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

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 s...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1406 - 1416
Main Authors Janai, Joel, Guney, Fatma, Wulff, Jonas, Black, Michael J., Geiger, Andreas
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2017
Subjects
Adaptive optics
Cameras
High-speed optical techniques
Optical imaging
Optical recording
Spatial resolution
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:1063-6919
DOI:10.1109/CVPR.2017.154