F Nous contacter

Multi angle

H 1 Transferring information across image and shape collections

Auteurs : Mitra, Niloy (Auteur de la Conférence)
CIRM (Editeur )

    Loading the player...

    Résumé : Large image and 3D model repositories of everyday objects are now ubiquitous and are increasingly being used in computer graphics and computer vision, both for analysis and synthesis. However, images of objects in the real world have a richness of appearance that these repositories do not capture, largely because most existing 3D models are untextured. In this work we develop an automated pipeline capable of linking the two collections, and transporting texture information from images of real objects to 3D models of similar objects. This is a challenging problem, as an object's texture as seen in a photograph is distorted by many factors, including pose, geometry, and illumination. These geometric and photometric distortions must be undone in order to transfer the pure underlying texture to a new object ? the 3D model. Instead of using problematic dense correspondences, we factorize the problem into the reconstruction of a set of base textures (materials) and an illumination model for the object in the image. By exploiting the geometry of the similar 3D model, we reconstruct certain reliable texture regions and correct for the illumination, from which a full texture map can be recovered and applied to the model. Our method allows for large-scale unsupervised production of richly textured 3D models directly from image data, providing high quality virtual objects for 3D scene design or photo editing applications, as well as a wealth of data for training machine learning algorithms for various inference tasks in graphics and vision. For more details, please visit: geometry.cs.ucl.ac.uk.

    Codes MSC :
    65D18 - Computer graphics, image analysis, and computational geometry
    68U10 - Image processing

      Informations sur la Vidéo

      Réalisateur : Hennenfent, Guillaume
      Langue : Anglais
      Date de publication : 10/11/16
      Date de captation : 02/11/2016
      Collection : Research talks
      Format : MP4
      Durée : 00:47:37
      Domaine : Computer Science ; Analyse & Applications ; Geometry
      Audience : Chercheurs ; Doctorants , Post - Doctorants
      Download : https://videos.cirm-math.fr/2016-11-02_Mitra.mp4

    Informations sur la rencontre

    Nom du congrès : SIGMA (Signal-Image-Geometry-Modelling-Approximation) / SIGMA (Signal-Image-Géométrie-Modélisation-Approximation)
    Organisteurs Congrès : Beckermann, Bernhard ; Chazal, Frédéric ; Lyche, Tom ; Mazure, Marie-Laurence ; Peyré, Gabriel
    Dates : 31/10/2016 - 04/11/2016
    Année de la rencontre : 2016
    URL Congrès : http://conferences.cirm-math.fr/1506.html

    Citation Data

    DOI : 10.24350/CIRM.V.19081303
    Cite this video as: Mitra, Niloy (2016). Transferring information across image and shape collections. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19081303
    URI : http://dx.doi.org/10.24350/CIRM.V.19081303

    Voir aussi


    1. Smart Geometry Processing Group, University College London - http://geometry.cs.ucl.ac.uk/