title: Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

authors: Jaehoon Hahm, Junho Lee, Sunghyun Kim, Joonseok Lee

year: 2023

doi: None

zotero: zotero://select/items/@hahmIsometricRepresentationLearning2023

---

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

Diffusion models have made remarkable progress in capturing and reproducing real-world data. Despite their success and further potential, however, their latent space, the core of diffusion models still remains underexplored. In fact, the latent spaces of existing diffusion models still do not perfectly align with the human perception, entangling multiple concepts in a distorted space. In this paper, we present \textit{Isometric Diffusion}, equipping a diffusion model with isometric representation learning to better reflect human intuition and understanding of visual data. Specifically, we propose a novel loss to promote isometry between the latent space and the data manifold, enabling a semantically clear and geometrically sound latent space. This approach allows smoother interpolation and more precise control over attributes directly in the latent space. Our extensive experiments demonstrate the effectiveness of Isometric Diffusion, marking a significant advance in aligning latent spaces with perceptual semantics. This work paves the way for fine-grained data generation and manipulation.