GGNN: Graph-based GPU Nearest Neighbor Search

1 code implementation • 2 Dec 2019 • Fabian Groh, Lukas Ruppert, Patrick Wieschollek, Hendrik P. A. Lensch

Approximate nearest neighbor (ANN) search in high dimensions is an integral part of several computer vision systems and gains importance in deep learning with explicit memory representations.

Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)

1 code implementation • 20 Mar 2018 • Fabian Groh, Patrick Wieschollek, Hendrik P. A. Lensch

Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid.

Classify 3D Point Clouds Semantic Segmentation

Backpropagation Training for Fisher Vectors within Neural Networks

no code implementations • 8 Feb 2017 • Patrick Wieschollek, Fabian Groh, Hendrik P. A. Lensch

Fisher-Vectors (FV) encode higher-order statistics of a set of multiple local descriptors like SIFT features.