Color Learning for Image Compression

TL;DR

This paper introduces a novel deep learning architecture for image compression that separately processes luminance and chrominance channels, optimizing color fidelity and outperforming existing codecs.

Contribution

It proposes a dual-branch deep learning model for image compression that explicitly incorporates color information and uses a color difference metric in the loss function.

Findings

Improved color fidelity in compressed images.

Enhanced compression performance compared to traditional codecs.

Insightful analysis of latent channel responses.

Abstract

Deep learning based image compression has gained a lot of momentum in recent times. To enable a method that is suitable for image compression and subsequently extended to video compression, we propose a novel deep learning model architecture, where the task of image compression is divided into two sub-tasks, learning structural information from luminance channel and color from chrominance channels. The model has two separate branches to process the luminance and chrominance components. The color difference metric CIEDE2000 is employed in the loss function to optimize the model for color fidelity. We demonstrate the benefits of our approach and compare the performance to other codecs. Additionally, the visualization and analysis of latent channel impulse response is performed.