Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction

by   Dong Wei, et al.

Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the diversity is typically characterized by randomly sampling a set of latent variables from the latent prior, which is then decoded into possible motions. This joint training of sampling and decoding, however, suffers from posterior collapse as the learned latent variables tend to be ignored by a strong decoder, leading to limited diversity. Alternatively, inspired by the diffusion process in nonequilibrium thermodynamics, we propose MotionDiff, a diffusion probabilistic model to treat the kinematics of human joints as heated particles, which will diffuse from original states to a noise distribution. This process offers a natural way to obtain the "whitened" latents without any trainable parameters, and human motion prediction can be regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence. Specifically, MotionDiff consists of two parts: a spatial-temporal transformer-based diffusion network to generate diverse yet plausible motions, and a graph convolutional network to further refine the outputs. Experimental results on two datasets demonstrate that our model yields the competitive performance in terms of both accuracy and diversity.


page 1

page 2

page 3

page 4


Towards Globally Consistent Stochastic Human Motion Prediction via Motion Diffusion

Stochastic human motion prediction aims to predict multiple possible upc...

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

After many researchers observed fruitfulness from the recent diffusion p...

Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks

Human motion prediction, which plays a key role in computer vision, gene...

Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors

Predicting diverse human motions given a sequence of historical poses ha...

BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction

Stochastic human motion prediction (HMP) has generally been tackled with...

Learning Variations in Human Motion via Mix-and-Match Perturbation

Human motion prediction is a stochastic process: Given an observed seque...

Physics-Guided Human Motion Capture with Pose Probability Modeling

Incorporating physics in human motion capture to avoid artifacts like fl...

Please sign up or login with your details

Forgot password? Click here to reset