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 3	99.87 20	99.98 3	99.75 66	99.70 34	100.00 1	99.73 75	100.00 1	99.89 34	99.79 16	99.88 192	99.98 1	100.00 1	99.98 3

test_fmvs2		99.72 36	99.85 16	99.34 230	99.91 29	98.08 315	99.48 100	100.00 1	99.90 30	99.99 7	99.91 24	99.50 46	99.98 21	99.98 1	99.99 16	99.96 10

test_fmvs3		99.83 19	99.93 2	99.53 173	99.96 7	98.62 277	99.67 49	100.00 1	99.95 18	100.00 1	99.95 13	99.85 10	99.99 8	99.98 1	99.99 16	99.98 3

test_fmvsmconf0.01_n		99.89 3	99.88 6	99.91 2	99.98 3	99.76 60	99.12 201	100.00 1	100.00 1	99.99 7	99.91 24	99.98 1	100.00 1	99.97 4	100.00 1	99.99 1

test_vis1_n_1920		99.72 36	99.88 6	99.27 249	99.93 24	97.84 327	99.34 127	100.00 1	99.99 2	99.99 7	99.82 75	99.87 9	99.99 8	99.97 4	99.99 16	99.97 7

test_vis1_n		99.68 45	99.79 27	99.36 227	99.94 18	98.18 305	99.52 87	100.00 1	99.86 45	100.00 1	99.88 42	98.99 105	99.96 54	99.97 4	99.96 66	99.95 11

test_fmvs1_n		99.68 45	99.81 23	99.28 246	99.95 15	97.93 324	99.49 99	100.00 1	99.82 60	99.99 7	99.89 34	99.21 75	99.98 21	99.97 4	99.98 39	99.93 15

test_f		99.75 32	99.88 6	99.37 223	99.96 7	98.21 302	99.51 94	100.00 1	99.94 21	100.00 1	99.93 17	99.58 36	99.94 79	99.97 4	99.99 16	99.97 7

test_fmvsmconf0.1_n		99.87 8	99.86 12	99.91 2	99.97 6	99.74 72	99.01 230	99.99 10	99.99 2	99.98 13	99.88 42	99.97 2	99.99 8	99.96 9	100.00 1	99.98 3

test_fmvsmvis_n_1920		99.84 15	99.86 12	99.81 38	99.88 42	99.55 138	99.17 181	99.98 11	99.99 2	99.96 23	99.84 64	99.96 3	99.99 8	99.96 9	99.99 16	99.88 24

test_cas_vis1_n_1920		99.76 31	99.86 12	99.45 194	99.93 24	98.40 290	99.30 140	99.98 11	99.94 21	99.99 7	99.89 34	99.80 15	99.97 34	99.96 9	99.97 53	99.97 7

fmvsm_l_conf0.5_n		99.80 23	99.78 31	99.85 26	99.88 42	99.66 100	99.11 205	99.91 33	99.98 13	99.96 23	99.64 182	99.60 34	99.99 8	99.95 12	99.99 16	99.88 24

test_fmvsm_n_1920		99.84 15	99.85 16	99.83 31	99.82 70	99.70 89	99.17 181	99.97 18	99.99 2	99.96 23	99.82 75	99.94 4	100.00 1	99.95 12	100.00 1	99.80 45

test_fmvs1		99.48 89	99.65 50	98.97 290	99.54 216	97.16 350	99.11 205	99.98 11	99.78 69	99.96 23	99.81 81	98.72 140	99.97 34	99.95 12	99.97 53	99.79 52

mvsany_test3		99.85 11	99.88 6	99.75 72	99.95 15	99.37 181	99.53 86	99.98 11	99.77 73	99.99 7	99.95 13	99.85 10	99.94 79	99.95 12	99.98 39	99.94 13

fmvsm_l_conf0.5_n_a		99.80 23	99.79 27	99.84 28	99.88 42	99.64 109	99.12 201	99.91 33	99.98 13	99.95 31	99.67 170	99.67 27	99.99 8	99.94 16	99.99 16	99.88 24

MM		99.18 175	99.05 182	99.55 167	99.35 284	98.81 257	99.05 219	97.79 383	99.99 2	99.48 216	99.59 222	96.29 304	99.95 64	99.94 16	99.98 39	99.88 24

test_fmvsmconf_n		99.85 11	99.84 19	99.88 16	99.91 29	99.73 75	98.97 242	99.98 11	99.99 2	99.96 23	99.85 58	99.93 7	99.99 8	99.94 16	99.99 16	99.93 15

fmvsm_s_conf0.1_n_a		99.85 11	99.83 20	99.91 2	99.95 15	99.82 34	99.10 208	99.98 11	99.99 2	99.98 13	99.91 24	99.68 26	99.93 96	99.93 19	99.99 16	99.99 1

fmvsm_s_conf0.1_n		99.86 9	99.85 16	99.89 10	99.93 24	99.78 48	99.07 218	99.98 11	99.99 2	99.98 13	99.90 29	99.88 8	99.92 118	99.93 19	99.99 16	99.98 3

fmvsm_s_conf0.5_n_a		99.82 21	99.79 27	99.89 10	99.85 56	99.82 34	99.03 225	99.96 23	99.99 2	99.97 19	99.84 64	99.58 36	99.93 96	99.92 21	99.98 39	99.93 15

fmvsm_s_conf0.5_n		99.83 19	99.81 23	99.87 20	99.85 56	99.78 48	99.03 225	99.96 23	99.99 2	99.97 19	99.84 64	99.78 17	99.92 118	99.92 21	99.99 16	99.92 18

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 18	99.99 2	100.00 1	99.98 10	99.78 17	100.00 1	99.92 21	100.00 1	99.87 28

v1921920		99.56 73	99.57 72	99.55 167	99.75 126	99.11 227	99.05 219	99.61 180	99.15 189	99.88 61	99.71 140	99.08 92	99.87 206	99.90 24	99.97 53	99.66 102

v1240		99.56 73	99.58 68	99.51 178	99.80 84	99.00 238	99.00 233	99.65 162	99.15 189	99.90 49	99.75 117	99.09 89	99.88 192	99.90 24	99.96 66	99.67 93

v10		99.69 42	99.69 43	99.66 115	99.81 78	99.39 176	99.66 53	99.75 105	99.60 118	99.92 43	99.87 47	98.75 135	99.86 225	99.90 24	99.99 16	99.73 68

v1192		99.57 70	99.57 72	99.57 161	99.77 111	99.22 213	99.04 222	99.60 191	99.18 178	99.87 69	99.72 132	99.08 92	99.85 242	99.89 27	99.98 39	99.66 102

v144192		99.55 76	99.54 78	99.58 155	99.78 103	99.20 218	99.11 205	99.62 173	99.18 178	99.89 53	99.72 132	98.66 148	99.87 206	99.88 28	99.97 53	99.66 102

v8		99.68 45	99.69 43	99.65 120	99.80 84	99.40 172	99.66 53	99.76 100	99.64 104	99.93 37	99.85 58	98.66 148	99.84 257	99.88 28	99.99 16	99.71 73

v1144		99.54 79	99.53 82	99.59 152	99.79 96	99.28 199	99.10 208	99.61 180	99.20 176	99.84 75	99.73 124	98.67 146	99.84 257	99.86 30	99.98 39	99.64 120

SSC-MVS		99.52 82	99.42 101	99.83 31	99.86 52	99.65 106	99.52 87	99.81 77	99.87 42	99.81 87	99.79 94	96.78 285	99.99 8	99.83 31	99.51 292	99.86 30

v7n		99.82 21	99.80 26	99.88 16	99.96 7	99.84 24	99.82 8	99.82 68	99.84 54	99.94 34	99.91 24	99.13 86	99.96 54	99.83 31	99.99 16	99.83 38

v2v482		99.50 84	99.47 87	99.58 155	99.78 103	99.25 206	99.14 191	99.58 206	99.25 167	99.81 87	99.62 200	98.24 204	99.84 257	99.83 31	99.97 53	99.64 120

test_vis1_rt		99.45 99	99.46 91	99.41 212	99.71 141	98.63 276	98.99 238	99.96 23	99.03 202	99.95 31	99.12 334	98.75 135	99.84 257	99.82 34	99.82 179	99.77 58

tt0805		99.63 59	99.57 72	99.81 38	99.87 49	99.88 12	99.58 77	98.70 350	99.72 80	99.91 46	99.60 217	99.43 48	99.81 296	99.81 35	99.53 288	99.73 68

V42		99.56 73	99.54 78	99.63 134	99.79 96	99.46 152	99.39 115	99.59 197	99.24 169	99.86 70	99.70 148	98.55 162	99.82 281	99.79 36	99.95 79	99.60 150

mvs_tets		99.90 2	99.90 3	99.90 7	99.96 7	99.79 45	99.72 29	99.88 45	99.92 26	99.98 13	99.93 17	99.94 4	99.98 21	99.77 37	100.00 1	99.92 18

WB-MVS		99.44 101	99.32 119	99.80 43	99.81 78	99.61 123	99.47 103	99.81 77	99.82 60	99.71 133	99.72 132	96.60 289	99.98 21	99.75 38	99.23 332	99.82 44

PS-MVSNAJss		99.84 15	99.82 22	99.89 10	99.96 7	99.77 53	99.68 45	99.85 55	99.95 18	99.98 13	99.92 21	99.28 66	99.98 21	99.75 38	100.00 1	99.94 13

jajsoiax		99.89 3	99.89 5	99.89 10	99.96 7	99.78 48	99.70 34	99.86 50	99.89 36	99.98 13	99.90 29	99.94 4	99.98 21	99.75 38	100.00 1	99.90 20

ANet_high		99.88 6	99.87 10	99.91 2	99.99 1	99.91 4	99.65 58	100.00 1	99.90 30	100.00 1	99.97 11	99.61 32	99.97 34	99.75 38	100.00 1	99.84 34

CS-MVS-test		99.68 45	99.70 40	99.64 127	99.57 202	99.83 29	99.78 13	99.97 18	99.92 26	99.50 213	99.38 285	99.57 38	99.95 64	99.69 42	99.90 113	99.15 296

MVS_0304		98.61 257	98.30 277	99.52 175	97.88 406	98.95 245	98.76 272	94.11 405	99.84 54	99.32 255	99.57 232	95.57 315	99.95 64	99.68 43	99.98 39	99.68 86

CS-MVS		99.67 51	99.70 40	99.58 155	99.53 222	99.84 24	99.79 12	99.96 23	99.90 30	99.61 174	99.41 275	99.51 45	99.95 64	99.66 44	99.89 124	98.96 339

mamv4		99.73 35	99.74 37	99.70 101	99.66 169	99.87 14	99.69 41	99.93 29	99.93 23	99.93 37	99.86 53	99.07 94	100.00 1	99.66 44	99.92 101	99.24 271

pmmvs6		99.86 9	99.86 12	99.83 31	99.94 18	99.90 7	99.83 6	99.91 33	99.85 51	99.94 34	99.95 13	99.73 21	99.90 159	99.65 46	99.97 53	99.69 80

MIMVSNet1		99.66 52	99.62 56	99.80 43	99.94 18	99.87 14	99.69 41	99.77 95	99.78 69	99.93 37	99.89 34	97.94 230	99.92 118	99.65 46	99.98 39	99.62 136

EC-MVSNet		99.69 42	99.69 43	99.68 105	99.71 141	99.91 4	99.76 19	99.96 23	99.86 45	99.51 211	99.39 283	99.57 38	99.93 96	99.64 48	99.86 153	99.20 285

K. test v3		98.87 236	98.60 245	99.69 103	99.93 24	99.46 152	99.74 23	94.97 400	99.78 69	99.88 61	99.88 42	93.66 334	99.97 34	99.61 49	99.95 79	99.64 120

KD-MVS_self_test		99.63 59	99.59 65	99.76 62	99.84 59	99.90 7	99.37 122	99.79 86	99.83 58	99.88 61	99.85 58	98.42 183	99.90 159	99.60 50	99.73 223	99.49 207

Anonymous20240521		99.44 101	99.42 101	99.49 182	99.89 37	98.96 244	99.62 63	99.76 100	99.85 51	99.82 80	99.88 42	96.39 299	99.97 34	99.59 51	99.98 39	99.55 172

TransMVSNet (Re)		99.78 27	99.77 33	99.81 38	99.91 29	99.85 19	99.75 21	99.86 50	99.70 87	99.91 46	99.89 34	99.60 34	99.87 206	99.59 51	99.74 218	99.71 73

