JND-Guided Light-Weight Neural Pre-Filter for Perceptual Image Coding
This provides a more efficient solution for perceptual image compression, though it appears incremental as it builds on existing JND-guided pre-filter techniques.
This paper tackles the problem of computationally expensive Just Noticeable Distortion (JND)-guided pre-filters for perceptual image coding by proposing a lightweight CNN framework, achieving state-of-the-art compression efficiency with only 7.15 GFLOPs for 1080p images (14.1% of recent lightweight network costs).
Just Noticeable Distortion (JND)-guided pre-filter is a promising technique for improving the perceptual compression efficiency of image coding. However, existing methods are often computationally expensive, and the field lacks standardized benchmarks for fair comparison. To address these challenges, this paper introduces a twofold contribution. First, we develop and open-source FJNDF-Pytorch, a unified benchmark for frequency-domain JND-Guided pre-filters. Second, leveraging this platform, we propose a complete learning framework for a novel, lightweight Convolutional Neural Network (CNN). Experimental results demonstrate that our proposed method achieves state-of-the-art compression efficiency, consistently outperforming competitors across multiple datasets and encoders. In terms of computational cost, our model is exceptionally lightweight, requiring only 7.15 GFLOPs to process a 1080p image, which is merely 14.1% of the cost of recent lightweight network. Our work presents a robust, state-of-the-art solution that excels in both performance and efficiency, supported by a reproducible research platform. The open-source implementation is available at https://github.com/viplab-fudan/FJNDF-Pytorch.