Bautembach, D., Oikonomidis, I., & Argyros, A. (2021). Multi-GPU SNN Simulation with Perfect Static Load Balancing. Submitted to IJCNN 2021.
We present the first SNN simulator to scale to 8 GPUs, allowing you to simulate larger models and in less time than ever before. Features include:
- State of the art performance (incl. lightning fast setup)
- Ability to define custom models in native C++
- Modern, user-friendly API
- No 3rd-party dependencies (except CUDA)
Bautembach, D., Oikonomidis, I., Kyriazis, N., & Argyros, A. (2020, July). Faster and Simpler SNN Simulation with Work Queues. In 2020 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
“Spice” is a state of the art spiking neural network simulator written in C++ and CUDA. It
- is up to 3x faster than the competition,
- allows you to specify your own models through a modern and intuitive API (you simply inherit from a model base class and override callbacks),
- builds out of the box without any 3rd-party dependencies (apart from CUDA), and
- does not involve any proprietary compilation steps or domain-specific languages.
Bautembach, D., Oikonomidis, I., & Argyros, A. (2018, June). A Comparative Study of Matrix Completion and Recovery Techniques for Human Pose Estimation. In Proceedings of the 11th PErvasive Technologies Related to Assistive Environments Conference (pp. 23-30).
We estimate human poses by treating them as missing/incomplete rows in a “pose database” matrix and calculating missing entries via matrix completion.
Chen, J., Bautembach, D., & Izadi, S. (2013). Scalable real-time volumetric surface reconstruction. ACM Transactions on Graphics (ToG), 32(4), 1-16.
KinectFusion is a well-known 3D scanner powered by Microsoft’s Kinect camera. It has recently found its way into the official Kinect for Windows SDK. While KinectFusion produces very high-quality scans in real-time, it is limited to relatively small spaces.
In this paper we extend KinectFusion with a sparse data structure and streaming, allowing us to scan areas of virtually infinite size while maintaining the quality and performance of the original algorithm.
Unpublished BSc thesis
Voxels date back 20 years. They have many advantages over polygon meshes. However, they always suffered form the lack of a hardware-accelerated rendering pipeline and the infeasiblity of animating them. I tackled this age-old computer graphics problem in my BSc thesis. The (GPU-accelerated) animation technique I developed enables:
- Skeletal animation of voxels models
- Rendering of mixed polygon- and voxel-based content.
Research Software Engineer
- Replacing polygon meshes with volumetric representations to unify the game content creation pipeline (combine modelling, texturing, animation into a single workflow).
- Non-rigid 3D reconstruction as an alternative to performance capture.
Developed cutscene animation tools for CINEBOX®, a film preproduction software based on the CRYENGINE.
2012 - 2013
Scaled KinectFusion to scenes of arbitrary size.
Authored “FuSci”, a non-invasive foliage measurement software for the University of Cambridge’s biology department.
Junior Software Developer
Designed a task planning software (“Maschinenbelegung”) for a local fulfillment service in Hamburg.
Created personal and commercial webistes.
University of Crete
PhD Computer Science
2015 - present
Area of specialization: Spiking Neural Networks (simulation, multi-GPU parallelization, applications). See publications/projects for more. Expected to graduate in summer 2021.