Media Information Processing for Robotics. Modeling from Reality.

摘要

This paper presents an overview of our efforts in modeling-from-realty to create virtual reality models through observation of real objects. These efforts span three aspects: how to create geometric models of virtual objects; how to create photometric models of virtual objects; and how to integrate such virtual objects with real scenes. For geometric model creation, we have developed a two-step method: simultaneous alignment and volumetric view merging. For photometric model creation, we have developed two methods, model-based and eigen-texture rendering methods, both of which automatically create models by observing the real objects. For the integration of virtual objects with real scenes, we have developed a method that renders virtual objects based on real illumination distribution. We have successfully tested the proposed methods by using real images to demonstrate their effectiveness.