— In this paper, we present a novel approach to controlling a robotic system online from scratch based on the reinforcement learning principle. In contrast to other approaches, o...
Abstract. We explore a new general-purpose heuristic for nding highquality solutions to hard optimization problems. The method, called extremal optimization, is inspired by self-or...
Stefan Boettcher, Allon G. Percus, Michelangelo Gr...
In this work we recover the 3D shape of mirroring objects such as mirrors, sunglasses, and stainless steel objects. A computer monitor displays several images of parallel stripes,...
Stas Rozenfeld, Ilan Shimshoni, Michael Lindenbaum
We propose a new framework design for exploiting multi-core architectures in the context of visualization dataflow systems. Recent hardware advancements have greatly increased the...
Huy T. Vo, Daniel K. Osmari, Brian Summa, Jo&atild...
Object pose (location and orientation) estimation is a
common task in many computer vision applications. Although
many methods exist, most algorithms need manual
initialization ...
Marcel Germann, Michael D. Breitenstein, In Kyu Pa...