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 73	99.70 35	100.00 1	99.73 86	100.00 1	99.89 38	99.79 19	99.88 206	99.98 1	100.00 1	99.98 5

test_fmvs2		99.72 45	99.85 17	99.34 243	99.91 31	98.08 330	99.48 102	100.00 1	99.90 38	99.99 7	99.91 28	99.50 53	99.98 23	99.98 1	99.99 16	99.96 13

test_fmvs3		99.83 21	99.93 2	99.53 185	99.96 7	98.62 291	99.67 50	100.00 1	99.95 26	100.00 1	99.95 16	99.85 12	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 65	99.12 208	100.00 1	100.00 1	99.99 7	99.91 28	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_vis1_n_1920		99.72 45	99.88 7	99.27 264	99.93 24	97.84 342	99.34 129	100.00 1	99.99 3	99.99 7	99.82 83	99.87 11	99.99 8	99.97 4	99.99 16	99.97 10

test_vis1_n		99.68 54	99.79 30	99.36 240	99.94 18	98.18 319	99.52 89	100.00 1	99.86 54	100.00 1	99.88 47	98.99 117	99.96 58	99.97 4	99.96 75	99.95 14

test_fmvs1_n		99.68 54	99.81 26	99.28 261	99.95 15	97.93 339	99.49 100	100.00 1	99.82 70	99.99 7	99.89 38	99.21 85	99.98 23	99.97 4	99.98 45	99.93 20

test_f		99.75 41	99.88 7	99.37 236	99.96 7	98.21 316	99.51 95	100.00 1	99.94 29	100.00 1	99.93 21	99.58 42	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 29	99.79 103	99.90 9	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 79	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 47	99.88 44	99.55 147	99.17 188	99.98 12	99.99 3	99.96 29	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 40	99.86 13	99.45 208	99.93 24	98.40 304	99.30 144	99.98 12	99.94 29	99.99 7	99.89 38	99.80 18	99.97 37	99.96 9	99.97 62	99.97 10

fmvsm_l_conf0.5_n		99.80 26	99.78 34	99.85 29	99.88 44	99.66 109	99.11 213	99.91 45	99.98 15	99.96 29	99.64 198	99.60 40	99.99 8	99.95 13	99.99 16	99.88 33

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 37	99.82 74	99.70 98	99.17 188	99.97 20	99.99 3	99.96 29	99.82 83	99.94 4	100.00 1	99.95 13	100.00 1	99.80 57

test_fmvs1		99.48 99	99.65 60	98.97 305	99.54 229	97.16 365	99.11 213	99.98 12	99.78 80	99.96 29	99.81 90	98.72 154	99.97 37	99.95 13	99.97 62	99.79 65

mvsany_test3		99.85 12	99.88 7	99.75 83	99.95 15	99.37 190	99.53 88	99.98 12	99.77 84	99.99 7	99.95 16	99.85 12	99.94 84	99.95 13	99.98 45	99.94 17

fmvsm_s_conf0.1_n_2		99.81 25	99.78 34	99.89 11	99.93 24	99.76 65	98.92 265	99.98 12	99.99 3	99.99 7	99.88 47	99.43 55	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 34	99.88 44	99.64 118	99.12 208	99.91 45	99.98 15	99.95 39	99.67 186	99.67 31	99.99 8	99.94 17	99.99 16	99.88 33

MM		99.18 187	99.05 194	99.55 179	99.35 299	98.81 270	99.05 229	97.79 405	99.99 3	99.48 232	99.59 239	96.29 316	99.95 68	99.94 17	99.98 45	99.88 33

test_fmvsmconf_n		99.85 12	99.84 20	99.88 18	99.91 31	99.73 82	98.97 256	99.98 12	99.99 3	99.96 29	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 32	99.76 43	99.85 29	99.79 102	99.72 87	98.84 274	99.96 28	99.96 23	99.96 29	99.72 146	99.71 25	99.99 8	99.93 21	99.98 45	99.85 42

fmvsm_s_conf0.5_n_2		99.78 32	99.75 45	99.88 18	99.82 74	99.76 65	98.88 268	99.92 39	99.98 15	99.98 14	99.85 65	99.42 57	99.94 84	99.93 21	99.98 45	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 30	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 10	99.92 131	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 28	99.99 3	99.97 22	99.84 72	99.58 42	99.93 104	99.92 25	99.98 45	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 28	99.99 3	99.97 22	99.84 72	99.78 20	99.92 131	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 20	100.00 1	99.92 25	100.00 1	99.87 37

fmvsm_s_conf0.5_n_6		99.80 26	99.78 34	99.85 29	99.78 110	99.78 52	99.00 245	99.97 20	99.96 23	99.97 22	99.56 253	99.92 8	99.93 104	99.91 28	99.99 16	99.83 49

fmvsm_s_conf0.5_n_4		99.78 32	99.78 34	99.79 59	99.75 135	99.56 143	98.98 254	99.94 36	99.92 34	99.97 22	99.72 146	99.84 14	99.92 131	99.91 28	99.98 45	99.89 31

MVStest1		98.22 314	98.09 309	98.62 340	99.04 369	96.23 386	99.20 176	99.92 39	99.44 157	99.98 14	99.87 53	85.87 409	99.67 378	99.91 28	99.57 293	99.95 14

v1921920		99.56 82	99.57 81	99.55 179	99.75 135	99.11 237	99.05 229	99.61 195	99.15 209	99.88 69	99.71 156	99.08 103	99.87 220	99.90 31	99.97 62	99.66 119

v1240		99.56 82	99.58 77	99.51 190	99.80 90	99.00 249	99.00 245	99.65 175	99.15 209	99.90 56	99.75 131	99.09 100	99.88 206	99.90 31	99.96 75	99.67 110

v10		99.69 51	99.69 52	99.66 126	99.81 83	99.39 185	99.66 54	99.75 118	99.60 131	99.92 50	99.87 53	98.75 149	99.86 239	99.90 31	99.99 16	99.73 81

v1192		99.57 79	99.57 81	99.57 172	99.77 119	99.22 222	99.04 234	99.60 206	99.18 198	99.87 77	99.72 146	99.08 103	99.85 257	99.89 34	99.98 45	99.66 119

fmvsm_s_conf0.5_n_3		99.79 30	99.77 39	99.85 29	99.81 83	99.71 90	98.97 256	99.92 39	99.98 15	99.97 22	99.86 60	99.53 49	99.95 68	99.88 35	99.99 16	99.89 31

v144192		99.55 85	99.54 88	99.58 166	99.78 110	99.20 227	99.11 213	99.62 188	99.18 198	99.89 60	99.72 146	98.66 162	99.87 220	99.88 35	99.97 62	99.66 119

v8		99.68 54	99.69 52	99.65 132	99.80 90	99.40 182	99.66 54	99.76 113	99.64 116	99.93 45	99.85 65	98.66 162	99.84 272	99.88 35	99.99 16	99.71 87

mvs5depth		99.88 6	99.91 3	99.80 52	99.92 29	99.42 175	99.94 3	100.00 1	99.97 20	99.89 60	99.99 12	99.63 34	99.97 37	99.87 38	99.99 16	100.00 1

v1144		99.54 88	99.53 92	99.59 163	99.79 102	99.28 208	99.10 216	99.61 195	99.20 196	99.84 84	99.73 139	98.67 160	99.84 272	99.86 39	99.98 45	99.64 137

mmtdpeth		99.78 32	99.83 21	99.66 126	99.85 59	99.05 248	99.79 12	99.97 20	100.00 1	99.43 244	99.94 19	99.64 32	99.94 84	99.83 40	99.99 16	99.98 5

SSC-MVS		99.52 91	99.42 110	99.83 37	99.86 55	99.65 115	99.52 89	99.81 90	99.87 51	99.81 97	99.79 103	96.78 297	99.99 8	99.83 40	99.51 309	99.86 39

v7n		99.82 23	99.80 29	99.88 18	99.96 7	99.84 25	99.82 9	99.82 81	99.84 63	99.94 42	99.91 28	99.13 96	99.96 58	99.83 40	99.99 16	99.83 49

v2v482		99.50 93	99.47 97	99.58 166	99.78 110	99.25 215	99.14 198	99.58 221	99.25 187	99.81 97	99.62 217	98.24 217	99.84 272	99.83 40	99.97 62	99.64 137

test_vis1_rt		99.45 112	99.46 101	99.41 225	99.71 152	98.63 290	98.99 251	99.96 28	99.03 222	99.95 39	99.12 355	98.75 149	99.84 272	99.82 44	99.82 190	99.77 71

tt0805		99.63 68	99.57 81	99.81 47	99.87 52	99.88 12	99.58 79	98.70 367	99.72 90	99.91 53	99.60 234	99.43 55	99.81 312	99.81 45	99.53 305	99.73 81

V42		99.56 82	99.54 88	99.63 146	99.79 102	99.46 161	99.39 117	99.59 212	99.24 189	99.86 78	99.70 164	98.55 176	99.82 297	99.79 46	99.95 89	99.60 167

SSC-MVS3.2		99.64 67	99.67 56	99.56 175	99.75 135	98.98 252	98.96 259	99.87 58	99.88 49	99.84 84	99.64 198	99.32 71	99.91 154	99.78 47	99.96 75	99.80 57

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 49	99.72 30	99.88 56	99.92 34	99.98 14	99.93 21	99.94 4	99.98 23	99.77 48	100.00 1	99.92 24

WB-MVS		99.44 114	99.32 131	99.80 52	99.81 83	99.61 131	99.47 105	99.81 90	99.82 70	99.71 146	99.72 146	96.60 301	99.98 23	99.75 49	99.23 350	99.82 56

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 58	99.68 46	99.85 68	99.95 26	99.98 14	99.92 25	99.28 76	99.98 23	99.75 49	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 62	99.89 44	99.98 14	99.90 33	99.94 4	99.98 23	99.75 49	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 38	100.00 1	99.97 14	99.61 38	99.97 37	99.75 49	100.00 1	99.84 45

reproduce_monomvs		97.40 346	97.46 340	97.20 394	99.05 366	91.91 422	99.20 176	99.18 340	99.84 63	99.86 78	99.75 131	80.67 417	99.83 287	99.69 53	99.95 89	99.85 42

SPE-MVS-test		99.68 54	99.70 49	99.64 139	99.57 213	99.83 30	99.78 14	99.97 20	99.92 34	99.50 229	99.38 304	99.57 44	99.95 68	99.69 53	99.90 124	99.15 316

MVS_0304		98.61 272	98.30 293	99.52 187	97.88 429	98.95 258	98.76 291	94.11 428	99.84 63	99.32 274	99.57 249	95.57 327	99.95 68	99.68 55	99.98 45	99.68 102

CS-MVS		99.67 60	99.70 49	99.58 166	99.53 235	99.84 25	99.79 12	99.96 28	99.90 38	99.61 188	99.41 294	99.51 52	99.95 68	99.66 56	99.89 134	98.96 358

mamv4		99.73 44	99.74 46	99.70 112	99.66 179	99.87 14	99.69 42	99.93 37	99.93 31	99.93 45	99.86 60	99.07 105	100.00 1	99.66 56	99.92 113	99.24 291

pmmvs6		99.86 10	99.86 13	99.83 37	99.94 18	99.90 7	99.83 7	99.91 45	99.85 60	99.94 42	99.95 16	99.73 24	99.90 173	99.65 58	99.97 62	99.69 96

MIMVSNet1		99.66 61	99.62 65	99.80 52	99.94 18	99.87 14	99.69 42	99.77 108	99.78 80	99.93 45	99.89 38	97.94 242	99.92 131	99.65 58	99.98 45	99.62 153

EC-MVSNet		99.69 51	99.69 52	99.68 116	99.71 152	99.91 4	99.76 20	99.96 28	99.86 54	99.51 227	99.39 302	99.57 44	99.93 104	99.64 60	99.86 163	99.20 304

K. test v3		98.87 249	98.60 258	99.69 114	99.93 24	99.46 161	99.74 24	94.97 423	99.78 80	99.88 69	99.88 47	93.66 348	99.97 37	99.61 61	99.95 89	99.64 137

KD-MVS_self_test		99.63 68	99.59 74	99.76 73	99.84 63	99.90 7	99.37 124	99.79 99	99.83 68	99.88 69	99.85 65	98.42 197	99.90 173	99.60 62	99.73 238	99.49 225

Anonymous20240521		99.44 114	99.42 110	99.49 196	99.89 39	98.96 257	99.62 64	99.76 113	99.85 60	99.82 90	99.88 47	96.39 311	99.97 37	99.59 63	99.98 45	99.55 189

TransMVSNet (Re)		99.78 32	99.77 39	99.81 47	99.91 31	99.85 20	99.75 22	99.86 62	99.70 97	99.91 53	99.89 38	99.60 40	99.87 220	99.59 63	99.74 232	99.71 87

