.png){kind=icon}
返回
Self-attention learning network for face super-resolution
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2023.01.006.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Existing face super-resolution methods depend on deep convolutional networks (DCN) to recover high -quality reconstructed images. They either acquire information in a single space by designing complex models for direct reconstruction, or employ additional networks to extract multiple prior information to enhance the representation of features. However, existing methods are still challenging to perform well due to the inability to learn complete and uniform representations. To this end, we propose a self-attention learning network (SLNet) for three-stage face super-resolution, which fully explores the interdependence of low-and high-level spaces to achieve compensation of the information used for reconstruction. Firstly, SLNet uses a hierarchical feature learning framework to obtain shallow information in the low-level space. Then, the shallow information with cumulative errors due to DCN is improved under high-resolution (HR) supervision, while bringing an intermediate reconstruction result and a powerful intermediate benchmark. Finally, the improved feature representation is further enhanced in high-level space by a multi-scale context-aware encoder-decoder for facial reconstruction. The features in both spaces are explored progressively from coarse to fine reconstruction informa-tion. The experimental results show that SLNet has a competitive performance compared to the state-of-the-art methods.(c) 2023 Elsevier Ltd. All rights reserved.
Keyword:
Feature learning
Information compensation
Supervised learning
Face super-resolution
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Non-linear perceptual multi-scale network for single image super-resolution.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Recent Advances in Halogen-Free Flame Retardants for Polyolefin Cable Sheath MaterialsPolymers
OAAI
PolymersIF0
OAAI分享收藏
分享收藏
查看更多内容