Wanyan Xu

Wanyan Xu

Auto-generated profile, based on publicly available information

Wanyan Xu

School of Advanced Manufacturing, Fuzhou University, Quanzhou, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 December 2022 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
WXWanyan Xu
Wanyan Xu
XDXingbo Dong
Xingbo Dong
LMLan Ma
Lan Ma
ABAndrew Beng
Andrew Beng
JTJin Teoh
Jin Teoh
ZLZhixian Lin
Zhixian Lin
Low-light image enhancement plays a central role in various downstream computer vision tasks. Vision Transformers (ViTs) have recently been adapted for low-level image processing and have achieved a promising performance. However, ViTs process images in a window- or patch-based manner, compromising their computational efficiency and long-range dependency. Additionally, existing ViTs process RGB images instead of RAW data from sensors, which is sub-optimal when it comes to utilizing the rich information from RAW data. We propose a fully endto-end Conv-Transformer-based model, RawFormer, to directly utilize RAW data for low-light image enhancement. RawFormer has a structure similar to that of U-Net, but it is integrated with a thoughtfully designed Conv-Transformer Fusing (CTF) block. The CTF block combines local attention and transposed selfattention mechanisms in one module and reduces the computational overhead by adopting a transposed self-attention operation. Experiments demonstrate that RawFormer outperforms state-ofthe-art models by a significant margin on low-light RAW image enhancement tasks.