OurMVSNet-221017-0		99.75 41	99.71 48	99.84 34	99.96 7	99.83 30	99.83 7	99.85 68	99.80 76	99.93 45	99.93 21	98.54 178	99.93 104	99.59 63	99.98 45	99.76 76

EU-MVSNet		99.39 130	99.62 65	98.72 336	99.88 44	96.44 380	99.56 84	99.85 68	99.90 38	99.90 56	99.85 65	98.09 231	99.83 287	99.58 66	99.95 89	99.90 26

mvs_anonymous		99.28 154	99.39 114	98.94 309	99.19 342	97.81 344	99.02 240	99.55 234	99.78 80	99.85 81	99.80 93	98.24 217	99.86 239	99.57 67	99.50 312	99.15 316

test1111		97.74 332	98.16 305	96.49 405	99.60 193	89.86 436	99.71 34	91.21 432	99.89 44	99.88 69	99.87 53	93.73 347	99.90 173	99.56 68	99.99 16	99.70 90

lessismore_v0				99.64 139	99.86 55	99.38 187		90.66 433		99.89 60	99.83 76	94.56 338	99.97 37	99.56 68	99.92 113	99.57 184

mvsany_test1		99.44 114	99.45 103	99.40 227	99.37 292	98.64 289	97.90 382	99.59 212	99.27 183	99.92 50	99.82 83	99.74 23	99.93 104	99.55 70	99.87 155	99.63 142

MVSMamba_PlusPlus		99.55 85	99.58 77	99.47 202	99.68 172	99.40 182	99.52 89	99.70 145	99.92 34	99.77 119	99.86 60	98.28 213	99.96 58	99.54 71	99.90 124	99.05 345

pm-mvs1		99.79 30	99.79 30	99.78 63	99.91 31	99.83 30	99.76 20	99.87 58	99.73 86	99.89 60	99.87 53	99.63 34	99.87 220	99.54 71	99.92 113	99.63 142

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 39	99.90 38	99.97 22	99.87 53	99.81 17	99.95 68	99.54 71	99.99 16	99.80 57
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 99	99.65 60	98.95 308	99.71 152	97.27 362	99.50 96	99.82 81	99.59 133	99.41 253	99.85 65	99.62 37	100.00 1	99.53 74	99.89 134	99.59 174

test2506		94.73 396	94.59 397	95.15 412	99.59 198	85.90 438	99.75 22	74.01 440	99.89 44	99.71 146	99.86 60	79.00 427	99.90 173	99.52 75	99.99 16	99.65 127

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 140	99.93 31	99.95 39	99.89 38	99.71 25	99.96 58	99.51 76	99.97 62	99.84 45

FC-MVSNet-test		99.70 49	99.65 60	99.86 27	99.88 44	99.86 18	99.72 30	99.78 105	99.90 38	99.82 90	99.83 76	98.45 193	99.87 220	99.51 76	99.97 62	99.86 39

BP-MVS1		98.72 264	98.46 274	99.50 192	99.53 235	99.00 249	99.34 129	98.53 377	99.65 113	99.73 139	99.38 304	90.62 383	99.96 58	99.50 78	99.86 163	99.55 189

UA-Net		99.78 32	99.76 43	99.86 27	99.72 149	99.71 90	99.91 4	99.95 34	99.96 23	99.71 146	99.91 28	99.15 91	99.97 37	99.50 78	100.00 1	99.90 26

PMMVS2		99.48 99	99.45 103	99.57 172	99.76 123	98.99 251	98.09 359	99.90 50	98.95 232	99.78 111	99.58 242	99.57 44	99.93 104	99.48 80	99.95 89	99.79 65

VPA-MVSNet		99.66 61	99.62 65	99.79 59	99.68 172	99.75 73	99.62 64	99.69 152	99.85 60	99.80 101	99.81 90	98.81 137	99.91 154	99.47 81	99.88 143	99.70 90

GDP-MVS		98.81 255	98.57 264	99.50 192	99.53 235	99.12 236	99.28 153	99.86 62	99.53 137	99.57 199	99.32 320	90.88 379	99.98 23	99.46 82	99.74 232	99.42 253

ECVR-MVS		97.73 333	98.04 312	96.78 398	99.59 198	90.81 431	99.72 30	90.43 434	99.89 44	99.86 78	99.86 60	93.60 349	99.89 192	99.46 82	99.99 16	99.65 127

nrg030		99.70 49	99.66 58	99.82 42	99.76 123	99.84 25	99.61 70	99.70 145	99.93 31	99.78 111	99.68 182	99.10 98	99.78 325	99.45 84	99.96 75	99.83 49

TAMVS		99.49 97	99.45 103	99.63 146	99.48 260	99.42 175	99.45 109	99.57 223	99.66 110	99.78 111	99.83 76	97.85 249	99.86 239	99.44 85	99.96 75	99.61 163

GeoE		99.69 51	99.66 58	99.78 63	99.76 123	99.76 65	99.60 76	99.82 81	99.46 152	99.75 127	99.56 253	99.63 34	99.95 68	99.43 86	99.88 143	99.62 153

new-patchmatchnet		99.35 140	99.57 81	98.71 338	99.82 74	96.62 377	98.55 315	99.75 118	99.50 141	99.88 69	99.87 53	99.31 72	99.88 206	99.43 86	100.00 1	99.62 153

test20.03		99.55 85	99.54 88	99.58 166	99.79 102	99.37 190	99.02 240	99.89 52	99.60 131	99.82 90	99.62 217	98.81 137	99.89 192	99.43 86	99.86 163	99.47 233

MVSFormer		99.41 124	99.44 106	99.31 254	99.57 213	98.40 304	99.77 16	99.80 93	99.73 86	99.63 173	99.30 325	98.02 236	99.98 23	99.43 86	99.69 253	99.55 189

test_djsdf		99.84 17	99.81 26	99.91 3	99.94 18	99.84 25	99.77 16	99.80 93	99.73 86	99.97 22	99.92 25	99.77 22	99.98 23	99.43 86	100.00 1	99.90 26

SDMVSNet		99.77 39	99.77 39	99.76 73	99.80 90	99.65 115	99.63 61	99.86 62	99.97 20	99.89 60	99.89 38	99.52 51	99.99 8	99.42 91	99.96 75	99.65 127

Anonymous20231211		99.62 74	99.57 81	99.76 73	99.61 191	99.60 134	99.81 10	99.73 128	99.82 70	99.90 56	99.90 33	97.97 241	99.86 239	99.42 91	99.96 75	99.80 57

SixPastTwentyTwo		99.42 120	99.30 138	99.76 73	99.92 29	99.67 107	99.70 35	99.14 345	99.65 113	99.89 60	99.90 33	96.20 318	99.94 84	99.42 91	99.92 113	99.67 110

balanced_conf03		99.50 93	99.50 94	99.50 192	99.42 283	99.49 154	99.52 89	99.75 118	99.86 54	99.78 111	99.71 156	98.20 224	99.90 173	99.39 94	99.88 143	99.10 327

patch_mono-2		99.51 92	99.46 101	99.64 139	99.70 160	99.11 237	99.04 234	99.87 58	99.71 92	99.47 234	99.79 103	98.24 217	99.98 23	99.38 95	99.96 75	99.83 49

UGNet		99.38 132	99.34 126	99.49 196	98.90 381	98.90 265	99.70 35	99.35 304	99.86 54	98.57 366	99.81 90	98.50 188	99.93 104	99.38 95	99.98 45	99.66 119
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 48	99.67 56	99.81 47	99.89 39	99.72 87	99.59 77	99.82 81	99.39 168	99.82 90	99.84 72	99.38 63	99.91 154	99.38 95	99.93 109	99.80 57

FIs		99.65 66	99.58 77	99.84 34	99.84 63	99.85 20	99.66 54	99.75 118	99.86 54	99.74 135	99.79 103	98.27 215	99.85 257	99.37 98	99.93 109	99.83 49

sd_testset		99.78 32	99.78 34	99.80 52	99.80 90	99.76 65	99.80 11	99.79 99	99.97 20	99.89 60	99.89 38	99.53 49	99.99 8	99.36 99	99.96 75	99.65 127

anonymousdsp		99.80 26	99.77 39	99.90 8	99.96 7	99.88 12	99.73 27	99.85 68	99.70 97	99.92 50	99.93 21	99.45 54	99.97 37	99.36 99	100.00 1	99.85 42

casdiffmvs_mvg		99.68 54	99.68 55	99.69 114	99.81 83	99.59 136	99.29 151	99.90 50	99.71 92	99.79 107	99.73 139	99.54 47	99.84 272	99.36 99	99.96 75	99.65 127
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 41	99.74 46	99.79 59	99.88 44	99.66 109	99.69 42	99.92 39	99.67 106	99.77 119	99.75 131	99.61 38	99.98 23	99.35 102	99.98 45	99.72 84
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 76	99.64 63	99.53 185	99.79 102	98.82 269	99.58 79	99.97 20	99.95 26	99.96 29	99.76 126	98.44 194	99.99 8	99.34 103	99.96 75	99.78 67

CHOSEN 1792x2688		99.39 130	99.30 138	99.65 132	99.88 44	99.25 215	98.78 289	99.88 56	98.66 272	99.96 29	99.79 103	97.45 271	99.93 104	99.34 103	99.99 16	99.78 67

CDS-MVSNet		99.22 173	99.13 166	99.50 192	99.35 299	99.11 237	98.96 259	99.54 240	99.46 152	99.61 188	99.70 164	96.31 314	99.83 287	99.34 103	99.88 143	99.55 189
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 229	99.16 160	98.51 346	99.75 135	95.90 392	98.07 362	99.84 74	99.84 63	99.89 60	99.73 139	96.01 321	99.99 8	99.33 106	100.00 1	99.63 142

HyFIR lowres test		98.91 242	98.64 255	99.73 97	99.85 59	99.47 157	98.07 362	99.83 76	98.64 274	99.89 60	99.60 234	92.57 358	100.00 1	99.33 106	99.97 62	99.72 84

pmmvs5		99.19 183	99.11 173	99.42 218	99.76 123	98.88 266	98.55 315	99.73 128	98.82 252	99.72 141	99.62 217	96.56 302	99.82 297	99.32 108	99.95 89	99.56 186

v148		99.40 126	99.41 112	99.39 230	99.76 123	98.94 259	99.09 221	99.59 212	99.17 203	99.81 97	99.61 226	98.41 198	99.69 361	99.32 108	99.94 102	99.53 203

baseline		99.63 68	99.62 65	99.66 126	99.80 90	99.62 125	99.44 111	99.80 93	99.71 92	99.72 141	99.69 171	99.15 91	99.83 287	99.32 108	99.94 102	99.53 203

CVMVSNet		98.61 272	98.88 235	97.80 377	99.58 203	93.60 415	99.26 159	99.64 183	99.66 110	99.72 141	99.67 186	93.26 351	99.93 104	99.30 111	99.81 200	99.87 37

PS-CasMVS		99.66 61	99.58 77	99.89 11	99.80 90	99.85 20	99.66 54	99.73 128	99.62 121	99.84 84	99.71 156	98.62 166	99.96 58	99.30 111	99.96 75	99.86 39

DTE-MVSNet		99.68 54	99.61 69	99.88 18	99.80 90	99.87 14	99.67 50	99.71 140	99.72 90	99.84 84	99.78 114	98.67 160	99.97 37	99.30 111	99.95 89	99.80 57

tmp_tt		95.75 389	95.42 384	96.76 399	89.90 439	94.42 409	98.86 271	97.87 403	78.01 430	99.30 284	99.69 171	97.70 257	95.89 432	99.29 114	98.14 408	99.95 14

PEN-MVS		99.66 61	99.59 74	99.89 11	99.83 67	99.87 14	99.66 54	99.73 128	99.70 97	99.84 84	99.73 139	98.56 175	99.96 58	99.29 114	99.94 102	99.83 49

WR-MVS_H		99.61 76	99.53 92	99.87 23	99.80 90	99.83 30	99.67 50	99.75 118	99.58 134	99.85 81	99.69 171	98.18 227	99.94 84	99.28 116	99.95 89	99.83 49

IterMVS		98.97 233	99.16 160	98.42 351	99.74 143	95.64 396	98.06 364	99.83 76	99.83 68	99.85 81	99.74 135	96.10 320	99.99 8	99.27 117	100.00 1	99.63 142
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WBMVS		97.50 343	97.18 349	98.48 348	98.85 389	95.89 393	98.44 332	99.52 254	99.53 137	99.52 221	99.42 293	80.10 420	99.86 239	99.24 118	99.95 89	99.68 102

h-mvs33		98.61 272	98.34 288	99.44 212	99.60 193	98.67 281	99.27 157	99.44 279	99.68 102	99.32 274	99.49 276	92.50 361	100.00 1	99.24 118	96.51 425	99.65 127

hse-mvs2		98.52 285	98.30 293	99.16 280	99.29 321	98.60 292	98.77 290	99.02 353	99.68 102	99.32 274	99.04 365	92.50 361	99.85 257	99.24 118	97.87 415	99.03 349

