Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
Abstract
Diffusion probabilistic models (DPMs) have achieved remarkable quality in image generation that rivals GANs'. But unlike GANs, DPMs use a set of latent variables that lack semantic meaning and cannot serve as a useful representation for other tasks. This paper explores the possibility of using DPMs for representation learning and seeks to extract a meaningful and decodable representation of an input image via autoencoding. Our key idea is to use a learnable encoder for discovering the high-level semantics, and a DPM as the decoder for modeling the remaining stochastic variations. Our method can encode any image into a two-part latent code, where the first part is semantically meaningful and linear, and the second part captures stochastic details, allowing near-exact reconstruction. This capability enables challenging applications that currently foil GAN-based methods, such as attribute manipulation on real images. We also show that this two-level encoding improves denoising efficiency and naturally facilitates various downstream tasks including few-shot conditional sampling. Please visit our project page: https://Diff-AE.github.io/
Cite
@article{arxiv.2111.15640,
title = {Diffusion Autoencoders: Toward a Meaningful and Decodable Representation},
author = {Konpat Preechakul and Nattanat Chatthee and Suttisak Wizadwongsa and Supasorn Suwajanakorn},
journal= {arXiv preprint arXiv:2111.15640},
year = {2022}
}
Comments
Please visit our project page: https://Diff-AE.github.io/