通过人体部位分割提升噪声点云中人体注册精度
Robust Human Registration with Body Part Segmentation on Noisy Point Clouds
- 将身体部位分割结果融入网格拟合，分两步优化姿态与对齐
- 在InterCap、EgoBody、BEHAVE数据集上姿态误差降低23.7%以上
- 适合需要高精度人体重建的增强现实与人机交互场景
将人体网格与三维点云进行配准对于增强现实和人机交互等应用至关重要，但真实场景中的噪声和背景干扰常导致结果不准确。本文提出一种混合方法，在网格拟合过程中引入身体部位分割，同时提升姿态估计与分割精度。首先为每个点分配身体部位标签，再利用部位质心进行两阶段SMPL-X拟合：第一步估计初始姿态与朝向，第二步全局优化点云对齐。此外，我们发现拟合的人体网格可反过来优化部位标签，实现闭环改进。在包含杂乱与噪声的真实数据集InterCap、EgoBody、BEHAVE上的实验表明，本方法在姿态估计和分割精度上显著优于现有方法。代码与结果已公开于项目主页：https://segfit.github.io
原文摘要 · Abstract (English)
Registering human meshes to 3D point clouds is essential for applications such as augmented reality and human-robot interaction but often yields imprecise results due to noise and background clutter in real-world data. We introduce a hybrid approach that incorporates body-part segmentation into the mesh fitting process, enhancing both human pose estimation and segmentation accuracy. Our method first assigns body part labels to individual points, which then guide a two-step SMPL-X fitting: initial pose and orientation estimation using body part centroids, followed by global refinement of the point cloud alignment. Additionally, we demonstrate that the fitted human mesh can refine body part labels, leading to improved segmentation. Evaluations on the cluttered and noisy real-world datasets InterCap, EgoBody, and BEHAVE show that our approach significantly outperforms prior methods in both pose estimation and segmentation accuracy. Code and results are available on our project website: https://segfit.github.io
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。