High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_vis3_rt		99.89 3	99.90 4	99.87 23	99.98 3	99.75 72	99.70 35	100.00 1	99.73 82	100.00 1	99.89 38	99.79 17	99.88 202	99.98 1	100.00 1	99.98 5

test_fmvs2		99.72 42	99.85 17	99.34 239	99.91 31	98.08 326	99.48 102	100.00 1	99.90 35	99.99 7	99.91 28	99.50 50	99.98 22	99.98 1	99.99 16	99.96 13

test_fmvs3		99.83 21	99.93 2	99.53 181	99.96 7	98.62 287	99.67 50	100.00 1	99.95 24	100.00 1	99.95 16	99.85 11	99.99 8	99.98 1	99.99 16	99.98 5

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

test_vis1_n_1920		99.72 42	99.88 7	99.27 260	99.93 24	97.84 338	99.34 129	100.00 1	99.99 3	99.99 7	99.82 83	99.87 10	99.99 8	99.97 4	99.99 16	99.97 10

test_vis1_n		99.68 51	99.79 30	99.36 236	99.94 18	98.18 315	99.52 89	100.00 1	99.86 50	100.00 1	99.88 47	98.99 113	99.96 57	99.97 4	99.96 72	99.95 14

test_fmvs1_n		99.68 51	99.81 26	99.28 257	99.95 15	97.93 335	99.49 100	100.00 1	99.82 66	99.99 7	99.89 38	99.21 81	99.98 22	99.97 4	99.98 44	99.93 20

test_f		99.75 38	99.88 7	99.37 232	99.96 7	98.21 312	99.51 95	100.00 1	99.94 27	100.00 1	99.93 21	99.58 39	99.94 83	99.97 4	99.99 16	99.97 10

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 44	99.86 18	99.08 223	99.97 20	99.98 15	99.96 27	99.79 103	99.90 8	99.99 8	99.96 9	99.99 16	99.90 26

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 78	99.01 241	99.99 11	99.99 3	99.98 14	99.88 47	99.97 2	99.99 8	99.96 9	100.00 1	99.98 5

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 45	99.88 44	99.55 144	99.17 188	99.98 12	99.99 3	99.96 27	99.84 72	99.96 3	99.99 8	99.96 9	99.99 16	99.88 32

test_cas_vis1_n_1920		99.76 37	99.86 13	99.45 204	99.93 24	98.40 300	99.30 144	99.98 12	99.94 27	99.99 7	99.89 38	99.80 16	99.97 36	99.96 9	99.97 59	99.97 10

fmvsm_l_conf0.5_n		99.80 26	99.78 34	99.85 29	99.88 44	99.66 107	99.11 213	99.91 42	99.98 15	99.96 27	99.64 196	99.60 37	99.99 8	99.95 13	99.99 16	99.88 32

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 35	99.82 74	99.70 96	99.17 188	99.97 20	99.99 3	99.96 27	99.82 83	99.94 4	100.00 1	99.95 13	100.00 1	99.80 54

test_fmvs1		99.48 95	99.65 56	98.97 301	99.54 225	97.16 361	99.11 213	99.98 12	99.78 76	99.96 27	99.81 90	98.72 150	99.97 36	99.95 13	99.97 59	99.79 61

mvsany_test3		99.85 12	99.88 7	99.75 80	99.95 15	99.37 187	99.53 88	99.98 12	99.77 80	99.99 7	99.95 16	99.85 11	99.94 83	99.95 13	99.98 44	99.94 17

fmvsm_s_conf0.1_n_2		99.81 25	99.78 34	99.89 11	99.93 24	99.76 64	98.92 261	99.98 12	99.99 3	99.99 7	99.88 47	99.43 52	99.94 83	99.94 17	99.99 16	99.99 2

fmvsm_l_conf0.5_n_a		99.80 26	99.79 30	99.84 32	99.88 44	99.64 116	99.12 208	99.91 42	99.98 15	99.95 36	99.67 184	99.67 28	99.99 8	99.94 17	99.99 16	99.88 32

MM		99.18 183	99.05 190	99.55 175	99.35 294	98.81 266	99.05 228	97.79 399	99.99 3	99.48 228	99.59 236	96.29 312	99.95 67	99.94 17	99.98 44	99.88 32

test_fmvsmconf_n		99.85 12	99.84 20	99.88 18	99.91 31	99.73 81	98.97 253	99.98 12	99.99 3	99.96 27	99.85 65	99.93 7	99.99 8	99.94 17	99.99 16	99.93 20

fmvsm_s_conf0.5_n_2		99.78 31	99.75 42	99.88 18	99.82 74	99.76 64	98.88 264	99.92 36	99.98 15	99.98 14	99.85 65	99.42 54	99.94 83	99.93 21	99.98 44	99.94 17

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 38	99.10 216	99.98 12	99.99 3	99.98 14	99.91 28	99.68 27	99.93 103	99.93 21	99.99 16	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 52	99.07 227	99.98 12	99.99 3	99.98 14	99.90 33	99.88 9	99.92 129	99.93 21	99.99 16	99.98 5

fmvsm_s_conf0.5_n_a		99.82 23	99.79 30	99.89 11	99.85 59	99.82 38	99.03 236	99.96 27	99.99 3	99.97 22	99.84 72	99.58 39	99.93 103	99.92 24	99.98 44	99.93 20

fmvsm_s_conf0.5_n		99.83 21	99.81 26	99.87 23	99.85 59	99.78 52	99.03 236	99.96 27	99.99 3	99.97 22	99.84 72	99.78 18	99.92 129	99.92 24	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 18	100.00 1	99.92 24	100.00 1	99.87 36

MVStest1		98.22 310	98.09 305	98.62 336	99.04 364	96.23 382	99.20 176	99.92 36	99.44 152	99.98 14	99.87 53	85.87 405	99.67 374	99.91 27	99.57 289	99.95 14

v1921920		99.56 78	99.57 77	99.55 175	99.75 133	99.11 234	99.05 228	99.61 191	99.15 204	99.88 66	99.71 154	99.08 99	99.87 216	99.90 28	99.97 59	99.66 115

v1240		99.56 78	99.58 73	99.51 186	99.80 90	99.00 246	99.00 244	99.65 171	99.15 204	99.90 53	99.75 131	99.09 96	99.88 202	99.90 28	99.96 72	99.67 106

v10		99.69 48	99.69 49	99.66 123	99.81 83	99.39 182	99.66 54	99.75 114	99.60 127	99.92 47	99.87 53	98.75 145	99.86 235	99.90 28	99.99 16	99.73 77

v1192		99.57 75	99.57 77	99.57 169	99.77 117	99.22 219	99.04 233	99.60 202	99.18 193	99.87 74	99.72 146	99.08 99	99.85 253	99.89 31	99.98 44	99.66 115

fmvsm_s_conf0.5_n_3		99.79 29	99.77 37	99.85 29	99.81 83	99.71 88	98.97 253	99.92 36	99.98 15	99.97 22	99.86 60	99.53 46	99.95 67	99.88 32	99.99 16	99.89 31

v144192		99.55 81	99.54 84	99.58 163	99.78 109	99.20 224	99.11 213	99.62 184	99.18 193	99.89 57	99.72 146	98.66 158	99.87 216	99.88 32	99.97 59	99.66 115

v8		99.68 51	99.69 49	99.65 129	99.80 90	99.40 179	99.66 54	99.76 109	99.64 112	99.93 42	99.85 65	98.66 158	99.84 268	99.88 32	99.99 16	99.71 83

mvs5depth		99.88 6	99.91 3	99.80 50	99.92 29	99.42 172	99.94 3	100.00 1	99.97 20	99.89 57	99.99 12	99.63 31	99.97 36	99.87 35	99.99 16	100.00 1

v1144		99.54 84	99.53 88	99.59 160	99.79 102	99.28 205	99.10 216	99.61 191	99.20 191	99.84 81	99.73 139	98.67 156	99.84 268	99.86 36	99.98 44	99.64 133

mmtdpeth		99.78 31	99.83 21	99.66 123	99.85 59	99.05 245	99.79 12	99.97 20	100.00 1	99.43 240	99.94 19	99.64 29	99.94 83	99.83 37	99.99 16	99.98 5

SSC-MVS		99.52 87	99.42 106	99.83 35	99.86 55	99.65 113	99.52 89	99.81 86	99.87 47	99.81 93	99.79 103	96.78 293	99.99 8	99.83 37	99.51 305	99.86 38

v7n		99.82 23	99.80 29	99.88 18	99.96 7	99.84 25	99.82 9	99.82 77	99.84 59	99.94 39	99.91 28	99.13 92	99.96 57	99.83 37	99.99 16	99.83 47

v2v482		99.50 89	99.47 93	99.58 163	99.78 109	99.25 212	99.14 198	99.58 217	99.25 182	99.81 93	99.62 214	98.24 213	99.84 268	99.83 37	99.97 59	99.64 133

test_vis1_rt		99.45 108	99.46 97	99.41 221	99.71 148	98.63 286	98.99 249	99.96 27	99.03 217	99.95 36	99.12 351	98.75 145	99.84 268	99.82 41	99.82 186	99.77 67

tt0805		99.63 64	99.57 77	99.81 45	99.87 52	99.88 12	99.58 79	98.70 363	99.72 86	99.91 50	99.60 231	99.43 52	99.81 308	99.81 42	99.53 301	99.73 77

V42		99.56 78	99.54 84	99.63 143	99.79 102	99.46 158	99.39 117	99.59 208	99.24 184	99.86 75	99.70 162	98.55 172	99.82 293	99.79 43	99.95 85	99.60 163

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 49	99.72 30	99.88 53	99.92 32	99.98 14	99.93 21	99.94 4	99.98 22	99.77 44	100.00 1	99.92 24

WB-MVS		99.44 110	99.32 127	99.80 50	99.81 83	99.61 129	99.47 105	99.81 86	99.82 66	99.71 142	99.72 146	96.60 297	99.98 22	99.75 45	99.23 345	99.82 53

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 57	99.68 46	99.85 64	99.95 24	99.98 14	99.92 25	99.28 72	99.98 22	99.75 45	100.00 1	99.94 17

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 52	99.70 35	99.86 58	99.89 41	99.98 14	99.90 33	99.94 4	99.98 22	99.75 45	100.00 1	99.90 26

ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 59	100.00 1	99.90 35	100.00 1	99.97 14	99.61 35	99.97 36	99.75 45	100.00 1	99.84 43

reproduce_monomvs		97.40 342	97.46 336	97.20 389	99.05 361	91.91 417	99.20 176	99.18 336	99.84 59	99.86 75	99.75 131	80.67 412	99.83 283	99.69 49	99.95 85	99.85 41

SPE-MVS-test		99.68 51	99.70 46	99.64 136	99.57 209	99.83 30	99.78 14	99.97 20	99.92 32	99.50 225	99.38 300	99.57 41	99.95 67	99.69 49	99.90 120	99.15 311

MVS_0304		98.61 268	98.30 289	99.52 183	97.88 422	98.95 254	98.76 286	94.11 421	99.84 59	99.32 270	99.57 246	95.57 323	99.95 67	99.68 51	99.98 44	99.68 98

CS-MVS		99.67 57	99.70 46	99.58 163	99.53 231	99.84 25	99.79 12	99.96 27	99.90 35	99.61 184	99.41 290	99.51 49	99.95 67	99.66 52	99.89 130	98.96 353

mamv4		99.73 41	99.74 43	99.70 109	99.66 175	99.87 14	99.69 42	99.93 34	99.93 29	99.93 42	99.86 60	99.07 101	100.00 1	99.66 52	99.92 109	99.24 287

pmmvs6		99.86 10	99.86 13	99.83 35	99.94 18	99.90 7	99.83 7	99.91 42	99.85 56	99.94 39	99.95 16	99.73 22	99.90 169	99.65 54	99.97 59	99.69 92

MIMVSNet1		99.66 58	99.62 61	99.80 50	99.94 18	99.87 14	99.69 42	99.77 104	99.78 76	99.93 42	99.89 38	97.94 238	99.92 129	99.65 54	99.98 44	99.62 149

EC-MVSNet		99.69 48	99.69 49	99.68 113	99.71 148	99.91 4	99.76 20	99.96 27	99.86 50	99.51 223	99.39 298	99.57 41	99.93 103	99.64 56	99.86 159	99.20 300

K. test v3		98.87 245	98.60 254	99.69 111	99.93 24	99.46 158	99.74 24	94.97 416	99.78 76	99.88 66	99.88 47	93.66 344	99.97 36	99.61 57	99.95 85	99.64 133

KD-MVS_self_test		99.63 64	99.59 70	99.76 70	99.84 63	99.90 7	99.37 124	99.79 95	99.83 64	99.88 66	99.85 65	98.42 193	99.90 169	99.60 58	99.73 234	99.49 221

