UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data

02/03/2021
by   Ru Li, et al.
9

The paper proposes a method to effectively fuse multi-exposure inputs and generates 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 provides information for the network getting HDR images without ghosting. Datasets without ground truth are hard to apply 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 paired dataset and learns the mapping from LDR domain to 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 modified GAN loss, improved discriminator network and useful initialization phase. The proposed method preserves the details of important regions and improves the total image perceptual quality. Qualitative and quantitative comparisons against other methods demonstrated the superiority of our method.

READ FULL TEXT

page 2

page 3

page 8

page 11

page 14

page 16

page 18

page 20

research
07/05/2017

AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks

Recently, several methods based on generative adversarial network (GAN) ...
research
09/08/2020

Unsupervised Change Detection in Satellite Images with Generative Adversarial Network

Detecting changed regions in paired satellite images plays a key role in...
research
09/13/2019

Coupling Rendering and Generative Adversarial Networks for Artificial SAS Image Generation

Acquisition of Synthetic Aperture Sonar (SAS) datasets is bottlenecked b...
research
08/05/2020

A feature-supervised generative adversarial network for environmental monitoring during hazy days

The adverse haze weather condition has brought considerable difficulties...
research
05/25/2022

DH-GAN: A Physics-driven Untrained Generative Adversarial Network for 3D Microscopic Imaging using Digital Holography

Digital holography is a 3D imaging technique by emitting a laser beam wi...
research
07/22/2022

Accelerated and Quantitative 3D Semisolid MT/CEST Imaging using a Generative Adversarial Network (GAN-CEST)

Purpose: To substantially shorten the acquisition time required for quan...
research
04/07/2020

Iconify: Converting Photographs into Icons

In this paper, we tackle a challenging domain conversion task between ph...

Please sign up or login with your details

Forgot password? Click here to reset