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 24	99.98 3	99.75 76	99.70 38	100.00 1	99.73 96	100.00 1	99.89 41	99.79 20	99.88 216	99.98 1	100.00 1	99.98 5

test_fmvs2		99.72 50	99.85 17	99.34 252	99.91 31	98.08 339	99.48 105	100.00 1	99.90 44	99.99 7	99.91 31	99.50 54	99.98 23	99.98 1	99.99 16	99.96 13

test_fmvs3		99.83 21	99.93 2	99.53 192	99.96 7	98.62 298	99.67 53	100.00 1	99.95 28	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 68	99.12 215	100.00 1	100.00 1	99.99 7	99.91 31	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_vis1_n_1920		99.72 50	99.88 7	99.27 273	99.93 24	97.84 351	99.34 133	100.00 1	99.99 3	99.99 7	99.82 87	99.87 11	99.99 8	99.97 4	99.99 16	99.97 10

test_vis1_n		99.68 59	99.79 32	99.36 249	99.94 18	98.18 328	99.52 92	100.00 1	99.86 60	100.00 1	99.88 50	98.99 122	99.96 61	99.97 4	99.96 80	99.95 14

test_fmvs1_n		99.68 59	99.81 27	99.28 270	99.95 15	97.93 348	99.49 103	100.00 1	99.82 78	99.99 7	99.89 41	99.21 88	99.98 23	99.97 4	99.98 46	99.93 20

test_f		99.75 45	99.88 7	99.37 245	99.96 7	98.21 325	99.51 98	100.00 1	99.94 32	100.00 1	99.93 22	99.58 43	99.94 88	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 45	99.86 19	99.08 231	99.97 20	99.98 15	99.96 31	99.79 108	99.90 9	99.99 8	99.96 9	99.99 16	99.90 27

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 83	99.01 250	99.99 11	99.99 3	99.98 14	99.88 50	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 50	99.88 45	99.55 152	99.17 194	99.98 12	99.99 3	99.96 31	99.84 75	99.96 3	99.99 8	99.96 9	99.99 16	99.88 36

test_cas_vis1_n_1920		99.76 43	99.86 13	99.45 215	99.93 24	98.40 313	99.30 148	99.98 12	99.94 32	99.99 7	99.89 41	99.80 19	99.97 37	99.96 9	99.97 66	99.97 10

fmvsm_s_conf0.5_n_7		99.73 48	99.78 37	99.60 167	99.74 151	98.93 268	98.85 282	99.96 28	99.96 24	99.97 23	99.76 133	99.82 16	99.96 61	99.95 13	99.98 46	99.90 27

fmvsm_l_conf0.5_n		99.80 28	99.78 37	99.85 30	99.88 45	99.66 113	99.11 220	99.91 47	99.98 15	99.96 31	99.64 207	99.60 41	99.99 8	99.95 13	99.99 16	99.88 36

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 38	99.82 79	99.70 102	99.17 194	99.97 20	99.99 3	99.96 31	99.82 87	99.94 4	100.00 1	99.95 13	100.00 1	99.80 60

test_fmvs1		99.48 105	99.65 65	98.97 314	99.54 239	97.16 374	99.11 220	99.98 12	99.78 90	99.96 31	99.81 94	98.72 159	99.97 37	99.95 13	99.97 66	99.79 68

mvsany_test3		99.85 12	99.88 7	99.75 88	99.95 15	99.37 196	99.53 91	99.98 12	99.77 94	99.99 7	99.95 16	99.85 12	99.94 88	99.95 13	99.98 46	99.94 17

fmvsm_s_conf0.1_n_2		99.81 26	99.78 37	99.89 11	99.93 24	99.76 68	98.92 274	99.98 12	99.99 3	99.99 7	99.88 50	99.43 56	99.94 88	99.94 18	99.99 16	99.99 2

fmvsm_l_conf0.5_n_a		99.80 28	99.79 32	99.84 35	99.88 45	99.64 122	99.12 215	99.91 47	99.98 15	99.95 41	99.67 195	99.67 32	99.99 8	99.94 18	99.99 16	99.88 36

MM		99.18 194	99.05 203	99.55 186	99.35 309	98.81 277	99.05 236	97.79 414	99.99 3	99.48 242	99.59 249	96.29 323	99.95 72	99.94 18	99.98 46	99.88 36

test_fmvsmconf_n		99.85 12	99.84 20	99.88 18	99.91 31	99.73 86	98.97 265	99.98 12	99.99 3	99.96 31	99.85 68	99.93 7	99.99 8	99.94 18	99.99 16	99.93 20

fmvsm_s_conf0.5_n_5		99.78 35	99.76 47	99.85 30	99.79 110	99.72 91	98.84 284	99.96 28	99.96 24	99.96 31	99.72 155	99.71 26	99.99 8	99.93 22	99.98 46	99.85 45

fmvsm_s_conf0.5_n_2		99.78 35	99.75 49	99.88 18	99.82 79	99.76 68	98.88 277	99.92 40	99.98 15	99.98 14	99.85 68	99.42 58	99.94 88	99.93 22	99.98 46	99.94 17

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 41	99.10 223	99.98 12	99.99 3	99.98 14	99.91 31	99.68 31	99.93 108	99.93 22	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 55	99.07 235	99.98 12	99.99 3	99.98 14	99.90 36	99.88 10	99.92 136	99.93 22	99.99 16	99.98 5

fmvsm_s_conf0.5_n_a		99.82 23	99.79 32	99.89 11	99.85 61	99.82 41	99.03 244	99.96 28	99.99 3	99.97 23	99.84 75	99.58 43	99.93 108	99.92 26	99.98 46	99.93 20

fmvsm_s_conf0.5_n		99.83 21	99.81 27	99.87 24	99.85 61	99.78 55	99.03 244	99.96 28	99.99 3	99.97 23	99.84 75	99.78 21	99.92 136	99.92 26	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 21	100.00 1	99.92 26	100.00 1	99.87 40

fmvsm_s_conf0.5_n_8		99.76 43	99.72 52	99.88 18	99.82 79	99.75 76	99.02 247	99.87 61	99.98 15	99.98 14	99.81 94	99.07 108	99.97 37	99.91 29	99.99 16	99.92 24

fmvsm_s_conf0.5_n_6		99.80 28	99.78 37	99.85 30	99.78 118	99.78 55	99.00 253	99.97 20	99.96 24	99.97 23	99.56 263	99.92 8	99.93 108	99.91 29	99.99 16	99.83 52

fmvsm_s_conf0.5_n_4		99.78 35	99.78 37	99.79 63	99.75 143	99.56 148	98.98 263	99.94 37	99.92 40	99.97 23	99.72 155	99.84 14	99.92 136	99.91 29	99.98 46	99.89 33

MVStest1		98.22 324	98.09 319	98.62 350	99.04 379	96.23 396	99.20 181	99.92 40	99.44 167	99.98 14	99.87 56	85.87 419	99.67 388	99.91 29	99.57 303	99.95 14

v1921920		99.56 88	99.57 87	99.55 186	99.75 143	99.11 243	99.05 236	99.61 202	99.15 219	99.88 77	99.71 165	99.08 106	99.87 230	99.90 33	99.97 66	99.66 129

v1240		99.56 88	99.58 83	99.51 197	99.80 98	99.00 255	99.00 253	99.65 182	99.15 219	99.90 62	99.75 139	99.09 103	99.88 216	99.90 33	99.96 80	99.67 119

v10		99.69 56	99.69 57	99.66 132	99.81 91	99.39 191	99.66 57	99.75 125	99.60 141	99.92 56	99.87 56	98.75 154	99.86 249	99.90 33	99.99 16	99.73 87

v1192		99.57 85	99.57 87	99.57 179	99.77 127	99.22 228	99.04 241	99.60 213	99.18 208	99.87 85	99.72 155	99.08 106	99.85 267	99.89 36	99.98 46	99.66 129

fmvsm_s_conf0.5_n_3		99.79 32	99.77 43	99.85 30	99.81 91	99.71 94	98.97 265	99.92 40	99.98 15	99.97 23	99.86 63	99.53 50	99.95 72	99.88 37	99.99 16	99.89 33

v144192		99.55 91	99.54 94	99.58 173	99.78 118	99.20 233	99.11 220	99.62 195	99.18 208	99.89 67	99.72 155	98.66 167	99.87 230	99.88 37	99.97 66	99.66 129

v8		99.68 59	99.69 57	99.65 138	99.80 98	99.40 188	99.66 57	99.76 120	99.64 126	99.93 49	99.85 68	98.66 167	99.84 282	99.88 37	99.99 16	99.71 94

mvs5depth		99.88 6	99.91 3	99.80 56	99.92 29	99.42 181	99.94 3	100.00 1	99.97 21	99.89 67	99.99 12	99.63 35	99.97 37	99.87 40	99.99 16	100.00 1

v1144		99.54 94	99.53 98	99.59 170	99.79 110	99.28 214	99.10 223	99.61 202	99.20 206	99.84 93	99.73 148	98.67 165	99.84 282	99.86 41	99.98 46	99.64 147

mmtdpeth		99.78 35	99.83 21	99.66 132	99.85 61	99.05 254	99.79 15	99.97 20	100.00 1	99.43 254	99.94 19	99.64 33	99.94 88	99.83 42	99.99 16	99.98 5

SSC-MVS		99.52 97	99.42 116	99.83 38	99.86 57	99.65 119	99.52 92	99.81 95	99.87 57	99.81 107	99.79 108	96.78 303	99.99 8	99.83 42	99.51 319	99.86 42

v7n		99.82 23	99.80 30	99.88 18	99.96 7	99.84 26	99.82 10	99.82 85	99.84 70	99.94 44	99.91 31	99.13 99	99.96 61	99.83 42	99.99 16	99.83 52

v2v482		99.50 99	99.47 103	99.58 173	99.78 118	99.25 221	99.14 204	99.58 228	99.25 197	99.81 107	99.62 227	98.24 223	99.84 282	99.83 42	99.97 66	99.64 147

test_vis1_rt		99.45 118	99.46 107	99.41 233	99.71 161	98.63 297	98.99 260	99.96 28	99.03 232	99.95 41	99.12 365	98.75 154	99.84 282	99.82 46	99.82 200	99.77 74

tt0805		99.63 74	99.57 87	99.81 50	99.87 54	99.88 12	99.58 82	98.70 375	99.72 100	99.91 59	99.60 244	99.43 56	99.81 322	99.81 47	99.53 315	99.73 87

VortexMVS		99.13 207	99.24 160	98.79 341	99.67 187	96.60 388	99.24 170	99.80 98	99.85 66	99.93 49	99.84 75	95.06 340	99.89 201	99.80 48	99.98 46	99.89 33

V42		99.56 88	99.54 94	99.63 152	99.79 110	99.46 167	99.39 120	99.59 219	99.24 199	99.86 87	99.70 173	98.55 182	99.82 307	99.79 49	99.95 96	99.60 177

SSC-MVS3.2		99.64 73	99.67 61	99.56 182	99.75 143	98.98 258	98.96 268	99.87 61	99.88 55	99.84 93	99.64 207	99.32 74	99.91 163	99.78 50	99.96 80	99.80 60

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 52	99.72 33	99.88 59	99.92 40	99.98 14	99.93 22	99.94 4	99.98 23	99.77 51	100.00 1	99.92 24

WB-MVS		99.44 120	99.32 137	99.80 56	99.81 91	99.61 135	99.47 108	99.81 95	99.82 78	99.71 156	99.72 155	96.60 307	99.98 23	99.75 52	99.23 360	99.82 59

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 61	99.68 49	99.85 72	99.95 28	99.98 14	99.92 27	99.28 79	99.98 23	99.75 52	100.00 1	99.94 17

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 55	99.70 38	99.86 66	99.89 50	99.98 14	99.90 36	99.94 4	99.98 23	99.75 52	100.00 1	99.90 27

ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 62	100.00 1	99.90 44	100.00 1	99.97 14	99.61 39	99.97 37	99.75 52	100.00 1	99.84 48

AstraMVS		99.15 204	99.06 198	99.42 225	99.85 61	98.59 301	99.13 210	97.26 422	99.84 70	99.87 85	99.77 129	96.11 326	99.93 108	99.71 56	99.96 80	99.74 84

tt0320-xc		99.82 23	99.82 25	99.82 43	99.82 79	99.84 26	99.82 10	99.92 40	99.94 32	99.94 44	99.93 22	99.34 71	99.92 136	99.70 57	99.96 80	99.70 97

reproduce_monomvs		97.40 356	97.46 350	97.20 404	99.05 376	91.91 432	99.20 181	99.18 347	99.84 70	99.86 87	99.75 139	80.67 427	99.83 297	99.69 58	99.95 96	99.85 45

SPE-MVS-test		99.68 59	99.70 54	99.64 145	99.57 223	99.83 33	99.78 17	99.97 20	99.92 40	99.50 239	99.38 314	99.57 45	99.95 72	99.69 58	99.90 134	99.15 326

guyue		99.12 210	99.02 212	99.41 233	99.84 66	98.56 302	99.19 187	98.30 400	99.82 78	99.84 93	99.75 139	94.84 343	99.92 136	99.68 60	99.94 109	99.74 84

tt0320		99.79 32	99.79 32	99.81 50	99.82 79	99.84 26	99.82 10	99.90 52	99.94 32	99.94 44	99.94 19	99.07 108	99.92 136	99.68 60	99.97 66	99.67 119

