End-to-end Rain Streak Removal with RAW Images

• DOI: 10.48550/arxiv.2312.13304
• Publication Date: 2023-01-01
• Authors: Guodong Du; HaoJian Deng; JiaHao Su; Yuan Huang
• Keywords: RGB color model; Streak

In this work we address the problem of rain streak removal with RAW images. The general approach is firstly processing data into RGB images and removing Actually original information in affected by image signal (ISP) pipelines including none-linear algorithms, unexpected noise, artifacts so on. It gains more benefit to directly remove before being processed format. To solve problem, propose a joint solution for obtain clean color from rainy image. be specific, generate converting space design simple but efficient algorithms synthesize both are used as reference help corrections. Different backbones show that our method conduct better result compared several other state-of-the-art deraining methods focused on addition, proposed network generalizes well cameras beyond selected dataset. Finally, give tested different ISP generalization performance model