	98.06 448	99.83 116	99.83 82	99.85 102	99.74 172	96.10 403	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.
SIFT-NN-NCMNet		97.22 455	97.27 447	97.07 510	99.64 258	99.20 278	96.53 532	95.91 536	96.91 495	97.38 518	98.95 478	96.01 404	98.29 546	94.87 512	99.21 450	93.73 548

IterMVS-SCA-FT		99.00 301	99.16 219	98.51 439	99.75 183	95.90 504	98.07 446	99.84 106	99.84 76	99.89 73	99.73 177	96.01 404	99.99 7	99.33 127	100.00 1	99.63 178

SCA		98.11 409	98.36 374	97.36 497	99.20 434	92.99 537	98.17 431	98.49 486	98.24 412	99.10 401	99.57 317	96.01 404	99.94 99	96.86 433	99.62 366	99.14 403

SIFT-ConvMatch		98.16 407	98.37 372	97.52 485	99.54 318	99.20 278	96.97 519	98.47 487	98.09 424	99.14 394	99.40 377	95.93 407	99.05 535	97.87 336	99.92 159	94.31 539

SP-LightGlue		98.62 351	98.51 351	98.94 388	98.69 509	99.01 313	98.34 414	99.54 322	99.27 248	97.72 513	99.15 445	95.88 408	99.54 506	98.53 274	99.47 410	98.27 501

PVSNet_0	95.53 19	95.85 499	95.31 500	97.47 489	98.78 500	93.48 536	95.72 539	99.40 378	96.18 509	97.37 519	97.73 528	95.73 409	99.58 500	95.49 502	81.40 556	99.36 343

CMPMVS	77.52 23	98.50 369	98.19 394	99.41 281	98.33 522	99.56 170	99.01 287	99.59 292	95.44 519	99.57 267	99.80 109	95.64 410	99.46 518	96.47 462	99.92 159	99.21 381
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
BH-w/o		97.20 456	97.01 458	97.76 477	99.08 460	95.69 510	98.03 451	98.52 483	95.76 515	97.96 495	98.02 520	95.62 411	99.47 516	92.82 531	97.25 534	98.12 511

SIFT-PCN-Cal		98.24 396	98.51 351	97.43 492	99.65 256	98.64 375	97.09 511	99.35 393	98.16 418	99.69 202	99.52 339	95.59 412	99.83 340	97.57 378	100.00 1	93.81 546

cascas		96.99 461	96.82 467	97.48 487	97.57 544	95.64 511	96.43 534	99.56 309	91.75 542	97.13 528	97.61 533	95.58 413	98.63 542	96.68 445	99.11 455	98.18 509

usedtu_dtu_shiyan1		98.87 324	98.71 326	99.35 306	99.59 278	98.88 341	97.17 507	99.64 259	98.94 307	99.27 365	99.22 433	95.57 414	99.83 340	99.08 185	99.92 159	99.35 346

FE-MVSNET3		98.87 324	98.71 326	99.35 306	99.59 278	98.88 341	97.17 507	99.64 259	98.94 307	99.27 365	99.22 433	95.57 414	99.83 340	99.08 185	99.92 159	99.35 346

MGCNet		98.61 352	98.30 382	99.52 235	97.88 537	98.95 325	98.76 350	94.11 550	99.84 76	99.32 353	99.57 317	95.57 414	99.95 82	99.68 67	99.98 55	99.68 128

SIFT-PointCN		98.28 391	98.47 356	97.71 482	99.70 225	98.91 335	96.98 518	99.70 218	97.90 442	99.36 340	99.35 399	95.51 417	99.83 340	97.84 345	99.89 193	94.39 538

MonoMVSNet		98.23 398	98.32 379	97.99 465	98.97 476	96.62 486	99.49 108	98.42 490	99.62 167	99.40 334	99.79 121	95.51 417	98.58 544	97.68 370	95.98 546	98.76 475

Syy-MVS		98.17 406	97.85 422	99.15 358	98.50 516	98.79 355	98.60 375	99.21 432	97.89 444	96.76 530	96.37 558	95.47 419	99.57 501	99.10 182	98.73 490	99.09 416

SIFT-UMatch		98.07 412	98.27 385	97.46 491	99.57 298	98.99 316	96.93 522	99.02 453	98.53 373	99.26 369	99.23 432	95.43 420	99.31 524	96.51 457	99.91 173	94.09 543

SIFT-NCMNet		98.18 403	98.46 358	97.36 497	99.67 249	99.19 281	96.33 536	98.99 457	98.83 329	99.62 249	99.63 266	95.41 421	99.33 523	97.64 371	100.00 1	93.54 550

UnsupCasMVSNet_bld		98.55 362	98.27 385	99.40 284	99.56 312	99.37 232	97.97 460	99.68 231	97.49 468	99.08 402	99.35 399	95.41 421	99.82 363	97.70 359	98.19 514	99.01 443

RRT-MVS		99.08 276	99.00 279	99.33 313	99.27 420	98.65 372	99.62 67	99.93 44	99.66 152	99.67 217	99.82 92	95.27 423	99.93 121	98.64 263	99.09 458	99.41 327

SIFT-CM-Cal		97.96 421	98.15 397	97.39 494	99.61 269	99.15 290	96.75 527	98.41 493	98.04 429	99.03 409	99.54 332	95.24 424	99.41 519	96.97 426	99.80 274	93.61 549

