Neural method smooths and improves large scale lidar maps
Neural Implicit Energy Optimization for LiDAR Mapping
Computer Vision and Pattern RecognitionGraphicsMachine Learning
Summary
LiDAR scans can create 3D maps, but these often have noisy or jittery surfaces. The authors show how to improve these maps by using a neural network to represent the surfaces while applying a mathematical smoothness rule based on the surface's curvature. This helps produce clearer, smoother 3D shapes without losing important details. Their approach works efficiently even on very large scenes.
What this means in practice
- •For mapping teams: Create smooth and accurate large scale 3D maps from noisy LiDAR data without extra processing time.
- •For autonomous vehicle engineers: Improve laser-based scene understanding by generating reliable surface geometry for navigation systems.
Authors
Hrishikesh Viswanath, Md Ashiqur Rahman, Chi Lin, Damon Conover, Aniket Bera
Abstract
Neural implicit representations provide memory-efficient signed distance field (SDF) parameterizations for large-scale LiDAR scenes, but the geometry recovered from sparse and often noisy inputs carries jitter and artifacts. Classical geometric optimization techniques resolve such artifacts with surface energy functionals, whose minimizers correspond to smooth surfaces. Motivated by this principle, we formulate neural LiDAR mapping as the optimization of energy functionals over the parameter space of neural implicit representations. Specifically, we regularize the signed distance field with an energy functional defined on the shape operator of its level set, which represents the curvature of the surface, thus encouraging smoothness along the surface. This adapts classical geometric priors to the scale of million-point LiDAR maps. Experiments on large-scale datasets show reconstructions with improved smoothness at preserved geometric fidelity, and no additional inference-time cost. The code is publicly available at \href{https://github.com/HrishikeshVish/nieo}{https://github.com/HrishikeshVish/nieo}