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 20	99.98 3	99.75 66	99.70 34	100.00 1	99.73 73	100.00 1	99.89 34	99.79 16	99.88 187	99.98 1	100.00 1	99.98 3

test_fmvs2		99.72 36	99.85 16	99.34 229	99.91 30	98.08 315	99.48 96	100.00 1	99.90 29	99.99 7	99.91 24	99.50 46	99.98 20	99.98 1	99.99 16	99.96 10

test_fmvs3		99.83 19	99.93 2	99.53 174	99.96 7	98.62 277	99.67 48	100.00 1	99.95 20	100.00 1	99.95 13	99.85 10	99.99 7	99.98 1	99.99 16	99.98 3

test_fmvsmconf0.01_n		99.89 3	99.88 6	99.91 2	99.98 3	99.76 60	99.12 196	100.00 1	100.00 1	99.99 7	99.91 24	99.98 1	100.00 1	99.97 4	100.00 1	99.99 1

test_vis1_n_1920		99.72 36	99.88 6	99.27 248	99.93 24	97.84 327	99.34 122	100.00 1	99.99 2	99.99 7	99.82 72	99.87 9	99.99 7	99.97 4	99.99 16	99.97 7

test_vis1_n		99.68 45	99.79 27	99.36 226	99.94 18	98.18 305	99.52 86	100.00 1	99.86 44	100.00 1	99.88 42	98.99 104	99.96 54	99.97 4	99.96 68	99.95 11

test_fmvs1_n		99.68 45	99.81 23	99.28 245	99.95 15	97.93 324	99.49 95	100.00 1	99.82 57	99.99 7	99.89 34	99.21 75	99.98 20	99.97 4	99.98 39	99.93 15

test_f		99.75 32	99.88 6	99.37 222	99.96 7	98.21 302	99.51 90	100.00 1	99.94 23	100.00 1	99.93 17	99.58 36	99.94 76	99.97 4	99.99 16	99.97 7

test_fmvsmconf0.1_n		99.87 8	99.86 12	99.91 2	99.97 6	99.74 72	99.01 226	99.99 10	99.99 2	99.98 13	99.88 42	99.97 2	99.99 7	99.96 9	100.00 1	99.98 3

test_fmvsmvis_n_1920		99.84 15	99.86 12	99.81 39	99.88 43	99.55 139	99.17 176	99.98 11	99.99 2	99.96 23	99.84 61	99.96 3	99.99 7	99.96 9	99.99 16	99.88 24

test_cas_vis1_n_1920		99.76 31	99.86 12	99.45 192	99.93 24	98.40 290	99.30 135	99.98 11	99.94 23	99.99 7	99.89 34	99.80 15	99.97 33	99.96 9	99.97 55	99.97 7

fmvsm_l_conf0.5_n		99.80 23	99.78 31	99.85 26	99.88 43	99.66 100	99.11 200	99.91 32	99.98 14	99.96 23	99.64 179	99.60 34	99.99 7	99.95 12	99.99 16	99.88 24

test_fmvsm_n_1920		99.84 15	99.85 16	99.83 32	99.82 71	99.70 89	99.17 176	99.97 18	99.99 2	99.96 23	99.82 72	99.94 4	100.00 1	99.95 12	100.00 1	99.80 46

test_fmvs1		99.48 86	99.65 50	98.97 290	99.54 215	97.16 350	99.11 200	99.98 11	99.78 66	99.96 23	99.81 78	98.72 139	99.97 33	99.95 12	99.97 55	99.79 53

mvsany_test3		99.85 11	99.88 6	99.75 73	99.95 15	99.37 181	99.53 85	99.98 11	99.77 70	99.99 7	99.95 13	99.85 10	99.94 76	99.95 12	99.98 39	99.94 13

fmvsm_l_conf0.5_n_a		99.80 23	99.79 27	99.84 29	99.88 43	99.64 110	99.12 196	99.91 32	99.98 14	99.95 31	99.67 165	99.67 27	99.99 7	99.94 16	99.99 16	99.88 24

MM		99.18 175	99.05 182	99.55 168	99.35 281	98.81 257	99.05 214	97.79 383	99.99 2	99.48 217	99.59 220	96.29 305	99.95 62	99.94 16	99.98 39	99.88 24

test_fmvsmconf_n		99.85 11	99.84 19	99.88 16	99.91 30	99.73 75	98.97 241	99.98 11	99.99 2	99.96 23	99.85 55	99.93 7	99.99 7	99.94 16	99.99 16	99.93 15

MVS_0304		99.17 180	99.03 190	99.59 152	99.44 259	98.90 251	99.04 217	95.32 400	99.99 2	99.68 140	99.57 230	98.30 198	99.97 33	99.94 16	99.98 39	99.88 24

fmvsm_s_conf0.1_n_a		99.85 11	99.83 20	99.91 2	99.95 15	99.82 34	99.10 203	99.98 11	99.99 2	99.98 13	99.91 24	99.68 26	99.93 93	99.93 20	99.99 16	99.99 1

fmvsm_s_conf0.1_n		99.86 9	99.85 16	99.89 10	99.93 24	99.78 48	99.07 213	99.98 11	99.99 2	99.98 13	99.90 29	99.88 8	99.92 115	99.93 20	99.99 16	99.98 3

fmvsm_s_conf0.5_n_a		99.82 21	99.79 27	99.89 10	99.85 57	99.82 34	99.03 221	99.96 23	99.99 2	99.97 19	99.84 61	99.58 36	99.93 93	99.92 22	99.98 39	99.93 15

fmvsm_s_conf0.5_n		99.83 19	99.81 23	99.87 20	99.85 57	99.78 48	99.03 221	99.96 23	99.99 2	99.97 19	99.84 61	99.78 17	99.92 115	99.92 22	99.99 16	99.92 18

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 18	99.99 2	100.00 1	99.98 10	99.78 17	100.00 1	99.92 22	100.00 1	99.87 29

v1921920		99.56 72	99.57 70	99.55 168	99.75 127	99.11 227	99.05 214	99.61 180	99.15 189	99.88 60	99.71 137	99.08 92	99.87 203	99.90 25	99.97 55	99.66 103

v1240		99.56 72	99.58 67	99.51 178	99.80 85	99.00 238	99.00 232	99.65 161	99.15 189	99.90 48	99.75 115	99.09 89	99.88 187	99.90 25	99.96 68	99.67 94

v10		99.69 42	99.69 43	99.66 115	99.81 79	99.39 176	99.66 52	99.75 104	99.60 117	99.92 41	99.87 47	98.75 134	99.86 224	99.90 25	99.99 16	99.73 70

v1192		99.57 69	99.57 70	99.57 162	99.77 112	99.22 213	99.04 217	99.60 191	99.18 178	99.87 68	99.72 129	99.08 92	99.85 242	99.89 28	99.98 39	99.66 103

v144192		99.55 75	99.54 76	99.58 156	99.78 104	99.20 219	99.11 200	99.62 173	99.18 178	99.89 52	99.72 129	98.66 147	99.87 203	99.88 29	99.97 55	99.66 103

v8		99.68 45	99.69 43	99.65 120	99.80 85	99.40 173	99.66 52	99.76 99	99.64 103	99.93 37	99.85 55	98.66 147	99.84 257	99.88 29	99.99 16	99.71 75

v1144		99.54 77	99.53 80	99.59 152	99.79 97	99.28 199	99.10 203	99.61 180	99.20 176	99.84 74	99.73 122	98.67 145	99.84 257	99.86 31	99.98 39	99.64 121

SSC-MVS		99.52 80	99.42 98	99.83 32	99.86 53	99.65 106	99.52 86	99.81 75	99.87 41	99.81 86	99.79 92	96.78 287	99.99 7	99.83 32	99.51 292	99.86 31

v7n		99.82 21	99.80 26	99.88 16	99.96 7	99.84 23	99.82 8	99.82 66	99.84 52	99.94 34	99.91 24	99.13 86	99.96 54	99.83 32	99.99 16	99.83 39

v2v482		99.50 82	99.47 84	99.58 156	99.78 104	99.25 206	99.14 186	99.58 206	99.25 166	99.81 86	99.62 197	98.24 203	99.84 257	99.83 32	99.97 55	99.64 121

test_vis1_rt		99.45 97	99.46 88	99.41 211	99.71 142	98.63 276	98.99 237	99.96 23	99.03 202	99.95 31	99.12 332	98.75 134	99.84 257	99.82 35	99.82 180	99.77 59

tt0805		99.63 58	99.57 70	99.81 39	99.87 50	99.88 12	99.58 76	98.70 350	99.72 79	99.91 44	99.60 215	99.43 48	99.81 296	99.81 36	99.53 288	99.73 70

V42		99.56 72	99.54 76	99.63 134	99.79 97	99.46 152	99.39 111	99.59 197	99.24 168	99.86 69	99.70 144	98.55 162	99.82 281	99.79 37	99.95 81	99.60 151

mvs_tets		99.90 2	99.90 3	99.90 7	99.96 7	99.79 45	99.72 29	99.88 43	99.92 27	99.98 13	99.93 17	99.94 4	99.98 20	99.77 38	100.00 1	99.92 18

WB-MVS		99.44 99	99.32 116	99.80 44	99.81 79	99.61 123	99.47 99	99.81 75	99.82 57	99.71 130	99.72 129	96.60 291	99.98 20	99.75 39	99.23 332	99.82 45

PS-MVSNAJss		99.84 15	99.82 22	99.89 10	99.96 7	99.77 53	99.68 44	99.85 53	99.95 20	99.98 13	99.92 21	99.28 66	99.98 20	99.75 39	100.00 1	99.94 13

jajsoiax		99.89 3	99.89 5	99.89 10	99.96 7	99.78 48	99.70 34	99.86 48	99.89 35	99.98 13	99.90 29	99.94 4	99.98 20	99.75 39	100.00 1	99.90 20

ANet_high		99.88 6	99.87 10	99.91 2	99.99 1	99.91 4	99.65 57	100.00 1	99.90 29	100.00 1	99.97 11	99.61 32	99.97 33	99.75 39	100.00 1	99.84 35

CS-MVS-test		99.68 45	99.70 39	99.64 127	99.57 201	99.83 28	99.78 12	99.97 18	99.92 27	99.50 214	99.38 283	99.57 38	99.95 62	99.69 43	99.90 115	99.15 295

CS-MVS		99.67 51	99.70 39	99.58 156	99.53 221	99.84 23	99.79 11	99.96 23	99.90 29	99.61 172	99.41 273	99.51 45	99.95 62	99.66 44	99.89 125	98.96 337

pmmvs6		99.86 9	99.86 12	99.83 32	99.94 18	99.90 7	99.83 6	99.91 32	99.85 49	99.94 34	99.95 13	99.73 21	99.90 155	99.65 45	99.97 55	99.69 82

MIMVSNet1		99.66 52	99.62 55	99.80 44	99.94 18	99.87 14	99.69 41	99.77 94	99.78 66	99.93 37	99.89 34	97.94 232	99.92 115	99.65 45	99.98 39	99.62 137

EC-MVSNet		99.69 42	99.69 43	99.68 105	99.71 142	99.91 4	99.76 18	99.96 23	99.86 44	99.51 212	99.39 281	99.57 38	99.93 93	99.64 47	99.86 154	99.20 284

K. test v3		98.87 237	98.60 246	99.69 103	99.93 24	99.46 152	99.74 23	94.97 401	99.78 66	99.88 60	99.88 42	93.66 334	99.97 33	99.61 48	99.95 81	99.64 121

KD-MVS_self_test		99.63 58	99.59 64	99.76 63	99.84 60	99.90 7	99.37 117	99.79 85	99.83 55	99.88 60	99.85 55	98.42 183	99.90 155	99.60 49	99.73 224	99.49 208

Anonymous20240521		99.44 99	99.42 98	99.49 181	99.89 38	98.96 244	99.62 62	99.76 99	99.85 49	99.82 79	99.88 42	96.39 301	99.97 33	99.59 50	99.98 39	99.55 173

TransMVSNet (Re)		99.78 27	99.77 33	99.81 39	99.91 30	99.85 18	99.75 21	99.86 48	99.70 86	99.91 44	99.89 34	99.60 34	99.87 203	99.59 50	99.74 219	99.71 75

OurMVSNet-221017-0		99.75 32	99.71 38	99.84 29	99.96 7	99.83 28	99.83 6	99.85 53	99.80 63	99.93 37	99.93 17	98.54 164	99.93 93	99.59 50	99.98 39	99.76 65

