1 Ocak 2021 Konferans bildirisi Açık Erişim

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

Citation Style Language JSON

{
  "DOI": "10.1109/ICCVW54120.2021.00227", 
  "abstract": "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.", 
  "author": [
    {
      "family": "Gokay", 
      "given": " Dilara"
    }, 
    {
      "family": "Simsar", 
      "given": " Enis"
    }, 
    {
      "family": "Atici", 
      "given": " Efehan"
    }, 
    {
      "family": "Ahmetoglu", 
      "given": " Alper"
    }, 
    {
      "family": "Yuksel", 
      "given": " Atif Emre"
    }, 
    {
      "family": "Yanardag", 
      "given": " Pinar"
    }
  ], 
  "id": "237762", 
  "issued": {
    "date-parts": [
      [
        2021, 
        1, 
        1
      ]
    ]
  }, 
  "title": "Graph2Pix: A Graph-Based Image to Image Translation Framework", 
  "type": "paper-conference"
}