SCR: Smooth Contour Regression with Geometric Priors

Autor: Bahl, Gaetan, Daniel, Lionel, Lafarge, Florent

While object detection methods traditionally make use of pixel-level masks or bounding boxes, alternative representations such as polygons or active contours have recently emerged. Among them, methods based on the regression of Fourier or Chebyshev c

Externí odkaz: http://arxiv.org/abs/2202.03784

Binary Graph Neural Networks

Autor: Bahri, Mehdi, Bahl, Gaétan, Zafeiriou, Stefanos

Graph Neural Networks (GNNs) have emerged as a powerful and flexible framework for representation learning on irregular data. As they generalize the operations of classical CNNs on grids to arbitrary topologies, GNNs also bring much of the implementa

Externí odkaz: http://arxiv.org/abs/2012.15823

Single-Shot End-to-end Road Graph Extraction

Autor: Bahl, Gaetan, Bahri, Mehdi, Lafarge, Florent

Publikováno v: CVPR 2022 – IEEE Conference on Computer Vision and Pattern Recognition EarthVision Workshop
CVPR 2022 – IEEE Conference on Computer Vision and Pattern Recognition EarthVision Workshop, Jun 2022, New Orleans (Louisiana), United States

International audience; Automatic road graph extraction from aerial and satellite images is a long-standing challenge. Existing algorithms are either based on pixel-level segmentation followed by vectorization, or on iterative graph construction usin

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76ba2e6928cb3e919161336ea7b6ea76
https://doi.org/10.1109/cvprw56347.2022.00146