FMVSNet1		99.66 61	99.63 64	99.73 97	99.78 110	99.77 58	99.68 46	99.70 145	99.67 106	99.82 90	99.83 76	98.98 119	99.90 173	99.24 118	99.97 62	99.53 203

casdiffmvs		99.63 68	99.61 69	99.67 119	99.79 102	99.59 136	99.13 204	99.85 68	99.79 78	99.76 122	99.72 146	99.33 70	99.82 297	99.21 122	99.94 102	99.59 174
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 88	99.43 108	99.87 23	99.76 123	99.82 38	99.57 82	99.61 195	99.54 135	99.80 101	99.64 198	97.79 253	99.95 68	99.21 122	99.94 102	99.84 45

DELS-MVS		99.34 145	99.30 138	99.48 200	99.51 244	99.36 194	98.12 355	99.53 249	99.36 173	99.41 253	99.61 226	99.22 84	99.87 220	99.21 122	99.68 258	99.20 304
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)		99.37 135	99.26 149	99.68 116	99.51 244	99.58 140	98.98 254	99.60 206	99.43 163	99.70 150	99.36 311	97.70 257	99.88 206	99.20 125	99.87 155	99.59 174

CANet		99.11 204	99.05 194	99.28 261	98.83 391	98.56 294	98.71 297	99.41 285	99.25 187	99.23 292	99.22 343	97.66 265	99.94 84	99.19 126	99.97 62	99.33 273

EI-MVSNet-UG-set		99.48 99	99.50 94	99.42 218	99.57 213	98.65 287	99.24 166	99.46 274	99.68 102	99.80 101	99.66 191	98.99 117	99.89 192	99.19 126	99.90 124	99.72 84

xiu_mvs_v1_base_debu		99.23 165	99.34 126	98.91 315	99.59 198	98.23 313	98.47 327	99.66 165	99.61 125	99.68 156	98.94 381	99.39 59	99.97 37	99.18 128	99.55 298	98.51 397

xiu_mvs_v1_base		99.23 165	99.34 126	98.91 315	99.59 198	98.23 313	98.47 327	99.66 165	99.61 125	99.68 156	98.94 381	99.39 59	99.97 37	99.18 128	99.55 298	98.51 397

xiu_mvs_v1_base_debi		99.23 165	99.34 126	98.91 315	99.59 198	98.23 313	98.47 327	99.66 165	99.61 125	99.68 156	98.94 381	99.39 59	99.97 37	99.18 128	99.55 298	98.51 397

VPNet		99.46 108	99.37 119	99.71 108	99.82 74	99.59 136	99.48 102	99.70 145	99.81 73	99.69 153	99.58 242	97.66 265	99.86 239	99.17 131	99.44 319	99.67 110

UniMVSNet_NR-MVSNet		99.37 135	99.25 151	99.72 103	99.47 266	99.56 143	98.97 256	99.61 195	99.43 163	99.67 161	99.28 329	97.85 249	99.95 68	99.17 131	99.81 200	99.65 127

DU-MVS		99.33 148	99.21 155	99.71 108	99.43 278	99.56 143	98.83 277	99.53 249	99.38 169	99.67 161	99.36 311	97.67 261	99.95 68	99.17 131	99.81 200	99.63 142

EI-MVSNet-Vis-set		99.47 107	99.49 96	99.42 218	99.57 213	98.66 284	99.24 166	99.46 274	99.67 106	99.79 107	99.65 196	98.97 121	99.89 192	99.15 134	99.89 134	99.71 87

EI-MVSNet		99.38 132	99.44 106	99.21 274	99.58 203	98.09 327	99.26 159	99.46 274	99.62 121	99.75 127	99.67 186	98.54 178	99.85 257	99.15 134	99.92 113	99.68 102

VNet		99.18 187	99.06 190	99.56 175	99.24 332	99.36 194	99.33 133	99.31 313	99.67 106	99.47 234	99.57 249	96.48 305	99.84 272	99.15 134	99.30 338	99.47 233

EG-PatchMatch MVS		99.57 79	99.56 86	99.62 155	99.77 119	99.33 200	99.26 159	99.76 113	99.32 177	99.80 101	99.78 114	99.29 74	99.87 220	99.15 134	99.91 123	99.66 119

PVSNet_Blended_VisFu		99.40 126	99.38 116	99.44 212	99.90 37	98.66 284	98.94 263	99.91 45	97.97 335	99.79 107	99.73 139	99.05 110	99.97 37	99.15 134	99.99 16	99.68 102

IterMVS-LS		99.41 124	99.47 97	99.25 270	99.81 83	98.09 327	98.85 273	99.76 113	99.62 121	99.83 89	99.64 198	98.54 178	99.97 37	99.15 134	99.99 16	99.68 102
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 88	99.47 97	99.76 73	99.58 203	99.64 118	99.30 144	99.63 185	99.61 125	99.71 146	99.56 253	98.76 147	99.96 58	99.14 140	99.92 113	99.68 102

MVSTER		98.47 292	98.22 298	99.24 272	99.06 365	98.35 310	99.08 224	99.46 274	99.27 183	99.75 127	99.66 191	88.61 396	99.85 257	99.14 140	99.92 113	99.52 213

Anonymous20231206		99.35 140	99.31 133	99.47 202	99.74 143	99.06 247	99.28 153	99.74 124	99.23 191	99.72 141	99.53 265	97.63 267	99.88 206	99.11 142	99.84 173	99.48 229

Syy-MVS		98.17 317	97.85 329	99.15 282	98.50 414	98.79 273	98.60 304	99.21 336	97.89 341	96.76 417	96.37 440	95.47 329	99.57 403	99.10 143	98.73 384	99.09 332

ttmdpeth		99.48 99	99.55 87	99.29 258	99.76 123	98.16 321	99.33 133	99.95 34	99.79 78	99.36 263	99.89 38	99.13 96	99.77 333	99.09 144	99.64 271	99.93 20

MVS_Test		99.28 154	99.31 133	99.19 277	99.35 299	98.79 273	99.36 127	99.49 267	99.17 203	99.21 297	99.67 186	98.78 144	99.66 383	99.09 144	99.66 267	99.10 327

testgi		99.29 153	99.26 149	99.37 236	99.75 135	98.81 270	98.84 274	99.89 52	98.38 302	99.75 127	99.04 365	99.36 68	99.86 239	99.08 146	99.25 346	99.45 238

1112_ss		99.05 215	98.84 240	99.67 119	99.66 179	99.29 206	98.52 321	99.82 81	97.65 353	99.43 244	99.16 349	96.42 308	99.91 154	99.07 147	99.84 173	99.80 57

CANet_DTU		98.91 242	98.85 238	99.09 291	98.79 397	98.13 322	98.18 348	99.31 313	99.48 144	98.86 337	99.51 269	96.56 302	99.95 68	99.05 148	99.95 89	99.19 307

Baseline_NR-MVSNet		99.49 97	99.37 119	99.82 42	99.91 31	99.84 25	98.83 277	99.86 62	99.68 102	99.65 168	99.88 47	97.67 261	99.87 220	99.03 149	99.86 163	99.76 76

FMVSNet2		99.35 140	99.28 145	99.55 179	99.49 255	99.35 197	99.45 109	99.57 223	99.44 157	99.70 150	99.74 135	97.21 282	99.87 220	99.03 149	99.94 102	99.44 243

Test_1112_low_res		98.95 239	98.73 249	99.63 146	99.68 172	99.15 233	98.09 359	99.80 93	97.14 379	99.46 238	99.40 298	96.11 319	99.89 192	99.01 151	99.84 173	99.84 45

VDD-MVS		99.20 180	99.11 173	99.44 212	99.43 278	98.98 252	99.50 96	98.32 391	99.80 76	99.56 207	99.69 171	96.99 292	99.85 257	98.99 152	99.73 238	99.50 220

DeepC-MVS	98.90 4	99.62 74	99.61 69	99.67 119	99.72 149	99.44 168	99.24 166	99.71 140	99.27 183	99.93 45	99.90 33	99.70 28	99.93 104	98.99 152	99.99 16	99.64 137
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 99	99.47 97	99.51 190	99.77 119	99.41 181	98.81 282	99.66 165	99.42 167	99.75 127	99.66 191	99.20 86	99.76 336	98.98 154	99.99 16	99.36 266

EPNet_dtu		97.62 338	97.79 332	97.11 397	96.67 434	92.31 420	98.51 322	98.04 397	99.24 189	95.77 426	99.47 283	93.78 346	99.66 383	98.98 154	99.62 275	99.37 263
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 145	99.32 131	99.39 230	99.67 178	98.77 275	98.57 313	99.81 90	99.61 125	99.48 232	99.41 294	98.47 189	99.86 239	98.97 156	99.90 124	99.53 203
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		99.40 126	99.31 133	99.68 116	99.43 278	99.55 147	99.73 27	99.50 263	99.46 152	99.88 69	99.36 311	97.54 268	99.87 220	98.97 156	99.87 155	99.63 142

GBi-Net		99.42 120	99.31 133	99.73 97	99.49 255	99.77 58	99.68 46	99.70 145	99.44 157	99.62 182	99.83 76	97.21 282	99.90 173	98.96 158	99.90 124	99.53 203

FMVSNet5		97.80 330	97.25 347	99.42 218	98.83 391	98.97 255	99.38 120	99.80 93	98.87 244	99.25 288	99.69 171	80.60 419	99.91 154	98.96 158	99.90 124	99.38 260

test1		99.42 120	99.31 133	99.73 97	99.49 255	99.77 58	99.68 46	99.70 145	99.44 157	99.62 182	99.83 76	97.21 282	99.90 173	98.96 158	99.90 124	99.53 203

FMVSNet3		98.80 256	98.63 257	99.32 251	99.13 351	98.72 278	99.10 216	99.48 268	99.23 191	99.62 182	99.64 198	92.57 358	99.86 239	98.96 158	99.90 124	99.39 258

UnsupCasMVSNet_eth		98.83 252	98.57 264	99.59 163	99.68 172	99.45 166	98.99 251	99.67 160	99.48 144	99.55 212	99.36 311	94.92 332	99.86 239	98.95 162	96.57 424	99.45 238

CHOSEN 280x420		98.41 297	98.41 280	98.40 352	99.34 308	95.89 393	96.94 418	99.44 279	98.80 256	99.25 288	99.52 267	93.51 350	99.98 23	98.94 163	99.98 45	99.32 276

TDRefinement		99.72 45	99.70 49	99.77 66	99.90 37	99.85 20	99.86 6	99.92 39	99.69 100	99.78 111	99.92 25	99.37 65	99.88 206	98.93 164	99.95 89	99.60 167

alignmvs		98.28 307	97.96 318	99.25 270	99.12 353	98.93 262	99.03 237	98.42 384	99.64 116	98.72 352	97.85 419	90.86 380	99.62 394	98.88 165	99.13 352	99.19 307

testing3-2		96.51 368	96.43 363	96.74 401	99.36 295	91.38 428	99.10 216	97.87 403	99.48 144	98.57 366	98.71 395	76.65 429	99.66 383	98.87 166	99.26 345	99.18 309

MGCFI-Net		99.02 221	99.01 206	99.06 298	99.11 358	98.60 292	99.63 61	99.67 160	99.63 118	98.58 364	97.65 422	99.07 105	99.57 403	98.85 167	98.92 368	99.03 349

sss		98.90 244	98.77 248	99.27 264	99.48 260	98.44 301	98.72 295	99.32 309	97.94 339	99.37 262	99.35 316	96.31 314	99.91 154	98.85 167	99.63 274	99.47 233

xiu_mvs_v2_base		99.02 221	99.11 173	98.77 333	99.37 292	98.09 327	98.13 354	99.51 259	99.47 149	99.42 247	98.54 404	99.38 63	99.97 37	98.83 169	99.33 334	98.24 409

PS-MVSNAJ		99.00 229	99.08 184	98.76 334	99.37 292	98.10 326	98.00 370	99.51 259	99.47 149	99.41 253	98.50 406	99.28 76	99.97 37	98.83 169	99.34 333	98.20 413

D2MVS		99.22 173	99.19 157	99.29 258	99.69 164	98.74 277	98.81 282	99.41 285	98.55 283	99.68 156	99.69 171	98.13 229	99.87 220	98.82 171	99.98 45	99.24 291

PatchT		98.45 294	98.32 290	98.83 328	98.94 379	98.29 311	99.24 166	98.82 361	99.84 63	99.08 314	99.76 126	91.37 369	99.94 84	98.82 171	99.00 363	98.26 408

testf1		99.63 68	99.60 72	99.72 103	99.94 18	99.95 2	99.47 105	99.89 52	99.43 163	99.88 69	99.80 93	99.26 80	99.90 173	98.81 173	99.88 143	99.32 276

APD_test2		99.63 68	99.60 72	99.72 103	99.94 18	99.95 2	99.47 105	99.89 52	99.43 163	99.88 69	99.80 93	99.26 80	99.90 173	98.81 173	99.88 143	99.32 276

sasdasda		99.02 221	99.00 210	99.09 291	99.10 360	98.70 279	99.61 70	99.66 165	99.63 118	98.64 358	97.65 422	99.04 111	99.54 407	98.79 175	98.92 368	99.04 347

Effi-MVS+		99.06 212	98.97 221	99.34 243	99.31 315	98.98 252	98.31 340	99.91 45	98.81 254	98.79 346	98.94 381	99.14 94	99.84 272	98.79 175	98.74 381	99.20 304

canonicalmvs		99.02 221	99.00 210	99.09 291	99.10 360	98.70 279	99.61 70	99.66 165	99.63 118	98.64 358	97.65 422	99.04 111	99.54 407	98.79 175	98.92 368	99.04 347

VDDNet		98.97 233	98.82 243	99.42 218	99.71 152	98.81 270	99.62 64	98.68 368	99.81 73	99.38 261	99.80 93	94.25 340	99.85 257	98.79 175	99.32 336	99.59 174

CR-MVSNet		98.35 304	98.20 300	98.83 328	99.05 366	98.12 323	99.30 144	99.67 160	97.39 367	99.16 303	99.79 103	91.87 366	99.91 154	98.78 179	98.77 377	98.44 402

test_method		91.72 397	92.32 400	89.91 415	93.49 438	70.18 441	90.28 429	99.56 228	61.71 433	95.39 428	99.52 267	93.90 342	99.94 84	98.76 180	98.27 401	99.62 153

RPMNet		98.60 275	98.53 270	98.83 328	99.05 366	98.12 323	99.30 144	99.62 188	99.86 54	99.16 303	99.74 135	92.53 360	99.92 131	98.75 181	98.77 377	98.44 402

pmmvs4		99.13 199	99.06 190	99.36 240	99.57 213	99.10 242	98.01 368	99.25 326	98.78 259	99.58 196	99.44 290	98.24 217	99.76 336	98.74 182	99.93 109	99.22 297

tttt0517		97.62 338	97.20 348	98.90 321	99.76 123	97.40 359	99.48 102	94.36 425	99.06 220	99.70 150	99.49 276	84.55 412	99.94 84	98.73 183	99.65 269	99.36 266

EPP-MVSNet		99.17 192	99.00 210	99.66 126	99.80 90	99.43 172	99.70 35	99.24 329	99.48 144	99.56 207	99.77 123	94.89 333	99.93 104	98.72 184	99.89 134	99.63 142

Anonymous20240529		99.42 120	99.34 126	99.65 132	99.53 235	99.60 134	99.63 61	99.39 295	99.47 149	99.76 122	99.78 114	98.13 229	99.86 239	98.70 185	99.68 258	99.49 225

ACMH	98.42 6	99.59 78	99.54 88	99.72 103	99.86 55	99.62 125	99.56 84	99.79 99	98.77 261	99.80 101	99.85 65	99.64 32	99.85 257	98.70 185	99.89 134	99.70 90
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 148	99.28 145	99.47 202	99.57 213	99.39 185	99.78 14	99.43 282	98.87 244	99.57 199	99.82 83	98.06 234	99.87 220	98.69 187	99.73 238	99.15 316

LFMVS		98.46 293	98.19 303	99.26 267	99.24 332	98.52 297	99.62 64	96.94 414	99.87 51	99.31 279	99.58 242	91.04 374	99.81 312	98.68 188	99.42 323	99.45 238

WR-MVS		99.11 204	98.93 226	99.66 126	99.30 319	99.42 175	98.42 333	99.37 300	99.04 221	99.57 199	99.20 347	96.89 294	99.86 239	98.66 189	99.87 155	99.70 90

mvsmamba		99.08 208	98.95 224	99.45 208	99.36 295	99.18 230	99.39 117	98.81 362	99.37 170	99.35 265	99.70 164	96.36 313	99.94 84	98.66 189	99.59 289	99.22 297

RRT-MVS		99.08 208	99.00 210	99.33 246	99.27 326	98.65 287	99.62 64	99.93 37	99.66 110	99.67 161	99.82 83	95.27 331	99.93 104	98.64 191	99.09 356	99.41 254

Anonymous202405211		98.75 260	98.46 274	99.63 146	99.34 308	99.66 109	99.47 105	97.65 406	99.28 182	99.56 207	99.50 272	93.15 352	99.84 272	98.62 192	99.58 291	99.40 256

EPNet		98.13 318	97.77 333	99.18 279	94.57 437	97.99 333	99.24 166	97.96 399	99.74 85	97.29 410	99.62 217	93.13 353	99.97 37	98.59 193	99.83 181	99.58 179
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 215	99.09 182	98.91 315	99.21 337	98.36 309	98.82 281	99.47 271	98.85 247	98.90 332	99.56 253	98.78 144	99.09 423	98.57 194	99.68 258	99.26 288

Patchmatch-RL test		98.60 275	98.36 285	99.33 246	99.77 119	99.07 245	98.27 342	99.87 58	98.91 239	99.74 135	99.72 146	90.57 385	99.79 322	98.55 195	99.85 168	99.11 325

pmmvs3		98.08 321	97.80 330	98.91 315	99.41 285	97.69 350	97.87 383	99.66 165	95.87 398	99.50 229	99.51 269	90.35 387	99.97 37	98.55 195	99.47 316	99.08 338

ETV-MVS		99.18 187	99.18 158	99.16 280	99.34 308	99.28 208	99.12 208	99.79 99	99.48 144	98.93 326	98.55 403	99.40 58	99.93 104	98.51 197	99.52 308	98.28 407

jason		99.16 193	99.11 173	99.32 251	99.75 135	98.44 301	98.26 344	99.39 295	98.70 269	99.74 135	99.30 325	98.54 178	99.97 37	98.48 198	99.82 190	99.55 189
jason: jason.
APDe-MVS		99.48 99	99.36 122	99.85 29	99.55 227	99.81 43	99.50 96	99.69 152	98.99 225	99.75 127	99.71 156	98.79 142	99.93 104	98.46 199	99.85 168	99.80 57
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CL-MVSNet_self_test		98.71 266	98.56 268	99.15 282	99.22 335	98.66 284	97.14 413	99.51 259	98.09 328	99.54 214	99.27 331	96.87 295	99.74 343	98.43 200	98.96 365	99.03 349

our_test_3		98.85 251	99.09 182	98.13 365	99.66 179	94.90 407	97.72 388	99.58 221	99.07 218	99.64 169	99.62 217	98.19 225	99.93 104	98.41 201	99.95 89	99.55 189

Gipuma		99.57 79	99.59 74	99.49 196	99.98 3	99.71 90	99.72 30	99.84 74	99.81 73	99.94 42	99.78 114	98.91 129	99.71 352	98.41 201	99.95 89	99.05 345
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 348	96.91 358	98.74 335	97.72 430	97.57 352	97.60 394	97.36 412	98.00 331	99.21 297	98.02 415	90.04 390	99.79 322	98.37 203	95.89 429	98.86 372

PM-MVS		99.36 138	99.29 143	99.58 166	99.83 67	99.66 109	98.95 261	99.86 62	98.85 247	99.81 97	99.73 139	98.40 202	99.92 131	98.36 204	99.83 181	99.17 312

baseline1		97.73 333	97.33 344	98.96 306	99.30 319	97.73 348	99.40 115	98.42 384	99.33 176	99.46 238	99.21 345	91.18 372	99.82 297	98.35 205	91.26 432	99.32 276

MVS-HIRNet		97.86 327	98.22 298	96.76 399	99.28 324	91.53 426	98.38 335	92.60 431	99.13 211	99.31 279	99.96 15	97.18 286	99.68 373	98.34 206	99.83 181	99.07 343

GA-MVS		97.99 326	97.68 336	98.93 312	99.52 242	98.04 331	97.19 412	99.05 352	98.32 315	98.81 342	98.97 377	89.89 392	99.41 418	98.33 207	99.05 359	99.34 272

Fast-Effi-MVS+		99.02 221	98.87 236	99.46 205	99.38 290	99.50 153	99.04 234	99.79 99	97.17 377	98.62 360	98.74 394	99.34 69	99.95 68	98.32 208	99.41 324	98.92 365

MDA-MVSNet_test_wron		98.95 239	98.99 217	98.85 324	99.64 184	97.16 365	98.23 346	99.33 307	98.93 236	99.56 207	99.66 191	97.39 275	99.83 287	98.29 209	99.88 143	99.55 189

N_pmnet		98.73 263	98.53 270	99.35 242	99.72 149	98.67 281	98.34 337	94.65 424	98.35 309	99.79 107	99.68 182	98.03 235	99.93 104	98.28 210	99.92 113	99.44 243

ET-MVSNet_ETH3D		96.78 360	96.07 370	98.91 315	99.26 329	97.92 340	97.70 390	96.05 419	97.96 338	92.37 432	98.43 407	87.06 400	99.90 173	98.27 211	97.56 418	98.91 366

thisisatest0530		97.45 344	96.95 355	98.94 309	99.68 172	97.73 348	99.09 221	94.19 427	98.61 279	99.56 207	99.30 325	84.30 414	99.93 104	98.27 211	99.54 303	99.16 314

YYNet1		98.95 239	98.99 217	98.84 326	99.64 184	97.14 367	98.22 347	99.32 309	98.92 238	99.59 194	99.66 191	97.40 273	99.83 287	98.27 211	99.90 124	99.55 189

reproduce_model		99.50 93	99.40 113	99.83 37	99.60 193	99.83 30	99.12 208	99.68 155	99.49 143	99.80 101	99.79 103	99.01 114	99.93 104	98.24 214	99.82 190	99.73 81

ACMM	98.09 11	99.46 108	99.38 116	99.72 103	99.80 90	99.69 102	99.13 204	99.65 175	98.99 225	99.64 169	99.72 146	99.39 59	99.86 239	98.23 215	99.81 200	99.60 167
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 236	98.87 236	99.24 272	99.57 213	98.40 304	98.12 355	99.18 340	98.28 317	99.63 173	99.13 351	98.02 236	99.97 37	98.22 216	99.69 253	99.35 269

3Dnovator	99.15 2	99.43 117	99.36 122	99.65 132	99.39 287	99.42 175	99.70 35	99.56 228	99.23 191	99.35 265	99.80 93	99.17 89	99.95 68	98.21 217	99.84 173	99.59 174

Fast-Effi-MVS+-dtu		99.20 180	99.12 170	99.43 216	99.25 330	99.69 102	99.05 229	99.82 81	99.50 141	98.97 322	99.05 363	98.98 119	99.98 23	98.20 218	99.24 348	98.62 387

MS-PatchMatch		99.00 229	98.97 221	99.09 291	99.11 358	98.19 317	98.76 291	99.33 307	98.49 292	99.44 240	99.58 242	98.21 222	99.69 361	98.20 218	99.62 275	99.39 258

TSAR-MVS + GP.		99.12 201	99.04 200	99.38 233	99.34 308	99.16 231	98.15 351	99.29 317	98.18 324	99.63 173	99.62 217	99.18 88	99.68 373	98.20 218	99.74 232	99.30 282

DP-MVS		99.48 99	99.39 114	99.74 88	99.57 213	99.62 125	99.29 151	99.61 195	99.87 51	99.74 135	99.76 126	98.69 156	99.87 220	98.20 218	99.80 207	99.75 79

MVP-Stereo		99.16 193	99.08 184	99.43 216	99.48 260	99.07 245	99.08 224	99.55 234	98.63 275	99.31 279	99.68 182	98.19 225	99.78 325	98.18 222	99.58 291	99.45 238
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 117	99.30 138	99.80 52	99.83 67	99.81 43	99.52 89	99.70 145	98.35 309	99.51 227	99.50 272	99.31 72	99.88 206	98.18 222	99.84 173	99.69 96

MDA-MVSNet-bldmvs		99.06 212	99.05 194	99.07 296	99.80 90	97.83 343	98.89 267	99.72 137	99.29 179	99.63 173	99.70 164	96.47 306	99.89 192	98.17 224	99.82 190	99.50 220

