使用 Gaussian Splatting 并结合渲染引导致密化与正则化优化的高保真 SLAM
High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization
AI总结：
提出基于 3D Gaussian Splatting 的稠密 RGBD SLAM，通过渲染引导致密化和正则化优化实现精确跟踪与高保真重建，在 Replica 和 TUM 上表现优异。
摘要：
我们提出一种基于 3D Gaussian Splatting 的稠密 RGBD SLAM 系统，可提供度量精确的位姿跟踪和视觉真实的重建。为此，我们首先提出一种基于渲染损失的 Gaussian 致密化策略，用于映射未观测区域并细化重新观测的区域。其次，我们引入额外的正则化参数，以缓解连续建图问题中的遗忘问题；在该问题中，参数往往会过拟合最新帧，导致先前帧的渲染质量下降。建图和跟踪均通过以可微方式最小化重渲染损失，利用 Gaussian 参数完成。与近期的神经方法以及同期开发的 Gaussian Splatting RGBD SLAM 基线相比，我们的方法在合成数据集 Replica 上取得了最先进结果，并在真实世界数据集 TUM 上取得了具有竞争力的结果。
英文摘要：
We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction. To this end, we first propose a Gaussian densification strategy based on the rendering loss to map unobserved areas and refine reobserved areas. Second, we introduce extra regularization parameters to alleviate the forgetting problem in the continuous mapping problem, where parameters tend to overfit the latest frame and result in decreasing rendering quality for previous frames. Both mapping and tracking are performed with Gaussian parameters by minimizing re-rendering loss in a differentiable way. Compared to recent neural and concurrently developed gaussian splatting RGBD SLAM baselines, our method achieves state-of-the-art results on the synthetic dataset Replica and competitive results on the real-world dataset TUM.
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。
