Summary of Shallow Signed Distance Functions For Kinematic Collision Bodies, by Osman Akar et al.
Shallow Signed Distance Functions for Kinematic Collision Bodies
by Osman Akar, Yushan Han, Yizhou Chen, Weixian Lan, Benn Gallagher, Ronald Fedkiw, Joseph Teran
First submitted to arxiv on: 11 Nov 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 The paper proposes learning-based implicit shape representations for real-time avatar collision queries in clothing simulation. It aims to improve upon existing methods, such as signed distance functions (SDFs) and deep neural networks (DeepSDFs), which are computationally expensive. The authors design a novel representation that uses shallow neural networks to model localized deformations caused by joint-based skinning, requiring a stitching process to combine the individual SDFs into one representing the entire body. This approach is demonstrated to be fast and accurate in real-time garment simulation driven by animated characters. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates new ways to show computer-generated characters (avatars) in clothes that look realistic and move naturally. It uses special math formulas called signed distance functions (SDFs) that help computers quickly find where avatars and clothing touch. The authors are trying to make these SDFs work better for 3D animations of people wearing clothes. They do this by breaking the avatar into smaller parts, modeling how each part moves separately, and then putting it all together again. |