MVS_0304		98.61 282	98.30 303	99.52 194	97.88 439	98.95 264	98.76 301	94.11 438	99.84 70	99.32 284	99.57 259	95.57 335	99.95 72	99.68 60	99.98 46	99.68 110

CS-MVS		99.67 65	99.70 54	99.58 173	99.53 245	99.84 26	99.79 15	99.96 28	99.90 44	99.61 198	99.41 304	99.51 53	99.95 72	99.66 63	99.89 144	98.96 368

mamv4		99.73 48	99.74 50	99.70 118	99.66 189	99.87 15	99.69 45	99.93 38	99.93 37	99.93 49	99.86 63	99.07 108	100.00 1	99.66 63	99.92 123	99.24 301

KinetiMVS		99.66 66	99.63 69	99.76 77	99.89 39	99.57 147	99.37 127	99.82 85	99.95 28	99.90 62	99.63 219	98.57 178	99.97 37	99.65 65	99.94 109	99.74 84

pmmvs6		99.86 10	99.86 13	99.83 38	99.94 18	99.90 7	99.83 7	99.91 47	99.85 66	99.94 44	99.95 16	99.73 25	99.90 182	99.65 65	99.97 66	99.69 104

MIMVSNet1		99.66 66	99.62 71	99.80 56	99.94 18	99.87 15	99.69 45	99.77 115	99.78 90	99.93 49	99.89 41	97.94 248	99.92 136	99.65 65	99.98 46	99.62 163

LuminaMVS		99.39 136	99.28 151	99.73 102	99.83 71	99.49 159	99.00 253	99.05 359	99.81 82	99.89 67	99.79 108	96.54 311	99.97 37	99.64 68	99.98 46	99.73 87

sc_t1		99.81 26	99.80 30	99.82 43	99.88 45	99.88 12	99.83 7	99.79 105	99.94 32	99.93 49	99.92 27	99.35 70	99.92 136	99.64 68	99.94 109	99.68 110

EC-MVSNet		99.69 56	99.69 57	99.68 122	99.71 161	99.91 4	99.76 23	99.96 28	99.86 60	99.51 237	99.39 312	99.57 45	99.93 108	99.64 68	99.86 173	99.20 314

K. test v3		98.87 259	98.60 268	99.69 120	99.93 24	99.46 167	99.74 27	94.97 433	99.78 90	99.88 77	99.88 50	93.66 358	99.97 37	99.61 71	99.95 96	99.64 147

KD-MVS_self_test		99.63 74	99.59 80	99.76 77	99.84 66	99.90 7	99.37 127	99.79 105	99.83 76	99.88 77	99.85 68	98.42 203	99.90 182	99.60 72	99.73 248	99.49 235

Anonymous20240521		99.44 120	99.42 116	99.49 203	99.89 39	98.96 263	99.62 67	99.76 120	99.85 66	99.82 100	99.88 50	96.39 318	99.97 37	99.59 73	99.98 46	99.55 199

TransMVSNet (Re)		99.78 35	99.77 43	99.81 50	99.91 31	99.85 21	99.75 25	99.86 66	99.70 107	99.91 59	99.89 41	99.60 41	99.87 230	99.59 73	99.74 242	99.71 94

OurMVSNet-221017-0		99.75 45	99.71 53	99.84 35	99.96 7	99.83 33	99.83 7	99.85 72	99.80 86	99.93 49	99.93 22	98.54 184	99.93 108	99.59 73	99.98 46	99.76 79

EU-MVSNet		99.39 136	99.62 71	98.72 346	99.88 45	96.44 390	99.56 87	99.85 72	99.90 44	99.90 62	99.85 68	98.09 237	99.83 297	99.58 76	99.95 96	99.90 27

mvs_anonymous		99.28 161	99.39 120	98.94 318	99.19 352	97.81 353	99.02 247	99.55 241	99.78 90	99.85 90	99.80 98	98.24 223	99.86 249	99.57 77	99.50 322	99.15 326

test1111		97.74 342	98.16 315	96.49 415	99.60 203	89.86 446	99.71 37	91.21 442	99.89 50	99.88 77	99.87 56	93.73 357	99.90 182	99.56 78	99.99 16	99.70 97

lessismore_v0				99.64 145	99.86 57	99.38 193		90.66 443		99.89 67	99.83 80	94.56 348	99.97 37	99.56 78	99.92 123	99.57 194

mvsany_test1		99.44 120	99.45 109	99.40 236	99.37 302	98.64 296	97.90 392	99.59 219	99.27 193	99.92 56	99.82 87	99.74 24	99.93 108	99.55 80	99.87 165	99.63 152

MVSMamba_PlusPlus		99.55 91	99.58 83	99.47 209	99.68 181	99.40 188	99.52 92	99.70 152	99.92 40	99.77 129	99.86 63	98.28 219	99.96 61	99.54 81	99.90 134	99.05 355

pm-mvs1		99.79 32	99.79 32	99.78 67	99.91 31	99.83 33	99.76 23	99.87 61	99.73 96	99.89 67	99.87 56	99.63 35	99.87 230	99.54 81	99.92 123	99.63 152

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 40	99.90 44	99.97 23	99.87 56	99.81 18	99.95 72	99.54 81	99.99 16	99.80 60
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		99.48 105	99.65 65	98.95 317	99.71 161	97.27 371	99.50 99	99.82 85	99.59 143	99.41 263	99.85 68	99.62 38	100.00 1	99.53 84	99.89 144	99.59 184

test2506		94.73 406	94.59 407	95.15 422	99.59 208	85.90 448	99.75 25	74.01 450	99.89 50	99.71 156	99.86 63	79.00 437	99.90 182	99.52 85	99.99 16	99.65 137

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 147	99.93 37	99.95 41	99.89 41	99.71 26	99.96 61	99.51 86	99.97 66	99.84 48

FC-MVSNet-test		99.70 54	99.65 65	99.86 28	99.88 45	99.86 19	99.72 33	99.78 112	99.90 44	99.82 100	99.83 80	98.45 199	99.87 230	99.51 86	99.97 66	99.86 42

BP-MVS1		98.72 274	98.46 284	99.50 199	99.53 245	99.00 255	99.34 133	98.53 385	99.65 123	99.73 149	99.38 314	90.62 393	99.96 61	99.50 88	99.86 173	99.55 199

UA-Net		99.78 35	99.76 47	99.86 28	99.72 158	99.71 94	99.91 4	99.95 35	99.96 24	99.71 156	99.91 31	99.15 94	99.97 37	99.50 88	100.00 1	99.90 27

PMMVS2		99.48 105	99.45 109	99.57 179	99.76 131	98.99 257	98.09 369	99.90 52	98.95 242	99.78 121	99.58 252	99.57 45	99.93 108	99.48 90	99.95 96	99.79 68

VPA-MVSNet		99.66 66	99.62 71	99.79 63	99.68 181	99.75 76	99.62 67	99.69 159	99.85 66	99.80 111	99.81 94	98.81 142	99.91 163	99.47 91	99.88 153	99.70 97

GDP-MVS		98.81 265	98.57 274	99.50 199	99.53 245	99.12 242	99.28 157	99.86 66	99.53 147	99.57 209	99.32 330	90.88 389	99.98 23	99.46 92	99.74 242	99.42 263

ECVR-MVS		97.73 343	98.04 322	96.78 408	99.59 208	90.81 441	99.72 33	90.43 444	99.89 50	99.86 87	99.86 63	93.60 359	99.89 201	99.46 92	99.99 16	99.65 137

nrg030		99.70 54	99.66 63	99.82 43	99.76 131	99.84 26	99.61 73	99.70 152	99.93 37	99.78 121	99.68 191	99.10 101	99.78 335	99.45 94	99.96 80	99.83 52

TAMVS		99.49 103	99.45 109	99.63 152	99.48 270	99.42 181	99.45 112	99.57 230	99.66 120	99.78 121	99.83 80	97.85 255	99.86 249	99.44 95	99.96 80	99.61 173

GeoE		99.69 56	99.66 63	99.78 67	99.76 131	99.76 68	99.60 79	99.82 85	99.46 162	99.75 137	99.56 263	99.63 35	99.95 72	99.43 96	99.88 153	99.62 163

new-patchmatchnet		99.35 147	99.57 87	98.71 348	99.82 79	96.62 386	98.55 325	99.75 125	99.50 151	99.88 77	99.87 56	99.31 75	99.88 216	99.43 96	100.00 1	99.62 163

test20.03		99.55 91	99.54 94	99.58 173	99.79 110	99.37 196	99.02 247	99.89 55	99.60 141	99.82 100	99.62 227	98.81 142	99.89 201	99.43 96	99.86 173	99.47 243

MVSFormer		99.41 130	99.44 112	99.31 263	99.57 223	98.40 313	99.77 19	99.80 98	99.73 96	99.63 183	99.30 335	98.02 242	99.98 23	99.43 96	99.69 263	99.55 199

test_djsdf		99.84 17	99.81 27	99.91 3	99.94 18	99.84 26	99.77 19	99.80 98	99.73 96	99.97 23	99.92 27	99.77 23	99.98 23	99.43 96	100.00 1	99.90 27

SDMVSNet		99.77 42	99.77 43	99.76 77	99.80 98	99.65 119	99.63 64	99.86 66	99.97 21	99.89 67	99.89 41	99.52 52	99.99 8	99.42 101	99.96 80	99.65 137

Anonymous20231211		99.62 80	99.57 87	99.76 77	99.61 201	99.60 138	99.81 13	99.73 135	99.82 78	99.90 62	99.90 36	97.97 247	99.86 249	99.42 101	99.96 80	99.80 60

SixPastTwentyTwo		99.42 126	99.30 144	99.76 77	99.92 29	99.67 111	99.70 38	99.14 352	99.65 123	99.89 67	99.90 36	96.20 325	99.94 88	99.42 101	99.92 123	99.67 119

balanced_conf03		99.50 99	99.50 100	99.50 199	99.42 293	99.49 159	99.52 92	99.75 125	99.86 60	99.78 121	99.71 165	98.20 230	99.90 182	99.39 104	99.88 153	99.10 337

patch_mono-2		99.51 98	99.46 107	99.64 145	99.70 169	99.11 243	99.04 241	99.87 61	99.71 102	99.47 244	99.79 108	98.24 223	99.98 23	99.38 105	99.96 80	99.83 52

UGNet		99.38 139	99.34 132	99.49 203	98.90 391	98.90 272	99.70 38	99.35 311	99.86 60	98.57 376	99.81 94	98.50 194	99.93 108	99.38 105	99.98 46	99.66 129
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 53	99.67 61	99.81 50	99.89 39	99.72 91	99.59 80	99.82 85	99.39 178	99.82 100	99.84 75	99.38 64	99.91 163	99.38 105	99.93 119	99.80 60

FIs		99.65 72	99.58 83	99.84 35	99.84 66	99.85 21	99.66 57	99.75 125	99.86 60	99.74 145	99.79 108	98.27 221	99.85 267	99.37 108	99.93 119	99.83 52

sd_testset		99.78 35	99.78 37	99.80 56	99.80 98	99.76 68	99.80 14	99.79 105	99.97 21	99.89 67	99.89 41	99.53 50	99.99 8	99.36 109	99.96 80	99.65 137

anonymousdsp		99.80 28	99.77 43	99.90 8	99.96 7	99.88 12	99.73 30	99.85 72	99.70 107	99.92 56	99.93 22	99.45 55	99.97 37	99.36 109	100.00 1	99.85 45

casdiffmvs_mvg		99.68 59	99.68 60	99.69 120	99.81 91	99.59 140	99.29 155	99.90 52	99.71 102	99.79 117	99.73 148	99.54 48	99.84 282	99.36 109	99.96 80	99.65 137
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 45	99.74 50	99.79 63	99.88 45	99.66 113	99.69 45	99.92 40	99.67 116	99.77 129	99.75 139	99.61 39	99.98 23	99.35 112	99.98 46	99.72 91
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 82	99.64 68	99.53 192	99.79 110	98.82 276	99.58 82	99.97 20	99.95 28	99.96 31	99.76 133	98.44 200	99.99 8	99.34 113	99.96 80	99.78 70

CHOSEN 1792x2688		99.39 136	99.30 144	99.65 138	99.88 45	99.25 221	98.78 299	99.88 59	98.66 282	99.96 31	99.79 108	97.45 277	99.93 108	99.34 113	99.99 16	99.78 70

CDS-MVSNet		99.22 180	99.13 174	99.50 199	99.35 309	99.11 243	98.96 268	99.54 247	99.46 162	99.61 198	99.70 173	96.31 321	99.83 297	99.34 113	99.88 153	99.55 199
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 239	99.16 168	98.51 356	99.75 143	95.90 402	98.07 372	99.84 78	99.84 70	99.89 67	99.73 148	96.01 329	99.99 8	99.33 116	100.00 1	99.63 152

HyFIR lowres test		98.91 252	98.64 265	99.73 102	99.85 61	99.47 163	98.07 372	99.83 80	98.64 284	99.89 67	99.60 244	92.57 368	100.00 1	99.33 116	99.97 66	99.72 91

pmmvs5		99.19 190	99.11 181	99.42 225	99.76 131	98.88 273	98.55 325	99.73 135	98.82 262	99.72 151	99.62 227	96.56 308	99.82 307	99.32 118	99.95 96	99.56 196

v148		99.40 132	99.41 118	99.39 239	99.76 131	98.94 265	99.09 228	99.59 219	99.17 213	99.81 107	99.61 236	98.41 204	99.69 371	99.32 118	99.94 109	99.53 213

baseline		99.63 74	99.62 71	99.66 132	99.80 98	99.62 129	99.44 114	99.80 98	99.71 102	99.72 151	99.69 180	99.15 94	99.83 297	99.32 118	99.94 109	99.53 213

CVMVSNet		98.61 282	98.88 245	97.80 387	99.58 213	93.60 425	99.26 163	99.64 190	99.66 120	99.72 151	99.67 195	93.26 361	99.93 108	99.30 121	99.81 210	99.87 40

PS-CasMVS		99.66 66	99.58 83	99.89 11	99.80 98	99.85 21	99.66 57	99.73 135	99.62 131	99.84 93	99.71 165	98.62 171	99.96 61	99.30 121	99.96 80	99.86 42

DTE-MVSNet		99.68 59	99.61 75	99.88 18	99.80 98	99.87 15	99.67 53	99.71 147	99.72 100	99.84 93	99.78 120	98.67 165	99.97 37	99.30 121	99.95 96	99.80 60

tmp_tt		95.75 399	95.42 394	96.76 409	89.90 449	94.42 419	98.86 280	97.87 412	78.01 440	99.30 294	99.69 180	97.70 263	95.89 442	99.29 124	98.14 418	99.95 14

PEN-MVS		99.66 66	99.59 80	99.89 11	99.83 71	99.87 15	99.66 57	99.73 135	99.70 107	99.84 93	99.73 148	98.56 181	99.96 61	99.29 124	99.94 109	99.83 52

WR-MVS_H		99.61 82	99.53 98	99.87 24	99.80 98	99.83 33	99.67 53	99.75 125	99.58 144	99.85 90	99.69 180	98.18 233	99.94 88	99.28 126	99.95 96	99.83 52

IterMVS		98.97 243	99.16 168	98.42 361	99.74 151	95.64 406	98.06 374	99.83 80	99.83 76	99.85 90	99.74 144	96.10 328	99.99 8	99.27 127	100.00 1	99.63 152
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WBMVS		97.50 353	97.18 359	98.48 358	98.85 399	95.89 403	98.44 342	99.52 261	99.53 147	99.52 231	99.42 303	80.10 430	99.86 249	99.24 128	99.95 96	99.68 110

h-mvs33		98.61 282	98.34 298	99.44 219	99.60 203	98.67 288	99.27 161	99.44 286	99.68 112	99.32 284	99.49 286	92.50 371	100.00 1	99.24 128	96.51 435	99.65 137

hse-mvs2		98.52 295	98.30 303	99.16 289	99.29 331	98.60 299	98.77 300	99.02 361	99.68 112	99.32 284	99.04 375	92.50 371	99.85 267	99.24 128	97.87 425	99.03 359

FMVSNet1		99.66 66	99.63 69	99.73 102	99.78 118	99.77 61	99.68 49	99.70 152	99.67 116	99.82 100	99.83 80	98.98 124	99.90 182	99.24 128	99.97 66	99.53 213

casdiffmvs		99.63 74	99.61 75	99.67 125	99.79 110	99.59 140	99.13 210	99.85 72	99.79 88	99.76 132	99.72 155	99.33 73	99.82 307	99.21 132	99.94 109	99.59 184
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 94	99.43 114	99.87 24	99.76 131	99.82 41	99.57 85	99.61 202	99.54 145	99.80 111	99.64 207	97.79 259	99.95 72	99.21 132	99.94 109	99.84 48

DELS-MVS		99.34 152	99.30 144	99.48 207	99.51 254	99.36 200	98.12 365	99.53 256	99.36 183	99.41 263	99.61 236	99.22 87	99.87 230	99.21 132	99.68 268	99.20 314
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)		99.37 142	99.26 156	99.68 122	99.51 254	99.58 144	98.98 263	99.60 213	99.43 173	99.70 160	99.36 321	97.70 263	99.88 216	99.20 135	99.87 165	99.59 184

CANet		99.11 214	99.05 203	99.28 270	98.83 401	98.56 302	98.71 307	99.41 292	99.25 197	99.23 302	99.22 353	97.66 271	99.94 88	99.19 136	99.97 66	99.33 283

EI-MVSNet-UG-set		99.48 105	99.50 100	99.42 225	99.57 223	98.65 294	99.24 170	99.46 281	99.68 112	99.80 111	99.66 200	98.99 122	99.89 201	99.19 136	99.90 134	99.72 91

xiu_mvs_v1_base_debu		99.23 172	99.34 132	98.91 324	99.59 208	98.23 322	98.47 337	99.66 172	99.61 135	99.68 166	98.94 391	99.39 60	99.97 37	99.18 138	99.55 308	98.51 407

xiu_mvs_v1_base		99.23 172	99.34 132	98.91 324	99.59 208	98.23 322	98.47 337	99.66 172	99.61 135	99.68 166	98.94 391	99.39 60	99.97 37	99.18 138	99.55 308	98.51 407

xiu_mvs_v1_base_debi		99.23 172	99.34 132	98.91 324	99.59 208	98.23 322	98.47 337	99.66 172	99.61 135	99.68 166	98.94 391	99.39 60	99.97 37	99.18 138	99.55 308	98.51 407

VPNet		99.46 114	99.37 125	99.71 114	99.82 79	99.59 140	99.48 105	99.70 152	99.81 82	99.69 163	99.58 252	97.66 271	99.86 249	99.17 141	99.44 329	99.67 119

UniMVSNet_NR-MVSNet		99.37 142	99.25 158	99.72 109	99.47 276	99.56 148	98.97 265	99.61 202	99.43 173	99.67 171	99.28 339	97.85 255	99.95 72	99.17 141	99.81 210	99.65 137

DU-MVS		99.33 155	99.21 163	99.71 114	99.43 288	99.56 148	98.83 287	99.53 256	99.38 179	99.67 171	99.36 321	97.67 267	99.95 72	99.17 141	99.81 210	99.63 152

EI-MVSNet-Vis-set		99.47 113	99.49 102	99.42 225	99.57 223	98.66 291	99.24 170	99.46 281	99.67 116	99.79 117	99.65 205	98.97 126	99.89 201	99.15 144	99.89 144	99.71 94

EI-MVSNet		99.38 139	99.44 112	99.21 283	99.58 213	98.09 336	99.26 163	99.46 281	99.62 131	99.75 137	99.67 195	98.54 184	99.85 267	99.15 144	99.92 123	99.68 110

VNet		99.18 194	99.06 198	99.56 182	99.24 342	99.36 200	99.33 137	99.31 320	99.67 116	99.47 244	99.57 259	96.48 312	99.84 282	99.15 144	99.30 348	99.47 243

EG-PatchMatch MVS		99.57 85	99.56 92	99.62 161	99.77 127	99.33 206	99.26 163	99.76 120	99.32 187	99.80 111	99.78 120	99.29 77	99.87 230	99.15 144	99.91 133	99.66 129

PVSNet_Blended_VisFu		99.40 132	99.38 122	99.44 219	99.90 37	98.66 291	98.94 272	99.91 47	97.97 345	99.79 117	99.73 148	99.05 115	99.97 37	99.15 144	99.99 16	99.68 110

IterMVS-LS		99.41 130	99.47 103	99.25 279	99.81 91	98.09 336	98.85 282	99.76 120	99.62 131	99.83 99	99.64 207	98.54 184	99.97 37	99.15 144	99.99 16	99.68 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 94	99.47 103	99.76 77	99.58 213	99.64 122	99.30 148	99.63 192	99.61 135	99.71 156	99.56 263	98.76 152	99.96 61	99.14 150	99.92 123	99.68 110

MVSTER		98.47 302	98.22 308	99.24 281	99.06 375	98.35 319	99.08 231	99.46 281	99.27 193	99.75 137	99.66 200	88.61 406	99.85 267	99.14 150	99.92 123	99.52 223

Anonymous20231206		99.35 147	99.31 139	99.47 209	99.74 151	99.06 253	99.28 157	99.74 131	99.23 201	99.72 151	99.53 275	97.63 273	99.88 216	99.11 152	99.84 183	99.48 239

Syy-MVS		98.17 327	97.85 339	99.15 291	98.50 424	98.79 280	98.60 314	99.21 343	97.89 351	96.76 427	96.37 450	95.47 337	99.57 413	99.10 153	98.73 394	99.09 342

ttmdpeth		99.48 105	99.55 93	99.29 267	99.76 131	98.16 330	99.33 137	99.95 35	99.79 88	99.36 273	99.89 41	99.13 99	99.77 343	99.09 154	99.64 281	99.93 20

MVS_Test		99.28 161	99.31 139	99.19 286	99.35 309	98.79 280	99.36 131	99.49 274	99.17 213	99.21 307	99.67 195	98.78 149	99.66 393	99.09 154	99.66 277	99.10 337

testgi		99.29 160	99.26 156	99.37 245	99.75 143	98.81 277	98.84 284	99.89 55	98.38 312	99.75 137	99.04 375	99.36 69	99.86 249	99.08 156	99.25 356	99.45 248

1112_ss		99.05 225	98.84 250	99.67 125	99.66 189	99.29 212	98.52 331	99.82 85	97.65 363	99.43 254	99.16 359	96.42 315	99.91 163	99.07 157	99.84 183	99.80 60

CANet_DTU		98.91 252	98.85 248	99.09 300	98.79 407	98.13 331	98.18 358	99.31 320	99.48 154	98.86 347	99.51 279	96.56 308	99.95 72	99.05 158	99.95 96	99.19 317

Baseline_NR-MVSNet		99.49 103	99.37 125	99.82 43	99.91 31	99.84 26	98.83 287	99.86 66	99.68 112	99.65 178	99.88 50	97.67 267	99.87 230	99.03 159	99.86 173	99.76 79

FMVSNet2		99.35 147	99.28 151	99.55 186	99.49 265	99.35 203	99.45 112	99.57 230	99.44 167	99.70 160	99.74 144	97.21 288	99.87 230	99.03 159	99.94 109	99.44 253

Test_1112_low_res		98.95 249	98.73 259	99.63 152	99.68 181	99.15 239	98.09 369	99.80 98	97.14 389	99.46 248	99.40 308	96.11 326	99.89 201	99.01 161	99.84 183	99.84 48

VDD-MVS		99.20 187	99.11 181	99.44 219	99.43 288	98.98 258	99.50 99	98.32 399	99.80 86	99.56 217	99.69 180	96.99 298	99.85 267	98.99 162	99.73 248	99.50 230

DeepC-MVS	98.90 4	99.62 80	99.61 75	99.67 125	99.72 158	99.44 174	99.24 170	99.71 147	99.27 193	99.93 49	99.90 36	99.70 29	99.93 108	98.99 162	99.99 16	99.64 147
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
pmmvs-eth3d		99.48 105	99.47 103	99.51 197	99.77 127	99.41 187	98.81 292	99.66 172	99.42 177	99.75 137	99.66 200	99.20 89	99.76 346	98.98 164	99.99 16	99.36 276

EPNet_dtu		97.62 348	97.79 342	97.11 407	96.67 444	92.31 430	98.51 332	98.04 406	99.24 199	95.77 436	99.47 293	93.78 356	99.66 393	98.98 164	99.62 285	99.37 273
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 152	99.32 137	99.39 239	99.67 187	98.77 282	98.57 323	99.81 95	99.61 135	99.48 242	99.41 304	98.47 195	99.86 249	98.97 166	99.90 134	99.53 213
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		99.40 132	99.31 139	99.68 122	99.43 288	99.55 152	99.73 30	99.50 270	99.46 162	99.88 77	99.36 321	97.54 274	99.87 230	98.97 166	99.87 165	99.63 152

GBi-Net		99.42 126	99.31 139	99.73 102	99.49 265	99.77 61	99.68 49	99.70 152	99.44 167	99.62 192	99.83 80	97.21 288	99.90 182	98.96 168	99.90 134	99.53 213

FMVSNet5		97.80 340	97.25 357	99.42 225	98.83 401	98.97 261	99.38 123	99.80 98	98.87 254	99.25 298	99.69 180	80.60 429	99.91 163	98.96 168	99.90 134	99.38 270

test1		99.42 126	99.31 139	99.73 102	99.49 265	99.77 61	99.68 49	99.70 152	99.44 167	99.62 192	99.83 80	97.21 288	99.90 182	98.96 168	99.90 134	99.53 213

FMVSNet3		98.80 266	98.63 267	99.32 260	99.13 361	98.72 285	99.10 223	99.48 275	99.23 201	99.62 192	99.64 207	92.57 368	99.86 249	98.96 168	99.90 134	99.39 268

UnsupCasMVSNet_eth		98.83 262	98.57 274	99.59 170	99.68 181	99.45 172	98.99 260	99.67 167	99.48 154	99.55 222	99.36 321	94.92 341	99.86 249	98.95 172	96.57 434	99.45 248

CHOSEN 280x420		98.41 307	98.41 290	98.40 362	99.34 318	95.89 403	96.94 428	99.44 286	98.80 266	99.25 298	99.52 277	93.51 360	99.98 23	98.94 173	99.98 46	99.32 286

TDRefinement		99.72 50	99.70 54	99.77 70	99.90 37	99.85 21	99.86 6	99.92 40	99.69 110	99.78 121	99.92 27	99.37 66	99.88 216	98.93 174	99.95 96	99.60 177

alignmvs		98.28 317	97.96 328	99.25 279	99.12 363	98.93 268	99.03 244	98.42 392	99.64 126	98.72 362	97.85 429	90.86 390	99.62 404	98.88 175	99.13 362	99.19 317

testing3-2		96.51 378	96.43 373	96.74 411	99.36 305	91.38 438	99.10 223	97.87 412	99.48 154	98.57 376	98.71 405	76.65 439	99.66 393	98.87 176	99.26 355	99.18 319

MGCFI-Net		99.02 231	99.01 216	99.06 307	99.11 368	98.60 299	99.63 64	99.67 167	99.63 128	98.58 374	97.65 432	99.07 108	99.57 413	98.85 177	98.92 378	99.03 359

sss		98.90 254	98.77 258	99.27 273	99.48 270	98.44 310	98.72 305	99.32 316	97.94 349	99.37 272	99.35 326	96.31 321	99.91 163	98.85 177	99.63 284	99.47 243

xiu_mvs_v2_base		99.02 231	99.11 181	98.77 343	99.37 302	98.09 336	98.13 364	99.51 266	99.47 159	99.42 257	98.54 414	99.38 64	99.97 37	98.83 179	99.33 344	98.24 419

PS-MVSNAJ		99.00 239	99.08 192	98.76 344	99.37 302	98.10 335	98.00 380	99.51 266	99.47 159	99.41 263	98.50 416	99.28 79	99.97 37	98.83 179	99.34 343	98.20 423

D2MVS		99.22 180	99.19 165	99.29 267	99.69 173	98.74 284	98.81 292	99.41 292	98.55 293	99.68 166	99.69 180	98.13 235	99.87 230	98.82 181	99.98 46	99.24 301

PatchT		98.45 304	98.32 300	98.83 337	98.94 389	98.29 320	99.24 170	98.82 369	99.84 70	99.08 324	99.76 133	91.37 379	99.94 88	98.82 181	99.00 373	98.26 418

testf1		99.63 74	99.60 78	99.72 109	99.94 18	99.95 2	99.47 108	99.89 55	99.43 173	99.88 77	99.80 98	99.26 83	99.90 182	98.81 183	99.88 153	99.32 286

APD_test2		99.63 74	99.60 78	99.72 109	99.94 18	99.95 2	99.47 108	99.89 55	99.43 173	99.88 77	99.80 98	99.26 83	99.90 182	98.81 183	99.88 153	99.32 286

sasdasda		99.02 231	99.00 220	99.09 300	99.10 370	98.70 286	99.61 73	99.66 172	99.63 128	98.64 368	97.65 432	99.04 116	99.54 417	98.79 185	98.92 378	99.04 357

Effi-MVS+		99.06 222	98.97 231	99.34 252	99.31 325	98.98 258	98.31 350	99.91 47	98.81 264	98.79 356	98.94 391	99.14 97	99.84 282	98.79 185	98.74 391	99.20 314

canonicalmvs		99.02 231	99.00 220	99.09 300	99.10 370	98.70 286	99.61 73	99.66 172	99.63 128	98.64 368	97.65 432	99.04 116	99.54 417	98.79 185	98.92 378	99.04 357

VDDNet		98.97 243	98.82 253	99.42 225	99.71 161	98.81 277	99.62 67	98.68 376	99.81 82	99.38 271	99.80 98	94.25 350	99.85 267	98.79 185	99.32 346	99.59 184

CR-MVSNet		98.35 314	98.20 310	98.83 337	99.05 376	98.12 332	99.30 148	99.67 167	97.39 377	99.16 313	99.79 108	91.87 376	99.91 163	98.78 189	98.77 387	98.44 412

test_method		91.72 407	92.32 410	89.91 425	93.49 448	70.18 451	90.28 439	99.56 235	61.71 443	95.39 438	99.52 277	93.90 352	99.94 88	98.76 190	98.27 411	99.62 163

RPMNet		98.60 285	98.53 280	98.83 337	99.05 376	98.12 332	99.30 148	99.62 195	99.86 60	99.16 313	99.74 144	92.53 370	99.92 136	98.75 191	98.77 387	98.44 412

pmmvs4		99.13 207	99.06 198	99.36 249	99.57 223	99.10 248	98.01 378	99.25 333	98.78 269	99.58 206	99.44 300	98.24 223	99.76 346	98.74 192	99.93 119	99.22 307

tttt0517		97.62 348	97.20 358	98.90 330	99.76 131	97.40 368	99.48 105	94.36 435	99.06 230	99.70 160	99.49 286	84.55 422	99.94 88	98.73 193	99.65 279	99.36 276

EPP-MVSNet		99.17 199	99.00 220	99.66 132	99.80 98	99.43 178	99.70 38	99.24 336	99.48 154	99.56 217	99.77 129	94.89 342	99.93 108	98.72 194	99.89 144	99.63 152

Anonymous20240529		99.42 126	99.34 132	99.65 138	99.53 245	99.60 138	99.63 64	99.39 302	99.47 159	99.76 132	99.78 120	98.13 235	99.86 249	98.70 195	99.68 268	99.49 235

ACMH	98.42 6	99.59 84	99.54 94	99.72 109	99.86 57	99.62 129	99.56 87	99.79 105	98.77 271	99.80 111	99.85 68	99.64 33	99.85 267	98.70 195	99.89 144	99.70 97
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 155	99.28 151	99.47 209	99.57 223	99.39 191	99.78 17	99.43 289	98.87 254	99.57 209	99.82 87	98.06 240	99.87 230	98.69 197	99.73 248	99.15 326

LFMVS		98.46 303	98.19 313	99.26 276	99.24 342	98.52 306	99.62 67	96.94 424	99.87 57	99.31 289	99.58 252	91.04 384	99.81 322	98.68 198	99.42 333	99.45 248

WR-MVS		99.11 214	98.93 236	99.66 132	99.30 329	99.42 181	98.42 343	99.37 307	99.04 231	99.57 209	99.20 357	96.89 300	99.86 249	98.66 199	99.87 165	99.70 97

mvsmamba		99.08 218	98.95 234	99.45 215	99.36 305	99.18 236	99.39 120	98.81 370	99.37 180	99.35 275	99.70 173	96.36 320	99.94 88	98.66 199	99.59 299	99.22 307

RRT-MVS		99.08 218	99.00 220	99.33 255	99.27 336	98.65 294	99.62 67	99.93 38	99.66 120	99.67 171	99.82 87	95.27 339	99.93 108	98.64 201	99.09 366	99.41 264

Anonymous202405211		98.75 270	98.46 284	99.63 152	99.34 318	99.66 113	99.47 108	97.65 415	99.28 192	99.56 217	99.50 282	93.15 362	99.84 282	98.62 202	99.58 301	99.40 266

EPNet		98.13 328	97.77 343	99.18 288	94.57 447	97.99 342	99.24 170	97.96 408	99.74 95	97.29 420	99.62 227	93.13 363	99.97 37	98.59 203	99.83 191	99.58 189
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 225	99.09 190	98.91 324	99.21 347	98.36 318	98.82 291	99.47 278	98.85 257	98.90 342	99.56 263	98.78 149	99.09 433	98.57 204	99.68 268	99.26 298

Patchmatch-RL test		98.60 285	98.36 295	99.33 255	99.77 127	99.07 251	98.27 352	99.87 61	98.91 249	99.74 145	99.72 155	90.57 395	99.79 332	98.55 205	99.85 178	99.11 335

pmmvs3		98.08 331	97.80 340	98.91 324	99.41 295	97.69 359	97.87 393	99.66 172	95.87 408	99.50 239	99.51 279	90.35 397	99.97 37	98.55 205	99.47 326	99.08 348

ETV-MVS		99.18 194	99.18 166	99.16 289	99.34 318	99.28 214	99.12 215	99.79 105	99.48 154	98.93 336	98.55 413	99.40 59	99.93 108	98.51 207	99.52 318	98.28 417

jason		99.16 200	99.11 181	99.32 260	99.75 143	98.44 310	98.26 354	99.39 302	98.70 279	99.74 145	99.30 335	98.54 184	99.97 37	98.48 208	99.82 200	99.55 199
jason: jason.
APDe-MVS		99.48 105	99.36 128	99.85 30	99.55 237	99.81 46	99.50 99	99.69 159	98.99 235	99.75 137	99.71 165	98.79 147	99.93 108	98.46 209	99.85 178	99.80 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CL-MVSNet_self_test		98.71 276	98.56 278	99.15 291	99.22 345	98.66 291	97.14 423	99.51 266	98.09 338	99.54 224	99.27 341	96.87 301	99.74 353	98.43 210	98.96 375	99.03 359

our_test_3		98.85 261	99.09 190	98.13 375	99.66 189	94.90 417	97.72 398	99.58 228	99.07 228	99.64 179	99.62 227	98.19 231	99.93 108	98.41 211	99.95 96	99.55 199

Gipuma		99.57 85	99.59 80	99.49 203	99.98 3	99.71 94	99.72 33	99.84 78	99.81 82	99.94 44	99.78 120	98.91 134	99.71 362	98.41 211	99.95 96	99.05 355
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 358	96.91 368	98.74 345	97.72 440	97.57 361	97.60 404	97.36 421	98.00 341	99.21 307	98.02 425	90.04 400	99.79 332	98.37 213	95.89 439	98.86 382

PM-MVS		99.36 145	99.29 149	99.58 173	99.83 71	99.66 113	98.95 270	99.86 66	98.85 257	99.81 107	99.73 148	98.40 208	99.92 136	98.36 214	99.83 191	99.17 322

baseline1		97.73 343	97.33 354	98.96 315	99.30 329	97.73 357	99.40 118	98.42 392	99.33 186	99.46 248	99.21 355	91.18 382	99.82 307	98.35 215	91.26 442	99.32 286

MVS-HIRNet		97.86 337	98.22 308	96.76 409	99.28 334	91.53 436	98.38 345	92.60 441	99.13 221	99.31 289	99.96 15	97.18 292	99.68 383	98.34 216	99.83 191	99.07 353

GA-MVS		97.99 336	97.68 346	98.93 321	99.52 252	98.04 340	97.19 422	99.05 359	98.32 325	98.81 352	98.97 387	89.89 402	99.41 428	98.33 217	99.05 369	99.34 282

Fast-Effi-MVS+		99.02 231	98.87 246	99.46 212	99.38 300	99.50 158	99.04 241	99.79 105	97.17 387	98.62 370	98.74 404	99.34 71	99.95 72	98.32 218	99.41 334	98.92 375

MDA-MVSNet_test_wron		98.95 249	98.99 227	98.85 333	99.64 194	97.16 374	98.23 356	99.33 314	98.93 246	99.56 217	99.66 200	97.39 281	99.83 297	98.29 219	99.88 153	99.55 199

N_pmnet		98.73 273	98.53 280	99.35 251	99.72 158	98.67 288	98.34 347	94.65 434	98.35 319	99.79 117	99.68 191	98.03 241	99.93 108	98.28 220	99.92 123	99.44 253

ET-MVSNet_ETH3D		96.78 370	96.07 380	98.91 324	99.26 339	97.92 349	97.70 400	96.05 429	97.96 348	92.37 442	98.43 417	87.06 410	99.90 182	98.27 221	97.56 428	98.91 376

thisisatest0530		97.45 354	96.95 365	98.94 318	99.68 181	97.73 357	99.09 228	94.19 437	98.61 289	99.56 217	99.30 335	84.30 424	99.93 108	98.27 221	99.54 313	99.16 324

YYNet1		98.95 249	98.99 227	98.84 335	99.64 194	97.14 376	98.22 357	99.32 316	98.92 248	99.59 204	99.66 200	97.40 279	99.83 297	98.27 221	99.90 134	99.55 199

reproduce_model		99.50 99	99.40 119	99.83 38	99.60 203	99.83 33	99.12 215	99.68 162	99.49 153	99.80 111	99.79 108	99.01 119	99.93 108	98.24 224	99.82 200	99.73 87

ACMM	98.09 11	99.46 114	99.38 122	99.72 109	99.80 98	99.69 106	99.13 210	99.65 182	98.99 235	99.64 179	99.72 155	99.39 60	99.86 249	98.23 225	99.81 210	99.60 177
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 246	98.87 246	99.24 281	99.57 223	98.40 313	98.12 365	99.18 347	98.28 327	99.63 183	99.13 361	98.02 242	99.97 37	98.22 226	99.69 263	99.35 279

3Dnovator	99.15 2	99.43 123	99.36 128	99.65 138	99.39 297	99.42 181	99.70 38	99.56 235	99.23 201	99.35 275	99.80 98	99.17 92	99.95 72	98.21 227	99.84 183	99.59 184

