no code implementations • 28 Nov 2023 • Boris Meinardus, Mariusz Trzeciakiewicz, Tim Herzig, Monika Kwiatkowski, Simon Matern, Olaf Hellwich
We present Decomposer, a semi-supervised reconstruction model that decomposes distorted image sequences into their fundamental building blocks - the original image and the applied augmentations, i. e., shadow, light, and occlusions.
no code implementations • 17 Oct 2023 • Monika Kwiatkowski, Simon Matern, Olaf Hellwich
When taking images of some occluded content, one is often faced with the problem that every individual image frame contains unwanted artifacts, but a collection of images contains all relevant information if properly aligned and aggregated.
1 code implementation • 19 May 2023 • Monika Kwiatkowski, Simon Matern, Olaf Hellwich
Our data generation pipeline is customizable and can be applied to any existing dataset, serving as a data augmentation to further improve the feature learning of any existing method.
1 code implementation • 3 Aug 2022 • Tianyi Hu, Monika Kwiatkowski, Simon Matern, Olaf Hellwich
A Siamese network is used for global feature extraction and metric learning, which gives an initial ranking of the landmark search.