EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Parameter Adaptive Network for Large-Scale Neural In-Loop Filtering in Versatile Video Coding

Yuansheng Wu, Fan Cai, Xiaodan Song iD, Xuguang Zuo

Sensors · 30.04.2026 · 26 (9) · 2808

DOI: 10.3390/s26092808 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.04.2026. Verfasst von Yuansheng Wu und 3 weiteren Autor:innen. Beteiligte Einrichtung: National Key Laboratory of Complex Aviation System Simulation, Southwest China Institute of Electronic Technology, Chengdu 610036, China. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Efficient in-loop filtering is critical for the latest video-coding standard, versatile video coding (H.266/VVC). While parameter-adaptive mechanisms are effective in traditional adaptive loop filters and overfitted small-scale neural in-loop filtering, there is difficulty when deploying them in large-scale models since both schemes require explicit parameter signaling within the bitstream, leading to prohibitive overhead. Existing parameter-generation networks avoid these transmission costs but introduce an excessive number of parameters. To address this, we propose modeling convolutional parameters as a linear combination of pre-trained kernels, where weights are adaptively estimated via input-driven attention. Specifically, we propose a multi-scale parameter-adaptive convolution and its extension, with side information, enabling parameter adaptation without transmission overhead or significant computational costs. Furthermore, we have designed an efficient parameter adaptive in-loop filtering network with the proposed convolutions to balance parameter efficiency and reconstruction performance. To improve the distortion guidance provided by side information, we have incorporated gradient information. Experiments on VTM-11.0 demonstrate {7.89%, 18.25%, and 19.15%} bitrate savings for {Y, U, and V} components, outperforming fixed-parameter baselines by an average of 1.41% with negligible computational overhead.

Schlagwörter

Stichwörter der Autor:innen

adaptive parameterconvolution neural networkgradientin-loop filteringversatile video coding

Autor:innen und Institutionen

  • National Key Laboratory of Complex Aviation System Simulation, Southwest China Institute of Electronic Technology, Chengdu 610036, China.
  • Guangzhou Institute of Technology, Xidian University, Guangzhou 510555, China.
  • NetInt, Shanghai 201203, China.

ORCID-Profile: Xiaodan Song

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wu, Y., Cai, F., Song, X., & Zuo, X. (2026). Parameter Adaptive Network for Large-Scale Neural In-Loop Filtering in Versatile Video Coding. Sensors, 26(9), 2808. https://doi.org/10.3390/s26092808

Vancouver

Wu Y, Cai F, Song X, Zuo X. Parameter Adaptive Network for Large-Scale Neural In-Loop Filtering in Versatile Video Coding. Sensors. 2026;26(9):2808. doi:10.3390/s26092808

BibTeX
@article{Wu2026,
  author = {Wu, Yuansheng and Cai, Fan and Song, Xiaodan and Zuo, Xuguang},
  title = {Parameter Adaptive Network for Large-Scale Neural In-Loop Filtering in Versatile Video Coding},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {9},
  pages = {2808},
  doi = {10.3390/s26092808}
}
Kostenlos starten →