Services
Selected Publications (Complete list…)
End-to-End 3D Dense Captioning with Vote2Cap-DETR
Sijin Chen, Hongyuan Zhu, Xin Chen,
Yinjie
Lei, Tao Chen, Gang Yu
CVPR 2023
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
[Project] [Code] [Arxiv] [Paper] [Video] [BibTex]
See all publications ...
Projects (More projects…)
MotionGPT:Motion-Language Generations
A unified and user-friendly motion-language model to learn the semantic coupling of two modalities and generate high-quality motions and text descriptions on multiple motion tasks.
Motion Latent Diffusion Models
Human-Object Motion Capture
Using 13 infrared cameras for complex motion capture. We collected a complex motion dataset to assist challenging monocular motion capture for sports video.
Light Stage
Multi-view light stage system for MoCap and 3D Reconstruction.
Dynamic 3D Mesh Player
Stand-alone development work for free-view browsing on 4D scans, which supports 3D mesh rendering, free-angle viewpoint change, Poisson Surface Reconstruction.
I am as a performer for boxing.
Multi-view Dome System
Using more than 72 cameras for dynamic human reconstruction.
Poping result with free view-points.
Avatar with high fidelity clothes and face.
Dome System for static objects
Using more than 80 cameras for multi-view stereo reconstruction. Lead the reconstruction project and aim to build a large 3D mesh sequences dataset.
Experiences
PCG QQ - Research Scientist
Feb. 2022 - Present
CSIG YouTu Lab -Research Scientist Intern
Nov. 2020 - Mar. 2021
I am working at Tencent, Shanghai and received Tencent STAR Award 2023.
I was a research scientist intern at Tencent YouTu Lab in 2020 focuing on the 3D human body reconstruction.
University of Chinese Academy of Sciences - 中国科学院大学
Sep. 2018 - Feb. 2022
Ph.D. Degree
I received my Ph.D. degree from UCAS under the supervision of Prof. Jingyi Yu, working on human performance capture including human reconstruction, clothing capture, and shape estimation.
ShanghaiTech University - 上海科技大学
Sep. 2016 - Jul. 2018
Master Student
I spent 2 years on computer graphics research, advised by Prof. Youyi Zheng and developed a fully automatic framework for recovering 3D editable objects from a single photograph, published on TVCG 2018 (Top journal in graphics).
Qingdao University of Technology
Sep. 2012 - Jul. 2016
Bachelor
I received a B.S. degree in electronic information science and technology and won honorable awards including:
Supervisors
Prof. Jingyi Yu - Supervisor
Prof. Youyi Zheng - Former Supervisor