VortexMVS		99.13 263	99.24 209	98.79 417	99.67 249	96.60 488	99.24 194	99.80 144	99.85 72	99.93 53	99.84 77	95.06 425	99.89 227	99.80 53	99.98 55	99.89 39

DKM-HiRes		98.95 311	98.73 323	99.62 185	99.82 100	99.47 190	98.50 397	99.81 136	99.41 224	97.76 510	99.58 309	95.04 426	99.83 340	98.89 218	99.76 297	99.58 223

UnsupCasMVSNet_eth		98.83 329	98.57 343	99.59 199	99.68 242	99.45 204	98.99 301	99.67 236	99.48 199	99.55 280	99.36 394	94.92 427	99.86 280	98.95 212	96.57 537	99.45 299

EPP-MVSNet		99.17 252	99.00 279	99.66 154	99.80 124	99.43 210	99.70 38	99.24 425	99.48 199	99.56 275	99.77 146	94.89 428	99.93 121	98.72 249	99.89 193	99.63 178

guyue		99.12 266	99.02 269	99.41 281	99.84 82	98.56 384	99.19 212	98.30 499	99.82 86	99.84 105	99.75 164	94.84 429	99.92 155	99.68 67	99.94 136	99.74 92

WTY-MVS		98.59 358	98.37 372	99.26 341	99.43 370	98.40 400	98.74 355	99.13 446	98.10 422	99.21 381	99.24 430	94.82 430	99.90 205	97.86 338	98.77 482	99.49 284

miper_enhance_ethall		98.03 414	97.94 416	98.32 451	98.27 524	96.43 491	96.95 520	99.41 371	96.37 506	99.43 319	98.96 476	94.74 431	99.69 457	97.71 356	99.62 366	98.83 466

IS-MVSNet		99.03 289	98.85 310	99.55 222	99.80 124	99.25 260	99.73 30	99.15 442	99.37 231	99.61 256	99.71 197	94.73 432	99.81 380	97.70 359	99.88 204	99.58 223

GLUNet-SfM		95.26 507	95.06 504	95.87 529	94.84 556	90.39 555	90.24 550	99.92 48	92.30 540	99.16 389	99.25 424	94.69 433	98.01 547	85.55 551	99.62 366	99.21 381

miper_lstm_enhance		98.65 350	98.60 337	98.82 416	99.20 434	97.33 466	97.78 472	99.66 241	99.01 297	99.59 262	99.50 346	94.62 434	99.85 299	98.12 312	99.90 177	99.26 370

lessismore_v0				99.64 168	99.86 61	99.38 227		90.66 556		99.89 73	99.83 84	94.56 435	99.97 45	99.56 84	99.92 159	99.57 230

ALIKED-NN		96.66 472	96.26 474	97.88 472	97.49 545	98.59 381	96.71 529	99.15 442	95.50 518	93.58 549	98.39 512	94.52 436	97.74 549	92.05 533	98.94 469	97.29 530

SIFT-NN-UMatch		97.18 457	97.24 449	97.01 511	99.57 298	98.65 372	96.33 536	97.31 526	97.07 490	97.48 517	98.73 495	94.39 437	98.87 539	95.75 497	98.50 502	93.50 551

PCF-MVS	96.03 18	96.73 469	95.86 485	99.33 313	99.44 367	99.16 288	96.87 524	99.44 364	86.58 548	98.95 416	99.40 377	94.38 438	99.88 243	87.93 544	99.80 274	98.95 449
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VDDNet		98.97 305	98.82 315	99.42 271	99.71 209	98.81 351	99.62 67	98.68 472	99.81 92	99.38 337	99.80 109	94.25 439	99.85 299	98.79 233	99.32 433	99.59 217

SP-NN		96.37 481	96.23 476	96.77 515	96.83 548	96.95 476	96.47 533	97.07 529	96.75 501	93.41 550	97.75 527	94.13 440	95.69 552	96.25 472	97.43 530	97.68 523

HY-MVS	98.23 9	98.21 402	97.95 412	98.99 381	99.03 468	98.24 409	99.61 73	98.72 470	96.81 499	98.73 444	99.51 343	94.06 441	99.86 280	96.91 430	98.20 512	98.86 463

test_method		91.72 515	92.32 515	89.91 535	93.49 559	70.18 563	90.28 549	99.56 309	61.71 555	95.39 542	99.52 339	93.90 442	99.94 99	98.76 240	98.27 510	99.62 190

DIV-MVS_self_test		98.54 364	98.42 366	98.92 393	99.03 468	97.80 444	97.46 494	99.59 292	98.90 317	99.60 259	99.46 362	93.87 443	99.78 398	97.97 326	99.89 193	99.18 391

cl____		98.54 364	98.41 367	98.92 393	99.03 468	97.80 444	97.46 494	99.59 292	98.90 317	99.60 259	99.46 362	93.85 444	99.78 398	97.97 326	99.89 193	99.17 394

EMVS		96.96 463	97.28 445	95.99 528	98.76 503	91.03 550	95.26 543	98.61 477	99.34 236	98.92 422	98.88 484	93.79 445	99.66 480	92.87 530	99.05 461	97.30 529

