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...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neurocomputing (Amsterdam) Jg. 633; S. 129814
Hauptverfasser:	Yang, Xiaobao, Luo, Wei, Ning, Hailong, Zhang, Guorui, Sun, Wei, Ma, Sugang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier B.V 07.06.2025
Schlagworte:	Diffusion model Generative model Image generation Unconditional generation Variational autoencoder Variational autoencoder Unconditional generation Diffusion model Image generation Generative model
ISSN:	0925-2312
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!