I am an assistant professor at the Technical University of Darmstadt, as well as a member of the Hessian Center for Artificial Intelligence (hessian.AI). The focus of my research is on developing efficient, robust, and understandable methods and algorithms for image and video analysis. I recently got the renowned Emmy Noether Programme (ENP) fund of the German Research Foundation (DFG) supporting my research on Interpretable Neural Networks for Dense Image and Video Analysis. Before starting my own group, I was a postdoctoral researcher in the Visual Inference Lab of Prof. Stefan Roth. Prior to joining TU Darmstadt, I was a postdoctoral researcher at the Media Technology Center at ETH Zurich working on augmented reality. I obtained my doctoral degree from ETH Zurich, advised by Prof. Dr. Markus Gross and in collaboration with Disney Research Zurich. In my doctoral thesis, awarded with the ETH Medal, I developed novel methods for motion representation and video frame interpolation.

News

Publications

Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images K. Singh, T. Navaratnam, J. Holmer, S. Schaub-Meyer, S. Roth 2024 CVPR Workshop: SyntaGen-Harnessing Generative Models for Synthetic Visual Datasets   (Best Paper Award) [ Paper | Project page ]

Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals O. Hahn, N. Araslanov, S. Schaub-Meyer, S. Roth 2024 Accepted to TMLR 2024 CVPR Workshop: Workshop on Foundation Models [ Preprint (arXiv) | Code ]

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods R. Hesse, S. Schaub-Meyer, S. Roth 2023 ICCV   (Oral Presentation) [ Paper | Supplement | Talk video | Code ]

Entropy-driven Unsupervised Keypoint Representation Learning in Videos A. Younes, S. Schaub-Meyer, G. Chalvatzaki 2023 ICML [ Paper | Project page | Code ]

Content-Adaptive Downsampling in Convolutional Neural Networks R. Hesse, S. Schaub-Meyer, S. Roth 2023 CVPR Workshop: Efficient Deep Learning for Computer Vision [ Paper | Supplement | Talk video | Poster | Code ]

Efficient Feature Extraction for High-resolution Video Frame Interpolation M. Nottebaum, S. Roth, S. Schaub-Meyer 2022 BMVC [ Paper | Supplement | Video | Talk video | Poster | Code ]

$S^2$-Flow: Joint Semantic and Style Editing of Facial Images K. Singh, S. Schaub-Meyer, S. Roth 2022 BMVC [ Paper | Supplement | Talk video | Poster | Code ]

Fast Axiomatic Attribution for Neural Networks R. Hesse, S. Schaub-Meyer, S. Roth 2021 NeurIPS [ Paper | Supplement | Talk video | Project page | Code ]

Dense Unsupervised Learning for Video Segmentation N. Araslanov, S. Schaub-Meyer, S. Roth 2021 NeurIPS [ Paper | Supplement | Video | Talk video | Code ]

Style Transfer for Keypoint Matching Under Adverse Conditions A. Uzpak, A. Djelouah, S. Schaub-Meyer 2020 3DV [ Paper | Code ]

Neural inter-frame compression for video coding A. Djelouah, J. Campos, S. Schaub-Meyer, C. Schroers 2019 ICCV [ Paper | Supplement ]

Deep Video Color Propagation S. Meyer, V. Cornillère, A. Djelouah, C. Schroers, M. Gross 2018 BMVC [ Preprint (arXiv) | Paper | Supplement | Video ]

PhaseNet for Video Frame Interpolation S. Meyer, A. Djelouah, B. McWilliams, A. Sorkine-Hornung, M. Gross, C. Schroers 2018 CVPR [ Paper | Supplement | Video | BibTex ]

Phase-Based Modification Transfer for Video S. Meyer, A. Sorkine-Hornung, M. Gross 2016 ECCV   (Oral Presentation) [ Paper | Video ]

Phase-based Frame Interpolation for Video S. Meyer, O. Wang, H. Zimmer, M. Grosse, A. Sorkine-Hornung 2015 CVPR   (Oral Presentation) [ Paper | Supplement | Video | Code ]