Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Augmented Reality large-scale localization
In this project we aim to develop real-time Augmented Reality (AR) system that robustly and accurately localizes in accurate 3D data. This project can follow different avenues based on the interest of the student.
Augmented Reality is at the verge of wide-spread application. One crucial functionality for such systems is to reason about the physical world and visually aid the user in interacting with it.
In this project we aim to develop real-time systems that robustly and accurately localize in 3D scans of the real-world using AR systems (preferably vision sensing). This project can follow different avenues based on the interest of the student, e.g., improving on existing localization frameworks towards robustness and accuracy, or looking into novel solutions to robustly bridge / fuse between sensor modalities (e.g., RGB, RGB-D, LiDAR). This project offers an open-ended discovery of novel technological solutions to one of the most relevant problems in AR technology.
Augmented Reality is at the verge of wide-spread application. One crucial functionality for such systems is to reason about the physical world and visually aid the user in interacting with it.
In this project we aim to develop real-time systems that robustly and accurately localize in 3D scans of the real-world using AR systems (preferably vision sensing). This project can follow different avenues based on the interest of the student, e.g., improving on existing localization frameworks towards robustness and accuracy, or looking into novel solutions to robustly bridge / fuse between sensor modalities (e.g., RGB, RGB-D, LiDAR). This project offers an open-ended discovery of novel technological solutions to one of the most relevant problems in AR technology.
- Familiarize yourself with the current state of the art.
- Investigate existing solutions for accurate RGB(-D) localization
- Develop novel algorithms to address the challenges of multi-modal localization in real-world applications.
- Test your algorithms on evaluation data, and real AR systems.
- Familiarize yourself with the current state of the art. - Investigate existing solutions for accurate RGB(-D) localization - Develop novel algorithms to address the challenges of multi-modal localization in real-world applications. - Test your algorithms on evaluation data, and real AR systems.
- Good understanding of algorithmic challenges.
- Knowledge of C++ is mandatory, Python is recommended.
- Knowledge of ROS is recommended.
- Knowledge in two of the following areas: SLAM, Localization, sensor fusion, computer vision, deep learning.
- Be curious about pushing the limits of today's Augmented Reality capabilities.
- Strong self-motivation and critical mind.
- Students from outside of D-MAVT (particularly, from D-INFK, D-ITET, D-PHYS, and D-MATH) are also highly encouraged to apply.
- Good understanding of algorithmic challenges. - Knowledge of C++ is mandatory, Python is recommended. - Knowledge of ROS is recommended. - Knowledge in two of the following areas: SLAM, Localization, sensor fusion, computer vision, deep learning. - Be curious about pushing the limits of today's Augmented Reality capabilities. - Strong self-motivation and critical mind. - Students from outside of D-MAVT (particularly, from D-INFK, D-ITET, D-PHYS, and D-MATH) are also highly encouraged to apply.
Please send your cv and transcripts (Bachelor & Master) to: Abel Gawel (gawela@ethz.ch), Fadri Furrer (fadri@ethz.ch), and Timothy Sandy (tsandy@ethz.ch).
Please send your cv and transcripts (Bachelor & Master) to: Abel Gawel (gawela@ethz.ch), Fadri Furrer (fadri@ethz.ch), and Timothy Sandy (tsandy@ethz.ch).