Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in Convolutional Networks

1 code implementation • 31 Jan 2018 • Timo Hackel, Mikhail Usvyatsov, Silvano Galliani, Jan D. Wegner, Konrad Schindler

While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data.

Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark

1 code implementation • 12 Apr 2017 • Timo Hackel, Nikolay Savinov, Lubor Ladicky, Jan D. Wegner, Konrad Schindler, Marc Pollefeys

With the massive data set presented in this paper, we aim at closing this data gap to help unleash the full potential of deep learning methods for 3D labelling tasks.

3D Point Cloud Classification Classification +5

Contour Detection in Unstructured 3D Point Clouds

no code implementations • CVPR 2016 • Timo Hackel, Jan D. Wegner, Konrad Schindler

The contour scores serve as a basis to construct an overcomplete graph of candidate contours.

Binary Classification Contour Detection +2

Fast semantic segmentation of 3d point clouds with strongly varying density

no code implementations • ISPRS annals of the photogrammetry, remote sensing and spatial information sciences 2016 • Timo Hackel, Jan D. Wegner, Konrad Schindler

We describe an effective and efficient method for point-wise semantic classification of 3D point clouds.

Classification General Classification +1