Institut für Informationsverarbeitung (TNT) - Homepage of Christoph Reinders

Christoph Reinders studied Computer Science at Leibniz Universität Hannover. For his Bachelor's thesis – "Handwriting Recognition On-The-Fly" – he was awarded the "Studienpreis 2014 des VDE Hannover". In the winter of 2014 he studied at the University of California, Berkeley, as a visiting student researcher and conducted research with Professor Alexei Efros on interactive editing during photo-capture for an iPad app.

Throughout his Master he focused on image processing and machine learning and graduated in October 2017. His Master's thesis, "Deep-Learning based Road Type Classification", deals with training fully convolutional networks with very little data by combining random forests and convolutional neural networks. Since November 2017, he has been working towards his PhD at the Institut für Informationsverarbeitung (TNT). His main research interests are deep learning and image processing.

Research topics

Convolutional Neural Networks / Deep Learning
Semantic Segmentation for Autonomous Driving
Random Forests
App Development (e.g. iOS)
Image processing

If you are interested in any of these topics for a student position, bachelor's thesis, or master's thesis, feel free to contact me.

Publications

Show recent publications only

Conference Contributions
- Christoph Reinders, Radu Berdan, Beril Besbinar, Junji Otsuka, Daisuke Iso
  RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation
  Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
  (arXiv.org, GitHub) BibTeX
- Maximilian Schier, Christoph Reinders, Bodo Rosenhahn
  Learned Fourier Bases for Deep Set Feature Extractors in Automotive Reinforcement Learning
  2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), IEEE, September 2023
  (pdfGitHub) BibTeX
- Timo Kaiser, Christoph Reinders, Bodo Rosenhahn
  Compensation Learning in Semantic Segmentation
  Computer Vision and Pattern Recognition Workshops (CVPRW) , June 2023
  (pdf, pdfGitHub, arXiv.org) BibTeX
- Maximilian Schier, Christoph Reinders, Bodo Rosenhahn
  Deep Reinforcement Learning for Autonomous Driving Using High-Level Heterogeneous Graph Representations
  2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 7147-7153, 2023
  (pdfGithub, Final Paper) BibTeX
- Maximilian Schier, Christoph Reinders, Bodo Rosenhahn
  Constrained Mean Shift Clustering
  Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), SIAM, April 2022
  (pdfGitHub) BibTeX
- Christoph Reinders, Frederik Schubert, Bodo Rosenhahn
  ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing
  Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI), 2022
  (arXiv.org, GitHub) BibTeX
- Kai Cordes, Christoph Reinders, Paul Hindricks, Jonas Lammers, Bodo Rosenhahn, Hellward Broszio
  RoadSaW: A Large-Scale Dataset for Camera-Based Road Surface and Wetness Estimation
  2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022
  (Link) BibTeX
- Florian Kluger, Christoph Reinders, Kevin Raetz, Philipp Schelske, Bastian Wandt, Hanno Ackermann, Bodo Rosenhahn
  Region-based Cycle-Consistent Data Augmentation for Object Detection
  2018 IEEE International Conference on Big Data, December 2018
  (pdf) BibTeX
- Christoph Reinders, Hanno Ackermann, Michael Ying Yang, Bodo Rosenhahn
  Object Recognition from very few Training Examples for Enhancing Bicycle Maps
  2018 IEEE Intelligent Vehicles Symposium (IV), June 2018
  (pdfarXiv.org) BibTeX
- Christoph Reinders, Florian Baumann, Björn Scheuermann, Arne Ehlers, Nicole Mühlpforte, Alfred O. Effenberg, Bodo Rosenhahn
  On-The-Fly Handwriting Recognition using a High-Level Representation
  The 16th International Conference on Computer Analysis of Images and Patterns (CAIP), Valetta, Malta, September 2015
  (DOI) BibTeX
Book Chapters
- Christoph Reinders, Michael Ying Yang, Bodo Rosenhahn
  Two Worlds in One Network: Fusing Deep Learning and Random Forests for Classification and Object Detection
  Volunteered Geographic Information, Springer Nature Switzerland, 2024
  (Link) BibTeX
- Christoph Reinders, Hanno Ackermann, Michael Ying Yang, Bodo Rosenhahn
  Learning Convolutional Neural Networks for Object Detection with very little Training Data
  Multimodal Scene Understanding, Academic Press, 2019, edited by Michael Ying Yang, Bodo Rosenhahn and Vittorio Murino
  BibTeX
Technical Report
- Timo Kaiser, Lukas Ehmann, Christoph Reinders, Bodo Rosenhahn
  Blind Knowledge Distillation for Robust Image Classification
  arXiv, arXiv, November 2022
  (pdfarXiv.org) BibTeX
- Christoph Reinders, Bodo Rosenhahn
  Adversarial Attacks and Defenses in Deep Learning
  We Are Developers!, 2022
  BibTeX
- Christoph Reinders, Bodo Rosenhahn
  Neuronale Netze: Angriffe und Verteidigung - Ich sehe was, was du nicht siehst
  iX Developer 2020 – Machine Learning 2.0, 2020
  BibTeX
- Christoph Reinders and Bodo Rosenhahn
  Neural Random Forest Imitation
  arXiv, November 2019
  (arXiv.org) BibTeX

Research topics

COVMAP-Dataset