通过统一的Sim(3)优化，解决长序列中视觉里程计漂移问题。
UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization
- 前端双视图轻量跟踪，后端周期性多视图子图优化
- 在TUM RGB-D上轨迹误差降低38.5%，7-Scenes上降45.9%
- 适合对精度和实时性有双重需求的移动机器人系统
近期的几何基础模型实现了SLAM的前馈推理，但其预测严重依赖输入视角集，导致在长序列中链式累积时产生几何不一致与轨迹漂移。在线部署还面临两视图追踪低延迟与多视图推理强约束之间的权衡。我们提出UniSim-SLAM，一个集成系统：前端运行轻量级双视图关键帧追踪，后端周期性执行多视图子图精化。为融合异构局部坐标系下、尺度不一致的预测结果，我们在Sim(3)上构建统一的多层次因子图，联合优化全局关键帧位姿与子图位姿。该图整合了时间视图间里程计边、带深度统计量尺度锚定的视图-子图桥接边，以及子图-子图间的匹配与尺度约束，以保持子图间的一致性相似关系。在TUM RGB-D与7-Scenes数据集上的实验表明，UniSim-SLAM在非标定设置下达到最新水平，相比先前最优结果，轨迹误差分别降低了38.5%和45.9%。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。