Anonymous20240521		99.44 110	99.42 106	99.49 192	99.89 39	98.96 253	99.62 64	99.76 109	99.85 56	99.82 86	99.88 47	96.39 307	99.97 36	99.59 59	99.98 44	99.55 185

TransMVSNet (Re)		99.78 31	99.77 37	99.81 45	99.91 31	99.85 20	99.75 22	99.86 58	99.70 93	99.91 50	99.89 38	99.60 37	99.87 216	99.59 59	99.74 228	99.71 83

OurMVSNet-221017-0		99.75 38	99.71 45	99.84 32	99.96 7	99.83 30	99.83 7	99.85 64	99.80 72	99.93 42	99.93 21	98.54 174	99.93 103	99.59 59	99.98 44	99.76 72

EU-MVSNet		99.39 126	99.62 61	98.72 332	99.88 44	96.44 376	99.56 84	99.85 64	99.90 35	99.90 53	99.85 65	98.09 227	99.83 283	99.58 62	99.95 85	99.90 26

mvs_anonymous		99.28 150	99.39 110	98.94 305	99.19 337	97.81 340	99.02 239	99.55 230	99.78 76	99.85 78	99.80 93	98.24 213	99.86 235	99.57 63	99.50 308	99.15 311

test1111		97.74 328	98.16 301	96.49 399	99.60 189	89.86 429	99.71 34	91.21 425	99.89 41	99.88 66	99.87 53	93.73 343	99.90 169	99.56 64	99.99 16	99.70 86

lessismore_v0				99.64 136	99.86 55	99.38 184		90.66 426		99.89 57	99.83 76	94.56 334	99.97 36	99.56 64	99.92 109	99.57 180

mvsany_test1		99.44 110	99.45 99	99.40 223	99.37 288	98.64 285	97.90 375	99.59 208	99.27 178	99.92 47	99.82 83	99.74 21	99.93 103	99.55 66	99.87 151	99.63 138

MVSMamba_PlusPlus		99.55 81	99.58 73	99.47 198	99.68 168	99.40 179	99.52 89	99.70 141	99.92 32	99.77 115	99.86 60	98.28 209	99.96 57	99.54 67	99.90 120	99.05 340

pm-mvs1		99.79 29	99.79 30	99.78 60	99.91 31	99.83 30	99.76 20	99.87 55	99.73 82	99.89 57	99.87 53	99.63 31	99.87 216	99.54 67	99.92 109	99.63 138

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 36	99.90 35	99.97 22	99.87 53	99.81 15	99.95 67	99.54 67	99.99 16	99.80 54
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 95	99.65 56	98.95 304	99.71 148	97.27 358	99.50 96	99.82 77	99.59 129	99.41 249	99.85 65	99.62 34	100.00 1	99.53 70	99.89 130	99.59 170

test2506		94.73 389	94.59 390	95.15 405	99.59 194	85.90 431	99.75 22	74.01 433	99.89 41	99.71 142	99.86 60	79.00 422	99.90 169	99.52 71	99.99 16	99.65 123

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 136	99.93 29	99.95 36	99.89 38	99.71 23	99.96 57	99.51 72	99.97 59	99.84 43

FC-MVSNet-test		99.70 46	99.65 56	99.86 27	99.88 44	99.86 18	99.72 30	99.78 101	99.90 35	99.82 86	99.83 76	98.45 189	99.87 216	99.51 72	99.97 59	99.86 38

BP-MVS1		98.72 260	98.46 270	99.50 188	99.53 231	99.00 246	99.34 129	98.53 373	99.65 109	99.73 135	99.38 300	90.62 379	99.96 57	99.50 74	99.86 159	99.55 185

UA-Net		99.78 31	99.76 41	99.86 27	99.72 145	99.71 88	99.91 4	99.95 32	99.96 23	99.71 142	99.91 28	99.15 87	99.97 36	99.50 74	100.00 1	99.90 26

PMMVS2		99.48 95	99.45 99	99.57 169	99.76 121	98.99 248	98.09 352	99.90 47	98.95 225	99.78 107	99.58 239	99.57 41	99.93 103	99.48 76	99.95 85	99.79 61

VPA-MVSNet		99.66 58	99.62 61	99.79 57	99.68 168	99.75 72	99.62 64	99.69 148	99.85 56	99.80 97	99.81 90	98.81 133	99.91 151	99.47 77	99.88 139	99.70 86

GDP-MVS		98.81 251	98.57 260	99.50 188	99.53 231	99.12 233	99.28 153	99.86 58	99.53 133	99.57 195	99.32 316	90.88 375	99.98 22	99.46 78	99.74 228	99.42 249

ECVR-MVS		97.73 329	98.04 308	96.78 393	99.59 194	90.81 425	99.72 30	90.43 427	99.89 41	99.86 75	99.86 60	93.60 345	99.89 188	99.46 78	99.99 16	99.65 123

nrg030		99.70 46	99.66 54	99.82 40	99.76 121	99.84 25	99.61 70	99.70 141	99.93 29	99.78 107	99.68 180	99.10 94	99.78 321	99.45 80	99.96 72	99.83 47

TAMVS		99.49 93	99.45 99	99.63 143	99.48 256	99.42 172	99.45 109	99.57 219	99.66 106	99.78 107	99.83 76	97.85 245	99.86 235	99.44 81	99.96 72	99.61 159

GeoE		99.69 48	99.66 54	99.78 60	99.76 121	99.76 64	99.60 76	99.82 77	99.46 147	99.75 123	99.56 250	99.63 31	99.95 67	99.43 82	99.88 139	99.62 149

new-patchmatchnet		99.35 136	99.57 77	98.71 334	99.82 74	96.62 373	98.55 309	99.75 114	99.50 137	99.88 66	99.87 53	99.31 68	99.88 202	99.43 82	100.00 1	99.62 149

test20.03		99.55 81	99.54 84	99.58 163	99.79 102	99.37 187	99.02 239	99.89 49	99.60 127	99.82 86	99.62 214	98.81 133	99.89 188	99.43 82	99.86 159	99.47 229

MVSFormer		99.41 120	99.44 102	99.31 250	99.57 209	98.40 300	99.77 16	99.80 89	99.73 82	99.63 169	99.30 321	98.02 232	99.98 22	99.43 82	99.69 249	99.55 185

test_djsdf		99.84 17	99.81 26	99.91 3	99.94 18	99.84 25	99.77 16	99.80 89	99.73 82	99.97 22	99.92 25	99.77 20	99.98 22	99.43 82	100.00 1	99.90 26

SDMVSNet		99.77 36	99.77 37	99.76 70	99.80 90	99.65 113	99.63 61	99.86 58	99.97 20	99.89 57	99.89 38	99.52 48	99.99 8	99.42 87	99.96 72	99.65 123

Anonymous20231211		99.62 70	99.57 77	99.76 70	99.61 187	99.60 132	99.81 10	99.73 124	99.82 66	99.90 53	99.90 33	97.97 237	99.86 235	99.42 87	99.96 72	99.80 54

SixPastTwentyTwo		99.42 116	99.30 134	99.76 70	99.92 29	99.67 105	99.70 35	99.14 341	99.65 109	99.89 57	99.90 33	96.20 314	99.94 83	99.42 87	99.92 109	99.67 106

balanced_conf03		99.50 89	99.50 90	99.50 188	99.42 279	99.49 151	99.52 89	99.75 114	99.86 50	99.78 107	99.71 154	98.20 220	99.90 169	99.39 90	99.88 139	99.10 322

patch_mono-2		99.51 88	99.46 97	99.64 136	99.70 156	99.11 234	99.04 233	99.87 55	99.71 88	99.47 230	99.79 103	98.24 213	99.98 22	99.38 91	99.96 72	99.83 47

UGNet		99.38 128	99.34 122	99.49 192	98.90 376	98.90 261	99.70 35	99.35 300	99.86 50	98.57 362	99.81 90	98.50 184	99.93 103	99.38 91	99.98 44	99.66 115
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 45	99.67 53	99.81 45	99.89 39	99.72 86	99.59 77	99.82 77	99.39 163	99.82 86	99.84 72	99.38 60	99.91 151	99.38 91	99.93 105	99.80 54

FIs		99.65 63	99.58 73	99.84 32	99.84 63	99.85 20	99.66 54	99.75 114	99.86 50	99.74 131	99.79 103	98.27 211	99.85 253	99.37 94	99.93 105	99.83 47

sd_testset		99.78 31	99.78 34	99.80 50	99.80 90	99.76 64	99.80 11	99.79 95	99.97 20	99.89 57	99.89 38	99.53 46	99.99 8	99.36 95	99.96 72	99.65 123

anonymousdsp		99.80 26	99.77 37	99.90 8	99.96 7	99.88 12	99.73 27	99.85 64	99.70 93	99.92 47	99.93 21	99.45 51	99.97 36	99.36 95	100.00 1	99.85 41

casdiffmvs_mvg		99.68 51	99.68 52	99.69 111	99.81 83	99.59 134	99.29 151	99.90 47	99.71 88	99.79 103	99.73 139	99.54 44	99.84 268	99.36 95	99.96 72	99.65 123
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 38	99.74 43	99.79 57	99.88 44	99.66 107	99.69 42	99.92 36	99.67 102	99.77 115	99.75 131	99.61 35	99.98 22	99.35 98	99.98 44	99.72 80
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 72	99.64 59	99.53 181	99.79 102	98.82 265	99.58 79	99.97 20	99.95 24	99.96 27	99.76 126	98.44 190	99.99 8	99.34 99	99.96 72	99.78 63

CHOSEN 1792x2688		99.39 126	99.30 134	99.65 129	99.88 44	99.25 212	98.78 284	99.88 53	98.66 265	99.96 27	99.79 103	97.45 267	99.93 103	99.34 99	99.99 16	99.78 63

CDS-MVSNet		99.22 169	99.13 162	99.50 188	99.35 294	99.11 234	98.96 256	99.54 236	99.46 147	99.61 184	99.70 162	96.31 310	99.83 283	99.34 99	99.88 139	99.55 185
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 225	99.16 156	98.51 342	99.75 133	95.90 388	98.07 355	99.84 70	99.84 59	99.89 57	99.73 139	96.01 317	99.99 8	99.33 102	100.00 1	99.63 138

HyFIR lowres test		98.91 238	98.64 251	99.73 94	99.85 59	99.47 154	98.07 355	99.83 72	98.64 267	99.89 57	99.60 231	92.57 354	100.00 1	99.33 102	99.97 59	99.72 80

pmmvs5		99.19 179	99.11 169	99.42 214	99.76 121	98.88 262	98.55 309	99.73 124	98.82 245	99.72 137	99.62 214	96.56 298	99.82 293	99.32 104	99.95 85	99.56 182

v148		99.40 122	99.41 108	99.39 226	99.76 121	98.94 255	99.09 220	99.59 208	99.17 198	99.81 93	99.61 223	98.41 194	99.69 357	99.32 104	99.94 98	99.53 199

baseline		99.63 64	99.62 61	99.66 123	99.80 90	99.62 123	99.44 111	99.80 89	99.71 88	99.72 137	99.69 169	99.15 87	99.83 283	99.32 104	99.94 98	99.53 199

CVMVSNet		98.61 268	98.88 231	97.80 373	99.58 199	93.60 410	99.26 159	99.64 179	99.66 106	99.72 137	99.67 184	93.26 347	99.93 103	99.30 107	99.81 196	99.87 36

PS-CasMVS		99.66 58	99.58 73	99.89 11	99.80 90	99.85 20	99.66 54	99.73 124	99.62 117	99.84 81	99.71 154	98.62 162	99.96 57	99.30 107	99.96 72	99.86 38

DTE-MVSNet		99.68 51	99.61 65	99.88 18	99.80 90	99.87 14	99.67 50	99.71 136	99.72 86	99.84 81	99.78 114	98.67 156	99.97 36	99.30 107	99.95 85	99.80 54

tmp_tt		95.75 383	95.42 377	96.76 394	89.90 432	94.42 404	98.86 267	97.87 398	78.01 423	99.30 280	99.69 169	97.70 253	95.89 425	99.29 110	98.14 401	99.95 14

PEN-MVS		99.66 58	99.59 70	99.89 11	99.83 67	99.87 14	99.66 54	99.73 124	99.70 93	99.84 81	99.73 139	98.56 171	99.96 57	99.29 110	99.94 98	99.83 47

WR-MVS_H		99.61 72	99.53 88	99.87 23	99.80 90	99.83 30	99.67 50	99.75 114	99.58 130	99.85 78	99.69 169	98.18 223	99.94 83	99.28 112	99.95 85	99.83 47

