High-res multi-view results

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

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

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

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

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

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

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

test_vis3_rt		99.89 3	99.90 3	99.87 15	99.98 3	99.75 62	99.70 34	100.00 1	99.73 58	100.00 1	99.89 31	99.79 9	99.88 173	99.98 1	100.00 1	99.98 1

IterMVS-SCA-FT		99.00 194	99.16 130	98.51 303	99.75 113	95.90 345	98.07 308	99.84 46	99.84 37	99.89 42	99.73 111	96.01 285	99.99 6	99.33 75	100.00 1	99.63 110

new-patchmatchnet		99.35 110	99.57 58	98.71 298	99.82 61	96.62 335	98.55 267	99.75 88	99.50 106	99.88 48	99.87 40	99.31 48	99.88 173	99.43 57	100.00 1	99.62 121

anonymousdsp		99.80 14	99.77 20	99.90 5	99.96 5	99.88 12	99.73 26	99.85 40	99.70 69	99.92 29	99.93 17	99.45 33	99.97 23	99.36 69	100.00 1	99.85 21

UA-Net		99.78 16	99.76 22	99.86 18	99.72 125	99.71 76	99.91 3	99.95 18	99.96 3	99.71 118	99.91 24	99.15 67	99.97 23	99.50 51	100.00 1	99.90 12

PS-MVSNAJss		99.84 10	99.82 14	99.89 8	99.96 5	99.77 50	99.68 44	99.85 40	99.95 5	99.98 11	99.92 21	99.28 52	99.98 11	99.75 24	100.00 1	99.94 8

jajsoiax		99.89 3	99.89 5	99.89 8	99.96 5	99.78 47	99.70 34	99.86 36	99.89 20	99.98 11	99.90 27	99.94 1	99.98 11	99.75 24	100.00 1	99.90 12

mvs_tets		99.90 2	99.90 3	99.90 5	99.96 5	99.79 44	99.72 29	99.88 31	99.92 12	99.98 11	99.93 17	99.94 1	99.98 11	99.77 23	100.00 1	99.92 11

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 11	99.99 1	100.00 1	99.98 10	99.78 10	100.00 1	99.92 10	100.00 1	99.87 17

test_djsdf		99.84 10	99.81 15	99.91 2	99.94 16	99.84 24	99.77 14	99.80 64	99.73 58	99.97 14	99.92 21	99.77 11	99.98 11	99.43 57	100.00 1	99.90 12

IterMVS		98.97 198	99.16 130	98.42 307	99.74 119	95.64 348	98.06 310	99.83 48	99.83 40	99.85 59	99.74 107	96.10 284	99.99 6	99.27 87	100.00 1	99.63 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ANet_high		99.88 5	99.87 9	99.91 2	99.99 1	99.91 4	99.65 58	100.00 1	99.90 14	100.00 1	99.97 11	99.61 22	99.97 23	99.75 24	100.00 1	99.84 22

test_vis1_n_1920		99.72 22	99.88 6	99.27 229	99.93 23	97.84 303	99.34 118	100.00 1	99.99 1	99.99 7	99.82 62	99.87 3	99.99 6	99.97 4	99.99 13	99.97 3

test_fmvs2		99.72 22	99.85 12	99.34 211	99.91 27	98.08 292	99.48 92	100.00 1	99.90 14	99.99 7	99.91 24	99.50 32	99.98 11	99.98 1	99.99 13	99.96 5

test_fmvs3		99.83 12	99.93 2	99.53 158	99.96 5	98.62 256	99.67 48	100.00 1	99.95 5	100.00 1	99.95 13	99.85 4	99.99 6	99.98 1	99.99 13	99.98 1

test_f		99.75 18	99.88 6	99.37 204	99.96 5	98.21 279	99.51 86	100.00 1	99.94 9	100.00 1	99.93 17	99.58 25	99.94 65	99.97 4	99.99 13	99.97 3

bld_raw_dy_0_64		99.70 26	99.65 36	99.85 20	99.95 13	99.77 50	99.66 52	99.71 109	99.95 5	99.91 32	99.77 95	98.35 176	100.00 1	99.54 44	99.99 13	99.79 38

test2506		94.73 341	94.59 343	95.15 357	99.59 171	85.90 382	99.75 21	74.01 383	99.89 20	99.71 118	99.86 47	79.00 381	99.90 142	99.52 48	99.99 13	99.65 97

test1111		97.74 292	98.16 268	96.49 351	99.60 167	89.86 380	99.71 33	91.21 377	99.89 20	99.88 48	99.87 40	93.73 307	99.90 142	99.56 41	99.99 13	99.70 64

ECVR-MVS		97.73 293	98.04 273	96.78 345	99.59 171	90.81 376	99.72 29	90.43 379	99.89 20	99.86 57	99.86 47	93.60 309	99.89 159	99.46 54	99.99 13	99.65 97

pmmvs-eth3d		99.48 73	99.47 72	99.51 162	99.77 98	99.41 155	98.81 241	99.66 132	99.42 127	99.75 100	99.66 158	99.20 62	99.76 297	98.98 122	99.99 13	99.36 233

v7n		99.82 13	99.80 17	99.88 12	99.96 5	99.84 24	99.82 8	99.82 53	99.84 37	99.94 22	99.91 24	99.13 72	99.96 42	99.83 18	99.99 13	99.83 26

RRT_MVS		99.67 38	99.59 51	99.91 2	99.94 16	99.88 12	99.78 11	99.27 287	99.87 26	99.91 32	99.87 40	98.04 204	99.96 42	99.68 28	99.99 13	99.90 12

v8		99.68 32	99.69 29	99.65 107	99.80 73	99.40 156	99.66 52	99.76 83	99.64 86	99.93 25	99.85 49	98.66 131	99.84 236	99.88 15	99.99 13	99.71 61

v10		99.69 29	99.69 29	99.66 102	99.81 68	99.39 158	99.66 52	99.75 88	99.60 98	99.92 29	99.87 40	98.75 118	99.86 205	99.90 11	99.99 13	99.73 56

CHOSEN 1792x2688		99.39 100	99.30 108	99.65 107	99.88 39	99.25 188	98.78 248	99.88 31	98.66 220	99.96 16	99.79 81	97.45 240	99.93 82	99.34 72	99.99 13	99.78 41

PVSNet_Blended_VisFu		99.40 96	99.38 89	99.44 178	99.90 32	98.66 250	98.94 226	99.91 22	97.97 282	99.79 82	99.73 111	99.05 83	99.97 23	99.15 104	99.99 13	99.68 74

IterMVS-LS		99.41 94	99.47 72	99.25 235	99.81 68	98.09 289	98.85 233	99.76 83	99.62 89	99.83 66	99.64 165	98.54 148	99.97 23	99.15 104	99.99 13	99.68 74
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DeepC-MVS	98.90 4	99.62 52	99.61 46	99.67 95	99.72 125	99.44 144	99.24 151	99.71 109	99.27 141	99.93 25	99.90 27	99.70 16	99.93 82	98.99 120	99.99 13	99.64 105
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LTVRE_ROB	99.19 1	99.88 5	99.87 9	99.88 12	99.91 27	99.90 7	99.96 1	99.92 19	99.90 14	99.97 14	99.87 40	99.81 8	99.95 52	99.54 44	99.99 13	99.80 32
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
test_fmvs1_n		99.68 32	99.81 15	99.28 226	99.95 13	97.93 301	99.49 91	100.00 1	99.82 42	99.99 7	99.89 31	99.21 61	99.98 11	99.97 4	99.98 31	99.93 10

mvsany_test3		99.85 8	99.88 6	99.75 60	99.95 13	99.37 163	99.53 82	99.98 9	99.77 56	99.99 7	99.95 13	99.85 4	99.94 65	99.95 8	99.98 31	99.94 8

Anonymous20240521		99.44 85	99.42 85	99.49 165	99.89 34	98.96 225	99.62 61	99.76 83	99.85 34	99.82 67	99.88 36	96.39 276	99.97 23	99.59 35	99.98 31	99.55 157

D2MVS		99.22 143	99.19 127	99.29 224	99.69 140	98.74 244	98.81 241	99.41 250	98.55 231	99.68 127	99.69 138	98.13 198	99.87 187	98.82 137	99.98 31	99.24 255

CHOSEN 280x420		98.41 261	98.41 244	98.40 308	99.34 271	95.89 346	96.94 363	99.44 244	98.80 208	99.25 250	99.52 231	93.51 310	99.98 11	98.94 131	99.98 31	99.32 242

v1192		99.57 57	99.57 58	99.57 147	99.77 98	99.22 195	99.04 205	99.60 171	99.18 156	99.87 56	99.72 118	99.08 78	99.85 222	99.89 14	99.98 31	99.66 89

v1144		99.54 65	99.53 68	99.59 138	99.79 83	99.28 181	99.10 193	99.61 159	99.20 154	99.84 62	99.73 111	98.67 129	99.84 236	99.86 17	99.98 31	99.64 105

mvsmamba		99.74 21	99.70 25	99.85 20	99.93 23	99.83 29	99.76 18	99.81 62	99.96 3	99.91 32	99.81 67	98.60 139	99.94 65	99.58 38	99.98 31	99.77 45

OurMVSNet-221017-0		99.75 18	99.71 24	99.84 23	99.96 5	99.83 29	99.83 6	99.85 40	99.80 47	99.93 25	99.93 17	98.54 148	99.93 82	99.59 35	99.98 31	99.76 51

UGNet		99.38 102	99.34 97	99.49 165	98.90 338	98.90 233	99.70 34	99.35 269	99.86 29	98.57 324	99.81 67	98.50 158	99.93 82	99.38 64	99.98 31	99.66 89
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
MIMVSNet1		99.66 40	99.62 42	99.80 34	99.94 16	99.87 15	99.69 41	99.77 78	99.78 52	99.93 25	99.89 31	97.94 212	99.92 102	99.65 30	99.98 31	99.62 121

Vis-MVSNet		99.75 18	99.74 23	99.79 38	99.88 39	99.66 93	99.69 41	99.92 19	99.67 78	99.77 91	99.75 104	99.61 22	99.98 11	99.35 71	99.98 31	99.72 58
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvs1		99.48 73	99.65 36	98.97 267	99.54 199	97.16 323	99.11 191	99.98 9	99.78 52	99.96 16	99.81 67	98.72 123	99.97 23	99.95 8	99.97 43	99.79 38

iter_conf_final		98.75 225	98.54 234	99.40 193	99.33 276	98.75 242	99.26 144	99.59 177	99.80 47	99.76 93	99.58 206	90.17 347	99.92 102	99.37 67	99.97 43	99.54 165

UniMVSNet_ETH3D		99.85 8	99.83 13	99.90 5	99.89 34	99.91 4	99.89 4	99.71 109	99.93 10	99.95 20	99.89 31	99.71 14	99.96 42	99.51 49	99.97 43	99.84 22

CANet		99.11 173	99.05 164	99.28 226	98.83 346	98.56 258	98.71 255	99.41 250	99.25 145	99.23 254	99.22 304	97.66 234	99.94 65	99.19 95	99.97 43	99.33 239

pmmvs6		99.86 7	99.86 11	99.83 25	99.94 16	99.90 7	99.83 6	99.91 22	99.85 34	99.94 22	99.95 13	99.73 13	99.90 142	99.65 30	99.97 43	99.69 68

v144192		99.55 63	99.54 64	99.58 141	99.78 90	99.20 200	99.11 191	99.62 152	99.18 156	99.89 42	99.72 118	98.66 131	99.87 187	99.88 15	99.97 43	99.66 89

v1921920		99.56 60	99.57 58	99.55 153	99.75 113	99.11 208	99.05 203	99.61 159	99.15 167	99.88 48	99.71 125	99.08 78	99.87 187	99.90 11	99.97 43	99.66 89

