NARF22: Neural Articulated Radiance Fields for Configuration-Aware Rendering

TL;DR

NARF22 introduces a neural radiance field model for articulated objects that enables high-quality rendering and configuration estimation without explicit structural knowledge, improving scalability and generalization in robotic perception.

Contribution

The paper presents a fully-differentiable, configuration-parameterized NeRF that generalizes across object configurations with minimal data, advancing scalable articulated object modeling.

Findings

Effective rendering of articulated objects with few configurations.

Successful application to real-world robotic datasets.

Improved pose estimation and configuration refinement.

Abstract

Articulated objects pose a unique challenge for robotic perception and manipulation. Their increased number of degrees-of-freedom makes tasks such as localization computationally difficult, while also making the process of real-world dataset collection unscalable. With the aim of addressing these scalability issues, we propose Neural Articulated Radiance Fields (NARF22), a pipeline which uses a fully-differentiable, configuration-parameterized Neural Radiance Field (NeRF) as a means of providing high quality renderings of articulated objects. NARF22 requires no explicit knowledge of the object structure at inference time. We propose a two-stage parts-based training mechanism which allows the object rendering models to generalize well across the configuration space even if the underlying training data has as few as one configuration represented. We demonstrate the efficacy of NARF22 by training configurable renderers on a real-world articulated tool dataset collected via a Fetch mobile manipulation robot. We show the applicability of the model to gradient-based inference methods through a configuration estimation and 6 degree-of-freedom pose refinement task. The project webpage is available at: https://progress.eecs.umich.edu/projects/narf/.