Half-body portrait relighting with overcomplete lighting representation

Guoxian Song, Tat-Jen Cham, Jianfei Cai, Jianmin Zheng

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)


We present a neural-based model for relighting a half-body portrait image by simply referring to another portrait image with the desired lighting condition. Rather than following classical inverse rendering methodology that involves estimating normals, albedo and environment maps, we implicitly encode the subject and lighting in a latent space, and use these latent codes to generate relighted images by neural rendering. A key technical innovation is the use of a novel overcomplete lighting representation, which facilitates lighting interpolation in the latent space, as well as helping regularize the self-organization of the lighting latent space during training. In addition, we propose a novel multiplicative neural render that more effectively combines the subject and lighting latent codes for rendering. We also created a large-scale photorealistic rendered relighting dataset for training, which allows our model to generalize well to real images. Extensive experiments demonstrate that our system not only outperforms existing methods for referral-based portrait relighting, but also has the capability generate sequences of relighted images via lighting rotations.

Original languageEnglish
Pages (from-to)371-381
Number of pages11
JournalComputer Graphics Forum
Issue number6
Publication statusPublished - Sep 2021


  • computational photography
  • computer vision - tracking
  • image and video processing
  • image processing
  • methods and applications

Cite this