@ARTICLE{10105495,
author={Li, Hui and Xu, Tianyang and Wu, Xiao-Jun and Lu, Jiwen and Kittler, Josef},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images},
year={2023},
volume={45},
number={9},
pages={11040-11052},
doi={10.1109/TPAMI.2023.3268209}}

論文級(jí)別：SCI A1
影響因子：23.6

??[論文下載地址]
??[代碼下載地址]

??論文解讀

作者構(gòu)建了一種【端到端】的【輕量級(jí)】融合網(wǎng)絡(luò)，該模型使用訓(xùn)練測(cè)試策略避免了網(wǎng)絡(luò)設(shè)計(jì)步驟。具體來(lái)說(shuō)，對(duì)融合任務(wù)使用了【可學(xué)習(xí)的表達(dá)方法】，其網(wǎng)絡(luò)模型構(gòu)建是由生成可學(xué)習(xí)模型的優(yōu)化算法指導(dǎo)的。【低秩表達(dá)】（low-rank representation ，【LRR】）是算法核心基礎(chǔ)。
并提出了一種新的細(xì)節(jié)語(yǔ)義信息損失函數(shù)

??關(guān)鍵詞

image fusion, network architecture, optimal model, infrared image, visible image.
圖像融合，網(wǎng)絡(luò)結(jié)構(gòu)，優(yōu)化模型，紅外圖像，可見(jiàn)光圖像

??核心思想

看的不是很懂，感覺(jué)和CDDFuse有點(diǎn)像，都是分別從源圖像提取兩個(gè)不同的特征，然后將不同源圖像相同的特征拼接在一起，然后融合，然后重構(gòu)生成融合圖像。本文最大的創(chuàng)新應(yīng)該就是LLRR-Blocks，使用這個(gè)東西可以避免設(shè)計(jì)復(fù)雜的網(wǎng)絡(luò)結(jié)構(gòu)，作者把問(wèn)題公式化了。（我理解的很淺）
回頭再看看吧
待更新……

參考鏈接
[什么是圖像融合？（一看就通，通俗易懂）]

??網(wǎng)絡(luò)結(jié)構(gòu)

作者提出的網(wǎng)絡(luò)結(jié)構(gòu)如下所示。

x

??損失函數(shù)

??數(shù)據(jù)集

• Train：KAIST
• TNO, VOT2020-RGBT

圖像融合數(shù)據(jù)集鏈接
[圖像融合常用數(shù)據(jù)集整理]

??訓(xùn)練設(shè)置

??實(shí)驗(yàn)

??評(píng)價(jià)指標(biāo)

• EN
• SD
• SSIMm
• MI
• VIFm
• Nabf

參考資料
[圖像融合定量指標(biāo)分析]

??Baseline

• DenseFuse, FusionGAN, IFCNN, CUNet, RFN-Nest, Tes2Fusion, YDTR, SwinFusion, U2Fusion

???參考資料
???強(qiáng)烈推薦必看博客[圖像融合論文baseline及其網(wǎng)絡(luò)模型]???

??實(shí)驗(yàn)結(jié)果

更多實(shí)驗(yàn)結(jié)果及分析可以查看原文：
??[論文下載地址]
??[代碼下載地址]

??傳送門(mén)

??圖像融合相關(guān)論文閱讀筆記

??[(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]
??綜述[Visible and Infrared Image Fusion Using Deep Learning]

??圖像融合論文baseline總結(jié)

??[圖像融合論文baseline及其網(wǎng)絡(luò)模型]

??其他論文

??[3D目標(biāo)檢測(cè)綜述：Multi-Modal 3D Object Detection in Autonomous Driving：A Survey]

??其他總結(jié)

??[CVPR2023、ICCV2023論文題目匯總及詞頻統(tǒng)計(jì)]

?精品文章總結(jié)

?[圖像融合論文及代碼整理最全大合集]
?[圖像融合常用數(shù)據(jù)集整理]

如有疑問(wèn)可聯(lián)系：420269520@qq.com;
碼字不易，【關(guān)注，收藏，點(diǎn)贊】一鍵三連是我持續(xù)更新的動(dòng)力，祝各位早發(fā)paper，順利畢業(yè)~文章來(lái)源地址http://www.zghlxwxcb.cn/news/detail-813050.html

到了這里，關(guān)于圖像融合論文閱讀：LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Imag的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！