Motion-aware gradient domain video composition

For images, gradient domain composition methods like Poisson blending offer practical solutions for uncertain object boundaries and differences in illumination conditions. However, adapting Poisson image blending to video presents new challenges due to the added temporal dimension. In video, the hum...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 22(2013), 7 vom: 11. Juli, Seite 2532-44
1. Verfasser: Chen, Tao (VerfasserIn)
Weitere Verfasser: Zhu, Jun-Yan, Shamir, Ariel, Hu, Shi-Min
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2013
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM225718065
003 DE-627
005 20231224065807.0
007 cr uuu---uuuuu
008 231224s2013 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2013.2251642  |2 doi 
028 5 2 |a pubmed24n0752.xml 
035 |a (DE-627)NLM225718065 
035 |a (NLM)23481851 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Chen, Tao  |e verfasserin  |4 aut 
245 1 0 |a Motion-aware gradient domain video composition 
264 1 |c 2013 
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 30.12.2013 
500 |a Date Revised 20.05.2013 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a For images, gradient domain composition methods like Poisson blending offer practical solutions for uncertain object boundaries and differences in illumination conditions. However, adapting Poisson image blending to video presents new challenges due to the added temporal dimension. In video, the human eye is sensitive to small changes in blending boundaries across frames and slight differences in motions of the source patch and target video. We present a novel video blending approach that tackles these problems by merging the gradient of source and target videos and optimizing a consistent blending boundary based on a user-provided blending trimap for the source video. Our approach extends mean-value coordinates interpolation to support hybrid blending with a dynamic boundary while maintaining interactive performance. We also provide a user interface and source object positioning method that can efficiently deal with complex video sequences beyond the capabilities of alpha blending 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Zhu, Jun-Yan  |e verfasserin  |4 aut 
700 1 |a Shamir, Ariel  |e verfasserin  |4 aut 
700 1 |a Hu, Shi-Min  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 22(2013), 7 vom: 11. Juli, Seite 2532-44  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:22  |g year:2013  |g number:7  |g day:11  |g month:07  |g pages:2532-44 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2013.2251642  |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 22  |j 2013  |e 7  |b 11  |c 07  |h 2532-44