Variational Separation of Light Field Layers

dc.contributor.authorJohannsen, Oleen_US
dc.contributor.authorSulc, Antoninen_US
dc.contributor.authorGoldluecke, Bastianen_US
dc.contributor.editorDavid Bommes and Tobias Ritschel and Thomas Schultzen_US
dc.date.accessioned2015-10-07T05:13:40Z
dc.date.available2015-10-07T05:13:40Z
dc.date.issued2015en_US
dc.description.abstractImages of scenes which contain reflective or transparent surfaces are composed of different layers which are observed at different depths. Analyzing such a scene requires separating the image into its individual layers, which remains a challenging and important problem. While the problem is very much ill-posed when only a single image is considered, recent work has shown that depth estimation for two layers becomes quite tractable when one instead captures a 4D light field of the scene. In this paper, we propose a novel variational approach to layer separation which is based on these ideas. We formulate a linear generative model to reconstruct the light field from disparity and luminance information for the individual layers on the center view. Comparing the model with the observerd data yields a convex variational problem for layer reconstruction, which can be solved to global optimality with a primal-dual scheme. Layer disparity is estimated in a first step, for which we improve upon a model based on second order structure tensors on the epipolar plane images. In contrast to previous work, the resulting approach is robust enough to be able to deal with light fields from the Lytro Illum camera, for which we obtain a compelling separation of the reflectance layer in real-world scenes.en_US
dc.description.sectionheadersAcquisitionen_US
dc.description.seriesinformationVision, Modeling & Visualizationen_US
dc.identifier.doi10.2312/vmv.20151268en_US
dc.identifier.isbn978-3-905674-95-8en_US
dc.identifier.pages135-142en_US
dc.identifier.urihttps://doi.org/10.2312/vmv.20151268en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectI.4.4 [Image Processing and Computer Vision]en_US
dc.subjectRestorationen_US
dc.subjectI.4.8 [Image Processing and Computer Vision]en_US
dc.subjectScene Analysisen_US
dc.subjectShapeen_US
dc.titleVariational Separation of Light Field Layersen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
135-142.pdf
Size:
8.92 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
paper1013_MM_CRC.pdf
Size:
3.59 MB
Format:
Adobe Portable Document Format
Collections