no code implementations • 12 Sep 2023 • Laurenz Reichardt, Nikolas Ebert, Oliver Wasenmüller
The teacher is used to pretrain the LiDAR segmentation student network, prior to optional fine-tuning on 360$^\circ$ data.
no code implementations • 18 Aug 2023 • Nikolas Ebert, Didier Stricker, Oliver Wasenmüller
Many medical or pharmaceutical processes have strict guidelines regarding continuous hygiene monitoring.
no code implementations • 18 Jul 2023 • Nikolas Ebert, Laurenz Reichardt, Didier Stricker, Oliver Wasenmüller
In our work, we redesign the powerful state-of-the-art Vision Transformer PLG-ViT to a much more compact and efficient architecture that is suitable for such tasks.
no code implementations • 3 May 2022 • Nikolas Ebert, Patrick Mangat, Oliver Wasenmüller
In order to ensure safe autonomous driving, precise information about the conditions in and around the vehicle must be available.
no code implementations • 21 Oct 2021 • Muhammad Fawwaz Yusri, Patrick Mangat, Oliver Wasenmüller
We consider a simple real-time detection system for drowsiness merely based on the eye blinking rate derived from the eye aspect ratio.
no code implementations • 14 Jul 2021 • Dennis Teutscher, Patrick Mangat, Oliver Wasenmüller
Depth completion from sparse LiDAR and high-resolution RGB data is one of the foundations for autonomous driving techniques.
no code implementations • 14 Jul 2021 • Laurenz Reichardt, Patrick Mangat, Oliver Wasenmüller
We evaluate our Dense Validity Mask Network (DVMN) on the KITTI depth completion benchmark and achieve state of the art results.
Ranked #6 on Depth Completion on KITTI Depth Completion
no code implementations • 7 May 2021 • Steve Dias Da Cruz, Bertram Taetz, Oliver Wasenmüller, Thomas Stifter, Didier Stricker
Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training.
no code implementations • 22 Feb 2021 • Dennis Stumpf, Stephan Krauß, Gerd Reis, Oliver Wasenmüller, Didier Stricker
Large labeled data sets are one of the essential basics of modern deep learning techniques.
1 code implementation • 16 Oct 2020 • Michael Fürst, Shriya T. P. Gupta, René Schuster, Oliver Wasenmüller, Didier Stricker
In-the-wild human pose estimation has a huge potential for various fields, ranging from animation and action recognition to intention recognition and prediction for autonomous driving.
no code implementations • 21 Aug 2020 • René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker
Interpolation of sparse pixel information towards a dense target resolution finds its application across multiple disciplines in computer vision.
no code implementations • 18 Aug 2020 • Rishav, Ramy Battrawy, René Schuster, Oliver Wasenmüller, Didier Stricker
In this paper, we present DeepLiDARFlow, a novel deep learning architecture which fuses high level RGB and LiDAR features at multiple scales in a monocular setup to predict dense scene flow.
no code implementations • 22 Jun 2020 • Rishav, René Schuster, Ramy Battrawy, Oliver Wasenmüller, Didier Stricker
Thus, we present ResFPN -- a multi-resolution feature pyramid network with multiple residual skip connections, where at any scale, we leverage the information from higher resolution maps for stronger and better localized features.
no code implementations • 17 Jun 2020 • Michael Fürst, Oliver Wasenmüller, Didier Stricker
The evaluation of our LRPD approach was done on the pedestrians from the KITTI benchmark.
no code implementations • 28 Jan 2020 • Hartmut Feld, Bruno Mirbach, Jigyasa Katrolia, Mohamed Selim, Oliver Wasenmüller, Didier Stricker
We present a test platform for visual in-cabin scene analysis and occupant monitoring functions.
1 code implementation • 10 Jan 2020 • Steve Dias Da Cruz, Oliver Wasenmüller, Hans-Peter Beise, Thomas Stifter, Didier Stricker
We release SVIRO, a synthetic dataset for sceneries in the passenger compartment of ten different vehicles, in order to analyze machine learning-based approaches for their generalization capacities and reliability when trained on a limited number of variations (e. g. identical backgrounds and textures, few instances per class).
no code implementations • 31 Oct 2019 • Ramy Battrawy, René Schuster, Oliver Wasenmüller, Qing Rao, Didier Stricker
We propose a new approach called LiDAR-Flow to robustly estimate a dense scene flow by fusing a sparse LiDAR with stereo images.
no code implementations • 31 Jul 2019 • Yuriy Anisimov, Oliver Wasenmüller, Didier Stricker
Running time of the light field depth estimation algorithms is typically high.
no code implementations • 25 Jul 2019 • Yuriy Anisimov, Oliver Wasenmüller, Didier Stricker
For the first time, we present a depth camera based on the light field principle, which provides real-time depth information as well as a compact design.
no code implementations • 29 Apr 2019 • Queens Maria Thomas, Oliver Wasenmüller, Didier Stricker
Most LiDAR odometry algorithms estimate the transformation between two consecutive frames by estimating the rotation and translation in an intervening fashion.
no code implementations • 12 Apr 2019 • René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker
Not only the tuning of hyperparameters, but also the gathering and selection of training data, the design of the loss function, and the construction of training schedules is important to get the most out of a model.
1 code implementation • 12 Apr 2019 • Rohan Saxena, René Schuster, Oliver Wasenmüller, Didier Stricker
In the last few years, convolutional neural networks (CNNs) have demonstrated increasing success at learning many computer vision tasks including dense estimation problems such as optical flow and stereo matching.
Ranked #2 on Scene Flow Estimation on KITTI 2015 Scene Flow Test
no code implementations • 5 Apr 2019 • René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker
Our network has a very large receptive field and avoids striding layers to maintain spatial resolution.
no code implementations • 26 Feb 2019 • René Schuster, Oliver Wasenmüller, Christian Unger, Georg Kuschk, Didier Stricker
State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness.
no code implementations • 30 Aug 2018 • René Schuster, Oliver Wasenmüller, Didier Stricker
Scene flow describes 3D motion in a 3D scene.
no code implementations • 30 Aug 2018 • Oliver Wasenmüller, René Schuster, Didier Stricker, Karl Leiss, Jürger Pfister, Oleksandra Ganus, Julian Tatsch, Artem Savkin, Nikolas Brasch
Scene flow describes the 3D position as well as the 3D motion of each pixel in an image.
no code implementations • 20 Jun 2018 • Patrik Feth, Mohammed Naveed Akram, René Schuster, Oliver Wasenmüller
Vehicles of higher automation levels require the creation of situation awareness.
no code implementations • 9 May 2018 • René Schuster, Christian Bailer, Oliver Wasenmüller, Didier Stricker
Thus, we propose in this paper FlowFields++, where we combine the accurate matches of Flow Fields with a robust interpolation.
no code implementations • 15 Jan 2018 • René Schuster, Christian Bailer, Oliver Wasenmüller, Didier Stricker
Scene flow is a description of real world motion in 3D that contains more information than optical flow.
no code implementations • 27 Oct 2017 • René Schuster, Oliver Wasenmüller, Georg Kuschk, Christian Bailer, Didier Stricker
While most scene flow methods use either variational optimization or a strong rigid motion assumption, we show for the first time that scene flow can also be estimated by dense interpolation of sparse matches.