Summary of Learning Gaze-aware Compositional Gan, by Nerea Aranjuelo et al.
Learning Gaze-aware Compositional GAN
by Nerea Aranjuelo, Siyu Huang, Ignacio Arganda-Carreras, Luis Unzueta, Oihana Otaegui, Hanspeter Pfister, Donglai Wei
First submitted to arxiv on: 31 May 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 proposed Gaze-aware Compositional GAN framework generates annotated gaze data by leveraging labeled and unlabeled data sources. This generative model learns from a limited labeled dataset to create within-domain image augmentations in the ETH-XGaze dataset and cross-domain augmentations in the CelebAMask-HQ dataset for training deep neural networks (DNNs) for gaze estimation. The framework also demonstrates additional applications, including facial image editing and gaze redirection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way is found to make fake pictures of faces that look like real people. This helps computers learn better about what people are looking at. It works by using a little bit of information from some known images and then making more images that fit in with those pictures. The results show that this method can help train computers to get better at guessing where someone is looking. |
Keywords
» Artificial intelligence » Gan » Generative model
