Baris Gecer
Senior Applied Scientist at Amazon
England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolBaris Gecer is a Senior Applied Scientist at Amazon Studios & Prime Video with a PhD from Imperial College London and a decade of experience translating human faces into photorealistic 3D assets for AR/VR. He specializes in 3D face reconstruction, neural rendering and GAN-based synthesis, combining research depth with production engineering from roles at Huawei, Facesoft and Meta Reality Labs. Baris has filed multiple patents on high-fidelity face generation and contributed to the widely used InsightFace project—adding graphonomy-based segmentation and AvatarMe compatibility to improve OSTeC reconstructions. His work balances preserving identity, expression and motion with practical export pipelines (OBJ) for downstream applications, and he maintains notable open-source impact (projects with 14K+ GitHub stars). Based in England, he brings a rare mix of academic pedigree, industrial delivery and hands-on ML engineering to digital human creation.
10 years of coding experience
6 years of employment as a software developer
Bachelor's degree, Computer Engineering, 3.55/ 4, Bachelor's degree, Computer Engineering, 3.55/ 4 at Hacettepe ÜniversitesiDoctor of Philosophy (PhD), Computer Science, Doctor of Philosophy (PhD), Computer Science at Imperial College LondonMaster of Science (M.S.), Computer Science, 3.83, Master of Science (M.S.), Computer Science, 3.83 at Bilkent UniversityExchange Program, Computer Science, 8.43/10, Exchange Program, Computer Science, 8.43/10 at University of Groningen
Turkish, English
Github Skills (9)
face-detection10
computer-vision10
pytorch10
python10
recovery10
image-processing10
face-recognition10
3d-reconstruction10
opencv9
Programming languages (2)
Github contributions (5)
deepinsight/insightface
May 2022 - May 2022
State-of-the-art 2D and 3D Face Analysis Project
Role in this project:
ML Engineer
ML EngineerContributions:11 commits, 2 pushes in 1 day
Contributions summary:Baris's contributions focus on improving the OSTeC (Optimized Structure-from-Texture and Environment Consistency) face reconstruction project. They implemented graphonomy-based face/hair segmentation for more robust masking, modified the image reading process, and optimized landmark differentiability by integrating heatmaps. The user also adapted the code to run with the AvatarMe topology and exported the final results as an OBJ file.
face-recognitionretinafacestate-of-the-artface-analysisarcface
barisgecer/facegan
Aug 2017 - Apr 2020
Contributions:156 commits, 14 pushes, 6 branches in 2 years 8 months
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.