WildFusion: Multimodal Implicit 3D Reconstructions in the Wild
arXiv:2409.19904 · doi:10.1109/ICRA55743.2025.11127508
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.
Our project website is at: http://generalroboticslab.com/WildFusion
References in corpus (8)
- ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
- ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
- DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes
- DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments
- Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning
- SuMa++: Efficient LiDAR-based Semantic SLAM
- NEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splatting
- Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving