# Efficient Active Training for Deep LiDAR Odometry

arXiv: https://arxiv.org/abs/2509.03211 · HTML: https://mlsanity.com/paper/2509.03211/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [Motion Transformer with Global Intention Localization and Local Movement Refinement](https://mlsanity.com/paper/2209.13508/) (2022)
- [HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding](https://mlsanity.com/paper/2205.09753/) (2022)
- [Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey](https://mlsanity.com/paper/2112.08936/) (2021)
- [LO-Net: Deep Real-time Lidar Odometry](https://mlsanity.com/paper/1904.08242/) (2019)
- [PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization](https://mlsanity.com/paper/2012.00972/) (2020)
- [LIBRE: The Multiple 3D LiDAR Dataset](https://mlsanity.com/paper/2003.06129/) (2020)
- [Efficient 3D Deep LiDAR Odometry](https://mlsanity.com/paper/2111.02135/) (2021)
- [DMLO: Deep Matching LiDAR Odometry](https://mlsanity.com/paper/2004.03796/) (2020)
- [LodoNet: A Deep Neural Network with 2D Keypoint Matchingfor 3D LiDAR Odometry Estimation](https://mlsanity.com/paper/2009.00164/) (2020)
- [ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving](https://mlsanity.com/paper/2403.02877/) (2024)
- [Self-supervised Learning of LiDAR Odometry for Robotic Applications](https://mlsanity.com/paper/2011.05418/) (2020)
- [DeepPCO: End-to-End Point Cloud Odometry through Deep Parallel Neural Network](https://mlsanity.com/paper/1910.11088/) (2019)
- [CNN for IMU Assisted Odometry Estimation using Velodyne LiDAR](https://mlsanity.com/paper/1712.06352/) (2017)
- [SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks](https://mlsanity.com/paper/2010.09343/) (2020)
- [DeepLO: Geometry-Aware Deep LiDAR Odometry](https://mlsanity.com/paper/1902.10562/) (2019)
- [DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport](https://mlsanity.com/paper/2308.07153/) (2023)
- [Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling](https://mlsanity.com/paper/2202.13353/) (2022)

## Abstract (arXiv)

Robust and efficient deep LiDAR odometry models are crucial for accurate localization and 3D reconstruction, but typically require extensive and diverse training data to adapt to diverse environments, leading to inefficiencies. To tackle this, we introduce an active training framework designed to selectively extract training data from diverse environments, thereby reducing the training load and enhancing model generalization. Our framework is based on two key strategies: Initial Training Set Selection (ITSS) and Active Incremental Selection (AIS). ITSS begins by breaking down motion sequences from general weather into nodes and edges for detailed trajectory analysis, prioritizing diverse sequences to form a rich initial training dataset for training the base model. For complex sequences that are difficult to analyze, especially under challenging snowy weather conditions, AIS uses scene reconstruction and prediction inconsistency to iteratively select training samples, refining the model to handle a wide range of real-world scenarios. Experiments across datasets and weather conditions validate our approach's effectiveness. Notably, our method matches the performance of full-dataset training with just 52% of the sequence volume, demonstrating the training efficiency and robustness of our active training paradigm. By optimizing the training process, our approach sets the stage for more agile and reliable LiDAR odometry systems, capable of navigating diverse environmental conditions with greater precision.