# Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?

## TL;DR

This paper explores the use of diffusion probabilistic models for predicting future 3D human motions, demonstrating their competitiveness and ability to balance accuracy and diversity in predictions.

## Contribution

It is the first study to evaluate diffusion probabilistic models for 3D human motion prediction, showing their effectiveness and potential advantages over existing methods.

## Key findings

- Diffusion models are competitive for 3D motion prediction tasks.
- They can balance likelihood and diversity of predictions.
- A single training process suffices for effective results.

## Abstract

After many researchers observed fruitfulness from the recent diffusion probabilistic model, its effectiveness in image generation is actively studied these days. In this paper, our objective is to evaluate the potential of diffusion probabilistic models for 3D human motion-related tasks. To this end, this paper presents a study of employing diffusion probabilistic models to predict future 3D human motion(s) from the previously observed motion. Based on the Human 3.6M and HumanEva-I datasets, our results show that diffusion probabilistic models are competitive for both single (deterministic) and multiple (stochastic) 3D motion prediction tasks, after finishing a single training process. In addition, we find out that diffusion probabilistic models can offer an attractive compromise, since they can strike the right balance between the likelihood and diversity of the predicted future motions. Our code is publicly available on the project website: https://sites.google.com/view/diffusion-motion-prediction.