Unified Framework for Diffusion Generative Models in SO(3): Applications in Computer Vision and Astrophysics
DOI:
https://doi.org/10.1609/aaai.v38i11.29171Keywords:
ML: Learning with Manifolds, APP: Natural Sciences, APP: Other Applications, CV: Applications, CV: Vision for Robotics & Autonomous Driving, ML: Bayesian Learning, ML: Deep Generative Models & AutoencodersAbstract
Diffusion-based generative models represent the current state-of-the-art for image generation. However, standard diffusion models are based on Euclidean geometry and do not translate directly to manifold-valued data. In this work, we develop extensions of both score-based generative models (SGMs) and Denoising Diffusion Probabilistic Models (DDPMs) to the Lie group of 3D rotations, SO(3). SO(3) is of particular interest in many disciplines such as robotics, biochemistry and astronomy/cosmology science. Contrary to more general Riemannian manifolds, SO(3) admits a tractable solution to heat diffusion, and allows us to implement efficient training of diffusion models. We apply both SO(3) DDPMs and SGMs to synthetic densities on SO(3) and demonstrate state-of-the-art results. Additionally, we demonstrate the practicality of our model on pose estimation tasks and in predicting correlated galaxy orientations for astrophysics/cosmology.Downloads
Published
2024-03-24
How to Cite
Jagvaral, Y., Lanusse, F., & Mandelbaum, R. (2024). Unified Framework for Diffusion Generative Models in SO(3): Applications in Computer Vision and Astrophysics. Proceedings of the AAAI Conference on Artificial Intelligence, 38(11), 12754-12762. https://doi.org/10.1609/aaai.v38i11.29171
Issue
Section
AAAI Technical Track on Machine Learning II