用贝塞尔曲线建模激光雷达人体动作，提升遮挡下的运动预测稳定性。
Bézier Degradation Modeling for LiDAR-based Human Motion Capture
- 通过保留轨迹的贝塞尔曲线压缩控制点，构建平滑可学习的动作表示。
- 在四个数据集上实现最优精度与时间连续性，有效缓解遮挡和噪声影响。
- 适合需要高鲁棒性人体动作捕捉的自动驾驶与机器人场景。
基于激光雷达的三维人体动作捕捉在自动驾驶与机器人等领域有广泛应用，准确的动作重建至关重要。然而，现有方法常因输入不稳定及严重遮挡导致动作预测抖动甚至失败。为此，我们提出BMLiCap，一种自粗到细的框架，利用时间可压缩的贝塞尔曲线建模运动。通过轨迹保持策略减少控制点，获得连贯且利于学习的动作表示。为从激光雷达点云中重建人体动作，设计了渐进式动作重建模块：引入时标运动变换器（TMT）在多时间尺度预测运动曲线，并使用多层级运动聚合器（MMA）自适应融合多尺度曲线，恢复细节丰富、时间连贯的姿态，有效填补遮挡和噪声造成的观测空白。在主流四大数据集LiDARHuman26M、FreeMotion、NoiseMotion和SLOPER4D上，BMLiCap实现了最先进的准确率与时间连续性，展现出对严重遮挡的补偿能力与预测抖动的显著降低。
原文摘要 · Abstract (English)
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 Bézier 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。