EUVIMEDEUVIMED entdecken
Crossref

Sensitivity Decouple Learning for Image Compression Artifacts Reduction

Li Ma, Yifan Zhao, Peixi Peng, Yonghong Tian

IEEE Transactions on Image Processing · 2024 · 33 · 3620-3633

DOI: 10.1109/tip.2024.3403034 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Li Ma und 3 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 78 Literaturangaben. Gefördert von: Key-Area Research and Development Program of Guangdong Province, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevailing methods only focus on learning a mapping from the compressed image to the original one but ignore the intrinsic attributes of the given compressed images, which greatly harms the performance of downstream parsing tasks. Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction, i.e., the compression-insensitive features to regularize the high-level semantic representations during training and the compression-sensitive features to be aware of the compression degree. To achieve this, we first employ adversarial training to regularize the compressed and original encoded features for retaining high-level semantics, and we then develop the compression quality-aware feature encoder for compression-sensitive features. Based on these dual complementary features, we propose a Dual Awareness Guidance Network (DAGN) to utilize these awareness features as transformation guidance during the decoding phase. In our proposed DAGN, we develop a cross-feature fusion module to maintain the consistency of compression-insensitive features by fusing compression-insensitive features into the artifacts reduction baseline. Our method achieves an average 2.06 dB PSNR gains on BSD500, outperforming state-of-the-art methods, and only requires 29.7 ms to process one image on BSD500. Besides, the experimental results on LIVE1 and LIU4K also demonstrate the efficiency, effectiveness, and superiority of the proposed method in terms of quantitative metrics, visual quality, and downstream machine vision tasks.

Förderung

  • Key-Area Research and Development Program of Guangdong Province
  • National Natural Science Foundation of China

Zitieren

APA

Ma, L., Zhao, Y., Peng, P., & Tian, Y. (2024). Sensitivity Decouple Learning for Image Compression Artifacts Reduction. IEEE Transactions on Image Processing, 33, 3620-3633. https://doi.org/10.1109/tip.2024.3403034

Vancouver

Ma L, Zhao Y, Peng P, Tian Y. Sensitivity Decouple Learning for Image Compression Artifacts Reduction. IEEE Transactions on Image Processing. 2024;33:3620-3633. doi:10.1109/tip.2024.3403034

BibTeX
@article{Ma2024,
  author = {Ma, Li and Zhao, Yifan and Peng, Peixi and Tian, Yonghong},
  title = {Sensitivity Decouple Learning for Image Compression Artifacts Reduction},
  journal = {IEEE Transactions on Image Processing},
  year = {2024},
  volume = {33},
  pages = {3620--3633},
  doi = {10.1109/tip.2024.3403034}
}
Kostenlos starten →