LISA has developed a software (RVS) that can generate novel views for virtual reality using only photographs of the real-world. The aim of this project is to extend the software’s input to a new type of cameras, i.e. plenoptic cameras (e.g. RayTrix), which capture in one shot hundreds of tiny images thanks to a lenslet objective (an objective composed of hundreds of micro lenses). The advantage of the produced lenslet images is that they contain the 3D information of the scene. A tool (RLC) has already been developed on CPU to transform the lenslet images to classical images, and will serve as a basis to extend our view synthesis software RVS. At the end of the project, 3D scenes photographed by a plenoptic camera will be rendered for virtual reality.
The ideal candidate for this Master thesis is driven and a problem solver. The student wants to learn optimization techniques and GPU programming while keeping high standards in the programmed code. The student will be able to work in a dynamic team.
Prerequisites: Programming skill (C++ and/or Python), familiarity with image processing is a plus.
Keywords: Computer vision, Image analysis, 3D Image processing
Promotor: Mehrdad TERATANI (mehrdad.teratani@ulb.be)
Support: Sarah Fachada