SCOUT-SLAM：野外环境下结构耦合的双不确定性感知3DGS SLAM
SCOUT-SLAM: Structurally-Coupled Dual Uncertainty-Aware 3DGS SLAM in the Wild
查看机构详情
- Indian Institute of Science（印度科学理工学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
SCOUT-SLAM提出结构耦合双不确定性框架，通过共享网络和低秩适应估计跟踪不确定性，打破跟踪与重建的循环依赖，在动态基准上实现最先进跟踪精度与无伪影静态重建。
中文摘要 AI 辅助
近年来，3D高斯泼溅SLAM（3DGS-SLAM）在同时定位与3DGS场景重建方面获得了显著的发展势头。在相机快速运动且动态环境杂乱的现实场景中，现有方法依赖底层场景重建的稳定性来建模不确定性。这导致相机跟踪精度与重建质量之间存在循环依赖：重建的不稳定性会降低不确定性建模的质量，进而影响精确的相机跟踪和静态场景重建。为解决这一问题，本文提出了SCOUT-SLAM，一种结构耦合的双不确定性框架，其中两种不确定性均由一个共享的基础网络估计。该网络的低秩适应版本，基于多视图特征一致性进行训练，估计出一种不完全依赖重建质量的跟踪不确定性。一种空间自适应先验调节网络的训练目标，使得重建不稳定性不会在静态区域上夸大不确定性，从而保持两个分支共享表示的完整性。在动态基准（TUM RGB-D、Bonn Dynamic、Wild-SLAM MoCap）上的评估表明，SCOUT-SLAM实现了最先进的相机跟踪精度和无伪影的静态场景重建。
英文摘要
Recently, 3D Gaussian Splatting SLAM (3DGS-SLAM) has gained significant momentum in simultaneous localization and 3DGS scene reconstruction. In real-world scenarios with rapid camera motion and cluttered dynamic environments, existing methods rely on the stability of the underlying scene reconstruction to model uncertainty. This leads to a circular dependency between camera tracking accuracy and reconstruction quality: reconstruction instabilities degrade uncertainty modeling, which affects accurate camera tracking and static scene reconstruction. To address this, the paper proposes SCOUT-SLAM, a structurally-coupled dual-uncertainty framework in which both uncertainties are estimated from a shared base network. A low-rank adaptation of this network, trained on multi-view feature consistency, estimates a tracking uncertainty that does not depend solely on the reconstruction quality. A spatially-adaptive prior modulates the network's training objective so that reconstruction instability does not inflate uncertainty on static regions, keeping the shared representation intact for both branches. Evaluations on dynamic benchmarks (TUM RGB-D, Bonn Dynamic, Wild-SLAM MoCap) demonstrate that SCOUT-SLAM achieves state-of-the-art camera tracking accuracy and artifact-free static scene reconstruction.