Fast-Effi-MVS+-dtu		99.20 187	99.12 178	99.43 223	99.25 340	99.69 106	99.05 236	99.82 85	99.50 151	98.97 332	99.05 373	98.98 124	99.98 23	98.20 228	99.24 358	98.62 397

MS-PatchMatch		99.00 239	98.97 231	99.09 300	99.11 368	98.19 326	98.76 301	99.33 314	98.49 302	99.44 250	99.58 252	98.21 228	99.69 371	98.20 228	99.62 285	99.39 268

TSAR-MVS + GP.		99.12 210	99.04 209	99.38 242	99.34 318	99.16 237	98.15 361	99.29 324	98.18 334	99.63 183	99.62 227	99.18 91	99.68 383	98.20 228	99.74 242	99.30 292

DP-MVS		99.48 105	99.39 120	99.74 93	99.57 223	99.62 129	99.29 155	99.61 202	99.87 57	99.74 145	99.76 133	98.69 161	99.87 230	98.20 228	99.80 217	99.75 82

MVP-Stereo		99.16 200	99.08 192	99.43 223	99.48 270	99.07 251	99.08 231	99.55 241	98.63 285	99.31 289	99.68 191	98.19 231	99.78 335	98.18 232	99.58 301	99.45 248
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 123	99.30 144	99.80 56	99.83 71	99.81 46	99.52 92	99.70 152	98.35 319	99.51 237	99.50 282	99.31 75	99.88 216	98.18 232	99.84 183	99.69 104

MDA-MVSNet-bldmvs		99.06 222	99.05 203	99.07 305	99.80 98	97.83 352	98.89 276	99.72 144	99.29 189	99.63 183	99.70 173	96.47 313	99.89 201	98.17 234	99.82 200	99.50 230

JIA-IIPM		98.06 332	97.92 335	98.50 357	98.59 420	97.02 378	98.80 295	98.51 387	99.88 55	97.89 406	99.87 56	91.89 375	99.90 182	98.16 235	97.68 427	98.59 400

EIA-MVS		99.12 210	99.01 216	99.45 215	99.36 305	99.62 129	99.34 133	99.79 105	98.41 308	98.84 349	98.89 395	98.75 154	99.84 282	98.15 236	99.51 319	98.89 379

miper_lstm_enhance		98.65 281	98.60 268	98.82 340	99.20 350	97.33 370	97.78 396	99.66 172	99.01 234	99.59 204	99.50 282	94.62 347	99.85 267	98.12 237	99.90 134	99.26 298

reproduce-ours		99.46 114	99.35 130	99.82 43	99.56 234	99.83 33	99.05 236	99.65 182	99.45 165	99.78 121	99.78 120	98.93 129	99.93 108	98.11 238	99.81 210	99.70 97

our_new_method		99.46 114	99.35 130	99.82 43	99.56 234	99.83 33	99.05 236	99.65 182	99.45 165	99.78 121	99.78 120	98.93 129	99.93 108	98.11 238	99.81 210	99.70 97

Effi-MVS+-dtu		99.07 221	98.92 240	99.52 194	98.89 394	99.78 55	99.15 202	99.66 172	99.34 184	98.92 339	99.24 351	97.69 265	99.98 23	98.11 238	99.28 351	98.81 386

tpm		97.15 362	96.95 365	97.75 389	98.91 390	94.24 420	99.32 140	97.96 408	97.71 361	98.29 387	99.32 330	86.72 416	99.92 136	98.10 241	96.24 437	99.09 342

DeepPCF-MVS	98.42 6	99.18 194	99.02 212	99.67 125	99.22 345	99.75 76	97.25 420	99.47 278	98.72 276	99.66 176	99.70 173	99.29 77	99.63 403	98.07 242	99.81 210	99.62 163

ppachtmachnet_test		98.89 257	99.12 178	98.20 373	99.66 189	95.24 413	97.63 402	99.68 162	99.08 226	99.78 121	99.62 227	98.65 169	99.88 216	98.02 243	99.96 80	99.48 239

tpmrst		97.73 343	98.07 321	96.73 412	98.71 416	92.00 431	99.10 223	98.86 366	98.52 298	98.92 339	99.54 273	91.90 374	99.82 307	98.02 243	99.03 371	98.37 414

CSCG		99.37 142	99.29 149	99.60 167	99.71 161	99.46 167	99.43 116	99.85 72	98.79 267	99.41 263	99.60 244	98.92 132	99.92 136	98.02 243	99.92 123	99.43 259

eth_miper_zixun_eth		98.68 279	98.71 261	98.60 352	99.10 370	96.84 383	97.52 410	99.54 247	98.94 243	99.58 206	99.48 289	96.25 324	99.76 346	98.01 246	99.93 119	99.21 310

Patchmtry		98.78 267	98.54 279	99.49 203	98.89 394	99.19 234	99.32 140	99.67 167	99.65 123	99.72 151	99.79 108	91.87 376	99.95 72	98.00 247	99.97 66	99.33 283

PVSNet_BlendedMVS		99.03 229	99.01 216	99.09 300	99.54 239	97.99 342	98.58 319	99.82 85	97.62 364	99.34 279	99.71 165	98.52 191	99.77 343	97.98 248	99.97 66	99.52 223

PVSNet_Blended		98.70 277	98.59 270	99.02 310	99.54 239	97.99 342	97.58 405	99.82 85	95.70 412	99.34 279	98.98 385	98.52 191	99.77 343	97.98 248	99.83 191	99.30 292

cl____		98.54 293	98.41 290	98.92 322	99.03 380	97.80 355	97.46 412	99.59 219	98.90 250	99.60 201	99.46 296	93.85 354	99.78 335	97.97 250	99.89 144	99.17 322

DIV-MVS_self_test		98.54 293	98.42 289	98.92 322	99.03 380	97.80 355	97.46 412	99.59 219	98.90 250	99.60 201	99.46 296	93.87 353	99.78 335	97.97 250	99.89 144	99.18 319

AUN-MVS		97.82 339	97.38 353	99.14 294	99.27 336	98.53 304	98.72 305	99.02 361	98.10 336	97.18 423	99.03 379	89.26 404	99.85 267	97.94 252	97.91 423	99.03 359

FA-MVS(test-final)		98.52 295	98.32 300	99.10 299	99.48 270	98.67 288	99.77 19	98.60 383	97.35 379	99.63 183	99.80 98	93.07 364	99.84 282	97.92 253	99.30 348	98.78 389

ambc				99.20 285	99.35 309	98.53 304	99.17 194	99.46 281		99.67 171	99.80 98	98.46 198	99.70 365	97.92 253	99.70 259	99.38 270

USDC		98.96 246	98.93 236	99.05 308	99.54 239	97.99 342	97.07 426	99.80 98	98.21 331	99.75 137	99.77 129	98.43 201	99.64 402	97.90 255	99.88 153	99.51 225

OPM-MVS		99.26 167	99.13 174	99.63 152	99.70 169	99.61 135	98.58 319	99.48 275	98.50 300	99.52 231	99.63 219	99.14 97	99.76 346	97.89 256	99.77 231	99.51 225
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 157	99.17 167	99.77 70	99.69 173	99.80 50	99.14 204	99.31 320	99.16 215	99.62 192	99.61 236	98.35 212	99.91 163	97.88 257	99.72 254	99.61 173
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 38	99.70 169	99.79 52	99.14 204	99.61 202					99.92 136	97.88 257	99.72 254	99.77 74

c3_l		98.72 274	98.71 261	98.72 346	99.12 363	97.22 373	97.68 401	99.56 235	98.90 250	99.54 224	99.48 289	96.37 319	99.73 356	97.88 257	99.88 153	99.21 310

3Dnovator+	98.92 3	99.35 147	99.24 160	99.67 125	99.35 309	99.47 163	99.62 67	99.50 270	99.44 167	99.12 320	99.78 120	98.77 151	99.94 88	97.87 260	99.72 254	99.62 163

miper_ehance_all_eth		98.59 288	98.59 270	98.59 353	98.98 386	97.07 377	97.49 411	99.52 261	98.50 300	99.52 231	99.37 317	96.41 317	99.71 362	97.86 261	99.62 285	99.00 366

WTY-MVS		98.59 288	98.37 294	99.26 276	99.43 288	98.40 313	98.74 303	99.13 354	98.10 336	99.21 307	99.24 351	94.82 344	99.90 182	97.86 261	98.77 387	99.49 235

APD_test1		99.36 145	99.28 151	99.61 164	99.89 39	99.89 10	99.32 140	99.74 131	99.18 208	99.69 163	99.75 139	98.41 204	99.84 282	97.85 263	99.70 259	99.10 337

SED-MVS		99.40 132	99.28 151	99.77 70	99.69 173	99.82 41	99.20 181	99.54 247	99.13 221	99.82 100	99.63 219	98.91 134	99.92 136	97.85 263	99.70 259	99.58 189

test_241102_TWO								99.54 247	99.13 221	99.76 132	99.63 219	98.32 217	99.92 136	97.85 263	99.69 263	99.75 82

MVS_111021_HR		99.12 210	99.02 212	99.40 236	99.50 260	99.11 243	97.92 389	99.71 147	98.76 274	99.08 324	99.47 293	99.17 92	99.54 417	97.85 263	99.76 233	99.54 208

MTAPA		99.35 147	99.20 164	99.80 56	99.81 91	99.81 46	99.33 137	99.53 256	99.27 193	99.42 257	99.63 219	98.21 228	99.95 72	97.83 267	99.79 222	99.65 137

MSC_two_6792asdad				99.74 93	99.03 380	99.53 155		99.23 337					99.92 136	97.77 268	99.69 263	99.78 70

No_MVS				99.74 93	99.03 380	99.53 155		99.23 337					99.92 136	97.77 268	99.69 263	99.78 70

TESTMET0.1,1		96.24 385	95.84 386	97.41 398	98.24 431	93.84 423	97.38 414	95.84 430	98.43 305	97.81 411	98.56 412	79.77 433	99.89 201	97.77 268	98.77 387	98.52 406

ACMH+	98.40 8	99.50 99	99.43 114	99.71 114	99.86 57	99.76 68	99.32 140	99.77 115	99.53 147	99.77 129	99.76 133	99.26 83	99.78 335	97.77 268	99.88 153	99.60 177

IU-MVS					99.69 173	99.77 61		99.22 340	97.50 371	99.69 163				97.75 272	99.70 259	99.77 74

114514_t		98.49 300	98.11 318	99.64 145	99.73 155	99.58 144	99.24 170	99.76 120	89.94 435	99.42 257	99.56 263	97.76 262	99.86 249	97.74 273	99.82 200	99.47 243

DVP-MVS++		99.38 139	99.25 158	99.77 70	99.03 380	99.77 61	99.74 27	99.61 202	99.18 208	99.76 132	99.61 236	99.00 120	99.92 136	97.72 274	99.60 295	99.62 163

test_0728_THIRD									99.18 208	99.62 192	99.61 236	98.58 177	99.91 163	97.72 274	99.80 217	99.77 74

EGC-MVSNET		89.05 409	85.52 412	99.64 145	99.89 39	99.78 55	99.56 87	99.52 261	24.19 444	49.96 445	99.83 80	99.15 94	99.92 136	97.71 276	99.85 178	99.21 310

miper_enhance_ethall		98.03 333	97.94 333	98.32 367	98.27 430	96.43 391	96.95 427	99.41 292	96.37 403	99.43 254	98.96 389	94.74 345	99.69 371	97.71 276	99.62 285	98.83 385

TSAR-MVS + MP.		99.34 152	99.24 160	99.63 152	99.82 79	99.37 196	99.26 163	99.35 311	98.77 271	99.57 209	99.70 173	99.27 82	99.88 216	97.71 276	99.75 235	99.65 137
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 351	97.28 355	98.40 362	98.37 428	96.75 384	97.24 421	99.37 307	97.31 381	99.41 263	99.22 353	87.30 408	99.37 429	97.70 279	99.62 285	99.08 348

MP-MVS-pluss		99.14 205	98.92 240	99.80 56	99.83 71	99.83 33	98.61 312	99.63 192	96.84 396	99.44 250	99.58 252	98.81 142	99.91 163	97.70 279	99.82 200	99.67 119
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 161	99.11 181	99.79 63	99.75 143	99.81 46	98.95 270	99.53 256	98.27 328	99.53 229	99.73 148	98.75 154	99.87 230	97.70 279	99.83 191	99.68 110

UnsupCasMVSNet_bld		98.55 292	98.27 306	99.40 236	99.56 234	99.37 196	97.97 385	99.68 162	97.49 372	99.08 324	99.35 326	95.41 338	99.82 307	97.70 279	98.19 415	99.01 365

MVS_111021_LR		99.13 207	99.03 211	99.42 225	99.58 213	99.32 208	97.91 391	99.73 135	98.68 280	99.31 289	99.48 289	99.09 103	99.66 393	97.70 279	99.77 231	99.29 295

