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.

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 16	100.00 1	99.85 29

Gipuma		99.03 79	99.16 61	98.64 211	99.94 2	98.51 109	99.32 26	99.75 42	99.58 38	98.60 260	99.62 40	98.22 103	99.51 389	97.70 184	99.73 176	97.89 422
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 41	99.53 38	99.91 3	98.98 71	99.63 7	99.58 83	99.44 52	99.78 39	99.76 15	96.39 242	99.92 64	99.44 54	99.92 68	99.68 69

pmmvs6		99.67 3	99.70 3	99.60 15	99.90 4	99.27 27	99.53 9	99.76 39	99.64 27	99.84 30	99.83 4	99.50 9	99.87 133	99.36 57	99.92 68	99.64 82

PS-MVSNAJss		99.46 17	99.49 16	99.35 77	99.90 4	98.15 136	99.20 48	99.65 67	99.48 44	99.92 8	99.71 22	98.07 117	99.96 14	99.53 47	100.00 1	99.93 11

testf1		99.25 41	99.16 61	99.51 48	99.89 6	99.63 4	98.71 104	99.69 54	98.90 132	99.43 102	99.35 103	98.86 34	99.67 315	97.81 173	99.81 127	99.24 270

APD_test2		99.25 41	99.16 61	99.51 48	99.89 6	99.63 4	98.71 104	99.69 54	98.90 132	99.43 102	99.35 103	98.86 34	99.67 315	97.81 173	99.81 127	99.24 270

ANet_high		99.57 10	99.67 6	99.28 93	99.89 6	98.09 143	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 42	99.31 61	100.00 1	99.82 35

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 54	98.93 128	99.65 63	99.72 21	98.93 32	99.95 26	99.11 77	100.00 1	99.82 35

v7n		99.53 12	99.57 13	99.41 67	99.88 9	98.54 107	99.45 14	99.61 76	99.66 24	99.68 57	99.66 32	98.44 77	99.95 26	99.73 27	99.96 28	99.75 58

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 99	99.34 23	99.71 47	99.27 73	99.90 14	99.74 18	99.68 4	99.97 7	99.55 42	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 71	99.87 12	98.13 139	98.08 183	99.95 1	99.45 50	99.98 2	99.75 16	99.80 1	99.97 7	99.82 12	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 56	99.87 12	98.61 99	99.28 40	99.66 63	99.09 107	99.89 18	99.68 25	99.53 7	99.97 7	99.50 50	99.99 5	99.87 21

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 89	99.39 20	99.56 97	99.11 97	99.70 51	99.73 20	99.00 27	99.97 7	99.26 65	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 39	99.55 28	99.86 14	99.19 42	99.41 17	99.59 81	99.59 36	99.71 49	99.57 49	97.12 197	99.90 80	99.21 70	99.87 96	99.54 138

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 36	99.63 29	99.78 39	99.67 30	99.48 10	99.81 218	99.30 62	99.97 21	99.77 49
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
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 83	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 87	99.95 38	99.78 46

SixPastTwentyTwo		98.75 126	98.62 139	99.16 115	99.83 18	97.96 163	99.28 40	98.20 369	99.37 60	99.70 51	99.65 36	92.65 348	99.93 53	99.04 84	99.84 110	99.60 98

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 71	99.88 4	99.86 24	99.80 11	99.03 24	99.89 96	99.48 52	99.93 55	99.60 98

Baseline_NR-MVSNet		98.98 87	98.86 105	99.36 71	99.82 19	98.55 104	97.47 287	99.57 90	99.37 60	99.21 155	99.61 43	96.76 224	99.83 191	98.06 151	99.83 117	99.71 61

pm-mvs1		99.44 19	99.48 18	99.33 86	99.80 21	98.63 96	99.29 36	99.63 71	99.30 70	99.65 63	99.60 45	99.16 22	99.82 201	99.07 80	99.83 117	99.56 125

TransMVSNet (Re)		99.44 19	99.47 21	99.36 71	99.80 21	98.58 102	99.27 42	99.57 90	99.39 58	99.75 44	99.62 40	99.17 20	99.83 191	99.06 82	99.62 232	99.66 76

K. test v3		98.00 242	97.66 267	99.03 142	99.79 23	97.56 199	99.19 52	92.47 455	99.62 32	99.52 84	99.66 32	89.61 379	99.96 14	99.25 67	99.81 127	99.56 125

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 80	99.78 24	98.11 140	97.77 239	99.90 11	99.33 65	99.97 3	99.66 32	99.71 3	99.96 14	99.79 19	99.99 5	99.96 8

APD_test1		98.83 110	98.66 132	99.34 80	99.78 24	99.47 9	98.42 145	99.45 145	98.28 184	98.98 189	99.19 145	97.76 145	99.58 363	96.57 278	99.55 259	98.97 324

test_vis3_rt		99.14 61	99.17 59	99.07 132	99.78 24	98.38 116	98.92 82	99.94 2	97.80 227	99.91 12	99.67 30	97.15 196	98.91 448	99.76 23	99.56 255	99.92 12

EGC-MVSNET		85.24 435	80.54 438	99.34 80	99.77 27	99.20 39	99.08 61	99.29 225	12.08 473	20.84 474	99.42 88	97.55 164	99.85 155	97.08 228	99.72 184	98.96 326

Anonymous20240521		98.69 138	98.87 101	98.16 287	99.77 27	95.11 328	99.08 61	99.44 153	99.34 64	99.33 125	99.55 57	94.10 323	99.94 42	99.25 67	99.96 28	99.42 200

FC-MVSNet-test		99.27 38	99.25 52	99.34 80	99.77 27	98.37 118	99.30 35	99.57 90	99.61 34	99.40 111	99.50 67	97.12 197	99.85 155	99.02 86	99.94 49	99.80 41

test_vis1_n		98.31 206	98.50 159	97.73 321	99.76 30	94.17 356	98.68 107	99.91 9	96.31 339	99.79 38	99.57 49	92.85 344	99.42 409	99.79 19	99.84 110	99.60 98

test_fmvs3		99.12 68	99.41 26	98.25 275	99.76 30	95.07 329	99.05 67	99.94 2	97.78 230	99.82 33	99.84 3	98.56 68	99.71 291	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 61	99.15 66	99.10 125	99.76 30	97.74 188	98.85 92	99.62 73	98.48 167	99.37 116	99.49 73	98.75 46	99.86 142	98.20 141	99.80 138	99.71 61

TDRefinement		99.42 24	99.38 29	99.55 28	99.76 30	99.33 21	99.68 6	99.71 47	99.38 59	99.53 82	99.61 43	98.64 56	99.80 226	98.24 136	99.84 110	99.52 150

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 179	99.75 34	96.59 262	97.97 213	99.86 16	98.22 187	99.88 21	99.71 22	98.59 62	99.84 173	99.73 27	99.98 12	99.98 3

tt0805		98.69 138	98.62 139	98.90 167	99.75 34	99.30 22	99.15 56	96.97 406	98.86 137	98.87 222	97.62 384	98.63 58	98.96 445	99.41 56	98.29 397	98.45 388

test_vis1_n_1920		98.40 189	98.92 94	96.81 383	99.74 36	90.76 434	98.15 171	99.91 9	98.33 175	99.89 18	99.55 57	95.07 294	99.88 114	99.76 23	99.93 55	99.79 43

FOURS1					99.73 37	99.67 3	99.43 15	99.54 106	99.43 54	99.26 143

PEN-MVS		99.41 25	99.34 36	99.62 9	99.73 37	99.14 57	99.29 36	99.54 106	99.62 32	99.56 73	99.42 88	98.16 111	99.96 14	98.78 101	99.93 55	99.77 49

lessismore_v0				98.97 154	99.73 37	97.53 201		86.71 470		99.37 116	99.52 66	89.93 375	99.92 64	98.99 88	99.72 184	99.44 193

SteuartSystems-ACMMP		98.79 119	98.54 152	99.54 31	99.73 37	99.16 48	98.23 161	99.31 209	97.92 218	98.90 211	98.90 231	98.00 123	99.88 114	96.15 310	99.72 184	99.58 113
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 227	98.15 219	98.22 281	99.73 37	95.15 325	97.36 301	99.68 59	94.45 396	98.99 188	99.27 122	96.87 213	99.94 42	97.13 225	99.91 77	99.57 119

Vis-MVSNet		99.34 30	99.36 33	99.27 96	99.73 37	98.26 125	99.17 53	99.78 36	99.11 97	99.27 139	99.48 74	98.82 37	99.95 26	98.94 91	99.93 55	99.59 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc		99.64 5	99.68 5	99.50 53	99.72 43	98.98 71	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 80	99.54 43	99.95 38	99.61 96

SSC-MVS		98.71 130	98.74 116	98.62 217	99.72 43	96.08 286	98.74 97	98.64 349	99.74 13	99.67 59	99.24 135	94.57 309	99.95 26	99.11 77	99.24 321	99.82 35

test_f		98.67 146	98.87 101	98.05 296	99.72 43	95.59 301	98.51 129	99.81 31	96.30 341	99.78 39	99.82 5	96.14 253	98.63 455	99.82 12	99.93 55	99.95 9

ACMH	96.65 7	99.25 41	99.24 53	99.26 98	99.72 43	98.38 116	99.07 64	99.55 101	98.30 179	99.65 63	99.45 83	99.22 17	99.76 262	98.44 127	99.77 155	99.64 82
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 56	99.71 47	98.94 78	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 80	99.54 43	99.95 38	99.59 105

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 211	99.71 47	96.10 281	97.87 225	99.85 18	98.56 163	99.90 14	99.68 25	98.69 52	99.85 155	99.72 29	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 37	99.62 9	99.71 47	99.10 65	99.29 36	99.53 110	99.53 41	99.46 97	99.41 92	98.23 100	99.95 26	98.89 95	99.95 38	99.81 39

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 22	99.31 30	99.51 116	99.64 27	99.56 73	99.46 79	98.23 100	99.97 7	98.78 101	99.93 55	99.72 60

WR-MVS_H		99.33 31	99.22 54	99.65 8	99.71 47	99.24 30	99.32 26	99.55 101	99.46 49	99.50 90	99.34 107	97.30 186	99.93 53	98.90 93	99.93 55	99.77 49

HPM-MVS_fast		99.01 81	98.82 109	99.57 21	99.71 47	99.35 17	99.00 72	99.50 119	97.33 275	98.94 206	98.86 241	98.75 46	99.82 201	97.53 196	99.71 193	99.56 125

ACMH+	96.62 9	99.08 75	99.00 86	99.33 86	99.71 47	98.83 84	98.60 115	99.58 83	99.11 97	99.53 82	99.18 149	98.81 38	99.67 315	96.71 266	99.77 155	99.50 156

PMVS	91.26 20	97.86 256	97.94 243	97.65 328	99.71 47	97.94 165	98.52 124	98.68 345	98.99 120	97.52 353	99.35 103	97.41 179	98.18 461	91.59 424	99.67 214	96.82 450
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 79	99.02 82	99.03 142	99.70 55	97.48 204	98.43 142	99.29 225	99.70 16	99.60 70	99.07 178	96.13 254	99.94 42	99.42 55	99.87 96	99.68 69

FIs		99.14 61	99.09 74	99.29 92	99.70 55	98.28 124	99.13 58	99.52 115	99.48 44	99.24 149	99.41 92	96.79 221	99.82 201	98.69 111	99.88 92	99.76 54

VPNet		98.87 101	98.83 108	99.01 146	99.70 55	97.62 197	98.43 142	99.35 190	99.47 47	99.28 137	99.05 186	96.72 227	99.82 201	98.09 148	99.36 300	99.59 105

fmvsm_s_conf0.1_n_2		99.20 50	99.38 29	98.65 209	99.69 58	96.08 286	97.49 284	99.90 11	99.53 41	99.88 21	99.64 37	98.51 71	99.90 80	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 203	98.68 129	97.27 359	99.69 58	92.29 408	98.03 194	99.85 18	97.62 240	99.96 4	99.62 40	93.98 324	99.74 275	99.52 49	99.86 103	99.79 43

MP-MVS-pluss		98.57 163	98.23 207	99.60 15	99.69 58	99.35 17	97.16 322	99.38 176	94.87 386	98.97 193	98.99 208	98.01 122	99.88 114	97.29 212	99.70 200	99.58 113
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 39	98.96 155	99.68 61	97.35 212	98.84 94	99.48 128	99.69 18	99.63 66	99.68 25	99.03 24	99.96 14	97.97 161	99.92 68	99.57 119

sd_testset		99.28 37	99.31 41	99.19 109	99.68 61	98.06 152	99.41 17	99.30 217	99.69 18	99.63 66	99.68 25	99.25 16	99.96 14	97.25 215	99.92 68	99.57 119

test_fmvs1_n		98.09 233	98.28 198	97.52 345	99.68 61	93.47 387	98.63 111	99.93 5	95.41 374	99.68 57	99.64 37	91.88 358	99.48 396	99.82 12	99.87 96	99.62 88

CHOSEN 1792x2688		97.49 285	97.14 300	98.54 239	99.68 61	96.09 284	96.50 358	99.62 73	91.58 434	98.84 225	98.97 215	92.36 350	99.88 114	96.76 259	99.95 38	99.67 74

tfpnnormal		98.90 97	98.90 96	98.91 164	99.67 65	97.82 180	99.00 72	99.44 153	99.45 50	99.51 89	99.24 135	98.20 106	99.86 142	95.92 319	99.69 203	99.04 311

MTAPA		98.88 100	98.64 135	99.61 13	99.67 65	99.36 16	98.43 142	99.20 249	98.83 141	98.89 214	98.90 231	96.98 207	99.92 64	97.16 220	99.70 200	99.56 125

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 239	99.66 67	96.97 242	98.00 201	99.85 18	99.24 75	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 365

mvs5depth		99.30 34	99.59 12	98.44 253	99.65 68	95.35 317	99.82 3	99.94 2	99.83 7	99.42 106	99.94 2	98.13 114	99.96 14	99.63 35	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 51	99.27 47	98.94 158	99.65 68	97.05 237	97.80 234	99.76 39	98.70 146	99.78 39	99.11 168	98.79 42	99.95 26	99.85 6	99.96 28	99.83 32

