Xinyu Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xinyu Hu has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Feng Yang
Guangxi Key Laboratory of Multimedia Communications Network Technology, Guangxi University, Nanning, China
2 shared publications - Yang Liu
Stanford University
2 shared publications - Bing Wu1 shared publication
- Danhua Lu1 shared publication
Latest Publications
- 29 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 307
APGFusion : Adaptive PoolFormer and CNN medical image fusion network based on convolutional gated linear units
- 29 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 307
APGFusion : Adaptive PoolFormer and CNN medical image fusion network based on convolutional gated linear units
- 2 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-14
PFCFuse: A Poolformer and CNN Fusion Network for Infrared-Visible Image Fusion
Infrared visible image fusion plays a central role in multi-modal image fusion. By integrating feature information, we obtain more comprehensive and richer visual data to enhance image quality. However, current image fusion methods often rely on intricate networks to extract parameters from multimodal source images, making it challenging to leverage valuable information for high-quality fusion results completely. In this research, we propose a Poolformer-CNN dual-branch feature extraction fusion network for the fusion of infrared and visible images, termed PFCFuse. This network fully exploits key features in the images and adaptively preserves critical features in the images. To begin with, we provide a feature extractor with a dual-branch poolformer-cnn, using poolformer blocks to extract low-frequency global information, where the basic spatial pooling procedures are used as a substitute for the attention module of the Transformer. Secondly, the model is designed with an adaptively adjusted a-Huber loss, which can stably adjust model parameters and reduce the influence of outliers on model predictions, thereby enhancing the model’s robustness while maintaining precision. Compared with state-of-the-art fusion models such as U2Fusion, RFNet, TarDAL, and CDDFuse, we obtain excellent experimental results in both qualitative and quantitative experiments. Compared to the latest dual-branch feature extraction, CDDFuse, our model parameters are reduced by half. Code available at https://github.com/HXY13/PFCFuse-Image-Fusion.
- 2 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-14
PFCFuse: A Poolformer and CNN Fusion Network for Infrared-Visible Image Fusion
Infrared visible image fusion plays a central role in multi-modal image fusion. By integrating feature information, we obtain more comprehensive and richer visual data to enhance image quality. However, current image fusion methods often rely on intricate networks to extract parameters from multimodal source images, making it challenging to leverage valuable information for high-quality fusion results completely. In this research, we propose a Poolformer-CNN dual-branch feature extraction fusion network for the fusion of infrared and visible images, termed PFCFuse. This network fully exploits key features in the images and adaptively preserves critical features in the images. To begin with, we provide a feature extractor with a dual-branch poolformer-cnn, using poolformer blocks to extract low-frequency global information, where the basic spatial pooling procedures are used as a substitute for the attention module of the Transformer. Secondly, the model is designed with an adaptively adjusted a-Huber loss, which can stably adjust model parameters and reduce the influence of outliers on model predictions, thereby enhancing the model’s robustness while maintaining precision. Compared with state-of-the-art fusion models such as U2Fusion, RFNet, TarDAL, and CDDFuse, we obtain excellent experimental results in both qualitative and quantitative experiments. Compared to the latest dual-branch feature extraction, CDDFuse, our model parameters are reduced by half. Code available at https://github.com/HXY13/PFCFuse-Image-Fusion.