IS-MVSNet		99.03 229	98.85 248	99.55 186	99.80 98	99.25 221	99.73 30	99.15 351	99.37 180	99.61 198	99.71 165	94.73 346	99.81 322	97.70 279	99.88 153	99.58 189

test-LLR		97.15 362	96.95 365	97.74 390	98.18 433	95.02 415	97.38 414	96.10 426	98.00 341	97.81 411	98.58 409	90.04 400	99.91 163	97.69 285	98.78 385	98.31 415

test-mter		96.23 386	95.73 389	97.74 390	98.18 433	95.02 415	97.38 414	96.10 426	97.90 350	97.81 411	98.58 409	79.12 436	99.91 163	97.69 285	98.78 385	98.31 415

MonoMVSNet		98.23 322	98.32 300	97.99 378	98.97 387	96.62 386	99.49 103	98.42 392	99.62 131	99.40 268	99.79 108	95.51 336	98.58 440	97.68 287	95.98 438	98.76 392

XVS		99.27 165	99.11 181	99.75 88	99.71 161	99.71 94	99.37 127	99.61 202	99.29 189	98.76 359	99.47 293	98.47 195	99.88 216	97.62 288	99.73 248	99.67 119

X-MVStestdata		96.09 390	94.87 403	99.75 88	99.71 161	99.71 94	99.37 127	99.61 202	99.29 189	98.76 359	61.30 453	98.47 195	99.88 216	97.62 288	99.73 248	99.67 119

SMA-MVS		99.19 190	99.00 220	99.73 102	99.46 280	99.73 86	99.13 210	99.52 261	97.40 376	99.57 209	99.64 207	98.93 129	99.83 297	97.61 290	99.79 222	99.63 152
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		96.71 373	96.79 372	96.46 416	98.90 391	90.71 442	99.41 117	98.68 376	94.69 425	98.14 397	99.34 329	86.32 418	99.80 329	97.60 291	98.07 421	98.88 380

PVSNet	97.47 15	98.42 306	98.44 287	98.35 364	99.46 280	96.26 395	96.70 431	99.34 313	97.68 362	99.00 331	99.13 361	97.40 279	99.72 358	97.59 292	99.68 268	99.08 348

new_pmnet		98.88 258	98.89 244	98.84 335	99.70 169	97.62 360	98.15 361	99.50 270	97.98 344	99.62 192	99.54 273	98.15 234	99.94 88	97.55 293	99.84 183	98.95 370

IB-MVS	95.41 20	95.30 405	94.46 409	97.84 386	98.76 412	95.33 411	97.33 417	96.07 428	96.02 407	95.37 439	97.41 436	76.17 440	99.96 61	97.54 294	95.44 441	98.22 420
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		99.24 171	99.11 181	99.61 164	98.38 427	99.79 52	99.57 85	99.68 162	99.61 135	99.15 315	99.71 165	98.70 160	99.91 163	97.54 294	99.68 268	99.13 334

ZNCC-MVS		99.22 180	99.04 209	99.77 70	99.76 131	99.73 86	99.28 157	99.56 235	98.19 333	99.14 317	99.29 338	98.84 141	99.92 136	97.53 296	99.80 217	99.64 147

CP-MVS		99.23 172	99.05 203	99.75 88	99.66 189	99.66 113	99.38 123	99.62 195	98.38 312	99.06 328	99.27 341	98.79 147	99.94 88	97.51 297	99.82 200	99.66 129

SD-MVS		99.01 237	99.30 144	98.15 374	99.50 260	99.40 188	98.94 272	99.61 202	99.22 205	99.75 137	99.82 87	99.54 48	95.51 444	97.48 298	99.87 165	99.54 208
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		98.49 300	98.29 305	99.11 297	98.96 388	98.42 312	97.54 406	99.32 316	97.53 369	98.47 382	98.15 424	97.88 252	99.82 307	97.46 299	99.24 358	99.09 342

DeepC-MVS_fast	98.47 5	99.23 172	99.12 178	99.56 182	99.28 334	99.22 228	98.99 260	99.40 299	99.08 226	99.58 206	99.64 207	98.90 137	99.83 297	97.44 300	99.75 235	99.63 152
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 168	99.08 192	99.76 77	99.73 155	99.70 102	99.31 145	99.59 219	98.36 314	99.36 273	99.37 317	98.80 146	99.91 163	97.43 301	99.75 235	99.68 110

ACMMPR		99.23 172	99.06 198	99.76 77	99.74 151	99.69 106	99.31 145	99.59 219	98.36 314	99.35 275	99.38 314	98.61 173	99.93 108	97.43 301	99.75 235	99.67 119

Vis-MVSNet (Re-imp)		98.77 268	98.58 273	99.34 252	99.78 118	98.88 273	99.61 73	99.56 235	99.11 225	99.24 301	99.56 263	93.00 366	99.78 335	97.43 301	99.89 144	99.35 279

MIMVSNet		98.43 305	98.20 310	99.11 297	99.53 245	98.38 317	99.58 82	98.61 381	98.96 239	99.33 281	99.76 133	90.92 386	99.81 322	97.38 304	99.76 233	99.15 326

WB-MVSnew		98.34 316	98.14 316	98.96 315	98.14 436	97.90 350	98.27 352	97.26 422	98.63 285	98.80 354	98.00 427	97.77 260	99.90 182	97.37 305	98.98 374	99.09 342

XVG-OURS-SEG-HR		99.16 200	98.99 227	99.66 132	99.84 66	99.64 122	98.25 355	99.73 135	98.39 311	99.63 183	99.43 301	99.70 29	99.90 182	97.34 306	98.64 398	99.44 253

COLMAP_ROB	98.06 12	99.45 118	99.37 125	99.70 118	99.83 71	99.70 102	99.38 123	99.78 112	99.53 147	99.67 171	99.78 120	99.19 90	99.86 249	97.32 307	99.87 165	99.55 199
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 231	98.81 254	99.65 138	99.58 213	99.49 159	98.58 319	99.07 356	98.40 310	99.04 329	99.25 346	98.51 193	99.80 329	97.31 308	99.51 319	99.65 137

region2R		99.23 172	99.05 203	99.77 70	99.76 131	99.70 102	99.31 145	99.59 219	98.41 308	99.32 284	99.36 321	98.73 158	99.93 108	97.29 309	99.74 242	99.67 119

APD-MVS_3200maxsize		99.31 158	99.16 168	99.74 93	99.53 245	99.75 76	99.27 161	99.61 202	99.19 207	99.57 209	99.64 207	98.76 152	99.90 182	97.29 309	99.62 285	99.56 196

TAPA-MVS	97.92 13	98.03 333	97.55 349	99.46 212	99.47 276	99.44 174	98.50 333	99.62 195	86.79 436	99.07 327	99.26 344	98.26 222	99.62 404	97.28 311	99.73 248	99.31 290
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 165	99.11 181	99.73 102	99.54 239	99.74 83	99.26 163	99.62 195	99.16 215	99.52 231	99.64 207	98.41 204	99.91 163	97.27 312	99.61 292	99.54 208

RE-MVS-def			99.13 174		99.54 239	99.74 83	99.26 163	99.62 195	99.16 215	99.52 231	99.64 207	98.57 178		97.27 312	99.61 292	99.54 208

testing11		96.05 392	95.41 395	97.97 380	98.78 409	95.27 412	98.59 317	98.23 402	98.86 256	96.56 430	96.91 443	75.20 441	99.69 371	97.26 314	98.29 410	98.93 373

test_yl		98.25 319	97.95 329	99.13 295	99.17 356	98.47 307	99.00 253	98.67 378	98.97 237	99.22 305	99.02 380	91.31 380	99.69 371	97.26 314	98.93 376	99.24 301

DCV-MVSNet		98.25 319	97.95 329	99.13 295	99.17 356	98.47 307	99.00 253	98.67 378	98.97 237	99.22 305	99.02 380	91.31 380	99.69 371	97.26 314	98.93 376	99.24 301

PHI-MVS		99.11 214	98.95 234	99.59 170	99.13 361	99.59 140	99.17 194	99.65 182	97.88 353	99.25 298	99.46 296	98.97 126	99.80 329	97.26 314	99.82 200	99.37 273

tfpnnormal		99.43 123	99.38 122	99.60 167	99.87 54	99.75 76	99.59 80	99.78 112	99.71 102	99.90 62	99.69 180	98.85 140	99.90 182	97.25 318	99.78 227	99.15 326

PatchmatchNet		97.65 347	97.80 340	97.18 405	98.82 404	92.49 429	99.17 194	98.39 395	98.12 335	98.79 356	99.58 252	90.71 392	99.89 201	97.23 319	99.41 334	99.16 324
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 242	98.80 256	99.56 182	99.25 340	99.43 178	98.54 328	99.27 328	98.58 291	98.80 354	99.43 301	98.53 188	99.70 365	97.22 320	99.59 299	99.54 208

testing3		96.48 379	95.63 391	99.01 311	99.23 344	97.81 353	98.90 275	99.10 355	98.72 276	97.84 410	97.92 428	72.44 445	99.85 267	97.21 321	99.33 344	99.35 279

HPM-MVS		99.25 168	99.07 196	99.78 67	99.81 91	99.75 76	99.61 73	99.67 167	97.72 360	99.35 275	99.25 346	99.23 86	99.92 136	97.21 321	99.82 200	99.67 119
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 190	99.00 220	99.76 77	99.76 131	99.68 109	99.38 123	99.54 247	98.34 323	99.01 330	99.50 282	98.53 188	99.93 108	97.18 323	99.78 227	99.66 129

ACMMP		99.25 168	99.08 192	99.74 93	99.79 110	99.68 109	99.50 99	99.65 182	98.07 339	99.52 231	99.69 180	98.57 178	99.92 136	97.18 323	99.79 222	99.63 152
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		96.23 386	95.74 388	97.70 392	98.86 398	95.59 408	98.66 309	98.14 404	98.96 239	97.67 416	97.06 440	76.78 438	98.92 436	97.10 325	98.41 407	98.58 402

thisisatest0515		96.98 366	96.42 374	98.66 349	99.42 293	97.47 364	97.27 419	94.30 436	97.24 383	99.15 315	98.86 397	85.01 420	99.87 230	97.10 325	99.39 336	98.63 396

XVG-ACMP-BASELINE		99.23 172	99.10 189	99.63 152	99.82 79	99.58 144	98.83 287	99.72 144	98.36 314	99.60 201	99.71 165	98.92 132	99.91 163	97.08 327	99.84 183	99.40 266

MSDG		99.08 218	98.98 230	99.37 245	99.60 203	99.13 240	97.54 406	99.74 131	98.84 260	99.53 229	99.55 271	99.10 101	99.79 332	97.07 328	99.86 173	99.18 319

SteuartSystems-ACMMP		99.30 159	99.14 172	99.76 77	99.87 54	99.66 113	99.18 189	99.60 213	98.55 293	99.57 209	99.67 195	99.03 118	99.94 88	97.01 329	99.80 217	99.69 104
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 388	95.78 387	97.49 394	98.53 422	93.83 424	98.04 375	93.94 439	98.96 239	98.46 383	98.17 423	79.86 431	99.87 230	96.99 330	99.06 367	98.78 389

EPMVS		96.53 376	96.32 375	97.17 406	98.18 433	92.97 428	99.39 120	89.95 445	98.21 331	98.61 371	99.59 249	86.69 417	99.72 358	96.99 330	99.23 360	98.81 386

MSP-MVS		99.04 228	98.79 257	99.81 50	99.78 118	99.73 86	99.35 132	99.57 230	98.54 296	99.54 224	98.99 382	96.81 302	99.93 108	96.97 332	99.53 315	99.77 74
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++		98.96 246	98.70 263	99.74 93	99.52 252	99.71 94	98.86 280	99.19 346	98.47 304	98.59 373	99.06 372	98.08 239	99.91 163	96.94 333	99.60 295	99.60 177

SR-MVS		99.19 190	99.00 220	99.74 93	99.51 254	99.72 91	99.18 189	99.60 213	98.85 257	99.47 244	99.58 252	98.38 209	99.92 136	96.92 334	99.54 313	99.57 194

PGM-MVS		99.20 187	99.01 216	99.77 70	99.75 143	99.71 94	99.16 200	99.72 144	97.99 343	99.42 257	99.60 244	98.81 142	99.93 108	96.91 335	99.74 242	99.66 129

HY-MVS	98.23 9	98.21 326	97.95 329	98.99 312	99.03 380	98.24 321	99.61 73	98.72 374	96.81 397	98.73 361	99.51 279	94.06 351	99.86 249	96.91 335	98.20 413	98.86 382

MDTV_nov1_ep13			97.73 344		98.70 417	90.83 440	99.15 202	98.02 407	98.51 299	98.82 351	99.61 236	90.98 385	99.66 393	96.89 337	98.92 378

GST-MVS		99.16 200	98.96 233	99.75 88	99.73 155	99.73 86	99.20 181	99.55 241	98.22 330	99.32 284	99.35 326	98.65 169	99.91 163	96.86 338	99.74 242	99.62 163

test_post1							99.14 204				51.63 455	89.54 403	99.82 307	96.86 338

SCA		98.11 329	98.36 295	97.36 399	99.20 350	92.99 427	98.17 360	98.49 389	98.24 329	99.10 323	99.57 259	96.01 329	99.94 88	96.86 338	99.62 285	99.14 331

