Generalizable Pose Estimation Using Implicit Scene Representations

6-DoF pose estimation is an essential component of robotic manipulation pipelines. However, it usually suffers from a lack of generalization to new instances and object types. Most widely used methods learn to infer the object pose in a discriminative setup where the model filters useful information to infer the exact pose of the object. While such methods offer accurate poses, the model does not store enough information to generalize to new objects. In this work, we address the generalization capability of pose estimation using models that contain enough information about the object to render it in different poses. We follow the line of work that inverts neural renderers to infer the pose. We propose i-σSRN to maximize the information flowing from the input pose to the rendered scene and invert them to infer the pose given an input image. Specifically, we extend Scene Representation Networks (SRNs) by incorporating a separate network for density estimation and introduce a new way of obtaining a weighted scene representation. We investigate several ways of initial pose estimates and losses for the neural renderer. Our final evaluation shows a significant improvement in inference performance and speed compared to existing approaches.

Authors

• Vaibhav Saxena
• Kamal Rahimi Malekshan
• Linh Tran
• Yotto Koga

Keywords

• Training
• Three-dimensional displays
• Computational modeling
• Pose estimation
• Robot vision systems
• Cameras
• Rendering (computer graphics)
• Scene Representation
• Implicit Scene Representation
• Input Image
• Estimation Network
• Object Pose
• Accurate Pose
• Deep Neural Network
• Image Object
• Point Cloud
• 3D Space
• RGB Images
• Depth Map
• Ray Tracing
• Structure From Motion
• Camera Pose
• Human Pose Estimation
• Object Instances
• Query Image
• Rotation Error
• Implicit Representation
• Pose Estimation Methods
• Unseen Objects
• Lowest Loss
• Instances In The Dataset
• Camera Intrinsics
• Accuracy Of Pose Estimation
• Transformation Matrix
• Loss Function
• Rigid Transformation