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...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Lizhe Zhang, Quan Zhou, Ruihua Liu, Lang Huyan, Juanni Liu, Yi Zhang
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	MDPI AG 2025-12-01
Цуврал:	Applied Sciences
Нөхцлүүд:	noise-aware image compression high-frequency vulnerability index (HFVI) hybrid codec selector zero-shot denoising compression
Онлайн хандалт:	https://www.mdpi.com/2076-3417/15/24/12882
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!