UBG		96.53 376	95.95 382	98.29 371	98.87 397	96.31 394	98.48 336	98.07 405	98.83 261	97.32 418	96.54 448	79.81 432	99.62 404	96.84 341	98.74 391	98.95 370

XVG-OURS		99.21 185	99.06 198	99.65 138	99.82 79	99.62 129	97.87 393	99.74 131	98.36 314	99.66 176	99.68 191	99.71 26	99.90 182	96.84 341	99.88 153	99.43 259

LCM-MVSNet-Re		99.28 161	99.15 171	99.67 125	99.33 323	99.76 68	99.34 133	99.97 20	98.93 246	99.91 59	99.79 108	98.68 162	99.93 108	96.80 343	99.56 304	99.30 292

RPSCF		99.18 194	99.02 212	99.64 145	99.83 71	99.85 21	99.44 114	99.82 85	98.33 324	99.50 239	99.78 120	97.90 250	99.65 400	96.78 344	99.83 191	99.44 253

旧先验2							97.94 387		95.33 416	98.94 335			99.88 216	96.75 345

MDTV_nov1_ep13_2view						91.44 437	99.14 204		97.37 378	99.21 307		91.78 378		96.75 345		99.03 359

CLD-MVS		98.76 269	98.57 274	99.33 255	99.57 223	98.97 261	97.53 408	99.55 241	96.41 401	99.27 296	99.13 361	99.07 108	99.78 335	96.73 347	99.89 144	99.23 305
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 330	97.98 327	98.48 358	99.27 336	96.48 389	99.40 118	99.07 356	98.81 264	99.23 302	99.57 259	90.11 399	99.87 230	96.69 348	99.64 281	99.09 342

baseline2		96.83 369	96.28 376	98.46 360	99.09 373	96.91 381	98.83 287	93.87 440	97.23 384	96.23 435	98.36 418	88.12 407	99.90 182	96.68 349	98.14 418	98.57 404

cascas		96.99 365	96.82 371	97.48 395	97.57 443	95.64 406	96.43 433	99.56 235	91.75 431	97.13 425	97.61 435	95.58 334	98.63 438	96.68 349	99.11 364	98.18 424

PC_three_1452									97.56 365	99.68 166	99.41 304	99.09 103	97.09 441	96.66 351	99.60 295	99.62 163

LPG-MVS_test		99.22 180	99.05 203	99.74 93	99.82 79	99.63 127	99.16 200	99.73 135	97.56 365	99.64 179	99.69 180	99.37 66	99.89 201	96.66 351	99.87 165	99.69 104

LGP-MVS_train				99.74 93	99.82 79	99.63 127		99.73 135	97.56 365	99.64 179	99.69 180	99.37 66	99.89 201	96.66 351	99.87 165	99.69 104

ETVMVS		96.14 389	95.22 400	98.89 331	98.80 405	98.01 341	98.66 309	98.35 398	98.71 278	97.18 423	96.31 452	74.23 444	99.75 350	96.64 354	98.13 420	98.90 377

TinyColmap		98.97 243	98.93 236	99.07 305	99.46 280	98.19 326	97.75 397	99.75 125	98.79 267	99.54 224	99.70 173	98.97 126	99.62 404	96.63 355	99.83 191	99.41 264

LF4IMVS		99.01 237	98.92 240	99.27 273	99.71 161	99.28 214	98.59 317	99.77 115	98.32 325	99.39 270	99.41 304	98.62 171	99.84 282	96.62 356	99.84 183	98.69 395

NCCC		98.82 263	98.57 274	99.58 173	99.21 347	99.31 209	98.61 312	99.25 333	98.65 283	98.43 384	99.26 344	97.86 253	99.81 322	96.55 357	99.27 354	99.61 173

OPU-MVS				99.29 267	99.12 363	99.44 174	99.20 181				99.40 308	99.00 120	98.84 437	96.54 358	99.60 295	99.58 189

F-COLMAP		98.74 271	98.45 286	99.62 161	99.57 223	99.47 163	98.84 284	99.65 182	96.31 404	98.93 336	99.19 358	97.68 266	99.87 230	96.52 359	99.37 339	99.53 213

testing99		95.86 397	95.19 401	97.87 384	98.76 412	95.03 414	98.62 311	98.44 391	98.68 280	96.67 429	96.66 447	74.31 443	99.69 371	96.51 360	98.03 422	98.90 377

ADS-MVSNet2		97.78 341	97.66 348	98.12 376	99.14 359	95.36 410	99.22 178	98.75 373	96.97 392	98.25 389	99.64 207	90.90 387	99.94 88	96.51 360	99.56 304	99.08 348

ADS-MVSNet		97.72 346	97.67 347	97.86 385	99.14 359	94.65 418	99.22 178	98.86 366	96.97 392	98.25 389	99.64 207	90.90 387	99.84 282	96.51 360	99.56 304	99.08 348

PatchMatch-RL		98.68 279	98.47 283	99.30 266	99.44 285	99.28 214	98.14 363	99.54 247	97.12 390	99.11 321	99.25 346	97.80 258	99.70 365	96.51 360	99.30 348	98.93 373

CMPMVS	77.52 23	98.50 298	98.19 313	99.41 233	98.33 429	99.56 148	99.01 250	99.59 219	95.44 414	99.57 209	99.80 98	95.64 332	99.46 427	96.47 364	99.92 123	99.21 310
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 393	95.32 398	98.02 377	98.76 412	95.39 409	98.38 345	98.65 380	98.82 262	96.84 426	96.71 446	75.06 442	99.71 362	96.46 365	98.23 412	98.98 367

SF-MVS		99.10 217	98.93 236	99.62 161	99.58 213	99.51 157	99.13 210	99.65 182	97.97 345	99.42 257	99.61 236	98.86 139	99.87 230	96.45 366	99.68 268	99.49 235

FE-MVS		97.85 338	97.42 352	99.15 291	99.44 285	98.75 283	99.77 19	98.20 403	95.85 409	99.33 281	99.80 98	88.86 405	99.88 216	96.40 367	99.12 363	98.81 386

DPE-MVS		99.14 205	98.92 240	99.82 43	99.57 223	99.77 61	98.74 303	99.60 213	98.55 293	99.76 132	99.69 180	98.23 227	99.92 136	96.39 368	99.75 235	99.76 79
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 441	89.02 447			93.47 427		98.30 419		99.84 282	96.38 369

AllTest		99.21 185	99.07 196	99.63 152	99.78 118	99.64 122	99.12 215	99.83 80	98.63 285	99.63 183	99.72 155	98.68 162	99.75 350	96.38 369	99.83 191	99.51 225

TestCases				99.63 152	99.78 118	99.64 122		99.83 80	98.63 285	99.63 183	99.72 155	98.68 162	99.75 350	96.38 369	99.83 191	99.51 225

testdata				99.42 225	99.51 254	98.93 268		99.30 323	96.20 405	98.87 346	99.40 308	98.33 216	99.89 201	96.29 372	99.28 351	99.44 253

dp		96.86 368	97.07 361	96.24 418	98.68 418	90.30 445	99.19 187	98.38 396	97.35 379	98.23 391	99.59 249	87.23 409	99.82 307	96.27 373	98.73 394	98.59 400

tpmvs		97.39 357	97.69 345	96.52 414	98.41 426	91.76 433	99.30 148	98.94 365	97.74 359	97.85 409	99.55 271	92.40 373	99.73 356	96.25 374	98.73 394	98.06 426

KD-MVS_2432*1600		95.89 394	95.41 395	97.31 402	94.96 445	93.89 421	97.09 424	99.22 340	97.23 384	98.88 343	99.04 375	79.23 434	99.54 417	96.24 375	96.81 432	98.50 410

miper_refine_blended		95.89 394	95.41 395	97.31 402	94.96 445	93.89 421	97.09 424	99.22 340	97.23 384	98.88 343	99.04 375	79.23 434	99.54 417	96.24 375	96.81 432	98.50 410

ACMP	97.51 14	99.05 225	98.84 250	99.67 125	99.78 118	99.55 152	98.88 277	99.66 172	97.11 391	99.47 244	99.60 244	99.07 108	99.89 201	96.18 377	99.85 178	99.58 189
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 254	98.72 260	99.44 219	99.39 297	99.42 181	98.58 319	99.64 190	97.31 381	99.44 250	99.62 227	98.59 175	99.69 371	96.17 378	99.79 222	99.22 307

DP-MVS Recon		98.50 298	98.23 307	99.31 263	99.49 265	99.46 167	98.56 324	99.63 192	94.86 423	98.85 348	99.37 317	97.81 257	99.59 411	96.08 379	99.44 329	98.88 380

tpm cat1		96.78 370	96.98 364	96.16 419	98.85 399	90.59 443	99.08 231	99.32 316	92.37 429	97.73 415	99.46 296	91.15 383	99.69 371	96.07 380	98.80 384	98.21 421

tpm2		96.35 382	96.22 377	96.73 412	98.88 396	91.75 434	99.21 180	98.51 387	93.27 428	97.89 406	99.21 355	84.83 421	99.70 365	96.04 381	98.18 416	98.75 393

dmvs_re		98.69 278	98.48 282	99.31 263	99.55 237	99.42 181	99.54 90	98.38 396	99.32 187	98.72 362	98.71 405	96.76 304	99.21 431	96.01 382	99.35 342	99.31 290

test_0402		99.22 180	99.14 172	99.45 215	99.79 110	99.43 178	99.28 157	99.68 162	99.54 145	99.40 268	99.56 263	99.07 108	99.82 307	96.01 382	99.96 80	99.11 335

ITE_SJBPF				99.38 242	99.63 196	99.44 174		99.73 135	98.56 292	99.33 281	99.53 275	98.88 138	99.68 383	96.01 382	99.65 279	99.02 364

test_prior2							97.95 386		97.87 354	98.05 399	99.05 373	97.90 250		95.99 385	99.49 324

testdata2													99.89 201	95.99 385

原ACMM1				99.37 245	99.47 276	98.87 275		99.27 328	96.74 399	98.26 388	99.32 330	97.93 249	99.82 307	95.96 387	99.38 337	99.43 259

新几何1				99.52 194	99.50 260	99.22 228		99.26 330	95.66 413	98.60 372	99.28 339	97.67 267	99.89 201	95.95 388	99.32 346	99.45 248

MP-MVS		99.06 222	98.83 252	99.76 77	99.76 131	99.71 94	99.32 140	99.50 270	98.35 319	98.97 332	99.48 289	98.37 210	99.92 136	95.95 388	99.75 235	99.63 152
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 404	94.59 407	98.61 351	98.66 419	97.45 366	98.54 328	97.90 411	98.53 297	96.54 431	96.47 449	70.62 448	99.81 322	95.91 390	98.15 417	98.56 405

wuyk23d		97.58 350	99.13 174	92.93 423	99.69 173	99.49 159	99.52 92	99.77 115	97.97 345	99.96 31	99.79 108	99.84 14	99.94 88	95.85 391	99.82 200	79.36 441

HQP_MVS		98.90 254	98.68 264	99.55 186	99.58 213	99.24 225	98.80 295	99.54 247	98.94 243	99.14 317	99.25 346	97.24 286	99.82 307	95.84 392	99.78 227	99.60 177

plane_prior5								99.54 247					99.82 307	95.84 392	99.78 227	99.60 177

无先验							98.01 378	99.23 337	95.83 410				99.85 267	95.79 394		99.44 253

CPTT-MVS		98.74 271	98.44 287	99.64 145	99.61 201	99.38 193	99.18 189	99.55 241	96.49 400	99.27 296	99.37 317	97.11 294	99.92 136	95.74 395	99.67 274	99.62 163

PLC	97.35 16	98.36 311	97.99 325	99.48 207	99.32 324	99.24 225	98.50 333	99.51 266	95.19 419	98.58 374	98.96 389	96.95 299	99.83 297	95.63 396	99.25 356	99.37 273
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 290	98.34 298	99.28 270	99.18 355	99.10 248	98.34 347	99.41 292	98.48 303	98.52 379	98.98 385	97.05 296	99.78 335	95.59 397	99.50 322	98.96 368

1314		98.00 335	97.90 337	98.27 372	98.90 391	97.45 366	99.30 148	99.06 358	94.98 420	97.21 422	99.12 365	98.43 201	99.67 388	95.58 398	98.56 401	97.71 430

PVSNet_0	95.53 19	95.85 398	95.31 399	97.47 396	98.78 409	93.48 426	95.72 435	99.40 299	96.18 406	97.37 417	97.73 430	95.73 331	99.58 412	95.49 399	81.40 443	99.36 276

MAR-MVS		98.24 321	97.92 335	99.19 286	98.78 409	99.65 119	99.17 194	99.14 352	95.36 415	98.04 400	98.81 401	97.47 276	99.72 358	95.47 400	99.06 367	98.21 421
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	98.23 322	97.89 338	99.26 276	99.19 352	99.26 218	99.65 62	99.69 159	91.33 433	98.14 397	99.77 129	98.28 219	99.96 61	95.41 401	99.55 308	98.58 402

train_agg		98.35 314	97.95 329	99.57 179	99.35 309	99.35 203	98.11 367	99.41 292	94.90 421	97.92 404	98.99 382	98.02 242	99.85 267	95.38 402	99.44 329	99.50 230