IterMVS		98.97 229	99.16 156	98.42 347	99.74 139	95.64 392	98.06 357	99.83 72	99.83 64	99.85 78	99.74 135	96.10 316	99.99 8	99.27 113	100.00 1	99.63 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WBMVS		97.50 339	97.18 345	98.48 344	98.85 383	95.89 389	98.44 325	99.52 250	99.53 133	99.52 217	99.42 289	80.10 415	99.86 235	99.24 114	99.95 85	99.68 98

h-mvs33		98.61 268	98.34 284	99.44 208	99.60 189	98.67 277	99.27 157	99.44 275	99.68 98	99.32 270	99.49 272	92.50 357	100.00 1	99.24 114	96.51 418	99.65 123

hse-mvs2		98.52 281	98.30 289	99.16 276	99.29 316	98.60 288	98.77 285	99.02 349	99.68 98	99.32 270	99.04 361	92.50 357	99.85 253	99.24 114	97.87 408	99.03 344

FMVSNet1		99.66 58	99.63 60	99.73 94	99.78 109	99.77 57	99.68 46	99.70 141	99.67 102	99.82 86	99.83 76	98.98 115	99.90 169	99.24 114	99.97 59	99.53 199

casdiffmvs		99.63 64	99.61 65	99.67 116	99.79 102	99.59 134	99.13 204	99.85 64	99.79 74	99.76 118	99.72 146	99.33 67	99.82 293	99.21 118	99.94 98	99.59 170
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 84	99.43 104	99.87 23	99.76 121	99.82 38	99.57 82	99.61 191	99.54 131	99.80 97	99.64 196	97.79 249	99.95 67	99.21 118	99.94 98	99.84 43

DELS-MVS		99.34 141	99.30 134	99.48 196	99.51 240	99.36 191	98.12 348	99.53 245	99.36 168	99.41 249	99.61 223	99.22 80	99.87 216	99.21 118	99.68 254	99.20 300
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)		99.37 131	99.26 145	99.68 113	99.51 240	99.58 138	98.98 252	99.60 202	99.43 158	99.70 146	99.36 307	97.70 253	99.88 202	99.20 121	99.87 151	99.59 170

CANet		99.11 200	99.05 190	99.28 257	98.83 385	98.56 290	98.71 292	99.41 281	99.25 182	99.23 288	99.22 339	97.66 261	99.94 83	99.19 122	99.97 59	99.33 269

EI-MVSNet-UG-set		99.48 95	99.50 90	99.42 214	99.57 209	98.65 283	99.24 166	99.46 270	99.68 98	99.80 97	99.66 189	98.99 113	99.89 188	99.19 122	99.90 120	99.72 80

xiu_mvs_v1_base_debu		99.23 161	99.34 122	98.91 311	99.59 194	98.23 309	98.47 320	99.66 161	99.61 121	99.68 152	98.94 377	99.39 56	99.97 36	99.18 124	99.55 294	98.51 390

xiu_mvs_v1_base		99.23 161	99.34 122	98.91 311	99.59 194	98.23 309	98.47 320	99.66 161	99.61 121	99.68 152	98.94 377	99.39 56	99.97 36	99.18 124	99.55 294	98.51 390

xiu_mvs_v1_base_debi		99.23 161	99.34 122	98.91 311	99.59 194	98.23 309	98.47 320	99.66 161	99.61 121	99.68 152	98.94 377	99.39 56	99.97 36	99.18 124	99.55 294	98.51 390

VPNet		99.46 104	99.37 115	99.71 105	99.82 74	99.59 134	99.48 102	99.70 141	99.81 69	99.69 149	99.58 239	97.66 261	99.86 235	99.17 127	99.44 315	99.67 106

UniMVSNet_NR-MVSNet		99.37 131	99.25 147	99.72 100	99.47 262	99.56 141	98.97 253	99.61 191	99.43 158	99.67 157	99.28 325	97.85 245	99.95 67	99.17 127	99.81 196	99.65 123

DU-MVS		99.33 144	99.21 151	99.71 105	99.43 274	99.56 141	98.83 272	99.53 245	99.38 164	99.67 157	99.36 307	97.67 257	99.95 67	99.17 127	99.81 196	99.63 138

EI-MVSNet-Vis-set		99.47 103	99.49 92	99.42 214	99.57 209	98.66 280	99.24 166	99.46 270	99.67 102	99.79 103	99.65 194	98.97 117	99.89 188	99.15 130	99.89 130	99.71 83

EI-MVSNet		99.38 128	99.44 102	99.21 270	99.58 199	98.09 323	99.26 159	99.46 270	99.62 117	99.75 123	99.67 184	98.54 174	99.85 253	99.15 130	99.92 109	99.68 98

VNet		99.18 183	99.06 186	99.56 172	99.24 327	99.36 191	99.33 133	99.31 309	99.67 102	99.47 230	99.57 246	96.48 301	99.84 268	99.15 130	99.30 334	99.47 229

EG-PatchMatch MVS		99.57 75	99.56 82	99.62 152	99.77 117	99.33 197	99.26 159	99.76 109	99.32 172	99.80 97	99.78 114	99.29 70	99.87 216	99.15 130	99.91 119	99.66 115

PVSNet_Blended_VisFu		99.40 122	99.38 112	99.44 208	99.90 37	98.66 280	98.94 259	99.91 42	97.97 328	99.79 103	99.73 139	99.05 106	99.97 36	99.15 130	99.99 16	99.68 98

IterMVS-LS		99.41 120	99.47 93	99.25 266	99.81 83	98.09 323	98.85 269	99.76 109	99.62 117	99.83 85	99.64 196	98.54 174	99.97 36	99.15 130	99.99 16	99.68 98
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 84	99.47 93	99.76 70	99.58 199	99.64 116	99.30 144	99.63 181	99.61 121	99.71 142	99.56 250	98.76 143	99.96 57	99.14 136	99.92 109	99.68 98

MVSTER		98.47 288	98.22 294	99.24 268	99.06 360	98.35 306	99.08 223	99.46 270	99.27 178	99.75 123	99.66 189	88.61 392	99.85 253	99.14 136	99.92 109	99.52 209

Anonymous20231206		99.35 136	99.31 129	99.47 198	99.74 139	99.06 244	99.28 153	99.74 120	99.23 186	99.72 137	99.53 261	97.63 263	99.88 202	99.11 138	99.84 169	99.48 225

Syy-MVS		98.17 313	97.85 325	99.15 278	98.50 408	98.79 269	98.60 298	99.21 332	97.89 334	96.76 410	96.37 433	95.47 325	99.57 398	99.10 139	98.73 379	99.09 327

ttmdpeth		99.48 95	99.55 83	99.29 254	99.76 121	98.16 317	99.33 133	99.95 32	99.79 74	99.36 259	99.89 38	99.13 92	99.77 329	99.09 140	99.64 267	99.93 20

MVS_Test		99.28 150	99.31 129	99.19 273	99.35 294	98.79 269	99.36 127	99.49 263	99.17 198	99.21 293	99.67 184	98.78 140	99.66 379	99.09 140	99.66 263	99.10 322

testgi		99.29 149	99.26 145	99.37 232	99.75 133	98.81 266	98.84 270	99.89 49	98.38 295	99.75 123	99.04 361	99.36 65	99.86 235	99.08 142	99.25 341	99.45 234

1112_ss		99.05 211	98.84 236	99.67 116	99.66 175	99.29 203	98.52 315	99.82 77	97.65 346	99.43 240	99.16 345	96.42 304	99.91 151	99.07 143	99.84 169	99.80 54

CANet_DTU		98.91 238	98.85 234	99.09 287	98.79 391	98.13 318	98.18 341	99.31 309	99.48 140	98.86 333	99.51 265	96.56 298	99.95 67	99.05 144	99.95 85	99.19 303

Baseline_NR-MVSNet		99.49 93	99.37 115	99.82 40	99.91 31	99.84 25	98.83 272	99.86 58	99.68 98	99.65 164	99.88 47	97.67 257	99.87 216	99.03 145	99.86 159	99.76 72

FMVSNet2		99.35 136	99.28 141	99.55 175	99.49 251	99.35 194	99.45 109	99.57 219	99.44 152	99.70 146	99.74 135	97.21 278	99.87 216	99.03 145	99.94 98	99.44 239

Test_1112_low_res		98.95 235	98.73 245	99.63 143	99.68 168	99.15 230	98.09 352	99.80 89	97.14 372	99.46 234	99.40 294	96.11 315	99.89 188	99.01 147	99.84 169	99.84 43

VDD-MVS		99.20 176	99.11 169	99.44 208	99.43 274	98.98 249	99.50 96	98.32 387	99.80 72	99.56 203	99.69 169	96.99 288	99.85 253	98.99 148	99.73 234	99.50 216

DeepC-MVS	98.90 4	99.62 70	99.61 65	99.67 116	99.72 145	99.44 165	99.24 166	99.71 136	99.27 178	99.93 42	99.90 33	99.70 25	99.93 103	98.99 148	99.99 16	99.64 133
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 95	99.47 93	99.51 186	99.77 117	99.41 178	98.81 277	99.66 161	99.42 162	99.75 123	99.66 189	99.20 82	99.76 332	98.98 150	99.99 16	99.36 262

EPNet_dtu		97.62 334	97.79 328	97.11 392	96.67 427	92.31 415	98.51 316	98.04 392	99.24 184	95.77 419	99.47 279	93.78 342	99.66 379	98.98 150	99.62 271	99.37 259
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 141	99.32 127	99.39 226	99.67 174	98.77 271	98.57 307	99.81 86	99.61 121	99.48 228	99.41 290	98.47 185	99.86 235	98.97 152	99.90 120	99.53 199
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		99.40 122	99.31 129	99.68 113	99.43 274	99.55 144	99.73 27	99.50 259	99.46 147	99.88 66	99.36 307	97.54 264	99.87 216	98.97 152	99.87 151	99.63 138

GBi-Net		99.42 116	99.31 129	99.73 94	99.49 251	99.77 57	99.68 46	99.70 141	99.44 152	99.62 178	99.83 76	97.21 278	99.90 169	98.96 154	99.90 120	99.53 199

FMVSNet5		97.80 326	97.25 343	99.42 214	98.83 385	98.97 251	99.38 120	99.80 89	98.87 237	99.25 284	99.69 169	80.60 414	99.91 151	98.96 154	99.90 120	99.38 256

test1		99.42 116	99.31 129	99.73 94	99.49 251	99.77 57	99.68 46	99.70 141	99.44 152	99.62 178	99.83 76	97.21 278	99.90 169	98.96 154	99.90 120	99.53 199

FMVSNet3		98.80 252	98.63 253	99.32 247	99.13 346	98.72 274	99.10 216	99.48 264	99.23 186	99.62 178	99.64 196	92.57 354	99.86 235	98.96 154	99.90 120	99.39 254

UnsupCasMVSNet_eth		98.83 248	98.57 260	99.59 160	99.68 168	99.45 163	98.99 249	99.67 156	99.48 140	99.55 208	99.36 307	94.92 328	99.86 235	98.95 158	96.57 417	99.45 234

CHOSEN 280x420		98.41 293	98.41 276	98.40 348	99.34 303	95.89 389	96.94 411	99.44 275	98.80 249	99.25 284	99.52 263	93.51 346	99.98 22	98.94 159	99.98 44	99.32 272

TDRefinement		99.72 42	99.70 46	99.77 63	99.90 37	99.85 20	99.86 6	99.92 36	99.69 96	99.78 107	99.92 25	99.37 62	99.88 202	98.93 160	99.95 85	99.60 163

alignmvs		98.28 303	97.96 314	99.25 266	99.12 348	98.93 258	99.03 236	98.42 380	99.64 112	98.72 348	97.85 413	90.86 376	99.62 389	98.88 161	99.13 347	99.19 303

MGCFI-Net		99.02 217	99.01 202	99.06 294	99.11 353	98.60 288	99.63 61	99.67 156	99.63 114	98.58 360	97.65 416	99.07 101	99.57 398	98.85 162	98.92 363	99.03 344

sss		98.90 240	98.77 244	99.27 260	99.48 256	98.44 297	98.72 290	99.32 305	97.94 332	99.37 258	99.35 312	96.31 310	99.91 151	98.85 162	99.63 270	99.47 229

xiu_mvs_v2_base		99.02 217	99.11 169	98.77 329	99.37 288	98.09 323	98.13 347	99.51 255	99.47 144	99.42 243	98.54 399	99.38 60	99.97 36	98.83 164	99.33 330	98.24 402

PS-MVSNAJ		99.00 225	99.08 180	98.76 330	99.37 288	98.10 322	98.00 363	99.51 255	99.47 144	99.41 249	98.50 401	99.28 72	99.97 36	98.83 164	99.34 329	98.20 406

