Work

Enhanced visual-inertial SLAM Using SuperPoint and semantic geometric dynamic feature detection

Year: 2026

Type: article

Abstract: Visual-inertial simultaneous localization and mapping (VI-SLAM) is fundamental for unmanned driving and VR. However, traditional feature-based SLAM systems rely on hand-crafted features and lack dedicated methods for handling dynamic objects, which results in degraded performance under challenging conditions, such as violent motion, varying illumination, and dynamic environments. To handle the issues, we propose SuperDynaSLAM, an enhanced VI-SLAM that integrates SuperPoint which is a deep learning-based feature extractor with a two-stage dynamic feature point detection method. By replacing the traditional ORB extractor with SuperPoint, SuperDynaSLAM can extract more robust feature points under challenging conditions. Furthermore, by fusing semantic information and geometric constraints, SuperDynaSLAM can accurately detect moving objects and remove associated dynamic feature points. Experiments conducted on multiple datasets demonstrate that SuperDynaSLAM achieves more competitive performance compared with ORB-SLAM3 and other SLAM systems.

Source: Scientific Reports

DOI: 10.1038/s41598-026-46629-0

Authors: Jianyuan Cui, Yingping Huang, Lele Wang

Institutions: University of Shanghai for Science and Technology, Suzhou Chien-Shiung Institute of Technology

Language: English

Topic: Robotics and Sensor-Based Localization

Subfield: Aerospace Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,690

Funder: National Natural Science Foundation of China