EPNet_dtu		97.62 436	97.79 426	97.11 509	96.67 550	92.31 541	98.51 396	98.04 507	99.24 255	95.77 540	99.47 359	93.78 446	99.66 480	98.98 200	99.62 366	99.37 340
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test1111		97.74 430	98.16 396	96.49 522	99.60 272	89.86 558	99.71 37	91.21 555	99.89 56	99.88 83	99.87 57	93.73 447	99.90 205	99.56 84	99.99 19	99.70 108

K. test v3		98.87 324	98.60 337	99.69 140	99.93 24	99.46 198	99.74 27	94.97 545	99.78 103	99.88 83	99.88 51	93.66 448	99.97 45	99.61 77	99.95 117	99.64 172

ECVR-MVS		97.73 431	98.04 405	96.78 514	99.59 278	90.81 552	99.72 33	90.43 557	99.89 56	99.86 97	99.86 64	93.60 449	99.89 227	99.46 102	99.99 19	99.65 160

CHOSEN 280x420		98.41 381	98.41 367	98.40 445	99.34 401	95.89 505	96.94 521	99.44 364	98.80 335	99.25 371	99.52 339	93.51 450	99.98 27	98.94 213	99.98 55	99.32 357

NormalMVS		99.09 275	98.91 305	99.62 185	99.78 147	99.11 296	99.36 145	99.77 171	99.82 86	99.68 209	99.53 335	93.30 451	99.99 7	99.24 140	99.76 297	99.74 92

SymmetryMVS		99.01 298	98.82 315	99.58 203	99.65 256	99.11 296	99.36 145	99.20 435	99.82 86	99.68 209	99.53 335	93.30 451	99.99 7	99.24 140	99.63 364	99.64 172

CVMVSNet		98.61 352	98.88 307	97.80 476	99.58 288	93.60 535	99.26 187	99.64 259	99.66 152	99.72 189	99.67 235	93.26 453	99.93 121	99.30 132	99.81 267	99.87 46

Anonymous202405211		98.75 338	98.46 358	99.63 176	99.34 401	99.66 124	99.47 113	97.65 519	99.28 247	99.56 275	99.50 346	93.15 454	99.84 317	98.62 265	99.58 383	99.40 330

EPNet		98.13 408	97.77 428	99.18 355	94.57 558	97.99 430	99.24 194	97.96 510	99.74 112	97.29 522	99.62 276	93.13 455	99.97 45	98.59 266	99.83 247	99.58 223
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FA-MVS(test-final)		98.52 366	98.32 379	99.10 367	99.48 352	98.67 365	99.77 19	98.60 480	97.35 476	99.63 239	99.80 109	93.07 456	99.84 317	97.92 329	99.30 435	98.78 471

PAPM		95.61 504	94.71 508	98.31 453	99.12 448	96.63 485	96.66 531	98.46 488	90.77 545	96.25 537	98.68 500	93.01 457	99.69 457	81.60 552	97.86 526	98.62 480

Vis-MVSNet (Re-imp)		98.77 336	98.58 342	99.34 310	99.78 147	98.88 341	99.61 73	99.56 309	99.11 285	99.24 374	99.56 321	93.00 458	99.78 398	97.43 388	99.89 193	99.35 346

blended_shiyan6		97.82 425	97.46 437	98.92 393	98.08 532	97.46 457	97.73 474	99.34 397	97.96 437	98.33 473	97.35 535	92.78 459	99.84 317	99.04 190	96.53 538	99.46 297

E-PMN		97.14 460	97.43 440	96.27 524	98.79 498	91.62 546	95.54 540	99.01 456	99.44 212	98.88 426	99.12 450	92.78 459	99.68 469	94.30 520	99.03 464	97.50 525

blended_shiyan8		97.82 425	97.45 439	98.92 393	98.06 533	97.45 459	97.73 474	99.35 393	97.96 437	98.35 472	97.34 536	92.76 461	99.84 317	99.04 190	96.49 544	99.47 292

FMVSNet3		98.80 333	98.63 335	99.32 318	99.13 446	98.72 361	99.10 255	99.48 352	99.23 257	99.62 249	99.64 250	92.57 462	99.86 280	98.96 205	99.90 177	99.39 334

HyFIR lowres test		98.91 316	98.64 333	99.73 114	99.85 76	99.47 190	98.07 446	99.83 116	98.64 358	99.89 73	99.60 296	92.57 462	100.00 1	99.33 127	99.97 78	99.72 100

RPMNet		98.60 355	98.53 349	98.83 413	99.05 463	98.12 420	99.30 168	99.62 266	99.86 66	99.16 389	99.74 172	92.53 464	99.92 155	98.75 241	98.77 482	98.44 495

SIFT-MNN		97.55 441	97.74 429	96.98 512	99.38 382	98.85 347	96.92 523	98.61 477	98.36 393	98.63 453	99.10 454	92.51 465	97.85 548	96.63 451	99.48 409	94.25 541

h-mvs33		98.61 352	98.34 377	99.44 264	99.60 272	98.67 365	99.27 182	99.44 364	99.68 137	99.32 353	99.49 351	92.50 466	100.00 1	99.24 140	96.51 542	99.65 160

hse-mvs2		98.52 366	98.30 382	99.16 356	99.29 415	98.60 379	98.77 349	99.02 453	99.68 137	99.32 353	99.04 462	92.50 466	99.85 299	99.24 140	97.87 525	99.03 437

PDCNetPlus		98.55 362	98.50 354	98.69 429	99.64 258	96.12 499	97.67 481	100.00 1	98.34 403	99.79 134	99.75 164	92.45 468	99.98 27	98.92 216	99.99 19	99.96 14

tpmvs		97.39 450	97.69 431	96.52 521	98.41 519	91.76 544	99.30 168	98.94 459	97.74 453	97.85 504	99.55 330	92.40 469	99.73 439	96.25 472	98.73 490	98.06 512

wanda-best-256-512		97.53 442	97.14 453	98.72 424	97.71 539	96.86 481	97.00 516	99.34 397	97.73 454	98.18 480	96.82 549	91.92 470	99.84 317	99.02 195	96.53 538	99.45 299

FE-blended-shiyan7		97.53 442	97.14 453	98.72 424	97.71 539	96.86 481	97.00 516	99.34 397	97.73 454	98.18 480	96.82 549	91.92 470	99.84 317	99.02 195	96.53 538	99.45 299

usedtu_blend_shiyan5		97.97 419	97.65 435	98.92 393	97.71 539	97.49 454	99.53 93	99.81 136	99.52 193	98.18 480	96.82 549	91.92 470	99.83 340	98.79 233	96.53 538	99.45 299

tpmrst		97.73 431	98.07 404	96.73 519	98.71 507	92.00 542	99.10 255	98.86 461	98.52 375	98.92 422	99.54 332	91.90 473	99.82 363	98.02 319	99.03 464	98.37 497

JIA-IIPM		98.06 413	97.92 418	98.50 440	98.59 512	97.02 475	98.80 344	98.51 484	99.88 61	97.89 500	99.87 57	91.89 474	99.90 205	98.16 310	97.68 527	98.59 483

CR-MVSNet		98.35 388	98.20 391	98.83 413	99.05 463	98.12 420	99.30 168	99.67 236	97.39 474	99.16 389	99.79 121	91.87 475	99.91 186	98.78 239	98.77 482	98.44 495

Patchmtry		98.78 334	98.54 348	99.49 245	98.89 484	99.19 281	99.32 159	99.67 236	99.65 158	99.72 189	99.79 121	91.87 475	99.95 82	98.00 323	99.97 78	99.33 353

MDTV_nov1_ep13_2view						91.44 548	99.14 234		97.37 475	99.21 381		91.78 477		96.75 441		99.03 437

XFeat-MNN		96.67 471	96.56 469	96.98 512	96.73 549	95.62 513	94.54 545	98.93 460	97.42 472	98.18 480	98.67 501	91.60 478	99.12 530	93.88 528	99.10 456	96.21 533

PatchT		98.45 376	98.32 379	98.83 413	98.94 478	98.29 408	99.24 194	98.82 464	99.84 76	99.08 402	99.76 156	91.37 479	99.94 99	98.82 226	99.00 466	98.26 502

test_yl		98.25 394	97.95 412	99.13 363	99.17 440	98.47 393	99.00 293	98.67 474	98.97 301	99.22 379	99.02 467	91.31 480	99.69 457	97.26 404	98.93 470	99.24 373

DCV-MVSNet		98.25 394	97.95 412	99.13 363	99.17 440	98.47 393	99.00 293	98.67 474	98.97 301	99.22 379	99.02 467	91.31 480	99.69 457	97.26 404	98.93 470	99.24 373

baseline1		97.73 431	97.33 444	98.96 385	99.30 413	97.73 446	99.40 128	98.42 490	99.33 239	99.46 312	99.21 437	91.18 482	99.82 363	98.35 289	91.26 550	99.32 357

tpm cat1		96.78 466	96.98 459	96.16 526	98.85 489	90.59 554	99.08 263	99.32 404	92.37 539	97.73 512	99.46 362	91.15 483	99.69 457	96.07 480	98.80 479	98.21 506

LFMVS		98.46 375	98.19 394	99.26 341	99.24 426	98.52 392	99.62 67	96.94 530	99.87 63	99.31 358	99.58 309	91.04 484	99.81 380	98.68 256	99.42 420	99.45 299

MDTV_nov1_ep13			97.73 430		98.70 508	90.83 551	99.15 230	98.02 508	98.51 376	98.82 434	99.61 286	90.98 485	99.66 480	96.89 432	98.92 472

MIMVSNet		98.43 378	98.20 391	99.11 365	99.53 327	98.38 404	99.58 83	98.61 477	98.96 303	99.33 350	99.76 156	90.92 486	99.81 380	97.38 391	99.76 297	99.15 398

ADS-MVSNet2		97.78 429	97.66 434	98.12 463	99.14 444	95.36 516	99.22 203	98.75 469	96.97 493	98.25 476	99.64 250	90.90 487	99.94 99	96.51 457	99.56 386	99.08 422

ADS-MVSNet		97.72 434	97.67 433	97.86 474	99.14 444	94.65 526	99.22 203	98.86 461	96.97 493	98.25 476	99.64 250	90.90 487	99.84 317	96.51 457	99.56 386	99.08 422

