news image

Xin Chen (陈欣)
[Watch My CV]
[Email | Github | LinkedIn] [Conference Timer]


Popup Image

SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos

Xin Chen, Anqi Pang, Wei Yang, Yuexin Ma, Lan Xu, Jingyi Yu

(Submit to IJCV 2020) International Journal of Computer Vision

We propose SportsCap – the first approach for simultaneously capturing 3D human motions and understanding fine-grained actions from monocular challenging sports video input.

[Paper] [Video] [BibTex]

Popup Image

Multiview Deformation for Dynamic Human Modeling

Xi Luo, Yuwei Li, Xin Chen, Jingyi Yu

Arxiv 2019

We present a novel multi-view dynamic 3D human reconstruction technique based on model-based shape deformation.

[Paper] [Video] [BibTex]

Popup Image

TightCap: 3D Human Shape Capture with Clothing Tightness

Xin Chen, Anqi Pang, Wei Yang, Lan Xu, Jingyi Yu

(Submit to TOG 2020) ACM Transactions on Graphics

We present TightCap, a data-driven scheme to capture both the human shape and dressed garments accurately with only a single 3D human scan.

[ProjectPage] [ArxivPage] [Paper] [Code] [Video] [BibTex]

Popup Image

Pose2Body: Pose-Guided Human Parts Segmentation

Xin Chen*, Zhong Li*, Wangyiteng Zhou, Yingliang Zhang, Jingyi Yu

(ICME 2019 Oral, 15% accept rate) IEEE Conference on Multimedia and Expo

We present a novel technique that we call Pose2Body that robustly conducts human parts segmentation based on the pose estimation results.

[Paper] [Supp] [BibTex]

Popup Image

Sparse Photometric 3D Face Reconstruction Guided by Morphable Models

Xuan Cao, Zhang Chen, Anpei Chen, Xin Chen, Shiying Li, Jingyi Yu

(CVPR 2018) IEEE Conference on Computer Vision and Pattern Recognition

We present a novel 3D face reconstruction technique that leverages sparse photometric stereo (PS) and the latest advances on face registration modeling from a single image.

[Paper] [Supp] [Video] [BibTex]

Popup Image

AutoSweep: Recovering 3D Editable Objects from a Single Photograph

Xin Chen, Yuwei Li, Xi Luo, Tianjia Shao, Jingyi Yu, Kun Zhou, Youyi Zheng

(TVCG 2018) IEEE Transactions on Visualization and Computer Graphics

We present a fully automatic framework for extracting editable 3D objects directly from a single photograph.

[ProjectPage] [ArxivPage] [Paper] [Code] [Video] [BibTex]


Tecent YouTu Lab

Nov. 2020 - Present

Algorithm Engineer Intern

I work as a algorithm engineer intern at Tecent YouTu Lab in 2020 for researching on the 3D human body reconstruction.

DGene Digital Technology Inc.

Jul. 2018 - Dec. 2019

R&D Intern

I work as a part-time research and development intern at DGene Digital Technology Inc. and won the Best Outstanding Intern Award in 2018 for leading the mobile virtual fitting project.

Ph.D. Student

I am now a Ph.D. student at VRVC under the supervision of Prof. Jingyi Yu, working on human performance capture including human reconstruction, clothing capture, and shape estimation.

ShanghaiTech University

Sep. 2016 - Jul. 2018

Master Student

I spent 2 years on computer graphics research, advised by Dr. Youyi Zheng and developed a fully automatic framework for recovering 3D editable objects from a single photograph, published on TVCG 2018.

Qingdao University of Technology

Sep. 2012 - Jul. 2016


I received a B.S. degree in electronic information science and technology and won honorable awards including:

  • National Encouragement Scholarship 2016
  • Provincial Government Scholarship 2015
  • Second Prize in China Mathematical Contest in Modeling 2015
  • Province-level Merit Student 2013
  • Supervisors

    Prof. Jingyi Yu - Supervisor

  • IEEE Fellow
  • Program chair of ICPR 2020 and CVPR 2021
  • Executive Dean, SIST, ShanghaiTech University
  • Founder, DGene Inc.
  • Ph.D.'s degree, MIT, 2005
  • Dr. Youyi Zheng - Former Supervisor

  • Hundred Talents Program, ZheJiang Univeristy
  • Researcher, State Key Lab of CAD&CG, ZheJiang Univeristy
  • Ph.D.'s degree, Hong Kong University of Science and Technology, 2011
  • Skills

    Programming Languages