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 Image Fusion Network for Dark Scenes
Jiahao Zhang,Wei Zong-shou +1 more
- 12 Jul 2024
TL;DR: This paper proposes a novel image fusion network that combines infrared and visible images to enhance visual quality and contrast in dark scenes, using a multi-level brightness adjustment unit and parallel attention module for improved feature extraction and luminance enhancement.
Res2NetFuse: A Novel Res2Net-based Fusion Method for Infrared and Visible Images
Song Xu,Yongbiao Xiao,Hui Li,Xiao‐Jun Wu,Jun Sun,Vasile Palade +5 more
- 22 Sep 2023
TL;DR: A novel fusion framework using Res2Net architecture, capturing features across diverse receptive fields and scales for effective extraction of global and local features is introduced, surpassing existing techniques.
Infrared and Visible Image Fusion via Interactive Compensatory Attention Adversarial Learning
TL;DR: A novel end-to-end mode based on generative adversarial training to achieve better fusion balance, termed as interactive compensatory attention fusion network (ICAFusion), which precedes other advanced methods in the subjective visual description and objective metric evaluation.
Infrared and Visible Image Fusion via Test-Time Training
Guoqing Zheng,Zhenqi Fu,Xiaopeng Lin,Xueye Chu,Yue Huang,Xinghao Ding +5 more
TL;DR: A self-supervised test-time training approach is proposed for infrared and visible image fusion, leveraging a novel loss function and fusion adapter to improve fusion quality and automatically learn fusion rules, outperforming existing methods on two public IVIF datasets.
HATF: Multi-Modal Feature Learning for Infrared and Visible Image Fusion via Hybrid Attention Transformer
Xiangzeng Liu,Ziyao Wang,Haojie Gao,Xiang Li,Lei Wang,Qiguang Miao +5 more
TL;DR: A novel framework, HATF, is proposed for infrared and visible image fusion, leveraging a cross-attention Transformer, residual U-Nets, and adaptive loss functions to achieve optimal fusion results with improved robustness and image quality.
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