Large-scale and high-quality multi-view stereo
Details
Acquisition of 3D model of real objects and scenes is indispensable and useful in many practical applications, such as digital archives, game and entertainment industries, engineering, advertisement. However, a single photograph, while records the color, the brightness of one scene, can not provide its 3D structure. Fortunately, with many photographs of the scene in different viewpoints, the 3D information can be revealed with a technique called multi-view stereo. This image-based technique is easier, cheaper, faster than the active range finding technique (laser-based technique), especially for large-scale outdoor scenes. Nevertheless, one disadvantage of the multi-view technique comparing to the laser-based technique is its lack of accuracy. In this work, we target the accuracy as well as scalability issues. We significantly improve some previous multi-view methods and combine them into a remarkably effective pipeline with GPU acceleration. We produce highly complete and accurate meshes that achieve best scores in many benchmarks. Then, we develop Divide and Conquer, mesh merging methods in order to build large 3D models from thousands of high-resolution images.
Autorentext
Hoang Hiep Vu is a doctor in computer science, specialized in 3D multi-view stereo and computer vision. He obtained his PhD while working for the research project IMAGINE in Ecole des Ponts ParisTech (France) under the supervisor of professor Renaud Keriven from 2008 to 2011. Previously, he graduated from Ecole Polytechnique (France) in 2008.
Weitere Informationen
- Allgemeine Informationen
- GTIN 09783847375296
- Sprache Englisch
- Auflage Aufl.
- Größe H11mm x B220mm x T150mm
- Jahr 2012
- EAN 9783847375296
- Format Kartonierter Einband (Kt)
- ISBN 978-3-8473-7529-6
- Titel Large-scale and high-quality multi-view stereo
- Autor Hoang Hiep Vu
- Untertitel Accurate 3D reconstruction from multiple high-resolution images of outdoor scenes
- Gewicht 308g
- Herausgeber LAP Lambert Academic Publishing
- Anzahl Seiten 220
- Genre Informatik