A Probabilistic Formulation of LiDAR Mapping with Neural Radiance Fields
This addresses a specific issue in LiDAR-based 3D reconstruction for robotics or autonomous systems, offering an incremental improvement over existing NeRF methods.
The paper tackles the problem of training Neural Radiance Fields (NeRF) for LiDAR mapping, where traditional methods cause phantom surfaces due to probabilistic LiDAR returns, and shows that reformulating the loss as an integral of probability allows learning multiple peaks per ray to sample different returns from a single channel.
In this paper we reexamine the process through which a Neural Radiance Field (NeRF) can be trained to produce novel LiDAR views of a scene. Unlike image applications where camera pixels integrate light over time, LiDAR pulses arrive at specific times. As such, multiple LiDAR returns are possible for any given detector and the classification of these returns is inherently probabilistic. Applying a traditional NeRF training routine can result in the network learning phantom surfaces in free space between conflicting range measurements, similar to how floater aberrations may be produced by an image model. We show that by formulating loss as an integral of probability (rather than as an integral of optical density) the network can learn multiple peaks for a given ray, allowing the sampling of first, nth, or strongest returns from a single output channel. Code is available at https://github.com/mcdermatt/PLINK