Stochastic Human Motion Prediction
4 papers with code • 0 benchmarks • 0 datasets
Stochastic Human Motion Prediction assumes future stochasticity and therefore tackles the task from a generative point of view. Instead of predicting a single future, it predicts N possible futures.
Benchmarks
These leaderboards are used to track progress in Stochastic Human Motion Prediction
Most implemented papers
Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction
We introduce the task of action-driven stochastic human motion prediction, which aims to predict multiple plausible future motions given a sequence of action labels and a short motion history.
BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction
To address these issues, we present BeLFusion, a model that, for the first time, leverages latent diffusion models in HMP to sample from a latent space where behavior is disentangled from pose and motion.
Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
Predicting diverse human motions given a sequence of historical poses has received increasing attention.
Stochastic Multi-Person 3D Motion Forecasting
This paper aims to deal with the ignored real-world complexities in prior work on human motion forecasting, emphasizing the social properties of multi-person motion, the diversity of motion and social interactions, and the complexity of articulated motion.