EU-MVSNet		99.39 115	99.62 55	98.72 321	99.88 43	96.44 364	99.56 81	99.85 53	99.90 29	99.90 48	99.85 55	98.09 219	99.83 272	99.58 53	99.95 81	99.90 20

mvsmamba		99.74 35	99.70 39	99.85 26	99.93 24	99.83 28	99.76 18	99.81 75	99.96 18	99.91 44	99.81 78	98.60 155	99.94 76	99.58 53	99.98 39	99.77 59

mvs_anonymous		99.28 141	99.39 101	98.94 294	99.19 324	97.81 329	99.02 224	99.55 219	99.78 66	99.85 71	99.80 82	98.24 203	99.86 224	99.57 55	99.50 295	99.15 295

test1111		97.74 315	98.16 289	96.49 383	99.60 182	89.86 413	99.71 33	91.21 409	99.89 35	99.88 60	99.87 47	93.73 333	99.90 155	99.56 56	99.99 16	99.70 78

lessismore_v0				99.64 127	99.86 53	99.38 178		90.66 410		99.89 52	99.83 65	94.56 324	99.97 33	99.56 56	99.92 104	99.57 168

mvsany_test1		99.44 99	99.45 90	99.40 213	99.37 276	98.64 275	97.90 359	99.59 197	99.27 162	99.92 41	99.82 72	99.74 20	99.93 93	99.55 58	99.87 146	99.63 126

pm-mvs1		99.79 26	99.79 27	99.78 53	99.91 30	99.83 28	99.76 18	99.87 45	99.73 73	99.89 52	99.87 47	99.63 29	99.87 203	99.54 59	99.92 104	99.63 126

LTVRE_ROB	99.19 1	99.88 6	99.87 10	99.88 16	99.91 30	99.90 7	99.96 1	99.92 29	99.90 29	99.97 19	99.87 47	99.81 14	99.95 62	99.54 59	99.99 16	99.80 46
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
DSMNet-mixed		99.48 86	99.65 50	98.95 293	99.71 142	97.27 347	99.50 91	99.82 66	99.59 119	99.41 238	99.85 55	99.62 31	100.00 1	99.53 61	99.89 125	99.59 158

test2506		94.73 373	94.59 374	95.15 389	99.59 186	85.90 415	99.75 21	74.01 417	99.89 35	99.71 130	99.86 53	79.00 406	99.90 155	99.52 62	99.99 16	99.65 111

UniMVSNet_ETH3D		99.85 11	99.83 20	99.90 7	99.89 38	99.91 4	99.89 4	99.71 126	99.93 25	99.95 31	99.89 34	99.71 22	99.96 54	99.51 63	99.97 55	99.84 35

FC-MVSNet-test		99.70 40	99.65 50	99.86 24	99.88 43	99.86 17	99.72 29	99.78 91	99.90 29	99.82 79	99.83 65	98.45 179	99.87 203	99.51 63	99.97 55	99.86 31

UA-Net		99.78 27	99.76 36	99.86 24	99.72 139	99.71 82	99.91 3	99.95 28	99.96 18	99.71 130	99.91 24	99.15 81	99.97 33	99.50 65	100.00 1	99.90 20

PMMVS2		99.48 86	99.45 90	99.57 162	99.76 116	98.99 239	98.09 334	99.90 37	98.95 210	99.78 99	99.58 223	99.57 38	99.93 93	99.48 66	99.95 81	99.79 53

VPA-MVSNet		99.66 52	99.62 55	99.79 50	99.68 163	99.75 66	99.62 62	99.69 138	99.85 49	99.80 90	99.81 78	98.81 122	99.91 137	99.47 67	99.88 135	99.70 78

ECVR-MVS		97.73 316	98.04 295	96.78 377	99.59 186	90.81 409	99.72 29	90.43 411	99.89 35	99.86 69	99.86 53	93.60 335	99.89 173	99.46 68	99.99 16	99.65 111

nrg030		99.70 40	99.66 48	99.82 36	99.76 116	99.84 23	99.61 67	99.70 131	99.93 25	99.78 99	99.68 161	99.10 87	99.78 309	99.45 69	99.96 68	99.83 39

TAMVS		99.49 84	99.45 90	99.63 134	99.48 244	99.42 166	99.45 103	99.57 208	99.66 99	99.78 99	99.83 65	97.85 239	99.86 224	99.44 70	99.96 68	99.61 147

GeoE		99.69 42	99.66 48	99.78 53	99.76 116	99.76 60	99.60 73	99.82 66	99.46 134	99.75 112	99.56 234	99.63 29	99.95 62	99.43 71	99.88 135	99.62 137

new-patchmatchnet		99.35 125	99.57 70	98.71 323	99.82 71	96.62 362	98.55 293	99.75 104	99.50 125	99.88 60	99.87 47	99.31 62	99.88 187	99.43 71	100.00 1	99.62 137

test20.03		99.55 75	99.54 76	99.58 156	99.79 97	99.37 181	99.02 224	99.89 39	99.60 117	99.82 79	99.62 197	98.81 122	99.89 173	99.43 71	99.86 154	99.47 216

MVSFormer		99.41 109	99.44 93	99.31 239	99.57 201	98.40 290	99.77 14	99.80 79	99.73 73	99.63 157	99.30 302	98.02 226	99.98 20	99.43 71	99.69 239	99.55 173

test_djsdf		99.84 15	99.81 23	99.91 2	99.94 18	99.84 23	99.77 14	99.80 79	99.73 73	99.97 19	99.92 21	99.77 19	99.98 20	99.43 71	100.00 1	99.90 20

SDMVSNet		99.77 30	99.77 33	99.76 63	99.80 85	99.65 106	99.63 59	99.86 48	99.97 16	99.89 52	99.89 34	99.52 44	99.99 7	99.42 76	99.96 68	99.65 111

Anonymous20231211		99.62 64	99.57 70	99.76 63	99.61 180	99.60 126	99.81 9	99.73 114	99.82 57	99.90 48	99.90 29	97.97 231	99.86 224	99.42 76	99.96 68	99.80 46

SixPastTwentyTwo		99.42 105	99.30 123	99.76 63	99.92 29	99.67 98	99.70 34	99.14 329	99.65 101	99.89 52	99.90 29	96.20 307	99.94 76	99.42 76	99.92 104	99.67 94

patch_mono-2		99.51 81	99.46 88	99.64 127	99.70 150	99.11 227	99.04 217	99.87 45	99.71 81	99.47 219	99.79 92	98.24 203	99.98 20	99.38 79	99.96 68	99.83 39

UGNet		99.38 117	99.34 111	99.49 181	98.90 363	98.90 251	99.70 34	99.35 289	99.86 44	98.57 347	99.81 78	98.50 174	99.93 93	99.38 79	99.98 39	99.66 103
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
XXY-MVS		99.71 39	99.67 47	99.81 39	99.89 38	99.72 80	99.59 74	99.82 66	99.39 147	99.82 79	99.84 61	99.38 54	99.91 137	99.38 79	99.93 99	99.80 46

FIs		99.65 57	99.58 67	99.84 29	99.84 60	99.85 18	99.66 52	99.75 104	99.86 44	99.74 120	99.79 92	98.27 201	99.85 242	99.37 82	99.93 99	99.83 39

sd_testset		99.78 27	99.78 31	99.80 44	99.80 85	99.76 60	99.80 10	99.79 85	99.97 16	99.89 52	99.89 34	99.53 43	99.99 7	99.36 83	99.96 68	99.65 111

anonymousdsp		99.80 23	99.77 33	99.90 7	99.96 7	99.88 12	99.73 26	99.85 53	99.70 86	99.92 41	99.93 17	99.45 47	99.97 33	99.36 83	100.00 1	99.85 34

casdiffmvs_mvg		99.68 45	99.68 46	99.69 103	99.81 79	99.59 128	99.29 142	99.90 37	99.71 81	99.79 95	99.73 122	99.54 41	99.84 257	99.36 83	99.96 68	99.65 111
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		99.75 32	99.74 37	99.79 50	99.88 43	99.66 100	99.69 41	99.92 29	99.67 95	99.77 105	99.75 115	99.61 32	99.98 20	99.35 86	99.98 39	99.72 72
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 66	99.64 53	99.53 174	99.79 97	98.82 256	99.58 76	99.97 18	99.95 20	99.96 23	99.76 110	98.44 180	99.99 7	99.34 87	99.96 68	99.78 55

CHOSEN 1792x2688		99.39 115	99.30 123	99.65 120	99.88 43	99.25 206	98.78 269	99.88 43	98.66 249	99.96 23	99.79 92	97.45 261	99.93 93	99.34 87	99.99 16	99.78 55

CDS-MVSNet		99.22 161	99.13 154	99.50 180	99.35 281	99.11 227	98.96 243	99.54 225	99.46 134	99.61 172	99.70 144	96.31 303	99.83 272	99.34 87	99.88 135	99.55 173
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 217	99.16 147	98.51 330	99.75 127	95.90 374	98.07 337	99.84 59	99.84 52	99.89 52	99.73 122	96.01 310	99.99 7	99.33 90	100.00 1	99.63 126

HyFIR lowres test		98.91 230	98.64 243	99.73 87	99.85 57	99.47 148	98.07 337	99.83 61	98.64 251	99.89 52	99.60 215	92.57 344	100.00 1	99.33 90	99.97 55	99.72 72

pmmvs5		99.19 171	99.11 161	99.42 204	99.76 116	98.88 253	98.55 293	99.73 114	98.82 229	99.72 125	99.62 197	96.56 292	99.82 281	99.32 92	99.95 81	99.56 170

v148		99.40 111	99.41 100	99.39 216	99.76 116	98.94 245	99.09 207	99.59 197	99.17 183	99.81 86	99.61 207	98.41 184	99.69 344	99.32 92	99.94 92	99.53 186

baseline		99.63 58	99.62 55	99.66 115	99.80 85	99.62 117	99.44 105	99.80 79	99.71 81	99.72 125	99.69 150	99.15 81	99.83 272	99.32 92	99.94 92	99.53 186

CVMVSNet		98.61 258	98.88 223	97.80 358	99.58 191	93.60 395	99.26 149	99.64 167	99.66 99	99.72 125	99.67 165	93.26 337	99.93 93	99.30 95	99.81 189	99.87 29

PS-CasMVS		99.66 52	99.58 67	99.89 10	99.80 85	99.85 18	99.66 52	99.73 114	99.62 108	99.84 74	99.71 137	98.62 151	99.96 54	99.30 95	99.96 68	99.86 31

DTE-MVSNet		99.68 45	99.61 59	99.88 16	99.80 85	99.87 14	99.67 48	99.71 126	99.72 79	99.84 74	99.78 100	98.67 145	99.97 33	99.30 95	99.95 81	99.80 46

tmp_tt		95.75 367	95.42 361	96.76 378	89.90 416	94.42 389	98.86 252	97.87 382	78.01 407	99.30 265	99.69 150	97.70 247	95.89 409	99.29 98	98.14 386	99.95 11

PEN-MVS		99.66 52	99.59 64	99.89 10	99.83 64	99.87 14	99.66 52	99.73 114	99.70 86	99.84 74	99.73 122	98.56 161	99.96 54	99.29 98	99.94 92	99.83 39

WR-MVS_H		99.61 66	99.53 80	99.87 20	99.80 85	99.83 28	99.67 48	99.75 104	99.58 120	99.85 71	99.69 150	98.18 213	99.94 76	99.28 100	99.95 81	99.83 39

IterMVS		98.97 221	99.16 147	98.42 334	99.74 133	95.64 377	98.06 339	99.83 61	99.83 55	99.85 71	99.74 118	96.10 309	99.99 7	99.27 101	100.00 1	99.63 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs33		98.61 258	98.34 274	99.44 197	99.60 182	98.67 268	99.27 147	99.44 264	99.68 91	99.32 256	99.49 256	92.50 347	100.00 1	99.24 102	96.51 403	99.65 111

hse-mvs2		98.52 270	98.30 278	99.16 265	99.29 303	98.60 278	98.77 270	99.02 337	99.68 91	99.32 256	99.04 343	92.50 347	99.85 242	99.24 102	97.87 393	99.03 328

