Visualizing 3D models with fine-grain surface depth

Master Specialization: Visualization, Virtual Reality and Graphic Interaction
Topic Aproval date: 18/02/09
Orientation: research

Student: Roi Méndez
Thesis advisor(s): Isabel Navazo & Roger Hubbold (Manchester University)
Contact: isabel at lsi.upc.edu

The Daedalus Project has devised novel techniques for recovering 3D models of scenes from wide-baseline photographs. Current work is focussed on using novel shape-from-shading methods (referred to as Depth Hallucination) to add fine-grain surface detail to the reconstructed models. In doing this, our goal is to reconstruct models that appear visually correct under varying illumination, including subtle effects such as surface self-shadowing. Output from the current software is in the form of a dense polygon mesh and corresponding albedo and normal-depth maps. The project will explore GPU algorithms for rendering such models at interactive frame rates. Aspects to be explored include rendering with normal maps and relief textures, and how best to store the raw data and process it on the GPU. Evaluation will include measures of performance, and test cases with varying illumination. A comparison could be made with a naive polygon rendering approach.