Détail de l'auteur
Auteur Tobias Plötz |
Documents disponibles écrits par cet auteur (1)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
![Tris disponibles](./images/orderby_az.gif)
Automatic registration of images to untextured geometry using average shading gradients / Tobias Plötz in International journal of computer vision, vol 125 n° 1-3 (December 2017)
![]()
[article]
Titre : Automatic registration of images to untextured geometry using average shading gradients Type de document : Article/Communication Auteurs : Tobias Plötz, Auteur ; Stefan Roth, Auteur Année de publication : 2017 Conférence : ICCV 2015, International Conference on Computer Vision 11/12/2015 18/12/2015 Santiago Chili OA Proceedings Article en page(s) : pp 65 - 81 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] attribut géomètrique
[Termes IGN] estimation de pose
[Termes IGN] gradient
[Termes IGN] maillage par triangles
[Termes IGN] ombre
[Termes IGN] SIFT (algorithme)
[Termes IGN] superposition d'imagesRésumé : (Auteur) Many existing approaches for image-to-geometry registration assume that either a textured 3D model or a good initial guess of the 3D pose is available to bootstrap the registration process. In this paper we consider the registration of photographs to 3D models even when no texture information is available. This is very challenging as we cannot rely on texture gradients, and even shading gradients are hard to estimate since the lighting conditions are unknown. To that end, we propose average shading gradients, a rendering technique that estimates the average gradient magnitude over all lighting directions under Lambertian shading. We use this gradient representation as the building block of a registration pipeline based on matching sparse features. To cope with inevitable false matches due to the missing texture information and to increase robustness, the pose of the 3D model is estimated in two stages. Coarse pose hypotheses are first obtained from a single correct match each, subsequently refined using SIFT flow, and finally verified. We apply our algorithm to registering images of real-world objects to untextured 3D meshes of limited accuracy. Moreover, we show that registration can be performed even for paintings despite lacking photo-realism. Numéro de notice : A2017-813 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s11263-017-1022-x En ligne : https://doi.org/10.1007/s11263-017-1022-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89255
in International journal of computer vision > vol 125 n° 1-3 (December 2017) . - pp 65 - 81[article]