WB-MVS		98.52 177	98.55 150	98.43 254	99.65 68	95.59 301	98.52 124	98.77 334	99.65 26	99.52 84	99.00 206	94.34 315	99.93 53	98.65 113	98.83 369	99.76 54

CP-MVSNet		99.21 48	99.09 74	99.56 26	99.65 68	98.96 77	99.13 58	99.34 196	99.42 55	99.33 125	99.26 128	97.01 205	99.94 42	98.74 106	99.93 55	99.79 43

HPM-MVS		98.79 119	98.53 154	99.59 19	99.65 68	99.29 24	99.16 54	99.43 159	96.74 321	98.61 258	98.38 329	98.62 59	99.87 133	96.47 290	99.67 214	99.59 105
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 155	98.36 185	99.42 65	99.65 68	99.42 11	98.55 120	99.57 90	97.72 234	98.90 211	99.26 128	96.12 256	99.52 384	95.72 330	99.71 193	99.32 247

NormalMVS		98.26 213	97.97 240	99.15 118	99.64 74	97.83 175	98.28 155	99.43 159	99.24 75	98.80 233	98.85 244	89.76 377	99.94 42	98.04 153	99.67 214	99.68 69

lecture		99.25 41	99.12 69	99.62 9	99.64 74	99.40 12	98.89 87	99.51 116	99.19 87	99.37 116	99.25 133	98.36 82	99.88 114	98.23 138	99.67 214	99.59 105

fmvsm_l_conf0.5_n		99.21 48	99.28 46	99.02 145	99.64 74	97.28 219	97.82 230	99.76 39	98.73 143	99.82 33	99.09 176	98.81 38	99.95 26	99.86 4	99.96 28	99.83 32

test_fmvsmconf_n		99.44 19	99.48 18	99.31 91	99.64 74	98.10 142	97.68 253	99.84 22	99.29 71	99.92 8	99.57 49	99.60 5	99.96 14	99.74 26	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 152	98.49 164	99.06 138	99.64 74	97.90 169	98.51 129	98.94 299	96.96 306	99.24 149	98.89 237	97.83 137	99.81 218	96.88 249	99.49 280	99.48 174
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 113	98.72 120	99.12 121	99.64 74	98.54 107	97.98 209	99.68 59	97.62 240	99.34 123	99.18 149	97.54 166	99.77 256	97.79 175	99.74 173	99.04 311

Elysia		99.15 57	99.14 67	99.18 110	99.63 80	97.92 166	98.50 131	99.43 159	99.67 21	99.70 51	99.13 164	96.66 230	99.98 4	99.54 43	99.96 28	99.64 82

StellarMVS		99.15 57	99.14 67	99.18 110	99.63 80	97.92 166	98.50 131	99.43 159	99.67 21	99.70 51	99.13 164	96.66 230	99.98 4	99.54 43	99.96 28	99.64 82

KD-MVS_self_test		99.25 41	99.18 58	99.44 63	99.63 80	99.06 70	98.69 106	99.54 106	99.31 68	99.62 69	99.53 63	97.36 183	99.86 142	99.24 69	99.71 193	99.39 213

EU-MVSNet		97.66 273	98.50 159	95.13 425	99.63 80	85.84 456	98.35 151	98.21 368	98.23 186	99.54 78	99.46 79	95.02 295	99.68 311	98.24 136	99.87 96	99.87 21

HyFIR lowres test		97.19 311	96.60 335	98.96 155	99.62 84	97.28 219	95.17 423	99.50 119	94.21 401	99.01 185	98.32 337	86.61 397	99.99 2	97.10 227	99.84 110	99.60 98

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 152	99.59 85	97.18 230	97.44 291	99.83 25	99.56 39	99.91 12	99.34 107	99.36 13	99.93 53	99.83 10	99.98 12	99.85 29

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 80	99.59 85	98.21 133	97.82 230	99.84 22	99.41 57	99.92 8	99.41 92	99.51 8	99.95 26	99.84 9	99.97 21	99.87 21

FE-MVSNET		98.59 160	98.50 159	98.87 168	99.58 87	97.30 217	98.08 183	99.74 43	96.94 308	98.97 193	99.10 171	96.94 209	99.74 275	97.33 210	99.86 103	99.55 132

mmtdpeth		99.30 34	99.42 25	98.92 163	99.58 87	96.89 249	99.48 13	99.92 7	99.92 2	98.26 296	99.80 11	98.33 88	99.91 73	99.56 40	99.95 38	99.97 4

ACMMP_NAP		98.75 126	98.48 165	99.57 21	99.58 87	99.29 24	97.82 230	99.25 238	96.94 308	98.78 235	99.12 167	98.02 121	99.84 173	97.13 225	99.67 214	99.59 105

nrg030		99.40 26	99.35 34	99.54 31	99.58 87	99.13 60	98.98 75	99.48 128	99.68 20	99.46 97	99.26 128	98.62 59	99.73 282	99.17 74	99.92 68	99.76 54

VDDNet		98.21 220	97.95 241	99.01 146	99.58 87	97.74 188	99.01 70	97.29 397	99.67 21	98.97 193	99.50 67	90.45 372	99.80 226	97.88 168	99.20 329	99.48 174

COLMAP_ROB	96.50 10	98.99 84	98.85 107	99.41 67	99.58 87	99.10 65	98.74 97	99.56 97	99.09 107	99.33 125	99.19 145	98.40 79	99.72 290	95.98 317	99.76 168	99.42 200
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 31	99.45 23	98.99 148	99.57 93	97.73 190	97.93 214	99.83 25	99.22 78	99.93 6	99.30 116	99.42 11	99.96 14	99.85 6	99.99 5	99.29 256

ZNCC-MVS		98.68 143	98.40 177	99.54 31	99.57 93	99.21 33	98.46 139	99.29 225	97.28 281	98.11 308	98.39 327	98.00 123	99.87 133	96.86 252	99.64 225	99.55 132

MSP-MVS		98.40 189	98.00 235	99.61 13	99.57 93	99.25 29	98.57 118	99.35 190	97.55 251	99.31 133	97.71 377	94.61 308	99.88 114	96.14 311	99.19 332	99.70 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
testgi		98.32 204	98.39 180	98.13 288	99.57 93	95.54 304	97.78 236	99.49 126	97.37 272	99.19 157	97.65 381	98.96 29	99.49 393	96.50 289	98.99 357	99.34 238

MP-MVS		98.46 183	98.09 224	99.54 31	99.57 93	99.22 32	98.50 131	99.19 253	97.61 243	97.58 347	98.66 289	97.40 180	99.88 114	94.72 356	99.60 239	99.54 138
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 130	98.46 169	99.47 60	99.57 93	98.97 73	98.23 161	99.48 128	96.60 326	99.10 167	99.06 179	98.71 50	99.83 191	95.58 337	99.78 149	99.62 88

LGP-MVS_train				99.47 60	99.57 93	98.97 73		99.48 128	96.60 326	99.10 167	99.06 179	98.71 50	99.83 191	95.58 337	99.78 149	99.62 88

IS-MVSNet		98.19 223	97.90 249	99.08 130	99.57 93	97.97 160	99.31 30	98.32 364	99.01 119	98.98 189	99.03 190	91.59 360	99.79 239	95.49 339	99.80 138	99.48 174

viewdifsd2359ckpt11		98.84 107	99.04 79	98.24 277	99.56 101	95.51 306	97.38 296	99.70 52	99.16 92	99.57 71	99.40 95	98.26 96	99.71 291	98.55 122	99.82 121	99.50 156

viewmsd2359difaftdt		98.84 107	99.04 79	98.24 277	99.56 101	95.51 306	97.38 296	99.70 52	99.16 92	99.57 71	99.40 95	98.26 96	99.71 291	98.55 122	99.82 121	99.50 156

dcpmvs_2		98.78 121	99.11 70	97.78 311	99.56 101	93.67 382	99.06 65	99.86 16	99.50 43	99.66 60	99.26 128	97.21 194	99.99 2	98.00 158	99.91 77	99.68 69

test_0402		98.76 125	98.71 123	98.93 160	99.56 101	98.14 138	98.45 141	99.34 196	99.28 72	98.95 199	98.91 228	98.34 87	99.79 239	95.63 334	99.91 77	98.86 343

EPP-MVSNet		98.30 207	98.04 231	99.07 132	99.56 101	97.83 175	99.29 36	98.07 375	99.03 117	98.59 262	99.13 164	92.16 354	99.90 80	96.87 250	99.68 208	99.49 163

ACMMP		98.75 126	98.50 159	99.52 44	99.56 101	99.16 48	98.87 88	99.37 180	97.16 296	98.82 229	99.01 202	97.71 148	99.87 133	96.29 302	99.69 203	99.54 138
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_s_conf0.5_n_a		99.10 70	99.20 57	98.78 185	99.55 107	96.59 262	97.79 235	99.82 30	98.21 189	99.81 36	99.53 63	98.46 75	99.84 173	99.70 32	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 71	99.26 50	98.61 220	99.55 107	96.09 284	97.74 246	99.81 31	98.55 164	99.85 27	99.55 57	98.60 61	99.84 173	99.69 34	99.98 12	99.89 16

FMVSNet1		99.17 52	99.17 59	99.17 112	99.55 107	98.24 127	99.20 48	99.44 153	99.21 80	99.43 102	99.55 57	97.82 140	99.86 142	98.42 129	99.89 90	99.41 203

Vis-MVSNet (Re-imp)		97.46 287	97.16 297	98.34 266	99.55 107	96.10 281	98.94 80	98.44 358	98.32 177	98.16 302	98.62 298	88.76 384	99.73 282	93.88 382	99.79 144	99.18 290

ACMM	96.08 12	98.91 95	98.73 118	99.48 56	99.55 107	99.14 57	98.07 187	99.37 180	97.62 240	99.04 181	98.96 218	98.84 36	99.79 239	97.43 205	99.65 223	99.49 163
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 135	98.97 90	97.89 304	99.54 112	94.05 359	98.55 120	99.92 7	96.78 319	99.72 47	99.78 13	96.60 234	99.67 315	99.91 2	99.90 84	99.94 10

mPP-MVS		98.64 150	98.34 188	99.54 31	99.54 112	99.17 44	98.63 111	99.24 243	97.47 259	98.09 310	98.68 284	97.62 157	99.89 96	96.22 305	99.62 232	99.57 119

XVG-ACMP-BASELINE		98.56 164	98.34 188	99.22 106	99.54 112	98.59 101	97.71 249	99.46 141	97.25 284	98.98 189	98.99 208	97.54 166	99.84 173	95.88 320	99.74 173	99.23 272

viewmacassd2359aftdt		98.86 104	98.87 101	98.83 173	99.53 115	97.32 216	97.70 251	99.64 69	98.22 187	99.25 147	99.27 122	98.40 79	99.61 349	97.98 160	99.87 96	99.55 132

region2R		98.69 138	98.40 177	99.54 31	99.53 115	99.17 44	98.52 124	99.31 209	97.46 264	98.44 281	98.51 312	97.83 137	99.88 114	96.46 291	99.58 248	99.58 113

PGM-MVS		98.66 147	98.37 184	99.55 28	99.53 115	99.18 43	98.23 161	99.49 126	97.01 305	98.69 246	98.88 238	98.00 123	99.89 96	95.87 323	99.59 243	99.58 113

Patchmatch-RL test		97.26 304	97.02 305	97.99 300	99.52 118	95.53 305	96.13 383	99.71 47	97.47 259	99.27 139	99.16 155	84.30 418	99.62 342	97.89 165	99.77 155	98.81 351

ACMMPR		98.70 135	98.42 175	99.54 31	99.52 118	99.14 57	98.52 124	99.31 209	97.47 259	98.56 268	98.54 307	97.75 146	99.88 114	96.57 278	99.59 243	99.58 113

fmvsm_s_conf0.5_n_9		99.17 52	99.38 29	98.53 241	99.51 120	95.82 296	97.62 264	99.78 36	99.72 15	99.90 14	99.48 74	98.66 54	99.89 96	99.85 6	99.93 55	99.89 16

AstraMVS		98.16 229	98.07 229	98.41 256	99.51 120	95.86 293	98.00 201	95.14 438	98.97 123	99.43 102	99.24 135	93.25 332	99.84 173	99.21 70	99.87 96	99.54 138

fmvsm_s_conf0.5_n_8		99.13 65	99.26 50	98.74 198	99.51 120	96.44 273	97.65 259	99.65 67	99.66 24	99.78 39	99.48 74	97.92 131	99.93 53	99.72 29	99.95 38	99.87 21

GST-MVS		98.61 156	98.30 195	99.52 44	99.51 120	99.20 39	98.26 159	99.25 238	97.44 267	98.67 249	98.39 327	97.68 149	99.85 155	96.00 315	99.51 270	99.52 150

Anonymous20231206		98.21 220	98.21 208	98.20 282	99.51 120	95.43 315	98.13 173	99.32 204	96.16 345	98.93 207	98.82 254	96.00 261	99.83 191	97.32 211	99.73 176	99.36 231

ACMP	95.32 15	98.41 187	98.09 224	99.36 71	99.51 120	98.79 87	97.68 253	99.38 176	95.76 361	98.81 231	98.82 254	98.36 82	99.82 201	94.75 353	99.77 155	99.48 174
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 195	98.20 209	98.98 152	99.50 126	97.49 202	97.78 236	97.69 384	98.75 142	99.49 91	99.25 133	92.30 352	99.94 42	99.14 75	99.88 92	99.50 156

DVP-MVS		98.77 124	98.52 155	99.52 44	99.50 126	99.21 33	98.02 197	98.84 323	97.97 212	99.08 169	99.02 191	97.61 159	99.88 114	96.99 236	99.63 229	99.48 174
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				99.60 15	99.50 126	99.23 31	98.02 197	99.32 204					99.88 114	96.99 236	99.63 229	99.68 69

test0726					99.50 126	99.21 33	98.17 169	99.35 190	97.97 212	99.26 143	99.06 179	97.61 159

