Sorry, you need to enable JavaScript to visit this website.

100+ Times Faster Video Completion by Optical-Flow-Guided Variational Refinement

Citation Author(s):
Alexander Bokov, Dmitriy Vatolin
Submitted by:
Alexander Bokov
Last updated:
4 October 2018 - 2:42pm
Document Type:
Poster
Document Year:
2018
Event:
Presenters:
Alexander Bokov
Paper Code:
1119
 

Despite the higher video-completion quality that recently proposed methods have enabled for a wide variety of cases, their computational complexity remains a major concern. These methods typically frame video completion as an optimization problem over the whole spatiotemporal domain—a problem that is expensive to solve both in time and space. In this paper we propose a lighter-weight multipass video-completion pipeline that replaces global spatiotemporal optimization with simpler frame-by-frame motion reconstruction and refinement. We achieve a processing speed of 2.6 seconds per frame on Full HD content while delivering nearly state-of-the-art completion quality for a wide range of dynamic scenes captured using a free-moving camera. To validate the performance of our proposed method, we conducted a subjective comparison of different video-completion results for 26 test sequences from the DAVIS data set.

up
0 users have voted: