Quanfeng Xu - Homepage

Quanfeng Xu (徐权峰)

Ph.D. Candidate

Shanghai Astronomical Observatory, University of Chinese Academy of Sciences

Email: xuquanfeng23@mails.ucas.ac.cn
[Github] [Orcid] [OpenReview] [Google Scholar]

Biography

I am currently a Ph.D. candidate (expected Nov 2026) in the Galaxy Cluster Group at the Shanghai Astronomical Observatory, supervised by Prof. Shiyin Shen. With a foundation in probability theory and mathematical statistics, my research focuses on AI for Science (AI4S), combining low-level computer vision with astrophysics to learn robust representations from raw astronomical images and support downstream scientific tasks. My broader research interests include 3D vision (NeRF and Gaussian Splatting), SLAM, generative AI, and GPU acceleration. I aim to keep expanding my expertise and contribute to technological advances in a dynamic R&D environment.

Selected Publications [Full paper] (^Co-first author; *Corresponding author)

	Plate-YOLO: An End-to-End Object Detection Framework for Robust Astrometric Registration of Historical Plates Quanfeng Xu, Zhengjun Shang, Shiyin Shen, Yong Yu, Mingyang Ma, Zhenghong Tang, et al. The Astronomical Journal (AJ), 2026. [Paper] [Project] [Code]
	FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution Shuhong Liu^, Xining Ge^, Quanfeng Xu^, Ziteng Cui, Liuzhuozheng Li, Gengjia Chang, Jun Liu, et al. Neural Information Processing Systems (NeurIPS), 2026. [Paper] [Project] [Code]
	Enhancing astrometric registration of Chinese historical Astronomical Digital Plates with deep learning Quanfeng Xu, Zhengjun Shang, Shiyin Shen, Yong Yu, Meiting Yang, Hao Luo, et al. Research in Astronomy and Astrophysics* (RAA), 2026. Cover Article Vol. 26 No. 9 . [Paper] [Project] [Code] [Report]
	From images to features: unbiased morphology classification via variational auto-encoders and domain adaptation Quanfeng Xu, Shiyin Shen, Rafael S. de Souza, Mi Chen, Renhao Ye, Yumei She, Zhu Chen, et al. Monthly Notices of the Royal Astronomical Society (MNRAS), 2023. [Paper] [Code]
	Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging Shuhong Liu, Xining Ge, Ziying Gu, Quanfeng Xu, Lin Gu, Ziteng Cui, Xuangeng Chu, Jun Liu, Dong Li, Tatsuya Harada European Conference on Computer Vision (ECCV), 2026. [Paper] [Code]
	DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments Shuhong Liu, Xiang Chen, Hongming Chen, Quanfeng Xu, Mingrui Li* AAAI Conference on Artificial Intelligence (AAAI), 2025. [Paper] [Project] [Code]
	Galmoss: A package for GPU-accelerated galaxy profile fitting Mi Chen, Rafael S. de Souza, Quanfeng Xu, Shiyin Shen, Ana L. Chies-Santos, Renhao Ye, et al. Astronomy and Computing (A&C), 2024. [Paper] [Code]
	qrpca: A package for fast principal component analysis with GPU acceleration Rafael S. de Souza^, Quanfeng Xu^, Shiyin Shen, Chen Peng, Zihao Mu Astronomy and Computing* (A&C), 2022. [Paper] [Code]