FMVSNet1		99.66 52	99.63 54	99.73 87	99.78 104	99.77 53	99.68 44	99.70 131	99.67 95	99.82 79	99.83 65	98.98 106	99.90 155	99.24 102	99.97 55	99.53 186

casdiffmvs		99.63 58	99.61 59	99.67 108	99.79 97	99.59 128	99.13 192	99.85 53	99.79 65	99.76 107	99.72 129	99.33 61	99.82 281	99.21 105	99.94 92	99.59 158
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CP-MVSNet		99.54 77	99.43 95	99.87 20	99.76 116	99.82 34	99.57 79	99.61 180	99.54 121	99.80 90	99.64 179	97.79 243	99.95 62	99.21 105	99.94 92	99.84 35

DELS-MVS		99.34 130	99.30 123	99.48 185	99.51 228	99.36 185	98.12 330	99.53 234	99.36 152	99.41 238	99.61 207	99.22 74	99.87 203	99.21 105	99.68 244	99.20 284
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
iter_conf05		99.48 86	99.43 95	99.63 134	99.70 150	99.65 106	99.01 226	99.75 104	99.73 73	99.78 99	99.62 197	98.05 223	99.88 187	99.20 108	99.98 39	99.37 244

UniMVSNet (Re)		99.37 120	99.26 136	99.68 105	99.51 228	99.58 132	98.98 240	99.60 191	99.43 142	99.70 134	99.36 289	97.70 247	99.88 187	99.20 108	99.87 146	99.59 158

CANet		99.11 193	99.05 182	99.28 245	98.83 370	98.56 280	98.71 276	99.41 270	99.25 166	99.23 273	99.22 320	97.66 255	99.94 76	99.19 110	99.97 55	99.33 255

EI-MVSNet-UG-set		99.48 86	99.50 82	99.42 204	99.57 201	98.65 274	99.24 156	99.46 258	99.68 91	99.80 90	99.66 171	98.99 104	99.89 173	99.19 110	99.90 115	99.72 72

xiu_mvs_v1_base_debu		99.23 153	99.34 111	98.91 300	99.59 186	98.23 299	98.47 303	99.66 151	99.61 111	99.68 140	98.94 360	99.39 50	99.97 33	99.18 112	99.55 281	98.51 373

xiu_mvs_v1_base		99.23 153	99.34 111	98.91 300	99.59 186	98.23 299	98.47 303	99.66 151	99.61 111	99.68 140	98.94 360	99.39 50	99.97 33	99.18 112	99.55 281	98.51 373

xiu_mvs_v1_base_debi		99.23 153	99.34 111	98.91 300	99.59 186	98.23 299	98.47 303	99.66 151	99.61 111	99.68 140	98.94 360	99.39 50	99.97 33	99.18 112	99.55 281	98.51 373

VPNet		99.46 95	99.37 106	99.71 98	99.82 71	99.59 128	99.48 96	99.70 131	99.81 60	99.69 137	99.58 223	97.66 255	99.86 224	99.17 115	99.44 302	99.67 94

UniMVSNet_NR-MVSNet		99.37 120	99.25 138	99.72 93	99.47 250	99.56 136	98.97 241	99.61 180	99.43 142	99.67 146	99.28 306	97.85 239	99.95 62	99.17 115	99.81 189	99.65 111

DU-MVS		99.33 134	99.21 142	99.71 98	99.43 263	99.56 136	98.83 257	99.53 234	99.38 148	99.67 146	99.36 289	97.67 251	99.95 62	99.17 115	99.81 189	99.63 126

EI-MVSNet-Vis-set		99.47 94	99.49 83	99.42 204	99.57 201	98.66 271	99.24 156	99.46 258	99.67 95	99.79 95	99.65 176	98.97 108	99.89 173	99.15 118	99.89 125	99.71 75

EI-MVSNet		99.38 117	99.44 93	99.21 258	99.58 191	98.09 312	99.26 149	99.46 258	99.62 108	99.75 112	99.67 165	98.54 164	99.85 242	99.15 118	99.92 104	99.68 88

VNet		99.18 175	99.06 178	99.56 165	99.24 314	99.36 185	99.33 125	99.31 298	99.67 95	99.47 219	99.57 230	96.48 295	99.84 257	99.15 118	99.30 321	99.47 216

EG-PatchMatch MVS		99.57 69	99.56 75	99.62 144	99.77 112	99.33 191	99.26 149	99.76 99	99.32 156	99.80 90	99.78 100	99.29 64	99.87 203	99.15 118	99.91 114	99.66 103

PVSNet_Blended_VisFu		99.40 111	99.38 103	99.44 197	99.90 36	98.66 271	98.94 246	99.91 32	97.97 312	99.79 95	99.73 122	99.05 98	99.97 33	99.15 118	99.99 16	99.68 88

IterMVS-LS		99.41 109	99.47 84	99.25 254	99.81 79	98.09 312	98.85 254	99.76 99	99.62 108	99.83 78	99.64 179	98.54 164	99.97 33	99.15 118	99.99 16	99.68 88
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 77	99.47 84	99.76 63	99.58 191	99.64 110	99.30 135	99.63 169	99.61 111	99.71 130	99.56 234	98.76 132	99.96 54	99.14 124	99.92 104	99.68 88

MVSTER		98.47 277	98.22 282	99.24 256	99.06 350	98.35 296	99.08 210	99.46 258	99.27 162	99.75 112	99.66 171	88.61 380	99.85 242	99.14 124	99.92 104	99.52 196

Anonymous20231206		99.35 125	99.31 118	99.47 187	99.74 133	99.06 237	99.28 144	99.74 110	99.23 170	99.72 125	99.53 245	97.63 257	99.88 187	99.11 126	99.84 163	99.48 212

Syy-MVS		98.17 300	97.85 312	99.15 267	98.50 393	98.79 260	98.60 282	99.21 321	97.89 318	96.76 394	96.37 415	95.47 316	99.57 383	99.10 127	98.73 364	99.09 310

MVS_Test		99.28 141	99.31 118	99.19 261	99.35 281	98.79 260	99.36 120	99.49 251	99.17 183	99.21 278	99.67 165	98.78 129	99.66 365	99.09 128	99.66 253	99.10 306

testgi		99.29 140	99.26 136	99.37 222	99.75 127	98.81 257	98.84 255	99.89 39	98.38 279	99.75 112	99.04 343	99.36 59	99.86 224	99.08 129	99.25 328	99.45 221

1112_ss		99.05 202	98.84 228	99.67 108	99.66 169	99.29 197	98.52 299	99.82 66	97.65 330	99.43 230	99.16 326	96.42 298	99.91 137	99.07 130	99.84 163	99.80 46

CANet_DTU		98.91 230	98.85 226	99.09 276	98.79 376	98.13 307	98.18 323	99.31 298	99.48 127	98.86 318	99.51 249	96.56 292	99.95 62	99.05 131	99.95 81	99.19 287

MVSMamba_pp		99.32 136	99.28 131	99.44 197	99.10 343	99.41 171	99.01 226	99.68 141	99.37 149	99.58 180	99.67 165	98.11 218	99.87 203	99.04 132	99.92 104	99.05 324

Baseline_NR-MVSNet		99.49 84	99.37 106	99.82 36	99.91 30	99.84 23	98.83 257	99.86 48	99.68 91	99.65 152	99.88 42	97.67 251	99.87 203	99.03 133	99.86 154	99.76 65

FMVSNet2		99.35 125	99.28 131	99.55 168	99.49 239	99.35 188	99.45 103	99.57 208	99.44 137	99.70 134	99.74 118	97.21 272	99.87 203	99.03 133	99.94 92	99.44 226

Test_1112_low_res		98.95 227	98.73 237	99.63 134	99.68 163	99.15 224	98.09 334	99.80 79	97.14 356	99.46 223	99.40 277	96.11 308	99.89 173	99.01 135	99.84 163	99.84 35

VDD-MVS		99.20 168	99.11 161	99.44 197	99.43 263	98.98 240	99.50 91	98.32 372	99.80 63	99.56 191	99.69 150	96.99 282	99.85 242	98.99 136	99.73 224	99.50 203

DeepC-MVS	98.90 4	99.62 64	99.61 59	99.67 108	99.72 139	99.44 159	99.24 156	99.71 126	99.27 162	99.93 37	99.90 29	99.70 24	99.93 93	98.99 136	99.99 16	99.64 121
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
pmmvs-eth3d		99.48 86	99.47 84	99.51 178	99.77 112	99.41 171	98.81 262	99.66 151	99.42 146	99.75 112	99.66 171	99.20 76	99.76 319	98.98 138	99.99 16	99.36 248

EPNet_dtu		97.62 321	97.79 315	97.11 376	96.67 411	92.31 400	98.51 300	98.04 376	99.24 168	95.77 403	99.47 263	93.78 332	99.66 365	98.98 138	99.62 260	99.37 244
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 130	99.32 116	99.39 216	99.67 168	98.77 262	98.57 291	99.81 75	99.61 111	99.48 217	99.41 273	98.47 175	99.86 224	98.97 140	99.90 115	99.53 186
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NR-MVSNet		99.40 111	99.31 118	99.68 105	99.43 263	99.55 139	99.73 26	99.50 247	99.46 134	99.88 60	99.36 289	97.54 258	99.87 203	98.97 140	99.87 146	99.63 126

bld_raw_dy_0_64		99.24 151	99.16 147	99.45 192	99.26 310	99.58 132	98.06 339	99.63 169	99.77 70	99.54 199	99.12 332	98.18 213	99.88 187	98.96 142	99.93 99	98.90 345

mamv4		99.34 130	99.30 123	99.45 192	99.13 333	99.40 173	99.01 226	99.70 131	99.73 73	99.56 191	99.65 176	98.04 224	99.87 203	98.96 142	99.90 115	99.09 310

GBi-Net		99.42 105	99.31 118	99.73 87	99.49 239	99.77 53	99.68 44	99.70 131	99.44 137	99.62 166	99.83 65	97.21 272	99.90 155	98.96 142	99.90 115	99.53 186

FMVSNet5		97.80 313	97.25 329	99.42 204	98.83 370	98.97 242	99.38 113	99.80 79	98.87 222	99.25 269	99.69 150	80.60 400	99.91 137	98.96 142	99.90 115	99.38 241

test1		99.42 105	99.31 118	99.73 87	99.49 239	99.77 53	99.68 44	99.70 131	99.44 137	99.62 166	99.83 65	97.21 272	99.90 155	98.96 142	99.90 115	99.53 186

FMVSNet3		98.80 243	98.63 245	99.32 236	99.13 333	98.72 265	99.10 203	99.48 252	99.23 170	99.62 166	99.64 179	92.57 344	99.86 224	98.96 142	99.90 115	99.39 239

UnsupCasMVSNet_eth		98.83 240	98.57 252	99.59 152	99.68 163	99.45 157	98.99 237	99.67 146	99.48 127	99.55 197	99.36 289	94.92 318	99.86 224	98.95 148	96.57 402	99.45 221

CHOSEN 280x420		98.41 282	98.41 266	98.40 335	99.34 290	95.89 375	96.94 395	99.44 264	98.80 233	99.25 269	99.52 247	93.51 336	99.98 20	98.94 149	99.98 39	99.32 258

TDRefinement		99.72 36	99.70 39	99.77 56	99.90 36	99.85 18	99.86 5	99.92 29	99.69 89	99.78 99	99.92 21	99.37 56	99.88 187	98.93 150	99.95 81	99.60 151

alignmvs		98.28 292	97.96 301	99.25 254	99.12 336	98.93 248	99.03 221	98.42 366	99.64 103	98.72 333	97.85 396	90.86 365	99.62 375	98.88 151	99.13 334	99.19 287

MGCFI-Net		99.02 209	99.01 195	99.06 283	99.11 341	98.60 278	99.63 59	99.67 146	99.63 105	98.58 345	97.65 399	99.07 94	99.57 383	98.85 152	98.92 349	99.03 328

sss		98.90 232	98.77 236	99.27 248	99.48 244	98.44 287	98.72 274	99.32 294	97.94 316	99.37 246	99.35 294	96.31 303	99.91 137	98.85 152	99.63 259	99.47 216

xiu_mvs_v2_base		99.02 209	99.11 161	98.77 318	99.37 276	98.09 312	98.13 329	99.51 243	99.47 131	99.42 232	98.54 382	99.38 54	99.97 33	98.83 154	99.33 317	98.24 386

PS-MVSNAJ		99.00 217	99.08 172	98.76 319	99.37 276	98.10 311	98.00 346	99.51 243	99.47 131	99.41 238	98.50 384	99.28 66	99.97 33	98.83 154	99.34 316	98.20 390

