Deep video inpainting

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 7
  • Download : 0
Video inpainting aims to fill spatio-temporal holes with plausible content in a video. Despite tremendous progress of deep neural networks for image inpainting, it is challenging to extend these methods to the video domain due to the additional time dimension. In this work, we propose a novel deep network architecture for fast video inpainting. Built upon an image-based encoder-decoder model, our framework is designed to collect and refine information from neighbor frames and synthesize still-unknown regions. At the same time, the output is enforced to be temporally consistent by a recurrent feedback and a temporal memory module. Compared with the state-of-the-art image inpainting algorithm, our method produces videos that are much more semantically correct and temporally smooth. In contrast to the prior video completion method which relies on time-consuming optimization, our method runs in near real-time while generating competitive video results. Finally, we applied our framework to video retargeting task, and obtain visually pleasing results.
Publisher
IEEE Computer Society
Issue Date
2019-07
Language
English
Citation

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, pp.5785 - 5794

DOI
10.1109/CVPR.2019.00594
URI
http://hdl.handle.net/10203/274427
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0