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 22	99.98 3	99.75 71	99.70 35	100.00 1	99.73 80	100.00 1	99.89 38	99.79 16	99.88 200	99.98 1	100.00 1	99.98 5

test_fmvs2		99.72 40	99.85 17	99.34 237	99.91 31	98.08 324	99.48 102	100.00 1	99.90 33	99.99 7	99.91 28	99.50 48	99.98 21	99.98 1	99.99 16	99.96 13

test_fmvs3		99.83 20	99.93 2	99.53 179	99.96 7	98.62 285	99.67 50	100.00 1	99.95 22	100.00 1	99.95 16	99.85 10	99.99 8	99.98 1	99.99 16	99.98 5

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 2	99.98 3	99.76 63	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 40	99.88 7	99.27 258	99.93 24	97.84 336	99.34 129	100.00 1	99.99 3	99.99 7	99.82 82	99.87 9	99.99 8	99.97 4	99.99 16	99.97 10

test_vis1_n		99.68 49	99.79 29	99.36 234	99.94 18	98.18 313	99.52 89	100.00 1	99.86 48	100.00 1	99.88 47	98.99 111	99.96 56	99.97 4	99.96 70	99.95 14

test_fmvs1_n		99.68 49	99.81 25	99.28 255	99.95 15	97.93 333	99.49 100	100.00 1	99.82 64	99.99 7	99.89 38	99.21 79	99.98 21	99.97 4	99.98 42	99.93 20

test_f		99.75 36	99.88 7	99.37 230	99.96 7	98.21 310	99.51 95	100.00 1	99.94 25	100.00 1	99.93 21	99.58 38	99.94 81	99.97 4	99.99 16	99.97 10

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 2	99.97 6	99.74 77	99.01 240	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 16	99.86 13	99.81 43	99.88 44	99.55 142	99.17 188	99.98 12	99.99 3	99.96 26	99.84 71	99.96 3	99.99 8	99.96 9	99.99 16	99.88 30

test_cas_vis1_n_1920		99.76 35	99.86 13	99.45 202	99.93 24	98.40 298	99.30 144	99.98 12	99.94 25	99.99 7	99.89 38	99.80 15	99.97 35	99.96 9	99.97 57	99.97 10

fmvsm_l_conf0.5_n		99.80 25	99.78 33	99.85 28	99.88 44	99.66 105	99.11 213	99.91 40	99.98 15	99.96 26	99.64 194	99.60 36	99.99 8	99.95 12	99.99 16	99.88 30

test_fmvsm_n_1920		99.84 16	99.85 17	99.83 33	99.82 73	99.70 94	99.17 188	99.97 20	99.99 3	99.96 26	99.82 82	99.94 4	100.00 1	99.95 12	100.00 1	99.80 52

test_fmvs1		99.48 93	99.65 54	98.97 299	99.54 223	97.16 359	99.11 213	99.98 12	99.78 74	99.96 26	99.81 89	98.72 148	99.97 35	99.95 12	99.97 57	99.79 59

mvsany_test3		99.85 12	99.88 7	99.75 78	99.95 15	99.37 185	99.53 88	99.98 12	99.77 78	99.99 7	99.95 16	99.85 10	99.94 81	99.95 12	99.98 42	99.94 17

fmvsm_s_conf0.1_n_2		99.81 24	99.78 33	99.89 10	99.93 24	99.76 63	98.92 259	99.98 12	99.99 3	99.99 7	99.88 47	99.43 50	99.94 81	99.94 16	99.99 16	99.99 2

fmvsm_l_conf0.5_n_a		99.80 25	99.79 29	99.84 30	99.88 44	99.64 114	99.12 208	99.91 40	99.98 15	99.95 34	99.67 182	99.67 27	99.99 8	99.94 16	99.99 16	99.88 30

MM		99.18 181	99.05 188	99.55 173	99.35 292	98.81 264	99.05 227	97.79 397	99.99 3	99.48 226	99.59 234	96.29 310	99.95 66	99.94 16	99.98 42	99.88 30

test_fmvsmconf_n		99.85 12	99.84 20	99.88 17	99.91 31	99.73 80	98.97 252	99.98 12	99.99 3	99.96 26	99.85 64	99.93 7	99.99 8	99.94 16	99.99 16	99.93 20

fmvsm_s_conf0.5_n_2		99.78 29	99.75 40	99.88 17	99.82 73	99.76 63	98.88 262	99.92 35	99.98 15	99.98 14	99.85 64	99.42 52	99.94 81	99.93 20	99.98 42	99.94 17

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 2	99.95 15	99.82 37	99.10 216	99.98 12	99.99 3	99.98 14	99.91 28	99.68 26	99.93 101	99.93 20	99.99 16	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 10	99.93 24	99.78 51	99.07 226	99.98 12	99.99 3	99.98 14	99.90 33	99.88 8	99.92 127	99.93 20	99.99 16	99.98 5

fmvsm_s_conf0.5_n_a		99.82 22	99.79 29	99.89 10	99.85 58	99.82 37	99.03 235	99.96 26	99.99 3	99.97 22	99.84 71	99.58 38	99.93 101	99.92 23	99.98 42	99.93 20

fmvsm_s_conf0.5_n		99.83 20	99.81 25	99.87 22	99.85 58	99.78 51	99.03 235	99.96 26	99.99 3	99.97 22	99.84 71	99.78 17	99.92 127	99.92 23	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 17	100.00 1	99.92 23	100.00 1	99.87 34

MVStest1		98.22 308	98.09 303	98.62 334	99.04 362	96.23 380	99.20 176	99.92 35	99.44 150	99.98 14	99.87 53	85.87 403	99.67 372	99.91 26	99.57 287	99.95 14

v1921920		99.56 76	99.57 75	99.55 173	99.75 131	99.11 232	99.05 227	99.61 189	99.15 202	99.88 64	99.71 152	99.08 97	99.87 214	99.90 27	99.97 57	99.66 113

v1240		99.56 76	99.58 71	99.51 184	99.80 88	99.00 244	99.00 243	99.65 169	99.15 202	99.90 51	99.75 129	99.09 94	99.88 200	99.90 27	99.96 70	99.67 104

v10		99.69 46	99.69 47	99.66 121	99.81 82	99.39 180	99.66 54	99.75 112	99.60 125	99.92 45	99.87 53	98.75 143	99.86 233	99.90 27	99.99 16	99.73 75

v1192		99.57 73	99.57 75	99.57 167	99.77 115	99.22 217	99.04 232	99.60 200	99.18 191	99.87 72	99.72 144	99.08 97	99.85 251	99.89 30	99.98 42	99.66 113

v144192		99.55 79	99.54 82	99.58 161	99.78 107	99.20 222	99.11 213	99.62 182	99.18 191	99.89 55	99.72 144	98.66 156	99.87 214	99.88 31	99.97 57	99.66 113

v8		99.68 49	99.69 47	99.65 127	99.80 88	99.40 177	99.66 54	99.76 107	99.64 110	99.93 40	99.85 64	98.66 156	99.84 266	99.88 31	99.99 16	99.71 81

mvs5depth		99.88 6	99.91 3	99.80 48	99.92 29	99.42 170	99.94 3	100.00 1	99.97 18	99.89 55	99.99 12	99.63 30	99.97 35	99.87 33	99.99 16	100.00 1

v1144		99.54 82	99.53 86	99.59 158	99.79 100	99.28 203	99.10 216	99.61 189	99.20 189	99.84 79	99.73 137	98.67 154	99.84 266	99.86 34	99.98 42	99.64 131

mmtdpeth		99.78 29	99.83 21	99.66 121	99.85 58	99.05 243	99.79 12	99.97 20	100.00 1	99.43 238	99.94 19	99.64 28	99.94 81	99.83 35	99.99 16	99.98 5

SSC-MVS		99.52 85	99.42 104	99.83 33	99.86 54	99.65 111	99.52 89	99.81 84	99.87 45	99.81 91	99.79 102	96.78 291	99.99 8	99.83 35	99.51 303	99.86 36

v7n		99.82 22	99.80 28	99.88 17	99.96 7	99.84 24	99.82 9	99.82 75	99.84 57	99.94 37	99.91 28	99.13 90	99.96 56	99.83 35	99.99 16	99.83 45

v2v482		99.50 87	99.47 91	99.58 161	99.78 107	99.25 210	99.14 198	99.58 215	99.25 180	99.81 91	99.62 212	98.24 211	99.84 266	99.83 35	99.97 57	99.64 131

test_vis1_rt		99.45 106	99.46 95	99.41 219	99.71 146	98.63 284	98.99 248	99.96 26	99.03 215	99.95 34	99.12 349	98.75 143	99.84 266	99.82 39	99.82 184	99.77 65

tt0805		99.63 62	99.57 75	99.81 43	99.87 51	99.88 12	99.58 79	98.70 361	99.72 84	99.91 48	99.60 229	99.43 50	99.81 306	99.81 40	99.53 299	99.73 75

V42		99.56 76	99.54 82	99.63 141	99.79 100	99.46 156	99.39 117	99.59 206	99.24 182	99.86 73	99.70 160	98.55 170	99.82 291	99.79 41	99.95 83	99.60 161

mvs_tets		99.90 2	99.90 4	99.90 7	99.96 7	99.79 48	99.72 30	99.88 51	99.92 30	99.98 14	99.93 21	99.94 4	99.98 21	99.77 42	100.00 1	99.92 24

WB-MVS		99.44 108	99.32 125	99.80 48	99.81 82	99.61 127	99.47 105	99.81 84	99.82 64	99.71 140	99.72 144	96.60 295	99.98 21	99.75 43	99.23 343	99.82 51

PS-MVSNAJss		99.84 16	99.82 24	99.89 10	99.96 7	99.77 56	99.68 46	99.85 62	99.95 22	99.98 14	99.92 25	99.28 70	99.98 21	99.75 43	100.00 1	99.94 17

jajsoiax		99.89 3	99.89 6	99.89 10	99.96 7	99.78 51	99.70 35	99.86 56	99.89 39	99.98 14	99.90 33	99.94 4	99.98 21	99.75 43	100.00 1	99.90 26

ANet_high		99.88 6	99.87 11	99.91 2	99.99 1	99.91 4	99.65 59	100.00 1	99.90 33	100.00 1	99.97 14	99.61 34	99.97 35	99.75 43	100.00 1	99.84 41

reproduce_monomvs		97.40 340	97.46 334	97.20 387	99.05 359	91.91 415	99.20 176	99.18 334	99.84 57	99.86 73	99.75 129	80.67 410	99.83 281	99.69 47	99.95 83	99.85 39

SPE-MVS-test		99.68 49	99.70 44	99.64 134	99.57 207	99.83 29	99.78 14	99.97 20	99.92 30	99.50 223	99.38 298	99.57 40	99.95 66	99.69 47	99.90 118	99.15 309

MVS_0304		98.61 266	98.30 287	99.52 181	97.88 420	98.95 252	98.76 284	94.11 419	99.84 57	99.32 268	99.57 244	95.57 321	99.95 66	99.68 49	99.98 42	99.68 96

CS-MVS		99.67 55	99.70 44	99.58 161	99.53 229	99.84 24	99.79 12	99.96 26	99.90 33	99.61 182	99.41 288	99.51 47	99.95 66	99.66 50	99.89 128	98.96 351

mamv4		99.73 39	99.74 41	99.70 107	99.66 173	99.87 14	99.69 42	99.93 33	99.93 27	99.93 40	99.86 60	99.07 99	100.00 1	99.66 50	99.92 107	99.24 285

pmmvs6		99.86 10	99.86 13	99.83 33	99.94 18	99.90 7	99.83 7	99.91 40	99.85 54	99.94 37	99.95 16	99.73 21	99.90 167	99.65 52	99.97 57	99.69 90

MIMVSNet1		99.66 56	99.62 59	99.80 48	99.94 18	99.87 14	99.69 42	99.77 102	99.78 74	99.93 40	99.89 38	97.94 236	99.92 127	99.65 52	99.98 42	99.62 147

EC-MVSNet		99.69 46	99.69 47	99.68 111	99.71 146	99.91 4	99.76 20	99.96 26	99.86 48	99.51 221	99.39 296	99.57 40	99.93 101	99.64 54	99.86 157	99.20 298

K. test v3		98.87 243	98.60 252	99.69 109	99.93 24	99.46 156	99.74 24	94.97 414	99.78 74	99.88 64	99.88 47	93.66 342	99.97 35	99.61 55	99.95 83	99.64 131

KD-MVS_self_test		99.63 62	99.59 68	99.76 68	99.84 62	99.90 7	99.37 124	99.79 93	99.83 62	99.88 64	99.85 64	98.42 191	99.90 167	99.60 56	99.73 232	99.49 219

