Toward Efficient Deep Blind RAW Image Restoration

TL;DR

This paper introduces a new pipeline for training deep models to restore RAW images directly, effectively handling realistic sensor noise, motion blur, and other degradations, advancing RAW image restoration techniques.

Contribution

It presents a realistic degradation pipeline for RAW images and demonstrates effective deep blind restoration models trained with this pipeline, addressing a gap in current methods.

Findings

Models successfully reduce noise and blur in RAW images.

The pipeline handles multiple sensor types effectively.

This is the most comprehensive analysis on RAW image restoration to date.

Abstract

Multiple low-vision tasks such as denoising, deblurring and super-resolution depart from RGB images and further reduce the degradations, improving the quality. However, modeling the degradations in the sRGB domain is complicated because of the Image Signal Processor (ISP) transformations. Despite of this known issue, very few methods in the literature work directly with sensor RAW images. In this work we tackle image restoration directly in the RAW domain. We design a new realistic degradation pipeline for training deep blind RAW restoration models. Our pipeline considers realistic sensor noise, motion blur, camera shake, and other common degradations. The models trained with our pipeline and data from multiple sensors, can successfully reduce noise and blur, and recover details in RAW images captured from different cameras. To the best of our knowledge, this is the most exhaustive analysis on RAW image restoration. Code available at https://github.com/mv-lab/AISP