Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?
This addresses motion prediction for robotics or animation, but it is incremental as it applies an existing method to a new domain.
The paper tackles 3D human motion prediction by evaluating diffusion probabilistic models, finding they are competitive for both deterministic and stochastic tasks on Human 3.6M and HumanEva-I datasets, offering a balance between likelihood and diversity.
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.