Learned HDR Image Compression for Perceptually Optimal Storage and Display

TL;DR

This paper introduces an end-to-end learned HDR image compression method that optimizes storage and display quality by generating compatible LDR images and auxiliary data for high-quality HDR reconstruction, outperforming traditional residual-based methods.

Contribution

The work presents a novel end-to-end deep learning approach for HDR image compression that jointly optimizes for perceptual quality and compatibility with legacy displays, surpassing conventional residual-based techniques.

Findings

Significant improvement in HDR and LDR image quality at all bit rates.

Effective use of perceptual metrics validated against human quality assessments.

End-to-end optimization enhances rate-distortion performance over traditional methods.

Abstract

High dynamic range (HDR) capture and display have seen significant growth in popularity driven by the advancements in technology and increasing consumer demand for superior image quality. As a result, HDR image compression is crucial to fully realize the benefits of HDR imaging without suffering from large file sizes and inefficient data handling. Conventionally, this is achieved by introducing a residual/gain map as additional metadata to bridge the gap between HDR and low dynamic range (LDR) images, making the former compatible with LDR image codecs but offering suboptimal rate-distortion performance. In this work, we initiate efforts towards end-to-end optimized HDR image compression for perceptually optimal storage and display. Specifically, we learn to compress an HDR image into two bitstreams: one for generating an LDR image to ensure compatibility with legacy LDR displays, and another as side information to aid HDR image reconstruction from the output LDR image. To measure the perceptual quality of output HDR and LDR images, we use two recently proposed image distortion metrics, both validated against human perceptual data of image quality and with reference to the uncompressed HDR image. Through end-to-end optimization for rate-distortion performance, our method dramatically improves HDR and LDR image quality at all bit rates.