Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling. In this work we conduct a systematic comparison and theoretical analysis of different approaches to learning conditional probability distributions with score-based diffusion models. In particular, we prove results which provide a theoretical justification for one of the most successful estimators of the conditional score. Moreover, we introduce a multi-speed diffusion framework, which leads to a new estimator for the conditional score, performing on par with previous state-of-the-art approaches. Our theoretical and experimental findings are accompanied by an open source library MSDiff which allows for application and further research of multi-speed diffusion models.
@article{arxiv.2111.13606,
title = {Conditional Image Generation with Score-Based Diffusion Models},
author = {Georgios Batzolis and Jan Stanczuk and Carola-Bibiane Schönlieb and Christian Etmann},
journal= {arXiv preprint arXiv:2111.13606},
year = {2021}
}