1 code implementation • ICLR 2022 • Wang Yifan, Lukas Rahmann, Olga Sorkine-Hornung
We present implicit displacement fields, a novel representation for detailed 3D geometry.
no code implementations • CVPR 2018 • Riccardo Roveri, Lukas Rahmann, Cengiz Oztireli, Markus Gross
We propose a novel neural network architecture for point cloud classification.
no code implementations • 15 Mar 2018 • Charlotte Bunne, Lukas Rahmann, Thomas Wolf
Convolutional Neural Networks (CNNs) define an exceptionally powerful class of models for image classification, but the theoretical background and the understanding of how invariances to certain transformations are learned is limited.