Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration. (arXiv:2205.10195v1 [cs.CV])

How to properly model the inter-frame relation within the video sequence is
an important but unsolved challenge for video restoration (VR). In this work,
we propose an unsupervised flow-aligned sequence-to-sequence model (S2SVR) to
address this problem. On the one hand, the sequence-to-sequence model, which
has proven capable of sequence modeling in the field of natural language
processing, is explored for the first time in VR. Optimized serialization
modeling shows potential in capturing long-range dependencies among frames. On
the other hand, …

arxiv cv flow learning unsupervised video