OnePose: One-Shot Object Pose Estimation without CAD Models

We propose a new method named OnePose for object pose estimation. Unlike existing instance-level or category-level methods, OnePose does not rely on CAD models and can handle objects in arbitrary categories without instance-or category-specific network training. OnePose draws the idea from visual localization and only requires a simple RGB video scan of the object to build a sparse SfM model of the object. Men, this model is registered to new query images with a generic feature matching network. To mitigate the slow runtime of existing visual localization methods, we propose a new graph attention network that directly matches 2D interest points in the query image with the 3D points in the SJM model, resulting in efficient and robust pose estimation. Coinbined with a feature-based pose tracker, OnePose is able to stably detect and track 6D poses of everyday household objects in real-time. We also collected a large-scale dataset that consists of 450 sequences of 150 objects. Code and data are available at the project page: https://zju3dv.github.io/onepose/.

Automated summary

OnePose is a novel method for object pose estimation that does not rely on CAD models and can handle objects in arbitrary categories. It efficiently matches 2D interest points in query images with 3D points in the SfM model, enabling stable detection and tracking of 6D poses in real-time.