SEGS-SLAM：结合外观嵌入的结构增强3D高斯泼溅SLAM
SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embedding
AI总结：
本文提出SEGS-SLAM，通过结构增强真实感建图框架利用结构化点云初始化3D高斯，并引入运动外观嵌入建模相机位姿变化，显著提升了SLAM的渲染质量与视觉一致性。
摘要：
3D高斯泼溅（3D-GS）近期彻底革新了同步定位与建图（SLAM）问题中的新视角合成。然而，大多数现有算法未能完全捕获底层结构，导致结构不一致。此外，它们难以应对外观的突变，导致视觉质量不一致。为解决这些问题，我们提出了SEGS-SLAM，一种结构增强的3D高斯泼溅SLAM，实现了高质量的真实感建图。我们的主要贡献有两方面。首先，我们提出了结构增强真实感建图（SEPM）框架，首次利用高度结构化的点云来初始化结构化3D高斯，从而显著提升了渲染质量。其次，我们提出了运动外观嵌入（AfME），使3D高斯能更好地建模不同相机位姿下的图像外观变化。在单目、双目和RGB-D数据集上的大量实验表明，SEGS-SLAM在真实感建图质量上显著优于最先进（SOTA）方法，例如在TUM RGB-D数据集的单目相机上，PSNR比MonoGS提升了19.86%。
英文摘要：
3D Gaussian splatting (3D-GS) has recently revolutionized novel view synthesis in the simultaneous localization and mapping (SLAM) problem. However, most existing algorithms fail to fully capture the underlying structure, resulting in structural inconsistency. Additionally, they struggle with abrupt appearance variations, leading to inconsistent visual quality. To address these problems, we propose SEGS-SLAM, a structure-enhanced 3D Gaussian Splatting SLAM, which achieves high-quality photorealistic mapping. Our main contributions are two-fold. First, we propose a structure-enhanced photorealistic mapping (SEPM) framework that, for the first time, leverages highly structured point cloud to initialize structured 3D Gaussians, leading to significant improvements in rendering quality. Second, we propose Appearance-from-Motion embedding (AfME), enabling 3D Gaussians to better model image appearance variations across different camera poses. Extensive experiments on monocular, stereo, and RGB-D datasets demonstrate that SEGS-SLAM significantly outperforms state-of-the-art (SOTA) methods in photorealistic mapping quality, e.g., an improvement of $19.86\%$ in PSNR over MonoGS on the TUM RGB-D dataset for monocular cameras. The project page is available at https://segs-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。
