UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data
This work addresses the problem of generating high-quality HDR images for computer vision and photography applications, specifically tackling the limitation of requiring paired datasets for deep learning methods.
This paper introduces UPHDR-GAN, a Generative Adversarial Network that generates high dynamic range (HDR) images from multi-exposure inputs without requiring paired datasets. The method effectively handles ghosting artifacts and improves image perceptual quality, outperforming representative methods in qualitative and quantitative comparisons.
The paper proposes a method to effectively fuse multi-exposure inputs and generate high-quality high dynamic range (HDR) images with unpaired datasets. Deep learning-based HDR image generation methods rely heavily on paired datasets. The ground truth images play a leading role in generating reasonable HDR images. Datasets without ground truth are hard to be applied to train deep neural networks. Recently, Generative Adversarial Networks (GAN) have demonstrated their potentials of translating images from source domain X to target domain Y in the absence of paired examples. In this paper, we propose a GAN-based network for solving such problems while generating enjoyable HDR results, named UPHDR-GAN. The proposed method relaxes the constraint of the paired dataset and learns the mapping from the LDR domain to the HDR domain. Although the pair data are missing, UPHDR-GAN can properly handle the ghosting artifacts caused by moving objects or misalignments with the help of the modified GAN loss, the improved discriminator network and the useful initialization phase. The proposed method preserves the details of important regions and improves the total image perceptual quality. Qualitative and quantitative comparisons against the representative methods demonstrate the superiority of the proposed UPHDR-GAN.