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 3	99.98 3	99.76 65	99.12 208	100.00 1	100.00 1	99.99 7	99.91 28	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 3	99.97 6	99.74 80	99.01 243	99.99 11	99.99 3	99.98 14	99.88 47	99.97 2	99.99 8	99.96 9	100.00 1	99.98 5

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 48	99.88 44	99.55 148	99.17 188	99.98 12	99.99 3	99.96 31	99.84 72	99.96 3	99.99 8	99.96 9	99.99 16	99.88 35

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 38	99.82 74	99.70 99	99.17 188	99.97 20	99.99 3	99.96 31	99.82 83	99.94 4	100.00 1	99.95 13	100.00 1	99.80 59

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 52	99.70 35	99.86 64	99.89 46	99.98 14	99.90 33	99.94 4	99.98 23	99.75 51	100.00 1	99.90 27

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 49	99.72 30	99.88 57	99.92 36	99.98 14	99.93 21	99.94 4	99.98 23	99.77 50	100.00 1	99.92 24

test_fmvsmconf_n		99.85 12	99.84 20	99.88 18	99.91 31	99.73 83	98.97 257	99.98 12	99.99 3	99.96 31	99.85 65	99.93 7	99.99 8	99.94 18	99.99 16	99.93 20

fmvsm_s_conf0.5_n_6		99.80 26	99.78 34	99.85 30	99.78 111	99.78 52	99.00 246	99.97 20	99.96 24	99.97 23	99.56 255	99.92 8	99.93 106	99.91 29	99.99 16	99.83 51

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 44	99.86 18	99.08 224	99.97 20	99.98 15	99.96 31	99.79 104	99.90 9	99.99 8	99.96 9	99.99 16	99.90 27

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 52	99.07 228	99.98 12	99.99 3	99.98 14	99.90 33	99.88 10	99.92 133	99.93 22	99.99 16	99.98 5

test_vis1_n_1920		99.72 47	99.88 7	99.27 266	99.93 24	97.84 344	99.34 129	100.00 1	99.99 3	99.99 7	99.82 83	99.87 11	99.99 8	99.97 4	99.99 16	99.97 10

test_fmvs3		99.83 21	99.93 2	99.53 187	99.96 7	98.62 293	99.67 50	100.00 1	99.95 28	100.00 1	99.95 16	99.85 12	99.99 8	99.98 1	99.99 16	99.98 5

mvsany_test3		99.85 12	99.88 7	99.75 84	99.95 15	99.37 191	99.53 88	99.98 12	99.77 86	99.99 7	99.95 16	99.85 12	99.94 86	99.95 13	99.98 46	99.94 17

fmvsm_s_conf0.5_n_4		99.78 32	99.78 34	99.79 60	99.75 136	99.56 144	98.98 255	99.94 37	99.92 36	99.97 23	99.72 148	99.84 14	99.92 133	99.91 29	99.98 46	99.89 33

wuyk23d		97.58 342	99.13 168	92.93 415	99.69 166	99.49 155	99.52 89	99.77 110	97.97 337	99.96 31	99.79 104	99.84 14	99.94 86	95.85 383	99.82 192	79.36 433

fmvsm_s_conf0.5_n_7		99.73 45	99.78 34	99.60 162	99.74 144	98.93 263	98.85 274	99.96 28	99.96 24	99.97 23	99.76 127	99.82 16	99.96 59	99.95 13	99.98 46	99.90 27

cdsmvs_eth3d_5k		24.88 405	33.17 407	0.00 421	0.00 444	0.00 446	0.00 432	99.62 190	0.00 439	0.00 440	99.13 353	99.82 16	0.00 440	0.00 439	0.00 438	0.00 436

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 18	99.91 31	99.90 7	99.96 1	99.92 40	99.90 40	99.97 23	99.87 53	99.81 18	99.95 70	99.54 73	99.99 16	99.80 59
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 40	99.86 13	99.45 210	99.93 24	98.40 306	99.30 144	99.98 12	99.94 31	99.99 7	99.89 38	99.80 19	99.97 37	99.96 9	99.97 64	99.97 10

test_vis3_rt		99.89 3	99.90 4	99.87 24	99.98 3	99.75 73	99.70 35	100.00 1	99.73 88	100.00 1	99.89 38	99.79 20	99.88 208	99.98 1	100.00 1	99.98 5

fmvsm_s_conf0.5_n		99.83 21	99.81 26	99.87 24	99.85 59	99.78 52	99.03 237	99.96 28	99.99 3	99.97 23	99.84 72	99.78 21	99.92 133	99.92 26	99.99 16	99.92 24

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 20	99.99 3	100.00 1	99.98 13	99.78 21	100.00 1	99.92 26	100.00 1	99.87 39

test_djsdf		99.84 17	99.81 26	99.91 3	99.94 18	99.84 25	99.77 16	99.80 95	99.73 88	99.97 23	99.92 25	99.77 23	99.98 23	99.43 88	100.00 1	99.90 27

mvsany_test1		99.44 116	99.45 105	99.40 229	99.37 294	98.64 291	97.90 384	99.59 214	99.27 185	99.92 52	99.82 83	99.74 24	99.93 106	99.55 72	99.87 157	99.63 144

pmmvs6		99.86 10	99.86 13	99.83 38	99.94 18	99.90 7	99.83 7	99.91 46	99.85 62	99.94 44	99.95 16	99.73 25	99.90 175	99.65 60	99.97 64	99.69 98

fmvsm_s_conf0.5_n_5		99.78 32	99.76 44	99.85 30	99.79 103	99.72 88	98.84 276	99.96 28	99.96 24	99.96 31	99.72 148	99.71 26	99.99 8	99.93 22	99.98 46	99.85 44

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 142	99.93 33	99.95 41	99.89 38	99.71 26	99.96 59	99.51 78	99.97 64	99.84 47

XVG-OURS		99.21 180	99.06 192	99.65 133	99.82 74	99.62 126	97.87 385	99.74 126	98.36 306	99.66 168	99.68 184	99.71 26	99.90 175	96.84 333	99.88 145	99.43 251

XVG-OURS-SEG-HR		99.16 195	98.99 219	99.66 127	99.84 63	99.64 119	98.25 347	99.73 130	98.39 303	99.63 175	99.43 293	99.70 29	99.90 175	97.34 298	98.64 390	99.44 245

DeepC-MVS	98.90 4	99.62 76	99.61 71	99.67 120	99.72 151	99.44 169	99.24 166	99.71 142	99.27 185	99.93 47	99.90 33	99.70 29	99.93 106	98.99 154	99.99 16	99.64 139
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 3	99.95 15	99.82 38	99.10 216	99.98 12	99.99 3	99.98 14	99.91 28	99.68 31	99.93 106	99.93 22	99.99 16	99.99 2

fmvsm_l_conf0.5_n_a		99.80 26	99.79 30	99.84 35	99.88 44	99.64 119	99.12 208	99.91 46	99.98 15	99.95 41	99.67 188	99.67 32	99.99 8	99.94 18	99.99 16	99.88 35

mmtdpeth		99.78 32	99.83 21	99.66 127	99.85 59	99.05 249	99.79 12	99.97 20	100.00 1	99.43 246	99.94 19	99.64 33	99.94 86	99.83 42	99.99 16	99.98 5

ACMH	98.42 6	99.59 80	99.54 90	99.72 104	99.86 55	99.62 126	99.56 84	99.79 101	98.77 263	99.80 103	99.85 65	99.64 33	99.85 259	98.70 187	99.89 136	99.70 92
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs5depth		99.88 6	99.91 3	99.80 53	99.92 29	99.42 176	99.94 3	100.00 1	99.97 21	99.89 62	99.99 12	99.63 35	99.97 37	99.87 40	99.99 16	100.00 1

GeoE		99.69 53	99.66 60	99.78 64	99.76 124	99.76 65	99.60 76	99.82 83	99.46 154	99.75 129	99.56 255	99.63 35	99.95 70	99.43 88	99.88 145	99.62 155

pm-mvs1		99.79 30	99.79 30	99.78 64	99.91 31	99.83 30	99.76 20	99.87 59	99.73 88	99.89 62	99.87 53	99.63 35	99.87 222	99.54 73	99.92 115	99.63 144

DSMNet-mixed		99.48 101	99.65 62	98.95 310	99.71 154	97.27 364	99.50 96	99.82 83	99.59 135	99.41 255	99.85 65	99.62 38	100.00 1	99.53 76	99.89 136	99.59 176

Vis-MVSNet		99.75 42	99.74 47	99.79 60	99.88 44	99.66 110	99.69 42	99.92 40	99.67 108	99.77 121	99.75 133	99.61 39	99.98 23	99.35 104	99.98 46	99.72 86
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 3	99.99 1	99.91 4	99.65 59	100.00 1	99.90 40	100.00 1	99.97 14	99.61 39	99.97 37	99.75 51	100.00 1	99.84 47

fmvsm_l_conf0.5_n		99.80 26	99.78 34	99.85 30	99.88 44	99.66 110	99.11 213	99.91 46	99.98 15	99.96 31	99.64 200	99.60 41	99.99 8	99.95 13	99.99 16	99.88 35

TransMVSNet (Re)		99.78 32	99.77 40	99.81 48	99.91 31	99.85 20	99.75 22	99.86 64	99.70 99	99.91 55	99.89 38	99.60 41	99.87 222	99.59 65	99.74 234	99.71 89

fmvsm_s_conf0.5_n_a		99.82 23	99.79 30	99.89 11	99.85 59	99.82 38	99.03 237	99.96 28	99.99 3	99.97 23	99.84 72	99.58 43	99.93 106	99.92 26	99.98 46	99.93 20

test_f		99.75 42	99.88 7	99.37 238	99.96 7	98.21 318	99.51 95	100.00 1	99.94 31	100.00 1	99.93 21	99.58 43	99.94 86	99.97 4	99.99 16	99.97 10

SPE-MVS-test		99.68 56	99.70 51	99.64 140	99.57 215	99.83 30	99.78 14	99.97 20	99.92 36	99.50 231	99.38 306	99.57 45	99.95 70	99.69 55	99.90 126	99.15 318

PMMVS2		99.48 101	99.45 105	99.57 174	99.76 124	98.99 252	98.09 361	99.90 51	98.95 234	99.78 113	99.58 244	99.57 45	99.93 106	99.48 82	99.95 91	99.79 67

EC-MVSNet		99.69 53	99.69 54	99.68 117	99.71 154	99.91 4	99.76 20	99.96 28	99.86 56	99.51 229	99.39 304	99.57 45	99.93 106	99.64 62	99.86 165	99.20 306

SD-MVS		99.01 229	99.30 140	98.15 366	99.50 252	99.40 183	98.94 264	99.61 197	99.22 197	99.75 129	99.82 83	99.54 48	95.51 436	97.48 290	99.87 157	99.54 200
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 56	99.68 57	99.69 115	99.81 84	99.59 137	99.29 151	99.90 51	99.71 94	99.79 109	99.73 141	99.54 48	99.84 274	99.36 101	99.96 77	99.65 129
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 30	99.77 40	99.85 30	99.81 84	99.71 91	98.97 257	99.92 40	99.98 15	99.97 23	99.86 60	99.53 50	99.95 70	99.88 37	99.99 16	99.89 33

sd_testset		99.78 32	99.78 34	99.80 53	99.80 91	99.76 65	99.80 11	99.79 101	99.97 21	99.89 62	99.89 38	99.53 50	99.99 8	99.36 101	99.96 77	99.65 129

SDMVSNet		99.77 39	99.77 40	99.76 74	99.80 91	99.65 116	99.63 61	99.86 64	99.97 21	99.89 62	99.89 38	99.52 52	99.99 8	99.42 93	99.96 77	99.65 129

CS-MVS		99.67 62	99.70 51	99.58 168	99.53 237	99.84 25	99.79 12	99.96 28	99.90 40	99.61 190	99.41 296	99.51 53	99.95 70	99.66 58	99.89 136	98.96 360

test_fmvs2		99.72 47	99.85 17	99.34 245	99.91 31	98.08 332	99.48 102	100.00 1	99.90 40	99.99 7	99.91 28	99.50 54	99.98 23	99.98 1	99.99 16	99.96 13

anonymousdsp		99.80 26	99.77 40	99.90 8	99.96 7	99.88 12	99.73 27	99.85 70	99.70 99	99.92 52	99.93 21	99.45 55	99.97 37	99.36 101	100.00 1	99.85 44

fmvsm_s_conf0.1_n_2		99.81 25	99.78 34	99.89 11	99.93 24	99.76 65	98.92 266	99.98 12	99.99 3	99.99 7	99.88 47	99.43 56	99.94 86	99.94 18	99.99 16	99.99 2

tt0805		99.63 70	99.57 83	99.81 48	99.87 52	99.88 12	99.58 79	98.70 369	99.72 92	99.91 55	99.60 236	99.43 56	99.81 314	99.81 47	99.53 307	99.73 83

fmvsm_s_conf0.5_n_2		99.78 32	99.75 46	99.88 18	99.82 74	99.76 65	98.88 269	99.92 40	99.98 15	99.98 14	99.85 65	99.42 58	99.94 86	99.93 22	99.98 46	99.94 17

ETV-MVS		99.18 189	99.18 160	99.16 282	99.34 310	99.28 209	99.12 208	99.79 101	99.48 146	98.93 328	98.55 405	99.40 59	99.93 106	98.51 199	99.52 310	98.28 409

xiu_mvs_v1_base_debu		99.23 167	99.34 128	98.91 317	99.59 200	98.23 315	98.47 329	99.66 167	99.61 127	99.68 158	98.94 383	99.39 60	99.97 37	99.18 130	99.55 300	98.51 399

xiu_mvs_v1_base		99.23 167	99.34 128	98.91 317	99.59 200	98.23 315	98.47 329	99.66 167	99.61 127	99.68 158	98.94 383	99.39 60	99.97 37	99.18 130	99.55 300	98.51 399

xiu_mvs_v1_base_debi		99.23 167	99.34 128	98.91 317	99.59 200	98.23 315	98.47 329	99.66 167	99.61 127	99.68 158	98.94 383	99.39 60	99.97 37	99.18 130	99.55 300	98.51 399

ACMM	98.09 11	99.46 110	99.38 118	99.72 104	99.80 91	99.69 103	99.13 204	99.65 177	98.99 227	99.64 171	99.72 148	99.39 60	99.86 241	98.23 217	99.81 202	99.60 169
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v2_base		99.02 223	99.11 175	98.77 335	99.37 294	98.09 329	98.13 356	99.51 261	99.47 151	99.42 249	98.54 406	99.38 64	99.97 37	98.83 171	99.33 336	98.24 411

XXY-MVS		99.71 50	99.67 58	99.81 48	99.89 39	99.72 88	99.59 77	99.82 83	99.39 170	99.82 92	99.84 72	99.38 64	99.91 156	99.38 97	99.93 111	99.80 59

LPG-MVS_test		99.22 175	99.05 196	99.74 89	99.82 74	99.63 124	99.16 194	99.73 130	97.56 357	99.64 171	99.69 173	99.37 66	99.89 194	96.66 343	99.87 157	99.69 98

LGP-MVS_train				99.74 89	99.82 74	99.63 124		99.73 130	97.56 357	99.64 171	99.69 173	99.37 66	99.89 194	96.66 343	99.87 157	99.69 98

TDRefinement		99.72 47	99.70 51	99.77 67	99.90 37	99.85 20	99.86 6	99.92 40	99.69 102	99.78 113	99.92 25	99.37 66	99.88 208	98.93 166	99.95 91	99.60 169

testgi		99.29 155	99.26 151	99.37 238	99.75 136	98.81 272	98.84 276	99.89 53	98.38 304	99.75 129	99.04 367	99.36 69	99.86 241	99.08 148	99.25 348	99.45 240

Fast-Effi-MVS+		99.02 223	98.87 238	99.46 207	99.38 292	99.50 154	99.04 234	99.79 101	97.17 379	98.62 362	98.74 396	99.34 70	99.95 70	98.32 210	99.41 326	98.92 367

casdiffmvs		99.63 70	99.61 71	99.67 120	99.79 103	99.59 137	99.13 204	99.85 70	99.79 80	99.76 124	99.72 148	99.33 71	99.82 299	99.21 124	99.94 104	99.59 176
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 69	99.67 58	99.56 177	99.75 136	98.98 253	98.96 260	99.87 59	99.88 51	99.84 86	99.64 200	99.32 72	99.91 156	99.78 49	99.96 77	99.80 59

new-patchmatchnet		99.35 142	99.57 83	98.71 340	99.82 74	96.62 379	98.55 317	99.75 120	99.50 143	99.88 71	99.87 53	99.31 73	99.88 208	99.43 88	100.00 1	99.62 155

HPM-MVS_fast		99.43 119	99.30 140	99.80 53	99.83 67	99.81 43	99.52 89	99.70 147	98.35 311	99.51 229	99.50 274	99.31 73	99.88 208	98.18 224	99.84 175	99.69 98

EG-PatchMatch MVS		99.57 81	99.56 88	99.62 156	99.77 120	99.33 201	99.26 159	99.76 115	99.32 179	99.80 103	99.78 115	99.29 75	99.87 222	99.15 136	99.91 125	99.66 121

DeepPCF-MVS	98.42 6	99.18 189	99.02 205	99.67 120	99.22 337	99.75 73	97.25 412	99.47 273	98.72 268	99.66 168	99.70 166	99.29 75	99.63 395	98.07 234	99.81 202	99.62 155

pcd_1.5k_mvsjas		16.61 406	22.14 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	99.28 77	0.00 440	0.00 439	0.00 438	0.00 436

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 58	99.68 46	99.85 70	99.95 28	99.98 14	99.92 25	99.28 77	99.98 23	99.75 51	100.00 1	99.94 17

PS-MVSNAJ		99.00 231	99.08 186	98.76 336	99.37 294	98.10 328	98.00 372	99.51 261	99.47 151	99.41 255	98.50 408	99.28 77	99.97 37	98.83 171	99.34 335	98.20 415

TSAR-MVS + MP.		99.34 147	99.24 155	99.63 147	99.82 74	99.37 191	99.26 159	99.35 306	98.77 263	99.57 201	99.70 166	99.27 80	99.88 208	97.71 268	99.75 227	99.65 129
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
testf1		99.63 70	99.60 74	99.72 104	99.94 18	99.95 2	99.47 105	99.89 53	99.43 165	99.88 71	99.80 94	99.26 81	99.90 175	98.81 175	99.88 145	99.32 278

APD_test2		99.63 70	99.60 74	99.72 104	99.94 18	99.95 2	99.47 105	99.89 53	99.43 165	99.88 71	99.80 94	99.26 81	99.90 175	98.81 175	99.88 145	99.32 278

ACMH+	98.40 8	99.50 95	99.43 110	99.71 109	99.86 55	99.76 65	99.32 136	99.77 110	99.53 139	99.77 121	99.76 127	99.26 81	99.78 327	97.77 260	99.88 145	99.60 169

HPM-MVS		99.25 163	99.07 190	99.78 64	99.81 84	99.75 73	99.61 70	99.67 162	97.72 352	99.35 267	99.25 338	99.23 84	99.92 133	97.21 313	99.82 192	99.67 112
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DELS-MVS		99.34 147	99.30 140	99.48 202	99.51 246	99.36 195	98.12 357	99.53 251	99.36 175	99.41 255	99.61 228	99.22 85	99.87 222	99.21 124	99.68 260	99.20 306
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
test_fmvs1_n		99.68 56	99.81 26	99.28 263	99.95 15	97.93 341	99.49 100	100.00 1	99.82 72	99.99 7	99.89 38	99.21 86	99.98 23	99.97 4	99.98 46	99.93 20

pmmvs-eth3d		99.48 101	99.47 99	99.51 192	99.77 120	99.41 182	98.81 284	99.66 167	99.42 169	99.75 129	99.66 193	99.20 87	99.76 338	98.98 156	99.99 16	99.36 268

COLMAP_ROB	98.06 12	99.45 114	99.37 121	99.70 113	99.83 67	99.70 99	99.38 120	99.78 107	99.53 139	99.67 163	99.78 115	99.19 88	99.86 241	97.32 299	99.87 157	99.55 191
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TSAR-MVS + GP.		99.12 203	99.04 202	99.38 235	99.34 310	99.16 232	98.15 353	99.29 319	98.18 326	99.63 175	99.62 219	99.18 89	99.68 375	98.20 220	99.74 234	99.30 284

MVS_111021_HR		99.12 203	99.02 205	99.40 229	99.50 252	99.11 238	97.92 381	99.71 142	98.76 266	99.08 316	99.47 285	99.17 90	99.54 409	97.85 255	99.76 225	99.54 200

3Dnovator	99.15 2	99.43 119	99.36 124	99.65 133	99.39 289	99.42 176	99.70 35	99.56 230	99.23 193	99.35 267	99.80 94	99.17 90	99.95 70	98.21 219	99.84 175	99.59 176

EGC-MVSNET		89.05 401	85.52 404	99.64 140	99.89 39	99.78 52	99.56 84	99.52 256	24.19 436	49.96 437	99.83 76	99.15 92	99.92 133	97.71 268	99.85 170	99.21 302

UA-Net		99.78 32	99.76 44	99.86 28	99.72 151	99.71 91	99.91 4	99.95 35	99.96 24	99.71 148	99.91 28	99.15 92	99.97 37	99.50 80	100.00 1	99.90 27

baseline		99.63 70	99.62 67	99.66 127	99.80 91	99.62 126	99.44 111	99.80 95	99.71 94	99.72 143	99.69 173	99.15 92	99.83 289	99.32 110	99.94 104	99.53 205

OPM-MVS		99.26 162	99.13 168	99.63 147	99.70 162	99.61 132	98.58 311	99.48 270	98.50 292	99.52 223	99.63 212	99.14 95	99.76 338	97.89 248	99.77 223	99.51 217
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Effi-MVS+		99.06 214	98.97 223	99.34 245	99.31 317	98.98 253	98.31 342	99.91 46	98.81 256	98.79 348	98.94 383	99.14 95	99.84 274	98.79 177	98.74 383	99.20 306

ttmdpeth		99.48 101	99.55 89	99.29 260	99.76 124	98.16 323	99.33 133	99.95 35	99.79 80	99.36 265	99.89 38	99.13 97	99.77 335	99.09 146	99.64 273	99.93 20

v7n		99.82 23	99.80 29	99.88 18	99.96 7	99.84 25	99.82 9	99.82 83	99.84 65	99.94 44	99.91 28	99.13 97	99.96 59	99.83 42	99.99 16	99.83 51

nrg030		99.70 51	99.66 60	99.82 43	99.76 124	99.84 25	99.61 70	99.70 147	99.93 33	99.78 113	99.68 184	99.10 99	99.78 327	99.45 86	99.96 77	99.83 51

MSDG		99.08 210	98.98 222	99.37 238	99.60 195	99.13 235	97.54 398	99.74 126	98.84 252	99.53 221	99.55 263	99.10 99	99.79 324	97.07 320	99.86 165	99.18 311

PC_three_1452									97.56 357	99.68 158	99.41 296	99.09 101	97.09 433	96.66 343	99.60 287	99.62 155

v1240		99.56 84	99.58 79	99.51 192	99.80 91	99.00 250	99.00 246	99.65 177	99.15 211	99.90 58	99.75 133	99.09 101	99.88 208	99.90 33	99.96 77	99.67 112

MVS_111021_LR		99.13 201	99.03 204	99.42 220	99.58 205	99.32 203	97.91 383	99.73 130	98.68 272	99.31 281	99.48 281	99.09 101	99.66 385	97.70 271	99.77 223	99.29 287

v1921920		99.56 84	99.57 83	99.55 181	99.75 136	99.11 238	99.05 229	99.61 197	99.15 211	99.88 71	99.71 158	99.08 104	99.87 222	99.90 33	99.97 64	99.66 121

v1192		99.57 81	99.57 83	99.57 174	99.77 120	99.22 223	99.04 234	99.60 208	99.18 200	99.87 79	99.72 148	99.08 104	99.85 259	99.89 36	99.98 46	99.66 121

fmvsm_s_conf0.5_n_8		99.76 40	99.72 49	99.88 18	99.82 74	99.75 73	99.02 240	99.87 59	99.98 15	99.98 14	99.81 90	99.07 106	99.97 37	99.91 29	99.99 16	99.92 24

MGCFI-Net		99.02 223	99.01 208	99.06 300	99.11 360	98.60 294	99.63 61	99.67 162	99.63 120	98.58 366	97.65 424	99.07 106	99.57 405	98.85 169	98.92 370	99.03 351

mamv4		99.73 45	99.74 47	99.70 113	99.66 181	99.87 14	99.69 42	99.93 38	99.93 33	99.93 47	99.86 60	99.07 106	100.00 1	99.66 58	99.92 115	99.24 293

test_0402		99.22 175	99.14 166	99.45 210	99.79 103	99.43 173	99.28 153	99.68 157	99.54 137	99.40 260	99.56 255	99.07 106	99.82 299	96.01 374	99.96 77	99.11 327

ACMP	97.51 14	99.05 217	98.84 242	99.67 120	99.78 111	99.55 148	98.88 269	99.66 167	97.11 383	99.47 236	99.60 236	99.07 106	99.89 194	96.18 369	99.85 170	99.58 181
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CLD-MVS		98.76 261	98.57 266	99.33 248	99.57 215	98.97 256	97.53 400	99.55 236	96.41 393	99.27 288	99.13 353	99.07 106	99.78 327	96.73 339	99.89 136	99.23 297
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PVSNet_Blended_VisFu		99.40 128	99.38 118	99.44 214	99.90 37	98.66 286	98.94 264	99.91 46	97.97 337	99.79 109	99.73 141	99.05 112	99.97 37	99.15 136	99.99 16	99.68 104

sasdasda		99.02 223	99.00 212	99.09 293	99.10 362	98.70 281	99.61 70	99.66 167	99.63 120	98.64 360	97.65 424	99.04 113	99.54 409	98.79 177	98.92 370	99.04 349

canonicalmvs		99.02 223	99.00 212	99.09 293	99.10 362	98.70 281	99.61 70	99.66 167	99.63 120	98.64 360	97.65 424	99.04 113	99.54 409	98.79 177	98.92 370	99.04 349

