NARF24: Estimating Articulated Object Structure for Implicit Rendering
This addresses the challenge of articulated object representation for robotics, which is incremental as it builds on existing NeRF and segmentation techniques.
The paper tackles the problem of representing articulated objects for robots by proposing a method that learns a common Neural Radiance Field (NeRF) representation from a few scenes, combined with parts-based segmentation, to estimate connectivity and joint parameters, enabling configuration-conditioned rendering.
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 implicit space part localization, from which the connectivity and joint parameters of the articulated object can be estimated, thus enabling configuration-conditioned rendering.