Based on scaling laws describing the statistical structure
of turbulent motion across scales, we propose a multiscale
and non-parametric regularizer for optic-flow estimation.
R...
Patrick H´eas, Etienne M´emin, Dominique Heitz, ...
We present a new approach to deformable image registration suitable for articulated images such as hand-drawn cartoon characters and human postures. For such type of data state-of...
Experiential image retrieval systems aim to provide the user with a natural and intuitive search experience. The goal is to empower the user to navigate large collections based on...
Bart Thomee, Mark J. Huiskes, Erwin M. Bakker, Mic...
We present a technique called Random Image Structure Evolution (RISE) for use in experimental investigations of high-level visual perception. Potential applications of RISE includ...
An unmanned aerial vehicle (UAV) needs to orient itself in its operating environment to fly autonomously. Localisation methods based on visual data are independent of erroneous GPS...