SteuartSystems-ACMMP		99.30 154	99.14 166	99.76 74	99.87 52	99.66 110	99.18 183	99.60 208	98.55 285	99.57 201	99.67 188	99.03 115	99.94 86	97.01 321	99.80 209	99.69 98
Skip Steuart: Steuart Systems R&D Blog.
reproduce_model		99.50 95	99.40 115	99.83 38	99.60 195	99.83 30	99.12 208	99.68 157	99.49 145	99.80 103	99.79 104	99.01 116	99.93 106	98.24 216	99.82 192	99.73 83

DVP-MVS++		99.38 134	99.25 153	99.77 67	99.03 372	99.77 58	99.74 24	99.61 197	99.18 200	99.76 124	99.61 228	99.00 117	99.92 133	97.72 266	99.60 287	99.62 155

OPU-MVS				99.29 260	99.12 355	99.44 169	99.20 176				99.40 300	99.00 117	98.84 429	96.54 350	99.60 287	99.58 181

test_vis1_n		99.68 56	99.79 30	99.36 242	99.94 18	98.18 321	99.52 89	100.00 1	99.86 56	100.00 1	99.88 47	98.99 119	99.96 59	99.97 4	99.96 77	99.95 14

EI-MVSNet-UG-set		99.48 101	99.50 96	99.42 220	99.57 215	98.65 289	99.24 166	99.46 276	99.68 104	99.80 103	99.66 193	98.99 119	99.89 194	99.19 128	99.90 126	99.72 86

Fast-Effi-MVS+-dtu		99.20 182	99.12 172	99.43 218	99.25 332	99.69 103	99.05 229	99.82 83	99.50 143	98.97 324	99.05 365	98.98 121	99.98 23	98.20 220	99.24 350	98.62 389

FMVSNet1		99.66 63	99.63 66	99.73 98	99.78 111	99.77 58	99.68 46	99.70 147	99.67 108	99.82 92	99.83 76	98.98 121	99.90 175	99.24 120	99.97 64	99.53 205

EI-MVSNet-Vis-set		99.47 109	99.49 98	99.42 220	99.57 215	98.66 286	99.24 166	99.46 276	99.67 108	99.79 109	99.65 198	98.97 123	99.89 194	99.15 136	99.89 136	99.71 89

PHI-MVS		99.11 206	98.95 226	99.59 165	99.13 353	99.59 137	99.17 188	99.65 177	97.88 345	99.25 290	99.46 288	98.97 123	99.80 321	97.26 306	99.82 192	99.37 265

TinyColmap		98.97 235	98.93 228	99.07 298	99.46 272	98.19 319	97.75 389	99.75 120	98.79 259	99.54 216	99.70 166	98.97 123	99.62 396	96.63 347	99.83 183	99.41 256

reproduce-ours		99.46 110	99.35 126	99.82 43	99.56 226	99.83 30	99.05 229	99.65 177	99.45 157	99.78 113	99.78 115	98.93 126	99.93 106	98.11 230	99.81 202	99.70 92

our_new_method		99.46 110	99.35 126	99.82 43	99.56 226	99.83 30	99.05 229	99.65 177	99.45 157	99.78 113	99.78 115	98.93 126	99.93 106	98.11 230	99.81 202	99.70 92

SMA-MVS		99.19 185	99.00 212	99.73 98	99.46 272	99.73 83	99.13 204	99.52 256	97.40 368	99.57 201	99.64 200	98.93 126	99.83 289	97.61 282	99.79 214	99.63 144
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
XVG-ACMP-BASELINE		99.23 167	99.10 183	99.63 147	99.82 74	99.58 141	98.83 279	99.72 139	98.36 306	99.60 193	99.71 158	98.92 129	99.91 156	97.08 319	99.84 175	99.40 258

CSCG		99.37 137	99.29 145	99.60 162	99.71 154	99.46 162	99.43 113	99.85 70	98.79 259	99.41 255	99.60 236	98.92 129	99.92 133	98.02 235	99.92 115	99.43 251

SED-MVS		99.40 128	99.28 147	99.77 67	99.69 166	99.82 38	99.20 176	99.54 242	99.13 213	99.82 92	99.63 212	98.91 131	99.92 133	97.85 255	99.70 251	99.58 181

test_241102_ONE					99.69 166	99.82 38		99.54 242	99.12 216	99.82 92	99.49 278	98.91 131	99.52 414

Gipuma		99.57 81	99.59 76	99.49 198	99.98 3	99.71 91	99.72 30	99.84 76	99.81 75	99.94 44	99.78 115	98.91 131	99.71 354	98.41 203	99.95 91	99.05 347
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepC-MVS_fast	98.47 5	99.23 167	99.12 172	99.56 177	99.28 326	99.22 223	98.99 252	99.40 294	99.08 218	99.58 198	99.64 200	98.90 134	99.83 289	97.44 292	99.75 227	99.63 144
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ITE_SJBPF				99.38 235	99.63 188	99.44 169		99.73 130	98.56 284	99.33 273	99.53 267	98.88 135	99.68 375	96.01 374	99.65 271	99.02 356

SF-MVS		99.10 209	98.93 228	99.62 156	99.58 205	99.51 153	99.13 204	99.65 177	97.97 337	99.42 249	99.61 228	98.86 136	99.87 222	96.45 358	99.68 260	99.49 227

tfpnnormal		99.43 119	99.38 118	99.60 162	99.87 52	99.75 73	99.59 77	99.78 107	99.71 94	99.90 58	99.69 173	98.85 137	99.90 175	97.25 310	99.78 219	99.15 318

ZNCC-MVS		99.22 175	99.04 202	99.77 67	99.76 124	99.73 83	99.28 153	99.56 230	98.19 325	99.14 309	99.29 330	98.84 138	99.92 133	97.53 288	99.80 209	99.64 139

MP-MVS-pluss		99.14 199	98.92 232	99.80 53	99.83 67	99.83 30	98.61 304	99.63 187	96.84 388	99.44 242	99.58 244	98.81 139	99.91 156	97.70 271	99.82 192	99.67 112
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VPA-MVSNet		99.66 63	99.62 67	99.79 60	99.68 174	99.75 73	99.62 64	99.69 154	99.85 62	99.80 103	99.81 90	98.81 139	99.91 156	99.47 83	99.88 145	99.70 92

test20.03		99.55 87	99.54 90	99.58 168	99.79 103	99.37 191	99.02 240	99.89 53	99.60 133	99.82 92	99.62 219	98.81 139	99.89 194	99.43 88	99.86 165	99.47 235

PGM-MVS		99.20 182	99.01 208	99.77 67	99.75 136	99.71 91	99.16 194	99.72 139	97.99 335	99.42 249	99.60 236	98.81 139	99.93 106	96.91 327	99.74 234	99.66 121

HFP-MVS		99.25 163	99.08 186	99.76 74	99.73 148	99.70 99	99.31 141	99.59 214	98.36 306	99.36 265	99.37 309	98.80 143	99.91 156	97.43 293	99.75 227	99.68 104

APDe-MVS		99.48 101	99.36 124	99.85 30	99.55 229	99.81 43	99.50 96	99.69 154	98.99 227	99.75 129	99.71 158	98.79 144	99.93 106	98.46 201	99.85 170	99.80 59
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CP-MVS		99.23 167	99.05 196	99.75 84	99.66 181	99.66 110	99.38 120	99.62 190	98.38 304	99.06 320	99.27 333	98.79 144	99.94 86	97.51 289	99.82 192	99.66 121

MSLP-MVS++		99.05 217	99.09 184	98.91 317	99.21 339	98.36 311	98.82 283	99.47 273	98.85 249	98.90 334	99.56 255	98.78 146	99.09 425	98.57 196	99.68 260	99.26 290

MVS_Test		99.28 156	99.31 135	99.19 279	99.35 301	98.79 275	99.36 127	99.49 269	99.17 205	99.21 299	99.67 188	98.78 146	99.66 385	99.09 146	99.66 269	99.10 329

3Dnovator+	98.92 3	99.35 142	99.24 155	99.67 120	99.35 301	99.47 158	99.62 64	99.50 265	99.44 159	99.12 312	99.78 115	98.77 148	99.94 86	97.87 252	99.72 246	99.62 155

APD-MVS_3200maxsize		99.31 153	99.16 162	99.74 89	99.53 237	99.75 73	99.27 157	99.61 197	99.19 199	99.57 201	99.64 200	98.76 149	99.90 175	97.29 301	99.62 277	99.56 188

TranMVSNet+NR-MVSNet		99.54 90	99.47 99	99.76 74	99.58 205	99.64 119	99.30 144	99.63 187	99.61 127	99.71 148	99.56 255	98.76 149	99.96 59	99.14 142	99.92 115	99.68 104

test_vis1_rt		99.45 114	99.46 103	99.41 227	99.71 154	98.63 292	98.99 252	99.96 28	99.03 224	99.95 41	99.12 357	98.75 151	99.84 274	99.82 46	99.82 192	99.77 73

EIA-MVS		99.12 203	99.01 208	99.45 210	99.36 297	99.62 126	99.34 129	99.79 101	98.41 300	98.84 341	98.89 387	98.75 151	99.84 274	98.15 228	99.51 311	98.89 371

ACMMP_NAP		99.28 156	99.11 175	99.79 60	99.75 136	99.81 43	98.95 262	99.53 251	98.27 320	99.53 221	99.73 141	98.75 151	99.87 222	97.70 271	99.83 183	99.68 104

v10		99.69 53	99.69 54	99.66 127	99.81 84	99.39 186	99.66 54	99.75 120	99.60 133	99.92 52	99.87 53	98.75 151	99.86 241	99.90 33	99.99 16	99.73 83

region2R		99.23 167	99.05 196	99.77 67	99.76 124	99.70 99	99.31 141	99.59 214	98.41 300	99.32 276	99.36 313	98.73 155	99.93 106	97.29 301	99.74 234	99.67 112

test_fmvs1		99.48 101	99.65 62	98.97 307	99.54 231	97.16 367	99.11 213	99.98 12	99.78 82	99.96 31	99.81 90	98.72 156	99.97 37	99.95 13	99.97 64	99.79 67

LS3D		99.24 166	99.11 175	99.61 159	98.38 419	99.79 49	99.57 82	99.68 157	99.61 127	99.15 307	99.71 158	98.70 157	99.91 156	97.54 286	99.68 260	99.13 326

DP-MVS		99.48 101	99.39 116	99.74 89	99.57 215	99.62 126	99.29 151	99.61 197	99.87 53	99.74 137	99.76 127	98.69 158	99.87 222	98.20 220	99.80 209	99.75 81

AllTest		99.21 180	99.07 190	99.63 147	99.78 111	99.64 119	99.12 208	99.83 78	98.63 277	99.63 175	99.72 148	98.68 159	99.75 342	96.38 361	99.83 183	99.51 217

TestCases				99.63 147	99.78 111	99.64 119		99.83 78	98.63 277	99.63 175	99.72 148	98.68 159	99.75 342	96.38 361	99.83 183	99.51 217

LCM-MVSNet-Re		99.28 156	99.15 165	99.67 120	99.33 315	99.76 65	99.34 129	99.97 20	98.93 238	99.91 55	99.79 104	98.68 159	99.93 106	96.80 335	99.56 296	99.30 284

v1144		99.54 90	99.53 94	99.59 165	99.79 103	99.28 209	99.10 216	99.61 197	99.20 198	99.84 86	99.73 141	98.67 162	99.84 274	99.86 41	99.98 46	99.64 139

DTE-MVSNet		99.68 56	99.61 71	99.88 18	99.80 91	99.87 14	99.67 50	99.71 142	99.72 92	99.84 86	99.78 115	98.67 162	99.97 37	99.30 113	99.95 91	99.80 59

v144192		99.55 87	99.54 90	99.58 168	99.78 111	99.20 228	99.11 213	99.62 190	99.18 200	99.89 62	99.72 148	98.66 164	99.87 222	99.88 37	99.97 64	99.66 121

v8		99.68 56	99.69 54	99.65 133	99.80 91	99.40 183	99.66 54	99.76 115	99.64 118	99.93 47	99.85 65	98.66 164	99.84 274	99.88 37	99.99 16	99.71 89

GST-MVS		99.16 195	98.96 225	99.75 84	99.73 148	99.73 83	99.20 176	99.55 236	98.22 322	99.32 276	99.35 318	98.65 166	99.91 156	96.86 330	99.74 234	99.62 155

ppachtmachnet_test		98.89 249	99.12 172	98.20 365	99.66 181	95.24 405	97.63 394	99.68 157	99.08 218	99.78 113	99.62 219	98.65 166	99.88 208	98.02 235	99.96 77	99.48 231

PS-CasMVS		99.66 63	99.58 79	99.89 11	99.80 91	99.85 20	99.66 54	99.73 130	99.62 123	99.84 86	99.71 158	98.62 168	99.96 59	99.30 113	99.96 77	99.86 41

