Show simple item record

dc.contributor.authorNi, Lixiaen_US
dc.contributor.authorJiang, Haiyongen_US
dc.contributor.authorCai, Jianfeien_US
dc.contributor.authorZheng, Jianminen_US
dc.contributor.authorLi, Haifengen_US
dc.contributor.authorLiu, Xuen_US
dc.contributor.editorLee, Jehee and Theobalt, Christian and Wetzstein, Gordonen_US
dc.description.abstractLight field (LF) reconstruction is a fundamental technique in light field imaging and has applications in both software and hardware aspects. This paper presents an unsupervised learning method for LF-oriented view synthesis, which provides a simple solution for generating quality light fields from a sparse set of views. The method is built on disparity estimation and image warping. Specifically, we first use per-view disparity as a geometry proxy to warp input views to novel views. Then we compensate the occlusion with a network by a forward-backward warping process. Cycle-consistency between different views are explored to enable unsupervised learning and accurate synthesis. The method overcomes the drawbacks of fully supervised learning methods that require large labeled training dataset and epipolar plane image based interpolation methods that do not make full use of geometry consistency in LFs. Experimental results demonstrate that the proposed method can generate high quality views for LF, which outperforms unsupervised approaches and is comparable to fully-supervised approaches.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectImage processing and computer vision
dc.titleUnsupervised Dense Light Field Reconstruction with Occlusion Awarenessen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersRendering and Sampling

Files in this item


This item appears in the following Collection(s)

  • 38-Issue 7
    Pacific Graphics 2019 - Symposium Proceedings

Show simple item record