EUVIMEDEUVIMED entdecken
Crossref

Hierarchical Frequency-Guided Alignment Transformer for Compressed Video Quality Enhancement

Liuhan Peng, Shuai Li, Yanbo Gao, Mao Ye, Chong Lv

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (10) · 8349-8357

DOI: 10.1609/aaai.v40i10.37784 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Liuhan Peng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

During the video encoding process, the original spatial domain signal is first transformed into the frequency domain, followed by quantization and compression. As a result, the quality degradation in compressed videos primarily stems from distortions in the frequency domain information. However, existing video enhancement methods typically directly fuse information from adjacent frames in the spatial domain, making it difficult for models to effectively compensate for frequency domain distortions, which leads to suboptimal detail restoration. To address this issue, we propose a Hierarchical Frequency-Guided Alignment Transformer. Additionally, by analyzing the characteristics of the frequency domain, we find that different frequency bands exhibit both correlations and a certain degree of independence. Based on this, we introduce a Frequency-Aware Transformer module that employs a combination of independent and mixed processing to optimize information exchange across different frequency domains, effectively mitigating cross-interference from irrelevant information. Experimental results demonstrate that, compared to existing methods, our approach achieves state-of-the-art performance in objective metrics (PSNR/SSIM), perceptual quality (LPIPS), and subjective visual effects, while reducing model complexity.

Zitieren

APA

Peng, L., Li, S., Gao, Y., Ye, M., & Lv, C. (2026). Hierarchical Frequency-Guided Alignment Transformer for Compressed Video Quality Enhancement. Proceedings of the AAAI Conference on Artificial Intelligence, 40(10), 8349-8357. https://doi.org/10.1609/aaai.v40i10.37784

Vancouver

Peng L, Li S, Gao Y, Ye M, Lv C. Hierarchical Frequency-Guided Alignment Transformer for Compressed Video Quality Enhancement. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(10):8349-8357. doi:10.1609/aaai.v40i10.37784

BibTeX
@article{Peng2026,
  author = {Peng, Liuhan and Li, Shuai and Gao, Yanbo and Ye, Mao and Lv, Chong},
  title = {Hierarchical Frequency-Guided Alignment Transformer for Compressed Video Quality Enhancement},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {10},
  pages = {8349--8357},
  doi = {10.1609/aaai.v40i10.37784}
}
Kostenlos starten →