CCDM: Continuous Conditional Diffusion Models for Image Generation

Xin Ding

doi:10.1109/TMM.2026.3660128

CCDM: Continuous Conditional Diffusion Models for Image Generation

2026-02-03

0

PRE

AI

DOI：10.1109/TMM.2026.3660128

Original

Original request for help

Save

Abstract

En 中文

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 $64\times 64$ to $192\times 192$, 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.

Keywords:

Continuous conditional generative modeling

conditional diffusion models

continuous scalar conditions

CCDM: Continuous Conditional Diffusion Models for Image Generation

Abstract

Journal

Organization