Our paper named “Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?” is accepted to 2023 ICRA!
Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?
Hyemin Ahn, Esteve Valls Mascaró, Dongheui Lee
Abstact : After many researchers observed fruitfulness from the recent diffusion probabilistic model, its effectiveness in image generation is actively studied these days. However, to the best of our knowledge, not many studies exist to evaluate the potential of diffusion probabilistic models for 3D motion-related tasks. To validate how much the diffusion probabilistic models can be effective for 3D motion-related tasks, this paper presents a study of employing diffusion probabilistic models to predict future 3D human motion(s) from the previously observed 3D 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 one 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.
