English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Light field cameras record not only the spatial information of observedscenes but also the directions of all incoming light rays. The spatial andangular information implicitly contain geometrical characteristics such asmulti-view or epipolar geometry, which can be exploited to improve theperformance of depth estimation. An Epipolar Plane Image (EPI), the unique 2Dspatial-angular slice of the light field, contains patterns of oriented lines.The slope of these lines is associated with the disparity. Benefiting from thisproperty of EPIs, some representative methods estimate depth maps by analyzingthe disparity of each line in EPIs. However, these methods often extract theoptimal slope of the lines from EPIs while ignoring the relationship betweenneighboring pixels, which leads to inaccurate depth map predictions. Based onthe observation that an oriented line and its neighboring pixels in an EPIshare a similar linear structure, we propose an end-to-end fully convolutionalnetwork (FCN) to estimate the depth value of the intersection point on thehorizontal and vertical EPIs. Specifically, we present a new feature-extractionmodule, called Oriented Relation Module (ORM), that constructs the relationshipbetween the line orientations. To facilitate training, we also propose arefocusing-based data augmentation method to obtain different slopes from EPIsof the same scene point. Extensive experiments verify the efficacy of learningrelations and show that our approach is competitive to other state-of-the-artmethods. The code and the trained models are available athttps://github.com/lkyahpu/EPI_ORM.git.

EPI-based Oriented Relation Networks for Light Field Depth Estimation