LEG-SLAM：面向SLAM的实时语言增强高斯泼溅
LEG-SLAM: Real-Time Language-Enhanced Gaussian Splatting for SLAM
AI总结：
LEG-SLAM将高斯泼溅与DINOv2视觉-语言特征及PCA压缩器融合，实现超过10 fps的实时语义稠密SLAM，无需先验数据准备，在重建速度上显著超越现有方法。
摘要：
现代高斯泼溅方法已被证明在三维场景的实时照片级真实感渲染中非常有效。然而，将语义信息整合到这种表示中仍然是一个重大挑战，尤其是在为SLAM（同时定位与建图）应用保持实时性能方面。在这项工作中，我们提出了LEG-SLAM——一种新颖的方法，它将优化的高斯泼溅实现与使用DINOv2的视觉-语言特征提取相融合，随后采用基于主成分分析的可学习特征压缩器，同时实现在线稠密SLAM。我们的方法同时生成高质量的照片级真实感图像和带有语义标签的场景地图，在Replica数据集上以超过10 fps的速度、在ScanNet上以18 fps的速度实现实时场景重建。实验结果表明，我们的方法在重建速度上显著优于最先进的方法，同时实现了具有竞争力的渲染质量。所提出的系统消除了对先验数据准备的需求，例如相机自身运动或预先计算的静态语义地图。凭借其在自主机器人、增强现实和其他交互领域的潜在应用，LEG-SLAM代表了基于实时语义三维高斯的SLAM的重要进步。项目页面：https://titrom025.github.io/LEG-SLAM/
英文摘要：
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: https://titrom025.github.io/LEG-SLAM/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
