no code implementations • ICCV 2023 • Stefano Zorzi, Friedrich Fraundorfer
Re:PolyWorld not only outperforms the original model on building extraction in aerial images, thanks to the proposed joint analysis of vertices and edges, but also beats the state-of-the-art in multiple other domains.
1 code implementation • CVPR 2022 • Stefano Zorzi, Shabab Bazrafkan, Stefan Habenschuss, Friedrich Fraundorfer
While most state-of-the-art instance segmentation methods produce binary segmentation masks, geographic and cartographic applications typically require precise vector polygons of extracted objects instead of rasterized output.
no code implementations • 13 Apr 2021 • Yi Wang, Stefano Zorzi, Ksenia Bittner
We propose a machine learning based approach for automatic 3D building reconstruction and vectorization.
no code implementations • 24 Jul 2020 • Stefano Zorzi, Ksenia Bittner, Friedrich Fraundorfer
We propose a machine learning based approach for automatic regularization and polygonization of building segmentation masks.
no code implementations • 24 Jul 2020 • Stefano Zorzi, Ksenia Bittner, Friedrich Fraundorfer
In the fast developing countries it is hard to trace new buildings construction or old structures destruction and, as a result, to keep the up-to-date cadastre maps.
no code implementations • 23 Jul 2020 • Stefano Zorzi, Friedrich Fraundorfer
In this paper we present a method for building boundary refinement and regularization in satellite images using a fully convolutional neural network trained with a combination of adversarial and regularized losses.