B\'ezier Degradation Modeling for LiDAR-based Human Motion Capture

TL;DR

This paper introduces BMLiCap, a novel coarse-to-fine framework using Bezier curves and multi-scale transformers to improve LiDAR-based human motion capture, especially under occlusions and noisy inputs.

Contribution

The work presents a new Bezier curve-based motion modeling approach with a progressive reconstruction module and multi-scale transformer, achieving state-of-the-art results in LiDAR human motion capture.

Findings

Achieves state-of-the-art accuracy on four benchmarks.

Effectively handles severe occlusions and noise.

Reduces jitter and improves temporal coherence.

Abstract

LiDAR-based 3D human motion capture has broad applications in fields such as autonomous driving and robotics, where accurate motion reconstruction is crucial. However, existing methods often struggle with unstable inputs and severe occlusions, leading to jittery or even failed pose predictions. To address these challenges, we propose BMLiCap, a coarse-to-fine framework that models motion using temporally compressible B\'ezier curves. By reducing control points through a trajectory-preserving strategy, we obtain a coherent and learning-friendly motion representation. To reconstruct human actions from LiDAR point-cloud cues, we design a progressive motion-reconstruction module. Specifically, a Time-scale Motion Transformer (TMT) is introduced to predict motion curves at multiple temporal scales, and a Multi-level Motion Aggregator (MMA) is utilized to adaptively fuse the multi-scale curves to recover detailed, temporally coherent poses, effectively bridging observation gaps caused by occlusions and noise. Across four mainstream benchmarks LiDARHuman26M, FreeMotion, NoiseMotion, and SLOPER4D, BMLiCap achieves state-of-the-art accuracy and temporal continuity in complex scenes, demonstrating its ability to compensate for severe occlusions and reduce prediction jitter.