Interactive 3D Scene Reconstruction from Images

Abstract

We propose an interactive framework for reconstructing an arbitrary 3D scene consistent with a set of images, for use in example-based image synthesis. Previous research has used human input to specify feature matches, which are then processed off-line; however, it is very difficult to correctly match images without feedback. The central idea of this paper is to perform and display 3D reconstruction during user modification. By allowing the user to interactively manipulate the image correspondence and the resulting 3D reconstruction, we can exploit both the user's intuitive image understanding and the computer's processing power. 1 Introduction and Related Work The traditional goal of computer vision research is to computationally understand 3D scenes from sensor data. This research primarily targets real-time applications (such as robot guidance) and understanding the human visual system; hence, there is ideally no human intervention in the image analysis process. Although many impr...