Journal of Imaging, Volume 10, Issue 4
2024 April - 23 articles
Cover Story: Digital cameras only capture a limited range of luminance levels because of sensor constraints. Cameras for high-dynamic-range (HDR) imaging are sometimes unaffordable. Most existing image content has a low dynamic range (LDR) comprising 8-bit imaging. Metals are typical object materials that saturate easily, and the luminance of the reflected light covers an extensive dynamic range. In this paper, we consider a method for reconstructing the original HDR image from a single LDR image suffering from saturation. A deep neural network approach is adopted to map the 8-bit LDR image to an HDR image. We first construct an HDR image database of metallic objects and then propose an LDR-to-HDR mapping method to predict the information that has been lost in saturated areas. View this paper
- Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Articles
There are no articles in this issue yet.
J. Imaging - ISSN 2313-433X