Object Registration in Neural Fields

David Hall, Stephen Hausler, Sutharsan Mahendren, Peyman Moghadam

Keywords: Neural Fields, Registration, Pose Estimation, Neural Field Editing, Neural Field Scene Generation

TL;DR: Extended analysis of the Reg-NF technique for registration of object neural fields within a larger scene neural field.

Abstract:

Neural fields provide a continuous scene representation of 3D geometry and appearance in a way which has great promise for robotics applications. One functionality that unlocks unique use-cases for neural fields in robotics is object 6-DoF registration.
In this paper, we provide an expanded analysis of the recent Reg-NF neural field registration method and its use-cases within a robotics context. We showcase the scenario of determining the 6-DoF pose of known objects within a scene using scene and object neural field models. We show how this may be used to better represent objects within imperfectly modelled scenes and generate new scenes by substituting object neural field models into the scene.

Submission Number: 8