Accurate Surface and Reflectance Modelling from 3D Radar Data with Neural Radiance Fields
This addresses the challenge of robust scene representation for autonomous systems in low-visibility environments like fog or dust, though it is incremental as it adapts neural implicit methods to radar data.
The paper tackles the problem of 3D surface reconstruction from sparse and noisy radar data by proposing a neural implicit approach that jointly models geometry and view-dependent radar intensities, resulting in smoother and more accurate reconstructions compared to existing lidar-based methods applied to radar data.
Robust scene representation is essential for autonomous systems to safely operate in challenging low-visibility environments. Radar has a clear advantage over cameras and lidars in these conditions due to its resilience to environmental factors such as fog, smoke, or dust. However, radar data is inherently sparse and noisy, making reliable 3D surface reconstruction challenging. To address these challenges, we propose a neural implicit approach for 3D mapping from radar point clouds, which jointly models scene geometry and view-dependent radar intensities. Our method leverages a memory-efficient hybrid feature encoding to learn a continuous Signed Distance Field (SDF) for surface reconstruction, while also capturing radar-specific reflective properties. We show that our approach produces smoother, more accurate 3D surface reconstructions compared to existing lidar-based reconstruction methods applied to radar data, and can reconstruct view-dependent radar intensities. We also show that in general, as input point clouds get sparser, neural implicit representations render more faithful surfaces, compared to traditional explicit SDFs and meshing techniques.