Register now After registration you will be able to apply for this opportunity online.
OpenSet Semantic SLAM
The goal of the project is to create a Simultaneous Localization and Mapping algorithm that, besides estimating the camera trajectory and the geometry of the scene, also obtains object instances. These object instances should not be restricted to a fixed set of classes (e.g., chair, table). Hence, the problem is open set segmentation.
Keywords: SLAM, semantics, reconstruction
The goal of the project is to create a Simultaneous Localization and Mapping algorithm that, besides estimating the camera trajectory and the geometry of the scene, also obtains object instances. These object instances should not be restricted to a fixed set of classes (e.g., chair, table). Hence, the problem is open-set segmentation. The main idea is to extend the recently published [1], so that it can handle openset object descriptors.
[a] Miao, Y., Armeni, I., Pollefeys, M. and Barath, D., 2023. Volumetric semantically consistent 3d panoptic mapping. arXiv preprint arXiv:2309.14737. (https://arxiv.org/abs/2309.14737)
The goal of the project is to create a Simultaneous Localization and Mapping algorithm that, besides estimating the camera trajectory and the geometry of the scene, also obtains object instances. These object instances should not be restricted to a fixed set of classes (e.g., chair, table). Hence, the problem is open-set segmentation. The main idea is to extend the recently published [1], so that it can handle openset object descriptors.
[a] Miao, Y., Armeni, I., Pollefeys, M. and Barath, D., 2023. Volumetric semantically consistent 3d panoptic mapping. arXiv preprint arXiv:2309.14737. (https://arxiv.org/abs/2309.14737)
