WDRN : A Wavelet Decomposed RelightNet for Image Relighting

TL;DR

This paper introduces WDRN, a wavelet-based encoder-decoder network for image relighting, featuring a novel loss function, achieving state-of-the-art results in a relighting challenge.

Contribution

It presents a novel wavelet decomposed RelightNet architecture with a new gray loss function for improved image relighting performance.

Findings

Won first place in the AIM 2020 relighting challenge

Achieved high SSIM and perceptual scores

Demonstrated superior visual quality in relit images

Abstract

The task of recalibrating the illumination settings in an image to a target configuration is known as relighting. Relighting techniques have potential applications in digital photography, gaming industry and in augmented reality. In this paper, we address the one-to-one relighting problem where an image at a target illumination settings is predicted given an input image with specific illumination conditions. To this end, we propose a wavelet decomposed RelightNet called WDRN which is a novel encoder-decoder network employing wavelet based decomposition followed by convolution layers under a muti-resolution framework. We also propose a novel loss function called gray loss that ensures efficient learning of gradient in illumination along different directions of the ground truth image giving rise to visually superior relit images. The proposed solution won the first position in the relighting challenge event in advances in image manipulation (AIM) 2020 workshop which proves its effectiveness measured in terms of a Mean Perceptual Score which in turn is measured using SSIM and a Learned Perceptual Image Patch Similarity score.