SR-ITM-GAN: Learning 4K UHD HDR With a Generative Adversarial Network
Currently, high dynamic range (HDR) videos with high resolution (HR) have become popular due to the display and the rendered technological advancements. However, making ultra-high definition (UHD) with HDR videos is expensive. The legacy low-resolution (LR) standard dynamic range (SDR) format is sti...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9212411/ |
id |
doaj-99de1a3587ec410cae75438d04d2a6d7 |
---|---|
record_format |
Article |
spelling |
doaj-99de1a3587ec410cae75438d04d2a6d72021-03-30T04:23:21ZengIEEEIEEE Access2169-35362020-01-01818281518282710.1109/ACCESS.2020.30285849212411SR-ITM-GAN: Learning 4K UHD HDR With a Generative Adversarial NetworkHuimin Zeng0Xinliang Zhang1Zhibin Yu2https://orcid.org/0000-0003-4372-1767Yubo Wang3https://orcid.org/0000-0002-2708-3526Department of Electronic Engineering, College of Information Science and Engineering, Ocean University of China, Qingdao, ChinaDepartment of Electronic Engineering, College of Information Science and Engineering, Ocean University of China, Qingdao, ChinaDepartment of Electronic Engineering, College of Information Science and Engineering, Ocean University of China, Qingdao, ChinaSchool of Life Science and Technology, Xidian University, Xi’an, ChinaCurrently, high dynamic range (HDR) videos with high resolution (HR) have become popular due to the display and the rendered technological advancements. However, making ultra-high definition (UHD) with HDR videos is expensive. The legacy low-resolution (LR) standard dynamic range (SDR) format is still largely used in practice. It is necessary to search for a solution to transform LR SDR videos into UHD HDR format. In this paper, we consider joint super resolution and learning inverse tone mapping an issue of high-frequency reconstruction and local contrast enhancement, and we propose an architecture based on a generative adversarial network to apply joint SR-ITM learning. Specifically, we include the residual ResNeXt block (RRXB) as a basic module to better capture high-frequency textures and adopt YUV interpolation to achieve local contrast enhancement. By adopting a generative adversarial network as a pivotal training mechanism, our designs show advantages in both integration and performance. Our code is now available on GitHub: SR-ITM-GAN.https://ieeexplore.ieee.org/document/9212411/Super resolutioninverse tone mappinggenerative adversarial networkhigh dynamic range |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Huimin Zeng Xinliang Zhang Zhibin Yu Yubo Wang |
spellingShingle |
Huimin Zeng Xinliang Zhang Zhibin Yu Yubo Wang SR-ITM-GAN: Learning 4K UHD HDR With a Generative Adversarial Network IEEE Access Super resolution inverse tone mapping generative adversarial network high dynamic range |
author_facet |
Huimin Zeng Xinliang Zhang Zhibin Yu Yubo Wang |
author_sort |
Huimin Zeng |
title |
SR-ITM-GAN: Learning 4K UHD HDR With a Generative Adversarial Network |
title_short |
SR-ITM-GAN: Learning 4K UHD HDR With a Generative Adversarial Network |
title_full |
SR-ITM-GAN: Learning 4K UHD HDR With a Generative Adversarial Network |
title_fullStr |
SR-ITM-GAN: Learning 4K UHD HDR With a Generative Adversarial Network |
title_full_unstemmed |
SR-ITM-GAN: Learning 4K UHD HDR With a Generative Adversarial Network |
title_sort |
sr-itm-gan: learning 4k uhd hdr with a generative adversarial network |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Currently, high dynamic range (HDR) videos with high resolution (HR) have become popular due to the display and the rendered technological advancements. However, making ultra-high definition (UHD) with HDR videos is expensive. The legacy low-resolution (LR) standard dynamic range (SDR) format is still largely used in practice. It is necessary to search for a solution to transform LR SDR videos into UHD HDR format. In this paper, we consider joint super resolution and learning inverse tone mapping an issue of high-frequency reconstruction and local contrast enhancement, and we propose an architecture based on a generative adversarial network to apply joint SR-ITM learning. Specifically, we include the residual ResNeXt block (RRXB) as a basic module to better capture high-frequency textures and adopt YUV interpolation to achieve local contrast enhancement. By adopting a generative adversarial network as a pivotal training mechanism, our designs show advantages in both integration and performance. Our code is now available on GitHub: SR-ITM-GAN. |
topic |
Super resolution inverse tone mapping generative adversarial network high dynamic range |
url |
https://ieeexplore.ieee.org/document/9212411/ |
work_keys_str_mv |
AT huiminzeng sritmganlearning4kuhdhdrwithagenerativeadversarialnetwork AT xinliangzhang sritmganlearning4kuhdhdrwithagenerativeadversarialnetwork AT zhibinyu sritmganlearning4kuhdhdrwithagenerativeadversarialnetwork AT yubowang sritmganlearning4kuhdhdrwithagenerativeadversarialnetwork |
_version_ |
1724181900628590592 |