Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

TL;DR

This paper introduces Isometric Diffusion, a method that adds a geometric regularizer to diffusion models to learn a more disentangled and geometrically meaningful latent space, improving interpolation, inversion, and attribute control.

Contribution

It proposes a novel geometric regularizer for diffusion models to achieve a more disentangled and geometrically sound latent space, which was previously unexplored.

Findings

Enhanced image interpolation quality

More accurate image inversion results

Improved attribute control in latent space

Abstract

The latent space of diffusion model mostly still remains unexplored, despite its great success and potential in the field of generative modeling. In fact, the latent space of existing diffusion models are entangled, with a distorted mapping from its latent space to image space. To tackle this problem, we present Isometric Diffusion, equipping a diffusion model with a geometric regularizer to guide the model to learn a geometrically sound latent space of the training data manifold. This approach allows diffusion models to learn a more disentangled latent space, which enables smoother interpolation, more accurate inversion, and more precise control over attributes directly in the latent space. Our extensive experiments consisting of image interpolations, image inversions, and linear editing show the effectiveness of our method.