Generalised Scale-Space Properties for Probabilistic Diffusion Models
This work provides theoretical insights into diffusion models for researchers, but it is incremental as it connects existing concepts without introducing new methods or applications.
The paper investigates probabilistic diffusion models from a scale-space perspective, showing they fulfill generalized scale-space properties on evolving probability distributions, and discusses similarities and differences with drift-diffusion interpretations and osmosis filters.
Probabilistic diffusion models enjoy increasing popularity in the deep learning community. They generate convincing samples from a learned distribution of input images with a wide field of practical applications. Originally, these approaches were motivated from drift-diffusion processes, but these origins find less attention in recent, practice-oriented publications. We investigate probabilistic diffusion models from the viewpoint of scale-space research and show that they fulfil generalised scale-space properties on evolving probability distributions. Moreover, we discuss similarities and differences between interpretations of the physical core concept of drift-diffusion in the deep learning and model-based world. To this end, we examine relations of probabilistic diffusion to osmosis filters.