Yiquan Xu
(Schweppes, 徐怡泉)                   

I am currently a research assistant at the School of Artificial Intelligence, Wuhan University. Previously, I received my master’s degree in 2025 from the State Key Laboratory of Surveying, Mapping and Remote Sensing Information Engineering, Wuhan University, where I was advised by Prof. Liangpei Zhang and Associate Prof. Xin Su.

My research interests include：

  • computer vision and deep learning
  • image generation with diffusion models
  • multi-temporal and multi-sensor remote sensing image change detection
Curriculum Vitae
Education
  • LIESMARS, Wuhan University
    LIESMARS, Wuhan University
    M.S. in Photogrammetry and Remote Sensing
    Sep. 2022 - Sep. 2025
  • SGG, Wuhan University
    SGG, Wuhan University
    B.S. in Photogrammetry and Remote Sensing
    Sep. 2018 - June. 2022
Experience
    Creation
  • Geo-spatial Information Science
    Geo-spatial Information Science
    Student Editor
    Dec. 2023 -- Present
  • Student Mental Health Education Center, Wuhan University
    Student Mental Health Education Center, Wuhan University
    Assistant Management
    July 2024 -- July 2025
Skills
Python
Matlab
C++
Java
R
Pytorch
TensorFlow
CUDA(GPU)
Linux
ArcGIS
Latex
Docker
Hobbies
Design
Knit
Crochet
Fashon
Non-fiction
Dance
Aerobics
Film
Video Editing
Pop Music
Gallery
Selected Publications
Diffpurifier: An Optical and SAR Image Change Detection Method Based on Diffusion Purification
Diffpurifier: An Optical and SAR Image Change Detection Method Based on Diffusion Purification

Y.Xu, X.Su, L.Zhang

IEEE Transactions on Geoscience and Remote Sensing (TGRS) 2025.6

This article proposes a CD network for optical and SAR images, named Diffpurifier. First, optical images are translated into SAR images using pre-trained denoising diffusion probabilistic models (DDPMs) and ordinary differential equations (ODEs) while simultaneously extracting multiscale features. Then, CD is performed under superpixel enhancement to improve the homogeneity of the CD maps. Diffpurifier not only integrates IT and feature extraction, simplifying the workflow, but also maintains high accuracy, stable training, and generalization to different types of data without the need for additional translation constraints. In comparative experiments on four public datasets, Diffpurifier outperforms the second-best method by an average of approximately 5% in terms of F1 -score, validating the effectiveness and robustness of the method.

[Paper] [Code]

Diffpurifier: An Optical and SAR Image Change Detection Method Based on Diffusion Purification
Diffpurifier: An Optical and SAR Image Change Detection Method Based on Diffusion Purification

Y.Xu, X.Su, L.Zhang

IEEE Transactions on Geoscience and Remote Sensing (TGRS) 2025.6

This article proposes a CD network for optical and SAR images, named Diffpurifier. First, optical images are translated into SAR images using pre-trained denoising diffusion probabilistic models (DDPMs) and ordinary differential equations (ODEs) while simultaneously extracting multiscale features. Then, CD is performed under superpixel enhancement to improve the homogeneity of the CD maps. Diffpurifier not only integrates IT and feature extraction, simplifying the workflow, but also maintains high accuracy, stable training, and generalization to different types of data without the need for additional translation constraints. In comparative experiments on four public datasets, Diffpurifier outperforms the second-best method by an average of approximately 5% in terms of F1 -score, validating the effectiveness and robustness of the method.

[Paper] [Code]

All researches
Honors & Awards
  • Graduate Freshman Scholarship
    2022
  • Outstanding Graduates
    2022
  • 2rd Class Academic Scholarship, Twice
    2021, 2020
  • Merit Student
    2021
  • 2rd Prize, Surveying and Mapping Skills Competition
    2021
  • Outstanding Student, Twice
    2020, 2019
  • Hi-Target Special Scholarship
    2019
  • 1st Class Academic Scholarship
    2019