Patched-Based Swin Transformer Hyperprior for Learned Image Compression

We present a hybrid end-to-end learned image compression framework that combines a CNN-based variational autoencoder (VAE) with an efficient hierarchical Swin Transformer to address the limitations of existing entropy models in capturing global dependencies under computational constraints. Tradition...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Sibusiso B. Buthelezi, Jules R. Tapamo
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2025-12-01
Serier:	Journal of Imaging
Fag:	differentiable quantization module variational inference swin transformer hyperprior rate-distortion optimization latent variable modelling
Online adgang:	https://www.mdpi.com/2313-433X/12/1/12
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!