Learning Switchable Priors for Neural Image Compression
IEEE Transactions on Circuits and Systems for Video Technology · 2025-11 · 35 (11) · 11567-11582
DOI: 10.1109/tcsvt.2025.3577134 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-11. Verfasst von Haotian Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Natural Science Foundation of China.
Abstract (Originalsprache)
Neural image compression (NIC) usually adopts a predefined family of probabilistic distributions as the prior of the latent variables, and meanwhile relies on entropy models to estimate the parameters for the probabilistic family. More complex probabilistic distributions may fit the latent variables more accurately, but also incur higher complexity of the entropy models, limiting their practical value. To address this dilemma, we propose a solution to decouple the entropy model complexity from the prior distributions. We use a finite set of trainable priors that correspond to samples of the parametric probabilistic distributions. We train the entropy model to predict the index of the appropriate prior within the set, rather than the specific parameters. Switching between the trained priors further enables us to embrace a skip mode into the prior set, which simply omits a latent variable during the entropy coding. To demonstrate the practical value of our solution, we present a lightweight NIC model, namely FastNIC, together with the learning of switchable priors. FastNIC outperforms BPG with encoding and decoding complexities below 12 and 10 KMACs/pixel, respectively. We also implanted the switchable priors into state-of-the-art NIC models and observed improved compression efficiency with a significant reduction of entropy coding complexity.
Förderung
- Natural Science Foundation of China
Zitieren
APA
Zhang, H., Li, Y., Li, L., & Liu, D. (2025). Learning Switchable Priors for Neural Image Compression. IEEE Transactions on Circuits and Systems for Video Technology, 35(11), 11567-11582. https://doi.org/10.1109/tcsvt.2025.3577134
Vancouver
Zhang H, Li Y, Li L, Liu D. Learning Switchable Priors for Neural Image Compression. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(11):11567-11582. doi:10.1109/tcsvt.2025.3577134
BibTeX
@article{Zhang2025,
author = {Zhang, Haotian and Li, Yuqi and Li, Li and Liu, Dong},
title = {Learning Switchable Priors for Neural Image Compression},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {11},
pages = {11567--11582},
doi = {10.1109/tcsvt.2025.3577134}
}
EUVIMED