Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mixture-of-Gaussians-Guided Schedule Design for Brownian Bridge Diffusion Models

About

Brownian Bridge Diffusion Models (BBDM) offer an appealing framework for image restoration and inverse problems by constructing a stochastic bridge from the clean signal directly to the degraded observation, rather than to pure noise. Despite their promise, the choice of bridge schedule is typically inherited from heuristics, and a principled analytical framework for schedule design has been lacking. In this work, we develop such a framework by offering a novel analysis of BBDM reverse dynamics under a Mixture-of-Gaussians (MoG) prior. This setting yields a closed-form ideal posterior and a corresponding MMSE denoiser, while the BBDM-induced reconstruction law is captured analytically through a tractable surrogate. Building on these expressions, we formulate two complementary schedule-design objectives: a Wasserstein criterion targeting perceptual quality and an MSE criterion targeting reconstruction fidelity. Our work exposes an inherent tradeoff between the two and proves the existence of universal schedules for both that are independent of the degradation and prior. Extensive experiments on controlled MoG settings confirm full alignment between theory and practice, and experiments on the FFHQ dataset across inpainting, deblurring, and super-resolution tasks validate the practical value of our schedule-design criteria.

Ron Levi, Michael Elad• 2026

Related benchmarks

TaskDatasetResultRank
Image InpaintingFFHQ (test)
LPIPS0.067
97
Image Restoration (Deblurring)FFHQ
FID2.967
16
Super-ResolutionFFHQ 4x (test)
FID5.066
4
Super-ResolutionFFHQ 8x (test)
FID12.258
4
Showing 4 of 4 rows

Other info

Follow for update