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
Proceedings ArticleDOI
Exploiting simple hierarchies for unsupervised human behavior analysis
TL;DR: The model of normality is established in a completely unsupervised manner and is updated automatically for scene-specific adaptation and the hierarchical representation on both an appearance and an action level paves the way for semantic interpretation.
Journal ArticleDOI
Segmenting Objects from Relational Visual Data.
TL;DR: In this article, an attentive graph neural network (AGNN) is proposed, which tackles pixel-wise object segmentation tasks in a holistic fashion by formulating the tasks as a process of iterative information fusion over data graphs.
Journal ArticleDOI
Online loop closure for real-time interactive 3D scanning
TL;DR: A real-time interactive 3D scanning system that allows users to scan complete object geometry by turning the object around in front of a real- time 3D range scanner and shows that the system has comparable accuracy to offline methods with the additional benefit of immediate feedback and results.
Proceedings ArticleDOI
DARN: A Deep Adversarial Residual Network for Intrinsic Image Decomposition
TL;DR: In this paper, a fully convolutional neural network is proposed to estimate absolute albedo and shading jointly. But, unlike our work, our approach does not require any physical priors like shading smoothness or albedos sparsity, nor does it rely on geometric information such as depth.
Journal ArticleDOI
Automatic detection and tracking of pedestrians from a moving stereo rig
TL;DR: A stereo system built around a probabilistic environment model which fuses evidence from dense 3D reconstruction and image-based pedestrian detection into a consistent interpretation of the observed scene, and a multi-hypothesis tracker to reconstruct the pedestrians’ trajectories in 3D coordinates over time.