Deep Residual Network for Joint Demosaicing and Super-Resolution

TL;DR

This paper introduces a deep residual network that jointly performs demosaicing and super-resolution, effectively reducing artifacts and improving image quality in digital photography.

Contribution

It presents the first end-to-end deep learning approach for simultaneous demosaicing and super-resolution from Bayer images, outperforming separate methods.

Findings

Achieves higher PSNR and SSIM than state-of-the-art methods.

Produces artifact-free high-resolution images from low-resolution Bayer mosaics.

Demonstrates superior qualitative and quantitative results.

Abstract

In digital photography, two image restoration tasks have been studied extensively and resolved independently: demosaicing and super-resolution. Both these tasks are related to resolution limitations of the camera. Performing super-resolution on a demosaiced images simply exacerbates the artifacts introduced by demosaicing. In this paper, we show that such accumulation of errors can be easily averted by jointly performing demosaicing and super-resolution. To this end, we propose a deep residual network for learning an end-to-end mapping between Bayer images and high-resolution images. By training on high-quality samples, our deep residual demosaicing and super-resolution network is able to recover high-quality super-resolved images from low-resolution Bayer mosaics in a single step without producing the artifacts common to such processing when the two operations are done separately. We perform extensive experiments to show that our deep residual network achieves demosaiced and super-resolved images that are superior to the state-of-the-art both qualitatively and in terms of PSNR and SSIM metrics.