HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation

HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation
Yongliang Lin, Yongzhi Su, Praveen Annamalai Nathan, Sandeep Prudhvi Krishna Inuganti, Yan Di, Martin Sundermayer, Fabian Manhardt, Didier Stricker, Jason Raphael Rambach, Yu Zhang
In: IEEE/CVF (Hrsg.). Proceedings of the. International Conference on Computer Vision and Pattern Recognition (CVPR-2024), June 17-21, Seattle, Washington, USA, IEEE/CVF, 2024.

Abstract:
In this work, we present a novel dense-correspondence method for 6DoF object pose estimation from a single RGBD 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. Code and models will be released.