Occlusion-aware Bi-directional Guided Network for Light Field Salient Object Detection

Dong JING, Shuo ZHANG*, Runmin CONG, Youfang LIN

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

20 Citations (Scopus)

Abstract

Existing light field based works utilize either views or focal stacks for saliency detection. However, since depth information exists implicitly in adjacent views or different focal slices, it is difficult to exploit scene depth information from both. By comparison, Epipolar Plane Images (EPIs) provide explicit accurate scene depth and occlusion information by projected pixel lines. Due to the fact that the depth of an object is often continuous, the distribution of occlusion edges concentrates more on object boundaries compared with traditional color edges, which is more beneficial for improving accuracy and completeness of saliency detection. In this paper, we propose a learning-based network to exploit occlusion features from EPIs and integrate high-level features from the central view for accurate salient object detection. Specifically, a novel Occlusion Extraction Module is proposed to extract occlusion boundary features from horizontal and vertical EPIs. In order to naturally combine occlusion features in EPIs and high-level features in central view, we design a concise Bi-directional Guiding Flow based on cascaded decoders. The flow leverages generated salient edge predictions and salient object predictions to refine features in mutual encoding processes. Experimental results demonstrate that our approach achieves state-of-the-art performance in both segmentation accuracy and edge clarity.

Original languageEnglish
Title of host publicationMM 2021 : Proceedings of the 29th ACM International Conference on Multimedia
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages1692-1701
Number of pages10
ISBN (Electronic)9781450386517
DOIs
Publication statusPublished - 17 Oct 2021
Externally publishedYes
Event29th ACM International Conference on Multimedia, MM 2021 - Virtual, Online, China
Duration: 20 Oct 202124 Oct 2021

Conference

Conference29th ACM International Conference on Multimedia, MM 2021
Country/TerritoryChina
CityVirtual, Online
Period20/10/2124/10/21

Bibliographical note

Publisher Copyright:
© 2021 ACM.

Keywords

  • light field
  • neural network
  • salient object detection

Fingerprint

Dive into the research topics of 'Occlusion-aware Bi-directional Guided Network for Light Field Salient Object Detection'. Together they form a unique fingerprint.

Cite this