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 4	99.87 23	99.98 3	99.75 72	99.70 35	100.00 1	99.73 85	100.00 1	99.89 38	99.79 18	99.88 205	99.98 1	100.00 1	99.98 5

test_fmvs2		99.72 44	99.85 17	99.34 242	99.91 31	98.08 329	99.48 102	100.00 1	99.90 37	99.99 7	99.91 28	99.50 52	99.98 23	99.98 1	99.99 16	99.96 13

test_fmvs3		99.83 21	99.93 2	99.53 184	99.96 7	98.62 290	99.67 50	100.00 1	99.95 25	100.00 1	99.95 16	99.85 11	99.99 8	99.98 1	99.99 16	99.98 5

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 64	99.12 208	100.00 1	100.00 1	99.99 7	99.91 28	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_vis1_n_1920		99.72 44	99.88 7	99.27 263	99.93 24	97.84 341	99.34 129	100.00 1	99.99 3	99.99 7	99.82 83	99.87 10	99.99 8	99.97 4	99.99 16	99.97 10

test_vis1_n		99.68 53	99.79 30	99.36 239	99.94 18	98.18 318	99.52 89	100.00 1	99.86 53	100.00 1	99.88 47	98.99 116	99.96 58	99.97 4	99.96 74	99.95 14

test_fmvs1_n		99.68 53	99.81 26	99.28 260	99.95 15	97.93 338	99.49 100	100.00 1	99.82 69	99.99 7	99.89 38	99.21 84	99.98 23	99.97 4	99.98 44	99.93 20

test_f		99.75 40	99.88 7	99.37 235	99.96 7	98.21 315	99.51 95	100.00 1	99.94 28	100.00 1	99.93 21	99.58 41	99.94 84	99.97 4	99.99 16	99.97 10

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 44	99.86 18	99.08 224	99.97 20	99.98 15	99.96 28	99.79 103	99.90 8	99.99 8	99.96 9	99.99 16	99.90 26

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 78	99.01 242	99.99 11	99.99 3	99.98 14	99.88 47	99.97 2	99.99 8	99.96 9	100.00 1	99.98 5

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 46	99.88 44	99.55 146	99.17 188	99.98 12	99.99 3	99.96 28	99.84 72	99.96 3	99.99 8	99.96 9	99.99 16	99.88 33

test_cas_vis1_n_1920		99.76 39	99.86 13	99.45 207	99.93 24	98.40 303	99.30 144	99.98 12	99.94 28	99.99 7	99.89 38	99.80 17	99.97 37	99.96 9	99.97 61	99.97 10

fmvsm_l_conf0.5_n		99.80 26	99.78 34	99.85 29	99.88 44	99.66 108	99.11 213	99.91 44	99.98 15	99.96 28	99.64 198	99.60 39	99.99 8	99.95 13	99.99 16	99.88 33

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 36	99.82 74	99.70 97	99.17 188	99.97 20	99.99 3	99.96 28	99.82 83	99.94 4	100.00 1	99.95 13	100.00 1	99.80 56

test_fmvs1		99.48 98	99.65 59	98.97 304	99.54 228	97.16 364	99.11 213	99.98 12	99.78 79	99.96 28	99.81 90	98.72 153	99.97 37	99.95 13	99.97 61	99.79 64

mvsany_test3		99.85 12	99.88 7	99.75 82	99.95 15	99.37 189	99.53 88	99.98 12	99.77 83	99.99 7	99.95 16	99.85 11	99.94 84	99.95 13	99.98 44	99.94 17

fmvsm_s_conf0.1_n_2		99.81 25	99.78 34	99.89 11	99.93 24	99.76 64	98.92 264	99.98 12	99.99 3	99.99 7	99.88 47	99.43 54	99.94 84	99.94 17	99.99 16	99.99 2

fmvsm_l_conf0.5_n_a		99.80 26	99.79 30	99.84 33	99.88 44	99.64 117	99.12 208	99.91 44	99.98 15	99.95 38	99.67 186	99.67 30	99.99 8	99.94 17	99.99 16	99.88 33

MM		99.18 186	99.05 193	99.55 178	99.35 298	98.81 269	99.05 229	97.79 404	99.99 3	99.48 231	99.59 239	96.29 315	99.95 68	99.94 17	99.98 44	99.88 33

test_fmvsmconf_n		99.85 12	99.84 20	99.88 18	99.91 31	99.73 81	98.97 255	99.98 12	99.99 3	99.96 28	99.85 65	99.93 7	99.99 8	99.94 17	99.99 16	99.93 20

fmvsm_s_conf0.5_n_5		99.78 31	99.76 42	99.85 29	99.79 102	99.72 86	98.84 273	99.96 27	99.96 23	99.96 28	99.72 146	99.71 24	99.99 8	99.93 21	99.98 44	99.85 42

fmvsm_s_conf0.5_n_2		99.78 31	99.75 44	99.88 18	99.82 74	99.76 64	98.88 267	99.92 38	99.98 15	99.98 14	99.85 65	99.42 56	99.94 84	99.93 21	99.98 44	99.94 17

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 38	99.10 216	99.98 12	99.99 3	99.98 14	99.91 28	99.68 29	99.93 104	99.93 21	99.99 16	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 52	99.07 228	99.98 12	99.99 3	99.98 14	99.90 33	99.88 9	99.92 130	99.93 21	99.99 16	99.98 5

fmvsm_s_conf0.5_n_a		99.82 23	99.79 30	99.89 11	99.85 59	99.82 38	99.03 237	99.96 27	99.99 3	99.97 22	99.84 72	99.58 41	99.93 104	99.92 25	99.98 44	99.93 20

fmvsm_s_conf0.5_n		99.83 21	99.81 26	99.87 23	99.85 59	99.78 52	99.03 237	99.96 27	99.99 3	99.97 22	99.84 72	99.78 19	99.92 130	99.92 25	99.99 16	99.92 24

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 20	99.99 3	100.00 1	99.98 13	99.78 19	100.00 1	99.92 25	100.00 1	99.87 37

fmvsm_s_conf0.5_n_4		99.78 31	99.78 34	99.79 58	99.75 134	99.56 142	98.98 253	99.94 35	99.92 33	99.97 22	99.72 146	99.84 13	99.92 130	99.91 28	99.98 44	99.89 31

MVStest1		98.22 313	98.09 308	98.62 339	99.04 368	96.23 385	99.20 176	99.92 38	99.44 156	99.98 14	99.87 53	85.87 408	99.67 377	99.91 28	99.57 292	99.95 14

v1921920		99.56 81	99.57 80	99.55 178	99.75 134	99.11 236	99.05 229	99.61 194	99.15 208	99.88 68	99.71 156	99.08 102	99.87 219	99.90 30	99.97 61	99.66 118

v1240		99.56 81	99.58 76	99.51 189	99.80 90	99.00 248	99.00 245	99.65 174	99.15 208	99.90 55	99.75 131	99.09 99	99.88 205	99.90 30	99.96 74	99.67 109

v10		99.69 50	99.69 51	99.66 125	99.81 83	99.39 184	99.66 54	99.75 117	99.60 130	99.92 49	99.87 53	98.75 148	99.86 238	99.90 30	99.99 16	99.73 80

v1192		99.57 78	99.57 80	99.57 171	99.77 118	99.22 221	99.04 234	99.60 205	99.18 197	99.87 76	99.72 146	99.08 102	99.85 256	99.89 33	99.98 44	99.66 118

fmvsm_s_conf0.5_n_3		99.79 29	99.77 38	99.85 29	99.81 83	99.71 89	98.97 255	99.92 38	99.98 15	99.97 22	99.86 60	99.53 48	99.95 68	99.88 34	99.99 16	99.89 31

v144192		99.55 84	99.54 87	99.58 165	99.78 110	99.20 226	99.11 213	99.62 187	99.18 197	99.89 59	99.72 146	98.66 161	99.87 219	99.88 34	99.97 61	99.66 118

v8		99.68 53	99.69 51	99.65 131	99.80 90	99.40 181	99.66 54	99.76 112	99.64 115	99.93 44	99.85 65	98.66 161	99.84 271	99.88 34	99.99 16	99.71 86

mvs5depth		99.88 6	99.91 3	99.80 51	99.92 29	99.42 174	99.94 3	100.00 1	99.97 20	99.89 59	99.99 12	99.63 33	99.97 37	99.87 37	99.99 16	100.00 1

v1144		99.54 87	99.53 91	99.59 162	99.79 102	99.28 207	99.10 216	99.61 194	99.20 195	99.84 83	99.73 139	98.67 159	99.84 271	99.86 38	99.98 44	99.64 136

mmtdpeth		99.78 31	99.83 21	99.66 125	99.85 59	99.05 247	99.79 12	99.97 20	100.00 1	99.43 243	99.94 19	99.64 31	99.94 84	99.83 39	99.99 16	99.98 5

SSC-MVS		99.52 90	99.42 109	99.83 36	99.86 55	99.65 114	99.52 89	99.81 89	99.87 50	99.81 96	99.79 103	96.78 296	99.99 8	99.83 39	99.51 308	99.86 39

v7n		99.82 23	99.80 29	99.88 18	99.96 7	99.84 25	99.82 9	99.82 80	99.84 62	99.94 41	99.91 28	99.13 95	99.96 58	99.83 39	99.99 16	99.83 49

v2v482		99.50 92	99.47 96	99.58 165	99.78 110	99.25 214	99.14 198	99.58 220	99.25 186	99.81 96	99.62 217	98.24 216	99.84 271	99.83 39	99.97 61	99.64 136

test_vis1_rt		99.45 111	99.46 100	99.41 224	99.71 151	98.63 289	98.99 250	99.96 27	99.03 221	99.95 38	99.12 354	98.75 148	99.84 271	99.82 43	99.82 189	99.77 70

tt0805		99.63 67	99.57 80	99.81 46	99.87 52	99.88 12	99.58 79	98.70 366	99.72 89	99.91 52	99.60 234	99.43 54	99.81 311	99.81 44	99.53 304	99.73 80

V42		99.56 81	99.54 87	99.63 145	99.79 102	99.46 160	99.39 117	99.59 211	99.24 188	99.86 77	99.70 164	98.55 175	99.82 296	99.79 45	99.95 88	99.60 166

SSC-MVS3.2		99.64 66	99.67 55	99.56 174	99.75 134	98.98 251	98.96 258	99.87 57	99.88 48	99.84 83	99.64 198	99.32 70	99.91 153	99.78 46	99.96 74	99.80 56

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 49	99.72 30	99.88 55	99.92 33	99.98 14	99.93 21	99.94 4	99.98 23	99.77 47	100.00 1	99.92 24

WB-MVS		99.44 113	99.32 130	99.80 51	99.81 83	99.61 130	99.47 105	99.81 89	99.82 69	99.71 145	99.72 146	96.60 300	99.98 23	99.75 48	99.23 349	99.82 55

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 57	99.68 46	99.85 67	99.95 25	99.98 14	99.92 25	99.28 75	99.98 23	99.75 48	100.00 1	99.94 17

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 52	99.70 35	99.86 61	99.89 43	99.98 14	99.90 33	99.94 4	99.98 23	99.75 48	100.00 1	99.90 26

ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 59	100.00 1	99.90 37	100.00 1	99.97 14	99.61 37	99.97 37	99.75 48	100.00 1	99.84 45

reproduce_monomvs		97.40 345	97.46 339	97.20 393	99.05 365	91.91 421	99.20 176	99.18 339	99.84 62	99.86 77	99.75 131	80.67 416	99.83 286	99.69 52	99.95 88	99.85 42

SPE-MVS-test		99.68 53	99.70 48	99.64 138	99.57 212	99.83 30	99.78 14	99.97 20	99.92 33	99.50 228	99.38 303	99.57 43	99.95 68	99.69 52	99.90 123	99.15 315

MVS_0304		98.61 271	98.30 292	99.52 186	97.88 428	98.95 257	98.76 290	94.11 427	99.84 62	99.32 273	99.57 249	95.57 326	99.95 68	99.68 54	99.98 44	99.68 101

CS-MVS		99.67 59	99.70 48	99.58 165	99.53 234	99.84 25	99.79 12	99.96 27	99.90 37	99.61 187	99.41 293	99.51 51	99.95 68	99.66 55	99.89 133	98.96 357

mamv4		99.73 43	99.74 45	99.70 111	99.66 178	99.87 14	99.69 42	99.93 36	99.93 30	99.93 44	99.86 60	99.07 104	100.00 1	99.66 55	99.92 112	99.24 290

pmmvs6		99.86 10	99.86 13	99.83 36	99.94 18	99.90 7	99.83 7	99.91 44	99.85 59	99.94 41	99.95 16	99.73 23	99.90 172	99.65 57	99.97 61	99.69 95

MIMVSNet1		99.66 60	99.62 64	99.80 51	99.94 18	99.87 14	99.69 42	99.77 107	99.78 79	99.93 44	99.89 38	97.94 241	99.92 130	99.65 57	99.98 44	99.62 152