Anonymous20240521		99.44 108	99.42 104	99.49 190	99.89 39	98.96 251	99.62 64	99.76 107	99.85 54	99.82 84	99.88 47	96.39 305	99.97 35	99.59 57	99.98 42	99.55 183

TransMVSNet (Re)		99.78 29	99.77 36	99.81 43	99.91 31	99.85 19	99.75 22	99.86 56	99.70 91	99.91 48	99.89 38	99.60 36	99.87 214	99.59 57	99.74 226	99.71 81

OurMVSNet-221017-0		99.75 36	99.71 43	99.84 30	99.96 7	99.83 29	99.83 7	99.85 62	99.80 70	99.93 40	99.93 21	98.54 172	99.93 101	99.59 57	99.98 42	99.76 70

EU-MVSNet		99.39 124	99.62 59	98.72 330	99.88 44	96.44 374	99.56 84	99.85 62	99.90 33	99.90 51	99.85 64	98.09 225	99.83 281	99.58 60	99.95 83	99.90 26

mvs_anonymous		99.28 148	99.39 108	98.94 303	99.19 335	97.81 338	99.02 238	99.55 228	99.78 74	99.85 76	99.80 92	98.24 211	99.86 233	99.57 61	99.50 306	99.15 309

test1111		97.74 326	98.16 299	96.49 397	99.60 187	89.86 427	99.71 34	91.21 423	99.89 39	99.88 64	99.87 53	93.73 341	99.90 167	99.56 62	99.99 16	99.70 84

lessismore_v0				99.64 134	99.86 54	99.38 182		90.66 424		99.89 55	99.83 75	94.56 332	99.97 35	99.56 62	99.92 107	99.57 178

mvsany_test1		99.44 108	99.45 97	99.40 221	99.37 286	98.64 283	97.90 373	99.59 206	99.27 176	99.92 45	99.82 82	99.74 20	99.93 101	99.55 64	99.87 149	99.63 136

MVSMamba_PlusPlus		99.55 79	99.58 71	99.47 196	99.68 166	99.40 177	99.52 89	99.70 139	99.92 30	99.77 113	99.86 60	98.28 207	99.96 56	99.54 65	99.90 118	99.05 338

pm-mvs1		99.79 28	99.79 29	99.78 58	99.91 31	99.83 29	99.76 20	99.87 53	99.73 80	99.89 55	99.87 53	99.63 30	99.87 214	99.54 65	99.92 107	99.63 136

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 17	99.91 31	99.90 7	99.96 1	99.92 35	99.90 33	99.97 22	99.87 53	99.81 14	99.95 66	99.54 65	99.99 16	99.80 52
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 93	99.65 54	98.95 302	99.71 146	97.27 356	99.50 96	99.82 75	99.59 127	99.41 247	99.85 64	99.62 33	100.00 1	99.53 68	99.89 128	99.59 168

test2506		94.73 387	94.59 388	95.15 403	99.59 192	85.90 429	99.75 22	74.01 431	99.89 39	99.71 140	99.86 60	79.00 420	99.90 167	99.52 69	99.99 16	99.65 121

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 7	99.89 39	99.91 4	99.89 5	99.71 134	99.93 27	99.95 34	99.89 38	99.71 22	99.96 56	99.51 70	99.97 57	99.84 41

FC-MVSNet-test		99.70 44	99.65 54	99.86 26	99.88 44	99.86 18	99.72 30	99.78 99	99.90 33	99.82 84	99.83 75	98.45 187	99.87 214	99.51 70	99.97 57	99.86 36

BP-MVS1		98.72 258	98.46 268	99.50 186	99.53 229	99.00 244	99.34 129	98.53 371	99.65 107	99.73 133	99.38 298	90.62 377	99.96 56	99.50 72	99.86 157	99.55 183

UA-Net		99.78 29	99.76 39	99.86 26	99.72 143	99.71 87	99.91 4	99.95 31	99.96 21	99.71 140	99.91 28	99.15 85	99.97 35	99.50 72	100.00 1	99.90 26

PMMVS2		99.48 93	99.45 97	99.57 167	99.76 119	98.99 246	98.09 350	99.90 45	98.95 223	99.78 105	99.58 237	99.57 40	99.93 101	99.48 74	99.95 83	99.79 59

VPA-MVSNet		99.66 56	99.62 59	99.79 55	99.68 166	99.75 71	99.62 64	99.69 146	99.85 54	99.80 95	99.81 89	98.81 131	99.91 149	99.47 75	99.88 137	99.70 84

GDP-MVS		98.81 249	98.57 258	99.50 186	99.53 229	99.12 231	99.28 153	99.86 56	99.53 131	99.57 193	99.32 314	90.88 373	99.98 21	99.46 76	99.74 226	99.42 247

ECVR-MVS		97.73 327	98.04 306	96.78 391	99.59 192	90.81 423	99.72 30	90.43 425	99.89 39	99.86 73	99.86 60	93.60 343	99.89 186	99.46 76	99.99 16	99.65 121

nrg030		99.70 44	99.66 52	99.82 38	99.76 119	99.84 24	99.61 70	99.70 139	99.93 27	99.78 105	99.68 178	99.10 92	99.78 319	99.45 78	99.96 70	99.83 45

TAMVS		99.49 91	99.45 97	99.63 141	99.48 254	99.42 170	99.45 109	99.57 217	99.66 104	99.78 105	99.83 75	97.85 243	99.86 233	99.44 79	99.96 70	99.61 157

GeoE		99.69 46	99.66 52	99.78 58	99.76 119	99.76 63	99.60 76	99.82 75	99.46 145	99.75 121	99.56 248	99.63 30	99.95 66	99.43 80	99.88 137	99.62 147

new-patchmatchnet		99.35 134	99.57 75	98.71 332	99.82 73	96.62 371	98.55 307	99.75 112	99.50 135	99.88 64	99.87 53	99.31 66	99.88 200	99.43 80	100.00 1	99.62 147

test20.03		99.55 79	99.54 82	99.58 161	99.79 100	99.37 185	99.02 238	99.89 47	99.60 125	99.82 84	99.62 212	98.81 131	99.89 186	99.43 80	99.86 157	99.47 227

MVSFormer		99.41 118	99.44 100	99.31 248	99.57 207	98.40 298	99.77 16	99.80 87	99.73 80	99.63 167	99.30 319	98.02 230	99.98 21	99.43 80	99.69 247	99.55 183

test_djsdf		99.84 16	99.81 25	99.91 2	99.94 18	99.84 24	99.77 16	99.80 87	99.73 80	99.97 22	99.92 25	99.77 19	99.98 21	99.43 80	100.00 1	99.90 26

SDMVSNet		99.77 34	99.77 36	99.76 68	99.80 88	99.65 111	99.63 61	99.86 56	99.97 18	99.89 55	99.89 38	99.52 46	99.99 8	99.42 85	99.96 70	99.65 121

Anonymous20231211		99.62 68	99.57 75	99.76 68	99.61 185	99.60 130	99.81 10	99.73 122	99.82 64	99.90 51	99.90 33	97.97 235	99.86 233	99.42 85	99.96 70	99.80 52

SixPastTwentyTwo		99.42 114	99.30 132	99.76 68	99.92 29	99.67 103	99.70 35	99.14 339	99.65 107	99.89 55	99.90 33	96.20 312	99.94 81	99.42 85	99.92 107	99.67 104

balanced_conf03		99.50 87	99.50 88	99.50 186	99.42 277	99.49 149	99.52 89	99.75 112	99.86 48	99.78 105	99.71 152	98.20 218	99.90 167	99.39 88	99.88 137	99.10 320

patch_mono-2		99.51 86	99.46 95	99.64 134	99.70 154	99.11 232	99.04 232	99.87 53	99.71 86	99.47 228	99.79 102	98.24 211	99.98 21	99.38 89	99.96 70	99.83 45

UGNet		99.38 126	99.34 120	99.49 190	98.90 374	98.90 259	99.70 35	99.35 298	99.86 48	98.57 360	99.81 89	98.50 182	99.93 101	99.38 89	99.98 42	99.66 113
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 43	99.67 51	99.81 43	99.89 39	99.72 85	99.59 77	99.82 75	99.39 161	99.82 84	99.84 71	99.38 58	99.91 149	99.38 89	99.93 103	99.80 52

FIs		99.65 61	99.58 71	99.84 30	99.84 62	99.85 19	99.66 54	99.75 112	99.86 48	99.74 129	99.79 102	98.27 209	99.85 251	99.37 92	99.93 103	99.83 45

sd_testset		99.78 29	99.78 33	99.80 48	99.80 88	99.76 63	99.80 11	99.79 93	99.97 18	99.89 55	99.89 38	99.53 45	99.99 8	99.36 93	99.96 70	99.65 121

anonymousdsp		99.80 25	99.77 36	99.90 7	99.96 7	99.88 12	99.73 27	99.85 62	99.70 91	99.92 45	99.93 21	99.45 49	99.97 35	99.36 93	100.00 1	99.85 39

casdiffmvs_mvg		99.68 49	99.68 50	99.69 109	99.81 82	99.59 132	99.29 151	99.90 45	99.71 86	99.79 101	99.73 137	99.54 43	99.84 266	99.36 93	99.96 70	99.65 121
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 36	99.74 41	99.79 55	99.88 44	99.66 105	99.69 42	99.92 35	99.67 100	99.77 113	99.75 129	99.61 34	99.98 21	99.35 96	99.98 42	99.72 78
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 70	99.64 57	99.53 179	99.79 100	98.82 263	99.58 79	99.97 20	99.95 22	99.96 26	99.76 124	98.44 188	99.99 8	99.34 97	99.96 70	99.78 61

CHOSEN 1792x2688		99.39 124	99.30 132	99.65 127	99.88 44	99.25 210	98.78 282	99.88 51	98.66 263	99.96 26	99.79 102	97.45 265	99.93 101	99.34 97	99.99 16	99.78 61

CDS-MVSNet		99.22 167	99.13 160	99.50 186	99.35 292	99.11 232	98.96 254	99.54 234	99.46 145	99.61 182	99.70 160	96.31 308	99.83 281	99.34 97	99.88 137	99.55 183
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 223	99.16 154	98.51 340	99.75 131	95.90 386	98.07 353	99.84 68	99.84 57	99.89 55	99.73 137	96.01 315	99.99 8	99.33 100	100.00 1	99.63 136

HyFIR lowres test		98.91 236	98.64 249	99.73 92	99.85 58	99.47 152	98.07 353	99.83 70	98.64 265	99.89 55	99.60 229	92.57 352	100.00 1	99.33 100	99.97 57	99.72 78

pmmvs5		99.19 177	99.11 167	99.42 212	99.76 119	98.88 260	98.55 307	99.73 122	98.82 243	99.72 135	99.62 212	96.56 296	99.82 291	99.32 102	99.95 83	99.56 180

v148		99.40 120	99.41 106	99.39 224	99.76 119	98.94 253	99.09 220	99.59 206	99.17 196	99.81 91	99.61 221	98.41 192	99.69 355	99.32 102	99.94 96	99.53 197

baseline		99.63 62	99.62 59	99.66 121	99.80 88	99.62 121	99.44 111	99.80 87	99.71 86	99.72 135	99.69 167	99.15 85	99.83 281	99.32 102	99.94 96	99.53 197

CVMVSNet		98.61 266	98.88 229	97.80 371	99.58 197	93.60 408	99.26 159	99.64 177	99.66 104	99.72 135	99.67 182	93.26 345	99.93 101	99.30 105	99.81 194	99.87 34

PS-CasMVS		99.66 56	99.58 71	99.89 10	99.80 88	99.85 19	99.66 54	99.73 122	99.62 115	99.84 79	99.71 152	98.62 160	99.96 56	99.30 105	99.96 70	99.86 36

DTE-MVSNet		99.68 49	99.61 63	99.88 17	99.80 88	99.87 14	99.67 50	99.71 134	99.72 84	99.84 79	99.78 112	98.67 154	99.97 35	99.30 105	99.95 83	99.80 52

tmp_tt		95.75 381	95.42 375	96.76 392	89.90 430	94.42 402	98.86 265	97.87 396	78.01 421	99.30 278	99.69 167	97.70 251	95.89 423	99.29 108	98.14 399	99.95 14

PEN-MVS		99.66 56	99.59 68	99.89 10	99.83 66	99.87 14	99.66 54	99.73 122	99.70 91	99.84 79	99.73 137	98.56 169	99.96 56	99.29 108	99.94 96	99.83 45

WR-MVS_H		99.61 70	99.53 86	99.87 22	99.80 88	99.83 29	99.67 50	99.75 112	99.58 128	99.85 76	99.69 167	98.18 221	99.94 81	99.28 110	99.95 83	99.83 45

