High-res multi-view results

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

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

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

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

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

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

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

test_vis3_rt		99.89 3	99.90 4	99.87 22	99.98 3	99.75 71	99.70 35	100.00 1	99.73 81	100.00 1	99.89 38	99.79 16	99.88 201	99.98 1	100.00 1	99.98 5

test_fmvs2		99.72 41	99.85 17	99.34 238	99.91 31	98.08 325	99.48 102	100.00 1	99.90 34	99.99 7	99.91 28	99.50 49	99.98 21	99.98 1	99.99 16	99.96 13

test_fmvs3		99.83 20	99.93 2	99.53 180	99.96 7	98.62 286	99.67 50	100.00 1	99.95 23	100.00 1	99.95 16	99.85 10	99.99 8	99.98 1	99.99 16	99.98 5

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 2	99.98 3	99.76 63	99.12 208	100.00 1	100.00 1	99.99 7	99.91 28	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_vis1_n_1920		99.72 41	99.88 7	99.27 259	99.93 24	97.84 337	99.34 129	100.00 1	99.99 3	99.99 7	99.82 83	99.87 9	99.99 8	99.97 4	99.99 16	99.97 10

test_vis1_n		99.68 50	99.79 29	99.36 235	99.94 18	98.18 314	99.52 89	100.00 1	99.86 49	100.00 1	99.88 47	98.99 112	99.96 56	99.97 4	99.96 71	99.95 14

test_fmvs1_n		99.68 50	99.81 25	99.28 256	99.95 15	97.93 334	99.49 100	100.00 1	99.82 65	99.99 7	99.89 38	99.21 80	99.98 21	99.97 4	99.98 43	99.93 20

test_f		99.75 37	99.88 7	99.37 231	99.96 7	98.21 311	99.51 95	100.00 1	99.94 26	100.00 1	99.93 21	99.58 38	99.94 82	99.97 4	99.99 16	99.97 10

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 2	99.97 6	99.74 77	99.01 240	99.99 11	99.99 3	99.98 14	99.88 47	99.97 2	99.99 8	99.96 9	100.00 1	99.98 5

test_fmvsmvis_n_1920		99.84 16	99.86 13	99.81 44	99.88 44	99.55 143	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 31

test_cas_vis1_n_1920		99.76 36	99.86 13	99.45 203	99.93 24	98.40 299	99.30 144	99.98 12	99.94 26	99.99 7	99.89 38	99.80 15	99.97 35	99.96 9	99.97 58	99.97 10

fmvsm_l_conf0.5_n		99.80 25	99.78 33	99.85 28	99.88 44	99.66 106	99.11 213	99.91 41	99.98 15	99.96 27	99.64 195	99.60 36	99.99 8	99.95 12	99.99 16	99.88 31

test_fmvsm_n_1920		99.84 16	99.85 17	99.83 34	99.82 73	99.70 95	99.17 188	99.97 20	99.99 3	99.96 27	99.82 83	99.94 4	100.00 1	99.95 12	100.00 1	99.80 53

test_fmvs1		99.48 94	99.65 55	98.97 300	99.54 224	97.16 360	99.11 213	99.98 12	99.78 75	99.96 27	99.81 90	98.72 149	99.97 35	99.95 12	99.97 58	99.79 60

mvsany_test3		99.85 12	99.88 7	99.75 79	99.95 15	99.37 186	99.53 88	99.98 12	99.77 79	99.99 7	99.95 16	99.85 10	99.94 82	99.95 12	99.98 43	99.94 17

fmvsm_s_conf0.1_n_2		99.81 24	99.78 33	99.89 10	99.93 24	99.76 63	98.92 260	99.98 12	99.99 3	99.99 7	99.88 47	99.43 51	99.94 82	99.94 16	99.99 16	99.99 2

fmvsm_l_conf0.5_n_a		99.80 25	99.79 29	99.84 31	99.88 44	99.64 115	99.12 208	99.91 41	99.98 15	99.95 35	99.67 183	99.67 27	99.99 8	99.94 16	99.99 16	99.88 31

MM		99.18 182	99.05 189	99.55 174	99.35 293	98.81 265	99.05 227	97.79 398	99.99 3	99.48 227	99.59 235	96.29 311	99.95 66	99.94 16	99.98 43	99.88 31

test_fmvsmconf_n		99.85 12	99.84 20	99.88 17	99.91 31	99.73 80	98.97 252	99.98 12	99.99 3	99.96 27	99.85 65	99.93 7	99.99 8	99.94 16	99.99 16	99.93 20

fmvsm_s_conf0.5_n_2		99.78 30	99.75 41	99.88 17	99.82 73	99.76 63	98.88 263	99.92 35	99.98 15	99.98 14	99.85 65	99.42 53	99.94 82	99.93 20	99.98 43	99.94 17

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 2	99.95 15	99.82 37	99.10 216	99.98 12	99.99 3	99.98 14	99.91 28	99.68 26	99.93 102	99.93 20	99.99 16	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 10	99.93 24	99.78 51	99.07 226	99.98 12	99.99 3	99.98 14	99.90 33	99.88 8	99.92 128	99.93 20	99.99 16	99.98 5

fmvsm_s_conf0.5_n_a		99.82 22	99.79 29	99.89 10	99.85 58	99.82 37	99.03 235	99.96 26	99.99 3	99.97 22	99.84 72	99.58 38	99.93 102	99.92 23	99.98 43	99.93 20

fmvsm_s_conf0.5_n		99.83 20	99.81 25	99.87 22	99.85 58	99.78 51	99.03 235	99.96 26	99.99 3	99.97 22	99.84 72	99.78 17	99.92 128	99.92 23	99.99 16	99.92 24

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 20	99.99 3	100.00 1	99.98 13	99.78 17	100.00 1	99.92 23	100.00 1	99.87 35

MVStest1		98.22 309	98.09 304	98.62 335	99.04 363	96.23 381	99.20 176	99.92 35	99.44 151	99.98 14	99.87 53	85.87 404	99.67 373	99.91 26	99.57 288	99.95 14

v1921920		99.56 77	99.57 76	99.55 174	99.75 132	99.11 233	99.05 227	99.61 190	99.15 203	99.88 65	99.71 153	99.08 98	99.87 215	99.90 27	99.97 58	99.66 114

v1240		99.56 77	99.58 72	99.51 185	99.80 89	99.00 245	99.00 243	99.65 170	99.15 203	99.90 52	99.75 130	99.09 95	99.88 201	99.90 27	99.96 71	99.67 105

v10		99.69 47	99.69 48	99.66 122	99.81 82	99.39 181	99.66 54	99.75 113	99.60 126	99.92 46	99.87 53	98.75 144	99.86 234	99.90 27	99.99 16	99.73 76

v1192		99.57 74	99.57 76	99.57 168	99.77 116	99.22 218	99.04 232	99.60 201	99.18 192	99.87 73	99.72 145	99.08 98	99.85 252	99.89 30	99.98 43	99.66 114

fmvsm_s_conf0.5_n_3		99.79 28	99.77 36	99.85 28	99.81 82	99.71 87	98.97 252	99.92 35	99.98 15	99.97 22	99.86 60	99.53 45	99.95 66	99.88 31	99.99 16	99.89 30

v144192		99.55 80	99.54 83	99.58 162	99.78 108	99.20 223	99.11 213	99.62 183	99.18 192	99.89 56	99.72 145	98.66 157	99.87 215	99.88 31	99.97 58	99.66 114

v8		99.68 50	99.69 48	99.65 128	99.80 89	99.40 178	99.66 54	99.76 108	99.64 111	99.93 41	99.85 65	98.66 157	99.84 267	99.88 31	99.99 16	99.71 82

mvs5depth		99.88 6	99.91 3	99.80 49	99.92 29	99.42 171	99.94 3	100.00 1	99.97 19	99.89 56	99.99 12	99.63 30	99.97 35	99.87 34	99.99 16	100.00 1

v1144		99.54 83	99.53 87	99.59 159	99.79 101	99.28 204	99.10 216	99.61 190	99.20 190	99.84 80	99.73 138	98.67 155	99.84 267	99.86 35	99.98 43	99.64 132

mmtdpeth		99.78 30	99.83 21	99.66 122	99.85 58	99.05 244	99.79 12	99.97 20	100.00 1	99.43 239	99.94 19	99.64 28	99.94 82	99.83 36	99.99 16	99.98 5

SSC-MVS		99.52 86	99.42 105	99.83 34	99.86 54	99.65 112	99.52 89	99.81 85	99.87 46	99.81 92	99.79 103	96.78 292	99.99 8	99.83 36	99.51 304	99.86 37

v7n		99.82 22	99.80 28	99.88 17	99.96 7	99.84 24	99.82 9	99.82 76	99.84 58	99.94 38	99.91 28	99.13 91	99.96 56	99.83 36	99.99 16	99.83 46

v2v482		99.50 88	99.47 92	99.58 162	99.78 108	99.25 211	99.14 198	99.58 216	99.25 181	99.81 92	99.62 213	98.24 212	99.84 267	99.83 36	99.97 58	99.64 132

test_vis1_rt		99.45 107	99.46 96	99.41 220	99.71 147	98.63 285	98.99 248	99.96 26	99.03 216	99.95 35	99.12 350	98.75 144	99.84 267	99.82 40	99.82 185	99.77 66

tt0805		99.63 63	99.57 76	99.81 44	99.87 51	99.88 12	99.58 79	98.70 362	99.72 85	99.91 49	99.60 230	99.43 51	99.81 307	99.81 41	99.53 300	99.73 76

V42		99.56 77	99.54 83	99.63 142	99.79 101	99.46 157	99.39 117	99.59 207	99.24 183	99.86 74	99.70 161	98.55 171	99.82 292	99.79 42	99.95 84	99.60 162

mvs_tets		99.90 2	99.90 4	99.90 7	99.96 7	99.79 48	99.72 30	99.88 52	99.92 31	99.98 14	99.93 21	99.94 4	99.98 21	99.77 43	100.00 1	99.92 24

WB-MVS		99.44 109	99.32 126	99.80 49	99.81 82	99.61 128	99.47 105	99.81 85	99.82 65	99.71 141	99.72 145	96.60 296	99.98 21	99.75 44	99.23 344	99.82 52

PS-MVSNAJss		99.84 16	99.82 24	99.89 10	99.96 7	99.77 56	99.68 46	99.85 63	99.95 23	99.98 14	99.92 25	99.28 71	99.98 21	99.75 44	100.00 1	99.94 17

jajsoiax		99.89 3	99.89 6	99.89 10	99.96 7	99.78 51	99.70 35	99.86 57	99.89 40	99.98 14	99.90 33	99.94 4	99.98 21	99.75 44	100.00 1	99.90 26

ANet_high		99.88 6	99.87 11	99.91 2	99.99 1	99.91 4	99.65 59	100.00 1	99.90 34	100.00 1	99.97 14	99.61 34	99.97 35	99.75 44	100.00 1	99.84 42

reproduce_monomvs		97.40 341	97.46 335	97.20 388	99.05 360	91.91 416	99.20 176	99.18 335	99.84 58	99.86 74	99.75 130	80.67 411	99.83 282	99.69 48	99.95 84	99.85 40

SPE-MVS-test		99.68 50	99.70 45	99.64 135	99.57 208	99.83 29	99.78 14	99.97 20	99.92 31	99.50 224	99.38 299	99.57 40	99.95 66	99.69 48	99.90 119	99.15 310

MVS_0304		98.61 267	98.30 288	99.52 182	97.88 421	98.95 253	98.76 285	94.11 420	99.84 58	99.32 269	99.57 245	95.57 322	99.95 66	99.68 50	99.98 43	99.68 97

CS-MVS		99.67 56	99.70 45	99.58 162	99.53 230	99.84 24	99.79 12	99.96 26	99.90 34	99.61 183	99.41 289	99.51 48	99.95 66	99.66 51	99.89 129	98.96 352

mamv4		99.73 40	99.74 42	99.70 108	99.66 174	99.87 14	99.69 42	99.93 33	99.93 28	99.93 41	99.86 60	99.07 100	100.00 1	99.66 51	99.92 108	99.24 286

pmmvs6		99.86 10	99.86 13	99.83 34	99.94 18	99.90 7	99.83 7	99.91 41	99.85 55	99.94 38	99.95 16	99.73 21	99.90 168	99.65 53	99.97 58	99.69 91

MIMVSNet1		99.66 57	99.62 60	99.80 49	99.94 18	99.87 14	99.69 42	99.77 103	99.78 75	99.93 41	99.89 38	97.94 237	99.92 128	99.65 53	99.98 43	99.62 148

EC-MVSNet		99.69 47	99.69 48	99.68 112	99.71 147	99.91 4	99.76 20	99.96 26	99.86 49	99.51 222	99.39 297	99.57 40	99.93 102	99.64 55	99.86 158	99.20 299

K. test v3		98.87 244	98.60 253	99.69 110	99.93 24	99.46 157	99.74 24	94.97 415	99.78 75	99.88 65	99.88 47	93.66 343	99.97 35	99.61 56	99.95 84	99.64 132

KD-MVS_self_test		99.63 63	99.59 69	99.76 69	99.84 62	99.90 7	99.37 124	99.79 94	99.83 63	99.88 65	99.85 65	98.42 192	99.90 168	99.60 57	99.73 233	99.49 220

Anonymous20240521		99.44 109	99.42 105	99.49 191	99.89 39	98.96 252	99.62 64	99.76 108	99.85 55	99.82 85	99.88 47	96.39 306	99.97 35	99.59 58	99.98 43	99.55 184

TransMVSNet (Re)		99.78 30	99.77 36	99.81 44	99.91 31	99.85 19	99.75 22	99.86 57	99.70 92	99.91 49	99.89 38	99.60 36	99.87 215	99.59 58	99.74 227	99.71 82

OurMVSNet-221017-0		99.75 37	99.71 44	99.84 31	99.96 7	99.83 29	99.83 7	99.85 63	99.80 71	99.93 41	99.93 21	98.54 173	99.93 102	99.59 58	99.98 43	99.76 71

EU-MVSNet		99.39 125	99.62 60	98.72 331	99.88 44	96.44 375	99.56 84	99.85 63	99.90 34	99.90 52	99.85 65	98.09 226	99.83 282	99.58 61	99.95 84	99.90 26

mvs_anonymous		99.28 149	99.39 109	98.94 304	99.19 336	97.81 339	99.02 238	99.55 229	99.78 75	99.85 77	99.80 93	98.24 212	99.86 234	99.57 62	99.50 307	99.15 310

test1111		97.74 327	98.16 300	96.49 398	99.60 188	89.86 428	99.71 34	91.21 424	99.89 40	99.88 65	99.87 53	93.73 342	99.90 168	99.56 63	99.99 16	99.70 85

lessismore_v0				99.64 135	99.86 54	99.38 183		90.66 425		99.89 56	99.83 76	94.56 333	99.97 35	99.56 63	99.92 108	99.57 179

mvsany_test1		99.44 109	99.45 98	99.40 222	99.37 287	98.64 284	97.90 374	99.59 207	99.27 177	99.92 46	99.82 83	99.74 20	99.93 102	99.55 65	99.87 150	99.63 137

MVSMamba_PlusPlus		99.55 80	99.58 72	99.47 197	99.68 167	99.40 178	99.52 89	99.70 140	99.92 31	99.77 114	99.86 60	98.28 208	99.96 56	99.54 66	99.90 119	99.05 339

pm-mvs1		99.79 28	99.79 29	99.78 59	99.91 31	99.83 29	99.76 20	99.87 54	99.73 81	99.89 56	99.87 53	99.63 30	99.87 215	99.54 66	99.92 108	99.63 137

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 17	99.91 31	99.90 7	99.96 1	99.92 35	99.90 34	99.97 22	99.87 53	99.81 14	99.95 66	99.54 66	99.99 16	99.80 53
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 94	99.65 55	98.95 303	99.71 147	97.27 357	99.50 96	99.82 76	99.59 128	99.41 248	99.85 65	99.62 33	100.00 1	99.53 69	99.89 129	99.59 169

test2506		94.73 388	94.59 389	95.15 404	99.59 193	85.90 430	99.75 22	74.01 432	99.89 40	99.71 141	99.86 60	79.00 421	99.90 168	99.52 70	99.99 16	99.65 122

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 7	99.89 39	99.91 4	99.89 5	99.71 135	99.93 28	99.95 35	99.89 38	99.71 22	99.96 56	99.51 71	99.97 58	99.84 42

FC-MVSNet-test		99.70 45	99.65 55	99.86 26	99.88 44	99.86 18	99.72 30	99.78 100	99.90 34	99.82 85	99.83 76	98.45 188	99.87 215	99.51 71	99.97 58	99.86 37

BP-MVS1		98.72 259	98.46 269	99.50 187	99.53 230	99.00 245	99.34 129	98.53 372	99.65 108	99.73 134	99.38 299	90.62 378	99.96 56	99.50 73	99.86 158	99.55 184

UA-Net		99.78 30	99.76 40	99.86 26	99.72 144	99.71 87	99.91 4	99.95 31	99.96 22	99.71 141	99.91 28	99.15 86	99.97 35	99.50 73	100.00 1	99.90 26

PMMVS2		99.48 94	99.45 98	99.57 168	99.76 120	98.99 247	98.09 351	99.90 46	98.95 224	99.78 106	99.58 238	99.57 40	99.93 102	99.48 75	99.95 84	99.79 60

VPA-MVSNet		99.66 57	99.62 60	99.79 56	99.68 167	99.75 71	99.62 64	99.69 147	99.85 55	99.80 96	99.81 90	98.81 132	99.91 150	99.47 76	99.88 138	99.70 85

GDP-MVS		98.81 250	98.57 259	99.50 187	99.53 230	99.12 232	99.28 153	99.86 57	99.53 132	99.57 194	99.32 315	90.88 374	99.98 21	99.46 77	99.74 227	99.42 248

ECVR-MVS		97.73 328	98.04 307	96.78 392	99.59 193	90.81 424	99.72 30	90.43 426	99.89 40	99.86 74	99.86 60	93.60 344	99.89 187	99.46 77	99.99 16	99.65 122

nrg030		99.70 45	99.66 53	99.82 39	99.76 120	99.84 24	99.61 70	99.70 140	99.93 28	99.78 106	99.68 179	99.10 93	99.78 320	99.45 79	99.96 71	99.83 46

TAMVS		99.49 92	99.45 98	99.63 142	99.48 255	99.42 171	99.45 109	99.57 218	99.66 105	99.78 106	99.83 76	97.85 244	99.86 234	99.44 80	99.96 71	99.61 158

GeoE		99.69 47	99.66 53	99.78 59	99.76 120	99.76 63	99.60 76	99.82 76	99.46 146	99.75 122	99.56 249	99.63 30	99.95 66	99.43 81	99.88 138	99.62 148

new-patchmatchnet		99.35 135	99.57 76	98.71 333	99.82 73	96.62 372	98.55 308	99.75 113	99.50 136	99.88 65	99.87 53	99.31 67	99.88 201	99.43 81	100.00 1	99.62 148

test20.03		99.55 80	99.54 83	99.58 162	99.79 101	99.37 186	99.02 238	99.89 48	99.60 126	99.82 85	99.62 213	98.81 132	99.89 187	99.43 81	99.86 158	99.47 228

MVSFormer		99.41 119	99.44 101	99.31 249	99.57 208	98.40 299	99.77 16	99.80 88	99.73 81	99.63 168	99.30 320	98.02 231	99.98 21	99.43 81	99.69 248	99.55 184

test_djsdf		99.84 16	99.81 25	99.91 2	99.94 18	99.84 24	99.77 16	99.80 88	99.73 81	99.97 22	99.92 25	99.77 19	99.98 21	99.43 81	100.00 1	99.90 26

SDMVSNet		99.77 35	99.77 36	99.76 69	99.80 89	99.65 112	99.63 61	99.86 57	99.97 19	99.89 56	99.89 38	99.52 47	99.99 8	99.42 86	99.96 71	99.65 122

Anonymous20231211		99.62 69	99.57 76	99.76 69	99.61 186	99.60 131	99.81 10	99.73 123	99.82 65	99.90 52	99.90 33	97.97 236	99.86 234	99.42 86	99.96 71	99.80 53

SixPastTwentyTwo		99.42 115	99.30 133	99.76 69	99.92 29	99.67 104	99.70 35	99.14 340	99.65 108	99.89 56	99.90 33	96.20 313	99.94 82	99.42 86	99.92 108	99.67 105

balanced_conf03		99.50 88	99.50 89	99.50 187	99.42 278	99.49 150	99.52 89	99.75 113	99.86 49	99.78 106	99.71 153	98.20 219	99.90 168	99.39 89	99.88 138	99.10 321

patch_mono-2		99.51 87	99.46 96	99.64 135	99.70 155	99.11 233	99.04 232	99.87 54	99.71 87	99.47 229	99.79 103	98.24 212	99.98 21	99.38 90	99.96 71	99.83 46

UGNet		99.38 127	99.34 121	99.49 191	98.90 375	98.90 260	99.70 35	99.35 299	99.86 49	98.57 361	99.81 90	98.50 183	99.93 102	99.38 90	99.98 43	99.66 114
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 44	99.67 52	99.81 44	99.89 39	99.72 85	99.59 77	99.82 76	99.39 162	99.82 85	99.84 72	99.38 59	99.91 150	99.38 90	99.93 104	99.80 53

FIs		99.65 62	99.58 72	99.84 31	99.84 62	99.85 19	99.66 54	99.75 113	99.86 49	99.74 130	99.79 103	98.27 210	99.85 252	99.37 93	99.93 104	99.83 46

sd_testset		99.78 30	99.78 33	99.80 49	99.80 89	99.76 63	99.80 11	99.79 94	99.97 19	99.89 56	99.89 38	99.53 45	99.99 8	99.36 94	99.96 71	99.65 122

anonymousdsp		99.80 25	99.77 36	99.90 7	99.96 7	99.88 12	99.73 27	99.85 63	99.70 92	99.92 46	99.93 21	99.45 50	99.97 35	99.36 94	100.00 1	99.85 40

casdiffmvs_mvg		99.68 50	99.68 51	99.69 110	99.81 82	99.59 133	99.29 151	99.90 46	99.71 87	99.79 102	99.73 138	99.54 43	99.84 267	99.36 94	99.96 71	99.65 122
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 37	99.74 42	99.79 56	99.88 44	99.66 106	99.69 42	99.92 35	99.67 101	99.77 114	99.75 130	99.61 34	99.98 21	99.35 97	99.98 43	99.72 79
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 71	99.64 58	99.53 180	99.79 101	98.82 264	99.58 79	99.97 20	99.95 23	99.96 27	99.76 125	98.44 189	99.99 8	99.34 98	99.96 71	99.78 62

CHOSEN 1792x2688		99.39 125	99.30 133	99.65 128	99.88 44	99.25 211	98.78 283	99.88 52	98.66 264	99.96 27	99.79 103	97.45 266	99.93 102	99.34 98	99.99 16	99.78 62

CDS-MVSNet		99.22 168	99.13 161	99.50 187	99.35 293	99.11 233	98.96 255	99.54 235	99.46 146	99.61 183	99.70 161	96.31 309	99.83 282	99.34 98	99.88 138	99.55 184
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 224	99.16 155	98.51 341	99.75 132	95.90 387	98.07 354	99.84 69	99.84 58	99.89 56	99.73 138	96.01 316	99.99 8	99.33 101	100.00 1	99.63 137

HyFIR lowres test		98.91 237	98.64 250	99.73 93	99.85 58	99.47 153	98.07 354	99.83 71	98.64 266	99.89 56	99.60 230	92.57 353	100.00 1	99.33 101	99.97 58	99.72 79

pmmvs5		99.19 178	99.11 168	99.42 213	99.76 120	98.88 261	98.55 308	99.73 123	98.82 244	99.72 136	99.62 213	96.56 297	99.82 292	99.32 103	99.95 84	99.56 181

v148		99.40 121	99.41 107	99.39 225	99.76 120	98.94 254	99.09 220	99.59 207	99.17 197	99.81 92	99.61 222	98.41 193	99.69 356	99.32 103	99.94 97	99.53 198

baseline		99.63 63	99.62 60	99.66 122	99.80 89	99.62 122	99.44 111	99.80 88	99.71 87	99.72 136	99.69 168	99.15 86	99.83 282	99.32 103	99.94 97	99.53 198

CVMVSNet		98.61 267	98.88 230	97.80 372	99.58 198	93.60 409	99.26 159	99.64 178	99.66 105	99.72 136	99.67 183	93.26 346	99.93 102	99.30 106	99.81 195	99.87 35

PS-CasMVS		99.66 57	99.58 72	99.89 10	99.80 89	99.85 19	99.66 54	99.73 123	99.62 116	99.84 80	99.71 153	98.62 161	99.96 56	99.30 106	99.96 71	99.86 37

DTE-MVSNet		99.68 50	99.61 64	99.88 17	99.80 89	99.87 14	99.67 50	99.71 135	99.72 85	99.84 80	99.78 113	98.67 155	99.97 35	99.30 106	99.95 84	99.80 53

tmp_tt		95.75 382	95.42 376	96.76 393	89.90 431	94.42 403	98.86 266	97.87 397	78.01 422	99.30 279	99.69 168	97.70 252	95.89 424	99.29 109	98.14 400	99.95 14

