Abstract

We propose an exemplar-based video completion algorithm together with a geometry-guided space-time artifact reduction technique. The proposed completion algorithm is the video extension of an inpainting algorithm proven to be effective on still images. Then, the proposed space-time artifact reduction technique blends multiple patches, guided by a tensor model in order to preserve local structures and textures as much as possible. The two contributions we propose are complementary, and provide video completion results of good quality without block-effect artifacts.

Results

with vs without
space-time patch blending

"Beach Umbrella"

"Fontaine Chatelet"

BibTeX

@inproceedings{DBTL-SA15-inpainting,
	title={Exemplar-based Video Completion with Geometry-guided Space-time Patch Blending},
	authors={Daisy, Maxime and Buyssens, Pierre and Tschumperl{\'e}, David and L{\'e}zoray, Olivier},
	booktitle={SIGGRAPH Asia 2015 Technical Briefs},
	year={2015},
	organization={ACM}
}

Material / Downloads

  • Paper (available soon)