City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation
Authors:
- Yongliang ShiYSYongliang Shi
- Runyi YangRYRunyi Yang
- Pengfei LiPLPengfei Li
- Zirui WuZWZirui Wu
- Hao ZhaoHZHao Zhao
- Guyue ZhouGZGuyue Zhou
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- iSDF: Real-Time Neural Signed Distance Fields for Robot Perception2022
- Neural Scene Representation for Locomotion on Structured TerrainIEEE Robotics and Automation Letters, 2022
- Vision-Only Robot Navigation in a Neural Radiance WorldIEEE Robotics and Automation Letters, 2022
- VDBFusion: Flexible and Efficient TSDF Integration of Range Sensor DataSensors, 2022
- SECOND: Sparsely Embedded Convolutional DetectionSensors, 2018
- OctoMap: an efficient probabilistic 3D mapping framework based on octreesAutonomous Robots, 2013
- The ball-pivoting algorithm for surface reconstructionIEEE Transactions on Visualization and Computer Graphics, 1999