David Schinagl

Dipl.-Ing. Dr.techn. BSc

I received my PhD in Computer Science from Graz University of Technology in 2024 under the supervision of Prof. Horst Bischof. In my thesis I focused on the explainability & optimization of LiDAR-based 3D Object Detection methods. Currently I am a postdoctoral researcher in the Learning, Recognition & Perception (LRP) group. My research focuses on efficient and explainable methods for 3D scene understanding especially in the context of autonomous driving.

david.schinagl@tugraz.at

+43 316 873 - 5046

dschinagl.github.io

Publications

MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds

Krispel, G., Schinagl, D., Fruhwirth-Reisinger, C., Possegger, H., Bischof, H.

Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024, 2023, 3371-3380

GACE: Geometry Aware Confidence Enhancement for Black-box 3D Object Detectors on LiDAR-Data

Schinagl, D., Krispel, G., Fruhwirth-Reisinger, C., Possegger, H., Bischof, H.

Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023, 6566-6576

OccAM’s Laser: Occlusion-Based Attribution Maps for 3D Object Detectors on LiDAR Data

Schinagl, D., Krispel, G., Possegger, H., Roth, P., Bischof, H.

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, 1131-1140

MURAUER: Mapping Unlabeled Real Data for Label AUstERity

Poier, G., Opitz, M., Schinagl, D., Bischof, H.

IEEE Winter Conference on Applications of Computer Vision, 2019

Being lazy at labelling for pose estimation

Poier, G., Schinagl, D., Bischof, H.

Proceedings of the OAGM Workshop 2018, 2018, 130

Learning Pose Specific Representations by Predicting Different Views

Poier, G., Schinagl, D., Bischof, H.

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018