Generalised Diffusion Probabilistic Scale-Spaces
This work addresses a theoretical gap for researchers in machine learning and image processing, though it is incremental as it builds on existing models without introducing new practical applications.
The paper tackles the lack of theoretical exploration in diffusion probabilistic models by proposing a generalized scale-space theory that connects them to classical image filtering, demonstrating conceptual and empirical links to diffusion and osmosis filters.
Diffusion probabilistic models excel at sampling new images from learned distributions. Originally motivated by drift-diffusion concepts from physics, they apply image perturbations such as noise and blur in a forward process that results in a tractable probability distribution. A corresponding learned reverse process generates images and can be conditioned on side information, which leads to a wide variety of practical applications. Most of the research focus currently lies on practice-oriented extensions. In contrast, the theoretical background remains largely unexplored, in particular the relations to drift-diffusion. In order to shed light on these connections to classical image filtering, we propose a generalised scale-space theory for diffusion probabilistic models. Moreover, we show conceptual and empirical connections to diffusion and osmosis filters.