Papers › BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction

BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction

25 Nov 2022ICCV 2023 1arXiv:2211.14304archive 2025-07-28

German Barquero, Sergio Escalera, Cristina Palmero

Stochastic human motion prediction (HMP) has generally been tackled with generative adversarial networks and variational autoencoders. Most prior works aim at predicting highly diverse movements in terms of the skeleton joints' dispersion. This has led to methods predicting fast and motion-divergent movements, which are often unrealistic and incoherent with past motion. Such methods also neglect contexts that need to anticipate diverse low-range behaviors, or actions, with subtle joint displacements. 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. As a result, diversity is encouraged from a behavioral perspective. Thanks to our behavior coupler's ability to transfer sampled behavior to ongoing motion, BeLFusion's predictions display a variety of behaviors that are significantly more realistic than the state of the art. To support it, we introduce two metrics, the Area of the Cumulative Motion Distribution, and the Average Pairwise Distance Error, which are correlated to our definition of realism according to a qualitative study with 126 participants. Finally, we prove BeLFusion's generalization power in a new cross-dataset scenario for stochastic HMP.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

BarqueroGerman/BeLFusion officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Diversity Human Pose Forecasting Human motion prediction Motion Synthesis Stochastic Human Motion Prediction motion prediction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Human Pose Forecasting	AMASS	BeLFusion	ADE	0.513	#8 of 11	Archive leaderboard	report
Human Pose Forecasting	AMASS	BeLFusion	APD	9.376	#8 of 11	Archive leaderboard	report
Human Pose Forecasting	AMASS	BeLFusion	APDE	1.977	#8 of 11	Archive leaderboard	report
Human Pose Forecasting	AMASS	BeLFusion	FDE	0.560	#8 of 11	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	BeLFusion	ADE	372	#27 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	BeLFusion	APD	7602	#27 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	BeLFusion	CMD	5.988	#27 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	BeLFusion	FDE	474	#27 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	BeLFusion	FID	0.209	#27 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	BeLFusion	MMADE	473	#27 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	BeLFusion	MMFDE	507	#27 of 33	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion Latent Diffusion Model

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections