Summary of Hisc4d: Human-centered Interaction and 4d Scene Capture in Large-scale Space Using Wearable Imus and Lidar, by Yudi Dai et al.
HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR
by Yudi Dai, Zhiyong Wang, Xiping Lin, Chenglu Wen, Lan Xu, Siqi Shen, Yuexin Ma, Cheng Wang
First submitted to arxiv on: 6 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Graphics (cs.GR); Multimedia (cs.MM)
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 novel HiSC4D method accurately and efficiently creates a dynamic digital world, capturing large-scale indoor-outdoor scenes, human motions, and interactions. This is achieved by using body-mounted IMUs and head-mounted LiDAR to capture egocentric human motions in unconstrained space without external devices or pre-built maps. The joint optimization method harmonizes sensor data and environment cues, yielding promising results for long-term capture in large scenes. A dataset of 8 sequences in 4 large scenes is presented, providing SMPL annotations and dynamic scene information. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary HiSC4D is a new way to create a digital world that shows how people move and interact with each other and their environment. It uses special sensors on the body and head to capture this data without needing any extra equipment or maps. This makes it flexible and accessible for use in different settings. The team also created a dataset of 8 sequences in 4 large scenes, which includes information about human movements, environment, and interactions. |
Keywords
» Artificial intelligence » Optimization
