|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM324544138 |
| 003 |
DE-627 |
| 005 |
20231225190538.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2021 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2021.3074306
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1081.xml
|
| 035 |
|
|
|a (DE-627)NLM324544138
|
| 035 |
|
|
|a (NLM)33900917
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Song, Xibin
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a MLDA-Net
|b Multi-Level Dual Attention-Based Network for Self-Supervised Monocular Depth Estimation
|
| 264 |
|
1 |
|c 2021
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 04.05.2021
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a The success of supervised learning-based single image depth estimation methods critically depends on the availability of large-scale dense per-pixel depth annotations, which requires both laborious and expensive annotation process. Therefore, the self-supervised methods are much desirable, which attract significant attention recently. However, depth maps predicted by existing self-supervised methods tend to be blurry with many depth details lost. To overcome these limitations, we propose a novel framework, named MLDA-Net, to obtain per-pixel depth maps with shaper boundaries and richer depth details. Our first innovation is a multi-level feature extraction (MLFE) strategy which can learn rich hierarchical representation. Then, a dual-attention strategy, combining global attention and structure attention, is proposed to intensify the obtained features both globally and locally, resulting in improved depth maps with sharper boundaries. Finally, a reweighted loss strategy based on multi-level outputs is proposed to conduct effective supervision for self-supervised depth estimation. Experimental results demonstrate that our MLDA-Net framework achieves state-of-the-art depth prediction results on the KITTI benchmark for self-supervised monocular depth estimation with different input modes and training modes. Extensive experiments on other benchmark datasets further confirm the superiority of our proposed approach
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Li, Wei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhou, Dingfu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Dai, Yuchao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Fang, Jin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Hongdong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Liangjun
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 30(2021) vom: 02., Seite 4691-4705
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:30
|g year:2021
|g day:02
|g pages:4691-4705
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2021.3074306
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 30
|j 2021
|b 02
|h 4691-4705
|