- published
- 2022-10-12
- reference
- Quentin Bammey, Experiments on Deep Single-Image Portrait Relighting, Image Processing On Line, 12 (2022), pp. 420–434. https://doi.org/10.5201/ipol.2022.429
Communicated by Jean-Michel Morel
Demo edited by Quentin Bammey
Abstract
This work describes deep single-image portrait relighting, a method to change the lighting of an image. The method is based on an hourglass convolutional neural network, which encodes the image and its estimated original lighting features, then replaces the lighting features with the target light. We highlight the overall good results produced by this method, as well as its limitations and the lighting artifacts that sometimes appear on relighted images.
This is an MLBriefs article, the source code has not been reviewed!
The original source code is available here (last checked 2022/10/10).
Download
- full text manuscript: PDF low-res. (843.1kB) PDF (83.1MB) [?]
- source code: TAR/GZ
History
- Note from the editor: The paper was modified on 2022-10-20 to correct the list of keywords. The original version of the paper is available here.