Séminaire Marco Calemme : codage sans pertes par déformation élastiques de courbes

A partir de cette rentrée, le groupe MM organise des séminaires mensuels sur nos sujets de recherche, auxquels tout le monde est chaleureusement invité.

Date : 16/09/2016
Heure : 9h30
Lieu : Salle B549

Orateur : Marco Calemme
Titre : Coding of depth maps by elastic deformations of curves
Abstract : Multiple-view video plus depth (MVD) is an emerging video format where the video information is coupled with geometrical information on the scene, the so-called depth. MVD allows effective synthesis of virtual view-points using depth, but it also requires specific compression tools, in particular for the geometrical information.

In depth maps can be represented by means of grayscale images and the corresponding temporal sequence can be thought as a standard grayscale video sequence. However depth maps have dierent properties from natural images: they present large areas of smooth surfaces separated by sharp edges. Arguably the most important information lies in object contours, as a consequence an interesting approach consists in performing a lossless coding of the contour map, possibly followed by a lossy coding of per-object depth values.
In this context, we propose a new technique for the lossless coding of object contours, based on the elastic deformation of curves. A continuous evolution of elastic deformations between two reference contour curves can be modelled, and an elastically deformed version of the reference contours can be sent to the decoder with an extremely small coding cost and used as side information to improve the lossless coding of the actual contour. After the main discontinuities have been captured by the contour description, the depth

Leave a Reply

You can use these HTML tags

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>