Lighting Transfer via Non-negative Matrix Factorization forime-varying Video
Date Issued
2009
Date
2009
Author(s)
Chen, Hsin-Yi
Abstract
Lighting makes a significant perceptual impact on visual perception,ut our photo are sometimes captured during rather bother lighting condition.e propose a method to transfer lights from one outdoor scene tonother by using sequences of time-varying videos taken from both scenes.ur algorithm first detect shadow area for each image. We consider pixels inhadow as unreliable data, then using an iterative photometric stereo frameworkith non-negative matrix factorization method to compute geometryerm and lighting term of the scene. The factorization result allows users toasily relight the scene by transfer lighting from user specified lighting modelo the target image. We demonstrate via several examples that our methodenerates good results and keep color consistency
Subjects
image-based rendering,inverse problem
computational photography
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-98-R96922129-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):a5a19c0b37a80216ec19fc85780590e9