FC-MVSNet-test		99.70 26	99.65 36	99.86 18	99.88 39	99.86 18	99.72 29	99.78 75	99.90 14	99.82 67	99.83 55	98.45 163	99.87 187	99.51 49	99.97 43	99.86 19

iter_conf05		98.46 256	98.23 259	99.15 247	99.04 327	97.99 294	99.10 193	99.61 159	99.79 50	99.76 93	99.58 206	87.88 357	99.92 102	99.31 80	99.97 43	99.53 171

v2v482		99.50 69	99.47 72	99.58 141	99.78 90	99.25 188	99.14 179	99.58 187	99.25 145	99.81 74	99.62 182	98.24 187	99.84 236	99.83 18	99.97 43	99.64 105

Patchmtry		98.78 222	98.54 234	99.49 165	98.89 341	99.19 201	99.32 123	99.67 128	99.65 84	99.72 113	99.79 81	91.87 326	99.95 52	98.00 197	99.97 43	99.33 239

PVSNet_BlendedMVS		99.03 186	99.01 175	99.09 256	99.54 199	97.99 294	98.58 261	99.82 53	97.62 299	99.34 232	99.71 125	98.52 155	99.77 295	97.98 198	99.97 43	99.52 182

FMVSNet1		99.66 40	99.63 41	99.73 74	99.78 90	99.77 50	99.68 44	99.70 115	99.67 78	99.82 67	99.83 55	98.98 90	99.90 142	99.24 88	99.97 43	99.53 171

HyFIR lowres test		98.91 207	98.64 221	99.73 74	99.85 49	99.47 133	98.07 308	99.83 48	98.64 222	99.89 42	99.60 199	92.57 318	100.00 1	99.33 75	99.97 43	99.72 58

test_vis1_n		99.68 32	99.79 18	99.36 208	99.94 16	98.18 282	99.52 83	100.00 1	99.86 29	100.00 1	99.88 36	98.99 88	99.96 42	99.97 4	99.96 57	99.95 6

patch_mono-2		99.51 68	99.46 76	99.64 114	99.70 136	99.11 208	99.04 205	99.87 33	99.71 64	99.47 201	99.79 81	98.24 187	99.98 11	99.38 64	99.96 57	99.83 26

dcpmvs_2		99.61 54	99.64 40	99.53 158	99.79 83	98.82 237	99.58 74	99.97 11	99.95 5	99.96 16	99.76 99	98.44 164	99.99 6	99.34 72	99.96 57	99.78 41

ppachtmachnet_test		98.89 212	99.12 140	98.20 317	99.66 154	95.24 352	97.63 337	99.68 124	99.08 174	99.78 86	99.62 182	98.65 133	99.88 173	98.02 193	99.96 57	99.48 198

Anonymous20231211		99.62 52	99.57 58	99.76 51	99.61 165	99.60 113	99.81 9	99.73 97	99.82 42	99.90 38	99.90 27	97.97 211	99.86 205	99.42 62	99.96 57	99.80 32

nrg030		99.70 26	99.66 34	99.82 27	99.76 102	99.84 24	99.61 66	99.70 115	99.93 10	99.78 86	99.68 149	99.10 73	99.78 287	99.45 55	99.96 57	99.83 26

v1240		99.56 60	99.58 55	99.51 162	99.80 73	99.00 219	99.00 213	99.65 141	99.15 167	99.90 38	99.75 104	99.09 75	99.88 173	99.90 11	99.96 57	99.67 80

PS-CasMVS		99.66 40	99.58 55	99.89 8	99.80 73	99.85 19	99.66 52	99.73 97	99.62 89	99.84 62	99.71 125	98.62 135	99.96 42	99.30 81	99.96 57	99.86 19

casdiffmvs_mvg		99.68 32	99.68 32	99.69 90	99.81 68	99.59 115	99.29 137	99.90 25	99.71 64	99.79 82	99.73 111	99.54 29	99.84 236	99.36 69	99.96 57	99.65 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TAMVS		99.49 71	99.45 78	99.63 121	99.48 228	99.42 151	99.45 98	99.57 189	99.66 82	99.78 86	99.83 55	97.85 219	99.86 205	99.44 56	99.96 57	99.61 131

test_0402		99.22 143	99.14 134	99.45 176	99.79 83	99.43 148	99.28 139	99.68 124	99.54 102	99.40 224	99.56 218	99.07 80	99.82 260	96.01 322	99.96 57	99.11 286

our_test_3		98.85 217	99.09 152	98.13 319	99.66 154	94.90 355	97.72 333	99.58 187	99.07 176	99.64 139	99.62 182	98.19 194	99.93 82	98.41 164	99.95 68	99.55 157

CANet_DTU		98.91 207	98.85 203	99.09 256	98.79 351	98.13 284	98.18 294	99.31 278	99.48 108	98.86 299	99.51 233	96.56 267	99.95 52	99.05 116	99.95 68	99.19 269

pmmvs5		99.19 153	99.11 143	99.42 184	99.76 102	98.88 234	98.55 267	99.73 97	98.82 205	99.72 113	99.62 182	96.56 267	99.82 260	99.32 77	99.95 68	99.56 154

V42		99.56 60	99.54 64	99.63 121	99.79 83	99.46 137	99.39 107	99.59 177	99.24 147	99.86 57	99.70 132	98.55 146	99.82 260	99.79 22	99.95 68	99.60 135

EU-MVSNet		99.39 100	99.62 42	98.72 296	99.88 39	96.44 337	99.56 79	99.85 40	99.90 14	99.90 38	99.85 49	98.09 200	99.83 251	99.58 38	99.95 68	99.90 12

PMMVS2		99.48 73	99.45 78	99.57 147	99.76 102	98.99 220	98.09 305	99.90 25	98.95 187	99.78 86	99.58 206	99.57 26	99.93 82	99.48 52	99.95 68	99.79 38

DTE-MVSNet		99.68 32	99.61 46	99.88 12	99.80 73	99.87 15	99.67 48	99.71 109	99.72 62	99.84 62	99.78 88	98.67 129	99.97 23	99.30 81	99.95 68	99.80 32

WR-MVS_H		99.61 54	99.53 68	99.87 15	99.80 73	99.83 29	99.67 48	99.75 88	99.58 101	99.85 59	99.69 138	98.18 196	99.94 65	99.28 86	99.95 68	99.83 26

K. test v3		98.87 215	98.60 224	99.69 90	99.93 23	99.46 137	99.74 23	94.97 370	99.78 52	99.88 48	99.88 36	93.66 308	99.97 23	99.61 33	99.95 68	99.64 105

TDRefinement		99.72 22	99.70 25	99.77 44	99.90 32	99.85 19	99.86 5	99.92 19	99.69 72	99.78 86	99.92 21	99.37 42	99.88 173	98.93 132	99.95 68	99.60 135

Gipuma		99.57 57	99.59 51	99.49 165	99.98 3	99.71 76	99.72 29	99.84 46	99.81 44	99.94 22	99.78 88	98.91 98	99.71 312	98.41 164	99.95 68	99.05 302
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVS_0304		98.88 213	98.71 216	99.39 197	98.85 344	98.91 232	99.45 98	99.30 281	98.56 229	97.26 363	99.68 149	96.18 282	99.96 42	99.17 100	99.94 79	99.29 250

v148		99.40 96	99.41 86	99.39 197	99.76 102	98.94 226	99.09 197	99.59 177	99.17 161	99.81 74	99.61 191	98.41 168	99.69 320	99.32 77	99.94 79	99.53 171

casdiffmvs		99.63 46	99.61 46	99.67 95	99.79 83	99.59 115	99.13 185	99.85 40	99.79 50	99.76 93	99.72 118	99.33 47	99.82 260	99.21 91	99.94 79	99.59 142
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PEN-MVS		99.66 40	99.59 51	99.89 8	99.83 54	99.87 15	99.66 52	99.73 97	99.70 69	99.84 62	99.73 111	98.56 145	99.96 42	99.29 84	99.94 79	99.83 26

CP-MVSNet		99.54 65	99.43 83	99.87 15	99.76 102	99.82 35	99.57 77	99.61 159	99.54 102	99.80 77	99.64 165	97.79 223	99.95 52	99.21 91	99.94 79	99.84 22

baseline		99.63 46	99.62 42	99.66 102	99.80 73	99.62 105	99.44 101	99.80 64	99.71 64	99.72 113	99.69 138	99.15 67	99.83 251	99.32 77	99.94 79	99.53 171

FMVSNet2		99.35 110	99.28 115	99.55 153	99.49 223	99.35 170	99.45 98	99.57 189	99.44 118	99.70 121	99.74 107	97.21 251	99.87 187	99.03 117	99.94 79	99.44 212

ACMMP++_ref															99.94 79

eth_miper_zixun_eth		98.68 233	98.71 216	98.60 300	99.10 320	96.84 332	97.52 345	99.54 206	98.94 188	99.58 166	99.48 243	96.25 280	99.76 297	98.01 196	99.93 87	99.21 262

FIs		99.65 45	99.58 55	99.84 23	99.84 50	99.85 19	99.66 52	99.75 88	99.86 29	99.74 108	99.79 81	98.27 185	99.85 222	99.37 67	99.93 87	99.83 26

pmmvs4		99.13 168	99.06 160	99.36 208	99.57 186	99.10 213	98.01 313	99.25 293	98.78 211	99.58 166	99.44 254	98.24 187	99.76 297	98.74 147	99.93 87	99.22 260

XXY-MVS		99.71 25	99.67 33	99.81 30	99.89 34	99.72 74	99.59 72	99.82 53	99.39 128	99.82 67	99.84 54	99.38 40	99.91 124	99.38 64	99.93 87	99.80 32

pm-mvs1		99.79 15	99.79 18	99.78 41	99.91 27	99.83 29	99.76 18	99.87 33	99.73 58	99.89 42	99.87 40	99.63 19	99.87 187	99.54 44	99.92 91	99.63 110

EI-MVSNet		99.38 102	99.44 81	99.21 239	99.58 176	98.09 289	99.26 144	99.46 239	99.62 89	99.75 100	99.67 154	98.54 148	99.85 222	99.15 104	99.92 91	99.68 74

TranMVSNet+NR-MVSNet		99.54 65	99.47 72	99.76 51	99.58 176	99.64 99	99.30 131	99.63 149	99.61 92	99.71 118	99.56 218	98.76 116	99.96 42	99.14 110	99.92 91	99.68 74

lessismore_v0				99.64 114	99.86 46	99.38 160		90.66 378		99.89 42	99.83 55	94.56 298	99.97 23	99.56 41	99.92 91	99.57 152

SixPastTwentyTwo		99.42 90	99.30 108	99.76 51	99.92 26	99.67 91	99.70 34	99.14 309	99.65 84	99.89 42	99.90 27	96.20 281	99.94 65	99.42 62	99.92 91	99.67 80

MVSTER		98.47 255	98.22 261	99.24 237	99.06 324	98.35 273	99.08 200	99.46 239	99.27 141	99.75 100	99.66 158	88.61 355	99.85 222	99.14 110	99.92 91	99.52 182

N_pmnet		98.73 229	98.53 236	99.35 210	99.72 125	98.67 247	98.34 284	94.65 371	98.35 256	99.79 82	99.68 149	98.03 205	99.93 82	98.28 173	99.92 91	99.44 212

