Conditional Image Synthesis with Diffusion Models: A Survey

Zheyuan Zhan, Defang Chen, Jian-Ping Mei, Zhenghe Zhao, Jiawei Chen, Chun Chen, Siwei Lyu, Can Wang

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, 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.

Certifications: Survey Certification

Submission Length: Long submission (more than 12 pages of main content)

Changes Since Last Submission: We have thoroughly reviewed the entire manuscript to correct typographical and grammatical errors and refined the overall language for improved clarity and academic rigor. In addition, we have added a new subsection, 5.6 Unified Conditional Synthesis Framework, to the Challenges and Future Directions section. This new content highlights the emerging potential of leveraging state-of-the-art Multimodal Large Language Models (MLLMs) to build unified conditional synthesis models that can seamlessly integrate diverse control signals.

Assigned Action Editor: ~Robert_Legenstein1

Submission Number: 3658