EUVIMEDEUVIMED entdecken
Crossref

Local Texture Pattern Estimation for Image Detail Super-Resolution

Fan Fan, Yang Zhao, Yuan Chen, Nannan Li, Wei Jia, Ronggang Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-06 · 47 (6) · 4517-4534

DOI: 10.1109/tpami.2025.3545571 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-06. Verfasst von Fan Fan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the image super-resolution (SR) field, recovering missing high-frequency textures has always been an important goal. However, deep SR networks based on pixel-level constraints tend to focus on stable edge details and cannot effectively restore random high-frequency textures. It was not until the emergence of the generative adversarial network (GAN) that GAN-based SR models achieved realistic texture restoration and quickly became the mainstream method for texture SR. However, GAN-based SR models still have some drawbacks, such as relying on a large number of parameters and generating fake textures that are inconsistent with ground truth. Inspired by traditional texture analysis research, this paper proposes a novel SR network based on local texture pattern estimation (LTPE), which can restore fine high-frequency texture details without GAN. A differentiable local texture operator is first designed to extract local texture structures, and a texture enhancement branch is used to predict the high-resolution local texture distribution based on the LTPE. Then, the predicted high-resolution texture structure map can be used as a reference for the texture fusion SR branch to obtain high-quality texture reconstruction. Finally, $L_{1}$L1 loss and Gram loss are simultaneously used to optimize the network. Experimental results demonstrate that the proposed method can effectively recover high-frequency texture without using GAN structures. In addition, the restored high-frequency details are constrained by local texture distribution, thereby reducing significant errors in texture generation.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Fan, F., Zhao, Y., Chen, Y., Li, N., Jia, W., & Wang, R. (2025). Local Texture Pattern Estimation for Image Detail Super-Resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(6), 4517-4534. https://doi.org/10.1109/tpami.2025.3545571

Vancouver

Fan F, Zhao Y, Chen Y, Li N, Jia W, Wang R. Local Texture Pattern Estimation for Image Detail Super-Resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(6):4517-4534. doi:10.1109/tpami.2025.3545571

BibTeX
@article{Fan2025,
  author = {Fan, Fan and Zhao, Yang and Chen, Yuan and Li, Nannan and Jia, Wei and Wang, Ronggang},
  title = {Local Texture Pattern Estimation for Image Detail Super-Resolution},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {6},
  pages = {4517--4534},
  doi = {10.1109/tpami.2025.3545571}
}
Kostenlos starten →