U<sup>2</sup>-Net Architecture Contingent Intelligent Depth Map Extraction Method Using Light Field Images
This paper presents a novel method of employing a two-level layered U-Structure called U<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>(U-Square)-Net deep learning architecture to yield depth map data from light field images of target objects captured by light field camera. The advantage of using U<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2_</sup>Net lies in its outstanding capability to detect salient objects.
Authors
- Ki‐Chul Kwon (ORCID: https://orcid.org/0000-0003-0334-504X)
- Kwon-Yeon Lee
- Ferdous Hossain (ORCID: https://orcid.org/0000-0003-0444-7320)
- Nam Kim (ORCID: https://orcid.org/0000-0001-8109-2055)
- Shariar Md Imtiaz
- Hui‐Ying Wu (ORCID: https://orcid.org/0009-0006-2612-5620)
Institutions
- Chungbuk National University (KR)
- Sunchon National University (KR)
Publication Details
- Published
- 2024-08-04
- DOI
- https://doi.org/10.1109/cleo-pr60912.2024.10676633
- Primary Topic
- Advanced Vision and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00