L
Luc Van Gool
Researcher at Katholieke Universiteit Leuven
Publications - 1458
Citations - 137230
Luc Van Gool is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 133, co-authored 1307 publications receiving 107743 citations. Previous affiliations of Luc Van Gool include Microsoft & ETH Zurich.
Papers
More filters
Robotic ADaptation to Humans Adapting to Robots: Overview of the FP7 project RADHAR
Eric Demeester,Emmanuel Vander Poorten,Alexander Hüntemann,Joris De Schutter,Michael Hofmann,Martijn Rooker,Gernot Kronreif,Boris Lau,Markus Kuderer,Wolfram Burgard,Anna Gelin,Katrien Vanopdenbosch,Pascal Van der Beeten,Monia Vereecken,Stephan Ilsbroukx,Andrea Fossati,Gemma Roig,Xavier Boix,Luc Van Gool,Hans Fraeyman,Lieven Broucke,Hendrik Goessaert,John Josten +22 more
TL;DR: The research objectives and current state of the FP7 project RADHAR, which proposes a framework to fuse the inherently uncertain information from both environment perception and a wheelchair driver’s steering signals by estimating the trajectory the wheelchair should execute, are presented.
An algorithm for the extraction of line drawings for polyhedral scenes and their use in stereo vision
TL;DR: An algorithm for the creation of line drawings of polyhedral scenes is described that finds the two-dimensional position of the vertices and it generates a topological description of the scene in term of the connectiveness of the Vertices by edges.
Book ChapterDOI
Automatic occlusion removal from facades for 3D urban reconstruction
TL;DR: This paper proposes using an object detection framework to explicitly recognize and remove several classes of occlusions to improve 3D urban reconstruction from street level imagery, in which building facades are frequently occluded by vegetation or vehicles.
Book ChapterDOI
Getting facial features and gestures in 3D
Marc Proesmans,Luc Van Gool +1 more
TL;DR: An active 3D acquisition system is proposed, that yields 3-D, textured snapshots from a single image, that is part of an effort to model facial expressions without taking recourse to the modeling of the underlying physiology.
Posted Content
Spectral Tensor Train Parameterization of Deep Learning Layers
Anton Obukhov,Maxim Rakhuba,Alexander Liniger,Zhiwu Huang,Stamatios Georgoulis,Dengxin Dai,Luc Van Gool +6 more
TL;DR: The effects of neural network compression in the image classification setting and both compression and improved training stability in the generative adversarial training setting are demonstrated.