IterMVS		98.97 227	99.16 154	98.42 345	99.74 137	95.64 390	98.06 355	99.83 70	99.83 62	99.85 76	99.74 133	96.10 314	99.99 8	99.27 111	100.00 1	99.63 136
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WBMVS		97.50 337	97.18 343	98.48 342	98.85 381	95.89 387	98.44 323	99.52 248	99.53 131	99.52 215	99.42 287	80.10 413	99.86 233	99.24 112	99.95 83	99.68 96

h-mvs33		98.61 266	98.34 282	99.44 206	99.60 187	98.67 275	99.27 157	99.44 273	99.68 96	99.32 268	99.49 270	92.50 355	100.00 1	99.24 112	96.51 416	99.65 121

hse-mvs2		98.52 279	98.30 287	99.16 274	99.29 314	98.60 286	98.77 283	99.02 347	99.68 96	99.32 268	99.04 359	92.50 355	99.85 251	99.24 112	97.87 406	99.03 342

FMVSNet1		99.66 56	99.63 58	99.73 92	99.78 107	99.77 56	99.68 46	99.70 139	99.67 100	99.82 84	99.83 75	98.98 113	99.90 167	99.24 112	99.97 57	99.53 197

casdiffmvs		99.63 62	99.61 63	99.67 114	99.79 100	99.59 132	99.13 204	99.85 62	99.79 72	99.76 116	99.72 144	99.33 65	99.82 291	99.21 116	99.94 96	99.59 168
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 82	99.43 102	99.87 22	99.76 119	99.82 37	99.57 82	99.61 189	99.54 129	99.80 95	99.64 194	97.79 247	99.95 66	99.21 116	99.94 96	99.84 41

DELS-MVS		99.34 139	99.30 132	99.48 194	99.51 238	99.36 189	98.12 346	99.53 243	99.36 166	99.41 247	99.61 221	99.22 78	99.87 214	99.21 116	99.68 252	99.20 298
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)		99.37 129	99.26 143	99.68 111	99.51 238	99.58 136	98.98 251	99.60 200	99.43 156	99.70 144	99.36 305	97.70 251	99.88 200	99.20 119	99.87 149	99.59 168

CANet		99.11 198	99.05 188	99.28 255	98.83 383	98.56 288	98.71 290	99.41 279	99.25 180	99.23 286	99.22 337	97.66 259	99.94 81	99.19 120	99.97 57	99.33 267

EI-MVSNet-UG-set		99.48 93	99.50 88	99.42 212	99.57 207	98.65 281	99.24 166	99.46 268	99.68 96	99.80 95	99.66 187	98.99 111	99.89 186	99.19 120	99.90 118	99.72 78

xiu_mvs_v1_base_debu		99.23 159	99.34 120	98.91 309	99.59 192	98.23 307	98.47 318	99.66 159	99.61 119	99.68 150	98.94 375	99.39 54	99.97 35	99.18 122	99.55 292	98.51 388

xiu_mvs_v1_base		99.23 159	99.34 120	98.91 309	99.59 192	98.23 307	98.47 318	99.66 159	99.61 119	99.68 150	98.94 375	99.39 54	99.97 35	99.18 122	99.55 292	98.51 388

xiu_mvs_v1_base_debi		99.23 159	99.34 120	98.91 309	99.59 192	98.23 307	98.47 318	99.66 159	99.61 119	99.68 150	98.94 375	99.39 54	99.97 35	99.18 122	99.55 292	98.51 388

VPNet		99.46 102	99.37 113	99.71 103	99.82 73	99.59 132	99.48 102	99.70 139	99.81 67	99.69 147	99.58 237	97.66 259	99.86 233	99.17 125	99.44 313	99.67 104

UniMVSNet_NR-MVSNet		99.37 129	99.25 145	99.72 98	99.47 260	99.56 139	98.97 252	99.61 189	99.43 156	99.67 155	99.28 323	97.85 243	99.95 66	99.17 125	99.81 194	99.65 121

DU-MVS		99.33 142	99.21 149	99.71 103	99.43 272	99.56 139	98.83 270	99.53 243	99.38 162	99.67 155	99.36 305	97.67 255	99.95 66	99.17 125	99.81 194	99.63 136

EI-MVSNet-Vis-set		99.47 101	99.49 90	99.42 212	99.57 207	98.66 278	99.24 166	99.46 268	99.67 100	99.79 101	99.65 192	98.97 115	99.89 186	99.15 128	99.89 128	99.71 81

EI-MVSNet		99.38 126	99.44 100	99.21 268	99.58 197	98.09 321	99.26 159	99.46 268	99.62 115	99.75 121	99.67 182	98.54 172	99.85 251	99.15 128	99.92 107	99.68 96

VNet		99.18 181	99.06 184	99.56 170	99.24 325	99.36 189	99.33 133	99.31 307	99.67 100	99.47 228	99.57 244	96.48 299	99.84 266	99.15 128	99.30 332	99.47 227

EG-PatchMatch MVS		99.57 73	99.56 80	99.62 150	99.77 115	99.33 195	99.26 159	99.76 107	99.32 170	99.80 95	99.78 112	99.29 68	99.87 214	99.15 128	99.91 117	99.66 113

PVSNet_Blended_VisFu		99.40 120	99.38 110	99.44 206	99.90 37	98.66 278	98.94 257	99.91 40	97.97 326	99.79 101	99.73 137	99.05 104	99.97 35	99.15 128	99.99 16	99.68 96

IterMVS-LS		99.41 118	99.47 91	99.25 264	99.81 82	98.09 321	98.85 267	99.76 107	99.62 115	99.83 83	99.64 194	98.54 172	99.97 35	99.15 128	99.99 16	99.68 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 82	99.47 91	99.76 68	99.58 197	99.64 114	99.30 144	99.63 179	99.61 119	99.71 140	99.56 248	98.76 141	99.96 56	99.14 134	99.92 107	99.68 96

MVSTER		98.47 286	98.22 292	99.24 266	99.06 358	98.35 304	99.08 223	99.46 268	99.27 176	99.75 121	99.66 187	88.61 390	99.85 251	99.14 134	99.92 107	99.52 207

Anonymous20231206		99.35 134	99.31 127	99.47 196	99.74 137	99.06 242	99.28 153	99.74 118	99.23 184	99.72 135	99.53 259	97.63 261	99.88 200	99.11 136	99.84 167	99.48 223

Syy-MVS		98.17 311	97.85 323	99.15 276	98.50 406	98.79 267	98.60 296	99.21 330	97.89 332	96.76 408	96.37 431	95.47 323	99.57 396	99.10 137	98.73 377	99.09 325

ttmdpeth		99.48 93	99.55 81	99.29 252	99.76 119	98.16 315	99.33 133	99.95 31	99.79 72	99.36 257	99.89 38	99.13 90	99.77 327	99.09 138	99.64 265	99.93 20

MVS_Test		99.28 148	99.31 127	99.19 271	99.35 292	98.79 267	99.36 127	99.49 261	99.17 196	99.21 291	99.67 182	98.78 138	99.66 377	99.09 138	99.66 261	99.10 320

testgi		99.29 147	99.26 143	99.37 230	99.75 131	98.81 264	98.84 268	99.89 47	98.38 293	99.75 121	99.04 359	99.36 63	99.86 233	99.08 140	99.25 339	99.45 232

1112_ss		99.05 209	98.84 234	99.67 114	99.66 173	99.29 201	98.52 313	99.82 75	97.65 344	99.43 238	99.16 343	96.42 302	99.91 149	99.07 141	99.84 167	99.80 52

CANet_DTU		98.91 236	98.85 232	99.09 285	98.79 389	98.13 316	98.18 339	99.31 307	99.48 138	98.86 331	99.51 263	96.56 296	99.95 66	99.05 142	99.95 83	99.19 301

Baseline_NR-MVSNet		99.49 91	99.37 113	99.82 38	99.91 31	99.84 24	98.83 270	99.86 56	99.68 96	99.65 162	99.88 47	97.67 255	99.87 214	99.03 143	99.86 157	99.76 70

FMVSNet2		99.35 134	99.28 139	99.55 173	99.49 249	99.35 192	99.45 109	99.57 217	99.44 150	99.70 144	99.74 133	97.21 276	99.87 214	99.03 143	99.94 96	99.44 237

Test_1112_low_res		98.95 233	98.73 243	99.63 141	99.68 166	99.15 228	98.09 350	99.80 87	97.14 370	99.46 232	99.40 292	96.11 313	99.89 186	99.01 145	99.84 167	99.84 41

VDD-MVS		99.20 174	99.11 167	99.44 206	99.43 272	98.98 247	99.50 96	98.32 385	99.80 70	99.56 201	99.69 167	96.99 286	99.85 251	98.99 146	99.73 232	99.50 214

DeepC-MVS	98.90 4	99.62 68	99.61 63	99.67 114	99.72 143	99.44 163	99.24 166	99.71 134	99.27 176	99.93 40	99.90 33	99.70 24	99.93 101	98.99 146	99.99 16	99.64 131
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 93	99.47 91	99.51 184	99.77 115	99.41 176	98.81 275	99.66 159	99.42 160	99.75 121	99.66 187	99.20 80	99.76 330	98.98 148	99.99 16	99.36 260

EPNet_dtu		97.62 332	97.79 326	97.11 390	96.67 425	92.31 413	98.51 314	98.04 390	99.24 182	95.77 417	99.47 277	93.78 340	99.66 377	98.98 148	99.62 269	99.37 257
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 139	99.32 125	99.39 224	99.67 172	98.77 269	98.57 305	99.81 84	99.61 119	99.48 226	99.41 288	98.47 183	99.86 233	98.97 150	99.90 118	99.53 197
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		99.40 120	99.31 127	99.68 111	99.43 272	99.55 142	99.73 27	99.50 257	99.46 145	99.88 64	99.36 305	97.54 262	99.87 214	98.97 150	99.87 149	99.63 136

GBi-Net		99.42 114	99.31 127	99.73 92	99.49 249	99.77 56	99.68 46	99.70 139	99.44 150	99.62 176	99.83 75	97.21 276	99.90 167	98.96 152	99.90 118	99.53 197

FMVSNet5		97.80 324	97.25 341	99.42 212	98.83 383	98.97 249	99.38 120	99.80 87	98.87 235	99.25 282	99.69 167	80.60 412	99.91 149	98.96 152	99.90 118	99.38 254

test1		99.42 114	99.31 127	99.73 92	99.49 249	99.77 56	99.68 46	99.70 139	99.44 150	99.62 176	99.83 75	97.21 276	99.90 167	98.96 152	99.90 118	99.53 197

FMVSNet3		98.80 250	98.63 251	99.32 245	99.13 344	98.72 272	99.10 216	99.48 262	99.23 184	99.62 176	99.64 194	92.57 352	99.86 233	98.96 152	99.90 118	99.39 252

UnsupCasMVSNet_eth		98.83 246	98.57 258	99.59 158	99.68 166	99.45 161	98.99 248	99.67 154	99.48 138	99.55 206	99.36 305	94.92 326	99.86 233	98.95 156	96.57 415	99.45 232

CHOSEN 280x420		98.41 291	98.41 274	98.40 346	99.34 301	95.89 387	96.94 409	99.44 273	98.80 247	99.25 282	99.52 261	93.51 344	99.98 21	98.94 157	99.98 42	99.32 270

TDRefinement		99.72 40	99.70 44	99.77 61	99.90 37	99.85 19	99.86 6	99.92 35	99.69 94	99.78 105	99.92 25	99.37 60	99.88 200	98.93 158	99.95 83	99.60 161

alignmvs		98.28 301	97.96 312	99.25 264	99.12 346	98.93 256	99.03 235	98.42 378	99.64 110	98.72 346	97.85 411	90.86 374	99.62 387	98.88 159	99.13 345	99.19 301

MGCFI-Net		99.02 215	99.01 200	99.06 292	99.11 351	98.60 286	99.63 61	99.67 154	99.63 112	98.58 358	97.65 414	99.07 99	99.57 396	98.85 160	98.92 361	99.03 342

sss		98.90 238	98.77 242	99.27 258	99.48 254	98.44 295	98.72 288	99.32 303	97.94 330	99.37 256	99.35 310	96.31 308	99.91 149	98.85 160	99.63 268	99.47 227

xiu_mvs_v2_base		99.02 215	99.11 167	98.77 327	99.37 286	98.09 321	98.13 345	99.51 253	99.47 142	99.42 241	98.54 397	99.38 58	99.97 35	98.83 162	99.33 328	98.24 400

PS-MVSNAJ		99.00 223	99.08 178	98.76 328	99.37 286	98.10 320	98.00 361	99.51 253	99.47 142	99.41 247	98.50 399	99.28 70	99.97 35	98.83 162	99.34 327	98.20 404

