EUVIMEDEUVIMED entdecken
Crossref

An Efficient Neural Rate Control for JPEG-AI

Xiang Pan, Guanchen Ding, Zhenzhong Chen, Chang Wen Chen

IEEE Transactions on Circuits and Systems for Video Technology · 2026-03 · 36 (3) · 3917-3922

DOI: 10.1109/tcsvt.2025.3614007 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-03. Verfasst von Xiang Pan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: China National Natural Science Foundation, Hong Kong Research Grants Council, Lingnan University Faculty Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rate control (RC) is a critical component in learned image compression (LIC), particularly in the emerging JPEG-AI standard, which enables adaptive bitrate achievement to meet diverse bandwidth constraints. JPEG-AI default RC employs an iterative optimization process, wherein a pre-trained RC model is selected and the (generated) latent representations are adjusted based on the mismatch between actual and target bitrates. Despite satisfactory results, such a trial-and-error paradigm necessitates multiple processing cycles, resulting in inevitable computational overhead. We propose an efficient neural rate control framework for JPEG-AI to address this limitation. Our idea is to train a ResNet-based neural control (NRC) to learn the mapping from the input images and target bitrates to the optimal coding parameters. The trained NRC can then be applied to predict the coding parameters based on the new input images and target bitrates directly. Experimental results on DIV2K and MSCOCO datasets show that our NRC achieves comparable rate-distortion performance while reducing encoding time by about $5\times $ compared to JPEG-AI default RC.

Förderung

  • China National Natural Science Foundation
  • Hong Kong Research Grants Council
  • Lingnan University Faculty Research

Zitieren

APA

Pan, X., Ding, G., Chen, Z., & Chen, C. W. (2026). An Efficient Neural Rate Control for JPEG-AI. IEEE Transactions on Circuits and Systems for Video Technology, 36(3), 3917-3922. https://doi.org/10.1109/tcsvt.2025.3614007

Vancouver

Pan X, Ding G, Chen Z, Chen CW. An Efficient Neural Rate Control for JPEG-AI. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(3):3917-3922. doi:10.1109/tcsvt.2025.3614007

BibTeX
@article{Pan2026,
  author = {Pan, Xiang and Ding, Guanchen and Chen, Zhenzhong and Chen, Chang Wen},
  title = {An Efficient Neural Rate Control for JPEG-AI},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {3},
  pages = {3917--3922},
  doi = {10.1109/tcsvt.2025.3614007}
}
Kostenlos starten →