Real-Time Object Pose Estimation with Pose Interpreter Networks

In this work, we introduce pose interpreter networks for 6-DoF object pose estimation. In contrast to other CNN-based approaches to pose estimation that require expensively annotated object pose data, our pose interpreter network is trained entirely on synthetic pose data. We use object masks as an intermediate representation to bridge real and synthetic. We show that when combined with a segmentation model trained on RGB images, our synthetically trained pose interpreter network is able to generalize to real data. Our end-to-end system for object pose estimation runs in real-time (20 Hz) on live RGB data, without using depth information or ICP refinement.

Authors

• Jimmy Wu
• Bolei Zhou
• Rebecca L. Russell
• Vincent Kee
• Syler Wagner
• Mitchell Hebert
• Antonio Torralba 0001
• David M. S. Johnson

Keywords

• Pose estimation
• Image segmentation
• Three-dimensional displays
• Quaternions
• Real-time systems
• Training
• Task analysis
• Human Pose Estimation
• Object Pose
• Segmentation Model
• RGB Images
• Iterative Closest Point
• RGB Data
• Loss Function
• Training Data
• Convolutional Neural Network
• Object Detection
• Image Object
• Point Cloud
• 3D Space
• Training Images
• Object Classification
• Semantic Segmentation
• Position Error
• Motion Capture
• Synthetic Images
• Orientation Error
• Unit Quaternion
• Object Instances
• Robot Manipulator
• Pose Prediction
• Domain Adaptation
• Forward Pass
• Object Point Cloud
• Receptive Field
• Residual Network