用热扩散机制增强像素间关联，提升图像生成细节质量
Heat Diffusion Models -- Interpixel Attention Mechanism
- 引入二维热方程建模像素间关系，改进扩散过程
- 在多个数据集上生成图像质量优于DDPM、LDM等主流模型
- 适合需要高保真细节生成的视觉任务
去噪扩散概率模型（DDPM）将图像视为整体进行处理。由于相邻像素很可能属于同一物体，本文提出热扩散模型（HDM），以进一步保留图像细节并生成更真实的图像。HDM本质上是一种融合像素间注意力机制的DDPM，将二维热方程的离散形式融入DDPM的扩散与生成公式中，使模型在图像处理过程中能够计算邻近像素间的关联关系。实验表明，与DDPM、一致性扩散模型（CDM）、潜在扩散模型（LDM）以及向量量化生成对抗网络（VQGAN）相比，HDM能生成更高品质的样本。
原文摘要 · Abstract (English)
Denoising Diffusion Probabilistic Models (DDPM) process images as a whole. Since adjacent pixels are highly likely to belong to the same object, we propose the Heat Diffusion Model (HDM) to further preserve image details and generate more realistic images. HDM essentially is a DDPM that incorporates an attention mechanism between pixels. In HDM, the discrete form of the two-dimensional heat equation is integrated into the diffusion and generation formulas of DDPM, enabling the model to compute relationships between neighboring pixels during image processing. Our experiments demonstrate that HDM can generate higher-quality samples compared to models such as DDPM, Consistency Diffusion Models (CDM), Latent Diffusion Models (LDM), and Vector Quantized Generative Adversarial Networks (VQGAN).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。