{
  "id": "2003.04858",
  "version": "v1",
  "published": "2020-03-10T17:10:38.000Z",
  "updated": "2020-03-10T17:10:38.000Z",
  "title": "Unpaired Image-to-Image Translation using Adversarial Consistency Loss",
  "authors": [
    "Yihao Zhao",
    "Ruihai Wu",
    "Hao Dong"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Unpaired image-to-image translation is a class of vision problems whose goal is to find the mapping between different image domains using unpaired training data. Cycle-consistency loss is a widely used constraint for such problems. However, due to the strict pixel-level constraint, it cannot perform geometric changes, remove large objects, or ignore irrelevant texture. In this paper, we propose a novel adversarial-consistency loss for image-to-image translation. This loss does not require the translated image to be translated back to be a specific source image but can encourage the translated images to retain important features of the source images and overcome the drawbacks of cycle-consistency loss noted above. Our method achieves state-of-the-art results on three challenging tasks: glasses removal, male-to-female translation, and selfie-to-anime translation.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-03-10T17:10:38.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "unpaired image-to-image translation",
      "adversarial consistency loss",
      "method achieves state-of-the-art results",
      "cycle-consistency loss",
      "ignore irrelevant texture"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}