Paper Info
Title
PlenoPatch: Patch-Based Plenoptic Image Manipulation.
Abstract
Patch-based image synthesis methods have been successfully applied for various editing tasks on still images, videos and stereo pairs. In this work we extend patch-based synthesis to plenoptic images captured by consumer-level lenselet-based devices for interactive, efficient light field editing. In our method the light field is represented as a set of images captured from different viewpoints. We decompose the central view into different depth layers, and present it to the user for specifying the editing goals. Given an editing task, our method performs patch-based image synthesis on all affected layers of the central view, and then propagates the edits to all other views. Interaction is done through a conventional 2D image editing user interface that is familiar to novice users. Our method correctly handles object boundary occlusion with semi-transparency, thus can generate more realistic results than previous methods. We demonstrate compelling results on a wide range of applications such as hole-filling, object reshuffling and resizing, changing object depth, light field upscaling and parallax magnification.
Year
DOI
Venue
2017
10.1109/TVCG.2016.2532329
IEEE Trans. Vis. Comput. Graph.
Keywords
Field
DocType
Cameras,Image generation,Image reconstruction,Visualization,Image color analysis,Coherence,Videos
Iterative reconstruction,Computer vision,Computer graphics (images),Parallax,Visualization,Computer science,Image editing,Layers,Light field,Coherence (physics),Artificial intelligence,User interface
Journal
Volume
Issue
ISSN
23
5
1077-2626
Citations 
PageRank 
References 
16
0.61
42
Authors
6
Name
Order
Citations
PageRank
Fang-Lue Zhang126915.60
Jue Wang22871155.89
Eli Shechtman34340177.94
Zi-Ye Zhou4160.61
Jiaxin Shi534918.02
Shi-Min Hu63466188.22