M
Maciej Ziaja
Publications - 7
Citations - 4
Maciej Ziaja is an academic researcher. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 1, co-authored 7 publications receiving 4 citations.
Papers
More filters
Journal ArticleDOI
MuS2: A Benchmark for Sentinel-2 Multi-Image Super-Resolution
Paweł Kowaleczko,Tomasz Tarasiewicz,Maciej Ziaja,Daniel Kostrzewa,Jakub Nalepa,Przemyslaw Stefan Rokita,Michal Kawulok +6 more
TL;DR: In this paper , the authors introduce a new MuS2 benchmark for multi-image super-resolution reconstruction of Sentinel-2 images, with WorldView-2 imagery used as the high-resolution reference.
Journal ArticleDOI
Self-Configuring nnU-Nets Detect Clouds in Satellite Images
Bartosz Grabowski,Maciej Ziaja,Michal Kawulok,Nicolas Long'ep'e,Bertrand Le Saux,Jakub Nalepa +5 more
TL;DR:
Proceedings ArticleDOI
Data Augmentation for Multi-Image Super-Resolution
TL;DR: A new data augmentation technique underpinned with learning the relation between high and low resolution is proposed that helps reduce the requirements concerned with the amount of real-life data necessary to train a super-resolution network, while providing higher-quality data for training, compared with the simulated low-resolution images.
Journal ArticleDOI
Squeezing nnU-Nets with Knowledge Distillation for On-Board Cloud Detection
Bartosz Grabowski,Maciej Ziaja,Michal Kawulok,Piotr Bosowski,Nicolas Long'ep'e,Bertrand Le Saux,Jakub Nalepa +6 more
TL;DR: In this article , a self-reconfigurable framework is proposed to perform meta-learning of a segmentation network over various datasets, which can reduce the amount of data to downlink by pruning the cloudy areas and make a satellite more autonomous through data-driven acquisition re-scheduling.
Proceedings ArticleDOI
Are Cloud Detection U-Nets Robust Against in-Orbit Image Acquisition Conditions?
Bartosz Grabowski,Maciej Ziaja,Michal Kawulok,Marcin Cwiek,Tomasz Lakota,Nicolas Longepe,Jakub Nalepa +6 more
TL;DR: In this article , the robustness of the fully-convolutional neural networks for cloud detection against the atmospheric conditions that resemble real acquisition settings of the Intuition-1 mission is investigated.