图像融合论文阅读：Real-time infrared and visible image fusion network using adaptive pixel weighting strategy

@article{zhang2023real,
title={Real-time infrared and visible image fusion network using adaptive pixel weighting strategy},
author={Zhang, Xuchong and Zhai, Han and Liu, Jiaxing and Wang, Zhiping and Sun, Hongbin},
journal={Information Fusion},
pages={101863},
year={2023},
publisher={Elsevier}
}

---

论文级别：SCI A1
影响因子：18.6

[论文下载地址]

---

---

【如侵权请私信我删除】

论文解读

本文作者提出了一个【轻量级、实时】的IVF网络，该网络能够自适应地学习像素权值进行图像融合。并且作者将【目标检测作为下游任务】，【联合优化】网络参数。

关键词

Multispectral image fusion 多光谱图像融合
Lightweight model 轻量级模型
Joint optimization 联合优化
Real-time 实时
Embedded platform 嵌入式平台

核心思想

采用【自适应像素加权】（Adaptive Pixel Weighting strategy， APWNet）策略融合图像，并联合【目标检测】下游任务。具体来说，将可见光和红外光图像concat后输入卷积层，提取权值图，然后将其分别与对应的源图逐元素乘和加操作得到融合图像，将融合图像作为yolov5s的输入进行目标检测。（在训练过程中，根据检测结果反向优化网络参数）

参考链接
[什么是图像融合？（一看就通，通俗易懂）]

网络结构

作者提出的网络结构如下所示。

首先将拼接后的红外和可见光图像送入一系列卷积层和sigmoid层，生成输入图像的权值图。然后对融合图像进行逐元运算和最大最小归一化。最后，将融合后的图像输入检测器，端到端联合训练整个网络。

$I_{ir}$和$I_{vi}$分别代表红外图像和可见光图像，$W_{ir}$和$W_{vi}$代表源图像对应的融合权重
$C[\cdot ]$是concatenation，即维度通道拼接。$P(\cdot )$代表自适应像素权重生成模块。
然后分别将源图与对应的权重相乘并相加，随后归一化融合图像：


最后，将融合图像输入目标检测网络得到检测结果：

网络详细结构如下图：

损失函数

清晰明了的损失函数，没什么多说的，大道至简。如有疑问可以阅读博主之前的文章。

数据集

• TNO、RoadScene 、MSRS

图像融合数据集链接
[图像融合常用数据集整理]

训练设置

实验

评价指标

• MI
• FMIdct
• FMIw
• Mutinf
• Qcv
• Var
• Qabf
• [email protected]
• mAP@[0.5:0.95]

参考资料
[图像融合定量指标分析]

Baseline

• U2Fusion ，RFNNest , MFEIF , PIAFusion

and three lightweight networks

• SeAFusion, SDNet, IFCNN

✨✨✨参考资料
✨✨✨强烈推荐必看博客[图像融合论文baseline及其网络模型]✨✨✨

实验结果

更多实验结果及分析可以查看原文：
[论文下载地址]

---

传送门

图像融合相关论文阅读笔记

[Dif-fusion: Towards high color fidelity in infrared and visible image fusion with diffusion models]
[Coconet: Coupled contrastive learning network with multi-level feature ensemble for multi-modality image fusion]
[LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images]
[(DeFusion)Fusion from decomposition: A self-supervised decomposition approach for image fusion]
[ReCoNet: Recurrent Correction Network for Fast and Efficient Multi-modality Image Fusion]
[RFN-Nest: An end-to-end resid- ual fusion network for infrared and visible images]
[SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Images]
[SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer]
[(MFEIF)Learning a Deep Multi-Scale Feature Ensemble and an Edge-Attention Guidance for Image Fusion]
[DenseFuse: A fusion approach to infrared and visible images]
[DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pair]
[GANMcC: A Generative Adversarial Network With Multiclassification Constraints for IVIF]
[DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion]
[IFCNN: A general image fusion framework based on convolutional neural network]
[(PMGI) Rethinking the image fusion: A fast unified image fusion network based on proportional maintenance of gradient and intensity]
[SDNet: A Versatile Squeeze-and-Decomposition Network for Real-Time Image Fusion]
[DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion]
[FusionGAN: A generative adversarial network for infrared and visible image fusion]
[PIAFusion: A progressive infrared and visible image fusion network based on illumination aw]
[CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion]
[U2Fusion: A Unified Unsupervised Image Fusion Network]
综述[Visible and Infrared Image Fusion Using Deep Learning]

图像融合论文baseline总结

[图像融合论文baseline及其网络模型]

其他论文

[3D目标检测综述：Multi-Modal 3D Object Detection in Autonomous Driving：A Survey]

其他总结

[CVPR2023、ICCV2023论文题目汇总及词频统计]

✨精品文章总结

✨[图像融合论文及代码整理最全大合集]
✨[图像融合常用数据集整理]

如有疑问可联系：[email protected];
码字不易，【关注，收藏，点赞】一键三连是我持续更新的动力，祝各位早发paper，顺利毕业~