# City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation

arXiv: https://arxiv.org/abs/2209.14072 · HTML: https://mlsanity.com/paper/2209.14072/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 49 references that are in the map.
- First posted on arXiv 28 Sep 2022.

## Builds on (most cited first, 30 of 30)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [Urban Radiance Fields](https://mlsanity.com/paper/2111.14643/) (2021)
- [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022)
- [Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering](https://mlsanity.com/paper/2109.01847/) (2021)
- [Training behavior of deep neural network in frequency domain](https://mlsanity.com/paper/1807.01251/) (2018)
- [Vision-Only Robot Navigation in a Neural Radiance World](https://mlsanity.com/paper/2110.00168/) (2021)
- [Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning](https://mlsanity.com/paper/1611.03631/) (2016)
- [iSDF: Real-Time Neural Signed Distance Fields for Robot Perception](https://mlsanity.com/paper/2204.02296/) (2022)
- [Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding](https://mlsanity.com/paper/2106.02795/) (2021)
- [Learning Shape Priors for Single-View 3D Completion and Reconstruction](https://mlsanity.com/paper/1809.05068/) (2018)
- [Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observations](https://mlsanity.com/paper/2108.05851/) (2021)
- [NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping](https://mlsanity.com/paper/2111.15207/) (2021)
- [LOL: Lidar-Only Odometry and Localization in 3D Point Cloud Maps](https://mlsanity.com/paper/2007.01595/) (2020)
- [Neural Scene Representation for Locomotion on Structured Terrain](https://mlsanity.com/paper/2206.08077/) (2022)
- [Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild](https://mlsanity.com/paper/2111.12728/) (2021)

## Built on by (most cited first, 7 of 7)

- [OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments](https://mlsanity.com/paper/2403.09412/) (2024)
- [EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark](https://mlsanity.com/paper/2510.06218/) (2025)
- [ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields](https://mlsanity.com/paper/2312.12122/) (2023)
- [OpenNav: Open-World Navigation with Multimodal Large Language Models](https://mlsanity.com/paper/2507.18033/) (2025)
- [SelFLoc: Selective Feature Fusion for Large-scale Point Cloud-based Place Recognition](https://mlsanity.com/paper/2306.01205/) (2023)
- [Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation](https://mlsanity.com/paper/2504.14249/) (2025)
- [LangStreet: Persistent Language Fields for Anchor-Decoded Street Gaussians](https://mlsanity.com/paper/2609.11616/) (2026)

## Abstract (arXiv)

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.