3D-modeling by ortho-image generation from image sequences

Abstract

A semi-automatic approach is presented that enables the generation of a high-quality 3D model of a static object from an image sequence that was taken by a moving, uncalibrated consumer camera. A bounding box is placed around the object, and orthographic projections onto the sides of the bounding box are automatically generated out of the image sequence. These ortho-images can be imported as background maps in the orthographic views (e.g., the top, side, and front view) of any modeling package. Modelers can now use these ortho-images to guide their modeling by tracing the shape of the object over the ortho-images. This greatly improves the accuracy and efficiency of the manual modeling process. An additional advantage over existing semi-automatic systems is that modelers can use the modeling package that they are trained in and can thereby increase their productivity by applying the advanced modeling features the package offers. The results presented show that accurate 3D models can even be generated for translucent or specular surfaces, and the approach is therefore still applicable in cases where today's fully automatic image-based approaches or laser scanners would fail.