1. [Publications](/publications)
2. Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image
 
 # Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image

  ![](/sites/default/files/styles/wide/public/publications/CenterPose.jpg?itok=j225YK8X)

 Prior work on 6-DoF object pose estimation has largely focused on instance-level processing, in which a textured CAD model is available for each object being detected. Category-level 6-DoF pose estimation represents an important step toward developing robotic vision systems that operate in unstructured, real-world scenarios. In this work, we propose a single-stage, keypoint-based approach for category-level object pose estimation that operates on unknown object instances within a known category using a single RGB image as input. The proposed network performs 2D object detection, detects 2D keypoints, estimates 6-DoF pose, and regresses relative bounding cuboid dimensions. These quantities are estimated in a sequential fashion, leveraging the recent idea of convGRU for propagating information from easier tasks to those that are more difficult. We favor simplicity in our design choices: generic cuboid vertex coordinates, single-stage network, and monocular RGB input. We conduct extensive experiments on the challenging Objectron benchmark, outperforming state-of-the-art methods on the 3D IoU metric (27.6% higher than the MobilePose single-stage approach and 7.1% higher than the related two-stage approach).



 ## Authors



Yunzhi Lin (NVIDIA, Georgia Institute of Technology)

[Jonathan Tremblay](/person/jonathan-tremblay)

[Stephen Tyree](/person/stephen-tyree)

Patricio A. Vela (Georgia Institute of Technology)

[Stan Birchfield](/person/stan-birchfield)

 

 

 ## Publication Date



Tuesday, February 1, 2022

 

 ## Published in



ICRA 2022

 

 ## Research Area



[Computer Vision](/research-area/computer-vision)

[Robotics](/research-area/robotics)

 

 

 ## External Links



[arXiv](https://arxiv.org/abs/2109.06161)

[code](https://github.com/NVlabs/CenterPose)