Marc Windsheimer
Marc Windsheimer, M.Sc.
Department Elektrotechnik-Elektronik-Informationstechnik (EEI)
Lehrstuhl für Multimediakommunikation und Signalverarbeitung
Cauerstr. 7
91058 Erlangen
Germany
- Phone number: +49 9131 85-27104
- Fax number: +49 9131 85-28849
- Email: marc.windsheimer@fau.de
- Website: https://www.lms.tf.fau.eu
I am engaged in the development of deep learning methods for image and video coding. The main focus is on machine communication, where the decoded results are evaluated by deep neural networks, e.g. Mask R-CNN. At the same time, however, a human observer should be able to understand the decision of the evaluation network. The goal is to maintain the accuracy of the detection networks while minimizing the required data rate.
Further information can be found at the following link:
- : Best Master Thesis Award 2023 (Freunde und Förderer der Erlangener Multimediakommunikation und Signalverarbeitung (EMSig) e.V.) – 2023
- : Department EEI Master Award (Department Elektrotechnik-Elektronik-Informationstechnik) – 2023
Thesis in the area of video coding for object detection
https://www.lms.tf.fau.eu/videocodierung-fuer-neunronale-detektionsnetzwerke/
2024
- , , :
Multiscale Augmented Normalizing Flows for Image Compression
International Conference on Acoustics, Speech and Signal Processing (Seoul, 14. April 2024 - 19. April 2024)
DOI: 10.1109/ICASSP48485.2024.10446147
URL: https://ieeexplore.ieee.org/document/10446147
BibTeX: Download - , , :
On Annotation-free Optimization of Video Coding for Machines
International Conference on Image Processing (ICIP) (Abu Dhabi, 27. October 2024 - 30. October 2024)
DOI: 10.1109/ICIP51287.2024.10647318
URL: https://ieeexplore.ieee.org/document/10647318
BibTeX: Download
2022
- , , , , :
RDONet: Rate-Distortion Optimized Learned Image Compression with Variable Depth
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022 (New Orleans, LA, USA, 19. June 2022 - 20. June 2022)
In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops 2022
DOI: 10.1109/CVPRW56347.2022.00186
BibTeX: Download - , , , , :
RDONet: Rate-Distortion Optimized Learned Image Compression With Variable Depth
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (New Orleans, 19. June 2022 - 23. June 2022)
DOI: 10.1109/CVPRW56347.2022.00186
URL: https://ieeexplore.ieee.org/document/9857403
BibTeX: Download