OurMVSNet-221017-0		99.75 32	99.71 39	99.84 28	99.96 7	99.83 29	99.83 6	99.85 55	99.80 66	99.93 37	99.93 17	98.54 164	99.93 96	99.59 51	99.98 39	99.76 63

EU-MVSNet		99.39 118	99.62 56	98.72 321	99.88 42	96.44 364	99.56 82	99.85 55	99.90 30	99.90 49	99.85 58	98.09 218	99.83 272	99.58 54	99.95 79	99.90 20

mvs_anonymous		99.28 142	99.39 104	98.94 294	99.19 326	97.81 329	99.02 228	99.55 219	99.78 69	99.85 72	99.80 84	98.24 204	99.86 225	99.57 55	99.50 295	99.15 296

test1111		97.74 315	98.16 289	96.49 383	99.60 183	89.86 413	99.71 33	91.21 409	99.89 36	99.88 61	99.87 47	93.73 333	99.90 159	99.56 56	99.99 16	99.70 76

lessismore_v0				99.64 127	99.86 52	99.38 178		90.66 410		99.89 53	99.83 68	94.56 324	99.97 34	99.56 56	99.92 101	99.57 167

mvsany_test1		99.44 101	99.45 93	99.40 214	99.37 278	98.64 275	97.90 359	99.59 197	99.27 163	99.92 43	99.82 75	99.74 20	99.93 96	99.55 58	99.87 145	99.63 125

MVSMamba_PlusPlus		99.55 76	99.58 68	99.47 188	99.68 161	99.40 172	99.52 87	99.70 132	99.92 26	99.77 106	99.86 53	98.28 199	99.96 54	99.54 59	99.90 113	99.05 325

iter_conf05		99.64 58	99.65 50	99.60 149	99.68 161	99.62 116	99.82 8	99.89 40	99.92 26	99.93 37	99.86 53	98.28 199	99.96 54	99.54 59	99.91 111	99.23 275

pm-mvs1		99.79 26	99.79 27	99.78 52	99.91 29	99.83 29	99.76 19	99.87 47	99.73 75	99.89 53	99.87 47	99.63 29	99.87 206	99.54 59	99.92 101	99.63 125

LTVRE_ROB	99.19 1	99.88 6	99.87 10	99.88 16	99.91 29	99.90 7	99.96 1	99.92 30	99.90 30	99.97 19	99.87 47	99.81 14	99.95 64	99.54 59	99.99 16	99.80 45
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 89	99.65 50	98.95 293	99.71 141	97.27 347	99.50 95	99.82 68	99.59 120	99.41 236	99.85 58	99.62 31	100.00 1	99.53 63	99.89 124	99.59 157

test2506		94.73 373	94.59 374	95.15 389	99.59 187	85.90 415	99.75 21	74.01 417	99.89 36	99.71 133	99.86 53	79.00 406	99.90 159	99.52 64	99.99 16	99.65 110

UniMVSNet_ETH3D		99.85 11	99.83 20	99.90 7	99.89 37	99.91 4	99.89 4	99.71 127	99.93 23	99.95 31	99.89 34	99.71 22	99.96 54	99.51 65	99.97 53	99.84 34

FC-MVSNet-test		99.70 40	99.65 50	99.86 24	99.88 42	99.86 18	99.72 29	99.78 92	99.90 30	99.82 80	99.83 68	98.45 179	99.87 206	99.51 65	99.97 53	99.86 30

UA-Net		99.78 27	99.76 36	99.86 24	99.72 138	99.71 82	99.91 3	99.95 28	99.96 17	99.71 133	99.91 24	99.15 81	99.97 34	99.50 67	100.00 1	99.90 20

PMMVS2		99.48 89	99.45 93	99.57 161	99.76 115	98.99 239	98.09 336	99.90 38	98.95 210	99.78 100	99.58 225	99.57 38	99.93 96	99.48 68	99.95 79	99.79 52

VPA-MVSNet		99.66 52	99.62 56	99.79 49	99.68 161	99.75 66	99.62 63	99.69 140	99.85 51	99.80 91	99.81 81	98.81 123	99.91 140	99.47 69	99.88 133	99.70 76

ECVR-MVS		97.73 316	98.04 295	96.78 377	99.59 187	90.81 409	99.72 29	90.43 411	99.89 36	99.86 70	99.86 53	93.60 335	99.89 178	99.46 70	99.99 16	99.65 110

nrg030		99.70 40	99.66 48	99.82 35	99.76 115	99.84 24	99.61 68	99.70 132	99.93 23	99.78 100	99.68 166	99.10 87	99.78 309	99.45 71	99.96 66	99.83 38

TAMVS		99.49 87	99.45 93	99.63 134	99.48 245	99.42 166	99.45 107	99.57 208	99.66 100	99.78 100	99.83 68	97.85 237	99.86 225	99.44 72	99.96 66	99.61 146

GeoE		99.69 42	99.66 48	99.78 52	99.76 115	99.76 60	99.60 74	99.82 68	99.46 135	99.75 115	99.56 236	99.63 29	99.95 64	99.43 73	99.88 133	99.62 136

new-patchmatchnet		99.35 128	99.57 72	98.71 323	99.82 70	96.62 362	98.55 295	99.75 105	99.50 126	99.88 61	99.87 47	99.31 62	99.88 192	99.43 73	100.00 1	99.62 136

test20.03		99.55 76	99.54 78	99.58 155	99.79 96	99.37 181	99.02 228	99.89 40	99.60 118	99.82 80	99.62 200	98.81 123	99.89 178	99.43 73	99.86 153	99.47 215

MVSFormer		99.41 112	99.44 96	99.31 240	99.57 202	98.40 290	99.77 15	99.80 80	99.73 75	99.63 159	99.30 304	98.02 224	99.98 21	99.43 73	99.69 238	99.55 172

test_djsdf		99.84 15	99.81 23	99.91 2	99.94 18	99.84 24	99.77 15	99.80 80	99.73 75	99.97 19	99.92 21	99.77 19	99.98 21	99.43 73	100.00 1	99.90 20

SDMVSNet		99.77 30	99.77 33	99.76 62	99.80 84	99.65 106	99.63 60	99.86 50	99.97 15	99.89 53	99.89 34	99.52 44	99.99 8	99.42 78	99.96 66	99.65 110

Anonymous20231211		99.62 65	99.57 72	99.76 62	99.61 181	99.60 126	99.81 10	99.73 115	99.82 60	99.90 49	99.90 29	97.97 229	99.86 225	99.42 78	99.96 66	99.80 45

SixPastTwentyTwo		99.42 108	99.30 126	99.76 62	99.92 28	99.67 98	99.70 34	99.14 328	99.65 102	99.89 53	99.90 29	96.20 306	99.94 79	99.42 78	99.92 101	99.67 93

balanced_conf03		99.50 84	99.50 84	99.50 180	99.42 268	99.49 145	99.52 87	99.75 105	99.86 45	99.78 100	99.71 140	98.20 211	99.90 159	99.39 81	99.88 133	99.10 307

patch_mono-2		99.51 83	99.46 91	99.64 127	99.70 149	99.11 227	99.04 222	99.87 47	99.71 82	99.47 218	99.79 94	98.24 204	99.98 21	99.38 82	99.96 66	99.83 38

UGNet		99.38 120	99.34 114	99.49 182	98.90 362	98.90 252	99.70 34	99.35 288	99.86 45	98.57 347	99.81 81	98.50 174	99.93 96	99.38 82	99.98 39	99.66 102
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 39	99.67 47	99.81 38	99.89 37	99.72 80	99.59 75	99.82 68	99.39 148	99.82 80	99.84 64	99.38 54	99.91 140	99.38 82	99.93 97	99.80 45

FIs		99.65 57	99.58 68	99.84 28	99.84 59	99.85 19	99.66 53	99.75 105	99.86 45	99.74 123	99.79 94	98.27 202	99.85 242	99.37 85	99.93 97	99.83 38

sd_testset		99.78 27	99.78 31	99.80 43	99.80 84	99.76 60	99.80 11	99.79 86	99.97 15	99.89 53	99.89 34	99.53 43	99.99 8	99.36 86	99.96 66	99.65 110

anonymousdsp		99.80 23	99.77 33	99.90 7	99.96 7	99.88 12	99.73 26	99.85 55	99.70 87	99.92 43	99.93 17	99.45 47	99.97 34	99.36 86	100.00 1	99.85 33

casdiffmvs_mvg		99.68 45	99.68 46	99.69 103	99.81 78	99.59 128	99.29 147	99.90 38	99.71 82	99.79 96	99.73 124	99.54 41	99.84 257	99.36 86	99.96 66	99.65 110
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 32	99.74 37	99.79 49	99.88 42	99.66 100	99.69 41	99.92 30	99.67 96	99.77 106	99.75 117	99.61 32	99.98 21	99.35 89	99.98 39	99.72 70
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dcpmvs_2		99.61 67	99.64 54	99.53 173	99.79 96	98.82 256	99.58 77	99.97 18	99.95 18	99.96 23	99.76 112	98.44 180	99.99 8	99.34 90	99.96 66	99.78 54

CHOSEN 1792x2688		99.39 118	99.30 126	99.65 120	99.88 42	99.25 206	98.78 270	99.88 45	98.66 249	99.96 23	99.79 94	97.45 259	99.93 96	99.34 90	99.99 16	99.78 54

CDS-MVSNet		99.22 161	99.13 154	99.50 180	99.35 284	99.11 227	98.96 244	99.54 225	99.46 135	99.61 174	99.70 148	96.31 302	99.83 272	99.34 90	99.88 133	99.55 172
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		99.00 216	99.16 148	98.51 330	99.75 126	95.90 374	98.07 339	99.84 61	99.84 54	99.89 53	99.73 124	96.01 309	99.99 8	99.33 93	100.00 1	99.63 125

HyFIR lowres test		98.91 229	98.64 242	99.73 86	99.85 56	99.47 148	98.07 339	99.83 63	98.64 251	99.89 53	99.60 217	92.57 344	100.00 1	99.33 93	99.97 53	99.72 70

pmmvs5		99.19 171	99.11 161	99.42 205	99.76 115	98.88 253	98.55 295	99.73 115	98.82 229	99.72 128	99.62 200	96.56 290	99.82 281	99.32 95	99.95 79	99.56 169

v148		99.40 114	99.41 103	99.39 217	99.76 115	98.94 246	99.09 212	99.59 197	99.17 183	99.81 87	99.61 209	98.41 184	99.69 344	99.32 95	99.94 90	99.53 185

baseline		99.63 59	99.62 56	99.66 115	99.80 84	99.62 116	99.44 109	99.80 80	99.71 82	99.72 128	99.69 155	99.15 81	99.83 272	99.32 95	99.94 90	99.53 185

CVMVSNet		98.61 257	98.88 222	97.80 358	99.58 192	93.60 395	99.26 154	99.64 168	99.66 100	99.72 128	99.67 170	93.26 337	99.93 96	99.30 98	99.81 188	99.87 28

PS-CasMVS		99.66 52	99.58 68	99.89 10	99.80 84	99.85 19	99.66 53	99.73 115	99.62 109	99.84 75	99.71 140	98.62 152	99.96 54	99.30 98	99.96 66	99.86 30

DTE-MVSNet		99.68 45	99.61 60	99.88 16	99.80 84	99.87 14	99.67 49	99.71 127	99.72 80	99.84 75	99.78 102	98.67 146	99.97 34	99.30 98	99.95 79	99.80 45

tmp_tt		95.75 367	95.42 361	96.76 378	89.90 416	94.42 389	98.86 253	97.87 382	78.01 407	99.30 265	99.69 155	97.70 245	95.89 409	99.29 101	98.14 386	99.95 11

PEN-MVS		99.66 52	99.59 65	99.89 10	99.83 63	99.87 14	99.66 53	99.73 115	99.70 87	99.84 75	99.73 124	98.56 161	99.96 54	99.29 101	99.94 90	99.83 38

WR-MVS_H		99.61 67	99.53 82	99.87 20	99.80 84	99.83 29	99.67 49	99.75 105	99.58 121	99.85 72	99.69 155	98.18 214	99.94 79	99.28 103	99.95 79	99.83 38

IterMVS		98.97 220	99.16 148	98.42 334	99.74 132	95.64 377	98.06 341	99.83 63	99.83 58	99.85 72	99.74 120	96.10 308	99.99 8	99.27 104	100.00 1	99.63 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs33		98.61 257	98.34 273	99.44 199	99.60 183	98.67 268	99.27 152	99.44 263	99.68 92	99.32 255	99.49 258	92.50 347	100.00 1	99.24 105	96.51 403	99.65 110

hse-mvs2		98.52 270	98.30 277	99.16 265	99.29 306	98.60 278	98.77 271	99.02 336	99.68 92	99.32 255	99.04 344	92.50 347	99.85 242	99.24 105	97.87 393	99.03 330

FMVSNet1		99.66 52	99.63 55	99.73 86	99.78 103	99.77 53	99.68 45	99.70 132	99.67 96	99.82 80	99.83 68	98.98 107	99.90 159	99.24 105	99.97 53	99.53 185

casdiffmvs		99.63 59	99.61 60	99.67 108	99.79 96	99.59 128	99.13 197	99.85 55	99.79 68	99.76 110	99.72 132	99.33 61	99.82 281	99.21 108	99.94 90	99.59 157
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 79	99.43 98	99.87 20	99.76 115	99.82 34	99.57 80	99.61 180	99.54 122	99.80 91	99.64 182	97.79 241	99.95 64	99.21 108	99.94 90	99.84 34

DELS-MVS		99.34 133	99.30 126	99.48 186	99.51 229	99.36 185	98.12 332	99.53 234	99.36 153	99.41 236	99.61 209	99.22 74	99.87 206	99.21 108	99.68 243	99.20 285
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)		99.37 123	99.26 137	99.68 105	99.51 229	99.58 132	98.98 241	99.60 191	99.43 143	99.70 137	99.36 291	97.70 245	99.88 192	99.20 111	99.87 145	99.59 157

CANet		99.11 192	99.05 182	99.28 246	98.83 369	98.56 280	98.71 278	99.41 269	99.25 167	99.23 273	99.22 322	97.66 253	99.94 79	99.19 112	99.97 53	99.33 253

EI-MVSNet-UG-set		99.48 89	99.50 84	99.42 205	99.57 202	98.65 274	99.24 161	99.46 258	99.68 92	99.80 91	99.66 175	98.99 105	99.89 178	99.19 112	99.90 113	99.72 70

xiu_mvs_v1_base_debu		99.23 153	99.34 114	98.91 300	99.59 187	98.23 299	98.47 305	99.66 152	99.61 112	99.68 143	98.94 360	99.39 50	99.97 34	99.18 114	99.55 281	98.51 374

xiu_mvs_v1_base		99.23 153	99.34 114	98.91 300	99.59 187	98.23 299	98.47 305	99.66 152	99.61 112	99.68 143	98.94 360	99.39 50	99.97 34	99.18 114	99.55 281	98.51 374

xiu_mvs_v1_base_debi		99.23 153	99.34 114	98.91 300	99.59 187	98.23 299	98.47 305	99.66 152	99.61 112	99.68 143	98.94 360	99.39 50	99.97 34	99.18 114	99.55 281	98.51 374

VPNet		99.46 97	99.37 109	99.71 97	99.82 70	99.59 128	99.48 100	99.70 132	99.81 63	99.69 140	99.58 225	97.66 253	99.86 225	99.17 117	99.44 302	99.67 93

UniMVSNet_NR-MVSNet		99.37 123	99.25 139	99.72 92	99.47 251	99.56 135	98.97 242	99.61 180	99.43 143	99.67 148	99.28 308	97.85 237	99.95 64	99.17 117	99.81 188	99.65 110

DU-MVS		99.33 136	99.21 143	99.71 97	99.43 263	99.56 135	98.83 258	99.53 234	99.38 149	99.67 148	99.36 291	97.67 249	99.95 64	99.17 117	99.81 188	99.63 125

EI-MVSNet-Vis-set		99.47 96	99.49 86	99.42 205	99.57 202	98.66 271	99.24 161	99.46 258	99.67 96	99.79 96	99.65 180	98.97 109	99.89 178	99.15 120	99.89 124	99.71 73

EI-MVSNet		99.38 120	99.44 96	99.21 259	99.58 192	98.09 312	99.26 154	99.46 258	99.62 109	99.75 115	99.67 170	98.54 164	99.85 242	99.15 120	99.92 101	99.68 86

VNet		99.18 175	99.06 178	99.56 164	99.24 316	99.36 185	99.33 130	99.31 297	99.67 96	99.47 218	99.57 232	96.48 293	99.84 257	99.15 120	99.30 321	99.47 215

EG-PatchMatch MVS		99.57 70	99.56 77	99.62 143	99.77 111	99.33 191	99.26 154	99.76 100	99.32 157	99.80 91	99.78 102	99.29 64	99.87 206	99.15 120	99.91 111	99.66 102

PVSNet_Blended_VisFu		99.40 114	99.38 106	99.44 199	99.90 35	98.66 271	98.94 247	99.91 33	97.97 312	99.79 96	99.73 124	99.05 99	99.97 34	99.15 120	99.99 16	99.68 86

IterMVS-LS		99.41 112	99.47 87	99.25 255	99.81 78	98.09 312	98.85 255	99.76 100	99.62 109	99.83 79	99.64 182	98.54 164	99.97 34	99.15 120	99.99 16	99.68 86
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TranMVSNet+NR-MVSNet		99.54 79	99.47 87	99.76 62	99.58 192	99.64 109	99.30 140	99.63 170	99.61 112	99.71 133	99.56 236	98.76 133	99.96 54	99.14 126	99.92 101	99.68 86

MVSTER		98.47 277	98.22 282	99.24 257	99.06 349	98.35 296	99.08 215	99.46 258	99.27 163	99.75 115	99.66 175	88.61 380	99.85 242	99.14 126	99.92 101	99.52 195

Anonymous20231206		99.35 128	99.31 121	99.47 188	99.74 132	99.06 237	99.28 149	99.74 111	99.23 171	99.72 128	99.53 247	97.63 255	99.88 192	99.11 128	99.84 162	99.48 211

Syy-MVS		98.17 300	97.85 312	99.15 267	98.50 392	98.79 260	98.60 284	99.21 320	97.89 318	96.76 394	96.37 415	95.47 316	99.57 383	99.10 129	98.73 364	99.09 312

MVS_Test		99.28 142	99.31 121	99.19 262	99.35 284	98.79 260	99.36 125	99.49 251	99.17 183	99.21 278	99.67 170	98.78 130	99.66 365	99.09 130	99.66 252	99.10 307

testgi		99.29 141	99.26 137	99.37 223	99.75 126	98.81 257	98.84 256	99.89 40	98.38 279	99.75 115	99.04 344	99.36 59	99.86 225	99.08 131	99.25 328	99.45 220

1112_ss		99.05 202	98.84 227	99.67 108	99.66 169	99.29 197	98.52 301	99.82 68	97.65 330	99.43 228	99.16 328	96.42 296	99.91 140	99.07 132	99.84 162	99.80 45

CANet_DTU		98.91 229	98.85 225	99.09 276	98.79 375	98.13 307	98.18 325	99.31 297	99.48 128	98.86 318	99.51 251	96.56 290	99.95 64	99.05 133	99.95 79	99.19 288

bld_raw_conf03		99.43 104	99.43 98	99.45 194	99.42 268	99.40 172	99.52 87	99.70 132	99.73 75	99.77 106	99.73 124	98.05 222	99.91 140	99.04 134	99.90 113	99.05 325

Baseline_NR-MVSNet		99.49 87	99.37 109	99.82 35	99.91 29	99.84 24	98.83 258	99.86 50	99.68 92	99.65 154	99.88 42	97.67 249	99.87 206	99.03 135	99.86 153	99.76 63

FMVSNet2		99.35 128	99.28 133	99.55 167	99.49 240	99.35 188	99.45 107	99.57 208	99.44 138	99.70 137	99.74 120	97.21 270	99.87 206	99.03 135	99.94 90	99.44 225

Test_1112_low_res		98.95 226	98.73 236	99.63 134	99.68 161	99.15 224	98.09 336	99.80 80	97.14 356	99.46 222	99.40 279	96.11 307	99.89 178	99.01 137	99.84 162	99.84 34

VDD-MVS		99.20 168	99.11 161	99.44 199	99.43 263	98.98 240	99.50 95	98.32 372	99.80 66	99.56 192	99.69 155	96.99 280	99.85 242	98.99 138	99.73 223	99.50 202

DeepC-MVS	98.90 4	99.62 65	99.61 60	99.67 108	99.72 138	99.44 159	99.24 161	99.71 127	99.27 163	99.93 37	99.90 29	99.70 24	99.93 96	98.99 138	99.99 16	99.64 120
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 89	99.47 87	99.51 178	99.77 111	99.41 171	98.81 263	99.66 152	99.42 147	99.75 115	99.66 175	99.20 76	99.76 319	98.98 140	99.99 16	99.36 246

EPNet_dtu		97.62 321	97.79 315	97.11 376	96.67 411	92.31 400	98.51 302	98.04 376	99.24 169	95.77 403	99.47 265	93.78 332	99.66 365	98.98 140	99.62 259	99.37 243
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
diffmvs		99.34 133	99.32 119	99.39 217	99.67 168	98.77 262	98.57 293	99.81 77	99.61 112	99.48 216	99.41 275	98.47 175	99.86 225	98.97 142	99.90 113	99.53 185
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		99.40 114	99.31 121	99.68 105	99.43 263	99.55 138	99.73 26	99.50 247	99.46 135	99.88 61	99.36 291	97.54 256	99.87 206	98.97 142	99.87 145	99.63 125

GBi-Net		99.42 108	99.31 121	99.73 86	99.49 240	99.77 53	99.68 45	99.70 132	99.44 138	99.62 168	99.83 68	97.21 270	99.90 159	98.96 144	99.90 113	99.53 185

FMVSNet5		97.80 313	97.25 329	99.42 205	98.83 369	98.97 242	99.38 118	99.80 80	98.87 222	99.25 269	99.69 155	80.60 400	99.91 140	98.96 144	99.90 113	99.38 240

test1		99.42 108	99.31 121	99.73 86	99.49 240	99.77 53	99.68 45	99.70 132	99.44 138	99.62 168	99.83 68	97.21 270	99.90 159	98.96 144	99.90 113	99.53 185

FMVSNet3		98.80 242	98.63 244	99.32 237	99.13 335	98.72 265	99.10 208	99.48 252	99.23 171	99.62 168	99.64 182	92.57 344	99.86 225	98.96 144	99.90 113	99.39 238

UnsupCasMVSNet_eth		98.83 239	98.57 251	99.59 152	99.68 161	99.45 157	98.99 238	99.67 147	99.48 128	99.55 197	99.36 291	94.92 318	99.86 225	98.95 148	96.57 402	99.45 220

CHOSEN 280x420		98.41 282	98.41 265	98.40 335	99.34 293	95.89 375	96.94 395	99.44 263	98.80 233	99.25 269	99.52 249	93.51 336	99.98 21	98.94 149	99.98 39	99.32 256

TDRefinement		99.72 36	99.70 40	99.77 55	99.90 35	99.85 19	99.86 5	99.92 30	99.69 90	99.78 100	99.92 21	99.37 56	99.88 192	98.93 150	99.95 79	99.60 150

alignmvs		98.28 292	97.96 301	99.25 255	99.12 337	98.93 249	99.03 225	98.42 366	99.64 104	98.72 333	97.85 396	90.86 365	99.62 375	98.88 151	99.13 334	99.19 288

MGCFI-Net		99.02 208	99.01 194	99.06 283	99.11 342	98.60 278	99.63 60	99.67 147	99.63 106	98.58 345	97.65 399	99.07 94	99.57 383	98.85 152	98.92 349	99.03 330

sss		98.90 231	98.77 235	99.27 249	99.48 245	98.44 287	98.72 276	99.32 293	97.94 316	99.37 244	99.35 296	96.31 302	99.91 140	98.85 152	99.63 258	99.47 215

xiu_mvs_v2_base		99.02 208	99.11 161	98.77 318	99.37 278	98.09 312	98.13 331	99.51 243	99.47 132	99.42 230	98.54 382	99.38 54	99.97 34	98.83 154	99.33 317	98.24 386

PS-MVSNAJ		99.00 216	99.08 172	98.76 319	99.37 278	98.10 311	98.00 347	99.51 243	99.47 132	99.41 236	98.50 384	99.28 66	99.97 34	98.83 154	99.34 316	98.20 390

D2MVS		99.22 161	99.19 145	99.29 244	99.69 153	98.74 264	98.81 263	99.41 269	98.55 260	99.68 143	99.69 155	98.13 216	99.87 206	98.82 156	99.98 39	99.24 271

PatchT		98.45 279	98.32 275	98.83 313	98.94 360	98.29 297	99.24 161	98.82 344	99.84 54	99.08 295	99.76 112	91.37 355	99.94 79	98.82 156	99.00 344	98.26 385

testf1		99.63 59	99.60 63	99.72 92	99.94 18	99.95 2	99.47 103	99.89 40	99.43 143	99.88 61	99.80 84	99.26 70	99.90 159	98.81 158	99.88 133	99.32 256

APD_test2		99.63 59	99.60 63	99.72 92	99.94 18	99.95 2	99.47 103	99.89 40	99.43 143	99.88 61	99.80 84	99.26 70	99.90 159	98.81 158	99.88 133	99.32 256

sasdasda		99.02 208	99.00 198	99.09 276	99.10 344	98.70 266	99.61 68	99.66 152	99.63 106	98.64 339	97.65 399	99.04 100	99.54 387	98.79 160	98.92 349	99.04 328

Effi-MVS+		99.06 199	98.97 208	99.34 230	99.31 300	98.98 240	98.31 317	99.91 33	98.81 231	98.79 327	98.94 360	99.14 84	99.84 257	98.79 160	98.74 362	99.20 285

canonicalmvs		99.02 208	99.00 198	99.09 276	99.10 344	98.70 266	99.61 68	99.66 152	99.63 106	98.64 339	97.65 399	99.04 100	99.54 387	98.79 160	98.92 349	99.04 328

VDDNet		98.97 220	98.82 230	99.42 205	99.71 141	98.81 257	99.62 63	98.68 351	99.81 63	99.38 243	99.80 84	94.25 326	99.85 242	98.79 160	99.32 319	99.59 157

CR-MVSNet		98.35 289	98.20 284	98.83 313	99.05 350	98.12 308	99.30 140	99.67 147	97.39 344	99.16 284	99.79 94	91.87 352	99.91 140	98.78 164	98.77 358	98.44 379

test_method		91.72 374	92.32 377	89.91 392	93.49 415	70.18 418	90.28 406	99.56 213	61.71 410	95.39 405	99.52 249	93.90 328	99.94 79	98.76 165	98.27 379	99.62 136

RPMNet		98.60 260	98.53 256	98.83 313	99.05 350	98.12 308	99.30 140	99.62 173	99.86 45	99.16 284	99.74 120	92.53 346	99.92 118	98.75 166	98.77 358	98.44 379

pmmvs4		99.13 187	99.06 178	99.36 227	99.57 202	99.10 232	98.01 345	99.25 310	98.78 236	99.58 182	99.44 272	98.24 204	99.76 319	98.74 167	99.93 97	99.22 278

tttt0517		97.62 321	97.20 330	98.90 306	99.76 115	97.40 344	99.48 100	94.36 402	99.06 200	99.70 137	99.49 258	84.55 395	99.94 79	98.73 168	99.65 254	99.36 246

EPP-MVSNet		99.17 180	99.00 198	99.66 115	99.80 84	99.43 163	99.70 34	99.24 313	99.48 128	99.56 192	99.77 109	94.89 319	99.93 96	98.72 169	99.89 124	99.63 125

Anonymous20240529		99.42 108	99.34 114	99.65 120	99.53 222	99.60 126	99.63 60	99.39 279	99.47 132	99.76 110	99.78 102	98.13 216	99.86 225	98.70 170	99.68 243	99.49 207

ACMH	98.42 6	99.59 69	99.54 78	99.72 92	99.86 52	99.62 116	99.56 82	99.79 86	98.77 238	99.80 91	99.85 58	99.64 28	99.85 242	98.70 170	99.89 124	99.70 76
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ab-mvs		99.33 136	99.28 133	99.47 188	99.57 202	99.39 176	99.78 13	99.43 266	98.87 222	99.57 185	99.82 75	98.06 221	99.87 206	98.69 172	99.73 223	99.15 296

LFMVS		98.46 278	98.19 287	99.26 252	99.24 316	98.52 283	99.62 63	96.94 392	99.87 42	99.31 260	99.58 225	91.04 360	99.81 296	98.68 173	99.42 306	99.45 220

WR-MVS		99.11 192	98.93 213	99.66 115	99.30 304	99.42 166	98.42 310	99.37 284	99.04 201	99.57 185	99.20 326	96.89 282	99.86 225	98.66 174	99.87 145	99.70 76

mvsmamba		99.08 196	98.95 211	99.45 194	99.36 281	99.18 221	99.39 115	98.81 345	99.37 150	99.35 246	99.70 148	96.36 301	99.94 79	98.66 174	99.59 273	99.22 278

Anonymous202405211		98.75 246	98.46 260	99.63 134	99.34 293	99.66 100	99.47 103	97.65 384	99.28 162	99.56 192	99.50 254	93.15 338	99.84 257	98.62 176	99.58 275	99.40 236

EPNet		98.13 301	97.77 316	99.18 264	94.57 414	97.99 318	99.24 161	97.96 378	99.74 74	97.29 387	99.62 200	93.13 339	99.97 34	98.59 177	99.83 170	99.58 162
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		99.05 202	99.09 170	98.91 300	99.21 321	98.36 295	98.82 262	99.47 255	98.85 225	98.90 313	99.56 236	98.78 130	99.09 402	98.57 178	99.68 243	99.26 268

Patchmatch-RL test		98.60 260	98.36 270	99.33 233	99.77 111	99.07 235	98.27 319	99.87 47	98.91 217	99.74 123	99.72 132	90.57 369	99.79 306	98.55 179	99.85 157	99.11 305

pmmvs3		98.08 304	97.80 313	98.91 300	99.41 271	97.69 335	97.87 360	99.66 152	95.87 375	99.50 213	99.51 251	90.35 371	99.97 34	98.55 179	99.47 299	99.08 318

ETV-MVS		99.18 175	99.18 146	99.16 265	99.34 293	99.28 199	99.12 201	99.79 86	99.48 128	98.93 307	98.55 381	99.40 49	99.93 96	98.51 181	99.52 291	98.28 384

jason		99.16 181	99.11 161	99.32 237	99.75 126	98.44 287	98.26 321	99.39 279	98.70 246	99.74 123	99.30 304	98.54 164	99.97 34	98.48 182	99.82 179	99.55 172
jason: jason.
APDe-MVS		99.48 89	99.36 112	99.85 26	99.55 214	99.81 39	99.50 95	99.69 140	98.99 204	99.75 115	99.71 140	98.79 128	99.93 96	98.46 183	99.85 157	99.80 45
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CL-MVSNet_self_test		98.71 251	98.56 254	99.15 267	99.22 319	98.66 271	97.14 390	99.51 243	98.09 305	99.54 199	99.27 310	96.87 283	99.74 326	98.43 184	98.96 346	99.03 330

our_test_3		98.85 238	99.09 170	98.13 347	99.66 169	94.90 387	97.72 365	99.58 206	99.07 198	99.64 155	99.62 200	98.19 212	99.93 96	98.41 185	99.95 79	99.55 172

Gipuma		99.57 70	99.59 65	99.49 182	99.98 3	99.71 82	99.72 29	99.84 61	99.81 63	99.94 34	99.78 102	98.91 115	99.71 335	98.41 185	99.95 79	99.05 325
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test0.0.03 1		97.37 329	96.91 339	98.74 320	97.72 407	97.57 337	97.60 371	97.36 390	98.00 308	99.21 278	98.02 392	90.04 374	99.79 306	98.37 187	95.89 406	98.86 352

PM-MVS		99.36 126	99.29 131	99.58 155	99.83 63	99.66 100	98.95 245	99.86 50	98.85 225	99.81 87	99.73 124	98.40 188	99.92 118	98.36 188	99.83 170	99.17 292

baseline1		97.73 316	97.33 326	98.96 291	99.30 304	97.73 333	99.40 113	98.42 366	99.33 156	99.46 222	99.21 324	91.18 358	99.82 281	98.35 189	91.26 409	99.32 256

MVS-HIRNet		97.86 310	98.22 282	96.76 378	99.28 309	91.53 405	98.38 312	92.60 408	99.13 191	99.31 260	99.96 12	97.18 274	99.68 356	98.34 190	99.83 170	99.07 323

GA-MVS		97.99 309	97.68 319	98.93 297	99.52 227	98.04 316	97.19 389	99.05 335	98.32 292	98.81 323	98.97 356	89.89 376	99.41 398	98.33 191	99.05 340	99.34 252

Fast-Effi-MVS+		99.02 208	98.87 223	99.46 191	99.38 276	99.50 144	99.04 222	99.79 86	97.17 354	98.62 341	98.74 373	99.34 60	99.95 64	98.32 192	99.41 307	98.92 345

MDA-MVSNet_test_wron		98.95 226	98.99 204	98.85 309	99.64 174	97.16 350	98.23 323	99.33 291	98.93 214	99.56 192	99.66 175	97.39 263	99.83 272	98.29 193	99.88 133	99.55 172

N_pmnet		98.73 249	98.53 256	99.35 229	99.72 138	98.67 268	98.34 314	94.65 401	98.35 286	99.79 96	99.68 166	98.03 223	99.93 96	98.28 194	99.92 101	99.44 225

ET-MVSNet_ETH3D		96.78 341	96.07 350	98.91 300	99.26 313	97.92 325	97.70 367	96.05 397	97.96 315	92.37 409	98.43 385	87.06 384	99.90 159	98.27 195	97.56 396	98.91 346

thisisatest0530		97.45 326	96.95 336	98.94 294	99.68 161	97.73 333	99.09 212	94.19 404	98.61 256	99.56 192	99.30 304	84.30 396	99.93 96	98.27 195	99.54 286	99.16 294

YYNet1		98.95 226	98.99 204	98.84 311	99.64 174	97.14 352	98.22 324	99.32 293	98.92 216	99.59 180	99.66 175	97.40 261	99.83 272	98.27 195	99.90 113	99.55 172

ACMM	98.09 11	99.46 97	99.38 106	99.72 92	99.80 84	99.69 93	99.13 197	99.65 162	98.99 204	99.64 155	99.72 132	99.39 50	99.86 225	98.23 198	99.81 188	99.60 150
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
lupinMVS		98.96 223	98.87 223	99.24 257	99.57 202	98.40 290	98.12 332	99.18 324	98.28 294	99.63 159	99.13 330	98.02 224	99.97 34	98.22 199	99.69 238	99.35 249

3Dnovator	99.15 2	99.43 104	99.36 112	99.65 120	99.39 273	99.42 166	99.70 34	99.56 213	99.23 171	99.35 246	99.80 84	99.17 79	99.95 64	98.21 200	99.84 162	99.59 157

Fast-Effi-MVS+-dtu		99.20 168	99.12 158	99.43 203	99.25 314	99.69 93	99.05 219	99.82 68	99.50 126	98.97 303	99.05 342	98.98 107	99.98 21	98.20 201	99.24 330	98.62 365

MS-PatchMatch		99.00 216	98.97 208	99.09 276	99.11 342	98.19 303	98.76 272	99.33 291	98.49 269	99.44 224	99.58 225	98.21 209	99.69 344	98.20 201	99.62 259	99.39 238

TSAR-MVS + GP.		99.12 189	99.04 188	99.38 220	99.34 293	99.16 222	98.15 328	99.29 301	98.18 301	99.63 159	99.62 200	99.18 78	99.68 356	98.20 201	99.74 218	99.30 262

DP-MVS		99.48 89	99.39 104	99.74 77	99.57 202	99.62 116	99.29 147	99.61 180	99.87 42	99.74 123	99.76 112	98.69 142	99.87 206	98.20 201	99.80 193	99.75 66

MVP-Stereo		99.16 181	99.08 172	99.43 203	99.48 245	99.07 235	99.08 215	99.55 219	98.63 252	99.31 260	99.68 166	98.19 212	99.78 309	98.18 205	99.58 275	99.45 220
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
HPM-MVS_fast		99.43 104	99.30 126	99.80 43	99.83 63	99.81 39	99.52 87	99.70 132	98.35 286	99.51 211	99.50 254	99.31 62	99.88 192	98.18 205	99.84 162	99.69 80

MDA-MVSNet-bldmvs		99.06 199	99.05 182	99.07 281	99.80 84	97.83 328	98.89 250	99.72 124	99.29 159	99.63 159	99.70 148	96.47 294	99.89 178	98.17 207	99.82 179	99.50 202

JIA-IIPM		98.06 305	97.92 308	98.50 331	98.59 388	97.02 354	98.80 266	98.51 361	99.88 41	97.89 375	99.87 47	91.89 351	99.90 159	98.16 208	97.68 395	98.59 368

EIA-MVS		99.12 189	99.01 194	99.45 194	99.36 281	99.62 116	99.34 127	99.79 86	98.41 275	98.84 320	98.89 364	98.75 135	99.84 257	98.15 209	99.51 292	98.89 349

miper_lstm_enhance		98.65 256	98.60 245	98.82 316	99.20 324	97.33 346	97.78 363	99.66 152	99.01 203	99.59 180	99.50 254	94.62 323	99.85 242	98.12 210	99.90 113	99.26 268

Effi-MVS+-dtu		99.07 198	98.92 217	99.52 175	98.89 365	99.78 48	99.15 189	99.66 152	99.34 154	98.92 310	99.24 320	97.69 247	99.98 21	98.11 211	99.28 324	98.81 356

tpm		97.15 333	96.95 336	97.75 360	98.91 361	94.24 390	99.32 132	97.96 378	97.71 328	98.29 357	99.32 300	86.72 390	99.92 118	98.10 212	96.24 405	99.09 312

DeepPCF-MVS	98.42 6	99.18 175	99.02 191	99.67 108	99.22 319	99.75 66	97.25 387	99.47 255	98.72 243	99.66 152	99.70 148	99.29 64	99.63 374	98.07 213	99.81 188	99.62 136

ppachtmachnet_test		98.89 234	99.12 158	98.20 345	99.66 169	95.24 383	97.63 369	99.68 143	99.08 196	99.78 100	99.62 200	98.65 150	99.88 192	98.02 214	99.96 66	99.48 211

tpmrst		97.73 316	98.07 294	96.73 380	98.71 384	92.00 401	99.10 208	98.86 341	98.52 265	98.92 310	99.54 245	91.90 350	99.82 281	98.02 214	99.03 342	98.37 381

CSCG		99.37 123	99.29 131	99.60 149	99.71 141	99.46 152	99.43 111	99.85 55	98.79 234	99.41 236	99.60 217	98.92 113	99.92 118	98.02 214	99.92 101	99.43 231

eth_miper_zixun_eth		98.68 254	98.71 238	98.60 326	99.10 344	96.84 359	97.52 377	99.54 225	98.94 211	99.58 182	99.48 261	96.25 305	99.76 319	98.01 217	99.93 97	99.21 281

Patchmtry		98.78 243	98.54 255	99.49 182	98.89 365	99.19 219	99.32 132	99.67 147	99.65 102	99.72 128	99.79 94	91.87 352	99.95 64	98.00 218	99.97 53	99.33 253

PVSNet_BlendedMVS		99.03 206	99.01 194	99.09 276	99.54 216	97.99 318	98.58 289	99.82 68	97.62 331	99.34 250	99.71 140	98.52 171	99.77 317	97.98 219	99.97 53	99.52 195

PVSNet_Blended		98.70 252	98.59 247	99.02 286	99.54 216	97.99 318	97.58 372	99.82 68	95.70 379	99.34 250	98.98 354	98.52 171	99.77 317	97.98 219	99.83 170	99.30 262

cl____		98.54 268	98.41 265	98.92 298	99.03 352	97.80 331	97.46 379	99.59 197	98.90 218	99.60 177	99.46 268	93.85 330	99.78 309	97.97 221	99.89 124	99.17 292

DIV-MVS_self_test		98.54 268	98.42 264	98.92 298	99.03 352	97.80 331	97.46 379	99.59 197	98.90 218	99.60 177	99.46 268	93.87 329	99.78 309	97.97 221	99.89 124	99.18 290

AUN-MVS		97.82 312	97.38 325	99.14 270	99.27 311	98.53 281	98.72 276	99.02 336	98.10 303	97.18 390	99.03 348	89.26 378	99.85 242	97.94 223	97.91 391	99.03 330

FA-MVS(test-final)		98.52 270	98.32 275	99.10 275	99.48 245	98.67 268	99.77 15	98.60 358	97.35 346	99.63 159	99.80 84	93.07 340	99.84 257	97.92 224	99.30 321	98.78 359

ambc				99.20 261	99.35 284	98.53 281	99.17 181	99.46 258		99.67 148	99.80 84	98.46 178	99.70 338	97.92 224	99.70 234	99.38 240

USDC		98.96 223	98.93 213	99.05 284	99.54 216	97.99 318	97.07 393	99.80 80	98.21 298	99.75 115	99.77 109	98.43 181	99.64 373	97.90 226	99.88 133	99.51 197

OPM-MVS		99.26 148	99.13 154	99.63 134	99.70 149	99.61 123	98.58 289	99.48 252	98.50 267	99.52 206	99.63 193	99.14 84	99.76 319	97.89 227	99.77 207	99.51 197
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DVP-MVS		99.32 138	99.17 147	99.77 55	99.69 153	99.80 43	99.14 191	99.31 297	99.16 185	99.62 168	99.61 209	98.35 192	99.91 140	97.88 228	99.72 229	99.61 146
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 31	99.70 149	99.79 45	99.14 191	99.61 180					99.92 118	97.88 228	99.72 229	99.77 58

c3_l		98.72 250	98.71 238	98.72 321	99.12 337	97.22 349	97.68 368	99.56 213	98.90 218	99.54 199	99.48 261	96.37 300	99.73 329	97.88 228	99.88 133	99.21 281

3Dnovator+	98.92 3	99.35 128	99.24 141	99.67 108	99.35 284	99.47 148	99.62 63	99.50 247	99.44 138	99.12 291	99.78 102	98.77 132	99.94 79	97.87 231	99.72 229	99.62 136

miper_ehance_all_eth		98.59 263	98.59 247	98.59 327	98.98 358	97.07 353	97.49 378	99.52 239	98.50 267	99.52 206	99.37 287	96.41 298	99.71 335	97.86 232	99.62 259	99.00 337

WTY-MVS		98.59 263	98.37 269	99.26 252	99.43 263	98.40 290	98.74 274	99.13 330	98.10 303	99.21 278	99.24 320	94.82 320	99.90 159	97.86 232	98.77 358	99.49 207

APD_test1		99.36 126	99.28 133	99.61 146	99.89 37	99.89 10	99.32 132	99.74 111	99.18 178	99.69 140	99.75 117	98.41 184	99.84 257	97.85 234	99.70 234	99.10 307

SED-MVS		99.40 114	99.28 133	99.77 55	99.69 153	99.82 34	99.20 171	99.54 225	99.13 191	99.82 80	99.63 193	98.91 115	99.92 118	97.85 234	99.70 234	99.58 162

test_241102_TWO								99.54 225	99.13 191	99.76 110	99.63 193	98.32 197	99.92 118	97.85 234	99.69 238	99.75 66

MVS_111021_HR		99.12 189	99.02 191	99.40 214	99.50 235	99.11 227	97.92 356	99.71 127	98.76 241	99.08 295	99.47 265	99.17 79	99.54 387	97.85 234	99.76 209	99.54 180

MTAPA		99.35 128	99.20 144	99.80 43	99.81 78	99.81 39	99.33 130	99.53 234	99.27 163	99.42 230	99.63 193	98.21 209	99.95 64	97.83 238	99.79 198	99.65 110

MSC_two_6792asdad				99.74 77	99.03 352	99.53 141		99.23 314					99.92 118	97.77 239	99.69 238	99.78 54

No_MVS				99.74 77	99.03 352	99.53 141		99.23 314					99.92 118	97.77 239	99.69 238	99.78 54

TESTMET0.1,1		96.24 354	95.84 355	97.41 368	98.24 399	93.84 393	97.38 381	95.84 398	98.43 272	97.81 380	98.56 380	79.77 402	99.89 178	97.77 239	98.77 358	98.52 373

ACMH+	98.40 8	99.50 84	99.43 98	99.71 97	99.86 52	99.76 60	99.32 132	99.77 95	99.53 124	99.77 106	99.76 112	99.26 70	99.78 309	97.77 239	99.88 133	99.60 150

IU-MVS					99.69 153	99.77 53		99.22 317	97.50 338	99.69 140				97.75 243	99.70 234	99.77 58

114514_t		98.49 275	98.11 292	99.64 127	99.73 135	99.58 132	99.24 161	99.76 100	89.94 402	99.42 230	99.56 236	97.76 244	99.86 225	97.74 244	99.82 179	99.47 215

DVP-MVS++		99.38 120	99.25 139	99.77 55	99.03 352	99.77 53	99.74 23	99.61 180	99.18 178	99.76 110	99.61 209	99.00 103	99.92 118	97.72 245	99.60 269	99.62 136

test_0728_THIRD									99.18 178	99.62 168	99.61 209	98.58 158	99.91 140	97.72 245	99.80 193	99.77 58

EGC-MVSNET		89.05 376	85.52 379	99.64 127	99.89 37	99.78 48	99.56 82	99.52 239	24.19 411	49.96 412	99.83 68	99.15 81	99.92 118	97.71 247	99.85 157	99.21 281

miper_enhance_ethall		98.03 306	97.94 306	98.32 340	98.27 398	96.43 365	96.95 394	99.41 269	96.37 370	99.43 228	98.96 358	94.74 321	99.69 344	97.71 247	99.62 259	98.83 355

TSAR-MVS + MP.		99.34 133	99.24 141	99.63 134	99.82 70	99.37 181	99.26 154	99.35 288	98.77 238	99.57 185	99.70 148	99.27 69	99.88 192	97.71 247	99.75 211	99.65 110
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
cl22		97.56 324	97.28 327	98.40 335	98.37 396	96.75 360	97.24 388	99.37 284	97.31 348	99.41 236	99.22 322	87.30 382	99.37 399	97.70 250	99.62 259	99.08 318

MP-MVS-pluss		99.14 185	98.92 217	99.80 43	99.83 63	99.83 29	98.61 282	99.63 170	96.84 363	99.44 224	99.58 225	98.81 123	99.91 140	97.70 250	99.82 179	99.67 93
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		99.28 142	99.11 161	99.79 49	99.75 126	99.81 39	98.95 245	99.53 234	98.27 295	99.53 204	99.73 124	98.75 135	99.87 206	97.70 250	99.83 170	99.68 86

UnsupCasMVSNet_bld		98.55 267	98.27 280	99.40 214	99.56 213	99.37 181	97.97 352	99.68 143	97.49 339	99.08 295	99.35 296	95.41 317	99.82 281	97.70 250	98.19 383	99.01 336

MVS_111021_LR		99.13 187	99.03 190	99.42 205	99.58 192	99.32 193	97.91 358	99.73 115	98.68 247	99.31 260	99.48 261	99.09 89	99.66 365	97.70 250	99.77 207	99.29 265

IS-MVSNet		99.03 206	98.85 225	99.55 167	99.80 84	99.25 206	99.73 26	99.15 327	99.37 150	99.61 174	99.71 140	94.73 322	99.81 296	97.70 250	99.88 133	99.58 162

test-LLR		97.15 333	96.95 336	97.74 361	98.18 401	95.02 385	97.38 381	96.10 394	98.00 308	97.81 380	98.58 377	90.04 374	99.91 140	97.69 256	98.78 356	98.31 382

test-mter		96.23 355	95.73 357	97.74 361	98.18 401	95.02 385	97.38 381	96.10 394	97.90 317	97.81 380	98.58 377	79.12 405	99.91 140	97.69 256	98.78 356	98.31 382

XVS		99.27 146	99.11 161	99.75 72	99.71 141	99.71 82	99.37 122	99.61 180	99.29 159	98.76 330	99.47 265	98.47 175	99.88 192	97.62 258	99.73 223	99.67 93

X-MVStestdata		96.09 358	94.87 370	99.75 72	99.71 141	99.71 82	99.37 122	99.61 180	99.29 159	98.76 330	61.30 418	98.47 175	99.88 192	97.62 258	99.73 223	99.67 93

SMA-MVS		99.19 171	99.00 198	99.73 86	99.46 255	99.73 75	99.13 197	99.52 239	97.40 343	99.57 185	99.64 182	98.93 112	99.83 272	97.61 260	99.79 198	99.63 125
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		96.71 344	96.79 343	96.46 384	98.90 362	90.71 410	99.41 112	98.68 351	94.69 392	98.14 367	99.34 299	86.32 392	99.80 303	97.60 261	98.07 389	98.88 350

PVSNet	97.47 15	98.42 281	98.44 262	98.35 337	99.46 255	96.26 368	96.70 398	99.34 290	97.68 329	99.00 302	99.13 330	97.40 261	99.72 331	97.59 262	99.68 243	99.08 318

new_pmnet		98.88 235	98.89 221	98.84 311	99.70 149	97.62 336	98.15 328	99.50 247	97.98 311	99.62 168	99.54 245	98.15 215	99.94 79	97.55 263	99.84 162	98.95 341

IB-MVS	95.41 20	95.30 372	94.46 376	97.84 357	98.76 380	95.33 381	97.33 384	96.07 396	96.02 374	95.37 406	97.41 403	76.17 407	99.96 54	97.54 264	95.44 408	98.22 387
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		99.24 152	99.11 161	99.61 146	98.38 395	99.79 45	99.57 80	99.68 143	99.61 112	99.15 286	99.71 140	98.70 141	99.91 140	97.54 264	99.68 243	99.13 304

ZNCC-MVS		99.22 161	99.04 188	99.77 55	99.76 115	99.73 75	99.28 149	99.56 213	98.19 300	99.14 288	99.29 307	98.84 122	99.92 118	97.53 266	99.80 193	99.64 120

CP-MVS		99.23 153	99.05 182	99.75 72	99.66 169	99.66 100	99.38 118	99.62 173	98.38 279	99.06 299	99.27 310	98.79 128	99.94 79	97.51 267	99.82 179	99.66 102

SD-MVS		99.01 214	99.30 126	98.15 346	99.50 235	99.40 172	98.94 247	99.61 180	99.22 175	99.75 115	99.82 75	99.54 41	95.51 411	97.48 268	99.87 145	99.54 180
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		98.49 275	98.29 279	99.11 273	98.96 359	98.42 289	97.54 373	99.32 293	97.53 336	98.47 352	98.15 391	97.88 234	99.82 281	97.46 269	99.24 330	99.09 312

DeepC-MVS_fast	98.47 5	99.23 153	99.12 158	99.56 164	99.28 309	99.22 213	98.99 238	99.40 276	99.08 196	99.58 182	99.64 182	98.90 118	99.83 272	97.44 270	99.75 211	99.63 125
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.25 149	99.08 172	99.76 62	99.73 135	99.70 89	99.31 137	99.59 197	98.36 281	99.36 245	99.37 287	98.80 127	99.91 140	97.43 271	99.75 211	99.68 86

ACMMPR		99.23 153	99.06 178	99.76 62	99.74 132	99.69 93	99.31 137	99.59 197	98.36 281	99.35 246	99.38 285	98.61 154	99.93 96	97.43 271	99.75 211	99.67 93

Vis-MVSNet (Re-imp)		98.77 244	98.58 250	99.34 230	99.78 103	98.88 253	99.61 68	99.56 213	99.11 195	99.24 272	99.56 236	93.00 342	99.78 309	97.43 271	99.89 124	99.35 249

MIMVSNet		98.43 280	98.20 284	99.11 273	99.53 222	98.38 294	99.58 77	98.61 356	98.96 208	99.33 252	99.76 112	90.92 362	99.81 296	97.38 274	99.76 209	99.15 296

WB-MVSnew		98.34 291	98.14 290	98.96 291	98.14 404	97.90 326	98.27 319	97.26 391	98.63 252	98.80 325	98.00 394	97.77 242	99.90 159	97.37 275	98.98 345	99.09 312

XVG-OURS-SEG-HR		99.16 181	98.99 204	99.66 115	99.84 59	99.64 109	98.25 322	99.73 115	98.39 278	99.63 159	99.43 273	99.70 24	99.90 159	97.34 276	98.64 368	99.44 225

COLMAP_ROB	98.06 12	99.45 99	99.37 109	99.70 101	99.83 63	99.70 89	99.38 118	99.78 92	99.53 124	99.67 148	99.78 102	99.19 77	99.86 225	97.32 277	99.87 145	99.55 172
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MCST-MVS		99.02 208	98.81 231	99.65 120	99.58 192	99.49 145	98.58 289	99.07 332	98.40 277	99.04 300	99.25 315	98.51 173	99.80 303	97.31 278	99.51 292	99.65 110

region2R		99.23 153	99.05 182	99.77 55	99.76 115	99.70 89	99.31 137	99.59 197	98.41 275	99.32 255	99.36 291	98.73 139	99.93 96	97.29 279	99.74 218	99.67 93

APD-MVS_3200maxsize		99.31 139	99.16 148	99.74 77	99.53 222	99.75 66	99.27 152	99.61 180	99.19 177	99.57 185	99.64 182	98.76 133	99.90 159	97.29 279	99.62 259	99.56 169

TAPA-MVS	97.92 13	98.03 306	97.55 322	99.46 191	99.47 251	99.44 159	98.50 303	99.62 173	86.79 403	99.07 298	99.26 313	98.26 203	99.62 375	97.28 281	99.73 223	99.31 260
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SR-MVS-dyc-post		99.27 146	99.11 161	99.73 86	99.54 216	99.74 72	99.26 154	99.62 173	99.16 185	99.52 206	99.64 182	98.41 184	99.91 140	97.27 282	99.61 266	99.54 180

RE-MVS-def			99.13 154		99.54 216	99.74 72	99.26 154	99.62 173	99.16 185	99.52 206	99.64 182	98.57 159		97.27 282	99.61 266	99.54 180

testing11		96.05 360	95.41 362	97.97 351	98.78 377	95.27 382	98.59 287	98.23 374	98.86 224	96.56 397	96.91 409	75.20 408	99.69 344	97.26 284	98.29 378	98.93 343

test_yl		98.25 294	97.95 302	99.13 271	99.17 330	98.47 284	99.00 233	98.67 353	98.97 206	99.22 276	99.02 349	91.31 356	99.69 344	97.26 284	98.93 347	99.24 271

DCV-MVSNet		98.25 294	97.95 302	99.13 271	99.17 330	98.47 284	99.00 233	98.67 353	98.97 206	99.22 276	99.02 349	91.31 356	99.69 344	97.26 284	98.93 347	99.24 271

PHI-MVS		99.11 192	98.95 211	99.59 152	99.13 335	99.59 128	99.17 181	99.65 162	97.88 320	99.25 269	99.46 268	98.97 109	99.80 303	97.26 284	99.82 179	99.37 243

tfpnnormal		99.43 104	99.38 106	99.60 149	99.87 49	99.75 66	99.59 75	99.78 92	99.71 82	99.90 49	99.69 155	98.85 121	99.90 159	97.25 288	99.78 203	99.15 296

PatchmatchNet		97.65 320	97.80 313	97.18 374	98.82 372	92.49 399	99.17 181	98.39 368	98.12 302	98.79 327	99.58 225	90.71 367	99.89 178	97.23 289	99.41 307	99.16 294
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CNVR-MVS		98.99 219	98.80 233	99.56 164	99.25 314	99.43 163	98.54 298	99.27 305	98.58 258	98.80 325	99.43 273	98.53 168	99.70 338	97.22 290	99.59 273	99.54 180

testing3		96.48 348	95.63 359	99.01 287	99.23 318	97.81 329	98.90 249	99.10 331	98.72 243	97.84 379	97.92 395	72.44 412	99.85 242	97.21 291	99.33 317	99.35 249

HPM-MVS		99.25 149	99.07 176	99.78 52	99.81 78	99.75 66	99.61 68	99.67 147	97.72 327	99.35 246	99.25 315	99.23 73	99.92 118	97.21 291	99.82 179	99.67 93
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		99.19 171	99.00 198	99.76 62	99.76 115	99.68 96	99.38 118	99.54 225	98.34 290	99.01 301	99.50 254	98.53 168	99.93 96	97.18 293	99.78 203	99.66 102

ACMMP		99.25 149	99.08 172	99.74 77	99.79 96	99.68 96	99.50 95	99.65 162	98.07 306	99.52 206	99.69 155	98.57 159	99.92 118	97.18 293	99.79 198	99.63 125
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		96.98 337	96.42 344	98.66 324	99.42 268	97.47 340	97.27 386	94.30 403	97.24 350	99.15 286	98.86 366	85.01 393	99.87 206	97.10 295	99.39 309	98.63 364

XVG-ACMP-BASELINE		99.23 153	99.10 169	99.63 134	99.82 70	99.58 132	98.83 258	99.72 124	98.36 281	99.60 177	99.71 140	98.92 113	99.91 140	97.08 296	99.84 162	99.40 236

MSDG		99.08 196	98.98 207	99.37 223	99.60 183	99.13 225	97.54 373	99.74 111	98.84 228	99.53 204	99.55 243	99.10 87	99.79 306	97.07 297	99.86 153	99.18 290

SteuartSystems-ACMMP		99.30 140	99.14 152	99.76 62	99.87 49	99.66 100	99.18 176	99.60 191	98.55 260	99.57 185	99.67 170	99.03 102	99.94 79	97.01 298	99.80 193	99.69 80
Skip Steuart: Steuart Systems R&D Blog.
UWE-MVS		96.21 356	95.78 356	97.49 364	98.53 390	93.83 394	98.04 342	93.94 406	98.96 208	98.46 353	98.17 390	79.86 401	99.87 206	96.99 299	99.06 338	98.78 359

EPMVS		96.53 347	96.32 345	97.17 375	98.18 401	92.97 398	99.39 115	89.95 412	98.21 298	98.61 342	99.59 222	86.69 391	99.72 331	96.99 299	99.23 332	98.81 356

MSP-MVS		99.04 205	98.79 234	99.81 38	99.78 103	99.73 75	99.35 126	99.57 208	98.54 263	99.54 199	98.99 351	96.81 284	99.93 96	96.97 301	99.53 288	99.77 58
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++		98.96 223	98.70 240	99.74 77	99.52 227	99.71 82	98.86 253	99.19 323	98.47 271	98.59 344	99.06 341	98.08 220	99.91 140	96.94 302	99.60 269	99.60 150

SR-MVS		99.19 171	99.00 198	99.74 77	99.51 229	99.72 80	99.18 176	99.60 191	98.85 225	99.47 218	99.58 225	98.38 189	99.92 118	96.92 303	99.54 286	99.57 167

PGM-MVS		99.20 168	99.01 194	99.77 55	99.75 126	99.71 82	99.16 187	99.72 124	97.99 310	99.42 230	99.60 217	98.81 123	99.93 96	96.91 304	99.74 218	99.66 102

HY-MVS	98.23 9	98.21 299	97.95 302	98.99 288	99.03 352	98.24 298	99.61 68	98.72 349	96.81 364	98.73 332	99.51 251	94.06 327	99.86 225	96.91 304	98.20 381	98.86 352

MDTV_nov1_ep13			97.73 317		98.70 385	90.83 408	99.15 189	98.02 377	98.51 266	98.82 322	99.61 209	90.98 361	99.66 365	96.89 306	98.92 349

GST-MVS		99.16 181	98.96 210	99.75 72	99.73 135	99.73 75	99.20 171	99.55 219	98.22 297	99.32 255	99.35 296	98.65 150	99.91 140	96.86 307	99.74 218	99.62 136

test_post1							99.14 191				51.63 420	89.54 377	99.82 281	96.86 307

SCA		98.11 302	98.36 270	97.36 369	99.20 324	92.99 397	98.17 327	98.49 363	98.24 296	99.10 294	99.57 232	96.01 309	99.94 79	96.86 307	99.62 259	99.14 301

XVG-OURS		99.21 166	99.06 178	99.65 120	99.82 70	99.62 116	97.87 360	99.74 111	98.36 281	99.66 152	99.68 166	99.71 22	99.90 159	96.84 310	99.88 133	99.43 231

LCM-MVSNet-Re		99.28 142	99.15 151	99.67 108	99.33 298	99.76 60	99.34 127	99.97 18	98.93 214	99.91 46	99.79 94	98.68 143	99.93 96	96.80 311	99.56 277	99.30 262

RPSCF		99.18 175	99.02 191	99.64 127	99.83 63	99.85 19	99.44 109	99.82 68	98.33 291	99.50 213	99.78 102	97.90 232	99.65 371	96.78 312	99.83 170	99.44 225

旧先验2							97.94 354		95.33 383	98.94 306			99.88 192	96.75 313

MDTV_nov1_ep13_2view						91.44 406	99.14 191		97.37 345	99.21 278		91.78 354		96.75 313		99.03 330

CLD-MVS		98.76 245	98.57 251	99.33 233	99.57 202	98.97 242	97.53 375	99.55 219	96.41 368	99.27 267	99.13 330	99.07 94	99.78 309	96.73 315	99.89 124	99.23 275
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Patchmatch-test		98.10 303	97.98 300	98.48 332	99.27 311	96.48 363	99.40 113	99.07 332	98.81 231	99.23 273	99.57 232	90.11 373	99.87 206	96.69 316	99.64 256	99.09 312

baseline2		96.83 340	96.28 346	98.46 333	99.09 347	96.91 357	98.83 258	93.87 407	97.23 351	96.23 402	98.36 386	88.12 381	99.90 159	96.68 317	98.14 386	98.57 371

cascas		96.99 336	96.82 342	97.48 365	97.57 410	95.64 377	96.43 400	99.56 213	91.75 398	97.13 392	97.61 402	95.58 314	98.63 406	96.68 317	99.11 336	98.18 391

PC_three_1452									97.56 332	99.68 143	99.41 275	99.09 89	97.09 408	96.66 319	99.60 269	99.62 136

LPG-MVS_test		99.22 161	99.05 182	99.74 77	99.82 70	99.63 114	99.16 187	99.73 115	97.56 332	99.64 155	99.69 155	99.37 56	99.89 178	96.66 319	99.87 145	99.69 80

LGP-MVS_train				99.74 77	99.82 70	99.63 114		99.73 115	97.56 332	99.64 155	99.69 155	99.37 56	99.89 178	96.66 319	99.87 145	99.69 80

ETVMVS		96.14 357	95.22 367	98.89 307	98.80 373	98.01 317	98.66 280	98.35 371	98.71 245	97.18 390	96.31 417	74.23 411	99.75 323	96.64 322	98.13 388	98.90 347

TinyColmap		98.97 220	98.93 213	99.07 281	99.46 255	98.19 303	97.75 364	99.75 105	98.79 234	99.54 199	99.70 148	98.97 109	99.62 375	96.63 323	99.83 170	99.41 235

LF4IMVS		99.01 214	98.92 217	99.27 249	99.71 141	99.28 199	98.59 287	99.77 95	98.32 292	99.39 242	99.41 275	98.62 152	99.84 257	96.62 324	99.84 162	98.69 363

NCCC		98.82 240	98.57 251	99.58 155	99.21 321	99.31 194	98.61 282	99.25 310	98.65 250	98.43 354	99.26 313	97.86 235	99.81 296	96.55 325	99.27 327	99.61 146

OPU-MVS				99.29 244	99.12 337	99.44 159	99.20 171				99.40 279	99.00 103	98.84 405	96.54 326	99.60 269	99.58 162

F-COLMAP		98.74 247	98.45 261	99.62 143	99.57 202	99.47 148	98.84 256	99.65 162	96.31 371	98.93 307	99.19 327	97.68 248	99.87 206	96.52 327	99.37 312	99.53 185

testing99		95.86 365	95.19 368	97.87 355	98.76 380	95.03 384	98.62 281	98.44 365	98.68 247	96.67 396	96.66 413	74.31 410	99.69 344	96.51 328	98.03 390	98.90 347

ADS-MVSNet2		97.78 314	97.66 321	98.12 348	99.14 333	95.36 380	99.22 168	98.75 348	96.97 359	98.25 359	99.64 182	90.90 363	99.94 79	96.51 328	99.56 277	99.08 318

ADS-MVSNet		97.72 319	97.67 320	97.86 356	99.14 333	94.65 388	99.22 168	98.86 341	96.97 359	98.25 359	99.64 182	90.90 363	99.84 257	96.51 328	99.56 277	99.08 318

PatchMatch-RL		98.68 254	98.47 259	99.30 243	99.44 260	99.28 199	98.14 330	99.54 225	97.12 357	99.11 292	99.25 315	97.80 240	99.70 338	96.51 328	99.30 321	98.93 343

CMPMVS	77.52 23	98.50 273	98.19 287	99.41 212	98.33 397	99.56 135	99.01 230	99.59 197	95.44 381	99.57 185	99.80 84	95.64 312	99.46 397	96.47 332	99.92 101	99.21 281
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing91		96.00 361	95.32 365	98.02 349	98.76 380	95.39 379	98.38 312	98.65 355	98.82 229	96.84 393	96.71 412	75.06 409	99.71 335	96.46 333	98.23 380	98.98 338

SF-MVS		99.10 195	98.93 213	99.62 143	99.58 192	99.51 143	99.13 197	99.65 162	97.97 312	99.42 230	99.61 209	98.86 120	99.87 206	96.45 334	99.68 243	99.49 207

FE-MVS		97.85 311	97.42 324	99.15 267	99.44 260	98.75 263	99.77 15	98.20 375	95.85 376	99.33 252	99.80 84	88.86 379	99.88 192	96.40 335	99.12 335	98.81 356

DPE-MVS		99.14 185	98.92 217	99.82 35	99.57 202	99.77 53	98.74 274	99.60 191	98.55 260	99.76 110	99.69 155	98.23 208	99.92 118	96.39 336	99.75 211	99.76 63
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
gm-plane-assit					97.59 408	89.02 414			93.47 394		98.30 387		99.84 257	96.38 337

AllTest		99.21 166	99.07 176	99.63 134	99.78 103	99.64 109	99.12 201	99.83 63	98.63 252	99.63 159	99.72 132	98.68 143	99.75 323	96.38 337	99.83 170	99.51 197

TestCases				99.63 134	99.78 103	99.64 109		99.83 63	98.63 252	99.63 159	99.72 132	98.68 143	99.75 323	96.38 337	99.83 170	99.51 197

testdata				99.42 205	99.51 229	98.93 249		99.30 300	96.20 372	98.87 317	99.40 279	98.33 196	99.89 178	96.29 340	99.28 324	99.44 225

dp		96.86 339	97.07 332	96.24 386	98.68 386	90.30 412	99.19 175	98.38 369	97.35 346	98.23 361	99.59 222	87.23 383	99.82 281	96.27 341	98.73 364	98.59 368

tpmvs		97.39 328	97.69 318	96.52 382	98.41 394	91.76 402	99.30 140	98.94 340	97.74 326	97.85 378	99.55 243	92.40 349	99.73 329	96.25 342	98.73 364	98.06 393

KD-MVS_2432*1600		95.89 362	95.41 362	97.31 372	94.96 412	93.89 391	97.09 391	99.22 317	97.23 351	98.88 314	99.04 344	79.23 403	99.54 387	96.24 343	96.81 400	98.50 377

miper_refine_blended		95.89 362	95.41 362	97.31 372	94.96 412	93.89 391	97.09 391	99.22 317	97.23 351	98.88 314	99.04 344	79.23 403	99.54 387	96.24 343	96.81 400	98.50 377

ACMP	97.51 14	99.05 202	98.84 227	99.67 108	99.78 103	99.55 138	98.88 251	99.66 152	97.11 358	99.47 218	99.60 217	99.07 94	99.89 178	96.18 345	99.85 157	99.58 162
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		98.90 231	98.72 237	99.44 199	99.39 273	99.42 166	98.58 289	99.64 168	97.31 348	99.44 224	99.62 200	98.59 156	99.69 344	96.17 346	99.79 198	99.22 278

DP-MVS Recon		98.50 273	98.23 281	99.31 240	99.49 240	99.46 152	98.56 294	99.63 170	94.86 390	98.85 319	99.37 287	97.81 239	99.59 381	96.08 347	99.44 302	98.88 350

tpm cat1		96.78 341	96.98 335	96.16 387	98.85 368	90.59 411	99.08 215	99.32 293	92.37 396	97.73 384	99.46 268	91.15 359	99.69 344	96.07 348	98.80 355	98.21 388

tpm2		96.35 351	96.22 347	96.73 380	98.88 367	91.75 403	99.21 170	98.51 361	93.27 395	97.89 375	99.21 324	84.83 394	99.70 338	96.04 349	98.18 384	98.75 362

dmvs_re		98.69 253	98.48 258	99.31 240	99.55 214	99.42 166	99.54 85	98.38 369	99.32 157	98.72 333	98.71 374	96.76 286	99.21 400	96.01 350	99.35 315	99.31 260

test_0402		99.22 161	99.14 152	99.45 194	99.79 96	99.43 163	99.28 149	99.68 143	99.54 122	99.40 241	99.56 236	99.07 94	99.82 281	96.01 350	99.96 66	99.11 305

ITE_SJBPF				99.38 220	99.63 176	99.44 159		99.73 115	98.56 259	99.33 252	99.53 247	98.88 119	99.68 356	96.01 350	99.65 254	99.02 335

test_prior2							97.95 353		97.87 321	98.05 369	99.05 342	97.90 232		95.99 353	99.49 297

testdata2													99.89 178	95.99 353

原ACMM1				99.37 223	99.47 251	98.87 255		99.27 305	96.74 366	98.26 358	99.32 300	97.93 231	99.82 281	95.96 355	99.38 310	99.43 231

新几何1				99.52 175	99.50 235	99.22 213		99.26 307	95.66 380	98.60 343	99.28 308	97.67 249	99.89 178	95.95 356	99.32 319	99.45 220

MP-MVS		99.06 199	98.83 229	99.76 62	99.76 115	99.71 82	99.32 132	99.50 247	98.35 286	98.97 303	99.48 261	98.37 190	99.92 118	95.95 356	99.75 211	99.63 125
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing222		95.60 371	94.59 374	98.61 325	98.66 387	97.45 342	98.54 298	97.90 381	98.53 264	96.54 398	96.47 414	70.62 415	99.81 296	95.91 358	98.15 385	98.56 372

wuyk23d		97.58 323	99.13 154	92.93 390	99.69 153	99.49 145	99.52 87	99.77 95	97.97 312	99.96 23	99.79 94	99.84 12	99.94 79	95.85 359	99.82 179	79.36 408

HQP_MVS		98.90 231	98.68 241	99.55 167	99.58 192	99.24 210	98.80 266	99.54 225	98.94 211	99.14 288	99.25 315	97.24 268	99.82 281	95.84 360	99.78 203	99.60 150

plane_prior5								99.54 225					99.82 281	95.84 360	99.78 203	99.60 150

无先验							98.01 345	99.23 314	95.83 377				99.85 242	95.79 362		99.44 225

CPTT-MVS		98.74 247	98.44 262	99.64 127	99.61 181	99.38 178	99.18 176	99.55 219	96.49 367	99.27 267	99.37 287	97.11 276	99.92 118	95.74 363	99.67 249	99.62 136

PLC	97.35 16	98.36 286	97.99 298	99.48 186	99.32 299	99.24 210	98.50 303	99.51 243	95.19 386	98.58 345	98.96 358	96.95 281	99.83 272	95.63 364	99.25 328	99.37 243
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		98.57 265	98.34 273	99.28 246	99.18 329	99.10 232	98.34 314	99.41 269	98.48 270	98.52 349	98.98 354	97.05 278	99.78 309	95.59 365	99.50 295	98.96 339

1314		98.00 308	97.90 310	98.27 344	98.90 362	97.45 342	99.30 140	99.06 334	94.98 387	97.21 389	99.12 334	98.43 181	99.67 361	95.58 366	98.56 371	97.71 397

PVSNet_0	95.53 19	95.85 366	95.31 366	97.47 366	98.78 377	93.48 396	95.72 402	99.40 276	96.18 373	97.37 385	97.73 397	95.73 311	99.58 382	95.49 367	81.40 410	99.36 246

MAR-MVS		98.24 296	97.92 308	99.19 262	98.78 377	99.65 106	99.17 181	99.14 328	95.36 382	98.04 370	98.81 370	97.47 258	99.72 331	95.47 368	99.06 338	98.21 388
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	98.23 297	97.89 311	99.26 252	99.19 326	99.26 203	99.65 58	99.69 140	91.33 400	98.14 367	99.77 109	98.28 199	99.96 54	95.41 369	99.55 281	98.58 370

train_agg		98.35 289	97.95 302	99.57 161	99.35 284	99.35 188	98.11 334	99.41 269	94.90 388	97.92 373	98.99 351	98.02 224	99.85 242	95.38 370	99.44 302	99.50 202

9.14			98.64 242		99.45 259		98.81 263	99.60 191	97.52 337	99.28 266	99.56 236	98.53 168	99.83 272	95.36 371	99.64 256

