Self-Intersection-Aware 3D Human Motion Generation Using an Efficient Human Sphere Proxy

2026-05-26

AI Summary

This work addresses the pervasive issue of body self-intersections in 3D human motion generation by introducing a model-agnostic, explicit self-intersection penalty loss. The method leverages an efficient sphere-based proxy geometry representation of the human body, replacing conventional triangle meshes to achieve high detection accuracy with substantially reduced computational overhead. By integrating this loss into mainstream generative frameworks such as MDM and MoMask, our approach reduces self-intersections in generated motions by up to 49%, accelerates training by 98%, and decreases memory consumption by 83%, all while preserving motion naturalness and significantly enhancing visual realism and computational efficiency.

Abstract

Human motion generation has made tremendous progress in recent years, with state-of-the-art approaches surpassing ground truth data in leading evaluation benchmarks. However, visual inspection of the generated motions paints a different picture. Even state-of-the-art approaches generate motions frequently containing self-intersections, i.e., body parts interpenetrating, which are strong artifacts, severely limiting the perceived motion quality. We introduce a novel loss, which explicitly penalizes self-intersections, to the training of human motion generation methods. We base our loss on a sphere proxy of human geometry, which allows us to calculate a self-intersection loss 98% faster and uses 83% less memory than comparable methods based on triangular meshes. The loss is agnostic to the specific approach, and we add it to the training of the recent human motion generation methods human motion diffusion model (MDM) and MoMask. Our extensive experiments show a reduction of self-intersections in generated motions of up to 49% while improving other evaluation metrics. The code is available at https://github.com/boschresearch/humansphereproxy .

Problem

• self-intersection
• 3D human motion generation
• motion artifacts
• body interpenetration

Innovation

• self-intersection-aware
• human sphere proxy
• 3D human motion generation
• efficient geometry representation
• penetration penalty