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...

Celý popis

Podrobná bibliografia

Vydané v:	Neurocomputing (Amsterdam) Ročník 633; s. 129814
Hlavní autori:	Yang, Xiaobao, Luo, Wei, Ning, Hailong, Zhang, Guorui, Sun, Wei, Ma, Sugang
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 07.06.2025
Predmet:	Diffusion model Generative model Image generation Unconditional generation Variational autoencoder Variational autoencoder Unconditional generation Diffusion model Image generation Generative model
ISSN:	0925-2312
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!