Fit-NGP: Fitting Object Models to Neural Graphics Primitives
This enables robust pose estimation for small, reflective objects in robotics, but it is incremental as it builds on existing neural graphics primitives and radiance field methods.
The paper tackled the problem of accurate 3D object pose estimation for robotic applications by using a density field from an efficient radiance field reconstruction method, achieving accuracy on the order of 1mm for small objects like bolts and nuts.
Accurate 3D object pose estimation is key to enabling many robotic applications that involve challenging object interactions. In this work, we show that the density field created by a state-of-the-art efficient radiance field reconstruction method is suitable for highly accurate and robust pose estimation for objects with known 3D models, even when they are very small and with challenging reflective surfaces. We present a fully automatic object pose estimation system based on a robot arm with a single wrist-mounted camera, which can scan a scene from scratch, detect and estimate the 6-Degrees of Freedom (DoF) poses of multiple objects within a couple of minutes of operation. Small objects such as bolts and nuts are estimated with accuracy on order of 1mm.