SME-net: Sparse motion estimation for parametric video prediction through reinforcement learning

Yung Han Ho*, Chuan Yuan Cho, Guo Lun Jin, Wen-Hsiao Peng

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Computer Vision, ICCV 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages10461-10469
Number of pages9
ISBN (Electronic)9781728148038
DOIs
StatePublished - Oct 2019
Event17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 - Seoul, Korea, Republic of
Duration: 27 Oct 20192 Nov 2019

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2019-October
ISSN (Print)1550-5499

Conference

Conference17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
CountryKorea, Republic of
CitySeoul
Period27/10/192/11/19

Fingerprint Dive into the research topics of 'SME-net: Sparse motion estimation for parametric video prediction through reinforcement learning'. Together they form a unique fingerprint.

Cite this