Registration of Multi-view Images of Planar Surfaces

0391429 - ÚTIA 2014 RIV DE eng C - Conference Paper (international conference)
Vávra, Radomír - Filip, Jiří
Registration of Multi-view Images of Planar Surfaces.
11th Asian Conference on Computer Vision ACCV, Revised Selected Papers. Vol. Part IV. Berlin: Springer Berlin Heidelberg, 2013, s. 497-509. Lecture Notes in Computer Science, 7727. ISBN 978-3-642-37446-3. ISSN 0302-9743.
[11th Asian Conference on Computer Vision (ACCV 2012). Daejeon (KR), 05.11.2012-09.11.2012]
R&D Projects: GA ČR GA102/08/0593; GA ČR GAP103/11/0335
Grant - others:EC(BE) 239294; CESNET(CZ) 409
Institutional support: RVO:67985556
Keywords : registration * BTF * texture * material * appearance * multi-view
Subject RIV: BD - Theory of Information
http://library.utia.cas.cz/separaty/2013/RO/vavra-registration of multi-view images of planar surfaces.pdf

This paper presents a novel image-based registration method for high-resolution multi-view images of a planar material surface. Contrary to standard registration approaches, this method aligns images based on a true plane of the material's surface and not on a plane defined by registration marks. It combines the camera calibration and the iterative fitting of desired position and slant of the surface plane, image re-registration, and evaluation of the surface alignment. To optimize image compression performance, we use an error of a compression method as a function evaluating the registration quality. The proposed method shows encouraging results on example visualizations of view- and illumination-dependent textures. In addition to a standard multi-view data registration approach, it provides a better alignment of multi-view images and thus allows more detailed visualization using the same compressed parameterization size.
Permanent Link: http://hdl.handle.net/11104/0220522