GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields

TL;DR

GeoNLF is a novel framework that combines geometric priors with neural reconstruction to improve pose-free LiDAR point cloud synthesis and registration, especially under sparse views, without relying on precomputed poses.

Contribution

It introduces a hybrid approach with alternating global neural reconstruction and geometric pose optimization, incorporating a selective-reweighting strategy and geometric constraints for robustness.

Findings

Outperforms existing methods in novel view synthesis.

Achieves superior multi-view registration on large-scale point clouds.

Demonstrates effectiveness on NuScenes and KITTI-360 datasets.

Abstract

Although recent efforts have extended Neural Radiance Fields (NeRF) into LiDAR point cloud synthesis, the majority of existing works exhibit a strong dependence on precomputed poses. However, point cloud registration methods struggle to achieve precise global pose estimation, whereas previous pose-free NeRFs overlook geometric consistency in global reconstruction. In light of this, we explore the geometric insights of point clouds, which provide explicit registration priors for reconstruction. Based on this, we propose Geometry guided Neural LiDAR Fields(GeoNLF), a hybrid framework performing alternately global neural reconstruction and pure geometric pose optimization. Furthermore, NeRFs tend to overfit individual frames and easily get stuck in local minima under sparse-view inputs. To tackle this issue, we develop a selective-reweighting strategy and introduce geometric constraints for robust optimization. Extensive experiments on NuScenes and KITTI-360 datasets demonstrate the superiority of GeoNLF in both novel view synthesis and multi-view registration of low-frequency large-scale point clouds.