Infrared and Visible Image Fusion Network Based on Self-Compensating Lightweight Convolution
Open Access
Abstract
Deep learning has significantly improved the quality of infrared and visible image fusion. However, existing mainstream deep fusion networks often come with complex architectures and a large number of parameters. While general lightweight techniques can effectively reduce model complexity, they often weaken feature interactions during the lightweighting process, resulting in the loss of complementary texture and thermal information in fused images and making it difficult to balance fusion performance and model efficiency. To address these issues, this paper constructs an infrared and visible image fusion network based on a self-compensating lightweight convolution mechanism, named LWC-DenseFuse. The core of the network lies in a self-compensating lightweight convolution module, which goes beyond conventional convolution replacement and explicitly addresses feature degradation introduced by lightweight design. The module decouples spatial and channel correlations of standard convolution through depthwise convolution and pointwise convolution, while incorporating a channel attention mechanism to adaptively enhance salient features. Additionally, channel shuffle technology is employed to promote information exchange between groups, thereby enhancing feature interaction and compensating for the loss of critical information caused by lightweight design. To further improve the representation capability of the lightweight network during optimization, a staged training strategy with progressive loss weighting is introduced. Experimental evaluations demonstrate that the proposed fusion network significantly reduces the number of model parameters while ensuring real-time inference performance. Meanwhile, it effectively alleviates the performance degradation typically associated with lightweight architectures, as evidenced by improvements in information entropy and visual fidelity.Keywords
Funding Information
- National Natural Science Foundation of China (62376224)
This publication has 25 references indexed in Scilit:
- SFDFuse: A lightweight spatial-frequency fusion network for infrared-visible imagesPattern Recognition, 2026
- HaarFuse: A dual-branch infrared and visible light image fusion network based on Haar wavelet transformPattern Recognition, 2025
- A model-based infrared and visible image fusion network with cooperative optimizationExpert Systems with Applications, 2024
- LMDFusion: A lightweight infrared and visible image fusion network for substation equipment based on mask and residual dense connectionInfrared Physics & Technology, 2024
- Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion networkInformation Fusion, 2022
- Self-supervised feature adaption for infrared and visible image fusionInformation Fusion, 2021
- GAN-FM: Infrared and Visible Image Fusion Using GAN With Full-Scale Skip Connection and Dual Markovian DiscriminatorsIEEE Transactions on Computational Imaging, 2021
- UNIFusion: A Lightweight Unified Image Fusion NetworkIEEE Transactions on Instrumentation and Measurement, 2021
- NestFuse: An Infrared and Visible Image Fusion Architecture Based on Nest Connection and Spatial/Channel Attention ModelsIEEE Transactions on Instrumentation and Measurement, 2020
- Infrared and visible image fusion via gradient transfer and total variation minimizationInformation Fusion, 2016