WDRN : A Wavelet Decomposed RelightNet for Image Relighting
This addresses the problem of adjusting illumination in images for applications in digital photography, gaming, and augmented reality, representing an incremental improvement with a novel method.
The paper tackled the one-to-one image relighting problem by proposing WDRN, a wavelet decomposed encoder-decoder network with a novel gray loss function, achieving first place in the AIM 2020 relighting challenge as measured by Mean Perceptual Score based on SSIM and LPIPS.
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.