NARF24: Estimating Articulated Object Structure for Implicit Rendering

Abstract-- Articulated objects and their representations pose a difficult problem for robots. These objects require not only representations of geometry and texture, but also of the various connections and joint parameters that make up each articulation. We propose a method that learns a common Neural Radiance Field (NeRF) representation across a small number of collected scenes. This representation is combined with a parts-based image segmentation to produce an implicitspace part localization, from which the connectivity and joint parameters of the articulated object can be estimated, thus enabling configuration-conditioned rendering. Articulated objects pose significant challenges for robots due to their complex degrees of freedom compared to rigidbody objects, complicating tasks like pose estimation and grasp synthesis.