EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Multi-Swin Transformer Based Spatio-Temporal Information Exploration for Compressed Video Quality Enhancement

Li Yu, Shiyu Wu, Moncef Gabbouj

IEEE Signal Processing Letters · 2024 · 31 · 1880-1884

DOI: 10.1109/lsp.2024.3429008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2024. Verfasst von Li Yu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China, The Startup Foundation for Introducing Talent of NUIST.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatio-temporal information plays an important role in compressed video quality enhancement. Most advanced studies use deformable convolution or Swin transformer to explore spatio-temporal information. However, deformable convolution based methods may incur inaccurate motion compensation due to the compression artifacts and limited receptive fields. The Swin transformer based approaches are unable to fully explore the spatio-temporal information, limited by its rigid window-based mechanism. To solve the above problems, we propose a novel multi-Swin transformer-based network for compressed video quality enhancement to better explore spatio-temporal information. The whole workflow consists of the Local Alignment (LA) Module, the Global Refinement Fusion (GRF) Module, and the Quality Enhancement (QE) Module. The LA module roughly perceives the local motion through the deformable fusion. Subsequently, the GRF module employs the proposed multi-Swin transformer to enhance the spatio-temporal perception. Finally, the QE module effectively restores the texture details across various scales. Extensive experimental results prove the effectiveness of the proposed method.

Förderung

  • National Natural Science Foundation of China
  • The Startup Foundation for Introducing Talent of NUIST

Zitieren

APA

Yu, L., Wu, S., & Gabbouj, M. (2024). Multi-Swin Transformer Based Spatio-Temporal Information Exploration for Compressed Video Quality Enhancement. IEEE Signal Processing Letters, 31, 1880-1884. https://doi.org/10.1109/lsp.2024.3429008

Vancouver

Yu L, Wu S, Gabbouj M. Multi-Swin Transformer Based Spatio-Temporal Information Exploration for Compressed Video Quality Enhancement. IEEE Signal Processing Letters. 2024;31:1880-1884. doi:10.1109/lsp.2024.3429008

BibTeX
@article{Yu2024,
  author = {Yu, Li and Wu, Shiyu and Gabbouj, Moncef},
  title = {Multi-Swin Transformer Based Spatio-Temporal Information Exploration for Compressed Video Quality Enhancement},
  journal = {IEEE Signal Processing Letters},
  year = {2024},
  volume = {31},
  pages = {1880--1884},
  doi = {10.1109/lsp.2024.3429008}
}
Kostenlos starten →