# NF-Atlas: Multi-Volume Neural Feature Fields for Large Scale LiDAR Mapping

arXiv: https://arxiv.org/abs/2304.04624 · HTML: https://mlsanity.com/paper/2304.04624/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2023.

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

- [PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency](https://mlsanity.com/paper/2401.09101/) (2024)
- [PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction](https://mlsanity.com/paper/2407.01349/) (2024)
- [PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments](https://mlsanity.com/paper/2402.09325/) (2024)
- [Leverage Cross-Attention for End-to-End Open-Vocabulary Panoptic Reconstruction](https://mlsanity.com/paper/2501.01119/) (2025)
- [PC-NeRF: Parent-Child Neural Radiance Fields under Partial Sensor Data Loss in Autonomous Driving Environments](https://mlsanity.com/paper/2310.00874/) (2023)
- [nu-DBA: Neural Implicit Dense Bundle Adjustment Enables Image-Only Driving Scene Reconstruction](https://mlsanity.com/paper/2404.18439/) (2024)
- [KN-LIO: Geometric Kinematics and Neural Field Coupled LiDAR-Inertial Odometry](https://mlsanity.com/paper/2501.04263/) (2025)

## Abstract (arXiv)

LiDAR Mapping has been a long-standing problem in robotics. Recent progress in neural implicit representation has brought new opportunities to robotic mapping. In this paper, we propose the multi-volume neural feature fields, called NF-Atlas, which bridge the neural feature volumes with pose graph optimization. By regarding the neural feature volume as pose graph nodes and the relative pose between volumes as pose graph edges, the entire neural feature field becomes both locally rigid and globally elastic. Locally, the neural feature volume employs a sparse feature Octree and a small MLP to encode the submap SDF with an option of semantics. Learning the map using this structure allows for end-to-end solving of maximum a posteriori (MAP) based probabilistic mapping. Globally, the map is built volume by volume independently, avoiding catastrophic forgetting when mapping incrementally. Furthermore, when a loop closure occurs, with the elastic pose graph based representation, only updating the origin of neural volumes is required without remapping. Finally, these functionalities of NF-Atlas are validated. Thanks to the sparsity and the optimization based formulation, NF-Atlas shows competitive performance in terms of accuracy, efficiency and memory usage on both simulation and real-world datasets.