ELMO: Enhanced Real-time LiDAR Motion Capture through Upsampling

• Published in: ACM transactions on graphics Vol. 43; no. 6; pp. 1 - 14
• Main Authors: Jang, Deok-Kyeong, Yang, Dongseok, Jang, Deok-Yun, Choi, Byeoli, Lee, Sung-Hee, Shin, Donghoon
• Format: Journal Article
• Language: English
• Published: New York, NY, USA ACM 19.12.2024
• Subjects: Animation; Computer graphics; Computing methodologies; Machine learning; Machine learning approaches; Motion capture; Motion processing; Neural networks; motion synthesis; deep learning; point cloud; character animation; motion capture

This paper introduces ELMO, a real-time upsampling motion capture framework designed for a single LiDAR sensor. Modeled as a conditional autoregressive transformer-based upsampling motion generator, ELMO achieves 60 fps motion capture from a 20 fps LiDAR point cloud sequence. The key feature of ELMO...