ODGS-SLAM：全向高斯泼溅 SLAM
ODGS-SLAM: Omnidirectional Gaussian Splatting SLAM
把 3DGS-SLAM 的建图与相机位姿估计梯度扩展到等距柱状投影的全景输入，并给出闭式梯度推导；做全景/鱼眼多相机 SLAM 或想把 3DGS 表示用于大视场重建的人可以直接复用这套投影梯度与基于图分析的关键帧剔除策略。
原文依据 We extended existing 3DGS-SLAM methods to handle omnidirectional input by including closed-form gradients for mapping and camera pose estimation, utilizing an equirectangular projection model.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 ODGS-SLAM，一个以三维高斯泼溅（3DGS）作为跟踪与建图统一表示的全向同时定位与建图（SLAM）系统。因此，它通过泼溅从全景图像序列（RGB 或 RGBD）重建场景几何，同时估计相机位姿。这样的框架对于理解完整周围环境十分重要，例如用于增强现实应用或自主系统。我们扩展了现有的 3DGS-SLAM 方法以处理全向输入，采用等距柱状投影模型，为建图和相机位姿估计引入闭式梯度。为降低内存占用，提出了一种基于图分析的关键帧剔除流程，使该方法能够处理更大规模的输入。在评测方面，我们提供了一个包含受控真实世界与合成测试场景（室内与室外）的数据集，使用自行研制的虚拟相机镜头。大量评测表明，在相机跟踪方面，所提方法相比近期的一个全向 SLAM 系统以及其他 3DGS-SLAM 框架取得了统计显著更低的 ATE RMSE 分数，同时达到相近的建图性能。
英文原文摘要 1230 字符
This work presents ODGS-SLAM, an omnidirectional simultaneous localization and mapping (SLAM) system utilizing 3D Gaussian Splatting (3DGS) as the unified representation for tracking and mapping. Thus, it reconstructs scene geometry from panoramic image sequences (RGB or RGBD) via splats while also estimating the camera poses. Such a framework is important to understand the full surrounding, e.g., for augmented reality applications or autonomous systems. We extended existing 3DGS-SLAM methods to handle omnidirectional input by including closed-form gradients for mapping and camera pose estimation, utilizing an equirectangular projection model. To reduce memory footprint, a key frame removal procedure based on graph analysis is proposed, enabling the application to handle larger input sizes. For evaluation, we provide a dataset of controlled real-world and synthetic test scenes (indoor and outdoor), employing a custom developed virtual camera lens. An extensive evaluation shows that, for camera tracking, the proposed method achieves statistically significant lower ATE RMSE scores compared to a recent omnidirectional SLAM system, as well as other 3DGS-SLAM frameworks, while reaching a similar mapping performance.