LF4IMVS		99.01 229	98.92 232	99.27 266	99.71 154	99.28 209	98.59 309	99.77 110	98.32 317	99.39 262	99.41 296	98.62 168	99.84 274	96.62 348	99.84 175	98.69 387

ACMMPR		99.23 167	99.06 192	99.76 74	99.74 144	99.69 103	99.31 141	99.59 214	98.36 306	99.35 267	99.38 306	98.61 170	99.93 106	97.43 293	99.75 227	99.67 112

API-MVS		98.38 302	98.39 284	98.35 356	98.83 393	99.26 213	99.14 198	99.18 342	98.59 282	98.66 359	98.78 394	98.61 170	99.57 405	94.14 410	99.56 296	96.21 430

test_one_0601					99.63 188	99.76 65		99.55 236	99.23 193	99.31 281	99.61 228	98.59 172

OMC-MVS		98.90 246	98.72 252	99.44 214	99.39 289	99.42 176	98.58 311	99.64 185	97.31 373	99.44 242	99.62 219	98.59 172	99.69 363	96.17 370	99.79 214	99.22 299

test_0728_THIRD									99.18 200	99.62 184	99.61 228	98.58 174	99.91 156	97.72 266	99.80 209	99.77 73

RE-MVS-def			99.13 168		99.54 231	99.74 80	99.26 159	99.62 190	99.16 207	99.52 223	99.64 200	98.57 175		97.27 304	99.61 284	99.54 200

ACMMP		99.25 163	99.08 186	99.74 89	99.79 103	99.68 106	99.50 96	99.65 177	98.07 331	99.52 223	99.69 173	98.57 175	99.92 133	97.18 315	99.79 214	99.63 144
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 63	99.59 76	99.89 11	99.83 67	99.87 14	99.66 54	99.73 130	99.70 99	99.84 86	99.73 141	98.56 177	99.96 59	99.29 116	99.94 104	99.83 51

V42		99.56 84	99.54 90	99.63 147	99.79 103	99.46 162	99.39 117	99.59 214	99.24 191	99.86 80	99.70 166	98.55 178	99.82 299	99.79 48	99.95 91	99.60 169

QAPM		98.40 301	97.99 317	99.65 133	99.39 289	99.47 158	99.67 50	99.52 256	91.70 424	98.78 350	99.80 94	98.55 178	99.95 70	94.71 404	99.75 227	99.53 205

EI-MVSNet		99.38 134	99.44 108	99.21 276	99.58 205	98.09 329	99.26 159	99.46 276	99.62 123	99.75 129	99.67 188	98.54 180	99.85 259	99.15 136	99.92 115	99.68 104

jason		99.16 195	99.11 175	99.32 253	99.75 136	98.44 303	98.26 346	99.39 297	98.70 271	99.74 137	99.30 327	98.54 180	99.97 37	98.48 200	99.82 192	99.55 191
jason: jason.
OurMVSNet-221017-0		99.75 42	99.71 50	99.84 35	99.96 7	99.83 30	99.83 7	99.85 70	99.80 78	99.93 47	99.93 21	98.54 180	99.93 106	99.59 65	99.98 46	99.76 78

IterMVS-LS		99.41 126	99.47 99	99.25 272	99.81 84	98.09 329	98.85 274	99.76 115	99.62 123	99.83 91	99.64 200	98.54 180	99.97 37	99.15 136	99.99 16	99.68 104
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
9.14			98.64 257		99.45 276		98.81 284	99.60 208	97.52 362	99.28 287	99.56 255	98.53 184	99.83 289	95.36 395	99.64 273

mPP-MVS		99.19 185	99.00 212	99.76 74	99.76 124	99.68 106	99.38 120	99.54 242	98.34 315	99.01 322	99.50 274	98.53 184	99.93 106	97.18 315	99.78 219	99.66 121

CNVR-MVS		98.99 234	98.80 248	99.56 177	99.25 332	99.43 173	98.54 320	99.27 323	98.58 283	98.80 346	99.43 293	98.53 184	99.70 357	97.22 312	99.59 291	99.54 200

PVSNet_BlendedMVS		99.03 221	99.01 208	99.09 293	99.54 231	97.99 335	98.58 311	99.82 83	97.62 356	99.34 271	99.71 158	98.52 187	99.77 335	97.98 240	99.97 64	99.52 215

PVSNet_Blended		98.70 269	98.59 262	99.02 303	99.54 231	97.99 335	97.58 397	99.82 83	95.70 404	99.34 271	98.98 377	98.52 187	99.77 335	97.98 240	99.83 183	99.30 284

MCST-MVS		99.02 223	98.81 246	99.65 133	99.58 205	99.49 155	98.58 311	99.07 351	98.40 302	99.04 321	99.25 338	98.51 189	99.80 321	97.31 300	99.51 311	99.65 129

UGNet		99.38 134	99.34 128	99.49 198	98.90 383	98.90 267	99.70 35	99.35 306	99.86 56	98.57 368	99.81 90	98.50 190	99.93 106	99.38 97	99.98 46	99.66 121
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
XVS		99.27 160	99.11 175	99.75 84	99.71 154	99.71 91	99.37 124	99.61 197	99.29 181	98.76 351	99.47 285	98.47 191	99.88 208	97.62 280	99.73 240	99.67 112

X-MVStestdata		96.09 382	94.87 395	99.75 84	99.71 154	99.71 91	99.37 124	99.61 197	99.29 181	98.76 351	61.30 445	98.47 191	99.88 208	97.62 280	99.73 240	99.67 112

diffmvs		99.34 147	99.32 133	99.39 232	99.67 180	98.77 277	98.57 315	99.81 92	99.61 127	99.48 234	99.41 296	98.47 191	99.86 241	98.97 158	99.90 126	99.53 205
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				99.20 278	99.35 301	98.53 297	99.17 188	99.46 276		99.67 163	99.80 94	98.46 194	99.70 357	97.92 245	99.70 251	99.38 262

FC-MVSNet-test		99.70 51	99.65 62	99.86 28	99.88 44	99.86 18	99.72 30	99.78 107	99.90 40	99.82 92	99.83 76	98.45 195	99.87 222	99.51 78	99.97 64	99.86 41

dcpmvs_2		99.61 78	99.64 65	99.53 187	99.79 103	98.82 271	99.58 79	99.97 20	99.95 28	99.96 31	99.76 127	98.44 196	99.99 8	99.34 105	99.96 77	99.78 69

1314		98.00 327	97.90 329	98.27 364	98.90 383	97.45 359	99.30 144	99.06 353	94.98 412	97.21 414	99.12 357	98.43 197	99.67 380	95.58 390	98.56 393	97.71 422

USDC		98.96 238	98.93 228	99.05 301	99.54 231	97.99 335	97.07 418	99.80 95	98.21 323	99.75 129	99.77 124	98.43 197	99.64 394	97.90 247	99.88 145	99.51 217

KD-MVS_self_test		99.63 70	99.59 76	99.76 74	99.84 63	99.90 7	99.37 124	99.79 101	99.83 70	99.88 71	99.85 65	98.42 199	99.90 175	99.60 64	99.73 240	99.49 227

APD_test1		99.36 140	99.28 147	99.61 159	99.89 39	99.89 10	99.32 136	99.74 126	99.18 200	99.69 155	99.75 133	98.41 200	99.84 274	97.85 255	99.70 251	99.10 329

SR-MVS-dyc-post		99.27 160	99.11 175	99.73 98	99.54 231	99.74 80	99.26 159	99.62 190	99.16 207	99.52 223	99.64 200	98.41 200	99.91 156	97.27 304	99.61 284	99.54 200

v148		99.40 128	99.41 114	99.39 232	99.76 124	98.94 260	99.09 221	99.59 214	99.17 205	99.81 99	99.61 228	98.41 200	99.69 363	99.32 110	99.94 104	99.53 205

Test By Simon												98.41 200

PM-MVS		99.36 140	99.29 145	99.58 168	99.83 67	99.66 110	98.95 262	99.86 64	98.85 249	99.81 99	99.73 141	98.40 204	99.92 133	98.36 206	99.83 183	99.17 314

SR-MVS		99.19 185	99.00 212	99.74 89	99.51 246	99.72 88	99.18 183	99.60 208	98.85 249	99.47 236	99.58 244	98.38 205	99.92 133	96.92 326	99.54 305	99.57 186

segment_acmp												98.37 206

MP-MVS		99.06 214	98.83 244	99.76 74	99.76 124	99.71 91	99.32 136	99.50 265	98.35 311	98.97 324	99.48 281	98.37 206	99.92 133	95.95 380	99.75 227	99.63 144
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DVP-MVS		99.32 152	99.17 161	99.77 67	99.69 166	99.80 47	99.14 198	99.31 315	99.16 207	99.62 184	99.61 228	98.35 208	99.91 156	97.88 249	99.72 246	99.61 165
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					99.69 166	99.80 47	99.24 166	99.57 225	99.16 207	99.73 141	99.65 198	98.35 208

MVS		95.72 392	94.63 398	98.99 305	98.56 413	97.98 340	99.30 144	98.86 360	72.71 434	97.30 411	99.08 362	98.34 210	99.74 345	89.21 423	98.33 400	99.26 290

CDPH-MVS		98.56 283	98.20 302	99.61 159	99.50 252	99.46 162	98.32 341	99.41 287	95.22 409	99.21 299	99.10 361	98.34 210	99.82 299	95.09 400	99.66 269	99.56 188

testdata				99.42 220	99.51 246	98.93 263		99.30 318	96.20 397	98.87 338	99.40 300	98.33 212	99.89 194	96.29 364	99.28 343	99.44 245

test_241102_TWO								99.54 242	99.13 213	99.76 124	99.63 212	98.32 213	99.92 133	97.85 255	99.69 255	99.75 81

APD-MVS		98.87 251	98.59 262	99.71 109	99.50 252	99.62 126	99.01 243	99.57 225	96.80 390	99.54 216	99.63 212	98.29 214	99.91 156	95.24 396	99.71 249	99.61 165
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVSMamba_PlusPlus		99.55 87	99.58 79	99.47 204	99.68 174	99.40 183	99.52 89	99.70 147	99.92 36	99.77 121	99.86 60	98.28 215	99.96 59	99.54 73	99.90 126	99.05 347

OpenMVS	98.12 10	98.23 314	97.89 330	99.26 269	99.19 344	99.26 213	99.65 59	99.69 154	91.33 425	98.14 389	99.77 124	98.28 215	99.96 59	95.41 393	99.55 300	98.58 394

FIs		99.65 68	99.58 79	99.84 35	99.84 63	99.85 20	99.66 54	99.75 120	99.86 56	99.74 137	99.79 104	98.27 217	99.85 259	99.37 100	99.93 111	99.83 51

TAPA-MVS	97.92 13	98.03 325	97.55 341	99.46 207	99.47 268	99.44 169	98.50 325	99.62 190	86.79 428	99.07 319	99.26 336	98.26 218	99.62 396	97.28 303	99.73 240	99.31 282
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
patch_mono-2		99.51 94	99.46 103	99.64 140	99.70 162	99.11 238	99.04 234	99.87 59	99.71 94	99.47 236	99.79 104	98.24 219	99.98 23	99.38 97	99.96 77	99.83 51

v2v482		99.50 95	99.47 99	99.58 168	99.78 111	99.25 216	99.14 198	99.58 223	99.25 189	99.81 99	99.62 219	98.24 219	99.84 274	99.83 42	99.97 64	99.64 139

pmmvs4		99.13 201	99.06 192	99.36 242	99.57 215	99.10 243	98.01 370	99.25 328	98.78 261	99.58 198	99.44 292	98.24 219	99.76 338	98.74 184	99.93 111	99.22 299

mvs_anonymous		99.28 156	99.39 116	98.94 311	99.19 344	97.81 346	99.02 240	99.55 236	99.78 82	99.85 83	99.80 94	98.24 219	99.86 241	99.57 69	99.50 314	99.15 318

DPE-MVS		99.14 199	98.92 232	99.82 43	99.57 215	99.77 58	98.74 295	99.60 208	98.55 285	99.76 124	99.69 173	98.23 223	99.92 133	96.39 360	99.75 227	99.76 78
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MTAPA		99.35 142	99.20 158	99.80 53	99.81 84	99.81 43	99.33 133	99.53 251	99.27 185	99.42 249	99.63 212	98.21 224	99.95 70	97.83 259	99.79 214	99.65 129

MS-PatchMatch		99.00 231	98.97 223	99.09 293	99.11 360	98.19 319	98.76 293	99.33 309	98.49 294	99.44 242	99.58 244	98.21 224	99.69 363	98.20 220	99.62 277	99.39 260

balanced_conf03		99.50 95	99.50 96	99.50 194	99.42 285	99.49 155	99.52 89	99.75 120	99.86 56	99.78 113	99.71 158	98.20 226	99.90 175	99.39 96	99.88 145	99.10 329

our_test_3		98.85 253	99.09 184	98.13 367	99.66 181	94.90 409	97.72 390	99.58 223	99.07 220	99.64 171	99.62 219	98.19 227	99.93 106	98.41 203	99.95 91	99.55 191

MVP-Stereo		99.16 195	99.08 186	99.43 218	99.48 262	99.07 246	99.08 224	99.55 236	98.63 277	99.31 281	99.68 184	98.19 227	99.78 327	98.18 224	99.58 293	99.45 240
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WR-MVS_H		99.61 78	99.53 94	99.87 24	99.80 91	99.83 30	99.67 50	99.75 120	99.58 136	99.85 83	99.69 173	98.18 229	99.94 86	99.28 118	99.95 91	99.83 51

new_pmnet		98.88 250	98.89 236	98.84 328	99.70 162	97.62 353	98.15 353	99.50 265	97.98 336	99.62 184	99.54 265	98.15 230	99.94 86	97.55 285	99.84 175	98.95 362

D2MVS		99.22 175	99.19 159	99.29 260	99.69 166	98.74 279	98.81 284	99.41 287	98.55 285	99.68 158	99.69 173	98.13 231	99.87 222	98.82 173	99.98 46	99.24 293

Anonymous20240529		99.42 122	99.34 128	99.65 133	99.53 237	99.60 135	99.63 61	99.39 297	99.47 151	99.76 124	99.78 115	98.13 231	99.86 241	98.70 187	99.68 260	99.49 227

EU-MVSNet		99.39 132	99.62 67	98.72 338	99.88 44	96.44 382	99.56 84	99.85 70	99.90 40	99.90 58	99.85 65	98.09 233	99.83 289	99.58 68	99.95 91	99.90 27

PMVS	92.94 21	98.82 255	98.81 246	98.85 326	99.84 63	97.99 335	99.20 176	99.47 273	99.71 94	99.42 249	99.82 83	98.09 233	99.47 417	93.88 415	99.85 170	99.07 345
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
HPM-MVS++		98.96 238	98.70 255	99.74 89	99.52 244	99.71 91	98.86 272	99.19 341	98.47 296	98.59 365	99.06 364	98.08 235	99.91 156	96.94 325	99.60 287	99.60 169

ab-mvs		99.33 150	99.28 147	99.47 204	99.57 215	99.39 186	99.78 14	99.43 284	98.87 246	99.57 201	99.82 83	98.06 236	99.87 222	98.69 189	99.73 240	99.15 318

N_pmnet		98.73 265	98.53 272	99.35 244	99.72 151	98.67 283	98.34 339	94.65 426	98.35 311	99.79 109	99.68 184	98.03 237	99.93 106	98.28 212	99.92 115	99.44 245

TEST9					99.35 301	99.35 198	98.11 359	99.41 287	94.83 416	97.92 396	98.99 374	98.02 238	99.85 259

train_agg		98.35 306	97.95 321	99.57 174	99.35 301	99.35 198	98.11 359	99.41 287	94.90 413	97.92 396	98.99 374	98.02 238	99.85 259	95.38 394	99.44 321	99.50 222

test_8					99.34 310	99.31 204	98.08 363	99.40 294	94.90 413	97.87 400	98.97 379	98.02 238	99.84 274

MVSFormer		99.41 126	99.44 108	99.31 256	99.57 215	98.40 306	99.77 16	99.80 95	99.73 88	99.63 175	99.30 327	98.02 238	99.98 23	99.43 88	99.69 255	99.55 191

lupinMVS		98.96 238	98.87 238	99.24 274	99.57 215	98.40 306	98.12 357	99.18 342	98.28 319	99.63 175	99.13 353	98.02 238	99.97 37	98.22 218	99.69 255	99.35 271

Anonymous20231211		99.62 76	99.57 83	99.76 74	99.61 193	99.60 135	99.81 10	99.73 130	99.82 72	99.90 58	99.90 33	97.97 243	99.86 241	99.42 93	99.96 77	99.80 59

MIMVSNet1		99.66 63	99.62 67	99.80 53	99.94 18	99.87 14	99.69 42	99.77 110	99.78 82	99.93 47	99.89 38	97.94 244	99.92 133	99.65 60	99.98 46	99.62 155

原ACMM1				99.37 238	99.47 268	98.87 270		99.27 323	96.74 391	98.26 380	99.32 322	97.93 245	99.82 299	95.96 379	99.38 329	99.43 251

test_prior2							97.95 378		97.87 346	98.05 391	99.05 365	97.90 246		95.99 377	99.49 316

RPSCF		99.18 189	99.02 205	99.64 140	99.83 67	99.85 20	99.44 111	99.82 83	98.33 316	99.50 231	99.78 115	97.90 246	99.65 392	96.78 336	99.83 183	99.44 245

PMMVS		98.49 292	98.29 297	99.11 290	98.96 380	98.42 305	97.54 398	99.32 311	97.53 361	98.47 374	98.15 416	97.88 248	99.82 299	97.46 291	99.24 350	99.09 334

ZD-MVS					99.43 280	99.61 132		99.43 284	96.38 394	99.11 313	99.07 363	97.86 249	99.92 133	94.04 412	99.49 316

NCCC		98.82 255	98.57 266	99.58 168	99.21 339	99.31 204	98.61 304	99.25 328	98.65 275	98.43 376	99.26 336	97.86 249	99.81 314	96.55 349	99.27 346	99.61 165

UniMVSNet_NR-MVSNet		99.37 137	99.25 153	99.72 104	99.47 268	99.56 144	98.97 257	99.61 197	99.43 165	99.67 163	99.28 331	97.85 251	99.95 70	99.17 133	99.81 202	99.65 129

TAMVS		99.49 99	99.45 105	99.63 147	99.48 262	99.42 176	99.45 109	99.57 225	99.66 112	99.78 113	99.83 76	97.85 251	99.86 241	99.44 87	99.96 77	99.61 165

DP-MVS Recon		98.50 290	98.23 299	99.31 256	99.49 257	99.46 162	98.56 316	99.63 187	94.86 415	98.85 340	99.37 309	97.81 253	99.59 403	96.08 371	99.44 321	98.88 372

PatchMatch-RL		98.68 271	98.47 275	99.30 259	99.44 277	99.28 209	98.14 355	99.54 242	97.12 382	99.11 313	99.25 338	97.80 254	99.70 357	96.51 352	99.30 340	98.93 365

CP-MVSNet		99.54 90	99.43 110	99.87 24	99.76 124	99.82 38	99.57 82	99.61 197	99.54 137	99.80 103	99.64 200	97.79 255	99.95 70	99.21 124	99.94 104	99.84 47

WB-MVSnew		98.34 308	98.14 308	98.96 308	98.14 428	97.90 343	98.27 344	97.26 415	98.63 277	98.80 346	98.00 419	97.77 256	99.90 175	97.37 297	98.98 366	99.09 334

DPM-MVS		98.28 309	97.94 325	99.32 253	99.36 297	99.11 238	97.31 410	98.78 366	96.88 386	98.84 341	99.11 360	97.77 256	99.61 401	94.03 413	99.36 332	99.23 297

114514_t		98.49 292	98.11 310	99.64 140	99.73 148	99.58 141	99.24 166	99.76 115	89.94 427	99.42 249	99.56 255	97.76 258	99.86 241	97.74 265	99.82 192	99.47 235

tmp_tt		95.75 391	95.42 386	96.76 401	89.90 441	94.42 411	98.86 272	97.87 405	78.01 432	99.30 286	99.69 173	97.70 259	95.89 434	99.29 116	98.14 410	99.95 14

UniMVSNet (Re)		99.37 137	99.26 151	99.68 117	99.51 246	99.58 141	98.98 255	99.60 208	99.43 165	99.70 152	99.36 313	97.70 259	99.88 208	99.20 127	99.87 157	99.59 176

Effi-MVS+-dtu		99.07 213	98.92 232	99.52 189	98.89 386	99.78 52	99.15 196	99.66 167	99.34 176	98.92 331	99.24 343	97.69 261	99.98 23	98.11 230	99.28 343	98.81 378

F-COLMAP		98.74 263	98.45 278	99.62 156	99.57 215	99.47 158	98.84 276	99.65 177	96.31 396	98.93 328	99.19 350	97.68 262	99.87 222	96.52 351	99.37 331	99.53 205

新几何1				99.52 189	99.50 252	99.22 223		99.26 325	95.66 405	98.60 364	99.28 331	97.67 263	99.89 194	95.95 380	99.32 338	99.45 240

旧先验1					99.49 257	99.29 207		99.26 325			99.39 304	97.67 263			99.36 332	99.46 239

DU-MVS		99.33 150	99.21 157	99.71 109	99.43 280	99.56 144	98.83 279	99.53 251	99.38 171	99.67 163	99.36 313	97.67 263	99.95 70	99.17 133	99.81 202	99.63 144

Baseline_NR-MVSNet		99.49 99	99.37 121	99.82 43	99.91 31	99.84 25	98.83 279	99.86 64	99.68 104	99.65 170	99.88 47	97.67 263	99.87 222	99.03 151	99.86 165	99.76 78

CANet		99.11 206	99.05 196	99.28 263	98.83 393	98.56 296	98.71 299	99.41 287	99.25 189	99.23 294	99.22 345	97.66 267	99.94 86	99.19 128	99.97 64	99.33 275

VPNet		99.46 110	99.37 121	99.71 109	99.82 74	99.59 137	99.48 102	99.70 147	99.81 75	99.69 155	99.58 244	97.66 267	99.86 241	99.17 133	99.44 321	99.67 112

Anonymous20231206		99.35 142	99.31 135	99.47 204	99.74 144	99.06 248	99.28 153	99.74 126	99.23 193	99.72 143	99.53 267	97.63 269	99.88 208	99.11 144	99.84 175	99.48 231

test12				99.54 186	99.29 323	99.33 201		99.16 345		98.43 376		97.54 270	99.82 299		99.47 318	99.48 231

NR-MVSNet		99.40 128	99.31 135	99.68 117	99.43 280	99.55 148	99.73 27	99.50 265	99.46 154	99.88 71	99.36 313	97.54 270	99.87 222	98.97 158	99.87 157	99.63 144

MAR-MVS		98.24 313	97.92 327	99.19 279	98.78 401	99.65 116	99.17 188	99.14 347	95.36 407	98.04 392	98.81 393	97.47 272	99.72 350	95.47 392	99.06 359	98.21 413
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		99.39 132	99.30 140	99.65 133	99.88 44	99.25 216	98.78 291	99.88 57	98.66 274	99.96 31	99.79 104	97.45 273	99.93 106	99.34 105	99.99 16	99.78 69

PAPR		97.56 343	97.07 353	99.04 302	98.80 397	98.11 327	97.63 394	99.25 328	94.56 418	98.02 394	98.25 413	97.43 274	99.68 375	90.90 422	98.74 383	99.33 275

YYNet1		98.95 241	98.99 219	98.84 328	99.64 186	97.14 369	98.22 349	99.32 311	98.92 240	99.59 196	99.66 193	97.40 275	99.83 289	98.27 213	99.90 126	99.55 191

PVSNet	97.47 15	98.42 298	98.44 279	98.35 356	99.46 272	96.26 387	96.70 423	99.34 308	97.68 354	99.00 323	99.13 353	97.40 275	99.72 350	97.59 284	99.68 260	99.08 340

MDA-MVSNet_test_wron		98.95 241	98.99 219	98.85 326	99.64 186	97.16 367	98.23 348	99.33 309	98.93 238	99.56 209	99.66 193	97.39 277	99.83 289	98.29 211	99.88 145	99.55 191

MG-MVS		98.52 287	98.39 284	98.94 311	99.15 350	97.39 362	98.18 350	99.21 338	98.89 245	99.23 294	99.63 212	97.37 278	99.74 345	94.22 409	99.61 284	99.69 98

OpenMVS_ROB	97.31 17	97.36 351	96.84 361	98.89 324	99.29 323	99.45 167	98.87 271	99.48 270	86.54 430	99.44 242	99.74 137	97.34 279	99.86 241	91.61 419	99.28 343	97.37 426

AdaColmap		98.60 277	98.35 289	99.38 235	99.12 355	99.22 223	98.67 300	99.42 286	97.84 349	98.81 344	99.27 333	97.32 280	99.81 314	95.14 398	99.53 307	99.10 329

test222					99.51 246	99.08 245	97.83 387	99.29 319	95.21 410	98.68 358	99.31 325	97.28 281			99.38 329	99.43 251

HQP_MVS		98.90 246	98.68 256	99.55 181	99.58 205	99.24 220	98.80 287	99.54 242	98.94 235	99.14 309	99.25 338	97.24 282	99.82 299	95.84 384	99.78 219	99.60 169

plane_prior6					99.47 268	99.26 213						97.24 282

GBi-Net		99.42 122	99.31 135	99.73 98	99.49 257	99.77 58	99.68 46	99.70 147	99.44 159	99.62 184	99.83 76	97.21 284	99.90 175	98.96 160	99.90 126	99.53 205

test1		99.42 122	99.31 135	99.73 98	99.49 257	99.77 58	99.68 46	99.70 147	99.44 159	99.62 184	99.83 76	97.21 284	99.90 175	98.96 160	99.90 126	99.53 205

