google-deepmind / google-deepmind/kinetics-i3d
LiteFlowNet over OpenCV TV-L1 optical flow algorithm. Can we ?
Open
- Dominant language
- Python
- Stars
- 1.8k
- Forks
- 467
- PR merge metrics
- No merged PRs in 30d
Description
I have read about other's people problematic experiences with OpenCV's TV-L1 optical flow algorithm about how time consuming it is and I have also witnessed it myself first-hand.
My question is simple, is it legitimate to choose another Optical Flow Estimation way, for instance the LiteFlowNet (http://mmlab.ie.cuhk.edu.hk/projects/LiteFlowNet/) which is currently the state-of-the-art at CVPR 2018. will this affect the results, especially when I intend to use the Flow Kinetics-i3d model solely for feature extraction purposes ?
Thanks in advance.
Contributor guide
Assessment
This issue has not been assessed yet.