EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention Mechanism
Author:
Gao Ming,Deng Huiping,Xiang Sen,Wu Jin,He Zeyang
Abstract
Light field (LF) image depth estimation is a critical technique for LF-related applications such as 3D reconstruction, target detection, and tracking. The refocusing property of LF images provide rich information for depth estimations; however, it is still challenging in cases of occlusion regions, edge regions, noise interference, etc. The epipolar plane image (EPI) of LF can effectively deal with the depth estimation because of its characteristics of multidirectionality and pixel consistency—in which the LF depth estimations are converted to calculate the EPI slope. This paper proposed an EPI LF depth estimation algorithm based on a directional relationship model and attention mechanism. Unlike the subaperture LF depth estimation method, the proposed method takes EPIs as input images. Specifically, a directional relationship model was used to extract direction features of the horizontal and vertical EPIs, respectively. Then, a multiviewpoint attention mechanism combining channel attention and spatial attention is used to give more weight to the EPI slope information. Subsequently, multiple residual modules are used to eliminate the redundant features that interfere with the EPI slope information—in which a small stride convolution operation is used to avoid losing key EPI slope information. The experimental results revealed that the proposed algorithm outperformed the compared algorithms in terms of accuracy.
Funder
National Natural Science Foundation of China
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference37 articles.
1. Single lens stereo with a plenoptic camera
2. Digital Light Field Photography;Ren;Ph.D. Thesis,2006
3. Light field rendering;Levoy;Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques,1996
4. Monocular 3d object detection for autonomous driving;Chen;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016
5. Deep Learning Based 3D Perception and Recognition for Robot Vision;Feng;Ph.D. Thesis,2019
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献