Image rain removal and illumination enhancement done in one go

作者：

Highlights：

• We propose a novel unified framework to simultaneously remove rain and enhance illumination.

• A new synthetic dataset for rainy day image restoration is proposed.

• Our SANet is extensively evaluated and attains new state-of-the-art performance.

摘要

•We propose a novel unified framework to simultaneously remove rain and enhance illumination.•A new synthetic dataset for rainy day image restoration is proposed.•Our SANet is extensively evaluated and attains new state-of-the-art performance.

论文关键词：Rain removal,Low-light image enhancement,Spatially-adaptive network,Contrastive learning

论文评审过程：Received 9 March 2022, Revised 7 June 2022, Accepted 8 June 2022, Available online 15 June 2022, Version of Record 6 July 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109244