PEN-MVS		99.66 57	99.59 69	99.89 10	99.83 66	99.87 14	99.66 54	99.73 123	99.70 92	99.84 80	99.73 138	98.56 170	99.96 56	99.29 109	99.94 97	99.83 46

WR-MVS_H		99.61 71	99.53 87	99.87 22	99.80 89	99.83 29	99.67 50	99.75 113	99.58 129	99.85 77	99.69 168	98.18 222	99.94 82	99.28 111	99.95 84	99.83 46

IterMVS		98.97 228	99.16 155	98.42 346	99.74 138	95.64 391	98.06 356	99.83 71	99.83 63	99.85 77	99.74 134	96.10 315	99.99 8	99.27 112	100.00 1	99.63 137
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WBMVS		97.50 338	97.18 344	98.48 343	98.85 382	95.89 388	98.44 324	99.52 249	99.53 132	99.52 216	99.42 288	80.10 414	99.86 234	99.24 113	99.95 84	99.68 97

h-mvs33		98.61 267	98.34 283	99.44 207	99.60 188	98.67 276	99.27 157	99.44 274	99.68 97	99.32 269	99.49 271	92.50 356	100.00 1	99.24 113	96.51 417	99.65 122

hse-mvs2		98.52 280	98.30 288	99.16 275	99.29 315	98.60 287	98.77 284	99.02 348	99.68 97	99.32 269	99.04 360	92.50 356	99.85 252	99.24 113	97.87 407	99.03 343

FMVSNet1		99.66 57	99.63 59	99.73 93	99.78 108	99.77 56	99.68 46	99.70 140	99.67 101	99.82 85	99.83 76	98.98 114	99.90 168	99.24 113	99.97 58	99.53 198

casdiffmvs		99.63 63	99.61 64	99.67 115	99.79 101	99.59 133	99.13 204	99.85 63	99.79 73	99.76 117	99.72 145	99.33 66	99.82 292	99.21 117	99.94 97	99.59 169
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 83	99.43 103	99.87 22	99.76 120	99.82 37	99.57 82	99.61 190	99.54 130	99.80 96	99.64 195	97.79 248	99.95 66	99.21 117	99.94 97	99.84 42

DELS-MVS		99.34 140	99.30 133	99.48 195	99.51 239	99.36 190	98.12 347	99.53 244	99.36 167	99.41 248	99.61 222	99.22 79	99.87 215	99.21 117	99.68 253	99.20 299
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)		99.37 130	99.26 144	99.68 112	99.51 239	99.58 137	98.98 251	99.60 201	99.43 157	99.70 145	99.36 306	97.70 252	99.88 201	99.20 120	99.87 150	99.59 169

CANet		99.11 199	99.05 189	99.28 256	98.83 384	98.56 289	98.71 291	99.41 280	99.25 181	99.23 287	99.22 338	97.66 260	99.94 82	99.19 121	99.97 58	99.33 268

EI-MVSNet-UG-set		99.48 94	99.50 89	99.42 213	99.57 208	98.65 282	99.24 166	99.46 269	99.68 97	99.80 96	99.66 188	98.99 112	99.89 187	99.19 121	99.90 119	99.72 79

xiu_mvs_v1_base_debu		99.23 160	99.34 121	98.91 310	99.59 193	98.23 308	98.47 319	99.66 160	99.61 120	99.68 151	98.94 376	99.39 55	99.97 35	99.18 123	99.55 293	98.51 389

xiu_mvs_v1_base		99.23 160	99.34 121	98.91 310	99.59 193	98.23 308	98.47 319	99.66 160	99.61 120	99.68 151	98.94 376	99.39 55	99.97 35	99.18 123	99.55 293	98.51 389

xiu_mvs_v1_base_debi		99.23 160	99.34 121	98.91 310	99.59 193	98.23 308	98.47 319	99.66 160	99.61 120	99.68 151	98.94 376	99.39 55	99.97 35	99.18 123	99.55 293	98.51 389

VPNet		99.46 103	99.37 114	99.71 104	99.82 73	99.59 133	99.48 102	99.70 140	99.81 68	99.69 148	99.58 238	97.66 260	99.86 234	99.17 126	99.44 314	99.67 105

UniMVSNet_NR-MVSNet		99.37 130	99.25 146	99.72 99	99.47 261	99.56 140	98.97 252	99.61 190	99.43 157	99.67 156	99.28 324	97.85 244	99.95 66	99.17 126	99.81 195	99.65 122

DU-MVS		99.33 143	99.21 150	99.71 104	99.43 273	99.56 140	98.83 271	99.53 244	99.38 163	99.67 156	99.36 306	97.67 256	99.95 66	99.17 126	99.81 195	99.63 137

EI-MVSNet-Vis-set		99.47 102	99.49 91	99.42 213	99.57 208	98.66 279	99.24 166	99.46 269	99.67 101	99.79 102	99.65 193	98.97 116	99.89 187	99.15 129	99.89 129	99.71 82

EI-MVSNet		99.38 127	99.44 101	99.21 269	99.58 198	98.09 322	99.26 159	99.46 269	99.62 116	99.75 122	99.67 183	98.54 173	99.85 252	99.15 129	99.92 108	99.68 97

VNet		99.18 182	99.06 185	99.56 171	99.24 326	99.36 190	99.33 133	99.31 308	99.67 101	99.47 229	99.57 245	96.48 300	99.84 267	99.15 129	99.30 333	99.47 228

EG-PatchMatch MVS		99.57 74	99.56 81	99.62 151	99.77 116	99.33 196	99.26 159	99.76 108	99.32 171	99.80 96	99.78 113	99.29 69	99.87 215	99.15 129	99.91 118	99.66 114

PVSNet_Blended_VisFu		99.40 121	99.38 111	99.44 207	99.90 37	98.66 279	98.94 258	99.91 41	97.97 327	99.79 102	99.73 138	99.05 105	99.97 35	99.15 129	99.99 16	99.68 97

IterMVS-LS		99.41 119	99.47 92	99.25 265	99.81 82	98.09 322	98.85 268	99.76 108	99.62 116	99.83 84	99.64 195	98.54 173	99.97 35	99.15 129	99.99 16	99.68 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 83	99.47 92	99.76 69	99.58 198	99.64 115	99.30 144	99.63 180	99.61 120	99.71 141	99.56 249	98.76 142	99.96 56	99.14 135	99.92 108	99.68 97

MVSTER		98.47 287	98.22 293	99.24 267	99.06 359	98.35 305	99.08 223	99.46 269	99.27 177	99.75 122	99.66 188	88.61 391	99.85 252	99.14 135	99.92 108	99.52 208

Anonymous20231206		99.35 135	99.31 128	99.47 197	99.74 138	99.06 243	99.28 153	99.74 119	99.23 185	99.72 136	99.53 260	97.63 262	99.88 201	99.11 137	99.84 168	99.48 224

Syy-MVS		98.17 312	97.85 324	99.15 277	98.50 407	98.79 268	98.60 297	99.21 331	97.89 333	96.76 409	96.37 432	95.47 324	99.57 397	99.10 138	98.73 378	99.09 326

ttmdpeth		99.48 94	99.55 82	99.29 253	99.76 120	98.16 316	99.33 133	99.95 31	99.79 73	99.36 258	99.89 38	99.13 91	99.77 328	99.09 139	99.64 266	99.93 20

MVS_Test		99.28 149	99.31 128	99.19 272	99.35 293	98.79 268	99.36 127	99.49 262	99.17 197	99.21 292	99.67 183	98.78 139	99.66 378	99.09 139	99.66 262	99.10 321

testgi		99.29 148	99.26 144	99.37 231	99.75 132	98.81 265	98.84 269	99.89 48	98.38 294	99.75 122	99.04 360	99.36 64	99.86 234	99.08 141	99.25 340	99.45 233

1112_ss		99.05 210	98.84 235	99.67 115	99.66 174	99.29 202	98.52 314	99.82 76	97.65 345	99.43 239	99.16 344	96.42 303	99.91 150	99.07 142	99.84 168	99.80 53

CANet_DTU		98.91 237	98.85 233	99.09 286	98.79 390	98.13 317	98.18 340	99.31 308	99.48 139	98.86 332	99.51 264	96.56 297	99.95 66	99.05 143	99.95 84	99.19 302

Baseline_NR-MVSNet		99.49 92	99.37 114	99.82 39	99.91 31	99.84 24	98.83 271	99.86 57	99.68 97	99.65 163	99.88 47	97.67 256	99.87 215	99.03 144	99.86 158	99.76 71

FMVSNet2		99.35 135	99.28 140	99.55 174	99.49 250	99.35 193	99.45 109	99.57 218	99.44 151	99.70 145	99.74 134	97.21 277	99.87 215	99.03 144	99.94 97	99.44 238

Test_1112_low_res		98.95 234	98.73 244	99.63 142	99.68 167	99.15 229	98.09 351	99.80 88	97.14 371	99.46 233	99.40 293	96.11 314	99.89 187	99.01 146	99.84 168	99.84 42

VDD-MVS		99.20 175	99.11 168	99.44 207	99.43 273	98.98 248	99.50 96	98.32 386	99.80 71	99.56 202	99.69 168	96.99 287	99.85 252	98.99 147	99.73 233	99.50 215

DeepC-MVS	98.90 4	99.62 69	99.61 64	99.67 115	99.72 144	99.44 164	99.24 166	99.71 135	99.27 177	99.93 41	99.90 33	99.70 24	99.93 102	98.99 147	99.99 16	99.64 132
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 94	99.47 92	99.51 185	99.77 116	99.41 177	98.81 276	99.66 160	99.42 161	99.75 122	99.66 188	99.20 81	99.76 331	98.98 149	99.99 16	99.36 261

EPNet_dtu		97.62 333	97.79 327	97.11 391	96.67 426	92.31 414	98.51 315	98.04 391	99.24 183	95.77 418	99.47 278	93.78 341	99.66 378	98.98 149	99.62 270	99.37 258
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 140	99.32 126	99.39 225	99.67 173	98.77 270	98.57 306	99.81 85	99.61 120	99.48 227	99.41 289	98.47 184	99.86 234	98.97 151	99.90 119	99.53 198
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		99.40 121	99.31 128	99.68 112	99.43 273	99.55 143	99.73 27	99.50 258	99.46 146	99.88 65	99.36 306	97.54 263	99.87 215	98.97 151	99.87 150	99.63 137

GBi-Net		99.42 115	99.31 128	99.73 93	99.49 250	99.77 56	99.68 46	99.70 140	99.44 151	99.62 177	99.83 76	97.21 277	99.90 168	98.96 153	99.90 119	99.53 198

FMVSNet5		97.80 325	97.25 342	99.42 213	98.83 384	98.97 250	99.38 120	99.80 88	98.87 236	99.25 283	99.69 168	80.60 413	99.91 150	98.96 153	99.90 119	99.38 255

test1		99.42 115	99.31 128	99.73 93	99.49 250	99.77 56	99.68 46	99.70 140	99.44 151	99.62 177	99.83 76	97.21 277	99.90 168	98.96 153	99.90 119	99.53 198

FMVSNet3		98.80 251	98.63 252	99.32 246	99.13 345	98.72 273	99.10 216	99.48 263	99.23 185	99.62 177	99.64 195	92.57 353	99.86 234	98.96 153	99.90 119	99.39 253

UnsupCasMVSNet_eth		98.83 247	98.57 259	99.59 159	99.68 167	99.45 162	98.99 248	99.67 155	99.48 139	99.55 207	99.36 306	94.92 327	99.86 234	98.95 157	96.57 416	99.45 233

CHOSEN 280x420		98.41 292	98.41 275	98.40 347	99.34 302	95.89 388	96.94 410	99.44 274	98.80 248	99.25 283	99.52 262	93.51 345	99.98 21	98.94 158	99.98 43	99.32 271

TDRefinement		99.72 41	99.70 45	99.77 62	99.90 37	99.85 19	99.86 6	99.92 35	99.69 95	99.78 106	99.92 25	99.37 61	99.88 201	98.93 159	99.95 84	99.60 162

alignmvs		98.28 302	97.96 313	99.25 265	99.12 347	98.93 257	99.03 235	98.42 379	99.64 111	98.72 347	97.85 412	90.86 375	99.62 388	98.88 160	99.13 346	99.19 302

MGCFI-Net		99.02 216	99.01 201	99.06 293	99.11 352	98.60 287	99.63 61	99.67 155	99.63 113	98.58 359	97.65 415	99.07 100	99.57 397	98.85 161	98.92 362	99.03 343

sss		98.90 239	98.77 243	99.27 259	99.48 255	98.44 296	98.72 289	99.32 304	97.94 331	99.37 257	99.35 311	96.31 309	99.91 150	98.85 161	99.63 269	99.47 228

xiu_mvs_v2_base		99.02 216	99.11 168	98.77 328	99.37 287	98.09 322	98.13 346	99.51 254	99.47 143	99.42 242	98.54 398	99.38 59	99.97 35	98.83 163	99.33 329	98.24 401

