@InProceedings{GoncalvesGayaDrewBote:2017:EnDeMe,
               author = "Goncalves, Lucas Teixeira and Gaya, Joel de Oliveira and Drews-Jr, 
                         Paulo and Botelho, Silvia Silva da Costa",
          affiliation = "{Universidade Federal do Rio Grande} and {Universidade Federal do 
                         Rio Grande} and {Universidade Federal do Rio Grande} and 
                         {Universidade Federal do Rio Grande}",
                title = "DeepDive: An End-to-End Dehazing Method Using Deep Learning",
            booktitle = "Proceedings...",
                 year = "2017",
               editor = "Torchelsen, Rafael Piccin and Nascimento, Erickson Rangel do and 
                         Panozzo, Daniele and Liu, Zicheng and Farias, Myl{\`e}ne and 
                         Viera, Thales and Sacht, Leonardo and Ferreira, Nivan and Comba, 
                         Jo{\~a}o Luiz Dihl and Hirata, Nina and Schiavon Porto, Marcelo 
                         and Vital, Creto and Pagot, Christian Azambuja and Petronetto, 
                         Fabiano and Clua, Esteban and Cardeal, Fl{\'a}vio",
         organization = "Conference on Graphics, Patterns and Images, 30. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "Deep Learning, Image Dehazing, Convolutional Neural Network.",
             abstract = "Image dehazing can be described as the problem of mapping from a 
                         hazy image to a haze-free image. Most approaches to this problem 
                         use physical models based on simplifications and priors. In this 
                         work we demonstrate that a convolutional neural network with a 
                         deep architecture and a large image database is able to learn the 
                         entire process of dehazing, without the need to adjust parameters, 
                         resulting in a much more generic method. We evaluate our approach 
                         applying it to real scenes corrupted by haze. The results show 
                         that even though our network is trained with simulated indoor 
                         images, it is capable of dehazing real outdoor scenes, learning to 
                         treat the degradation effect itself, not to reconstruct the scene 
                         behind it.",
  conference-location = "Niter{\'o}i, RJ, Brazil",
      conference-year = "17-20 Oct. 2017",
                  doi = "10.1109/SIBGRAPI.2017.64",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI.2017.64",
             language = "en",
                  ibi = "8JMKD3MGPAW/3PFMFUH",
                  url = "http://urlib.net/ibi/8JMKD3MGPAW/3PFMFUH",
           targetfile = "PID4958913.pdf",
        urlaccessdate = "2024, May 02"
}