Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation

TL;DR

This paper introduces a unified RGB-based framework that uses fixed external cameras as prior maps to improve active 3D scene graph generation and exploration efficiency in robotic systems.

Contribution

It presents a hardware-agnostic, RGB-only pipeline that fuses external and onboard camera data for incremental scene understanding and active exploration.

Findings

Bootstrapping with a single external camera increases initial object recall by up to 79%.

The prior context significantly enhances the efficiency of active exploration.

The framework requires no hardware modifications and processes all cameras identically.

Abstract

Commonly available prior information, such as BIM models, floor plans, and remote sensing images, can provide valuable geometric and semantic context for autonomous robotic systems. In this paper, we treat observations from fixed external RGB cameras as Common Prior Maps (CPMs): wide-field views of the environment that initialize a semantic and geometric scene prior before any robot motion begins. We present an RGB-only framework for active, incremental 3D scene graph (3DSG) generation that seamlessly fuses observations from both onboard robot cameras and fixed external cameras within a single hardware-agnostic pipeline. By relying solely on RGB observations processed by a feed-forward 3D reconstruction model, the system treats all cameras - onboard or external - identically, requiring no hardware modifications. A graph-based active semantic exploration framework then directly leverages the partial scene graph to guide the robot toward regions of high semantic uncertainty, progressively completing and refining the prior. Experiments demonstrate that bootstrapping the scene graph with even a single external camera increases initial object recall by up to +79%, and that the richer context of the prior significantly improves the efficiency of subsequent active exploration.