Abstract

Potent usage of the multi-scale light field information for salient object detection (SOD) is the essential requirement of three-dimensional (3D) SOD. On this basis, a light field 3D-SOD scheme is proposed that employs the pixel mapping algorithm to achieve a more distinct representation of spatial and angular information in the four-dimensional (4D) light field, collaboratively mining the global saliency cues via the co-salient object detection (CoSOD) network. Compared with the previous method, our scheme filters out most of the noise by thoroughly leveraging the global dependence of the 4D light field, offering significant enhancements in saliency extraction performance and efficiency. Additionally, the 3D reconstruction results demonstrate the integral retention of the spatial and angular information of the original light field.

© 2023 Optica Publishing Group

Deep-learning-based 3D object salient detection via light-field integral imaging

Ying Li, Tianhao Wang, Yanheng Liao, Da-Hai Li, and Xiaowei Li
Opt. Lett. 47(7) 1758-1761 (2022)

3D medical images security via light-field imaging

Ying Li, Tianhao Wang, Yanheng Liao, Da-Hai Li, and Xiaowei Li
Opt. Lett. 47(14) 3535-3538 (2022)

Full-color holographic system featuring three-dimensional salient object detection based on a U²-RAS network

Jing-Wen Bu, Yu Zhao, and Jia-Hui Ji
J. Opt. Soc. Am. A 40(4) B1-B7 (2023)

Implementation of a full-color holographic system using RGB-D salient object detection and divided point cloud gridding

Yu Zhao, Jing-Wen Bu, Wei Liu, Jia-Hui Ji, Qin-Hui Yang, and Shu-Feng Lin
Opt. Express 31(2) 1641-1655 (2023)

Light-field 3D encryption based on the monocular depth rendering

Zhiqing Ren, Junfeng Guo, Hang Liu, and Xiaowei Li
Opt. Lett. 47(18) 4762-4765 (2022)