Reconstructing HDR image of high color fidelity using Generative Adversarial Networks

Guangkun Zhen; Long Chen; Shuchang Xu; Dandan Ding

doi:10.1117/12.2589386

27 January 2021 Reconstructing HDR image of high color fidelity using Generative Adversarial Networks

Guangkun Zhen, Long Chen, Shuchang Xu, Dandan Ding

Proceedings Volume 11720, Twelfth International Conference on Graphics and Image Processing (ICGIP 2020); 117200T (2021) https://doi.org/10.1117/12.2589386
Event: Twelfth International Conference on Graphics and Image Processing, 2020, Xi'an, China

Abstract

The conversion from SDR contents to HDR version, termed inverse Tone Mapping (iTM), is substantially a non- linear mapping problem. The neural network provides the potential of learning this kind of non-linear mapping in an end-to-end way. This paper proposes a Generative Adversarial Network (GAN) with an aim to reconstruct an HDR image from a single-exposure. Unlike previous work that adopts a U-net as generator, the proposed GAN structures the generator using three branches to extract the global level, regional level, and local level details of an image for further fusion. Our discriminator adopts a slim architecture, which successfully solves the conventional color excursion problem at a low cost. Moreover, to train the proposed GAN effectively, we design a mixed loss function where the pixel-wise color is incorporated. Experimental results demonstrate that the proposed GAN scheme achieves state-of-the-art performance.

Citation Download Citation

Guangkun Zhen, Long Chen, Shuchang Xu, and Dandan Ding "Reconstructing HDR image of high color fidelity using Generative Adversarial Networks", Proc. SPIE 11720, Twelfth International Conference on Graphics and Image Processing (ICGIP 2020), 117200T (27 January 2021); https://doi.org/10.1117/12.2589386

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available