D2MVS		99.22 167	99.19 151	99.29 252	99.69 158	98.74 271	98.81 275	99.41 279	98.55 274	99.68 150	99.69 167	98.13 223	99.87 214	98.82 164	99.98 42	99.24 285

PatchT		98.45 288	98.32 284	98.83 322	98.94 372	98.29 305	99.24 166	98.82 355	99.84 57	99.08 308	99.76 124	91.37 363	99.94 81	98.82 164	99.00 356	98.26 399

testf1		99.63 62	99.60 66	99.72 98	99.94 18	99.95 2	99.47 105	99.89 47	99.43 156	99.88 64	99.80 92	99.26 74	99.90 167	98.81 166	99.88 137	99.32 270

APD_test2		99.63 62	99.60 66	99.72 98	99.94 18	99.95 2	99.47 105	99.89 47	99.43 156	99.88 64	99.80 92	99.26 74	99.90 167	98.81 166	99.88 137	99.32 270

sasdasda		99.02 215	99.00 204	99.09 285	99.10 353	98.70 273	99.61 70	99.66 159	99.63 112	98.64 352	97.65 414	99.04 105	99.54 400	98.79 168	98.92 361	99.04 340

Effi-MVS+		99.06 206	98.97 215	99.34 237	99.31 308	98.98 247	98.31 331	99.91 40	98.81 245	98.79 340	98.94 375	99.14 88	99.84 266	98.79 168	98.74 374	99.20 298

canonicalmvs		99.02 215	99.00 204	99.09 285	99.10 353	98.70 273	99.61 70	99.66 159	99.63 112	98.64 352	97.65 414	99.04 105	99.54 400	98.79 168	98.92 361	99.04 340

VDDNet		98.97 227	98.82 237	99.42 212	99.71 146	98.81 264	99.62 64	98.68 362	99.81 67	99.38 255	99.80 92	94.25 334	99.85 251	98.79 168	99.32 330	99.59 168

CR-MVSNet		98.35 298	98.20 294	98.83 322	99.05 359	98.12 317	99.30 144	99.67 154	97.39 358	99.16 297	99.79 102	91.87 360	99.91 149	98.78 172	98.77 370	98.44 393

test_method		91.72 388	92.32 391	89.91 406	93.49 429	70.18 432	90.28 420	99.56 222	61.71 424	95.39 419	99.52 261	93.90 336	99.94 81	98.76 173	98.27 392	99.62 147

RPMNet		98.60 269	98.53 264	98.83 322	99.05 359	98.12 317	99.30 144	99.62 182	99.86 48	99.16 297	99.74 133	92.53 354	99.92 127	98.75 174	98.77 370	98.44 393

pmmvs4		99.13 193	99.06 184	99.36 234	99.57 207	99.10 237	98.01 359	99.25 320	98.78 250	99.58 190	99.44 284	98.24 211	99.76 330	98.74 175	99.93 103	99.22 291

tttt0517		97.62 332	97.20 342	98.90 315	99.76 119	97.40 353	99.48 102	94.36 416	99.06 213	99.70 144	99.49 270	84.55 406	99.94 81	98.73 176	99.65 263	99.36 260

EPP-MVSNet		99.17 186	99.00 204	99.66 121	99.80 88	99.43 167	99.70 35	99.24 323	99.48 138	99.56 201	99.77 121	94.89 327	99.93 101	98.72 177	99.89 128	99.63 136

Anonymous20240529		99.42 114	99.34 120	99.65 127	99.53 229	99.60 130	99.63 61	99.39 289	99.47 142	99.76 116	99.78 112	98.13 223	99.86 233	98.70 178	99.68 252	99.49 219

ACMH	98.42 6	99.59 72	99.54 82	99.72 98	99.86 54	99.62 121	99.56 84	99.79 93	98.77 252	99.80 95	99.85 64	99.64 28	99.85 251	98.70 178	99.89 128	99.70 84
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 142	99.28 139	99.47 196	99.57 207	99.39 180	99.78 14	99.43 276	98.87 235	99.57 193	99.82 82	98.06 228	99.87 214	98.69 180	99.73 232	99.15 309

LFMVS		98.46 287	98.19 297	99.26 261	99.24 325	98.52 291	99.62 64	96.94 406	99.87 45	99.31 273	99.58 237	91.04 368	99.81 306	98.68 181	99.42 317	99.45 232

WR-MVS		99.11 198	98.93 220	99.66 121	99.30 312	99.42 170	98.42 324	99.37 294	99.04 214	99.57 193	99.20 341	96.89 288	99.86 233	98.66 182	99.87 149	99.70 84

mvsmamba		99.08 202	98.95 218	99.45 202	99.36 289	99.18 225	99.39 117	98.81 356	99.37 163	99.35 259	99.70 160	96.36 307	99.94 81	98.66 182	99.59 283	99.22 291

RRT-MVS		99.08 202	99.00 204	99.33 240	99.27 319	98.65 281	99.62 64	99.93 33	99.66 104	99.67 155	99.82 82	95.27 325	99.93 101	98.64 184	99.09 349	99.41 248

Anonymous202405211		98.75 254	98.46 268	99.63 141	99.34 301	99.66 105	99.47 105	97.65 398	99.28 175	99.56 201	99.50 266	93.15 346	99.84 266	98.62 185	99.58 285	99.40 250

EPNet		98.13 312	97.77 327	99.18 273	94.57 428	97.99 327	99.24 166	97.96 392	99.74 79	97.29 401	99.62 212	93.13 347	99.97 35	98.59 186	99.83 175	99.58 173
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 209	99.09 176	98.91 309	99.21 330	98.36 303	98.82 274	99.47 265	98.85 238	98.90 326	99.56 248	98.78 138	99.09 415	98.57 187	99.68 252	99.26 282

Patchmatch-RL test		98.60 269	98.36 279	99.33 240	99.77 115	99.07 240	98.27 333	99.87 53	98.91 230	99.74 129	99.72 144	90.57 379	99.79 316	98.55 188	99.85 162	99.11 318

pmmvs3		98.08 315	97.80 324	98.91 309	99.41 279	97.69 344	97.87 374	99.66 159	95.87 389	99.50 223	99.51 263	90.35 381	99.97 35	98.55 188	99.47 310	99.08 331

ETV-MVS		99.18 181	99.18 152	99.16 274	99.34 301	99.28 203	99.12 208	99.79 93	99.48 138	98.93 320	98.55 396	99.40 53	99.93 101	98.51 190	99.52 302	98.28 398

jason		99.16 187	99.11 167	99.32 245	99.75 131	98.44 295	98.26 335	99.39 289	98.70 260	99.74 129	99.30 319	98.54 172	99.97 35	98.48 191	99.82 184	99.55 183
jason: jason.
APDe-MVS		99.48 93	99.36 116	99.85 28	99.55 221	99.81 42	99.50 96	99.69 146	98.99 217	99.75 121	99.71 152	98.79 136	99.93 101	98.46 192	99.85 162	99.80 52
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CL-MVSNet_self_test		98.71 260	98.56 262	99.15 276	99.22 328	98.66 278	97.14 404	99.51 253	98.09 319	99.54 208	99.27 325	96.87 289	99.74 337	98.43 193	98.96 358	99.03 342

our_test_3		98.85 245	99.09 176	98.13 359	99.66 173	94.90 400	97.72 379	99.58 215	99.07 211	99.64 163	99.62 212	98.19 219	99.93 101	98.41 194	99.95 83	99.55 183

Gipuma		99.57 73	99.59 68	99.49 190	99.98 3	99.71 87	99.72 30	99.84 68	99.81 67	99.94 37	99.78 112	98.91 123	99.71 346	98.41 194	99.95 83	99.05 338
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 342	96.91 352	98.74 329	97.72 421	97.57 346	97.60 385	97.36 404	98.00 322	99.21 291	98.02 407	90.04 384	99.79 316	98.37 196	95.89 420	98.86 365

PM-MVS		99.36 132	99.29 137	99.58 161	99.83 66	99.66 105	98.95 255	99.86 56	98.85 238	99.81 91	99.73 137	98.40 196	99.92 127	98.36 197	99.83 175	99.17 305

baseline1		97.73 327	97.33 338	98.96 300	99.30 312	97.73 342	99.40 115	98.42 378	99.33 169	99.46 232	99.21 339	91.18 366	99.82 291	98.35 198	91.26 423	99.32 270

MVS-HIRNet		97.86 321	98.22 292	96.76 392	99.28 317	91.53 419	98.38 326	92.60 422	99.13 204	99.31 273	99.96 15	97.18 280	99.68 367	98.34 199	99.83 175	99.07 336

GA-MVS		97.99 320	97.68 330	98.93 306	99.52 236	98.04 325	97.19 403	99.05 346	98.32 306	98.81 336	98.97 371	89.89 386	99.41 411	98.33 200	99.05 352	99.34 266

Fast-Effi-MVS+		99.02 215	98.87 230	99.46 199	99.38 284	99.50 148	99.04 232	99.79 93	97.17 368	98.62 354	98.74 388	99.34 64	99.95 66	98.32 201	99.41 318	98.92 358

MDA-MVSNet_test_wron		98.95 233	98.99 211	98.85 318	99.64 178	97.16 359	98.23 337	99.33 301	98.93 227	99.56 201	99.66 187	97.39 269	99.83 281	98.29 202	99.88 137	99.55 183

N_pmnet		98.73 257	98.53 264	99.35 236	99.72 143	98.67 275	98.34 328	94.65 415	98.35 300	99.79 101	99.68 178	98.03 229	99.93 101	98.28 203	99.92 107	99.44 237

ET-MVSNet_ETH3D		96.78 354	96.07 363	98.91 309	99.26 322	97.92 334	97.70 381	96.05 411	97.96 329	92.37 423	98.43 400	87.06 394	99.90 167	98.27 204	97.56 409	98.91 359

thisisatest0530		97.45 338	96.95 349	98.94 303	99.68 166	97.73 342	99.09 220	94.19 418	98.61 270	99.56 201	99.30 319	84.30 407	99.93 101	98.27 204	99.54 297	99.16 307

YYNet1		98.95 233	98.99 211	98.84 320	99.64 178	97.14 361	98.22 338	99.32 303	98.92 229	99.59 188	99.66 187	97.40 267	99.83 281	98.27 204	99.90 118	99.55 183

reproduce_model		99.50 87	99.40 107	99.83 33	99.60 187	99.83 29	99.12 208	99.68 149	99.49 137	99.80 95	99.79 102	99.01 108	99.93 101	98.24 207	99.82 184	99.73 75

ACMM	98.09 11	99.46 102	99.38 110	99.72 98	99.80 88	99.69 98	99.13 204	99.65 169	98.99 217	99.64 163	99.72 144	99.39 54	99.86 233	98.23 208	99.81 194	99.60 161
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 230	98.87 230	99.24 266	99.57 207	98.40 298	98.12 346	99.18 334	98.28 308	99.63 167	99.13 345	98.02 230	99.97 35	98.22 209	99.69 247	99.35 263

3Dnovator	99.15 2	99.43 111	99.36 116	99.65 127	99.39 281	99.42 170	99.70 35	99.56 222	99.23 184	99.35 259	99.80 92	99.17 83	99.95 66	98.21 210	99.84 167	99.59 168

Fast-Effi-MVS+-dtu		99.20 174	99.12 164	99.43 210	99.25 323	99.69 98	99.05 227	99.82 75	99.50 135	98.97 316	99.05 357	98.98 113	99.98 21	98.20 211	99.24 341	98.62 379

MS-PatchMatch		99.00 223	98.97 215	99.09 285	99.11 351	98.19 311	98.76 284	99.33 301	98.49 283	99.44 234	99.58 237	98.21 216	99.69 355	98.20 211	99.62 269	99.39 252

TSAR-MVS + GP.		99.12 195	99.04 194	99.38 227	99.34 301	99.16 226	98.15 342	99.29 311	98.18 315	99.63 167	99.62 212	99.18 82	99.68 367	98.20 211	99.74 226	99.30 276

DP-MVS		99.48 93	99.39 108	99.74 83	99.57 207	99.62 121	99.29 151	99.61 189	99.87 45	99.74 129	99.76 124	98.69 150	99.87 214	98.20 211	99.80 201	99.75 73

MVP-Stereo		99.16 187	99.08 178	99.43 210	99.48 254	99.07 240	99.08 223	99.55 228	98.63 266	99.31 273	99.68 178	98.19 219	99.78 319	98.18 215	99.58 285	99.45 232
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 111	99.30 132	99.80 48	99.83 66	99.81 42	99.52 89	99.70 139	98.35 300	99.51 221	99.50 266	99.31 66	99.88 200	98.18 215	99.84 167	99.69 90

