Motion Graph Unleashed: A Novel Approach to Video Prediction

TL;DR

This paper introduces motion graph, a new method for video prediction that models complex spatial-temporal relationships efficiently, outperforming existing methods in accuracy and resource consumption across multiple datasets.

Contribution

The paper presents a novel motion graph representation for video prediction, significantly improving performance and reducing memory usage compared to prior approaches.

Findings

Outperforms state-of-the-art methods on UCF Sports dataset

Reduces model size by 78% and GPU memory by 47%

Demonstrates strong generalization across datasets like KITTI and Cityscapes

Abstract

We introduce motion graph, a novel approach to the video prediction problem, which predicts future video frames from limited past data. The motion graph transforms patches of video frames into interconnected graph nodes, to comprehensively describe the spatial-temporal relationships among them. This representation overcomes the limitations of existing motion representations such as image differences, optical flow, and motion matrix that either fall short in capturing complex motion patterns or suffer from excessive memory consumption. We further present a video prediction pipeline empowered by motion graph, exhibiting substantial performance improvements and cost reductions. Experiments on various datasets, including UCF Sports, KITTI and Cityscapes, highlight the strong representative ability of motion graph. Especially on UCF Sports, our method matches and outperforms the SOTA methods with a significant reduction in model size by 78% and a substantial decrease in GPU memory utilization by 47%.