no code implementations • CVPR 2022 • Xiaotian Qiao, Gerhard P. Hancke, Rynson W.H. Lau
We also show that our model enables a wide range of applications, including novel-view image synthesis, novel-view image editing, and amodal object estimation.
1 code implementation • ICCV 2021 • Xiaotian Qiao, Gerhard P. Hancke, Rynson W.H. Lau
In particular, we first detect the light source regions and the flare regions separately, and then remove the flare artifacts based on the light source aware guidance.
no code implementations • CVPR 2019 • Xiaotian Qiao, Quanlong Zheng, Ying Cao, Rynson W.H. Lau
In this paper, we consider an inverse problem of how to hallucinate missing contextual information from the properties of a few standalone objects.