Xingyu Liu

Xingyu Liu | 刘星雨

I am a fourth-year Ph.D. student at Tsinghua University, supervised by Prof. Xiangyang Ji. Previously, I received my B.E. degree in Automation at Beihang University.

Email / Github / Linkedin / Google Scholar

Research

My research interest lies in computer vision combined with robotics. Specifically, I am willing to explore the application of robotic vision in real-world scenarios, which takes domain transfer, self-supervised learning, and continuous refinement into consideration. Recently I am studying deep learning methods on object pose estimation for point cloud and RGB data.

	GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator Xingyu Liu, Ruida Zhang, Chenyangguang Zhang, Gu Wang, Jiwen Tang, Zhihang Li, Xiangyang Ji. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2025 Winner of BOP Challenge 2022 @ ECCV R6D Workshop, Winner of BOP Challenge 2023 @ ICCV R6D Workshop, Paper / code
	UNOPose: Unseen Object Pose Estimation with One RGB-D Reference Image Xingyu Liu, Gu Wang, Ruida Zhang, Chenyangguang Zhang, Xiangyang Ji. Conference on Computer Vision and Pattern Recognition (CVPR), 2025 arXiv / code
	CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement Xingyu Liu, Gu Wang, Yi Li, Xiangyang Ji. European Conference on Computer Vision (ECCV), 2022 Paper / arXiv / code
	GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024 Xingyu Liu, Gu Wang, Chengxi Li, Yingyu Li, Chenyangguang Zhang, Ziqin Huang, Xiangyang Ji. Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2025 arXiv
	RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications Xingyu Liu, Chenyangguang Zhang, Gu Wang, Ruida Zhang, Xiangyang Ji. IEEE International Conference on Robotics and Automation (ICRA), 2024 Paper / code
	Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation Gu Wang, Fabian Manhardt, Xingyu Liu, Xiangyang Ji, Federico Tombari. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2021 Paper / arXiv / code
	Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition Yansong Tang, Xingyu Liu, Xumin Yu, Danyang Zhang, Jiwen Lu, Jie Zhou. ACM Transactions on Multimedia Computing, Communications, and Applications (ACM TOMM), 2021 Paper / arXiv / code

Experience

	Tsinghua University, China 2021.09 - Present Ph.D. Student in Automation
	Beihang University, China 2017.09 - 2021.07 B.S. in Automation, GPA rank 1/205
	Oxford University, England 2019.07 - 2019.08 Visiting Student

Template stolen from Jon Barron.
Last updated: 03/05/2025