Konferans bildirisi Açık Erişim

Graph2Pix: A Graph-Based Image to Image Translation Framework

Gokay, Dilara; Simsar, Enis; Atici, Efehan; Ahmetoglu, Alper; Yuksel, Atif Emre; Yanardag, Pinar


JSON-LD (schema.org)

{
  "@context": "https://schema.org/", 
  "@id": 237762, 
  "@type": "ScholarlyArticle", 
  "creator": [
    {
      "@type": "Person", 
      "affiliation": "Tech Univ Munich, Munich, Germany", 
      "name": "Gokay, Dilara"
    }, 
    {
      "@type": "Person", 
      "name": "Simsar, Enis"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Bogazici Univ, Bebek, Turkey", 
      "name": "Atici, Efehan"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Bogazici Univ, Bebek, Turkey", 
      "name": "Ahmetoglu, Alper"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Bogazici Univ, Bebek, Turkey", 
      "name": "Yuksel, Atif Emre"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Bogazici Univ, Bebek, Turkey", 
      "name": "Yanardag, Pinar"
    }
  ], 
  "datePublished": "2021-01-01", 
  "description": "In this paper, we propose a graph-based image-to-image translation framework for generating images. We use rich data collected from the popular creativity platform Artbreeder', where users interpolate multiple GAN-generated images to create artworks. This unique approach of creating new images leads to a tree-like structure where one can track historical data about the creation of a particular image. Inspired by this structure, we propose a novel graph-to-image translation model called Graph2Pix, which takes a graph and corresponding images as input and generates a single image as output. Our experiments show that Graph2Pix is able to outperform several image-to-image translation frameworks on benchmark metrics, including LPIPS (with a 25% improvement) and human perception studies (n = 60), where users preferred the images generated by our method 81.5% of the time.", 
  "headline": "Graph2Pix: A Graph-Based Image to Image Translation Framework", 
  "identifier": 237762, 
  "image": "https://aperta.ulakbim.gov.tr/static/img/logo/aperta_logo_with_icon.svg", 
  "license": "http://www.opendefinition.org/licenses/cc-by", 
  "name": "Graph2Pix: A Graph-Based Image to Image Translation Framework", 
  "url": "https://aperta.ulakbim.gov.tr/record/237762"
}
20
5
görüntülenme
indirilme
Görüntülenme 20
İndirme 5
Veri hacmi 1.1 kB
Tekil görüntülenme 18
Tekil indirme 5

Alıntı yap