Noise-Aware Hybrid Compression of Deep Models with Zero-Shot Denoising and Failure Prediction

Deep learning-based image compression achieves remarkable average rate-distortion performance but is prone to failure on noisy, high-frequency, or high-entropy inputs. This work systematically investigates these failure cases and proposes a noise-aware hybrid compression framework to address them. A...

Ausführliche Beschreibung

Gespeichert in:

Bibliografische Detailangaben
Hauptverfasser:	Lizhe Zhang, Quan Zhou, Ruihua Liu, Lang Huyan, Juanni Liu, Yi Zhang
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2025-12-01
Schriftenreihe:	Applied Sciences
Schlagworte:	noise-aware image compression high-frequency vulnerability index (HFVI) hybrid codec selector zero-shot denoising compression
Online-Zugang:	https://www.mdpi.com/2076-3417/15/24/12882
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!

Noise-Aware Hybrid Compression of Deep Models with Zero-Shot Denoising and Failure Prediction

Ähnliche Einträge