Refining Coded Image in Human Vision Layer Using CNN-Based Post-Processing

TL;DR

This paper introduces a novel scalable image coding method that incorporates post-processing to enhance image quality for human viewers, improving compression performance and bridging the gap between human and machine image decoding.

Contribution

It is the first to integrate post-processing into scalable coding schemes for both human vision and machine recognition, enhancing image quality and compression efficiency.

Findings

Post-processing improves image quality in scalable coding.

The proposed method outperforms traditional image compression techniques.

Enhanced compression performance validated through experiments.

Abstract

Scalable image coding for both humans and machines is a technique that has gained a lot of attention recently. This technology enables the hierarchical decoding of images for human vision and image recognition models. It is a highly effective method when images need to serve both purposes. However, no research has yet incorporated the post-processing commonly used in popular image compression schemes into scalable image coding method for humans and machines. In this paper, we propose a method to enhance the quality of decoded images for humans by integrating post-processing into scalable coding scheme. Experimental results show that the post-processing improves compression performance. Furthermore, the effectiveness of the proposed method is validated through comparisons with traditional methods.