We review the AIM 2020 challenge on virtual image relighting and illumination estimation. This paper presents the novel VIDIT dataset used in the challenge and the different proposed solutions and final evaluation results over the 3 challenge tracks. The first track considered one-to-one relighting; the objective was to relight an input photo of a scene with a different color temperature and illuminant orientation (i.e., light source position). The goal of the second track was to estimate illumination settings, namely the color temperature and orientation, from a given image. Lastly, the third track dealt with any-to-any relighting, thus a generalization of the first track. The target color temperature and orientation, rather than being pre-determined, are instead given by a guide image. Participants were allowed to make use of their track 1 and 2 solutions for track 3. The tracks had 94, 52, and 56 registered participants, respectively, leading to 20 confirmed submissions in the final competition stage.
@article{arxiv.2009.12798,
title = {AIM 2020: Scene Relighting and Illumination Estimation Challenge},
author = {Majed El Helou and Ruofan Zhou and Sabine Süsstrunk and Radu Timofte and Mahmoud Afifi and Michael S. Brown and Kele Xu and Hengxing Cai and Yuzhong Liu and Li-Wen Wang and Zhi-Song Liu and Chu-Tak Li and Sourya Dipta Das and Nisarg A. Shah and Akashdeep Jassal and Tongtong Zhao and Shanshan Zhao and Sabari Nathan and M. Parisa Beham and R. Suganya and Qing Wang and Zhongyun Hu and Xin Huang and Yaning Li and Maitreya Suin and Kuldeep Purohit and A. N. Rajagopalan and Densen Puthussery and Hrishikesh P S and Melvin Kuriakose and Jiji C and Yu Zhu and Liping Dong and Zhuolong Jiang and Chenghua Li and Cong Leng and Jian Cheng},
journal= {arXiv preprint arXiv:2009.12798},
year = {2020}
}
Comments
ECCVW 2020. Data and more information on https://github.com/majedelhelou/VIDIT