28 citations · 81 across the 10 of their papers we have counts for
10 papers
Label-Efficient LiDAR Panoptic Segmentation
Ahmet Selim Çanakçı, Niclas Vödisch, Kürsat Petek +2
A main bottleneck of learning-based robotic scene understanding methods is the heavy reliance on extensive annotated training data, which often limits their generalization ability.…
LetsMap: Unsupervised Representation Learning for Semantic BEV Mapping
Nikhil Gosala, Kürsat Petek, B Ravi Kiran +4
Semantic Bird's Eye View (BEV) maps offer a rich representation with strong occlusion reasoning for various decision making tasks in autonomous driving. However, most BEV mapping a…
A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation
Niclas Vödisch, Kürsat Petek, Markus Käppeler +2
A key challenge for the widespread application of learning-based models for robotic perception is to significantly reduce the required amount of annotated training data while achie…
Automatic Target-Less Camera-LiDAR Calibration From Motion and Deep Point Correspondences
Kürsat Petek, Niclas Vödisch, Johannes Meyer +3
Sensor setups of robotic platforms commonly include both camera and LiDAR as they provide complementary information. However, fusing these two modalities typically requires a highl…
BEVCar: Camera-Radar Fusion for BEV Map and Object Segmentation
Jonas Schramm, Niclas Vödisch, Kürsat Petek +4
Semantic scene segmentation from a bird's-eye-view (BEV) perspective plays a crucial role in facilitating planning and decision-making for mobile robots. Although recent vision-onl…
Panoptic Out-of-Distribution Segmentation
Rohit Mohan, Kiran Kumaraswamy, Juana Valeria Hurtado +2
Deep learning has led to remarkable strides in scene understanding with panoptic segmentation emerging as a key holistic scene interpretation task. However, the performance of pano…
Few-Shot Panoptic Segmentation With Foundation Models
Markus Käppeler, Kürsat Petek, Niclas Vödisch +2
Current state-of-the-art methods for panoptic segmentation require an immense amount of annotated training data that is both arduous and expensive to obtain posing a significant ch…
CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation
Niclas Vödisch, Kürsat Petek, Wolfram Burgard +1
Operating a robot in the open world requires a high level of robustness with respect to previously unseen environments. Optimally, the robot is able to adapt by itself to new condi…
SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images
Nikhil Gosala, Kürsat Petek, Paulo L. J. Drews-Jr +2
Bird's-Eye-View (BEV) semantic maps have become an essential component of automated driving pipelines due to the rich representation they provide for decision-making tasks. However…
Robust Monocular Localization in Sparse HD Maps Leveraging Multi-Task Uncertainty Estimation
Kürsat Petek, Kshitij Sirohi, Daniel Büscher +1
Robust localization in dense urban scenarios using a low-cost sensor setup and sparse HD maps is highly relevant for the current advances in autonomous driving, but remains a chall…