JIA-IIPM		98.06 322	97.92 325	98.50 347	98.59 410	97.02 369	98.80 285	98.51 379	99.88 49	97.89 396	99.87 53	91.89 365	99.90 173	98.16 225	97.68 417	98.59 390

EIA-MVS		99.12 201	99.01 206	99.45 208	99.36 295	99.62 125	99.34 129	99.79 99	98.41 298	98.84 339	98.89 385	98.75 149	99.84 272	98.15 226	99.51 309	98.89 369

miper_lstm_enhance		98.65 271	98.60 258	98.82 331	99.20 340	97.33 361	97.78 386	99.66 165	99.01 224	99.59 194	99.50 272	94.62 337	99.85 257	98.12 227	99.90 124	99.26 288

reproduce-ours		99.46 108	99.35 124	99.82 42	99.56 224	99.83 30	99.05 229	99.65 175	99.45 155	99.78 111	99.78 114	98.93 124	99.93 104	98.11 228	99.81 200	99.70 90

our_new_method		99.46 108	99.35 124	99.82 42	99.56 224	99.83 30	99.05 229	99.65 175	99.45 155	99.78 111	99.78 114	98.93 124	99.93 104	98.11 228	99.81 200	99.70 90

Effi-MVS+-dtu		99.07 211	98.92 230	99.52 187	98.89 384	99.78 52	99.15 196	99.66 165	99.34 174	98.92 329	99.24 341	97.69 259	99.98 23	98.11 228	99.28 341	98.81 376

tpm		97.15 352	96.95 355	97.75 379	98.91 380	94.24 410	99.32 136	97.96 399	97.71 351	98.29 377	99.32 320	86.72 406	99.92 131	98.10 231	96.24 427	99.09 332

DeepPCF-MVS	98.42 6	99.18 187	99.02 203	99.67 119	99.22 335	99.75 73	97.25 410	99.47 271	98.72 266	99.66 166	99.70 164	99.29 74	99.63 393	98.07 232	99.81 200	99.62 153

ppachtmachnet_test		98.89 247	99.12 170	98.20 363	99.66 179	95.24 403	97.63 392	99.68 155	99.08 216	99.78 111	99.62 217	98.65 164	99.88 206	98.02 233	99.96 75	99.48 229

tpmrst		97.73 333	98.07 311	96.73 402	98.71 406	92.00 421	99.10 216	98.86 358	98.52 288	98.92 329	99.54 263	91.90 364	99.82 297	98.02 233	99.03 361	98.37 404

CSCG		99.37 135	99.29 143	99.60 161	99.71 152	99.46 161	99.43 113	99.85 68	98.79 257	99.41 253	99.60 234	98.92 127	99.92 131	98.02 233	99.92 113	99.43 249

eth_miper_zixun_eth		98.68 269	98.71 251	98.60 342	99.10 360	96.84 374	97.52 400	99.54 240	98.94 233	99.58 196	99.48 279	96.25 317	99.76 336	98.01 236	99.93 109	99.21 300

Patchmtry		98.78 257	98.54 269	99.49 196	98.89 384	99.19 228	99.32 136	99.67 160	99.65 113	99.72 141	99.79 103	91.87 366	99.95 68	98.00 237	99.97 62	99.33 273

PVSNet_BlendedMVS		99.03 219	99.01 206	99.09 291	99.54 229	97.99 333	98.58 309	99.82 81	97.62 354	99.34 269	99.71 156	98.52 185	99.77 333	97.98 238	99.97 62	99.52 213

PVSNet_Blended		98.70 267	98.59 260	99.02 301	99.54 229	97.99 333	97.58 395	99.82 81	95.70 402	99.34 269	98.98 375	98.52 185	99.77 333	97.98 238	99.83 181	99.30 282

cl____		98.54 283	98.41 280	98.92 313	99.03 370	97.80 346	97.46 402	99.59 212	98.90 240	99.60 191	99.46 286	93.85 344	99.78 325	97.97 240	99.89 134	99.17 312

DIV-MVS_self_test		98.54 283	98.42 279	98.92 313	99.03 370	97.80 346	97.46 402	99.59 212	98.90 240	99.60 191	99.46 286	93.87 343	99.78 325	97.97 240	99.89 134	99.18 309

AUN-MVS		97.82 329	97.38 343	99.14 285	99.27 326	98.53 295	98.72 295	99.02 353	98.10 326	97.18 413	99.03 369	89.26 394	99.85 257	97.94 242	97.91 413	99.03 349

FA-MVS(test-final)		98.52 285	98.32 290	99.10 290	99.48 260	98.67 281	99.77 16	98.60 375	97.35 369	99.63 173	99.80 93	93.07 354	99.84 272	97.92 243	99.30 338	98.78 379

ambc				99.20 276	99.35 299	98.53 295	99.17 188	99.46 274		99.67 161	99.80 93	98.46 192	99.70 355	97.92 243	99.70 249	99.38 260

USDC		98.96 236	98.93 226	99.05 299	99.54 229	97.99 333	97.07 416	99.80 93	98.21 321	99.75 127	99.77 123	98.43 195	99.64 392	97.90 245	99.88 143	99.51 215

OPM-MVS		99.26 160	99.13 166	99.63 146	99.70 160	99.61 131	98.58 309	99.48 268	98.50 290	99.52 221	99.63 210	99.14 94	99.76 336	97.89 246	99.77 221	99.51 215
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 150	99.17 159	99.77 66	99.69 164	99.80 47	99.14 198	99.31 313	99.16 205	99.62 182	99.61 226	98.35 206	99.91 154	97.88 247	99.72 244	99.61 163
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 37	99.70 160	99.79 49	99.14 198	99.61 195					99.92 131	97.88 247	99.72 244	99.77 71

c3_l		98.72 264	98.71 251	98.72 336	99.12 353	97.22 364	97.68 391	99.56 228	98.90 240	99.54 214	99.48 279	96.37 312	99.73 346	97.88 247	99.88 143	99.21 300

3Dnovator+	98.92 3	99.35 140	99.24 153	99.67 119	99.35 299	99.47 157	99.62 64	99.50 263	99.44 157	99.12 310	99.78 114	98.77 146	99.94 84	97.87 250	99.72 244	99.62 153

miper_ehance_all_eth		98.59 278	98.59 260	98.59 343	98.98 376	97.07 368	97.49 401	99.52 254	98.50 290	99.52 221	99.37 307	96.41 310	99.71 352	97.86 251	99.62 275	99.00 356

WTY-MVS		98.59 278	98.37 284	99.26 267	99.43 278	98.40 304	98.74 293	99.13 347	98.10 326	99.21 297	99.24 341	94.82 334	99.90 173	97.86 251	98.77 377	99.49 225

APD_test1		99.36 138	99.28 145	99.61 158	99.89 39	99.89 10	99.32 136	99.74 124	99.18 198	99.69 153	99.75 131	98.41 198	99.84 272	97.85 253	99.70 249	99.10 327

SED-MVS		99.40 126	99.28 145	99.77 66	99.69 164	99.82 38	99.20 176	99.54 240	99.13 211	99.82 90	99.63 210	98.91 129	99.92 131	97.85 253	99.70 249	99.58 179

test_241102_TWO								99.54 240	99.13 211	99.76 122	99.63 210	98.32 211	99.92 131	97.85 253	99.69 253	99.75 79

MVS_111021_HR		99.12 201	99.02 203	99.40 227	99.50 250	99.11 237	97.92 379	99.71 140	98.76 264	99.08 314	99.47 283	99.17 89	99.54 407	97.85 253	99.76 223	99.54 198

MTAPA		99.35 140	99.20 156	99.80 52	99.81 83	99.81 43	99.33 133	99.53 249	99.27 183	99.42 247	99.63 210	98.21 222	99.95 68	97.83 257	99.79 212	99.65 127

MSC_two_6792asdad				99.74 88	99.03 370	99.53 150		99.23 330					99.92 131	97.77 258	99.69 253	99.78 67

No_MVS				99.74 88	99.03 370	99.53 150		99.23 330					99.92 131	97.77 258	99.69 253	99.78 67

TESTMET0.1,1		96.24 375	95.84 376	97.41 388	98.24 421	93.84 413	97.38 404	95.84 420	98.43 295	97.81 401	98.56 402	79.77 423	99.89 192	97.77 258	98.77 377	98.52 396

ACMH+	98.40 8	99.50 93	99.43 108	99.71 108	99.86 55	99.76 65	99.32 136	99.77 108	99.53 137	99.77 119	99.76 126	99.26 80	99.78 325	97.77 258	99.88 143	99.60 167

IU-MVS					99.69 164	99.77 58		99.22 333	97.50 361	99.69 153				97.75 262	99.70 249	99.77 71

114514_t		98.49 290	98.11 308	99.64 139	99.73 146	99.58 140	99.24 166	99.76 113	89.94 425	99.42 247	99.56 253	97.76 256	99.86 239	97.74 263	99.82 190	99.47 233

DVP-MVS++		99.38 132	99.25 151	99.77 66	99.03 370	99.77 58	99.74 24	99.61 195	99.18 198	99.76 122	99.61 226	99.00 115	99.92 131	97.72 264	99.60 285	99.62 153

test_0728_THIRD									99.18 198	99.62 182	99.61 226	98.58 172	99.91 154	97.72 264	99.80 207	99.77 71

EGC-MVSNET		89.05 399	85.52 402	99.64 139	99.89 39	99.78 52	99.56 84	99.52 254	24.19 434	49.96 435	99.83 76	99.15 91	99.92 131	97.71 266	99.85 168	99.21 300

miper_enhance_ethall		98.03 323	97.94 323	98.32 357	98.27 420	96.43 381	96.95 417	99.41 285	96.37 393	99.43 244	98.96 379	94.74 335	99.69 361	97.71 266	99.62 275	98.83 375

TSAR-MVS + MP.		99.34 145	99.24 153	99.63 146	99.82 74	99.37 190	99.26 159	99.35 304	98.77 261	99.57 199	99.70 164	99.27 79	99.88 206	97.71 266	99.75 225	99.65 127
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 341	97.28 345	98.40 352	98.37 418	96.75 375	97.24 411	99.37 300	97.31 371	99.41 253	99.22 343	87.30 398	99.37 419	97.70 269	99.62 275	99.08 338

MP-MVS-pluss		99.14 197	98.92 230	99.80 52	99.83 67	99.83 30	98.61 302	99.63 185	96.84 386	99.44 240	99.58 242	98.81 137	99.91 154	97.70 269	99.82 190	99.67 110
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 154	99.11 173	99.79 59	99.75 135	99.81 43	98.95 261	99.53 249	98.27 318	99.53 219	99.73 139	98.75 149	99.87 220	97.70 269	99.83 181	99.68 102

UnsupCasMVSNet_bld		98.55 282	98.27 296	99.40 227	99.56 224	99.37 190	97.97 375	99.68 155	97.49 362	99.08 314	99.35 316	95.41 330	99.82 297	97.70 269	98.19 405	99.01 355

MVS_111021_LR		99.13 199	99.03 202	99.42 218	99.58 203	99.32 202	97.91 381	99.73 128	98.68 270	99.31 279	99.48 279	99.09 100	99.66 383	97.70 269	99.77 221	99.29 285

IS-MVSNet		99.03 219	98.85 238	99.55 179	99.80 90	99.25 215	99.73 27	99.15 344	99.37 170	99.61 188	99.71 156	94.73 336	99.81 312	97.70 269	99.88 143	99.58 179

test-LLR		97.15 352	96.95 355	97.74 380	98.18 423	95.02 405	97.38 404	96.10 416	98.00 331	97.81 401	98.58 399	90.04 390	99.91 154	97.69 275	98.78 375	98.31 405

test-mter		96.23 376	95.73 379	97.74 380	98.18 423	95.02 405	97.38 404	96.10 416	97.90 340	97.81 401	98.58 399	79.12 426	99.91 154	97.69 275	98.78 375	98.31 405

MonoMVSNet		98.23 312	98.32 290	97.99 368	98.97 377	96.62 377	99.49 100	98.42 384	99.62 121	99.40 258	99.79 103	95.51 328	98.58 430	97.68 277	95.98 428	98.76 382

XVS		99.27 158	99.11 173	99.75 83	99.71 152	99.71 90	99.37 124	99.61 195	99.29 179	98.76 349	99.47 283	98.47 189	99.88 206	97.62 278	99.73 238	99.67 110

X-MVStestdata		96.09 380	94.87 393	99.75 83	99.71 152	99.71 90	99.37 124	99.61 195	99.29 179	98.76 349	61.30 443	98.47 189	99.88 206	97.62 278	99.73 238	99.67 110

