Han Xue

薛寒
CS Ph.D. Candidate @SJTU
Research Interests: Robotics, 3D Vision

🦸🏻‍♂️ About Me

I am a third-year Computer Science Ph.D. candidate at Shanghai Jiao Tong University and a member of Machine Intelligence and Vision Group (MVIG) under the supervision of Prof. Cewu Lu (卢策吾). I am also a member of Wu Wen Jun Honorary Doctoral Program (吴文俊荣誉博士班).

I receive my bachelor degree from Shanghai Jiao Tong Universiy in 2021. My research interests lie in Robotics and 3D Vision. Previously, I have been working on deformable object perception and manipulation. Now I am particularly interested in imitation learning with tactile/force sensing and low-cost data collection system.

In the past, I have interned at Microsoft Research Asia under the supervsion of Han Hu and Yue Cao. I also spent time with Prof. Huazhe Xu at Tsinghua University on my projects. In my spare time, I enjoy watching movies and playing with robots🤖.

📰 News

More news >>>

🏫 Experiences

Shanghai Jiao Tong University
Ph.D. Student / Master Student.
Research assistant in Machine Intelligence and Vision Group (MVIG), advised by Prof. Cewu Lu
Sep. 2021 - Present

Microsoft Research Asia
Research Intern, advised by Han Hu and Yue Cao.
Jul. 2019 - Mar. 2020

Shanghai Jiao Tong University
Bachelor of Engineering in Computer Science.
GPA 4.04/4.3, Rank 3/150 (Top 2%)
Sep 2016 - Jun. 2021

📄 Selected Publications

arXiv'25|WebsitearXiv

Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation

Han Xue*, Jieji Ren*, Wendi Chen*, Gu Zhang, Yuan Fang, Guoying Gu, Huazhe Xu†, Cewu Lu† (†Equal advising) 

arXiv

ICRA'25|WebsitearXivCode

DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment

Wendi Chen*, Han Xue*, Fangyuan Zhou, Yuan Fang, Cewu Lu (*Equal contribution) 

IEEE International Conference on Robotics and Automation (ICRA)

CoRL'23|ProceedingarXivCodeWebsite

UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding

Han Xue*, Yutong Li*, Wenqiang Xu, Huanyu Li, Dongzhe Zheng, Cewu Lu (*Equal contribution) 

7th Annual Conference on Robot Learning.

ICCV'23|Proceeding

ClothPose: A Real-world Benchmark for Visual Analysis of Garment Pose via An Indirect Recording Solution

Wenqiang Xu*, Wenxin Du*, Han Xue, Yutong Li, Ruolin Ye, Yan-Feng Wang, Cewu Lu (*Equal contribution) 

Proceedings of the IEEE/CVF International Conference on Computer Vision

🔥 Oral Presentation.

CVPR'23|ProceedingarXivCodeWebsite

GarmentTracking: Category-Level Garment Pose Tracking

Han Xue, Wenqiang Xu, Jieyi Zhang, Tutian Tang, Yutong Li, Wenxin Du, Ruolin Ye, Cewu Lu 

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

CVPR'23|ProceedingarXivCodeWebsite

Visual-Tactile Sensing for In-Hand Object Reconstruction

Wenqiang Xu*, Zhenjun Yu*, Han Xue, Ruolin Ye, Siqiong Yao, Cewu Lu (*Equal contribution) 

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

RSS'23|ProceedingCodeWebsite

Demonstrating RFUniverse: A Multiphysics Simulation Platform for Embodied AI

Haoyuan Fu*, Wenqiang Xu*, Ruolin Ye*, Han Xue, Zhenjun Yu, Tutian Tang, Yutong Li, Wenxin Du, Jieyi Zhang, Cewu Lu (*Equal contribution) 

Robotics: Science and Systems.

TIP'22|arXiv

Toward Real-World Category-Level Articulation Pose Estimation

Liu Liu*, Han Xue*, Wenqiang Xu, Haoyuan Fu, Cewu Lu (*Equal contribution) 

IEEE Transactions on Image Processing.

BMVC'21|ProceedingarXivCode

OMAD: Object Model with Articulated Deformations for Pose Estimation and Retrieval

Han Xue*, Liu Liu*, Wenqiang Xu, Haoyuan Fu, Cewu Lu (*Equal contribution) 

The 32nd British Machine Vision Conference.

ECCV'20|ProceedingarXivCode

Dense RepPoints: Representing Visual Objects with Dense Point Sets

Ze Yang*, Yinghao Xu*, Han Xue*, Zheng Zhang, Raquel Urtasun, Liwei Wang, Stephen Lin, Han Hu (*Equal contribution) 

The European Conference on Computer Vision.

CVPR'18|ProceedingCodeWebsite

Lidar-video driving dataset: Learning driving policies effectively

Yiping Chen*, Jingkang Wang*, Jonathan Li, Cewu Lu, Zhipeng Luo, Han Xue, Cheng Wang (*Equal contribution) 

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

Full publication list >>>

✨ Talks

• [Oct. 2024] Invited talk @ TEA lab in Tsinghua University, IIIS on "Efficient Learning for Long-horizon Deformable Object Manipulation"
• [Dec. 2024] Invited talk @ ROSCon China 2024 workshop on "Development Trends and Challenges in Embodied AI". The link of the recorded video is here.

🏆 Awards

• Outstanding Graduates in Shanghai (Top 3%) [上海市优秀毕业生] in 2021.
• Rongchang Technology Innovation Scholarship (Top 10 students in SJTU) [荣昶科技创新奖学金] in 2020.
• SenseTime Scholarship (Top 21 undergraduates in China) [商汤奖学金] in 2020.
• National Scholarship (Top 3 students in CS Department) in 2017, 2018 and 2019 (three consecutive years) [国家奖学金（连续三年）].
• Academic Excellence Scholarship (Class A) of SJTU (Top 1% in SJTU) in 2018.
• Meritorious Winner Prize of Mathematical Contest in Modeling in 2018.
• 1st Prize in China Undergraduate Mathematical Contest in Modeling (Shanghai Division) in 2017.

📧 Find Me

Email

GitHub

Twitter