EC-MVSNet		99.69 50	99.69 51	99.68 115	99.71 151	99.91 4	99.76 20	99.96 27	99.86 53	99.51 226	99.39 301	99.57 43	99.93 104	99.64 59	99.86 162	99.20 303

K. test v3		98.87 248	98.60 257	99.69 113	99.93 24	99.46 160	99.74 24	94.97 422	99.78 79	99.88 68	99.88 47	93.66 347	99.97 37	99.61 60	99.95 88	99.64 136

KD-MVS_self_test		99.63 67	99.59 73	99.76 72	99.84 63	99.90 7	99.37 124	99.79 98	99.83 67	99.88 68	99.85 65	98.42 196	99.90 172	99.60 61	99.73 237	99.49 224

Anonymous20240521		99.44 113	99.42 109	99.49 195	99.89 39	98.96 256	99.62 64	99.76 112	99.85 59	99.82 89	99.88 47	96.39 310	99.97 37	99.59 62	99.98 44	99.55 188

TransMVSNet (Re)		99.78 31	99.77 38	99.81 46	99.91 31	99.85 20	99.75 22	99.86 61	99.70 96	99.91 52	99.89 38	99.60 39	99.87 219	99.59 62	99.74 231	99.71 86

OurMVSNet-221017-0		99.75 40	99.71 47	99.84 33	99.96 7	99.83 30	99.83 7	99.85 67	99.80 75	99.93 44	99.93 21	98.54 177	99.93 104	99.59 62	99.98 44	99.76 75

EU-MVSNet		99.39 129	99.62 64	98.72 335	99.88 44	96.44 379	99.56 84	99.85 67	99.90 37	99.90 55	99.85 65	98.09 230	99.83 286	99.58 65	99.95 88	99.90 26

mvs_anonymous		99.28 153	99.39 113	98.94 308	99.19 341	97.81 343	99.02 240	99.55 233	99.78 79	99.85 80	99.80 93	98.24 216	99.86 238	99.57 66	99.50 311	99.15 315

test1111		97.74 331	98.16 304	96.49 404	99.60 192	89.86 435	99.71 34	91.21 431	99.89 43	99.88 68	99.87 53	93.73 346	99.90 172	99.56 67	99.99 16	99.70 89

lessismore_v0				99.64 138	99.86 55	99.38 186		90.66 432		99.89 59	99.83 76	94.56 337	99.97 37	99.56 67	99.92 112	99.57 183

mvsany_test1		99.44 113	99.45 102	99.40 226	99.37 291	98.64 288	97.90 381	99.59 211	99.27 182	99.92 49	99.82 83	99.74 22	99.93 104	99.55 69	99.87 154	99.63 141

MVSMamba_PlusPlus		99.55 84	99.58 76	99.47 201	99.68 171	99.40 181	99.52 89	99.70 144	99.92 33	99.77 118	99.86 60	98.28 212	99.96 58	99.54 70	99.90 123	99.05 344

pm-mvs1		99.79 29	99.79 30	99.78 62	99.91 31	99.83 30	99.76 20	99.87 57	99.73 85	99.89 59	99.87 53	99.63 33	99.87 219	99.54 70	99.92 112	99.63 141

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 18	99.91 31	99.90 7	99.96 1	99.92 38	99.90 37	99.97 22	99.87 53	99.81 16	99.95 68	99.54 70	99.99 16	99.80 56
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 98	99.65 59	98.95 307	99.71 151	97.27 361	99.50 96	99.82 80	99.59 132	99.41 252	99.85 65	99.62 36	100.00 1	99.53 73	99.89 133	99.59 173

test2506		94.73 395	94.59 396	95.15 411	99.59 197	85.90 437	99.75 22	74.01 439	99.89 43	99.71 145	99.86 60	79.00 426	99.90 172	99.52 74	99.99 16	99.65 126

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 139	99.93 30	99.95 38	99.89 38	99.71 24	99.96 58	99.51 75	99.97 61	99.84 45

FC-MVSNet-test		99.70 48	99.65 59	99.86 27	99.88 44	99.86 18	99.72 30	99.78 104	99.90 37	99.82 89	99.83 76	98.45 192	99.87 219	99.51 75	99.97 61	99.86 39

BP-MVS1		98.72 263	98.46 273	99.50 191	99.53 234	99.00 248	99.34 129	98.53 376	99.65 112	99.73 138	99.38 303	90.62 382	99.96 58	99.50 77	99.86 162	99.55 188

UA-Net		99.78 31	99.76 42	99.86 27	99.72 148	99.71 89	99.91 4	99.95 33	99.96 23	99.71 145	99.91 28	99.15 90	99.97 37	99.50 77	100.00 1	99.90 26

PMMVS2		99.48 98	99.45 102	99.57 171	99.76 122	98.99 250	98.09 358	99.90 49	98.95 231	99.78 110	99.58 242	99.57 43	99.93 104	99.48 79	99.95 88	99.79 64

VPA-MVSNet		99.66 60	99.62 64	99.79 58	99.68 171	99.75 72	99.62 64	99.69 151	99.85 59	99.80 100	99.81 90	98.81 136	99.91 153	99.47 80	99.88 142	99.70 89

GDP-MVS		98.81 254	98.57 263	99.50 191	99.53 234	99.12 235	99.28 153	99.86 61	99.53 136	99.57 198	99.32 319	90.88 378	99.98 23	99.46 81	99.74 231	99.42 252

ECVR-MVS		97.73 332	98.04 311	96.78 397	99.59 197	90.81 430	99.72 30	90.43 433	99.89 43	99.86 77	99.86 60	93.60 348	99.89 191	99.46 81	99.99 16	99.65 126

nrg030		99.70 48	99.66 57	99.82 41	99.76 122	99.84 25	99.61 70	99.70 144	99.93 30	99.78 110	99.68 182	99.10 97	99.78 324	99.45 83	99.96 74	99.83 49

TAMVS		99.49 96	99.45 102	99.63 145	99.48 259	99.42 174	99.45 109	99.57 222	99.66 109	99.78 110	99.83 76	97.85 248	99.86 238	99.44 84	99.96 74	99.61 162

GeoE		99.69 50	99.66 57	99.78 62	99.76 122	99.76 64	99.60 76	99.82 80	99.46 151	99.75 126	99.56 253	99.63 33	99.95 68	99.43 85	99.88 142	99.62 152

new-patchmatchnet		99.35 139	99.57 80	98.71 337	99.82 74	96.62 376	98.55 314	99.75 117	99.50 140	99.88 68	99.87 53	99.31 71	99.88 205	99.43 85	100.00 1	99.62 152

test20.03		99.55 84	99.54 87	99.58 165	99.79 102	99.37 189	99.02 240	99.89 51	99.60 130	99.82 89	99.62 217	98.81 136	99.89 191	99.43 85	99.86 162	99.47 232

MVSFormer		99.41 123	99.44 105	99.31 253	99.57 212	98.40 303	99.77 16	99.80 92	99.73 85	99.63 172	99.30 324	98.02 235	99.98 23	99.43 85	99.69 252	99.55 188

test_djsdf		99.84 17	99.81 26	99.91 3	99.94 18	99.84 25	99.77 16	99.80 92	99.73 85	99.97 22	99.92 25	99.77 21	99.98 23	99.43 85	100.00 1	99.90 26

SDMVSNet		99.77 38	99.77 38	99.76 72	99.80 90	99.65 114	99.63 61	99.86 61	99.97 20	99.89 59	99.89 38	99.52 50	99.99 8	99.42 90	99.96 74	99.65 126

Anonymous20231211		99.62 73	99.57 80	99.76 72	99.61 190	99.60 133	99.81 10	99.73 127	99.82 69	99.90 55	99.90 33	97.97 240	99.86 238	99.42 90	99.96 74	99.80 56

SixPastTwentyTwo		99.42 119	99.30 137	99.76 72	99.92 29	99.67 106	99.70 35	99.14 344	99.65 112	99.89 59	99.90 33	96.20 317	99.94 84	99.42 90	99.92 112	99.67 109

balanced_conf03		99.50 92	99.50 93	99.50 191	99.42 282	99.49 153	99.52 89	99.75 117	99.86 53	99.78 110	99.71 156	98.20 223	99.90 172	99.39 93	99.88 142	99.10 326

patch_mono-2		99.51 91	99.46 100	99.64 138	99.70 159	99.11 236	99.04 234	99.87 57	99.71 91	99.47 233	99.79 103	98.24 216	99.98 23	99.38 94	99.96 74	99.83 49

UGNet		99.38 131	99.34 125	99.49 195	98.90 380	98.90 264	99.70 35	99.35 303	99.86 53	98.57 365	99.81 90	98.50 187	99.93 104	99.38 94	99.98 44	99.66 118
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 47	99.67 55	99.81 46	99.89 39	99.72 86	99.59 77	99.82 80	99.39 167	99.82 89	99.84 72	99.38 62	99.91 153	99.38 94	99.93 108	99.80 56

FIs		99.65 65	99.58 76	99.84 33	99.84 63	99.85 20	99.66 54	99.75 117	99.86 53	99.74 134	99.79 103	98.27 214	99.85 256	99.37 97	99.93 108	99.83 49

sd_testset		99.78 31	99.78 34	99.80 51	99.80 90	99.76 64	99.80 11	99.79 98	99.97 20	99.89 59	99.89 38	99.53 48	99.99 8	99.36 98	99.96 74	99.65 126

anonymousdsp		99.80 26	99.77 38	99.90 8	99.96 7	99.88 12	99.73 27	99.85 67	99.70 96	99.92 49	99.93 21	99.45 53	99.97 37	99.36 98	100.00 1	99.85 42

casdiffmvs_mvg		99.68 53	99.68 54	99.69 113	99.81 83	99.59 135	99.29 151	99.90 49	99.71 91	99.79 106	99.73 139	99.54 46	99.84 271	99.36 98	99.96 74	99.65 126
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 40	99.74 45	99.79 58	99.88 44	99.66 108	99.69 42	99.92 38	99.67 105	99.77 118	99.75 131	99.61 37	99.98 23	99.35 101	99.98 44	99.72 83
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 75	99.64 62	99.53 184	99.79 102	98.82 268	99.58 79	99.97 20	99.95 25	99.96 28	99.76 126	98.44 193	99.99 8	99.34 102	99.96 74	99.78 66

CHOSEN 1792x2688		99.39 129	99.30 137	99.65 131	99.88 44	99.25 214	98.78 288	99.88 55	98.66 271	99.96 28	99.79 103	97.45 270	99.93 104	99.34 102	99.99 16	99.78 66

CDS-MVSNet		99.22 172	99.13 165	99.50 191	99.35 298	99.11 236	98.96 258	99.54 239	99.46 151	99.61 187	99.70 164	96.31 313	99.83 286	99.34 102	99.88 142	99.55 188
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 228	99.16 159	98.51 345	99.75 134	95.90 391	98.07 361	99.84 73	99.84 62	99.89 59	99.73 139	96.01 320	99.99 8	99.33 105	100.00 1	99.63 141

HyFIR lowres test		98.91 241	98.64 254	99.73 96	99.85 59	99.47 156	98.07 361	99.83 75	98.64 273	99.89 59	99.60 234	92.57 357	100.00 1	99.33 105	99.97 61	99.72 83

pmmvs5		99.19 182	99.11 172	99.42 217	99.76 122	98.88 265	98.55 314	99.73 127	98.82 251	99.72 140	99.62 217	96.56 301	99.82 296	99.32 107	99.95 88	99.56 185

v148		99.40 125	99.41 111	99.39 229	99.76 122	98.94 258	99.09 221	99.59 211	99.17 202	99.81 96	99.61 226	98.41 197	99.69 360	99.32 107	99.94 101	99.53 202

baseline		99.63 67	99.62 64	99.66 125	99.80 90	99.62 124	99.44 111	99.80 92	99.71 91	99.72 140	99.69 171	99.15 90	99.83 286	99.32 107	99.94 101	99.53 202

CVMVSNet		98.61 271	98.88 234	97.80 376	99.58 202	93.60 414	99.26 159	99.64 182	99.66 109	99.72 140	99.67 186	93.26 350	99.93 104	99.30 110	99.81 199	99.87 37

PS-CasMVS		99.66 60	99.58 76	99.89 11	99.80 90	99.85 20	99.66 54	99.73 127	99.62 120	99.84 83	99.71 156	98.62 165	99.96 58	99.30 110	99.96 74	99.86 39

DTE-MVSNet		99.68 53	99.61 68	99.88 18	99.80 90	99.87 14	99.67 50	99.71 139	99.72 89	99.84 83	99.78 114	98.67 159	99.97 37	99.30 110	99.95 88	99.80 56

tmp_tt		95.75 388	95.42 383	96.76 398	89.90 438	94.42 408	98.86 270	97.87 402	78.01 429	99.30 283	99.69 171	97.70 256	95.89 431	99.29 113	98.14 407	99.95 14

PEN-MVS		99.66 60	99.59 73	99.89 11	99.83 67	99.87 14	99.66 54	99.73 127	99.70 96	99.84 83	99.73 139	98.56 174	99.96 58	99.29 113	99.94 101	99.83 49

WR-MVS_H		99.61 75	99.53 91	99.87 23	99.80 90	99.83 30	99.67 50	99.75 117	99.58 133	99.85 80	99.69 171	98.18 226	99.94 84	99.28 115	99.95 88	99.83 49

IterMVS		98.97 232	99.16 159	98.42 350	99.74 142	95.64 395	98.06 363	99.83 75	99.83 67	99.85 80	99.74 135	96.10 319	99.99 8	99.27 116	100.00 1	99.63 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WBMVS		97.50 342	97.18 348	98.48 347	98.85 388	95.89 392	98.44 331	99.52 253	99.53 136	99.52 220	99.42 292	80.10 419	99.86 238	99.24 117	99.95 88	99.68 101

h-mvs33		98.61 271	98.34 287	99.44 211	99.60 192	98.67 280	99.27 157	99.44 278	99.68 101	99.32 273	99.49 275	92.50 360	100.00 1	99.24 117	96.51 424	99.65 126

hse-mvs2		98.52 284	98.30 292	99.16 279	99.29 320	98.60 291	98.77 289	99.02 352	99.68 101	99.32 273	99.04 364	92.50 360	99.85 256	99.24 117	97.87 414	99.03 348

FMVSNet1		99.66 60	99.63 63	99.73 96	99.78 110	99.77 57	99.68 46	99.70 144	99.67 105	99.82 89	99.83 76	98.98 118	99.90 172	99.24 117	99.97 61	99.53 202

casdiffmvs		99.63 67	99.61 68	99.67 118	99.79 102	99.59 135	99.13 204	99.85 67	99.79 77	99.76 121	99.72 146	99.33 69	99.82 296	99.21 121	99.94 101	99.59 173
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 87	99.43 107	99.87 23	99.76 122	99.82 38	99.57 82	99.61 194	99.54 134	99.80 100	99.64 198	97.79 252	99.95 68	99.21 121	99.94 101	99.84 45

DELS-MVS		99.34 144	99.30 137	99.48 199	99.51 243	99.36 193	98.12 354	99.53 248	99.36 172	99.41 252	99.61 226	99.22 83	99.87 219	99.21 121	99.68 257	99.20 303
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
UniMVSNet (Re)		99.37 134	99.26 148	99.68 115	99.51 243	99.58 139	98.98 253	99.60 205	99.43 162	99.70 149	99.36 310	97.70 256	99.88 205	99.20 124	99.87 154	99.59 173

CANet		99.11 203	99.05 193	99.28 260	98.83 390	98.56 293	98.71 296	99.41 284	99.25 186	99.23 291	99.22 342	97.66 264	99.94 84	99.19 125	99.97 61	99.33 272

EI-MVSNet-UG-set		99.48 98	99.50 93	99.42 217	99.57 212	98.65 286	99.24 166	99.46 273	99.68 101	99.80 100	99.66 191	98.99 116	99.89 191	99.19 125	99.90 123	99.72 83

xiu_mvs_v1_base_debu		99.23 164	99.34 125	98.91 314	99.59 197	98.23 312	98.47 326	99.66 164	99.61 124	99.68 155	98.94 380	99.39 58	99.97 37	99.18 127	99.55 297	98.51 396

xiu_mvs_v1_base		99.23 164	99.34 125	98.91 314	99.59 197	98.23 312	98.47 326	99.66 164	99.61 124	99.68 155	98.94 380	99.39 58	99.97 37	99.18 127	99.55 297	98.51 396

xiu_mvs_v1_base_debi		99.23 164	99.34 125	98.91 314	99.59 197	98.23 312	98.47 326	99.66 164	99.61 124	99.68 155	98.94 380	99.39 58	99.97 37	99.18 127	99.55 297	98.51 396

VPNet		99.46 107	99.37 118	99.71 107	99.82 74	99.59 135	99.48 102	99.70 144	99.81 72	99.69 152	99.58 242	97.66 264	99.86 238	99.17 130	99.44 318	99.67 109

UniMVSNet_NR-MVSNet		99.37 134	99.25 150	99.72 102	99.47 265	99.56 142	98.97 255	99.61 194	99.43 162	99.67 160	99.28 328	97.85 248	99.95 68	99.17 130	99.81 199	99.65 126

DU-MVS		99.33 147	99.21 154	99.71 107	99.43 277	99.56 142	98.83 276	99.53 248	99.38 168	99.67 160	99.36 310	97.67 260	99.95 68	99.17 130	99.81 199	99.63 141

EI-MVSNet-Vis-set		99.47 106	99.49 95	99.42 217	99.57 212	98.66 283	99.24 166	99.46 273	99.67 105	99.79 106	99.65 196	98.97 120	99.89 191	99.15 133	99.89 133	99.71 86

EI-MVSNet		99.38 131	99.44 105	99.21 273	99.58 202	98.09 326	99.26 159	99.46 273	99.62 120	99.75 126	99.67 186	98.54 177	99.85 256	99.15 133	99.92 112	99.68 101

VNet		99.18 186	99.06 189	99.56 174	99.24 331	99.36 193	99.33 133	99.31 312	99.67 105	99.47 233	99.57 249	96.48 304	99.84 271	99.15 133	99.30 337	99.47 232

EG-PatchMatch MVS		99.57 78	99.56 85	99.62 154	99.77 118	99.33 199	99.26 159	99.76 112	99.32 176	99.80 100	99.78 114	99.29 73	99.87 219	99.15 133	99.91 122	99.66 118

PVSNet_Blended_VisFu		99.40 125	99.38 115	99.44 211	99.90 37	98.66 283	98.94 262	99.91 44	97.97 334	99.79 106	99.73 139	99.05 109	99.97 37	99.15 133	99.99 16	99.68 101

IterMVS-LS		99.41 123	99.47 96	99.25 269	99.81 83	98.09 326	98.85 272	99.76 112	99.62 120	99.83 88	99.64 198	98.54 177	99.97 37	99.15 133	99.99 16	99.68 101
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 87	99.47 96	99.76 72	99.58 202	99.64 117	99.30 144	99.63 184	99.61 124	99.71 145	99.56 253	98.76 146	99.96 58	99.14 139	99.92 112	99.68 101

MVSTER		98.47 291	98.22 297	99.24 271	99.06 364	98.35 309	99.08 224	99.46 273	99.27 182	99.75 126	99.66 191	88.61 395	99.85 256	99.14 139	99.92 112	99.52 212

Anonymous20231206		99.35 139	99.31 132	99.47 201	99.74 142	99.06 246	99.28 153	99.74 123	99.23 190	99.72 140	99.53 264	97.63 266	99.88 205	99.11 141	99.84 172	99.48 228

Syy-MVS		98.17 316	97.85 328	99.15 281	98.50 413	98.79 272	98.60 303	99.21 335	97.89 340	96.76 416	96.37 439	95.47 328	99.57 402	99.10 142	98.73 383	99.09 331

ttmdpeth		99.48 98	99.55 86	99.29 257	99.76 122	98.16 320	99.33 133	99.95 33	99.79 77	99.36 262	99.89 38	99.13 95	99.77 332	99.09 143	99.64 270	99.93 20

MVS_Test		99.28 153	99.31 132	99.19 276	99.35 298	98.79 272	99.36 127	99.49 266	99.17 202	99.21 296	99.67 186	98.78 143	99.66 382	99.09 143	99.66 266	99.10 326

testgi		99.29 152	99.26 148	99.37 235	99.75 134	98.81 269	98.84 273	99.89 51	98.38 301	99.75 126	99.04 364	99.36 67	99.86 238	99.08 145	99.25 345	99.45 237

1112_ss		99.05 214	98.84 239	99.67 118	99.66 178	99.29 205	98.52 320	99.82 80	97.65 352	99.43 243	99.16 348	96.42 307	99.91 153	99.07 146	99.84 172	99.80 56

CANet_DTU		98.91 241	98.85 237	99.09 290	98.79 396	98.13 321	98.18 347	99.31 312	99.48 143	98.86 336	99.51 268	96.56 301	99.95 68	99.05 147	99.95 88	99.19 306

Baseline_NR-MVSNet		99.49 96	99.37 118	99.82 41	99.91 31	99.84 25	98.83 276	99.86 61	99.68 101	99.65 167	99.88 47	97.67 260	99.87 219	99.03 148	99.86 162	99.76 75

FMVSNet2		99.35 139	99.28 144	99.55 178	99.49 254	99.35 196	99.45 109	99.57 222	99.44 156	99.70 149	99.74 135	97.21 281	99.87 219	99.03 148	99.94 101	99.44 242

Test_1112_low_res		98.95 238	98.73 248	99.63 145	99.68 171	99.15 232	98.09 358	99.80 92	97.14 378	99.46 237	99.40 297	96.11 318	99.89 191	99.01 150	99.84 172	99.84 45

VDD-MVS		99.20 179	99.11 172	99.44 211	99.43 277	98.98 251	99.50 96	98.32 390	99.80 75	99.56 206	99.69 171	96.99 291	99.85 256	98.99 151	99.73 237	99.50 219

DeepC-MVS	98.90 4	99.62 73	99.61 68	99.67 118	99.72 148	99.44 167	99.24 166	99.71 139	99.27 182	99.93 44	99.90 33	99.70 27	99.93 104	98.99 151	99.99 16	99.64 136
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 98	99.47 96	99.51 189	99.77 118	99.41 180	98.81 281	99.66 164	99.42 166	99.75 126	99.66 191	99.20 85	99.76 335	98.98 153	99.99 16	99.36 265

EPNet_dtu		97.62 337	97.79 331	97.11 396	96.67 433	92.31 419	98.51 321	98.04 396	99.24 188	95.77 425	99.47 282	93.78 345	99.66 382	98.98 153	99.62 274	99.37 262
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 144	99.32 130	99.39 229	99.67 177	98.77 274	98.57 312	99.81 89	99.61 124	99.48 231	99.41 293	98.47 188	99.86 238	98.97 155	99.90 123	99.53 202
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		99.40 125	99.31 132	99.68 115	99.43 277	99.55 146	99.73 27	99.50 262	99.46 151	99.88 68	99.36 310	97.54 267	99.87 219	98.97 155	99.87 154	99.63 141

GBi-Net		99.42 119	99.31 132	99.73 96	99.49 254	99.77 57	99.68 46	99.70 144	99.44 156	99.62 181	99.83 76	97.21 281	99.90 172	98.96 157	99.90 123	99.53 202

FMVSNet5		97.80 329	97.25 346	99.42 217	98.83 390	98.97 254	99.38 120	99.80 92	98.87 243	99.25 287	99.69 171	80.60 418	99.91 153	98.96 157	99.90 123	99.38 259

test1		99.42 119	99.31 132	99.73 96	99.49 254	99.77 57	99.68 46	99.70 144	99.44 156	99.62 181	99.83 76	97.21 281	99.90 172	98.96 157	99.90 123	99.53 202

FMVSNet3		98.80 255	98.63 256	99.32 250	99.13 350	98.72 277	99.10 216	99.48 267	99.23 190	99.62 181	99.64 198	92.57 357	99.86 238	98.96 157	99.90 123	99.39 257

UnsupCasMVSNet_eth		98.83 251	98.57 263	99.59 162	99.68 171	99.45 165	98.99 250	99.67 159	99.48 143	99.55 211	99.36 310	94.92 331	99.86 238	98.95 161	96.57 423	99.45 237

CHOSEN 280x420		98.41 296	98.41 279	98.40 351	99.34 307	95.89 392	96.94 417	99.44 278	98.80 255	99.25 287	99.52 266	93.51 349	99.98 23	98.94 162	99.98 44	99.32 275

TDRefinement		99.72 44	99.70 48	99.77 65	99.90 37	99.85 20	99.86 6	99.92 38	99.69 99	99.78 110	99.92 25	99.37 64	99.88 205	98.93 163	99.95 88	99.60 166

alignmvs		98.28 306	97.96 317	99.25 269	99.12 352	98.93 261	99.03 237	98.42 383	99.64 115	98.72 351	97.85 418	90.86 379	99.62 393	98.88 164	99.13 351	99.19 306

testing3-2		96.51 367	96.43 362	96.74 400	99.36 294	91.38 427	99.10 216	97.87 402	99.48 143	98.57 365	98.71 394	76.65 428	99.66 382	98.87 165	99.26 344	99.18 308

