# Towards Real-time Semantic RGB-D SLAM in Dynamic Environments

arXiv: https://arxiv.org/abs/2104.01316 · HTML: https://mlsanity.com/paper/2104.01316/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2021.

## Built on by (most cited first, 6 of 6)

- [BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking](https://mlsanity.com/paper/2205.02301/) (2022)
- [AirDOS: Dynamic SLAM benefits from Articulated Objects](https://mlsanity.com/paper/2109.09903/) (2021)
- [MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2309.11839/) (2023)
- [V3D-SLAM: Robust RGB-D SLAM in Dynamic Environments with 3D Semantic Geometry Voting](https://mlsanity.com/paper/2410.12068/) (2024)
- [NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU](https://mlsanity.com/paper/2405.07392/) (2024)
- [GeneA-SLAM2: Dynamic SLAM with AutoEncoder-Preprocessed Genetic Keypoints Resampling and Depth Variance-Guided Dynamic Region Removal](https://mlsanity.com/paper/2506.02736/) (2025)

## Abstract (arXiv)

Most of the existing visual SLAM methods heavily rely on a static world assumption and easily fail in dynamic environments. Some recent works eliminate the influence of dynamic objects by introducing deep learning-based semantic information to SLAM systems. However such methods suffer from high computational cost and cannot handle unknown objects. In this paper, we propose a real-time semantic RGB-D SLAM system for dynamic environments that is capable of detecting both known and unknown moving objects. To reduce the computational cost, we only perform semantic segmentation on keyframes to remove known dynamic objects, and maintain a static map for robust camera tracking. Furthermore, we propose an efficient geometry module to detect unknown moving objects by clustering the depth image into a few regions and identifying the dynamic regions via their reprojection errors. The proposed method is evaluated on public datasets and real-world conditions. To the best of our knowledge, it is one of the first semantic RGB-D SLAM systems that run in real-time on a low-power embedded platform and provide high localization accuracy in dynamic environments.