# DGS-SLAM: Gaussian Splatting SLAM in Dynamic Environment

arXiv: https://arxiv.org/abs/2411.10722 · HTML: https://mlsanity.com/paper/2411.10722/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2024.

## Built on by (most cited first, 10 of 10)

- [DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes](https://mlsanity.com/paper/2503.11979/) (2025)
- [4D Gaussian Splatting SLAM](https://mlsanity.com/paper/2503.16710/) (2025)
- [Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM](https://mlsanity.com/paper/2604.22339/) (2026)
- [ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos](https://mlsanity.com/paper/2509.17864/) (2025)
- [VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping](https://mlsanity.com/paper/2604.02696/) (2026)
- [ConfidentSplat: Confidence-Weighted Depth Fusion for Accurate 3D Gaussian Splatting SLAM](https://mlsanity.com/paper/2509.16863/) (2025)
- [GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow](https://mlsanity.com/paper/2604.15612/) (2026)
- [MoPe: Motion Permanence for Robust Monocular Gaussian Mapping in Dynamic Environments](https://mlsanity.com/paper/2606.29237/) (2026)
- [EndoMD-SLAM: Endoscopic Gaussian Splatting SLAM under Optical Degradation with Memory and Static-Transient Decomposition](https://mlsanity.com/paper/2608.08949/) (2026)
- [RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos](https://mlsanity.com/paper/2608.29003/) (2026)

## Abstract (arXiv)

We introduce Dynamic Gaussian Splatting SLAM (DGS-SLAM), the first dynamic SLAM framework built on the foundation of Gaussian Splatting. While recent advancements in dense SLAM have leveraged Gaussian Splatting to enhance scene representation, most approaches assume a static environment, making them vulnerable to photometric and geometric inconsistencies caused by dynamic objects. To address these challenges, we integrate Gaussian Splatting SLAM with a robust filtering process to handle dynamic objects throughout the entire pipeline, including Gaussian insertion and keyframe selection. Within this framework, to further improve the accuracy of dynamic object removal, we introduce a robust mask generation method that enforces photometric consistency across keyframes, reducing noise from inaccurate segmentation and artifacts such as shadows. Additionally, we propose the loop-aware window selection mechanism, which utilizes unique keyframe IDs of 3D Gaussians to detect loops between the current and past frames, facilitating joint optimization of the current camera poses and the Gaussian map. DGS-SLAM achieves state-of-the-art performance in both camera tracking and novel view synthesis on various dynamic SLAM benchmarks, proving its effectiveness in handling real-world dynamic scenes.