ShiftLIC: Lightweight Learned Image Compression With Spatial-Channel Shift Operations
IEEE Transactions on Circuits and Systems for Video Technology · 2025-09 · 35 (9) · 9428-9442
DOI: 10.1109/tcsvt.2025.3556708 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-09. Verfasst von Youneng Bao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Province Key Construction Discipline Scientific Research Capacity Improvement Project, Shenzhen Colleges and Universities Stable Support Program.
Abstract (Originalsprache)
Learned Image Compression (LIC) has attracted considerable attention due to their outstanding rate-distortion (R-D) performance and flexibility. However, the substantial computational cost poses challenges for practical deployment. The issue of feature redundancy in LIC is rarely addressed. Our findings indicate that many features within the LIC backbone network exhibit similarities. This paper introduces ShiftLIC, a novel and efficient LIC framework that employs parameter-free shift operations to replace large-kernel convolutions, significantly reducing the model’s computational burden and parameter count. Specifically, we propose the Spatial Shift Block (SSB), which combines shift operations with small-kernel convolutions to replace large-kernel. This approach maintains feature extraction efficiency while reducing both computational complexity and model size. To further enhance the representation capability in the channel dimension, we propose a channel attention module based on recursive feature fusion. This module enhances feature interaction while minimizing computational overhead. Additionally, we introduce an improved entropy model integrated with the SSB module, making the entropy estimation process more lightweight and thereby comprehensively reducing computational costs. Experimental results demonstrate that ShiftLIC outperforms leading compression methods, such as VVC Intra and GMM, in terms of computational cost, parameter count, and decoding latency. Additionally, ShiftLIC sets a new SOTA benchmark with a BD-rate gain per MACs/pixel of −102.6%, showcasing its potential for practical deployment in resource-constrained environments. The code is released at https://github.com/baoyu2020/ShiftLIC.
Förderung
- National Natural Science Foundation of China
- Guangdong Province Key Construction Discipline Scientific Research Capacity Improvement Project
- Shenzhen Colleges and Universities Stable Support Program
- Peng Cheng Laboratory
Zitieren
APA
Bao, Y., Tan, W., Jia, C., Li, M., Liang, Y., & Tian, Y. (2025). ShiftLIC: Lightweight Learned Image Compression With Spatial-Channel Shift Operations. IEEE Transactions on Circuits and Systems for Video Technology, 35(9), 9428-9442. https://doi.org/10.1109/tcsvt.2025.3556708
Vancouver
Bao Y, Tan W, Jia C, Li M, Liang Y, Tian Y. ShiftLIC: Lightweight Learned Image Compression With Spatial-Channel Shift Operations. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(9):9428-9442. doi:10.1109/tcsvt.2025.3556708
BibTeX
@article{Bao2025,
author = {Bao, Youneng and Tan, Wen and Jia, Chuanmin and Li, Mu and Liang, Yongsheng and Tian, Yonghong},
title = {ShiftLIC: Lightweight Learned Image Compression With Spatial-Channel Shift Operations},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {9},
pages = {9428--9442},
doi = {10.1109/tcsvt.2025.3556708}
}
EUVIMED