A Lightweight Model for Perceptual Image Compression via Implicit Priors

TL;DR

This paper introduces a lightweight perceptual image compression method that leverages implicit semantic priors and frequency-aware modules, achieving competitive performance with fewer parameters suitable for resource-limited devices.

Contribution

The paper proposes a novel lightweight compression framework using implicit semantic priors and frequency decomposition, reducing model complexity while maintaining high perceptual quality.

Findings

Achieves competitive compression performance on benchmarks.

Uses significantly fewer parameters and FLOPs than state-of-the-art methods.

Demonstrates effectiveness on resource-constrained devices.

Abstract

Perceptual image compression has shown strong potential for producing visually appealing results at low bitrates, surpassing classical standards and pixel-wise distortion-oriented neural methods. However, existing methods typically improve compression performance by incorporating explicit semantic priors, such as segmentation maps and textual features, into the encoder or decoder, which increases model complexity by adding parameters and floating-point operations. This limits the model's practicality, as image compression often occurs on resource-limited mobile devices. To alleviate this problem, we propose a lightweight perceptual Image Compression method using Implicit Semantic Priors (ICISP). We first develop an enhanced visual state space block that exploits local and global spatial dependencies to reduce redundancy. Since different frequency information contributes unequally to compression, we develop a frequency decomposition modulation block to adaptively preserve or reduce the low-frequency and high-frequency information. We establish the above blocks as the main modules of the encoder-decoder, and to further improve the perceptual quality of the reconstructed images, we develop a semantic-informed discriminator that uses implicit semantic priors from a pretrained DINOv2 encoder. Experiments on popular benchmarks show that our method achieves competitive compression performance and has significantly fewer network parameters and floating point operations than the existing state-of-the-art.