Research Areas: Image-Based Modeling and Rendering
Traditionally, the acquisition of three-dimensional avatars from real humans relied on the utilization of body suits, optical or magnetic markers, or complex and expensive three-dimensional scanners. Major drawbacks that these capture systems introduce are equipment cost, portability and the required degree of human intervention to ensure compelling visual results. Our research in this area is targeting the development of an image-based modeling and rendering pipeline that enables the creation of photorealistic 3D models from sets of images or video streams. We are particularly interested in the construction of realistic human avatars that combine a high-quality geometric model with a bio-mechanically correct skeleton.
- Automatic Creation of Three-Dimensional Avatars
- Kinematic Synthesis
- Avatar Centric Risk Evaluation
- 3D Modeling from Images and Video Streams
- Vision Based Motion Tracking for Risk Assesment During Seismic Events