Vision-based system identification and 3D keypoint discovery using dynamics constraints
arXiv:2109.05928
Abstract
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.
References in corpus (10)
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- SfM-Net: Learning of Structure and Motion from Video
- Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
- Unsupervised Learning of Object Keypoints for Perception and Control
- Unsupervised Learning of Object Landmarks through Conditional Image Generation
- gradSim: Differentiable simulation for system identification and visuomotor control
- Scalable Differentiable Physics for Learning and Control
- Unsupervised Learning of Object Structure and Dynamics from Videos
- Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from Video
- Vid2Param: Modelling of Dynamics Parameters from Video