MGCFI-Net		99.02 220	99.01 205	99.06 297	99.11 357	98.60 291	99.63 61	99.67 159	99.63 117	98.58 363	97.65 421	99.07 104	99.57 402	98.85 166	98.92 367	99.03 348

sss		98.90 243	98.77 247	99.27 263	99.48 259	98.44 300	98.72 294	99.32 308	97.94 338	99.37 261	99.35 315	96.31 313	99.91 153	98.85 166	99.63 273	99.47 232

xiu_mvs_v2_base		99.02 220	99.11 172	98.77 332	99.37 291	98.09 326	98.13 353	99.51 258	99.47 148	99.42 246	98.54 403	99.38 62	99.97 37	98.83 168	99.33 333	98.24 408

PS-MVSNAJ		99.00 228	99.08 183	98.76 333	99.37 291	98.10 325	98.00 369	99.51 258	99.47 148	99.41 252	98.50 405	99.28 75	99.97 37	98.83 168	99.34 332	98.20 412

D2MVS		99.22 172	99.19 156	99.29 257	99.69 163	98.74 276	98.81 281	99.41 284	98.55 282	99.68 155	99.69 171	98.13 228	99.87 219	98.82 170	99.98 44	99.24 290

PatchT		98.45 293	98.32 289	98.83 327	98.94 378	98.29 310	99.24 166	98.82 360	99.84 62	99.08 313	99.76 126	91.37 368	99.94 84	98.82 170	99.00 362	98.26 407

testf1		99.63 67	99.60 71	99.72 102	99.94 18	99.95 2	99.47 105	99.89 51	99.43 162	99.88 68	99.80 93	99.26 79	99.90 172	98.81 172	99.88 142	99.32 275

APD_test2		99.63 67	99.60 71	99.72 102	99.94 18	99.95 2	99.47 105	99.89 51	99.43 162	99.88 68	99.80 93	99.26 79	99.90 172	98.81 172	99.88 142	99.32 275

sasdasda		99.02 220	99.00 209	99.09 290	99.10 359	98.70 278	99.61 70	99.66 164	99.63 117	98.64 357	97.65 421	99.04 110	99.54 406	98.79 174	98.92 367	99.04 346

Effi-MVS+		99.06 211	98.97 220	99.34 242	99.31 314	98.98 251	98.31 339	99.91 44	98.81 253	98.79 345	98.94 380	99.14 93	99.84 271	98.79 174	98.74 380	99.20 303

canonicalmvs		99.02 220	99.00 209	99.09 290	99.10 359	98.70 278	99.61 70	99.66 164	99.63 117	98.64 357	97.65 421	99.04 110	99.54 406	98.79 174	98.92 367	99.04 346

VDDNet		98.97 232	98.82 242	99.42 217	99.71 151	98.81 269	99.62 64	98.68 367	99.81 72	99.38 260	99.80 93	94.25 339	99.85 256	98.79 174	99.32 335	99.59 173

CR-MVSNet		98.35 303	98.20 299	98.83 327	99.05 365	98.12 322	99.30 144	99.67 159	97.39 366	99.16 302	99.79 103	91.87 365	99.91 153	98.78 178	98.77 376	98.44 401

test_method		91.72 396	92.32 399	89.91 414	93.49 437	70.18 440	90.28 428	99.56 227	61.71 432	95.39 427	99.52 266	93.90 341	99.94 84	98.76 179	98.27 400	99.62 152

RPMNet		98.60 274	98.53 269	98.83 327	99.05 365	98.12 322	99.30 144	99.62 187	99.86 53	99.16 302	99.74 135	92.53 359	99.92 130	98.75 180	98.77 376	98.44 401

pmmvs4		99.13 198	99.06 189	99.36 239	99.57 212	99.10 241	98.01 367	99.25 325	98.78 258	99.58 195	99.44 289	98.24 216	99.76 335	98.74 181	99.93 108	99.22 296

tttt0517		97.62 337	97.20 347	98.90 320	99.76 122	97.40 358	99.48 102	94.36 424	99.06 219	99.70 149	99.49 275	84.55 411	99.94 84	98.73 182	99.65 268	99.36 265

EPP-MVSNet		99.17 191	99.00 209	99.66 125	99.80 90	99.43 171	99.70 35	99.24 328	99.48 143	99.56 206	99.77 123	94.89 332	99.93 104	98.72 183	99.89 133	99.63 141

Anonymous20240529		99.42 119	99.34 125	99.65 131	99.53 234	99.60 133	99.63 61	99.39 294	99.47 148	99.76 121	99.78 114	98.13 228	99.86 238	98.70 184	99.68 257	99.49 224

ACMH	98.42 6	99.59 77	99.54 87	99.72 102	99.86 55	99.62 124	99.56 84	99.79 98	98.77 260	99.80 100	99.85 65	99.64 31	99.85 256	98.70 184	99.89 133	99.70 89
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 147	99.28 144	99.47 201	99.57 212	99.39 184	99.78 14	99.43 281	98.87 243	99.57 198	99.82 83	98.06 233	99.87 219	98.69 186	99.73 237	99.15 315

LFMVS		98.46 292	98.19 302	99.26 266	99.24 331	98.52 296	99.62 64	96.94 413	99.87 50	99.31 278	99.58 242	91.04 373	99.81 311	98.68 187	99.42 322	99.45 237

WR-MVS		99.11 203	98.93 225	99.66 125	99.30 318	99.42 174	98.42 332	99.37 299	99.04 220	99.57 198	99.20 346	96.89 293	99.86 238	98.66 188	99.87 154	99.70 89

mvsmamba		99.08 207	98.95 223	99.45 207	99.36 294	99.18 229	99.39 117	98.81 361	99.37 169	99.35 264	99.70 164	96.36 312	99.94 84	98.66 188	99.59 288	99.22 296

RRT-MVS		99.08 207	99.00 209	99.33 245	99.27 325	98.65 286	99.62 64	99.93 36	99.66 109	99.67 160	99.82 83	95.27 330	99.93 104	98.64 190	99.09 355	99.41 253

Anonymous202405211		98.75 259	98.46 273	99.63 145	99.34 307	99.66 108	99.47 105	97.65 405	99.28 181	99.56 206	99.50 271	93.15 351	99.84 271	98.62 191	99.58 290	99.40 255

EPNet		98.13 317	97.77 332	99.18 278	94.57 436	97.99 332	99.24 166	97.96 398	99.74 84	97.29 409	99.62 217	93.13 352	99.97 37	98.59 192	99.83 180	99.58 178
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 214	99.09 181	98.91 314	99.21 336	98.36 308	98.82 280	99.47 270	98.85 246	98.90 331	99.56 253	98.78 143	99.09 422	98.57 193	99.68 257	99.26 287

Patchmatch-RL test		98.60 274	98.36 284	99.33 245	99.77 118	99.07 244	98.27 341	99.87 57	98.91 238	99.74 134	99.72 146	90.57 384	99.79 321	98.55 194	99.85 167	99.11 324

pmmvs3		98.08 320	97.80 329	98.91 314	99.41 284	97.69 349	97.87 382	99.66 164	95.87 397	99.50 228	99.51 268	90.35 386	99.97 37	98.55 194	99.47 315	99.08 337

ETV-MVS		99.18 186	99.18 157	99.16 279	99.34 307	99.28 207	99.12 208	99.79 98	99.48 143	98.93 325	98.55 402	99.40 57	99.93 104	98.51 196	99.52 307	98.28 406

jason		99.16 192	99.11 172	99.32 250	99.75 134	98.44 300	98.26 343	99.39 294	98.70 268	99.74 134	99.30 324	98.54 177	99.97 37	98.48 197	99.82 189	99.55 188
jason: jason.
APDe-MVS		99.48 98	99.36 121	99.85 29	99.55 226	99.81 43	99.50 96	99.69 151	98.99 224	99.75 126	99.71 156	98.79 141	99.93 104	98.46 198	99.85 167	99.80 56
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CL-MVSNet_self_test		98.71 265	98.56 267	99.15 281	99.22 334	98.66 283	97.14 412	99.51 258	98.09 327	99.54 213	99.27 330	96.87 294	99.74 342	98.43 199	98.96 364	99.03 348

our_test_3		98.85 250	99.09 181	98.13 364	99.66 178	94.90 406	97.72 387	99.58 220	99.07 217	99.64 168	99.62 217	98.19 224	99.93 104	98.41 200	99.95 88	99.55 188

Gipuma		99.57 78	99.59 73	99.49 195	99.98 3	99.71 89	99.72 30	99.84 73	99.81 72	99.94 41	99.78 114	98.91 128	99.71 351	98.41 200	99.95 88	99.05 344
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 347	96.91 357	98.74 334	97.72 429	97.57 351	97.60 393	97.36 411	98.00 330	99.21 296	98.02 414	90.04 389	99.79 321	98.37 202	95.89 428	98.86 371

PM-MVS		99.36 137	99.29 142	99.58 165	99.83 67	99.66 108	98.95 260	99.86 61	98.85 246	99.81 96	99.73 139	98.40 201	99.92 130	98.36 203	99.83 180	99.17 311

baseline1		97.73 332	97.33 343	98.96 305	99.30 318	97.73 347	99.40 115	98.42 383	99.33 175	99.46 237	99.21 344	91.18 371	99.82 296	98.35 204	91.26 431	99.32 275

MVS-HIRNet		97.86 326	98.22 297	96.76 398	99.28 323	91.53 425	98.38 334	92.60 430	99.13 210	99.31 278	99.96 15	97.18 285	99.68 372	98.34 205	99.83 180	99.07 342

GA-MVS		97.99 325	97.68 335	98.93 311	99.52 241	98.04 330	97.19 411	99.05 351	98.32 314	98.81 341	98.97 376	89.89 391	99.41 417	98.33 206	99.05 358	99.34 271

Fast-Effi-MVS+		99.02 220	98.87 235	99.46 204	99.38 289	99.50 152	99.04 234	99.79 98	97.17 376	98.62 359	98.74 393	99.34 68	99.95 68	98.32 207	99.41 323	98.92 364

MDA-MVSNet_test_wron		98.95 238	98.99 216	98.85 323	99.64 183	97.16 364	98.23 345	99.33 306	98.93 235	99.56 206	99.66 191	97.39 274	99.83 286	98.29 208	99.88 142	99.55 188

N_pmnet		98.73 262	98.53 269	99.35 241	99.72 148	98.67 280	98.34 336	94.65 423	98.35 308	99.79 106	99.68 182	98.03 234	99.93 104	98.28 209	99.92 112	99.44 242

ET-MVSNet_ETH3D		96.78 359	96.07 369	98.91 314	99.26 328	97.92 339	97.70 389	96.05 418	97.96 337	92.37 431	98.43 406	87.06 399	99.90 172	98.27 210	97.56 417	98.91 365

thisisatest0530		97.45 343	96.95 354	98.94 308	99.68 171	97.73 347	99.09 221	94.19 426	98.61 278	99.56 206	99.30 324	84.30 413	99.93 104	98.27 210	99.54 302	99.16 313

YYNet1		98.95 238	98.99 216	98.84 325	99.64 183	97.14 366	98.22 346	99.32 308	98.92 237	99.59 193	99.66 191	97.40 272	99.83 286	98.27 210	99.90 123	99.55 188

reproduce_model		99.50 92	99.40 112	99.83 36	99.60 192	99.83 30	99.12 208	99.68 154	99.49 142	99.80 100	99.79 103	99.01 113	99.93 104	98.24 213	99.82 189	99.73 80

ACMM	98.09 11	99.46 107	99.38 115	99.72 102	99.80 90	99.69 101	99.13 204	99.65 174	98.99 224	99.64 168	99.72 146	99.39 58	99.86 238	98.23 214	99.81 199	99.60 166
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 235	98.87 235	99.24 271	99.57 212	98.40 303	98.12 354	99.18 339	98.28 316	99.63 172	99.13 350	98.02 235	99.97 37	98.22 215	99.69 252	99.35 268

3Dnovator	99.15 2	99.43 116	99.36 121	99.65 131	99.39 286	99.42 174	99.70 35	99.56 227	99.23 190	99.35 264	99.80 93	99.17 88	99.95 68	98.21 216	99.84 172	99.59 173

Fast-Effi-MVS+-dtu		99.20 179	99.12 169	99.43 215	99.25 329	99.69 101	99.05 229	99.82 80	99.50 140	98.97 321	99.05 362	98.98 118	99.98 23	98.20 217	99.24 347	98.62 386

MS-PatchMatch		99.00 228	98.97 220	99.09 290	99.11 357	98.19 316	98.76 290	99.33 306	98.49 291	99.44 239	99.58 242	98.21 221	99.69 360	98.20 217	99.62 274	99.39 257

TSAR-MVS + GP.		99.12 200	99.04 199	99.38 232	99.34 307	99.16 230	98.15 350	99.29 316	98.18 323	99.63 172	99.62 217	99.18 87	99.68 372	98.20 217	99.74 231	99.30 281

DP-MVS		99.48 98	99.39 113	99.74 87	99.57 212	99.62 124	99.29 151	99.61 194	99.87 50	99.74 134	99.76 126	98.69 155	99.87 219	98.20 217	99.80 206	99.75 78

