no code implementations • 13 Sep 2021 • Miguel Jaques, Martin Asenov, Michael Burke, Timothy Hospedales
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.
no code implementations • CVPR 2021 • Miguel Jaques, Michael Burke, Timothy Hospedales
Learning low-dimensional latent state space dynamics models has been a powerful paradigm for enabling vision-based planning and learning for control.
1 code implementation • ICLR 2020 • Miguel Jaques, Michael Burke, Timothy Hospedales
Our approach significantly outperforms related unsupervised methods in long-term future frame prediction of systems with interacting objects (such as ball-spring or 3-body gravitational systems), due to its ability to build dynamics into the model as an inductive bias.
1 code implementation • 20 Mar 2017 • Nick Pawlowski, Miguel Jaques, Ben Glocker
In this work we perform outlier detection using ensembles of neural networks obtained by variational approximation of the posterior in a Bayesian neural network setting.