D2MVS		99.22 161	99.19 144	99.29 243	99.69 155	98.74 264	98.81 262	99.41 270	98.55 260	99.68 140	99.69 150	98.13 216	99.87 203	98.82 156	99.98 39	99.24 273

PatchT		98.45 279	98.32 276	98.83 313	98.94 361	98.29 297	99.24 156	98.82 345	99.84 52	99.08 295	99.76 110	91.37 355	99.94 76	98.82 156	99.00 344	98.26 385

testf1		99.63 58	99.60 62	99.72 93	99.94 18	99.95 2	99.47 99	99.89 39	99.43 142	99.88 60	99.80 82	99.26 70	99.90 155	98.81 158	99.88 135	99.32 258

APD_test2		99.63 58	99.60 62	99.72 93	99.94 18	99.95 2	99.47 99	99.89 39	99.43 142	99.88 60	99.80 82	99.26 70	99.90 155	98.81 158	99.88 135	99.32 258

sasdasda		99.02 209	99.00 199	99.09 276	99.10 343	98.70 266	99.61 67	99.66 151	99.63 105	98.64 339	97.65 399	99.04 99	99.54 387	98.79 160	98.92 349	99.04 326

Effi-MVS+		99.06 199	98.97 210	99.34 229	99.31 297	98.98 240	98.31 315	99.91 32	98.81 231	98.79 327	98.94 360	99.14 84	99.84 257	98.79 160	98.74 362	99.20 284

canonicalmvs		99.02 209	99.00 199	99.09 276	99.10 343	98.70 266	99.61 67	99.66 151	99.63 105	98.64 339	97.65 399	99.04 99	99.54 387	98.79 160	98.92 349	99.04 326

VDDNet		98.97 221	98.82 231	99.42 204	99.71 142	98.81 257	99.62 62	98.68 351	99.81 60	99.38 245	99.80 82	94.25 326	99.85 242	98.79 160	99.32 319	99.59 158

CR-MVSNet		98.35 289	98.20 284	98.83 313	99.05 351	98.12 308	99.30 135	99.67 146	97.39 344	99.16 284	99.79 92	91.87 352	99.91 137	98.78 164	98.77 358	98.44 378

test_method		91.72 374	92.32 377	89.91 392	93.49 415	70.18 418	90.28 406	99.56 213	61.71 410	95.39 405	99.52 247	93.90 328	99.94 76	98.76 165	98.27 379	99.62 137

RPMNet		98.60 260	98.53 257	98.83 313	99.05 351	98.12 308	99.30 135	99.62 173	99.86 44	99.16 284	99.74 118	92.53 346	99.92 115	98.75 166	98.77 358	98.44 378

pmmvs4		99.13 188	99.06 178	99.36 226	99.57 201	99.10 232	98.01 344	99.25 311	98.78 236	99.58 180	99.44 270	98.24 203	99.76 319	98.74 167	99.93 99	99.22 278

tttt0517		97.62 321	97.20 330	98.90 306	99.76 116	97.40 344	99.48 96	94.36 403	99.06 200	99.70 134	99.49 256	84.55 395	99.94 76	98.73 168	99.65 255	99.36 248

EPP-MVSNet		99.17 180	99.00 199	99.66 115	99.80 85	99.43 163	99.70 34	99.24 314	99.48 127	99.56 191	99.77 107	94.89 319	99.93 93	98.72 169	99.89 125	99.63 126

Anonymous20240529		99.42 105	99.34 111	99.65 120	99.53 221	99.60 126	99.63 59	99.39 280	99.47 131	99.76 107	99.78 100	98.13 216	99.86 224	98.70 170	99.68 244	99.49 208

ACMH	98.42 6	99.59 68	99.54 76	99.72 93	99.86 53	99.62 117	99.56 81	99.79 85	98.77 238	99.80 90	99.85 55	99.64 28	99.85 242	98.70 170	99.89 125	99.70 78
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 134	99.28 131	99.47 187	99.57 201	99.39 176	99.78 12	99.43 267	98.87 222	99.57 184	99.82 72	98.06 222	99.87 203	98.69 172	99.73 224	99.15 295

LFMVS		98.46 278	98.19 287	99.26 251	99.24 314	98.52 283	99.62 62	96.94 392	99.87 41	99.31 260	99.58 223	91.04 360	99.81 296	98.68 173	99.42 306	99.45 221

iter_conf05_11		99.03 206	98.98 208	99.17 264	99.07 349	99.22 213	97.92 355	99.46 258	99.23 170	99.44 225	98.98 353	98.19 210	99.86 224	98.66 174	99.89 125	98.42 380

WR-MVS		99.11 193	98.93 214	99.66 115	99.30 301	99.42 166	98.42 308	99.37 285	99.04 201	99.57 184	99.20 324	96.89 284	99.86 224	98.66 174	99.87 146	99.70 78

Anonymous202405211		98.75 247	98.46 261	99.63 134	99.34 290	99.66 100	99.47 99	97.65 384	99.28 161	99.56 191	99.50 252	93.15 338	99.84 257	98.62 176	99.58 275	99.40 237

EPNet		98.13 301	97.77 316	99.18 263	94.57 414	97.99 318	99.24 156	97.96 378	99.74 72	97.29 387	99.62 197	93.13 339	99.97 33	98.59 177	99.83 171	99.58 163
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 202	99.09 170	98.91 300	99.21 319	98.36 295	98.82 261	99.47 255	98.85 225	98.90 313	99.56 234	98.78 129	99.09 402	98.57 178	99.68 244	99.26 270

Patchmatch-RL test		98.60 260	98.36 271	99.33 232	99.77 112	99.07 235	98.27 317	99.87 45	98.91 217	99.74 120	99.72 129	90.57 369	99.79 306	98.55 179	99.85 158	99.11 304

pmmvs3		98.08 304	97.80 313	98.91 300	99.41 269	97.69 335	97.87 360	99.66 151	95.87 375	99.50 214	99.51 249	90.35 371	99.97 33	98.55 179	99.47 299	99.08 317

ETV-MVS		99.18 175	99.18 145	99.16 265	99.34 290	99.28 199	99.12 196	99.79 85	99.48 127	98.93 307	98.55 381	99.40 49	99.93 93	98.51 181	99.52 291	98.28 384

jason		99.16 182	99.11 161	99.32 236	99.75 127	98.44 287	98.26 319	99.39 280	98.70 246	99.74 120	99.30 302	98.54 164	99.97 33	98.48 182	99.82 180	99.55 173
jason: jason.
APDe-MVS		99.48 86	99.36 109	99.85 26	99.55 213	99.81 39	99.50 91	99.69 138	98.99 204	99.75 112	99.71 137	98.79 127	99.93 93	98.46 183	99.85 158	99.80 46
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CL-MVSNet_self_test		98.71 252	98.56 255	99.15 267	99.22 317	98.66 271	97.14 390	99.51 243	98.09 305	99.54 199	99.27 308	96.87 285	99.74 326	98.43 184	98.96 346	99.03 328

our_test_3		98.85 239	99.09 170	98.13 347	99.66 169	94.90 387	97.72 365	99.58 206	99.07 198	99.64 153	99.62 197	98.19 210	99.93 93	98.41 185	99.95 81	99.55 173

Gipuma		99.57 69	99.59 64	99.49 181	99.98 3	99.71 82	99.72 29	99.84 59	99.81 60	99.94 34	99.78 100	98.91 114	99.71 335	98.41 185	99.95 81	99.05 324
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 329	96.91 339	98.74 320	97.72 407	97.57 337	97.60 371	97.36 390	98.00 308	99.21 278	98.02 392	90.04 374	99.79 306	98.37 187	95.89 406	98.86 351

PM-MVS		99.36 123	99.29 129	99.58 156	99.83 64	99.66 100	98.95 244	99.86 48	98.85 225	99.81 86	99.73 122	98.40 188	99.92 115	98.36 188	99.83 171	99.17 291

baseline1		97.73 316	97.33 326	98.96 291	99.30 301	97.73 333	99.40 109	98.42 366	99.33 155	99.46 223	99.21 322	91.18 358	99.82 281	98.35 189	91.26 409	99.32 258

MVS-HIRNet		97.86 310	98.22 282	96.76 378	99.28 306	91.53 405	98.38 310	92.60 408	99.13 191	99.31 260	99.96 12	97.18 276	99.68 356	98.34 190	99.83 171	99.07 322

GA-MVS		97.99 309	97.68 319	98.93 297	99.52 226	98.04 316	97.19 389	99.05 336	98.32 292	98.81 323	98.97 356	89.89 376	99.41 398	98.33 191	99.05 340	99.34 254

Fast-Effi-MVS+		99.02 209	98.87 224	99.46 189	99.38 274	99.50 145	99.04 217	99.79 85	97.17 354	98.62 341	98.74 373	99.34 60	99.95 62	98.32 192	99.41 307	98.92 343

MDA-MVSNet_test_wron		98.95 227	98.99 205	98.85 309	99.64 173	97.16 350	98.23 321	99.33 292	98.93 214	99.56 191	99.66 171	97.39 265	99.83 272	98.29 193	99.88 135	99.55 173

N_pmnet		98.73 250	98.53 257	99.35 228	99.72 139	98.67 268	98.34 312	94.65 402	98.35 286	99.79 95	99.68 161	98.03 225	99.93 93	98.28 194	99.92 104	99.44 226

ET-MVSNet_ETH3D		96.78 341	96.07 350	98.91 300	99.26 310	97.92 325	97.70 367	96.05 397	97.96 315	92.37 409	98.43 385	87.06 384	99.90 155	98.27 195	97.56 396	98.91 344

thisisatest0530		97.45 326	96.95 336	98.94 294	99.68 163	97.73 333	99.09 207	94.19 405	98.61 256	99.56 191	99.30 302	84.30 396	99.93 93	98.27 195	99.54 286	99.16 293

YYNet1		98.95 227	98.99 205	98.84 311	99.64 173	97.14 352	98.22 322	99.32 294	98.92 216	99.59 178	99.66 171	97.40 263	99.83 272	98.27 195	99.90 115	99.55 173

ACMM	98.09 11	99.46 95	99.38 103	99.72 93	99.80 85	99.69 93	99.13 192	99.65 161	98.99 204	99.64 153	99.72 129	99.39 50	99.86 224	98.23 198	99.81 189	99.60 151
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 224	98.87 224	99.24 256	99.57 201	98.40 290	98.12 330	99.18 325	98.28 294	99.63 157	99.13 328	98.02 226	99.97 33	98.22 199	99.69 239	99.35 251

3Dnovator	99.15 2	99.43 102	99.36 109	99.65 120	99.39 271	99.42 166	99.70 34	99.56 213	99.23 170	99.35 248	99.80 82	99.17 79	99.95 62	98.21 200	99.84 163	99.59 158

Fast-Effi-MVS+-dtu		99.20 168	99.12 158	99.43 202	99.25 312	99.69 93	99.05 214	99.82 66	99.50 125	98.97 303	99.05 341	98.98 106	99.98 20	98.20 201	99.24 330	98.62 364

MS-PatchMatch		99.00 217	98.97 210	99.09 276	99.11 341	98.19 303	98.76 271	99.33 292	98.49 269	99.44 225	99.58 223	98.21 208	99.69 344	98.20 201	99.62 260	99.39 239

TSAR-MVS + GP.		99.12 190	99.04 188	99.38 219	99.34 290	99.16 222	98.15 326	99.29 302	98.18 301	99.63 157	99.62 197	99.18 78	99.68 356	98.20 201	99.74 219	99.30 264

DP-MVS		99.48 86	99.39 101	99.74 78	99.57 201	99.62 117	99.29 142	99.61 180	99.87 41	99.74 120	99.76 110	98.69 141	99.87 203	98.20 201	99.80 194	99.75 68

MVP-Stereo		99.16 182	99.08 172	99.43 202	99.48 244	99.07 235	99.08 210	99.55 219	98.63 252	99.31 260	99.68 161	98.19 210	99.78 309	98.18 205	99.58 275	99.45 221
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 102	99.30 123	99.80 44	99.83 64	99.81 39	99.52 86	99.70 131	98.35 286	99.51 212	99.50 252	99.31 62	99.88 187	98.18 205	99.84 163	99.69 82

