EUVIMEDEUVIMED entdecken
Crossref

JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer

Mingyu Ouyang, Zhenzhong Chen

IEEE Transactions on Image Processing · 2024 · 33 · 3385-3398

DOI: 10.1109/tip.2024.3403054 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Mingyu Ouyang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Tencent.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

JPEG compression adopts the quantization of Discrete Cosine Transform (DCT) coefficients for effective bit-rate reduction, whilst the quantization could lead to a significant loss of important image details. Recovering compressed JPEG images in the frequency domain has recently garnered increasing interest, complementing the multitude of restoration techniques established in the pixel domain. However, existing DCT domain methods typically suffer from limited effectiveness in handling a wide range of compression quality factors or fall short in recovering sparse quantized coefficients and the components across different colorspaces. To address these challenges, we propose a DCT domain spatial-frequential Transformer, namely DCTransformer, for JPEG quantized coefficient recovery. Specifically, a dual-branch architecture is designed to capture both spatial and frequential correlations within the collocated DCT coefficients. Moreover, we incorporate the operation of quantization matrix embedding, which effectively allows our single model to handle a wide range of quality factors, and a luminance-chrominance alignment head that produces a unified feature map to align different-sized luminance and chrominance components. Our proposed DCTransformer outperforms the current state-of-the-art JPEG artifact removal techniques, as demonstrated by our extensive experiments.

Förderung

  • National Natural Science Foundation of China
  • Tencent

Zitieren

APA

Ouyang, M., & Chen, Z. (2024). JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer. IEEE Transactions on Image Processing, 33, 3385-3398. https://doi.org/10.1109/tip.2024.3403054

Vancouver

Ouyang M, Chen Z. JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer. IEEE Transactions on Image Processing. 2024;33:3385-3398. doi:10.1109/tip.2024.3403054

BibTeX
@article{Ouyang2024,
  author = {Ouyang, Mingyu and Chen, Zhenzhong},
  title = {JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer},
  journal = {IEEE Transactions on Image Processing},
  year = {2024},
  volume = {33},
  pages = {3385--3398},
  doi = {10.1109/tip.2024.3403054}
}
Kostenlos starten →