EUVIMEDEUVIMED entdecken
Crossref

Efficient Diffusion Model for Image Restoration by Residual Shifting

Zongsheng Yue, Jianyi Wang, Chen Change Loy

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-01 · 47 (1) · 116-130

DOI: 10.1109/tpami.2024.3461721 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-01. Verfasst von Zongsheng Yue und 2 weiteren Autor:innen. Die Arbeit wurde bisher 104-mal zitiert (Crossref) und nennt 111 Literaturangaben. Gefördert von: RIE2020 Industry Alignment Fund Industry Collaboration Projects.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While diffusion-based image restoration (IR) methods have achieved remarkable success, they are still limited by the low inference speed attributed to the necessity of executing hundreds or even thousands of sampling steps. Existing acceleration sampling techniques, though seeking to expedite the process, inevitably sacrifice performance to some extent, resulting in over-blurry restored outcomes. To address this issue, this study proposes a novel and efficient diffusion model for IR that significantly reduces the required number of diffusion steps. Our method avoids the need for post-acceleration during inference, thereby avoiding the associated performance deterioration. Specifically, our proposed method establishes a Markov chain that facilitates the transitions between the high-quality and low-quality images by shifting their residuals, substantially improving the transition efficiency. A carefully formulated noise schedule is devised to flexibly control the shifting speed and the noise strength during the diffusion process. Extensive experimental evaluations demonstrate that the proposed method achieves superior or comparable performance to current state-of-the-art methods on four classical IR tasks, namely image super-resolution, image inpainting, blind face restoration, and image deblurring, even only with four sampling steps.

Förderung

  • RIE2020 Industry Alignment Fund Industry Collaboration Projects

Zitieren

APA

Yue, Z., Wang, J., & Loy, C. C. (2025). Efficient Diffusion Model for Image Restoration by Residual Shifting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(1), 116-130. https://doi.org/10.1109/tpami.2024.3461721

Vancouver

Yue Z, Wang J, Loy CC. Efficient Diffusion Model for Image Restoration by Residual Shifting. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(1):116-130. doi:10.1109/tpami.2024.3461721

BibTeX
@article{Yue2025,
  author = {Yue, Zongsheng and Wang, Jianyi and Loy, Chen Change},
  title = {Efficient Diffusion Model for Image Restoration by Residual Shifting},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {1},
  pages = {116--130},
  doi = {10.1109/tpami.2024.3461721}
}
Kostenlos starten →