GDP-MVS		98.81 332	98.57 343	99.50 241	99.53 327	99.12 295	99.28 178	99.86 90	99.53 189	99.57 267	99.32 404	90.88 489	99.98 27	99.46 102	99.74 312	99.42 326

alignmvs		98.28 391	97.96 411	99.25 344	99.12 448	98.93 330	99.03 278	98.42 490	99.64 162	98.72 445	97.85 526	90.86 490	99.62 492	98.88 219	99.13 453	99.19 389

sam_mvs1												90.81 491				99.14 403

gbinet_0.2-2-1-0.02		97.52 444	97.07 455	98.88 407	97.35 547	97.35 465	97.17 507	99.25 421	97.86 449	98.41 470	96.54 555	90.74 492	99.85 299	98.80 232	97.51 529	99.43 321

PatchmatchNet		97.65 435	97.80 424	97.18 504	98.82 495	92.49 540	99.17 221	98.39 494	98.12 421	98.79 439	99.58 309	90.71 493	99.89 227	97.23 409	99.41 421	99.16 396
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
BP-MVS1		98.72 342	98.46 358	99.50 241	99.53 327	99.00 314	99.34 150	98.53 482	99.65 158	99.73 183	99.38 385	90.62 494	99.96 70	99.50 96	99.86 226	99.55 238

patchmatchnet-post											99.62 276	90.58 495	99.94 99

Patchmatch-RL test		98.60 355	98.36 374	99.33 313	99.77 160	99.07 306	98.27 421	99.87 81	98.91 316	99.74 177	99.72 187	90.57 496	99.79 394	98.55 271	99.85 233	99.11 407

sam_mvs												90.52 497

pmmvs3		98.08 411	97.80 424	98.91 398	99.41 377	97.69 448	97.87 468	99.66 241	95.87 511	99.50 301	99.51 343	90.35 498	99.97 45	98.55 271	99.47 410	99.08 422

SIFT-NN		94.78 509	94.89 505	94.45 531	98.23 526	97.29 467	94.93 544	95.84 540	95.82 514	94.78 545	97.12 541	90.26 499	92.28 556	88.91 539	98.14 517	93.77 547

test_post											52.41 568	90.25 500	99.86 280

Patchmatch-test		98.10 410	97.98 410	98.48 441	99.27 420	96.48 489	99.40 128	99.07 448	98.81 333	99.23 375	99.57 317	90.11 501	99.87 260	96.69 444	99.64 361	99.09 416

test-LLR		97.15 458	96.95 460	97.74 479	98.18 528	95.02 523	97.38 497	96.10 532	98.00 430	97.81 507	98.58 503	90.04 502	99.91 186	97.69 365	98.78 480	98.31 498

test0.0.03 1		97.37 451	96.91 463	98.74 422	97.72 538	97.57 451	97.60 486	97.36 525	98.00 430	99.21 381	98.02 520	90.04 502	99.79 394	98.37 287	95.89 547	98.86 463

GA-MVS		97.99 418	97.68 432	98.93 392	99.52 334	98.04 428	97.19 506	99.05 451	98.32 407	98.81 435	98.97 474	89.89 504	99.41 519	98.33 291	99.05 461	99.34 352

test_post1							99.14 234				51.63 569	89.54 505	99.82 363	96.86 433

AUN-MVS		97.82 425	97.38 442	99.14 361	99.27 420	98.53 390	98.72 358	99.02 453	98.10 422	97.18 525	99.03 466	89.26 506	99.85 299	97.94 328	97.91 523	99.03 437

FE-MVS		97.85 424	97.42 441	99.15 358	99.44 367	98.75 359	99.77 19	98.20 502	95.85 512	99.33 350	99.80 109	88.86 507	99.88 243	96.40 465	99.12 454	98.81 468

MVSTER		98.47 373	98.22 389	99.24 346	99.06 461	98.35 406	99.08 263	99.46 358	99.27 248	99.75 166	99.66 241	88.61 508	99.85 299	99.14 172	99.92 159	99.52 270

XFeat-NN		93.89 511	93.91 513	93.83 532	95.49 552	92.69 539	90.85 548	97.98 509	94.69 531	95.08 544	96.98 544	88.36 509	94.23 555	88.42 543	97.34 531	94.57 537

testing915		98.42 379	98.12 400	99.32 318	99.72 203	98.35 406	99.59 80	99.36 391	99.66 152	98.94 417	99.07 457	88.34 510	99.89 227	98.83 223	99.56 386	99.70 108

baseline2		96.83 465	96.28 473	98.46 443	99.09 459	96.91 479	98.83 336	93.87 552	97.23 482	96.23 539	98.36 513	88.12 511	99.90 205	96.68 445	98.14 517	98.57 487

cl22		97.56 439	97.28 445	98.40 445	98.37 521	96.75 484	97.24 505	99.37 387	97.31 478	99.41 328	99.22 433	87.30 512	99.37 522	97.70 359	99.62 366	99.08 422

dp		96.86 464	97.07 455	96.24 525	98.68 510	90.30 557	99.19 212	98.38 495	97.35 476	98.23 478	99.59 306	87.23 513	99.82 363	96.27 471	98.73 490	98.59 483

ET-MVSNet_ETH3D		96.78 466	96.07 480	98.91 398	99.26 423	97.92 437	97.70 479	96.05 535	97.96 437	92.37 551	98.43 511	87.06 514	99.90 205	98.27 296	97.56 528	98.91 457

thres100view900		96.39 480	96.03 481	97.47 489	99.63 263	95.93 503	99.18 216	97.57 520	98.75 346	98.70 448	97.31 539	87.04 515	99.67 475	87.62 545	98.51 499	96.81 531

thres600view7		96.60 474	96.16 478	97.93 470	99.63 263	96.09 502	99.18 216	97.57 520	98.77 342	98.72 445	97.32 538	87.04 515	99.72 441	88.57 541	98.62 495	97.98 517

tfpn200view9		96.30 484	95.89 483	97.53 484	99.58 288	96.11 500	99.00 293	97.54 523	98.43 383	98.52 463	96.98 544	86.85 517	99.67 475	87.62 545	98.51 499	96.81 531

thres400		96.40 479	95.89 483	97.92 471	99.58 288	96.11 500	99.00 293	97.54 523	98.43 383	98.52 463	96.98 544	86.85 517	99.67 475	87.62 545	98.51 499	97.98 517

thres200		96.09 490	95.68 490	97.33 500	99.48 352	96.22 497	98.53 393	97.57 520	98.06 428	98.37 471	96.73 552	86.84 519	99.61 497	86.99 548	98.57 496	96.16 535

tpm		97.15 458	96.95 460	97.75 478	98.91 479	94.24 529	99.32 159	97.96 510	97.71 457	98.29 474	99.32 404	86.72 520	99.92 155	98.10 317	96.24 545	99.09 416

EPMVS		96.53 475	96.32 472	97.17 506	98.18 528	92.97 538	99.39 130	89.95 558	98.21 414	98.61 455	99.59 306	86.69 521	99.72 441	96.99 424	99.23 448	98.81 468

CostFormer		96.71 470	96.79 468	96.46 523	98.90 480	90.71 553	99.41 123	98.68 472	94.69 531	98.14 489	99.34 403	86.32 522	99.80 390	97.60 376	98.07 521	98.88 461

MVStest1		98.22 400	98.09 402	98.62 431	99.04 466	96.23 496	99.20 206	99.92 48	99.44 212	99.98 14	99.87 57	85.87 523	99.67 475	99.91 34	99.57 385	99.95 16

thisisatest0515		96.98 462	96.42 471	98.66 430	99.42 375	97.47 456	97.27 502	94.30 548	97.24 481	99.15 392	98.86 485	85.01 524	99.87 260	97.10 419	99.39 423	98.63 479

tpm2		96.35 482	96.22 477	96.73 519	98.88 486	91.75 545	99.21 205	98.51 484	93.27 536	97.89 500	99.21 437	84.83 525	99.70 450	96.04 481	98.18 515	98.75 476

tttt0517		97.62 436	97.20 450	98.90 404	99.76 165	97.40 463	99.48 110	94.36 547	99.06 291	99.70 198	99.49 351	84.55 526	99.94 99	98.73 247	99.65 359	99.36 343

UWE-MVS-28		95.64 502	95.47 493	96.14 527	97.98 534	90.39 555	98.49 400	95.81 542	99.02 296	98.03 493	98.19 517	84.49 527	99.28 525	88.75 540	98.47 503	98.75 476

thisisatest0530		97.45 446	96.95 460	98.94 388	99.68 242	97.73 446	99.09 260	94.19 549	98.61 364	99.56 275	99.30 410	84.30 528	99.93 121	98.27 296	99.54 396	99.16 396

FPMVS		96.32 483	95.50 492	98.79 417	99.60 272	98.17 417	98.46 406	98.80 467	97.16 486	96.28 536	99.63 266	82.19 529	99.09 533	88.45 542	98.89 477	99.10 410

gg-mvs-nofinetune		95.87 497	95.17 503	97.97 468	98.19 527	96.95 476	99.69 45	89.23 559	99.89 56	96.24 538	99.94 20	81.19 530	99.51 513	93.99 527	98.20 512	97.44 526

reproduce_monomvs		97.40 449	97.46 437	97.20 503	99.05 463	91.91 543	99.20 206	99.18 438	99.84 76	99.86 97	99.75 164	80.67 531	99.83 340	99.69 65	99.95 117	99.85 51

GG-mvs-BLEND				97.36 497	97.59 542	96.87 480	99.70 38	88.49 560		94.64 546	97.26 540	80.66 532	99.12 530	91.50 535	96.50 543	96.08 536

FMVSNet5		97.80 428	97.25 448	99.42 271	98.83 492	98.97 321	99.38 133	99.80 144	98.87 321	99.25 371	99.69 216	80.60 533	99.91 186	98.96 205	99.90 177	99.38 336

WBMVS		97.50 445	97.18 451	98.48 441	98.85 489	95.89 505	98.44 408	99.52 338	99.53 189	99.52 291	99.42 369	80.10 534	99.86 280	99.24 140	99.95 117	99.68 128

UWE-MVS		96.21 488	95.78 487	97.49 486	98.53 514	93.83 533	98.04 449	93.94 551	98.96 303	98.46 467	98.17 518	79.86 535	99.87 260	96.99 424	99.06 459	98.78 471

UBG		96.53 475	95.95 482	98.29 456	98.87 487	96.31 494	98.48 401	98.07 506	98.83 329	97.32 520	96.54 555	79.81 536	99.62 492	96.84 437	98.74 487	98.95 449

TESTMET0.1,1		96.24 485	95.84 486	97.41 493	98.24 525	93.84 532	97.38 497	95.84 540	98.43 383	97.81 507	98.56 506	79.77 537	99.89 227	97.77 347	98.77 482	98.52 489

nomal-1		96.75 468	96.26 474	98.21 459	99.06 461	95.71 509	98.65 371	97.76 518	98.51 376	97.96 495	97.91 525	79.57 538	99.88 243	98.11 313	98.84 478	99.05 431

KD-MVS_2432*1600		95.89 495	95.41 496	97.31 501	94.96 553	93.89 530	97.09 511	99.22 429	97.23 482	98.88 426	99.04 462	79.23 539	99.54 506	96.24 474	96.81 535	98.50 493

miper_refine_blended		95.89 495	95.41 496	97.31 501	94.96 553	93.89 530	97.09 511	99.22 429	97.23 482	98.88 426	99.04 462	79.23 539	99.54 506	96.24 474	96.81 535	98.50 493

test-mter		96.23 486	95.73 489	97.74 479	98.18 528	95.02 523	97.38 497	96.10 532	97.90 442	97.81 507	98.58 503	79.12 541	99.91 186	97.69 365	98.78 480	98.31 498

test2506		94.73 510	94.59 510	95.15 530	99.59 278	85.90 560	99.75 25	74.01 563	99.89 56	99.71 194	99.86 64	79.00 542	99.90 205	99.52 92	99.99 19	99.65 160

0.4-1-1-0.1		93.18 512	91.66 516	97.73 481	95.83 551	95.29 518	95.30 542	95.90 538	93.59 534	90.58 553	94.40 561	77.87 543	99.77 411	97.31 396	84.20 552	98.15 510

0.4-1-1-0.2		92.59 513	91.07 517	97.15 507	94.73 557	93.68 534	93.50 547	95.91 536	92.68 538	90.48 554	93.52 563	77.77 544	99.75 429	97.19 414	83.88 553	98.01 516

blend_shiyan4		95.04 508	93.76 514	98.88 407	97.92 535	97.49 454	97.72 476	99.34 397	97.93 441	97.65 515	97.11 542	77.69 545	99.83 340	98.79 233	79.72 557	99.33 353

myMVS_eth3d28		96.23 486	95.74 488	97.70 483	98.86 488	95.59 514	98.66 368	98.14 504	98.96 303	97.67 514	97.06 543	76.78 546	98.92 538	97.10 419	98.41 505	98.58 485

testing3-2		96.51 477	96.43 470	96.74 518	99.36 388	91.38 549	99.10 255	97.87 515	99.48 199	98.57 460	98.71 496	76.65 547	99.66 480	98.87 220	99.26 442	99.18 391

IB-MVS	95.41 20	95.30 506	94.46 512	97.84 475	98.76 503	95.33 517	97.33 500	96.07 534	96.02 510	95.37 543	97.41 534	76.17 548	99.96 70	97.54 380	95.44 549	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
0.3-1-1-0.015		92.36 514	90.68 518	97.39 494	94.94 555	94.41 528	94.21 546	95.89 539	92.87 537	88.87 555	93.49 564	75.30 549	99.76 418	97.19 414	83.41 554	98.02 515

testing11		96.05 493	95.41 496	97.97 468	98.78 500	95.27 519	98.59 378	98.23 501	98.86 323	96.56 534	96.91 547	75.20 550	99.69 457	97.26 404	98.29 509	98.93 453

testing91		96.00 494	95.32 499	98.02 464	98.76 503	95.39 515	98.38 412	98.65 476	98.82 331	96.84 529	96.71 553	75.06 551	99.71 446	96.46 463	98.23 511	98.98 446

FBQ-MVS		96.06 492	95.42 494	97.98 466	98.90 480	95.77 507	98.71 362	98.20 502	98.34 403	97.83 506	97.34 536	74.90 552	99.39 521	96.20 476	98.40 506	98.78 471

testing99		95.86 498	95.19 502	97.87 473	98.76 503	95.03 522	98.62 372	98.44 489	98.68 352	96.67 532	96.66 554	74.31 553	99.69 457	96.51 457	98.03 522	98.90 458

ETVMVS		96.14 489	95.22 501	98.89 405	98.80 496	98.01 429	98.66 368	98.35 497	98.71 349	97.18 525	96.31 560	74.23 554	99.75 429	96.64 450	98.13 520	98.90 458

testing3		96.48 478	95.63 491	99.01 380	99.23 428	97.81 442	98.90 321	99.10 447	98.72 347	97.84 505	97.92 524	72.44 555	99.85 299	97.21 411	99.33 431	99.35 346

myMVS_eth3d		95.63 503	94.73 507	98.34 450	98.50 516	96.36 492	98.60 375	99.21 432	97.89 444	96.76 530	96.37 558	72.10 556	99.57 501	94.38 518	98.73 490	99.09 416

dongtai		89.37 516	88.91 519	90.76 534	99.19 436	77.46 561	95.47 541	87.82 561	92.28 541	94.17 547	98.82 490	71.22 557	95.54 553	63.85 556	97.34 531	99.27 368

testing222		95.60 505	94.59 510	98.61 432	98.66 511	97.45 459	98.54 391	97.90 514	98.53 373	96.54 535	96.47 557	70.62 558	99.81 380	95.91 491	98.15 516	98.56 488

kuosan		85.65 518	84.57 521	88.90 536	97.91 536	77.11 562	96.37 535	87.62 562	85.24 550	85.45 556	96.83 548	69.94 559	90.98 557	45.90 558	95.83 548	98.62 480

