Summary
Onat Şahin is a PhD candidate at Technical University of Munich with eight years of hands-on experience in computer vision, machine learning and deep learning, specializing in AI-generated content and simulation-empowering models. He has applied NeRF-based 3D reconstruction and synthetic data generation for object recognition, built OCR multi-task networks for historical Ottoman documents, and experimented with few-shot and self-supervised detection pipelines using Detectron2. His work bridges academic research and industry practice through collaborations with Huawei and PreciTaste, combining rigorous experimentation in PyTorch with deployment-minded skills in ROS and point-cloud processing. Based in Munich, he brings a practical focus on robust model training (e.g., manifold mixup, feature pyramid exploration) that reflects both research depth and applied product impact.
8 years of coding experience
1 year of employment as a software developer
Bachelor of Science - BS, Computer Engineering, GPA: 3.63 / 4.00, Bachelor of Science - BS, Computer Engineering, GPA: 3.63 / 4.00 at İstanbul Teknik Üniversitesi
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at Technical University of Munich
Turkish, English, German