Get Started
Research questionHow can we accurately track an athlete’s 3D center of mass from a single phone camera?A single camera provides incomplete depth and pose information, while standard 3D tracking may not represent the anatomical mass distribution needed for center-of-mass estimation. Systems accurate enough for movement analysis can also require computation or capture infrastructure unavailable during training and competition.
Computer Vision
Image & Video Processing
Small / On-device Models
Latest papersRecent research connected to this question, newest first.MuyBridge: Mobile Human Center-of-Mass Estimation from Monocular Video via Sparse FusionThe evidence concerns segmental center-of-mass estimation from a single phone-camera stream using anatomical and physical priors, one-time calibration, and no 3D or task-specific supervision. Evaluation covers running, track and field, and figure skating in AthletePose3D, with on-device results reported on an iPhone 15.research paper · Sep 2, 2026
Related questions
How can athletes be localized in world coordinates from a single ultra-high-resolution calibrated broadcast frame?How can dynamic human bodies be reconstructed from monocular video faster without sacrificing rendering quality?How can inertial measurements recover metric scale in pretrained monocular 3D predictions?How can ground-to-satellite localization bridge severe viewpoint gaps without 3D lifting or depth models?
Home
Topics
Search
Library