Georgia Gkioxari
Assistant Professor at Caltech
United States
Summary
🤩
Rockstar🎓
Top SchoolGeorgia Gkioxari is an Assistant Professor at Caltech with 11 years of experience at the intersection of computer vision and 3D deep learning. Trained in electrical and computer engineering in Athens and AI at UC Berkeley, she brings a strong academic foundation to hands-on engineering challenges. Her open-source contributions to high-profile Facebook Research projects like PyTorch3D and Mesh R-CNN demonstrate expertise in point cloud and mesh processing, numerical robustness, and performance optimization. She has implemented core functions for point-to-mesh distance, texture sampling, and mesh smoothing—skills that translate directly into scalable research code and reproducible systems. Known for bridging research and production, she focuses on making advanced 3D algorithms both reliable and efficient. An underrated strength is her ability to improve legacy codebases pragmatically, enhancing compatibility and stability while advancing new features.
11 years of coding experience
Artificial Intelligence, Artificial Intelligence at University of California, BerkeleyDiploma, Electrical and Computer Engineering, Diploma, Electrical and Computer Engineering at National Technical University of Athens
Github Skills (21)
pytorch10
3d-graphics10
python10
computer-vision10
point-cloud10
mesh-processing10
preprocess9
preprocessing9
c-language9
algorithm9
code-optimization9
algorithms9
optimisation9
numerical-optimization9
dataprep9
Programming languages (4)
Github contributions (5)
facebookresearch/meshrcnn
Jan 2020 - Sep 2021
code for Mesh R-CNN, ICCV 2019
Role in this project:
ML Engineer
ML EngineerContributions:11 commits, 3 PRs, 5 branches in 1 year 7 months
Contributions summary:Georgia primarily contributes to the Mesh R-CNN project by modifying and improving existing code related to the processing of 3D mesh data and evaluation metrics. They've focused on logging, incorporating PyTorch3D compatibility, and optimizing code performance by setting flags. The user has also worked on the dataset pipeline.
pytorchiccviccv-2019meshdeep-learning
facebookresearch/pytorch3d
Jan 2020 - Aug 2022
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Role in this project:ML Engineer
ML EngineerContributions:38 commits, 2 PRs, 1 push in 2 years 7 months
Contributions summary:Georgia contributed significantly to the PyTorch3D library, focusing on enhancing the point cloud and mesh processing capabilities. Their work included implementing and optimizing core functions for point-to-mesh distance calculations, integrating texture sampling functionalities, and adding features related to mesh filtering and smoothing. They also addressed numerical stability issues in existing code, ensuring the library's robustness.
pytorchdeep-learningcomputer-graphicscomputer-vision3d-data
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.