EUVIMEDEUVIMED entdecken
Crossref

Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration

Xiaole Tang, Xiang Gu, Xiaoyi He, Xin Hu, Jian Sun

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-08 · 47 (8) · 6764-6779

DOI: 10.1109/tpami.2025.3562211 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-08. Verfasst von Xiaole Tang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 92 Literaturangaben. Gefördert von: National Key R&D Program, National Natural Science Foundation of China, National Postdoctoral Program for Innovative Talents.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unified, or more formally, all-in-one image restoration has emerged as a practical and promising low-level vision task for real-world applications. In this context, the key issue lies in how to deal with different types of degraded images simultaneously. Existing methods fit joint regression models over multi-domain degraded-clean image pairs of different degradations. However, due to the severe ill-posedness of inverting heterogeneous degradations, they often struggle with thoroughly perceiving the degradation semantics and rely on paired data for supervised training, yielding suboptimal restoration maps with structurally compromised results and lacking practicality for real-world or unpaired data. To break the barriers, we present a Degradation-Aware Residual-Conditioned Optimal Transport (DA-RCOT) approach that models (all-in-one) image restoration as an optimal transport (OT) problem for unpaired and paired settings, introducing the transport residual as a degradation-specific cue for both the transport cost and the transport map. Specifically, we formalize image restoration with a residual-guided OT objective by exploiting the degradation-specific patterns of the Fourier residual in the transport cost. More crucially, we design the transport map for restoration as a two-pass DA-RCOT map, in which the transport residual is computed in the first pass and then encoded as multi-scale residual embeddings to condition the second-pass restoration. This conditioning process injects intrinsic degradation knowledge (e.g., degradation type and level) and structural information from the multi-scale residual embeddings into the OT map, which thereby can dynamically adjust its behaviors for all-in-one restoration. Extensive experiments across five degradations demonstrate the favorable performance of DA-RCOT as compared to state-of-the-art methods, in terms of distortion measures, perceptual quality, and image structure preservation. Notably, DA-RCOT delivers superior adaptability to real-world scenarios even with mixed degradations and shows distinctive robustness to both degradation levels and the number of degradations.

Förderung

  • National Key R&D Program
  • National Natural Science Foundation of China
  • National Postdoctoral Program for Innovative Talents
  • Fundamental Research Funds for the Central Universities, China

Zitieren

APA

Tang, X., Gu, X., He, X., Hu, X., & Sun, J. (2025). Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(8), 6764-6779. https://doi.org/10.1109/tpami.2025.3562211

Vancouver

Tang X, Gu X, He X, Hu X, Sun J. Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(8):6764-6779. doi:10.1109/tpami.2025.3562211

BibTeX
@article{Tang2025,
  author = {Tang, Xiaole and Gu, Xiang and He, Xiaoyi and Hu, Xin and Sun, Jian},
  title = {Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {8},
  pages = {6764--6779},
  doi = {10.1109/tpami.2025.3562211}
}
Kostenlos starten →