Conditional Simulation Using Diffusion Schr\"odinger Bridges - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Conditional Simulation Using Diffusion Schr\"odinger Bridges

Yuyang Shi
  • Fonction : Auteur
Valentin de Bortoli
  • Fonction : Auteur
  • PersonId : 1084097
  • IdRef : 249460300
George Deligiannidis
  • Fonction : Auteur
Arnaud Doucet
  • Fonction : Auteur

Résumé

Denoising diffusion models have recently emerged as a powerful class of generative models. They provide state-of-the-art results, not only for unconditional simulation, but also when used to solve conditional simulation problems arising in a wide range of inverse problems. A limitation of these models is that they are computationally intensive at generation time as they require simulating a diffusion process over a long time horizon. When performing unconditional simulation, a Schr\"odinger bridge formulation of generative modeling leads to a theoretically grounded algorithm shortening generation time which is complementary to other proposed acceleration techniques. We extend the Schr\"odinger bridge framework to conditional simulation. We demonstrate this novel methodology on various applications including image super-resolution, optimal filtering for state-space models and the refinement of pre-trained networks. Our code can be found at https://github.com/vdeborto/cdsb.

Dates et versions

hal-03945479 , version 1 (18-01-2023)

Identifiants

Citer

Yuyang Shi, Valentin de Bortoli, George Deligiannidis, Arnaud Doucet. Conditional Simulation Using Diffusion Schr\"odinger Bridges. 2023. ⟨hal-03945479⟩
9 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More