# Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions

## TL;DR

This paper introduces a new object-centric video prediction framework that decouples object dynamics and interactions using transformer modules, leading to improved future frame prediction and object representation accuracy.

## Contribution

The paper presents two novel transformer-based modules for object-centric video prediction that separately model object dynamics and interactions, enhancing prediction performance.

## Key findings

- Outperforms object-agnostic models on multiple datasets
- Maintains consistent and accurate object representations
- Improves future frame prediction accuracy

## Abstract

We propose a novel framework for the task of object-centric video prediction, i.e., extracting the compositional structure of a video sequence, as well as modeling objects dynamics and interactions from visual observations in order to predict the future object states, from which we can then generate subsequent video frames. With the goal of learning meaningful spatio-temporal object representations and accurately forecasting object states, we propose two novel object-centric video predictor (OCVP) transformer modules, which decouple the processing of temporal dynamics and object interactions, thus presenting an improved prediction performance. In our experiments, we show how our object-centric prediction framework utilizing our OCVP predictors outperforms object-agnostic video prediction models on two different datasets, while maintaining consistent and accurate object representations.