GSFF-SLAM：基于特征场的3D语义高斯泼溅SLAM
GSFF-SLAM: 3D Semantic Gaussian Splatting SLAM via Feature Field
AI总结：
针对现有语义SLAM依赖2D真值先验、受真实环境中信号稀疏与噪声限制的问题，提出基于3D高斯泼溅的GSFF-SLAM系统，通过特征场实现多维度信息联合渲染与独立特征梯度优化，在跟踪、渲染及语义分割性能上表现更优且速度提升显著。
摘要：
具备语义感知能力的3D场景重建对自主机器人执行复杂交互至关重要。语义SLAM作为一种在线方法，将位姿跟踪、几何重建与语义建图整合到统一框架中，展现出巨大潜力。然而，现有系统依赖2D真值先验进行监督，在真实环境中往往受限于这些信号的稀疏性与噪声。为解决这一挑战，我们提出GSFF-SLAM，这是一种基于3D Gaussian Splatting（3D高斯泼溅）的新型稠密语义SLAM系统，利用特征场实现外观、几何与N维语义特征的联合渲染。通过独立优化特征梯度，我们的方法支持采用多种形式的2D先验进行语义重建，尤其是稀疏且含噪的信号。实验结果表明，我们的方法在跟踪精度与照片级真实感渲染质量上均优于此前的方法。在使用2D真值先验时，GSFF-SLAM取得了当前最优的语义分割性能，mIoU达95.03%，同时实现最高2.9倍的速度提升，且性能仅有轻微下降。
英文摘要：
Semantic-aware 3D scene reconstruction is essential for autonomous robots to perform complex interactions. Semantic SLAM, an online approach, integrates pose tracking, geometric reconstruction, and semantic mapping into a unified framework, shows significant potential. However, existing systems, which rely on 2D ground truth priors for supervision, are often limited by the sparsity and noise of these signals in real-world environments. To address this challenge, we propose GSFF-SLAM, a novel dense semantic SLAM system based on 3D Gaussian Splatting that leverages feature fields to achieve joint rendering of appearance, geometry, and N-dimensional semantic features. By independently optimizing feature gradients, our method supports semantic reconstruction using various forms of 2D priors, particularly sparse and noisy signals. Experimental results demonstrate that our approach outperforms previous methods in both tracking accuracy and photorealistic rendering quality. When utilizing 2D ground truth priors, GSFF-SLAM achieves state-of-the-art semantic segmentation performance with 95.03\% mIoU, while achieving up to 2.9$\times$ speedup with only marginal performance degradation.
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。
