Improving Human Motion Plausibility with Body Momentum

2025-09-11

AI Summary

Existing motion generation methods typically decouple local joint motions from global root-node trajectories, neglecting the physics-based coupling between them induced by environmental interactions—leading to artifacts such as foot sliding, jitter, and poor balance. This paper introduces whole-body linear and angular momentum as a physical bridge and proposes a momentum consistency loss term, embedding momentum dynamics constraints into the root-motion decomposition paradigm within a supervised learning framework. Unlike prior approaches, our method avoids explicit computation of joint torques or external forces, significantly reducing computational complexity while achieving superior trade-offs between physical plausibility (e.g., momentum conservation) and motion fidelity. Experiments demonstrate that our approach effectively suppresses sliding and jitter, markedly improving motion stability and naturalness, while preserving high-fidelity action reconstruction.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Motion and Path Planning
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Many studies decompose human motion into local motion in a frame attached to the root joint and global motion of the root joint in the world frame, treating them separately. However, these two components are not independent. Global movement arises from interactions with the environment, which are, in turn, driven by changes in the body configuration. Motion models often fail to precisely capture this physical coupling between local and global dynamics, while deriving global trajectories from joint torques and external forces is computationally expensive and complex. To address these challenges, we propose using whole-body linear and angular momentum as a constraint to link local motion with global movement. Since momentum reflects the aggregate effect of joint-level dynamics on the body's movement through space, it provides a physically grounded way to relate local joint behavior to global displacement. Building on this insight, we introduce a new loss term that enforces consistency between the generated momentum profiles and those observed in ground-truth data. Incorporating our loss reduces foot sliding and jitter, improves balance, and preserves the accuracy of the recovered motion. Code and data are available at the project page https://hlinhn.github.io/momentum_bmvc.

Problem

• Coupling local and global human motion dynamics
• Reducing physical implausibility in generated motion
• Addressing foot sliding and balance issues

Innovation

• Using body momentum as physical constraint
• Introducing loss for momentum-ground truth consistency
• Reducing foot sliding and improving balance