End-to-end Rain Streak Removal with RAW Images

TL;DR

This paper introduces a novel end-to-end method for removing rain streaks directly from RAW images, improving deraining performance by addressing RAW data before ISP processing and demonstrating better generalization across cameras and pipelines.

Contribution

The work presents a joint RAW processing and rain removal approach that operates directly on RAW data, outperforming existing RGB-based deraining methods and enhancing generalization.

Findings

Outperforms state-of-the-art RGB deraining methods.

Generalizes well across different camera RAW datasets.

Maintains effectiveness across various ISP pipelines.

Abstract

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