SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspection

TL;DR

SiLVR introduces a scalable neural reconstruction system that fuses lidar and vision data using neural radiance fields, enabling high-quality, large-scale, and geometrically accurate 3D reconstructions for robotic inspection tasks.

Contribution

The paper adapts neural radiance fields to incorporate lidar data, enabling scalable, large-scale 3D reconstructions with geometric accuracy and photo-realistic textures in robotic environments.

Findings

Achieved high-quality reconstructions over 600 meters of environment.

Reduced computation time through SfM-based bootstrapping.

Demonstrated system on diverse robotic platforms and environments.

Abstract

We present a neural-field-based large-scale reconstruction system that fuses lidar and vision data to generate high-quality reconstructions that are geometrically accurate and capture photo-realistic textures. This system adapts the state-of-the-art neural radiance field (NeRF) representation to also incorporate lidar data which adds strong geometric constraints on the depth and surface normals. We exploit the trajectory from a real-time lidar SLAM system to bootstrap a Structure-from-Motion (SfM) procedure to both significantly reduce the computation time and to provide metric scale which is crucial for lidar depth loss. We use submapping to scale the system to large-scale environments captured over long trajectories. We demonstrate the reconstruction system with data from a multi-camera, lidar sensor suite onboard a legged robot, hand-held while scanning building scenes for 600 metres, and onboard an aerial robot surveying a multi-storey mock disaster site-building. Website: https://ori-drs.github.io/projects/silvr/