Zhixuan Yu

3D Computer Vision Research Scientist at Meta

Redwood City, California, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Zhixuan Yu is a 3D computer vision research scientist with nine years of experience building photorealistic human models and perception systems, currently advancing telepresence at Meta Reality Labs. He blends deep academic rigor—a PhD from the University of Minnesota and NeurIPS/CVPR publications—with hands-on industry work at Google and Meta on NeRF-based head avatars, multi-view human capture, and few-shot user adaptation. His projects span dense keypoint estimation, large-scale multiview datasets (HUMBI), and practical system engineering from a 107-camera capture rig to auto-calibration for sports and autonomous sensing. Notably, he has led teams for large data collection efforts and translated research into patents and top-tier conference submissions, demonstrating both experimental depth and production-minded impact. Based in Redwood City, he combines expertise in machine learning, multiple-view geometry, and digital human modeling to push realistic VR/AR communication forward.
code9 years of coding experience
job7 years of employment as a software developer
bookDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Minnesota
bookBachelor’s Degree, Biomedical Engineering, Bachelor’s Degree, Biomedical Engineering at Huazhong University of Science and Technology
bookMaster’s Degree, Biomedical Engineering, Master’s Degree, Biomedical Engineering at Carnegie Mellon University
languagesEnglish, Chinese
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (14)

matlab9
skeleton6
action-recognition6
video-understanding5
data-efficient4
3d4
autoencoder4
self-supervised-learning4
deep-learning3
pytorch3
computer-vision3
graph3
vision-transformer3
transformer2

Programming languages (2)

MATLABPython

Github contributions (5)

github-logo-circle
zhixuany/HUMBI

Jun 2020 - Mar 2022

This repository contains official code (in MATLAB) for exploring and visualizing HUMBI dataset introduced in the paper "HUMBI: A Large Multiview Dataset of Human Body Expressions" (CVPR 2020).
Contributions:5 commits, 2 PRs, 8 pushes in 1 year 9 months
matlab
Contributions:6 pushes in 5 days
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial