GSORB-SLAM: 融合ORB特征与透射率信息的高斯溅射SLAM
GSORB-SLAM: Gaussian Splatting SLAM benefits from ORB features and Transmittance information
AI总结：
针对现有3DGS稠密SLAM方法的伪影噪声敏感、视角选择欠佳等问题，提出GSORB-SLAM框架，通过紧耦合ORB特征与3DGS，结合新型跟踪优化、自适应高斯扩展及混合图视角选择，在跟踪精度和重建质量上均实现性能突破。
摘要：
3D高斯溅射（3DGS）的出现近期在稠密视觉SLAM领域掀起了新的研究浪潮。然而现有方法面临挑战，包括对伪影和噪声敏感、训练视角选择欠佳以及缺乏全局优化。本文提出GSORB-SLAM，一种通过紧耦合优化管线集成3DGS与ORB特征的稠密SLAM框架。为减轻噪声和伪影影响，我们提出一种用于跟踪的新型几何表示和优化方法，显著提升了定位精度和鲁棒性。为实现高保真建图，我们开发了自适应高斯扩展和正则化方法，在抑制冗余基元的同时促进紧凑且富有表现力的场景建模。此外，我们设计了混合图基视角选择机制，有效减少过拟合并加速收敛。在各类数据集上的广泛评估表明，我们的系统在跟踪精度（相比ORB-SLAM2基线RMSE提升16.2%）和重建质量（相比3DGS-SLAM基线PSNR提升3.93 dB）方面均达到最先进性能。项目地址：https://aczheng-cai.github.io/gsorb-slam.github.io/
英文摘要：
The emergence of 3D Gaussian Splatting (3DGS) has recently ignited a renewed wave of research in dense visual SLAM. However, existing approaches encounter challenges, including sensitivity to artifacts and noise, suboptimal selection of training viewpoints, and the absence of global optimization. In this paper, we propose GSORB-SLAM, a dense SLAM framework that integrates 3DGS with ORB features through a tightly coupled optimization pipeline. To mitigate the effects of noise and artifacts, we propose a novel geometric representation and optimization method for tracking, which significantly enhances localization accuracy and robustness. For high-fidelity mapping, we develop an adaptive Gaussian expansion and regularization method that facilitates compact yet expressive scene modeling while suppressing redundant primitives. Furthermore, we design a hybrid graph-based viewpoint selection mechanism that effectively reduces overfitting and accelerates convergence. Extensive evaluations across various datasets demonstrate that our system achieves state-of-the-art performance in both tracking precision-improving RMSE by 16.2% compared to ORB-SLAM2 baselines-and reconstruction quality-improving PSNR by 3.93 dB compared to 3DGS-SLAM baselines. The project: https://aczheng-cai.github.io/gsorb-slam.github.io/
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。
