Enhancing Diffusion-Based Quantitatively Controllable Image Generation via Matrix-Form EDM and Adaptive Vicinal Training

TL;DR

This paper introduces iCCDM, an improved diffusion-based image generation framework that combines matrix-form EDM and adaptive vicinal training, leading to higher quality images and faster sampling compared to previous methods.

Contribution

The paper presents a novel iCCDM framework that integrates matrix-form EDM and adaptive vicinal training to enhance image quality and sampling efficiency in continuous conditional diffusion models.

Findings

iCCDM outperforms existing diffusion and GAN-based methods on benchmark datasets.

iCCDM achieves higher image quality with reduced sampling cost.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Continuous Conditional Diffusion Model (CCDM) is a diffusion-based framework designed to generate high-quality images conditioned on continuous regression labels. Although CCDM has demonstrated clear advantages over prior approaches across a range of datasets, it still exhibits notable limitations and has recently been surpassed by a GAN-based method, namely CcGAN-AVAR. These limitations mainly arise from its reliance on an outdated diffusion framework and its low sampling efficiency due to long sampling trajectories. To address these issues, we propose an improved CCDM framework, termed iCCDM, which incorporates the more advanced \textit{Elucidated Diffusion Model} (EDM) framework with substantial modifications to improve both generation quality and sampling efficiency. Specifically, iCCDM introduces a novel matrix-form EDM formulation together with an adaptive vicinal training strategy. Extensive experiments on four benchmark datasets, spanning image resolutions from $64\times64$ to $256\times256$, demonstrate that iCCDM consistently outperforms existing methods, including state-of-the-art large-scale text-to-image diffusion models (e.g., Stable Diffusion 3, FLUX.1, and Qwen-Image), achieving higher generation quality while significantly reducing sampling cost.