SMA-MVS		99.19 183	99.00 210	99.73 97	99.46 270	99.73 82	99.13 204	99.52 254	97.40 366	99.57 199	99.64 198	98.93 124	99.83 287	97.61 280	99.79 212	99.63 142
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		96.71 363	96.79 362	96.46 406	98.90 381	90.71 432	99.41 114	98.68 368	94.69 415	98.14 387	99.34 319	86.32 408	99.80 319	97.60 281	98.07 411	98.88 370

PVSNet	97.47 15	98.42 296	98.44 277	98.35 354	99.46 270	96.26 385	96.70 421	99.34 306	97.68 352	99.00 321	99.13 351	97.40 273	99.72 348	97.59 282	99.68 258	99.08 338

new_pmnet		98.88 248	98.89 234	98.84 326	99.70 160	97.62 351	98.15 351	99.50 263	97.98 334	99.62 182	99.54 263	98.15 228	99.94 84	97.55 283	99.84 173	98.95 360

IB-MVS	95.41 20	95.30 395	94.46 399	97.84 376	98.76 402	95.33 401	97.33 407	96.07 418	96.02 397	95.37 429	97.41 426	76.17 430	99.96 58	97.54 284	95.44 431	98.22 410
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		99.24 164	99.11 173	99.61 158	98.38 417	99.79 49	99.57 82	99.68 155	99.61 125	99.15 305	99.71 156	98.70 155	99.91 154	97.54 284	99.68 258	99.13 324

ZNCC-MVS		99.22 173	99.04 200	99.77 66	99.76 123	99.73 82	99.28 153	99.56 228	98.19 323	99.14 307	99.29 328	98.84 136	99.92 131	97.53 286	99.80 207	99.64 137

CP-MVS		99.23 165	99.05 194	99.75 83	99.66 179	99.66 109	99.38 120	99.62 188	98.38 302	99.06 318	99.27 331	98.79 142	99.94 84	97.51 287	99.82 190	99.66 119

SD-MVS		99.01 227	99.30 138	98.15 364	99.50 250	99.40 182	98.94 263	99.61 195	99.22 195	99.75 127	99.82 83	99.54 47	95.51 434	97.48 288	99.87 155	99.54 198
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		98.49 290	98.29 295	99.11 288	98.96 378	98.42 303	97.54 396	99.32 309	97.53 359	98.47 372	98.15 414	97.88 246	99.82 297	97.46 289	99.24 348	99.09 332

DeepC-MVS_fast	98.47 5	99.23 165	99.12 170	99.56 175	99.28 324	99.22 222	98.99 251	99.40 292	99.08 216	99.58 196	99.64 198	98.90 132	99.83 287	97.44 290	99.75 225	99.63 142
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 161	99.08 184	99.76 73	99.73 146	99.70 98	99.31 141	99.59 212	98.36 304	99.36 263	99.37 307	98.80 141	99.91 154	97.43 291	99.75 225	99.68 102

ACMMPR		99.23 165	99.06 190	99.76 73	99.74 143	99.69 102	99.31 141	99.59 212	98.36 304	99.35 265	99.38 304	98.61 168	99.93 104	97.43 291	99.75 225	99.67 110

Vis-MVSNet (Re-imp)		98.77 258	98.58 263	99.34 243	99.78 110	98.88 266	99.61 70	99.56 228	99.11 215	99.24 291	99.56 253	93.00 356	99.78 325	97.43 291	99.89 134	99.35 269

MIMVSNet		98.43 295	98.20 300	99.11 288	99.53 235	98.38 308	99.58 79	98.61 373	98.96 229	99.33 271	99.76 126	90.92 376	99.81 312	97.38 294	99.76 223	99.15 316

WB-MVSnew		98.34 306	98.14 306	98.96 306	98.14 426	97.90 341	98.27 342	97.26 413	98.63 275	98.80 344	98.00 417	97.77 254	99.90 173	97.37 295	98.98 364	99.09 332

XVG-OURS-SEG-HR		99.16 193	98.99 217	99.66 126	99.84 63	99.64 118	98.25 345	99.73 128	98.39 301	99.63 173	99.43 291	99.70 28	99.90 173	97.34 296	98.64 388	99.44 243

COLMAP_ROB	98.06 12	99.45 112	99.37 119	99.70 112	99.83 67	99.70 98	99.38 120	99.78 105	99.53 137	99.67 161	99.78 114	99.19 87	99.86 239	97.32 297	99.87 155	99.55 189
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 221	98.81 244	99.65 132	99.58 203	99.49 154	98.58 309	99.07 349	98.40 300	99.04 319	99.25 336	98.51 187	99.80 319	97.31 298	99.51 309	99.65 127

region2R		99.23 165	99.05 194	99.77 66	99.76 123	99.70 98	99.31 141	99.59 212	98.41 298	99.32 274	99.36 311	98.73 153	99.93 104	97.29 299	99.74 232	99.67 110

APD-MVS_3200maxsize		99.31 151	99.16 160	99.74 88	99.53 235	99.75 73	99.27 157	99.61 195	99.19 197	99.57 199	99.64 198	98.76 147	99.90 173	97.29 299	99.62 275	99.56 186

TAPA-MVS	97.92 13	98.03 323	97.55 339	99.46 205	99.47 266	99.44 168	98.50 323	99.62 188	86.79 426	99.07 317	99.26 334	98.26 216	99.62 394	97.28 301	99.73 238	99.31 280
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 158	99.11 173	99.73 97	99.54 229	99.74 79	99.26 159	99.62 188	99.16 205	99.52 221	99.64 198	98.41 198	99.91 154	97.27 302	99.61 282	99.54 198

RE-MVS-def			99.13 166		99.54 229	99.74 79	99.26 159	99.62 188	99.16 205	99.52 221	99.64 198	98.57 173		97.27 302	99.61 282	99.54 198

testing11		96.05 382	95.41 385	97.97 370	98.78 399	95.27 402	98.59 307	98.23 393	98.86 246	96.56 420	96.91 433	75.20 431	99.69 361	97.26 304	98.29 400	98.93 363

test_yl		98.25 309	97.95 319	99.13 286	99.17 346	98.47 298	99.00 245	98.67 370	98.97 227	99.22 295	99.02 370	91.31 370	99.69 361	97.26 304	98.93 366	99.24 291

DCV-MVSNet		98.25 309	97.95 319	99.13 286	99.17 346	98.47 298	99.00 245	98.67 370	98.97 227	99.22 295	99.02 370	91.31 370	99.69 361	97.26 304	98.93 366	99.24 291

PHI-MVS		99.11 204	98.95 224	99.59 163	99.13 351	99.59 136	99.17 188	99.65 175	97.88 343	99.25 288	99.46 286	98.97 121	99.80 319	97.26 304	99.82 190	99.37 263

tfpnnormal		99.43 117	99.38 116	99.60 161	99.87 52	99.75 73	99.59 77	99.78 105	99.71 92	99.90 56	99.69 171	98.85 135	99.90 173	97.25 308	99.78 217	99.15 316

PatchmatchNet		97.65 337	97.80 330	97.18 395	98.82 394	92.49 419	99.17 188	98.39 387	98.12 325	98.79 346	99.58 242	90.71 382	99.89 192	97.23 309	99.41 324	99.16 314
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 232	98.80 246	99.56 175	99.25 330	99.43 172	98.54 318	99.27 321	98.58 281	98.80 344	99.43 291	98.53 182	99.70 355	97.22 310	99.59 289	99.54 198

testing3		96.48 369	95.63 381	99.01 302	99.23 334	97.81 344	98.90 266	99.10 348	98.72 266	97.84 400	97.92 418	72.44 435	99.85 257	97.21 311	99.33 334	99.35 269

HPM-MVS		99.25 161	99.07 188	99.78 63	99.81 83	99.75 73	99.61 70	99.67 160	97.72 350	99.35 265	99.25 336	99.23 83	99.92 131	97.21 311	99.82 190	99.67 110
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 183	99.00 210	99.76 73	99.76 123	99.68 105	99.38 120	99.54 240	98.34 313	99.01 320	99.50 272	98.53 182	99.93 104	97.18 313	99.78 217	99.66 119

ACMMP		99.25 161	99.08 184	99.74 88	99.79 102	99.68 105	99.50 96	99.65 175	98.07 329	99.52 221	99.69 171	98.57 173	99.92 131	97.18 313	99.79 212	99.63 142
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		96.23 376	95.74 378	97.70 382	98.86 388	95.59 398	98.66 299	98.14 395	98.96 229	97.67 406	97.06 430	76.78 428	98.92 426	97.10 315	98.41 397	98.58 392

thisisatest0515		96.98 356	96.42 364	98.66 339	99.42 283	97.47 355	97.27 409	94.30 426	97.24 373	99.15 305	98.86 387	85.01 410	99.87 220	97.10 315	99.39 326	98.63 386

XVG-ACMP-BASELINE		99.23 165	99.10 181	99.63 146	99.82 74	99.58 140	98.83 277	99.72 137	98.36 304	99.60 191	99.71 156	98.92 127	99.91 154	97.08 317	99.84 173	99.40 256

MSDG		99.08 208	98.98 220	99.37 236	99.60 193	99.13 234	97.54 396	99.74 124	98.84 250	99.53 219	99.55 261	99.10 98	99.79 322	97.07 318	99.86 163	99.18 309

SteuartSystems-ACMMP		99.30 152	99.14 164	99.76 73	99.87 52	99.66 109	99.18 183	99.60 206	98.55 283	99.57 199	99.67 186	99.03 113	99.94 84	97.01 319	99.80 207	99.69 96
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 378	95.78 377	97.49 384	98.53 412	93.83 414	98.04 365	93.94 429	98.96 229	98.46 373	98.17 413	79.86 421	99.87 220	96.99 320	99.06 357	98.78 379

EPMVS		96.53 366	96.32 365	97.17 396	98.18 423	92.97 418	99.39 117	89.95 435	98.21 321	98.61 361	99.59 239	86.69 407	99.72 348	96.99 320	99.23 350	98.81 376

MSP-MVS		99.04 218	98.79 247	99.81 47	99.78 110	99.73 82	99.35 128	99.57 223	98.54 286	99.54 214	98.99 372	96.81 296	99.93 104	96.97 322	99.53 305	99.77 71
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++		98.96 236	98.70 253	99.74 88	99.52 242	99.71 90	98.86 271	99.19 339	98.47 294	98.59 363	99.06 362	98.08 233	99.91 154	96.94 323	99.60 285	99.60 167

SR-MVS		99.19 183	99.00 210	99.74 88	99.51 244	99.72 87	99.18 183	99.60 206	98.85 247	99.47 234	99.58 242	98.38 203	99.92 131	96.92 324	99.54 303	99.57 184

PGM-MVS		99.20 180	99.01 206	99.77 66	99.75 135	99.71 90	99.16 194	99.72 137	97.99 333	99.42 247	99.60 234	98.81 137	99.93 104	96.91 325	99.74 232	99.66 119

HY-MVS	98.23 9	98.21 316	97.95 319	98.99 303	99.03 370	98.24 312	99.61 70	98.72 366	96.81 387	98.73 351	99.51 269	94.06 341	99.86 239	96.91 325	98.20 403	98.86 372

MDTV_nov1_ep13			97.73 334		98.70 407	90.83 430	99.15 196	98.02 398	98.51 289	98.82 341	99.61 226	90.98 375	99.66 383	96.89 327	98.92 368

GST-MVS		99.16 193	98.96 223	99.75 83	99.73 146	99.73 82	99.20 176	99.55 234	98.22 320	99.32 274	99.35 316	98.65 164	99.91 154	96.86 328	99.74 232	99.62 153

test_post1							99.14 198				51.63 445	89.54 393	99.82 297	96.86 328

SCA		98.11 319	98.36 285	97.36 389	99.20 340	92.99 417	98.17 350	98.49 381	98.24 319	99.10 313	99.57 249	96.01 321	99.94 84	96.86 328	99.62 275	99.14 321

UBG		96.53 366	95.95 372	98.29 361	98.87 387	96.31 384	98.48 326	98.07 396	98.83 251	97.32 408	96.54 438	79.81 422	99.62 394	96.84 331	98.74 381	98.95 360

XVG-OURS		99.21 178	99.06 190	99.65 132	99.82 74	99.62 125	97.87 383	99.74 124	98.36 304	99.66 166	99.68 182	99.71 25	99.90 173	96.84 331	99.88 143	99.43 249

LCM-MVSNet-Re		99.28 154	99.15 163	99.67 119	99.33 313	99.76 65	99.34 129	99.97 20	98.93 236	99.91 53	99.79 103	98.68 157	99.93 104	96.80 333	99.56 294	99.30 282

RPSCF		99.18 187	99.02 203	99.64 139	99.83 67	99.85 20	99.44 111	99.82 81	98.33 314	99.50 229	99.78 114	97.90 244	99.65 390	96.78 334	99.83 181	99.44 243