APD-MVS		98.87 236	98.59 247	99.71 97	99.50 235	99.62 116	99.01 230	99.57 208	96.80 365	99.54 199	99.63 193	98.29 198	99.91 140	95.24 372	99.71 232	99.61 146
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WAC-MVS						96.36 366								95.20 373

AdaColmap		98.60 260	98.35 272	99.38 220	99.12 337	99.22 213	98.67 279	99.42 268	97.84 324	98.81 323	99.27 310	97.32 266	99.81 296	95.14 374	99.53 288	99.10 307

test9_res														95.10 375	99.44 302	99.50 202

CDPH-MVS		98.56 266	98.20 284	99.61 146	99.50 235	99.46 152	98.32 316	99.41 269	95.22 384	99.21 278	99.10 338	98.34 194	99.82 281	95.09 376	99.66 252	99.56 169

BH-untuned		98.22 298	98.09 293	98.58 329	99.38 276	97.24 348	98.55 295	98.98 339	97.81 325	99.20 283	98.76 372	97.01 279	99.65 371	94.83 377	98.33 376	98.86 352

BP-MVS														94.73 378

HQP-MVS		98.36 286	98.02 297	99.39 217	99.31 300	98.94 246	97.98 349	99.37 284	97.45 340	98.15 363	98.83 367	96.67 287	99.70 338	94.73 378	99.67 249	99.53 185

QAPM		98.40 284	97.99 298	99.65 120	99.39 273	99.47 148	99.67 49	99.52 239	91.70 399	98.78 329	99.80 84	98.55 162	99.95 64	94.71 380	99.75 211	99.53 185

agg_prior2														94.58 381	99.46 301	99.50 202

myMVS_eth3d		95.63 369	94.73 371	98.34 339	98.50 392	96.36 366	98.60 284	99.21 320	97.89 318	96.76 394	96.37 415	72.10 413	99.57 383	94.38 382	98.73 364	99.09 312

BH-RMVSNet		98.41 282	98.14 290	99.21 259	99.21 321	98.47 284	98.60 284	98.26 373	98.35 286	98.93 307	99.31 302	97.20 273	99.66 365	94.32 383	99.10 337	99.51 197

E-PMN		97.14 335	97.43 323	96.27 385	98.79 375	91.62 404	95.54 403	99.01 338	99.44 138	98.88 314	99.12 334	92.78 343	99.68 356	94.30 384	99.03 342	97.50 398

MG-MVS		98.52 270	98.39 267	98.94 294	99.15 332	97.39 345	98.18 325	99.21 320	98.89 221	99.23 273	99.63 193	97.37 264	99.74 326	94.22 385	99.61 266	99.69 80

API-MVS		98.38 285	98.39 267	98.35 337	98.83 369	99.26 203	99.14 191	99.18 324	98.59 257	98.66 338	98.78 371	98.61 154	99.57 383	94.14 386	99.56 277	96.21 405

PAPM_NR		98.36 286	98.04 295	99.33 233	99.48 245	98.93 249	98.79 269	99.28 304	97.54 335	98.56 348	98.57 379	97.12 275	99.69 344	94.09 387	98.90 353	99.38 240

ZD-MVS					99.43 263	99.61 123		99.43 266	96.38 369	99.11 292	99.07 340	97.86 235	99.92 118	94.04 388	99.49 297

DPM-MVS		98.28 292	97.94 306	99.32 237	99.36 281	99.11 227	97.31 385	98.78 347	96.88 361	98.84 320	99.11 337	97.77 242	99.61 379	94.03 389	99.36 313	99.23 275

gg-mvs-nofinetune		95.87 364	95.17 369	97.97 351	98.19 400	96.95 355	99.69 41	89.23 413	99.89 36	96.24 401	99.94 16	81.19 398	99.51 393	93.99 390	98.20 381	97.44 399

PMVS	92.94 21	98.82 240	98.81 231	98.85 309	99.84 59	97.99 318	99.20 171	99.47 255	99.71 82	99.42 230	99.82 75	98.09 218	99.47 395	93.88 391	99.85 157	99.07 323
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		96.96 338	97.28 327	95.99 388	98.76 380	91.03 407	95.26 405	98.61 356	99.34 154	98.92 310	98.88 365	93.79 331	99.66 365	92.87 392	99.05 340	97.30 402

BH-w/o		97.20 332	97.01 334	97.76 359	99.08 348	95.69 376	98.03 344	98.52 360	95.76 378	97.96 372	98.02 392	95.62 313	99.47 395	92.82 393	97.25 399	98.12 392

TR-MVS		97.44 327	97.15 331	98.32 340	98.53 390	97.46 341	98.47 305	97.91 380	96.85 362	98.21 362	98.51 383	96.42 296	99.51 393	92.16 394	97.29 398	97.98 394

OpenMVS_ROB	97.31 17	97.36 330	96.84 340	98.89 307	99.29 306	99.45 157	98.87 252	99.48 252	86.54 405	99.44 224	99.74 120	97.34 265	99.86 225	91.61 395	99.28 324	97.37 401

GG-mvs-BLEND				97.36 369	97.59 408	96.87 358	99.70 34	88.49 414		94.64 407	97.26 406	80.66 399	99.12 401	91.50 396	96.50 404	96.08 407

DeepMVS_CX				97.98 350	99.69 153	96.95 355		99.26 307	75.51 408	95.74 404	98.28 388	96.47 294	99.62 375	91.23 397	97.89 392	97.38 400

PAPR		97.56 324	97.07 332	99.04 285	98.80 373	98.11 310	97.63 369	99.25 310	94.56 393	98.02 371	98.25 389	97.43 260	99.68 356	90.90 398	98.74 362	99.33 253

MVS		95.72 368	94.63 373	98.99 288	98.56 389	97.98 323	99.30 140	98.86 341	72.71 409	97.30 386	99.08 339	98.34 194	99.74 326	89.21 399	98.33 376	99.26 268

thres600view7		96.60 346	96.16 348	97.93 353	99.63 176	96.09 372	99.18 176	97.57 385	98.77 238	98.72 333	97.32 404	87.04 385	99.72 331	88.57 400	98.62 369	97.98 394

FPMVS		96.32 352	95.50 360	98.79 317	99.60 183	98.17 306	98.46 309	98.80 346	97.16 355	96.28 399	99.63 193	82.19 397	99.09 402	88.45 401	98.89 354	99.10 307

PCF-MVS	96.03 18	96.73 343	95.86 354	99.33 233	99.44 260	99.16 222	96.87 396	99.44 263	86.58 404	98.95 305	99.40 279	94.38 325	99.88 192	87.93 402	99.80 193	98.95 341
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres100view900		96.39 350	96.03 351	97.47 366	99.63 176	95.93 373	99.18 176	97.57 385	98.75 242	98.70 336	97.31 405	87.04 385	99.67 361	87.62 403	98.51 373	96.81 403

tfpn200view9		96.30 353	95.89 352	97.53 363	99.58 192	96.11 370	99.00 233	97.54 388	98.43 272	98.52 349	96.98 407	86.85 387	99.67 361	87.62 403	98.51 373	96.81 403

thres400		96.40 349	95.89 352	97.92 354	99.58 192	96.11 370	99.00 233	97.54 388	98.43 272	98.52 349	96.98 407	86.85 387	99.67 361	87.62 403	98.51 373	97.98 394

thres200		96.09 358	95.68 358	97.33 371	99.48 245	96.22 369	98.53 300	97.57 385	98.06 307	98.37 356	96.73 411	86.84 389	99.61 379	86.99 406	98.57 370	96.16 406

MVE	92.54 22	96.66 345	96.11 349	98.31 342	99.68 161	97.55 338	97.94 354	95.60 399	99.37 150	90.68 410	98.70 375	96.56 290	98.61 407	86.94 407	99.55 281	98.77 361
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dmvs_testset		97.27 331	96.83 341	98.59 327	99.46 255	97.55 338	99.25 160	96.84 393	98.78 236	97.24 388	97.67 398	97.11 276	98.97 404	86.59 408	98.54 372	99.27 266

PAPM		95.61 370	94.71 372	98.31 342	99.12 337	96.63 361	96.66 399	98.46 364	90.77 401	96.25 400	98.68 376	93.01 341	99.69 344	81.60 409	97.86 394	98.62 365

dongtai		89.37 375	88.91 378	90.76 391	99.19 326	77.46 416	95.47 404	87.82 415	92.28 397	94.17 408	98.82 369	71.22 414	95.54 410	63.85 410	97.34 397	99.27 266

kuosan		85.65 377	84.57 380	88.90 393	97.91 405	77.11 417	96.37 401	87.62 416	85.24 406	85.45 411	96.83 410	69.94 416	90.98 412	45.90 411	95.83 407	98.62 365

test123		29.31 378	33.05 383	18.08 394	25.93 418	12.24 419	97.53 375	10.93 419	11.78 412	24.21 413	50.08 422	21.04 417	8.60 413	23.51 412	32.43 412	33.39 409

testmvs		28.94 379	33.33 381	15.79 395	26.03 417	9.81 420	96.77 397	15.67 418	11.55 413	23.87 414	50.74 421	19.03 418	8.53 414	23.21 413	33.07 411	29.03 410

test_blank		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		24.88 380	33.17 382	0.00 396	0.00 419	0.00 421	0.00 407	99.62 173	0.00 414	0.00 415	99.13 330	99.82 13	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		16.61 381	22.14 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	99.28 66	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		8.26 390	11.02 393	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	99.16 328	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		8.33 382	11.11 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	100.00 1	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

FOURS1					99.83 63	99.89 10	99.74 23	99.71 127	99.69 90	99.63 159

test_one_0601					99.63 176	99.76 60		99.55 219	99.23 171	99.31 260	99.61 209	98.59 156

eth-test2					0.00 419

eth-test					0.00 419

test_241102_ONE					99.69 153	99.82 34		99.54 225	99.12 194	99.82 80	99.49 258	98.91 115	99.52 392

save fliter					99.53 222	99.25 206	98.29 318	99.38 283	99.07 198

test0726					99.69 153	99.80 43	99.24 161	99.57 208	99.16 185	99.73 127	99.65 180	98.35 192

GSMVS																99.14 301

test_part2					99.62 180	99.67 98				99.55 197

sam_mvs1												90.81 366				99.14 301

sam_mvs												90.52 370

MTGPA								99.53 234

test_post											52.41 419	90.25 372	99.86 225

patchmatchnet-post											99.62 200	90.58 368	99.94 79

MTMP							99.09 212	98.59 359

TEST9					99.35 284	99.35 188	98.11 334	99.41 269	94.83 391	97.92 373	98.99 351	98.02 224	99.85 242

test_8					99.34 293	99.31 194	98.08 338	99.40 276	94.90 388	97.87 377	98.97 356	98.02 224	99.84 257

agg_prior					99.35 284	99.36 185		99.39 279		97.76 383			99.85 242

test_prior4						99.19 219	98.00 347

test_prior				99.46 191	99.35 284	99.22 213		99.39 279					99.69 344			99.48 211

新几何2							98.04 342

旧先验1					99.49 240	99.29 197		99.26 307			99.39 283	97.67 249			99.36 313	99.46 219

原ACMM2							97.92 356

test222					99.51 229	99.08 234	97.83 362	99.29 301	95.21 385	98.68 337	99.31 302	97.28 267			99.38 310	99.43 231

segment_acmp												98.37 190

testdata1							97.72 365		97.86 323

test12				99.54 172	99.29 306	99.33 191		99.16 326		98.43 354		97.54 256	99.82 281		99.47 299	99.48 211

plane_prior7					99.58 192	99.38 178

plane_prior6					99.47 251	99.26 203						97.24 268

plane_prior4											99.25 315

plane_prior3						99.31 194			98.36 281	99.14 288

plane_prior2							98.80 266		98.94 211

plane_prior1					99.51 229

plane_prior						99.24 210	98.42 310		97.87 321						99.71 232

n2								0.00 420

nn								0.00 420

door-mid								99.83 63

test11								99.29 301

door								99.77 95

HQP5-MVS						98.94 246

HQP-NCC					99.31 300		97.98 349		97.45 340	98.15 363

ACMP_Plane					99.31 300		97.98 349		97.45 340	98.15 363

HQP4-MVS										98.15 363			99.70 338			99.53 185

HQP3-MVS								99.37 284							99.67 249

HQP2-MVS												96.67 287

NP-MVS					99.40 272	99.13 225					98.83 367

ACMMP++_ref															99.94 90

ACMMP++															99.79 198

Test By Simon												98.41 184

High-resolution multi-view benchmark