1 citations · 1 across the 7 of their papers we have counts for
8 papers
PointTransformerX: Portable and Efficient 3D Point Cloud Processing without Sparse Algorithms
Laurenz Reichardt, Nikolas Ebert, Oliver Wasenmüller
3D point cloud perception remains tightly coupled to custom CUDA operators for spatial operations, limiting portability and efficiency on non-NVIDIA, AMD, and embedded hardware. We…
D-PLS: Decoupled Semantic Segmentation for 4D-Panoptic-LiDAR-Segmentation
Maik Steinhauser, Laurenz Reichardt, Nikolas Ebert +1
This paper introduces a novel approach to 4D Panoptic LiDAR Segmentation that decouples semantic and instance segmentation, leveraging single-scan semantic predictions as prior inf…
Classifier Ensemble for Efficient Uncertainty Calibration of Deep Neural Networks for Image Classification
Michael Schulze, Nikolas Ebert, Laurenz Reichardt +1
This paper investigates novel classifier ensemble techniques for uncertainty calibration applied to various deep neural networks for image classification. We evaluate both accuracy…
Text3DAug -- Prompted Instance Augmentation for LiDAR Perception
Laurenz Reichardt, Luca Uhr, Oliver Wasenmüller
LiDAR data of urban scenarios poses unique challenges, such as heterogeneous characteristics and inherent class imbalance. Therefore, large-scale datasets are necessary to apply de…
RadarPillars: Efficient Object Detection from 4D Radar Point Clouds
Alexander Musiat, Laurenz Reichardt, Michael Schulze +1
Automotive radar systems have evolved to provide not only range, azimuth and Doppler velocity, but also elevation data. This additional dimension allows for the representation of 4…
360 from a Single Camera: A Few-Shot Approach for LiDAR Segmentation
Laurenz Reichardt, Nikolas Ebert, Oliver Wasenmüller
Deep learning applications on LiDAR data suffer from a strong domain gap when applied to different sensors or tasks. In order for these methods to obtain similar accuracy on differ…