
Dr. Ahmed Elhayek
E-Mail: | ahmed.elhayek@dfki.de |
---|---|
Position: | Former Employee |
Phone: | +49 (0)631 20575 3560 |
Dr. Ahmed Elhayek received his Master degree from Saarland University in the year 2010 where he developed a novel simultaneous interpolation and deconvolution approach for 3D reconstruction of cell images. He worked on implementing a deblurring algorithm for high-speed motion capture during his internship in the Max-Planck-Institute for Informatics. He received his PhD degree from the Max-Planck-Institute and Saarland University in the 2015. The research topic of his PhD was “human motion capture in general uncontrolled environments with sparse multi-camera setup”. After his PhD, he joined the the Augmented Vision group at DFKI as a researcher.
THOR-Net: End-to-End Graformer-Based Realistic Two Hands and Object Reconstruction With Self-Supervision
In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE Winter Conference on Applications of Computer Vision (WACV-2023), January 3-7, Waikoloa, Hawaii, USA, Pages 1001-1010, IEEE, 2023.
Details
| Link 1
| Link 2
HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 1 Seiten 1-13 IEEE 11/2021 .
Details
| Link 1
HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). International Conference on Computer Vision and Pattern Recognition (CVPR-2020) June 14-19 The Washington State Convention Center Washington United States IEEE 2020 .
Details
| Link 1
| Link 2
| Link 3
Real-Time Energy Efficient Hand Pose Estimation: A Case Study
Sensors - Open Access Journal (sensors) 20 Seiten 1-27 MDPI 5/2020 .
Details
| Link 1
| Link 2
WHSP-Net: A Weakly-Supervised Approach for 3D Hand Shape and Pose Recovery from a Single Depth Image
Sensors - Open Access Journal (sensors) 19 Seiten 2-15 Sensors 8/2019 .
Details
| Link 1
| Link 2
Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data
Sensors - Open Access Journal (sensors) 19 20 Seite 20 MDPI 10/2019 .
Details
| Link 1
| Link 2
Simple and effective deep hand shape and pose regression from a single depth image
Computers & Graphics (CAG) 85 Seiten 85-91 ELSEVIER 10/2019 .
Details
| Link 1
Structure-aware 3D Hand Pose Regression from a Single Depth Image
EuroVR (EuroVR-2018), October 22-23, London, United Kingdom
Details
| Link 1
DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth
International Conference on 3D Vision (3DVision-2018), September 5-8, Verona, Italy
Details
| Link 1
| Link 2
Fully Automatic Multi-person Human Motion Capture for VR Applications
EuroVR (EuroVR-2018), October 22-23, London, United Kingdom
Details
| Link 1
3DAirSig: A Framework for Enabling In-Air Signatures Using a Multi-Modal Depth Sensor
Sensors - Open Access Journal (sensors) 18 11 Seite 3872 MDPI AG Basel, Switzerland 11/2018 .
Details
| Link 1
Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image
International Conference on 3DVision (3DV-2017), 5th, October 10-12, Qingdao, China
Details
| Link 1
3D Human Pose Tracking inside Car using Single RGB Spherical Camera
ACM Chapters Computer Science in Cars Symposium (CSCS-17), July 6, Munich, Germany
Details
| Link 1