標題: SME-Net: Sparse Motion Estimation for Parametric Video Prediction through Reinforcement Learning
作者: Ho, Yung-Han
Cho, Chuan-Yuan
Peng, Wen-Hsiao
Jin, Guo-Lun
資訊工程學系
Department of Computer Science
公開日期: 1-一月-2019
摘要: 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.
URI: http://dx.doi.org/10.1109/ICCV.2019.01056
http://hdl.handle.net/11536/155286
ISBN: 978-1-7281-4803-8
ISSN: 1550-5499
DOI: 10.1109/ICCV.2019.01056
期刊: 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
起始頁: 10461
結束頁: 10469
顯示於類別:會議論文