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 |