MDA-MVSNet-bldmvs		99.06 199	99.05 182	99.07 281	99.80 85	97.83 328	98.89 249	99.72 123	99.29 158	99.63 157	99.70 144	96.47 296	99.89 173	98.17 207	99.82 180	99.50 203

JIA-IIPM		98.06 305	97.92 308	98.50 331	98.59 389	97.02 354	98.80 265	98.51 361	99.88 40	97.89 375	99.87 47	91.89 351	99.90 155	98.16 208	97.68 395	98.59 367

EIA-MVS		99.12 190	99.01 195	99.45 192	99.36 279	99.62 117	99.34 122	99.79 85	98.41 275	98.84 320	98.89 364	98.75 134	99.84 257	98.15 209	99.51 292	98.89 348

miper_lstm_enhance		98.65 257	98.60 246	98.82 316	99.20 322	97.33 346	97.78 363	99.66 151	99.01 203	99.59 178	99.50 252	94.62 323	99.85 242	98.12 210	99.90 115	99.26 270

Effi-MVS+-dtu		99.07 198	98.92 218	99.52 176	98.89 366	99.78 48	99.15 184	99.66 151	99.34 153	98.92 310	99.24 318	97.69 249	99.98 20	98.11 211	99.28 324	98.81 355

tpm		97.15 333	96.95 336	97.75 360	98.91 362	94.24 390	99.32 127	97.96 378	97.71 328	98.29 357	99.32 298	86.72 390	99.92 115	98.10 212	96.24 405	99.09 310

DeepPCF-MVS	98.42 6	99.18 175	99.02 192	99.67 108	99.22 317	99.75 66	97.25 387	99.47 255	98.72 243	99.66 150	99.70 144	99.29 64	99.63 374	98.07 213	99.81 189	99.62 137

ppachtmachnet_test		98.89 235	99.12 158	98.20 345	99.66 169	95.24 383	97.63 369	99.68 141	99.08 196	99.78 99	99.62 197	98.65 149	99.88 187	98.02 214	99.96 68	99.48 212

tpmrst		97.73 316	98.07 294	96.73 380	98.71 385	92.00 401	99.10 203	98.86 342	98.52 265	98.92 310	99.54 243	91.90 350	99.82 281	98.02 214	99.03 342	98.37 381

CSCG		99.37 120	99.29 129	99.60 150	99.71 142	99.46 152	99.43 107	99.85 53	98.79 234	99.41 238	99.60 215	98.92 112	99.92 115	98.02 214	99.92 104	99.43 232

eth_miper_zixun_eth		98.68 255	98.71 239	98.60 326	99.10 343	96.84 359	97.52 377	99.54 225	98.94 211	99.58 180	99.48 259	96.25 306	99.76 319	98.01 217	99.93 99	99.21 280

Patchmtry		98.78 244	98.54 256	99.49 181	98.89 366	99.19 220	99.32 127	99.67 146	99.65 101	99.72 125	99.79 92	91.87 352	99.95 62	98.00 218	99.97 55	99.33 255

PVSNet_BlendedMVS		99.03 206	99.01 195	99.09 276	99.54 215	97.99 318	98.58 287	99.82 66	97.62 331	99.34 251	99.71 137	98.52 171	99.77 317	97.98 219	99.97 55	99.52 196

PVSNet_Blended		98.70 253	98.59 248	99.02 286	99.54 215	97.99 318	97.58 372	99.82 66	95.70 379	99.34 251	98.98 353	98.52 171	99.77 317	97.98 219	99.83 171	99.30 264

cl____		98.54 268	98.41 266	98.92 298	99.03 353	97.80 331	97.46 379	99.59 197	98.90 218	99.60 175	99.46 266	93.85 330	99.78 309	97.97 221	99.89 125	99.17 291

DIV-MVS_self_test		98.54 268	98.42 265	98.92 298	99.03 353	97.80 331	97.46 379	99.59 197	98.90 218	99.60 175	99.46 266	93.87 329	99.78 309	97.97 221	99.89 125	99.18 289

AUN-MVS		97.82 312	97.38 325	99.14 270	99.27 308	98.53 281	98.72 274	99.02 337	98.10 303	97.18 390	99.03 347	89.26 378	99.85 242	97.94 223	97.91 391	99.03 328

FA-MVS(test-final)		98.52 270	98.32 276	99.10 275	99.48 244	98.67 268	99.77 14	98.60 358	97.35 346	99.63 157	99.80 82	93.07 340	99.84 257	97.92 224	99.30 321	98.78 358

ambc				99.20 260	99.35 281	98.53 281	99.17 176	99.46 258		99.67 146	99.80 82	98.46 178	99.70 338	97.92 224	99.70 235	99.38 241

USDC		98.96 224	98.93 214	99.05 284	99.54 215	97.99 318	97.07 393	99.80 79	98.21 298	99.75 112	99.77 107	98.43 181	99.64 373	97.90 226	99.88 135	99.51 198

OPM-MVS		99.26 147	99.13 154	99.63 134	99.70 150	99.61 123	98.58 287	99.48 252	98.50 267	99.52 207	99.63 190	99.14 84	99.76 319	97.89 227	99.77 208	99.51 198
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 136	99.17 146	99.77 56	99.69 155	99.80 43	99.14 186	99.31 298	99.16 185	99.62 166	99.61 207	98.35 192	99.91 137	97.88 228	99.72 230	99.61 147
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 32	99.70 150	99.79 45	99.14 186	99.61 180					99.92 115	97.88 228	99.72 230	99.77 59

c3_l		98.72 251	98.71 239	98.72 321	99.12 336	97.22 349	97.68 368	99.56 213	98.90 218	99.54 199	99.48 259	96.37 302	99.73 329	97.88 228	99.88 135	99.21 280

3Dnovator+	98.92 3	99.35 125	99.24 140	99.67 108	99.35 281	99.47 148	99.62 62	99.50 247	99.44 137	99.12 291	99.78 100	98.77 131	99.94 76	97.87 231	99.72 230	99.62 137

miper_ehance_all_eth		98.59 263	98.59 248	98.59 327	98.98 359	97.07 353	97.49 378	99.52 239	98.50 267	99.52 207	99.37 285	96.41 300	99.71 335	97.86 232	99.62 260	99.00 335

WTY-MVS		98.59 263	98.37 270	99.26 251	99.43 263	98.40 290	98.74 272	99.13 331	98.10 303	99.21 278	99.24 318	94.82 320	99.90 155	97.86 232	98.77 358	99.49 208

APD_test1		99.36 123	99.28 131	99.61 147	99.89 38	99.89 10	99.32 127	99.74 110	99.18 178	99.69 137	99.75 115	98.41 184	99.84 257	97.85 234	99.70 235	99.10 306

SED-MVS		99.40 111	99.28 131	99.77 56	99.69 155	99.82 34	99.20 166	99.54 225	99.13 191	99.82 79	99.63 190	98.91 114	99.92 115	97.85 234	99.70 235	99.58 163

test_241102_TWO								99.54 225	99.13 191	99.76 107	99.63 190	98.32 197	99.92 115	97.85 234	99.69 239	99.75 68

MVS_111021_HR		99.12 190	99.02 192	99.40 213	99.50 234	99.11 227	97.92 355	99.71 126	98.76 241	99.08 295	99.47 263	99.17 79	99.54 387	97.85 234	99.76 210	99.54 181

MTAPA		99.35 125	99.20 143	99.80 44	99.81 79	99.81 39	99.33 125	99.53 234	99.27 162	99.42 232	99.63 190	98.21 208	99.95 62	97.83 238	99.79 199	99.65 111

MSC_two_6792asdad				99.74 78	99.03 353	99.53 142		99.23 315					99.92 115	97.77 239	99.69 239	99.78 55

No_MVS				99.74 78	99.03 353	99.53 142		99.23 315					99.92 115	97.77 239	99.69 239	99.78 55

TESTMET0.1,1		96.24 354	95.84 355	97.41 368	98.24 400	93.84 393	97.38 381	95.84 398	98.43 272	97.81 380	98.56 380	79.77 402	99.89 173	97.77 239	98.77 358	98.52 372

ACMH+	98.40 8	99.50 82	99.43 95	99.71 98	99.86 53	99.76 60	99.32 127	99.77 94	99.53 123	99.77 105	99.76 110	99.26 70	99.78 309	97.77 239	99.88 135	99.60 151

IU-MVS					99.69 155	99.77 53		99.22 318	97.50 338	99.69 137				97.75 243	99.70 235	99.77 59

114514_t		98.49 275	98.11 292	99.64 127	99.73 136	99.58 132	99.24 156	99.76 99	89.94 402	99.42 232	99.56 234	97.76 246	99.86 224	97.74 244	99.82 180	99.47 216

DVP-MVS++		99.38 117	99.25 138	99.77 56	99.03 353	99.77 53	99.74 23	99.61 180	99.18 178	99.76 107	99.61 207	99.00 102	99.92 115	97.72 245	99.60 270	99.62 137

test_0728_THIRD									99.18 178	99.62 166	99.61 207	98.58 158	99.91 137	97.72 245	99.80 194	99.77 59

EGC-MVSNET		89.05 376	85.52 379	99.64 127	99.89 38	99.78 48	99.56 81	99.52 239	24.19 411	49.96 412	99.83 65	99.15 81	99.92 115	97.71 247	99.85 158	99.21 280

miper_enhance_ethall		98.03 306	97.94 306	98.32 340	98.27 399	96.43 365	96.95 394	99.41 270	96.37 370	99.43 230	98.96 358	94.74 321	99.69 344	97.71 247	99.62 260	98.83 354

TSAR-MVS + MP.		99.34 130	99.24 140	99.63 134	99.82 71	99.37 181	99.26 149	99.35 289	98.77 238	99.57 184	99.70 144	99.27 69	99.88 187	97.71 247	99.75 212	99.65 111
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 324	97.28 327	98.40 335	98.37 397	96.75 360	97.24 388	99.37 285	97.31 348	99.41 238	99.22 320	87.30 382	99.37 399	97.70 250	99.62 260	99.08 317

MP-MVS-pluss		99.14 186	98.92 218	99.80 44	99.83 64	99.83 28	98.61 280	99.63 169	96.84 363	99.44 225	99.58 223	98.81 122	99.91 137	97.70 250	99.82 180	99.67 94
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 141	99.11 161	99.79 50	99.75 127	99.81 39	98.95 244	99.53 234	98.27 295	99.53 205	99.73 122	98.75 134	99.87 203	97.70 250	99.83 171	99.68 88

UnsupCasMVSNet_bld		98.55 267	98.27 280	99.40 213	99.56 212	99.37 181	97.97 351	99.68 141	97.49 339	99.08 295	99.35 294	95.41 317	99.82 281	97.70 250	98.19 383	99.01 334

MVS_111021_LR		99.13 188	99.03 190	99.42 204	99.58 191	99.32 193	97.91 358	99.73 114	98.68 247	99.31 260	99.48 259	99.09 89	99.66 365	97.70 250	99.77 208	99.29 267

IS-MVSNet		99.03 206	98.85 226	99.55 168	99.80 85	99.25 206	99.73 26	99.15 328	99.37 149	99.61 172	99.71 137	94.73 322	99.81 296	97.70 250	99.88 135	99.58 163

test-LLR		97.15 333	96.95 336	97.74 361	98.18 402	95.02 385	97.38 381	96.10 394	98.00 308	97.81 380	98.58 377	90.04 374	99.91 137	97.69 256	98.78 356	98.31 382

test-mter		96.23 355	95.73 357	97.74 361	98.18 402	95.02 385	97.38 381	96.10 394	97.90 317	97.81 380	98.58 377	79.12 405	99.91 137	97.69 256	98.78 356	98.31 382

XVS		99.27 145	99.11 161	99.75 73	99.71 142	99.71 82	99.37 117	99.61 180	99.29 158	98.76 330	99.47 263	98.47 175	99.88 187	97.62 258	99.73 224	99.67 94

X-MVStestdata		96.09 358	94.87 370	99.75 73	99.71 142	99.71 82	99.37 117	99.61 180	99.29 158	98.76 330	61.30 418	98.47 175	99.88 187	97.62 258	99.73 224	99.67 94

SMA-MVS		99.19 171	99.00 199	99.73 87	99.46 254	99.73 75	99.13 192	99.52 239	97.40 343	99.57 184	99.64 179	98.93 111	99.83 272	97.61 260	99.79 199	99.63 126
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
CostFormer		96.71 344	96.79 343	96.46 384	98.90 363	90.71 410	99.41 108	98.68 351	94.69 392	98.14 367	99.34 297	86.32 392	99.80 303	97.60 261	98.07 389	98.88 349

