Xingyu Chen (陈星宇)

✉ chenxy.sean[at]gmail.com  

I am currently a Postdoctoral Research Fellow at Peking University, and also an academic visitor at IDEA-CVR, working closely with Prof. Lei Zhang.

Before joining PKU, I have 3.5 years of experience in corporations, Kuaishou and Xiaobing, working closely with Dr. Baoyaun Wang.

I obtained my Ph.D. in Control Science and Engineering from Institute of Automation, Chinese Academy of Science in 2020, under the supervision of Prof. Junzhi Yu. Previously I received my B.S. in Electrical Engineering and Automation from Chengdu University of Technology in 2015.

I'm seeking research interns. Feel free to send me an email if you are interested.

(here for full publications)

We propose a end-to-end framework for hand detection, 2D pose estimation, and 3D mesh reconstruction. Also, the HandOS is a unified representation for left and right hands.

Our HaveFun framework can create human avatars from few-shot unconstrained images.

We propose a novel 3D-aware GAN that can directly render high-resolution images.

We propose a HandAvatar framework, the first method for neural hand rendering with self-occluded illumination.

We propose a framework for single-view hand mesh reconstruction, which can simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal coherence.

We reconstruct 3D hand by dividing camera-space mesh recovery into two sub-tasks, i.e., root-relative mesh recovery and root recovery.

We propose a temporal detection method based on anchor and feature offset refinements.

We propose a GAN-RS to elevate underwater visual quality.

The website template was adapted from Yu Deng.