NLIC: Non-Uniform Quantization-Based Learned Image Compression

In recent years, Learned Image Compression (LIC) has undergone rapid evolution. However, it is worthy noting that most prevalent LIC methodologies still rely on uniform Scalar Quantization (SQ) for latent features. This overlooks the untapped potential of contextual information, which could be lever...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on circuits and systems for video technology 2024-10, Vol.34 (10), p.9647-9663
Hauptverfasser:	Ge, Ziqing, Ma, Siwei, Gao, Wen, Pan, Jingshan, Jia, Chuanmin
Format:	Artikel
Sprache:	eng
Schlagworte:	Computational modeling Context modeling Entanglement Entropy Image coding Image compression Image enhancement Image reconstruction Modules neural image codec non-linear transformation non-uniform quantization Optimization Quantization (signal) Redundancy
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!