MDA-MVSNet-bldmvs		99.06 206	99.05 188	99.07 290	99.80 88	97.83 337	98.89 261	99.72 131	99.29 172	99.63 167	99.70 160	96.47 300	99.89 186	98.17 217	99.82 184	99.50 214

JIA-IIPM		98.06 316	97.92 319	98.50 341	98.59 402	97.02 363	98.80 278	98.51 373	99.88 44	97.89 388	99.87 53	91.89 359	99.90 167	98.16 218	97.68 408	98.59 382

EIA-MVS		99.12 195	99.01 200	99.45 202	99.36 289	99.62 121	99.34 129	99.79 93	98.41 289	98.84 333	98.89 379	98.75 143	99.84 266	98.15 219	99.51 303	98.89 362

miper_lstm_enhance		98.65 265	98.60 252	98.82 325	99.20 333	97.33 355	97.78 377	99.66 159	99.01 216	99.59 188	99.50 266	94.62 331	99.85 251	98.12 220	99.90 118	99.26 282

reproduce-ours		99.46 102	99.35 118	99.82 38	99.56 218	99.83 29	99.05 227	99.65 169	99.45 148	99.78 105	99.78 112	98.93 118	99.93 101	98.11 221	99.81 194	99.70 84

our_new_method		99.46 102	99.35 118	99.82 38	99.56 218	99.83 29	99.05 227	99.65 169	99.45 148	99.78 105	99.78 112	98.93 118	99.93 101	98.11 221	99.81 194	99.70 84

Effi-MVS+-dtu		99.07 205	98.92 224	99.52 181	98.89 377	99.78 51	99.15 196	99.66 159	99.34 167	98.92 323	99.24 335	97.69 253	99.98 21	98.11 221	99.28 335	98.81 369

tpm		97.15 346	96.95 349	97.75 373	98.91 373	94.24 403	99.32 136	97.96 392	97.71 342	98.29 370	99.32 314	86.72 400	99.92 127	98.10 224	96.24 418	99.09 325

DeepPCF-MVS	98.42 6	99.18 181	99.02 197	99.67 114	99.22 328	99.75 71	97.25 401	99.47 265	98.72 257	99.66 160	99.70 160	99.29 68	99.63 386	98.07 225	99.81 194	99.62 147

ppachtmachnet_test		98.89 241	99.12 164	98.20 357	99.66 173	95.24 396	97.63 383	99.68 149	99.08 209	99.78 105	99.62 212	98.65 158	99.88 200	98.02 226	99.96 70	99.48 223

tpmrst		97.73 327	98.07 305	96.73 394	98.71 398	92.00 414	99.10 216	98.86 352	98.52 279	98.92 323	99.54 257	91.90 358	99.82 291	98.02 226	99.03 354	98.37 395

CSCG		99.37 129	99.29 137	99.60 156	99.71 146	99.46 156	99.43 113	99.85 62	98.79 248	99.41 247	99.60 229	98.92 121	99.92 127	98.02 226	99.92 107	99.43 243

eth_miper_zixun_eth		98.68 263	98.71 245	98.60 336	99.10 353	96.84 368	97.52 391	99.54 234	98.94 224	99.58 190	99.48 273	96.25 311	99.76 330	98.01 229	99.93 103	99.21 294

Patchmtry		98.78 251	98.54 263	99.49 190	98.89 377	99.19 223	99.32 136	99.67 154	99.65 107	99.72 135	99.79 102	91.87 360	99.95 66	98.00 230	99.97 57	99.33 267

PVSNet_BlendedMVS		99.03 213	99.01 200	99.09 285	99.54 223	97.99 327	98.58 301	99.82 75	97.62 345	99.34 263	99.71 152	98.52 179	99.77 327	97.98 231	99.97 57	99.52 207

PVSNet_Blended		98.70 261	98.59 254	99.02 295	99.54 223	97.99 327	97.58 386	99.82 75	95.70 393	99.34 263	98.98 369	98.52 179	99.77 327	97.98 231	99.83 175	99.30 276

cl____		98.54 277	98.41 274	98.92 307	99.03 363	97.80 340	97.46 393	99.59 206	98.90 231	99.60 185	99.46 280	93.85 338	99.78 319	97.97 233	99.89 128	99.17 305

DIV-MVS_self_test		98.54 277	98.42 273	98.92 307	99.03 363	97.80 340	97.46 393	99.59 206	98.90 231	99.60 185	99.46 280	93.87 337	99.78 319	97.97 233	99.89 128	99.18 303

AUN-MVS		97.82 323	97.38 337	99.14 279	99.27 319	98.53 289	98.72 288	99.02 347	98.10 317	97.18 404	99.03 363	89.26 388	99.85 251	97.94 235	97.91 404	99.03 342

FA-MVS(test-final)		98.52 279	98.32 284	99.10 284	99.48 254	98.67 275	99.77 16	98.60 369	97.35 360	99.63 167	99.80 92	93.07 348	99.84 266	97.92 236	99.30 332	98.78 372

ambc				99.20 270	99.35 292	98.53 289	99.17 188	99.46 268		99.67 155	99.80 92	98.46 186	99.70 349	97.92 236	99.70 243	99.38 254

USDC		98.96 230	98.93 220	99.05 293	99.54 223	97.99 327	97.07 407	99.80 87	98.21 312	99.75 121	99.77 121	98.43 189	99.64 385	97.90 238	99.88 137	99.51 209

OPM-MVS		99.26 154	99.13 160	99.63 141	99.70 154	99.61 127	98.58 301	99.48 262	98.50 281	99.52 215	99.63 205	99.14 88	99.76 330	97.89 239	99.77 215	99.51 209
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 144	99.17 153	99.77 61	99.69 158	99.80 46	99.14 198	99.31 307	99.16 198	99.62 176	99.61 221	98.35 200	99.91 149	97.88 240	99.72 238	99.61 157
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 33	99.70 154	99.79 48	99.14 198	99.61 189					99.92 127	97.88 240	99.72 238	99.77 65

c3_l		98.72 258	98.71 245	98.72 330	99.12 346	97.22 358	97.68 382	99.56 222	98.90 231	99.54 208	99.48 273	96.37 306	99.73 340	97.88 240	99.88 137	99.21 294

3Dnovator+	98.92 3	99.35 134	99.24 147	99.67 114	99.35 292	99.47 152	99.62 64	99.50 257	99.44 150	99.12 304	99.78 112	98.77 140	99.94 81	97.87 243	99.72 238	99.62 147

miper_ehance_all_eth		98.59 272	98.59 254	98.59 337	98.98 369	97.07 362	97.49 392	99.52 248	98.50 281	99.52 215	99.37 301	96.41 304	99.71 346	97.86 244	99.62 269	99.00 349

WTY-MVS		98.59 272	98.37 278	99.26 261	99.43 272	98.40 298	98.74 286	99.13 341	98.10 317	99.21 291	99.24 335	94.82 328	99.90 167	97.86 244	98.77 370	99.49 219

APD_test1		99.36 132	99.28 139	99.61 153	99.89 39	99.89 10	99.32 136	99.74 118	99.18 191	99.69 147	99.75 129	98.41 192	99.84 266	97.85 246	99.70 243	99.10 320

SED-MVS		99.40 120	99.28 139	99.77 61	99.69 158	99.82 37	99.20 176	99.54 234	99.13 204	99.82 84	99.63 205	98.91 123	99.92 127	97.85 246	99.70 243	99.58 173

test_241102_TWO								99.54 234	99.13 204	99.76 116	99.63 205	98.32 205	99.92 127	97.85 246	99.69 247	99.75 73

MVS_111021_HR		99.12 195	99.02 197	99.40 221	99.50 244	99.11 232	97.92 370	99.71 134	98.76 255	99.08 308	99.47 277	99.17 83	99.54 400	97.85 246	99.76 217	99.54 192

MTAPA		99.35 134	99.20 150	99.80 48	99.81 82	99.81 42	99.33 133	99.53 243	99.27 176	99.42 241	99.63 205	98.21 216	99.95 66	97.83 250	99.79 206	99.65 121

MSC_two_6792asdad				99.74 83	99.03 363	99.53 145		99.23 324					99.92 127	97.77 251	99.69 247	99.78 61

No_MVS				99.74 83	99.03 363	99.53 145		99.23 324					99.92 127	97.77 251	99.69 247	99.78 61

TESTMET0.1,1		96.24 368	95.84 369	97.41 381	98.24 413	93.84 406	97.38 395	95.84 412	98.43 286	97.81 393	98.56 395	79.77 416	99.89 186	97.77 251	98.77 370	98.52 387

ACMH+	98.40 8	99.50 87	99.43 102	99.71 103	99.86 54	99.76 63	99.32 136	99.77 102	99.53 131	99.77 113	99.76 124	99.26 74	99.78 319	97.77 251	99.88 137	99.60 161

IU-MVS					99.69 158	99.77 56		99.22 327	97.50 352	99.69 147				97.75 255	99.70 243	99.77 65

114514_t		98.49 284	98.11 302	99.64 134	99.73 140	99.58 136	99.24 166	99.76 107	89.94 416	99.42 241	99.56 248	97.76 250	99.86 233	97.74 256	99.82 184	99.47 227

DVP-MVS++		99.38 126	99.25 145	99.77 61	99.03 363	99.77 56	99.74 24	99.61 189	99.18 191	99.76 116	99.61 221	99.00 109	99.92 127	97.72 257	99.60 279	99.62 147

test_0728_THIRD									99.18 191	99.62 176	99.61 221	98.58 166	99.91 149	97.72 257	99.80 201	99.77 65

EGC-MVSNET		89.05 390	85.52 393	99.64 134	99.89 39	99.78 51	99.56 84	99.52 248	24.19 425	49.96 426	99.83 75	99.15 85	99.92 127	97.71 259	99.85 162	99.21 294

miper_enhance_ethall		98.03 317	97.94 317	98.32 351	98.27 412	96.43 375	96.95 408	99.41 279	96.37 384	99.43 238	98.96 373	94.74 329	99.69 355	97.71 259	99.62 269	98.83 368

TSAR-MVS + MP.		99.34 139	99.24 147	99.63 141	99.82 73	99.37 185	99.26 159	99.35 298	98.77 252	99.57 193	99.70 160	99.27 73	99.88 200	97.71 259	99.75 219	99.65 121
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 335	97.28 339	98.40 346	98.37 410	96.75 369	97.24 402	99.37 294	97.31 362	99.41 247	99.22 337	87.30 392	99.37 412	97.70 262	99.62 269	99.08 331

MP-MVS-pluss		99.14 191	98.92 224	99.80 48	99.83 66	99.83 29	98.61 294	99.63 179	96.84 377	99.44 234	99.58 237	98.81 131	99.91 149	97.70 262	99.82 184	99.67 104
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 148	99.11 167	99.79 55	99.75 131	99.81 42	98.95 255	99.53 243	98.27 309	99.53 213	99.73 137	98.75 143	99.87 214	97.70 262	99.83 175	99.68 96

UnsupCasMVSNet_bld		98.55 276	98.27 290	99.40 221	99.56 218	99.37 185	97.97 366	99.68 149	97.49 353	99.08 308	99.35 310	95.41 324	99.82 291	97.70 262	98.19 396	99.01 348

MVS_111021_LR		99.13 193	99.03 196	99.42 212	99.58 197	99.32 197	97.91 372	99.73 122	98.68 261	99.31 273	99.48 273	99.09 94	99.66 377	97.70 262	99.77 215	99.29 279

IS-MVSNet		99.03 213	98.85 232	99.55 173	99.80 88	99.25 210	99.73 27	99.15 338	99.37 163	99.61 182	99.71 152	94.73 330	99.81 306	97.70 262	99.88 137	99.58 173

test-LLR		97.15 346	96.95 349	97.74 374	98.18 415	95.02 398	97.38 395	96.10 408	98.00 322	97.81 393	98.58 392	90.04 384	99.91 149	97.69 268	98.78 368	98.31 396

test-mter		96.23 369	95.73 371	97.74 374	98.18 415	95.02 398	97.38 395	96.10 408	97.90 331	97.81 393	98.58 392	79.12 419	99.91 149	97.69 268	98.78 368	98.31 396

MonoMVSNet		98.23 306	98.32 284	97.99 362	98.97 370	96.62 371	99.49 100	98.42 378	99.62 115	99.40 252	99.79 102	95.51 322	98.58 421	97.68 270	95.98 419	98.76 375

XVS		99.27 152	99.11 167	99.75 78	99.71 146	99.71 87	99.37 124	99.61 189	99.29 172	98.76 343	99.47 277	98.47 183	99.88 200	97.62 271	99.73 232	99.67 104

