Explorable Tone Mapping Operators

TL;DR

This paper introduces a learning-based multimodal tone-mapping method for HDR images that offers diverse style options and outperforms existing algorithms in quality, addressing the subjective nature of tone-mapping preferences.

Contribution

It proposes a BicycleGAN-based framework enabling multiple tone-mapped outputs from a single HDR image, capturing style diversity and improving visual quality.

Findings

Provides diverse tone-mapped results by manipulating latent codes.

Achieves superior visual quality compared to state-of-the-art methods.

Performs well both quantitatively and qualitatively.

Abstract

Tone-mapping plays an essential role in high dynamic range (HDR) imaging. It aims to preserve visual information of HDR images in a medium with a limited dynamic range. Although many works have been proposed to provide tone-mapped results from HDR images, most of them can only perform tone-mapping in a single pre-designed way. However, the subjectivity of tone-mapping quality varies from person to person, and the preference of tone-mapping style also differs from application to application. In this paper, a learning-based multimodal tone-mapping method is proposed, which not only achieves excellent visual quality but also explores the style diversity. Based on the framework of BicycleGAN, the proposed method can provide a variety of expert-level tone-mapped results by manipulating different latent codes. Finally, we show that the proposed method performs favorably against state-of-the-art tone-mapping algorithms both quantitatively and qualitatively.