旧先验2							97.94 377		95.33 406	98.94 325			99.88 206	96.75 335

MDTV_nov1_ep13_2view						91.44 427	99.14 198		97.37 368	99.21 297		91.78 368		96.75 335		99.03 349

CLD-MVS		98.76 259	98.57 264	99.33 246	99.57 213	98.97 255	97.53 398	99.55 234	96.41 391	99.27 286	99.13 351	99.07 105	99.78 325	96.73 337	99.89 134	99.23 295
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 320	97.98 317	98.48 348	99.27 326	96.48 379	99.40 115	99.07 349	98.81 254	99.23 292	99.57 249	90.11 389	99.87 220	96.69 338	99.64 271	99.09 332

baseline2		96.83 359	96.28 366	98.46 350	99.09 363	96.91 372	98.83 277	93.87 430	97.23 374	96.23 425	98.36 408	88.12 397	99.90 173	96.68 339	98.14 408	98.57 394

cascas		96.99 355	96.82 361	97.48 385	97.57 433	95.64 396	96.43 423	99.56 228	91.75 421	97.13 415	97.61 425	95.58 326	98.63 428	96.68 339	99.11 354	98.18 414

PC_three_1452									97.56 355	99.68 156	99.41 294	99.09 100	97.09 431	96.66 341	99.60 285	99.62 153

LPG-MVS_test		99.22 173	99.05 194	99.74 88	99.82 74	99.63 123	99.16 194	99.73 128	97.56 355	99.64 169	99.69 171	99.37 65	99.89 192	96.66 341	99.87 155	99.69 96

LGP-MVS_train				99.74 88	99.82 74	99.63 123		99.73 128	97.56 355	99.64 169	99.69 171	99.37 65	99.89 192	96.66 341	99.87 155	99.69 96

ETVMVS		96.14 379	95.22 390	98.89 322	98.80 395	98.01 332	98.66 299	98.35 390	98.71 268	97.18 413	96.31 442	74.23 434	99.75 340	96.64 344	98.13 410	98.90 367

TinyColmap		98.97 233	98.93 226	99.07 296	99.46 270	98.19 317	97.75 387	99.75 118	98.79 257	99.54 214	99.70 164	98.97 121	99.62 394	96.63 345	99.83 181	99.41 254

LF4IMVS		99.01 227	98.92 230	99.27 264	99.71 152	99.28 208	98.59 307	99.77 108	98.32 315	99.39 260	99.41 294	98.62 166	99.84 272	96.62 346	99.84 173	98.69 385

NCCC		98.82 253	98.57 264	99.58 166	99.21 337	99.31 203	98.61 302	99.25 326	98.65 273	98.43 374	99.26 334	97.86 247	99.81 312	96.55 347	99.27 344	99.61 163

OPU-MVS				99.29 258	99.12 353	99.44 168	99.20 176				99.40 298	99.00 115	98.84 427	96.54 348	99.60 285	99.58 179

F-COLMAP		98.74 261	98.45 276	99.62 155	99.57 213	99.47 157	98.84 274	99.65 175	96.31 394	98.93 326	99.19 348	97.68 260	99.87 220	96.52 349	99.37 329	99.53 203

testing99		95.86 387	95.19 391	97.87 374	98.76 402	95.03 404	98.62 301	98.44 383	98.68 270	96.67 419	96.66 437	74.31 433	99.69 361	96.51 350	98.03 412	98.90 367

ADS-MVSNet2		97.78 331	97.66 338	98.12 366	99.14 349	95.36 400	99.22 173	98.75 365	96.97 382	98.25 379	99.64 198	90.90 377	99.94 84	96.51 350	99.56 294	99.08 338

ADS-MVSNet		97.72 336	97.67 337	97.86 375	99.14 349	94.65 408	99.22 173	98.86 358	96.97 382	98.25 379	99.64 198	90.90 377	99.84 272	96.51 350	99.56 294	99.08 338

PatchMatch-RL		98.68 269	98.47 273	99.30 257	99.44 275	99.28 208	98.14 353	99.54 240	97.12 380	99.11 311	99.25 336	97.80 252	99.70 355	96.51 350	99.30 338	98.93 363

CMPMVS	77.52 23	98.50 288	98.19 303	99.41 225	98.33 419	99.56 143	99.01 242	99.59 212	95.44 404	99.57 199	99.80 93	95.64 324	99.46 417	96.47 354	99.92 113	99.21 300
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 383	95.32 388	98.02 367	98.76 402	95.39 399	98.38 335	98.65 372	98.82 252	96.84 416	96.71 436	75.06 432	99.71 352	96.46 355	98.23 402	98.98 357

SF-MVS		99.10 207	98.93 226	99.62 155	99.58 203	99.51 152	99.13 204	99.65 175	97.97 335	99.42 247	99.61 226	98.86 134	99.87 220	96.45 356	99.68 258	99.49 225

FE-MVS		97.85 328	97.42 342	99.15 282	99.44 275	98.75 276	99.77 16	98.20 394	95.85 399	99.33 271	99.80 93	88.86 395	99.88 206	96.40 357	99.12 353	98.81 376

DPE-MVS		99.14 197	98.92 230	99.82 42	99.57 213	99.77 58	98.74 293	99.60 206	98.55 283	99.76 122	99.69 171	98.23 221	99.92 131	96.39 358	99.75 225	99.76 76
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 431	89.02 437			93.47 417		98.30 409		99.84 272	96.38 359

AllTest		99.21 178	99.07 188	99.63 146	99.78 110	99.64 118	99.12 208	99.83 76	98.63 275	99.63 173	99.72 146	98.68 157	99.75 340	96.38 359	99.83 181	99.51 215

TestCases				99.63 146	99.78 110	99.64 118		99.83 76	98.63 275	99.63 173	99.72 146	98.68 157	99.75 340	96.38 359	99.83 181	99.51 215

testdata				99.42 218	99.51 244	98.93 262		99.30 316	96.20 395	98.87 336	99.40 298	98.33 210	99.89 192	96.29 362	99.28 341	99.44 243

dp		96.86 358	97.07 351	96.24 408	98.68 408	90.30 435	99.19 182	98.38 388	97.35 369	98.23 381	99.59 239	87.23 399	99.82 297	96.27 363	98.73 384	98.59 390

tpmvs		97.39 347	97.69 335	96.52 404	98.41 416	91.76 423	99.30 144	98.94 357	97.74 349	97.85 399	99.55 261	92.40 363	99.73 346	96.25 364	98.73 384	98.06 416

KD-MVS_2432*1600		95.89 384	95.41 385	97.31 392	94.96 435	93.89 411	97.09 414	99.22 333	97.23 374	98.88 333	99.04 365	79.23 424	99.54 407	96.24 365	96.81 422	98.50 400

miper_refine_blended		95.89 384	95.41 385	97.31 392	94.96 435	93.89 411	97.09 414	99.22 333	97.23 374	98.88 333	99.04 365	79.23 424	99.54 407	96.24 365	96.81 422	98.50 400

ACMP	97.51 14	99.05 215	98.84 240	99.67 119	99.78 110	99.55 147	98.88 268	99.66 165	97.11 381	99.47 234	99.60 234	99.07 105	99.89 192	96.18 367	99.85 168	99.58 179
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 244	98.72 250	99.44 212	99.39 287	99.42 175	98.58 309	99.64 183	97.31 371	99.44 240	99.62 217	98.59 170	99.69 361	96.17 368	99.79 212	99.22 297

DP-MVS Recon		98.50 288	98.23 297	99.31 254	99.49 255	99.46 161	98.56 314	99.63 185	94.86 413	98.85 338	99.37 307	97.81 251	99.59 401	96.08 369	99.44 319	98.88 370

tpm cat1		96.78 360	96.98 354	96.16 409	98.85 389	90.59 433	99.08 224	99.32 309	92.37 419	97.73 405	99.46 286	91.15 373	99.69 361	96.07 370	98.80 374	98.21 411

tpm2		96.35 372	96.22 367	96.73 402	98.88 386	91.75 424	99.21 175	98.51 379	93.27 418	97.89 396	99.21 345	84.83 411	99.70 355	96.04 371	98.18 406	98.75 383

dmvs_re		98.69 268	98.48 272	99.31 254	99.55 227	99.42 175	99.54 87	98.38 388	99.32 177	98.72 352	98.71 395	96.76 298	99.21 421	96.01 372	99.35 332	99.31 280

test_0402		99.22 173	99.14 164	99.45 208	99.79 102	99.43 172	99.28 153	99.68 155	99.54 135	99.40 258	99.56 253	99.07 105	99.82 297	96.01 372	99.96 75	99.11 325

ITE_SJBPF				99.38 233	99.63 186	99.44 168		99.73 128	98.56 282	99.33 271	99.53 265	98.88 133	99.68 373	96.01 372	99.65 269	99.02 354

test_prior2							97.95 376		97.87 344	98.05 389	99.05 363	97.90 244		95.99 375	99.49 314

testdata2													99.89 192	95.99 375

原ACMM1				99.37 236	99.47 266	98.87 268		99.27 321	96.74 389	98.26 378	99.32 320	97.93 243	99.82 297	95.96 377	99.38 327	99.43 249

新几何1				99.52 187	99.50 250	99.22 222		99.26 323	95.66 403	98.60 362	99.28 329	97.67 261	99.89 192	95.95 378	99.32 336	99.45 238

MP-MVS		99.06 212	98.83 242	99.76 73	99.76 123	99.71 90	99.32 136	99.50 263	98.35 309	98.97 322	99.48 279	98.37 204	99.92 131	95.95 378	99.75 225	99.63 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 394	94.59 397	98.61 341	98.66 409	97.45 357	98.54 318	97.90 402	98.53 287	96.54 421	96.47 439	70.62 438	99.81 312	95.91 380	98.15 407	98.56 395

wuyk23d		97.58 340	99.13 166	92.93 413	99.69 164	99.49 154	99.52 89	99.77 108	97.97 335	99.96 29	99.79 103	99.84 14	99.94 84	95.85 381	99.82 190	79.36 431

HQP_MVS		98.90 244	98.68 254	99.55 179	99.58 203	99.24 219	98.80 285	99.54 240	98.94 233	99.14 307	99.25 336	97.24 280	99.82 297	95.84 382	99.78 217	99.60 167

plane_prior5								99.54 240					99.82 297	95.84 382	99.78 217	99.60 167

无先验							98.01 368	99.23 330	95.83 400				99.85 257	95.79 384		99.44 243

CPTT-MVS		98.74 261	98.44 277	99.64 139	99.61 191	99.38 187	99.18 183	99.55 234	96.49 390	99.27 286	99.37 307	97.11 288	99.92 131	95.74 385	99.67 264	99.62 153

PLC	97.35 16	98.36 301	97.99 315	99.48 200	99.32 314	99.24 219	98.50 323	99.51 259	95.19 409	98.58 364	98.96 379	96.95 293	99.83 287	95.63 386	99.25 346	99.37 263
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 280	98.34 288	99.28 261	99.18 345	99.10 242	98.34 337	99.41 285	98.48 293	98.52 369	98.98 375	97.05 290	99.78 325	95.59 387	99.50 312	98.96 358

1314		98.00 325	97.90 327	98.27 362	98.90 381	97.45 357	99.30 144	99.06 351	94.98 410	97.21 412	99.12 355	98.43 195	99.67 378	95.58 388	98.56 391	97.71 420

PVSNet_0	95.53 19	95.85 388	95.31 389	97.47 386	98.78 399	93.48 416	95.72 425	99.40 292	96.18 396	97.37 407	97.73 420	95.73 323	99.58 402	95.49 389	81.40 433	99.36 266

MAR-MVS		98.24 311	97.92 325	99.19 277	98.78 399	99.65 115	99.17 188	99.14 345	95.36 405	98.04 390	98.81 391	97.47 270	99.72 348	95.47 390	99.06 357	98.21 411
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	98.23 312	97.89 328	99.26 267	99.19 342	99.26 212	99.65 59	99.69 152	91.33 423	98.14 387	99.77 123	98.28 213	99.96 58	95.41 391	99.55 298	98.58 392

train_agg		98.35 304	97.95 319	99.57 172	99.35 299	99.35 197	98.11 357	99.41 285	94.90 411	97.92 394	98.99 372	98.02 236	99.85 257	95.38 392	99.44 319	99.50 220

9.14			98.64 255		99.45 274		98.81 282	99.60 206	97.52 360	99.28 285	99.56 253	98.53 182	99.83 287	95.36 393	99.64 271

APD-MVS		98.87 249	98.59 260	99.71 108	99.50 250	99.62 125	99.01 242	99.57 223	96.80 388	99.54 214	99.63 210	98.29 212	99.91 154	95.24 394	99.71 247	99.61 163
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 382								95.20 395

AdaColmap		98.60 275	98.35 287	99.38 233	99.12 353	99.22 222	98.67 298	99.42 284	97.84 347	98.81 342	99.27 331	97.32 278	99.81 312	95.14 396	99.53 305	99.10 327

test9_res														95.10 397	99.44 319	99.50 220

CDPH-MVS		98.56 281	98.20 300	99.61 158	99.50 250	99.46 161	98.32 339	99.41 285	95.22 407	99.21 297	99.10 359	98.34 208	99.82 297	95.09 398	99.66 267	99.56 186

BH-untuned		98.22 314	98.09 309	98.58 345	99.38 290	97.24 363	98.55 315	98.98 356	97.81 348	99.20 302	98.76 393	97.01 291	99.65 390	94.83 399	98.33 398	98.86 372

BP-MVS														94.73 400

HQP-MVS		98.36 301	98.02 314	99.39 230	99.31 315	98.94 259	97.98 372	99.37 300	97.45 363	98.15 383	98.83 388	96.67 299	99.70 355	94.73 400	99.67 264	99.53 203

QAPM		98.40 299	97.99 315	99.65 132	99.39 287	99.47 157	99.67 50	99.52 254	91.70 422	98.78 348	99.80 93	98.55 176	99.95 68	94.71 402	99.75 225	99.53 203

agg_prior2														94.58 403	99.46 318	99.50 220

myMVS_eth3d		95.63 392	94.73 394	98.34 356	98.50 414	96.36 382	98.60 304	99.21 336	97.89 341	96.76 417	96.37 440	72.10 436	99.57 403	94.38 404	98.73 384	99.09 332

BH-RMVSNet		98.41 297	98.14 306	99.21 274	99.21 337	98.47 298	98.60 304	98.26 392	98.35 309	98.93 326	99.31 323	97.20 285	99.66 383	94.32 405	99.10 355	99.51 215

E-PMN		97.14 354	97.43 341	96.27 407	98.79 397	91.62 425	95.54 426	99.01 355	99.44 157	98.88 333	99.12 355	92.78 357	99.68 373	94.30 406	99.03 361	97.50 421

MG-MVS		98.52 285	98.39 282	98.94 309	99.15 348	97.39 360	98.18 348	99.21 336	98.89 243	99.23 292	99.63 210	97.37 276	99.74 343	94.22 407	99.61 282	99.69 96

API-MVS		98.38 300	98.39 282	98.35 354	98.83 391	99.26 212	99.14 198	99.18 340	98.59 280	98.66 357	98.78 392	98.61 168	99.57 403	94.14 408	99.56 294	96.21 428

PAPM_NR		98.36 301	98.04 312	99.33 246	99.48 260	98.93 262	98.79 288	99.28 320	97.54 358	98.56 368	98.57 401	97.12 287	99.69 361	94.09 409	98.90 372	99.38 260

ZD-MVS					99.43 278	99.61 131		99.43 282	96.38 392	99.11 311	99.07 361	97.86 247	99.92 131	94.04 410	99.49 314

DPM-MVS		98.28 307	97.94 323	99.32 251	99.36 295	99.11 237	97.31 408	98.78 364	96.88 384	98.84 339	99.11 358	97.77 254	99.61 399	94.03 411	99.36 330	99.23 295

gg-mvs-nofinetune		95.87 386	95.17 392	97.97 370	98.19 422	96.95 370	99.69 42	89.23 436	99.89 44	96.24 424	99.94 19	81.19 416	99.51 413	93.99 412	98.20 403	97.44 422

PMVS	92.94 21	98.82 253	98.81 244	98.85 324	99.84 63	97.99 333	99.20 176	99.47 271	99.71 92	99.42 247	99.82 83	98.09 231	99.47 415	93.88 413	99.85 168	99.07 343
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 357	97.28 345	95.99 411	98.76 402	91.03 429	95.26 428	98.61 373	99.34 174	98.92 329	98.88 386	93.79 345	99.66 383	92.87 414	99.05 359	97.30 425

BH-w/o		97.20 351	97.01 353	97.76 378	99.08 364	95.69 395	98.03 367	98.52 378	95.76 401	97.96 393	98.02 415	95.62 325	99.47 415	92.82 415	97.25 421	98.12 415

TR-MVS		97.44 345	97.15 350	98.32 357	98.53 412	97.46 356	98.47 327	97.91 401	96.85 385	98.21 382	98.51 405	96.42 308	99.51 413	92.16 416	97.29 420	97.98 417

OpenMVS_ROB	97.31 17	97.36 349	96.84 359	98.89 322	99.29 321	99.45 166	98.87 270	99.48 268	86.54 428	99.44 240	99.74 135	97.34 277	99.86 239	91.61 417	99.28 341	97.37 424

GG-mvs-BLEND				97.36 389	97.59 431	96.87 373	99.70 35	88.49 437		94.64 430	97.26 429	80.66 418	99.12 422	91.50 418	96.50 426	96.08 430

DeepMVS_CX				97.98 369	99.69 164	96.95 370		99.26 323	75.51 431	95.74 427	98.28 410	96.47 306	99.62 394	91.23 419	97.89 414	97.38 423

PAPR		97.56 341	97.07 351	99.04 300	98.80 395	98.11 325	97.63 392	99.25 326	94.56 416	98.02 392	98.25 411	97.43 272	99.68 373	90.90 420	98.74 381	99.33 273

MVS		95.72 390	94.63 396	98.99 303	98.56 411	97.98 338	99.30 144	98.86 358	72.71 432	97.30 409	99.08 360	98.34 208	99.74 343	89.21 421	98.33 398	99.26 288

UWE-MVS-28		95.64 391	95.47 383	96.14 410	97.98 427	90.39 434	98.49 325	95.81 421	99.02 223	98.03 391	98.19 412	84.49 413	99.28 420	88.75 422	98.47 396	98.75 383

thres600view7		96.60 365	96.16 368	97.93 372	99.63 186	96.09 390	99.18 183	97.57 407	98.77 261	98.72 352	97.32 427	87.04 401	99.72 348	88.57 423	98.62 389	97.98 417

FPMVS		96.32 373	95.50 382	98.79 332	99.60 193	98.17 320	98.46 331	98.80 363	97.16 378	96.28 422	99.63 210	82.19 415	99.09 423	88.45 424	98.89 373	99.10 327

PCF-MVS	96.03 18	96.73 362	95.86 375	99.33 246	99.44 275	99.16 231	96.87 419	99.44 279	86.58 427	98.95 324	99.40 298	94.38 339	99.88 206	87.93 425	99.80 207	98.95 360
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 371	96.03 371	97.47 386	99.63 186	95.93 391	99.18 183	97.57 407	98.75 265	98.70 355	97.31 428	87.04 401	99.67 378	87.62 426	98.51 393	96.81 426

tfpn200view9		96.30 374	95.89 373	97.53 383	99.58 203	96.11 388	99.00 245	97.54 410	98.43 295	98.52 369	96.98 431	86.85 403	99.67 378	87.62 426	98.51 393	96.81 426

thres400		96.40 370	95.89 373	97.92 373	99.58 203	96.11 388	99.00 245	97.54 410	98.43 295	98.52 369	96.98 431	86.85 403	99.67 378	87.62 426	98.51 393	97.98 417

thres200		96.09 380	95.68 380	97.33 391	99.48 260	96.22 387	98.53 320	97.57 407	98.06 330	98.37 376	96.73 435	86.84 405	99.61 399	86.99 429	98.57 390	96.16 429

MVE	92.54 22	96.66 364	96.11 369	98.31 359	99.68 172	97.55 353	97.94 377	95.60 422	99.37 170	90.68 433	98.70 397	96.56 302	98.61 429	86.94 430	99.55 298	98.77 381
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 350	96.83 360	98.59 343	99.46 270	97.55 353	99.25 165	96.84 415	98.78 259	97.24 411	97.67 421	97.11 288	98.97 425	86.59 431	98.54 392	99.27 286

PAPM		95.61 393	94.71 395	98.31 359	99.12 353	96.63 376	96.66 422	98.46 382	90.77 424	96.25 423	98.68 398	93.01 355	99.69 361	81.60 432	97.86 416	98.62 387

dongtai		89.37 398	88.91 401	90.76 414	99.19 342	77.46 439	95.47 427	87.82 438	92.28 420	94.17 431	98.82 390	71.22 437	95.54 433	63.85 433	97.34 419	99.27 286

kuosan		85.65 400	84.57 403	88.90 416	97.91 428	77.11 440	96.37 424	87.62 439	85.24 429	85.45 434	96.83 434	69.94 439	90.98 435	45.90 434	95.83 430	98.62 387

test123		29.31 401	33.05 406	18.08 417	25.93 441	12.24 442	97.53 398	10.93 442	11.78 435	24.21 436	50.08 447	21.04 440	8.60 436	23.51 435	32.43 435	33.39 432

testmvs		28.94 402	33.33 404	15.79 418	26.03 440	9.81 443	96.77 420	15.67 441	11.55 436	23.87 437	50.74 446	19.03 441	8.53 437	23.21 436	33.07 434	29.03 433

mmdepth		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

monomultidepth		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

test_blank		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet_test		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

DCPMVS		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

cdsmvs_eth3d_5k		24.88 403	33.17 405	0.00 419	0.00 442	0.00 444	0.00 430	99.62 188	0.00 437	0.00 438	99.13 351	99.82 16	0.00 438	0.00 437	0.00 436	0.00 434

pcd_1.5k_mvsjas		16.61 404	22.14 407	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	99.28 76	0.00 438	0.00 437	0.00 436	0.00 434

sosnet-low-res		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

sosnet		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uncertanet		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

Regformer		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

ab-mvs-re		8.26 415	11.02 418	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	99.16 349	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet		8.33 405	11.11 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	100.00 1	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

FOURS1					99.83 67	99.89 10	99.74 24	99.71 140	99.69 100	99.63 173

test_one_0601					99.63 186	99.76 65		99.55 234	99.23 191	99.31 279	99.61 226	98.59 170

eth-test2					0.00 442

eth-test					0.00 442

test_241102_ONE					99.69 164	99.82 38		99.54 240	99.12 214	99.82 90	99.49 276	98.91 129	99.52 412

save fliter					99.53 235	99.25 215	98.29 341	99.38 299	99.07 218

test0726					99.69 164	99.80 47	99.24 166	99.57 223	99.16 205	99.73 139	99.65 196	98.35 206

GSMVS																99.14 321

test_part2					99.62 190	99.67 107				99.55 212

sam_mvs1												90.81 381				99.14 321

sam_mvs												90.52 386

MTGPA								99.53 249

test_post											52.41 444	90.25 388	99.86 239

patchmatchnet-post											99.62 217	90.58 384	99.94 84

MTMP							99.09 221	98.59 376

TEST9					99.35 299	99.35 197	98.11 357	99.41 285	94.83 414	97.92 394	98.99 372	98.02 236	99.85 257

test_8					99.34 308	99.31 203	98.08 361	99.40 292	94.90 411	97.87 398	98.97 377	98.02 236	99.84 272

agg_prior					99.35 299	99.36 194		99.39 295		97.76 404			99.85 257

test_prior4						99.19 228	98.00 370

test_prior				99.46 205	99.35 299	99.22 222		99.39 295					99.69 361			99.48 229

新几何2							98.04 365

旧先验1					99.49 255	99.29 206		99.26 323			99.39 302	97.67 261			99.36 330	99.46 237

原ACMM2							97.92 379

test222					99.51 244	99.08 244	97.83 385	99.29 317	95.21 408	98.68 356	99.31 323	97.28 279			99.38 327	99.43 249

segment_acmp												98.37 204

testdata1							97.72 388		97.86 346

test12				99.54 184	99.29 321	99.33 200		99.16 343		98.43 374		97.54 268	99.82 297		99.47 316	99.48 229

plane_prior7					99.58 203	99.38 187

plane_prior6					99.47 266	99.26 212						97.24 280

plane_prior4											99.25 336

plane_prior3						99.31 203			98.36 304	99.14 307

plane_prior2							98.80 285		98.94 233

plane_prior1					99.51 244

plane_prior						99.24 219	98.42 333		97.87 344						99.71 247

n2								0.00 443

nn								0.00 443

door-mid								99.83 76

test11								99.29 317

door								99.77 108

HQP5-MVS						98.94 259

HQP-NCC					99.31 315		97.98 372		97.45 363	98.15 383

ACMP_Plane					99.31 315		97.98 372		97.45 363	98.15 383

HQP4-MVS										98.15 383			99.70 355			99.53 203

HQP3-MVS								99.37 300							99.67 264

HQP2-MVS												96.67 299

NP-MVS					99.40 286	99.13 234					98.83 388

ACMMP++_ref															99.94 102

ACMMP++															99.79 212

Test By Simon												98.41 198

High-resolution multi-view benchmark