X-MVStestdata		96.09 372	94.87 384	99.75 78	99.71 146	99.71 87	99.37 124	99.61 189	99.29 172	98.76 343	61.30 434	98.47 183	99.88 200	97.62 271	99.73 232	99.67 104

SMA-MVS		99.19 177	99.00 204	99.73 92	99.46 264	99.73 80	99.13 204	99.52 248	97.40 357	99.57 193	99.64 194	98.93 118	99.83 281	97.61 273	99.79 206	99.63 136
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		96.71 357	96.79 356	96.46 398	98.90 374	90.71 424	99.41 114	98.68 362	94.69 406	98.14 380	99.34 313	86.32 402	99.80 313	97.60 274	98.07 402	98.88 363

PVSNet	97.47 15	98.42 290	98.44 271	98.35 348	99.46 264	96.26 379	96.70 412	99.34 300	97.68 343	99.00 315	99.13 345	97.40 267	99.72 342	97.59 275	99.68 252	99.08 331

new_pmnet		98.88 242	98.89 228	98.84 320	99.70 154	97.62 345	98.15 342	99.50 257	97.98 325	99.62 176	99.54 257	98.15 222	99.94 81	97.55 276	99.84 167	98.95 353

IB-MVS	95.41 20	95.30 386	94.46 390	97.84 370	98.76 394	95.33 394	97.33 398	96.07 410	96.02 388	95.37 420	97.41 418	76.17 421	99.96 56	97.54 277	95.44 422	98.22 401
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		99.24 158	99.11 167	99.61 153	98.38 409	99.79 48	99.57 82	99.68 149	99.61 119	99.15 299	99.71 152	98.70 149	99.91 149	97.54 277	99.68 252	99.13 317

ZNCC-MVS		99.22 167	99.04 194	99.77 61	99.76 119	99.73 80	99.28 153	99.56 222	98.19 314	99.14 301	99.29 322	98.84 130	99.92 127	97.53 279	99.80 201	99.64 131

CP-MVS		99.23 159	99.05 188	99.75 78	99.66 173	99.66 105	99.38 120	99.62 182	98.38 293	99.06 312	99.27 325	98.79 136	99.94 81	97.51 280	99.82 184	99.66 113

SD-MVS		99.01 221	99.30 132	98.15 358	99.50 244	99.40 177	98.94 257	99.61 189	99.22 188	99.75 121	99.82 82	99.54 43	95.51 425	97.48 281	99.87 149	99.54 192
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		98.49 284	98.29 289	99.11 282	98.96 371	98.42 297	97.54 387	99.32 303	97.53 350	98.47 365	98.15 406	97.88 240	99.82 291	97.46 282	99.24 341	99.09 325

DeepC-MVS_fast	98.47 5	99.23 159	99.12 164	99.56 170	99.28 317	99.22 217	98.99 248	99.40 286	99.08 209	99.58 190	99.64 194	98.90 126	99.83 281	97.44 283	99.75 219	99.63 136
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 155	99.08 178	99.76 68	99.73 140	99.70 94	99.31 141	99.59 206	98.36 295	99.36 257	99.37 301	98.80 135	99.91 149	97.43 284	99.75 219	99.68 96

ACMMPR		99.23 159	99.06 184	99.76 68	99.74 137	99.69 98	99.31 141	99.59 206	98.36 295	99.35 259	99.38 298	98.61 162	99.93 101	97.43 284	99.75 219	99.67 104

Vis-MVSNet (Re-imp)		98.77 252	98.58 257	99.34 237	99.78 107	98.88 260	99.61 70	99.56 222	99.11 208	99.24 285	99.56 248	93.00 350	99.78 319	97.43 284	99.89 128	99.35 263

MIMVSNet		98.43 289	98.20 294	99.11 282	99.53 229	98.38 302	99.58 79	98.61 367	98.96 221	99.33 265	99.76 124	90.92 370	99.81 306	97.38 287	99.76 217	99.15 309

WB-MVSnew		98.34 300	98.14 300	98.96 300	98.14 418	97.90 335	98.27 333	97.26 405	98.63 266	98.80 338	98.00 409	97.77 248	99.90 167	97.37 288	98.98 357	99.09 325

XVG-OURS-SEG-HR		99.16 187	98.99 211	99.66 121	99.84 62	99.64 114	98.25 336	99.73 122	98.39 292	99.63 167	99.43 285	99.70 24	99.90 167	97.34 289	98.64 381	99.44 237

COLMAP_ROB	98.06 12	99.45 106	99.37 113	99.70 107	99.83 66	99.70 94	99.38 120	99.78 99	99.53 131	99.67 155	99.78 112	99.19 81	99.86 233	97.32 290	99.87 149	99.55 183
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 215	98.81 238	99.65 127	99.58 197	99.49 149	98.58 301	99.07 343	98.40 291	99.04 313	99.25 330	98.51 181	99.80 313	97.31 291	99.51 303	99.65 121

region2R		99.23 159	99.05 188	99.77 61	99.76 119	99.70 94	99.31 141	99.59 206	98.41 289	99.32 268	99.36 305	98.73 147	99.93 101	97.29 292	99.74 226	99.67 104

APD-MVS_3200maxsize		99.31 145	99.16 154	99.74 83	99.53 229	99.75 71	99.27 157	99.61 189	99.19 190	99.57 193	99.64 194	98.76 141	99.90 167	97.29 292	99.62 269	99.56 180

TAPA-MVS	97.92 13	98.03 317	97.55 333	99.46 199	99.47 260	99.44 163	98.50 315	99.62 182	86.79 417	99.07 311	99.26 328	98.26 210	99.62 387	97.28 294	99.73 232	99.31 274
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 152	99.11 167	99.73 92	99.54 223	99.74 77	99.26 159	99.62 182	99.16 198	99.52 215	99.64 194	98.41 192	99.91 149	97.27 295	99.61 276	99.54 192

RE-MVS-def			99.13 160		99.54 223	99.74 77	99.26 159	99.62 182	99.16 198	99.52 215	99.64 194	98.57 167		97.27 295	99.61 276	99.54 192

testing11		96.05 374	95.41 376	97.97 364	98.78 391	95.27 395	98.59 299	98.23 387	98.86 237	96.56 411	96.91 424	75.20 422	99.69 355	97.26 297	98.29 391	98.93 356

test_yl		98.25 303	97.95 313	99.13 280	99.17 339	98.47 292	99.00 243	98.67 364	98.97 219	99.22 289	99.02 364	91.31 364	99.69 355	97.26 297	98.93 359	99.24 285

DCV-MVSNet		98.25 303	97.95 313	99.13 280	99.17 339	98.47 292	99.00 243	98.67 364	98.97 219	99.22 289	99.02 364	91.31 364	99.69 355	97.26 297	98.93 359	99.24 285

PHI-MVS		99.11 198	98.95 218	99.59 158	99.13 344	99.59 132	99.17 188	99.65 169	97.88 334	99.25 282	99.46 280	98.97 115	99.80 313	97.26 297	99.82 184	99.37 257

tfpnnormal		99.43 111	99.38 110	99.60 156	99.87 51	99.75 71	99.59 77	99.78 99	99.71 86	99.90 51	99.69 167	98.85 129	99.90 167	97.25 301	99.78 211	99.15 309

PatchmatchNet		97.65 331	97.80 324	97.18 388	98.82 386	92.49 412	99.17 188	98.39 381	98.12 316	98.79 340	99.58 237	90.71 376	99.89 186	97.23 302	99.41 318	99.16 307
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 226	98.80 240	99.56 170	99.25 323	99.43 167	98.54 310	99.27 315	98.58 272	98.80 338	99.43 285	98.53 176	99.70 349	97.22 303	99.59 283	99.54 192

testing3		96.48 362	95.63 373	99.01 296	99.23 327	97.81 338	98.90 260	99.10 342	98.72 257	97.84 392	97.92 410	72.44 426	99.85 251	97.21 304	99.33 328	99.35 263

HPM-MVS		99.25 155	99.07 182	99.78 58	99.81 82	99.75 71	99.61 70	99.67 154	97.72 341	99.35 259	99.25 330	99.23 77	99.92 127	97.21 304	99.82 184	99.67 104
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 177	99.00 204	99.76 68	99.76 119	99.68 101	99.38 120	99.54 234	98.34 304	99.01 314	99.50 266	98.53 176	99.93 101	97.18 306	99.78 211	99.66 113

ACMMP		99.25 155	99.08 178	99.74 83	99.79 100	99.68 101	99.50 96	99.65 169	98.07 320	99.52 215	99.69 167	98.57 167	99.92 127	97.18 306	99.79 206	99.63 136
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
thisisatest0515		96.98 350	96.42 357	98.66 333	99.42 277	97.47 349	97.27 400	94.30 417	97.24 364	99.15 299	98.86 381	85.01 404	99.87 214	97.10 308	99.39 320	98.63 378

XVG-ACMP-BASELINE		99.23 159	99.10 175	99.63 141	99.82 73	99.58 136	98.83 270	99.72 131	98.36 295	99.60 185	99.71 152	98.92 121	99.91 149	97.08 309	99.84 167	99.40 250

MSDG		99.08 202	98.98 214	99.37 230	99.60 187	99.13 229	97.54 387	99.74 118	98.84 241	99.53 213	99.55 255	99.10 92	99.79 316	97.07 310	99.86 157	99.18 303

SteuartSystems-ACMMP		99.30 146	99.14 158	99.76 68	99.87 51	99.66 105	99.18 183	99.60 200	98.55 274	99.57 193	99.67 182	99.03 107	99.94 81	97.01 311	99.80 201	99.69 90
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 370	95.78 370	97.49 377	98.53 404	93.83 407	98.04 356	93.94 420	98.96 221	98.46 366	98.17 405	79.86 414	99.87 214	96.99 312	99.06 350	98.78 372

EPMVS		96.53 360	96.32 358	97.17 389	98.18 415	92.97 411	99.39 117	89.95 426	98.21 312	98.61 355	99.59 234	86.69 401	99.72 342	96.99 312	99.23 343	98.81 369

MSP-MVS		99.04 212	98.79 241	99.81 43	99.78 107	99.73 80	99.35 128	99.57 217	98.54 277	99.54 208	98.99 366	96.81 290	99.93 101	96.97 314	99.53 299	99.77 65
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++		98.96 230	98.70 247	99.74 83	99.52 236	99.71 87	98.86 265	99.19 333	98.47 285	98.59 357	99.06 356	98.08 227	99.91 149	96.94 315	99.60 279	99.60 161

SR-MVS		99.19 177	99.00 204	99.74 83	99.51 238	99.72 85	99.18 183	99.60 200	98.85 238	99.47 228	99.58 237	98.38 197	99.92 127	96.92 316	99.54 297	99.57 178

PGM-MVS		99.20 174	99.01 200	99.77 61	99.75 131	99.71 87	99.16 194	99.72 131	97.99 324	99.42 241	99.60 229	98.81 131	99.93 101	96.91 317	99.74 226	99.66 113

HY-MVS	98.23 9	98.21 310	97.95 313	98.99 297	99.03 363	98.24 306	99.61 70	98.72 360	96.81 378	98.73 345	99.51 263	94.06 335	99.86 233	96.91 317	98.20 394	98.86 365

MDTV_nov1_ep13			97.73 328		98.70 399	90.83 422	99.15 196	98.02 391	98.51 280	98.82 335	99.61 221	90.98 369	99.66 377	96.89 319	98.92 361

GST-MVS		99.16 187	98.96 217	99.75 78	99.73 140	99.73 80	99.20 176	99.55 228	98.22 311	99.32 268	99.35 310	98.65 158	99.91 149	96.86 320	99.74 226	99.62 147

test_post1							99.14 198				51.63 436	89.54 387	99.82 291	96.86 320

SCA		98.11 313	98.36 279	97.36 382	99.20 333	92.99 410	98.17 341	98.49 375	98.24 310	99.10 307	99.57 244	96.01 315	99.94 81	96.86 320	99.62 269	99.14 314

UBG		96.53 360	95.95 365	98.29 355	98.87 380	96.31 378	98.48 317	98.07 389	98.83 242	97.32 399	96.54 429	79.81 415	99.62 387	96.84 323	98.74 374	98.95 353

XVG-OURS		99.21 172	99.06 184	99.65 127	99.82 73	99.62 121	97.87 374	99.74 118	98.36 295	99.66 160	99.68 178	99.71 22	99.90 167	96.84 323	99.88 137	99.43 243

LCM-MVSNet-Re		99.28 148	99.15 157	99.67 114	99.33 306	99.76 63	99.34 129	99.97 20	98.93 227	99.91 48	99.79 102	98.68 151	99.93 101	96.80 325	99.56 288	99.30 276

