HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Hantang, Zhu, Qiang, Meng, Xiandong, Xiong, Lei, Zhu, Shuyuan, Fan, Xiaopeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918493154181120
author Li, Hantang
Zhu, Qiang
Meng, Xiandong
Xiong, Lei
Zhu, Shuyuan
Fan, Xiaopeng
author_facet Li, Hantang
Zhu, Qiang
Meng, Xiandong
Xiong, Lei
Zhu, Shuyuan
Fan, Xiaopeng
contents In practical applications, low-light images are often compressed for efficient storage and transmission. Most existing methods disregard compression artifacts removal or hardly establish a unified framework for joint task enhancement of low-light images with varying compression qualities. To address this problem, we propose an efficient hybrid priors-guided network (HPGN) that enhances compressed low-light images by integrating both compression and illumination priors. Our approach fully utilizes the JPEG quality factor (QF) and DCT quantization matrix (QM) to guide the design of efficient plug-and-play modules for joint tasks. Additionally, we employ a random QF generation strategy to guide model training, enabling a single model to enhance low-light images with different compression levels. Experimental results demonstrate the superiority of our proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02373
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement
Li, Hantang
Zhu, Qiang
Meng, Xiandong
Xiong, Lei
Zhu, Shuyuan
Fan, Xiaopeng
Image and Video Processing
Computer Vision and Pattern Recognition
In practical applications, low-light images are often compressed for efficient storage and transmission. Most existing methods disregard compression artifacts removal or hardly establish a unified framework for joint task enhancement of low-light images with varying compression qualities. To address this problem, we propose an efficient hybrid priors-guided network (HPGN) that enhances compressed low-light images by integrating both compression and illumination priors. Our approach fully utilizes the JPEG quality factor (QF) and DCT quantization matrix (QM) to guide the design of efficient plug-and-play modules for joint tasks. Additionally, we employ a random QF generation strategy to guide model training, enabling a single model to enhance low-light images with different compression levels. Experimental results demonstrate the superiority of our proposed method.
title HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.02373