# BDGS-SLAM: A Probabilistic 3D Gaussian Splatting Framework for Robust SLAM in Dynamic Environments

## TL;DR

BDGS-SLAM improves 3D mapping and tracking in dynamic environments by using probabilistic methods and semantic detection to reduce errors from moving objects.

## Contribution

BDGS-SLAM introduces a Bayesian framework with dynamic Gaussian suppression and probabilistic updates for robust SLAM in dynamic settings.

## Key findings

- BDGS-SLAM achieves comparable tracking accuracy with fewer artifacts in rendered results.
- The framework effectively restores static Gaussians mistakenly removed due to dynamic interference.
- Experiments show higher-fidelity scene reconstruction compared to baseline methods.

## Abstract

Simultaneous Localization and Mapping (SLAM) utilizes sensor data to concurrently construct environmental maps and estimate its own position, finding wide application in scenarios like robotic navigation and augmented reality. SLAM systems based on 3D Gaussian Splatting (3DGS) have garnered significant attention due to their real-time, high-fidelity rendering capabilities. However, in real-world environments containing dynamic objects, existing 3DGS-SLAM methods often suffer from mapping errors and tracking drift due to dynamic interference. To address this challenge, this paper proposes BDGS-SLAM—a Bayesian Dynamic Gaussian Splatting SLAM framework specifically designed for dynamic environments. During the tracking phase, the system integrates semantic detection results from YOLOv5 to build a dynamic prior probability model based on Bayesian filtering, enabling accurate identification of dynamic Gaussians. In the mapping phase, a multi-view probabilistic update mechanism is employed, which aggregates historical observation information from co-visible keyframes. By introducing an exponential decay factor to dynamically adjust weights, this mechanism effectively restores static Gaussians that were mistakenly culled. Furthermore, an adaptive dynamic Gaussian optimization strategy is proposed. This strategy applies penalizing constraints to suppress the negative impact of dynamic Gaussians on rendering while avoiding the erroneous removal of static Gaussians and ensuring the integrity of critical scene information. Experimental results demonstrate that, compared to baseline methods, BDGS-SLAM achieves comparable tracking accuracy while generating fewer artifacts in rendered results and realizing higher-fidelity scene reconstruction.