CCDM: Continuous Conditional Diffusion Models for Image Generation

TL;DR

This paper introduces Continuous Conditional Diffusion Models (CCDMs), a novel approach tailored for high-dimensional data conditioned on continuous variables, outperforming existing methods like CcGANs in image generation tasks.

Contribution

The paper develops the first CDM specifically designed for continuous conditional generative modeling, with new diffusion processes, loss functions, and sampling methods optimized for this task.

Findings

CCDMs outperform state-of-the-art CCGMs on multiple datasets.

The proposed methods establish a new benchmark in continuous conditional image generation.

Ablation studies confirm the effectiveness of the model components.

Abstract

Continuous Conditional Generative Modeling (CCGM) estimates high-dimensional data distributions, such as images, conditioned on scalar continuous variables (aka regression labels). While Continuous Conditional Generative Adversarial Networks (CcGANs) were designed for this task, their instability during adversarial learning often leads to suboptimal results. Conditional Diffusion Models (CDMs) offer a promising alternative, generating more realistic images, but their diffusion processes, label conditioning, and model fitting procedures are either not optimized for or incompatible with CCGM, making it difficult to integrate CcGANs' vicinal approach. To address these issues, we introduce Continuous Conditional Diffusion Models (CCDMs), the first CDM specifically tailored for CCGM. CCDMs address existing limitations with specially designed conditional diffusion processes, a novel hard vicinal image denoising loss, a customized label embedding method, and efficient conditional sampling procedures. Through comprehensive experiments on four datasets with resolutions ranging from 64x64 to 192x192, we demonstrate that CCDMs outperform state-of-the-art CCGM models, establishing a new benchmark. Ablation studies further validate the model design and implementation, highlighting that some widely used CDM implementations are ineffective for the CCGM task. Our code is publicly available at https://github.com/UBCDingXin/CCDM.