Seminar: Simulating Reality for Boosting AI: Application of 3D Synthetic Data in Object Detection

Important: This page is currently under construction - changes (including content) are still possible until the start of the event.

Seminar Overview

Large quantities of labeled data are needed for deep learning concepts. In the recent research and trends, synthetic data has provided promising results to boost the learning procedure. In addition to reducing ethical concerns (e.g., privacy) and providing the possibility to acquire data that are difficult to be produced in the real world, synthetic data are easier to generate and pre-annotate. Currently there are several frameworks that provide the possibility to accelerate the training and accuracy of perception networks based on the synthetic data (for example: NVIDIA Omniverse ReplicatorUnity Computer Vision, and Unreal GT). In this seminar students have the possibility to use any available framework to implement an object detection application based on 3D synthetic data. The 3D data will be provided to the students and students will have free choice for selecting an open source or commercial technology for building their prototype. The result of this hands-on project will be an object detection system in virtual reality using the same 3D objects that are used during training phase. Students will be presenting their research and prototype findings in several stages of the seminar. These projects will be realized in groups of three participants (total of four groups).  

Requirements

Hands-on skills, motivation to do research and build prototypes. Previous background in machine and deep learning as well as computer vision is beneficial but not required if you are committed to learn fast the relevant fundamentals.

General Information

  • Location: tbd
  • Time: tbd 
  • Credit Points: 7 
  • Language: English 
  • Places: max. 12

Contact

Registration

If you want to attend the seminar, please register here.