{
  "id": "2307.10281",
  "version": "v1",
  "published": "2023-07-18T10:58:29.000Z",
  "updated": "2023-07-18T10:58:29.000Z",
  "title": "Semi-supervised Cycle-GAN for face photo-sketch translation in the wild",
  "authors": [
    "Chaofeng Chen",
    "Wei Liu",
    "Xiao Tan",
    "Kwan-Yee K. Wong"
  ],
  "comment": "11 pages, 11 figures, 5 tables (+ 7 page appendix)",
  "categories": [
    "cs.CV"
  ],
  "abstract": "The performance of face photo-sketch translation has improved a lot thanks to deep neural networks. GAN based methods trained on paired images can produce high-quality results under laboratory settings. Such paired datasets are, however, often very small and lack diversity. Meanwhile, Cycle-GANs trained with unpaired photo-sketch datasets suffer from the \\emph{steganography} phenomenon, which makes them not effective to face photos in the wild. In this paper, we introduce a semi-supervised approach with a noise-injection strategy, named Semi-Cycle-GAN (SCG), to tackle these problems. For the first problem, we propose a {\\em pseudo sketch feature} representation for each input photo composed from a small reference set of photo-sketch pairs, and use the resulting {\\em pseudo pairs} to supervise a photo-to-sketch generator $G_{p2s}$. The outputs of $G_{p2s}$ can in turn help to train a sketch-to-photo generator $G_{s2p}$ in a self-supervised manner. This allows us to train $G_{p2s}$ and $G_{s2p}$ using a small reference set of photo-sketch pairs together with a large face photo dataset (without ground-truth sketches). For the second problem, we show that the simple noise-injection strategy works well to alleviate the \\emph{steganography} effect in SCG and helps to produce more reasonable sketch-to-photo results with less overfitting than fully supervised approaches. Experiments show that SCG achieves competitive performance on public benchmarks and superior results on photos in the wild.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-07-18T10:58:29.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "face photo-sketch translation",
      "semi-supervised cycle-gan",
      "small reference set",
      "large face photo dataset",
      "photo-sketch pairs"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 11,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}