Paper Info
Title
Saliency Guided Fast Interpolation For Large Displacement Optical Flow
Abstract
The optical flow estimation is still an open question nowadays. One of the bottlenecks of it is the interpolation speed. In this paper, a saliency guide fast interpolation method is proposed which is more than about 2 times faster than the traditional one. The method runs on CPU without any supervision or semantic segmentation information. To make it faster, a fast saliency detection method is introduced to separate the image into two parts. The non-saliency superpixels are interpolated faster with random search only. The salient superpixels are interpolated by propagation and random search. To keep it accurate, the relative initial movement is used to guide the search area when computing the affine model. A soft affine model evaluation is introduced to make the optical flow result more robust. Extensive experiments on challenging datasets MPI-Sintel and KITTI-15 show that our method is efficient and effective.
Year
DOI
Venue
2018
10.1109/ICPR.2018.8545304
2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
Field
DocType
ISSN
Affine transformation,Random search,Computer vision,Pattern recognition,Segmentation,Salience (neuroscience),Computer science,Interpolation,Optical flow estimation,Artificial intelligence,Optical flow,Salient
Conference
1051-4651
Citations 
PageRank 
References 
0
0.34
0
Authors
4
Name
Order
Citations
PageRank
Yueran Zu100.34
Ke Gao236924.62
Xiuguo Bao3144.99
Wenzhong Tang411.70