MVP-Stereo		99.16 192	99.08 183	99.43 215	99.48 259	99.07 244	99.08 224	99.55 233	98.63 274	99.31 278	99.68 182	98.19 224	99.78 324	98.18 221	99.58 290	99.45 237
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 116	99.30 137	99.80 51	99.83 67	99.81 43	99.52 89	99.70 144	98.35 308	99.51 226	99.50 271	99.31 71	99.88 205	98.18 221	99.84 172	99.69 95

MDA-MVSNet-bldmvs		99.06 211	99.05 193	99.07 295	99.80 90	97.83 342	98.89 266	99.72 136	99.29 178	99.63 172	99.70 164	96.47 305	99.89 191	98.17 223	99.82 189	99.50 219

JIA-IIPM		98.06 321	97.92 324	98.50 346	98.59 409	97.02 368	98.80 284	98.51 378	99.88 48	97.89 395	99.87 53	91.89 364	99.90 172	98.16 224	97.68 416	98.59 389

EIA-MVS		99.12 200	99.01 205	99.45 207	99.36 294	99.62 124	99.34 129	99.79 98	98.41 297	98.84 338	98.89 384	98.75 148	99.84 271	98.15 225	99.51 308	98.89 368

miper_lstm_enhance		98.65 270	98.60 257	98.82 330	99.20 339	97.33 360	97.78 385	99.66 164	99.01 223	99.59 193	99.50 271	94.62 336	99.85 256	98.12 226	99.90 123	99.26 287

reproduce-ours		99.46 107	99.35 123	99.82 41	99.56 223	99.83 30	99.05 229	99.65 174	99.45 154	99.78 110	99.78 114	98.93 123	99.93 104	98.11 227	99.81 199	99.70 89

our_new_method		99.46 107	99.35 123	99.82 41	99.56 223	99.83 30	99.05 229	99.65 174	99.45 154	99.78 110	99.78 114	98.93 123	99.93 104	98.11 227	99.81 199	99.70 89

Effi-MVS+-dtu		99.07 210	98.92 229	99.52 186	98.89 383	99.78 52	99.15 196	99.66 164	99.34 173	98.92 328	99.24 340	97.69 258	99.98 23	98.11 227	99.28 340	98.81 375

tpm		97.15 351	96.95 354	97.75 378	98.91 379	94.24 409	99.32 136	97.96 398	97.71 350	98.29 376	99.32 319	86.72 405	99.92 130	98.10 230	96.24 426	99.09 331

DeepPCF-MVS	98.42 6	99.18 186	99.02 202	99.67 118	99.22 334	99.75 72	97.25 409	99.47 270	98.72 265	99.66 165	99.70 164	99.29 73	99.63 392	98.07 231	99.81 199	99.62 152

ppachtmachnet_test		98.89 246	99.12 169	98.20 362	99.66 178	95.24 402	97.63 391	99.68 154	99.08 215	99.78 110	99.62 217	98.65 163	99.88 205	98.02 232	99.96 74	99.48 228

tpmrst		97.73 332	98.07 310	96.73 401	98.71 405	92.00 420	99.10 216	98.86 357	98.52 287	98.92 328	99.54 262	91.90 363	99.82 296	98.02 232	99.03 360	98.37 403

CSCG		99.37 134	99.29 142	99.60 160	99.71 151	99.46 160	99.43 113	99.85 67	98.79 256	99.41 252	99.60 234	98.92 126	99.92 130	98.02 232	99.92 112	99.43 248

eth_miper_zixun_eth		98.68 268	98.71 250	98.60 341	99.10 359	96.84 373	97.52 399	99.54 239	98.94 232	99.58 195	99.48 278	96.25 316	99.76 335	98.01 235	99.93 108	99.21 299

Patchmtry		98.78 256	98.54 268	99.49 195	98.89 383	99.19 227	99.32 136	99.67 159	99.65 112	99.72 140	99.79 103	91.87 365	99.95 68	98.00 236	99.97 61	99.33 272

PVSNet_BlendedMVS		99.03 218	99.01 205	99.09 290	99.54 228	97.99 332	98.58 308	99.82 80	97.62 353	99.34 268	99.71 156	98.52 184	99.77 332	97.98 237	99.97 61	99.52 212

PVSNet_Blended		98.70 266	98.59 259	99.02 300	99.54 228	97.99 332	97.58 394	99.82 80	95.70 401	99.34 268	98.98 374	98.52 184	99.77 332	97.98 237	99.83 180	99.30 281

cl____		98.54 282	98.41 279	98.92 312	99.03 369	97.80 345	97.46 401	99.59 211	98.90 239	99.60 190	99.46 285	93.85 343	99.78 324	97.97 239	99.89 133	99.17 311

DIV-MVS_self_test		98.54 282	98.42 278	98.92 312	99.03 369	97.80 345	97.46 401	99.59 211	98.90 239	99.60 190	99.46 285	93.87 342	99.78 324	97.97 239	99.89 133	99.18 308

AUN-MVS		97.82 328	97.38 342	99.14 284	99.27 325	98.53 294	98.72 294	99.02 352	98.10 325	97.18 412	99.03 368	89.26 393	99.85 256	97.94 241	97.91 412	99.03 348

FA-MVS(test-final)		98.52 284	98.32 289	99.10 289	99.48 259	98.67 280	99.77 16	98.60 374	97.35 368	99.63 172	99.80 93	93.07 353	99.84 271	97.92 242	99.30 337	98.78 378

ambc				99.20 275	99.35 298	98.53 294	99.17 188	99.46 273		99.67 160	99.80 93	98.46 191	99.70 354	97.92 242	99.70 248	99.38 259

USDC		98.96 235	98.93 225	99.05 298	99.54 228	97.99 332	97.07 415	99.80 92	98.21 320	99.75 126	99.77 123	98.43 194	99.64 391	97.90 244	99.88 142	99.51 214

OPM-MVS		99.26 159	99.13 165	99.63 145	99.70 159	99.61 130	98.58 308	99.48 267	98.50 289	99.52 220	99.63 210	99.14 93	99.76 335	97.89 245	99.77 220	99.51 214
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 149	99.17 158	99.77 65	99.69 163	99.80 47	99.14 198	99.31 312	99.16 204	99.62 181	99.61 226	98.35 205	99.91 153	97.88 246	99.72 243	99.61 162
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 36	99.70 159	99.79 49	99.14 198	99.61 194					99.92 130	97.88 246	99.72 243	99.77 70

c3_l		98.72 263	98.71 250	98.72 335	99.12 352	97.22 363	97.68 390	99.56 227	98.90 239	99.54 213	99.48 278	96.37 311	99.73 345	97.88 246	99.88 142	99.21 299

3Dnovator+	98.92 3	99.35 139	99.24 152	99.67 118	99.35 298	99.47 156	99.62 64	99.50 262	99.44 156	99.12 309	99.78 114	98.77 145	99.94 84	97.87 249	99.72 243	99.62 152

miper_ehance_all_eth		98.59 277	98.59 259	98.59 342	98.98 375	97.07 367	97.49 400	99.52 253	98.50 289	99.52 220	99.37 306	96.41 309	99.71 351	97.86 250	99.62 274	99.00 355

WTY-MVS		98.59 277	98.37 283	99.26 266	99.43 277	98.40 303	98.74 292	99.13 346	98.10 325	99.21 296	99.24 340	94.82 333	99.90 172	97.86 250	98.77 376	99.49 224

APD_test1		99.36 137	99.28 144	99.61 157	99.89 39	99.89 10	99.32 136	99.74 123	99.18 197	99.69 152	99.75 131	98.41 197	99.84 271	97.85 252	99.70 248	99.10 326

SED-MVS		99.40 125	99.28 144	99.77 65	99.69 163	99.82 38	99.20 176	99.54 239	99.13 210	99.82 89	99.63 210	98.91 128	99.92 130	97.85 252	99.70 248	99.58 178

test_241102_TWO								99.54 239	99.13 210	99.76 121	99.63 210	98.32 210	99.92 130	97.85 252	99.69 252	99.75 78

MVS_111021_HR		99.12 200	99.02 202	99.40 226	99.50 249	99.11 236	97.92 378	99.71 139	98.76 263	99.08 313	99.47 282	99.17 88	99.54 406	97.85 252	99.76 222	99.54 197

MTAPA		99.35 139	99.20 155	99.80 51	99.81 83	99.81 43	99.33 133	99.53 248	99.27 182	99.42 246	99.63 210	98.21 221	99.95 68	97.83 256	99.79 211	99.65 126

MSC_two_6792asdad				99.74 87	99.03 369	99.53 149		99.23 329					99.92 130	97.77 257	99.69 252	99.78 66

No_MVS				99.74 87	99.03 369	99.53 149		99.23 329					99.92 130	97.77 257	99.69 252	99.78 66

TESTMET0.1,1		96.24 374	95.84 375	97.41 387	98.24 420	93.84 412	97.38 403	95.84 419	98.43 294	97.81 400	98.56 401	79.77 422	99.89 191	97.77 257	98.77 376	98.52 395

ACMH+	98.40 8	99.50 92	99.43 107	99.71 107	99.86 55	99.76 64	99.32 136	99.77 107	99.53 136	99.77 118	99.76 126	99.26 79	99.78 324	97.77 257	99.88 142	99.60 166

IU-MVS					99.69 163	99.77 57		99.22 332	97.50 360	99.69 152				97.75 261	99.70 248	99.77 70

114514_t		98.49 289	98.11 307	99.64 138	99.73 145	99.58 139	99.24 166	99.76 112	89.94 424	99.42 246	99.56 253	97.76 255	99.86 238	97.74 262	99.82 189	99.47 232

DVP-MVS++		99.38 131	99.25 150	99.77 65	99.03 369	99.77 57	99.74 24	99.61 194	99.18 197	99.76 121	99.61 226	99.00 114	99.92 130	97.72 263	99.60 284	99.62 152

test_0728_THIRD									99.18 197	99.62 181	99.61 226	98.58 171	99.91 153	97.72 263	99.80 206	99.77 70

EGC-MVSNET		89.05 398	85.52 401	99.64 138	99.89 39	99.78 52	99.56 84	99.52 253	24.19 433	49.96 434	99.83 76	99.15 90	99.92 130	97.71 265	99.85 167	99.21 299

miper_enhance_ethall		98.03 322	97.94 322	98.32 356	98.27 419	96.43 380	96.95 416	99.41 284	96.37 392	99.43 243	98.96 378	94.74 334	99.69 360	97.71 265	99.62 274	98.83 374

TSAR-MVS + MP.		99.34 144	99.24 152	99.63 145	99.82 74	99.37 189	99.26 159	99.35 303	98.77 260	99.57 198	99.70 164	99.27 78	99.88 205	97.71 265	99.75 224	99.65 126
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 340	97.28 344	98.40 351	98.37 417	96.75 374	97.24 410	99.37 299	97.31 370	99.41 252	99.22 342	87.30 397	99.37 418	97.70 268	99.62 274	99.08 337

MP-MVS-pluss		99.14 196	98.92 229	99.80 51	99.83 67	99.83 30	98.61 301	99.63 184	96.84 385	99.44 239	99.58 242	98.81 136	99.91 153	97.70 268	99.82 189	99.67 109
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 153	99.11 172	99.79 58	99.75 134	99.81 43	98.95 260	99.53 248	98.27 317	99.53 218	99.73 139	98.75 148	99.87 219	97.70 268	99.83 180	99.68 101

UnsupCasMVSNet_bld		98.55 281	98.27 295	99.40 226	99.56 223	99.37 189	97.97 374	99.68 154	97.49 361	99.08 313	99.35 315	95.41 329	99.82 296	97.70 268	98.19 404	99.01 354

MVS_111021_LR		99.13 198	99.03 201	99.42 217	99.58 202	99.32 201	97.91 380	99.73 127	98.68 269	99.31 278	99.48 278	99.09 99	99.66 382	97.70 268	99.77 220	99.29 284

IS-MVSNet		99.03 218	98.85 237	99.55 178	99.80 90	99.25 214	99.73 27	99.15 343	99.37 169	99.61 187	99.71 156	94.73 335	99.81 311	97.70 268	99.88 142	99.58 178

test-LLR		97.15 351	96.95 354	97.74 379	98.18 422	95.02 404	97.38 403	96.10 415	98.00 330	97.81 400	98.58 398	90.04 389	99.91 153	97.69 274	98.78 374	98.31 404

test-mter		96.23 375	95.73 378	97.74 379	98.18 422	95.02 404	97.38 403	96.10 415	97.90 339	97.81 400	98.58 398	79.12 425	99.91 153	97.69 274	98.78 374	98.31 404

MonoMVSNet		98.23 311	98.32 289	97.99 367	98.97 376	96.62 376	99.49 100	98.42 383	99.62 120	99.40 257	99.79 103	95.51 327	98.58 429	97.68 276	95.98 427	98.76 381

