Perception-based contrast enhancement model for complex images in high dynamic range

2008 ◽  
Author(s):  
Akiko Yoshida ◽  
Grzegorz Krawczyk ◽  
Karol Myszkowski ◽  
Hans-Peter Seidel
Keyword(s):  
Contrast Enhancement ◽  
Dynamic Range ◽  
High Dynamic Range ◽  
High Dynamic ◽  
Complex Images

P-108: Contrast Enhancement based on Advanced Local Dimming System for High Dynamic Range LCDs

2017 ◽  
Vol 48 (1) ◽  
pp. 1667-1669 ◽  
Author(s):  
Ooksang Yoo ◽  
Sangjin Nam ◽  
JoungMi Choi ◽  
Seungjin Yoo ◽  
Kyu-Jin Kim ◽  
...  
Keyword(s):  
Contrast Enhancement ◽  
Dynamic Range ◽  
High Dynamic Range ◽  
High Dynamic ◽  
Local Dimming

High dynamic range for contrast enhancement

2006 ◽  
Vol 52 (4) ◽  
pp. 1454-1462 ◽  
Author(s):  
Bo Lim ◽  
Rae-hong Park ◽  
Sunghee Kim
Keyword(s):  
Contrast Enhancement ◽  
Dynamic Range ◽  
High Dynamic Range ◽  
High Dynamic

scholarly journals JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video

2020 ◽  
Vol 34 (07) ◽  
pp. 11287-11295
Author(s):  
Soo Ye Kim ◽  
Jihyong Oh ◽  
Munchurl Kim
Keyword(s):  
Contrast Enhancement ◽  
Dynamic Range ◽  
Super Resolution ◽  
High Dynamic Range ◽  
Divide And Conquer ◽  
Tone Mapping ◽  
Local Contrast ◽  
Joint Learning ◽  
High Dynamic ◽  
Inverse Tone Mapping

Joint learning of super-resolution (SR) and inverse tone-mapping (ITM) has been explored recently, to convert legacy low resolution (LR) standard dynamic range (SDR) videos to high resolution (HR) high dynamic range (HDR) videos for the growing need of UHD HDR TV/broadcasting applications. However, previous CNN-based methods directly reconstruct the HR HDR frames from LR SDR frames, and are only trained with a simple L2 loss. In this paper, we take a divide-and-conquer approach in designing a novel GAN-based joint SR-ITM network, called JSI-GAN, which is composed of three task-specific subnets: an image reconstruction subnet, a detail restoration (DR) subnet and a local contrast enhancement (LCE) subnet. We delicately design these subnets so that they are appropriately trained for the intended purpose, learning a pair of pixel-wise 1D separable filters via the DR subnet for detail restoration and a pixel-wise 2D local filter by the LCE subnet for contrast enhancement. Moreover, to train the JSI-GAN effectively, we propose a novel detail GAN loss alongside the conventional GAN loss, which helps enhancing both local details and contrasts to reconstruct high quality HR HDR results. When all subnets are jointly trained well, the predicted HR HDR results of higher quality are obtained with at least 0.41 dB gain in PSNR over those generated by the previous methods. The official Tensorflow code is available at https://github.com/JihyongOh/JSI-GAN.

Sign in / Sign up

Export Citation Format

Share Document