RPSCF		99.18 181	99.02 197	99.64 134	99.83 66	99.85 19	99.44 111	99.82 75	98.33 305	99.50 223	99.78 112	97.90 238	99.65 383	96.78 326	99.83 175	99.44 237

旧先验2							97.94 368		95.33 397	98.94 319			99.88 200	96.75 327

MDTV_nov1_ep13_2view						91.44 420	99.14 198		97.37 359	99.21 291		91.78 362		96.75 327		99.03 342

CLD-MVS		98.76 253	98.57 258	99.33 240	99.57 207	98.97 249	97.53 389	99.55 228	96.41 382	99.27 280	99.13 345	99.07 99	99.78 319	96.73 329	99.89 128	99.23 289
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 314	97.98 311	98.48 342	99.27 319	96.48 373	99.40 115	99.07 343	98.81 245	99.23 286	99.57 244	90.11 383	99.87 214	96.69 330	99.64 265	99.09 325

baseline2		96.83 353	96.28 359	98.46 344	99.09 356	96.91 366	98.83 270	93.87 421	97.23 365	96.23 416	98.36 401	88.12 391	99.90 167	96.68 331	98.14 399	98.57 385

cascas		96.99 349	96.82 355	97.48 378	97.57 424	95.64 390	96.43 414	99.56 222	91.75 412	97.13 406	97.61 417	95.58 320	98.63 419	96.68 331	99.11 347	98.18 405

PC_three_1452									97.56 346	99.68 150	99.41 288	99.09 94	97.09 422	96.66 333	99.60 279	99.62 147

LPG-MVS_test		99.22 167	99.05 188	99.74 83	99.82 73	99.63 119	99.16 194	99.73 122	97.56 346	99.64 163	99.69 167	99.37 60	99.89 186	96.66 333	99.87 149	99.69 90

LGP-MVS_train				99.74 83	99.82 73	99.63 119		99.73 122	97.56 346	99.64 163	99.69 167	99.37 60	99.89 186	96.66 333	99.87 149	99.69 90

ETVMVS		96.14 371	95.22 381	98.89 316	98.80 387	98.01 326	98.66 292	98.35 384	98.71 259	97.18 404	96.31 433	74.23 425	99.75 334	96.64 336	98.13 401	98.90 360

TinyColmap		98.97 227	98.93 220	99.07 290	99.46 264	98.19 311	97.75 378	99.75 112	98.79 248	99.54 208	99.70 160	98.97 115	99.62 387	96.63 337	99.83 175	99.41 248

LF4IMVS		99.01 221	98.92 224	99.27 258	99.71 146	99.28 203	98.59 299	99.77 102	98.32 306	99.39 254	99.41 288	98.62 160	99.84 266	96.62 338	99.84 167	98.69 377

NCCC		98.82 247	98.57 258	99.58 161	99.21 330	99.31 198	98.61 294	99.25 320	98.65 264	98.43 367	99.26 328	97.86 241	99.81 306	96.55 339	99.27 338	99.61 157

OPU-MVS				99.29 252	99.12 346	99.44 163	99.20 176				99.40 292	99.00 109	98.84 418	96.54 340	99.60 279	99.58 173

F-COLMAP		98.74 255	98.45 270	99.62 150	99.57 207	99.47 152	98.84 268	99.65 169	96.31 385	98.93 320	99.19 342	97.68 254	99.87 214	96.52 341	99.37 323	99.53 197

testing99		95.86 379	95.19 382	97.87 368	98.76 394	95.03 397	98.62 293	98.44 377	98.68 261	96.67 410	96.66 428	74.31 424	99.69 355	96.51 342	98.03 403	98.90 360

ADS-MVSNet2		97.78 325	97.66 332	98.12 360	99.14 342	95.36 393	99.22 173	98.75 359	96.97 373	98.25 372	99.64 194	90.90 371	99.94 81	96.51 342	99.56 288	99.08 331

ADS-MVSNet		97.72 330	97.67 331	97.86 369	99.14 342	94.65 401	99.22 173	98.86 352	96.97 373	98.25 372	99.64 194	90.90 371	99.84 266	96.51 342	99.56 288	99.08 331

PatchMatch-RL		98.68 263	98.47 267	99.30 251	99.44 269	99.28 203	98.14 344	99.54 234	97.12 371	99.11 305	99.25 330	97.80 246	99.70 349	96.51 342	99.30 332	98.93 356

CMPMVS	77.52 23	98.50 282	98.19 297	99.41 219	98.33 411	99.56 139	99.01 240	99.59 206	95.44 395	99.57 193	99.80 92	95.64 318	99.46 410	96.47 346	99.92 107	99.21 294
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 375	95.32 379	98.02 361	98.76 394	95.39 392	98.38 326	98.65 366	98.82 243	96.84 407	96.71 427	75.06 423	99.71 346	96.46 347	98.23 393	98.98 350

SF-MVS		99.10 201	98.93 220	99.62 150	99.58 197	99.51 147	99.13 204	99.65 169	97.97 326	99.42 241	99.61 221	98.86 128	99.87 214	96.45 348	99.68 252	99.49 219

FE-MVS		97.85 322	97.42 336	99.15 276	99.44 269	98.75 270	99.77 16	98.20 388	95.85 390	99.33 265	99.80 92	88.86 389	99.88 200	96.40 349	99.12 346	98.81 369

DPE-MVS		99.14 191	98.92 224	99.82 38	99.57 207	99.77 56	98.74 286	99.60 200	98.55 274	99.76 116	99.69 167	98.23 215	99.92 127	96.39 350	99.75 219	99.76 70
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 422	89.02 428			93.47 408		98.30 402		99.84 266	96.38 351

AllTest		99.21 172	99.07 182	99.63 141	99.78 107	99.64 114	99.12 208	99.83 70	98.63 266	99.63 167	99.72 144	98.68 151	99.75 334	96.38 351	99.83 175	99.51 209

TestCases				99.63 141	99.78 107	99.64 114		99.83 70	98.63 266	99.63 167	99.72 144	98.68 151	99.75 334	96.38 351	99.83 175	99.51 209

testdata				99.42 212	99.51 238	98.93 256		99.30 310	96.20 386	98.87 330	99.40 292	98.33 204	99.89 186	96.29 354	99.28 335	99.44 237

dp		96.86 352	97.07 345	96.24 400	98.68 400	90.30 426	99.19 182	98.38 382	97.35 360	98.23 374	99.59 234	87.23 393	99.82 291	96.27 355	98.73 377	98.59 382

tpmvs		97.39 341	97.69 329	96.52 396	98.41 408	91.76 416	99.30 144	98.94 351	97.74 340	97.85 391	99.55 255	92.40 357	99.73 340	96.25 356	98.73 377	98.06 407

KD-MVS_2432*1600		95.89 376	95.41 376	97.31 385	94.96 426	93.89 404	97.09 405	99.22 327	97.23 365	98.88 327	99.04 359	79.23 417	99.54 400	96.24 357	96.81 413	98.50 391

miper_refine_blended		95.89 376	95.41 376	97.31 385	94.96 426	93.89 404	97.09 405	99.22 327	97.23 365	98.88 327	99.04 359	79.23 417	99.54 400	96.24 357	96.81 413	98.50 391

ACMP	97.51 14	99.05 209	98.84 234	99.67 114	99.78 107	99.55 142	98.88 262	99.66 159	97.11 372	99.47 228	99.60 229	99.07 99	99.89 186	96.18 359	99.85 162	99.58 173
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 238	98.72 244	99.44 206	99.39 281	99.42 170	98.58 301	99.64 177	97.31 362	99.44 234	99.62 212	98.59 164	99.69 355	96.17 360	99.79 206	99.22 291

DP-MVS Recon		98.50 282	98.23 291	99.31 248	99.49 249	99.46 156	98.56 306	99.63 179	94.86 404	98.85 332	99.37 301	97.81 245	99.59 394	96.08 361	99.44 313	98.88 363

tpm cat1		96.78 354	96.98 348	96.16 401	98.85 381	90.59 425	99.08 223	99.32 303	92.37 410	97.73 397	99.46 280	91.15 367	99.69 355	96.07 362	98.80 367	98.21 402

tpm2		96.35 365	96.22 360	96.73 394	98.88 379	91.75 417	99.21 175	98.51 373	93.27 409	97.89 388	99.21 339	84.83 405	99.70 349	96.04 363	98.18 397	98.75 376

dmvs_re		98.69 262	98.48 266	99.31 248	99.55 221	99.42 170	99.54 87	98.38 382	99.32 170	98.72 346	98.71 389	96.76 292	99.21 413	96.01 364	99.35 326	99.31 274

test_0402		99.22 167	99.14 158	99.45 202	99.79 100	99.43 167	99.28 153	99.68 149	99.54 129	99.40 252	99.56 248	99.07 99	99.82 291	96.01 364	99.96 70	99.11 318

ITE_SJBPF				99.38 227	99.63 180	99.44 163		99.73 122	98.56 273	99.33 265	99.53 259	98.88 127	99.68 367	96.01 364	99.65 263	99.02 347

test_prior2							97.95 367		97.87 335	98.05 382	99.05 357	97.90 238		95.99 367	99.49 308

testdata2													99.89 186	95.99 367

原ACMM1				99.37 230	99.47 260	98.87 262		99.27 315	96.74 380	98.26 371	99.32 314	97.93 237	99.82 291	95.96 369	99.38 321	99.43 243

新几何1				99.52 181	99.50 244	99.22 217		99.26 317	95.66 394	98.60 356	99.28 323	97.67 255	99.89 186	95.95 370	99.32 330	99.45 232

MP-MVS		99.06 206	98.83 236	99.76 68	99.76 119	99.71 87	99.32 136	99.50 257	98.35 300	98.97 316	99.48 273	98.37 198	99.92 127	95.95 370	99.75 219	99.63 136
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 385	94.59 388	98.61 335	98.66 401	97.45 351	98.54 310	97.90 395	98.53 278	96.54 412	96.47 430	70.62 429	99.81 306	95.91 372	98.15 398	98.56 386

wuyk23d		97.58 334	99.13 160	92.93 404	99.69 158	99.49 149	99.52 89	99.77 102	97.97 326	99.96 26	99.79 102	99.84 12	99.94 81	95.85 373	99.82 184	79.36 422

HQP_MVS		98.90 238	98.68 248	99.55 173	99.58 197	99.24 214	98.80 278	99.54 234	98.94 224	99.14 301	99.25 330	97.24 274	99.82 291	95.84 374	99.78 211	99.60 161

plane_prior5								99.54 234					99.82 291	95.84 374	99.78 211	99.60 161

无先验							98.01 359	99.23 324	95.83 391				99.85 251	95.79 376		99.44 237

CPTT-MVS		98.74 255	98.44 271	99.64 134	99.61 185	99.38 182	99.18 183	99.55 228	96.49 381	99.27 280	99.37 301	97.11 282	99.92 127	95.74 377	99.67 258	99.62 147

PLC	97.35 16	98.36 295	97.99 309	99.48 194	99.32 307	99.24 214	98.50 315	99.51 253	95.19 400	98.58 358	98.96 373	96.95 287	99.83 281	95.63 378	99.25 339	99.37 257
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 274	98.34 282	99.28 255	99.18 338	99.10 237	98.34 328	99.41 279	98.48 284	98.52 362	98.98 369	97.05 284	99.78 319	95.59 379	99.50 306	98.96 351

1314		98.00 319	97.90 321	98.27 356	98.90 374	97.45 351	99.30 144	99.06 345	94.98 401	97.21 403	99.12 349	98.43 189	99.67 372	95.58 380	98.56 384	97.71 411

PVSNet_0	95.53 19	95.85 380	95.31 380	97.47 379	98.78 391	93.48 409	95.72 416	99.40 286	96.18 387	97.37 398	97.73 412	95.73 317	99.58 395	95.49 381	81.40 424	99.36 260

MAR-MVS		98.24 305	97.92 319	99.19 271	98.78 391	99.65 111	99.17 188	99.14 339	95.36 396	98.04 383	98.81 385	97.47 264	99.72 342	95.47 382	99.06 350	98.21 402
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	98.23 306	97.89 322	99.26 261	99.19 335	99.26 207	99.65 59	99.69 146	91.33 414	98.14 380	99.77 121	98.28 207	99.96 56	95.41 383	99.55 292	98.58 384

train_agg		98.35 298	97.95 313	99.57 167	99.35 292	99.35 192	98.11 348	99.41 279	94.90 402	97.92 386	98.99 366	98.02 230	99.85 251	95.38 384	99.44 313	99.50 214

9.14			98.64 249		99.45 268		98.81 275	99.60 200	97.52 351	99.28 279	99.56 248	98.53 176	99.83 281	95.36 385	99.64 265

