Home Examples Abstract Links BibTex Acknowledgments

Overview Video

Please watch the video here if Youtube doesn't work for you.

Abstract

We present a new flow-based video completion algorithm. Previous flow completion methods are often unable to retain the sharpness of motion boundaries. Our method first extracts and completes motion edges, and then uses them to guide piecewise-smooth flow completion with sharp edges. Existing methods propagate colors among local flow connections between adjacent frames. However, not all missing regions in a video can be reached in this way because the motion boundaries form impenetrable barriers. Our method alleviates this problem by introducing non-local flow connections to temporally distant frames, enabling propagating video content over motion boundaries. We validate our approach on the DAVIS dataset. Both visual and quantitative results show that our method compares favorably against the state-of-the-art algorithms.

Paper


Flow-edge Guided Video Completion


arXiv


Citation

Chen Gao, Ayush Saraf, Jia-Bin Huang, and Johannes Kopf. "Flow-edge Guided Video Completion", in European Conference on Computer Vision (ECCV), 2020

BibTex

@inproceedings{Gao-ECCV-FGVC,
  Author    = {Gao, Chen and Saraf, Ayush and Huang, Jia-Bin and Kopf, Johannes},
  Title     = {Flow-edge Guided Video Completion},
  booktitle = {Proc. European Conference on Computer Vision (ECCV)},
  year      = {2020}
  }

Acknowledgments

We thank Meng-Li Shih for providing this website template. Teaser video sources and credits:
DAVIS: DAVIS: Densely Annotated VIdeo Segmentation
Bird: Our Planet | Frozen Worlds | FULL EPISODE | Netflix
Yellowstone: Five Must-See Attractions in Yellowstone | National Geographic
Great Wall of China: THE WORLD as you have never seen before 2019 | 10 HOURS | Cinematic Aerial | Beauty Planet Earth