BriefGPT.xyz
Apr, 2025
基于热扩散模型的图像生成方法
Image Generation Method Based on Heat Diffusion Models
HTML
PDF
Pengfei Zhang, Shouqing Jia
TL;DR
本研究解决了当前图像生成方法在细节保留方面的不足，提出了一种热扩散模型（HDM），该模型结合了像素级操作的优势，同时保持与去噪扩散概率模型（DDPM）相同的训练过程。实验表明，HDM在图像生成质量上优于现有的主流模型，如DDPM和一致性扩散模型（CDM）。
Abstract
Denoising Diffusion Probabilistic Models
(DDPMs) achieve high-quality
Image Generation
without adversarial training, but they process images as a whole. Since adjacent pixels are highly likely to belong to the sa
→