Despite the rising popularity of message-passing neural networks (MPNNs), their ability to fit complex functions over graphs is limited as node representations become more similar with increasing depth—a phenomenon known as over-smoothing. Most approaches to mitigate...
Safe navigation of self-driving cars and robots requires a precise understanding of their environment. Training data for perception systems cannot cover the wide variety of objects that may appear during deployment. Thus, reliable identification of unknown objects,...
Im Heise-KI-Podcast spricht Dr. Stefan Kesselheim vom Jülich Supercomputing Centre über OpenGPT-X und JUPITER, den ersten Exascale Supercomputer Europas. Das KI-Servicezentrum WestAI rückt im Gespräch ebenfalls in den Mittelpunkt. Dr. Kesselheim, der als »Lead...
Zwei Partner, ein Schloss, ein Event im Herbst – wir laden Sie herzlich ein zum Smart Data Innovation Day 2023 am Donnerstag, 16. November 2023. Dieses Jahr gibt es eine Besonderheit: Zusätzlich zu den Möglichkeiten im Smart Data Innovation Lab werden Sie auch...
In this paper, we present an inverse rendering method for the simple reconstruction of shape and appearance of real-world objects from only roughly calibrated RGB images captured under collocated point light illumination. To this end, we gradually reconstruct the...