“Escaping Specularity: Recovering Specular-Free Video Sequences from Rank-Constrained Data” by Alsaleh, Aviles, Casals and Hahn

  • ©Samar M. Alsaleh, Angelica I. Aviles, Alicia Casals, and James K. Hahn

  • ©Samar M. Alsaleh, Angelica I. Aviles, Alicia Casals, and James K. Hahn

  • ©Samar M. Alsaleh, Angelica I. Aviles, Alicia Casals, and James K. Hahn

Conference:


Type:


Entry Number: 78

Title:

    Escaping Specularity: Recovering Specular-Free Video Sequences from Rank-Constrained Data

Presenter(s)/Author(s):



Abstract:


    The appearance of objects is significantly affected by the illumination conditions in the environment. Particularly with objects that have strong reflectivity as they suffer from more dominant specular highlights, causing information loss and discontinuity in the image domain. Many computer vision algorithms are vulnerable to errors in the presence of specular highlights because they violate the image consistency assumption and hinder the performance of many vision tasks, such as object recognition, tracking and surface reconstruction [Artusi et al. 2011]. This is further complicated when we consider video sequences with free-moving cameras or dynamic objects, which is the focus of this work.

Keyword(s):



PDF:



ACM Digital Library Publication:



Overview Page: