Three-dimensional scene reconstruction from images

Abstract

Modeling of three-dimensional (3D) objects from image sequences is a challenging problem and has been a research topic for many years. Important theoretical and algorithmic results were achieved that allow to extract even complex 3D models of scenes from sequences of images. One recent effort has been to reduce the amount of calibration and to avoid restrictions on the camera motion. In this contribution an approach is described which achieves this goal by combining state-of-the-art algorithms for uncalibrated projective reconstruction, self-calibration and dense correspondence matching. Keywords: 3D reconstruction, structure-from-motion, image sequences, camera (self-)calibration 1. INTRODUCTION Obtaining 3D models from objects is an ongoing research topic in computer vision. A few years ago the main applications were robot guidance and visual inspection. Nowadays however the emphasis is shifting. There is more and more demand for 3D models in computer graphics, virtual reality and...