MDLatLRR: A Novel Decomposition Method for Infrared and Visible Image Fusion
Hui Li,Xiaojun Wu,Josef Kittler +2 more
458
TL;DR: Zhang et al. as discussed by the authors proposed a multi-level image decomposition method based on latent low-rank representation (LatLRR), which is called MD LatLRR, which is used to decompose source images into detail parts and base parts.
read more
Abstract: Image decomposition is crucial for many image processing tasks, as it allows to extract salient features from source images. A good image decomposition method could lead to a better performance, especially in image fusion tasks. We propose a multi-level image decomposition method based on latent low-rank representation(LatLRR), which is called MDLatLRR. This decomposition method is applicable to many image processing fields. In this paper, we focus on the image fusion task. We build a novel image fusion framework based on MDLatLRR which is used to decompose source images into detail parts(salient features) and base parts. A nuclear-norm based fusion strategy is used to fuse the detail parts and the base parts are fused by an averaging strategy. Compared with other state-of-the-art fusion methods, the proposed algorithm exhibits better fusion performance in both subjective and objective evaluation.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
An Infrared and Visible Fusion Framework Based on a Novel Decomposition Method
TL;DR: A novel decomposition-based image fusion framework is proposed, which overcomes the problems of noise, blurring, and loss of details and outperforms other methods in both subjective observation and objective evaluation.
GuideFuse: A novel guided auto-encoder fusion network for infrared and visible images
Zeyang Zhang,Hui Li,Tianyang Xu,Xiao-jun Wu,Yu Fu +4 more
TL;DR: This paper proposes GuideFuse, a novel auto-encoder fusion network for infrared and visible images, which introduces image details into a deep network using a gradient-based guide value, achieving the best fusion effect compared to existing methods.
2
FusionOC: Research on optimal control method for infrared and visible light image fusion
Linlu Dong,Jun Wang +1 more
2
A dual-path residual attention fusion network for infrared and visible images
Zhishe Wang,Fan Yang,Junyao Wang,Jiawei Xu,Fengbao Yang,Li-e Ji +5 more
TL;DR: A dual-path residual attention fusion network (DRAFusion) is proposed to merge infrared and visible image key information, producing a comprehensive image with superior target perception and detail representation, outperforming existing methods in qualitative and quantitative evaluations.
2
A Novel Steganography Method for Infrared Image Based on Smooth Wavelet Transform and Convolutional Neural Network
TL;DR: Wang et al. as discussed by the authors proposed a novel framework SSCNNP: a Convolutional Neural-Network Predictor (CNNP) based on Smooth-Wavelet Transform (SWT) and Squeeze-Excitation (SE) attention for infrared image prediction, which combines CNN with SWT.
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
Robust Face Recognition via Sparse Representation
TL;DR: This work considers the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise, and proposes a general classification algorithm for (image-based) object recognition based on a sparse representation computed by C1-minimization.
Image information and visual quality
Hamid R. Sheikh,Alan C. Bovik +1 more
TL;DR: An image information measure is proposed that quantifies the information that is present in the reference image and how much of this reference information can be extracted from the distorted image and combined these two quantities form a visual information fidelity measure for image QA.
3.9K