arXiv:2503.01254cs.CVcs.RO2025-03

用凸包约束提升四元数物体建图精度,改善单目与深度相机的定位效果。

Convex Hull-based Algebraic Constraint for Visual Quadric SLAM

  • 基于凸包设计更精确的代数约束,融合语义分割减少轮廓错配。
  • 在多个公开数据集上优于现有四元数SLAM方法,定位精度显著提升。
  • 适用于单目和RGB-D SLAM,适合需要高精度物体建模的场景。

使用四元数作为物体表示具有通用性及图像与世界空间间闭式投影推导的优势。尽管已有多种双四元数重建约束被提出,但许多方法精度不足,对定位提升有限。通过深入分析现有约束,本文提出一种简洁且更精确的基于凸包的代数约束,应用于物体重建、前端位姿估计及后端捆绑调整。该约束充分利用精确语义分割,有效缓解复杂形状物体轮廓与双四元数之间的匹配误差。在多个公开数据集上的实验表明,本方法适用于单目与RGB-D SLAM,实现比现有四元数SLAM方法更优的物体映射与定位性能。代码已开源:https://github.com/tiev-tongji/convexhull-based-algebraic-constraint。

原文摘要 · Abstract (English)

Using Quadrics as the object representation has the benefits of both generality and closed-form projection derivation between image and world spaces. Although numerous constraints have been proposed for dual quadric reconstruction, we found that many of them are imprecise and provide minimal improvements to localization.After scrutinizing the existing constraints, we introduce a concise yet more precise convex hull-based algebraic constraint for object landmarks, which is applied to object reconstruction, frontend pose estimation, and backend bundle adjustment.This constraint is designed to fully leverage precise semantic segmentation, effectively mitigating mismatches between complex-shaped object contours and dual quadrics.Experiments on public datasets demonstrate that our approach is applicable to both monocular and RGB-D SLAM and achieves improved object mapping and localization than existing quadric SLAM methods. The implementation of our method is available at https://github.com/tiev-tongji/convexhull-based-algebraic-constraint.

SLAM四元数物体建模视觉定位

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。