Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_cv 96% Match Research Paper AI Researchers,Machine Learning Engineers,Computer Vision Practitioners,Generative Model Developers 2 weeks ago

Latent Diffusion Models with Masked AutoEncoders

computer-vision › diffusion-models
📄 Abstract

Abstract: In spite of the remarkable potential of Latent Diffusion Models (LDMs) in image generation, the desired properties and optimal design of the autoencoders have been underexplored. In this work, we analyze the role of autoencoders in LDMs and identify three key properties: latent smoothness, perceptual compression quality, and reconstruction quality. We demonstrate that existing autoencoders fail to simultaneously satisfy all three properties, and propose Variational Masked AutoEncoders (VMAEs), taking advantage of the hierarchical features maintained by Masked AutoEncoders. We integrate VMAEs into the LDM framework, introducing Latent Diffusion Models with Masked AutoEncoders (LDMAEs). Our code is available at https://github.com/isno0907/ldmae.
Authors (4)
Junho Lee
Jeongwoo Shin
Hyungwook Choi
Joonseok Lee
Submitted
July 14, 2025
arXiv Category
cs.CV
arXiv PDF Code

Key Contributions

This paper analyzes the crucial role of autoencoders in Latent Diffusion Models (LDMs) and identifies key properties (latent smoothness, perceptual compression, reconstruction quality). It proposes Variational Masked Autoencoders (VMAEs), which leverage hierarchical features from Masked Autoencoders, to address the limitations of existing autoencoders and improve LDM performance.

Business Value

Leads to more efficient and higher-quality image generation systems, benefiting applications in digital art, content creation, and synthetic data generation. Improved latent space representations can also aid in downstream tasks.

View Code on GitHub