MDLatLRR: A novel decomposition method for infrared and visible image fusion

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 develop 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.

IEEE Trans. Image Processing 2020, 14 pages, 17 figures, 3 tables. arXiv admin note: text overlap with arXiv:1804.08992

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DenseFuse: A Fusion Approach to Infrared and Visible Images
• Infrared and Visible Image Fusion using a Deep Learning Framework
• Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Tracking
• Infrared and Visible Image Fusion with ResNet and zero-phase component analysis
• Multi-focus Image Fusion using dictionary learning and Low-Rank Representation
• Image Fusion With Cosparse Analysis Operator
• An Accelerated Correlation Filter Tracker

Cited by in corpus (15)

• RFN-Nest: An end-to-end residual fusion network for infrared and visible images
• UIU-Net: U-Net in U-Net for Infrared Small Object Detection
• NestFuse: An Infrared and Visible Image Fusion Architecture based on Nest Connection and Spatial/Channel Attention Models
• SODFormer: Streaming Object Detection with Transformer Using Events and Frames
• PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion
• FS-Diff: Semantic guidance and clarity-aware simultaneous multimodal image fusion and super-resolution
• Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysis
• FIRe-GAN: A novel Deep Learning-based infrared-visible fusion method for wildfire imagery
• A Dual-branch Network for Infrared and Visible Image Fusion
• Cross Attention-guided Dense Network for Images Fusion
• AE-Net: Autonomous Evolution Image Fusion Method Inspired by Human Cognitive Mechanism
• Dynamic Brightness Adaptation for Robust Multi-modal Image Fusion
• Deep Decomposition Network for Image Processing: A Case Study for Visible and Infrared Image Fusion
• Non-linear and Selective Fusion of Cross-Modal Images
• AE-Netv2: Optimization of Image Fusion Efficiency and Network Architecture