Summary of My Body My Choice: Human-centric Full-body Anonymization, by Umur Aybars Ciftci et al.
My Body My Choice: Human-Centric Full-Body Anonymization
by Umur Aybars Ciftci, Ali Kemal Tanriverdi, Ilke Demir
First submitted to arxiv on: 13 Jun 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 proposes a novel approach to online privacy called “My Body My Choice” (MBMC), which enables individuals to control the decision to appear in certain content. The authors argue that human-guided anonymization is more effective than automatic methods, as it can adapt to various contexts such as cultural norms and esthetic concerns. MBMC uses a combination of ControlNet and GAN modules with several diffusion models for physical and adversarial anonymization. The authors evaluate the method on seven datasets using image, adversarial, and generative metrics, and compare its performance with state-of-the-art inpainting and anonymization methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to keep our online presence private called “My Body My Choice”. It lets people decide what they want to show or hide in photos. The method uses special computer programs to remove or swap parts of the image, making it harder for others to recognize who’s in it. The authors tested this approach on many different images and compared it to other methods that are already being used. They found that their approach works well and can help protect people’s privacy online. |
Keywords
» Artificial intelligence » Gan