9.14			98.64 265		99.45 284		98.81 292	99.60 213	97.52 370	99.28 295	99.56 263	98.53 188	99.83 297	95.36 403	99.64 281

APD-MVS		98.87 259	98.59 270	99.71 114	99.50 260	99.62 129	99.01 250	99.57 230	96.80 398	99.54 224	99.63 219	98.29 218	99.91 163	95.24 404	99.71 257	99.61 173
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 392								95.20 405

AdaColmap		98.60 285	98.35 297	99.38 242	99.12 363	99.22 228	98.67 308	99.42 291	97.84 357	98.81 352	99.27 341	97.32 284	99.81 322	95.14 406	99.53 315	99.10 337

test9_res														95.10 407	99.44 329	99.50 230

CDPH-MVS		98.56 291	98.20 310	99.61 164	99.50 260	99.46 167	98.32 349	99.41 292	95.22 417	99.21 307	99.10 369	98.34 214	99.82 307	95.09 408	99.66 277	99.56 196

BH-untuned		98.22 324	98.09 319	98.58 355	99.38 300	97.24 372	98.55 325	98.98 364	97.81 358	99.20 312	98.76 403	97.01 297	99.65 400	94.83 409	98.33 408	98.86 382

BP-MVS														94.73 410

HQP-MVS		98.36 311	98.02 324	99.39 239	99.31 325	98.94 265	97.98 382	99.37 307	97.45 373	98.15 393	98.83 398	96.67 305	99.70 365	94.73 410	99.67 274	99.53 213

QAPM		98.40 309	97.99 325	99.65 138	99.39 297	99.47 163	99.67 53	99.52 261	91.70 432	98.78 358	99.80 98	98.55 182	99.95 72	94.71 412	99.75 235	99.53 213

agg_prior2														94.58 413	99.46 328	99.50 230

myMVS_eth3d		95.63 402	94.73 404	98.34 366	98.50 424	96.36 392	98.60 314	99.21 343	97.89 351	96.76 427	96.37 450	72.10 446	99.57 413	94.38 414	98.73 394	99.09 342

BH-RMVSNet		98.41 307	98.14 316	99.21 283	99.21 347	98.47 307	98.60 314	98.26 401	98.35 319	98.93 336	99.31 333	97.20 291	99.66 393	94.32 415	99.10 365	99.51 225

E-PMN		97.14 364	97.43 351	96.27 417	98.79 407	91.62 435	95.54 436	99.01 363	99.44 167	98.88 343	99.12 365	92.78 367	99.68 383	94.30 416	99.03 371	97.50 431

MG-MVS		98.52 295	98.39 292	98.94 318	99.15 358	97.39 369	98.18 358	99.21 343	98.89 253	99.23 302	99.63 219	97.37 282	99.74 353	94.22 417	99.61 292	99.69 104

API-MVS		98.38 310	98.39 292	98.35 364	98.83 401	99.26 218	99.14 204	99.18 347	98.59 290	98.66 367	98.78 402	98.61 173	99.57 413	94.14 418	99.56 304	96.21 438

PAPM_NR		98.36 311	98.04 322	99.33 255	99.48 270	98.93 268	98.79 298	99.28 327	97.54 368	98.56 378	98.57 411	97.12 293	99.69 371	94.09 419	98.90 382	99.38 270

ZD-MVS					99.43 288	99.61 135		99.43 289	96.38 402	99.11 321	99.07 371	97.86 253	99.92 136	94.04 420	99.49 324

DPM-MVS		98.28 317	97.94 333	99.32 260	99.36 305	99.11 243	97.31 418	98.78 372	96.88 394	98.84 349	99.11 368	97.77 260	99.61 409	94.03 421	99.36 340	99.23 305

gg-mvs-nofinetune		95.87 396	95.17 402	97.97 380	98.19 432	96.95 379	99.69 45	89.23 446	99.89 50	96.24 434	99.94 19	81.19 426	99.51 423	93.99 422	98.20 413	97.44 432

PMVS	92.94 21	98.82 263	98.81 254	98.85 333	99.84 66	97.99 342	99.20 181	99.47 278	99.71 102	99.42 257	99.82 87	98.09 237	99.47 425	93.88 423	99.85 178	99.07 353
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 367	97.28 355	95.99 421	98.76 412	91.03 439	95.26 438	98.61 381	99.34 184	98.92 339	98.88 396	93.79 355	99.66 393	92.87 424	99.05 369	97.30 435

BH-w/o		97.20 361	97.01 363	97.76 388	99.08 374	95.69 405	98.03 377	98.52 386	95.76 411	97.96 403	98.02 425	95.62 333	99.47 425	92.82 425	97.25 431	98.12 425

TR-MVS		97.44 355	97.15 360	98.32 367	98.53 422	97.46 365	98.47 337	97.91 410	96.85 395	98.21 392	98.51 415	96.42 315	99.51 423	92.16 426	97.29 430	97.98 427

OpenMVS_ROB	97.31 17	97.36 359	96.84 369	98.89 331	99.29 331	99.45 172	98.87 279	99.48 275	86.54 438	99.44 250	99.74 144	97.34 283	99.86 249	91.61 427	99.28 351	97.37 434

GG-mvs-BLEND				97.36 399	97.59 441	96.87 382	99.70 38	88.49 447		94.64 440	97.26 439	80.66 428	99.12 432	91.50 428	96.50 436	96.08 440

DeepMVS_CX				97.98 379	99.69 173	96.95 379		99.26 330	75.51 441	95.74 437	98.28 420	96.47 313	99.62 404	91.23 429	97.89 424	97.38 433

PAPR		97.56 351	97.07 361	99.04 309	98.80 405	98.11 334	97.63 402	99.25 333	94.56 426	98.02 402	98.25 421	97.43 278	99.68 383	90.90 430	98.74 391	99.33 283

MVS		95.72 400	94.63 406	98.99 312	98.56 421	97.98 347	99.30 148	98.86 366	72.71 442	97.30 419	99.08 370	98.34 214	99.74 353	89.21 431	98.33 408	99.26 298

UWE-MVS-28		95.64 401	95.47 393	96.14 420	97.98 437	90.39 444	98.49 335	95.81 431	99.02 233	98.03 401	98.19 422	84.49 423	99.28 430	88.75 432	98.47 406	98.75 393

thres600view7		96.60 375	96.16 378	97.93 382	99.63 196	96.09 400	99.18 189	97.57 416	98.77 271	98.72 362	97.32 437	87.04 411	99.72 358	88.57 433	98.62 399	97.98 427

FPMVS		96.32 383	95.50 392	98.79 341	99.60 203	98.17 329	98.46 341	98.80 371	97.16 388	96.28 432	99.63 219	82.19 425	99.09 433	88.45 434	98.89 383	99.10 337

PCF-MVS	96.03 18	96.73 372	95.86 385	99.33 255	99.44 285	99.16 237	96.87 429	99.44 286	86.58 437	98.95 334	99.40 308	94.38 349	99.88 216	87.93 435	99.80 217	98.95 370
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 381	96.03 381	97.47 396	99.63 196	95.93 401	99.18 189	97.57 416	98.75 275	98.70 365	97.31 438	87.04 411	99.67 388	87.62 436	98.51 403	96.81 436

tfpn200view9		96.30 384	95.89 383	97.53 393	99.58 213	96.11 398	99.00 253	97.54 419	98.43 305	98.52 379	96.98 441	86.85 413	99.67 388	87.62 436	98.51 403	96.81 436

thres400		96.40 380	95.89 383	97.92 383	99.58 213	96.11 398	99.00 253	97.54 419	98.43 305	98.52 379	96.98 441	86.85 413	99.67 388	87.62 436	98.51 403	97.98 427

thres200		96.09 390	95.68 390	97.33 401	99.48 270	96.22 397	98.53 330	97.57 416	98.06 340	98.37 386	96.73 445	86.84 415	99.61 409	86.99 439	98.57 400	96.16 439

MVE	92.54 22	96.66 374	96.11 379	98.31 369	99.68 181	97.55 362	97.94 387	95.60 432	99.37 180	90.68 443	98.70 407	96.56 308	98.61 439	86.94 440	99.55 308	98.77 391
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 360	96.83 370	98.59 353	99.46 280	97.55 362	99.25 169	96.84 425	98.78 269	97.24 421	97.67 431	97.11 294	98.97 435	86.59 441	98.54 402	99.27 296

PAPM		95.61 403	94.71 405	98.31 369	99.12 363	96.63 385	96.66 432	98.46 390	90.77 434	96.25 433	98.68 408	93.01 365	99.69 371	81.60 442	97.86 426	98.62 397

dongtai		89.37 408	88.91 411	90.76 424	99.19 352	77.46 449	95.47 437	87.82 448	92.28 430	94.17 441	98.82 400	71.22 447	95.54 443	63.85 443	97.34 429	99.27 296

kuosan		85.65 410	84.57 413	88.90 426	97.91 438	77.11 450	96.37 434	87.62 449	85.24 439	85.45 444	96.83 444	69.94 449	90.98 445	45.90 444	95.83 440	98.62 397

test123		29.31 411	33.05 416	18.08 427	25.93 451	12.24 452	97.53 408	10.93 452	11.78 445	24.21 446	50.08 457	21.04 450	8.60 446	23.51 445	32.43 445	33.39 442

testmvs		28.94 412	33.33 414	15.79 428	26.03 450	9.81 453	96.77 430	15.67 451	11.55 446	23.87 447	50.74 456	19.03 451	8.53 447	23.21 446	33.07 444	29.03 443

mmdepth		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

monomultidepth		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

test_blank		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

uanet_test		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

DCPMVS		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

cdsmvs_eth3d_5k		24.88 413	33.17 415	0.00 429	0.00 452	0.00 454	0.00 440	99.62 195	0.00 447	0.00 448	99.13 361	99.82 16	0.00 448	0.00 447	0.00 446	0.00 444

pcd_1.5k_mvsjas		16.61 414	22.14 417	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	99.28 79	0.00 448	0.00 447	0.00 446	0.00 444

sosnet-low-res		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

sosnet		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

uncertanet		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

Regformer		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

ab-mvs-re		8.26 425	11.02 428	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	99.16 359	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

uanet		8.33 415	11.11 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	100.00 1	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

FOURS1					99.83 71	99.89 10	99.74 27	99.71 147	99.69 110	99.63 183

test_one_0601					99.63 196	99.76 68		99.55 241	99.23 201	99.31 289	99.61 236	98.59 175

eth-test2					0.00 452

eth-test					0.00 452

test_241102_ONE					99.69 173	99.82 41		99.54 247	99.12 224	99.82 100	99.49 286	98.91 134	99.52 422

save fliter					99.53 245	99.25 221	98.29 351	99.38 306	99.07 228

test0726					99.69 173	99.80 50	99.24 170	99.57 230	99.16 215	99.73 149	99.65 205	98.35 212

GSMVS																99.14 331

test_part2					99.62 200	99.67 111				99.55 222

sam_mvs1												90.81 391				99.14 331

sam_mvs												90.52 396

MTGPA								99.53 256

test_post											52.41 454	90.25 398	99.86 249

patchmatchnet-post											99.62 227	90.58 394	99.94 88

MTMP							99.09 228	98.59 384

TEST9					99.35 309	99.35 203	98.11 367	99.41 292	94.83 424	97.92 404	98.99 382	98.02 242	99.85 267

test_8					99.34 318	99.31 209	98.08 371	99.40 299	94.90 421	97.87 408	98.97 387	98.02 242	99.84 282

agg_prior					99.35 309	99.36 200		99.39 302		97.76 414			99.85 267

test_prior4						99.19 234	98.00 380

test_prior				99.46 212	99.35 309	99.22 228		99.39 302					99.69 371			99.48 239

新几何2							98.04 375

旧先验1					99.49 265	99.29 212		99.26 330			99.39 312	97.67 267			99.36 340	99.46 247

原ACMM2							97.92 389

test222					99.51 254	99.08 250	97.83 395	99.29 324	95.21 418	98.68 366	99.31 333	97.28 285			99.38 337	99.43 259

segment_acmp												98.37 210

testdata1							97.72 398		97.86 356

test12				99.54 191	99.29 331	99.33 206		99.16 350		98.43 384		97.54 274	99.82 307		99.47 326	99.48 239

plane_prior7					99.58 213	99.38 193

plane_prior6					99.47 276	99.26 218						97.24 286

plane_prior4											99.25 346

plane_prior3						99.31 209			98.36 314	99.14 317

plane_prior2							98.80 295		98.94 243

plane_prior1					99.51 254

plane_prior						99.24 225	98.42 343		97.87 354						99.71 257

n2								0.00 453

nn								0.00 453

door-mid								99.83 80

test11								99.29 324

door								99.77 115

HQP5-MVS						98.94 265

HQP-NCC					99.31 325		97.98 382		97.45 373	98.15 393

ACMP_Plane					99.31 325		97.98 382		97.45 373	98.15 393

HQP4-MVS										98.15 393			99.70 365			99.53 213

HQP3-MVS								99.37 307							99.67 274

HQP2-MVS												96.67 305

NP-MVS					99.40 296	99.13 240					98.83 398

ACMMP++_ref															99.94 109

ACMMP++															99.79 222

Test By Simon												98.41 204

High-resolution multi-view benchmark