Smooth Loops from Unconstrained Video

Converting unconstrained video sequences into videos that loop seamlessly is an extremely challenging problem. In this work, we take the first steps towards automating this process by focusing on an important subclass of videos containing a single dominant foreground object. Our technique makes two...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum 2015-07, Vol.34 (4), p.99-107
Main Authors: Sevilla-Lara, L., Wulff, J., Sunkavalli, K., Shechtman, E.
Format: Article
Language:English
Subjects:
Cameras
Computer graphics
Converting
Customization
Dynamics
Image processing systems
Internet
Morphing
Path planning
Similarity
Studies
Transition points
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Converting unconstrained video sequences into videos that loop seamlessly is an extremely challenging problem. In this work, we take the first steps towards automating this process by focusing on an important subclass of videos containing a single dominant foreground object. Our technique makes two novel contributions over previous work: first, we propose a correspondence‐based similarity metric to automatically identify a good transition point in the video where the appearance and dynamics of the foreground are most consistent. Second, we develop a technique that aligns both the foreground and background about this transition point using a combination of global camera path planning and patch‐based video morphing. We demonstrate that this allows us to create natural, compelling, loopy videos from a wide range of videos collected from the internet.
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.12682