论文题目:《CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion》 作者:Zixiang Zhao, Haowen Bai, Jiangshe Zhang,Yulun Zhang,Shuang Xu, Zudi Lin,Radu Timofte, Luc Van Gool 单位:西安交通大学、苏黎世联邦理工学院、西北工业大学、哈佛大学、维尔茨堡大学 会议:CVPR...
本文的研究目的是提出一种新颖的多模态图像融合网络,名为CDDFuse(Correlation-Driven Dual-Branch Feature Decomposition Fusion),用于处理不同模态图像融合的挑战。具体来说,CDDFuse旨在生成融合图像,同时保留不同模态的优势,例如在红外图像中保留热辐射信息和在可见光图像中保留详细的纹理信息。该网络通过建模跨模态特征...
To this end, we proposed the Correlation-Driven feature Decomposition Fusion (CDDFuse) model, where modality- specific and modality-shared feature extractions are realized by a dual-branch encoder, with the fused image reconstructed by the decoder...
CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion SUPPLEMENTARY MATERIALS Zixiang Zhao1,2 Haowen Bai1 Jiangshe Zhang1* Yulun Zhang2 Shuang Xu3,4 Zudi Lin5 Radu Timofte2,6 Luc Van Gool2 1 Xi'an Jiaotong University 2 Computer Vis...
[CVPR 2023] Official implementation for "CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion." - Zhaozixiang1228/MMIF-CDDFuse
# 图像融合论文阅读:CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion @inproceedings{zhao2023cddfuse, title={Cddfuse: Correlation-driven dual-branch fea…