CSCG		99.37 105	99.29 113	99.60 136	99.71 128	99.46 137	99.43 103	99.85 40	98.79 209	99.41 219	99.60 199	98.92 96	99.92 102	98.02 193	99.92 91	99.43 218

CMPMVS	77.52 23	98.50 251	98.19 266	99.41 191	98.33 366	99.56 122	99.01 211	99.59 177	95.44 349	99.57 169	99.80 71	95.64 288	99.46 367	96.47 305	99.92 91	99.21 262
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EG-PatchMatch MVS		99.57 57	99.56 63	99.62 130	99.77 98	99.33 173	99.26 144	99.76 83	99.32 136	99.80 77	99.78 88	99.29 50	99.87 187	99.15 104	99.91 100	99.66 89

miper_lstm_enhance		98.65 235	98.60 224	98.82 291	99.20 302	97.33 319	97.78 331	99.66 132	99.01 181	99.59 164	99.50 236	94.62 297	99.85 222	98.12 189	99.90 101	99.26 252

CS-MVS-test		99.68 32	99.70 25	99.64 114	99.57 186	99.83 29	99.78 11	99.97 11	99.92 12	99.50 197	99.38 267	99.57 26	99.95 52	99.69 27	99.90 101	99.15 277

EI-MVSNet-UG-set		99.48 73	99.50 70	99.42 184	99.57 186	98.65 253	99.24 151	99.46 239	99.68 74	99.80 77	99.66 158	98.99 88	99.89 159	99.19 95	99.90 101	99.72 58

diffmvs		99.34 115	99.32 102	99.39 197	99.67 153	98.77 241	98.57 265	99.81 62	99.61 92	99.48 200	99.41 257	98.47 159	99.86 205	98.97 124	99.90 101	99.53 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
YYNet1		98.95 204	98.99 183	98.84 286	99.64 158	97.14 325	98.22 293	99.32 274	98.92 193	99.59 164	99.66 158	97.40 242	99.83 251	98.27 174	99.90 101	99.55 157

GBi-Net		99.42 90	99.31 103	99.73 74	99.49 223	99.77 50	99.68 44	99.70 115	99.44 118	99.62 152	99.83 55	97.21 251	99.90 142	98.96 126	99.90 101	99.53 171

FMVSNet5		97.80 290	97.25 306	99.42 184	98.83 346	98.97 223	99.38 109	99.80 64	98.87 199	99.25 250	99.69 138	80.60 376	99.91 124	98.96 126	99.90 101	99.38 227

test1		99.42 90	99.31 103	99.73 74	99.49 223	99.77 50	99.68 44	99.70 115	99.44 118	99.62 152	99.83 55	97.21 251	99.90 142	98.96 126	99.90 101	99.53 171

FMVSNet3		98.80 221	98.63 223	99.32 218	99.13 312	98.72 245	99.10 193	99.48 233	99.23 149	99.62 152	99.64 165	92.57 318	99.86 205	98.96 126	99.90 101	99.39 225

cl____		98.54 246	98.41 244	98.92 274	99.03 328	97.80 306	97.46 347	99.59 177	98.90 195	99.60 161	99.46 250	93.85 304	99.78 287	97.97 200	99.89 110	99.17 273

DIV-MVS_self_test		98.54 246	98.42 243	98.92 274	99.03 328	97.80 306	97.46 347	99.59 177	98.90 195	99.60 161	99.46 250	93.87 303	99.78 287	97.97 200	99.89 110	99.18 271

CS-MVS		99.67 38	99.70 25	99.58 141	99.53 205	99.84 24	99.79 10	99.96 15	99.90 14	99.61 158	99.41 257	99.51 31	99.95 52	99.66 29	99.89 110	98.96 311

EI-MVSNet-Vis-set		99.47 80	99.49 71	99.42 184	99.57 186	98.66 250	99.24 151	99.46 239	99.67 78	99.79 82	99.65 163	98.97 92	99.89 159	99.15 104	99.89 110	99.71 61

DSMNet-mixed		99.48 73	99.65 36	98.95 269	99.71 128	97.27 320	99.50 87	99.82 53	99.59 100	99.41 219	99.85 49	99.62 21	100.00 1	99.53 47	99.89 110	99.59 142

Vis-MVSNet (Re-imp)		98.77 223	98.58 229	99.34 211	99.78 90	98.88 234	99.61 66	99.56 194	99.11 173	99.24 253	99.56 218	93.00 316	99.78 287	97.43 250	99.89 110	99.35 236

EPP-MVSNet		99.17 161	99.00 178	99.66 102	99.80 73	99.43 148	99.70 34	99.24 296	99.48 108	99.56 176	99.77 95	94.89 293	99.93 82	98.72 149	99.89 110	99.63 110

CLD-MVS		98.76 224	98.57 230	99.33 214	99.57 186	98.97 223	97.53 343	99.55 200	96.41 336	99.27 248	99.13 312	99.07 80	99.78 287	96.73 290	99.89 110	99.23 258
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ACMH	98.42 6	99.59 56	99.54 64	99.72 80	99.86 46	99.62 105	99.56 79	99.79 70	98.77 212	99.80 77	99.85 49	99.64 18	99.85 222	98.70 150	99.89 110	99.70 64
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testf1		99.63 46	99.60 49	99.72 80	99.94 16	99.95 2	99.47 95	99.89 27	99.43 123	99.88 48	99.80 71	99.26 56	99.90 142	98.81 139	99.88 119	99.32 242

APD_test2		99.63 46	99.60 49	99.72 80	99.94 16	99.95 2	99.47 95	99.89 27	99.43 123	99.88 48	99.80 71	99.26 56	99.90 142	98.81 139	99.88 119	99.32 242

GeoE		99.69 29	99.66 34	99.78 41	99.76 102	99.76 58	99.60 71	99.82 53	99.46 115	99.75 100	99.56 218	99.63 19	99.95 52	99.43 57	99.88 119	99.62 121

c3_l		98.72 230	98.71 216	98.72 296	99.12 314	97.22 322	97.68 336	99.56 194	98.90 195	99.54 183	99.48 243	96.37 277	99.73 306	97.88 207	99.88 119	99.21 262

VPA-MVSNet		99.66 40	99.62 42	99.79 38	99.68 148	99.75 62	99.62 61	99.69 121	99.85 34	99.80 77	99.81 67	98.81 106	99.91 124	99.47 53	99.88 119	99.70 64

MDA-MVSNet_test_wron		98.95 204	98.99 183	98.85 284	99.64 158	97.16 323	98.23 292	99.33 272	98.93 191	99.56 176	99.66 158	97.39 244	99.83 251	98.29 172	99.88 119	99.55 157

XVG-OURS		99.21 148	99.06 160	99.65 107	99.82 61	99.62 105	97.87 328	99.74 93	98.36 251	99.66 136	99.68 149	99.71 14	99.90 142	96.84 285	99.88 119	99.43 218

CDS-MVSNet		99.22 143	99.13 136	99.50 164	99.35 263	99.11 208	98.96 223	99.54 206	99.46 115	99.61 158	99.70 132	96.31 278	99.83 251	99.34 72	99.88 119	99.55 157
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS-MVSNet		99.03 186	98.85 203	99.55 153	99.80 73	99.25 188	99.73 26	99.15 308	99.37 130	99.61 158	99.71 125	94.73 296	99.81 275	97.70 229	99.88 119	99.58 147

USDC		98.96 201	98.93 191	99.05 262	99.54 199	97.99 294	97.07 361	99.80 64	98.21 268	99.75 100	99.77 95	98.43 165	99.64 347	97.90 205	99.88 119	99.51 184

ACMH+	98.40 8	99.50 69	99.43 83	99.71 85	99.86 46	99.76 58	99.32 123	99.77 78	99.53 104	99.77 91	99.76 99	99.26 56	99.78 287	97.77 218	99.88 119	99.60 135

mvsany_test1		99.44 85	99.45 78	99.40 193	99.37 258	98.64 254	97.90 327	99.59 177	99.27 141	99.92 29	99.82 62	99.74 12	99.93 82	99.55 43	99.87 130	99.63 110

SD-MVS		99.01 192	99.30 108	98.15 318	99.50 218	99.40 156	98.94 226	99.61 159	99.22 153	99.75 100	99.82 62	99.54 29	95.51 378	97.48 247	99.87 130	99.54 165
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
UniMVSNet (Re)		99.37 105	99.26 119	99.68 92	99.51 212	99.58 119	98.98 221	99.60 171	99.43 123	99.70 121	99.36 273	97.70 226	99.88 173	99.20 94	99.87 130	99.59 142

WR-MVS		99.11 173	98.93 191	99.66 102	99.30 283	99.42 151	98.42 281	99.37 265	99.04 179	99.57 169	99.20 308	96.89 262	99.86 205	98.66 154	99.87 130	99.70 64

NR-MVSNet		99.40 96	99.31 103	99.68 92	99.43 245	99.55 125	99.73 26	99.50 228	99.46 115	99.88 48	99.36 273	97.54 237	99.87 187	98.97 124	99.87 130	99.63 110

LPG-MVS_test		99.22 143	99.05 164	99.74 65	99.82 61	99.63 103	99.16 175	99.73 97	97.56 300	99.64 139	99.69 138	99.37 42	99.89 159	96.66 294	99.87 130	99.69 68

LGP-MVS_train				99.74 65	99.82 61	99.63 103		99.73 97	97.56 300	99.64 139	99.69 138	99.37 42	99.89 159	96.66 294	99.87 130	99.69 68

COLMAP_ROB	98.06 12	99.45 83	99.37 92	99.70 89	99.83 54	99.70 83	99.38 109	99.78 75	99.53 104	99.67 132	99.78 88	99.19 63	99.86 205	97.32 255	99.87 130	99.55 157
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test20.03		99.55 63	99.54 64	99.58 141	99.79 83	99.37 163	99.02 209	99.89 27	99.60 98	99.82 67	99.62 182	98.81 106	99.89 159	99.43 57	99.86 138	99.47 202

Baseline_NR-MVSNet		99.49 71	99.37 92	99.82 27	99.91 27	99.84 24	98.83 236	99.86 36	99.68 74	99.65 138	99.88 36	97.67 230	99.87 187	99.03 117	99.86 138	99.76 51

DROMVSNet		99.69 29	99.69 29	99.68 92	99.71 128	99.91 4	99.76 18	99.96 15	99.86 29	99.51 195	99.39 265	99.57 26	99.93 82	99.64 32	99.86 138	99.20 266

MSDG		99.08 177	98.98 186	99.37 204	99.60 167	99.13 206	97.54 341	99.74 93	98.84 204	99.53 188	99.55 225	99.10 73	99.79 284	97.07 273	99.86 138	99.18 271

EGC-MVSNET		89.05 343	85.52 346	99.64 114	99.89 34	99.78 47	99.56 79	99.52 220	24.19 377	49.96 378	99.83 55	99.15 67	99.92 102	97.71 226	99.85 142	99.21 262

Patchmatch-RL test		98.60 238	98.36 249	99.33 214	99.77 98	99.07 216	98.27 289	99.87 33	98.91 194	99.74 108	99.72 118	90.57 343	99.79 284	98.55 158	99.85 142	99.11 286

APDe-MVS		99.48 73	99.36 95	99.85 20	99.55 198	99.81 38	99.50 87	99.69 121	98.99 182	99.75 100	99.71 125	98.79 111	99.93 82	98.46 162	99.85 142	99.80 32

