Frequency-aware Learned Image Compression for Quality Scalability

TL;DR

This paper introduces a neural network-based image compression method that uses frequency decomposition to enable scalable quality and region-specific enhancement, achieving competitive rate-distortion performance.

Contribution

It presents a novel frequency-aware neural image coding framework with scalable quality and ROI enhancement capabilities, integrating wavelet transforms into neural compression.

Findings

Competitive rate-distortion performance compared to non-scalable codecs.

Effective two-level quality scalability demonstrated.

Practical ROI quality enhancement shown.

Abstract

Spatial frequency analysis and transforms serve a central role in most engineered image and video lossy codecs, but are rarely employed in neural network (NN)-based approaches. We propose a novel NN-based image coding framework that utilizes forward wavelet transforms to decompose the input signal by spatial frequency. Our encoder generates separate bitstreams for each latent representation of low and high frequencies. This enables our decoder to selectively decode bitstreams in a quality-scalable manner. Hence, the decoder can produce an enhanced image by using an enhancement bitstream in addition to the base bitstream. Furthermore, our method is able to enhance only a specific region of interest (ROI) by using a corresponding part of the enhancement latent representation. Our experiments demonstrate that the proposed method shows competitive rate-distortion performance compared to several non-scalable image codecs. We also showcase the effectiveness of our two-level quality scalability, as well as its practicality in ROI quality enhancement.