WildFusion: Multimodal Implicit 3D Reconstructions in the Wild

TL;DR

WildFusion introduces a multimodal implicit neural approach for detailed 3D scene reconstruction in complex outdoor environments, integrating diverse sensor data to enhance robotic navigation and environmental understanding.

Contribution

It is the first to fuse multiple sensor modalities into a unified implicit neural representation for in-the-wild 3D scene reconstruction.

Findings

Improved route selection in forest environments.

Accurate prediction of traversability.

Enhanced environmental mapping capabilities.

Abstract

We propose WildFusion, a novel approach for 3D scene reconstruction in unstructured, in-the-wild environments using multimodal implicit neural representations. WildFusion integrates signals from LiDAR, RGB camera, contact microphones, tactile sensors, and IMU. This multimodal fusion generates comprehensive, continuous environmental representations, including pixel-level geometry, color, semantics, and traversability. Through real-world experiments on legged robot navigation in challenging forest environments, WildFusion demonstrates improved route selection by accurately predicting traversability. Our results highlight its potential to advance robotic navigation and 3D mapping in complex outdoor terrains.