Luc Van Gool

TL;DR: An algorithm for efficient depth calculations and view synthesis that applies a min-cut/max-flow algorithm on a graph, implemented on the CPU, to ameliorate this result by a global optimisation.

TL;DR: This paper proposes a novel affinity measure by leveraging the power of single-target visual tracking (VT), which has proven reliable to locally track objects of interest given a bounding-box initialization, and learns a metric with features extracted from the behaviours of the two tracking trajectories.

TL;DR: A method for populating procedurally generated 3D city models with crowds of artificial agents targeted towards the analysis, prediction and visualization of occupant behaviour in urban planning and the application of this method to evaluate planning interventions in the urban fabric and monitor the correlating effects.

TL;DR: In this article, a fully convolutional architecture is proposed to recover the dense 3D surface of the hand from depth maps and propose a network that can predict mesh vertices, transformation matrices for every joint and joint coordinates in a single forward pass.

TL;DR: This work proposes a principled meta-learning based approach to OCDA for semantic segmentation, MOCDA, by modeling the unlabeled target domain continuously, and achieves the state-of-the-art performance in both compound and open domains.