{
  "id": "2103.13922",
  "version": "v1",
  "published": "2021-03-25T15:34:18.000Z",
  "updated": "2021-03-25T15:34:18.000Z",
  "title": "ScanGAN360: A Generative Model of Realistic Scanpaths for 360$^{\\circ}$ Images",
  "authors": [
    "Daniel Martin",
    "Ana Serrano",
    "Alexander W. Bergman",
    "Gordon Wetzstein",
    "Belen Masia"
  ],
  "categories": [
    "cs.CV",
    "cs.GR"
  ],
  "abstract": "Understanding and modeling the dynamics of human gaze behavior in 360$^\\circ$ environments is a key challenge in computer vision and virtual reality. Generative adversarial approaches could alleviate this challenge by generating a large number of possible scanpaths for unseen images. Existing methods for scanpath generation, however, do not adequately predict realistic scanpaths for 360$^\\circ$ images. We present ScanGAN360, a new generative adversarial approach to address this challenging problem. Our network generator is tailored to the specifics of 360$^\\circ$ images representing immersive environments. Specifically, we accomplish this by leveraging the use of a spherical adaptation of dynamic-time warping as a loss function and proposing a novel parameterization of 360$^\\circ$ scanpaths. The quality of our scanpaths outperforms competing approaches by a large margin and is almost on par with the human baseline. ScanGAN360 thus allows fast simulation of large numbers of virtual observers, whose behavior mimics real users, enabling a better understanding of gaze behavior and novel applications in virtual scene design.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-03-25T15:34:18.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "generative model",
      "scangan360",
      "generative adversarial approach",
      "large number",
      "behavior mimics real users"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}