59 citations · 60 across the 2 of their papers we have counts for
4 papers
Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)
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. However, unstructured data like 3D point…
Learning Blind Motion Deblurring
Patrick Wieschollek, Michael Hirsch, Bernhard Schölkopf +1
As handheld video cameras are now commonplace and available in every smartphone, images and videos can be recorded almost everywhere at anytime. However, taking a quick shot freque…
Efficient Large-scale Approximate Nearest Neighbor Search on the GPU
Patrick Wieschollek, Oliver Wang, Alexander Sorkine-Hornung +1
We present a new approach for efficient approximate nearest neighbor (ANN) search in high dimensional spaces, extending the idea of Product Quantization. We propose a two-level pro…
Backpropagation Training for Fisher Vectors within Neural Networks
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. They already show good performance in combination with shallow learnin…