AllTest		98.44 185	98.20 209	99.16 115	99.50 126	98.55 104	98.25 160	99.58 83	96.80 317	98.88 218	99.06 179	97.65 152	99.57 365	94.45 363	99.61 237	99.37 224

TestCases				99.16 115	99.50 126	98.55 104		99.58 83	96.80 317	98.88 218	99.06 179	97.65 152	99.57 365	94.45 363	99.61 237	99.37 224

XVG-OURS		98.53 173	98.34 188	99.11 123	99.50 126	98.82 86	95.97 389	99.50 119	97.30 279	99.05 179	98.98 213	99.35 14	99.32 423	95.72 330	99.68 208	99.18 290

EG-PatchMatch MVS		98.99 84	99.01 84	98.94 158	99.50 126	97.47 205	98.04 192	99.59 81	98.15 204	99.40 111	99.36 102	98.58 67	99.76 262	98.78 101	99.68 208	99.59 105

fmvsm_s_conf0.5_n_2		99.14 61	99.31 41	98.63 215	99.49 134	96.08 286	97.38 296	99.81 31	99.48 44	99.84 30	99.57 49	98.46 75	99.89 96	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 95	98.72 120	99.49 54	99.49 134	99.17 44	98.10 180	99.31 209	98.03 208	99.66 60	99.02 191	98.36 82	99.88 114	96.91 242	99.62 232	99.41 203

IU-MVS					99.49 134	99.15 52		98.87 314	92.97 419	99.41 108				96.76 259	99.62 232	99.66 76

test_241102_ONE					99.49 134	99.17 44		99.31 209	97.98 211	99.66 60	98.90 231	98.36 82	99.48 396

UA-Net		99.47 16	99.40 27	99.70 2	99.49 134	99.29 24	99.80 4	99.72 45	99.82 8	99.04 181	99.81 8	98.05 120	99.96 14	98.85 97	99.99 5	99.86 27

HFP-MVS		98.71 130	98.44 172	99.51 48	99.49 134	99.16 48	98.52 124	99.31 209	97.47 259	98.58 264	98.50 316	97.97 127	99.85 155	96.57 278	99.59 243	99.53 147

VPA-MVSNet		99.30 34	99.30 44	99.28 93	99.49 134	98.36 121	99.00 72	99.45 145	99.63 29	99.52 84	99.44 84	98.25 98	99.88 114	99.09 79	99.84 110	99.62 88

XVG-OURS-SEG-HR		98.49 180	98.28 198	99.14 119	99.49 134	98.83 84	96.54 354	99.48 128	97.32 277	99.11 164	98.61 300	99.33 15	99.30 426	96.23 304	98.38 393	99.28 259

114514_t		96.50 344	95.77 353	98.69 204	99.48 142	97.43 209	97.84 229	99.55 101	81.42 466	96.51 406	98.58 304	95.53 281	99.67 315	93.41 395	99.58 248	98.98 321

IterMVS-LS		98.55 168	98.70 126	98.09 289	99.48 142	94.73 339	97.22 316	99.39 174	98.97 123	99.38 114	99.31 115	96.00 261	99.93 53	98.58 116	99.97 21	99.60 98
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_10		99.15 57	99.27 47	98.78 185	99.47 144	96.56 267	97.75 245	99.71 47	99.60 35	99.74 46	99.44 84	97.96 128	99.95 26	99.86 4	99.94 49	99.82 35

fmvsm_s_conf0.5_n_5		99.07 77	99.10 72	98.99 148	99.47 144	97.22 224	97.40 293	99.83 25	97.61 243	99.85 27	99.30 116	98.80 40	99.95 26	99.71 31	99.90 84	99.78 46

v8		99.01 81	99.16 61	98.57 227	99.47 144	96.31 278	98.90 83	99.47 137	99.03 117	99.52 84	99.57 49	96.93 210	99.81 218	99.60 36	99.98 12	99.60 98

SSC-MVS3.2		98.53 173	98.79 112	97.74 318	99.46 147	93.62 385	96.45 360	99.34 196	99.33 65	98.93 207	98.70 280	97.90 132	99.90 80	99.12 76	99.92 68	99.69 68

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 185	99.46 147	96.58 265	97.65 259	99.72 45	99.47 47	99.86 24	99.50 67	98.94 30	99.89 96	99.75 25	99.97 21	99.86 27

XVS		98.72 129	98.45 170	99.53 38	99.46 147	99.21 33	98.65 109	99.34 196	98.62 153	97.54 351	98.63 296	97.50 172	99.83 191	96.79 255	99.53 265	99.56 125

X-MVStestdata		94.32 393	92.59 412	99.53 38	99.46 147	99.21 33	98.65 109	99.34 196	98.62 153	97.54 351	45.85 471	97.50 172	99.83 191	96.79 255	99.53 265	99.56 125

test20.03		98.78 121	98.77 115	98.78 185	99.46 147	97.20 227	97.78 236	99.24 243	99.04 116	99.41 108	98.90 231	97.65 152	99.76 262	97.70 184	99.79 144	99.39 213

guyue		98.01 241	97.93 245	98.26 273	99.45 152	95.48 310	98.08 183	96.24 421	98.89 134	99.34 123	99.14 162	91.32 364	99.82 201	99.07 80	99.83 117	99.48 174

CSCG		98.68 143	98.50 159	99.20 107	99.45 152	98.63 96	98.56 119	99.57 90	97.87 222	98.85 223	98.04 358	97.66 151	99.84 173	96.72 264	99.81 127	99.13 300

GeoE		99.05 78	98.99 88	99.25 101	99.44 154	98.35 122	98.73 101	99.56 97	98.42 170	98.91 210	98.81 257	98.94 30	99.91 73	98.35 131	99.73 176	99.49 163

v148		98.45 184	98.60 144	98.00 299	99.44 154	94.98 331	97.44 291	99.06 279	98.30 179	99.32 131	98.97 215	96.65 232	99.62 342	98.37 130	99.85 105	99.39 213

v10		98.97 88	99.11 70	98.55 234	99.44 154	96.21 280	98.90 83	99.55 101	98.73 143	99.48 92	99.60 45	96.63 233	99.83 191	99.70 32	99.99 5	99.61 96

V42		98.78 121	98.78 114	98.76 192	99.44 154	97.04 238	98.27 158	99.19 253	97.87 222	99.25 147	99.16 155	96.84 214	99.78 250	99.21 70	99.84 110	99.46 184

MDA-MVSNet-bldmvs		97.94 247	97.91 248	98.06 294	99.44 154	94.96 332	96.63 350	99.15 269	98.35 173	98.83 226	99.11 168	94.31 316	99.85 155	96.60 275	98.72 375	99.37 224

viewdifsd2359ckpt07		98.71 130	98.86 105	98.26 273	99.43 159	95.65 300	97.20 317	99.66 63	99.20 82	99.29 135	99.01 202	98.29 91	99.73 282	97.92 164	99.75 172	99.39 213

casdiffmvs_mvg		99.12 68	99.16 61	98.99 148	99.43 159	97.73 190	98.00 201	99.62 73	99.22 78	99.55 76	99.22 141	98.93 32	99.75 270	98.66 112	99.81 127	99.50 156
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_0404		98.90 97	99.01 84	98.57 227	99.42 161	96.59 262	98.13 173	99.66 63	99.09 107	99.30 134	99.02 191	98.79 42	99.89 96	97.87 170	99.80 138	99.23 272

test1111		96.49 345	96.82 319	95.52 418	99.42 161	87.08 453	99.22 45	87.14 469	99.11 97	99.46 97	99.58 47	88.69 385	99.86 142	98.80 99	99.95 38	99.62 88

v2v482		98.56 164	98.62 139	98.37 263	99.42 161	95.81 297	97.58 272	99.16 264	97.90 220	99.28 137	99.01 202	95.98 266	99.79 239	99.33 59	99.90 84	99.51 153

OPM-MVS		98.56 164	98.32 193	99.25 101	99.41 164	98.73 92	97.13 324	99.18 257	97.10 299	98.75 241	98.92 226	98.18 107	99.65 333	96.68 268	99.56 255	99.37 224
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 235	98.08 227	98.04 297	99.41 164	94.59 345	94.59 441	99.40 172	97.50 256	98.82 229	98.83 251	96.83 216	99.84 173	97.50 199	99.81 127	99.71 61

test_one_0601					99.39 166	99.20 39		99.31 209	98.49 166	98.66 251	99.02 191	97.64 155

mvsany_test3		98.87 101	98.92 94	98.74 198	99.38 167	96.94 246	98.58 117	99.10 274	96.49 331	99.96 4	99.81 8	98.18 107	99.45 404	98.97 89	99.79 144	99.83 32

patch_mono-2		98.51 178	98.63 137	98.17 285	99.38 167	94.78 336	97.36 301	99.69 54	98.16 199	98.49 277	99.29 119	97.06 200	99.97 7	98.29 135	99.91 77	99.76 54

test2506		92.39 424	91.89 426	93.89 439	99.38 167	82.28 470	99.32 26	66.03 477	99.08 111	98.77 238	99.57 49	66.26 465	99.84 173	98.71 109	99.95 38	99.54 138

ECVR-MVS		96.42 347	96.61 333	95.85 410	99.38 167	88.18 448	99.22 45	86.00 471	99.08 111	99.36 119	99.57 49	88.47 390	99.82 201	98.52 124	99.95 38	99.54 138

casdiffmvs		98.95 91	99.00 86	98.81 177	99.38 167	97.33 214	97.82 230	99.57 90	99.17 91	99.35 121	99.17 153	98.35 86	99.69 302	98.46 126	99.73 176	99.41 203
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		98.96 90	99.02 82	98.76 192	99.38 167	97.26 221	98.49 134	99.50 119	98.86 137	99.19 157	99.06 179	98.23 100	99.69 302	98.71 109	99.76 168	99.33 244

TranMVSNet+NR-MVSNet		99.17 52	99.07 77	99.46 62	99.37 173	98.87 82	98.39 147	99.42 165	99.42 55	99.36 119	99.06 179	98.38 81	99.95 26	98.34 132	99.90 84	99.57 119

fmvsm_s_conf0.5_n_6		99.08 75	99.21 56	98.69 204	99.36 174	96.51 268	97.62 264	99.68 59	98.43 169	99.85 27	99.10 171	99.12 23	99.88 114	99.77 22	99.92 68	99.67 74

tttt0517		95.64 372	94.98 382	97.64 331	99.36 174	93.81 377	98.72 102	90.47 463	98.08 207	98.67 249	98.34 334	73.88 451	99.92 64	97.77 177	99.51 270	99.20 282

test_part2					99.36 174	99.10 65				99.05 179

v1144		98.60 158	98.66 132	98.41 256	99.36 174	95.90 291	97.58 272	99.34 196	97.51 255	99.27 139	99.15 159	96.34 247	99.80 226	99.47 53	99.93 55	99.51 153

CP-MVS		98.70 135	98.42 175	99.52 44	99.36 174	99.12 62	98.72 102	99.36 184	97.54 253	98.30 290	98.40 326	97.86 136	99.89 96	96.53 287	99.72 184	99.56 125

diffmvs_AUTHOR		98.50 179	98.59 146	98.23 280	99.35 179	95.48 310	96.61 351	99.60 77	98.37 171	98.90 211	99.00 206	97.37 182	99.76 262	98.22 139	99.85 105	99.46 184

Test_1112_low_res		96.99 326	96.55 337	98.31 269	99.35 179	95.47 313	95.84 401	99.53 110	91.51 436	96.80 393	98.48 319	91.36 363	99.83 191	96.58 276	99.53 265	99.62 88

DeepC-MVS	97.60 4	98.97 88	98.93 93	99.10 125	99.35 179	97.98 159	98.01 200	99.46 141	97.56 249	99.54 78	99.50 67	98.97 28	99.84 173	98.06 151	99.92 68	99.49 163
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 303	96.86 315	98.58 224	99.34 182	96.32 277	96.75 343	99.58 83	93.14 417	96.89 388	97.48 391	92.11 355	99.86 142	96.91 242	99.54 261	99.57 119

reproduce_model		99.15 57	98.97 90	99.67 4	99.33 183	99.44 10	98.15 171	99.47 137	99.12 96	99.52 84	99.32 114	98.31 89	99.90 80	97.78 176	99.73 176	99.66 76

MVSMamba_PlusPlus		98.83 110	98.98 89	98.36 264	99.32 184	96.58 265	98.90 83	99.41 169	99.75 11	98.72 244	99.50 67	96.17 252	99.94 42	99.27 64	99.78 149	98.57 381

fmvsm_s_conf0.5_n_4		99.01 81	99.22 54	98.38 260	99.31 185	95.48 310	97.56 274	99.73 44	98.87 135	99.75 44	99.27 122	98.80 40	99.86 142	99.80 17	99.90 84	99.81 39

SF-MVS		98.53 173	98.27 201	99.32 88	99.31 185	98.75 88	98.19 165	99.41 169	96.77 320	98.83 226	98.90 231	97.80 142	99.82 201	95.68 333	99.52 268	99.38 222

CPTT-MVS		97.84 262	97.36 286	99.27 96	99.31 185	98.46 112	98.29 154	99.27 232	94.90 385	97.83 331	98.37 330	94.90 297	99.84 173	93.85 384	99.54 261	99.51 153

