Abstract
In this paper, we propose a convolutional neural network based on epipolar geometry and image segmentation for light-field depth estimation. Epipolar geometry is utilized to estimate the initial disparity map. Multi-orientation epipolar images are selected as input data, and the convolutional blocks are adopted based on the disparity of different-direction epipolar images. Image segmentation is used to obtain the edge information of the central sub-aperture image. By concatenating the output of the two parts, an accurate depth map could be generated with fast speed. Our method achieves a high rank on most quality assessment metrics in the HCI 4D Light Field Benchmark and also shows effectiveness in estimating accurate depth on real-world light-field images.
© 2020 Optical Society of America
Full Article | PDF ArticleMore Like This
Zhuang Ma, Zhaofeng Cen, and Xiaotong Li
Appl. Opt. 56(23) 6603-6610 (2017)
Bo Liu, Jing Chen, Zhen Leng, Yanfeng Tong, and Yongtian Wang
Opt. Express 30(14) 25130-25146 (2022)
Ligen Shi, Chang Liu, Di He, Xing Zhao, and Jun Qiu
Opt. Express 31(4) 6111-6131 (2023)