Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Semantic SLAM with Quality-adaptive Properties
We do not need everything in anything. Reconstructing our 3D world is not an exception. In many applications (e.g., construction progress monitoring) we only need to reconstruct certain semantics in high fidelity (quality) — e.g., only walls or chairs; the rest of the world can be reconstructed in lower quality. The goal of this project is to devise a semantic Simultaneous Localization and Mapping (SLAM) method that reconstructs the world in a quality-adaptive manner; which means it only reconstructs with high fidelity a queried semantic, leaving the rest in a lower level of fidelity.
Not specified
Not specified
Daniel Barath (dbarath@ethz.ch), Iro Armeni (armeni@ibi.baug.ethz.ch)
Daniel Barath (dbarath@ethz.ch), Iro Armeni (armeni@ibi.baug.ethz.ch)