2 code implementations • 24 Aug 2023 • Justice Mason, Christine Allen-Blanchette, Nicholas Zolman, Elizabeth Davison, Naomi Ehrich Leonard
In many real-world settings, image observations of freely rotating 3D rigid bodies may be available when low-dimensional measurements are not.
no code implementations • 22 Aug 2023 • Christine Allen-Blanchette
In this work, we present a GAN-based video generation pipeline with a learned configuration space map and Hamiltonian neural network motion model, to learn a representation of the configuration space from data.
1 code implementation • 23 Sep 2022 • Justice Mason, Christine Allen-Blanchette, Nicholas Zolman, Elizabeth Davison, Naomi Leonard
In many real-world settings, image observations of freely rotating 3D rigid bodies, such as satellites, may be available when low-dimensional measurements are not.
no code implementations • 5 Dec 2020 • Christine Allen-Blanchette, Kostas Daniilidis
In both approaches, the underlying dynamics of the image sequence are modelled explicitly to disentangle them from the image representations.
no code implementations • 24 Oct 2020 • Christine Allen-Blanchette, Sushant Veer, Anirudha Majumdar, Naomi Ehrich Leonard
In this paper, we introduce a video prediction model where the equations of motion are explicitly constructed from learned representations of the underlying physical quantities.
1 code implementation • ICCV 2019 • Carlos Esteves, Yinshuang Xu, Christine Allen-Blanchette, Kostas Daniilidis
Several popular approaches to 3D vision tasks process multiple views of the input independently with deep neural networks pre-trained on natural images, achieving view permutation invariance through a single round of pooling over all views.
3 code implementations • ECCV 2018 • Carlos Esteves, Christine Allen-Blanchette, Ameesh Makadia, Kostas Daniilidis
We address the problem of 3D rotation equivariance in convolutional neural networks.
1 code implementation • ICLR 2018 • Carlos Esteves, Christine Allen-Blanchette, Xiaowei Zhou, Kostas Daniilidis
The result is a network invariant to translation and equivariant to both rotation and scale.