NTIRE 2021 Depth Guided Image Relighting Challenge
This addresses image relighting for applications like domain adaptation and photo enhancement, but it is incremental as it focuses on organizing and reporting a competition rather than introducing new methods.
The paper reviewed the NTIRE 2021 depth guided image relighting challenge, which tackled the problem of transforming illumination setups in images using depth information, with two tracks (one-to-one and any-to-any relighting) and involved 250 registered participants and 18 final submissions.
Image relighting is attracting increasing interest due to its various applications. From a research perspective, image relighting can be exploited to conduct both image normalization for domain adaptation, and also for data augmentation. It also has multiple direct uses for photo montage and aesthetic enhancement. In this paper, we review the NTIRE 2021 depth guided image relighting challenge. We rely on the VIDIT dataset for each of our two challenge tracks, including depth information. The first track is on one-to-one relighting where the goal is to transform the illumination setup of an input image (color temperature and light source position) to the target illumination setup. In the second track, the any-to-any relighting challenge, the objective is to transform the illumination settings of the input image to match those of another guide image, similar to style transfer. In both tracks, participants were given depth information about the captured scenes. We had nearly 250 registered participants, leading to 18 confirmed team submissions in the final competition stage. The competitions, methods, and final results are presented in this paper.