Paper Info
Title
Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image.
Abstract
Recently, high dynamic range (HDR) imaging has attracted much attention as a technology to reflect human visual characteristics owing to the development of the display and camera technology. This paper proposes a novel deep neural network model that reconstructs an HDR image from a single low dynamic range (LDR) image. The proposed model is based on a convolutional neural network composed of dilated convolutional layers and infers LDR images with various exposures and illumination from a single LDR image of the same scene. Then, the final HDR image can be formed by merging these inference results. It is relatively simple for the proposed method to find the mapping between the LDR and an HDR with a different bit depth because of the chaining structure inferring the relationship between the LDR images with brighter (or darker) exposures from a given LDR image. The method not only extends the range but also has the advantage of restoring the light information of the actual physical world. The proposed method is an end-to-end reconstruction process, and it has the advantage of being able to easily combine a network to extend an additional range. In the experimental results, the proposed method shows quantitative and qualitative improvement in performance, compared with the conventional algorithms.
Year
DOI
Venue
2018
10.1109/ACCESS.2018.2868246
IEEE ACCESS
Keywords
DocType
Volume
High dynamic range imaging,image restoration,computational photography,convolutional neural network
Journal
6
ISSN
Citations 
PageRank 
2169-3536
2
0.36
References 
Authors
19
3
Name
Order
Citations
PageRank
Siyeong Lee173.16
Gwon Hwan An221.71
Suk-Ju Kang312727.68