Summary of Super: Selfie Undistortion and Head Pose Editing with Identity Preservation, by Polina Karpikova et al.
SUPER: Selfie Undistortion and Head Pose Editing with Identity Preservation
by Polina Karpikova, Andrei Spiridonov, Anna Vorontsova, Anastasia Yaschenko, Ekaterina Radionova, Igor Medvedev, Alexander Limonov
First submitted to arxiv on: 18 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 This paper proposes a novel method called SUPER to eliminate distortions and adjust head pose in close-up face crops. The method uses 3D GAN inversion to optimize camera parameters and facial features, generating an image that can be used as input for further processing. The authors also estimate depth from the latent code and use it to create a 3D mesh, which is then rendered with updated camera parameters to obtain a warped portrait. To complete the process, visibility-based blending is applied to reproject visible regions and restore occluded parts using a generative model. The results on face undistortion benchmarks and the self-collected Head Rotation dataset (HeRo) show that SUPER outperforms previous approaches both qualitatively and quantitatively. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make selfies look more natural by fixing distortions and bad head angles. They developed a new way to do this called SUPER, which uses special computer vision techniques to correct the image. First, they generate an image that looks like the original selfie. Then, they use this image to create a 3D model of the face. Finally, they blend the corrected parts together so the result looks natural and realistic. |
Keywords
» Artificial intelligence » Gan » Generative model
