Separating reflections from a single image using spatial smoothness and structure information (Contributo in atti di convegno)

Type
Label
  • Separating reflections from a single image using spatial smoothness and structure information (Contributo in atti di convegno) (literal)
Anno
  • 2010-01-01T00:00:00+01:00 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#doi
  • 10.1007/978-3-642-15995-4_79 (literal)
Alternative label
  • Yan Q., Kuruoglu E. E., Yang X., Xu Y., Kayabol K. (2010)
    Separating reflections from a single image using spatial smoothness and structure information
    in LVA/ICA 2010 - Latent Variable Analysis and Signal Separation. 9th International Conference, St. Malo, France, 27-30 September 2010
    (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
  • Yan Q., Kuruoglu E. E., Yang X., Xu Y., Kayabol K. (literal)
Pagina inizio
  • 637 (literal)
Pagina fine
  • 644 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#url
  • http://www.springerlink.com/content/t297381505430v07/ (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#volumeInCollana
  • 6365 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#note
  • In: LVA/ICA 2010 - Latent Variable Analysis and Signal Separation. 9th International Conference (St. Malo, France, 27-30 September 2010). Proceedings, pp. 637 - 644. Vincent Vigneron, Vicente Zarzoso, Eric Moreau, Rémi Gribonval, Emmanuel Vincent (eds.). (Lecture Notes in Computer Science, vol. 6365). Springer, 2010. (literal)
Note
  • Scopu (literal)
  • PuMa (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
  • Shanghai Jiao Tong University, China; CNR-ISTI, Pisa, Italy; Shanghai Jiao Tong University, China; Shanghai Jiao Tong University, China; CNR-ISTI, Pisa, Italy (literal)
Titolo
  • Separating reflections from a single image using spatial smoothness and structure information (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#isbn
  • 978-3-642-15995-4 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#curatoriVolume
  • Vincent Vigneron, Vicente Zarzoso, Eric Moreau, Rémi Gribonval, Emmanuel Vincent (literal)
Abstract
  • We adopt two priors to realize reflection separation from a single image, namely spatial smoothness, which is based on pixels' color dependency, and structure difference, which is got from different source images (transmitted image and reflected image) and different color channels of the same image. By analysing the optical model of reflection, we simplify the mixing matrix further and realize the method for getting spatially varying mixing coefficients. Based on the priors and using Gibbs sampling and appropriate probability density with Bayesian framework, our approach can achieve impressive results for many real world images that corrupted with reflections. (literal)
Prodotto di
Autore CNR
Insieme di parole chiave

Incoming links:


Prodotto
Autore CNR di
Insieme di parole chiave di
data.CNR.it