XVS		99.27 157	99.11 172	99.75 82	99.71 151	99.71 89	99.37 124	99.61 194	99.29 178	98.76 348	99.47 282	98.47 188	99.88 205	97.62 277	99.73 237	99.67 109

X-MVStestdata		96.09 379	94.87 392	99.75 82	99.71 151	99.71 89	99.37 124	99.61 194	99.29 178	98.76 348	61.30 442	98.47 188	99.88 205	97.62 277	99.73 237	99.67 109

SMA-MVS		99.19 182	99.00 209	99.73 96	99.46 269	99.73 81	99.13 204	99.52 253	97.40 365	99.57 198	99.64 198	98.93 123	99.83 286	97.61 279	99.79 211	99.63 141
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		96.71 362	96.79 361	96.46 405	98.90 380	90.71 431	99.41 114	98.68 367	94.69 414	98.14 386	99.34 318	86.32 407	99.80 318	97.60 280	98.07 410	98.88 369

PVSNet	97.47 15	98.42 295	98.44 276	98.35 353	99.46 269	96.26 384	96.70 420	99.34 305	97.68 351	99.00 320	99.13 350	97.40 272	99.72 347	97.59 281	99.68 257	99.08 337

new_pmnet		98.88 247	98.89 233	98.84 325	99.70 159	97.62 350	98.15 350	99.50 262	97.98 333	99.62 181	99.54 262	98.15 227	99.94 84	97.55 282	99.84 172	98.95 359

IB-MVS	95.41 20	95.30 394	94.46 398	97.84 375	98.76 401	95.33 400	97.33 406	96.07 417	96.02 396	95.37 428	97.41 425	76.17 429	99.96 58	97.54 283	95.44 430	98.22 409
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		99.24 163	99.11 172	99.61 157	98.38 416	99.79 49	99.57 82	99.68 154	99.61 124	99.15 304	99.71 156	98.70 154	99.91 153	97.54 283	99.68 257	99.13 323

ZNCC-MVS		99.22 172	99.04 199	99.77 65	99.76 122	99.73 81	99.28 153	99.56 227	98.19 322	99.14 306	99.29 327	98.84 135	99.92 130	97.53 285	99.80 206	99.64 136

CP-MVS		99.23 164	99.05 193	99.75 82	99.66 178	99.66 108	99.38 120	99.62 187	98.38 301	99.06 317	99.27 330	98.79 141	99.94 84	97.51 286	99.82 189	99.66 118

SD-MVS		99.01 226	99.30 137	98.15 363	99.50 249	99.40 181	98.94 262	99.61 194	99.22 194	99.75 126	99.82 83	99.54 46	95.51 433	97.48 287	99.87 154	99.54 197
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		98.49 289	98.29 294	99.11 287	98.96 377	98.42 302	97.54 395	99.32 308	97.53 358	98.47 371	98.15 413	97.88 245	99.82 296	97.46 288	99.24 347	99.09 331

DeepC-MVS_fast	98.47 5	99.23 164	99.12 169	99.56 174	99.28 323	99.22 221	98.99 250	99.40 291	99.08 215	99.58 195	99.64 198	98.90 131	99.83 286	97.44 289	99.75 224	99.63 141
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 160	99.08 183	99.76 72	99.73 145	99.70 97	99.31 141	99.59 211	98.36 303	99.36 262	99.37 306	98.80 140	99.91 153	97.43 290	99.75 224	99.68 101

ACMMPR		99.23 164	99.06 189	99.76 72	99.74 142	99.69 101	99.31 141	99.59 211	98.36 303	99.35 264	99.38 303	98.61 167	99.93 104	97.43 290	99.75 224	99.67 109

Vis-MVSNet (Re-imp)		98.77 257	98.58 262	99.34 242	99.78 110	98.88 265	99.61 70	99.56 227	99.11 214	99.24 290	99.56 253	93.00 355	99.78 324	97.43 290	99.89 133	99.35 268

MIMVSNet		98.43 294	98.20 299	99.11 287	99.53 234	98.38 307	99.58 79	98.61 372	98.96 228	99.33 270	99.76 126	90.92 375	99.81 311	97.38 293	99.76 222	99.15 315

WB-MVSnew		98.34 305	98.14 305	98.96 305	98.14 425	97.90 340	98.27 341	97.26 412	98.63 274	98.80 343	98.00 416	97.77 253	99.90 172	97.37 294	98.98 363	99.09 331

XVG-OURS-SEG-HR		99.16 192	98.99 216	99.66 125	99.84 63	99.64 117	98.25 344	99.73 127	98.39 300	99.63 172	99.43 290	99.70 27	99.90 172	97.34 295	98.64 387	99.44 242

COLMAP_ROB	98.06 12	99.45 111	99.37 118	99.70 111	99.83 67	99.70 97	99.38 120	99.78 104	99.53 136	99.67 160	99.78 114	99.19 86	99.86 238	97.32 296	99.87 154	99.55 188
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 220	98.81 243	99.65 131	99.58 202	99.49 153	98.58 308	99.07 348	98.40 299	99.04 318	99.25 335	98.51 186	99.80 318	97.31 297	99.51 308	99.65 126

region2R		99.23 164	99.05 193	99.77 65	99.76 122	99.70 97	99.31 141	99.59 211	98.41 297	99.32 273	99.36 310	98.73 152	99.93 104	97.29 298	99.74 231	99.67 109

APD-MVS_3200maxsize		99.31 150	99.16 159	99.74 87	99.53 234	99.75 72	99.27 157	99.61 194	99.19 196	99.57 198	99.64 198	98.76 146	99.90 172	97.29 298	99.62 274	99.56 185

TAPA-MVS	97.92 13	98.03 322	97.55 338	99.46 204	99.47 265	99.44 167	98.50 322	99.62 187	86.79 425	99.07 316	99.26 333	98.26 215	99.62 393	97.28 300	99.73 237	99.31 279
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 157	99.11 172	99.73 96	99.54 228	99.74 78	99.26 159	99.62 187	99.16 204	99.52 220	99.64 198	98.41 197	99.91 153	97.27 301	99.61 281	99.54 197

RE-MVS-def			99.13 165		99.54 228	99.74 78	99.26 159	99.62 187	99.16 204	99.52 220	99.64 198	98.57 172		97.27 301	99.61 281	99.54 197

testing11		96.05 381	95.41 384	97.97 369	98.78 398	95.27 401	98.59 306	98.23 392	98.86 245	96.56 419	96.91 432	75.20 430	99.69 360	97.26 303	98.29 399	98.93 362

test_yl		98.25 308	97.95 318	99.13 285	99.17 345	98.47 297	99.00 245	98.67 369	98.97 226	99.22 294	99.02 369	91.31 369	99.69 360	97.26 303	98.93 365	99.24 290

DCV-MVSNet		98.25 308	97.95 318	99.13 285	99.17 345	98.47 297	99.00 245	98.67 369	98.97 226	99.22 294	99.02 369	91.31 369	99.69 360	97.26 303	98.93 365	99.24 290

PHI-MVS		99.11 203	98.95 223	99.59 162	99.13 350	99.59 135	99.17 188	99.65 174	97.88 342	99.25 287	99.46 285	98.97 120	99.80 318	97.26 303	99.82 189	99.37 262

tfpnnormal		99.43 116	99.38 115	99.60 160	99.87 52	99.75 72	99.59 77	99.78 104	99.71 91	99.90 55	99.69 171	98.85 134	99.90 172	97.25 307	99.78 216	99.15 315

PatchmatchNet		97.65 336	97.80 329	97.18 394	98.82 393	92.49 418	99.17 188	98.39 386	98.12 324	98.79 345	99.58 242	90.71 381	99.89 191	97.23 308	99.41 323	99.16 313
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 231	98.80 245	99.56 174	99.25 329	99.43 171	98.54 317	99.27 320	98.58 280	98.80 343	99.43 290	98.53 181	99.70 354	97.22 309	99.59 288	99.54 197

testing3		96.48 368	95.63 380	99.01 301	99.23 333	97.81 343	98.90 265	99.10 347	98.72 265	97.84 399	97.92 417	72.44 434	99.85 256	97.21 310	99.33 333	99.35 268

HPM-MVS		99.25 160	99.07 187	99.78 62	99.81 83	99.75 72	99.61 70	99.67 159	97.72 349	99.35 264	99.25 335	99.23 82	99.92 130	97.21 310	99.82 189	99.67 109
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 182	99.00 209	99.76 72	99.76 122	99.68 104	99.38 120	99.54 239	98.34 312	99.01 319	99.50 271	98.53 181	99.93 104	97.18 312	99.78 216	99.66 118

ACMMP		99.25 160	99.08 183	99.74 87	99.79 102	99.68 104	99.50 96	99.65 174	98.07 328	99.52 220	99.69 171	98.57 172	99.92 130	97.18 312	99.79 211	99.63 141
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
myMVS_eth3d28		96.23 375	95.74 377	97.70 381	98.86 387	95.59 397	98.66 298	98.14 394	98.96 228	97.67 405	97.06 429	76.78 427	98.92 425	97.10 314	98.41 396	98.58 391

thisisatest0515		96.98 355	96.42 363	98.66 338	99.42 282	97.47 354	97.27 408	94.30 425	97.24 372	99.15 304	98.86 386	85.01 409	99.87 219	97.10 314	99.39 325	98.63 385

XVG-ACMP-BASELINE		99.23 164	99.10 180	99.63 145	99.82 74	99.58 139	98.83 276	99.72 136	98.36 303	99.60 190	99.71 156	98.92 126	99.91 153	97.08 316	99.84 172	99.40 255

MSDG		99.08 207	98.98 219	99.37 235	99.60 192	99.13 233	97.54 395	99.74 123	98.84 249	99.53 218	99.55 260	99.10 97	99.79 321	97.07 317	99.86 162	99.18 308

SteuartSystems-ACMMP		99.30 151	99.14 163	99.76 72	99.87 52	99.66 108	99.18 183	99.60 205	98.55 282	99.57 198	99.67 186	99.03 112	99.94 84	97.01 318	99.80 206	99.69 95
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 377	95.78 376	97.49 383	98.53 411	93.83 413	98.04 364	93.94 428	98.96 228	98.46 372	98.17 412	79.86 420	99.87 219	96.99 319	99.06 356	98.78 378

EPMVS		96.53 365	96.32 364	97.17 395	98.18 422	92.97 417	99.39 117	89.95 434	98.21 320	98.61 360	99.59 239	86.69 406	99.72 347	96.99 319	99.23 349	98.81 375

MSP-MVS		99.04 217	98.79 246	99.81 46	99.78 110	99.73 81	99.35 128	99.57 222	98.54 285	99.54 213	98.99 371	96.81 295	99.93 104	96.97 321	99.53 304	99.77 70
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++		98.96 235	98.70 252	99.74 87	99.52 241	99.71 89	98.86 270	99.19 338	98.47 293	98.59 362	99.06 361	98.08 232	99.91 153	96.94 322	99.60 284	99.60 166

SR-MVS		99.19 182	99.00 209	99.74 87	99.51 243	99.72 86	99.18 183	99.60 205	98.85 246	99.47 233	99.58 242	98.38 202	99.92 130	96.92 323	99.54 302	99.57 183

PGM-MVS		99.20 179	99.01 205	99.77 65	99.75 134	99.71 89	99.16 194	99.72 136	97.99 332	99.42 246	99.60 234	98.81 136	99.93 104	96.91 324	99.74 231	99.66 118

HY-MVS	98.23 9	98.21 315	97.95 318	98.99 302	99.03 369	98.24 311	99.61 70	98.72 365	96.81 386	98.73 350	99.51 268	94.06 340	99.86 238	96.91 324	98.20 402	98.86 371

MDTV_nov1_ep13			97.73 333		98.70 406	90.83 429	99.15 196	98.02 397	98.51 288	98.82 340	99.61 226	90.98 374	99.66 382	96.89 326	98.92 367

GST-MVS		99.16 192	98.96 222	99.75 82	99.73 145	99.73 81	99.20 176	99.55 233	98.22 319	99.32 273	99.35 315	98.65 163	99.91 153	96.86 327	99.74 231	99.62 152

test_post1							99.14 198				51.63 444	89.54 392	99.82 296	96.86 327

SCA		98.11 318	98.36 284	97.36 388	99.20 339	92.99 416	98.17 349	98.49 380	98.24 318	99.10 312	99.57 249	96.01 320	99.94 84	96.86 327	99.62 274	99.14 320

UBG		96.53 365	95.95 371	98.29 360	98.87 386	96.31 383	98.48 325	98.07 395	98.83 250	97.32 407	96.54 437	79.81 421	99.62 393	96.84 330	98.74 380	98.95 359

XVG-OURS		99.21 177	99.06 189	99.65 131	99.82 74	99.62 124	97.87 382	99.74 123	98.36 303	99.66 165	99.68 182	99.71 24	99.90 172	96.84 330	99.88 142	99.43 248

LCM-MVSNet-Re		99.28 153	99.15 162	99.67 118	99.33 312	99.76 64	99.34 129	99.97 20	98.93 235	99.91 52	99.79 103	98.68 156	99.93 104	96.80 332	99.56 293	99.30 281

RPSCF		99.18 186	99.02 202	99.64 138	99.83 67	99.85 20	99.44 111	99.82 80	98.33 313	99.50 228	99.78 114	97.90 243	99.65 389	96.78 333	99.83 180	99.44 242

旧先验2							97.94 376		95.33 405	98.94 324			99.88 205	96.75 334

MDTV_nov1_ep13_2view						91.44 426	99.14 198		97.37 367	99.21 296		91.78 367		96.75 334		99.03 348

CLD-MVS		98.76 258	98.57 263	99.33 245	99.57 212	98.97 254	97.53 397	99.55 233	96.41 390	99.27 285	99.13 350	99.07 104	99.78 324	96.73 336	99.89 133	99.23 294
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 319	97.98 316	98.48 347	99.27 325	96.48 378	99.40 115	99.07 348	98.81 253	99.23 291	99.57 249	90.11 388	99.87 219	96.69 337	99.64 270	99.09 331

baseline2		96.83 358	96.28 365	98.46 349	99.09 362	96.91 371	98.83 276	93.87 429	97.23 373	96.23 424	98.36 407	88.12 396	99.90 172	96.68 338	98.14 407	98.57 393

cascas		96.99 354	96.82 360	97.48 384	97.57 432	95.64 395	96.43 422	99.56 227	91.75 420	97.13 414	97.61 424	95.58 325	98.63 427	96.68 338	99.11 353	98.18 413

PC_three_1452									97.56 354	99.68 155	99.41 293	99.09 99	97.09 430	96.66 340	99.60 284	99.62 152

LPG-MVS_test		99.22 172	99.05 193	99.74 87	99.82 74	99.63 122	99.16 194	99.73 127	97.56 354	99.64 168	99.69 171	99.37 64	99.89 191	96.66 340	99.87 154	99.69 95

LGP-MVS_train				99.74 87	99.82 74	99.63 122		99.73 127	97.56 354	99.64 168	99.69 171	99.37 64	99.89 191	96.66 340	99.87 154	99.69 95

ETVMVS		96.14 378	95.22 389	98.89 321	98.80 394	98.01 331	98.66 298	98.35 389	98.71 267	97.18 412	96.31 441	74.23 433	99.75 339	96.64 343	98.13 409	98.90 366

TinyColmap		98.97 232	98.93 225	99.07 295	99.46 269	98.19 316	97.75 386	99.75 117	98.79 256	99.54 213	99.70 164	98.97 120	99.62 393	96.63 344	99.83 180	99.41 253

LF4IMVS		99.01 226	98.92 229	99.27 263	99.71 151	99.28 207	98.59 306	99.77 107	98.32 314	99.39 259	99.41 293	98.62 165	99.84 271	96.62 345	99.84 172	98.69 384

NCCC		98.82 252	98.57 263	99.58 165	99.21 336	99.31 202	98.61 301	99.25 325	98.65 272	98.43 373	99.26 333	97.86 246	99.81 311	96.55 346	99.27 343	99.61 162

OPU-MVS				99.29 257	99.12 352	99.44 167	99.20 176				99.40 297	99.00 114	98.84 426	96.54 347	99.60 284	99.58 178

F-COLMAP		98.74 260	98.45 275	99.62 154	99.57 212	99.47 156	98.84 273	99.65 174	96.31 393	98.93 325	99.19 347	97.68 259	99.87 219	96.52 348	99.37 328	99.53 202

testing99		95.86 386	95.19 390	97.87 373	98.76 401	95.03 403	98.62 300	98.44 382	98.68 269	96.67 418	96.66 436	74.31 432	99.69 360	96.51 349	98.03 411	98.90 366

ADS-MVSNet2		97.78 330	97.66 337	98.12 365	99.14 348	95.36 399	99.22 173	98.75 364	96.97 381	98.25 378	99.64 198	90.90 376	99.94 84	96.51 349	99.56 293	99.08 337

ADS-MVSNet		97.72 335	97.67 336	97.86 374	99.14 348	94.65 407	99.22 173	98.86 357	96.97 381	98.25 378	99.64 198	90.90 376	99.84 271	96.51 349	99.56 293	99.08 337

PatchMatch-RL		98.68 268	98.47 272	99.30 256	99.44 274	99.28 207	98.14 352	99.54 239	97.12 379	99.11 310	99.25 335	97.80 251	99.70 354	96.51 349	99.30 337	98.93 362

CMPMVS	77.52 23	98.50 287	98.19 302	99.41 224	98.33 418	99.56 142	99.01 242	99.59 211	95.44 403	99.57 198	99.80 93	95.64 323	99.46 416	96.47 353	99.92 112	99.21 299
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 382	95.32 387	98.02 366	98.76 401	95.39 398	98.38 334	98.65 371	98.82 251	96.84 415	96.71 435	75.06 431	99.71 351	96.46 354	98.23 401	98.98 356

SF-MVS		99.10 206	98.93 225	99.62 154	99.58 202	99.51 151	99.13 204	99.65 174	97.97 334	99.42 246	99.61 226	98.86 133	99.87 219	96.45 355	99.68 257	99.49 224

FE-MVS		97.85 327	97.42 341	99.15 281	99.44 274	98.75 275	99.77 16	98.20 393	95.85 398	99.33 270	99.80 93	88.86 394	99.88 205	96.40 356	99.12 352	98.81 375

DPE-MVS		99.14 196	98.92 229	99.82 41	99.57 212	99.77 57	98.74 292	99.60 205	98.55 282	99.76 121	99.69 171	98.23 220	99.92 130	96.39 357	99.75 224	99.76 75
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 430	89.02 436			93.47 416		98.30 408		99.84 271	96.38 358

AllTest		99.21 177	99.07 187	99.63 145	99.78 110	99.64 117	99.12 208	99.83 75	98.63 274	99.63 172	99.72 146	98.68 156	99.75 339	96.38 358	99.83 180	99.51 214

TestCases				99.63 145	99.78 110	99.64 117		99.83 75	98.63 274	99.63 172	99.72 146	98.68 156	99.75 339	96.38 358	99.83 180	99.51 214

testdata				99.42 217	99.51 243	98.93 261		99.30 315	96.20 394	98.87 335	99.40 297	98.33 209	99.89 191	96.29 361	99.28 340	99.44 242

dp		96.86 357	97.07 350	96.24 407	98.68 407	90.30 434	99.19 182	98.38 387	97.35 368	98.23 380	99.59 239	87.23 398	99.82 296	96.27 362	98.73 383	98.59 389

tpmvs		97.39 346	97.69 334	96.52 403	98.41 415	91.76 422	99.30 144	98.94 356	97.74 348	97.85 398	99.55 260	92.40 362	99.73 345	96.25 363	98.73 383	98.06 415

KD-MVS_2432*1600		95.89 383	95.41 384	97.31 391	94.96 434	93.89 410	97.09 413	99.22 332	97.23 373	98.88 332	99.04 364	79.23 423	99.54 406	96.24 364	96.81 421	98.50 399

miper_refine_blended		95.89 383	95.41 384	97.31 391	94.96 434	93.89 410	97.09 413	99.22 332	97.23 373	98.88 332	99.04 364	79.23 423	99.54 406	96.24 364	96.81 421	98.50 399

ACMP	97.51 14	99.05 214	98.84 239	99.67 118	99.78 110	99.55 146	98.88 267	99.66 164	97.11 380	99.47 233	99.60 234	99.07 104	99.89 191	96.18 366	99.85 167	99.58 178
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 243	98.72 249	99.44 211	99.39 286	99.42 174	98.58 308	99.64 182	97.31 370	99.44 239	99.62 217	98.59 169	99.69 360	96.17 367	99.79 211	99.22 296

DP-MVS Recon		98.50 287	98.23 296	99.31 253	99.49 254	99.46 160	98.56 313	99.63 184	94.86 412	98.85 337	99.37 306	97.81 250	99.59 400	96.08 368	99.44 318	98.88 369

tpm cat1		96.78 359	96.98 353	96.16 408	98.85 388	90.59 432	99.08 224	99.32 308	92.37 418	97.73 404	99.46 285	91.15 372	99.69 360	96.07 369	98.80 373	98.21 410

tpm2		96.35 371	96.22 366	96.73 401	98.88 385	91.75 423	99.21 175	98.51 378	93.27 417	97.89 395	99.21 344	84.83 410	99.70 354	96.04 370	98.18 405	98.75 382

dmvs_re		98.69 267	98.48 271	99.31 253	99.55 226	99.42 174	99.54 87	98.38 387	99.32 176	98.72 351	98.71 394	96.76 297	99.21 420	96.01 371	99.35 331	99.31 279

test_0402		99.22 172	99.14 163	99.45 207	99.79 102	99.43 171	99.28 153	99.68 154	99.54 134	99.40 257	99.56 253	99.07 104	99.82 296	96.01 371	99.96 74	99.11 324

ITE_SJBPF				99.38 232	99.63 185	99.44 167		99.73 127	98.56 281	99.33 270	99.53 264	98.88 132	99.68 372	96.01 371	99.65 268	99.02 353

test_prior2							97.95 375		97.87 343	98.05 388	99.05 362	97.90 243		95.99 374	99.49 313

testdata2													99.89 191	95.99 374

原ACMM1				99.37 235	99.47 265	98.87 267		99.27 320	96.74 388	98.26 377	99.32 319	97.93 242	99.82 296	95.96 376	99.38 326	99.43 248

新几何1				99.52 186	99.50 249	99.22 221		99.26 322	95.66 402	98.60 361	99.28 328	97.67 260	99.89 191	95.95 377	99.32 335	99.45 237

MP-MVS		99.06 211	98.83 241	99.76 72	99.76 122	99.71 89	99.32 136	99.50 262	98.35 308	98.97 321	99.48 278	98.37 203	99.92 130	95.95 377	99.75 224	99.63 141
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 393	94.59 396	98.61 340	98.66 408	97.45 356	98.54 317	97.90 401	98.53 286	96.54 420	96.47 438	70.62 437	99.81 311	95.91 379	98.15 406	98.56 394

wuyk23d		97.58 339	99.13 165	92.93 412	99.69 163	99.49 153	99.52 89	99.77 107	97.97 334	99.96 28	99.79 103	99.84 13	99.94 84	95.85 380	99.82 189	79.36 430

HQP_MVS		98.90 243	98.68 253	99.55 178	99.58 202	99.24 218	98.80 284	99.54 239	98.94 232	99.14 306	99.25 335	97.24 279	99.82 296	95.84 381	99.78 216	99.60 166

plane_prior5								99.54 239					99.82 296	95.84 381	99.78 216	99.60 166

无先验							98.01 367	99.23 329	95.83 399				99.85 256	95.79 383		99.44 242

CPTT-MVS		98.74 260	98.44 276	99.64 138	99.61 190	99.38 186	99.18 183	99.55 233	96.49 389	99.27 285	99.37 306	97.11 287	99.92 130	95.74 384	99.67 263	99.62 152

PLC	97.35 16	98.36 300	97.99 314	99.48 199	99.32 313	99.24 218	98.50 322	99.51 258	95.19 408	98.58 363	98.96 378	96.95 292	99.83 286	95.63 385	99.25 345	99.37 262
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 279	98.34 287	99.28 260	99.18 344	99.10 241	98.34 336	99.41 284	98.48 292	98.52 368	98.98 374	97.05 289	99.78 324	95.59 386	99.50 311	98.96 357

1314		98.00 324	97.90 326	98.27 361	98.90 380	97.45 356	99.30 144	99.06 350	94.98 409	97.21 411	99.12 354	98.43 194	99.67 377	95.58 387	98.56 390	97.71 419

PVSNet_0	95.53 19	95.85 387	95.31 388	97.47 385	98.78 398	93.48 415	95.72 424	99.40 291	96.18 395	97.37 406	97.73 419	95.73 322	99.58 401	95.49 388	81.40 432	99.36 265

MAR-MVS		98.24 310	97.92 324	99.19 276	98.78 398	99.65 114	99.17 188	99.14 344	95.36 404	98.04 389	98.81 390	97.47 269	99.72 347	95.47 389	99.06 356	98.21 410
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	98.23 311	97.89 327	99.26 266	99.19 341	99.26 211	99.65 59	99.69 151	91.33 422	98.14 386	99.77 123	98.28 212	99.96 58	95.41 390	99.55 297	98.58 391

train_agg		98.35 303	97.95 318	99.57 171	99.35 298	99.35 196	98.11 356	99.41 284	94.90 410	97.92 393	98.99 371	98.02 235	99.85 256	95.38 391	99.44 318	99.50 219

