Abstract
We introduce a tool which allows an untrained user to take three images of an object freehand with a simple consumer camera. From these images a 3d model of the visible parts of the object is reconstructed within seconds and visualized realistically. From a research point of view we propose solutions for three weaknesses of the state-of-the-art reconstruction pipeline. These contributions allow for a more robust and a considerably faster reconstruction process than before, which can be used, e.g., to create new types of interfaces or to assist in creating virtual environments.
Chapter PDF
Similar content being viewed by others
Keywords
References
Saxena, A., Sun, M., Ng, A.Y.: Make3d: Depth perception from a single still image. In: Fox, D., Gomes, C.P. (eds.) AAAI, pp. 1571–1576 (2008)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 IFIP International Federation for Information Processing
About this paper
Cite this paper
Peters, G., Häming, K. (2009). Take Three Snapshots - A Tool for Fast Freehand Acquisition of 3D Objects. In: Gross, T., et al. Human-Computer Interaction – INTERACT 2009. INTERACT 2009. Lecture Notes in Computer Science, vol 5727. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03658-3_91
Download citation
DOI: https://doi.org/10.1007/978-3-642-03658-3_91
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03657-6
Online ISBN: 978-3-642-03658-3
eBook Packages: Computer ScienceComputer Science (R0)