activity
20182021
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2021

FAST3D: Flow-Aware Self-Training for 3D Object Detectors

Christian Fruhwirth-Reisinger, Michael Opitz, Horst Possegger +1

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high…

cs.CV2021

Robustness of Object Detectors in Degrading Weather Conditions

Muhammad Jehanzeb Mirza, Cornelius Buerkle, Julio Jarquin +4

State-of-the-art object detection systems for autonomous driving achieve promising results in clear weather conditions. However, such autonomous safety critical systems also need t…

cs.CV2019

FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data

Georg Krispel, Michael Opitz, Georg Waltner +2

We introduce a simple yet effective fusion method of LiDAR and RGB data to segment LiDAR point clouds. Utilizing the dense native range representation of a LiDAR sensor and the set…

cs.CV2018

MURAUER: Mapping Unlabeled Real Data for Label AUstERity

Georg Poier, Michael Opitz, David Schinagl +1

Data labeling for learning 3D hand pose estimation models is a huge effort. Readily available, accurately labeled synthetic data has the potential to reduce the effort. However, to…

cs.CV2018

Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems

Georg Waltner, Michael Maurer, Thomas Holzmann +5

Automated toll systems rely on proper classification of the passing vehicles. This is especially difficult when the images used for classification only cover parts of the vehicle.…

cs.CV2018

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly

Michael Opitz, Georg Waltner, Horst Possegger +1

Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of embeddings. In this work, we show how to improve the robustness…