6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints

2019/10/23 by Wang, Chen, Martín-Martín, Roberto, Xu, Danfei +5 · 7 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.1910.10750

Abstract

We present 6-PACK, a deep learning approach to category-level 6D object pose tracking on RGB-D data. Our method tracks in real-time novel object instances of known object categories such as bowls, laptops, and mugs. 6-PACK learns to compactly represent an object by a handful of 3D keypoints, based on which the interframe motion of an object instance can be estimated through keypoint matching. These keypoints are learned end-to-end without manual supervision in order to be most effective for tracking. Our experiments show that our method substantially outperforms existing methods on the NOCS category-level 6D pose estimation benchmark and supports a physical robot to perform simple vision-based closed-loop manipulation tasks. Our code and video are available at https://sites.google.com/view/6packtracking.

Cited by

• Robust 6-DoF Object Pose Tracking with Built-In Recovery under Occlusions and Rapid Object Motions
• Light Field Based 6DoF Tracking of Previously Unobserved Objects
• PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning
• STORM: Segment, Track, and Object Re-Localization from a Single Image
• Color-Pair Guided Robust Zero-Shot 6D Pose Estimation and Tracking of Cluttered Objects on Edge Devices
• FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation
• DynamicPose: Real-time and Robust 6D Object Pose Tracking for Fast-Moving Cameras and Objects

Related

• BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
• Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation
• Instance- and Category-level 6D Object Pose Estimation
• RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking
• Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset