# DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization

arXiv: https://arxiv.org/abs/2212.06331 · HTML: https://mlsanity.com/paper/2212.06331/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 63 references that are in the map.
- First posted on arXiv 13 Dec 2022.

## Builds on (most cited first, 26 of 26)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping](https://mlsanity.com/paper/2007.00258/) (2020)
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://mlsanity.com/paper/1605.03344/) (2016)
- [KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way](https://mlsanity.com/paper/2209.15397/) (2022)
- [3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration](https://mlsanity.com/paper/1807.09413/) (2018)
- [LaMAR: Benchmarking Localization and Mapping for Augmented Reality](https://mlsanity.com/paper/2210.10770/) (2022)
- [Learning multiview 3D point cloud registration](https://mlsanity.com/paper/2001.05119/) (2020)
- [OverlapNet: Loop Closing for LiDAR-based SLAM](https://mlsanity.com/paper/2105.11344/) (2021)
- [LO-Net: Deep Real-time Lidar Odometry](https://mlsanity.com/paper/1904.08242/) (2019)
- [HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration](https://mlsanity.com/paper/2107.11992/) (2021)
- [NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge](https://mlsanity.com/paper/2103.11470/) (2021)
- [DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds](https://mlsanity.com/paper/1811.11397/) (2018)
- [LAMP: Large-Scale Autonomous Mapping and Positioning for Exploration of Perceptually-Degraded Subterranean Environments](https://mlsanity.com/paper/2003.01744/) (2020)
- [LOCUS: A Multi-Sensor Lidar-Centric Solution for High-Precision Odometry and 3D Mapping in Real-Time](https://mlsanity.com/paper/2012.14447/) (2020)
- [LOCUS 2.0: Robust and Computationally Efficient Lidar Odometry for Real-Time Underground 3D Mapping](https://mlsanity.com/paper/2205.11784/) (2022)
- [Self-Supervised Place Recognition by Refining Temporal and Featural Pseudo Labels from Panoramic Data](https://mlsanity.com/paper/2208.09315/) (2022)
- [Registration of 3D Point Sets Using Correntropy Similarity Matrix](https://mlsanity.com/paper/2107.09725/) (2021)

## Built on by (most cited first, 14 of 14)

- [SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving](https://mlsanity.com/paper/2306.09001/) (2023)
- [LiDAR-based 4D Occupancy Completion and Forecasting](https://mlsanity.com/paper/2310.11239/) (2023)
- [Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset](https://mlsanity.com/paper/2406.09383/) (2024)
- [Boosting Detection in Crowd Analysis via Underutilized Output Features](https://mlsanity.com/paper/2308.16187/) (2023)
- [Multiway Point Cloud Mosaicking with Diffusion and Global Optimization](https://mlsanity.com/paper/2404.00429/) (2024)
- [TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight](https://mlsanity.com/paper/2410.15674/) (2024)
- [Multiview Scene Graph](https://mlsanity.com/paper/2410.11187/) (2024)
- [DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition](https://mlsanity.com/paper/2312.10616/) (2023)
- [SRMamba: Mamba for Super-Resolution of LiDAR Point Clouds](https://mlsanity.com/paper/2505.10601/) (2025)
- [Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI](https://mlsanity.com/paper/2511.20620/) (2025)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [Scene Summarization: Clustering Scene Videos into Spatially Diverse Frames](https://mlsanity.com/paper/2311.17940/) (2023)
- [Conceptual Evaluation of Deep Visual Stereo Odometry for the MARWIN Radiation Monitoring Robot in Accelerator Tunnels](https://mlsanity.com/paper/2512.00080/) (2025)
- [Spectral Consistency-Guided Multiview Point Cloud Registration for Low-Overlap Scenes](https://mlsanity.com/paper/2609.12417/) (2026)

## Abstract (arXiv)

LiDAR mapping is important yet challenging in self-driving and mobile robotics. To tackle such a global point cloud registration problem, DeepMapping converts the complex map estimation into a self-supervised training of simple deep networks. Despite its broad convergence range on small datasets, DeepMapping still cannot produce satisfactory results on large-scale datasets with thousands of frames. This is due to the lack of loop closures and exact cross-frame point correspondences, and the slow convergence of its global localization network. We propose DeepMapping2 by adding two novel techniques to address these issues: (1) organization of training batch based on map topology from loop closing, and (2) self-supervised local-to-global point consistency loss leveraging pairwise registration. Our experiments and ablation studies on public datasets (KITTI, NCLT, and Nebula) demonstrate the effectiveness of our method.