Zhixuan Yu (喻志轩)

I am a Ph.D. candidate in Computer Science at University of Minnesota, Twin Cities, advised by Prof. Hyun Soo Park. Before this journey, I earned my Master's degree from Carnegie Mellon University, under the guidance of Prof. George Stetten, and Bachelor's degree from Huazhong University of Science and Technology. I grew up in Nanjing, a beautiful and historic city in China.

My background spans the fields of computer vision, machine learning, and robot perception, with a particular interest in 3D vision. Over the past few years, my work has primarily focused on humans: 2D/3D pose estimation, geometry reconstruction, 3D animatable avatar creation/generation. Additionally, I led the creation of a large-scale multi-view dataset for human body, hand, face and gaze.


Email: yu000064 (at) umn (dot) edu | zhixuan (dot) yu (at) outlook (dot) com

Google Scholar | Linkedin

Publications

One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation

Zhixuan Yu, Ziqian Bai, Abhimitra Meka, Feitong Tan, Qiangeng Xu, Rohit Pandey, Sean Fanello, Hyun Soo Park, Yinda Zhang

arXiv. 2024.

Paper | Project webpage

Multiview Human Body Reconstruction from Uncalibrated Cameras

Zhixuan Yu, Linguang Zhang, Yuanlu Xu, Chengcheng Tang, Luan Tran, Cem Keskin and Hyun Soo Park

Conference on Neural Information Processing Systems (NeurIPS). 2022.

Paper | Presentation | Poster

HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge

Jae Shin Yoon, Zhixuan Yu, Jaesik Park and Hyun Soo Park

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2021.

(An extension of the CVPR version)

Paper | Dataset

Semi-supervised Dense Keypoints using Unlabeled Multiview Images

Zhixuan Yu, Haozheng Yu, Long Sha, Sujoy Ganguly and Hyun Soo Park

Conference on Neural Information Processing Systems (NeurIPS). 2021.

Spotlight (acceptance rate < 3%)

Paper | Presentation | Poster

HUMBI: A Large Multiview Dataset of Human Body Expressions

Zhixuan Yu*, Jae Shin Yoon*, In Kyu Lee, Prashanth Venkatesh, Jaesik Park, Jihun Yu and Hyun Soo Park

Conference on Computer Vision and Pattern Recognition (CVPR). 2020.

Paper | Dataset | Video | Poster | Github

PalmSight: an assistive technology helping the blind to locate and grasp objects

Zhixuan Yu, Samantha Horvath, Alexandra Delazio, Jihang Wang, Rebeka Almasi, Roberta Klatzky, John Galeotti and George Stetten

Tech. Report, Robotics Institute, Carnegie Mellon University. 2016.

Paper

One-Dimensional Haptic Rendering Using Audio Speaker with Displacement Determined by Inductance

{Avin Khera*, Randy Lee*, Avi Marcovici*, Zhixuan Yu*}, Roberta Klatzky, Mel Siegel, Sanjeev G. Shroff and George Stetten*

Machines. 2016.

Paper

Experience

Google, Mountain View

Research Intern in AR & VR

Jun 2023 - Feb 2024

Meta, Redmond (remote)

Research Intern in Reality Labs

Jun 2021 - Jan 2022

Stats Perform, Chicago

Intern

Jun 2019 - Aug 2019

Delphi, Pittsburgh

Automated Driving Engineer

Apr 2017 - July 2017

Huazhong University of Science and Technology, Wuhan

B.Eng. in Department of Biomedical Engineering

Sep 2011 - Jun 2015

Services

CVPR Reviewer 2019 - 2024

ICCV Reviewer 2023

ECCV Reviewer 2020

NeurIPS Reviewer 2021 / 2023

WACV Reviewer 2020 / 2023

3DV Reviewer 2020

IJCV Reviewer 2021

Last updated: 03/20/2024