Dr. René Schuster
| E-Mail: | rene.schuster@dfki.de |
|---|---|
| Position: | Senior Researcher |
| Phone: | +49 631 20575-3605 |
René Schuster received a master degree in Computational Engineering from the Technical University of Darmstadt, where he was student assistant at the Visual Inference Group under Prof. Stefan Roth.
His master thesis about 3D vehicle detection based on motion and geometry was completed at the Robert Bosch GmbH.
In 2017 he joined the department Augmented Vision (AV) of the German Research Center for Artifical Intelligence (DFKI) under Prof. Didier Stricker. In 2022, he completed his PhD in the field of 3D motion estimation for automotive applications.
Since 2020, he leads the team Automotive Scene Understanding (ASU) that focusses on a variety of visual perception tasks for assisted and automated driving. A special emphasis of the team’s research is on (multi-modal, heterogeneous) sensor fusion for increased robustness, compact networks which exploit domain knowledge, and data-efficient learning.
Next to his research activities, René is deeply committed to teaching. He is organzing the projects and seminars on “3D Computer Vision”, “2D Image Processing”, and “Computer Vision and Deep Learning”, and is lecturer for “Advanced Topics in Computer Vision and Deep Learning” at the RPTU in Kaiserslautern. Additionally, René is reviewer for major conferences in the fields of Computer Vision, Pattern Recognition, Robotics, and Automotive.
ShapeAug++: More Realistic Shape Augmentation for Event Data
In: ArXiv e-prints (arxiv), Vol. 2409, No. 11075, Pages 1-11, arXiv, 2024.
Details
| Link 1
CLEO: Continual Learning of Evolving Ontologies
In: European Conference on Computer Vision. European Conference on Computer Vision (ECCV-2024), September 29 - October 4, Mailand, Germany, Springer, 2024.
Details
| Link 1
RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds
In: International Journal of Computer Vision (IJCV), Vol. 132, Pages 01-22, Springer, 5/2024.
Details
| Link 1
ShapeAug: Occlusion Augmentation for Event Camera Data
In: International Conference on Pattern Recognition Applications and Methods. International Conference on Pattern Recognition Applications and Methods (ICPRAM-2024), February 24-26, Rome, Italy, SCITEPRESS, 2024.
Details
| Link 1
Learned Fusion: 3D Object Detection using Calibration-Free Transformer Feature Fusion
In: Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods. International Conference on Pattern Recognition Applications and Methods (ICPRAM-2024), February 24-26, Rome, Italy, SCITEPRESS, 2024.
Details
| Link 1
JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentation
In: SN Computer Science (SNCS), Vol. 5, Pages 0-16, Springer, 2024.
Details
| Link 1
EvLiDAR-Flow: Attention-Guided Fusion between Point Clouds and Events for Scene Flow Estimation
In: International Conference on Pattern Recognition Applications and Methods. International Conference on Pattern Recognition Applications and Methods (ICPRAM-2023), February 22-24, Lissabon, Portugal, Scitepress, 2023.
Details
| Link 1
Multi-task Fusion for Efficient Panoptic-Part Segmentation
In: Proceedings of the International Conference on Pattern Recognition Applications and Methods. International Conference on Pattern Recognition Applications and Methods (ICPRAM-2023), February 22-24, Lissabon, Portugal, Scitepress, 2023.
Details
| Link 1
On the Future of Training Spiking Neural Networks
In: International Conference on Pattern Recognition Applications and Methods. International Conference on Pattern Recognition Applications and Methods (ICPRAM-2023), February 22-24, Lissabon, Portugal, SCITEPRESS, 2023.
Details
| Link 1
Severity of Catastrophic Forgetting in Object Detection for Autonomous Driving
In: Proceedings of the International Conference on Pattern Recognition Applications and Methods. International Conference on Pattern Recognition Applications and Methods (ICPRAM-2023), February 22-24, Lissabon, Portugal, Scitepress, 2023.
Details
| Link 1
EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Support
In: British Machine Vision Conference. British Machine Vision Conference (BMVC-2023), located at The 34th British Machine Vision Conference, November 20-24, Aberdeen, Scotland, United Kingdom, BMVA, 2023.
Details
| Link 1
| Link 2
| Link 3
| Link 4
Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation
In: Winter Conference on Applications of Computer Vision 2023. IEEE Winter Conference on Applications of Computer Vision (WACV-2023), January 2-7, Waikoloa, HI, USA, IEEE, 2023.
Details
| Link 1
Object Permanence in Object Detection Leveraging Temporal Priors at Inference Time
ernational Conference on Pattern Recognition (ICPR-2022) August 21-25 Montreal Quebec Canada IEEE 2022 .
Details
| Link 1
Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences
International Conference on Image Processing. IEEE International Conference on Image Processing (ICIP-2022) October 16-19 Bordeaux France IEEE 2022 .
