Xiao Wu

Xiao Wu

Auto-generated profile, based on publicly available information

Xiao Wu

University of Electronic Science and Technology of China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 December 2024 in IEEE Geoscience and Remote Sensing Magazine
Verified
Journal Article
Closed access
Gemine VivoneGemine Vivone
Gemine Vivone
Liang-Jian DengLiang-Jian Deng
Liang-Jian Deng
SDShangqi Deng
Shangqi Deng
Danfeng HongDanfeng Hong
Danfeng Hong
MJMenghui Jiang
Menghui Jiang
Antonio PlazaAntonio Plaza
Antonio Plaza
Image fusion can be conducted at different levels, with pixel-level image fusion involving the direct combination of original information from source images. The objective of methods falling under this category is to generate a fused image that enhances both visual perception and subsequent processing tasks. This survey draws upon research findings in pixel-level image fusion for remote sensing, outlining primary research directions, such as image sharpening, multi-modal image fusion, and spatio-temporal image fusion. For each area, state-of-the-art deep learning solutions are deeply reviewed. Furthermore, this survey discusses open issues and potential future directions. It also examines common downstream image fusion tasks to underscore how they can benefit from image fusion techniques to achieve improved performance. This paper aims to extend beyond a conventional survey by not only reviewing existing methodologies but also providing practical insights such as assessment protocols, available datasets for training and testing deep learning models, and guidelines for deep learning remote sensing image fusion. This survey is geared towards students and professionals who want to approach pixel-level image fusion in remote sensing, offering valuable cues and tools for addressing specific challenges. The authors wish this work to contribute to reducing barriers to entry for interested scientists in adjacent research fields and aiding the growth of a new generation of image fusion researchers.

5 February 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XWXiao Wu
Xiao Wu
ZCZi-Han Cao
Zi-Han Cao
THTing-Zhu Huang
Ting-Zhu Huang
Liang-Jian DengLiang-Jian Deng
Liang-Jian Deng
Jocelyn  ChanussotJocelyn Chanussot
Jocelyn Chanussot
Gemine VivoneGemine Vivone
Gemine Vivone
Multi-source image fusion combines the information coming from multiple images into one data, thus improving imaging quality. This topic has aroused great interest in the community. How to integrate information from different sources is still a big challenge, although the existing self-attention based transformer methods can capture spatial and channel similarities. In this paper, we first discuss the mathematical concepts behind the proposed generalized self-attention mechanism, where the existing self-attentions are considered basic forms. The proposed mechanism employs multilinear algebra to drive the development of a novel fully-connected self-attention (FCSA) method to fully exploit local and non-local domain-specific correlations among multi-source images. Moreover, we propose a multi-source image representation embedding it into the FCSA framework as a non-local prior within an optimization problem. Some different fusion problems are unfolded into the proposed fully-connected transformer fusion network (FC-Former). More specifically, the concept of generalized self-attention can promote the potential development of self-attention. Hence, the FC-Former can be viewed as a network model unifying different fusion tasks. Compared with state-of-the-art methods, the proposed FC-Former method exhibits robust and superior performance, showing its capability of faithfully preserving information.

28 March 2024 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
RRRan Ran
Ran Ran
Liang-Jian DengLiang-Jian Deng
Liang-Jian Deng
TZTianjing Zhang
Tianjing Zhang
JCJianlong Chang
Jianlong Chang
XWXiao Wu
Xiao Wu
QTQi Tian
Qi Tian
Pixel-level adaptive convolution, which overcomes the deficiency of the spatial-invariance of standard convolution, is always limited to performing feature extraction from local patches and ignores the latent long-range dependencies imperceptible in the feature space, which are more significant in pixel-level tasks such as hyperspectral image super-resolution (HSISR). To handle such limitations, we propose kernel-space non-local convolution (KNLConv), which explores non-local dependencies in the generated kernel space, to leverage these global information to guide the network to extract image features more flexibly. Technically, the proposed KNLConv first decomposes the convolutional kernel space into spatial and channel dimensions, and designs a depth-wise non-local expansion convolution (NLEC) in the spatial dimension of the kernel-space to explore underlying global correlations. Then introduce an adaptive point-wise convolution (APC), generalizing the NLEC to the pixel-level while integrating features in the channel dimension. In addition, applying KNLConv, we design an effective network architecture for hyperspectral image super-resolution. Extensive experiments demonstrate that our approach performs favorably against current state-of-the-art HSISR methods, both on quantitative indicators and visual quality.

26 October 2023
Verified
Conference Paper
Open access
SPSiran Peng
Siran Peng
CGChenhao Guo
Chenhao Guo
XWXiao Wu
Xiao Wu
Liang-Jian DengLiang-Jian Deng
Liang-Jian Deng
In image fusion tasks, images obtained from different sources exhibit distinct properties. Consequently, treating them uniformly with a single-branch network can lead to inadequate feature extraction. Additionally, numerous works have demonstrated that multi-scaled networks capture information more sufficiently than single-scaled models in pixel-level computer vision problems. Considering these factors, we propose U2Net, a spatial-spectral-integrated double U-shape network for image fusion. The U2Net utilizes a spatial U-Net and a spectral U-Net to extract spatial details and spectral characteristics, which allows for the discriminative and hierarchical learning of features from diverse images. In contrast to most previous works that merely employ concatenation to merge spatial and spectral information, this paper introduces a novel spatial-spectral integration structure called S2Block, which combines feature maps from different sources in a logical and effective way. We conduct a series of experiments on two image fusion tasks, including remote sensing pansharpening and hyperspectral image super-resolution (HISR). The U2Net outperforms representative state-of-the-art (SOTA) approaches in both quantitative and qualitative evaluations, demonstrating the superiority of our method. The code is available at https://github.com/PSRben/U2Net.

28 October 2024
Verified
Conference Paper
Open access
ZCZihan Cao
Zihan Cao
XWXiao Wu
Xiao Wu
Liang-Jian DengLiang-Jian Deng
Liang-Jian Deng
YZYu Zhong
Yu Zhong
In image fusion tasks, images from different sources possess distinct characteristics. This has driven the development of numerous methods to explore better ways of fusing them while preserving their respective characteristics. Mamba, as a state space model, has emerged in the field of natural language processing. Recently, many studies have attempted to extend Mamba to vision tasks. However, due to the nature of images different from causal language sequences, the limited state capacity of Mamba weakens its ability to model image information. Additionally, the sequence modeling ability of Mamba is only capable of spatial information and cannot effectively capture the rich spectral information in images. Motivated by these challenges, we customize and improve the vision Mamba network designed for the image fusion task. Specifically, we propose the local-enhanced vision Mamba block, dubbed as LEVM. The LEVM block can improve local information perception of the network and simultaneously learn local and global spatial information. Furthermore, we propose the state sharing technique to enhance spatial details and integrate spatial and spectral information. Finally, the overall network is a multi-scale structure based on vision Mamba, called LE-Mamba. Extensive experiments show the proposed methods achieve state-of-the-art results on multispectral pansharpening and multispectral and hyperspectral image fusion datasets, and demonstrate the effectiveness of the proposed approach. Code can be accessed at https://github.com/294coder/Efficient-MIF.

13 July 2026 in Geo-spatial Information Science
Verified
Journal Article
Open access
CLChuang Liu
Chuang Liu
JGJianhua Guo
Jianhua Guo
XWXiao Wu
Xiao Wu
ZZZhang Zhiqi
Zhang Zhiqi
Mi WangMi Wang
Mi Wang
WQWU Qianyu
WU Qianyu