Timezone: »

 
Vision-based system identification and 3D keypoint discovery using dynamics constraints
Miguel Jaques · Martin Asenov · Michael Burke · Timothy Hospedales

Tue Dec 14 10:50 AM -- 11:00 AM (PST) @
in Physical Reasoning and Inductive Biases for the Real World »

This paper introduces V-SysId, a novel method that enables simultaneous keypoint discovery, 3D system identification, and extrinsic camera calibration from an unlabeled video taken from a static camera, using only the family of equations of motion of the object of interest as weak supervision. V-SysId takes keypoint trajectory proposals and alternates between maximum likelihood parameter estimation and extrinsic camera calibration, before applying a suitable selection criterion to identify the track of interest. This is then used to train a keypoint tracking model using supervised learning. Results on a range of settings (robotics, physics, physiology) highlight the utility of this approach.

Author Information

Miguel Jaques (University of Edinburgh)
Martin Asenov (The University of Edinburgh)
Michael Burke (Monash University)
Timothy Hospedales (University of Edinburgh)

More from the Same Authors