Ahmed Tawfik Aboukhadra

I'm a Researcher at the Augmented Vision department at DFKI and a PhD student at RPTU in Kaiserslautern working on hand object pose estimation and 3D reconstruction from RGB and Depth using Deep Learning methods such as GCNs and Transformers since October 2021. I have a M.Sc. in Artificial Intelligence from Maastricht University and a B.Sc. in Computer Science from the German University in Cairo.

Email | Google Scholar | LinkedIn | GitHub

Experience

Oct 2021 - Now Researcher

Augmented Vision, DFKI Kaiserslautern, Germany

Hand-Object 3D Reconstruction from RGB and depth using Deep Learning networks such as GCNs and Transformers

March 2021 - August 2021 M.Sc. Thesis

CISPA Saarbrücken, Germany

ML Privacy: Investigating defenses against ML attacks on deep ConvNets as a Master thesis

Sep 2020 - Jan 2021 ML Intern

HackerOne Groningen, The Netherlands

Worked on developing an ML-based system for detecting duplicate vulnerability reports using NLP techniques such as Word Embedding and BERT

Education

October 2021 - Ongoing Ph.D. in Computer Science

RPTU Kaiserslautern, Germany

Sep 2019 - August 2021 M.Sc. in Artificial Intelligence

Maastricht University Maastricht, The Netherlands

Oct 2014 - May 2019 B.Sc. in Computer Science and Engineering

German University in Cairo (GUC) Cairo, Egypt

Teaching

Nov 2022 Lecturer

RPTU Kaiserslautern, Germany

Graph Convolutional Networks and Transformers and their applications in 3D Pose Estimation

Oct 2019 - May 2020 Teaching Assistant

Maastricht University Maastricht, The Netherlands

OOP using Java, Machine Learning, and Data Structures and Algorithms

Oct 2018 - May 2019 Teaching Assistant

German University in Cairo (GUC) Cairo, Egypt

Introduction to CS using Python

Publications

SurgeoNet: Realtime 3D Pose Estimation of Articulated Surgical Instruments using a Synthetically-trained Network

Ahmed Tawfik Aboukhadra, Nadia Robertini, Jameel Malik, Ahmed Elhayek, Gerd Reis, Didier Stricker; German Conference on Pattern Recognition (GCPR), 2024

Paper | Code

ShapeGraFormer: GraFormer-Based Network for Hand-Object Reconstruction from a Single Depth Map

Ahmed Tawfik Aboukhadra, Jameel Malik, Nadia Robertini, Ahmed Elhayek, Didier Stricker; IEEE Access, 2024

Paper

THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervision

Ahmed Tawfik Aboukhadra, Jameel Malik, Ahmed Elhayek, Nadia Robertini, Didier Stricker; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023

Paper | Code

Achievements

2019 M.Sc. Scholarship

UM Holland High-Potential Scholarship Holder 2019. €58,000 grant to pursue a MSc in AI.

2017 ACPC Finalist

Finalist at Arab Collegiate Programming Contest (ACPC) 2017, 28th Place.