Learning to Jointly Deblur, Demosaick and Denoise Raw Images
This work addresses image quality enhancement for raw camera data, but it is incremental as it builds on an existing method with modifications for raw images.
The paper tackles the problem of non-blind deblurring, demosaicking, and denoising of raw images by adapting an existing learning-based approach to handle raw data with a new interpretable module, demonstrating effectiveness over two-stage methods on benchmarks and applying it to remove camera blur from real images.
We address the problem of non-blind deblurring and demosaicking of noisy raw images. We adapt an existing learning-based approach to RGB image deblurring to handle raw images by introducing a new interpretable module that jointly demosaicks and deblurs them. We train this model on RGB images converted into raw ones following a realistic invertible camera pipeline. We demonstrate the effectiveness of this model over two-stage approaches stacking demosaicking and deblurring modules on quantitive benchmarks. We also apply our approach to remove a camera's inherent blur (its color-dependent point-spread function) from real images, in essence deblurring sharp images.