EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Scene-Adaptive Super-Resolution Framework for Video Compression

Qiyu Zha, Jiangling Guo

Journal of Imaging · 05.05.2026 · 12 (5) · 200

DOI: 10.3390/jimaging12050200 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 05.05.2026. Verfasst von Qiyu Zha und 1 weiteren Autor:innen. Beteiligte Einrichtung: College of Intelligent Science and Engineering, Jinan University, 206 Qianshan Road, Xiangzhou District, Zhuhai 519000, China. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video compression is central to large-scale video delivery, where better rate–distortion efficiency directly reduces bandwidth and storage cost. A practical way to improve efficiency is to encode a low-resolution video stream with a standard codec and restore high-resolution details with a learned super-resolution model at the decoder. However, prior SR-assisted compression methods usually update the reconstruction model at fixed temporal intervals, which can waste bitrate when those update boundaries do not match actual scene changes. In this paper, we present SASVC, a scene-adaptive super-resolution video compression framework for offline codec-augmented compression. SASVC detects scene changes using frame-wise grayscale differences, updates only compact adapter modules when a content transition is observed, and compresses the resulting model updates with chained differencing, quantization, and entropy coding. In this way, the method reduces unnecessary model-stream overhead while preserving scene-specific reconstruction fidelity. Experimental results on both long-form and short-form datasets show that SASVC consistently outperforms SRVC-style baselines and conventional codec-based alternatives under the Bjontegaard delta rate based on peak signal-to-noise ratio (BD-rate/PSNR) criterion. Complementary rate–distortion (RD) comparisons in terms of structural similarity index measure (SSIM) and Video Multi-Method Assessment Fusion (VMAF) show the same overall trend, indicating that the gain is not limited to a single distortion metric. Specifically, SASVC achieves BD-rate gains of −41.33% and −53.49% on Vimeo and Xiph, respectively, and further reaches −51.53% and −39.83% on UVG and MCL-JCV. The decoder also maintains real-time 1080p reconstruction at 125 frames per second (FPS) on an NVIDIA RTX 3080 Ti GPU, indicating that scene-aligned model updates can improve compression efficiency while keeping decoder-side deployment practical.

Schlagwörter

Stichwörter der Autor:innen

adapterchained differential codingparameter-efficient fine-tuningscene-adaptive segmentationsuper-resolutionvideo compression

Autor:innen und Institutionen

  • College of Intelligent Science and Engineering, Jinan University, 206 Qianshan Road, Xiangzhou District, Zhuhai 519000, China.

Zitieren

APA

Zha, Q., & Guo, J. (2026). A Scene-Adaptive Super-Resolution Framework for Video Compression. Journal of Imaging, 12(5), 200. https://doi.org/10.3390/jimaging12050200

Vancouver

Zha Q, Guo J. A Scene-Adaptive Super-Resolution Framework for Video Compression. Journal of Imaging. 2026;12(5):200. doi:10.3390/jimaging12050200

BibTeX
@article{Zha2026,
  author = {Zha, Qiyu and Guo, Jiangling},
  title = {A Scene-Adaptive Super-Resolution Framework for Video Compression},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {5},
  pages = {200},
  doi = {10.3390/jimaging12050200}
}
Kostenlos starten →