Deep chroma compression of tone-mapped images

TL;DR

This paper introduces a GAN-based method for fast, accurate chroma compression of HDR tone-mapped images, improving color fidelity and enabling real-time processing on resource-limited devices.

Contribution

It proposes a novel generative adversarial network with a hue-aware loss function for efficient chroma compression in HDR images, outperforming existing methods.

Findings

Outperforms state-of-the-art in color accuracy

Achieves real-time processing on limited hardware

Maintains or improves visual quality of compressed images

Abstract

Acquisition of high dynamic range (HDR) images is thriving due to the increasing use of smart devices and the demand for high-quality output. Extensive research has focused on developing methods for reducing the luminance range in HDR images using conventional and deep learning-based tone mapping operators to enable accurate reproduction on conventional 8 and 10-bit digital displays. However, these methods often fail to account for pixels that may lie outside the target display's gamut, resulting in visible chromatic distortions or color clipping artifacts. Previous studies suggested that a gamut management step ensures that all pixels remain within the target gamut. However, such approaches are computationally expensive and cannot be deployed on devices with limited computational resources. We propose a generative adversarial network for fast and reliable chroma compression of HDR tone-mapped images. We design a loss function that considers the hue property of generated images to improve color accuracy, and train the model on an extensive image dataset. Quantitative experiments demonstrate that the proposed model outperforms state-of-the-art image generation and enhancement networks in color accuracy, while a subjective study suggests that the generated images are on par or superior to those produced by conventional chroma compression methods in terms of visual quality. Additionally, the model achieves real-time performance, showing promising results for deployment on devices with limited computational resources.