ACMP	97.51 14	99.05 182	98.84 205	99.67 95	99.78 90	99.55 125	98.88 229	99.66 132	97.11 326	99.47 201	99.60 199	99.07 80	99.89 159	96.18 317	99.85 142	99.58 147
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PMVS	92.94 21	98.82 219	98.81 209	98.85 284	99.84 50	97.99 294	99.20 161	99.47 236	99.71 64	99.42 213	99.82 62	98.09 200	99.47 365	93.88 359	99.85 142	99.07 300
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Anonymous20231206		99.35 110	99.31 103	99.47 171	99.74 119	99.06 218	99.28 139	99.74 93	99.23 149	99.72 113	99.53 229	97.63 236	99.88 173	99.11 112	99.84 147	99.48 198

HPM-MVS_fast		99.43 87	99.30 108	99.80 34	99.83 54	99.81 38	99.52 83	99.70 115	98.35 256	99.51 195	99.50 236	99.31 48	99.88 173	98.18 184	99.84 147	99.69 68

XVG-ACMP-BASELINE		99.23 135	99.10 151	99.63 121	99.82 61	99.58 119	98.83 236	99.72 106	98.36 251	99.60 161	99.71 125	98.92 96	99.91 124	97.08 272	99.84 147	99.40 223

new_pmnet		98.88 213	98.89 199	98.84 286	99.70 136	97.62 311	98.15 297	99.50 228	97.98 281	99.62 152	99.54 227	98.15 197	99.94 65	97.55 242	99.84 147	98.95 313

Test_1112_low_res		98.95 204	98.73 214	99.63 121	99.68 148	99.15 205	98.09 305	99.80 64	97.14 324	99.46 205	99.40 261	96.11 283	99.89 159	99.01 119	99.84 147	99.84 22

1112_ss		99.05 182	98.84 205	99.67 95	99.66 154	99.29 179	98.52 272	99.82 53	97.65 298	99.43 211	99.16 310	96.42 273	99.91 124	99.07 115	99.84 147	99.80 32

3Dnovator	99.15 2	99.43 87	99.36 95	99.65 107	99.39 253	99.42 151	99.70 34	99.56 194	99.23 149	99.35 229	99.80 71	99.17 65	99.95 52	98.21 179	99.84 147	99.59 142

LF4IMVS		99.01 192	98.92 195	99.27 229	99.71 128	99.28 181	98.59 260	99.77 78	98.32 262	99.39 225	99.41 257	98.62 135	99.84 236	96.62 298	99.84 147	98.69 331

ACMMP_NAP		99.28 124	99.11 143	99.79 38	99.75 113	99.81 38	98.95 224	99.53 215	98.27 265	99.53 188	99.73 111	98.75 118	99.87 187	97.70 229	99.83 155	99.68 74

AllTest		99.21 148	99.07 158	99.63 121	99.78 90	99.64 99	99.12 189	99.83 48	98.63 223	99.63 143	99.72 118	98.68 126	99.75 301	96.38 309	99.83 155	99.51 184

TestCases				99.63 121	99.78 90	99.64 99		99.83 48	98.63 223	99.63 143	99.72 118	98.68 126	99.75 301	96.38 309	99.83 155	99.51 184

PM-MVS		99.36 108	99.29 113	99.58 141	99.83 54	99.66 93	98.95 224	99.86 36	98.85 201	99.81 74	99.73 111	98.40 172	99.92 102	98.36 167	99.83 155	99.17 273

EPNet		98.13 278	97.77 293	99.18 244	94.57 380	97.99 294	99.24 151	97.96 352	99.74 57	97.29 362	99.62 182	93.13 313	99.97 23	98.59 156	99.83 155	99.58 147
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended		98.70 232	98.59 226	99.02 264	99.54 199	97.99 294	97.58 340	99.82 53	95.70 347	99.34 232	98.98 336	98.52 155	99.77 295	97.98 198	99.83 155	99.30 247

MVS-HIRNet		97.86 287	98.22 261	96.76 346	99.28 288	91.53 372	98.38 283	92.60 376	99.13 169	99.31 241	99.96 12	97.18 255	99.68 330	98.34 169	99.83 155	99.07 300

RPSCF		99.18 157	99.02 172	99.64 114	99.83 54	99.85 19	99.44 101	99.82 53	98.33 261	99.50 197	99.78 88	97.90 214	99.65 345	96.78 287	99.83 155	99.44 212

TinyColmap		98.97 198	98.93 191	99.07 260	99.46 238	98.19 280	97.75 332	99.75 88	98.79 209	99.54 183	99.70 132	98.97 92	99.62 349	96.63 297	99.83 155	99.41 222

test_vis1_rt		99.45 83	99.46 76	99.41 191	99.71 128	98.63 255	98.99 218	99.96 15	99.03 180	99.95 20	99.12 316	98.75 118	99.84 236	99.82 20	99.82 164	99.77 45

MP-MVS-pluss		99.14 166	98.92 195	99.80 34	99.83 54	99.83 29	98.61 257	99.63 149	96.84 331	99.44 207	99.58 206	98.81 106	99.91 124	97.70 229	99.82 164	99.67 80
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDA-MVSNet-bldmvs		99.06 179	99.05 164	99.07 260	99.80 73	97.83 304	98.89 228	99.72 106	99.29 137	99.63 143	99.70 132	96.47 271	99.89 159	98.17 186	99.82 164	99.50 189

jason		99.16 162	99.11 143	99.32 218	99.75 113	98.44 265	98.26 290	99.39 260	98.70 218	99.74 108	99.30 286	98.54 148	99.97 23	98.48 161	99.82 164	99.55 157
jason: jason.
HPM-MVS		99.25 131	99.07 158	99.78 41	99.81 68	99.75 62	99.61 66	99.67 128	97.72 295	99.35 229	99.25 297	99.23 59	99.92 102	97.21 268	99.82 164	99.67 80
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
114514_t		98.49 253	98.11 270	99.64 114	99.73 122	99.58 119	99.24 151	99.76 83	89.94 369	99.42 213	99.56 218	97.76 225	99.86 205	97.74 223	99.82 164	99.47 202

CP-MVS		99.23 135	99.05 164	99.75 60	99.66 154	99.66 93	99.38 109	99.62 152	98.38 249	99.06 280	99.27 292	98.79 111	99.94 65	97.51 246	99.82 164	99.66 89

PHI-MVS		99.11 173	98.95 190	99.59 138	99.13 312	99.59 115	99.17 171	99.65 141	97.88 288	99.25 250	99.46 250	98.97 92	99.80 281	97.26 262	99.82 164	99.37 230

wuyk23d		97.58 300	99.13 136	92.93 358	99.69 140	99.49 131	99.52 83	99.77 78	97.97 282	99.96 16	99.79 81	99.84 6	99.94 65	95.85 329	99.82 164	79.36 374

CVMVSNet		98.61 236	98.88 200	97.80 327	99.58 176	93.60 362	99.26 144	99.64 147	99.66 82	99.72 113	99.67 154	93.26 311	99.93 82	99.30 81	99.81 173	99.87 17

UniMVSNet_NR-MVSNet		99.37 105	99.25 121	99.72 80	99.47 234	99.56 122	98.97 222	99.61 159	99.43 123	99.67 132	99.28 290	97.85 219	99.95 52	99.17 100	99.81 173	99.65 97

DU-MVS		99.33 118	99.21 125	99.71 85	99.43 245	99.56 122	98.83 236	99.53 215	99.38 129	99.67 132	99.36 273	97.67 230	99.95 52	99.17 100	99.81 173	99.63 110

DeepPCF-MVS	98.42 6	99.18 157	99.02 172	99.67 95	99.22 297	99.75 62	97.25 355	99.47 236	98.72 217	99.66 136	99.70 132	99.29 50	99.63 348	98.07 192	99.81 173	99.62 121

ACMM	98.09 11	99.46 81	99.38 89	99.72 80	99.80 73	99.69 86	99.13 185	99.65 141	98.99 182	99.64 139	99.72 118	99.39 36	99.86 205	98.23 177	99.81 173	99.60 135
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ZNCC-MVS		99.22 143	99.04 169	99.77 44	99.76 102	99.73 70	99.28 139	99.56 194	98.19 270	99.14 269	99.29 289	98.84 105	99.92 102	97.53 245	99.80 178	99.64 105

test_0728_THIRD									99.18 156	99.62 152	99.61 191	98.58 142	99.91 124	97.72 224	99.80 178	99.77 45

SteuartSystems-ACMMP		99.30 122	99.14 134	99.76 51	99.87 43	99.66 93	99.18 166	99.60 171	98.55 231	99.57 169	99.67 154	99.03 85	99.94 65	97.01 274	99.80 178	99.69 68
Skip Steuart: Steuart Systems R&D Blog.
DP-MVS		99.48 73	99.39 87	99.74 65	99.57 186	99.62 105	99.29 137	99.61 159	99.87 26	99.74 108	99.76 99	98.69 125	99.87 187	98.20 180	99.80 178	99.75 54

PCF-MVS	96.03 18	96.73 319	95.86 330	99.33 214	99.44 242	99.16 203	96.87 364	99.44 244	86.58 371	98.95 286	99.40 261	94.38 299	99.88 173	87.93 370	99.80 178	98.95 313
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
SMA-MVS		99.19 153	99.00 178	99.73 74	99.46 238	99.73 70	99.13 185	99.52 220	97.40 311	99.57 169	99.64 165	98.93 95	99.83 251	97.61 239	99.79 183	99.63 110
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
MTAPA		99.35 110	99.20 126	99.80 34	99.81 68	99.81 38	99.33 121	99.53 215	99.27 141	99.42 213	99.63 175	98.21 192	99.95 52	97.83 217	99.79 183	99.65 97

ACMMP++															99.79 183

ACMMP		99.25 131	99.08 154	99.74 65	99.79 83	99.68 89	99.50 87	99.65 141	98.07 276	99.52 190	99.69 138	98.57 143	99.92 102	97.18 269	99.79 183	99.63 110
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
OMC-MVS		98.90 209	98.72 215	99.44 178	99.39 253	99.42 151	98.58 261	99.64 147	97.31 316	99.44 207	99.62 182	98.59 140	99.69 320	96.17 318	99.79 183	99.22 260

tfpnnormal		99.43 87	99.38 89	99.60 136	99.87 43	99.75 62	99.59 72	99.78 75	99.71 64	99.90 38	99.69 138	98.85 104	99.90 142	97.25 265	99.78 188	99.15 277

HQP_MVS		98.90 209	98.68 220	99.55 153	99.58 176	99.24 192	98.80 244	99.54 206	98.94 188	99.14 269	99.25 297	97.24 249	99.82 260	95.84 330	99.78 188	99.60 135

plane_prior5								99.54 206					99.82 260	95.84 330	99.78 188	99.60 135

mPP-MVS		99.19 153	99.00 178	99.76 51	99.76 102	99.68 89	99.38 109	99.54 206	98.34 260	99.01 282	99.50 236	98.53 152	99.93 82	97.18 269	99.78 188	99.66 89

OPM-MVS		99.26 130	99.13 136	99.63 121	99.70 136	99.61 111	98.58 261	99.48 233	98.50 237	99.52 190	99.63 175	99.14 70	99.76 297	97.89 206	99.77 192	99.51 184
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MVS_111021_LR		99.13 168	99.03 171	99.42 184	99.58 176	99.32 175	97.91 326	99.73 97	98.68 219	99.31 241	99.48 243	99.09 75	99.66 339	97.70 229	99.77 192	99.29 250

MIMVSNet		98.43 259	98.20 263	99.11 253	99.53 205	98.38 271	99.58 74	98.61 334	98.96 186	99.33 234	99.76 99	90.92 336	99.81 275	97.38 253	99.76 194	99.15 277

