Hyperspectral Image Super-Resolution Meets Deep Learning: A Survey and Perspective
Xinya Wang, Qian Hu, Yingsong Cheng and Jiayi Ma
IEEE/CAA Journal of Automatica Sinica 2023
[paper]
About Me
I am currently a Ph.D. student in Electronic Information School, Wuhan University, China, supervised by Prof. Jiayi Ma in the lab of Multi-spectral Vision Processing (MVP). I am also supervised by Prof. Junjun Jiang in the School of Computer Science and Technology, Harbin Institute of Technology, China. Before that, I obtained the BEng. degree from the Wuhan University.
My research focuses on processing multi-dimensional data and developing novel algorithms for high-resolution image enhancement and restoration. My work has been applied to several real-world applications, including blind super-resolution, hyperspectral sharpening, light field super-resolution and infrared image enhancement.
Currently, I am seeking a Postdoctoral position to continue advancing my research and applying my skills and expertise to new challenges. You can find my full CV here.
Education
Ph.D. in Signal and Information Processing 2018 - present
Wuhan University, Wuhan, China
B.Eng. in Communication Engineering 2014 - 2018
Wuhan University, Wuhan, China
Selected Publications
For a full list of publications please see my CV or Google Scholar.
A Group-Based Embedding Learning and Integration Network for Hyperspectral Image Super-Resolution
Xinya Wang, Qian Hu, Junjun Jiang and Jiayi Ma
IEEE Transactions on Geoscience and Remote Sensing 2022
[paper]
Group Shuffle and Spectral-Spatial Fusion for
Hyperspectral Image Super-Resolution
Xinya Wang, Yingsong Cheng, Xiaoguang Mei, Junjun Jiang and Jiayi Ma
IEEE Transactions on Computational Imaging 2022
[paper]
Learning an Epipolar Shift Compensation for Light Field Image Super-Resolution
Xinya Wang, Jiayi Ma, Peng Yi, Xin Tian, Junjun Jiang and Xiaoping Zhang
Information Fusion 2022
[paper]
Hyperspectral Image Super-Resolution via Recurrent Feedback Embedding and Spatial–Spectral Consistency Regularization
Xinya Wang, Jiayi Ma and Junjun Jiang
IEEE Transactions on Geoscience and Remote Sensing 2022
[paper]
Contrastive Learning for Blind Super-Resolution via a Distortion-Specific Network
Xinya Wang, Jiayi Ma and Junjun Jiang
IEEE/CAA Journal of Automatica Sinica 2022
[paper]
Dilated Projection Correction Network based on Autoencoder for Hyperspectral Image Super-Resolution Neural Networks
Xinya Wang, Jiayi Ma, Junjun Jiang and Xiaoping Zhang
Neural Networks 2021
[paper]
DRF: Disentangled Representation for Visible and Infrared Image Fusion
Han Xu, Xinya Wang and Jiayi Ma
IEEE Transactions on Instrumentation and Measurement 2021
[paper]
Research
Infrared Image Enhancement Based on Infrared Light Filed Imaging
Infrared imaging, generally, of low quality, plays an important role
in security surveillance and target detection, which hinders the progress of large-scale AI-based studies and a range of applications. To this end, an infrared light field imaging
enhancement system is built for the first time, including a infrared light field imaging device, a large-scale infrared light field dataset (IRLF-WHU), and a progressive fusion network for infrared image enhancement (IR-PFNet).
[Paper] [Code] [Dataset]
Multi-modal Fusion-based Hyperspectral Image Generation
Acquiring and processing hyperspectral data can be time-consuming and expensive, which causes a series of issues involving data scarcity, class skew and target background restriction. To this end, we tend to raise a new paradigm of HSI generation, generating a vast amount of HSI with a rich diversity in various categories and scenes, closely resembling realistic data.
[Project]
Services
Journal Reviewer
Conference Reviewer
Teaching Assistant
Natural Science Introductory Course (Undergraduate course, TA, 2022 Fall)