UnsupCasMVSNet_eth		97.89 251	97.60 272	98.75 194	99.31 185	97.17 232	97.62 264	99.35 190	98.72 145	98.76 240	98.68 284	92.57 349	99.74 275	97.76 181	95.60 455	99.34 238

fmvsm_s_conf0.5_n_7		98.83 110	99.04 79	98.20 282	99.30 189	94.83 334	97.23 312	99.36 184	98.64 148	99.84 30	99.43 87	98.10 116	99.91 73	99.56 40	99.96 28	99.87 21

pmmvs-eth3d		98.47 182	98.34 188	98.86 170	99.30 189	97.76 186	97.16 322	99.28 229	95.54 367	99.42 106	99.19 145	97.27 189	99.63 339	97.89 165	99.97 21	99.20 282

mamv4		99.44 19	99.39 28	99.58 20	99.30 189	99.74 2	99.04 68	99.81 31	99.77 10	99.82 33	99.57 49	97.82 140	99.98 4	99.53 47	99.89 90	99.01 315

viewcassd2359sk11		98.55 168	98.51 156	98.67 207	99.29 192	96.99 241	97.39 294	99.54 106	97.73 232	98.81 231	99.08 177	97.55 164	99.66 326	97.52 198	99.67 214	99.36 231

SymmetryMVS		98.05 237	97.71 262	99.09 129	99.29 192	97.83 175	98.28 155	97.64 389	99.24 75	98.80 233	98.85 244	89.76 377	99.94 42	98.04 153	99.50 278	99.49 163

Anonymous20231211		99.27 38	99.27 47	99.26 98	99.29 192	98.18 134	99.49 12	99.51 116	99.70 16	99.80 37	99.68 25	96.84 214	99.83 191	99.21 70	99.91 77	99.77 49

viewmanbaseed2359cas		98.58 162	98.54 152	98.70 202	99.28 195	97.13 236	97.47 287	99.55 101	97.55 251	98.96 198	98.92 226	97.77 144	99.59 356	97.59 192	99.77 155	99.39 213

UnsupCasMVSNet_bld		97.30 301	96.92 311	98.45 251	99.28 195	96.78 256	96.20 377	99.27 232	95.42 371	98.28 294	98.30 338	93.16 335	99.71 291	94.99 347	97.37 431	98.87 342

EC-MVSNet		99.09 71	99.05 78	99.20 107	99.28 195	98.93 79	99.24 44	99.84 22	99.08 111	98.12 307	98.37 330	98.72 49	99.90 80	99.05 83	99.77 155	98.77 359

mamba_0408		98.80 117	98.88 99	98.55 234	99.27 198	96.50 269	98.00 201	99.60 77	98.93 128	99.22 152	98.84 249	98.59 62	99.89 96	97.74 182	99.72 184	99.27 260

SSM_04072		98.80 117	98.88 99	98.56 232	99.27 198	96.50 269	98.00 201	99.60 77	98.93 128	99.22 152	98.84 249	98.59 62	99.90 80	97.74 182	99.72 184	99.27 260

SSM_0407		98.86 104	98.96 92	98.55 234	99.27 198	96.50 269	98.04 192	99.66 63	99.09 107	99.22 152	99.02 191	98.79 42	99.87 133	97.87 170	99.72 184	99.27 260

reproduce-ours		99.09 71	98.90 96	99.67 4	99.27 198	99.49 6	98.00 201	99.42 165	99.05 114	99.48 92	99.27 122	98.29 91	99.89 96	97.61 189	99.71 193	99.62 88

our_new_method		99.09 71	98.90 96	99.67 4	99.27 198	99.49 6	98.00 201	99.42 165	99.05 114	99.48 92	99.27 122	98.29 91	99.89 96	97.61 189	99.71 193	99.62 88

DPE-MVS		98.59 160	98.26 202	99.57 21	99.27 198	99.15 52	97.01 327	99.39 174	97.67 236	99.44 101	98.99 208	97.53 168	99.89 96	95.40 341	99.68 208	99.66 76
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 261	98.18 214	96.87 379	99.27 198	91.16 428	95.53 411	99.25 238	99.10 104	99.41 108	99.35 103	93.10 337	99.96 14	98.65 113	99.94 49	99.49 163

v1192		98.60 158	98.66 132	98.41 256	99.27 198	95.88 292	97.52 279	99.36 184	97.41 268	99.33 125	99.20 144	96.37 245	99.82 201	99.57 38	99.92 68	99.55 132

N_pmnet		97.63 275	97.17 296	98.99 148	99.27 198	97.86 172	95.98 388	93.41 452	95.25 376	99.47 96	98.90 231	95.63 278	99.85 155	96.91 242	99.73 176	99.27 260

viewdifsd2359ckpt13		98.39 195	98.29 197	98.70 202	99.26 207	97.19 228	97.51 281	99.48 128	96.94 308	98.58 264	98.82 254	97.47 177	99.55 372	97.21 217	99.33 305	99.34 238

FPMVS		93.44 410	92.23 417	97.08 367	99.25 208	97.86 172	95.61 408	97.16 401	92.90 421	93.76 454	98.65 291	75.94 449	95.66 468	79.30 466	97.49 424	97.73 432

MED-MVS		98.61 156	98.33 192	99.44 63	99.24 209	98.93 79	97.45 289	99.06 279	98.14 205	99.06 171	98.77 264	96.97 208	99.82 201	96.67 269	99.64 225	99.58 113

new-patchmatchnet		98.35 198	98.74 116	97.18 362	99.24 209	92.23 410	96.42 364	99.48 128	98.30 179	99.69 55	99.53 63	97.44 178	99.82 201	98.84 98	99.77 155	99.49 163

MCST-MVS		98.00 242	97.63 270	99.10 125	99.24 209	98.17 135	96.89 336	98.73 342	95.66 362	97.92 322	97.70 379	97.17 195	99.66 326	96.18 309	99.23 324	99.47 182

UniMVSNet (Re)		98.87 101	98.71 123	99.35 77	99.24 209	98.73 92	97.73 248	99.38 176	98.93 128	99.12 163	98.73 270	96.77 222	99.86 142	98.63 115	99.80 138	99.46 184

jason		97.45 289	97.35 287	97.76 315	99.24 209	93.93 371	95.86 398	98.42 360	94.24 400	98.50 276	98.13 348	94.82 301	99.91 73	97.22 216	99.73 176	99.43 197
jason: jason.
IterMVS		97.73 267	98.11 223	96.57 389	99.24 209	90.28 437	95.52 413	99.21 247	98.86 137	99.33 125	99.33 110	93.11 336	99.94 42	98.49 125	99.94 49	99.48 174
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 168	98.62 139	98.32 267	99.22 215	95.58 303	97.51 281	99.45 145	97.16 296	99.45 100	99.24 135	96.12 256	99.85 155	99.60 36	99.88 92	99.55 132

ITE_SJBPF				98.87 168	99.22 215	98.48 111		99.35 190	97.50 256	98.28 294	98.60 302	97.64 155	99.35 419	93.86 383	99.27 316	98.79 357

h-mvs33		97.77 265	97.33 289	99.10 125	99.21 217	97.84 174	98.35 151	98.57 352	99.11 97	98.58 264	99.02 191	88.65 388	99.96 14	98.11 146	96.34 447	99.49 163

v144192		98.54 171	98.57 148	98.45 251	99.21 217	95.98 289	97.63 263	99.36 184	97.15 298	99.32 131	99.18 149	95.84 273	99.84 173	99.50 50	99.91 77	99.54 138

APDe-MVS		98.99 84	98.79 112	99.60 15	99.21 217	99.15 52	98.87 88	99.48 128	97.57 247	99.35 121	99.24 135	97.83 137	99.89 96	97.88 168	99.70 200	99.75 58
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 93	98.81 111	99.28 93	99.21 217	98.45 113	98.46 139	99.33 202	99.63 29	99.48 92	99.15 159	97.23 192	99.75 270	97.17 219	99.66 222	99.63 87

SR-MVS-dyc-post		98.81 115	98.55 150	99.57 21	99.20 221	99.38 13	98.48 137	99.30 217	98.64 148	98.95 199	98.96 218	97.49 175	99.86 142	96.56 282	99.39 296	99.45 189

RE-MVS-def			98.58 147		99.20 221	99.38 13	98.48 137	99.30 217	98.64 148	98.95 199	98.96 218	97.75 146		96.56 282	99.39 296	99.45 189

v1921920		98.54 171	98.60 144	98.38 260	99.20 221	95.76 299	97.56 274	99.36 184	97.23 290	99.38 114	99.17 153	96.02 259	99.84 173	99.57 38	99.90 84	99.54 138

thisisatest0530		95.27 379	94.45 390	97.74 318	99.19 224	94.37 349	97.86 226	90.20 464	97.17 295	98.22 297	97.65 381	73.53 452	99.90 80	96.90 247	99.35 302	98.95 327

Anonymous20240529		98.93 93	98.87 101	99.12 121	99.19 224	98.22 132	99.01 70	98.99 297	99.25 74	99.54 78	99.37 98	97.04 201	99.80 226	97.89 165	99.52 268	99.35 236

APD-MVS_3200maxsize		98.84 107	98.61 143	99.53 38	99.19 224	99.27 27	98.49 134	99.33 202	98.64 148	99.03 184	98.98 213	97.89 134	99.85 155	96.54 286	99.42 293	99.46 184

HQP_MVS		97.99 245	97.67 264	98.93 160	99.19 224	97.65 194	97.77 239	99.27 232	98.20 193	97.79 334	97.98 362	94.90 297	99.70 298	94.42 365	99.51 270	99.45 189

plane_prior7					99.19 224	97.87 171

ab-mvs		98.41 187	98.36 185	98.59 223	99.19 224	97.23 222	99.32 26	98.81 328	97.66 237	98.62 256	99.40 95	96.82 217	99.80 226	95.88 320	99.51 270	98.75 362

F-COLMAP		97.30 301	96.68 328	99.14 119	99.19 224	98.39 115	97.27 311	99.30 217	92.93 420	96.62 399	98.00 360	95.73 276	99.68 311	92.62 411	98.46 392	99.35 236

viewdifsd2359ckpt09		98.13 230	97.92 246	98.77 190	99.18 231	97.35 212	97.29 307	99.53 110	95.81 359	98.09 310	98.47 320	96.34 247	99.66 326	97.02 232	99.51 270	99.29 256

SR-MVS		98.71 130	98.43 173	99.57 21	99.18 231	99.35 17	98.36 150	99.29 225	98.29 182	98.88 218	98.85 244	97.53 168	99.87 133	96.14 311	99.31 309	99.48 174

UniMVSNet_NR-MVSNet		98.86 104	98.68 129	99.40 69	99.17 233	98.74 89	97.68 253	99.40 172	99.14 95	99.06 171	98.59 303	96.71 228	99.93 53	98.57 118	99.77 155	99.53 147

LF4IMVS		97.90 249	97.69 263	98.52 242	99.17 233	97.66 193	97.19 321	99.47 137	96.31 339	97.85 330	98.20 345	96.71 228	99.52 384	94.62 357	99.72 184	98.38 398

SMA-MVS		98.40 189	98.03 232	99.51 48	99.16 235	99.21 33	98.05 190	99.22 246	94.16 402	98.98 189	99.10 171	97.52 170	99.79 239	96.45 292	99.64 225	99.53 147
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
DU-MVS		98.82 113	98.63 137	99.39 70	99.16 235	98.74 89	97.54 277	99.25 238	98.84 140	99.06 171	98.76 267	96.76 224	99.93 53	98.57 118	99.77 155	99.50 156

NR-MVSNet		98.95 91	98.82 109	99.36 71	99.16 235	98.72 94	99.22 45	99.20 249	99.10 104	99.72 47	98.76 267	96.38 244	99.86 142	98.00 158	99.82 121	99.50 156

MVS_111021_LR		98.30 207	98.12 222	98.83 173	99.16 235	98.03 154	96.09 385	99.30 217	97.58 246	98.10 309	98.24 341	98.25 98	99.34 420	96.69 267	99.65 223	99.12 301

DSMNet-mixed		97.42 292	97.60 272	96.87 379	99.15 239	91.46 417	98.54 122	99.12 271	92.87 422	97.58 347	99.63 39	96.21 251	99.90 80	95.74 329	99.54 261	99.27 260

D2MVS		97.84 262	97.84 253	97.83 307	99.14 240	94.74 338	96.94 331	98.88 312	95.84 358	98.89 214	98.96 218	94.40 313	99.69 302	97.55 193	99.95 38	99.05 307

pmmvs5		97.64 274	97.49 278	98.08 292	99.14 240	95.12 327	96.70 346	99.05 283	93.77 409	98.62 256	98.83 251	93.23 333	99.75 270	98.33 134	99.76 168	99.36 231

SPE-MVS-test		99.13 65	99.09 74	99.26 98	99.13 242	98.97 73	99.31 30	99.88 14	99.44 52	98.16 302	98.51 312	98.64 56	99.93 53	98.91 92	99.85 105	98.88 341

VDD-MVS		98.56 164	98.39 180	99.07 132	99.13 242	98.07 149	98.59 116	97.01 404	99.59 36	99.11 164	99.27 122	94.82 301	99.79 239	98.34 132	99.63 229	99.34 238

save fliter					99.11 244	97.97 160	96.53 356	99.02 291	98.24 185

APD-MVS		98.10 231	97.67 264	99.42 65	99.11 244	98.93 79	97.76 242	99.28 229	94.97 383	98.72 244	98.77 264	97.04 201	99.85 155	93.79 385	99.54 261	99.49 163
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 138	98.71 123	98.62 217	99.10 246	96.37 275	97.23 312	98.87 314	99.20 82	99.19 157	98.99 208	97.30 186	99.85 155	98.77 104	99.79 144	99.65 81

EI-MVSNet		98.40 189	98.51 156	98.04 297	99.10 246	94.73 339	97.20 317	98.87 314	98.97 123	99.06 171	99.02 191	96.00 261	99.80 226	98.58 116	99.82 121	99.60 98

CVMVSNet		96.25 353	97.21 295	93.38 446	99.10 246	80.56 474	97.20 317	98.19 371	96.94 308	99.00 186	99.02 191	89.50 381	99.80 226	96.36 298	99.59 243	99.78 46

EI-MVSNet-Vis-set		98.68 143	98.70 126	98.63 215	99.09 249	96.40 274	97.23 312	98.86 319	99.20 82	99.18 161	98.97 215	97.29 188	99.85 155	98.72 108	99.78 149	99.64 82

HPM-MVS++		98.10 231	97.64 269	99.48 56	99.09 249	99.13 60	97.52 279	98.75 339	97.46 264	96.90 387	97.83 372	96.01 260	99.84 173	95.82 327	99.35 302	99.46 184

