Multi-Band NIR-Based Low-Light Image Enhancement via Dual-Teacher Cross Attention

Low-light images often lack visibility and information, and traditional methods of adjusting camera sensitivity and exposure time can result in visual quality degradation. In this paper, we propose a low-light enhancement method that utilizes two novel approaches to address these issues. The first a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024, Vol.12, p.111360-111370
Main Authors: Park, Jeong-Hyeok, Lee, Dong-Min, Kim, Tae-Hyeon, Park, Tae-Sung, Kim, Jong-Ok
Format: Article
Language:English
Subjects:
Ablation
Brightness
cross-attention
Image enhancement
Image quality
Knowledge acquisition
knowledge distillation
Knowledge management
Knowledge transfer
Lighting
multi-band NIR
Photodegradation
Reflectivity
Retinex-theory
Signal to noise ratio
Teachers
Transformers
Visualization
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Low-light images often lack visibility and information, and traditional methods of adjusting camera sensitivity and exposure time can result in visual quality degradation. In this paper, we propose a low-light enhancement method that utilizes two novel approaches to address these issues. The first approach involves using multi-band NIR (Near Infra-red) to preserve structural components, while a transformer-based cross-attention module efficiently calculates the correlation between NIR and RGB for effective fusion. The second approach involves implementing dual-teacher knowledge distillation, where normal- and mid-light teacher networks transfer low-light enhancement knowledge to the student. Our proposed method produces better color and detail restoration results than existing methods, particularly in ultra low-light environments. We also provide our own datasets for two different low-light conditions, enabling wide evaluations and ablation studies.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3440410