ADA-DPM: A Neural Descriptors-based Adaptive Noise Filtering Strategy for SLAM

2025/06/22 by Yongxin Shao, Shao, Yongxin, A. C. Tan +9
Computer Science · Engineering · Environmental Science · #Advanced Image and Video Retrieval Techniques #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Remote Sensing and LiDAR Applications #Robotics (cs.RO) #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.2506.18016

openalex publication_date 2025/06/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Lidar SLAM plays a significant role in mobile robot navigation and high-definition map construction. However, existing methods often face a trade-off between localization accuracy and system robustness in scenarios with a high proportion of dynamic objects, point cloud distortion, and unstructured environments. To address this issue, we propose a neural descriptors-based adaptive noise filtering strategy for SLAM, named ADA-DPM, which improves the performance of localization and mapping tasks through three key technical innovations. Firstly, to tackle dynamic object interference, we design the Dynamic Segmentation Head to predict and filter out dynamic feature points, eliminating the ego-motion interference caused by dynamic objects. Secondly, to mitigate the impact of noise and unstructured feature points, we propose the Global Importance Scoring Head that adaptively selects high-contribution feature points while suppressing the influence of noise and unstructured feature points. Moreover, we introduce the Cross-Layer Graph Convolution Module (GLI-GCN) to construct multi-scale neighborhood graphs, fusing local structural information across different scales and improving the discriminative power of overlapping features. Finally, experimental validations on multiple public datasets confirm the effectiveness of ADA-DPM.

Citations

• SP-SLAM: Neural Real-Time Dense SLAM With Scene Priors
• KAN: Kolmogorov-Arnold Networks
• DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors
• MS23D: A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layer
• GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer
• UTOPIC: Uncertainty-aware Overlap Prediction Network for Partial Point Cloud Registration
• PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
• REGTR: End-to-end Point Cloud Correspondences with Transformers
• KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
• Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments
• CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure
• FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration
• Robust Point Cloud Registration Framework Based on Deep Graph Matching
• OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration
• MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Square
• FAST-LIO: A Fast, Robust LiDAR-inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter
• PRNet: Self-Supervised Learning for Partial-to-Partial Registration
• Deep Closest Point: Learning Representations for Point Cloud Registration
• LO-Net: Deep Real-time Lidar Odometry
• PointNetLK: Robust & Efficient Point Cloud Registration using PointNet
• Representation Learning with Contrastive Predictive Coding
• IMLS-SLAM: scan-to-model matching based on 3D data
• On the Convergence of Adam and Beyond
• Open3D: A Modern Library for 3D Data Processing
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• PointNet: Deep Learning on Point Sets for 3D Classification and\n Segmentation
• Training Region-based Object Detectors with Online Hard Example Mining

Related

• DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors
• PFilter: Building Persistent Maps through Feature Filtering for Fast and Accurate LiDAR-based SLAM
• SD-SLAM: A Semantic SLAM Approach for Dynamic Scenes Based on LiDAR Point Clouds
• On the descriptive power of LiDAR intensity images for segment-based loop closing in 3-D SLAM
• CAD-SLAM: Consistency-Aware Dynamic SLAM with Dynamic-Static Decoupled Mapping