A PDE Solution of Brownian Warping

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Mads Nielsen, Peter Johansen

A Brownian motion model in the group of diffeomorphisms has been introduced as creating a least committed prior on warps. This prior is source destination symmetric, fulfills a natural semi-group property for warps, and with probability 1 create invertible warps. In this paper, we formulate a Partial Differential Equation for obtaining the maximum likelihood warp given matching constraints derived from the images. We solve for the free boundary conditions, and the bias toward smaller areas in the finite domain setting. Furthermore, we demonstrate the technique on 2D images, and show that the obtained warps are also in practice source-destination symmetric.
OriginalsprogEngelsk
TitelComputer Vision - ECCV 2004 : 8th European Conference on Computer Vision, Prague, Czech Republic, May 11-14, 2004. Proceedings, Part IV
Forlag
Publikationsdato2004
Sider180-191
ISBN (Trykt)978-3-540-21981-1
DOI
StatusUdgivet - 2004
Eksternt udgivetJa
BegivenhedEuropean Conference on Computer Vision - Prague, Tjekkiet
Varighed: 29 nov. 2010 → …
Konferencens nummer: 8

Konference

KonferenceEuropean Conference on Computer Vision
Nummer8
LandTjekkiet
ByPrague
Periode29/11/2010 → …
NavnLecture notes in computer science
Vol/bind3024/2004
ISSN0302-9743

Bibliografisk note

Poster presentation

ID: 5521062