{
  "id": "2401.00370",
  "version": "v1",
  "published": "2023-12-31T02:16:29.000Z",
  "updated": "2023-12-31T02:16:29.000Z",
  "title": "UGPNet: Universal Generative Prior for Image Restoration",
  "authors": [
    "Hwayoon Lee",
    "Kyoungkook Kang",
    "Hyeongmin Lee",
    "Seung-Hwan Baek",
    "Sunghyun Cho"
  ],
  "comment": "Accepted to WACV 2024",
  "categories": [
    "cs.CV",
    "eess.IV"
  ],
  "abstract": "Recent image restoration methods can be broadly categorized into two classes: (1) regression methods that recover the rough structure of the original image without synthesizing high-frequency details and (2) generative methods that synthesize perceptually-realistic high-frequency details even though the resulting image deviates from the original structure of the input. While both directions have been extensively studied in isolation, merging their benefits with a single framework has been rarely studied. In this paper, we propose UGPNet, a universal image restoration framework that can effectively achieve the benefits of both approaches by simply adopting a pair of an existing regression model and a generative model. UGPNet first restores the image structure of a degraded input using a regression model and synthesizes a perceptually-realistic image with a generative model on top of the regressed output. UGPNet then combines the regressed output and the synthesized output, resulting in a final result that faithfully reconstructs the structure of the original image in addition to perceptually-realistic textures. Our extensive experiments on deblurring, denoising, and super-resolution demonstrate that UGPNet can successfully exploit both regression and generative methods for high-fidelity image restoration.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-12-31T02:16:29.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "universal generative prior",
      "original image",
      "regression model",
      "universal image restoration framework",
      "generative model"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}