Learning to Jointly Deblur, Demosaick and Denoise Raw Images

TL;DR

This paper introduces a novel learning-based method that jointly performs deblurring and demosaicking on raw images, improving quality over traditional two-step approaches and effectively removing camera-specific blur.

Contribution

It proposes an interpretable, unified model trained on realistically simulated raw images, advancing the integration of deblurring and demosaicking tasks.

Findings

Outperforms two-stage approaches on quantitative benchmarks

Successfully removes camera-specific blur from real images

Demonstrates effectiveness on raw images with realistic pipeline simulation

Abstract

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.