Summary of Monocular Expressive Body Regression Through Body-driven Attention, by Vasileios Choutas et al.
Monocular Expressive Body Regression through Body-Driven Attention
by Vasileios Choutas, Georgios Pavlakos, Timo Bolkart, Dimitrios Tzionas, Michael J. Black
First submitted to arxiv on: 20 Aug 2020
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Graphics (cs.GR)
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 introduces ExPose, a novel approach to estimating expressive 3D humans from RGB images. Unlike existing methods that focus on specific parts of the body, ExPose directly regresses the entire human form in SMPL-X format. The method addresses limitations in optimization-based approaches by being faster and more accurate. Key innovations include curating a dataset of SMPL-X fits on in-the-wild images to account for data scarcity, introducing body-driven attention for face and hand regions, and exploiting part-specific knowledge from existing datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary ExPose is a new way to understand how people look, interact, or perform tasks by quickly capturing their 3D bodies, faces, and hands. Most methods focus on just one part of the body. ExPose does it all! It uses special computer vision techniques to make very accurate predictions from just an RGB image. This is important because we need better ways to understand human behavior and movement. |
Keywords
» Artificial intelligence » Attention » Optimization
