WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
Authors:
Top Cited Papers
- 10 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11461-11471
Abstract
We present WildGS-SLAM, a robust and efficient monocular RGB SLAM system designed to handle dynamic environments by leveraging uncertainty-aware geometric mapping. Unlike traditional SLAM systems, which assume static scenes, our approach integrates depth and uncertainty information to enhance tracking, mapping, and rendering performance in the presence of moving objects. We introduce an uncertainty map, predicted by a shallow multi-layer perceptron and DI-NOv2 features, to guide dynamic object removal during both tracking and mapping. This uncertainty map enhances dense bundle adjustment and Gaussian map optimization, improving reconstruction accuracy. Our system is evaluated on multiple datasets and demonstrates artifact-free view synthesis. Results showcase WildGS-SLAM’s superior performance in dynamic environments compared to state-of-the-art methods.Keywords
All Related Versions
This publication has 51 references indexed in Scilit:
- SGS-SLAM: Semantic Gaussian Splatting for Neural Dense SLAM2024
- CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-Aware 3D Gaussian Field2024
- RGBD GS-ICP SLAM2024
- Improving 2D Feature Representations by 3D-Aware Fine-Tuning2024
- SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow2024
- YOLO-SLAM: A semantic SLAM system towards dynamic environment with geometric constraintNeural Computing and Applications, 2022
- Crowd-SLAM: Visual SLAM Towards Crowded Environments using Object DetectionJournal of Intelligent & Robotic Systems, 2021
- Comparative Analysis of OptiTrack Motion Capture Systems2019
- Motion removal for reliable RGB-D SLAM in dynamic environmentsRobotics and Autonomous Systems, 2018
- Mahalanobis distanceResonance, 1999