DP-MVS Recon		97.33 299	96.92 311	98.57 227	99.09 249	97.99 156	96.79 339	99.35 190	93.18 416	97.71 338	98.07 356	95.00 296	99.31 424	93.97 378	99.13 340	98.42 395

MVS_111021_HR		98.25 216	98.08 227	98.75 194	99.09 249	97.46 206	95.97 389	99.27 232	97.60 245	97.99 320	98.25 340	98.15 113	99.38 415	96.87 250	99.57 252	99.42 200

BP-MVS1		97.40 294	96.97 307	98.71 201	99.07 253	96.81 252	98.34 153	97.18 399	98.58 159	98.17 299	98.61 300	84.01 420	99.94 42	98.97 89	99.78 149	99.37 224

9.14			97.78 255		99.07 253		97.53 278	99.32 204	95.53 368	98.54 272	98.70 280	97.58 161	99.76 262	94.32 370	99.46 283

PAPM_NR		96.82 333	96.32 344	98.30 270	99.07 253	96.69 260	97.48 285	98.76 336	95.81 359	96.61 400	96.47 417	94.12 322	99.17 437	90.82 438	97.78 418	99.06 306

TAMVS		98.24 217	98.05 230	98.80 179	99.07 253	97.18 230	97.88 222	98.81 328	96.66 325	99.17 162	99.21 142	94.81 303	99.77 256	96.96 240	99.88 92	99.44 193

CLD-MVS		97.49 285	97.16 297	98.48 248	99.07 253	97.03 239	94.71 434	99.21 247	94.46 394	98.06 313	97.16 403	97.57 162	99.48 396	94.46 362	99.78 149	98.95 327
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		99.13 65	99.10 72	99.24 103	99.06 258	99.15 52	99.36 22	99.88 14	99.36 63	98.21 298	98.46 321	98.68 53	99.93 53	99.03 85	99.85 105	98.64 374

thres100view900		94.19 396	93.67 401	95.75 413	99.06 258	91.35 421	98.03 194	94.24 447	98.33 175	97.40 363	94.98 447	79.84 436	99.62 342	83.05 459	98.08 409	96.29 454

thres600view7		94.45 391	93.83 398	96.29 397	99.06 258	91.53 416	97.99 208	94.24 447	98.34 174	97.44 361	95.01 445	79.84 436	99.67 315	84.33 457	98.23 398	97.66 435

plane_prior1					99.05 261

YYNet1		97.60 276	97.67 264	97.39 355	99.04 262	93.04 394	95.27 420	98.38 363	97.25 284	98.92 209	98.95 222	95.48 285	99.73 282	96.99 236	98.74 373	99.41 203

MDA-MVSNet_test_wron		97.60 276	97.66 267	97.41 354	99.04 262	93.09 390	95.27 420	98.42 360	97.26 283	98.88 218	98.95 222	95.43 286	99.73 282	97.02 232	98.72 375	99.41 203

MIMVSNet		96.62 340	96.25 348	97.71 322	99.04 262	94.66 342	99.16 54	96.92 410	97.23 290	97.87 327	99.10 171	86.11 403	99.65 333	91.65 422	99.21 328	98.82 346

icg_test_0407_2		98.20 222	98.38 182	97.65 328	99.03 265	94.03 362	95.78 403	99.45 145	98.16 199	99.06 171	98.71 273	98.27 94	99.68 311	97.50 199	99.45 285	99.22 277

IMVS_0407		98.39 195	98.64 135	97.66 326	99.03 265	94.03 362	98.10 180	99.45 145	98.16 199	99.06 171	98.71 273	98.27 94	99.71 291	97.50 199	99.45 285	99.22 277

IMVS_0404		98.07 235	98.20 209	97.69 323	99.03 265	94.03 362	96.67 347	99.45 145	98.16 199	98.03 317	98.71 273	96.80 220	99.82 201	97.50 199	99.45 285	99.22 277

IMVS_0403		98.34 199	98.56 149	97.66 326	99.03 265	94.03 362	97.98 209	99.45 145	98.16 199	98.89 214	98.71 273	97.90 132	99.74 275	97.50 199	99.45 285	99.22 277

PatchMatch-RL		97.24 307	96.78 322	98.61 220	99.03 265	97.83 175	96.36 367	99.06 279	93.49 414	97.36 367	97.78 373	95.75 275	99.49 393	93.44 394	98.77 372	98.52 383

viewmambaseed2359dif		98.19 223	98.26 202	97.99 300	99.02 270	95.03 330	96.59 353	99.53 110	96.21 342	99.00 186	98.99 208	97.62 157	99.61 349	97.62 188	99.72 184	99.33 244

GDP-MVS		97.50 282	97.11 301	98.67 207	99.02 270	96.85 250	98.16 170	99.71 47	98.32 177	98.52 275	98.54 307	83.39 424	99.95 26	98.79 100	99.56 255	99.19 287

ZD-MVS					99.01 272	98.84 83		99.07 278	94.10 404	98.05 315	98.12 350	96.36 246	99.86 142	92.70 410	99.19 332

CDPH-MVS		97.26 304	96.66 331	99.07 132	99.00 273	98.15 136	96.03 387	99.01 294	91.21 440	97.79 334	97.85 371	96.89 212	99.69 302	92.75 408	99.38 299	99.39 213

diffmvs		98.22 218	98.24 206	98.17 285	99.00 273	95.44 314	96.38 366	99.58 83	97.79 229	98.53 273	98.50 316	96.76 224	99.74 275	97.95 163	99.64 225	99.34 238
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 189	98.19 213	99.03 142	99.00 273	97.65 194	96.85 337	98.94 299	98.57 160	98.89 214	98.50 316	95.60 279	99.85 155	97.54 195	99.85 105	99.59 105

plane_prior6					98.99 276	97.70 192						94.90 297

xiu_mvs_v1_base_debu		97.86 256	98.17 215	96.92 376	98.98 277	93.91 372	96.45 360	99.17 261	97.85 224	98.41 284	97.14 405	98.47 72	99.92 64	98.02 155	99.05 346	96.92 447

xiu_mvs_v1_base		97.86 256	98.17 215	96.92 376	98.98 277	93.91 372	96.45 360	99.17 261	97.85 224	98.41 284	97.14 405	98.47 72	99.92 64	98.02 155	99.05 346	96.92 447

xiu_mvs_v1_base_debi		97.86 256	98.17 215	96.92 376	98.98 277	93.91 372	96.45 360	99.17 261	97.85 224	98.41 284	97.14 405	98.47 72	99.92 64	98.02 155	99.05 346	96.92 447

MVP-Stereo		98.08 234	97.92 246	98.57 227	98.96 280	96.79 253	97.90 220	99.18 257	96.41 335	98.46 279	98.95 222	95.93 270	99.60 352	96.51 288	98.98 360	99.31 251
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 189	98.68 129	97.54 343	98.96 280	97.99 156	97.88 222	99.36 184	98.20 193	99.63 66	99.04 188	98.76 45	95.33 470	96.56 282	99.74 173	99.31 251
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
新几何1				98.91 164	98.94 282	97.76 186		98.76 336	87.58 457	96.75 395	98.10 352	94.80 304	99.78 250	92.73 409	99.00 355	99.20 282

USDC		97.41 293	97.40 282	97.44 352	98.94 282	93.67 382	95.17 423	99.53 110	94.03 406	98.97 193	99.10 171	95.29 288	99.34 420	95.84 326	99.73 176	99.30 254

tfpn200view9		94.03 400	93.44 403	95.78 412	98.93 284	91.44 419	97.60 269	94.29 445	97.94 216	97.10 373	94.31 454	79.67 438	99.62 342	83.05 459	98.08 409	96.29 454

testdata				98.09 289	98.93 284	95.40 316		98.80 330	90.08 448	97.45 360	98.37 330	95.26 289	99.70 298	93.58 390	98.95 363	99.17 294

thres400		94.14 398	93.44 403	96.24 400	98.93 284	91.44 419	97.60 269	94.29 445	97.94 216	97.10 373	94.31 454	79.67 438	99.62 342	83.05 459	98.08 409	97.66 435

TAPA-MVS	96.21 11	96.63 339	95.95 350	98.65 209	98.93 284	98.09 143	96.93 333	99.28 229	83.58 463	98.13 306	97.78 373	96.13 254	99.40 411	93.52 391	99.29 314	98.45 388
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 288	96.93 247	95.54 410	98.78 333	85.72 460	96.86 390	98.11 351	94.43 311			99.10 345	99.23 272

PVSNet_BlendedMVS		97.55 281	97.53 275	97.60 335	98.92 288	93.77 379	96.64 349	99.43 159	94.49 392	97.62 343	99.18 149	96.82 217	99.67 315	94.73 354	99.93 55	99.36 231

PVSNet_Blended		96.88 329	96.68 328	97.47 350	98.92 288	93.77 379	94.71 434	99.43 159	90.98 442	97.62 343	97.36 399	96.82 217	99.67 315	94.73 354	99.56 255	98.98 321

MSDG		97.71 269	97.52 276	98.28 272	98.91 291	96.82 251	94.42 444	99.37 180	97.65 238	98.37 289	98.29 339	97.40 180	99.33 422	94.09 376	99.22 325	98.68 372

Anonymous202405211		97.90 249	97.50 277	99.08 130	98.90 292	98.25 126	98.53 123	96.16 422	98.87 135	99.11 164	98.86 241	90.40 373	99.78 250	97.36 208	99.31 309	99.19 287

原ACMM1				98.35 265	98.90 292	96.25 279		98.83 327	92.48 426	96.07 417	98.10 352	95.39 287	99.71 291	92.61 412	98.99 357	99.08 303

GBi-Net		98.65 148	98.47 167	99.17 112	98.90 292	98.24 127	99.20 48	99.44 153	98.59 156	98.95 199	99.55 57	94.14 319	99.86 142	97.77 177	99.69 203	99.41 203

test1		98.65 148	98.47 167	99.17 112	98.90 292	98.24 127	99.20 48	99.44 153	98.59 156	98.95 199	99.55 57	94.14 319	99.86 142	97.77 177	99.69 203	99.41 203

FMVSNet2		98.49 180	98.40 177	98.75 194	98.90 292	97.14 235	98.61 114	99.13 270	98.59 156	99.19 157	99.28 120	94.14 319	99.82 201	97.97 161	99.80 138	99.29 256

OMC-MVS		97.88 253	97.49 278	99.04 141	98.89 297	98.63 96	96.94 331	99.25 238	95.02 381	98.53 273	98.51 312	97.27 189	99.47 399	93.50 393	99.51 270	99.01 315

VortexMVS		97.98 246	98.31 194	97.02 370	98.88 298	91.45 418	98.03 194	99.47 137	98.65 147	99.55 76	99.47 77	91.49 362	99.81 218	99.32 60	99.91 77	99.80 41

MVSFormer		98.26 213	98.43 173	97.77 312	98.88 298	93.89 375	99.39 20	99.56 97	99.11 97	98.16 302	98.13 348	93.81 327	99.97 7	99.26 65	99.57 252	99.43 197

lupinMVS		97.06 319	96.86 315	97.65 328	98.88 298	93.89 375	95.48 414	97.97 377	93.53 412	98.16 302	97.58 385	93.81 327	99.91 73	96.77 258	99.57 252	99.17 294

dmvs_re		95.98 361	95.39 371	97.74 318	98.86 301	97.45 207	98.37 149	95.69 434	97.95 214	96.56 401	95.95 426	90.70 370	97.68 464	88.32 447	96.13 451	98.11 410

DELS-MVS		98.27 211	98.20 209	98.48 248	98.86 301	96.70 259	95.60 409	99.20 249	97.73 232	98.45 280	98.71 273	97.50 172	99.82 201	98.21 140	99.59 243	98.93 332
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
TinyColmap		97.89 251	97.98 237	97.60 335	98.86 301	94.35 350	96.21 376	99.44 153	97.45 266	99.06 171	98.88 238	97.99 126	99.28 430	94.38 369	99.58 248	99.18 290

LCM-MVSNet-Re		98.64 150	98.48 165	99.11 123	98.85 304	98.51 109	98.49 134	99.83 25	98.37 171	99.69 55	99.46 79	98.21 105	99.92 64	94.13 375	99.30 312	98.91 336

pmmvs4		97.58 279	97.28 290	98.51 243	98.84 305	96.93 247	95.40 418	98.52 355	93.60 411	98.61 258	98.65 291	95.10 293	99.60 352	96.97 239	99.79 144	98.99 320

NP-MVS					98.84 305	97.39 211					96.84 408

sss		97.21 309	96.93 309	98.06 294	98.83 307	95.22 323	96.75 343	98.48 357	94.49 392	97.27 369	97.90 368	92.77 345	99.80 226	96.57 278	99.32 307	99.16 297

PVSNet	93.40 17	95.67 370	95.70 356	95.57 417	98.83 307	88.57 444	92.50 461	97.72 382	92.69 424	96.49 409	96.44 418	93.72 330	99.43 407	93.61 388	99.28 315	98.71 365

MVE	83.40 22	92.50 423	91.92 425	94.25 433	98.83 307	91.64 415	92.71 460	83.52 473	95.92 356	86.46 471	95.46 439	95.20 290	95.40 469	80.51 464	98.64 384	95.73 462
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 404	93.91 396	93.39 445	98.82 310	81.72 472	97.76 242	95.28 436	98.60 155	96.54 402	96.66 412	65.85 468	99.62 342	96.65 271	98.99 357	98.82 346

ambc				98.24 277	98.82 310	95.97 290	98.62 113	99.00 296		99.27 139	99.21 142	96.99 206	99.50 390	96.55 285	99.50 278	99.26 266

旧先验1					98.82 310	97.45 207		98.76 336			98.34 334	95.50 284			99.01 354	99.23 272

test_vis1_rt		97.75 266	97.72 261	97.83 307	98.81 313	96.35 276	97.30 306	99.69 54	94.61 390	97.87 327	98.05 357	96.26 250	98.32 458	98.74 106	98.18 401	98.82 346

WTY-MVS		96.67 337	96.27 347	97.87 305	98.81 313	94.61 344	96.77 341	97.92 379	94.94 384	97.12 372	97.74 376	91.11 366	99.82 201	93.89 381	98.15 405	99.18 290

3Dnovator+	97.89 3	98.69 138	98.51 156	99.24 103	98.81 313	98.40 114	99.02 69	99.19 253	98.99 120	98.07 312	99.28 120	97.11 199	99.84 173	96.84 253	99.32 307	99.47 182

QAPM		97.31 300	96.81 321	98.82 175	98.80 316	97.49 202	99.06 65	99.19 253	90.22 446	97.69 340	99.16 155	96.91 211	99.90 80	90.89 437	99.41 294	99.07 305

VNet		98.42 186	98.30 195	98.79 182	98.79 317	97.29 218	98.23 161	98.66 346	99.31 68	98.85 223	98.80 258	94.80 304	99.78 250	98.13 145	99.13 340	99.31 251

DPM-MVS		96.32 349	95.59 362	98.51 243	98.76 318	97.21 226	94.54 443	98.26 366	91.94 431	96.37 410	97.25 401	93.06 339	99.43 407	91.42 427	98.74 373	98.89 338

3Dnovator	98.27 2	98.81 115	98.73 118	99.05 139	98.76 318	97.81 183	99.25 43	99.30 217	98.57 160	98.55 270	99.33 110	97.95 129	99.90 80	97.16 220	99.67 214	99.44 193

PLC	94.65 16	96.51 342	95.73 355	98.85 171	98.75 320	97.91 168	96.42 364	99.06 279	90.94 443	95.59 423	97.38 397	94.41 312	99.59 356	90.93 435	98.04 414	99.05 307
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 331	96.75 324	97.08 367	98.74 321	93.33 388	96.71 345	98.26 366	96.72 322	98.44 281	97.37 398	95.20 290	99.47 399	91.89 417	97.43 428	98.44 391

hse-mvs2		97.46 287	97.07 302	98.64 211	98.73 322	97.33 214	97.45 289	97.64 389	99.11 97	98.58 264	97.98 362	88.65 388	99.79 239	98.11 146	97.39 430	98.81 351

CDS-MVSNet		97.69 270	97.35 287	98.69 204	98.73 322	97.02 240	96.92 335	98.75 339	95.89 357	98.59 262	98.67 286	92.08 356	99.74 275	96.72 264	99.81 127	99.32 247
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 351	95.83 352	97.64 331	98.72 324	94.30 351	98.87 88	98.77 334	97.80 227	96.53 403	98.02 359	97.34 184	99.47 399	76.93 468	99.48 281	99.16 297

EIA-MVS		98.00 242	97.74 258	98.80 179	98.72 324	98.09 143	98.05 190	99.60 77	97.39 270	96.63 398	95.55 434	97.68 149	99.80 226	96.73 263	99.27 316	98.52 383

LFMVS		97.20 310	96.72 325	98.64 211	98.72 324	96.95 245	98.93 81	94.14 449	99.74 13	98.78 235	99.01 202	84.45 415	99.73 282	97.44 204	99.27 316	99.25 267

new_pmnet		96.99 326	96.76 323	97.67 324	98.72 324	94.89 333	95.95 393	98.20 369	92.62 425	98.55 270	98.54 307	94.88 300	99.52 384	93.96 379	99.44 292	98.59 380

Fast-Effi-MVS+		97.67 272	97.38 284	98.57 227	98.71 328	97.43 209	97.23 312	99.45 145	94.82 387	96.13 414	96.51 414	98.52 70	99.91 73	96.19 307	98.83 369	98.37 400

TEST9					98.71 328	98.08 147	95.96 391	99.03 288	91.40 437	95.85 420	97.53 387	96.52 237	99.76 262

train_agg		97.10 316	96.45 341	99.07 132	98.71 328	98.08 147	95.96 391	99.03 288	91.64 432	95.85 420	97.53 387	96.47 239	99.76 262	93.67 387	99.16 335	99.36 231

TSAR-MVS + GP.		98.18 225	97.98 237	98.77 190	98.71 328	97.88 170	96.32 370	98.66 346	96.33 337	99.23 151	98.51 312	97.48 176	99.40 411	97.16 220	99.46 283	99.02 314

FA-MVS(test-final)		96.99 326	96.82 319	97.50 347	98.70 332	94.78 336	99.34 23	96.99 405	95.07 380	98.48 278	99.33 110	88.41 391	99.65 333	96.13 313	98.92 366	98.07 413

AUN-MVS		96.24 355	95.45 367	98.60 222	98.70 332	97.22 224	97.38 296	97.65 387	95.95 355	95.53 430	97.96 366	82.11 432	99.79 239	96.31 300	97.44 427	98.80 356

our_test_3		97.39 295	97.73 260	96.34 395	98.70 332	89.78 440	94.61 440	98.97 298	96.50 330	99.04 181	98.85 244	95.98 266	99.84 173	97.26 214	99.67 214	99.41 203

ppachtmachnet_test		97.50 282	97.74 258	96.78 385	98.70 332	91.23 427	94.55 442	99.05 283	96.36 336	99.21 155	98.79 260	96.39 242	99.78 250	96.74 261	99.82 121	99.34 238

PCF-MVS	92.86 18	94.36 392	93.00 410	98.42 255	98.70 332	97.56 199	93.16 459	99.11 273	79.59 467	97.55 350	97.43 394	92.19 353	99.73 282	79.85 465	99.45 285	97.97 419
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 248	98.02 233	97.58 337	98.69 337	94.10 358	98.13 173	98.90 308	97.95 214	97.32 368	99.58 47	95.95 269	98.75 453	96.41 294	99.22 325	99.87 21

ETV-MVS		98.03 238	97.86 252	98.56 232	98.69 337	98.07 149	97.51 281	99.50 119	98.10 206	97.50 355	95.51 435	98.41 78	99.88 114	96.27 303	99.24 321	97.71 434

test_prior				98.95 157	98.69 337	97.95 164		99.03 288					99.59 356			99.30 254

mvsmamba		97.57 280	97.26 291	98.51 243	98.69 337	96.73 258	98.74 97	97.25 398	97.03 304	97.88 326	99.23 140	90.95 367	99.87 133	96.61 274	99.00 355	98.91 336

agg_prior					98.68 341	97.99 156		99.01 294		95.59 423			99.77 256

test_8					98.67 342	98.01 155	95.91 397	99.02 291	91.64 432	95.79 422	97.50 390	96.47 239	99.76 262

HQP-NCC					98.67 342		96.29 372		96.05 348	95.55 426

ACMP_Plane					98.67 342		96.29 372		96.05 348	95.55 426

CNVR-MVS		98.17 227	97.87 251	99.07 132	98.67 342	98.24 127	97.01 327	98.93 302	97.25 284	97.62 343	98.34 334	97.27 189	99.57 365	96.42 293	99.33 305	99.39 213

HQP-MVS		97.00 325	96.49 340	98.55 234	98.67 342	96.79 253	96.29 372	99.04 286	96.05 348	95.55 426	96.84 408	93.84 325	99.54 378	92.82 405	99.26 319	99.32 247

MM		98.22 218	97.99 236	98.91 164	98.66 347	96.97 242	97.89 221	94.44 443	99.54 40	98.95 199	99.14 162	93.50 331	99.92 64	99.80 17	99.96 28	99.85 29

test_fmvs1		97.72 268	97.94 243	97.07 369	98.66 347	92.39 405	97.68 253	99.81 31	95.20 379	99.54 78	99.44 84	91.56 361	99.41 410	99.78 21	99.77 155	99.40 212

balanced_conf03		98.63 152	98.72 120	98.38 260	98.66 347	96.68 261	98.90 83	99.42 165	98.99 120	98.97 193	99.19 145	95.81 274	99.85 155	98.77 104	99.77 155	98.60 377

thres200		93.72 406	93.14 408	95.46 421	98.66 347	91.29 423	96.61 351	94.63 442	97.39 270	96.83 391	93.71 457	79.88 435	99.56 368	82.40 462	98.13 406	95.54 463

wuyk23d		96.06 357	97.62 271	91.38 450	98.65 351	98.57 103	98.85 92	96.95 408	96.86 315	99.90 14	99.16 155	99.18 19	98.40 457	89.23 445	99.77 155	77.18 470

NCCC		97.86 256	97.47 281	99.05 139	98.61 352	98.07 149	96.98 329	98.90 308	97.63 239	97.04 377	97.93 367	95.99 265	99.66 326	95.31 342	98.82 371	99.43 197

DeepC-MVS_fast	96.85 6	98.30 207	98.15 219	98.75 194	98.61 352	97.23 222	97.76 242	99.09 276	97.31 278	98.75 241	98.66 289	97.56 163	99.64 336	96.10 314	99.55 259	99.39 213
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 408	92.09 419	97.75 316	98.60 354	94.40 348	97.32 304	95.26 437	97.56 249	96.79 394	95.50 436	53.57 476	99.77 256	95.26 343	98.97 361	99.08 303

thisisatest0515		94.12 399	93.16 407	96.97 374	98.60 354	92.90 395	93.77 455	90.61 462	94.10 404	96.91 384	95.87 429	74.99 450	99.80 226	94.52 360	99.12 343	98.20 406

GA-MVS		95.86 364	95.32 374	97.49 348	98.60 354	94.15 357	93.83 454	97.93 378	95.49 369	96.68 396	97.42 395	83.21 425	99.30 426	96.22 305	98.55 390	99.01 315

dmvs_testset		92.94 418	92.21 418	95.13 425	98.59 357	90.99 430	97.65 259	92.09 458	96.95 307	94.00 450	93.55 458	92.34 351	96.97 467	72.20 469	92.52 465	97.43 442

OPU-MVS				98.82 175	98.59 357	98.30 123	98.10 180				98.52 311	98.18 107	98.75 453	94.62 357	99.48 281	99.41 203

MSLP-MVS++		98.02 239	98.14 221	97.64 331	98.58 359	95.19 324	97.48 285	99.23 245	97.47 259	97.90 324	98.62 298	97.04 201	98.81 451	97.55 193	99.41 294	98.94 331

test12				98.93 160	98.58 359	97.83 175		98.66 346		96.53 403		95.51 283	99.69 302		99.13 340	99.27 260

CL-MVSNet_self_test		97.44 290	97.22 294	98.08 292	98.57 361	95.78 298	94.30 447	98.79 331	96.58 328	98.60 260	98.19 346	94.74 307	99.64 336	96.41 294	98.84 368	98.82 346

PS-MVSNAJ		97.08 318	97.39 283	96.16 406	98.56 362	92.46 403	95.24 422	98.85 322	97.25 284	97.49 356	95.99 425	98.07 117	99.90 80	96.37 296	98.67 383	96.12 459

CNLPA		97.17 313	96.71 326	98.55 234	98.56 362	98.05 153	96.33 369	98.93 302	96.91 312	97.06 376	97.39 396	94.38 314	99.45 404	91.66 421	99.18 334	98.14 409

xiu_mvs_v2_base		97.16 314	97.49 278	96.17 404	98.54 364	92.46 403	95.45 415	98.84 323	97.25 284	97.48 357	96.49 415	98.31 89	99.90 80	96.34 299	98.68 382	96.15 458

alignmvs		97.35 297	96.88 314	98.78 185	98.54 364	98.09 143	97.71 249	97.69 384	99.20 82	97.59 346	95.90 428	88.12 393	99.55 372	98.18 142	98.96 362	98.70 368

FE-MVS		95.66 371	94.95 384	97.77 312	98.53 366	95.28 320	99.40 19	96.09 425	93.11 418	97.96 321	99.26 128	79.10 442	99.77 256	92.40 414	98.71 377	98.27 404

Effi-MVS+		98.02 239	97.82 254	98.62 217	98.53 366	97.19 228	97.33 303	99.68 59	97.30 279	96.68 396	97.46 393	98.56 68	99.80 226	96.63 272	98.20 400	98.86 343

baseline1		95.96 362	95.44 368	97.52 345	98.51 368	93.99 369	98.39 147	96.09 425	98.21 189	98.40 288	97.76 375	86.88 395	99.63 339	95.42 340	89.27 468	98.95 327

MVS_Test		98.18 225	98.36 185	97.67 324	98.48 369	94.73 339	98.18 166	99.02 291	97.69 235	98.04 316	99.11 168	97.22 193	99.56 368	98.57 118	98.90 367	98.71 365

MGCFI-Net		98.34 199	98.28 198	98.51 243	98.47 370	97.59 198	98.96 77	99.48 128	99.18 90	97.40 363	95.50 436	98.66 54	99.50 390	98.18 142	98.71 377	98.44 391

BH-RMVSNet		96.83 331	96.58 336	97.58 337	98.47 370	94.05 359	96.67 347	97.36 393	96.70 324	97.87 327	97.98 362	95.14 292	99.44 406	90.47 440	98.58 389	99.25 267

sasdasda		98.34 199	98.26 202	98.58 224	98.46 372	97.82 180	98.96 77	99.46 141	99.19 87	97.46 358	95.46 439	98.59 62	99.46 402	98.08 149	98.71 377	98.46 385

canonicalmvs		98.34 199	98.26 202	98.58 224	98.46 372	97.82 180	98.96 77	99.46 141	99.19 87	97.46 358	95.46 439	98.59 62	99.46 402	98.08 149	98.71 377	98.46 385

MVS-HIRNet		94.32 393	95.62 359	90.42 451	98.46 372	75.36 475	96.29 372	89.13 466	95.25 376	95.38 432	99.75 16	92.88 342	99.19 436	94.07 377	99.39 296	96.72 452

PHI-MVS		98.29 210	97.95 241	99.34 80	98.44 375	99.16 48	98.12 177	99.38 176	96.01 352	98.06 313	98.43 324	97.80 142	99.67 315	95.69 332	99.58 248	99.20 282

