FD-LSCIC: Frequency Decomposition-based Learned Screen Content Image Compression

TL;DR

This paper introduces a novel frequency decomposition-based learned screen content image compression method that effectively captures multi-frequency features, adapts quantization, and leverages a large dataset, outperforming existing methods in quality metrics.

Contribution

The paper proposes a new multi-frequency two-stage residual network, adaptive quantization, and a large SC image dataset to improve compression of screen content images.

Findings

Significant PSNR and MS-SSIM improvements over traditional and state-of-the-art methods.

Effective multi-frequency feature extraction and adaptive quantization enhance compression quality.

Constructed a large, diverse SC image dataset for training and evaluation.

Abstract

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).