no code implementations • 7 Jul 2023 • Owen Howell, David Klee, Ondrej Biza, Linfeng Zhao, Robin Walters
We show that an algorithm that learns a three-dimensional representation of the world from two dimensional images must satisfy certain geometric consistency properties which we formulate as SO(2)-equivariance constraints.
no code implementations • 18 Jul 2022 • David Klee, Ondrej Biza, Robert Platt, Robin Walters
In this paper, we propose a novel architecture based on icosahedral group convolutions that reasons in $\mathrm{SO(3)}$ by learning a projection of the input image onto an icosahedron.
1 code implementation • 10 Feb 2022 • Ondrej Biza, Thomas Kipf, David Klee, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong
In this paper, we learn to generalize over robotic pick-and-place tasks using object-factored world models, which combat the combinatorial explosion by ensuring that predictions are equivariant to permutations of objects.