Click to Move: Controlling Video Generation with Sparse Motion

TL;DR

This paper presents Click to Move (C2M), a framework enabling user-controlled video generation through sparse motion inputs, utilizing a GCN to model object interactions and outperform existing methods.

Contribution

Introducing a novel GCN-based architecture for user-controlled video synthesis with sparse motion inputs and holistic object interaction modeling.

Findings

C2M outperforms existing methods on benchmark datasets.

The GCN effectively models object interactions in scene motion.

User control via sparse clicks produces realistic video sequences.

Abstract

This paper introduces Click to Move (C2M), a novel framework for video generation where the user can control the motion of the synthesized video through mouse clicks specifying simple object trajectories of the key objects in the scene. Our model receives as input an initial frame, its corresponding segmentation map and the sparse motion vectors encoding the input provided by the user. It outputs a plausible video sequence starting from the given frame and with a motion that is consistent with user input. Notably, our proposed deep architecture incorporates a Graph Convolution Network (GCN) modelling the movements of all the objects in the scene in a holistic manner and effectively combining the sparse user motion information and image features. Experimental results show that C2M outperforms existing methods on two publicly available datasets, thus demonstrating the effectiveness of our GCN framework at modelling object interactions. The source code is publicly available at https://github.com/PierfrancescoArdino/C2M.