Deep Relighting Networks for Image Light Source Manipulation

19 Aug 2020  ·  Li-Wen Wang, Wan-Chi Siu, Zhi-Song Liu, Chu-Tak Li, Daniel P. K. Lun ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Relighting VIDIT’20 validation set DRN PSNR 17.59 # 2
SSIM 0.596 # 3
LPIPS 0.440 # 5
MPS 0.578 # 4
Runtime(s) 0.5 # 3


No methods listed for this paper. Add relevant methods here