PS-MVSNAJ		99.00 224	99.08 179	98.76 329	99.37 287	98.10 321	98.00 362	99.51 254	99.47 143	99.41 248	98.50 400	99.28 71	99.97 35	98.83 163	99.34 328	98.20 405

D2MVS		99.22 168	99.19 152	99.29 253	99.69 159	98.74 272	98.81 276	99.41 280	98.55 275	99.68 151	99.69 168	98.13 224	99.87 215	98.82 165	99.98 43	99.24 286

PatchT		98.45 289	98.32 285	98.83 323	98.94 373	98.29 306	99.24 166	98.82 356	99.84 58	99.08 309	99.76 125	91.37 364	99.94 82	98.82 165	99.00 357	98.26 400

testf1		99.63 63	99.60 67	99.72 99	99.94 18	99.95 2	99.47 105	99.89 48	99.43 157	99.88 65	99.80 93	99.26 75	99.90 168	98.81 167	99.88 138	99.32 271

APD_test2		99.63 63	99.60 67	99.72 99	99.94 18	99.95 2	99.47 105	99.89 48	99.43 157	99.88 65	99.80 93	99.26 75	99.90 168	98.81 167	99.88 138	99.32 271

sasdasda		99.02 216	99.00 205	99.09 286	99.10 354	98.70 274	99.61 70	99.66 160	99.63 113	98.64 353	97.65 415	99.04 106	99.54 401	98.79 169	98.92 362	99.04 341

Effi-MVS+		99.06 207	98.97 216	99.34 238	99.31 309	98.98 248	98.31 332	99.91 41	98.81 246	98.79 341	98.94 376	99.14 89	99.84 267	98.79 169	98.74 375	99.20 299

canonicalmvs		99.02 216	99.00 205	99.09 286	99.10 354	98.70 274	99.61 70	99.66 160	99.63 113	98.64 353	97.65 415	99.04 106	99.54 401	98.79 169	98.92 362	99.04 341

VDDNet		98.97 228	98.82 238	99.42 213	99.71 147	98.81 265	99.62 64	98.68 363	99.81 68	99.38 256	99.80 93	94.25 335	99.85 252	98.79 169	99.32 331	99.59 169

CR-MVSNet		98.35 299	98.20 295	98.83 323	99.05 360	98.12 318	99.30 144	99.67 155	97.39 359	99.16 298	99.79 103	91.87 361	99.91 150	98.78 173	98.77 371	98.44 394

test_method		91.72 389	92.32 392	89.91 407	93.49 430	70.18 433	90.28 421	99.56 223	61.71 425	95.39 420	99.52 262	93.90 337	99.94 82	98.76 174	98.27 393	99.62 148

RPMNet		98.60 270	98.53 265	98.83 323	99.05 360	98.12 318	99.30 144	99.62 183	99.86 49	99.16 298	99.74 134	92.53 355	99.92 128	98.75 175	98.77 371	98.44 394

pmmvs4		99.13 194	99.06 185	99.36 235	99.57 208	99.10 238	98.01 360	99.25 321	98.78 251	99.58 191	99.44 285	98.24 212	99.76 331	98.74 176	99.93 104	99.22 292

tttt0517		97.62 333	97.20 343	98.90 316	99.76 120	97.40 354	99.48 102	94.36 417	99.06 214	99.70 145	99.49 271	84.55 407	99.94 82	98.73 177	99.65 264	99.36 261

EPP-MVSNet		99.17 187	99.00 205	99.66 122	99.80 89	99.43 168	99.70 35	99.24 324	99.48 139	99.56 202	99.77 122	94.89 328	99.93 102	98.72 178	99.89 129	99.63 137

Anonymous20240529		99.42 115	99.34 121	99.65 128	99.53 230	99.60 131	99.63 61	99.39 290	99.47 143	99.76 117	99.78 113	98.13 224	99.86 234	98.70 179	99.68 253	99.49 220

ACMH	98.42 6	99.59 73	99.54 83	99.72 99	99.86 54	99.62 122	99.56 84	99.79 94	98.77 253	99.80 96	99.85 65	99.64 28	99.85 252	98.70 179	99.89 129	99.70 85
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 143	99.28 140	99.47 197	99.57 208	99.39 181	99.78 14	99.43 277	98.87 236	99.57 194	99.82 83	98.06 229	99.87 215	98.69 181	99.73 233	99.15 310

LFMVS		98.46 288	98.19 298	99.26 262	99.24 326	98.52 292	99.62 64	96.94 407	99.87 46	99.31 274	99.58 238	91.04 369	99.81 307	98.68 182	99.42 318	99.45 233

WR-MVS		99.11 199	98.93 221	99.66 122	99.30 313	99.42 171	98.42 325	99.37 295	99.04 215	99.57 194	99.20 342	96.89 289	99.86 234	98.66 183	99.87 150	99.70 85

mvsmamba		99.08 203	98.95 219	99.45 203	99.36 290	99.18 226	99.39 117	98.81 357	99.37 164	99.35 260	99.70 161	96.36 308	99.94 82	98.66 183	99.59 284	99.22 292

RRT-MVS		99.08 203	99.00 205	99.33 241	99.27 320	98.65 282	99.62 64	99.93 33	99.66 105	99.67 156	99.82 83	95.27 326	99.93 102	98.64 185	99.09 350	99.41 249

Anonymous202405211		98.75 255	98.46 269	99.63 142	99.34 302	99.66 106	99.47 105	97.65 399	99.28 176	99.56 202	99.50 267	93.15 347	99.84 267	98.62 186	99.58 286	99.40 251

EPNet		98.13 313	97.77 328	99.18 274	94.57 429	97.99 328	99.24 166	97.96 393	99.74 80	97.29 402	99.62 213	93.13 348	99.97 35	98.59 187	99.83 176	99.58 174
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 210	99.09 177	98.91 310	99.21 331	98.36 304	98.82 275	99.47 266	98.85 239	98.90 327	99.56 249	98.78 139	99.09 416	98.57 188	99.68 253	99.26 283

Patchmatch-RL test		98.60 270	98.36 280	99.33 241	99.77 116	99.07 241	98.27 334	99.87 54	98.91 231	99.74 130	99.72 145	90.57 380	99.79 317	98.55 189	99.85 163	99.11 319

pmmvs3		98.08 316	97.80 325	98.91 310	99.41 280	97.69 345	97.87 375	99.66 160	95.87 390	99.50 224	99.51 264	90.35 382	99.97 35	98.55 189	99.47 311	99.08 332

ETV-MVS		99.18 182	99.18 153	99.16 275	99.34 302	99.28 204	99.12 208	99.79 94	99.48 139	98.93 321	98.55 397	99.40 54	99.93 102	98.51 191	99.52 303	98.28 399

jason		99.16 188	99.11 168	99.32 246	99.75 132	98.44 296	98.26 336	99.39 290	98.70 261	99.74 130	99.30 320	98.54 173	99.97 35	98.48 192	99.82 185	99.55 184
jason: jason.
APDe-MVS		99.48 94	99.36 117	99.85 28	99.55 222	99.81 42	99.50 96	99.69 147	98.99 218	99.75 122	99.71 153	98.79 137	99.93 102	98.46 193	99.85 163	99.80 53
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CL-MVSNet_self_test		98.71 261	98.56 263	99.15 277	99.22 329	98.66 279	97.14 405	99.51 254	98.09 320	99.54 209	99.27 326	96.87 290	99.74 338	98.43 194	98.96 359	99.03 343

our_test_3		98.85 246	99.09 177	98.13 360	99.66 174	94.90 401	97.72 380	99.58 216	99.07 212	99.64 164	99.62 213	98.19 220	99.93 102	98.41 195	99.95 84	99.55 184

Gipuma		99.57 74	99.59 69	99.49 191	99.98 3	99.71 87	99.72 30	99.84 69	99.81 68	99.94 38	99.78 113	98.91 124	99.71 347	98.41 195	99.95 84	99.05 339
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 343	96.91 353	98.74 330	97.72 422	97.57 347	97.60 386	97.36 405	98.00 323	99.21 292	98.02 408	90.04 385	99.79 317	98.37 197	95.89 421	98.86 366

PM-MVS		99.36 133	99.29 138	99.58 162	99.83 66	99.66 106	98.95 256	99.86 57	98.85 239	99.81 92	99.73 138	98.40 197	99.92 128	98.36 198	99.83 176	99.17 306

baseline1		97.73 328	97.33 339	98.96 301	99.30 313	97.73 343	99.40 115	98.42 379	99.33 170	99.46 233	99.21 340	91.18 367	99.82 292	98.35 199	91.26 424	99.32 271

MVS-HIRNet		97.86 322	98.22 293	96.76 393	99.28 318	91.53 420	98.38 327	92.60 423	99.13 205	99.31 274	99.96 15	97.18 281	99.68 368	98.34 200	99.83 176	99.07 337

GA-MVS		97.99 321	97.68 331	98.93 307	99.52 237	98.04 326	97.19 404	99.05 347	98.32 307	98.81 337	98.97 372	89.89 387	99.41 412	98.33 201	99.05 353	99.34 267

Fast-Effi-MVS+		99.02 216	98.87 231	99.46 200	99.38 285	99.50 149	99.04 232	99.79 94	97.17 369	98.62 355	98.74 389	99.34 65	99.95 66	98.32 202	99.41 319	98.92 359

MDA-MVSNet_test_wron		98.95 234	98.99 212	98.85 319	99.64 179	97.16 360	98.23 338	99.33 302	98.93 228	99.56 202	99.66 188	97.39 270	99.83 282	98.29 203	99.88 138	99.55 184

N_pmnet		98.73 258	98.53 265	99.35 237	99.72 144	98.67 276	98.34 329	94.65 416	98.35 301	99.79 102	99.68 179	98.03 230	99.93 102	98.28 204	99.92 108	99.44 238

ET-MVSNet_ETH3D		96.78 355	96.07 364	98.91 310	99.26 323	97.92 335	97.70 382	96.05 412	97.96 330	92.37 424	98.43 401	87.06 395	99.90 168	98.27 205	97.56 410	98.91 360

thisisatest0530		97.45 339	96.95 350	98.94 304	99.68 167	97.73 343	99.09 220	94.19 419	98.61 271	99.56 202	99.30 320	84.30 408	99.93 102	98.27 205	99.54 298	99.16 308

YYNet1		98.95 234	98.99 212	98.84 321	99.64 179	97.14 362	98.22 339	99.32 304	98.92 230	99.59 189	99.66 188	97.40 268	99.83 282	98.27 205	99.90 119	99.55 184

reproduce_model		99.50 88	99.40 108	99.83 34	99.60 188	99.83 29	99.12 208	99.68 150	99.49 138	99.80 96	99.79 103	99.01 109	99.93 102	98.24 208	99.82 185	99.73 76

ACMM	98.09 11	99.46 103	99.38 111	99.72 99	99.80 89	99.69 99	99.13 204	99.65 170	98.99 218	99.64 164	99.72 145	99.39 55	99.86 234	98.23 209	99.81 195	99.60 162
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 231	98.87 231	99.24 267	99.57 208	98.40 299	98.12 347	99.18 335	98.28 309	99.63 168	99.13 346	98.02 231	99.97 35	98.22 210	99.69 248	99.35 264

3Dnovator	99.15 2	99.43 112	99.36 117	99.65 128	99.39 282	99.42 171	99.70 35	99.56 223	99.23 185	99.35 260	99.80 93	99.17 84	99.95 66	98.21 211	99.84 168	99.59 169

Fast-Effi-MVS+-dtu		99.20 175	99.12 165	99.43 211	99.25 324	99.69 99	99.05 227	99.82 76	99.50 136	98.97 317	99.05 358	98.98 114	99.98 21	98.20 212	99.24 342	98.62 380

MS-PatchMatch		99.00 224	98.97 216	99.09 286	99.11 352	98.19 312	98.76 285	99.33 302	98.49 284	99.44 235	99.58 238	98.21 217	99.69 356	98.20 212	99.62 270	99.39 253

TSAR-MVS + GP.		99.12 196	99.04 195	99.38 228	99.34 302	99.16 227	98.15 343	99.29 312	98.18 316	99.63 168	99.62 213	99.18 83	99.68 368	98.20 212	99.74 227	99.30 277

DP-MVS		99.48 94	99.39 109	99.74 84	99.57 208	99.62 122	99.29 151	99.61 190	99.87 46	99.74 130	99.76 125	98.69 151	99.87 215	98.20 212	99.80 202	99.75 74