PVSNet	97.47 15	98.42 281	98.44 263	98.35 337	99.46 254	96.26 368	96.70 398	99.34 291	97.68 329	99.00 302	99.13 328	97.40 263	99.72 331	97.59 262	99.68 244	99.08 317

new_pmnet		98.88 236	98.89 222	98.84 311	99.70 150	97.62 336	98.15 326	99.50 247	97.98 311	99.62 166	99.54 243	98.15 215	99.94 76	97.55 263	99.84 163	98.95 339

IB-MVS	95.41 20	95.30 372	94.46 376	97.84 357	98.76 381	95.33 381	97.33 384	96.07 396	96.02 374	95.37 406	97.41 403	76.17 407	99.96 54	97.54 264	95.44 408	98.22 387
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
LS3D		99.24 151	99.11 161	99.61 147	98.38 396	99.79 45	99.57 79	99.68 141	99.61 111	99.15 286	99.71 137	98.70 140	99.91 137	97.54 264	99.68 244	99.13 303

ZNCC-MVS		99.22 161	99.04 188	99.77 56	99.76 116	99.73 75	99.28 144	99.56 213	98.19 300	99.14 288	99.29 305	98.84 121	99.92 115	97.53 266	99.80 194	99.64 121

CP-MVS		99.23 153	99.05 182	99.75 73	99.66 169	99.66 100	99.38 113	99.62 173	98.38 279	99.06 299	99.27 308	98.79 127	99.94 76	97.51 267	99.82 180	99.66 103

SD-MVS		99.01 215	99.30 123	98.15 346	99.50 234	99.40 173	98.94 246	99.61 180	99.22 175	99.75 112	99.82 72	99.54 41	95.51 411	97.48 268	99.87 146	99.54 181
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
PMMVS		98.49 275	98.29 279	99.11 273	98.96 360	98.42 289	97.54 373	99.32 294	97.53 336	98.47 352	98.15 391	97.88 236	99.82 281	97.46 269	99.24 330	99.09 310

DeepC-MVS_fast	98.47 5	99.23 153	99.12 158	99.56 165	99.28 306	99.22 213	98.99 237	99.40 277	99.08 196	99.58 180	99.64 179	98.90 117	99.83 272	97.44 270	99.75 212	99.63 126
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 148	99.08 172	99.76 63	99.73 136	99.70 89	99.31 132	99.59 197	98.36 281	99.36 247	99.37 285	98.80 126	99.91 137	97.43 271	99.75 212	99.68 88

ACMMPR		99.23 153	99.06 178	99.76 63	99.74 133	99.69 93	99.31 132	99.59 197	98.36 281	99.35 248	99.38 283	98.61 153	99.93 93	97.43 271	99.75 212	99.67 94

Vis-MVSNet (Re-imp)		98.77 245	98.58 251	99.34 229	99.78 104	98.88 253	99.61 67	99.56 213	99.11 195	99.24 272	99.56 234	93.00 342	99.78 309	97.43 271	99.89 125	99.35 251

MIMVSNet		98.43 280	98.20 284	99.11 273	99.53 221	98.38 294	99.58 76	98.61 356	98.96 208	99.33 253	99.76 110	90.92 362	99.81 296	97.38 274	99.76 210	99.15 295

WB-MVSnew		98.34 291	98.14 290	98.96 291	98.14 405	97.90 326	98.27 317	97.26 391	98.63 252	98.80 325	98.00 394	97.77 244	99.90 155	97.37 275	98.98 345	99.09 310

XVG-OURS-SEG-HR		99.16 182	98.99 205	99.66 115	99.84 60	99.64 110	98.25 320	99.73 114	98.39 278	99.63 157	99.43 271	99.70 24	99.90 155	97.34 276	98.64 368	99.44 226

COLMAP_ROB	98.06 12	99.45 97	99.37 106	99.70 102	99.83 64	99.70 89	99.38 113	99.78 91	99.53 123	99.67 146	99.78 100	99.19 77	99.86 224	97.32 277	99.87 146	99.55 173
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 209	98.81 232	99.65 120	99.58 191	99.49 146	98.58 287	99.07 333	98.40 277	99.04 300	99.25 313	98.51 173	99.80 303	97.31 278	99.51 292	99.65 111

region2R		99.23 153	99.05 182	99.77 56	99.76 116	99.70 89	99.31 132	99.59 197	98.41 275	99.32 256	99.36 289	98.73 138	99.93 93	97.29 279	99.74 219	99.67 94

APD-MVS_3200maxsize		99.31 138	99.16 147	99.74 78	99.53 221	99.75 66	99.27 147	99.61 180	99.19 177	99.57 184	99.64 179	98.76 132	99.90 155	97.29 279	99.62 260	99.56 170

TAPA-MVS	97.92 13	98.03 306	97.55 322	99.46 189	99.47 250	99.44 159	98.50 301	99.62 173	86.79 403	99.07 298	99.26 311	98.26 202	99.62 375	97.28 281	99.73 224	99.31 262
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 145	99.11 161	99.73 87	99.54 215	99.74 72	99.26 149	99.62 173	99.16 185	99.52 207	99.64 179	98.41 184	99.91 137	97.27 282	99.61 267	99.54 181

RE-MVS-def			99.13 154		99.54 215	99.74 72	99.26 149	99.62 173	99.16 185	99.52 207	99.64 179	98.57 159		97.27 282	99.61 267	99.54 181

testing11		96.05 360	95.41 362	97.97 351	98.78 378	95.27 382	98.59 285	98.23 374	98.86 224	96.56 397	96.91 409	75.20 408	99.69 344	97.26 284	98.29 378	98.93 341

test_yl		98.25 294	97.95 302	99.13 271	99.17 328	98.47 284	99.00 232	98.67 353	98.97 206	99.22 276	99.02 348	91.31 356	99.69 344	97.26 284	98.93 347	99.24 273

DCV-MVSNet		98.25 294	97.95 302	99.13 271	99.17 328	98.47 284	99.00 232	98.67 353	98.97 206	99.22 276	99.02 348	91.31 356	99.69 344	97.26 284	98.93 347	99.24 273

PHI-MVS		99.11 193	98.95 213	99.59 152	99.13 333	99.59 128	99.17 176	99.65 161	97.88 320	99.25 269	99.46 266	98.97 108	99.80 303	97.26 284	99.82 180	99.37 244

tfpnnormal		99.43 102	99.38 103	99.60 150	99.87 50	99.75 66	99.59 74	99.78 91	99.71 81	99.90 48	99.69 150	98.85 120	99.90 155	97.25 288	99.78 204	99.15 295

PatchmatchNet		97.65 320	97.80 313	97.18 374	98.82 373	92.49 399	99.17 176	98.39 368	98.12 302	98.79 327	99.58 223	90.71 367	99.89 173	97.23 289	99.41 307	99.16 293
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 220	98.80 234	99.56 165	99.25 312	99.43 163	98.54 296	99.27 306	98.58 258	98.80 325	99.43 271	98.53 168	99.70 338	97.22 290	99.59 274	99.54 181

testing3		96.48 348	95.63 359	99.01 287	99.23 316	97.81 329	98.90 248	99.10 332	98.72 243	97.84 379	97.92 395	72.44 412	99.85 242	97.21 291	99.33 317	99.35 251

HPM-MVS		99.25 148	99.07 176	99.78 53	99.81 79	99.75 66	99.61 67	99.67 146	97.72 327	99.35 248	99.25 313	99.23 73	99.92 115	97.21 291	99.82 180	99.67 94
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 171	99.00 199	99.76 63	99.76 116	99.68 96	99.38 113	99.54 225	98.34 290	99.01 301	99.50 252	98.53 168	99.93 93	97.18 293	99.78 204	99.66 103

ACMMP		99.25 148	99.08 172	99.74 78	99.79 97	99.68 96	99.50 91	99.65 161	98.07 306	99.52 207	99.69 150	98.57 159	99.92 115	97.18 293	99.79 199	99.63 126
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
thisisatest0515		96.98 337	96.42 344	98.66 324	99.42 268	97.47 340	97.27 386	94.30 404	97.24 350	99.15 286	98.86 366	85.01 393	99.87 203	97.10 295	99.39 309	98.63 363

XVG-ACMP-BASELINE		99.23 153	99.10 169	99.63 134	99.82 71	99.58 132	98.83 257	99.72 123	98.36 281	99.60 175	99.71 137	98.92 112	99.91 137	97.08 296	99.84 163	99.40 237

MSDG		99.08 197	98.98 208	99.37 222	99.60 182	99.13 225	97.54 373	99.74 110	98.84 228	99.53 205	99.55 241	99.10 87	99.79 306	97.07 297	99.86 154	99.18 289

SteuartSystems-ACMMP		99.30 139	99.14 152	99.76 63	99.87 50	99.66 100	99.18 171	99.60 191	98.55 260	99.57 184	99.67 165	99.03 101	99.94 76	97.01 298	99.80 194	99.69 82
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 356	95.78 356	97.49 364	98.53 391	93.83 394	98.04 341	93.94 406	98.96 208	98.46 353	98.17 390	79.86 401	99.87 203	96.99 299	99.06 338	98.78 358

EPMVS		96.53 347	96.32 345	97.17 375	98.18 402	92.97 398	99.39 111	89.95 412	98.21 298	98.61 342	99.59 220	86.69 391	99.72 331	96.99 299	99.23 332	98.81 355

MSP-MVS		99.04 205	98.79 235	99.81 39	99.78 104	99.73 75	99.35 121	99.57 208	98.54 263	99.54 199	98.99 350	96.81 286	99.93 93	96.97 301	99.53 288	99.77 59
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
HPM-MVS++		98.96 224	98.70 241	99.74 78	99.52 226	99.71 82	98.86 252	99.19 324	98.47 271	98.59 344	99.06 340	98.08 221	99.91 137	96.94 302	99.60 270	99.60 151

SR-MVS		99.19 171	99.00 199	99.74 78	99.51 228	99.72 80	99.18 171	99.60 191	98.85 225	99.47 219	99.58 223	98.38 189	99.92 115	96.92 303	99.54 286	99.57 168

PGM-MVS		99.20 168	99.01 195	99.77 56	99.75 127	99.71 82	99.16 182	99.72 123	97.99 310	99.42 232	99.60 215	98.81 122	99.93 93	96.91 304	99.74 219	99.66 103

HY-MVS	98.23 9	98.21 299	97.95 302	98.99 288	99.03 353	98.24 298	99.61 67	98.72 349	96.81 364	98.73 332	99.51 249	94.06 327	99.86 224	96.91 304	98.20 381	98.86 351

MDTV_nov1_ep13			97.73 317		98.70 386	90.83 408	99.15 184	98.02 377	98.51 266	98.82 322	99.61 207	90.98 361	99.66 365	96.89 306	98.92 349

GST-MVS		99.16 182	98.96 212	99.75 73	99.73 136	99.73 75	99.20 166	99.55 219	98.22 297	99.32 256	99.35 294	98.65 149	99.91 137	96.86 307	99.74 219	99.62 137

test_post1							99.14 186				51.63 420	89.54 377	99.82 281	96.86 307

SCA		98.11 302	98.36 271	97.36 369	99.20 322	92.99 397	98.17 325	98.49 363	98.24 296	99.10 294	99.57 230	96.01 310	99.94 76	96.86 307	99.62 260	99.14 300

XVG-OURS		99.21 166	99.06 178	99.65 120	99.82 71	99.62 117	97.87 360	99.74 110	98.36 281	99.66 150	99.68 161	99.71 22	99.90 155	96.84 310	99.88 135	99.43 232

LCM-MVSNet-Re		99.28 141	99.15 151	99.67 108	99.33 295	99.76 60	99.34 122	99.97 18	98.93 214	99.91 44	99.79 92	98.68 142	99.93 93	96.80 311	99.56 277	99.30 264

RPSCF		99.18 175	99.02 192	99.64 127	99.83 64	99.85 18	99.44 105	99.82 66	98.33 291	99.50 214	99.78 100	97.90 234	99.65 371	96.78 312	99.83 171	99.44 226

旧先验2							97.94 353		95.33 383	98.94 306			99.88 187	96.75 313

MDTV_nov1_ep13_2view						91.44 406	99.14 186		97.37 345	99.21 278		91.78 354		96.75 313		99.03 328

CLD-MVS		98.76 246	98.57 252	99.33 232	99.57 201	98.97 242	97.53 375	99.55 219	96.41 368	99.27 267	99.13 328	99.07 94	99.78 309	96.73 315	99.89 125	99.23 276
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 303	97.98 300	98.48 332	99.27 308	96.48 363	99.40 109	99.07 333	98.81 231	99.23 273	99.57 230	90.11 373	99.87 203	96.69 316	99.64 257	99.09 310

baseline2		96.83 340	96.28 346	98.46 333	99.09 347	96.91 357	98.83 257	93.87 407	97.23 351	96.23 402	98.36 386	88.12 381	99.90 155	96.68 317	98.14 386	98.57 370

cascas		96.99 336	96.82 342	97.48 365	97.57 410	95.64 377	96.43 400	99.56 213	91.75 398	97.13 392	97.61 402	95.58 315	98.63 406	96.68 317	99.11 336	98.18 391

PC_three_1452									97.56 332	99.68 140	99.41 273	99.09 89	97.09 408	96.66 319	99.60 270	99.62 137

LPG-MVS_test		99.22 161	99.05 182	99.74 78	99.82 71	99.63 115	99.16 182	99.73 114	97.56 332	99.64 153	99.69 150	99.37 56	99.89 173	96.66 319	99.87 146	99.69 82

LGP-MVS_train				99.74 78	99.82 71	99.63 115		99.73 114	97.56 332	99.64 153	99.69 150	99.37 56	99.89 173	96.66 319	99.87 146	99.69 82

ETVMVS		96.14 357	95.22 367	98.89 307	98.80 374	98.01 317	98.66 278	98.35 371	98.71 245	97.18 390	96.31 417	74.23 411	99.75 323	96.64 322	98.13 388	98.90 345

TinyColmap		98.97 221	98.93 214	99.07 281	99.46 254	98.19 303	97.75 364	99.75 104	98.79 234	99.54 199	99.70 144	98.97 108	99.62 375	96.63 323	99.83 171	99.41 236

LF4IMVS		99.01 215	98.92 218	99.27 248	99.71 142	99.28 199	98.59 285	99.77 94	98.32 292	99.39 244	99.41 273	98.62 151	99.84 257	96.62 324	99.84 163	98.69 362

NCCC		98.82 241	98.57 252	99.58 156	99.21 319	99.31 194	98.61 280	99.25 311	98.65 250	98.43 354	99.26 311	97.86 237	99.81 296	96.55 325	99.27 327	99.61 147

OPU-MVS				99.29 243	99.12 336	99.44 159	99.20 166				99.40 277	99.00 102	98.84 405	96.54 326	99.60 270	99.58 163

F-COLMAP		98.74 248	98.45 262	99.62 144	99.57 201	99.47 148	98.84 255	99.65 161	96.31 371	98.93 307	99.19 325	97.68 250	99.87 203	96.52 327	99.37 312	99.53 186

testing99		95.86 365	95.19 368	97.87 355	98.76 381	95.03 384	98.62 279	98.44 365	98.68 247	96.67 396	96.66 413	74.31 410	99.69 344	96.51 328	98.03 390	98.90 345

ADS-MVSNet2		97.78 314	97.66 321	98.12 348	99.14 331	95.36 380	99.22 163	98.75 348	96.97 359	98.25 359	99.64 179	90.90 363	99.94 76	96.51 328	99.56 277	99.08 317

ADS-MVSNet		97.72 319	97.67 320	97.86 356	99.14 331	94.65 388	99.22 163	98.86 342	96.97 359	98.25 359	99.64 179	90.90 363	99.84 257	96.51 328	99.56 277	99.08 317

PatchMatch-RL		98.68 255	98.47 260	99.30 242	99.44 259	99.28 199	98.14 328	99.54 225	97.12 357	99.11 292	99.25 313	97.80 242	99.70 338	96.51 328	99.30 321	98.93 341

CMPMVS	77.52 23	98.50 273	98.19 287	99.41 211	98.33 398	99.56 136	99.01 226	99.59 197	95.44 381	99.57 184	99.80 82	95.64 313	99.46 397	96.47 332	99.92 104	99.21 280
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 361	95.32 365	98.02 349	98.76 381	95.39 379	98.38 310	98.65 355	98.82 229	96.84 393	96.71 412	75.06 409	99.71 335	96.46 333	98.23 380	98.98 336

SF-MVS		99.10 196	98.93 214	99.62 144	99.58 191	99.51 144	99.13 192	99.65 161	97.97 312	99.42 232	99.61 207	98.86 119	99.87 203	96.45 334	99.68 244	99.49 208

FE-MVS		97.85 311	97.42 324	99.15 267	99.44 259	98.75 263	99.77 14	98.20 375	95.85 376	99.33 253	99.80 82	88.86 379	99.88 187	96.40 335	99.12 335	98.81 355

DPE-MVS		99.14 186	98.92 218	99.82 36	99.57 201	99.77 53	98.74 272	99.60 191	98.55 260	99.76 107	99.69 150	98.23 207	99.92 115	96.39 336	99.75 212	99.76 65
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 408	89.02 414			93.47 394		98.30 387		99.84 257	96.38 337

AllTest		99.21 166	99.07 176	99.63 134	99.78 104	99.64 110	99.12 196	99.83 61	98.63 252	99.63 157	99.72 129	98.68 142	99.75 323	96.38 337	99.83 171	99.51 198

TestCases				99.63 134	99.78 104	99.64 110		99.83 61	98.63 252	99.63 157	99.72 129	98.68 142	99.75 323	96.38 337	99.83 171	99.51 198

testdata				99.42 204	99.51 228	98.93 248		99.30 301	96.20 372	98.87 317	99.40 277	98.33 196	99.89 173	96.29 340	99.28 324	99.44 226

dp		96.86 339	97.07 332	96.24 386	98.68 387	90.30 412	99.19 170	98.38 369	97.35 346	98.23 361	99.59 220	87.23 383	99.82 281	96.27 341	98.73 364	98.59 367

tpmvs		97.39 328	97.69 318	96.52 382	98.41 395	91.76 402	99.30 135	98.94 341	97.74 326	97.85 378	99.55 241	92.40 349	99.73 329	96.25 342	98.73 364	98.06 393

KD-MVS_2432*1600		95.89 362	95.41 362	97.31 372	94.96 412	93.89 391	97.09 391	99.22 318	97.23 351	98.88 314	99.04 343	79.23 403	99.54 387	96.24 343	96.81 400	98.50 376

miper_refine_blended		95.89 362	95.41 362	97.31 372	94.96 412	93.89 391	97.09 391	99.22 318	97.23 351	98.88 314	99.04 343	79.23 403	99.54 387	96.24 343	96.81 400	98.50 376

ACMP	97.51 14	99.05 202	98.84 228	99.67 108	99.78 104	99.55 139	98.88 250	99.66 151	97.11 358	99.47 219	99.60 215	99.07 94	99.89 173	96.18 345	99.85 158	99.58 163
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 232	98.72 238	99.44 197	99.39 271	99.42 166	98.58 287	99.64 167	97.31 348	99.44 225	99.62 197	98.59 156	99.69 344	96.17 346	99.79 199	99.22 278

DP-MVS Recon		98.50 273	98.23 281	99.31 239	99.49 239	99.46 152	98.56 292	99.63 169	94.86 390	98.85 319	99.37 285	97.81 241	99.59 381	96.08 347	99.44 302	98.88 349

tpm cat1		96.78 341	96.98 335	96.16 387	98.85 369	90.59 411	99.08 210	99.32 294	92.37 396	97.73 384	99.46 266	91.15 359	99.69 344	96.07 348	98.80 355	98.21 388

tpm2		96.35 351	96.22 347	96.73 380	98.88 368	91.75 403	99.21 165	98.51 361	93.27 395	97.89 375	99.21 322	84.83 394	99.70 338	96.04 349	98.18 384	98.75 361

dmvs_re		98.69 254	98.48 259	99.31 239	99.55 213	99.42 166	99.54 84	98.38 369	99.32 156	98.72 333	98.71 374	96.76 288	99.21 400	96.01 350	99.35 315	99.31 262

test_0402		99.22 161	99.14 152	99.45 192	99.79 97	99.43 163	99.28 144	99.68 141	99.54 121	99.40 243	99.56 234	99.07 94	99.82 281	96.01 350	99.96 68	99.11 304

ITE_SJBPF				99.38 219	99.63 175	99.44 159		99.73 114	98.56 259	99.33 253	99.53 245	98.88 118	99.68 356	96.01 350	99.65 255	99.02 333

test_prior2							97.95 352		97.87 321	98.05 369	99.05 341	97.90 234		95.99 353	99.49 297

testdata2													99.89 173	95.99 353

原ACMM1				99.37 222	99.47 250	98.87 255		99.27 306	96.74 366	98.26 358	99.32 298	97.93 233	99.82 281	95.96 355	99.38 310	99.43 232

新几何1				99.52 176	99.50 234	99.22 213		99.26 308	95.66 380	98.60 343	99.28 306	97.67 251	99.89 173	95.95 356	99.32 319	99.45 221

MP-MVS		99.06 199	98.83 230	99.76 63	99.76 116	99.71 82	99.32 127	99.50 247	98.35 286	98.97 303	99.48 259	98.37 190	99.92 115	95.95 356	99.75 212	99.63 126
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 371	94.59 374	98.61 325	98.66 388	97.45 342	98.54 296	97.90 381	98.53 264	96.54 398	96.47 414	70.62 415	99.81 296	95.91 358	98.15 385	98.56 371

wuyk23d		97.58 323	99.13 154	92.93 390	99.69 155	99.49 146	99.52 86	99.77 94	97.97 312	99.96 23	99.79 92	99.84 12	99.94 76	95.85 359	99.82 180	79.36 408

HQP_MVS		98.90 232	98.68 242	99.55 168	99.58 191	99.24 210	98.80 265	99.54 225	98.94 211	99.14 288	99.25 313	97.24 270	99.82 281	95.84 360	99.78 204	99.60 151

plane_prior5								99.54 225					99.82 281	95.84 360	99.78 204	99.60 151

无先验							98.01 344	99.23 315	95.83 377				99.85 242	95.79 362		99.44 226

CPTT-MVS		98.74 248	98.44 263	99.64 127	99.61 180	99.38 178	99.18 171	99.55 219	96.49 367	99.27 267	99.37 285	97.11 278	99.92 115	95.74 363	99.67 250	99.62 137

PLC	97.35 16	98.36 286	97.99 298	99.48 185	99.32 296	99.24 210	98.50 301	99.51 243	95.19 386	98.58 345	98.96 358	96.95 283	99.83 272	95.63 364	99.25 328	99.37 244
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 265	98.34 274	99.28 245	99.18 327	99.10 232	98.34 312	99.41 270	98.48 270	98.52 349	98.98 353	97.05 280	99.78 309	95.59 365	99.50 295	98.96 337

1314		98.00 308	97.90 310	98.27 344	98.90 363	97.45 342	99.30 135	99.06 335	94.98 387	97.21 389	99.12 332	98.43 181	99.67 361	95.58 366	98.56 371	97.71 397

PVSNet_0	95.53 19	95.85 366	95.31 366	97.47 366	98.78 378	93.48 396	95.72 402	99.40 277	96.18 373	97.37 385	97.73 397	95.73 312	99.58 382	95.49 367	81.40 410	99.36 248

MAR-MVS		98.24 296	97.92 308	99.19 261	98.78 378	99.65 106	99.17 176	99.14 329	95.36 382	98.04 370	98.81 370	97.47 260	99.72 331	95.47 368	99.06 338	98.21 388
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
OpenMVS	98.12 10	98.23 297	97.89 311	99.26 251	99.19 324	99.26 203	99.65 57	99.69 138	91.33 400	98.14 367	99.77 107	98.28 200	99.96 54	95.41 369	99.55 281	98.58 369

train_agg		98.35 289	97.95 302	99.57 162	99.35 281	99.35 188	98.11 332	99.41 270	94.90 388	97.92 373	98.99 350	98.02 226	99.85 242	95.38 370	99.44 302	99.50 203

9.14			98.64 243		99.45 258		98.81 262	99.60 191	97.52 337	99.28 266	99.56 234	98.53 168	99.83 272	95.36 371	99.64 257

APD-MVS		98.87 237	98.59 248	99.71 98	99.50 234	99.62 117	99.01 226	99.57 208	96.80 365	99.54 199	99.63 190	98.29 199	99.91 137	95.24 372	99.71 233	99.61 147
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 366								95.20 373

AdaColmap		98.60 260	98.35 273	99.38 219	99.12 336	99.22 213	98.67 277	99.42 269	97.84 324	98.81 323	99.27 308	97.32 268	99.81 296	95.14 374	99.53 288	99.10 306

test9_res														95.10 375	99.44 302	99.50 203

CDPH-MVS		98.56 266	98.20 284	99.61 147	99.50 234	99.46 152	98.32 314	99.41 270	95.22 384	99.21 278	99.10 337	98.34 194	99.82 281	95.09 376	99.66 253	99.56 170

BH-untuned		98.22 298	98.09 293	98.58 329	99.38 274	97.24 348	98.55 293	98.98 340	97.81 325	99.20 283	98.76 372	97.01 281	99.65 371	94.83 377	98.33 376	98.86 351

BP-MVS														94.73 378

HQP-MVS		98.36 286	98.02 297	99.39 216	99.31 297	98.94 245	97.98 348	99.37 285	97.45 340	98.15 363	98.83 367	96.67 289	99.70 338	94.73 378	99.67 250	99.53 186

QAPM		98.40 284	97.99 298	99.65 120	99.39 271	99.47 148	99.67 48	99.52 239	91.70 399	98.78 329	99.80 82	98.55 162	99.95 62	94.71 380	99.75 212	99.53 186

agg_prior2														94.58 381	99.46 301	99.50 203

myMVS_eth3d		95.63 369	94.73 371	98.34 339	98.50 393	96.36 366	98.60 282	99.21 321	97.89 318	96.76 394	96.37 415	72.10 413	99.57 383	94.38 382	98.73 364	99.09 310

BH-RMVSNet		98.41 282	98.14 290	99.21 258	99.21 319	98.47 284	98.60 282	98.26 373	98.35 286	98.93 307	99.31 300	97.20 275	99.66 365	94.32 383	99.10 337	99.51 198

E-PMN		97.14 335	97.43 323	96.27 385	98.79 376	91.62 404	95.54 403	99.01 339	99.44 137	98.88 314	99.12 332	92.78 343	99.68 356	94.30 384	99.03 342	97.50 398

MG-MVS		98.52 270	98.39 268	98.94 294	99.15 330	97.39 345	98.18 323	99.21 321	98.89 221	99.23 273	99.63 190	97.37 266	99.74 326	94.22 385	99.61 267	99.69 82

API-MVS		98.38 285	98.39 268	98.35 337	98.83 370	99.26 203	99.14 186	99.18 325	98.59 257	98.66 338	98.78 371	98.61 153	99.57 383	94.14 386	99.56 277	96.21 405

PAPM_NR		98.36 286	98.04 295	99.33 232	99.48 244	98.93 248	98.79 268	99.28 305	97.54 335	98.56 348	98.57 379	97.12 277	99.69 344	94.09 387	98.90 353	99.38 241

ZD-MVS					99.43 263	99.61 123		99.43 267	96.38 369	99.11 292	99.07 339	97.86 237	99.92 115	94.04 388	99.49 297

DPM-MVS		98.28 292	97.94 306	99.32 236	99.36 279	99.11 227	97.31 385	98.78 347	96.88 361	98.84 320	99.11 336	97.77 244	99.61 379	94.03 389	99.36 313	99.23 276

gg-mvs-nofinetune		95.87 364	95.17 369	97.97 351	98.19 401	96.95 355	99.69 41	89.23 413	99.89 35	96.24 401	99.94 16	81.19 398	99.51 393	93.99 390	98.20 381	97.44 399

PMVS	92.94 21	98.82 241	98.81 232	98.85 309	99.84 60	97.99 318	99.20 166	99.47 255	99.71 81	99.42 232	99.82 72	98.09 219	99.47 395	93.88 391	99.85 158	99.07 322
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 338	97.28 327	95.99 388	98.76 381	91.03 407	95.26 405	98.61 356	99.34 153	98.92 310	98.88 365	93.79 331	99.66 365	92.87 392	99.05 340	97.30 402

BH-w/o		97.20 332	97.01 334	97.76 359	99.08 348	95.69 376	98.03 343	98.52 360	95.76 378	97.96 372	98.02 392	95.62 314	99.47 395	92.82 393	97.25 399	98.12 392

TR-MVS		97.44 327	97.15 331	98.32 340	98.53 391	97.46 341	98.47 303	97.91 380	96.85 362	98.21 362	98.51 383	96.42 298	99.51 393	92.16 394	97.29 398	97.98 394

OpenMVS_ROB	97.31 17	97.36 330	96.84 340	98.89 307	99.29 303	99.45 157	98.87 251	99.48 252	86.54 405	99.44 225	99.74 118	97.34 267	99.86 224	91.61 395	99.28 324	97.37 401

GG-mvs-BLEND				97.36 369	97.59 408	96.87 358	99.70 34	88.49 414		94.64 407	97.26 406	80.66 399	99.12 401	91.50 396	96.50 404	96.08 407

DeepMVS_CX				97.98 350	99.69 155	96.95 355		99.26 308	75.51 408	95.74 404	98.28 388	96.47 296	99.62 375	91.23 397	97.89 392	97.38 400

PAPR		97.56 324	97.07 332	99.04 285	98.80 374	98.11 310	97.63 369	99.25 311	94.56 393	98.02 371	98.25 389	97.43 262	99.68 356	90.90 398	98.74 362	99.33 255

MVS		95.72 368	94.63 373	98.99 288	98.56 390	97.98 323	99.30 135	98.86 342	72.71 409	97.30 386	99.08 338	98.34 194	99.74 326	89.21 399	98.33 376	99.26 270

thres600view7		96.60 346	96.16 348	97.93 353	99.63 175	96.09 372	99.18 171	97.57 385	98.77 238	98.72 333	97.32 404	87.04 385	99.72 331	88.57 400	98.62 369	97.98 394

FPMVS		96.32 352	95.50 360	98.79 317	99.60 182	98.17 306	98.46 307	98.80 346	97.16 355	96.28 399	99.63 190	82.19 397	99.09 402	88.45 401	98.89 354	99.10 306

PCF-MVS	96.03 18	96.73 343	95.86 354	99.33 232	99.44 259	99.16 222	96.87 396	99.44 264	86.58 404	98.95 305	99.40 277	94.38 325	99.88 187	87.93 402	99.80 194	98.95 339
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 350	96.03 351	97.47 366	99.63 175	95.93 373	99.18 171	97.57 385	98.75 242	98.70 336	97.31 405	87.04 385	99.67 361	87.62 403	98.51 373	96.81 403

tfpn200view9		96.30 353	95.89 352	97.53 363	99.58 191	96.11 370	99.00 232	97.54 388	98.43 272	98.52 349	96.98 407	86.85 387	99.67 361	87.62 403	98.51 373	96.81 403

thres400		96.40 349	95.89 352	97.92 354	99.58 191	96.11 370	99.00 232	97.54 388	98.43 272	98.52 349	96.98 407	86.85 387	99.67 361	87.62 403	98.51 373	97.98 394

thres200		96.09 358	95.68 358	97.33 371	99.48 244	96.22 369	98.53 298	97.57 385	98.06 307	98.37 356	96.73 411	86.84 389	99.61 379	86.99 406	98.57 370	96.16 406

MVE	92.54 22	96.66 345	96.11 349	98.31 342	99.68 163	97.55 338	97.94 353	95.60 399	99.37 149	90.68 410	98.70 375	96.56 292	98.61 407	86.94 407	99.55 281	98.77 360
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 331	96.83 341	98.59 327	99.46 254	97.55 338	99.25 155	96.84 393	98.78 236	97.24 388	97.67 398	97.11 278	98.97 404	86.59 408	98.54 372	99.27 268

PAPM		95.61 370	94.71 372	98.31 342	99.12 336	96.63 361	96.66 399	98.46 364	90.77 401	96.25 400	98.68 376	93.01 341	99.69 344	81.60 409	97.86 394	98.62 364

dongtai		89.37 375	88.91 378	90.76 391	99.19 324	77.46 416	95.47 404	87.82 415	92.28 397	94.17 408	98.82 369	71.22 414	95.54 410	63.85 410	97.34 397	99.27 268

kuosan		85.65 377	84.57 380	88.90 393	97.91 406	77.11 417	96.37 401	87.62 416	85.24 406	85.45 411	96.83 410	69.94 416	90.98 412	45.90 411	95.83 407	98.62 364

test123		29.31 378	33.05 383	18.08 394	25.93 418	12.24 419	97.53 375	10.93 419	11.78 412	24.21 413	50.08 422	21.04 417	8.60 413	23.51 412	32.43 412	33.39 409

testmvs		28.94 379	33.33 381	15.79 395	26.03 417	9.81 420	96.77 397	15.67 418	11.55 413	23.87 414	50.74 421	19.03 418	8.53 414	23.21 413	33.07 411	29.03 410

test_blank		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		24.88 380	33.17 382	0.00 396	0.00 419	0.00 421	0.00 407	99.62 173	0.00 414	0.00 415	99.13 328	99.82 13	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		16.61 381	22.14 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	99.28 66	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		8.26 390	11.02 393	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	99.16 326	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

FOURS1					99.83 64	99.89 10	99.74 23	99.71 126	99.69 89	99.63 157

test_one_0601					99.63 175	99.76 60		99.55 219	99.23 170	99.31 260	99.61 207	98.59 156

eth-test2					0.00 419

eth-test					0.00 419

test_241102_ONE					99.69 155	99.82 34		99.54 225	99.12 194	99.82 79	99.49 256	98.91 114	99.52 392

save fliter					99.53 221	99.25 206	98.29 316	99.38 284	99.07 198

test0726					99.69 155	99.80 43	99.24 156	99.57 208	99.16 185	99.73 124	99.65 176	98.35 192

GSMVS																99.14 300

test_part2					99.62 179	99.67 98				99.55 197

sam_mvs1												90.81 366				99.14 300

sam_mvs												90.52 370

MTGPA								99.53 234

test_post											52.41 419	90.25 372	99.86 224

patchmatchnet-post											99.62 197	90.58 368	99.94 76

MTMP							99.09 207	98.59 359

TEST9					99.35 281	99.35 188	98.11 332	99.41 270	94.83 391	97.92 373	98.99 350	98.02 226	99.85 242

test_8					99.34 290	99.31 194	98.08 336	99.40 277	94.90 388	97.87 377	98.97 356	98.02 226	99.84 257

agg_prior					99.35 281	99.36 185		99.39 280		97.76 383			99.85 242

test_prior4						99.19 220	98.00 346

test_prior				99.46 189	99.35 281	99.22 213		99.39 280					99.69 344			99.48 212

新几何2							98.04 341

旧先验1					99.49 239	99.29 197		99.26 308			99.39 281	97.67 251			99.36 313	99.46 220

原ACMM2							97.92 355

test222					99.51 228	99.08 234	97.83 362	99.29 302	95.21 385	98.68 337	99.31 300	97.28 269			99.38 310	99.43 232

segment_acmp												98.37 190

testdata1							97.72 365		97.86 323

test12				99.54 173	99.29 303	99.33 191		99.16 327		98.43 354		97.54 258	99.82 281		99.47 299	99.48 212

plane_prior7					99.58 191	99.38 178

plane_prior6					99.47 250	99.26 203						97.24 270

plane_prior4											99.25 313

plane_prior3						99.31 194			98.36 281	99.14 288

plane_prior2							98.80 265		98.94 211

plane_prior1					99.51 228

plane_prior						99.24 210	98.42 308		97.87 321						99.71 233

n2								0.00 420

nn								0.00 420

door-mid								99.83 61

test11								99.29 302

door								99.77 94

HQP5-MVS						98.94 245

HQP-NCC					99.31 297		97.98 348		97.45 340	98.15 363

ACMP_Plane					99.31 297		97.98 348		97.45 340	98.15 363

HQP4-MVS										98.15 363			99.70 338			99.53 186

HQP3-MVS								99.37 285							99.67 250

HQP2-MVS												96.67 289

NP-MVS					99.40 270	99.13 225					98.83 367

ACMMP++_ref															99.94 92

ACMMP++															99.79 199

Test By Simon												98.41 184

High-resolution multi-view benchmark