DVP-MVS++		98.90 97	98.70 126	99.51 48	98.43 376	99.15 52	99.43 15	99.32 204	98.17 196	99.26 143	99.02 191	98.18 107	99.88 114	97.07 229	99.45 285	99.49 163

MSC_two_6792asdad				99.32 88	98.43 376	98.37 118		98.86 319					99.89 96	97.14 223	99.60 239	99.71 61

No_MVS				99.32 88	98.43 376	98.37 118		98.86 319					99.89 96	97.14 223	99.60 239	99.71 61

Fast-Effi-MVS+-dtu		98.27 211	98.09 224	98.81 177	98.43 376	98.11 140	97.61 268	99.50 119	98.64 148	97.39 365	97.52 389	98.12 115	99.95 26	96.90 247	98.71 377	98.38 398

OpenMVS_ROB	95.38 14	95.84 366	95.18 379	97.81 309	98.41 380	97.15 234	97.37 300	98.62 350	83.86 462	98.65 252	98.37 330	94.29 317	99.68 311	88.41 446	98.62 387	96.60 453

DeepPCF-MVS	96.93 5	98.32 204	98.01 234	99.23 105	98.39 381	98.97 73	95.03 427	99.18 257	96.88 313	99.33 125	98.78 262	98.16 111	99.28 430	96.74 261	99.62 232	99.44 193

Patchmatch-test		96.55 341	96.34 343	97.17 364	98.35 382	93.06 391	98.40 146	97.79 380	97.33 275	98.41 284	98.67 286	83.68 423	99.69 302	95.16 345	99.31 309	98.77 359

AdaColmap		97.14 315	96.71 326	98.46 250	98.34 383	97.80 184	96.95 330	98.93 302	95.58 366	96.92 382	97.66 380	95.87 272	99.53 380	90.97 434	99.14 338	98.04 414

OpenMVS	96.65 7	97.09 317	96.68 328	98.32 267	98.32 384	97.16 233	98.86 91	99.37 180	89.48 450	96.29 412	99.15 159	96.56 235	99.90 80	92.90 402	99.20 329	97.89 422

MG-MVS		96.77 334	96.61 333	97.26 360	98.31 385	93.06 391	95.93 394	98.12 374	96.45 334	97.92 322	98.73 270	93.77 329	99.39 413	91.19 432	99.04 349	99.33 244

test_yl		96.69 335	96.29 345	97.90 302	98.28 386	95.24 321	97.29 307	97.36 393	98.21 189	98.17 299	97.86 369	86.27 399	99.55 372	94.87 351	98.32 394	98.89 338

DCV-MVSNet		96.69 335	96.29 345	97.90 302	98.28 386	95.24 321	97.29 307	97.36 393	98.21 189	98.17 299	97.86 369	86.27 399	99.55 372	94.87 351	98.32 394	98.89 338

CHOSEN 280x420		95.51 376	95.47 365	95.65 416	98.25 388	88.27 447	93.25 458	98.88 312	93.53 412	94.65 441	97.15 404	86.17 401	99.93 53	97.41 206	99.93 55	98.73 364

SCA		96.41 348	96.66 331	95.67 414	98.24 389	88.35 446	95.85 400	96.88 411	96.11 346	97.67 341	98.67 286	93.10 337	99.85 155	94.16 371	99.22 325	98.81 351

DeepMVS_CX				93.44 444	98.24 389	94.21 354		94.34 444	64.28 470	91.34 464	94.87 451	89.45 382	92.77 471	77.54 467	93.14 464	93.35 466

MS-PatchMatch		97.68 271	97.75 257	97.45 351	98.23 391	93.78 378	97.29 307	98.84 323	96.10 347	98.64 253	98.65 291	96.04 258	99.36 416	96.84 253	99.14 338	99.20 282

BH-w/o		95.13 382	94.89 386	95.86 409	98.20 392	91.31 422	95.65 407	97.37 392	93.64 410	96.52 405	95.70 432	93.04 340	99.02 442	88.10 448	95.82 454	97.24 445

mvs_anonymous		97.83 264	98.16 218	96.87 379	98.18 393	91.89 412	97.31 305	98.90 308	97.37 272	98.83 226	99.46 79	96.28 249	99.79 239	98.90 93	98.16 404	98.95 327

miper_lstm_enhance		97.18 312	97.16 297	97.25 361	98.16 394	92.85 396	95.15 425	99.31 209	97.25 284	98.74 243	98.78 262	90.07 374	99.78 250	97.19 218	99.80 138	99.11 302

RRT-MVS		97.88 253	97.98 237	97.61 334	98.15 395	93.77 379	98.97 76	99.64 69	99.16 92	98.69 246	99.42 88	91.60 359	99.89 96	97.63 187	98.52 391	99.16 297

ET-MVSNet_ETH3D		94.30 395	93.21 406	97.58 337	98.14 396	94.47 347	94.78 433	93.24 454	94.72 388	89.56 466	95.87 429	78.57 445	99.81 218	96.91 242	97.11 439	98.46 385

ADS-MVSNet2		95.43 377	94.98 382	96.76 386	98.14 396	91.74 413	97.92 217	97.76 381	90.23 444	96.51 406	98.91 228	85.61 406	99.85 155	92.88 403	96.90 440	98.69 369

ADS-MVSNet		95.24 380	94.93 385	96.18 403	98.14 396	90.10 439	97.92 217	97.32 396	90.23 444	96.51 406	98.91 228	85.61 406	99.74 275	92.88 403	96.90 440	98.69 369

c3_l		97.36 296	97.37 285	97.31 356	98.09 399	93.25 389	95.01 428	99.16 264	97.05 301	98.77 238	98.72 272	92.88 342	99.64 336	96.93 241	99.76 168	99.05 307

FMVSNet3		97.50 282	97.24 293	98.29 271	98.08 400	95.83 295	97.86 226	98.91 307	97.89 221	98.95 199	98.95 222	87.06 394	99.81 218	97.77 177	99.69 203	99.23 272

PAPM		91.88 432	90.34 435	96.51 390	98.06 401	92.56 401	92.44 462	97.17 400	86.35 458	90.38 465	96.01 424	86.61 397	99.21 435	70.65 471	95.43 456	97.75 431

Effi-MVS+-dtu		98.26 213	97.90 249	99.35 77	98.02 402	99.49 6	98.02 197	99.16 264	98.29 182	97.64 342	97.99 361	96.44 241	99.95 26	96.66 270	98.93 365	98.60 377

eth_miper_zixun_eth		97.23 308	97.25 292	97.17 364	98.00 403	92.77 398	94.71 434	99.18 257	97.27 282	98.56 268	98.74 269	91.89 357	99.69 302	97.06 231	99.81 127	99.05 307

HY-MVS	95.94 13	95.90 363	95.35 373	97.55 342	97.95 404	94.79 335	98.81 96	96.94 409	92.28 429	95.17 434	98.57 305	89.90 376	99.75 270	91.20 431	97.33 435	98.10 411

UGNet		98.53 173	98.45 170	98.79 182	97.94 405	96.96 244	99.08 61	98.54 353	99.10 104	96.82 392	99.47 77	96.55 236	99.84 173	98.56 121	99.94 49	99.55 132
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
MAR-MVS		96.47 346	95.70 356	98.79 182	97.92 406	99.12 62	98.28 155	98.60 351	92.16 430	95.54 429	96.17 422	94.77 306	99.52 384	89.62 443	98.23 398	97.72 433
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
MVSTER		96.86 330	96.55 337	97.79 310	97.91 407	94.21 354	97.56 274	98.87 314	97.49 258	99.06 171	99.05 186	80.72 433	99.80 226	98.44 127	99.82 121	99.37 224

API-MVS		97.04 321	96.91 313	97.42 353	97.88 408	98.23 131	98.18 166	98.50 356	97.57 247	97.39 365	96.75 410	96.77 222	99.15 439	90.16 441	99.02 353	94.88 464

myMVS_eth3d28		92.92 419	92.31 415	94.77 428	97.84 409	87.59 451	96.19 378	96.11 424	97.08 300	94.27 444	93.49 460	66.07 467	98.78 452	91.78 419	97.93 417	97.92 421

miper_ehance_all_eth		97.06 319	97.03 304	97.16 366	97.83 410	93.06 391	94.66 437	99.09 276	95.99 353	98.69 246	98.45 322	92.73 347	99.61 349	96.79 255	99.03 350	98.82 346

cl____		97.02 322	96.83 318	97.58 337	97.82 411	94.04 361	94.66 437	99.16 264	97.04 302	98.63 254	98.71 273	88.68 387	99.69 302	97.00 234	99.81 127	99.00 319

DIV-MVS_self_test		97.02 322	96.84 317	97.58 337	97.82 411	94.03 362	94.66 437	99.16 264	97.04 302	98.63 254	98.71 273	88.69 385	99.69 302	97.00 234	99.81 127	99.01 315

CANet		97.87 255	97.76 256	98.19 284	97.75 413	95.51 306	96.76 342	99.05 283	97.74 231	96.93 381	98.21 344	95.59 280	99.89 96	97.86 172	99.93 55	99.19 287

UBG		93.25 413	92.32 414	96.04 408	97.72 414	90.16 438	95.92 396	95.91 429	96.03 351	93.95 452	93.04 463	69.60 457	99.52 384	90.72 439	97.98 415	98.45 388

mvsany_test1		97.60 276	97.54 274	97.77 312	97.72 414	95.35 317	95.36 419	97.13 402	94.13 403	99.71 49	99.33 110	97.93 130	99.30 426	97.60 191	98.94 364	98.67 373

PVSNet_0	89.98 21	91.15 433	90.30 436	93.70 441	97.72 414	84.34 465	90.24 465	97.42 391	90.20 447	93.79 453	93.09 462	90.90 369	98.89 450	86.57 454	72.76 471	97.87 424

CR-MVSNet		96.28 351	95.95 350	97.28 358	97.71 417	94.22 352	98.11 178	98.92 305	92.31 428	96.91 384	99.37 98	85.44 409	99.81 218	97.39 207	97.36 433	97.81 427

RPMNet		97.02 322	96.93 309	97.30 357	97.71 417	94.22 352	98.11 178	99.30 217	99.37 60	96.91 384	99.34 107	86.72 396	99.87 133	97.53 196	97.36 433	97.81 427

ETVMVS		92.60 422	91.08 431	97.18 362	97.70 419	93.65 384	96.54 354	95.70 432	96.51 329	94.68 440	92.39 466	61.80 473	99.50 390	86.97 451	97.41 429	98.40 396

pmmvs3		95.03 384	94.40 391	96.93 375	97.70 419	92.53 402	95.08 426	97.71 383	88.57 454	97.71 338	98.08 355	79.39 440	99.82 201	96.19 307	99.11 344	98.43 393

baseline2		93.73 405	92.83 411	96.42 393	97.70 419	91.28 424	96.84 338	89.77 465	93.96 408	92.44 460	95.93 427	79.14 441	99.77 256	92.94 401	96.76 444	98.21 405

WBMVS		95.18 381	94.78 387	96.37 394	97.68 422	89.74 441	95.80 402	98.73 342	97.54 253	98.30 290	98.44 323	70.06 455	99.82 201	96.62 273	99.87 96	99.54 138

tpm		94.67 389	94.34 393	95.66 415	97.68 422	88.42 445	97.88 222	94.90 439	94.46 394	96.03 419	98.56 306	78.66 443	99.79 239	95.88 320	95.01 458	98.78 358

CANet_DTU		97.26 304	97.06 303	97.84 306	97.57 424	94.65 343	96.19 378	98.79 331	97.23 290	95.14 435	98.24 341	93.22 334	99.84 173	97.34 209	99.84 110	99.04 311

testing11		93.08 416	92.02 421	96.26 399	97.56 425	90.83 433	96.32 370	95.70 432	96.47 333	92.66 459	93.73 456	64.36 471	99.59 356	93.77 386	97.57 422	98.37 400

tpm2		93.09 415	92.58 413	94.62 430	97.56 425	86.53 454	97.66 257	95.79 431	86.15 459	94.07 449	98.23 343	75.95 448	99.53 380	90.91 436	96.86 443	97.81 427

testing91		93.32 411	92.27 416	96.47 392	97.54 427	91.25 425	96.17 382	96.76 413	97.18 294	93.65 455	93.50 459	65.11 470	99.63 339	93.04 400	97.45 426	98.53 382

TR-MVS		95.55 374	95.12 380	96.86 382	97.54 427	93.94 370	96.49 359	96.53 418	94.36 399	97.03 379	96.61 413	94.26 318	99.16 438	86.91 453	96.31 448	97.47 441

testing99		93.04 417	91.98 424	96.23 401	97.53 429	90.70 435	96.35 368	95.94 428	96.87 314	93.41 456	93.43 461	63.84 472	99.59 356	93.24 398	97.19 436	98.40 396

1314		95.74 368	95.60 360	96.17 404	97.53 429	92.75 399	98.07 187	98.31 365	91.22 439	94.25 445	96.68 411	95.53 281	99.03 441	91.64 423	97.18 437	96.74 451

CostFormer		93.97 401	93.78 399	94.51 431	97.53 429	85.83 457	97.98 209	95.96 427	89.29 452	94.99 437	98.63 296	78.63 444	99.62 342	94.54 359	96.50 445	98.09 412

FMVSNet5		96.01 359	95.20 378	98.41 256	97.53 429	96.10 281	98.74 97	99.50 119	97.22 293	98.03 317	99.04 188	69.80 456	99.88 114	97.27 213	99.71 193	99.25 267

PMMVS		96.51 342	95.98 349	98.09 289	97.53 429	95.84 294	94.92 430	98.84 323	91.58 434	96.05 418	95.58 433	95.68 277	99.66 326	95.59 336	98.09 408	98.76 361

reproduce_monomvs		95.00 386	95.25 375	94.22 434	97.51 434	83.34 466	97.86 226	98.44 358	98.51 165	99.29 135	99.30 116	67.68 461	99.56 368	98.89 95	99.81 127	99.77 49

