发表机构
National Institute of Science and Technology（国立科学技术研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
UniSim-SLAM是采用统一Sim(3)优化的前馈SLAM系统，通过前端两视图跟踪与后端多视图子图优化，在TUM RGB-D和7-Scenes数据集上实现了当前最佳未校准设置下的轨迹精度，误差显著降低。
AI 中文摘要
近期的几何基础模型能够实现SLAM的前馈推理，但其预测结果高度依赖输入视图集，当在长序列中链式使用这些结果时，会引发几何不一致和轨迹漂移问题。在线部署时还会面临两视图跟踪的低延迟与多视图推理的约束丰富性之间的权衡难题。本文提出UniSim-SLAM，这一集成系统在前端运行轻量级两视图关键帧跟踪，在后端定期执行多视图子图优化。为结合异构局部坐标系下定义且尺度不一致的预测结果，我们在Sim(3)上构建统一多级因子图，联合优化全局关键帧位姿与子图位姿。该图整合了时序视图间里程计边、带深度统计尺度锚定的视图-子图桥接边，以及子图间的关联与尺度约束，以确保各子图间的相似关系保持一致。在TUM RGB-D和7-Scenes数据集上的实验表明，UniSim-SLAM在校准未设置的情况下达到了当前最佳精度，与此前最优结果相比，TUM RGB-D上的轨迹误差降低了38.5%，7-Scenes上降低了45.9%。项目页面：this https URL
英文摘要
Recent geometric foundation models enable feed-forward inference for SLAM, but their predictions are strongly dependent on the input view set, which leads to geometric inconsistencies and trajectory drift when results are chained over long sequences. Online deployment further exposes a trade-off between the low latency of two-view tracking and the constraint richness of multi-view inference. We introduce UniSim-SLAM, an integrated system that runs lightweight two-view keyframe tracking in the frontend and performs periodic multi-view submap refinement in the backend. To combine predictions defined in heterogeneous local coordinates with inconsistent scales, we formulate a unified multi-level factor graph on $Sim(3)$ that jointly optimizes global keyframe poses and submap poses. The graph integrates temporal view-to-view odometry edges, view-to-submap bridge edges with depth-statistics scale anchoring, and submap-to-submap tie and scale constraints to enforce consistent similarity relations across submaps. Experiments on TUM RGB-D and 7-Scenes show that UniSim-SLAM achieves state-of-the-art accuracy in the uncalibrated setting, reducing trajectory error by $38.5\% $ on TUM RGB-D and $45.9\%$ on 7-Scenes compared to prior best results. Project page: https://vision3d-lab.github.io/unisim-slam/
CommentsAccepted at ECCV 2026. Project page: https://vision3d-lab.github.io/unisim-slam/
