Abstract
Stochastic human motion prediction (HMP) has generally been tackled with generative adversarial networks and variational autoencoders. Most prior works aim at predicting highly diverse motion in terms of the skeleton joints' dispersion. This has led to methods predicting fast and divergent movements, which are often unrealistic and incoherent with past motion. Such methods also neglect scenarios where anticipating diverse short-range behaviors with subtle joint displacements is important. To address these issues, we present BeLFusion, a model that, for the first time, leverages latent diffusion models in HMP to sample from a behavioral latent space where behavior is disentangled from pose and motion. Thanks to our behavior coupler, which is able to transfer sampled behavior to ongoing motion, BeLFusion's predictions display a variety of behaviors that are significantly more realistic, and coherent with past motion 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 realism according to a qualitative study (126 participants). Finally, we prove BeLFusion's generalization power in a new cross-dataset scenario for stochastic HMP.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 |
Antal sider | 11 |
Forlag | IEEE Signal Processing Society |
Publikationsdato | 2023 |
Sider | 2317-2327 |
ISBN (Elektronisk) | 9798350307184 |
DOI | |
Status | Udgivet - 2023 |
Udgivet eksternt | Ja |
Begivenhed | 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, Frankrig Varighed: 2 okt. 2023 → 6 okt. 2023 |
Konference
Konference | 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 |
---|---|
Land/Område | Frankrig |
By | Paris |
Periode | 02/10/2023 → 06/10/2023 |
Navn | Proceedings of the IEEE International Conference on Computer Vision |
---|---|
ISSN | 1550-5499 |
Bibliografisk note
Publisher Copyright:© 2023 IEEE.