9.14			98.64 254		99.45 273		98.81 281	99.60 205	97.52 359	99.28 284	99.56 253	98.53 181	99.83 286	95.36 392	99.64 270

APD-MVS		98.87 248	98.59 259	99.71 107	99.50 249	99.62 124	99.01 242	99.57 222	96.80 387	99.54 213	99.63 210	98.29 211	99.91 153	95.24 393	99.71 246	99.61 162
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 381								95.20 394

AdaColmap		98.60 274	98.35 286	99.38 232	99.12 352	99.22 221	98.67 297	99.42 283	97.84 346	98.81 341	99.27 330	97.32 277	99.81 311	95.14 395	99.53 304	99.10 326

test9_res														95.10 396	99.44 318	99.50 219

CDPH-MVS		98.56 280	98.20 299	99.61 157	99.50 249	99.46 160	98.32 338	99.41 284	95.22 406	99.21 296	99.10 358	98.34 207	99.82 296	95.09 397	99.66 266	99.56 185

BH-untuned		98.22 313	98.09 308	98.58 344	99.38 289	97.24 362	98.55 314	98.98 355	97.81 347	99.20 301	98.76 392	97.01 290	99.65 389	94.83 398	98.33 397	98.86 371

BP-MVS														94.73 399

HQP-MVS		98.36 300	98.02 313	99.39 229	99.31 314	98.94 258	97.98 371	99.37 299	97.45 362	98.15 382	98.83 387	96.67 298	99.70 354	94.73 399	99.67 263	99.53 202

QAPM		98.40 298	97.99 314	99.65 131	99.39 286	99.47 156	99.67 50	99.52 253	91.70 421	98.78 347	99.80 93	98.55 175	99.95 68	94.71 401	99.75 224	99.53 202

agg_prior2														94.58 402	99.46 317	99.50 219

myMVS_eth3d		95.63 391	94.73 393	98.34 355	98.50 413	96.36 381	98.60 303	99.21 335	97.89 340	96.76 416	96.37 439	72.10 435	99.57 402	94.38 403	98.73 383	99.09 331

BH-RMVSNet		98.41 296	98.14 305	99.21 273	99.21 336	98.47 297	98.60 303	98.26 391	98.35 308	98.93 325	99.31 322	97.20 284	99.66 382	94.32 404	99.10 354	99.51 214

E-PMN		97.14 353	97.43 340	96.27 406	98.79 396	91.62 424	95.54 425	99.01 354	99.44 156	98.88 332	99.12 354	92.78 356	99.68 372	94.30 405	99.03 360	97.50 420

MG-MVS		98.52 284	98.39 281	98.94 308	99.15 347	97.39 359	98.18 347	99.21 335	98.89 242	99.23 291	99.63 210	97.37 275	99.74 342	94.22 406	99.61 281	99.69 95

API-MVS		98.38 299	98.39 281	98.35 353	98.83 390	99.26 211	99.14 198	99.18 339	98.59 279	98.66 356	98.78 391	98.61 167	99.57 402	94.14 407	99.56 293	96.21 427

PAPM_NR		98.36 300	98.04 311	99.33 245	99.48 259	98.93 261	98.79 287	99.28 319	97.54 357	98.56 367	98.57 400	97.12 286	99.69 360	94.09 408	98.90 371	99.38 259

ZD-MVS					99.43 277	99.61 130		99.43 281	96.38 391	99.11 310	99.07 360	97.86 246	99.92 130	94.04 409	99.49 313

DPM-MVS		98.28 306	97.94 322	99.32 250	99.36 294	99.11 236	97.31 407	98.78 363	96.88 383	98.84 338	99.11 357	97.77 253	99.61 398	94.03 410	99.36 329	99.23 294

gg-mvs-nofinetune		95.87 385	95.17 391	97.97 369	98.19 421	96.95 369	99.69 42	89.23 435	99.89 43	96.24 423	99.94 19	81.19 415	99.51 412	93.99 411	98.20 402	97.44 421

PMVS	92.94 21	98.82 252	98.81 243	98.85 323	99.84 63	97.99 332	99.20 176	99.47 270	99.71 91	99.42 246	99.82 83	98.09 230	99.47 414	93.88 412	99.85 167	99.07 342
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 356	97.28 344	95.99 410	98.76 401	91.03 428	95.26 427	98.61 372	99.34 173	98.92 328	98.88 385	93.79 344	99.66 382	92.87 413	99.05 358	97.30 424

BH-w/o		97.20 350	97.01 352	97.76 377	99.08 363	95.69 394	98.03 366	98.52 377	95.76 400	97.96 392	98.02 414	95.62 324	99.47 414	92.82 414	97.25 420	98.12 414

TR-MVS		97.44 344	97.15 349	98.32 356	98.53 411	97.46 355	98.47 326	97.91 400	96.85 384	98.21 381	98.51 404	96.42 307	99.51 412	92.16 415	97.29 419	97.98 416

OpenMVS_ROB	97.31 17	97.36 348	96.84 358	98.89 321	99.29 320	99.45 165	98.87 269	99.48 267	86.54 427	99.44 239	99.74 135	97.34 276	99.86 238	91.61 416	99.28 340	97.37 423

GG-mvs-BLEND				97.36 388	97.59 430	96.87 372	99.70 35	88.49 436		94.64 429	97.26 428	80.66 417	99.12 421	91.50 417	96.50 425	96.08 429

DeepMVS_CX				97.98 368	99.69 163	96.95 369		99.26 322	75.51 430	95.74 426	98.28 409	96.47 305	99.62 393	91.23 418	97.89 413	97.38 422

PAPR		97.56 340	97.07 350	99.04 299	98.80 394	98.11 324	97.63 391	99.25 325	94.56 415	98.02 391	98.25 410	97.43 271	99.68 372	90.90 419	98.74 380	99.33 272

MVS		95.72 389	94.63 395	98.99 302	98.56 410	97.98 337	99.30 144	98.86 357	72.71 431	97.30 408	99.08 359	98.34 207	99.74 342	89.21 420	98.33 397	99.26 287

UWE-MVS-28		95.64 390	95.47 382	96.14 409	97.98 426	90.39 433	98.49 324	95.81 420	99.02 222	98.03 390	98.19 411	84.49 412	99.28 419	88.75 421	98.47 395	98.75 382

thres600view7		96.60 364	96.16 367	97.93 371	99.63 185	96.09 389	99.18 183	97.57 406	98.77 260	98.72 351	97.32 426	87.04 400	99.72 347	88.57 422	98.62 388	97.98 416

FPMVS		96.32 372	95.50 381	98.79 331	99.60 192	98.17 319	98.46 330	98.80 362	97.16 377	96.28 421	99.63 210	82.19 414	99.09 422	88.45 423	98.89 372	99.10 326

PCF-MVS	96.03 18	96.73 361	95.86 374	99.33 245	99.44 274	99.16 230	96.87 418	99.44 278	86.58 426	98.95 323	99.40 297	94.38 338	99.88 205	87.93 424	99.80 206	98.95 359
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 370	96.03 370	97.47 385	99.63 185	95.93 390	99.18 183	97.57 406	98.75 264	98.70 354	97.31 427	87.04 400	99.67 377	87.62 425	98.51 392	96.81 425

tfpn200view9		96.30 373	95.89 372	97.53 382	99.58 202	96.11 387	99.00 245	97.54 409	98.43 294	98.52 368	96.98 430	86.85 402	99.67 377	87.62 425	98.51 392	96.81 425

thres400		96.40 369	95.89 372	97.92 372	99.58 202	96.11 387	99.00 245	97.54 409	98.43 294	98.52 368	96.98 430	86.85 402	99.67 377	87.62 425	98.51 392	97.98 416

thres200		96.09 379	95.68 379	97.33 390	99.48 259	96.22 386	98.53 319	97.57 406	98.06 329	98.37 375	96.73 434	86.84 404	99.61 398	86.99 428	98.57 389	96.16 428

MVE	92.54 22	96.66 363	96.11 368	98.31 358	99.68 171	97.55 352	97.94 376	95.60 421	99.37 169	90.68 432	98.70 396	96.56 301	98.61 428	86.94 429	99.55 297	98.77 380
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 349	96.83 359	98.59 342	99.46 269	97.55 352	99.25 165	96.84 414	98.78 258	97.24 410	97.67 420	97.11 287	98.97 424	86.59 430	98.54 391	99.27 285

PAPM		95.61 392	94.71 394	98.31 358	99.12 352	96.63 375	96.66 421	98.46 381	90.77 423	96.25 422	98.68 397	93.01 354	99.69 360	81.60 431	97.86 415	98.62 386

dongtai		89.37 397	88.91 400	90.76 413	99.19 341	77.46 438	95.47 426	87.82 437	92.28 419	94.17 430	98.82 389	71.22 436	95.54 432	63.85 432	97.34 418	99.27 285

kuosan		85.65 399	84.57 402	88.90 415	97.91 427	77.11 439	96.37 423	87.62 438	85.24 428	85.45 433	96.83 433	69.94 438	90.98 434	45.90 433	95.83 429	98.62 386

test123		29.31 400	33.05 405	18.08 416	25.93 440	12.24 441	97.53 397	10.93 441	11.78 434	24.21 435	50.08 446	21.04 439	8.60 435	23.51 434	32.43 434	33.39 431

testmvs		28.94 401	33.33 403	15.79 417	26.03 439	9.81 442	96.77 419	15.67 440	11.55 435	23.87 436	50.74 445	19.03 440	8.53 436	23.21 435	33.07 433	29.03 432

mmdepth		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet_test		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

cdsmvs_eth3d_5k		24.88 402	33.17 404	0.00 418	0.00 441	0.00 443	0.00 429	99.62 187	0.00 436	0.00 437	99.13 350	99.82 15	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		16.61 403	22.14 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	99.28 75	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

ab-mvs-re		8.26 414	11.02 417	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	99.16 348	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		8.33 404	11.11 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	100.00 1	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

FOURS1					99.83 67	99.89 10	99.74 24	99.71 139	99.69 99	99.63 172

test_one_0601					99.63 185	99.76 64		99.55 233	99.23 190	99.31 278	99.61 226	98.59 169

eth-test2					0.00 441

eth-test					0.00 441

test_241102_ONE					99.69 163	99.82 38		99.54 239	99.12 213	99.82 89	99.49 275	98.91 128	99.52 411

save fliter					99.53 234	99.25 214	98.29 340	99.38 298	99.07 217

test0726					99.69 163	99.80 47	99.24 166	99.57 222	99.16 204	99.73 138	99.65 196	98.35 205

GSMVS																99.14 320

test_part2					99.62 189	99.67 106				99.55 211

sam_mvs1												90.81 380				99.14 320

sam_mvs												90.52 385

MTGPA								99.53 248

test_post											52.41 443	90.25 387	99.86 238

patchmatchnet-post											99.62 217	90.58 383	99.94 84

MTMP							99.09 221	98.59 375

TEST9					99.35 298	99.35 196	98.11 356	99.41 284	94.83 413	97.92 393	98.99 371	98.02 235	99.85 256

test_8					99.34 307	99.31 202	98.08 360	99.40 291	94.90 410	97.87 397	98.97 376	98.02 235	99.84 271

agg_prior					99.35 298	99.36 193		99.39 294		97.76 403			99.85 256

test_prior4						99.19 227	98.00 369

test_prior				99.46 204	99.35 298	99.22 221		99.39 294					99.69 360			99.48 228

新几何2							98.04 364

旧先验1					99.49 254	99.29 205		99.26 322			99.39 301	97.67 260			99.36 329	99.46 236

原ACMM2							97.92 378

test222					99.51 243	99.08 243	97.83 384	99.29 316	95.21 407	98.68 355	99.31 322	97.28 278			99.38 326	99.43 248

segment_acmp												98.37 203

testdata1							97.72 387		97.86 345

test12				99.54 183	99.29 320	99.33 199		99.16 342		98.43 373		97.54 267	99.82 296		99.47 315	99.48 228

plane_prior7					99.58 202	99.38 186

plane_prior6					99.47 265	99.26 211						97.24 279

plane_prior4											99.25 335

plane_prior3						99.31 202			98.36 303	99.14 306

plane_prior2							98.80 284		98.94 232

plane_prior1					99.51 243

plane_prior						99.24 218	98.42 332		97.87 343						99.71 246

n2								0.00 442

nn								0.00 442

door-mid								99.83 75

test11								99.29 316

door								99.77 107

HQP5-MVS						98.94 258

HQP-NCC					99.31 314		97.98 371		97.45 362	98.15 382

ACMP_Plane					99.31 314		97.98 371		97.45 362	98.15 382

HQP4-MVS										98.15 382			99.70 354			99.53 202

HQP3-MVS								99.37 299							99.67 263

HQP2-MVS												96.67 298

NP-MVS					99.40 285	99.13 233					98.83 387

ACMMP++_ref															99.94 101

ACMMP++															99.79 211

Test By Simon												98.41 197

High-resolution multi-view benchmark