@InProceedings{AriasFeli:2018:ViDeQu,
               author = "Arias, Rafael L. B. and Felinto, Alan Salvany",
          affiliation = "{Londrina State University (UEL)} and {Londrina State University 
                         (UEL)}",
                title = "Video Denoising Quality Assessment for Different Noise 
                         Distributions",
            booktitle = "Proceedings...",
                 year = "2018",
               editor = "Ross, Arun and Gastal, Eduardo S. L. and Jorge, Joaquim A. and 
                         Queiroz, Ricardo L. de and Minetto, Rodrigo and Sarkar, Sudeep and 
                         Papa, Jo{\~a}o Paulo and Oliveira, Manuel M. and Arbel{\'a}ez, 
                         Pablo and Mery, Domingo and Oliveira, Maria Cristina Ferreira de 
                         and Spina, Thiago Vallin and Mendes, Caroline Mazetto and Costa, 
                         Henrique S{\'e}rgio Gutierrez and Mejail, Marta Estela and Geus, 
                         Klaus de and Scheer, Sergio",
         organization = "Conference on Graphics, Patterns and Images, 31. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "denoising, noise, video, quality metrics.",
             abstract = "Denoising algorithms often presume a single noise model, for 
                         instance, Gaussian noise, but it has been observed that during 
                         acquisition, image and video sequences can be corrupted by 
                         different types of noise, which follow a distinct probability 
                         distribution model depending on the application. This paper aims 
                         to compare the performance of several denoising algorithms, among 
                         them Non-Local Means and Block-Matching 3D, and other classical 
                         techniques such as median, Gaussian, bilateral and anisotropic 
                         diffusion, by simulating different noise distributions in videos 
                         and comparing the methods efficiency in multiple scenarios. 
                         Objective evaluation uses structural similarity (SSIM) and 
                         provides video specific assessment scores with NTIA Video Quality 
                         Metric (VQM). Results show considerable differences between 
                         intraframe and interframe filtering quality, while variations in 
                         filtering responses to each type of noise contribute to more 
                         appropriate selection of techniques to noise reduction and provide 
                         insight to noise difficulty levels.",
  conference-location = "Foz do Igua{\c{c}}u, PR, Brazil",
      conference-year = "29 Oct.-1 Nov. 2018",
                  doi = "10.1109/SIBGRAPI.2018.00015",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI.2018.00015",
             language = "en",
                  ibi = "8JMKD3MGPAW/3RMQBE2",
                  url = "http://urlib.net/ibi/8JMKD3MGPAW/3RMQBE2",
           targetfile = "Paper ID 55.pdf",
        urlaccessdate = "2024, Apr. 28"
}