Fast global stereo matching via energy pyramid minimization - École des Ponts ParisTech Access content directly
Conference Papers ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences Year : 2014

Fast global stereo matching via energy pyramid minimization


We define a global matching framework based on energy pyramid, the Global Matching via Energy Pyramid (GM-EP) algorithm, which estimates the disparity map from a single stereo-pair by solving an energy minimization problem. We efficiently address this minimization by globally optimizing a coarse to fine sequence of sparse Conditional Random Fields (CRF) directly defined on the energy. This global discrete optimization approach guarantees that at each scale we obtain a near optimal solution, and we demonstrate its superiority over state of the art image pyramid approaches through application to real stereo-pairs. We conclude that multiscale approaches should be build on energy pyramids rather than on image pyramids.
Fichier principal
Vignette du fichier
PCV14.pdf (13.16 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01081593 , version 1 (10-11-2014)



B Conejo, S Leprince, F Ayoub, Jean-Philippe Avouac. Fast global stereo matching via energy pyramid minimization. Photogrammetric Computer Vision - PCV2014, ISPRS Technical Commission III Midterm Symposium, Sep 2014, Zurich, Switzerland. pp.41 - 48, ⟨10.5194/isprsannals-II-3-41-2014⟩. ⟨hal-01081593⟩
226 View
490 Download



Gmail Facebook Twitter LinkedIn More