Yinyu Nie
Generative ML Engineer
Stony Stratford, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolYinyu Nie is a Generative ML Engineer at Snap Inc. with eight years of research and applied experience in 3D computer vision, geometric learning and scene reconstruction stemming from a PhD and postdoctoral work at Technical University of Munich. He has transitioned research into industry roles at Huawei and now Snap, focusing on practical generative and 3D modeling systems. Beyond papers, he maintains tooling-oriented open-source work—automating and UX-improving a curated 3D shape/scene paper repository—to streamline literature curation and reproducibility. Based in the UK, he blends deep academic rigor with production-focused engineering, often tackling unsupervised and geometry-aware learning problems that bridge vision research and real-world product needs.
8 years of coding experience
5 years of employment as a software developer
Doctor of Philosophy - PhD 3D Computer Vision, Doctor of Philosophy - PhD 3D Computer Vision at Bournemouth University
Github Skills (7)
python10
command-line9
3d-reconstruction9
command-line-interface9
markdown-it8
regular-expression8
markdown8
Programming languages (2)
Github contributions (5)
yinyunie/3D-Shape-Analysis-Paper-List
Dec 2019 - Jan 2023
A list of recent papers, libraries and datasets about 3D shape/scene analysis (by topics, updating).
Role in this project:
Back-end Developer
Back-end DeveloperContributions:152 commits, 4 PRs, 146 pushes in 3 years 1 month
Contributions summary:Yinyu's primary contribution involves enhancing and automating a paper list repository. They developed a Python script (`add_paper_script.py`) to add new papers, incorporating functionalities like parsing arXiv links and extracting titles. The user optimized the user interface by implementing an interactive command-line interface. They further maintained the repository by updating dependencies and fixing existing code to ensure the continued smooth addition of new entries.
scene-reconstructionshape-completionscene-understanding3d-reconstructioncomputer-vision
GAP-LAB-CUHK-SZ/RfDNet
Apr 2021 - Dec 2022
Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
Contributions:23 commits, 21 pushes, 13 comments in 1 year 9 months
scene-reconstructionscene-understandingpoint-cloudpointcloudunderstanding
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.