FD-LSCIC: Frequency Decomposition-Based Learned Screen Content Image Compression
IEEE Transactions on Broadcasting · 2025-12 · 71 (4) · 1034-1047
DOI: 10.1109/tbc.2025.3609052 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Broadcasting, 2025-12. Verfasst von Shiqi Jiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Taishan Scholar Project of Shandong Province, Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
The learned image compression (LIC) methods have already surpassed traditional techniques in compressing natural scene (NS) images. However, directly applying these methods to screen content (SC) images, which possess distinct characteristics such as sharp edges, repetitive patterns, embedded text and graphics, yields suboptimal results. This paper addresses three key challenges in SC image compression: learning compact latent features, adapting quantization step sizes, and the lack of large SC datasets. To overcome these challenges, we propose a novel compression method that employs a multi-frequency two-stage octave residual block (MToRB) for feature extraction, a cascaded triple-scale feature fusion residual block (CTSFRB) for multi-scale feature integration and a multi-frequency context interaction module (MFCIM) to reduce inter-frequency correlations. Additionally, we introduce an adaptive quantization module that learns scaled uniform noise for each frequency component, enabling flexible control over quantization granularity. Furthermore, we construct a large SC image compression dataset (SDU-SCICD10K), which includes over 10,000 images spanning basic SC images, computer-rendered images, and mixed NS and SC images from both PC and mobile platforms. Experimental results demonstrate that our approach significantly improves SC image compression performance, outperforming traditional standards and state-of-the-art learning-based methods in terms of peak signal-to-noise ratio (PSNR) and multi-scale structural similarity (MS-SSIM). The source code will be opened later in https://github.com/SunshineSki/Screen-content-image-dataset/tree/main/SDU-SCICD10K
Förderung
- National Natural Science Foundation of China
- Taishan Scholar Project of Shandong Province
- Natural Science Foundation of Shandong Province
- OPPO Research Fund
Zitieren
APA
Jiang, S., Yuan, H., Li, S., Zeng, H., & Kwong, S. (2025). FD-LSCIC: Frequency Decomposition-Based Learned Screen Content Image Compression. IEEE Transactions on Broadcasting, 71(4), 1034-1047. https://doi.org/10.1109/tbc.2025.3609052
Vancouver
Jiang S, Yuan H, Li S, Zeng H, Kwong S. FD-LSCIC: Frequency Decomposition-Based Learned Screen Content Image Compression. IEEE Transactions on Broadcasting. 2025;71(4):1034-1047. doi:10.1109/tbc.2025.3609052
BibTeX
@article{Jiang2025,
author = {Jiang, Shiqi and Yuan, Hui and Li, Shuai and Zeng, Huanqiang and Kwong, Sam},
title = {FD-LSCIC: Frequency Decomposition-Based Learned Screen Content Image Compression},
journal = {IEEE Transactions on Broadcasting},
year = {2025},
volume = {71},
number = {4},
pages = {1034--1047},
doi = {10.1109/tbc.2025.3609052}
}
EUVIMED