PlenoPatch : Patch-Based Plenoptic Image Manipulation

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...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics. - 1998. - 23(2017), 5 vom: 25. Mai, Seite 1561-1573
1. Verfasser: Zhang, Fang-Lue (VerfasserIn)
Weitere Verfasser: Wang, Jue, Shechtman, Eli, Zhou, Zi-Ye, Shi, Jia-Xin, Hu, Shi-Min
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2017
Zugriff auf das übergeordnete Werk:IEEE transactions on visualization and computer graphics
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000caa a22002652 4500
001 NLM257843914
003 DE-627
005 20250219184438.0
007 cr uuu---uuuuu
008 231224s2017 xx |||||o 00| ||eng c
024 7 |a 10.1109/TVCG.2016.2532329  |2 doi 
028 5 2 |a pubmed25n0859.xml 
035 |a (DE-627)NLM257843914 
035 |a (NLM)26915124 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Zhang, Fang-Lue  |e verfasserin  |4 aut 
245 1 0 |a PlenoPatch  |b Patch-Based Plenoptic Image Manipulation 
264 1 |c 2017 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 18.10.2018 
500 |a Date Revised 18.10.2018 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a 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 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Wang, Jue  |e verfasserin  |4 aut 
700 1 |a Shechtman, Eli  |e verfasserin  |4 aut 
700 1 |a Zhou, Zi-Ye  |e verfasserin  |4 aut 
700 1 |a Shi, Jia-Xin  |e verfasserin  |4 aut 
700 1 |a Hu, Shi-Min  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1998  |g 23(2017), 5 vom: 25. Mai, Seite 1561-1573  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnns 
773 1 8 |g volume:23  |g year:2017  |g number:5  |g day:25  |g month:05  |g pages:1561-1573 
856 4 0 |u http://dx.doi.org/10.1109/TVCG.2016.2532329  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 23  |j 2017  |e 5  |b 25  |c 05  |h 1561-1573