扩散模型的几何自编码器

Geometric Autoencoder for Diffusion Models

March 11, 2026

作者: Hangyu Liu, Jianyong Wang, Yutao Sun

cs.AI

摘要

潜扩散模型已在高清视觉生成领域确立了新的技术标杆。融合视觉基础模型的先验知识虽能提升生成效率，但现有潜空间设计仍多基于经验性方法。这些方案往往难以兼顾语义可分性、重建保真度与潜空间紧凑性。本文提出几何自编码器（GAE），这一理论驱动型框架系统性地解决了上述难题。通过分析多种对齐范式，GAE从视觉基础模型中构建出优化的低维语义监督目标，为自编码器提供指导。此外，我们采用潜归一化技术替代标准变分自编码器中限制性的KL散度，构建了专为扩散学习优化的稳定潜流形。为实现高强度噪声下的稳健重建，GAE引入了动态噪声采样机制。实验表明，GAE在ImageNet-1K 256×256基准测试中表现卓越：无需分类器无关指导时，仅80轮训练即达1.82的gFID指标，800轮后进一步降至1.31，显著超越现有最优方法。除生成质量外，GAE更在压缩率、语义深度与重建稳定性间建立了优越平衡。这些结果验证了我们的设计思路，为潜扩散建模提供了新范式。代码与模型已开源：https://github.com/freezing-index/Geometric-Autoencoder-for-Diffusion-Models。

English

Latent diffusion models have established a new state-of-the-art in high-resolution visual generation. Integrating Vision Foundation Model priors improves generative efficiency, yet existing latent designs remain largely heuristic. These approaches often struggle to unify semantic discriminability, reconstruction fidelity, and latent compactness. In this paper, we propose Geometric Autoencoder (GAE), a principled framework that systematically addresses these challenges. By analyzing various alignment paradigms, GAE constructs an optimized low-dimensional semantic supervision target from VFMs to provide guidance for the autoencoder. Furthermore, we leverage latent normalization that replaces the restrictive KL-divergence of standard VAEs, enabling a more stable latent manifold specifically optimized for diffusion learning. To ensure robust reconstruction under high-intensity noise, GAE incorporates a dynamic noise sampling mechanism. Empirically, GAE achieves compelling performance on the ImageNet-1K 256 times 256 benchmark, reaching a gFID of 1.82 at only 80 epochs and 1.31 at 800 epochs without Classifier-Free Guidance, significantly surpassing existing state-of-the-art methods. Beyond generative quality, GAE establishes a superior equilibrium between compression, semantic depth and robust reconstruction stability. These results validate our design considerations, offering a promising paradigm for latent diffusion modeling. Code and models are publicly available at https://github.com/freezing-index/Geometric-Autoencoder-for-Diffusion-Models.