OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow.
Lingtong KongXiaohang YangJie YangPublished in: CoRR (2021)
Keyphrases
- optical flow
- motion boundaries
- high quality
- optical flow estimation
- network structure
- computationally efficient
- wireless sensor networks
- peer to peer
- motion discontinuities
- least squares
- random sampling
- network architecture
- dense optical flow
- high accuracy
- motion estimation
- complex networks
- computer networks
- active learning
- neural network
- optical flow algorithm