Hi-LOAM: Hierarchical Implicit Neural Fields for LiDAR Odometry and Mapping

Abstract

LiDAR Odometry and Mapping (LOAM) is a pivotal technique for embodied-AI applications such as autonomous driving and robot navigation. Most existing LOAM frameworks are either contingent on the supervision signal, or lack of the reconstruction fidelity, which are deficient in depicting details of large-scale complex scenes. To overcome these limitations, we propose a multi-scale implicit neural localization and mapping framework using LiDAR sensor, called Hi-LOAM. Hi-LOAM receives LiDAR point cloud as the input data modality, learns and stores hierarchical latent features in multiple levels of hash tables based on an octree structure, then these multi-scale latent features are decoded into signed distance value through shallow Multilayer Perceptrons (MLPs) in the mapping procedure. For pose estimation procedure, we rely on a correspondence-free, scan-to-implicit matching paradigm to estimate optimal pose and register current scan into the submap. The entire training process is conducted in a self-supervised manner, which waives the model pre-training and manifests its generalizability when applied to diverse environments. Extensive experiments on multiple real-world and synthetic datasets demonstrate the superior performance, in terms of the effectiveness and generalization capabilities, of our Hi-LOAM compared to existing state-of-the-art methods.

Figures (11)

• Figure 1: Reconstructed map and estimated trajectory generated via our implicit Hi-LOAM. The above case is evaluated on the sequence 07 of KITTI dataset, superior mapping quality and accurate poses are obtained via deep utilization of hierarchical neural features.
• Figure 2: The Overview of Our Hi-LOAM Framework. The main data stream is depicted as following. Sampled points $\mathbf{P}_{\mathrm{C}_t}$ along the ray is used to construct neural signed distance fields (nSDF) based on the octree. For the first two scans, poses $\mathbf{P}_{0}$ and $\mathbf{P}_{1}$ are predefined and nSDF are created. For following scans, original points $\mathbf{P}_{t}$ are firstly matched with octree of sub map to estimate the pose $\mathbf{T}_{\mathrm{WC}_t}^*$. Then, $\mathbf{P}_{t}$ is transformed into the global coordinate system via $\mathbf{T}_{\mathrm{WC}_t}^*$, $\mathbf{P}_{\mathrm{W}_t}$ is registered to expand the nSDF, this process is repeated in turn. The separate optimization strategies are designed for odometry and mapping, the trainable parameters and frozen parameters are marked correspondingly.
• Figure 3: The correspondence among the three tables in certain level of octree. The eight corners of a node correspond to eight features stored in table $\mathbf{F}$. The hierarchical nodes and their corresponding corners are stored in Morton code form in tables $\mathbf{N}$ and $\mathbf{G}$.
• Figure 4: The Qualitative Results of Odometry Comparison on Sequence 00 of KITTI Dataset. The left side displays trajectories comparison of different methods. The right side compares errors along the X, Y, and Z axes among our method and other methods. The black dashed line represents the ground truth trajectory. (Best viewed with zoom-in.)
• Figure 5: The Qualitative Results of Our Odometry on MulRAN Dataset. The black dashed line represents the ground truth, while the blue solid line represents our trajectory. (Best viewed with zoom-in.)