Journal
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
Volume -, Issue -, Pages 3767-3776Publisher
IEEE
DOI: 10.1109/CVPR.2017.401
Keywords
-
Categories
Funding
- ONR [N00014-15-1-2261]
- AFOSR [FA9550-15-1-0229]
Ask authors/readers for more resources
We introduce a method to compute optical flow at multiple scales of motion, without resorting to multi-resolution or combinatorial methods. It addresses the key problem of small objects moving fast, and resolves the artificial binding between how large an object is and how fast it can move before being diffused away by classical scale-space. Even with no learning, it achieves top performance on the most challenging optical flow benchmark. Moreover, the results are interpretable, and indeed we list the assumptions underlying our method explicitly. The key to our approach is the matching progression from slow to fast, as well as the choice of interpolation method, or equivalently the prior, to fill in regions where the data allows it. We use several off-the- shelf components, with relatively low sensitivity to parameter tuning. Computational cost is comparable to the state-of-the-art.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available