Toward Efficient Deep Blind RAW Image Restoration
This addresses the problem of complex degradation modeling in image restoration for computer vision applications, though it is incremental as it builds on known issues with RAW data.
The paper tackles image restoration by working directly with sensor RAW images instead of RGB, designing a realistic degradation pipeline for training deep blind models that reduces noise and blur and recovers details across multiple cameras.
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