Universal Features Guided Zero-Shot Category-Level Object Pose Estimation

TL;DR

This paper introduces a zero-shot, category-level 6-DOF object pose estimation method that leverages universal 2D and 3D features from RGB-D images, enabling accurate pose estimation for unseen categories without additional training.

Contribution

The proposed approach uniquely combines 2D and 3D universal features with an iterative optimization strategy for zero-shot pose estimation across unseen categories.

Findings

Outperforms previous methods on REAL275 and Wild6D benchmarks.

Effectively handles unseen categories without fine-tuning.

Utilizes universal features for robust pose estimation.

Abstract

Object pose estimation, crucial in computer vision and robotics applications, faces challenges with the diversity of unseen categories. We propose a zero-shot method to achieve category-level 6-DOF object pose estimation, which exploits both 2D and 3D universal features of input RGB-D image to establish semantic similarity-based correspondences and can be extended to unseen categories without additional model fine-tuning. Our method begins with combining efficient 2D universal features to find sparse correspondences between intra-category objects and gets initial coarse pose. To handle the correspondence degradation of 2D universal features if the pose deviates much from the target pose, we use an iterative strategy to optimize the pose. Subsequently, to resolve pose ambiguities due to shape differences between intra-category objects, the coarse pose is refined by optimizing with dense alignment constraint of 3D universal features. Our method outperforms previous methods on the REAL275 and Wild6D benchmarks for unseen categories.