DCVNet for improved optical flow pixel tracking in video
DCVNet for improved optical flow pixel tracking in video
DCVNet: Dilated Cost Volume Networks for Fast Optical Flow
arXiv paper abstract https://arxiv.org/abs/2103.17271
arXiv PDF paper https://arxiv.org/pdf/2103.17271.pdf
Optical flow, as a dense matching problem, is about estimating every single pixel's displacement between two consecutive video frames, capturing the motion of brightness
patterns.
... ...
By combining the dilated cost volumes and 3D convolutions, our proposed model DCVNet not only exhibits real-time inference (71 fps on a mid-end 1080ti GPU) but is also compact and obtains comparable accuracy to existing approaches.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments