Modern Gaussian Splatting methods have proven highly effective for real-time photorealistic rendering of 3D scenes. However, integrating semantic information into this representation remains a significant challenge, especially in maintaining real-time performance for SLAM (Simultaneous Localization and Mapping) applications. In this work, we introduce LEG-SLAM -- a novel approach that fuses an optimized Gaussian Splatting implementation with visual-language feature extraction using DINOv2 followed by a learnable feature compressor based on Principal Component Analysis, while enabling an online dense SLAM. Our method simultaneously generates high-quality photorealistic images and semantically labeled scene maps, achieving real-time scene reconstruction with more than 10 fps on the Replica dataset and 18 fps on ScanNet. Experimental results show that our approach significantly outperforms state-of-the-art methods in reconstruction speed while achieving competitive rendering quality. The proposed system eliminates the need for prior data preparation such as camera's ego motion or pre-computed static semantic maps. With its potential applications in autonomous robotics, augmented reality, and other interactive domains, LEG-SLAM represents a significant step forward in real-time semantic 3D Gaussian-based SLAM. Project page:this https URL
View on arXiv@article{titkov2025_2506.03073,
title={ LEG-SLAM: Real-Time Language-Enhanced Gaussian Splatting for SLAM },
author={ Roman Titkov and Egor Zubkov and Dmitry Yudin and Jaafar Mahmoud and Malik Mohrat and Gennady Sidorov },
journal={arXiv preprint arXiv:2506.03073},
year={ 2025 }
}