Category-Agnostic Pose Estimation for Point Clouds
This addresses the challenge of pose estimation for new object categories without requiring prior category information, which is incremental as it builds on existing methods but removes the category dependency.
The paper tackled the problem of object pose estimation for unseen categories by proposing a category-agnostic method using geometric patch features, achieving results comparable to category-based methods on CAMERA25 and ModelNet40 datasets.
The goal of object pose estimation is to visually determine the pose of a specific object in the RGB-D input. Unfortunately, when faced with new categories, both instance-based and category-based methods are unable to deal with unseen objects of unseen categories, which is a challenge for pose estimation. To address this issue, this paper proposes a method to introduce geometric features for pose estimation of point clouds without requiring category information. The method is based only on the patch feature of the point cloud, a geometric feature with rotation invariance. After training without category information, our method achieves as good results as other category-based methods. Our method successfully achieved pose annotation of no category information instances on the CAMERA25 dataset and ModelNet40 dataset.