PAPR		95.29 378	94.47 389	97.75 316	97.50 435	95.14 326	94.89 431	98.71 344	91.39 438	95.35 433	95.48 438	94.57 309	99.14 440	84.95 456	97.37 431	98.97 324

testing222		91.96 430	90.37 434	96.72 387	97.47 436	92.59 400	96.11 384	94.76 440	96.83 316	92.90 458	92.87 464	57.92 474	99.55 372	86.93 452	97.52 423	98.00 418

PatchT		96.65 338	96.35 342	97.54 343	97.40 437	95.32 319	97.98 209	96.64 415	99.33 65	96.89 388	99.42 88	84.32 417	99.81 218	97.69 186	97.49 424	97.48 440

tpm cat1		93.29 412	93.13 409	93.75 440	97.39 438	84.74 460	97.39 294	97.65 387	83.39 464	94.16 446	98.41 325	82.86 428	99.39 413	91.56 425	95.35 457	97.14 446

PatchmatchNet		95.58 373	95.67 358	95.30 424	97.34 439	87.32 452	97.65 259	96.65 414	95.30 375	97.07 375	98.69 282	84.77 412	99.75 270	94.97 349	98.64 384	98.83 345
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 297	96.97 307	98.50 247	97.31 440	96.47 272	98.18 166	98.92 305	98.95 127	98.78 235	99.37 98	85.44 409	99.85 155	95.96 318	99.83 117	99.17 294

LS3D		98.63 152	98.38 182	99.36 71	97.25 441	99.38 13	99.12 60	99.32 204	99.21 80	98.44 281	98.88 238	97.31 185	99.80 226	96.58 276	99.34 304	98.92 333

IB-MVS	91.63 19	92.24 428	90.90 432	96.27 398	97.22 442	91.24 426	94.36 446	93.33 453	92.37 427	92.24 462	94.58 453	66.20 466	99.89 96	93.16 399	94.63 460	97.66 435
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
UWE-MVS		92.38 425	91.76 428	94.21 435	97.16 443	84.65 461	95.42 417	88.45 467	95.96 354	96.17 413	95.84 431	66.36 464	99.71 291	91.87 418	98.64 384	98.28 403

tpmrst		95.07 383	95.46 366	93.91 438	97.11 444	84.36 464	97.62 264	96.96 407	94.98 382	96.35 411	98.80 258	85.46 408	99.59 356	95.60 335	96.23 449	97.79 430

Syy-MVS		96.04 358	95.56 364	97.49 348	97.10 445	94.48 346	96.18 380	96.58 416	95.65 363	94.77 438	92.29 467	91.27 365	99.36 416	98.17 144	98.05 412	98.63 375

myMVS_eth3d		91.92 431	90.45 433	96.30 396	97.10 445	90.90 431	96.18 380	96.58 416	95.65 363	94.77 438	92.29 467	53.88 475	99.36 416	89.59 444	98.05 412	98.63 375

MDTV_nov1_ep13			95.22 377		97.06 447	83.20 467	97.74 246	96.16 422	94.37 398	96.99 380	98.83 251	83.95 421	99.53 380	93.90 380	97.95 416

MVS		93.19 414	92.09 419	96.50 391	96.91 448	94.03 362	98.07 187	98.06 376	68.01 469	94.56 443	96.48 416	95.96 268	99.30 426	83.84 458	96.89 442	96.17 456

E-PMN		94.17 397	94.37 392	93.58 442	96.86 449	85.71 458	90.11 467	97.07 403	98.17 196	97.82 333	97.19 402	84.62 414	98.94 446	89.77 442	97.68 421	96.09 460

JIA-IIPM		95.52 375	95.03 381	97.00 371	96.85 450	94.03 362	96.93 333	95.82 430	99.20 82	94.63 442	99.71 22	83.09 426	99.60 352	94.42 365	94.64 459	97.36 444

EMVS		93.83 403	94.02 395	93.23 447	96.83 451	84.96 459	89.77 468	96.32 420	97.92 218	97.43 362	96.36 421	86.17 401	98.93 447	87.68 449	97.73 420	95.81 461

cl22		95.79 367	95.39 371	96.98 373	96.77 452	92.79 397	94.40 445	98.53 354	94.59 391	97.89 325	98.17 347	82.82 429	99.24 432	96.37 296	99.03 350	98.92 333

WB-MVSnew		95.73 369	95.57 363	96.23 401	96.70 453	90.70 435	96.07 386	93.86 450	95.60 365	97.04 377	95.45 442	96.00 261	99.55 372	91.04 433	98.31 396	98.43 393

dp		93.47 409	93.59 402	93.13 448	96.64 454	81.62 473	97.66 257	96.42 419	92.80 423	96.11 415	98.64 294	78.55 446	99.59 356	93.31 396	92.18 467	98.16 408

MonoMVSNet		96.25 353	96.53 339	95.39 422	96.57 455	91.01 429	98.82 95	97.68 386	98.57 160	98.03 317	99.37 98	90.92 368	97.78 463	94.99 347	93.88 463	97.38 443

test-LLR		93.90 402	93.85 397	94.04 436	96.53 456	84.62 462	94.05 451	92.39 456	96.17 343	94.12 447	95.07 443	82.30 430	99.67 315	95.87 323	98.18 401	97.82 425

test-mter		92.33 427	91.76 428	94.04 436	96.53 456	84.62 462	94.05 451	92.39 456	94.00 407	94.12 447	95.07 443	65.63 469	99.67 315	95.87 323	98.18 401	97.82 425

TESTMET0.1,1		92.19 429	91.77 427	93.46 443	96.48 458	82.80 469	94.05 451	91.52 461	94.45 396	94.00 450	94.88 449	66.65 463	99.56 368	95.78 328	98.11 407	98.02 415

MGCNet		97.44 290	97.01 306	98.72 200	96.42 459	96.74 257	97.20 317	91.97 459	98.46 168	98.30 290	98.79 260	92.74 346	99.91 73	99.30 62	99.94 49	99.52 150

miper_enhance_ethall		96.01 359	95.74 354	96.81 383	96.41 460	92.27 409	93.69 456	98.89 311	91.14 441	98.30 290	97.35 400	90.58 371	99.58 363	96.31 300	99.03 350	98.60 377

tpmvs		95.02 385	95.25 375	94.33 432	96.39 461	85.87 455	98.08 183	96.83 412	95.46 370	95.51 431	98.69 282	85.91 404	99.53 380	94.16 371	96.23 449	97.58 438

CMPMVS	75.91 23	96.29 350	95.44 368	98.84 172	96.25 462	98.69 95	97.02 326	99.12 271	88.90 453	97.83 331	98.86 241	89.51 380	98.90 449	91.92 416	99.51 270	98.92 333
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 390	93.69 400	96.99 372	96.05 463	93.61 386	94.97 429	93.49 451	96.17 343	97.57 349	94.88 449	82.30 430	99.01 444	93.60 389	94.17 462	98.37 400

EPMVS		93.72 406	93.27 405	95.09 427	96.04 464	87.76 449	98.13 173	85.01 472	94.69 389	96.92 382	98.64 294	78.47 447	99.31 424	95.04 346	96.46 446	98.20 406

cascas		94.79 388	94.33 394	96.15 407	96.02 465	92.36 407	92.34 463	99.26 237	85.34 461	95.08 436	94.96 448	92.96 341	98.53 456	94.41 368	98.59 388	97.56 439

MVStest1		95.86 364	95.60 360	96.63 388	95.87 466	91.70 414	97.93 214	98.94 299	98.03 208	99.56 73	99.66 32	71.83 453	98.26 459	99.35 58	99.24 321	99.91 13

gg-mvs-nofinetune		92.37 426	91.20 430	95.85 410	95.80 467	92.38 406	99.31 30	81.84 474	99.75 11	91.83 463	99.74 18	68.29 458	99.02 442	87.15 450	97.12 438	96.16 457

gm-plane-assit					94.83 468	81.97 471			88.07 456		94.99 446		99.60 352	91.76 420

GG-mvs-BLEND				94.76 429	94.54 469	92.13 411	99.31 30	80.47 475		88.73 469	91.01 469	67.59 462	98.16 462	82.30 463	94.53 461	93.98 465

UWE-MVS-28		90.22 434	89.28 437	93.02 449	94.50 470	82.87 468	96.52 357	87.51 468	95.21 378	92.36 461	96.04 423	71.57 454	98.25 460	72.04 470	97.77 419	97.94 420

EPNet_dtu		94.93 387	94.78 387	95.38 423	93.58 471	87.68 450	96.78 340	95.69 434	97.35 274	89.14 468	98.09 354	88.15 392	99.49 393	94.95 350	99.30 312	98.98 321
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 438	75.95 441	77.12 454	92.39 472	67.91 478	90.16 466	59.44 479	82.04 465	89.42 467	94.67 452	49.68 477	81.74 472	48.06 472	77.66 470	81.72 468

KD-MVS_2432*1600		92.87 420	91.99 422	95.51 419	91.37 473	89.27 442	94.07 449	98.14 372	95.42 371	97.25 370	96.44 418	67.86 459	99.24 432	91.28 429	96.08 452	98.02 415

miper_refine_blended		92.87 420	91.99 422	95.51 419	91.37 473	89.27 442	94.07 449	98.14 372	95.42 371	97.25 370	96.44 418	67.86 459	99.24 432	91.28 429	96.08 452	98.02 415

EPNet		96.14 356	95.44 368	98.25 275	90.76 475	95.50 309	97.92 217	94.65 441	98.97 123	92.98 457	98.85 244	89.12 383	99.87 133	95.99 316	99.68 208	99.39 213
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 439	68.95 442	70.34 455	87.68 476	65.00 479	91.11 464	59.90 478	69.02 468	74.46 473	88.89 470	48.58 478	68.03 474	28.61 473	72.33 472	77.99 469

test_method		79.78 436	79.50 439	80.62 452	80.21 477	45.76 480	70.82 469	98.41 362	31.08 472	80.89 472	97.71 377	84.85 411	97.37 465	91.51 426	80.03 469	98.75 362

tmp_tt		78.77 437	78.73 440	78.90 453	58.45 478	74.76 477	94.20 448	78.26 476	39.16 471	86.71 470	92.82 465	80.50 434	75.19 473	86.16 455	92.29 466	86.74 467

testmvs		17.12 441	20.53 444	6.87 457	12.05 479	4.20 482	93.62 457	6.73 480	4.62 475	10.41 475	24.33 472	8.28 480	3.56 476	9.69 475	15.07 473	12.86 472

test123		17.04 442	20.11 445	7.82 456	10.25 480	4.91 481	94.80 432	4.47 481	4.93 474	10.00 476	24.28 473	9.69 479	3.64 475	10.14 474	12.43 474	14.92 471

mmdepth		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

monomultidepth		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

test_blank		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

eth-test2					0.00 481

eth-test					0.00 481

uanet_test		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

DCPMVS		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

cdsmvs_eth3d_5k		24.66 440	32.88 443	0.00 458	0.00 481	0.00 483	0.00 470	99.10 274	0.00 476	0.00 477	97.58 385	99.21 18	0.00 477	0.00 476	0.00 475	0.00 473

pcd_1.5k_mvsjas		8.17 443	10.90 446	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	98.07 117	0.00 477	0.00 476	0.00 475	0.00 473

sosnet-low-res		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

sosnet		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uncertanet		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

Regformer		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

ab-mvs-re		8.12 444	10.83 447	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	97.48 391	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

uanet		0.00 445	0.00 448	0.00 458	0.00 481	0.00 483	0.00 470	0.00 482	0.00 476	0.00 477	0.00 476	0.00 481	0.00 477	0.00 476	0.00 475	0.00 473

TestfortrainingZip							98.68 107

WAC-MVS						90.90 431								91.37 428

PC_three_1452									93.27 415	99.40 111	98.54 307	98.22 103	97.00 466	95.17 344	99.45 285	99.49 163

test_241102_TWO								99.30 217	98.03 208	99.26 143	99.02 191	97.51 171	99.88 114	96.91 242	99.60 239	99.66 76

test_0728_THIRD									98.17 196	99.08 169	99.02 191	97.89 134	99.88 114	97.07 229	99.71 193	99.70 66

GSMVS																98.81 351

sam_mvs1												84.74 413				98.81 351

sam_mvs												84.29 419

MTGPA								99.20 249

test_post1							97.59 271				20.48 475	83.07 427	99.66 326	94.16 371

test_post											21.25 474	83.86 422	99.70 298

patchmatchnet-post											98.77 264	84.37 416	99.85 155

MTMP							97.93 214	91.91 460

test9_res														93.28 397	99.15 337	99.38 222

agg_prior2														92.50 413	99.16 335	99.37 224

test_prior4						97.97 160	95.86 398

test_prior2							95.74 405		96.48 332	96.11 415	97.63 383	95.92 271		94.16 371	99.20 329

旧先验2							95.76 404		88.56 455	97.52 353			99.66 326	94.48 361

新几何2							95.93 394

无先验							95.74 405	98.74 341	89.38 451				99.73 282	92.38 415		99.22 277

原ACMM2							95.53 411

testdata2													99.79 239	92.80 407

segment_acmp												97.02 204

testdata1							95.44 416		96.32 338

plane_prior5								99.27 232					99.70 298	94.42 365	99.51 270	99.45 189

plane_prior4											97.98 362

plane_prior3						97.78 185			97.41 268	97.79 334

plane_prior2							97.77 239		98.20 193

plane_prior						97.65 194	97.07 325		96.72 322						99.36 300

n2								0.00 482

nn								0.00 482

door-mid								99.57 90

test11								98.87 314

door								99.41 169

HQP5-MVS						96.79 253

BP-MVS														92.82 405

HQP4-MVS										95.56 425			99.54 378			99.32 247

HQP3-MVS								99.04 286							99.26 319

HQP2-MVS												93.84 325

MDTV_nov1_ep13_2view						74.92 476	97.69 252		90.06 449	97.75 337		85.78 405		93.52 391		98.69 369

ACMMP++_ref															99.77 155

ACMMP++															99.68 208

Test By Simon												96.52 237

High-resolution multi-view benchmark