Conditional Image Synthesis with Diffusion Models: A Survey

TL;DR

This survey reviews recent advances in diffusion-based models for conditional image synthesis, categorizing conditioning mechanisms, discussing core principles, and highlighting challenges and future directions.

Contribution

It provides a comprehensive categorization and analysis of conditioning methods in diffusion models, clarifying their principles, advantages, and challenges in conditional image synthesis.

Findings

Categorization of conditioning mechanisms during training and sampling

Analysis of principles and advantages of different conditioning approaches

Identification of unresolved challenges and future research directions

Abstract

Conditional image synthesis based on user-specified requirements is a key component in creating complex visual content. In recent years, diffusion-based generative modeling has become a highly effective way for conditional image synthesis, leading to exponential growth in the literature. However, the complexity of diffusion-based modeling, the wide range of image synthesis tasks, and the diversity of conditioning mechanisms present significant challenges for researchers to keep up with rapid developments and to understand the core concepts on this topic. In this survey, we categorize existing works based on how conditions are integrated into the two fundamental components of diffusion-based modeling, $\textit{i.e.}$, the denoising network and the sampling process. We specifically highlight the underlying principles, advantages, and potential challenges of various conditioning approaches during the training, re-purposing, and specialization stages to construct a desired denoising network. We also summarize six mainstream conditioning mechanisms in the sampling process. All discussions are centered around popular applications. Finally, we pinpoint several critical yet still unsolved problems and suggest some possible solutions for future research. Our reviewed works are itemized at https://github.com/zju-pi/Awesome-Conditional-Diffusion-Models.