RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos. (arXiv:2207.11075v1 [cs.CV])

Obtaining the ground truth labels from a video is challenging since the
manual annotation of pixel-wise flow labels is prohibitively expensive and
laborious. Besides, existing approaches try to adapt the trained model on
synthetic datasets to authentic videos, which inevitably suffers from domain
discrepancy and hinders the performance for real-world applications. To solve
these problems, we propose RealFlow, an Expectation-Maximization based
framework that can create large-scale optical flow datasets directly from any
unlabeled realistic videos. Specifically, we first estimate optical …

arxiv cv dataset dataset generation flow generation videos