{
  "id": "2304.01598",
  "version": "v1",
  "published": "2023-04-04T07:38:14.000Z",
  "updated": "2023-04-04T07:38:14.000Z",
  "title": "MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network",
  "authors": [
    "Dan Zhang",
    "Fangfang Zhou",
    "Yuwen Jiang",
    "Zhengming Fu"
  ],
  "comment": "denoising, self-supervised, sRGB, BSN",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Recent advances in deep learning have been pushing image denoising techniques to a new level. In self-supervised image denoising, blind-spot network (BSN) is one of the most common methods. However, most of the existing BSN algorithms use a dot-based central mask, which is recognized as inefficient for images with large-scale spatially correlated noise. In this paper, we give the definition of large-noise and propose a multi-mask strategy using multiple convolutional kernels masked in different shapes to further break the noise spatial correlation. Furthermore, we propose a novel self-supervised image denoising method that combines the multi-mask strategy with BSN (MM-BSN). We show that different masks can cause significant performance differences, and the proposed MM-BSN can efficiently fuse the features extracted by multi-masked layers, while recovering the texture structures destroyed by multi-masking and information transmission. Our MM-BSN can be used to address the problem of large-noise denoising, which cannot be efficiently handled by other BSN methods. Extensive experiments on public real-world datasets demonstrate that the proposed MM-BSN achieves state-of-the-art performance among self-supervised and even unpaired image denoising methods for sRGB images denoising, without any labelling effort or prior knowledge. Code can be found in https://github.com/dannie125/MM-BSN.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-04-04T07:38:14.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "blind-spot network",
      "public real-world datasets demonstrate",
      "mm-bsn achieves state-of-the-art performance",
      "multi-mask strategy",
      "novel self-supervised image denoising method"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}