APD-MVS		98.87 243	98.59 254	99.71 103	99.50 244	99.62 121	99.01 240	99.57 217	96.80 379	99.54 208	99.63 205	98.29 206	99.91 149	95.24 386	99.71 241	99.61 157
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 376								95.20 387

AdaColmap		98.60 269	98.35 281	99.38 227	99.12 346	99.22 217	98.67 291	99.42 278	97.84 338	98.81 336	99.27 325	97.32 272	99.81 306	95.14 388	99.53 299	99.10 320

test9_res														95.10 389	99.44 313	99.50 214

CDPH-MVS		98.56 275	98.20 294	99.61 153	99.50 244	99.46 156	98.32 330	99.41 279	95.22 398	99.21 291	99.10 353	98.34 202	99.82 291	95.09 390	99.66 261	99.56 180

BH-untuned		98.22 308	98.09 303	98.58 339	99.38 284	97.24 357	98.55 307	98.98 350	97.81 339	99.20 296	98.76 387	97.01 285	99.65 383	94.83 391	98.33 389	98.86 365

BP-MVS														94.73 392

HQP-MVS		98.36 295	98.02 308	99.39 224	99.31 308	98.94 253	97.98 363	99.37 294	97.45 354	98.15 376	98.83 382	96.67 293	99.70 349	94.73 392	99.67 258	99.53 197

QAPM		98.40 293	97.99 309	99.65 127	99.39 281	99.47 152	99.67 50	99.52 248	91.70 413	98.78 342	99.80 92	98.55 170	99.95 66	94.71 394	99.75 219	99.53 197

agg_prior2														94.58 395	99.46 312	99.50 214

myMVS_eth3d		95.63 383	94.73 385	98.34 350	98.50 406	96.36 376	98.60 296	99.21 330	97.89 332	96.76 408	96.37 431	72.10 427	99.57 396	94.38 396	98.73 377	99.09 325

BH-RMVSNet		98.41 291	98.14 300	99.21 268	99.21 330	98.47 292	98.60 296	98.26 386	98.35 300	98.93 320	99.31 317	97.20 279	99.66 377	94.32 397	99.10 348	99.51 209

E-PMN		97.14 348	97.43 335	96.27 399	98.79 389	91.62 418	95.54 417	99.01 349	99.44 150	98.88 327	99.12 349	92.78 351	99.68 367	94.30 398	99.03 354	97.50 412

MG-MVS		98.52 279	98.39 276	98.94 303	99.15 341	97.39 354	98.18 339	99.21 330	98.89 234	99.23 286	99.63 205	97.37 270	99.74 337	94.22 399	99.61 276	99.69 90

API-MVS		98.38 294	98.39 276	98.35 348	98.83 383	99.26 207	99.14 198	99.18 334	98.59 271	98.66 351	98.78 386	98.61 162	99.57 396	94.14 400	99.56 288	96.21 419

PAPM_NR		98.36 295	98.04 306	99.33 240	99.48 254	98.93 256	98.79 281	99.28 314	97.54 349	98.56 361	98.57 394	97.12 281	99.69 355	94.09 401	98.90 365	99.38 254

ZD-MVS					99.43 272	99.61 127		99.43 276	96.38 383	99.11 305	99.07 355	97.86 241	99.92 127	94.04 402	99.49 308

DPM-MVS		98.28 301	97.94 317	99.32 245	99.36 289	99.11 232	97.31 399	98.78 358	96.88 375	98.84 333	99.11 352	97.77 248	99.61 392	94.03 403	99.36 324	99.23 289

gg-mvs-nofinetune		95.87 378	95.17 383	97.97 364	98.19 414	96.95 364	99.69 42	89.23 427	99.89 39	96.24 415	99.94 19	81.19 409	99.51 406	93.99 404	98.20 394	97.44 413

PMVS	92.94 21	98.82 247	98.81 238	98.85 318	99.84 62	97.99 327	99.20 176	99.47 265	99.71 86	99.42 241	99.82 82	98.09 225	99.47 408	93.88 405	99.85 162	99.07 336
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 351	97.28 339	95.99 402	98.76 394	91.03 421	95.26 419	98.61 367	99.34 167	98.92 323	98.88 380	93.79 339	99.66 377	92.87 406	99.05 352	97.30 416

BH-w/o		97.20 345	97.01 347	97.76 372	99.08 357	95.69 389	98.03 358	98.52 372	95.76 392	97.96 385	98.02 407	95.62 319	99.47 408	92.82 407	97.25 412	98.12 406

TR-MVS		97.44 339	97.15 344	98.32 351	98.53 404	97.46 350	98.47 318	97.91 394	96.85 376	98.21 375	98.51 398	96.42 302	99.51 406	92.16 408	97.29 411	97.98 408

OpenMVS_ROB	97.31 17	97.36 343	96.84 353	98.89 316	99.29 314	99.45 161	98.87 264	99.48 262	86.54 419	99.44 234	99.74 133	97.34 271	99.86 233	91.61 409	99.28 335	97.37 415

GG-mvs-BLEND				97.36 382	97.59 422	96.87 367	99.70 35	88.49 428		94.64 421	97.26 421	80.66 411	99.12 414	91.50 410	96.50 417	96.08 421

DeepMVS_CX				97.98 363	99.69 158	96.95 364		99.26 317	75.51 422	95.74 418	98.28 403	96.47 300	99.62 387	91.23 411	97.89 405	97.38 414

PAPR		97.56 335	97.07 345	99.04 294	98.80 387	98.11 319	97.63 383	99.25 320	94.56 407	98.02 384	98.25 404	97.43 266	99.68 367	90.90 412	98.74 374	99.33 267

MVS		95.72 382	94.63 387	98.99 297	98.56 403	97.98 332	99.30 144	98.86 352	72.71 423	97.30 400	99.08 354	98.34 202	99.74 337	89.21 413	98.33 389	99.26 282

thres600view7		96.60 359	96.16 361	97.93 366	99.63 180	96.09 384	99.18 183	97.57 399	98.77 252	98.72 346	97.32 419	87.04 395	99.72 342	88.57 414	98.62 382	97.98 408

FPMVS		96.32 366	95.50 374	98.79 326	99.60 187	98.17 314	98.46 322	98.80 357	97.16 369	96.28 413	99.63 205	82.19 408	99.09 415	88.45 415	98.89 366	99.10 320

PCF-MVS	96.03 18	96.73 356	95.86 368	99.33 240	99.44 269	99.16 226	96.87 410	99.44 273	86.58 418	98.95 318	99.40 292	94.38 333	99.88 200	87.93 416	99.80 201	98.95 353
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 364	96.03 364	97.47 379	99.63 180	95.93 385	99.18 183	97.57 399	98.75 256	98.70 349	97.31 420	87.04 395	99.67 372	87.62 417	98.51 386	96.81 417

tfpn200view9		96.30 367	95.89 366	97.53 376	99.58 197	96.11 382	99.00 243	97.54 402	98.43 286	98.52 362	96.98 422	86.85 397	99.67 372	87.62 417	98.51 386	96.81 417

thres400		96.40 363	95.89 366	97.92 367	99.58 197	96.11 382	99.00 243	97.54 402	98.43 286	98.52 362	96.98 422	86.85 397	99.67 372	87.62 417	98.51 386	97.98 408

thres200		96.09 372	95.68 372	97.33 384	99.48 254	96.22 381	98.53 312	97.57 399	98.06 321	98.37 369	96.73 426	86.84 399	99.61 392	86.99 420	98.57 383	96.16 420

MVE	92.54 22	96.66 358	96.11 362	98.31 353	99.68 166	97.55 347	97.94 368	95.60 413	99.37 163	90.68 424	98.70 390	96.56 296	98.61 420	86.94 421	99.55 292	98.77 374
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 344	96.83 354	98.59 337	99.46 264	97.55 347	99.25 165	96.84 407	98.78 250	97.24 402	97.67 413	97.11 282	98.97 417	86.59 422	98.54 385	99.27 280

PAPM		95.61 384	94.71 386	98.31 353	99.12 346	96.63 370	96.66 413	98.46 376	90.77 415	96.25 414	98.68 391	93.01 349	99.69 355	81.60 423	97.86 407	98.62 379

dongtai		89.37 389	88.91 392	90.76 405	99.19 335	77.46 430	95.47 418	87.82 429	92.28 411	94.17 422	98.82 384	71.22 428	95.54 424	63.85 424	97.34 410	99.27 280

kuosan		85.65 391	84.57 394	88.90 407	97.91 419	77.11 431	96.37 415	87.62 430	85.24 420	85.45 425	96.83 425	69.94 430	90.98 426	45.90 425	95.83 421	98.62 379

test123		29.31 392	33.05 397	18.08 408	25.93 432	12.24 433	97.53 389	10.93 433	11.78 426	24.21 427	50.08 438	21.04 431	8.60 427	23.51 426	32.43 426	33.39 423

testmvs		28.94 393	33.33 395	15.79 409	26.03 431	9.81 434	96.77 411	15.67 432	11.55 427	23.87 428	50.74 437	19.03 432	8.53 428	23.21 427	33.07 425	29.03 424

mmdepth		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

monomultidepth		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

test_blank		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet_test		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

DCPMVS		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

cdsmvs_eth3d_5k		24.88 394	33.17 396	0.00 410	0.00 433	0.00 435	0.00 421	99.62 182	0.00 428	0.00 429	99.13 345	99.82 13	0.00 429	0.00 428	0.00 427	0.00 425

pcd_1.5k_mvsjas		16.61 395	22.14 398	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	99.28 70	0.00 429	0.00 428	0.00 427	0.00 425

sosnet-low-res		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

sosnet		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uncertanet		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

Regformer		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

ab-mvs-re		8.26 406	11.02 409	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	99.16 343	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet		8.33 396	11.11 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	100.00 1	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

FOURS1					99.83 66	99.89 10	99.74 24	99.71 134	99.69 94	99.63 167

test_one_0601					99.63 180	99.76 63		99.55 228	99.23 184	99.31 273	99.61 221	98.59 164

eth-test2					0.00 433

eth-test					0.00 433

test_241102_ONE					99.69 158	99.82 37		99.54 234	99.12 207	99.82 84	99.49 270	98.91 123	99.52 405

save fliter					99.53 229	99.25 210	98.29 332	99.38 293	99.07 211

test0726					99.69 158	99.80 46	99.24 166	99.57 217	99.16 198	99.73 133	99.65 192	98.35 200

GSMVS																99.14 314

test_part2					99.62 184	99.67 103				99.55 206

sam_mvs1												90.81 375				99.14 314

sam_mvs												90.52 380

MTGPA								99.53 243

test_post											52.41 435	90.25 382	99.86 233

patchmatchnet-post											99.62 212	90.58 378	99.94 81

MTMP							99.09 220	98.59 370

TEST9					99.35 292	99.35 192	98.11 348	99.41 279	94.83 405	97.92 386	98.99 366	98.02 230	99.85 251

test_8					99.34 301	99.31 198	98.08 352	99.40 286	94.90 402	97.87 390	98.97 371	98.02 230	99.84 266

agg_prior					99.35 292	99.36 189		99.39 289		97.76 396			99.85 251

test_prior4						99.19 223	98.00 361

test_prior				99.46 199	99.35 292	99.22 217		99.39 289					99.69 355			99.48 223

新几何2							98.04 356

旧先验1					99.49 249	99.29 201		99.26 317			99.39 296	97.67 255			99.36 324	99.46 231

原ACMM2							97.92 370

test222					99.51 238	99.08 239	97.83 376	99.29 311	95.21 399	98.68 350	99.31 317	97.28 273			99.38 321	99.43 243

segment_acmp												98.37 198

testdata1							97.72 379		97.86 337

test12				99.54 178	99.29 314	99.33 195		99.16 337		98.43 367		97.54 262	99.82 291		99.47 310	99.48 223

plane_prior7					99.58 197	99.38 182

plane_prior6					99.47 260	99.26 207						97.24 274

plane_prior4											99.25 330

plane_prior3						99.31 198			98.36 295	99.14 301

plane_prior2							98.80 278		98.94 224

plane_prior1					99.51 238

plane_prior						99.24 214	98.42 324		97.87 335						99.71 241

n2								0.00 434

nn								0.00 434

door-mid								99.83 70

test11								99.29 311

door								99.77 102

HQP5-MVS						98.94 253

HQP-NCC					99.31 308		97.98 363		97.45 354	98.15 376

ACMP_Plane					99.31 308		97.98 363		97.45 354	98.15 376

HQP4-MVS										98.15 376			99.70 349			99.53 197

HQP3-MVS								99.37 294							99.67 258

HQP2-MVS												96.67 293

NP-MVS					99.40 280	99.13 229					98.83 382

ACMMP++_ref															99.94 96

ACMMP++															99.79 206

Test By Simon												98.41 192

High-resolution multi-view benchmark