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. Using the Subjectify.us web service we collected 945 pairwise comparison results from 63 participants and computed the overall subjective quality scores of 3 different methods according to the Crowd Bradley-Terry model.
"100+ Times Faster Video Completion by Optical-Flow-Guided Variational Refinement"|
Alexander Bokov, Dmitriy Vatolin
IEEE International Conference on Image Processing (ICIP) 2018
VideoCompletion.org dataset (zip)
|||A. Newson, A. Almansa, M. Fradet, Y. Gousseau, and P. Perez. Video Inpainting of Complex Scenes. SIAM Journal on Imaging Sciences, pages 1993–2019, 2014. [ project page ]|
|||J.-B Huang, S. B. Kang, N. Ahuja, and J. Kopf. Temporally Coherent Completion of Dynamic Video. ACM Transactions on Graphics, vol. 35, no. 6, 2016. [ project page ]|