Ziyang Xu (徐子扬)

I am currently pursuing my third-year Master's degree within the School of Electronic Information and Communications(EIC) at Huazhong University of Science and Technology(HUST), benefitting from the guidance of Professors Xinggang Wang and Wenyu Liu. Prior to this, I obtained a B.E. degree in Information Engineering from School of Information Engineering(IE), Wuhan University of Technology(WHUT) in 2022.

Email  |  Google Scholar  |  Github

profile photo

Research

My scholarly interests revolve around the fields of Artificial General Intelligence, Computer Vision, Medical Image Analysis, and Object Detection/Segmentation. Representative papers are highlighted.

Large-scale Pretrained Frame Generative Model Enables Real-Time Low-Dose DSA Imaging: an AI System Development and Multicenter Validation Study
Huangxuan Zhao*, Ziyang Xu*, Linxia Wu*, Lei Chen*, Ziwei Cui, Jinqiang Ma, Tao Sun, Yu Lei, Nan Wang, Hongyao Hu, Yiqing Tan, Wei Lu, Wenzhong Yang, Kaibing Liao, Gaojun Teng, Xiaoyun Liang, Yi Li, Congcong Feng, Xiaoyu Han, P.Matthijs van der Sluij, Charles B.L.M. Majoie, Wim H. van Zwam, Yun Feng, Theo van Walsum, Aad van der Lugt, Wenyu Liu, Xuefeng Kan, Ruisheng Su, Weihua Zhang, Xinggang Wang, Chuansheng Zheng
Med (Cell Press), 2024
paper / github

GenDSA is pre-trained, fine-tuned and tested on ten million of images from 35 hospitals. The generated videos reach a comparable level to the full-sampled videos, both in terms of overall quality (4.905 vs 4.935) and lesion assessment (4.825 vs 4.860).

MoSt-DSA: Modeling Motion and Structural Interactions for Direct Multi-Frame Interpolation in DSA Images
Ziyang Xu, Huangxuan Zhao, Ziwei Cui, Wenyu Liu, Chuansheng Zheng, Xinggang Wang
European Conference on Artificial Intelligence, 2024
arXiv / github

The first work that uses deep learning for DSA frame interpolation, comprehensively achieving SOTA in accuracy, speed, visual effect, and memory usage.


This website is based on jonbarron's template.