City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation
This addresses the challenge of scalable, continuous mapping for robotics applications, though it appears incremental over existing neural implicit methods.
The paper tackles city-scale continual neural mapping from sparse LiDAR data by proposing a three-layer sampling strategy and panoptic representation, achieving improved mapping fidelity on the SemanticKITTI dataset with quantitative gains.
Neural implicit representations are drawing a lot of attention from the robotics community recently, as they are expressive, continuous and compact. However, city-scale continual implicit dense mapping based on sparse LiDAR input is still an under-explored challenge. To this end, we successfully build a city-scale continual neural mapping system with a panoptic representation that consists of environment-level and instance-level modelling. Given a stream of sparse LiDAR point cloud, it maintains a dynamic generative model that maps 3D coordinates to signed distance field (SDF) values. To address the difficulty of representing geometric information at different levels in city-scale space, we propose a tailored three-layer sampling strategy to dynamically sample the global, local and near-surface domains. Meanwhile, to realize high fidelity mapping of instance under incomplete observation, category-specific prior is introduced to better model the geometric details. We evaluate on the public SemanticKITTI dataset and demonstrate the significance of the newly proposed three-layer sampling strategy and panoptic representation, using both quantitative and qualitative results. Codes and model will be publicly available.