HiPose:面向RGB-D 6DoF物体姿态估计的分层二值表面编码与对应关系剪枝
HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation
AI总结:
HiPose提出一种基于分层二值表面编码和由粗到精3D-3D对应关系剪枝的RGB-D 6DoF姿态估计方法,在多个基准上超越所有免优化方法并达到实时高精度。
摘要:
在这项工作中,我们提出了一种新颖的稠密对应方法,用于从单张RGB-D图像中估计6DoF物体姿态。虽然许多现有的数据驱动方法取得了令人印象深刻的性能,但由于依赖基于渲染的优化方法,它们往往耗时较长。为了规避这一限制,我们提出了HiPose,它通过分层二值表面编码以由粗到精的方式建立3D-3D对应关系。与以往的稠密对应方法不同,我们通过采用点到表面匹配来估计对应表面,并迭代地收缩该表面,直到其变为一个对应点,同时逐步去除离群点。在公开基准LM-O、YCB-V和T-Less上的大量实验表明,我们的方法超越了所有无需优化的方法,甚至可与昂贵的基于优化的方法相媲美。关键的是,我们的方法计算效率高,能够支持对精度要求较高的实时关键应用。
英文摘要:
In this work, we present a novel dense-correspondence method for 6DoF object pose estimation from a single RGB-D image. While many existing data-driven methods achieve impressive performance, they tend to be time-consuming due to their reliance on rendering-based refinement approaches. To circumvent this limitation, we present HiPose, which establishes 3D-3D correspondences in a coarse-to-fine manner with a hierarchical binary surface encoding. Unlike previous dense-correspondence methods, we estimate the correspondence surface by employing point-to-surface matching and iteratively constricting the surface until it becomes a correspondence point while gradually removing outliers. Extensive experiments on public benchmarks LM-O, YCB-V, and T-Less demonstrate that our method surpasses all refinement-free methods and is even on par with expensive refinement-based approaches. Crucially, our approach is computationally efficient and enables real-time critical applications with high accuracy requirements.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。