MVS_111021_HR		99.12 170	99.02 172	99.40 193	99.50 218	99.11 208	97.92 324	99.71 109	98.76 215	99.08 276	99.47 247	99.17 65	99.54 358	97.85 213	99.76 194	99.54 165

DPE-MVS		99.14 166	98.92 195	99.82 27	99.57 186	99.77 50	98.74 251	99.60 171	98.55 231	99.76 93	99.69 138	98.23 191	99.92 102	96.39 308	99.75 196	99.76 51
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + MP.		99.34 115	99.24 123	99.63 121	99.82 61	99.37 163	99.26 144	99.35 269	98.77 212	99.57 169	99.70 132	99.27 55	99.88 173	97.71 226	99.75 196	99.65 97
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HFP-MVS		99.25 131	99.08 154	99.76 51	99.73 122	99.70 83	99.31 128	99.59 177	98.36 251	99.36 228	99.37 269	98.80 110	99.91 124	97.43 250	99.75 196	99.68 74

ACMMPR		99.23 135	99.06 160	99.76 51	99.74 119	99.69 86	99.31 128	99.59 177	98.36 251	99.35 229	99.38 267	98.61 137	99.93 82	97.43 250	99.75 196	99.67 80

MP-MVS		99.06 179	98.83 207	99.76 51	99.76 102	99.71 76	99.32 123	99.50 228	98.35 256	98.97 284	99.48 243	98.37 174	99.92 102	95.95 327	99.75 196	99.63 110
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
QAPM		98.40 263	97.99 276	99.65 107	99.39 253	99.47 133	99.67 48	99.52 220	91.70 366	98.78 309	99.80 71	98.55 146	99.95 52	94.71 349	99.75 196	99.53 171

DeepC-MVS_fast	98.47 5	99.23 135	99.12 140	99.56 150	99.28 288	99.22 195	98.99 218	99.40 257	99.08 174	99.58 166	99.64 165	98.90 101	99.83 251	97.44 249	99.75 196	99.63 110
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
GST-MVS		99.16 162	98.96 189	99.75 60	99.73 122	99.73 70	99.20 161	99.55 200	98.22 267	99.32 237	99.35 278	98.65 133	99.91 124	96.86 282	99.74 203	99.62 121

region2R		99.23 135	99.05 164	99.77 44	99.76 102	99.70 83	99.31 128	99.59 177	98.41 245	99.32 237	99.36 273	98.73 122	99.93 82	97.29 257	99.74 203	99.67 80

PGM-MVS		99.20 150	99.01 175	99.77 44	99.75 113	99.71 76	99.16 175	99.72 106	97.99 280	99.42 213	99.60 199	98.81 106	99.93 82	96.91 279	99.74 203	99.66 89

TransMVSNet (Re)		99.78 16	99.77 20	99.81 30	99.91 27	99.85 19	99.75 21	99.86 36	99.70 69	99.91 32	99.89 31	99.60 24	99.87 187	99.59 35	99.74 203	99.71 61

TSAR-MVS + GP.		99.12 170	99.04 169	99.38 201	99.34 271	99.16 203	98.15 297	99.29 283	98.18 271	99.63 143	99.62 182	99.18 64	99.68 330	98.20 180	99.74 203	99.30 247

KD-MVS_self_test		99.63 46	99.59 51	99.76 51	99.84 50	99.90 7	99.37 113	99.79 70	99.83 40	99.88 48	99.85 49	98.42 167	99.90 142	99.60 34	99.73 208	99.49 194

XVS		99.27 128	99.11 143	99.75 60	99.71 128	99.71 76	99.37 113	99.61 159	99.29 137	98.76 310	99.47 247	98.47 159	99.88 173	97.62 237	99.73 208	99.67 80

X-MVStestdata		96.09 331	94.87 340	99.75 60	99.71 128	99.71 76	99.37 113	99.61 159	99.29 137	98.76 310	61.30 384	98.47 159	99.88 173	97.62 237	99.73 208	99.67 80

VDD-MVS		99.20 150	99.11 143	99.44 178	99.43 245	98.98 221	99.50 87	98.32 347	99.80 47	99.56 176	99.69 138	96.99 260	99.85 222	98.99 120	99.73 208	99.50 189

ab-mvs		99.33 118	99.28 115	99.47 171	99.57 186	99.39 158	99.78 11	99.43 247	98.87 199	99.57 169	99.82 62	98.06 203	99.87 187	98.69 152	99.73 208	99.15 277

TAPA-MVS	97.92 13	98.03 283	97.55 299	99.46 173	99.47 234	99.44 144	98.50 274	99.62 152	86.79 370	99.07 279	99.26 295	98.26 186	99.62 349	97.28 259	99.73 208	99.31 246
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DVP-MVS		99.32 120	99.17 129	99.77 44	99.69 140	99.80 42	99.14 179	99.31 278	99.16 163	99.62 152	99.61 191	98.35 176	99.91 124	97.88 207	99.72 214	99.61 131
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.83 25	99.70 136	99.79 44	99.14 179	99.61 159					99.92 102	97.88 207	99.72 214	99.77 45

3Dnovator+	98.92 3	99.35 110	99.24 123	99.67 95	99.35 263	99.47 133	99.62 61	99.50 228	99.44 118	99.12 272	99.78 88	98.77 115	99.94 65	97.87 210	99.72 214	99.62 121

plane_prior						99.24 192	98.42 281		97.87 289						99.71 217

APD-MVS		98.87 215	98.59 226	99.71 85	99.50 218	99.62 105	99.01 211	99.57 189	96.80 333	99.54 183	99.63 175	98.29 183	99.91 124	95.24 342	99.71 217	99.61 131
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
APD_test1		99.36 108	99.28 115	99.61 133	99.89 34	99.89 10	99.32 123	99.74 93	99.18 156	99.69 124	99.75 104	98.41 168	99.84 236	97.85 213	99.70 219	99.10 288

SED-MVS		99.40 96	99.28 115	99.77 44	99.69 140	99.82 35	99.20 161	99.54 206	99.13 169	99.82 67	99.63 175	98.91 98	99.92 102	97.85 213	99.70 219	99.58 147

IU-MVS					99.69 140	99.77 50		99.22 300	97.50 306	99.69 124				97.75 222	99.70 219	99.77 45

ambc				99.20 241	99.35 263	98.53 259	99.17 171	99.46 239		99.67 132	99.80 71	98.46 162	99.70 314	97.92 203	99.70 219	99.38 227

MSC_two_6792asdad				99.74 65	99.03 328	99.53 127		99.23 297					99.92 102	97.77 218	99.69 223	99.78 41

No_MVS				99.74 65	99.03 328	99.53 127		99.23 297					99.92 102	97.77 218	99.69 223	99.78 41

test_241102_TWO								99.54 206	99.13 169	99.76 93	99.63 175	98.32 182	99.92 102	97.85 213	99.69 223	99.75 54

MVSFormer		99.41 94	99.44 81	99.31 221	99.57 186	98.40 268	99.77 14	99.80 64	99.73 58	99.63 143	99.30 286	98.02 206	99.98 11	99.43 57	99.69 223	99.55 157

lupinMVS		98.96 201	98.87 201	99.24 237	99.57 186	98.40 268	98.12 301	99.18 305	98.28 264	99.63 143	99.13 312	98.02 206	99.97 23	98.22 178	99.69 223	99.35 236

SF-MVS		99.10 176	98.93 191	99.62 130	99.58 176	99.51 129	99.13 185	99.65 141	97.97 282	99.42 213	99.61 191	98.86 103	99.87 187	96.45 306	99.68 228	99.49 194

Anonymous20240529		99.42 90	99.34 97	99.65 107	99.53 205	99.60 113	99.63 60	99.39 260	99.47 112	99.76 93	99.78 88	98.13 198	99.86 205	98.70 150	99.68 228	99.49 194

MSLP-MVS++		99.05 182	99.09 152	98.91 276	99.21 299	98.36 272	98.82 240	99.47 236	98.85 201	98.90 294	99.56 218	98.78 113	99.09 371	98.57 157	99.68 228	99.26 252

DELS-MVS		99.34 115	99.30 108	99.48 169	99.51 212	99.36 167	98.12 301	99.53 215	99.36 132	99.41 219	99.61 191	99.22 60	99.87 187	99.21 91	99.68 228	99.20 266
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
PVSNet	97.47 15	98.42 260	98.44 241	98.35 310	99.46 238	96.26 339	96.70 366	99.34 271	97.68 297	99.00 283	99.13 312	97.40 242	99.72 308	97.59 241	99.68 228	99.08 295

LS3D		99.24 134	99.11 143	99.61 133	98.38 364	99.79 44	99.57 77	99.68 124	99.61 92	99.15 267	99.71 125	98.70 124	99.91 124	97.54 243	99.68 228	99.13 285

HQP3-MVS								99.37 265							99.67 234

CPTT-MVS		98.74 227	98.44 241	99.64 114	99.61 165	99.38 160	99.18 166	99.55 200	96.49 335	99.27 248	99.37 269	97.11 257	99.92 102	95.74 333	99.67 234	99.62 121

HQP-MVS		98.36 265	98.02 275	99.39 197	99.31 279	98.94 226	97.98 317	99.37 265	97.45 308	98.15 339	98.83 349	96.67 265	99.70 314	94.73 347	99.67 234	99.53 171

MVS_Test		99.28 124	99.31 103	99.19 242	99.35 263	98.79 240	99.36 116	99.49 232	99.17 161	99.21 259	99.67 154	98.78 113	99.66 339	99.09 113	99.66 237	99.10 288

CDPH-MVS		98.56 244	98.20 263	99.61 133	99.50 218	99.46 137	98.32 286	99.41 250	95.22 352	99.21 259	99.10 320	98.34 179	99.82 260	95.09 345	99.66 237	99.56 154

tttt0517		97.62 298	97.20 307	98.90 282	99.76 102	97.40 317	99.48 92	94.36 372	99.06 178	99.70 121	99.49 240	84.55 371	99.94 65	98.73 148	99.65 239	99.36 233

ITE_SJBPF				99.38 201	99.63 160	99.44 144		99.73 97	98.56 229	99.33 234	99.53 229	98.88 102	99.68 330	96.01 322	99.65 239	99.02 308

9.14			98.64 221		99.45 241		98.81 241	99.60 171	97.52 305	99.28 247	99.56 218	98.53 152	99.83 251	95.36 341	99.64 241

Patchmatch-test		98.10 280	97.98 278	98.48 305	99.27 290	96.48 336	99.40 105	99.07 312	98.81 206	99.23 254	99.57 215	90.11 348	99.87 187	96.69 291	99.64 241	99.09 292

sss		98.90 209	98.77 213	99.27 229	99.48 228	98.44 265	98.72 253	99.32 274	97.94 286	99.37 227	99.35 278	96.31 278	99.91 124	98.85 134	99.63 243	99.47 202

cl22		97.56 301	97.28 304	98.40 308	98.37 365	96.75 333	97.24 356	99.37 265	97.31 316	99.41 219	99.22 304	87.30 358	99.37 369	97.70 229	99.62 244	99.08 295

miper_ehance_all_eth		98.59 241	98.59 226	98.59 301	98.98 334	97.07 326	97.49 346	99.52 220	98.50 237	99.52 190	99.37 269	96.41 275	99.71 312	97.86 211	99.62 244	99.00 310

miper_enhance_ethall		98.03 283	97.94 284	98.32 312	98.27 367	96.43 338	96.95 362	99.41 250	96.37 338	99.43 211	98.96 340	94.74 295	99.69 320	97.71 226	99.62 244	98.83 324

