期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 23, 期 -, 页码 2561-2574出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2020.3013378
关键词
Dynamic range; Neural networks; Image restoration; Distortion; Training; Light sources; Brightness; High dynamic range imaging; inverse-tone mapping; image restoration; deep learning
资金
- MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program [IITP-2020-2018-0-01421]
- Ministry of the Interior and Safety of Korean government [19PQWO-B153369-01]
- National Research Foundation of Korea (NRF) - Korea government (MSIT) [2020M3H4A1A02084899]
The study introduces an inverse tone mapping method that uses a pair of neural networks to construct a multiple exposure image synthesis approach for recovering lost scene radiances and flexibly expanding the dynamic range of images. The method demonstrates significant advantages in HDR imaging compared to traditional methods.
Inverse tone mapping aims at recovering the lost scene radiances from a single exposure image. With the successful use of deep learning in numerous applications, many inverse tone mapping methods use convolution neural networks in a supervised manner. As these approaches are trained with many pre-fixed high dynamic range (HDR) images, they fail to flexibly expand the dynamic ranges of images. To overcome this limitation, we consider a multiple exposure image synthesis approach for HDR imaging. In particular, we propose a pair of neural networks that represent mappings between images that have exposure levels one unit apart (stop-up/down network). Therefore, it is possible to construct two positive-feedback systems to generate images with greater or lesser exposure. Compared to previous works using the conditional generative adversarial learning framework, the stop-up/down network employs HDR friendly network structures and several techniques to stabilize the training processes. Experiments on HDR datasets demonstrate the advantages of the proposed method compared to conventional methods. Consequently, we apply our approach to restore the full dynamic range of scenes agilely with only two networks and generate photorealistic images in complex lighting situations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据