Conditional Image Generation with Score-Based Diffusion Models

11/26/2021
by   Georgios Batzolis, et al.
0

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.

READ FULL TEXT

page 1

page 6

page 7

page 8

page 11

page 17

page 18

page 19

research
07/20/2022

Non-Uniform Diffusion Models

Diffusion models have emerged as one of the most promising frameworks fo...
research
08/25/2022

Understanding Diffusion Models: A Unified Perspective

Diffusion models have shown incredible capabilities as generative models...
research
03/14/2023

Interpretable ODE-style Generative Diffusion Model via Force Field Construction

For a considerable time, researchers have focused on developing a method...
research
03/08/2023

Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation

Score-based diffusion models (SBDM) have recently emerged as state-of-th...
research
03/16/2023

Efficient Diffusion Training via Min-SNR Weighting Strategy

Denoising diffusion models have been a mainstream approach for image gen...
research
08/09/2023

Do Diffusion Models Suffer Error Propagation? Theoretical Analysis and Consistency Regularization

While diffusion models have achieved promising performances in data synt...
research
06/30/2023

Practical and Asymptotically Exact Conditional Sampling in Diffusion Models

Diffusion models have been successful on a range of conditional generati...

Please sign up or login with your details

Forgot password? Click here to reset