Universität Bonn: Autonomous Intelligent Systems Group   Computer Science Institute VI: Autonomous Intelligent Systems


Radu Alexandru Rosu

Autonomous Intelligent Systems Group


   Radu Alexandru Rosu
   Rheinische Friedrich-Wilhelms-Universität Bonn
   Institut für Informatik VI
   Friedrich-Ebert-Allee 144
   53113 Bonn 

Tel:  +49 (0) 228 73-54159
Fax: +49 (0) 228 73-4425 

Email: rosu _at_ ais.uni-bonn.de

Office: 0.050

Software Releases:

EasyPBR - Lightweight Physically-Based Renderer designed for ease of use and fast prototyping

EasyPBR is a lightweight Physically-Based Renderer designed for ease of use and fast prototyping. It abstracts away most of the complexity of rendering allowing the user to display high quality images in only a couple of lines of code. By default, EasyPBR tries to choose parameters in order to best render a particular scene but if more control is needed, the whole rendering process is controllable through either a Python script or C++ program. EasyPBR is written in C++ and OpenGL and provides Python bindings to most of it's functionality.

LatticeNet - Fast Point Cloud Segmentation Using Permutohedral Lattices

LatticeNet is a 3D neural network that can process raw point clouds for the task of semantic segmentation. Sparse permutohedral lattices are used to embedd the point cloud and apply convolutions in the high dimensional space of the lattice. We define novel operations that allow for data-dependent interpolation between the lattice and the point cloud. The implementation is written in C++ and CUDA and exposed through PyTorch.





Universität Bonn, Institute for Computer Science, Departments: I, II, III, IV, V, VI