SCA		98.11 279	98.36 249	97.36 337	99.20 302	92.99 364	98.17 296	98.49 341	98.24 266	99.10 275	99.57 215	96.01 285	99.94 65	96.86 282	99.62 244	99.14 282

MS-PatchMatch		99.00 194	98.97 187	99.09 256	99.11 319	98.19 280	98.76 250	99.33 272	98.49 239	99.44 207	99.58 206	98.21 192	99.69 320	98.20 180	99.62 244	99.39 225

APD-MVS_3200maxsize		99.31 121	99.16 130	99.74 65	99.53 205	99.75 62	99.27 142	99.61 159	99.19 155	99.57 169	99.64 165	98.76 116	99.90 142	97.29 257	99.62 244	99.56 154

EPNet_dtu		97.62 298	97.79 292	97.11 344	96.67 377	92.31 367	98.51 273	98.04 350	99.24 147	95.77 371	99.47 247	93.78 306	99.66 339	98.98 122	99.62 244	99.37 230
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SR-MVS-dyc-post		99.27 128	99.11 143	99.73 74	99.54 199	99.74 68	99.26 144	99.62 152	99.16 163	99.52 190	99.64 165	98.41 168	99.91 124	97.27 260	99.61 251	99.54 165

RE-MVS-def			99.13 136		99.54 199	99.74 68	99.26 144	99.62 152	99.16 163	99.52 190	99.64 165	98.57 143		97.27 260	99.61 251	99.54 165

MG-MVS		98.52 248	98.39 246	98.94 270	99.15 309	97.39 318	98.18 294	99.21 303	98.89 198	99.23 254	99.63 175	97.37 245	99.74 303	94.22 353	99.61 251	99.69 68

DVP-MVS++		99.38 102	99.25 121	99.77 44	99.03 328	99.77 50	99.74 23	99.61 159	99.18 156	99.76 93	99.61 191	99.00 86	99.92 102	97.72 224	99.60 254	99.62 121

PC_three_1452									97.56 300	99.68 127	99.41 257	99.09 75	97.09 376	96.66 294	99.60 254	99.62 121

OPU-MVS				99.29 224	99.12 314	99.44 144	99.20 161				99.40 261	99.00 86	98.84 373	96.54 300	99.60 254	99.58 147

HPM-MVS++		98.96 201	98.70 219	99.74 65	99.52 210	99.71 76	98.86 231	99.19 304	98.47 241	98.59 322	99.06 323	98.08 202	99.91 124	96.94 277	99.60 254	99.60 135

CNVR-MVS		98.99 197	98.80 211	99.56 150	99.25 293	99.43 148	98.54 270	99.27 287	98.58 228	98.80 306	99.43 255	98.53 152	99.70 314	97.22 267	99.59 258	99.54 165

Anonymous202405211		98.75 225	98.46 239	99.63 121	99.34 271	99.66 93	99.47 95	97.65 356	99.28 140	99.56 176	99.50 236	93.15 312	99.84 236	98.62 155	99.58 259	99.40 223

MVP-Stereo		99.16 162	99.08 154	99.43 182	99.48 228	99.07 216	99.08 200	99.55 200	98.63 223	99.31 241	99.68 149	98.19 194	99.78 287	98.18 184	99.58 259	99.45 207
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ADS-MVSNet2		97.78 291	97.66 298	98.12 320	99.14 310	95.36 350	99.22 158	98.75 327	96.97 327	98.25 335	99.64 165	90.90 337	99.94 65	96.51 302	99.56 261	99.08 295

ADS-MVSNet		97.72 296	97.67 297	97.86 325	99.14 310	94.65 356	99.22 158	98.86 321	96.97 327	98.25 335	99.64 165	90.90 337	99.84 236	96.51 302	99.56 261	99.08 295

LCM-MVSNet-Re		99.28 124	99.15 133	99.67 95	99.33 276	99.76 58	99.34 118	99.97 11	98.93 191	99.91 32	99.79 81	98.68 126	99.93 82	96.80 286	99.56 261	99.30 247

API-MVS		98.38 264	98.39 246	98.35 310	98.83 346	99.26 185	99.14 179	99.18 305	98.59 227	98.66 317	98.78 352	98.61 137	99.57 357	94.14 354	99.56 261	96.21 371

xiu_mvs_v1_base_debu		99.23 135	99.34 97	98.91 276	99.59 171	98.23 276	98.47 276	99.66 132	99.61 92	99.68 127	98.94 342	99.39 36	99.97 23	99.18 97	99.55 265	98.51 340

xiu_mvs_v1_base		99.23 135	99.34 97	98.91 276	99.59 171	98.23 276	98.47 276	99.66 132	99.61 92	99.68 127	98.94 342	99.39 36	99.97 23	99.18 97	99.55 265	98.51 340

xiu_mvs_v1_base_debi		99.23 135	99.34 97	98.91 276	99.59 171	98.23 276	98.47 276	99.66 132	99.61 92	99.68 127	98.94 342	99.39 36	99.97 23	99.18 97	99.55 265	98.51 340

OpenMVS	98.12 10	98.23 275	97.89 289	99.26 232	99.19 304	99.26 185	99.65 58	99.69 121	91.33 367	98.14 343	99.77 95	98.28 184	99.96 42	95.41 339	99.55 265	98.58 337

MVE	92.54 22	96.66 321	96.11 325	98.31 314	99.68 148	97.55 313	97.94 322	95.60 369	99.37 130	90.68 377	98.70 355	96.56 267	98.61 375	86.94 375	99.55 265	98.77 329
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SR-MVS		99.19 153	99.00 178	99.74 65	99.51 212	99.72 74	99.18 166	99.60 171	98.85 201	99.47 201	99.58 206	98.38 173	99.92 102	96.92 278	99.54 270	99.57 152

thisisatest0530		97.45 303	96.95 313	98.94 270	99.68 148	97.73 308	99.09 197	94.19 374	98.61 226	99.56 176	99.30 286	84.30 372	99.93 82	98.27 174	99.54 270	99.16 275

tt0805		99.63 46	99.57 58	99.81 30	99.87 43	99.88 12	99.58 74	98.70 329	99.72 62	99.91 32	99.60 199	99.43 34	99.81 275	99.81 21	99.53 272	99.73 56

MSP-MVS		99.04 185	98.79 212	99.81 30	99.78 90	99.73 70	99.35 117	99.57 189	98.54 234	99.54 183	98.99 333	96.81 264	99.93 82	96.97 276	99.53 272	99.77 45
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
AdaColmap		98.60 238	98.35 251	99.38 201	99.12 314	99.22 195	98.67 256	99.42 249	97.84 292	98.81 304	99.27 292	97.32 247	99.81 275	95.14 343	99.53 272	99.10 288

ETV-MVS		99.18 157	99.18 128	99.16 245	99.34 271	99.28 181	99.12 189	99.79 70	99.48 108	98.93 288	98.55 361	99.40 35	99.93 82	98.51 160	99.52 275	98.28 350

EIA-MVS		99.12 170	99.01 175	99.45 176	99.36 261	99.62 105	99.34 118	99.79 70	98.41 245	98.84 301	98.89 346	98.75 118	99.84 236	98.15 188	99.51 276	98.89 318

MCST-MVS		99.02 188	98.81 209	99.65 107	99.58 176	99.49 131	98.58 261	99.07 312	98.40 247	99.04 281	99.25 297	98.51 157	99.80 281	97.31 256	99.51 276	99.65 97

mvs_anonymous		99.28 124	99.39 87	98.94 270	99.19 304	97.81 305	99.02 209	99.55 200	99.78 52	99.85 59	99.80 71	98.24 187	99.86 205	99.57 40	99.50 278	99.15 277

CNLPA		98.57 243	98.34 252	99.28 226	99.18 306	99.10 213	98.34 284	99.41 250	98.48 240	98.52 326	98.98 336	97.05 258	99.78 287	95.59 335	99.50 278	98.96 311

ZD-MVS					99.43 245	99.61 111		99.43 247	96.38 337	99.11 273	99.07 322	97.86 217	99.92 102	94.04 356	99.49 280

test_prior2							97.95 321		97.87 289	98.05 345	99.05 324	97.90 214		95.99 324	99.49 280

pmmvs3		98.08 281	97.80 290	98.91 276	99.41 251	97.69 310	97.87 328	99.66 132	95.87 343	99.50 197	99.51 233	90.35 345	99.97 23	98.55 158	99.47 282	99.08 295

test12				99.54 157	99.29 285	99.33 173		99.16 307		98.43 330		97.54 237	99.82 260		99.47 282	99.48 198

agg_prior2														94.58 350	99.46 284	99.50 189

test9_res														95.10 344	99.44 285	99.50 189

train_agg		98.35 268	97.95 280	99.57 147	99.35 263	99.35 170	98.11 303	99.41 250	94.90 356	97.92 349	98.99 333	98.02 206	99.85 222	95.38 340	99.44 285	99.50 189

VPNet		99.46 81	99.37 92	99.71 85	99.82 61	99.59 115	99.48 92	99.70 115	99.81 44	99.69 124	99.58 206	97.66 234	99.86 205	99.17 100	99.44 285	99.67 80

DP-MVS Recon		98.50 251	98.23 259	99.31 221	99.49 223	99.46 137	98.56 266	99.63 149	94.86 358	98.85 300	99.37 269	97.81 221	99.59 355	96.08 319	99.44 285	98.88 319

LFMVS		98.46 256	98.19 266	99.26 232	99.24 295	98.52 261	99.62 61	96.94 363	99.87 26	99.31 241	99.58 206	91.04 334	99.81 275	98.68 153	99.42 289	99.45 207

Fast-Effi-MVS+		99.02 188	98.87 201	99.46 173	99.38 256	99.50 130	99.04 205	99.79 70	97.17 322	98.62 319	98.74 354	99.34 46	99.95 52	98.32 171	99.41 290	98.92 316

PatchmatchNet		97.65 297	97.80 290	97.18 342	98.82 349	92.49 366	99.17 171	98.39 345	98.12 272	98.79 307	99.58 206	90.71 341	99.89 159	97.23 266	99.41 290	99.16 275
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0515		96.98 313	96.42 320	98.66 299	99.42 250	97.47 314	97.27 354	94.30 373	97.24 318	99.15 267	98.86 348	85.01 369	99.87 187	97.10 271	99.39 292	98.63 332

原ACMM1				99.37 204	99.47 234	98.87 236		99.27 287	96.74 334	98.26 334	99.32 282	97.93 213	99.82 260	95.96 326	99.38 293	99.43 218

test222					99.51 212	99.08 215	97.83 330	99.29 283	95.21 353	98.68 316	99.31 284	97.28 248			99.38 293	99.43 218

F-COLMAP		98.74 227	98.45 240	99.62 130	99.57 186	99.47 133	98.84 234	99.65 141	96.31 339	98.93 288	99.19 309	97.68 229	99.87 187	96.52 301	99.37 295	99.53 171

DPM-MVS		98.28 270	97.94 284	99.32 218	99.36 261	99.11 208	97.31 353	98.78 326	96.88 329	98.84 301	99.11 319	97.77 224	99.61 353	94.03 357	99.36 296	99.23 258

旧先验1					99.49 223	99.29 179		99.26 290			99.39 265	97.67 230			99.36 296	99.46 206

