HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation
Yongliang Lin, Yongzhi Su, Praveen Nathan, Sandeep Inuganti, Yan Di, Martin Sundermeyer, Fabian Manhardt, Didier Stricker
Abstract
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.
BibTeX
@inproceedings{cvpr2024_hiposehierarchic,
title = {HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation},
author = {Yongliang Lin and Yongzhi Su and Praveen Nathan and Sandeep Inuganti and Yan Di and Martin Sundermeyer and Fabian Manhardt and Didier Stricker and Jason Rambach and Yu Zhang},
booktitle = {CVPR 2024},
year = {2024}
}