MVP-Stereo		99.16 188	99.08 179	99.43 211	99.48 255	99.07 241	99.08 223	99.55 229	98.63 267	99.31 274	99.68 179	98.19 220	99.78 320	98.18 216	99.58 286	99.45 233
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 112	99.30 133	99.80 49	99.83 66	99.81 42	99.52 89	99.70 140	98.35 301	99.51 222	99.50 267	99.31 67	99.88 201	98.18 216	99.84 168	99.69 91

MDA-MVSNet-bldmvs		99.06 207	99.05 189	99.07 291	99.80 89	97.83 338	98.89 262	99.72 132	99.29 173	99.63 168	99.70 161	96.47 301	99.89 187	98.17 218	99.82 185	99.50 215

JIA-IIPM		98.06 317	97.92 320	98.50 342	98.59 403	97.02 364	98.80 279	98.51 374	99.88 45	97.89 389	99.87 53	91.89 360	99.90 168	98.16 219	97.68 409	98.59 383

EIA-MVS		99.12 196	99.01 201	99.45 203	99.36 290	99.62 122	99.34 129	99.79 94	98.41 290	98.84 334	98.89 380	98.75 144	99.84 267	98.15 220	99.51 304	98.89 363

miper_lstm_enhance		98.65 266	98.60 253	98.82 326	99.20 334	97.33 356	97.78 378	99.66 160	99.01 217	99.59 189	99.50 267	94.62 332	99.85 252	98.12 221	99.90 119	99.26 283

reproduce-ours		99.46 103	99.35 119	99.82 39	99.56 219	99.83 29	99.05 227	99.65 170	99.45 149	99.78 106	99.78 113	98.93 119	99.93 102	98.11 222	99.81 195	99.70 85

our_new_method		99.46 103	99.35 119	99.82 39	99.56 219	99.83 29	99.05 227	99.65 170	99.45 149	99.78 106	99.78 113	98.93 119	99.93 102	98.11 222	99.81 195	99.70 85

Effi-MVS+-dtu		99.07 206	98.92 225	99.52 182	98.89 378	99.78 51	99.15 196	99.66 160	99.34 168	98.92 324	99.24 336	97.69 254	99.98 21	98.11 222	99.28 336	98.81 370

tpm		97.15 347	96.95 350	97.75 374	98.91 374	94.24 404	99.32 136	97.96 393	97.71 343	98.29 371	99.32 315	86.72 401	99.92 128	98.10 225	96.24 419	99.09 326

DeepPCF-MVS	98.42 6	99.18 182	99.02 198	99.67 115	99.22 329	99.75 71	97.25 402	99.47 266	98.72 258	99.66 161	99.70 161	99.29 69	99.63 387	98.07 226	99.81 195	99.62 148

ppachtmachnet_test		98.89 242	99.12 165	98.20 358	99.66 174	95.24 397	97.63 384	99.68 150	99.08 210	99.78 106	99.62 213	98.65 159	99.88 201	98.02 227	99.96 71	99.48 224

tpmrst		97.73 328	98.07 306	96.73 395	98.71 399	92.00 415	99.10 216	98.86 353	98.52 280	98.92 324	99.54 258	91.90 359	99.82 292	98.02 227	99.03 355	98.37 396

CSCG		99.37 130	99.29 138	99.60 157	99.71 147	99.46 157	99.43 113	99.85 63	98.79 249	99.41 248	99.60 230	98.92 122	99.92 128	98.02 227	99.92 108	99.43 244

eth_miper_zixun_eth		98.68 264	98.71 246	98.60 337	99.10 354	96.84 369	97.52 392	99.54 235	98.94 225	99.58 191	99.48 274	96.25 312	99.76 331	98.01 230	99.93 104	99.21 295

Patchmtry		98.78 252	98.54 264	99.49 191	98.89 378	99.19 224	99.32 136	99.67 155	99.65 108	99.72 136	99.79 103	91.87 361	99.95 66	98.00 231	99.97 58	99.33 268

PVSNet_BlendedMVS		99.03 214	99.01 201	99.09 286	99.54 224	97.99 328	98.58 302	99.82 76	97.62 346	99.34 264	99.71 153	98.52 180	99.77 328	97.98 232	99.97 58	99.52 208

PVSNet_Blended		98.70 262	98.59 255	99.02 296	99.54 224	97.99 328	97.58 387	99.82 76	95.70 394	99.34 264	98.98 370	98.52 180	99.77 328	97.98 232	99.83 176	99.30 277

cl____		98.54 278	98.41 275	98.92 308	99.03 364	97.80 341	97.46 394	99.59 207	98.90 232	99.60 186	99.46 281	93.85 339	99.78 320	97.97 234	99.89 129	99.17 306

DIV-MVS_self_test		98.54 278	98.42 274	98.92 308	99.03 364	97.80 341	97.46 394	99.59 207	98.90 232	99.60 186	99.46 281	93.87 338	99.78 320	97.97 234	99.89 129	99.18 304

AUN-MVS		97.82 324	97.38 338	99.14 280	99.27 320	98.53 290	98.72 289	99.02 348	98.10 318	97.18 405	99.03 364	89.26 389	99.85 252	97.94 236	97.91 405	99.03 343

FA-MVS(test-final)		98.52 280	98.32 285	99.10 285	99.48 255	98.67 276	99.77 16	98.60 370	97.35 361	99.63 168	99.80 93	93.07 349	99.84 267	97.92 237	99.30 333	98.78 373

ambc				99.20 271	99.35 293	98.53 290	99.17 188	99.46 269		99.67 156	99.80 93	98.46 187	99.70 350	97.92 237	99.70 244	99.38 255

USDC		98.96 231	98.93 221	99.05 294	99.54 224	97.99 328	97.07 408	99.80 88	98.21 313	99.75 122	99.77 122	98.43 190	99.64 386	97.90 239	99.88 138	99.51 210

OPM-MVS		99.26 155	99.13 161	99.63 142	99.70 155	99.61 128	98.58 302	99.48 263	98.50 282	99.52 216	99.63 206	99.14 89	99.76 331	97.89 240	99.77 216	99.51 210
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 145	99.17 154	99.77 62	99.69 159	99.80 46	99.14 198	99.31 308	99.16 199	99.62 177	99.61 222	98.35 201	99.91 150	97.88 241	99.72 239	99.61 158
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 34	99.70 155	99.79 48	99.14 198	99.61 190					99.92 128	97.88 241	99.72 239	99.77 66

c3_l		98.72 259	98.71 246	98.72 331	99.12 347	97.22 359	97.68 383	99.56 223	98.90 232	99.54 209	99.48 274	96.37 307	99.73 341	97.88 241	99.88 138	99.21 295

3Dnovator+	98.92 3	99.35 135	99.24 148	99.67 115	99.35 293	99.47 153	99.62 64	99.50 258	99.44 151	99.12 305	99.78 113	98.77 141	99.94 82	97.87 244	99.72 239	99.62 148

miper_ehance_all_eth		98.59 273	98.59 255	98.59 338	98.98 370	97.07 363	97.49 393	99.52 249	98.50 282	99.52 216	99.37 302	96.41 305	99.71 347	97.86 245	99.62 270	99.00 350

WTY-MVS		98.59 273	98.37 279	99.26 262	99.43 273	98.40 299	98.74 287	99.13 342	98.10 318	99.21 292	99.24 336	94.82 329	99.90 168	97.86 245	98.77 371	99.49 220

APD_test1		99.36 133	99.28 140	99.61 154	99.89 39	99.89 10	99.32 136	99.74 119	99.18 192	99.69 148	99.75 130	98.41 193	99.84 267	97.85 247	99.70 244	99.10 321

SED-MVS		99.40 121	99.28 140	99.77 62	99.69 159	99.82 37	99.20 176	99.54 235	99.13 205	99.82 85	99.63 206	98.91 124	99.92 128	97.85 247	99.70 244	99.58 174

test_241102_TWO								99.54 235	99.13 205	99.76 117	99.63 206	98.32 206	99.92 128	97.85 247	99.69 248	99.75 74

MVS_111021_HR		99.12 196	99.02 198	99.40 222	99.50 245	99.11 233	97.92 371	99.71 135	98.76 256	99.08 309	99.47 278	99.17 84	99.54 401	97.85 247	99.76 218	99.54 193

MTAPA		99.35 135	99.20 151	99.80 49	99.81 82	99.81 42	99.33 133	99.53 244	99.27 177	99.42 242	99.63 206	98.21 217	99.95 66	97.83 251	99.79 207	99.65 122

MSC_two_6792asdad				99.74 84	99.03 364	99.53 146		99.23 325					99.92 128	97.77 252	99.69 248	99.78 62

No_MVS				99.74 84	99.03 364	99.53 146		99.23 325					99.92 128	97.77 252	99.69 248	99.78 62

TESTMET0.1,1		96.24 369	95.84 370	97.41 382	98.24 414	93.84 407	97.38 396	95.84 413	98.43 287	97.81 394	98.56 396	79.77 417	99.89 187	97.77 252	98.77 371	98.52 388

ACMH+	98.40 8	99.50 88	99.43 103	99.71 104	99.86 54	99.76 63	99.32 136	99.77 103	99.53 132	99.77 114	99.76 125	99.26 75	99.78 320	97.77 252	99.88 138	99.60 162

IU-MVS					99.69 159	99.77 56		99.22 328	97.50 353	99.69 148				97.75 256	99.70 244	99.77 66

114514_t		98.49 285	98.11 303	99.64 135	99.73 141	99.58 137	99.24 166	99.76 108	89.94 417	99.42 242	99.56 249	97.76 251	99.86 234	97.74 257	99.82 185	99.47 228

DVP-MVS++		99.38 127	99.25 146	99.77 62	99.03 364	99.77 56	99.74 24	99.61 190	99.18 192	99.76 117	99.61 222	99.00 110	99.92 128	97.72 258	99.60 280	99.62 148

test_0728_THIRD									99.18 192	99.62 177	99.61 222	98.58 167	99.91 150	97.72 258	99.80 202	99.77 66

EGC-MVSNET		89.05 391	85.52 394	99.64 135	99.89 39	99.78 51	99.56 84	99.52 249	24.19 426	49.96 427	99.83 76	99.15 86	99.92 128	97.71 260	99.85 163	99.21 295

miper_enhance_ethall		98.03 318	97.94 318	98.32 352	98.27 413	96.43 376	96.95 409	99.41 280	96.37 385	99.43 239	98.96 374	94.74 330	99.69 356	97.71 260	99.62 270	98.83 369

TSAR-MVS + MP.		99.34 140	99.24 148	99.63 142	99.82 73	99.37 186	99.26 159	99.35 299	98.77 253	99.57 194	99.70 161	99.27 74	99.88 201	97.71 260	99.75 220	99.65 122
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 336	97.28 340	98.40 347	98.37 411	96.75 370	97.24 403	99.37 295	97.31 363	99.41 248	99.22 338	87.30 393	99.37 413	97.70 263	99.62 270	99.08 332

MP-MVS-pluss		99.14 192	98.92 225	99.80 49	99.83 66	99.83 29	98.61 295	99.63 180	96.84 378	99.44 235	99.58 238	98.81 132	99.91 150	97.70 263	99.82 185	99.67 105
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 149	99.11 168	99.79 56	99.75 132	99.81 42	98.95 256	99.53 244	98.27 310	99.53 214	99.73 138	98.75 144	99.87 215	97.70 263	99.83 176	99.68 97

UnsupCasMVSNet_bld		98.55 277	98.27 291	99.40 222	99.56 219	99.37 186	97.97 367	99.68 150	97.49 354	99.08 309	99.35 311	95.41 325	99.82 292	97.70 263	98.19 397	99.01 349

MVS_111021_LR		99.13 194	99.03 197	99.42 213	99.58 198	99.32 198	97.91 373	99.73 123	98.68 262	99.31 274	99.48 274	99.09 95	99.66 378	97.70 263	99.77 216	99.29 280

IS-MVSNet		99.03 214	98.85 233	99.55 174	99.80 89	99.25 211	99.73 27	99.15 339	99.37 164	99.61 183	99.71 153	94.73 331	99.81 307	97.70 263	99.88 138	99.58 174

test-LLR		97.15 347	96.95 350	97.74 375	98.18 416	95.02 399	97.38 396	96.10 409	98.00 323	97.81 394	98.58 393	90.04 385	99.91 150	97.69 269	98.78 369	98.31 397

test-mter		96.23 370	95.73 372	97.74 375	98.18 416	95.02 399	97.38 396	96.10 409	97.90 332	97.81 394	98.58 393	79.12 420	99.91 150	97.69 269	98.78 369	98.31 397

MonoMVSNet		98.23 307	98.32 285	97.99 363	98.97 371	96.62 372	99.49 100	98.42 379	99.62 116	99.40 253	99.79 103	95.51 323	98.58 422	97.68 271	95.98 420	98.76 376

XVS		99.27 153	99.11 168	99.75 79	99.71 147	99.71 87	99.37 124	99.61 190	99.29 173	98.76 344	99.47 278	98.47 184	99.88 201	97.62 272	99.73 233	99.67 105

X-MVStestdata		96.09 373	94.87 385	99.75 79	99.71 147	99.71 87	99.37 124	99.61 190	99.29 173	98.76 344	61.30 435	98.47 184	99.88 201	97.62 272	99.73 233	99.67 105

SMA-MVS		99.19 178	99.00 205	99.73 93	99.46 265	99.73 80	99.13 204	99.52 249	97.40 358	99.57 194	99.64 195	98.93 119	99.83 282	97.61 274	99.79 207	99.63 137
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		96.71 358	96.79 357	96.46 399	98.90 375	90.71 425	99.41 114	98.68 363	94.69 407	98.14 381	99.34 314	86.32 403	99.80 314	97.60 275	98.07 403	98.88 364

PVSNet	97.47 15	98.42 291	98.44 272	98.35 349	99.46 265	96.26 380	96.70 413	99.34 301	97.68 344	99.00 316	99.13 346	97.40 268	99.72 343	97.59 276	99.68 253	99.08 332

new_pmnet		98.88 243	98.89 229	98.84 321	99.70 155	97.62 346	98.15 343	99.50 258	97.98 326	99.62 177	99.54 258	98.15 223	99.94 82	97.55 277	99.84 168	98.95 354

IB-MVS	95.41 20	95.30 387	94.46 391	97.84 371	98.76 395	95.33 395	97.33 399	96.07 411	96.02 389	95.37 421	97.41 419	76.17 422	99.96 56	97.54 278	95.44 423	98.22 402
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		99.24 159	99.11 168	99.61 154	98.38 410	99.79 48	99.57 82	99.68 150	99.61 120	99.15 300	99.71 153	98.70 150	99.91 150	97.54 278	99.68 253	99.13 318

ZNCC-MVS		99.22 168	99.04 195	99.77 62	99.76 120	99.73 80	99.28 153	99.56 223	98.19 315	99.14 302	99.29 323	98.84 131	99.92 128	97.53 280	99.80 202	99.64 132

CP-MVS		99.23 160	99.05 189	99.75 79	99.66 174	99.66 106	99.38 120	99.62 183	98.38 294	99.06 313	99.27 326	98.79 137	99.94 82	97.51 281	99.82 185	99.66 114

SD-MVS		99.01 222	99.30 133	98.15 359	99.50 245	99.40 178	98.94 258	99.61 190	99.22 189	99.75 122	99.82 83	99.54 43	95.51 426	97.48 282	99.87 150	99.54 193
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		98.49 285	98.29 290	99.11 283	98.96 372	98.42 298	97.54 388	99.32 304	97.53 351	98.47 366	98.15 407	97.88 241	99.82 292	97.46 283	99.24 342	99.09 326

DeepC-MVS_fast	98.47 5	99.23 160	99.12 165	99.56 171	99.28 318	99.22 218	98.99 248	99.40 287	99.08 210	99.58 191	99.64 195	98.90 127	99.83 282	97.44 284	99.75 220	99.63 137
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 156	99.08 179	99.76 69	99.73 141	99.70 95	99.31 141	99.59 207	98.36 296	99.36 258	99.37 302	98.80 136	99.91 150	97.43 285	99.75 220	99.68 97

ACMMPR		99.23 160	99.06 185	99.76 69	99.74 138	99.69 99	99.31 141	99.59 207	98.36 296	99.35 260	99.38 299	98.61 163	99.93 102	97.43 285	99.75 220	99.67 105

Vis-MVSNet (Re-imp)		98.77 253	98.58 258	99.34 238	99.78 108	98.88 261	99.61 70	99.56 223	99.11 209	99.24 286	99.56 249	93.00 351	99.78 320	97.43 285	99.89 129	99.35 264

MIMVSNet		98.43 290	98.20 295	99.11 283	99.53 230	98.38 303	99.58 79	98.61 368	98.96 222	99.33 266	99.76 125	90.92 371	99.81 307	97.38 288	99.76 218	99.15 310

WB-MVSnew		98.34 301	98.14 301	98.96 301	98.14 419	97.90 336	98.27 334	97.26 406	98.63 267	98.80 339	98.00 410	97.77 249	99.90 168	97.37 289	98.98 358	99.09 326

XVG-OURS-SEG-HR		99.16 188	98.99 212	99.66 122	99.84 62	99.64 115	98.25 337	99.73 123	98.39 293	99.63 168	99.43 286	99.70 24	99.90 168	97.34 290	98.64 382	99.44 238

COLMAP_ROB	98.06 12	99.45 107	99.37 114	99.70 108	99.83 66	99.70 95	99.38 120	99.78 100	99.53 132	99.67 156	99.78 113	99.19 82	99.86 234	97.32 291	99.87 150	99.55 184
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 216	98.81 239	99.65 128	99.58 198	99.49 150	98.58 302	99.07 344	98.40 292	99.04 314	99.25 331	98.51 182	99.80 314	97.31 292	99.51 304	99.65 122

region2R		99.23 160	99.05 189	99.77 62	99.76 120	99.70 95	99.31 141	99.59 207	98.41 290	99.32 269	99.36 306	98.73 148	99.93 102	97.29 293	99.74 227	99.67 105

APD-MVS_3200maxsize		99.31 146	99.16 155	99.74 84	99.53 230	99.75 71	99.27 157	99.61 190	99.19 191	99.57 194	99.64 195	98.76 142	99.90 168	97.29 293	99.62 270	99.56 181

TAPA-MVS	97.92 13	98.03 318	97.55 334	99.46 200	99.47 261	99.44 164	98.50 316	99.62 183	86.79 418	99.07 312	99.26 329	98.26 211	99.62 388	97.28 295	99.73 233	99.31 275
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 153	99.11 168	99.73 93	99.54 224	99.74 77	99.26 159	99.62 183	99.16 199	99.52 216	99.64 195	98.41 193	99.91 150	97.27 296	99.61 277	99.54 193

RE-MVS-def			99.13 161		99.54 224	99.74 77	99.26 159	99.62 183	99.16 199	99.52 216	99.64 195	98.57 168		97.27 296	99.61 277	99.54 193

testing11		96.05 375	95.41 377	97.97 365	98.78 392	95.27 396	98.59 300	98.23 388	98.86 238	96.56 412	96.91 425	75.20 423	99.69 356	97.26 298	98.29 392	98.93 357

test_yl		98.25 304	97.95 314	99.13 281	99.17 340	98.47 293	99.00 243	98.67 365	98.97 220	99.22 290	99.02 365	91.31 365	99.69 356	97.26 298	98.93 360	99.24 286

DCV-MVSNet		98.25 304	97.95 314	99.13 281	99.17 340	98.47 293	99.00 243	98.67 365	98.97 220	99.22 290	99.02 365	91.31 365	99.69 356	97.26 298	98.93 360	99.24 286

PHI-MVS		99.11 199	98.95 219	99.59 159	99.13 345	99.59 133	99.17 188	99.65 170	97.88 335	99.25 283	99.46 281	98.97 116	99.80 314	97.26 298	99.82 185	99.37 258

tfpnnormal		99.43 112	99.38 111	99.60 157	99.87 51	99.75 71	99.59 77	99.78 100	99.71 87	99.90 52	99.69 168	98.85 130	99.90 168	97.25 302	99.78 212	99.15 310

PatchmatchNet		97.65 332	97.80 325	97.18 389	98.82 387	92.49 413	99.17 188	98.39 382	98.12 317	98.79 341	99.58 238	90.71 377	99.89 187	97.23 303	99.41 319	99.16 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 227	98.80 241	99.56 171	99.25 324	99.43 168	98.54 311	99.27 316	98.58 273	98.80 339	99.43 286	98.53 177	99.70 350	97.22 304	99.59 284	99.54 193

testing3		96.48 363	95.63 374	99.01 297	99.23 328	97.81 339	98.90 261	99.10 343	98.72 258	97.84 393	97.92 411	72.44 427	99.85 252	97.21 305	99.33 329	99.35 264

HPM-MVS		99.25 156	99.07 183	99.78 59	99.81 82	99.75 71	99.61 70	99.67 155	97.72 342	99.35 260	99.25 331	99.23 78	99.92 128	97.21 305	99.82 185	99.67 105
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 178	99.00 205	99.76 69	99.76 120	99.68 102	99.38 120	99.54 235	98.34 305	99.01 315	99.50 267	98.53 177	99.93 102	97.18 307	99.78 212	99.66 114

ACMMP		99.25 156	99.08 179	99.74 84	99.79 101	99.68 102	99.50 96	99.65 170	98.07 321	99.52 216	99.69 168	98.57 168	99.92 128	97.18 307	99.79 207	99.63 137
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		96.98 351	96.42 358	98.66 334	99.42 278	97.47 350	97.27 401	94.30 418	97.24 365	99.15 300	98.86 382	85.01 405	99.87 215	97.10 309	99.39 321	98.63 379

XVG-ACMP-BASELINE		99.23 160	99.10 176	99.63 142	99.82 73	99.58 137	98.83 271	99.72 132	98.36 296	99.60 186	99.71 153	98.92 122	99.91 150	97.08 310	99.84 168	99.40 251

MSDG		99.08 203	98.98 215	99.37 231	99.60 188	99.13 230	97.54 388	99.74 119	98.84 242	99.53 214	99.55 256	99.10 93	99.79 317	97.07 311	99.86 158	99.18 304

SteuartSystems-ACMMP		99.30 147	99.14 159	99.76 69	99.87 51	99.66 106	99.18 183	99.60 201	98.55 275	99.57 194	99.67 183	99.03 108	99.94 82	97.01 312	99.80 202	99.69 91
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 371	95.78 371	97.49 378	98.53 405	93.83 408	98.04 357	93.94 421	98.96 222	98.46 367	98.17 406	79.86 415	99.87 215	96.99 313	99.06 351	98.78 373

EPMVS		96.53 361	96.32 359	97.17 390	98.18 416	92.97 412	99.39 117	89.95 427	98.21 313	98.61 356	99.59 235	86.69 402	99.72 343	96.99 313	99.23 344	98.81 370

MSP-MVS		99.04 213	98.79 242	99.81 44	99.78 108	99.73 80	99.35 128	99.57 218	98.54 278	99.54 209	98.99 367	96.81 291	99.93 102	96.97 315	99.53 300	99.77 66
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++		98.96 231	98.70 248	99.74 84	99.52 237	99.71 87	98.86 266	99.19 334	98.47 286	98.59 358	99.06 357	98.08 228	99.91 150	96.94 316	99.60 280	99.60 162

SR-MVS		99.19 178	99.00 205	99.74 84	99.51 239	99.72 85	99.18 183	99.60 201	98.85 239	99.47 229	99.58 238	98.38 198	99.92 128	96.92 317	99.54 298	99.57 179

PGM-MVS		99.20 175	99.01 201	99.77 62	99.75 132	99.71 87	99.16 194	99.72 132	97.99 325	99.42 242	99.60 230	98.81 132	99.93 102	96.91 318	99.74 227	99.66 114

HY-MVS	98.23 9	98.21 311	97.95 314	98.99 298	99.03 364	98.24 307	99.61 70	98.72 361	96.81 379	98.73 346	99.51 264	94.06 336	99.86 234	96.91 318	98.20 395	98.86 366

MDTV_nov1_ep13			97.73 329		98.70 400	90.83 423	99.15 196	98.02 392	98.51 281	98.82 336	99.61 222	90.98 370	99.66 378	96.89 320	98.92 362

GST-MVS		99.16 188	98.96 218	99.75 79	99.73 141	99.73 80	99.20 176	99.55 229	98.22 312	99.32 269	99.35 311	98.65 159	99.91 150	96.86 321	99.74 227	99.62 148

test_post1							99.14 198				51.63 437	89.54 388	99.82 292	96.86 321

SCA		98.11 314	98.36 280	97.36 383	99.20 334	92.99 411	98.17 342	98.49 376	98.24 311	99.10 308	99.57 245	96.01 316	99.94 82	96.86 321	99.62 270	99.14 315

UBG		96.53 361	95.95 366	98.29 356	98.87 381	96.31 379	98.48 318	98.07 390	98.83 243	97.32 400	96.54 430	79.81 416	99.62 388	96.84 324	98.74 375	98.95 354

XVG-OURS		99.21 173	99.06 185	99.65 128	99.82 73	99.62 122	97.87 375	99.74 119	98.36 296	99.66 161	99.68 179	99.71 22	99.90 168	96.84 324	99.88 138	99.43 244

LCM-MVSNet-Re		99.28 149	99.15 158	99.67 115	99.33 307	99.76 63	99.34 129	99.97 20	98.93 228	99.91 49	99.79 103	98.68 152	99.93 102	96.80 326	99.56 289	99.30 277