FMVSNet2		99.35 142	99.28 147	99.55 181	99.49 257	99.35 198	99.45 109	99.57 225	99.44 159	99.70 152	99.74 137	97.21 284	99.87 222	99.03 151	99.94 104	99.44 245

BH-RMVSNet		98.41 299	98.14 308	99.21 276	99.21 339	98.47 300	98.60 306	98.26 394	98.35 311	98.93 328	99.31 325	97.20 287	99.66 385	94.32 407	99.10 357	99.51 217

MVS-HIRNet		97.86 329	98.22 300	96.76 401	99.28 326	91.53 428	98.38 337	92.60 433	99.13 213	99.31 281	99.96 15	97.18 288	99.68 375	98.34 208	99.83 183	99.07 345

PAPM_NR		98.36 303	98.04 314	99.33 248	99.48 262	98.93 263	98.79 290	99.28 322	97.54 360	98.56 370	98.57 403	97.12 289	99.69 363	94.09 411	98.90 374	99.38 262

dmvs_testset		97.27 352	96.83 362	98.59 345	99.46 272	97.55 355	99.25 165	96.84 417	98.78 261	97.24 413	97.67 423	97.11 290	98.97 427	86.59 433	98.54 394	99.27 288

CPTT-MVS		98.74 263	98.44 279	99.64 140	99.61 193	99.38 188	99.18 183	99.55 236	96.49 392	99.27 288	99.37 309	97.11 290	99.92 133	95.74 387	99.67 266	99.62 155

CNLPA		98.57 282	98.34 290	99.28 263	99.18 347	99.10 243	98.34 339	99.41 287	98.48 295	98.52 371	98.98 377	97.05 292	99.78 327	95.59 389	99.50 314	98.96 360

BH-untuned		98.22 316	98.09 311	98.58 347	99.38 292	97.24 365	98.55 317	98.98 358	97.81 350	99.20 304	98.76 395	97.01 293	99.65 392	94.83 401	98.33 400	98.86 374

VDD-MVS		99.20 182	99.11 175	99.44 214	99.43 280	98.98 253	99.50 96	98.32 393	99.80 78	99.56 209	99.69 173	96.99 294	99.85 259	98.99 154	99.73 240	99.50 222

PLC	97.35 16	98.36 303	97.99 317	99.48 202	99.32 316	99.24 220	98.50 325	99.51 261	95.19 411	98.58 366	98.96 381	96.95 295	99.83 289	95.63 388	99.25 348	99.37 265
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
WR-MVS		99.11 206	98.93 228	99.66 127	99.30 321	99.42 176	98.42 335	99.37 302	99.04 223	99.57 201	99.20 349	96.89 296	99.86 241	98.66 191	99.87 157	99.70 92

CL-MVSNet_self_test		98.71 268	98.56 270	99.15 284	99.22 337	98.66 286	97.14 415	99.51 261	98.09 330	99.54 216	99.27 333	96.87 297	99.74 345	98.43 202	98.96 367	99.03 351

MSP-MVS		99.04 220	98.79 249	99.81 48	99.78 111	99.73 83	99.35 128	99.57 225	98.54 288	99.54 216	98.99 374	96.81 298	99.93 106	96.97 324	99.53 307	99.77 73
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 93	99.42 112	99.83 38	99.86 55	99.65 116	99.52 89	99.81 92	99.87 53	99.81 99	99.79 104	96.78 299	99.99 8	99.83 42	99.51 311	99.86 41

dmvs_re		98.69 270	98.48 274	99.31 256	99.55 229	99.42 176	99.54 87	98.38 390	99.32 179	98.72 354	98.71 397	96.76 300	99.21 423	96.01 374	99.35 334	99.31 282

HQP2-MVS												96.67 301

HQP-MVS		98.36 303	98.02 316	99.39 232	99.31 317	98.94 260	97.98 374	99.37 302	97.45 365	98.15 385	98.83 390	96.67 301	99.70 357	94.73 402	99.67 266	99.53 205

WB-MVS		99.44 116	99.32 133	99.80 53	99.81 84	99.61 132	99.47 105	99.81 92	99.82 72	99.71 148	99.72 148	96.60 303	99.98 23	99.75 51	99.23 352	99.82 58

CANet_DTU		98.91 244	98.85 240	99.09 293	98.79 399	98.13 324	98.18 350	99.31 315	99.48 146	98.86 339	99.51 271	96.56 304	99.95 70	99.05 150	99.95 91	99.19 309

pmmvs5		99.19 185	99.11 175	99.42 220	99.76 124	98.88 268	98.55 317	99.73 130	98.82 254	99.72 143	99.62 219	96.56 304	99.82 299	99.32 110	99.95 91	99.56 188

MVE	92.54 22	96.66 366	96.11 371	98.31 361	99.68 174	97.55 355	97.94 379	95.60 424	99.37 172	90.68 435	98.70 399	96.56 304	98.61 431	86.94 432	99.55 300	98.77 383
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VNet		99.18 189	99.06 192	99.56 177	99.24 334	99.36 195	99.33 133	99.31 315	99.67 108	99.47 236	99.57 251	96.48 307	99.84 274	99.15 136	99.30 340	99.47 235

MDA-MVSNet-bldmvs		99.06 214	99.05 196	99.07 298	99.80 91	97.83 345	98.89 268	99.72 139	99.29 181	99.63 175	99.70 166	96.47 308	99.89 194	98.17 226	99.82 192	99.50 222

DeepMVS_CX				97.98 371	99.69 166	96.95 372		99.26 325	75.51 433	95.74 429	98.28 412	96.47 308	99.62 396	91.23 421	97.89 416	97.38 425

1112_ss		99.05 217	98.84 242	99.67 120	99.66 181	99.29 207	98.52 323	99.82 83	97.65 355	99.43 246	99.16 351	96.42 310	99.91 156	99.07 149	99.84 175	99.80 59

TR-MVS		97.44 347	97.15 352	98.32 359	98.53 414	97.46 358	98.47 329	97.91 403	96.85 387	98.21 384	98.51 407	96.42 310	99.51 415	92.16 418	97.29 422	97.98 419

miper_ehance_all_eth		98.59 280	98.59 262	98.59 345	98.98 378	97.07 370	97.49 403	99.52 256	98.50 292	99.52 223	99.37 309	96.41 312	99.71 354	97.86 253	99.62 277	99.00 358

Anonymous20240521		99.44 116	99.42 112	99.49 198	99.89 39	98.96 258	99.62 64	99.76 115	99.85 62	99.82 92	99.88 47	96.39 313	99.97 37	99.59 65	99.98 46	99.55 191

c3_l		98.72 266	98.71 253	98.72 338	99.12 355	97.22 366	97.68 393	99.56 230	98.90 242	99.54 216	99.48 281	96.37 314	99.73 348	97.88 249	99.88 145	99.21 302

mvsmamba		99.08 210	98.95 226	99.45 210	99.36 297	99.18 231	99.39 117	98.81 364	99.37 172	99.35 267	99.70 166	96.36 315	99.94 86	98.66 191	99.59 291	99.22 299

sss		98.90 246	98.77 250	99.27 266	99.48 262	98.44 303	98.72 297	99.32 311	97.94 341	99.37 264	99.35 318	96.31 316	99.91 156	98.85 169	99.63 276	99.47 235

CDS-MVSNet		99.22 175	99.13 168	99.50 194	99.35 301	99.11 238	98.96 260	99.54 242	99.46 154	99.61 190	99.70 166	96.31 316	99.83 289	99.34 105	99.88 145	99.55 191
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MM		99.18 189	99.05 196	99.55 181	99.35 301	98.81 272	99.05 229	97.79 407	99.99 3	99.48 234	99.59 241	96.29 318	99.95 70	99.94 18	99.98 46	99.88 35

eth_miper_zixun_eth		98.68 271	98.71 253	98.60 344	99.10 362	96.84 376	97.52 402	99.54 242	98.94 235	99.58 198	99.48 281	96.25 319	99.76 338	98.01 238	99.93 111	99.21 302

SixPastTwentyTwo		99.42 122	99.30 140	99.76 74	99.92 29	99.67 108	99.70 35	99.14 347	99.65 115	99.89 62	99.90 33	96.20 320	99.94 86	99.42 93	99.92 115	99.67 112

Test_1112_low_res		98.95 241	98.73 251	99.63 147	99.68 174	99.15 234	98.09 361	99.80 95	97.14 381	99.46 240	99.40 300	96.11 321	99.89 194	99.01 153	99.84 175	99.84 47

IterMVS		98.97 235	99.16 162	98.42 353	99.74 144	95.64 398	98.06 366	99.83 78	99.83 70	99.85 83	99.74 137	96.10 322	99.99 8	99.27 119	100.00 1	99.63 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		99.00 231	99.16 162	98.51 348	99.75 136	95.90 394	98.07 364	99.84 76	99.84 65	99.89 62	99.73 141	96.01 323	99.99 8	99.33 108	100.00 1	99.63 144

SCA		98.11 321	98.36 287	97.36 391	99.20 342	92.99 419	98.17 352	98.49 383	98.24 321	99.10 315	99.57 251	96.01 323	99.94 86	96.86 330	99.62 277	99.14 323

PVSNet_0	95.53 19	95.85 390	95.31 391	97.47 388	98.78 401	93.48 418	95.72 427	99.40 294	96.18 398	97.37 409	97.73 422	95.73 325	99.58 404	95.49 391	81.40 435	99.36 268

CMPMVS	77.52 23	98.50 290	98.19 305	99.41 227	98.33 421	99.56 144	99.01 243	99.59 214	95.44 406	99.57 201	99.80 94	95.64 326	99.46 419	96.47 356	99.92 115	99.21 302
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
BH-w/o		97.20 353	97.01 355	97.76 380	99.08 366	95.69 397	98.03 369	98.52 380	95.76 403	97.96 395	98.02 417	95.62 327	99.47 417	92.82 417	97.25 423	98.12 417

cascas		96.99 357	96.82 363	97.48 387	97.57 435	95.64 398	96.43 425	99.56 230	91.75 423	97.13 417	97.61 427	95.58 328	98.63 430	96.68 341	99.11 356	98.18 416

MVS_0304		98.61 274	98.30 295	99.52 189	97.88 431	98.95 259	98.76 293	94.11 430	99.84 65	99.32 276	99.57 251	95.57 329	99.95 70	99.68 57	99.98 46	99.68 104

MonoMVSNet		98.23 314	98.32 292	97.99 370	98.97 379	96.62 379	99.49 100	98.42 386	99.62 123	99.40 260	99.79 104	95.51 330	98.58 432	97.68 279	95.98 430	98.76 384

Syy-MVS		98.17 319	97.85 331	99.15 284	98.50 416	98.79 275	98.60 306	99.21 338	97.89 343	96.76 419	96.37 442	95.47 331	99.57 405	99.10 145	98.73 386	99.09 334

UnsupCasMVSNet_bld		98.55 284	98.27 298	99.40 229	99.56 226	99.37 191	97.97 377	99.68 157	97.49 364	99.08 316	99.35 318	95.41 332	99.82 299	97.70 271	98.19 407	99.01 357

RRT-MVS		99.08 210	99.00 212	99.33 248	99.27 328	98.65 289	99.62 64	99.93 38	99.66 112	99.67 163	99.82 83	95.27 333	99.93 106	98.64 193	99.09 358	99.41 256

UnsupCasMVSNet_eth		98.83 254	98.57 266	99.59 165	99.68 174	99.45 167	98.99 252	99.67 162	99.48 146	99.55 214	99.36 313	94.92 334	99.86 241	98.95 164	96.57 426	99.45 240

EPP-MVSNet		99.17 194	99.00 212	99.66 127	99.80 91	99.43 173	99.70 35	99.24 331	99.48 146	99.56 209	99.77 124	94.89 335	99.93 106	98.72 186	99.89 136	99.63 144

WTY-MVS		98.59 280	98.37 286	99.26 269	99.43 280	98.40 306	98.74 295	99.13 349	98.10 328	99.21 299	99.24 343	94.82 336	99.90 175	97.86 253	98.77 379	99.49 227

miper_enhance_ethall		98.03 325	97.94 325	98.32 359	98.27 422	96.43 383	96.95 419	99.41 287	96.37 395	99.43 246	98.96 381	94.74 337	99.69 363	97.71 268	99.62 277	98.83 377

IS-MVSNet		99.03 221	98.85 240	99.55 181	99.80 91	99.25 216	99.73 27	99.15 346	99.37 172	99.61 190	99.71 158	94.73 338	99.81 314	97.70 271	99.88 145	99.58 181

miper_lstm_enhance		98.65 273	98.60 260	98.82 333	99.20 342	97.33 363	97.78 388	99.66 167	99.01 226	99.59 196	99.50 274	94.62 339	99.85 259	98.12 229	99.90 126	99.26 290

lessismore_v0				99.64 140	99.86 55	99.38 188		90.66 435		99.89 62	99.83 76	94.56 340	99.97 37	99.56 70	99.92 115	99.57 186

PCF-MVS	96.03 18	96.73 364	95.86 377	99.33 248	99.44 277	99.16 232	96.87 421	99.44 281	86.58 429	98.95 326	99.40 300	94.38 341	99.88 208	87.93 427	99.80 209	98.95 362
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VDDNet		98.97 235	98.82 245	99.42 220	99.71 154	98.81 272	99.62 64	98.68 370	99.81 75	99.38 263	99.80 94	94.25 342	99.85 259	98.79 177	99.32 338	99.59 176

