The novel VIDIT dataset used in the AIM 2020 challenge and the different proposed solutions and final evaluation results over the 3 challenge tracks are presented.
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.
Jian Cheng
2 papers
Radu Timofte
49 papers
Cong Leng
5 papers
M. Afifi
10 papers
Majed El Helou
6 papers
Ruofan Zhou
5 papers
Nisarg A. Shah
4 papers
Shanshan Zhao
2 papers
Michael S. Brown
2 papers
Kuldeep Purohit
2 papers
A. Rajagopalan
2 papers
Sourya Dipta Das
3 papers
Yu Zhu
2 papers
Sabine E. Susstrunk
1 papers
Hengxing Cai
1 papers
Yuzhong Liu
1 papers
Li-Wen Wang
1 papers
Zhi-Song Liu
1 papers
Chu-Tak Li
1 papers
Akashdeep Jassal
1 papers
Tongtong Zhao
1 papers
S. Nathan
1 papers
M. Beham
1 papers
R. Suganya
1 papers
Qing Wang
1 papers
Zhongyun Hu
1 papers
Xin Huang
1 papers
Yaning Li
1 papers
Maitreya Suin
1 papers
Densen Puthussery
1 papers
S. HrishikeshP.
1 papers
M. Kuriakose
1 papers
V. JijiC.
1 papers
Liping Dong
1 papers
Zhuolong Jiang
1 papers
Chenghua Li
1 papers