RPSCF		99.18 182	99.02 198	99.64 135	99.83 66	99.85 19	99.44 111	99.82 76	98.33 306	99.50 224	99.78 113	97.90 239	99.65 384	96.78 327	99.83 176	99.44 238

旧先验2							97.94 369		95.33 398	98.94 320			99.88 201	96.75 328

MDTV_nov1_ep13_2view						91.44 421	99.14 198		97.37 360	99.21 292		91.78 363		96.75 328		99.03 343

CLD-MVS		98.76 254	98.57 259	99.33 241	99.57 208	98.97 250	97.53 390	99.55 229	96.41 383	99.27 281	99.13 346	99.07 100	99.78 320	96.73 330	99.89 129	99.23 290
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 315	97.98 312	98.48 343	99.27 320	96.48 374	99.40 115	99.07 344	98.81 246	99.23 287	99.57 245	90.11 384	99.87 215	96.69 331	99.64 266	99.09 326

baseline2		96.83 354	96.28 360	98.46 345	99.09 357	96.91 367	98.83 271	93.87 422	97.23 366	96.23 417	98.36 402	88.12 392	99.90 168	96.68 332	98.14 400	98.57 386

cascas		96.99 350	96.82 356	97.48 379	97.57 425	95.64 391	96.43 415	99.56 223	91.75 413	97.13 407	97.61 418	95.58 321	98.63 420	96.68 332	99.11 348	98.18 406

PC_three_1452									97.56 347	99.68 151	99.41 289	99.09 95	97.09 423	96.66 334	99.60 280	99.62 148

LPG-MVS_test		99.22 168	99.05 189	99.74 84	99.82 73	99.63 120	99.16 194	99.73 123	97.56 347	99.64 164	99.69 168	99.37 61	99.89 187	96.66 334	99.87 150	99.69 91

LGP-MVS_train				99.74 84	99.82 73	99.63 120		99.73 123	97.56 347	99.64 164	99.69 168	99.37 61	99.89 187	96.66 334	99.87 150	99.69 91

ETVMVS		96.14 372	95.22 382	98.89 317	98.80 388	98.01 327	98.66 293	98.35 385	98.71 260	97.18 405	96.31 434	74.23 426	99.75 335	96.64 337	98.13 402	98.90 361

TinyColmap		98.97 228	98.93 221	99.07 291	99.46 265	98.19 312	97.75 379	99.75 113	98.79 249	99.54 209	99.70 161	98.97 116	99.62 388	96.63 338	99.83 176	99.41 249

LF4IMVS		99.01 222	98.92 225	99.27 259	99.71 147	99.28 204	98.59 300	99.77 103	98.32 307	99.39 255	99.41 289	98.62 161	99.84 267	96.62 339	99.84 168	98.69 378

NCCC		98.82 248	98.57 259	99.58 162	99.21 331	99.31 199	98.61 295	99.25 321	98.65 265	98.43 368	99.26 329	97.86 242	99.81 307	96.55 340	99.27 339	99.61 158

OPU-MVS				99.29 253	99.12 347	99.44 164	99.20 176				99.40 293	99.00 110	98.84 419	96.54 341	99.60 280	99.58 174

F-COLMAP		98.74 256	98.45 271	99.62 151	99.57 208	99.47 153	98.84 269	99.65 170	96.31 386	98.93 321	99.19 343	97.68 255	99.87 215	96.52 342	99.37 324	99.53 198

testing99		95.86 380	95.19 383	97.87 369	98.76 395	95.03 398	98.62 294	98.44 378	98.68 262	96.67 411	96.66 429	74.31 425	99.69 356	96.51 343	98.03 404	98.90 361

ADS-MVSNet2		97.78 326	97.66 333	98.12 361	99.14 343	95.36 394	99.22 173	98.75 360	96.97 374	98.25 373	99.64 195	90.90 372	99.94 82	96.51 343	99.56 289	99.08 332

ADS-MVSNet		97.72 331	97.67 332	97.86 370	99.14 343	94.65 402	99.22 173	98.86 353	96.97 374	98.25 373	99.64 195	90.90 372	99.84 267	96.51 343	99.56 289	99.08 332

PatchMatch-RL		98.68 264	98.47 268	99.30 252	99.44 270	99.28 204	98.14 345	99.54 235	97.12 372	99.11 306	99.25 331	97.80 247	99.70 350	96.51 343	99.30 333	98.93 357

CMPMVS	77.52 23	98.50 283	98.19 298	99.41 220	98.33 412	99.56 140	99.01 240	99.59 207	95.44 396	99.57 194	99.80 93	95.64 319	99.46 411	96.47 347	99.92 108	99.21 295
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 376	95.32 380	98.02 362	98.76 395	95.39 393	98.38 327	98.65 367	98.82 244	96.84 408	96.71 428	75.06 424	99.71 347	96.46 348	98.23 394	98.98 351

SF-MVS		99.10 202	98.93 221	99.62 151	99.58 198	99.51 148	99.13 204	99.65 170	97.97 327	99.42 242	99.61 222	98.86 129	99.87 215	96.45 349	99.68 253	99.49 220

FE-MVS		97.85 323	97.42 337	99.15 277	99.44 270	98.75 271	99.77 16	98.20 389	95.85 391	99.33 266	99.80 93	88.86 390	99.88 201	96.40 350	99.12 347	98.81 370

DPE-MVS		99.14 192	98.92 225	99.82 39	99.57 208	99.77 56	98.74 287	99.60 201	98.55 275	99.76 117	99.69 168	98.23 216	99.92 128	96.39 351	99.75 220	99.76 71
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 423	89.02 429			93.47 409		98.30 403		99.84 267	96.38 352

AllTest		99.21 173	99.07 183	99.63 142	99.78 108	99.64 115	99.12 208	99.83 71	98.63 267	99.63 168	99.72 145	98.68 152	99.75 335	96.38 352	99.83 176	99.51 210

TestCases				99.63 142	99.78 108	99.64 115		99.83 71	98.63 267	99.63 168	99.72 145	98.68 152	99.75 335	96.38 352	99.83 176	99.51 210

testdata				99.42 213	99.51 239	98.93 257		99.30 311	96.20 387	98.87 331	99.40 293	98.33 205	99.89 187	96.29 355	99.28 336	99.44 238

dp		96.86 353	97.07 346	96.24 401	98.68 401	90.30 427	99.19 182	98.38 383	97.35 361	98.23 375	99.59 235	87.23 394	99.82 292	96.27 356	98.73 378	98.59 383

tpmvs		97.39 342	97.69 330	96.52 397	98.41 409	91.76 417	99.30 144	98.94 352	97.74 341	97.85 392	99.55 256	92.40 358	99.73 341	96.25 357	98.73 378	98.06 408

KD-MVS_2432*1600		95.89 377	95.41 377	97.31 386	94.96 427	93.89 405	97.09 406	99.22 328	97.23 366	98.88 328	99.04 360	79.23 418	99.54 401	96.24 358	96.81 414	98.50 392

miper_refine_blended		95.89 377	95.41 377	97.31 386	94.96 427	93.89 405	97.09 406	99.22 328	97.23 366	98.88 328	99.04 360	79.23 418	99.54 401	96.24 358	96.81 414	98.50 392

ACMP	97.51 14	99.05 210	98.84 235	99.67 115	99.78 108	99.55 143	98.88 263	99.66 160	97.11 373	99.47 229	99.60 230	99.07 100	99.89 187	96.18 360	99.85 163	99.58 174
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 239	98.72 245	99.44 207	99.39 282	99.42 171	98.58 302	99.64 178	97.31 363	99.44 235	99.62 213	98.59 165	99.69 356	96.17 361	99.79 207	99.22 292

DP-MVS Recon		98.50 283	98.23 292	99.31 249	99.49 250	99.46 157	98.56 307	99.63 180	94.86 405	98.85 333	99.37 302	97.81 246	99.59 395	96.08 362	99.44 314	98.88 364

tpm cat1		96.78 355	96.98 349	96.16 402	98.85 382	90.59 426	99.08 223	99.32 304	92.37 411	97.73 398	99.46 281	91.15 368	99.69 356	96.07 363	98.80 368	98.21 403

tpm2		96.35 366	96.22 361	96.73 395	98.88 380	91.75 418	99.21 175	98.51 374	93.27 410	97.89 389	99.21 340	84.83 406	99.70 350	96.04 364	98.18 398	98.75 377

dmvs_re		98.69 263	98.48 267	99.31 249	99.55 222	99.42 171	99.54 87	98.38 383	99.32 171	98.72 347	98.71 390	96.76 293	99.21 414	96.01 365	99.35 327	99.31 275

test_0402		99.22 168	99.14 159	99.45 203	99.79 101	99.43 168	99.28 153	99.68 150	99.54 130	99.40 253	99.56 249	99.07 100	99.82 292	96.01 365	99.96 71	99.11 319

ITE_SJBPF				99.38 228	99.63 181	99.44 164		99.73 123	98.56 274	99.33 266	99.53 260	98.88 128	99.68 368	96.01 365	99.65 264	99.02 348

test_prior2							97.95 368		97.87 336	98.05 383	99.05 358	97.90 239		95.99 368	99.49 309

testdata2													99.89 187	95.99 368

原ACMM1				99.37 231	99.47 261	98.87 263		99.27 316	96.74 381	98.26 372	99.32 315	97.93 238	99.82 292	95.96 370	99.38 322	99.43 244

新几何1				99.52 182	99.50 245	99.22 218		99.26 318	95.66 395	98.60 357	99.28 324	97.67 256	99.89 187	95.95 371	99.32 331	99.45 233

MP-MVS		99.06 207	98.83 237	99.76 69	99.76 120	99.71 87	99.32 136	99.50 258	98.35 301	98.97 317	99.48 274	98.37 199	99.92 128	95.95 371	99.75 220	99.63 137
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 386	94.59 389	98.61 336	98.66 402	97.45 352	98.54 311	97.90 396	98.53 279	96.54 413	96.47 431	70.62 430	99.81 307	95.91 373	98.15 399	98.56 387

wuyk23d		97.58 335	99.13 161	92.93 405	99.69 159	99.49 150	99.52 89	99.77 103	97.97 327	99.96 27	99.79 103	99.84 12	99.94 82	95.85 374	99.82 185	79.36 423

HQP_MVS		98.90 239	98.68 249	99.55 174	99.58 198	99.24 215	98.80 279	99.54 235	98.94 225	99.14 302	99.25 331	97.24 275	99.82 292	95.84 375	99.78 212	99.60 162

plane_prior5								99.54 235					99.82 292	95.84 375	99.78 212	99.60 162

无先验							98.01 360	99.23 325	95.83 392				99.85 252	95.79 377		99.44 238

CPTT-MVS		98.74 256	98.44 272	99.64 135	99.61 186	99.38 183	99.18 183	99.55 229	96.49 382	99.27 281	99.37 302	97.11 283	99.92 128	95.74 378	99.67 259	99.62 148

PLC	97.35 16	98.36 296	97.99 310	99.48 195	99.32 308	99.24 215	98.50 316	99.51 254	95.19 401	98.58 359	98.96 374	96.95 288	99.83 282	95.63 379	99.25 340	99.37 258
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 275	98.34 283	99.28 256	99.18 339	99.10 238	98.34 329	99.41 280	98.48 285	98.52 363	98.98 370	97.05 285	99.78 320	95.59 380	99.50 307	98.96 352

1314		98.00 320	97.90 322	98.27 357	98.90 375	97.45 352	99.30 144	99.06 346	94.98 402	97.21 404	99.12 350	98.43 190	99.67 373	95.58 381	98.56 385	97.71 412

PVSNet_0	95.53 19	95.85 381	95.31 381	97.47 380	98.78 392	93.48 410	95.72 417	99.40 287	96.18 388	97.37 399	97.73 413	95.73 318	99.58 396	95.49 382	81.40 425	99.36 261

MAR-MVS		98.24 306	97.92 320	99.19 272	98.78 392	99.65 112	99.17 188	99.14 340	95.36 397	98.04 384	98.81 386	97.47 265	99.72 343	95.47 383	99.06 351	98.21 403
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	98.23 307	97.89 323	99.26 262	99.19 336	99.26 208	99.65 59	99.69 147	91.33 415	98.14 381	99.77 122	98.28 208	99.96 56	95.41 384	99.55 293	98.58 385

train_agg		98.35 299	97.95 314	99.57 168	99.35 293	99.35 193	98.11 349	99.41 280	94.90 403	97.92 387	98.99 367	98.02 231	99.85 252	95.38 385	99.44 314	99.50 215

9.14			98.64 250		99.45 269		98.81 276	99.60 201	97.52 352	99.28 280	99.56 249	98.53 177	99.83 282	95.36 386	99.64 266

