ActiveGS: Active Scene Reconstruction Using Gaussian Splatting

TL;DR

This paper introduces ActiveGS, a method for actively building accurate scene maps using a hybrid Gaussian splatting and voxel map approach, improving reconstruction quality and exploration efficiency with real-world UAV tests.

Contribution

It presents a novel hybrid map representation and confidence modeling technique for active scene reconstruction with RGB-D cameras, integrating Gaussian splatting and voxel maps.

Findings

Outperforms state-of-the-art scene reconstruction methods.

Enables collision-free exploration and mapping.

Demonstrated on real UAV platform.

Abstract

Robotics applications often rely on scene reconstructions to enable downstream tasks. In this work, we tackle the challenge of actively building an accurate map of an unknown scene using an RGB-D camera on a mobile platform. We propose a hybrid map representation that combines a Gaussian splatting map with a coarse voxel map, leveraging the strengths of both representations: the high-fidelity scene reconstruction capabilities of Gaussian splatting and the spatial modelling strengths of the voxel map. At the core of our framework is an effective confidence modelling technique for the Gaussian splatting map to identify under-reconstructed areas, while utilising spatial information from the voxel map to target unexplored areas and assist in collision-free path planning. By actively collecting scene information in under-reconstructed and unexplored areas for map updates, our approach achieves superior Gaussian splatting reconstruction results compared to state-of-the-art approaches. Additionally, we demonstrate the real-world applicability of our framework using an unmanned aerial vehicle.