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
Superpixel meshes for fast edge-preserving surface reconstruction
TL;DR: This work proposes a novel surface reconstruction method based on image edges, superpixels and second-order smoothness constraints, producing meshes comparable to classic MVS surfaces in quality but orders of magnitudes faster.
Proceedings ArticleDOI
Visual interestingness in image sequences
TL;DR: This work investigates what humans consider as "interesting" in image sequences and proposes a computer vision algorithm to automatically spot these interesting events and integrates multiple cues inspired by cognitive concepts.
Proceedings ArticleDOI
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation
TL;DR: In this article, Li et al. proposed a semi-supervised semantic segmentation framework for unlabeled image sequences, which is enhanced by self-supervision of monocular depth estimation from image sequences.
Posted Content
Some like it hot - visual guidance for preference prediction
TL;DR: This work improves the state of-the-art, but also predicts - based on someone's known preferences - how much that particular person is attracted to a novel face, and validates the collaborative filtering solution on the standard MovieLens rating dataset.
Proceedings ArticleDOI
Energy-Efficient ConvNets Through Approximate Computing
TL;DR: Methods based on approximate computing to reduce energy consumption in state-of-the-art ConvNet accelerators are proposed and can gain energy in the systems arithmetic: up to 30× without losing classification accuracy and more than 100× at 99% classification accuracy, compared to the commonly used 16-bit fixed point number format.