Summary of Toonaging: Face Re-aging Upon Artistic Portrait Style Transfer, by Bumsoo Kim et al.
ToonAging: Face Re-Aging upon Artistic Portrait Style Transfer
by Bumsoo Kim, Abdul Muqeet, Kyuchul Lee, Sanghyun Seo
First submitted to arxiv on: 5 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Graphics (cs.GR); Machine Learning (cs.LG); Multimedia (cs.MM)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel one-stage method for face re-aging combined with portrait style transfer in non-photorealistic (NPR) images. The authors leverage existing networks trained within the photorealistic (PR) domain to fuse distinct latent vectors, which manage aging-related attributes and NPR appearance. This approach offers greater flexibility compared to domain-level fine-tuning methods, which typically require separate training or fine-tuning for each domain. The method is executed in a single generative step and can effortlessly generate re-aged images while simultaneously transferring the style of examples, maintaining both natural appearance and controllability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way to make people’s faces look younger or older in cartoons, comic books, and animation movies. This is important because it’s hard to make people’s faces look good in these types of images when they’re being aged or de-agered. The authors use existing computer programs that work well for making faces look old or young again, but this time they modify them to also change the style of the image, like from realistic to cartoonish. This makes it easier to make the changes and keeps the face looking natural. |
Keywords
* Artificial intelligence * Fine tuning * Style transfer
