NARF24: Estimating Articulated Object Structure for Implicit Rendering

TL;DR

This paper introduces a method that combines neural radiance fields with parts-based segmentation to model and estimate the structure and articulation of objects, enabling configuration-aware rendering.

Contribution

It presents a novel approach that learns a shared NeRF representation for articulated objects and estimates their joint parameters from limited scene data.

Findings

Effective articulation estimation from few scenes

Accurate part localization and joint parameter inference

Enables realistic configuration-conditioned 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 implicit space part localization, from which the connectivity and joint parameters of the articulated object can be estimated, thus enabling configuration-conditioned rendering.