Summary of Facet: Fast and Accurate Event-based Eye Tracking Using Ellipse Modeling For Extended Reality, by Junyuan Ding et al.
FACET: Fast and Accurate Event-Based Eye Tracking Using Ellipse Modeling for Extended Reality
by Junyuan Ding, Ziteng Wang, Chang Gao, Min Liu, Qinyu Chen
First submitted to arxiv on: 23 Sep 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 FACET, an end-to-end neural network that outputs pupil ellipse parameters from event data for real-time Extended Reality (XR) applications. This is achieved through a novel trigonometric loss and fast causal event volume representation method. Compared to the prior art EV-Eye, FACET reduces pixel error and inference time by 1.6 times and 1.8 times, respectively, with fewer parameters and arithmetic operations. The model is optimized for high accuracy, low latency, and power efficiency, making it suitable for XR applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new eye-tracking system called FACET that works fast and accurately in virtual reality settings. It uses special cameras to track the movement of your eyes and can do this quickly and efficiently. This is important because current systems struggle to meet these demands. The researchers used a lot of data to train their model, which performed well on tests. |
Keywords
» Artificial intelligence » Inference » Neural network » Tracking
