DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression

TL;DR

DeepFGS introduces a novel fine-grained scalable image compression framework that enhances scalability and performance by feature separation and mutual entropy modeling, outperforming existing methods in PSNR and MS-SSIM.

Contribution

The paper presents a new scalable coding framework with feature separation and a mutual entropy model, improving scalability and compression quality over prior approaches.

Findings

Outperforms previous learning-based scalable image compression models.

Achieves higher PSNR and MS-SSIM metrics than traditional codecs.

Reduces parameters and computational complexity through decoder reuse.

Abstract

Scalable coding, which can adapt to channel bandwidth variation, performs well in today's complex network environment. However, most existing scalable compression methods face two challenges: reduced compression performance and insufficient scalability. To overcome the above problems, this paper proposes a learned fine-grained scalable image compression framework, namely DeepFGS. Specifically, we introduce a feature separation backbone to divide the image information into basic and scalable features, then redistribute the features channel by channel through an information rearrangement strategy. In this way, we can generate a continuously scalable bitstream via one-pass encoding. For entropy coding, we design a mutual entropy model to fully explore the correlation between the basic and scalable features. In addition, we reuse the decoder to reduce the parameters and computational complexity. Experiments demonstrate that our proposed DeepFGS outperforms previous learning-based scalable image compression models and traditional scalable image codecs in both PSNR and MS-SSIM metrics.