Staged Contact-Aware Global Human Motion Forecasting
Luca Scofano, Alessio Sampieri, Elisabeth Schiele, Edoardo De Matteis,, Laura Leal-Taix\'e, Fabio Galasso

TL;DR
This paper introduces STAG, a three-stage approach for scene-aware global human motion forecasting that significantly improves accuracy over previous end-to-end methods by modeling contact points, coarse trajectory, and fine joint motion separately.
Contribution
The paper presents a novel staged pipeline for human motion prediction that outperforms state-of-the-art methods and introduces the 'time-to-go' temporal counter for better contact prediction.
Findings
STAG achieves 1.8% and 16.2% improvements in pose and trajectory prediction.
Ablation study confirms staged modeling's advantages over end-to-end approaches.
The method generalizes well to datasets without scene context, setting new benchmarks.
Abstract
Scene-aware global human motion forecasting is critical for manifold applications, including virtual reality, robotics, and sports. The task combines human trajectory and pose forecasting within the provided scene context, which represents a significant challenge. So far, only Mao et al. NeurIPS'22 have addressed scene-aware global motion, cascading the prediction of future scene contact points and the global motion estimation. They perform the latter as the end-to-end forecasting of future trajectories and poses. However, end-to-end contrasts with the coarse-to-fine nature of the task and it results in lower performance, as we demonstrate here empirically. We propose a STAGed contact-aware global human motion forecasting STAG, a novel three-stage pipeline for predicting global human motion in a 3D environment. We first consider the scene and the respective human interaction as…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Autonomous Vehicle Technology and Safety · Anomaly Detection Techniques and Applications