HY-MVS	98.23 9	98.21 318	97.95 321	98.99 305	99.03 372	98.24 314	99.61 70	98.72 368	96.81 389	98.73 353	99.51 271	94.06 343	99.86 241	96.91 327	98.20 405	98.86 374

test_method		91.72 399	92.32 402	89.91 417	93.49 440	70.18 443	90.28 431	99.56 230	61.71 435	95.39 430	99.52 269	93.90 344	99.94 86	98.76 182	98.27 403	99.62 155

DIV-MVS_self_test		98.54 285	98.42 281	98.92 315	99.03 372	97.80 348	97.46 404	99.59 214	98.90 242	99.60 193	99.46 288	93.87 345	99.78 327	97.97 242	99.89 136	99.18 311

cl____		98.54 285	98.41 282	98.92 315	99.03 372	97.80 348	97.46 404	99.59 214	98.90 242	99.60 193	99.46 288	93.85 346	99.78 327	97.97 242	99.89 136	99.17 314

EMVS		96.96 359	97.28 347	95.99 413	98.76 404	91.03 431	95.26 430	98.61 375	99.34 176	98.92 331	98.88 388	93.79 347	99.66 385	92.87 416	99.05 361	97.30 427

EPNet_dtu		97.62 340	97.79 334	97.11 399	96.67 436	92.31 422	98.51 324	98.04 399	99.24 191	95.77 428	99.47 285	93.78 348	99.66 385	98.98 156	99.62 277	99.37 265
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test1111		97.74 334	98.16 307	96.49 407	99.60 195	89.86 438	99.71 34	91.21 434	99.89 46	99.88 71	99.87 53	93.73 349	99.90 175	99.56 70	99.99 16	99.70 92

K. test v3		98.87 251	98.60 260	99.69 115	99.93 24	99.46 162	99.74 24	94.97 425	99.78 82	99.88 71	99.88 47	93.66 350	99.97 37	99.61 63	99.95 91	99.64 139

ECVR-MVS		97.73 335	98.04 314	96.78 400	99.59 200	90.81 433	99.72 30	90.43 436	99.89 46	99.86 80	99.86 60	93.60 351	99.89 194	99.46 84	99.99 16	99.65 129

CHOSEN 280x420		98.41 299	98.41 282	98.40 354	99.34 310	95.89 395	96.94 420	99.44 281	98.80 258	99.25 290	99.52 269	93.51 352	99.98 23	98.94 165	99.98 46	99.32 278

CVMVSNet		98.61 274	98.88 237	97.80 379	99.58 205	93.60 417	99.26 159	99.64 185	99.66 112	99.72 143	99.67 188	93.26 353	99.93 106	99.30 113	99.81 202	99.87 39

Anonymous202405211		98.75 262	98.46 276	99.63 147	99.34 310	99.66 110	99.47 105	97.65 408	99.28 184	99.56 209	99.50 274	93.15 354	99.84 274	98.62 194	99.58 293	99.40 258

EPNet		98.13 320	97.77 335	99.18 281	94.57 439	97.99 335	99.24 166	97.96 401	99.74 87	97.29 412	99.62 219	93.13 355	99.97 37	98.59 195	99.83 183	99.58 181
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FA-MVS(test-final)		98.52 287	98.32 292	99.10 292	99.48 262	98.67 283	99.77 16	98.60 377	97.35 371	99.63 175	99.80 94	93.07 356	99.84 274	97.92 245	99.30 340	98.78 381

PAPM		95.61 395	94.71 397	98.31 361	99.12 355	96.63 378	96.66 424	98.46 384	90.77 426	96.25 425	98.68 400	93.01 357	99.69 363	81.60 434	97.86 418	98.62 389

Vis-MVSNet (Re-imp)		98.77 260	98.58 265	99.34 245	99.78 111	98.88 268	99.61 70	99.56 230	99.11 217	99.24 293	99.56 255	93.00 358	99.78 327	97.43 293	99.89 136	99.35 271

E-PMN		97.14 356	97.43 343	96.27 409	98.79 399	91.62 427	95.54 428	99.01 357	99.44 159	98.88 335	99.12 357	92.78 359	99.68 375	94.30 408	99.03 363	97.50 423

FMVSNet3		98.80 258	98.63 259	99.32 253	99.13 353	98.72 280	99.10 216	99.48 270	99.23 193	99.62 184	99.64 200	92.57 360	99.86 241	98.96 160	99.90 126	99.39 260

HyFIR lowres test		98.91 244	98.64 257	99.73 98	99.85 59	99.47 158	98.07 364	99.83 78	98.64 276	99.89 62	99.60 236	92.57 360	100.00 1	99.33 108	99.97 64	99.72 86

RPMNet		98.60 277	98.53 272	98.83 330	99.05 368	98.12 325	99.30 144	99.62 190	99.86 56	99.16 305	99.74 137	92.53 362	99.92 133	98.75 183	98.77 379	98.44 404

h-mvs33		98.61 274	98.34 290	99.44 214	99.60 195	98.67 283	99.27 157	99.44 281	99.68 104	99.32 276	99.49 278	92.50 363	100.00 1	99.24 120	96.51 427	99.65 129

hse-mvs2		98.52 287	98.30 295	99.16 282	99.29 323	98.60 294	98.77 292	99.02 355	99.68 104	99.32 276	99.04 367	92.50 363	99.85 259	99.24 120	97.87 417	99.03 351

tpmvs		97.39 349	97.69 337	96.52 406	98.41 418	91.76 425	99.30 144	98.94 359	97.74 351	97.85 401	99.55 263	92.40 365	99.73 348	96.25 366	98.73 386	98.06 418

tpmrst		97.73 335	98.07 313	96.73 404	98.71 408	92.00 423	99.10 216	98.86 360	98.52 290	98.92 331	99.54 265	91.90 366	99.82 299	98.02 235	99.03 363	98.37 406

JIA-IIPM		98.06 324	97.92 327	98.50 349	98.59 412	97.02 371	98.80 287	98.51 381	99.88 51	97.89 398	99.87 53	91.89 367	99.90 175	98.16 227	97.68 419	98.59 392

CR-MVSNet		98.35 306	98.20 302	98.83 330	99.05 368	98.12 325	99.30 144	99.67 162	97.39 369	99.16 305	99.79 104	91.87 368	99.91 156	98.78 181	98.77 379	98.44 404

Patchmtry		98.78 259	98.54 271	99.49 198	98.89 386	99.19 229	99.32 136	99.67 162	99.65 115	99.72 143	99.79 104	91.87 368	99.95 70	98.00 239	99.97 64	99.33 275

MDTV_nov1_ep13_2view						91.44 429	99.14 198		97.37 370	99.21 299		91.78 370		96.75 337		99.03 351

PatchT		98.45 296	98.32 292	98.83 330	98.94 381	98.29 313	99.24 166	98.82 363	99.84 65	99.08 316	99.76 127	91.37 371	99.94 86	98.82 173	99.00 365	98.26 410

test_yl		98.25 311	97.95 321	99.13 288	99.17 348	98.47 300	99.00 246	98.67 372	98.97 229	99.22 297	99.02 372	91.31 372	99.69 363	97.26 306	98.93 368	99.24 293

DCV-MVSNet		98.25 311	97.95 321	99.13 288	99.17 348	98.47 300	99.00 246	98.67 372	98.97 229	99.22 297	99.02 372	91.31 372	99.69 363	97.26 306	98.93 368	99.24 293

baseline1		97.73 335	97.33 346	98.96 308	99.30 321	97.73 350	99.40 115	98.42 386	99.33 178	99.46 240	99.21 347	91.18 374	99.82 299	98.35 207	91.26 434	99.32 278

tpm cat1		96.78 362	96.98 356	96.16 411	98.85 391	90.59 435	99.08 224	99.32 311	92.37 421	97.73 407	99.46 288	91.15 375	99.69 363	96.07 372	98.80 376	98.21 413

LFMVS		98.46 295	98.19 305	99.26 269	99.24 334	98.52 299	99.62 64	96.94 416	99.87 53	99.31 281	99.58 244	91.04 376	99.81 314	98.68 190	99.42 325	99.45 240

MDTV_nov1_ep13			97.73 336		98.70 409	90.83 432	99.15 196	98.02 400	98.51 291	98.82 343	99.61 228	90.98 377	99.66 385	96.89 329	98.92 370

MIMVSNet		98.43 297	98.20 302	99.11 290	99.53 237	98.38 310	99.58 79	98.61 375	98.96 231	99.33 273	99.76 127	90.92 378	99.81 314	97.38 296	99.76 225	99.15 318

ADS-MVSNet2		97.78 333	97.66 340	98.12 368	99.14 351	95.36 402	99.22 173	98.75 367	96.97 384	98.25 381	99.64 200	90.90 379	99.94 86	96.51 352	99.56 296	99.08 340

ADS-MVSNet		97.72 338	97.67 339	97.86 377	99.14 351	94.65 410	99.22 173	98.86 360	96.97 384	98.25 381	99.64 200	90.90 379	99.84 274	96.51 352	99.56 296	99.08 340

GDP-MVS		98.81 257	98.57 266	99.50 194	99.53 237	99.12 237	99.28 153	99.86 64	99.53 139	99.57 201	99.32 322	90.88 381	99.98 23	99.46 84	99.74 234	99.42 255

alignmvs		98.28 309	97.96 320	99.25 272	99.12 355	98.93 263	99.03 237	98.42 386	99.64 118	98.72 354	97.85 421	90.86 382	99.62 396	98.88 167	99.13 354	99.19 309

sam_mvs1												90.81 383				99.14 323

PatchmatchNet		97.65 339	97.80 332	97.18 397	98.82 396	92.49 421	99.17 188	98.39 389	98.12 327	98.79 348	99.58 244	90.71 384	99.89 194	97.23 311	99.41 326	99.16 316
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
BP-MVS1		98.72 266	98.46 276	99.50 194	99.53 237	99.00 250	99.34 129	98.53 379	99.65 115	99.73 141	99.38 306	90.62 385	99.96 59	99.50 80	99.86 165	99.55 191

patchmatchnet-post											99.62 219	90.58 386	99.94 86

Patchmatch-RL test		98.60 277	98.36 287	99.33 248	99.77 120	99.07 246	98.27 344	99.87 59	98.91 241	99.74 137	99.72 148	90.57 387	99.79 324	98.55 197	99.85 170	99.11 327

sam_mvs												90.52 388

pmmvs3		98.08 323	97.80 332	98.91 317	99.41 287	97.69 352	97.87 385	99.66 167	95.87 400	99.50 231	99.51 271	90.35 389	99.97 37	98.55 197	99.47 318	99.08 340

test_post											52.41 446	90.25 390	99.86 241

Patchmatch-test		98.10 322	97.98 319	98.48 350	99.27 328	96.48 381	99.40 115	99.07 351	98.81 256	99.23 294	99.57 251	90.11 391	99.87 222	96.69 340	99.64 273	99.09 334

test-LLR		97.15 354	96.95 357	97.74 382	98.18 425	95.02 407	97.38 406	96.10 418	98.00 333	97.81 403	98.58 401	90.04 392	99.91 156	97.69 277	98.78 377	98.31 407

test0.0.03 1		97.37 350	96.91 360	98.74 337	97.72 432	97.57 354	97.60 396	97.36 414	98.00 333	99.21 299	98.02 417	90.04 392	99.79 324	98.37 205	95.89 431	98.86 374

GA-MVS		97.99 328	97.68 338	98.93 314	99.52 244	98.04 333	97.19 414	99.05 354	98.32 317	98.81 344	98.97 379	89.89 394	99.41 420	98.33 209	99.05 361	99.34 274

test_post1							99.14 198				51.63 447	89.54 395	99.82 299	96.86 330

AUN-MVS		97.82 331	97.38 345	99.14 287	99.27 328	98.53 297	98.72 297	99.02 355	98.10 328	97.18 415	99.03 371	89.26 396	99.85 259	97.94 244	97.91 415	99.03 351

FE-MVS		97.85 330	97.42 344	99.15 284	99.44 277	98.75 278	99.77 16	98.20 396	95.85 401	99.33 273	99.80 94	88.86 397	99.88 208	96.40 359	99.12 355	98.81 378

MVSTER		98.47 294	98.22 300	99.24 274	99.06 367	98.35 312	99.08 224	99.46 276	99.27 185	99.75 129	99.66 193	88.61 398	99.85 259	99.14 142	99.92 115	99.52 215

baseline2		96.83 361	96.28 368	98.46 352	99.09 365	96.91 374	98.83 279	93.87 432	97.23 376	96.23 427	98.36 410	88.12 399	99.90 175	96.68 341	98.14 410	98.57 396

cl22		97.56 343	97.28 347	98.40 354	98.37 420	96.75 377	97.24 413	99.37 302	97.31 373	99.41 255	99.22 345	87.30 400	99.37 421	97.70 271	99.62 277	99.08 340

dp		96.86 360	97.07 353	96.24 410	98.68 410	90.30 437	99.19 182	98.38 390	97.35 371	98.23 383	99.59 241	87.23 401	99.82 299	96.27 365	98.73 386	98.59 392

