Realistic 3-D Scene Modeling from Uncalibrated Image Sequences

This contribution addresses the problem of obtaining photorealistic 3D models of a scene from images alone with a structure-from-motion approach. The 3D scene is observed from multiple viewpoints by freely moving a camera around the object. No restrictions on camera movement and internal camera parameters like zoom are imposed, as the camera pose and intrinsic parameters are calibrated from the sequence. The only restrictions on the scene content are the rigidity of the scene objects and opaque, piecewise smooth object surfaces. The approach operates independently of object scale and requires only a single low-cost consumer photo or video camera. The modeling system described here uses a three-step approach. First, the camera pose and intrinsic parameters are calibrated on-line by tracking salient feature points between the different views. Next, consecutive images of the sequence are treated as stereoscopic image pairs and dense correspondence maps are computed by area matching. Fina...

• Type: Conference
• Year: 1999
• Where: ICIP
• Authors: Reinhard Koch, Marc Pollefeys, Luc J. Van Gool
• Keywords: Camera Pose, ICIP 1999, Image Processing, Internal Camera Parameters, Intrinsic Parameters