ANFIC: Image Compression Using Augmented Normalizing Flows
This paper introduces an end-to-end learned image compression system, termed ANFIC, based on Augmented Normalizing Flows (ANF). ANF is a new type of flow model, which stacks multiple variational autoencoders (VAE) for greater model expressiveness. The VAE-based image compression has gone mainstream,...
Guardado en:
Autores principales: | Yung-Han Ho, Chih-Chun Chan, Wen-Hsiao Peng, Hsueh-Ming Hang, Marek Domanski |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
IEEE
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/c929fe6d235b4cfdaefe91c5b076a3cc |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Learned Image Compression With Separate Hyperprior Decoders
por: Zhao Zan, et al.
Publicado: (2021) -
Rate-Distortion Optimized Encoding for Deep Image Compression
por: Michael Schafer, et al.
Publicado: (2021) -
End-to-End Compression Towards Machine Vision: Network Architecture Design and Optimization
por: Shurun Wang, et al.
Publicado: (2021) -
REDUCCIÓN DE LOS TIEMPOS DE ADQUISICIÓN DE IMÁGENES POR RESONANCIA MAGNÉTICA UTILIZANDO TÉCNICAS DE COMPRESSED SENSING
por: Sing-Long C,Carlos, et al.
Publicado: (2009) -
Guest Editorial Circuits and Systems for Flexible Electronics
por: Lian Yong, et al.
Publicado: (2021)