Multi-focus image fusion based on non-negative sparse representation and patch-level consistency rectification

Zhang, Qiang; Li, Guanghe; Cao, Yunfeng; Han, Jungong

doi:10.1016/j.patcog.2020.107325

Cited by 22 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the different feature extraction and fusion strategies, these methods can be classified into conventional fusion methods and end-to-end deep learning methods. According to the hand-crafted feature decomposition and generation rules, conventional fusion methods mainly consist of multiscale transform-based [10], sparse representation-based [11][12][13], saliency-based [14][15][16][17], fuzzy set-based [18][19][20], and hybridbased [21][22][23] methods. To summarize, conventional methods for image fusion typically comprise three primary stages.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Infrared and Visible Image Fusion via Adaptive DenseNet with Knowledge Distillation

Zhao

Juanli

et al. 2023

Electronics

View full text Add to dashboard Cite

The fusion of infrared and visible images produces a complementary image that captures both infrared radiation information and visible texture structure details using the respective sensors. However, the current deep-learning-based fusion approaches mainly tend to prioritize visual quality and statistical metrics, leading to an increased model complexity and weight parameter sizes. To address these challenges, we propose a novel dual-light fusion approach using adaptive DenseNet with knowledge distillation to learn and compress from pre-existing fusion models, which achieves the goals of model compression through the use of hyperparameters such as the width and depth of the model network. The effectiveness of our proposed approach is evaluated on a new dataset comprising three public datasets (MSRS, M3FD, and LLVIP), and both qualitative and quantitative experimental results show that the distillated adaptive DenseNet model effectively matches the original fusion models’ performance with smaller model weight parameters and shorter inference times.

show abstract

Section: Introductionmentioning

confidence: 99%

Lightweight Infrared and Visible Image Fusion via Adaptive DenseNet with Knowledge Distillation

Zhao

Juanli

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

A critical analysis of the multi-focus image fusion using discrete wavelet transform and computer vision

Gebremeskel

2022

Soft Comput

View full text Add to dashboard Cite

A novel multiscale transform decomposition based multi-focus image fusion framework

Jia

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

Multi-focus image fusion based on non-negative sparse representation and patch-level consistency rectification

Abstract: Please refer to published version for the most recent bibliographic citation information. If a published version is known of, the repository item page linked to above, will contain details on accessing it.

Cited by 22 publications

References 42 publications

Lightweight Infrared and Visible Image Fusion via Adaptive DenseNet with Knowledge Distillation

Lightweight Infrared and Visible Image Fusion via Adaptive DenseNet with Knowledge Distillation

A critical analysis of the multi-focus image fusion using discrete wavelet transform and computer vision

A novel multiscale transform decomposition based multi-focus image fusion framework

Contact Info

Product

Resources

About