Recent years have witnessed the surge of learned representations that directly build upon point clouds. Inspired by spherical multi-view scanners, we propose a novel sampling model called Spotlights to represent 3D shape as compact 1D array depth values. It simulates configuration cameras evenly distributed on sphere, where each virtual camera casts light rays from its principal probe for possi...

This note responds to the problem encountered in meetings of many kinds when a complex of interrelated issues is discussed by participants having very different standpoints and approaches. Usually each participant's contribution is received politely, but very little is achieved towards linking it to others presented, especially when the papers and presentations are lengthy and somewhat difficul...

Advanced driver assistance using cameras is a first important step towards autonomous driving tasks. However, the computational power in automobiles is highly limited and hardware platforms with enormous processing resources such as GPUs are not available in serial production vehicles. In our paper we address the need for a highly efficient fusion method that is well suited for standard CPUs. W...

Traditional class-based object-oriented data models and programming languages do not allow an object to have several types or to play diierent roles while keeping the same identity. Therefore, the modeling of persistent evolving entities is a diicult task. Some speciic models and languages exist, but do not support some of the features of traditional OODB models such as inheritance, late bindin...