Year: 2025
Type: preprint
Abstract: Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$β$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with recovering large-scale image structures and low noise levels with recovering details, this configuration can result in low-quality and blurry images. However, it should be possible to improve details while spending fewer steps recovering structures because the latent code should already contain structural information. Based on this insight, we propose a new DAE training method that improves the quality of reconstructed images. We divide training into two phases. In the first phase, the DAE is trained as a vanilla autoencoder by always setting the noise level to the highest, forcing the encoder and decoder to populate the latent code with structural information. In the second phase, we incorporate a noise schedule that spends more time in the low-noise region, allowing the DAE to learn how to perfect the details. Our method results in images that have accurate high-level structures and low-level details while still preserving useful properties of the latent codes.
Source: arXiv (Cornell University)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417522671
Cites:
Cited by:
Related to: