296 citations · 1.4k across the 42 of their papers we have counts for
4 papers · 1 filter
Topological Map Extraction from Overhead Images
Zuoyue Li, Jan Dirk Wegner, Aurélien Lucchi
We propose a new approach, named PolyMapper, to circumvent the conventional pixel-wise segmentation of (aerial) images and predict objects in a vector representation directly. Poly…
The Perfect Match: 3D Point Cloud Matching with Smoothed Densities
Zan Gojcic, Caifa Zhou, Jan D. Wegner +1
We propose 3DSmoothNet, a full workflow to match 3D point clouds with a siamese deep learning architecture and fully convolutional layers using a voxelized smoothed density value (…
Counting the uncountable: deep semantic density estimation from Space
Andres C. Rodriguez, Jan D. Wegner
We propose a new method to count objects of specific categories that are significantly smaller than the ground sampling distance of a satellite image. This task is hard due to the…
Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in Convolutional Networks
Timo Hackel, Mikhail Usvyatsov, Silvano Galliani +2
While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data. In this wor…