Motion Capture
Motion capture (MoCap) aims to record and reconstruct human movement, primarily for applications in animation, virtual reality, and human-computer interaction. Current research emphasizes developing robust and efficient MoCap systems using diverse sensor modalities, including cameras (both multi-view and egocentric), inertial measurement units (IMUs), and even smartwatches, often incorporating deep learning models like transformers and diffusion models for pose estimation and motion synthesis. These advancements are driving progress in areas such as human-object interaction modeling, ergonomic analysis in industrial settings, and the creation of realistic digital avatars for immersive experiences, impacting fields ranging from healthcare to entertainment.
Papers
Markerless 3D human pose tracking through multiple cameras and AI: Enabling high accuracy, robustness, and real-time performance
Luca Fortini, Mattia Leonori, Juan M. Gandarias, Elena de Momi, Arash Ajoudani
CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
Ming Yan, Xin Wang, Yudi Dai, Siqi Shen, Chenglu Wen, Lan Xu, Yuexin Ma, Cheng Wang
Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild
Gyeongsik Moon
3D-POP -- An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion capture
Hemal Naik, Alex Hoi Hang Chan, Junran Yang, Mathilde Delacoux, Iain D. Couzin, Fumihiro Kano, Máté Nagy