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.

Probabilistic diffusion 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 probabilistic diffusion models. Moreover, we show conceptual and empirical connections to diffusion and osmosis filters.

If Netflix's new Dating Around reality series is a touch too maudlin for your taste, then you'll probably dig its upcoming French original Osmosis. The first trailer for the technophobic show, which premieres March 29th, just landed and it's a literal head trip. Set in a near future, it follows several young Parisians who sign up to a beta program for an experimental dating technology designed to pair up soul mates. The clip shows the eager participants pop a pill like Neo in The Matrix (which turns 20 next month). But instead of taking back their life from a machine-dominated simulation, it puts their romantic fate in the hands of an AI named Martin.

One of the great things about Netflix's global expansion is that it allows audiences to enjoy new movies and TV shows that have been produced in other countries. French subscribers, for example, saw their first local original -- Marseille -- debut around this time last year. Today, as part of a wider statement confirming the creation of 400 new European jobs, Netflix announced that it has greenlit its second French-language TV series, Osmosis. Judging by the show's synopsis, fans of Charlie Brooker's Black Mirror could be in for a treat. Netflix says its new original will be an 8-episode drama set in Paris in the near future. It's centered around a new dating app called "Osmosis," which is capable of reading its users' thoughts and feelings -- or brain data -- to "find a perfect match with 100 percent accuracy."