Unpaired Learning for High Dynamic Range Image Tone Mapping

TL;DR

This paper introduces an unpaired adversarial learning method for HDR image tone mapping that does not require ground-truth data, enabling effective training with unrelated HDR and LDR image sets.

Contribution

It proposes a novel unpaired training approach with specific preprocessing, loss functions, and discriminator design for HDR tone mapping without ground-truth images.

Findings

Produces photo-realistic, artifact-free tone-mapped images

Achieves state-of-the-art performance on image fidelity metrics

Effective training with unpaired HDR and LDR datasets

Abstract

High dynamic range (HDR) photography is becoming increasingly popular and available by DSLR and mobile-phone cameras. While deep neural networks (DNN) have greatly impacted other domains of image manipulation, their use for HDR tone-mapping is limited due to the lack of a definite notion of ground-truth solution, which is needed for producing training data. In this paper we describe a new tone-mapping approach guided by the distinct goal of producing low dynamic range (LDR) renditions that best reproduce the visual characteristics of native LDR images. This goal enables the use of an unpaired adversarial training based on unrelated sets of HDR and LDR images, both of which are widely available and easy to acquire. In order to achieve an effective training under this minimal requirements, we introduce the following new steps and components: (i) a range-normalizing pre-process which estimates and applies a different level of curve-based compression, (ii) a loss that preserves the input content while allowing the network to achieve its goal, and (iii) the use of a more concise discriminator network, designed to promote the reproduction of low-level attributes native LDR possess. Evaluation of the resulting network demonstrates its ability to produce photo-realistic artifact-free tone-mapped images, and state-of-the-art performance on different image fidelity indices and visual distances.