Deep Relighting Networks for Image Light Source Manipulation
This addresses the challenge of manipulating light sources in images for applications like photography and cinematography, offering a novel method that is incremental over existing approaches.
The paper tackles the problem of single image relighting without requiring additional geometric information, proposing a Deep Relighting Network (DRN) that achieved the best PSNR in the AIM2020 challenge at ECCV 2020.
Manipulating the light source of given images is an interesting task and useful in various applications, including photography and cinematography. Existing methods usually require additional information like the geometric structure of the scene, which may not be available for most images. In this paper, we formulate the single image relighting task and propose a novel Deep Relighting Network (DRN) with three parts: 1) scene reconversion, which aims to reveal the primary scene structure through a deep auto-encoder network, 2) shadow prior estimation, to predict light effect from the new light direction through adversarial learning, and 3) re-renderer, to combine the primary structure with the reconstructed shadow view to form the required estimation under the target light source. Experimental results show that the proposed method outperforms other possible methods, both qualitatively and quantitatively. Specifically, the proposed DRN has achieved the best PSNR in the "AIM2020 - Any to one relighting challenge" of the 2020 ECCV conference.