Details
| Link 1
Multi-scale Iterative Residuals for Fast and Scalable Stereo Matching
Computer Science in Cars Symposium. ACM Computer Science in Cars Symposium (CSCS-2021) November 30-30 Ingolstadt Germany ACM 2021 .
Details
| Link 1
RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds
In: International Conference on Robotics and Automation. IEEE International Conference on Robotics and Automation (ICRA-2022), IEEE International Conference on Robotics and Automation, May 23-27, Philadelphia, Pennsylvania (PA), USA, IEEE, 2022.
Details
| Link 1
| Link 2
| Link 3
| Link 4
A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions
Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision (WACV-2021) January 5-9 Waikoloa HI United States IEEE 2021 .
Details
| Link 1
HPERL: 3D Human Pose Estimation from RGB and LiDAR
International Conference on Pattern Recognition. International Conference on Pattern Recognition (ICPR-2020) January 10-15 Milan Italy IEEE 2021 .
Details
| Link 1
MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene Flow
Computer Science in Cars Symposium. ACM Computer Science in Cars Symposium (CSCS-2020) December 2-2 Feldkirchen Germany ACM 2020 .
Details
| Link 1
deepRGBXYZ: Dense Pixel Description Utilizing RGB and Depth with Stacked Dilated Convolutions
International Conference on Intelligent Transportation Systems. IEEE Intelligent Transportation Systems Conference (IEEE ITSC-2020) September 20-23 Rhodes Greece IEEE 9/2020 .
Details
| Link 1
SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation
Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision (WACV-2021) January 5-9 Waikoloa HI United States IEEE 2021 .
Details
| Link 1
ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching
International Conference on Pattern Recognition. International Conference on Pattern Recognition (ICPR-2021) January 12-15 Mailand Italy IEEE 1/2021 .
Details
| Link 1
DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDAR
International conference in robotics and intelligent systems. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2020) October 25-29 Las Vegas NV United States Minor Outlying Islands IEEE 10/2020 .
Details
| Link 1
SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks
Conference on Computer Vision and Pattern Recognition. International Conference on Computer Vision and Pattern Recognition (CVPR-2019) June 16-20 Long Beach CA United States IEEE 2019 .
Details
| Link 1
| Link 2
PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation
Intelligent Vehicles Symposium. IEEE Intelligent Vehicle Symposium (IV-2019) June 10-12 Paris France IEEE 2019 .
Details
| Link 1
| Link 2
An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching
Conference on Computer Vision and Pattern Recognition Workshops. Safe Artificial Intelligence for Automated Driving Workshop (SAIAD-2019) befindet sich CVPR 2019 June 17-17 Long Beach CA United States IEEE Xplore 2019 .
Details
| Link 1
SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimation
International Journal of Computer Vision (IJCV) tba Springer 2019 .
Details
| Link 1
SDC - Stacked Dilated Convolutions
Computer Science in Cars Sympoisum. ACM Computer Science in Cars Symposium (CSCS-2019) October 8-8 Germany ACM 10/2019 .
Details
| Link 1
LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Images
International conference in robotics and intelligent systems. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2019) IEEE/RSJ International Conference on Intelligent Robots and Systems November 4-8 MACAO, CHINA Macao SAR of China IEEE 2019 .
Details
| Link 1
SceneFlowFields: Dense Interpolation of Sparse Scene Flow Correspondences
IEEE Winter Conference on Applications of Computer Vision (WACV-18), March 12-14, Lake Tahoe, NV/CA, USA
Details
| Link 1
Combining Stereo Disparity and Optical Flow for Basic Scene Flow
Commercial Vehicle Technology Symposium (CVT-18), March 13-15, Kaiserslautern, Germany
Details
| Link 1
FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation
IEEE International Conference on Image Processing
Details
| Link 1
Dynamic Risk Assessment for Vehicles of Higher Automation Levels by Deep Learning
International Workshop on Artificial Intelligence Safety Engineering (WAISE-2018), located at SAFECOMP 2018, September 18, Västerås, Sweden
Details
| Link 1
Automated Scene Flow Data Generation for Training and Verification
ACM Computer Science in Cars Symposium (CSCS) ACM Computer Science in Cars Symposium (CSCS-2018), Munich, Germany
Details
| Link 1
Dense Scene Flow from Stereo Disparity and Optical Flow
Computer Science in Cars Symposium ACM Chapters Computer Science in Cars Symposium (CSCS-2018), September 13-14, Munich, Germany
Details
| Link 1
Towards Flow Estimation in Automotive Scenarios
Computer Science in Cars Symposium ACM Chapters Computer Science in Cars Symposium (CSCS-17), Computer Science in Cars Symposium 2017, July 6, Munich, Germany
Details
| Link 1