APD-MVS		98.87 244	98.59 255	99.71 104	99.50 245	99.62 122	99.01 240	99.57 218	96.80 380	99.54 209	99.63 206	98.29 207	99.91 150	95.24 387	99.71 242	99.61 158
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 377								95.20 388

AdaColmap		98.60 270	98.35 282	99.38 228	99.12 347	99.22 218	98.67 292	99.42 279	97.84 339	98.81 337	99.27 326	97.32 273	99.81 307	95.14 389	99.53 300	99.10 321

test9_res														95.10 390	99.44 314	99.50 215

CDPH-MVS		98.56 276	98.20 295	99.61 154	99.50 245	99.46 157	98.32 331	99.41 280	95.22 399	99.21 292	99.10 354	98.34 203	99.82 292	95.09 391	99.66 262	99.56 181

BH-untuned		98.22 309	98.09 304	98.58 340	99.38 285	97.24 358	98.55 308	98.98 351	97.81 340	99.20 297	98.76 388	97.01 286	99.65 384	94.83 392	98.33 390	98.86 366

BP-MVS														94.73 393

HQP-MVS		98.36 296	98.02 309	99.39 225	99.31 309	98.94 254	97.98 364	99.37 295	97.45 355	98.15 377	98.83 383	96.67 294	99.70 350	94.73 393	99.67 259	99.53 198

QAPM		98.40 294	97.99 310	99.65 128	99.39 282	99.47 153	99.67 50	99.52 249	91.70 414	98.78 343	99.80 93	98.55 171	99.95 66	94.71 395	99.75 220	99.53 198

agg_prior2														94.58 396	99.46 313	99.50 215

myMVS_eth3d		95.63 384	94.73 386	98.34 351	98.50 407	96.36 377	98.60 297	99.21 331	97.89 333	96.76 409	96.37 432	72.10 428	99.57 397	94.38 397	98.73 378	99.09 326

BH-RMVSNet		98.41 292	98.14 301	99.21 269	99.21 331	98.47 293	98.60 297	98.26 387	98.35 301	98.93 321	99.31 318	97.20 280	99.66 378	94.32 398	99.10 349	99.51 210

E-PMN		97.14 349	97.43 336	96.27 400	98.79 390	91.62 419	95.54 418	99.01 350	99.44 151	98.88 328	99.12 350	92.78 352	99.68 368	94.30 399	99.03 355	97.50 413

MG-MVS		98.52 280	98.39 277	98.94 304	99.15 342	97.39 355	98.18 340	99.21 331	98.89 235	99.23 287	99.63 206	97.37 271	99.74 338	94.22 400	99.61 277	99.69 91

API-MVS		98.38 295	98.39 277	98.35 349	98.83 384	99.26 208	99.14 198	99.18 335	98.59 272	98.66 352	98.78 387	98.61 163	99.57 397	94.14 401	99.56 289	96.21 420

PAPM_NR		98.36 296	98.04 307	99.33 241	99.48 255	98.93 257	98.79 282	99.28 315	97.54 350	98.56 362	98.57 395	97.12 282	99.69 356	94.09 402	98.90 366	99.38 255

ZD-MVS					99.43 273	99.61 128		99.43 277	96.38 384	99.11 306	99.07 356	97.86 242	99.92 128	94.04 403	99.49 309

DPM-MVS		98.28 302	97.94 318	99.32 246	99.36 290	99.11 233	97.31 400	98.78 359	96.88 376	98.84 334	99.11 353	97.77 249	99.61 393	94.03 404	99.36 325	99.23 290

gg-mvs-nofinetune		95.87 379	95.17 384	97.97 365	98.19 415	96.95 365	99.69 42	89.23 428	99.89 40	96.24 416	99.94 19	81.19 410	99.51 407	93.99 405	98.20 395	97.44 414

PMVS	92.94 21	98.82 248	98.81 239	98.85 319	99.84 62	97.99 328	99.20 176	99.47 266	99.71 87	99.42 242	99.82 83	98.09 226	99.47 409	93.88 406	99.85 163	99.07 337
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 352	97.28 340	95.99 403	98.76 395	91.03 422	95.26 420	98.61 368	99.34 168	98.92 324	98.88 381	93.79 340	99.66 378	92.87 407	99.05 353	97.30 417

BH-w/o		97.20 346	97.01 348	97.76 373	99.08 358	95.69 390	98.03 359	98.52 373	95.76 393	97.96 386	98.02 408	95.62 320	99.47 409	92.82 408	97.25 413	98.12 407

TR-MVS		97.44 340	97.15 345	98.32 352	98.53 405	97.46 351	98.47 319	97.91 395	96.85 377	98.21 376	98.51 399	96.42 303	99.51 407	92.16 409	97.29 412	97.98 409

OpenMVS_ROB	97.31 17	97.36 344	96.84 354	98.89 317	99.29 315	99.45 162	98.87 265	99.48 263	86.54 420	99.44 235	99.74 134	97.34 272	99.86 234	91.61 410	99.28 336	97.37 416

GG-mvs-BLEND				97.36 383	97.59 423	96.87 368	99.70 35	88.49 429		94.64 422	97.26 422	80.66 412	99.12 415	91.50 411	96.50 418	96.08 422

DeepMVS_CX				97.98 364	99.69 159	96.95 365		99.26 318	75.51 423	95.74 419	98.28 404	96.47 301	99.62 388	91.23 412	97.89 406	97.38 415

PAPR		97.56 336	97.07 346	99.04 295	98.80 388	98.11 320	97.63 384	99.25 321	94.56 408	98.02 385	98.25 405	97.43 267	99.68 368	90.90 413	98.74 375	99.33 268

MVS		95.72 383	94.63 388	98.99 298	98.56 404	97.98 333	99.30 144	98.86 353	72.71 424	97.30 401	99.08 355	98.34 203	99.74 338	89.21 414	98.33 390	99.26 283

thres600view7		96.60 360	96.16 362	97.93 367	99.63 181	96.09 385	99.18 183	97.57 400	98.77 253	98.72 347	97.32 420	87.04 396	99.72 343	88.57 415	98.62 383	97.98 409

FPMVS		96.32 367	95.50 375	98.79 327	99.60 188	98.17 315	98.46 323	98.80 358	97.16 370	96.28 414	99.63 206	82.19 409	99.09 416	88.45 416	98.89 367	99.10 321

PCF-MVS	96.03 18	96.73 357	95.86 369	99.33 241	99.44 270	99.16 227	96.87 411	99.44 274	86.58 419	98.95 319	99.40 293	94.38 334	99.88 201	87.93 417	99.80 202	98.95 354
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 365	96.03 365	97.47 380	99.63 181	95.93 386	99.18 183	97.57 400	98.75 257	98.70 350	97.31 421	87.04 396	99.67 373	87.62 418	98.51 387	96.81 418

tfpn200view9		96.30 368	95.89 367	97.53 377	99.58 198	96.11 383	99.00 243	97.54 403	98.43 287	98.52 363	96.98 423	86.85 398	99.67 373	87.62 418	98.51 387	96.81 418

thres400		96.40 364	95.89 367	97.92 368	99.58 198	96.11 383	99.00 243	97.54 403	98.43 287	98.52 363	96.98 423	86.85 398	99.67 373	87.62 418	98.51 387	97.98 409

thres200		96.09 373	95.68 373	97.33 385	99.48 255	96.22 382	98.53 313	97.57 400	98.06 322	98.37 370	96.73 427	86.84 400	99.61 393	86.99 421	98.57 384	96.16 421

MVE	92.54 22	96.66 359	96.11 363	98.31 354	99.68 167	97.55 348	97.94 369	95.60 414	99.37 164	90.68 425	98.70 391	96.56 297	98.61 421	86.94 422	99.55 293	98.77 375
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 345	96.83 355	98.59 338	99.46 265	97.55 348	99.25 165	96.84 408	98.78 251	97.24 403	97.67 414	97.11 283	98.97 418	86.59 423	98.54 386	99.27 281

PAPM		95.61 385	94.71 387	98.31 354	99.12 347	96.63 371	96.66 414	98.46 377	90.77 416	96.25 415	98.68 392	93.01 350	99.69 356	81.60 424	97.86 408	98.62 380

dongtai		89.37 390	88.91 393	90.76 406	99.19 336	77.46 431	95.47 419	87.82 430	92.28 412	94.17 423	98.82 385	71.22 429	95.54 425	63.85 425	97.34 411	99.27 281

kuosan		85.65 392	84.57 395	88.90 408	97.91 420	77.11 432	96.37 416	87.62 431	85.24 421	85.45 426	96.83 426	69.94 431	90.98 427	45.90 426	95.83 422	98.62 380

test123		29.31 393	33.05 398	18.08 409	25.93 433	12.24 434	97.53 390	10.93 434	11.78 427	24.21 428	50.08 439	21.04 432	8.60 428	23.51 427	32.43 427	33.39 424

testmvs		28.94 394	33.33 396	15.79 410	26.03 432	9.81 435	96.77 412	15.67 433	11.55 428	23.87 429	50.74 438	19.03 433	8.53 429	23.21 428	33.07 426	29.03 425

mmdepth		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

monomultidepth		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

test_blank		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet_test		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

DCPMVS		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

cdsmvs_eth3d_5k		24.88 395	33.17 397	0.00 411	0.00 434	0.00 436	0.00 422	99.62 183	0.00 429	0.00 430	99.13 346	99.82 13	0.00 430	0.00 429	0.00 428	0.00 426

pcd_1.5k_mvsjas		16.61 396	22.14 399	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	99.28 71	0.00 430	0.00 429	0.00 428	0.00 426

sosnet-low-res		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

sosnet		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uncertanet		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

Regformer		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

ab-mvs-re		8.26 407	11.02 410	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	99.16 344	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet		8.33 397	11.11 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	100.00 1	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

FOURS1					99.83 66	99.89 10	99.74 24	99.71 135	99.69 95	99.63 168

test_one_0601					99.63 181	99.76 63		99.55 229	99.23 185	99.31 274	99.61 222	98.59 165

eth-test2					0.00 434

eth-test					0.00 434

test_241102_ONE					99.69 159	99.82 37		99.54 235	99.12 208	99.82 85	99.49 271	98.91 124	99.52 406

save fliter					99.53 230	99.25 211	98.29 333	99.38 294	99.07 212

test0726					99.69 159	99.80 46	99.24 166	99.57 218	99.16 199	99.73 134	99.65 193	98.35 201

GSMVS																99.14 315

test_part2					99.62 185	99.67 104				99.55 207

sam_mvs1												90.81 376				99.14 315

sam_mvs												90.52 381

MTGPA								99.53 244

test_post											52.41 436	90.25 383	99.86 234

patchmatchnet-post											99.62 213	90.58 379	99.94 82

MTMP							99.09 220	98.59 371

TEST9					99.35 293	99.35 193	98.11 349	99.41 280	94.83 406	97.92 387	98.99 367	98.02 231	99.85 252

test_8					99.34 302	99.31 199	98.08 353	99.40 287	94.90 403	97.87 391	98.97 372	98.02 231	99.84 267

agg_prior					99.35 293	99.36 190		99.39 290		97.76 397			99.85 252

test_prior4						99.19 224	98.00 362

test_prior				99.46 200	99.35 293	99.22 218		99.39 290					99.69 356			99.48 224

新几何2							98.04 357

旧先验1					99.49 250	99.29 202		99.26 318			99.39 297	97.67 256			99.36 325	99.46 232

原ACMM2							97.92 371

test222					99.51 239	99.08 240	97.83 377	99.29 312	95.21 400	98.68 351	99.31 318	97.28 274			99.38 322	99.43 244

segment_acmp												98.37 199

testdata1							97.72 380		97.86 338

test12				99.54 179	99.29 315	99.33 196		99.16 338		98.43 368		97.54 263	99.82 292		99.47 311	99.48 224

plane_prior7					99.58 198	99.38 183

plane_prior6					99.47 261	99.26 208						97.24 275

plane_prior4											99.25 331

plane_prior3						99.31 199			98.36 296	99.14 302

plane_prior2							98.80 279		98.94 225

plane_prior1					99.51 239

plane_prior						99.24 215	98.42 325		97.87 336						99.71 242

n2								0.00 435

nn								0.00 435

door-mid								99.83 71

test11								99.29 312

door								99.77 103

HQP5-MVS						98.94 254

HQP-NCC					99.31 309		97.98 364		97.45 355	98.15 377

ACMP_Plane					99.31 309		97.98 364		97.45 355	98.15 377

HQP4-MVS										98.15 377			99.70 350			99.53 198

HQP3-MVS								99.37 295							99.67 259

HQP2-MVS												96.67 294

NP-MVS					99.40 281	99.13 230					98.83 383

ACMMP++_ref															99.94 97

ACMMP++															99.79 207

Test By Simon												98.41 193

High-resolution multi-view benchmark