D2MVS		99.22 169	99.19 153	99.29 254	99.69 160	98.74 273	98.81 277	99.41 281	98.55 276	99.68 152	99.69 169	98.13 225	99.87 216	98.82 166	99.98 44	99.24 287

PatchT		98.45 290	98.32 286	98.83 324	98.94 374	98.29 307	99.24 166	98.82 357	99.84 59	99.08 310	99.76 126	91.37 365	99.94 83	98.82 166	99.00 358	98.26 401

testf1		99.63 64	99.60 68	99.72 100	99.94 18	99.95 2	99.47 105	99.89 49	99.43 158	99.88 66	99.80 93	99.26 76	99.90 169	98.81 168	99.88 139	99.32 272

APD_test2		99.63 64	99.60 68	99.72 100	99.94 18	99.95 2	99.47 105	99.89 49	99.43 158	99.88 66	99.80 93	99.26 76	99.90 169	98.81 168	99.88 139	99.32 272

sasdasda		99.02 217	99.00 206	99.09 287	99.10 355	98.70 275	99.61 70	99.66 161	99.63 114	98.64 354	97.65 416	99.04 107	99.54 402	98.79 170	98.92 363	99.04 342

Effi-MVS+		99.06 208	98.97 217	99.34 239	99.31 310	98.98 249	98.31 333	99.91 42	98.81 247	98.79 342	98.94 377	99.14 90	99.84 268	98.79 170	98.74 376	99.20 300

canonicalmvs		99.02 217	99.00 206	99.09 287	99.10 355	98.70 275	99.61 70	99.66 161	99.63 114	98.64 354	97.65 416	99.04 107	99.54 402	98.79 170	98.92 363	99.04 342

VDDNet		98.97 229	98.82 239	99.42 214	99.71 148	98.81 266	99.62 64	98.68 364	99.81 69	99.38 257	99.80 93	94.25 336	99.85 253	98.79 170	99.32 332	99.59 170

CR-MVSNet		98.35 300	98.20 296	98.83 324	99.05 361	98.12 319	99.30 144	99.67 156	97.39 360	99.16 299	99.79 103	91.87 362	99.91 151	98.78 174	98.77 372	98.44 395

test_method		91.72 390	92.32 393	89.91 408	93.49 431	70.18 434	90.28 422	99.56 224	61.71 426	95.39 421	99.52 263	93.90 338	99.94 83	98.76 175	98.27 394	99.62 149

RPMNet		98.60 271	98.53 266	98.83 324	99.05 361	98.12 319	99.30 144	99.62 184	99.86 50	99.16 299	99.74 135	92.53 356	99.92 129	98.75 176	98.77 372	98.44 395

pmmvs4		99.13 195	99.06 186	99.36 236	99.57 209	99.10 239	98.01 361	99.25 322	98.78 252	99.58 192	99.44 286	98.24 213	99.76 332	98.74 177	99.93 105	99.22 293

tttt0517		97.62 334	97.20 344	98.90 317	99.76 121	97.40 355	99.48 102	94.36 418	99.06 215	99.70 146	99.49 272	84.55 408	99.94 83	98.73 178	99.65 265	99.36 262

EPP-MVSNet		99.17 188	99.00 206	99.66 123	99.80 90	99.43 169	99.70 35	99.24 325	99.48 140	99.56 203	99.77 123	94.89 329	99.93 103	98.72 179	99.89 130	99.63 138

Anonymous20240529		99.42 116	99.34 122	99.65 129	99.53 231	99.60 132	99.63 61	99.39 291	99.47 144	99.76 118	99.78 114	98.13 225	99.86 235	98.70 180	99.68 254	99.49 221

ACMH	98.42 6	99.59 74	99.54 84	99.72 100	99.86 55	99.62 123	99.56 84	99.79 95	98.77 254	99.80 97	99.85 65	99.64 29	99.85 253	98.70 180	99.89 130	99.70 86
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 144	99.28 141	99.47 198	99.57 209	99.39 182	99.78 14	99.43 278	98.87 237	99.57 195	99.82 83	98.06 230	99.87 216	98.69 182	99.73 234	99.15 311

LFMVS		98.46 289	98.19 299	99.26 263	99.24 327	98.52 293	99.62 64	96.94 408	99.87 47	99.31 275	99.58 239	91.04 370	99.81 308	98.68 183	99.42 319	99.45 234

WR-MVS		99.11 200	98.93 222	99.66 123	99.30 314	99.42 172	98.42 326	99.37 296	99.04 216	99.57 195	99.20 343	96.89 290	99.86 235	98.66 184	99.87 151	99.70 86

mvsmamba		99.08 204	98.95 220	99.45 204	99.36 291	99.18 227	99.39 117	98.81 358	99.37 165	99.35 261	99.70 162	96.36 309	99.94 83	98.66 184	99.59 285	99.22 293

RRT-MVS		99.08 204	99.00 206	99.33 242	99.27 321	98.65 283	99.62 64	99.93 34	99.66 106	99.67 157	99.82 83	95.27 327	99.93 103	98.64 186	99.09 351	99.41 250

Anonymous202405211		98.75 256	98.46 270	99.63 143	99.34 303	99.66 107	99.47 105	97.65 400	99.28 177	99.56 203	99.50 268	93.15 348	99.84 268	98.62 187	99.58 287	99.40 252

EPNet		98.13 314	97.77 329	99.18 275	94.57 430	97.99 329	99.24 166	97.96 394	99.74 81	97.29 403	99.62 214	93.13 349	99.97 36	98.59 188	99.83 177	99.58 175
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 211	99.09 178	98.91 311	99.21 332	98.36 305	98.82 276	99.47 267	98.85 240	98.90 328	99.56 250	98.78 140	99.09 417	98.57 189	99.68 254	99.26 284

Patchmatch-RL test		98.60 271	98.36 281	99.33 242	99.77 117	99.07 242	98.27 335	99.87 55	98.91 232	99.74 131	99.72 146	90.57 381	99.79 318	98.55 190	99.85 164	99.11 320

pmmvs3		98.08 317	97.80 326	98.91 311	99.41 281	97.69 346	97.87 376	99.66 161	95.87 391	99.50 225	99.51 265	90.35 383	99.97 36	98.55 190	99.47 312	99.08 333

ETV-MVS		99.18 183	99.18 154	99.16 276	99.34 303	99.28 205	99.12 208	99.79 95	99.48 140	98.93 322	98.55 398	99.40 55	99.93 103	98.51 192	99.52 304	98.28 400

jason		99.16 189	99.11 169	99.32 247	99.75 133	98.44 297	98.26 337	99.39 291	98.70 262	99.74 131	99.30 321	98.54 174	99.97 36	98.48 193	99.82 186	99.55 185
jason: jason.
APDe-MVS		99.48 95	99.36 118	99.85 29	99.55 223	99.81 43	99.50 96	99.69 148	98.99 219	99.75 123	99.71 154	98.79 138	99.93 103	98.46 194	99.85 164	99.80 54
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CL-MVSNet_self_test		98.71 262	98.56 264	99.15 278	99.22 330	98.66 280	97.14 406	99.51 255	98.09 321	99.54 210	99.27 327	96.87 291	99.74 339	98.43 195	98.96 360	99.03 344

our_test_3		98.85 247	99.09 178	98.13 361	99.66 175	94.90 402	97.72 381	99.58 217	99.07 213	99.64 165	99.62 214	98.19 221	99.93 103	98.41 196	99.95 85	99.55 185

Gipuma		99.57 75	99.59 70	99.49 192	99.98 3	99.71 88	99.72 30	99.84 70	99.81 69	99.94 39	99.78 114	98.91 125	99.71 348	98.41 196	99.95 85	99.05 340
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 344	96.91 354	98.74 331	97.72 423	97.57 348	97.60 387	97.36 406	98.00 324	99.21 293	98.02 409	90.04 386	99.79 318	98.37 198	95.89 422	98.86 367

PM-MVS		99.36 134	99.29 139	99.58 163	99.83 67	99.66 107	98.95 257	99.86 58	98.85 240	99.81 93	99.73 139	98.40 198	99.92 129	98.36 199	99.83 177	99.17 307

baseline1		97.73 329	97.33 340	98.96 302	99.30 314	97.73 344	99.40 115	98.42 380	99.33 171	99.46 234	99.21 341	91.18 368	99.82 293	98.35 200	91.26 425	99.32 272

MVS-HIRNet		97.86 323	98.22 294	96.76 394	99.28 319	91.53 421	98.38 328	92.60 424	99.13 206	99.31 275	99.96 15	97.18 282	99.68 369	98.34 201	99.83 177	99.07 338

GA-MVS		97.99 322	97.68 332	98.93 308	99.52 238	98.04 327	97.19 405	99.05 348	98.32 308	98.81 338	98.97 373	89.89 388	99.41 413	98.33 202	99.05 354	99.34 268

Fast-Effi-MVS+		99.02 217	98.87 232	99.46 201	99.38 286	99.50 150	99.04 233	99.79 95	97.17 370	98.62 356	98.74 390	99.34 66	99.95 67	98.32 203	99.41 320	98.92 360

MDA-MVSNet_test_wron		98.95 235	98.99 213	98.85 320	99.64 180	97.16 361	98.23 339	99.33 303	98.93 229	99.56 203	99.66 189	97.39 271	99.83 283	98.29 204	99.88 139	99.55 185

N_pmnet		98.73 259	98.53 266	99.35 238	99.72 145	98.67 277	98.34 330	94.65 417	98.35 302	99.79 103	99.68 180	98.03 231	99.93 103	98.28 205	99.92 109	99.44 239

ET-MVSNet_ETH3D		96.78 356	96.07 365	98.91 311	99.26 324	97.92 336	97.70 383	96.05 413	97.96 331	92.37 425	98.43 402	87.06 396	99.90 169	98.27 206	97.56 411	98.91 361

thisisatest0530		97.45 340	96.95 351	98.94 305	99.68 168	97.73 344	99.09 220	94.19 420	98.61 272	99.56 203	99.30 321	84.30 409	99.93 103	98.27 206	99.54 299	99.16 309

YYNet1		98.95 235	98.99 213	98.84 322	99.64 180	97.14 363	98.22 340	99.32 305	98.92 231	99.59 190	99.66 189	97.40 269	99.83 283	98.27 206	99.90 120	99.55 185

reproduce_model		99.50 89	99.40 109	99.83 35	99.60 189	99.83 30	99.12 208	99.68 151	99.49 139	99.80 97	99.79 103	99.01 110	99.93 103	98.24 209	99.82 186	99.73 77

ACMM	98.09 11	99.46 104	99.38 112	99.72 100	99.80 90	99.69 100	99.13 204	99.65 171	98.99 219	99.64 165	99.72 146	99.39 56	99.86 235	98.23 210	99.81 196	99.60 163
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 232	98.87 232	99.24 268	99.57 209	98.40 300	98.12 348	99.18 336	98.28 310	99.63 169	99.13 347	98.02 232	99.97 36	98.22 211	99.69 249	99.35 265

3Dnovator	99.15 2	99.43 113	99.36 118	99.65 129	99.39 283	99.42 172	99.70 35	99.56 224	99.23 186	99.35 261	99.80 93	99.17 85	99.95 67	98.21 212	99.84 169	99.59 170

Fast-Effi-MVS+-dtu		99.20 176	99.12 166	99.43 212	99.25 325	99.69 100	99.05 228	99.82 77	99.50 137	98.97 318	99.05 359	98.98 115	99.98 22	98.20 213	99.24 343	98.62 381

MS-PatchMatch		99.00 225	98.97 217	99.09 287	99.11 353	98.19 313	98.76 286	99.33 303	98.49 285	99.44 236	99.58 239	98.21 218	99.69 357	98.20 213	99.62 271	99.39 254

TSAR-MVS + GP.		99.12 197	99.04 196	99.38 229	99.34 303	99.16 228	98.15 344	99.29 313	98.18 317	99.63 169	99.62 214	99.18 84	99.68 369	98.20 213	99.74 228	99.30 278

DP-MVS		99.48 95	99.39 110	99.74 85	99.57 209	99.62 123	99.29 151	99.61 191	99.87 47	99.74 131	99.76 126	98.69 152	99.87 216	98.20 213	99.80 203	99.75 75

MVP-Stereo		99.16 189	99.08 180	99.43 212	99.48 256	99.07 242	99.08 223	99.55 230	98.63 268	99.31 275	99.68 180	98.19 221	99.78 321	98.18 217	99.58 287	99.45 234
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 113	99.30 134	99.80 50	99.83 67	99.81 43	99.52 89	99.70 141	98.35 302	99.51 223	99.50 268	99.31 68	99.88 202	98.18 217	99.84 169	99.69 92

