Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation

2024/03/28 by Xiao Lin, Lin, Xiao, Wenfei Yang +5 · 11 citations
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Image and Object Detection Techniques #Robot Manipulation and Learning

paper · pdf · doi:10.48550/arxiv.2403.19527

openalex publication_date 2024/03/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Category-level 6D object pose estimation aims to estimate the rotation, translation and size of unseen instances within specific categories. In this area, dense correspondence-based methods have achieved leading performance. However, they do not explicitly consider the local and global geometric information of different instances, resulting in poor generalization ability to unseen instances with significant shape variations. To deal with this problem, we propose a novel Instance-Adaptive and Geometric-Aware Keypoint Learning method for category-level 6D object pose estimation (AG-Pose), which includes two key designs: (1) The first design is an Instance-Adaptive Keypoint Detection module, which can adaptively detect a set of sparse keypoints for various instances to represent their geometric structures. (2) The second design is a Geometric-Aware Feature Aggregation module, which can efficiently integrate the local and global geometric information into keypoint features. These two modules can work together to establish robust keypoint-level correspondences for unseen instances, thus enhancing the generalization ability of the model.Experimental results on CAMERA25 and REAL275 datasets show that the proposed AG-Pose outperforms state-of-the-art methods by a large margin without category-specific shape priors.

Cited by

• THE-Pose: Topological Prior with Hybrid Graph Fusion for Estimating Category-Level 6D Object Pose
• PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning
• Box6D : Zero-shot Category-level 6D Pose Estimation of Warehouse Boxes
• OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding
• Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation
• Robotic Manipulation Framework Based on Semantic Keypoints for Packing Shoes of Different Sizes, Shapes, and Softness
• UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation
• You Only Pose Once: A Minimalist's Detection Transformer for Monocular RGB Category-level 9D Multi-Object Pose Estimation
• Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimation
• RCGNet: RGB-based Category-Level 6D Object Pose Estimation with Geometric Guidance
• Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes

Related

• Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation
• TriCons-Pose: Triangle-Invariant Geometric Consistency Learning for Category-Level Object Pose Estimation
• Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild
• GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting
• Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimation