Perceiving Systems, Computer Vision

Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data

2017

Conference Paper

avg

ps


Existing optical flow datasets are limited in size and variability due to the difficulty of capturing dense ground truth. In this paper, we tackle this problem by tracking pixels through densely sampled space-time volumes recorded with a high-speed video camera. Our model exploits the linearity of small motions and reasons about occlusions from multiple frames. Using our technique, we are able to establish accurate reference flow fields outside the laboratory in natural environments. Besides, we show how our predictions can be used to augment the input images with realistic motion blur. We demonstrate the quality of the produced flow fields on synthetic and real-world datasets. Finally, we collect a novel challenging optical flow dataset by applying our technique on data from a high-speed camera and analyze the performance of the state-of-the-art in optical flow under various levels of motion blur.

Author(s): Joel Janai and Fatma Güney and Jonas Wulff and Michael Black and Andreas Geiger
Book Title: Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017
Pages: 1406--1416
Year: 2017
Month: July
Day: 21-26
Publisher: IEEE

Department(s): Autonomous Vision, Perceiving Systems
Research Project(s): Slow Flow
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1109/CVPR.2017.154
Event Name: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Event Place: Honolulu, HI, USA

Address: Piscataway, NJ, USA
ISBN: 978-1-5386-0457-1
ISSN: 1063-6919

Links: pdf
suppmat
Project page
Video
Video:

BibTex

@inproceedings{Janai2017CVPR,
  title = {Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data },
  author = {Janai, Joel and G{\"u}ney, Fatma and Wulff, Jonas and Black, Michael and Geiger, Andreas},
  booktitle = {Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017},
  pages = {1406--1416},
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = jul,
  year = {2017},
  doi = {10.1109/CVPR.2017.154},
  month_numeric = {7}
}