MDA-MVSNet-bldmvs		99.06 208	99.05 190	99.07 292	99.80 90	97.83 339	98.89 263	99.72 133	99.29 174	99.63 169	99.70 162	96.47 302	99.89 188	98.17 219	99.82 186	99.50 216

JIA-IIPM		98.06 318	97.92 321	98.50 343	98.59 404	97.02 365	98.80 280	98.51 375	99.88 46	97.89 390	99.87 53	91.89 361	99.90 169	98.16 220	97.68 410	98.59 384

EIA-MVS		99.12 197	99.01 202	99.45 204	99.36 291	99.62 123	99.34 129	99.79 95	98.41 291	98.84 335	98.89 381	98.75 145	99.84 268	98.15 221	99.51 305	98.89 364

miper_lstm_enhance		98.65 267	98.60 254	98.82 327	99.20 335	97.33 357	97.78 379	99.66 161	99.01 218	99.59 190	99.50 268	94.62 333	99.85 253	98.12 222	99.90 120	99.26 284

reproduce-ours		99.46 104	99.35 120	99.82 40	99.56 220	99.83 30	99.05 228	99.65 171	99.45 150	99.78 107	99.78 114	98.93 120	99.93 103	98.11 223	99.81 196	99.70 86

our_new_method		99.46 104	99.35 120	99.82 40	99.56 220	99.83 30	99.05 228	99.65 171	99.45 150	99.78 107	99.78 114	98.93 120	99.93 103	98.11 223	99.81 196	99.70 86

Effi-MVS+-dtu		99.07 207	98.92 226	99.52 183	98.89 379	99.78 52	99.15 196	99.66 161	99.34 169	98.92 325	99.24 337	97.69 255	99.98 22	98.11 223	99.28 337	98.81 371

tpm		97.15 348	96.95 351	97.75 375	98.91 375	94.24 405	99.32 136	97.96 394	97.71 344	98.29 372	99.32 316	86.72 402	99.92 129	98.10 226	96.24 420	99.09 327

DeepPCF-MVS	98.42 6	99.18 183	99.02 199	99.67 116	99.22 330	99.75 72	97.25 403	99.47 267	98.72 259	99.66 162	99.70 162	99.29 70	99.63 388	98.07 227	99.81 196	99.62 149

ppachtmachnet_test		98.89 243	99.12 166	98.20 359	99.66 175	95.24 398	97.63 385	99.68 151	99.08 211	99.78 107	99.62 214	98.65 160	99.88 202	98.02 228	99.96 72	99.48 225

tpmrst		97.73 329	98.07 307	96.73 396	98.71 400	92.00 416	99.10 216	98.86 354	98.52 281	98.92 325	99.54 259	91.90 360	99.82 293	98.02 228	99.03 356	98.37 397

CSCG		99.37 131	99.29 139	99.60 158	99.71 148	99.46 158	99.43 113	99.85 64	98.79 250	99.41 249	99.60 231	98.92 123	99.92 129	98.02 228	99.92 109	99.43 245

eth_miper_zixun_eth		98.68 265	98.71 247	98.60 338	99.10 355	96.84 370	97.52 393	99.54 236	98.94 226	99.58 192	99.48 275	96.25 313	99.76 332	98.01 231	99.93 105	99.21 296

Patchmtry		98.78 253	98.54 265	99.49 192	98.89 379	99.19 225	99.32 136	99.67 156	99.65 109	99.72 137	99.79 103	91.87 362	99.95 67	98.00 232	99.97 59	99.33 269

PVSNet_BlendedMVS		99.03 215	99.01 202	99.09 287	99.54 225	97.99 329	98.58 303	99.82 77	97.62 347	99.34 265	99.71 154	98.52 181	99.77 329	97.98 233	99.97 59	99.52 209

PVSNet_Blended		98.70 263	98.59 256	99.02 297	99.54 225	97.99 329	97.58 388	99.82 77	95.70 395	99.34 265	98.98 371	98.52 181	99.77 329	97.98 233	99.83 177	99.30 278

cl____		98.54 279	98.41 276	98.92 309	99.03 365	97.80 342	97.46 395	99.59 208	98.90 233	99.60 187	99.46 282	93.85 340	99.78 321	97.97 235	99.89 130	99.17 307

DIV-MVS_self_test		98.54 279	98.42 275	98.92 309	99.03 365	97.80 342	97.46 395	99.59 208	98.90 233	99.60 187	99.46 282	93.87 339	99.78 321	97.97 235	99.89 130	99.18 305

AUN-MVS		97.82 325	97.38 339	99.14 281	99.27 321	98.53 291	98.72 290	99.02 349	98.10 319	97.18 406	99.03 365	89.26 390	99.85 253	97.94 237	97.91 406	99.03 344

FA-MVS(test-final)		98.52 281	98.32 286	99.10 286	99.48 256	98.67 277	99.77 16	98.60 371	97.35 362	99.63 169	99.80 93	93.07 350	99.84 268	97.92 238	99.30 334	98.78 374

ambc				99.20 272	99.35 294	98.53 291	99.17 188	99.46 270		99.67 157	99.80 93	98.46 188	99.70 351	97.92 238	99.70 245	99.38 256

USDC		98.96 232	98.93 222	99.05 295	99.54 225	97.99 329	97.07 409	99.80 89	98.21 314	99.75 123	99.77 123	98.43 191	99.64 387	97.90 240	99.88 139	99.51 211

OPM-MVS		99.26 156	99.13 162	99.63 143	99.70 156	99.61 129	98.58 303	99.48 264	98.50 283	99.52 217	99.63 207	99.14 90	99.76 332	97.89 241	99.77 217	99.51 211
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 146	99.17 155	99.77 63	99.69 160	99.80 47	99.14 198	99.31 309	99.16 200	99.62 178	99.61 223	98.35 202	99.91 151	97.88 242	99.72 240	99.61 159
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 35	99.70 156	99.79 49	99.14 198	99.61 191					99.92 129	97.88 242	99.72 240	99.77 67

c3_l		98.72 260	98.71 247	98.72 332	99.12 348	97.22 360	97.68 384	99.56 224	98.90 233	99.54 210	99.48 275	96.37 308	99.73 342	97.88 242	99.88 139	99.21 296

3Dnovator+	98.92 3	99.35 136	99.24 149	99.67 116	99.35 294	99.47 154	99.62 64	99.50 259	99.44 152	99.12 306	99.78 114	98.77 142	99.94 83	97.87 245	99.72 240	99.62 149

miper_ehance_all_eth		98.59 274	98.59 256	98.59 339	98.98 371	97.07 364	97.49 394	99.52 250	98.50 283	99.52 217	99.37 303	96.41 306	99.71 348	97.86 246	99.62 271	99.00 351

WTY-MVS		98.59 274	98.37 280	99.26 263	99.43 274	98.40 300	98.74 288	99.13 343	98.10 319	99.21 293	99.24 337	94.82 330	99.90 169	97.86 246	98.77 372	99.49 221

APD_test1		99.36 134	99.28 141	99.61 155	99.89 39	99.89 10	99.32 136	99.74 120	99.18 193	99.69 149	99.75 131	98.41 194	99.84 268	97.85 248	99.70 245	99.10 322

SED-MVS		99.40 122	99.28 141	99.77 63	99.69 160	99.82 38	99.20 176	99.54 236	99.13 206	99.82 86	99.63 207	98.91 125	99.92 129	97.85 248	99.70 245	99.58 175

test_241102_TWO								99.54 236	99.13 206	99.76 118	99.63 207	98.32 207	99.92 129	97.85 248	99.69 249	99.75 75

MVS_111021_HR		99.12 197	99.02 199	99.40 223	99.50 246	99.11 234	97.92 372	99.71 136	98.76 257	99.08 310	99.47 279	99.17 85	99.54 402	97.85 248	99.76 219	99.54 194

MTAPA		99.35 136	99.20 152	99.80 50	99.81 83	99.81 43	99.33 133	99.53 245	99.27 178	99.42 243	99.63 207	98.21 218	99.95 67	97.83 252	99.79 208	99.65 123

MSC_two_6792asdad				99.74 85	99.03 365	99.53 147		99.23 326					99.92 129	97.77 253	99.69 249	99.78 63

No_MVS				99.74 85	99.03 365	99.53 147		99.23 326					99.92 129	97.77 253	99.69 249	99.78 63

TESTMET0.1,1		96.24 370	95.84 371	97.41 383	98.24 415	93.84 408	97.38 397	95.84 414	98.43 288	97.81 395	98.56 397	79.77 418	99.89 188	97.77 253	98.77 372	98.52 389

ACMH+	98.40 8	99.50 89	99.43 104	99.71 105	99.86 55	99.76 64	99.32 136	99.77 104	99.53 133	99.77 115	99.76 126	99.26 76	99.78 321	97.77 253	99.88 139	99.60 163

IU-MVS					99.69 160	99.77 57		99.22 329	97.50 354	99.69 149				97.75 257	99.70 245	99.77 67

114514_t		98.49 286	98.11 304	99.64 136	99.73 142	99.58 138	99.24 166	99.76 109	89.94 418	99.42 243	99.56 250	97.76 252	99.86 235	97.74 258	99.82 186	99.47 229

DVP-MVS++		99.38 128	99.25 147	99.77 63	99.03 365	99.77 57	99.74 24	99.61 191	99.18 193	99.76 118	99.61 223	99.00 111	99.92 129	97.72 259	99.60 281	99.62 149

test_0728_THIRD									99.18 193	99.62 178	99.61 223	98.58 168	99.91 151	97.72 259	99.80 203	99.77 67

EGC-MVSNET		89.05 392	85.52 395	99.64 136	99.89 39	99.78 52	99.56 84	99.52 250	24.19 427	49.96 428	99.83 76	99.15 87	99.92 129	97.71 261	99.85 164	99.21 296

miper_enhance_ethall		98.03 319	97.94 319	98.32 353	98.27 414	96.43 377	96.95 410	99.41 281	96.37 386	99.43 240	98.96 375	94.74 331	99.69 357	97.71 261	99.62 271	98.83 370

TSAR-MVS + MP.		99.34 141	99.24 149	99.63 143	99.82 74	99.37 187	99.26 159	99.35 300	98.77 254	99.57 195	99.70 162	99.27 75	99.88 202	97.71 261	99.75 221	99.65 123
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 337	97.28 341	98.40 348	98.37 412	96.75 371	97.24 404	99.37 296	97.31 364	99.41 249	99.22 339	87.30 394	99.37 414	97.70 264	99.62 271	99.08 333

MP-MVS-pluss		99.14 193	98.92 226	99.80 50	99.83 67	99.83 30	98.61 296	99.63 181	96.84 379	99.44 236	99.58 239	98.81 133	99.91 151	97.70 264	99.82 186	99.67 106
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 150	99.11 169	99.79 57	99.75 133	99.81 43	98.95 257	99.53 245	98.27 311	99.53 215	99.73 139	98.75 145	99.87 216	97.70 264	99.83 177	99.68 98

UnsupCasMVSNet_bld		98.55 278	98.27 292	99.40 223	99.56 220	99.37 187	97.97 368	99.68 151	97.49 355	99.08 310	99.35 312	95.41 326	99.82 293	97.70 264	98.19 398	99.01 350

MVS_111021_LR		99.13 195	99.03 198	99.42 214	99.58 199	99.32 199	97.91 374	99.73 124	98.68 263	99.31 275	99.48 275	99.09 96	99.66 379	97.70 264	99.77 217	99.29 281

IS-MVSNet		99.03 215	98.85 234	99.55 175	99.80 90	99.25 212	99.73 27	99.15 340	99.37 165	99.61 184	99.71 154	94.73 332	99.81 308	97.70 264	99.88 139	99.58 175

test-LLR		97.15 348	96.95 351	97.74 376	98.18 417	95.02 400	97.38 397	96.10 410	98.00 324	97.81 395	98.58 394	90.04 386	99.91 151	97.69 270	98.78 370	98.31 398

test-mter		96.23 371	95.73 373	97.74 376	98.18 417	95.02 400	97.38 397	96.10 410	97.90 333	97.81 395	98.58 394	79.12 421	99.91 151	97.69 270	98.78 370	98.31 398

MonoMVSNet		98.23 308	98.32 286	97.99 364	98.97 372	96.62 373	99.49 100	98.42 380	99.62 117	99.40 254	99.79 103	95.51 324	98.58 423	97.68 272	95.98 421	98.76 377

XVS		99.27 154	99.11 169	99.75 80	99.71 148	99.71 88	99.37 124	99.61 191	99.29 174	98.76 345	99.47 279	98.47 185	99.88 202	97.62 273	99.73 234	99.67 106

X-MVStestdata		96.09 374	94.87 386	99.75 80	99.71 148	99.71 88	99.37 124	99.61 191	99.29 174	98.76 345	61.30 436	98.47 185	99.88 202	97.62 273	99.73 234	99.67 106

SMA-MVS		99.19 179	99.00 206	99.73 94	99.46 266	99.73 81	99.13 204	99.52 250	97.40 359	99.57 195	99.64 196	98.93 120	99.83 283	97.61 275	99.79 208	99.63 138
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		96.71 359	96.79 358	96.46 400	98.90 376	90.71 426	99.41 114	98.68 364	94.69 408	98.14 382	99.34 315	86.32 404	99.80 315	97.60 276	98.07 404	98.88 365

PVSNet	97.47 15	98.42 292	98.44 273	98.35 350	99.46 266	96.26 381	96.70 414	99.34 302	97.68 345	99.00 317	99.13 347	97.40 269	99.72 344	97.59 277	99.68 254	99.08 333

new_pmnet		98.88 244	98.89 230	98.84 322	99.70 156	97.62 347	98.15 344	99.50 259	97.98 327	99.62 178	99.54 259	98.15 224	99.94 83	97.55 278	99.84 169	98.95 355

IB-MVS	95.41 20	95.30 388	94.46 392	97.84 372	98.76 396	95.33 396	97.33 400	96.07 412	96.02 390	95.37 422	97.41 420	76.17 423	99.96 57	97.54 279	95.44 424	98.22 403
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		99.24 160	99.11 169	99.61 155	98.38 411	99.79 49	99.57 82	99.68 151	99.61 121	99.15 301	99.71 154	98.70 151	99.91 151	97.54 279	99.68 254	99.13 319

ZNCC-MVS		99.22 169	99.04 196	99.77 63	99.76 121	99.73 81	99.28 153	99.56 224	98.19 316	99.14 303	99.29 324	98.84 132	99.92 129	97.53 281	99.80 203	99.64 133

CP-MVS		99.23 161	99.05 190	99.75 80	99.66 175	99.66 107	99.38 120	99.62 184	98.38 295	99.06 314	99.27 327	98.79 138	99.94 83	97.51 282	99.82 186	99.66 115

SD-MVS		99.01 223	99.30 134	98.15 360	99.50 246	99.40 179	98.94 259	99.61 191	99.22 190	99.75 123	99.82 83	99.54 44	95.51 427	97.48 283	99.87 151	99.54 194
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		98.49 286	98.29 291	99.11 284	98.96 373	98.42 299	97.54 389	99.32 305	97.53 352	98.47 367	98.15 408	97.88 242	99.82 293	97.46 284	99.24 343	99.09 327

DeepC-MVS_fast	98.47 5	99.23 161	99.12 166	99.56 172	99.28 319	99.22 219	98.99 249	99.40 288	99.08 211	99.58 192	99.64 196	98.90 128	99.83 283	97.44 285	99.75 221	99.63 138
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 157	99.08 180	99.76 70	99.73 142	99.70 96	99.31 141	99.59 208	98.36 297	99.36 259	99.37 303	98.80 137	99.91 151	97.43 286	99.75 221	99.68 98

ACMMPR		99.23 161	99.06 186	99.76 70	99.74 139	99.69 100	99.31 141	99.59 208	98.36 297	99.35 261	99.38 300	98.61 164	99.93 103	97.43 286	99.75 221	99.67 106

Vis-MVSNet (Re-imp)		98.77 254	98.58 259	99.34 239	99.78 109	98.88 262	99.61 70	99.56 224	99.11 210	99.24 287	99.56 250	93.00 352	99.78 321	97.43 286	99.89 130	99.35 265

MIMVSNet		98.43 291	98.20 296	99.11 284	99.53 231	98.38 304	99.58 79	98.61 369	98.96 223	99.33 267	99.76 126	90.92 372	99.81 308	97.38 289	99.76 219	99.15 311

WB-MVSnew		98.34 302	98.14 302	98.96 302	98.14 420	97.90 337	98.27 335	97.26 407	98.63 268	98.80 340	98.00 411	97.77 250	99.90 169	97.37 290	98.98 359	99.09 327

XVG-OURS-SEG-HR		99.16 189	98.99 213	99.66 123	99.84 63	99.64 116	98.25 338	99.73 124	98.39 294	99.63 169	99.43 287	99.70 25	99.90 169	97.34 291	98.64 383	99.44 239

COLMAP_ROB	98.06 12	99.45 108	99.37 115	99.70 109	99.83 67	99.70 96	99.38 120	99.78 101	99.53 133	99.67 157	99.78 114	99.19 83	99.86 235	97.32 292	99.87 151	99.55 185
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 217	98.81 240	99.65 129	99.58 199	99.49 151	98.58 303	99.07 345	98.40 293	99.04 315	99.25 332	98.51 183	99.80 315	97.31 293	99.51 305	99.65 123

region2R		99.23 161	99.05 190	99.77 63	99.76 121	99.70 96	99.31 141	99.59 208	98.41 291	99.32 270	99.36 307	98.73 149	99.93 103	97.29 294	99.74 228	99.67 106

APD-MVS_3200maxsize		99.31 147	99.16 156	99.74 85	99.53 231	99.75 72	99.27 157	99.61 191	99.19 192	99.57 195	99.64 196	98.76 143	99.90 169	97.29 294	99.62 271	99.56 182

TAPA-MVS	97.92 13	98.03 319	97.55 335	99.46 201	99.47 262	99.44 165	98.50 317	99.62 184	86.79 419	99.07 313	99.26 330	98.26 212	99.62 389	97.28 296	99.73 234	99.31 276
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 154	99.11 169	99.73 94	99.54 225	99.74 78	99.26 159	99.62 184	99.16 200	99.52 217	99.64 196	98.41 194	99.91 151	97.27 297	99.61 278	99.54 194

RE-MVS-def			99.13 162		99.54 225	99.74 78	99.26 159	99.62 184	99.16 200	99.52 217	99.64 196	98.57 169		97.27 297	99.61 278	99.54 194

testing11		96.05 376	95.41 378	97.97 366	98.78 393	95.27 397	98.59 301	98.23 389	98.86 239	96.56 413	96.91 426	75.20 424	99.69 357	97.26 299	98.29 393	98.93 358

test_yl		98.25 305	97.95 315	99.13 282	99.17 341	98.47 294	99.00 244	98.67 366	98.97 221	99.22 291	99.02 366	91.31 366	99.69 357	97.26 299	98.93 361	99.24 287

DCV-MVSNet		98.25 305	97.95 315	99.13 282	99.17 341	98.47 294	99.00 244	98.67 366	98.97 221	99.22 291	99.02 366	91.31 366	99.69 357	97.26 299	98.93 361	99.24 287

PHI-MVS		99.11 200	98.95 220	99.59 160	99.13 346	99.59 134	99.17 188	99.65 171	97.88 336	99.25 284	99.46 282	98.97 117	99.80 315	97.26 299	99.82 186	99.37 259

tfpnnormal		99.43 113	99.38 112	99.60 158	99.87 52	99.75 72	99.59 77	99.78 101	99.71 88	99.90 53	99.69 169	98.85 131	99.90 169	97.25 303	99.78 213	99.15 311

PatchmatchNet		97.65 333	97.80 326	97.18 390	98.82 388	92.49 414	99.17 188	98.39 383	98.12 318	98.79 342	99.58 239	90.71 378	99.89 188	97.23 304	99.41 320	99.16 309
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 228	98.80 242	99.56 172	99.25 325	99.43 169	98.54 312	99.27 317	98.58 274	98.80 340	99.43 287	98.53 178	99.70 351	97.22 305	99.59 285	99.54 194

testing3		96.48 364	95.63 375	99.01 298	99.23 329	97.81 340	98.90 262	99.10 344	98.72 259	97.84 394	97.92 412	72.44 428	99.85 253	97.21 306	99.33 330	99.35 265

HPM-MVS		99.25 157	99.07 184	99.78 60	99.81 83	99.75 72	99.61 70	99.67 156	97.72 343	99.35 261	99.25 332	99.23 79	99.92 129	97.21 306	99.82 186	99.67 106
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 179	99.00 206	99.76 70	99.76 121	99.68 103	99.38 120	99.54 236	98.34 306	99.01 316	99.50 268	98.53 178	99.93 103	97.18 308	99.78 213	99.66 115

ACMMP		99.25 157	99.08 180	99.74 85	99.79 102	99.68 103	99.50 96	99.65 171	98.07 322	99.52 217	99.69 169	98.57 169	99.92 129	97.18 308	99.79 208	99.63 138
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		96.98 352	96.42 359	98.66 335	99.42 279	97.47 351	97.27 402	94.30 419	97.24 366	99.15 301	98.86 383	85.01 406	99.87 216	97.10 310	99.39 322	98.63 380

XVG-ACMP-BASELINE		99.23 161	99.10 177	99.63 143	99.82 74	99.58 138	98.83 272	99.72 133	98.36 297	99.60 187	99.71 154	98.92 123	99.91 151	97.08 311	99.84 169	99.40 252

MSDG		99.08 204	98.98 216	99.37 232	99.60 189	99.13 231	97.54 389	99.74 120	98.84 243	99.53 215	99.55 257	99.10 94	99.79 318	97.07 312	99.86 159	99.18 305

SteuartSystems-ACMMP		99.30 148	99.14 160	99.76 70	99.87 52	99.66 107	99.18 183	99.60 202	98.55 276	99.57 195	99.67 184	99.03 109	99.94 83	97.01 313	99.80 203	99.69 92
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 372	95.78 372	97.49 379	98.53 406	93.83 409	98.04 358	93.94 422	98.96 223	98.46 368	98.17 407	79.86 416	99.87 216	96.99 314	99.06 352	98.78 374

EPMVS		96.53 362	96.32 360	97.17 391	98.18 417	92.97 413	99.39 117	89.95 428	98.21 314	98.61 357	99.59 236	86.69 403	99.72 344	96.99 314	99.23 345	98.81 371

MSP-MVS		99.04 214	98.79 243	99.81 45	99.78 109	99.73 81	99.35 128	99.57 219	98.54 279	99.54 210	98.99 368	96.81 292	99.93 103	96.97 316	99.53 301	99.77 67
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++		98.96 232	98.70 249	99.74 85	99.52 238	99.71 88	98.86 267	99.19 335	98.47 287	98.59 359	99.06 358	98.08 229	99.91 151	96.94 317	99.60 281	99.60 163

SR-MVS		99.19 179	99.00 206	99.74 85	99.51 240	99.72 86	99.18 183	99.60 202	98.85 240	99.47 230	99.58 239	98.38 199	99.92 129	96.92 318	99.54 299	99.57 180

PGM-MVS		99.20 176	99.01 202	99.77 63	99.75 133	99.71 88	99.16 194	99.72 133	97.99 326	99.42 243	99.60 231	98.81 133	99.93 103	96.91 319	99.74 228	99.66 115

HY-MVS	98.23 9	98.21 312	97.95 315	98.99 299	99.03 365	98.24 308	99.61 70	98.72 362	96.81 380	98.73 347	99.51 265	94.06 337	99.86 235	96.91 319	98.20 396	98.86 367

MDTV_nov1_ep13			97.73 330		98.70 401	90.83 424	99.15 196	98.02 393	98.51 282	98.82 337	99.61 223	90.98 371	99.66 379	96.89 321	98.92 363

GST-MVS		99.16 189	98.96 219	99.75 80	99.73 142	99.73 81	99.20 176	99.55 230	98.22 313	99.32 270	99.35 312	98.65 160	99.91 151	96.86 322	99.74 228	99.62 149

test_post1							99.14 198				51.63 438	89.54 389	99.82 293	96.86 322

SCA		98.11 315	98.36 281	97.36 384	99.20 335	92.99 412	98.17 343	98.49 377	98.24 312	99.10 309	99.57 246	96.01 317	99.94 83	96.86 322	99.62 271	99.14 316

UBG		96.53 362	95.95 367	98.29 357	98.87 382	96.31 380	98.48 319	98.07 391	98.83 244	97.32 401	96.54 431	79.81 417	99.62 389	96.84 325	98.74 376	98.95 355

XVG-OURS		99.21 174	99.06 186	99.65 129	99.82 74	99.62 123	97.87 376	99.74 120	98.36 297	99.66 162	99.68 180	99.71 23	99.90 169	96.84 325	99.88 139	99.43 245

LCM-MVSNet-Re		99.28 150	99.15 159	99.67 116	99.33 308	99.76 64	99.34 129	99.97 20	98.93 229	99.91 50	99.79 103	98.68 153	99.93 103	96.80 327	99.56 290	99.30 278

RPSCF		99.18 183	99.02 199	99.64 136	99.83 67	99.85 20	99.44 111	99.82 77	98.33 307	99.50 225	99.78 114	97.90 240	99.65 385	96.78 328	99.83 177	99.44 239

旧先验2							97.94 370		95.33 399	98.94 321			99.88 202	96.75 329

MDTV_nov1_ep13_2view						91.44 422	99.14 198		97.37 361	99.21 293		91.78 364		96.75 329		99.03 344

CLD-MVS		98.76 255	98.57 260	99.33 242	99.57 209	98.97 251	97.53 391	99.55 230	96.41 384	99.27 282	99.13 347	99.07 101	99.78 321	96.73 331	99.89 130	99.23 291
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 316	97.98 313	98.48 344	99.27 321	96.48 375	99.40 115	99.07 345	98.81 247	99.23 288	99.57 246	90.11 385	99.87 216	96.69 332	99.64 267	99.09 327

baseline2		96.83 355	96.28 361	98.46 346	99.09 358	96.91 368	98.83 272	93.87 423	97.23 367	96.23 418	98.36 403	88.12 393	99.90 169	96.68 333	98.14 401	98.57 387

cascas		96.99 351	96.82 357	97.48 380	97.57 426	95.64 392	96.43 416	99.56 224	91.75 414	97.13 408	97.61 419	95.58 322	98.63 421	96.68 333	99.11 349	98.18 407

PC_three_1452									97.56 348	99.68 152	99.41 290	99.09 96	97.09 424	96.66 335	99.60 281	99.62 149

LPG-MVS_test		99.22 169	99.05 190	99.74 85	99.82 74	99.63 121	99.16 194	99.73 124	97.56 348	99.64 165	99.69 169	99.37 62	99.89 188	96.66 335	99.87 151	99.69 92

LGP-MVS_train				99.74 85	99.82 74	99.63 121		99.73 124	97.56 348	99.64 165	99.69 169	99.37 62	99.89 188	96.66 335	99.87 151	99.69 92

ETVMVS		96.14 373	95.22 383	98.89 318	98.80 389	98.01 328	98.66 294	98.35 386	98.71 261	97.18 406	96.31 435	74.23 427	99.75 336	96.64 338	98.13 403	98.90 362

TinyColmap		98.97 229	98.93 222	99.07 292	99.46 266	98.19 313	97.75 380	99.75 114	98.79 250	99.54 210	99.70 162	98.97 117	99.62 389	96.63 339	99.83 177	99.41 250

LF4IMVS		99.01 223	98.92 226	99.27 260	99.71 148	99.28 205	98.59 301	99.77 104	98.32 308	99.39 256	99.41 290	98.62 162	99.84 268	96.62 340	99.84 169	98.69 379

NCCC		98.82 249	98.57 260	99.58 163	99.21 332	99.31 200	98.61 296	99.25 322	98.65 266	98.43 369	99.26 330	97.86 243	99.81 308	96.55 341	99.27 340	99.61 159

OPU-MVS				99.29 254	99.12 348	99.44 165	99.20 176				99.40 294	99.00 111	98.84 420	96.54 342	99.60 281	99.58 175

F-COLMAP		98.74 257	98.45 272	99.62 152	99.57 209	99.47 154	98.84 270	99.65 171	96.31 387	98.93 322	99.19 344	97.68 256	99.87 216	96.52 343	99.37 325	99.53 199

testing99		95.86 381	95.19 384	97.87 370	98.76 396	95.03 399	98.62 295	98.44 379	98.68 263	96.67 412	96.66 430	74.31 426	99.69 357	96.51 344	98.03 405	98.90 362

ADS-MVSNet2		97.78 327	97.66 334	98.12 362	99.14 344	95.36 395	99.22 173	98.75 361	96.97 375	98.25 374	99.64 196	90.90 373	99.94 83	96.51 344	99.56 290	99.08 333

ADS-MVSNet		97.72 332	97.67 333	97.86 371	99.14 344	94.65 403	99.22 173	98.86 354	96.97 375	98.25 374	99.64 196	90.90 373	99.84 268	96.51 344	99.56 290	99.08 333

PatchMatch-RL		98.68 265	98.47 269	99.30 253	99.44 271	99.28 205	98.14 346	99.54 236	97.12 373	99.11 307	99.25 332	97.80 248	99.70 351	96.51 344	99.30 334	98.93 358

CMPMVS	77.52 23	98.50 284	98.19 299	99.41 221	98.33 413	99.56 141	99.01 241	99.59 208	95.44 397	99.57 195	99.80 93	95.64 320	99.46 412	96.47 348	99.92 109	99.21 296
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 377	95.32 381	98.02 363	98.76 396	95.39 394	98.38 328	98.65 368	98.82 245	96.84 409	96.71 429	75.06 425	99.71 348	96.46 349	98.23 395	98.98 352

SF-MVS		99.10 203	98.93 222	99.62 152	99.58 199	99.51 149	99.13 204	99.65 171	97.97 328	99.42 243	99.61 223	98.86 130	99.87 216	96.45 350	99.68 254	99.49 221

FE-MVS		97.85 324	97.42 338	99.15 278	99.44 271	98.75 272	99.77 16	98.20 390	95.85 392	99.33 267	99.80 93	88.86 391	99.88 202	96.40 351	99.12 348	98.81 371

DPE-MVS		99.14 193	98.92 226	99.82 40	99.57 209	99.77 57	98.74 288	99.60 202	98.55 276	99.76 118	99.69 169	98.23 217	99.92 129	96.39 352	99.75 221	99.76 72
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 424	89.02 430			93.47 410		98.30 404		99.84 268	96.38 353

AllTest		99.21 174	99.07 184	99.63 143	99.78 109	99.64 116	99.12 208	99.83 72	98.63 268	99.63 169	99.72 146	98.68 153	99.75 336	96.38 353	99.83 177	99.51 211

TestCases				99.63 143	99.78 109	99.64 116		99.83 72	98.63 268	99.63 169	99.72 146	98.68 153	99.75 336	96.38 353	99.83 177	99.51 211

testdata				99.42 214	99.51 240	98.93 258		99.30 312	96.20 388	98.87 332	99.40 294	98.33 206	99.89 188	96.29 356	99.28 337	99.44 239

dp		96.86 354	97.07 347	96.24 402	98.68 402	90.30 428	99.19 182	98.38 384	97.35 362	98.23 376	99.59 236	87.23 395	99.82 293	96.27 357	98.73 379	98.59 384

tpmvs		97.39 343	97.69 331	96.52 398	98.41 410	91.76 418	99.30 144	98.94 353	97.74 342	97.85 393	99.55 257	92.40 359	99.73 342	96.25 358	98.73 379	98.06 409

KD-MVS_2432*1600		95.89 378	95.41 378	97.31 387	94.96 428	93.89 406	97.09 407	99.22 329	97.23 367	98.88 329	99.04 361	79.23 419	99.54 402	96.24 359	96.81 415	98.50 393

miper_refine_blended		95.89 378	95.41 378	97.31 387	94.96 428	93.89 406	97.09 407	99.22 329	97.23 367	98.88 329	99.04 361	79.23 419	99.54 402	96.24 359	96.81 415	98.50 393

ACMP	97.51 14	99.05 211	98.84 236	99.67 116	99.78 109	99.55 144	98.88 264	99.66 161	97.11 374	99.47 230	99.60 231	99.07 101	99.89 188	96.18 361	99.85 164	99.58 175
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 240	98.72 246	99.44 208	99.39 283	99.42 172	98.58 303	99.64 179	97.31 364	99.44 236	99.62 214	98.59 166	99.69 357	96.17 362	99.79 208	99.22 293

DP-MVS Recon		98.50 284	98.23 293	99.31 250	99.49 251	99.46 158	98.56 308	99.63 181	94.86 406	98.85 334	99.37 303	97.81 247	99.59 396	96.08 363	99.44 315	98.88 365

tpm cat1		96.78 356	96.98 350	96.16 403	98.85 383	90.59 427	99.08 223	99.32 305	92.37 412	97.73 399	99.46 282	91.15 369	99.69 357	96.07 364	98.80 369	98.21 404

tpm2		96.35 367	96.22 362	96.73 396	98.88 381	91.75 419	99.21 175	98.51 375	93.27 411	97.89 390	99.21 341	84.83 407	99.70 351	96.04 365	98.18 399	98.75 378

dmvs_re		98.69 264	98.48 268	99.31 250	99.55 223	99.42 172	99.54 87	98.38 384	99.32 172	98.72 348	98.71 391	96.76 294	99.21 415	96.01 366	99.35 328	99.31 276

test_0402		99.22 169	99.14 160	99.45 204	99.79 102	99.43 169	99.28 153	99.68 151	99.54 131	99.40 254	99.56 250	99.07 101	99.82 293	96.01 366	99.96 72	99.11 320

ITE_SJBPF				99.38 229	99.63 182	99.44 165		99.73 124	98.56 275	99.33 267	99.53 261	98.88 129	99.68 369	96.01 366	99.65 265	99.02 349

test_prior2							97.95 369		97.87 337	98.05 384	99.05 359	97.90 240		95.99 369	99.49 310

testdata2													99.89 188	95.99 369

原ACMM1				99.37 232	99.47 262	98.87 264		99.27 317	96.74 382	98.26 373	99.32 316	97.93 239	99.82 293	95.96 371	99.38 323	99.43 245

新几何1				99.52 183	99.50 246	99.22 219		99.26 319	95.66 396	98.60 358	99.28 325	97.67 257	99.89 188	95.95 372	99.32 332	99.45 234

MP-MVS		99.06 208	98.83 238	99.76 70	99.76 121	99.71 88	99.32 136	99.50 259	98.35 302	98.97 318	99.48 275	98.37 200	99.92 129	95.95 372	99.75 221	99.63 138
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 387	94.59 390	98.61 337	98.66 403	97.45 353	98.54 312	97.90 397	98.53 280	96.54 414	96.47 432	70.62 431	99.81 308	95.91 374	98.15 400	98.56 388

wuyk23d		97.58 336	99.13 162	92.93 406	99.69 160	99.49 151	99.52 89	99.77 104	97.97 328	99.96 27	99.79 103	99.84 13	99.94 83	95.85 375	99.82 186	79.36 424

HQP_MVS		98.90 240	98.68 250	99.55 175	99.58 199	99.24 216	98.80 280	99.54 236	98.94 226	99.14 303	99.25 332	97.24 276	99.82 293	95.84 376	99.78 213	99.60 163

plane_prior5								99.54 236					99.82 293	95.84 376	99.78 213	99.60 163

无先验							98.01 361	99.23 326	95.83 393				99.85 253	95.79 378		99.44 239

CPTT-MVS		98.74 257	98.44 273	99.64 136	99.61 187	99.38 184	99.18 183	99.55 230	96.49 383	99.27 282	99.37 303	97.11 284	99.92 129	95.74 379	99.67 260	99.62 149

PLC	97.35 16	98.36 297	97.99 311	99.48 196	99.32 309	99.24 216	98.50 317	99.51 255	95.19 402	98.58 360	98.96 375	96.95 289	99.83 283	95.63 380	99.25 341	99.37 259
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 276	98.34 284	99.28 257	99.18 340	99.10 239	98.34 330	99.41 281	98.48 286	98.52 364	98.98 371	97.05 286	99.78 321	95.59 381	99.50 308	98.96 353

1314		98.00 321	97.90 323	98.27 358	98.90 376	97.45 353	99.30 144	99.06 347	94.98 403	97.21 405	99.12 351	98.43 191	99.67 374	95.58 382	98.56 386	97.71 413

PVSNet_0	95.53 19	95.85 382	95.31 382	97.47 381	98.78 393	93.48 411	95.72 418	99.40 288	96.18 389	97.37 400	97.73 414	95.73 319	99.58 397	95.49 383	81.40 426	99.36 262

MAR-MVS		98.24 307	97.92 321	99.19 273	98.78 393	99.65 113	99.17 188	99.14 341	95.36 398	98.04 385	98.81 387	97.47 266	99.72 344	95.47 384	99.06 352	98.21 404
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	98.23 308	97.89 324	99.26 263	99.19 337	99.26 209	99.65 59	99.69 148	91.33 416	98.14 382	99.77 123	98.28 209	99.96 57	95.41 385	99.55 294	98.58 386

train_agg		98.35 300	97.95 315	99.57 169	99.35 294	99.35 194	98.11 350	99.41 281	94.90 404	97.92 388	98.99 368	98.02 232	99.85 253	95.38 386	99.44 315	99.50 216

9.14			98.64 251		99.45 270		98.81 277	99.60 202	97.52 353	99.28 281	99.56 250	98.53 178	99.83 283	95.36 387	99.64 267

