no code implementations • 14 Dec 2023 • Thomas W. Mitchel, Carlos Esteves, Ameesh Makadia
We introduce a framework for intrinsic latent diffusion models operating directly on the surfaces of 3D shapes, with the goal of synthesizing high-quality textures.
1 code implementation • 28 Jan 2022 • Thomas W. Mitchel, Noam Aigerman, Vladimir G. Kim, Michael Kazhdan
M\"obius transformations play an important role in both geometry and spherical image processing - they are the group of conformal automorphisms of 2D surfaces and the spherical equivalent of homographies.
1 code implementation • ICCV 2021 • Thomas W. Mitchel, Vladimir G. Kim, Michael Kazhdan
We present a novel surface convolution operator acting on vector fields that is based on a simple observation: instead of combining neighboring features with respect to a single coordinate parameterization defined at a given point, we have every neighbor describe the position of the point within its own coordinate frame.
no code implementations • 23 Jun 2020 • Thomas W. Mitchel, Benedict Brown, David Koller, Tim Weyrich, Szymon Rusinkiewicz, Michael Kazhdan
Fast methods for convolution and correlation underlie a variety of applications in computer vision and graphics, including efficient filtering, analysis, and simulation.
no code implementations • 21 Mar 2019 • Thomas W. Mitchel, Christian Wuelker, Jin Seob Kim, Sipu Ruan, Gregory S. Chirikjian
The foundation of this approach is a novel camera motion model that allows for real-world camera poses to be recovered directly from 3D motion fields.
no code implementations • 18 Jul 2018 • Thomas W. Mitchel, Sipu Ruan, Gregory S. Chirikjian
Here, we introduce a variant of GORA for humanoid action recognition with skeleton sequences, which we call GORA-S. We briefly review the algorithm's mathematical foundations and contextualize them in the problem of action recognition with skeleton sequences.