ET-MVSNet_ETH3D		96.78 362	96.07 372	98.91 317	99.26 331	97.92 342	97.70 392	96.05 421	97.96 340	92.37 434	98.43 409	87.06 402	99.90 175	98.27 213	97.56 420	98.91 368

thres100view900		96.39 373	96.03 373	97.47 388	99.63 188	95.93 393	99.18 183	97.57 409	98.75 267	98.70 357	97.31 430	87.04 403	99.67 380	87.62 428	98.51 395	96.81 428

thres600view7		96.60 367	96.16 370	97.93 374	99.63 188	96.09 392	99.18 183	97.57 409	98.77 263	98.72 354	97.32 429	87.04 403	99.72 350	88.57 425	98.62 391	97.98 419

tfpn200view9		96.30 376	95.89 375	97.53 385	99.58 205	96.11 390	99.00 246	97.54 412	98.43 297	98.52 371	96.98 433	86.85 405	99.67 380	87.62 428	98.51 395	96.81 428

thres400		96.40 372	95.89 375	97.92 375	99.58 205	96.11 390	99.00 246	97.54 412	98.43 297	98.52 371	96.98 433	86.85 405	99.67 380	87.62 428	98.51 395	97.98 419

thres200		96.09 382	95.68 382	97.33 393	99.48 262	96.22 389	98.53 322	97.57 409	98.06 332	98.37 378	96.73 437	86.84 407	99.61 401	86.99 431	98.57 392	96.16 431

tpm		97.15 354	96.95 357	97.75 381	98.91 382	94.24 412	99.32 136	97.96 401	97.71 353	98.29 379	99.32 322	86.72 408	99.92 133	98.10 233	96.24 429	99.09 334

EPMVS		96.53 368	96.32 367	97.17 398	98.18 425	92.97 420	99.39 117	89.95 437	98.21 323	98.61 363	99.59 241	86.69 409	99.72 350	96.99 322	99.23 352	98.81 378

CostFormer		96.71 365	96.79 364	96.46 408	98.90 383	90.71 434	99.41 114	98.68 370	94.69 417	98.14 389	99.34 321	86.32 410	99.80 321	97.60 283	98.07 413	98.88 372

MVStest1		98.22 316	98.09 311	98.62 342	99.04 371	96.23 388	99.20 176	99.92 40	99.44 159	99.98 14	99.87 53	85.87 411	99.67 380	99.91 29	99.57 295	99.95 14

thisisatest0515		96.98 358	96.42 366	98.66 341	99.42 285	97.47 357	97.27 411	94.30 428	97.24 375	99.15 307	98.86 389	85.01 412	99.87 222	97.10 317	99.39 328	98.63 388

tpm2		96.35 374	96.22 369	96.73 404	98.88 388	91.75 426	99.21 175	98.51 381	93.27 420	97.89 398	99.21 347	84.83 413	99.70 357	96.04 373	98.18 408	98.75 385

tttt0517		97.62 340	97.20 350	98.90 323	99.76 124	97.40 361	99.48 102	94.36 427	99.06 222	99.70 152	99.49 278	84.55 414	99.94 86	98.73 185	99.65 271	99.36 268

UWE-MVS-28		95.64 393	95.47 385	96.14 412	97.98 429	90.39 436	98.49 327	95.81 423	99.02 225	98.03 393	98.19 414	84.49 415	99.28 422	88.75 424	98.47 398	98.75 385

thisisatest0530		97.45 346	96.95 357	98.94 311	99.68 174	97.73 350	99.09 221	94.19 429	98.61 281	99.56 209	99.30 327	84.30 416	99.93 106	98.27 213	99.54 305	99.16 316

FPMVS		96.32 375	95.50 384	98.79 334	99.60 195	98.17 322	98.46 333	98.80 365	97.16 380	96.28 424	99.63 212	82.19 417	99.09 425	88.45 426	98.89 375	99.10 329

gg-mvs-nofinetune		95.87 388	95.17 394	97.97 372	98.19 424	96.95 372	99.69 42	89.23 438	99.89 46	96.24 426	99.94 19	81.19 418	99.51 415	93.99 414	98.20 405	97.44 424

reproduce_monomvs		97.40 348	97.46 342	97.20 396	99.05 368	91.91 424	99.20 176	99.18 342	99.84 65	99.86 80	99.75 133	80.67 419	99.83 289	99.69 55	99.95 91	99.85 44

GG-mvs-BLEND				97.36 391	97.59 433	96.87 375	99.70 35	88.49 439		94.64 432	97.26 431	80.66 420	99.12 424	91.50 420	96.50 428	96.08 432

FMVSNet5		97.80 332	97.25 349	99.42 220	98.83 393	98.97 256	99.38 120	99.80 95	98.87 246	99.25 290	99.69 173	80.60 421	99.91 156	98.96 160	99.90 126	99.38 262

WBMVS		97.50 345	97.18 351	98.48 350	98.85 391	95.89 395	98.44 334	99.52 256	99.53 139	99.52 223	99.42 295	80.10 422	99.86 241	99.24 120	99.95 91	99.68 104

UWE-MVS		96.21 380	95.78 379	97.49 386	98.53 414	93.83 416	98.04 367	93.94 431	98.96 231	98.46 375	98.17 415	79.86 423	99.87 222	96.99 322	99.06 359	98.78 381

UBG		96.53 368	95.95 374	98.29 363	98.87 389	96.31 386	98.48 328	98.07 398	98.83 253	97.32 410	96.54 440	79.81 424	99.62 396	96.84 333	98.74 383	98.95 362

TESTMET0.1,1		96.24 377	95.84 378	97.41 390	98.24 423	93.84 415	97.38 406	95.84 422	98.43 297	97.81 403	98.56 404	79.77 425	99.89 194	97.77 260	98.77 379	98.52 398

KD-MVS_2432*1600		95.89 386	95.41 387	97.31 394	94.96 437	93.89 413	97.09 416	99.22 335	97.23 376	98.88 335	99.04 367	79.23 426	99.54 409	96.24 367	96.81 424	98.50 402

miper_refine_blended		95.89 386	95.41 387	97.31 394	94.96 437	93.89 413	97.09 416	99.22 335	97.23 376	98.88 335	99.04 367	79.23 426	99.54 409	96.24 367	96.81 424	98.50 402

test-mter		96.23 378	95.73 381	97.74 382	98.18 425	95.02 407	97.38 406	96.10 418	97.90 342	97.81 403	98.58 401	79.12 428	99.91 156	97.69 277	98.78 377	98.31 407

test2506		94.73 398	94.59 399	95.15 414	99.59 200	85.90 440	99.75 22	74.01 442	99.89 46	99.71 148	99.86 60	79.00 429	99.90 175	99.52 77	99.99 16	99.65 129

myMVS_eth3d28		96.23 378	95.74 380	97.70 384	98.86 390	95.59 400	98.66 301	98.14 397	98.96 231	97.67 408	97.06 432	76.78 430	98.92 428	97.10 317	98.41 399	98.58 394

testing3-2		96.51 370	96.43 365	96.74 403	99.36 297	91.38 430	99.10 216	97.87 405	99.48 146	98.57 368	98.71 397	76.65 431	99.66 385	98.87 168	99.26 347	99.18 311

IB-MVS	95.41 20	95.30 397	94.46 401	97.84 378	98.76 404	95.33 403	97.33 409	96.07 420	96.02 399	95.37 431	97.41 428	76.17 432	99.96 59	97.54 286	95.44 433	98.22 412
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
testing11		96.05 384	95.41 387	97.97 372	98.78 401	95.27 404	98.59 309	98.23 395	98.86 248	96.56 422	96.91 435	75.20 433	99.69 363	97.26 306	98.29 402	98.93 365

testing91		96.00 385	95.32 390	98.02 369	98.76 404	95.39 401	98.38 337	98.65 374	98.82 254	96.84 418	96.71 438	75.06 434	99.71 354	96.46 357	98.23 404	98.98 359

testing99		95.86 389	95.19 393	97.87 376	98.76 404	95.03 406	98.62 303	98.44 385	98.68 272	96.67 421	96.66 439	74.31 435	99.69 363	96.51 352	98.03 414	98.90 369

ETVMVS		96.14 381	95.22 392	98.89 324	98.80 397	98.01 334	98.66 301	98.35 392	98.71 270	97.18 415	96.31 444	74.23 436	99.75 342	96.64 346	98.13 412	98.90 369

testing3		96.48 371	95.63 383	99.01 304	99.23 336	97.81 346	98.90 267	99.10 350	98.72 268	97.84 402	97.92 420	72.44 437	99.85 259	97.21 313	99.33 336	99.35 271

myMVS_eth3d		95.63 394	94.73 396	98.34 358	98.50 416	96.36 384	98.60 306	99.21 338	97.89 343	96.76 419	96.37 442	72.10 438	99.57 405	94.38 406	98.73 386	99.09 334

dongtai		89.37 400	88.91 403	90.76 416	99.19 344	77.46 441	95.47 429	87.82 440	92.28 422	94.17 433	98.82 392	71.22 439	95.54 435	63.85 435	97.34 421	99.27 288

testing222		95.60 396	94.59 399	98.61 343	98.66 411	97.45 359	98.54 320	97.90 404	98.53 289	96.54 423	96.47 441	70.62 440	99.81 314	95.91 382	98.15 409	98.56 397

kuosan		85.65 402	84.57 405	88.90 418	97.91 430	77.11 442	96.37 426	87.62 441	85.24 431	85.45 436	96.83 436	69.94 441	90.98 437	45.90 436	95.83 432	98.62 389

test123		29.31 403	33.05 408	18.08 419	25.93 443	12.24 444	97.53 400	10.93 444	11.78 437	24.21 438	50.08 449	21.04 442	8.60 438	23.51 437	32.43 437	33.39 434

testmvs		28.94 404	33.33 406	15.79 420	26.03 442	9.81 445	96.77 422	15.67 443	11.55 438	23.87 439	50.74 448	19.03 443	8.53 439	23.21 438	33.07 436	29.03 435

mmdepth		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

ab-mvs-re		8.26 417	11.02 420	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	99.16 351	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		8.33 407	11.11 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						96.36 384								95.20 397

FOURS1					99.83 67	99.89 10	99.74 24	99.71 142	99.69 102	99.63 175

MSC_two_6792asdad				99.74 89	99.03 372	99.53 151		99.23 332					99.92 133	97.77 260	99.69 255	99.78 69

No_MVS				99.74 89	99.03 372	99.53 151		99.23 332					99.92 133	97.77 260	99.69 255	99.78 69

eth-test2					0.00 444

eth-test					0.00 444

IU-MVS					99.69 166	99.77 58		99.22 335	97.50 363	99.69 155				97.75 264	99.70 251	99.77 73

save fliter					99.53 237	99.25 216	98.29 343	99.38 301	99.07 220

test_0728_SECOND				99.83 38	99.70 162	99.79 49	99.14 198	99.61 197					99.92 133	97.88 249	99.72 246	99.77 73

GSMVS																99.14 323

test_part2					99.62 192	99.67 108				99.55 214

MTGPA								99.53 251

MTMP							99.09 221	98.59 378

gm-plane-assit					97.59 433	89.02 439			93.47 419		98.30 411		99.84 274	96.38 361

test9_res														95.10 399	99.44 321	99.50 222

agg_prior2														94.58 405	99.46 320	99.50 222

agg_prior					99.35 301	99.36 195		99.39 297		97.76 406			99.85 259

test_prior4						99.19 229	98.00 372

test_prior				99.46 207	99.35 301	99.22 223		99.39 297					99.69 363			99.48 231

旧先验2							97.94 379		95.33 408	98.94 327			99.88 208	96.75 337

新几何2							98.04 367

无先验							98.01 370	99.23 332	95.83 402				99.85 259	95.79 386		99.44 245

原ACMM2							97.92 381

testdata2													99.89 194	95.99 377

testdata1							97.72 390		97.86 348

plane_prior7					99.58 205	99.38 188

plane_prior5								99.54 242					99.82 299	95.84 384	99.78 219	99.60 169

plane_prior4											99.25 338

plane_prior3						99.31 204			98.36 306	99.14 309

plane_prior2							98.80 287		98.94 235

plane_prior1					99.51 246

plane_prior						99.24 220	98.42 335		97.87 346						99.71 249

n2								0.00 445

nn								0.00 445

door-mid								99.83 78

test11								99.29 319

door								99.77 110

HQP5-MVS						98.94 260

HQP-NCC					99.31 317		97.98 374		97.45 365	98.15 385

ACMP_Plane					99.31 317		97.98 374		97.45 365	98.15 385

BP-MVS														94.73 402

HQP4-MVS										98.15 385			99.70 357			99.53 205

HQP3-MVS								99.37 302							99.67 266

NP-MVS					99.40 288	99.13 235					98.83 390

ACMMP++_ref															99.94 104

ACMMP++															99.79 214

High-resolution multi-view benchmark