Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
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.
Code (1)
Tasks
Representation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation
Diffusion models have attained impressive visual quality for image synthesis. However, how to interpret and manipulate the latent space of diffusion models has not been extensively explored. Prior work diffusion autoenco…
Image GenerationImage ManipulationImage ReconstructionDisentanglement with Hyperspherical Latent Spaces using Diffusion Variational Autoencoders
A disentangled representation of a data set should be capable of recovering the underlying factors that generated it. One question that arises is whether using Euclidean space for latent variable models can produce a dis…
DisentanglementDisentanglement with Hyperspherical Latent Spaces using Diffusion Variational Autoencoders
A disentangled representation of a data set should be capable of recovering the underlying factors that generated it. One question that arises is whether using Euclidean space for latent variable models can produce a dis…
DisentanglementInfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models
While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning. Here, we propose InfoDiffusion, an algorithm that …
Representation LearningBoosting Latent Diffusion Models via Disentangled Representation Alignment
Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attempted to obtain generation-friendly VAEs b…
Image Generation