Summary of Diffusionact: Controllable Diffusion Autoencoder For One-shot Face Reenactment, by Stella Bounareli et al.
DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment
by Stella Bounareli, Christos Tzelepis, Vasileios Argyriou, Ioannis Patras, Georgios Tzimiropoulos
First submitted to arxiv on: 25 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 presents a novel method called DiffusionAct that leverages diffusion models to perform neural face reenactment. The goal is to synthesize realistic facial images that preserve the identity and appearance of a source face while transferring the target head pose and facial expressions. Existing GAN-based methods suffer from distortions, visual artifacts, or poor reconstruction quality, which are addressed by using diffusion models for photo-realistic image generation. The method controls the semantic space of a Diffusion Autoencoder (DiffAE) to edit the facial pose, allowing one-shot, self, and cross-subject reenactment without requiring fine-tuning. Experimental results show better or on-par performance compared to state-of-the-art GAN-, StyleGAN2-, and diffusion-based methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to make fake faces that look really real. It’s called DiffusionAct, and it uses special computer models to change the pose of someone’s face. Right now, most ways of doing this have problems like making the face look weird or not including important details like hair color or glasses. But this new method can do it all without needing lots of practice with each person’s face. It even works when the faces are very different from each other! The paper compares its results to other methods and shows that it does just as well or better. |
Keywords
» Artificial intelligence » Autoencoder » Diffusion » Fine tuning » Gan » Image generation » One shot
