Pay Attention to Hidden States for Video Deblurring: Ping-Pong Recurrent Neural Networks and Selective Non-Local Attention. (arXiv:2203.16063v2 [cs.CV] UPDATED)

Video deblurring models exploit information in the neighboring frames to
remove blur caused by the motion of the camera and the objects. Recurrent
Neural Networks~(RNNs) are often adopted to model the temporal dependency
between frames via hidden states. When motion blur is strong, however, hidden
states are hard to deliver proper information due to the displacement between
different frames. While there have been attempts to update the hidden states,
it is difficult to handle misaligned features beyond the receptive field …

arxiv attention cv local attention networks neural networks video