1. SR-ITM-GAN: Learning 4K UHD HDR With a Generative Adversarial Network
- Author
-
Xinliang Zhang, Yubo Wang, Huimin Zeng, and Zhibin Yu
- Subjects
General Computer Science ,Computer science ,generative adversarial network ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,General Engineering ,020206 networking & telecommunications ,020207 software engineering ,02 engineering and technology ,high dynamic range ,Superresolution ,Super resolution ,Computer engineering ,0202 electrical engineering, electronic engineering, information engineering ,Code (cryptography) ,General Materials Science ,lcsh:Electrical engineering. Electronics. Nuclear engineering ,inverse tone mapping ,Joint (audio engineering) ,lcsh:TK1-9971 ,Generative adversarial network ,High dynamic range ,Interpolation ,Standard dynamic range ,Block (data storage) - Abstract
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.
- Published
- 2020