@InProceedings{SantosLaRiNePrMe:2022:FaSuUs,
               author = "Santos, Marcelo dos and Laroca, Rayson and Ribeiro, Rafael O. and 
                         Neves, Jo{\~a}o and Proen{\c{c}}a, Hugo and Menotti, David",
          affiliation = "Department of Informatics, Federal University of Paran{\'a}, 
                         Curitiba, Brazil and Department of Informatics, Federal University 
                         of Paran{\'a}, Curitiba, Brazil and † National Institute of 
                         Criminalistics, Brazilian Federal Police, Bras{\'{\i}}lia, 
                         Brazil and Instituto de Telecomunica{\c{c}}{\~o}es, University 
                         of Beira Interior, Covilh{\~a}, Portugal and Instituto de 
                         Telecomunica{\c{c}}{\~o}es, University of Beira Interior, 
                         Covilh{\~a}, Portugal and Department of Informatics, Federal 
                         University of Paran{\'a}, Curitiba, Brazil",
                title = "Face Super-Resolution Using Stochastic Differential Equations",
            booktitle = "Proceedings...",
                 year = "2022",
         organization = "Conference on Graphics, Patterns and Images, 35. (SIBGRAPI)",
             keywords = "Super-Resolution, Stochastic Differencial Equaitons, Face 
                         Recognition.",
             abstract = "Diffusion models have proven effective for various applications 
                         such as images, audio and graph generation. Other important 
                         applications are image super-resolution and the solution of 
                         inverse problems. More recently, some works have used stochastic 
                         differential equations (SDEs) to generalize diffusion models to 
                         continuous time. In this work, we introduce SDEs to generate 
                         super-resolution face images. To the best of our knowledge, this 
                         is the first time SDEs have been used for such an application. The 
                         proposed method provides an improved peak signal-to-noise ratio 
                         (PSNR), structural similarity index measure (SSIM), and 
                         consistency than the existing super-resolution methods based on 
                         diffusion models. In particular, we also assess the potential 
                         application of this method for the face recognition task. A 
                         generic facial feature extractor is used to compare the 
                         super-resolution images with the ground truth, and superior 
                         results were obtained compared with other methods. Our code is 
                         publicly available at https://github.com/marcelowds/sr-sde.",
  conference-location = "Natal, RN",
      conference-year = "24-27 Oct. 2022",
                  doi = "10.1109/SIBGRAPI55357.2022.9991799",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI55357.2022.9991799",
             language = "en",
                  ibi = "8JMKD3MGPEW34M/47MDRPP",
                  url = "http://urlib.net/ibi/8JMKD3MGPEW34M/47MDRPP",
           targetfile = "2022_SIBGRAPI_SDE_INPE.pdf",
        urlaccessdate = "2024, Apr. 28"
}