MVS_clip		74.80 520	77.14 522	67.78 538	84.58 561	66.83 564	78.80 551	52.59 565	49.02 556	94.13 548	97.99 523	68.69 560	48.60 560	80.92 553	87.52 551	87.92 553

VLMVS_CLIP		76.68 519	76.70 523	76.61 537	60.81 562	61.63 565	78.48 552	91.77 554	64.66 554	83.93 557	93.59 562	55.35 561	75.94 558	79.82 554	81.86 555	92.28 552

VLMVS		62.60 521	63.55 524	59.72 539	60.35 563	58.44 566	68.37 553	54.75 564	23.35 558	80.04 558	90.18 566	54.59 562	52.33 559	63.04 557	77.30 558	68.41 555

MVS_baseline		39.37 522	46.36 525	18.41 540	48.75 564	10.55 568	42.43 554	13.32 567	4.65 561	75.25 559	91.61 565	29.41 563	0.06 563	38.83 559	72.99 559	44.63 556

test123		29.31 523	33.05 528	18.08 541	25.93 566	12.24 567	97.53 490	10.93 568	11.78 559	24.21 561	50.08 571	21.04 564	8.60 561	23.51 560	32.43 561	33.39 557

testmvs		28.94 524	33.33 526	15.79 542	26.03 565	9.81 569	96.77 525	15.67 566	11.55 560	23.87 562	50.74 570	19.03 565	8.53 562	23.21 561	33.07 560	29.03 558

mmdepth		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

monomultidepth		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

test_blank		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uanet_test		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

DCPMVS		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

sosnet-low-res		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

sosnet		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uncertanet		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

Regformer		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

ab-mvs-re		8.26 537	11.02 540	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	99.16 443	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uanet		8.33 527	11.11 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	100.00 1	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet2					0.00 567	95.19 521	97.64 482	99.19 436	98.09 424
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														98.28 294	99.92 159	99.44 314
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
aaatest				99.74 104	99.76 165	99.65 130	99.38 133	99.78 166	99.58 183	99.81 120	99.66 241		99.90 205	97.69 365	99.79 280	99.67 137

WAC-MVS						96.36 492								95.20 508

FOURS1					99.83 91	99.89 10	99.74 27	99.71 209	99.69 133	99.63 239

MSC_two_6792asdad				99.74 104	99.03 468	99.53 177		99.23 426					99.92 155	97.77 347	99.69 343	99.78 78

No_MVS				99.74 104	99.03 468	99.53 177		99.23 426					99.92 155	97.77 347	99.69 343	99.78 78

eth-test2					0.00 567

eth-test					0.00 567

IU-MVS					99.69 233	99.77 64		99.22 429	97.50 467	99.69 202				97.75 351	99.70 334	99.77 82

save fliter					99.53 327	99.25 260	98.29 420	99.38 386	99.07 289

test_0728_SECOND				99.83 42	99.70 225	99.79 55	99.14 234	99.61 274					99.92 155	97.88 333	99.72 327	99.77 82

GSMVS																99.14 403

test_part2					99.62 267	99.67 121				99.55 280

MTGPA								99.53 333

MTMP							99.09 260	98.59 481

gm-plane-assit					97.59 542	89.02 559			93.47 535		98.30 514		99.84 317	96.38 467

test9_res														95.10 510	99.44 415	99.50 279

agg_prior2														94.58 517	99.46 414	99.50 279

agg_prior					99.35 392	99.36 236		99.39 381		97.76 510			99.85 299

test_prior4						99.19 281	98.00 455

test_prior				99.46 257	99.35 392	99.22 271		99.39 381					99.69 457			99.48 288

旧先验2							97.94 462		95.33 521	98.94 417			99.88 243	96.75 441

新几何2							98.04 449

无先验							98.01 452	99.23 426	95.83 513				99.85 299	95.79 496		99.44 314

原ACMM2							97.92 464

testdata2													99.89 227	95.99 485

testdata1							97.72 476		97.86 449

plane_prior7					99.58 288	99.38 227

plane_prior5								99.54 322					99.82 363	95.84 493	99.78 288	99.60 210

plane_prior4											99.25 424

plane_prior3						99.31 246			98.36 393	99.14 394

plane_prior2							98.80 344		98.94 307

plane_prior1					99.51 336

plane_prior						99.24 265	98.42 410		97.87 447						99.71 331

n2								0.00 569

nn								0.00 569

door-mid								99.83 116

test11								99.29 412

door								99.77 171

HQP5-MVS						98.94 327

HQP-NCC					99.31 409		97.98 457		97.45 469	98.15 485

ACMP_Plane					99.31 409		97.98 457		97.45 469	98.15 485

BP-MVS														94.73 514

HQP4-MVS										98.15 485			99.70 450			99.53 259

HQP3-MVS								99.37 387							99.67 354

NP-MVS					99.40 378	99.13 293					98.83 488

ACMMP++_ref															99.94 136

ACMMP++															99.79 280

High-resolution multi-view benchmark