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
Journal ArticleDOI
Evaluation of the effectiveness of HDR tone-mapping operators for photogrammetric applications
Rossella Suma,Georgia Stavropoulou,E. K. Stathopoulou,Luc Van Gool,Andreas Georgopoulos,Alan Chalmers +5 more
TL;DR: Four different HDR tone-mapping operators that have been used to convert raw HDR images into a format suitable for state-of-the-art algorithms are evaluated, and in particular keypoint detection techniques are evaluated.
Journal Article
Monkeys - a software architecture for ViRoom - low-cost multicamera system
TL;DR: This paper presents a software architecture for a software-synchronized multicamera setup that allows consistent multiimage acquisition, image processing and decision making and can easily accommodate different number of FireWire digital cameras and networked computers.
Journal Article
Learning generative models for monocular body pose estimation
TL;DR: A generative model of the relationship of body pose and image appearance using a sparse kernel regressor and a nonlinear dynamical model is proposed, making both pose and bounding box estimation more robust.
Posted Content
Fast Perceptual Image Enhancement
TL;DR: This work builds upon the prior work and explores different network architectures targeting an increase in image quality and speed and achieves a significantly higher mean opinion score (MOS) than the baseline while speeding up the computation by 6.3 times on a consumer-grade CPU.
Posted Content
Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning
TL;DR: In this paper, pixel-wise retrieval in a learned embedding space is formulated as pixelwise retrieval, where the annotated pixels are set as reference and the rest of the pixels are classified using a nearest-neighbor approach.