APD-MVS		98.87 245	98.59 256	99.71 105	99.50 246	99.62 123	99.01 241	99.57 219	96.80 381	99.54 210	99.63 207	98.29 208	99.91 151	95.24 388	99.71 243	99.61 159
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 378								95.20 389

AdaColmap		98.60 271	98.35 283	99.38 229	99.12 348	99.22 219	98.67 293	99.42 280	97.84 340	98.81 338	99.27 327	97.32 274	99.81 308	95.14 390	99.53 301	99.10 322

test9_res														95.10 391	99.44 315	99.50 216

CDPH-MVS		98.56 277	98.20 296	99.61 155	99.50 246	99.46 158	98.32 332	99.41 281	95.22 400	99.21 293	99.10 355	98.34 204	99.82 293	95.09 392	99.66 263	99.56 182

BH-untuned		98.22 310	98.09 305	98.58 341	99.38 286	97.24 359	98.55 309	98.98 352	97.81 341	99.20 298	98.76 389	97.01 287	99.65 385	94.83 393	98.33 391	98.86 367

BP-MVS														94.73 394

HQP-MVS		98.36 297	98.02 310	99.39 226	99.31 310	98.94 255	97.98 365	99.37 296	97.45 356	98.15 378	98.83 384	96.67 295	99.70 351	94.73 394	99.67 260	99.53 199

QAPM		98.40 295	97.99 311	99.65 129	99.39 283	99.47 154	99.67 50	99.52 250	91.70 415	98.78 344	99.80 93	98.55 172	99.95 67	94.71 396	99.75 221	99.53 199

agg_prior2														94.58 397	99.46 314	99.50 216

myMVS_eth3d		95.63 385	94.73 387	98.34 352	98.50 408	96.36 378	98.60 298	99.21 332	97.89 334	96.76 410	96.37 433	72.10 429	99.57 398	94.38 398	98.73 379	99.09 327

BH-RMVSNet		98.41 293	98.14 302	99.21 270	99.21 332	98.47 294	98.60 298	98.26 388	98.35 302	98.93 322	99.31 319	97.20 281	99.66 379	94.32 399	99.10 350	99.51 211

E-PMN		97.14 350	97.43 337	96.27 401	98.79 391	91.62 420	95.54 419	99.01 351	99.44 152	98.88 329	99.12 351	92.78 353	99.68 369	94.30 400	99.03 356	97.50 414

MG-MVS		98.52 281	98.39 278	98.94 305	99.15 343	97.39 356	98.18 341	99.21 332	98.89 236	99.23 288	99.63 207	97.37 272	99.74 339	94.22 401	99.61 278	99.69 92

API-MVS		98.38 296	98.39 278	98.35 350	98.83 385	99.26 209	99.14 198	99.18 336	98.59 273	98.66 353	98.78 388	98.61 164	99.57 398	94.14 402	99.56 290	96.21 421

PAPM_NR		98.36 297	98.04 308	99.33 242	99.48 256	98.93 258	98.79 283	99.28 316	97.54 351	98.56 363	98.57 396	97.12 283	99.69 357	94.09 403	98.90 367	99.38 256

ZD-MVS					99.43 274	99.61 129		99.43 278	96.38 385	99.11 307	99.07 357	97.86 243	99.92 129	94.04 404	99.49 310

DPM-MVS		98.28 303	97.94 319	99.32 247	99.36 291	99.11 234	97.31 401	98.78 360	96.88 377	98.84 335	99.11 354	97.77 250	99.61 394	94.03 405	99.36 326	99.23 291

gg-mvs-nofinetune		95.87 380	95.17 385	97.97 366	98.19 416	96.95 366	99.69 42	89.23 429	99.89 41	96.24 417	99.94 19	81.19 411	99.51 408	93.99 406	98.20 396	97.44 415

PMVS	92.94 21	98.82 249	98.81 240	98.85 320	99.84 63	97.99 329	99.20 176	99.47 267	99.71 88	99.42 243	99.82 83	98.09 227	99.47 410	93.88 407	99.85 164	99.07 338
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 353	97.28 341	95.99 404	98.76 396	91.03 423	95.26 421	98.61 369	99.34 169	98.92 325	98.88 382	93.79 341	99.66 379	92.87 408	99.05 354	97.30 418

BH-w/o		97.20 347	97.01 349	97.76 374	99.08 359	95.69 391	98.03 360	98.52 374	95.76 394	97.96 387	98.02 409	95.62 321	99.47 410	92.82 409	97.25 414	98.12 408

TR-MVS		97.44 341	97.15 346	98.32 353	98.53 406	97.46 352	98.47 320	97.91 396	96.85 378	98.21 377	98.51 400	96.42 304	99.51 408	92.16 410	97.29 413	97.98 410

OpenMVS_ROB	97.31 17	97.36 345	96.84 355	98.89 318	99.29 316	99.45 163	98.87 266	99.48 264	86.54 421	99.44 236	99.74 135	97.34 273	99.86 235	91.61 411	99.28 337	97.37 417

GG-mvs-BLEND				97.36 384	97.59 424	96.87 369	99.70 35	88.49 430		94.64 423	97.26 423	80.66 413	99.12 416	91.50 412	96.50 419	96.08 423

DeepMVS_CX				97.98 365	99.69 160	96.95 366		99.26 319	75.51 424	95.74 420	98.28 405	96.47 302	99.62 389	91.23 413	97.89 407	97.38 416

PAPR		97.56 337	97.07 347	99.04 296	98.80 389	98.11 321	97.63 385	99.25 322	94.56 409	98.02 386	98.25 406	97.43 268	99.68 369	90.90 414	98.74 376	99.33 269

MVS		95.72 384	94.63 389	98.99 299	98.56 405	97.98 334	99.30 144	98.86 354	72.71 425	97.30 402	99.08 356	98.34 204	99.74 339	89.21 415	98.33 391	99.26 284

thres600view7		96.60 361	96.16 363	97.93 368	99.63 182	96.09 386	99.18 183	97.57 401	98.77 254	98.72 348	97.32 421	87.04 397	99.72 344	88.57 416	98.62 384	97.98 410

FPMVS		96.32 368	95.50 376	98.79 328	99.60 189	98.17 316	98.46 324	98.80 359	97.16 371	96.28 415	99.63 207	82.19 410	99.09 417	88.45 417	98.89 368	99.10 322

PCF-MVS	96.03 18	96.73 358	95.86 370	99.33 242	99.44 271	99.16 228	96.87 412	99.44 275	86.58 420	98.95 320	99.40 294	94.38 335	99.88 202	87.93 418	99.80 203	98.95 355
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 366	96.03 366	97.47 381	99.63 182	95.93 387	99.18 183	97.57 401	98.75 258	98.70 351	97.31 422	87.04 397	99.67 374	87.62 419	98.51 388	96.81 419

tfpn200view9		96.30 369	95.89 368	97.53 378	99.58 199	96.11 384	99.00 244	97.54 404	98.43 288	98.52 364	96.98 424	86.85 399	99.67 374	87.62 419	98.51 388	96.81 419

thres400		96.40 365	95.89 368	97.92 369	99.58 199	96.11 384	99.00 244	97.54 404	98.43 288	98.52 364	96.98 424	86.85 399	99.67 374	87.62 419	98.51 388	97.98 410

thres200		96.09 374	95.68 374	97.33 386	99.48 256	96.22 383	98.53 314	97.57 401	98.06 323	98.37 371	96.73 428	86.84 401	99.61 394	86.99 422	98.57 385	96.16 422

MVE	92.54 22	96.66 360	96.11 364	98.31 355	99.68 168	97.55 349	97.94 370	95.60 415	99.37 165	90.68 426	98.70 392	96.56 298	98.61 422	86.94 423	99.55 294	98.77 376
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 346	96.83 356	98.59 339	99.46 266	97.55 349	99.25 165	96.84 409	98.78 252	97.24 404	97.67 415	97.11 284	98.97 419	86.59 424	98.54 387	99.27 282

PAPM		95.61 386	94.71 388	98.31 355	99.12 348	96.63 372	96.66 415	98.46 378	90.77 417	96.25 416	98.68 393	93.01 351	99.69 357	81.60 425	97.86 409	98.62 381

dongtai		89.37 391	88.91 394	90.76 407	99.19 337	77.46 432	95.47 420	87.82 431	92.28 413	94.17 424	98.82 386	71.22 430	95.54 426	63.85 426	97.34 412	99.27 282

kuosan		85.65 393	84.57 396	88.90 409	97.91 421	77.11 433	96.37 417	87.62 432	85.24 422	85.45 427	96.83 427	69.94 432	90.98 428	45.90 427	95.83 423	98.62 381

test123		29.31 394	33.05 399	18.08 410	25.93 434	12.24 435	97.53 391	10.93 435	11.78 428	24.21 429	50.08 440	21.04 433	8.60 429	23.51 428	32.43 428	33.39 425

testmvs		28.94 395	33.33 397	15.79 411	26.03 433	9.81 436	96.77 413	15.67 434	11.55 429	23.87 430	50.74 439	19.03 434	8.53 430	23.21 429	33.07 427	29.03 426

mmdepth		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

monomultidepth		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

test_blank		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uanet_test		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

DCPMVS		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

cdsmvs_eth3d_5k		24.88 396	33.17 398	0.00 412	0.00 435	0.00 437	0.00 423	99.62 184	0.00 430	0.00 431	99.13 347	99.82 14	0.00 431	0.00 430	0.00 429	0.00 427

pcd_1.5k_mvsjas		16.61 397	22.14 400	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	99.28 72	0.00 431	0.00 430	0.00 429	0.00 427

sosnet-low-res		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

sosnet		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uncertanet		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

Regformer		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

ab-mvs-re		8.26 408	11.02 411	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	99.16 345	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uanet		8.33 398	11.11 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	100.00 1	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

FOURS1					99.83 67	99.89 10	99.74 24	99.71 136	99.69 96	99.63 169

test_one_0601					99.63 182	99.76 64		99.55 230	99.23 186	99.31 275	99.61 223	98.59 166

eth-test2					0.00 435

eth-test					0.00 435

test_241102_ONE					99.69 160	99.82 38		99.54 236	99.12 209	99.82 86	99.49 272	98.91 125	99.52 407

save fliter					99.53 231	99.25 212	98.29 334	99.38 295	99.07 213

test0726					99.69 160	99.80 47	99.24 166	99.57 219	99.16 200	99.73 135	99.65 194	98.35 202

GSMVS																99.14 316

test_part2					99.62 186	99.67 105				99.55 208

sam_mvs1												90.81 377				99.14 316

sam_mvs												90.52 382

MTGPA								99.53 245

test_post											52.41 437	90.25 384	99.86 235

patchmatchnet-post											99.62 214	90.58 380	99.94 83

MTMP							99.09 220	98.59 372

TEST9					99.35 294	99.35 194	98.11 350	99.41 281	94.83 407	97.92 388	98.99 368	98.02 232	99.85 253

test_8					99.34 303	99.31 200	98.08 354	99.40 288	94.90 404	97.87 392	98.97 373	98.02 232	99.84 268

agg_prior					99.35 294	99.36 191		99.39 291		97.76 398			99.85 253

test_prior4						99.19 225	98.00 363

test_prior				99.46 201	99.35 294	99.22 219		99.39 291					99.69 357			99.48 225

新几何2							98.04 358

旧先验1					99.49 251	99.29 203		99.26 319			99.39 298	97.67 257			99.36 326	99.46 233

原ACMM2							97.92 372

test222					99.51 240	99.08 241	97.83 378	99.29 313	95.21 401	98.68 352	99.31 319	97.28 275			99.38 323	99.43 245

segment_acmp												98.37 200

testdata1							97.72 381		97.86 339

test12				99.54 180	99.29 316	99.33 197		99.16 339		98.43 369		97.54 264	99.82 293		99.47 312	99.48 225

plane_prior7					99.58 199	99.38 184

plane_prior6					99.47 262	99.26 209						97.24 276

plane_prior4											99.25 332

plane_prior3						99.31 200			98.36 297	99.14 303

plane_prior2							98.80 280		98.94 226

plane_prior1					99.51 240

plane_prior						99.24 216	98.42 326		97.87 337						99.71 243

n2								0.00 436

nn								0.00 436

door-mid								99.83 72

test11								99.29 313

door								99.77 104

HQP5-MVS						98.94 255

HQP-NCC					99.31 310		97.98 365		97.45 356	98.15 378

ACMP_Plane					99.31 310		97.98 365		97.45 356	98.15 378

HQP4-MVS										98.15 378			99.70 351			99.53 199

HQP3-MVS								99.37 296							99.67 260

HQP2-MVS												96.67 295

NP-MVS					99.40 282	99.13 231					98.83 384

ACMMP++_ref															99.94 98

ACMMP++															99.79 208

Test By Simon												98.41 194

High-resolution multi-view benchmark