4 papers
From 3D Pose to Prose: Biomechanics-Grounded Vision--Language Coaching
Yuyang Ji, Yixuan Shen, Shengjie Zhu +2
We present BioCoach, a biomechanics-grounded vision--language framework for fitness coaching from streaming video. BioCoach fuses visual appearance and 3D skeletal kinematics, thro…
Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimates
Shengjie Zhu, Ahmed Abdelkader, Mark J. Matthews +2
Structure-from-Motion (SfM) is a fundamental 3D vision task for recovering camera parameters and scene geometry from multi-view images. While recent deep learning advances enable a…
Revisit Self-supervised Depth Estimation with Local Structure-from-Motion
Shengjie Zhu, Xiaoming Liu
Both self-supervised depth estimation and Structure-from-Motion (SfM) recover scene depth from RGB videos. Despite sharing a similar objective, the two approaches are disconnected.…
RePLAy: Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry
Shengjie Zhu, Girish Chandar Ganesan, Abhinav Kumar +1
3D sensing is a fundamental task for Autonomous Vehicles. Its deployment often relies on aligned RGB cameras and LiDAR. Despite meticulous synchronization and calibration, systemat…