A2Net: Adjacent Aggregation Networks for Image Raindrop Removal

IEEE Access

Huangxing Lin¹  Yue Huang¹  Changxing Jing¹  Xinghao Ding¹ 

[1] School of Information, Xiamen University, Xiamen, China;

关键词: Raindrop removal;    feature aggregation;    YUV space;    deep learning;   

DOI  :  10.1109/ACCESS.2020.2983087

来源: DOAJ

【 摘 要 】

Existing methods for single images raindrop removal either have poor robustness or suffer from parameter burdens. In this paper, we propose a new Adjacent Aggregation Network (A²Net) with lightweight architectures to remove raindrops from single images. Instead of directly cascading convolutional layers, we design an adjacent aggregation architecture to better fuse features for rich representations generation, which can lead to high quality images reconstruction. To further simplify the learning process, we utilize a problem-specific knowledge to force the network focus on the luminance channel in the YUV color space instead of all RGB channels. By combining adjacent aggregating operation with color space transformation, the proposed A²Net can achieve state-of-the-art performances on raindrop removal with significant parameters reduction.

【 授权许可】

Unknown