articleIEEE Transactions on Pattern Analysis and Machine IntelligenceFeb 18, 2022GREEN OA

Disentangling Light Fields for Super-Resolution and Disparity Estimation

YWYingqian WangLWLongguang WangGWGaochang WuJYJungang YangWAWei An

National University of Defense Technology · Northeastern University · +1 more institution

PubMed
Indexed inarxivcrossrefpubmed

Abstract

Light field (LF) cameras record both intensity and directions of light rays, and encode 3D scenes into 4D LF images. Recently, many convolutional neural networks (CNNs) have been proposed for various LF image processing tasks. However, it is challenging for CNNs to effectively process LF images since the spatial and angular information are highly inter-twined with varying disparities. In this paper, we propose a generic mechanism to disentangle these coupled information for LF image processing. Specifically, we first design a class of domain-specific convolutions to disentangle LFs from different dimensions, and then leverage these disentangled features by designing task-specific modules. Our disentangling…

Citation impact

277
total citations
FWCI
26.08
Percentile
100%
References
80
Citations per year

Authors

7
  • YW
    Yingqian WangCorresponding

    National University of Defense Technology

  • LW
    Longguang Wang

    National University of Defense Technology

  • GW
    Gaochang Wu

    Northeastern University

  • JY
    Jungang Yang

    National University of Defense Technology

  • WA
    Wei An

    National University of Defense Technology

Topics & keywords

Topics
Keywords
  • Leverage (statistics)
  • ENCODE
  • Convolutional neural network
  • Light field
  • Pattern recognition (psychology)
  • Generality
  • Feature extraction
  • Histogram
No related works found for this paper.

Funding