DiffuseVAE++: Mitigating training-sampling mismatch based on additional noise for higher fidelity image generation

Denoising Diffusion Probabilistic Models (DDPMs) have demonstrated remarkable results in image generation. However, there exist a mismatch between the training and sampling process in current diffusion models, in addition, the U-Net denoising network based on simple residual blocks cannot predict no...

Full description

Bibliographic Details

Published in:	Neurocomputing (Amsterdam) Vol. 633; p. 129814
Main Authors:	Yang, Xiaobao, Luo, Wei, Ning, Hailong, Zhang, Guorui, Sun, Wei, Ma, Sugang
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 07.06.2025
Subjects:	Diffusion model Generative model Image generation Unconditional generation Variational autoencoder Variational autoencoder Unconditional generation Diffusion model Image generation Generative model
ISSN:	0925-2312
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!