Publications

Jenny Schmalfuss, Philipp Scholze, and Andrés Bruhn. A perturbation-constrained adversarial attack for evaluating the robustness of optical flow. In S. Avidan, G. Brostow, M. Cissé, G.M. Farinella, and T. Hassner (Eds.), Proc. European Conference on Computer Vision (ECCV), (13682):183--200, Springer Nature Switzerland, 2022. [PUMA: myown visus:schmaljy visus:bruhnas] URL

Jenny Schmalfuss, Lukas Mehl, and Andrés Bruhn. Attacking Motion Estimation with Adversarial Snow. ECCV 2022 Workshop on Adversarial Robustness in the Real World (AROW), 2022. [PUMA: myown visus:schmaljy visus:mehlls visus:bruhnas]

Jenny Schmalfuss, Erik Scheurer, Heng Zhao, Nikolaos Karantzas, Andres Bruhn, and Demetrio Labate. Blind image inpainting with sparse directional filter dictionaries for lightweight CNNs. Journal of Mathematical Imaging and Vision (JMIV), (65):323-339, 2023. [PUMA: myown visus:schmaljy visus:bruhnas] URL

Erik Scheurer, Jenny Schmalfuss, Alexander Lis, and Andrés Bruhn. Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow. Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE/CVF, 2024. [PUMA: myown visus:schmaljy visus:bruhnas] URL

Jenny Schmalfuss, Lukas Mehl, and Andrés Bruhn. Distracting Downpour: Adversarial Weather Attacks for Motion Estimation. Proc. International Conference on Computer Vision (ICCV), IEEE/CVF, October 2023. [PUMA: myown 2023 visus:schmaljy visus:mehlls visus:bruhnas] URL

Lukas Mehl, Jenny Schmalfuss, Azin Jahedi, Yaroslava Nalivayko, and Andrés Bruhn. Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [PUMA: myown sfbtrr161 b04 visus:jahedian 2023 visus:schmaljy visus:mehlls visus:bruhnas visus] URL