SME-Net: Sparse Motion Estimation for Parametric Video Prediction Through Reinforcement Learning

Yung-Han Ho, Chuan-Yuan Cho, Guo-Lun Jin, Wen-Hsiao PengICCV 2019 · OpenReview

Abstract

This paper leverages a classic prediction technique, known as parametric overlapped block motion compensation (POBMC), in a reinforcement learning framework for video prediction. Learning-based prediction methods with explicit motion models often suffer from having to estimate large numbers of motion parameters with artificial regularization. Inspired by the success of sparse motion-based prediction for video compression, we propose a parametric video prediction on a sparse motion field composed of few critical pixels and their motion vectors. The prediction is achieved by gradually refining the estimate of a future frame in iterative, discrete steps. Along the way, the identification of critical pixels and their motion estimation are addressed by two neural networks trained under a reinforcement learning setting. Our model achieves the state-of-the-art performance on CaltchPed, UCF101 and CIF datasets in one-step and multi-step prediction tests. It shows good generalization results and is able to learn well on small training data.
BibTeX
@inproceedings{ho2019sme,
  author = {Yung-Han Ho and Chuan-Yuan Cho and Guo-Lun Jin and Wen-Hsiao Peng},
  title = {{SME-Net: Sparse Motion Estimation for Parametric Video Prediction Through Reinforcement Learning}},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {2019},
  url = {https://openreview.net/forum?id=Qsilpg89sC},
}

Loading related content...

Figure