PS-MVSNAJ		99.00 194	99.08 154	98.76 294	99.37 258	98.10 288	98.00 315	99.51 224	99.47 112	99.41 219	98.50 364	99.28 52	99.97 23	98.83 135	99.34 298	98.20 356

xiu_mvs_v2_base		99.02 188	99.11 143	98.77 293	99.37 258	98.09 289	98.13 300	99.51 224	99.47 112	99.42 213	98.54 362	99.38 40	99.97 23	98.83 135	99.33 299	98.24 352

新几何1				99.52 160	99.50 218	99.22 195		99.26 290	95.66 348	98.60 321	99.28 290	97.67 230	99.89 159	95.95 327	99.32 300	99.45 207

VDDNet		98.97 198	98.82 208	99.42 184	99.71 128	98.81 238	99.62 61	98.68 330	99.81 44	99.38 226	99.80 71	94.25 300	99.85 222	98.79 141	99.32 300	99.59 142

FA-MVS(test-final)		98.52 248	98.32 254	99.10 255	99.48 228	98.67 247	99.77 14	98.60 336	97.35 314	99.63 143	99.80 71	93.07 314	99.84 236	97.92 203	99.30 302	98.78 328

VNet		99.18 157	99.06 160	99.56 150	99.24 295	99.36 167	99.33 121	99.31 278	99.67 78	99.47 201	99.57 215	96.48 270	99.84 236	99.15 104	99.30 302	99.47 202

PatchMatch-RL		98.68 233	98.47 238	99.30 223	99.44 242	99.28 181	98.14 299	99.54 206	97.12 325	99.11 273	99.25 297	97.80 222	99.70 314	96.51 302	99.30 302	98.93 315

Effi-MVS+-dtu		99.07 178	98.92 195	99.52 160	98.89 341	99.78 47	99.15 177	99.66 132	99.34 133	98.92 291	99.24 302	97.69 228	99.98 11	98.11 190	99.28 305	98.81 325

testdata				99.42 184	99.51 212	98.93 229		99.30 281	96.20 340	98.87 298	99.40 261	98.33 181	99.89 159	96.29 312	99.28 305	99.44 212

OpenMVS_ROB	97.31 17	97.36 307	96.84 317	98.89 283	99.29 285	99.45 142	98.87 230	99.48 233	86.54 372	99.44 207	99.74 107	97.34 246	99.86 205	91.61 363	99.28 305	97.37 367

NCCC		98.82 219	98.57 230	99.58 141	99.21 299	99.31 176	98.61 257	99.25 293	98.65 221	98.43 330	99.26 295	97.86 217	99.81 275	96.55 299	99.27 308	99.61 131

testgi		99.29 123	99.26 119	99.37 204	99.75 113	98.81 238	98.84 234	99.89 27	98.38 249	99.75 100	99.04 326	99.36 45	99.86 205	99.08 114	99.25 309	99.45 207

PLC	97.35 16	98.36 265	97.99 276	99.48 169	99.32 278	99.24 192	98.50 274	99.51 224	95.19 354	98.58 323	98.96 340	96.95 261	99.83 251	95.63 334	99.25 309	99.37 230
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Fast-Effi-MVS+-dtu		99.20 150	99.12 140	99.43 182	99.25 293	99.69 86	99.05 203	99.82 53	99.50 106	98.97 284	99.05 324	98.98 90	99.98 11	98.20 180	99.24 311	98.62 333

PMMVS		98.49 253	98.29 257	99.11 253	98.96 335	98.42 267	97.54 341	99.32 274	97.53 304	98.47 329	98.15 370	97.88 216	99.82 260	97.46 248	99.24 311	99.09 292

EPMVS		96.53 323	96.32 321	97.17 343	98.18 370	92.97 365	99.39 107	89.95 380	98.21 268	98.61 320	99.59 204	86.69 367	99.72 308	96.99 275	99.23 313	98.81 325

alignmvs		98.28 270	97.96 279	99.25 235	99.12 314	98.93 229	99.03 208	98.42 343	99.64 86	98.72 313	97.85 373	90.86 339	99.62 349	98.88 133	99.13 314	99.19 269

FE-MVS		97.85 288	97.42 301	99.15 247	99.44 242	98.75 242	99.77 14	98.20 349	95.85 344	99.33 234	99.80 71	88.86 354	99.88 173	96.40 307	99.12 315	98.81 325

cascas		96.99 312	96.82 318	97.48 333	97.57 376	95.64 348	96.43 368	99.56 194	91.75 365	97.13 366	97.61 376	95.58 290	98.63 374	96.68 292	99.11 316	98.18 357

BH-RMVSNet		98.41 261	98.14 269	99.21 239	99.21 299	98.47 262	98.60 259	98.26 348	98.35 256	98.93 288	99.31 284	97.20 254	99.66 339	94.32 351	99.10 317	99.51 184

MAR-MVS		98.24 274	97.92 286	99.19 242	98.78 353	99.65 98	99.17 171	99.14 309	95.36 350	98.04 346	98.81 351	97.47 239	99.72 308	95.47 338	99.06 318	98.21 354
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
GA-MVS		97.99 286	97.68 296	98.93 273	99.52 210	98.04 293	97.19 357	99.05 315	98.32 262	98.81 304	98.97 338	89.89 351	99.41 368	98.33 170	99.05 319	99.34 238

EMVS		96.96 314	97.28 304	95.99 356	98.76 355	91.03 374	95.26 371	98.61 334	99.34 133	98.92 291	98.88 347	93.79 305	99.66 339	92.87 360	99.05 319	97.30 368

E-PMN		97.14 311	97.43 300	96.27 353	98.79 351	91.62 371	95.54 370	99.01 318	99.44 118	98.88 295	99.12 316	92.78 317	99.68 330	94.30 352	99.03 321	97.50 364

tpmrst		97.73 293	98.07 272	96.73 348	98.71 357	92.00 368	99.10 193	98.86 321	98.52 235	98.92 291	99.54 227	91.90 324	99.82 260	98.02 193	99.03 321	98.37 347

PatchT		98.45 258	98.32 254	98.83 288	98.94 336	98.29 274	99.24 151	98.82 324	99.84 37	99.08 276	99.76 99	91.37 329	99.94 65	98.82 137	99.00 323	98.26 351

CL-MVSNet_self_test		98.71 231	98.56 233	99.15 247	99.22 297	98.66 250	97.14 358	99.51 224	98.09 275	99.54 183	99.27 292	96.87 263	99.74 303	98.43 163	98.96 324	99.03 304

test_yl		98.25 272	97.95 280	99.13 251	99.17 307	98.47 262	99.00 213	98.67 332	98.97 184	99.22 257	99.02 331	91.31 330	99.69 320	97.26 262	98.93 325	99.24 255

DCV-MVSNet		98.25 272	97.95 280	99.13 251	99.17 307	98.47 262	99.00 213	98.67 332	98.97 184	99.22 257	99.02 331	91.31 330	99.69 320	97.26 262	98.93 325	99.24 255

canonicalmvs		99.02 188	99.00 178	99.09 256	99.10 320	98.70 246	99.61 66	99.66 132	99.63 88	98.64 318	97.65 375	99.04 84	99.54 358	98.79 141	98.92 327	99.04 303

MDTV_nov1_ep13			97.73 294		98.70 358	90.83 375	99.15 177	98.02 351	98.51 236	98.82 303	99.61 191	90.98 335	99.66 339	96.89 281	98.92 327

PAPM_NR		98.36 265	98.04 273	99.33 214	99.48 228	98.93 229	98.79 247	99.28 286	97.54 303	98.56 325	98.57 359	97.12 256	99.69 320	94.09 355	98.90 329	99.38 227

FPMVS		96.32 327	95.50 334	98.79 292	99.60 167	98.17 283	98.46 280	98.80 325	97.16 323	96.28 367	99.63 175	82.19 373	99.09 371	88.45 369	98.89 330	99.10 288

tpm cat1		96.78 317	96.98 312	96.16 355	98.85 344	90.59 378	99.08 200	99.32 274	92.37 364	97.73 359	99.46 250	91.15 333	99.69 320	96.07 320	98.80 331	98.21 354

test-LLR		97.15 309	96.95 313	97.74 330	98.18 370	95.02 353	97.38 349	96.10 364	98.00 278	97.81 355	98.58 357	90.04 349	99.91 124	97.69 235	98.78 332	98.31 348

test-mter		96.23 330	95.73 332	97.74 330	98.18 370	95.02 353	97.38 349	96.10 364	97.90 287	97.81 355	98.58 357	79.12 380	99.91 124	97.69 235	98.78 332	98.31 348

TESTMET0.1,1		96.24 329	95.84 331	97.41 336	98.24 368	93.84 361	97.38 349	95.84 368	98.43 242	97.81 355	98.56 360	79.77 377	99.89 159	97.77 218	98.77 334	98.52 339

CR-MVSNet		98.35 268	98.20 263	98.83 288	99.05 325	98.12 285	99.30 131	99.67 128	97.39 312	99.16 265	99.79 81	91.87 326	99.91 124	98.78 144	98.77 334	98.44 345

RPMNet		98.60 238	98.53 236	98.83 288	99.05 325	98.12 285	99.30 131	99.62 152	99.86 29	99.16 265	99.74 107	92.53 320	99.92 102	98.75 146	98.77 334	98.44 345

WTY-MVS		98.59 241	98.37 248	99.26 232	99.43 245	98.40 268	98.74 251	99.13 311	98.10 273	99.21 259	99.24 302	94.82 294	99.90 142	97.86 211	98.77 334	99.49 194

Effi-MVS+		99.06 179	98.97 187	99.34 211	99.31 279	98.98 221	98.31 287	99.91 22	98.81 206	98.79 307	98.94 342	99.14 70	99.84 236	98.79 141	98.74 338	99.20 266

PAPR		97.56 301	97.07 309	99.04 263	98.80 350	98.11 287	97.63 337	99.25 293	94.56 361	98.02 347	98.25 369	97.43 241	99.68 330	90.90 366	98.74 338	99.33 239

tpmvs		97.39 305	97.69 295	96.52 350	98.41 363	91.76 369	99.30 131	98.94 320	97.74 294	97.85 354	99.55 225	92.40 323	99.73 306	96.25 314	98.73 340	98.06 359

dp		96.86 315	97.07 309	96.24 354	98.68 359	90.30 379	99.19 165	98.38 346	97.35 314	98.23 337	99.59 204	87.23 359	99.82 260	96.27 313	98.73 340	98.59 335

XVG-OURS-SEG-HR		99.16 162	98.99 183	99.66 102	99.84 50	99.64 99	98.25 291	99.73 97	98.39 248	99.63 143	99.43 255	99.70 16	99.90 142	97.34 254	98.64 342	99.44 212

thres600view7		96.60 322	96.16 324	97.93 323	99.63 160	96.09 343	99.18 166	97.57 357	98.77 212	98.72 313	97.32 378	87.04 361	99.72 308	88.57 368	98.62 343	97.98 360

thres200		96.09 331	95.68 333	97.33 339	99.48 228	96.22 340	98.53 271	97.57 357	98.06 277	98.37 332	96.73 383	86.84 365	99.61 353	86.99 374	98.57 344	96.16 372

1314		98.00 285	97.90 288	98.27 316	98.90 338	97.45 316	99.30 131	99.06 314	94.98 355	97.21 364	99.12 316	98.43 165	99.67 335	95.58 336	98.56 345	97.71 363

thres100view900		96.39 325	96.03 327	97.47 334	99.63 160	95.93 344	99.18 166	97.57 357	98.75 216	98.70 315	97.31 379	87.04 361	99.67 335	87.62 371	98.51 346	96.81 369

tfpn200view9		96.30 328	95.89 328	97.53 332	99.58 176	96.11 341	99.00 213	97.54 360	98.43 242	98.52 326	96.98 381	86.85 363	99.67 335	87.62 371	98.51 346	96.81 369

thres400		96.40 324	95.89 328	97.92 324	99.58 176	96.11 341	99.00 213	97.54 360	98.43 242	98.52 326	96.98 381	86.85 363	99.67 335	87.62 371	98.51 346	97.98 360

MVS		95.72 338	94.63 342	98.99 265	98.56 361	97.98 300	99.30 131	98.86 321	72.71 375	97.30 361	99.08 321	98.34 179	99.74 303	89.21 367	98.33 349	99.26 252

BH-untuned		98.22 276	98.09 271	98.58 302	99.38 256	97.24 321	98.55 267	98.98 319	97.81 293	99.20 264	98.76 353	97.01 259	99.65 345	94.83 346	98.33 349	98.86 321

test_method		91.72 342	92.32 345	89.91 359	93.49 381	70.18 383	90.28 372	99.56 194	61.71 376	95.39 373	99.52 231	93.90 302	99.94 65	98.76 145	98.27 351	99.62 121

gg-mvs-nofinetune		95.87 335	95.17 339	97.97 322	98.19 369	96.95 328	99.69 41	89.23 381	99.89 20	96.24 369	99.94 16	81.19 374	99.51 363	93.99 358	98.20 352	97.44 365

HY-MVS	98.23 9	98.21 277	97.95 280	98.99 265	99.03 328	98.24 275	99.61 66	98.72 328	96.81 332	98.73 312	99.51 233	94.06 301	99.86 205	96.91 279	98.20 352	98.86 321

UnsupCasMVSNet_bld		98.55 245	98.27 258	99.40 193	99.56 197	99.37 163	97.97 320	99.68 124	97.49 307	99.08 276	99.35 278	95.41 291	99.82 260	97.70 229	98.19 354	99.01 309

tpm2		96.35 326	96.22 323	96.73 348	98.88 343	91.75 370	99.21 160	98.51 339	93.27 363	97.89 351	99.21 306	84.83 370	99.70 314	96.04 321	98.18 355	98.75 330

tmp_tt		95.75 337	95.42 335	96.76 346	89.90 382	94.42 357	98.86 231	97.87 355	78.01 373	99.30 246	99.69 138	97.70 226	95.89 377	99.29 84	98.14 356	99.95 6

baseline2		96.83 316	96.28 322	98.46 306	99.09 322	96.91 330	98.83 236	93.87 375	97.23 319	96.23 370	98.36 366	88.12 356	99.90 142	96.68 292	98.14 356	98.57 338

CostFormer		96.71 320	96.79 319	96.46 352	98.90 338	90.71 377	99.41 104	98.68 330	94.69 360	98.14 343	99.34 281	86.32 368	99.80 281	97.60 240	98.07 358	98.88 319

AUN-MVS		97.82 289	97.38 302	99.14 250	99.27 290	98.53 259	98.72 253	99.02 316	98.10 273	97.18 365	99.03 330	89.26 353	99.85 222	97.94 202	97.91 359	99.03 304

DeepMVS_CX				97.98 321	99.69 140	96.95 328		99.26 290	75.51 374	95.74 372	98.28 368	96.47 271	99.62 349	91.23 365	97.89 360	97.38 366

hse-mvs2		98.52 248	98.30 256	99.16 245	99.29 285	98.60 257	98.77 249	99.02 316	99.68 74	99.32 237	99.04 326	92.50 321	99.85 222	99.24 88	97.87 361	99.03 304

PAPM		95.61 339	94.71 341	98.31 314	99.12 314	96.63 334	96.66 367	98.46 342	90.77 368	96.25 368	98.68 356	93.01 315	99.69 320	81.60 376	97.86 362	98.62 333

JIA-IIPM		98.06 282	97.92 286	98.50 304	98.59 360	97.02 327	98.80 244	98.51 339	99.88 25	97.89 351	99.87 40	91.89 325	99.90 142	98.16 187	97.68 363	98.59 335

ET-MVSNet_ETH3D		96.78 317	96.07 326	98.91 276	99.26 292	97.92 302	97.70 335	96.05 367	97.96 285	92.37 376	98.43 365	87.06 360	99.90 142	98.27 174	97.56 364	98.91 317

TR-MVS		97.44 304	97.15 308	98.32 312	98.53 362	97.46 315	98.47 276	97.91 354	96.85 330	98.21 338	98.51 363	96.42 273	99.51 363	92.16 362	97.29 365	97.98 360

BH-w/o		97.20 308	97.01 311	97.76 328	99.08 323	95.69 347	98.03 312	98.52 338	95.76 346	97.96 348	98.02 371	95.62 289	99.47 365	92.82 361	97.25 366	98.12 358

KD-MVS_2432*1600		95.89 333	95.41 336	97.31 340	94.96 378	93.89 359	97.09 359	99.22 300	97.23 319	98.88 295	99.04 326	79.23 378	99.54 358	96.24 315	96.81 367	98.50 343

miper_refine_blended		95.89 333	95.41 336	97.31 340	94.96 378	93.89 359	97.09 359	99.22 300	97.23 319	98.88 295	99.04 326	79.23 378	99.54 358	96.24 315	96.81 367	98.50 343

UnsupCasMVSNet_eth		98.83 218	98.57 230	99.59 138	99.68 148	99.45 142	98.99 218	99.67 128	99.48 108	99.55 181	99.36 273	94.92 292	99.86 205	98.95 130	96.57 369	99.45 207

h-mvs33		98.61 236	98.34 252	99.44 178	99.60 167	98.67 247	99.27 142	99.44 244	99.68 74	99.32 237	99.49 240	92.50 321	100.00 1	99.24 88	96.51 370	99.65 97

GG-mvs-BLEND				97.36 337	97.59 374	96.87 331	99.70 34	88.49 382		94.64 375	97.26 380	80.66 375	99.12 370	91.50 364	96.50 371	96.08 373

tpm		97.15 309	96.95 313	97.75 329	98.91 337	94.24 358	99.32 123	97.96 352	97.71 296	98.29 333	99.32 282	86.72 366	99.92 102	98.10 191	96.24 372	99.09 292

test0.0.03 1		97.37 306	96.91 316	98.74 295	97.72 373	97.57 312	97.60 339	97.36 362	98.00 278	99.21 259	98.02 371	90.04 349	99.79 284	98.37 166	95.89 373	98.86 321

IB-MVS	95.41 20	95.30 340	94.46 344	97.84 326	98.76 355	95.33 351	97.33 352	96.07 366	96.02 342	95.37 374	97.41 377	76.17 382	99.96 42	97.54 243	95.44 374	98.22 353
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
baseline1		97.73 293	97.33 303	98.96 268	99.30 283	97.73 308	99.40 105	98.42 343	99.33 135	99.46 205	99.21 306	91.18 332	99.82 260	98.35 168	91.26 375	99.32 242

PVSNet_0	95.53 19	95.85 336	95.31 338	97.47 334	98.78 353	93.48 363	95.72 369	99.40 257	96.18 341	97.37 360	97.73 374	95.73 287	99.58 356	95.49 337	81.40 376	99.36 233

testmvs		28.94 345	33.33 347	15.79 361	26.03 383	9.81 385	96.77 365	15.67 384	11.55 379	23.87 380	50.74 387	19.03 384	8.53 380	23.21 378	33.07 377	29.03 376

test123		29.31 344	33.05 349	18.08 360	25.93 384	12.24 384	97.53 343	10.93 385	11.78 378	24.21 379	50.08 388	21.04 383	8.60 379	23.51 377	32.43 378	33.39 375

test_blank		8.33 348	11.11 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	100.00 1	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		8.33 348	11.11 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	100.00 1	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		8.33 348	11.11 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	100.00 1	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

cdsmvs_eth3d_5k		24.88 346	33.17 348	0.00 362	0.00 385	0.00 386	0.00 373	99.62 152	0.00 380	0.00 381	99.13 312	99.82 7	0.00 381	0.00 379	0.00 379	0.00 377

pcd_1.5k_mvsjas		16.61 347	22.14 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	100.00 1	99.28 52	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		8.33 348	11.11 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	100.00 1	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		8.33 348	11.11 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	100.00 1	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		8.33 348	11.11 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	100.00 1	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		8.33 348	11.11 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	100.00 1	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		8.26 356	11.02 359	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	99.16 310	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		8.33 348	11.11 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	100.00 1	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

FOURS1					99.83 54	99.89 10	99.74 23	99.71 109	99.69 72	99.63 143

test_one_0601					99.63 160	99.76 58		99.55 200	99.23 149	99.31 241	99.61 191	98.59 140

eth-test2					0.00 385

eth-test					0.00 385

test_241102_ONE					99.69 140	99.82 35		99.54 206	99.12 172	99.82 67	99.49 240	98.91 98	99.52 362

save fliter					99.53 205	99.25 188	98.29 288	99.38 264	99.07 176

test0726					99.69 140	99.80 42	99.24 151	99.57 189	99.16 163	99.73 112	99.65 163	98.35 176

GSMVS																99.14 282

test_part2					99.62 164	99.67 91				99.55 181

sam_mvs1												90.81 340				99.14 282

sam_mvs												90.52 344

MTGPA								99.53 215

test_post1							99.14 179				51.63 386	89.54 352	99.82 260	96.86 282

test_post											52.41 385	90.25 346	99.86 205

patchmatchnet-post											99.62 182	90.58 342	99.94 65

MTMP							99.09 197	98.59 337

gm-plane-assit					97.59 374	89.02 381			93.47 362		98.30 367		99.84 236	96.38 309

TEST9					99.35 263	99.35 170	98.11 303	99.41 250	94.83 359	97.92 349	98.99 333	98.02 206	99.85 222

test_8					99.34 271	99.31 176	98.08 307	99.40 257	94.90 356	97.87 353	98.97 338	98.02 206	99.84 236

agg_prior					99.35 263	99.36 167		99.39 260		97.76 358			99.85 222

test_prior4						99.19 201	98.00 315

test_prior				99.46 173	99.35 263	99.22 195		99.39 260					99.69 320			99.48 198

旧先验2							97.94 322		95.33 351	98.94 287			99.88 173	96.75 288

新几何2							98.04 311

无先验							98.01 313	99.23 297	95.83 345				99.85 222	95.79 332		99.44 212

原ACMM2							97.92 324

testdata2													99.89 159	95.99 324

segment_acmp												98.37 174

testdata1							97.72 333		97.86 291

plane_prior7					99.58 176	99.38 160

plane_prior6					99.47 234	99.26 185						97.24 249

plane_prior4											99.25 297

plane_prior3						99.31 176			98.36 251	99.14 269

plane_prior2							98.80 244		98.94 188

plane_prior1					99.51 212

n2								0.00 386

nn								0.00 386

door-mid								99.83 48

test11								99.29 283

door								99.77 78

HQP5-MVS						98.94 226

HQP-NCC					99.31 279		97.98 317		97.45 308	98.15 339

ACMP_Plane					99.31 279		97.98 317		97.45 308	98.15 339

BP-MVS														94.73 347

HQP4-MVS										98.15 339			99.70 314			99.53 171

HQP2-MVS												96.67 265

NP-MVS					99.40 252	99.13 206					98.83 349

MDTV_nov1_ep13_2view						91.44 373	99.14 179		97.37 313	99.21 259		91.78 328		96.75 288		99.03 304

Test By Simon												98.41 168

High-resolution multi-view benchmark