no code implementations • 19 Oct 2023 • Christopher Scarvelis, Haitz Sáez de Ocáriz Borde, Justin Solomon
In this work, we instead explicitly smooth the closed-form score to obtain an SGM that generates novel samples without training.
no code implementations • 18 May 2022 • Christopher Scarvelis, Justin Solomon
We introduce an optimal transport-based model for learning a metric tensor from cross-sectional samples of evolving probability measures on a common Riemannian manifold.
no code implementations • 24 Feb 2020 • Gabriel Rioux, Rustum Choksi, Tim Hoheisel, Pierre Marechal, Christopher Scarvelis
Image deblurring is a notoriously challenging ill-posed inverse problem.