WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
Authors:
Preprint
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 DINOv2 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 23 references indexed in Scilit:
- Splat-SLAM: Globally Optimized RGB-Only SLAM with 3D Gaussians2025
- MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos2025
- RGBD GS-ICP SLAM2024
- ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields2023
- YOLO-SLAM: A semantic SLAM system towards dynamic environment with geometric constraintNeural Computing and Applications, 2022
- Improving monocular visual SLAM in dynamic environments: an optical-flow-based approachAdvanced Robotics, 2019
- Motion removal for reliable RGB-D SLAM in dynamic environmentsRobotics and Autonomous Systems, 2018
- Mask-SLAM: Robust Feature-Based Monocular SLAM by Masking Using Semantic Segmentation2018
- Rotation Averaging with Application to Camera-Rig Calibration2010
- Least-squares estimation of transformation parameters between two point patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991