cs.CVNov 18, 2026

Dual-Manifold Variational Autoencoders

Authors: Hongxu Chen, Chun Wang, Yanghao Wang, Hongxiang Li, Zhen Wang, Zhixiang Zhang, Long Chen

Organizations: The Hong Kong University of Science and Technology

Abstract

In latent diffusion models, expanding the latent dimension of variational autoencoders (VAEs) is essential to push the upper bound of reconstruction quality. However, without explicit structural constraints, such unregularized expansion easily yields a rugged and ill-conditioned latent manifold, causing generated latents to drift off the manifold during generation (i.e., off-manifold problem). Recent works smooth this manifold by using external foundation models (e.g., DINOv2) as a topological regularizer. However, we argue that tying the latent space to frozen external priors inherently restricts generalization: bound by their pre-training distributions and semantic biases, they may fail to capture faithful visual details on out-of-distribution domains. Observing that low-dimensional latents naturally form a smoother, generation-friendly manifold, we propose dual-manifold VAE (DM-VAE) to leverage internal representations as a topological regularizer. Specifically, DM-VAE pairs a high-dimensional reconstructive branch with a low-dimensional branch that extracts a clean topological skeleton, anchoring the high-dimensional manifold to this smooth subspace. Building upon this framework, we further introduce topological representation alignment (TRA) to supervise intermediate generator features during training, and internal guidance with topological skeleton (IG_TS) to guide structural components while preserving high-frequency details at inference. On ImageNet-1K (256x256), our foundation-model-free DM-VAE achieves a state-of-the-art rFID of 0.12 and a generation FID50K of 1.28 (w/o CFG) and 1.20 (w/CFG), and further reaches 1.11 when orthogonally combined with DINOv2.

Figures & tables

Explore similar work

CardsList
  1. Distribution Matching Variational AutoEncoder

    Dec 8, 2025Sen Ye, Jianning Pei, Mengde Xu +4Variational AutoencodersGenerative Modeling

  2. Geometric Autoencoder for Diffusion Models

    Mar 11, 2026Hangyu Liu, Jianyong Wang, Yutao SunLatent Diffusion ModelsDiffusion Models

  3. Improved Baselines with Representation Autoencoders

    May 18, 2026Jaskirat Singh, Boyang Zheng, Zongze Wu +3Diffusion Model GuidanceDiffusion Transformer