首个支持无限长前端后端处理的SLAM Transformer，突破距离限制。
SLAMFormer-$\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing
- 用记忆条件构建灵活坐标系，替代固定首帧基准
- 在17公里超长轨迹上仍保持高精度定位与建图
- 适合需要无限扩展的自动驾驶与机器人导航场景
我们提出无限SLAM Transformer（SLAMFormer-∞），首个能够支持无显式距离限制的长距离前端与后端处理的几何Transformer。不同于依赖首帧锚定的范式，SLAMFormer-∞采用记忆条件定义灵活的坐标系与尺度，实现更强的结构约束能力。在此基础上，前端保持高效的局部计算，后端则全局一致地联合优化长程位姿与场景几何。实验表明，该方法在大规模数据集上轨迹估计与场景重建性能优于或接近现有最优水平。特别地，其可泛化至极长轨迹，在超过17km的序列中成功运行。
原文摘要 · Abstract (English)
We introduce the Infinite SLAM Transformer (SLAMFormer-$\infty$), the first geometric transformer capable of supporting both long-range frontend and backend processing without an explicit distance bound. Instead of relying on a first-frame-anchored formulation, SLAMFormer-$\infty$ employs memory conditions to define flexible coordinate systems and scales for input frames, enabling more expressive structural conditioning. Built upon this formulation, the frontend preserves efficient local computation, while the backend jointly optimizes long-range trajectories and scene geometry in a globally consistent manner. Experimental results demonstrate that SLAMFormer-$\infty$ achieves superior or highly competitive performance in both trajectory estimation and scene reconstruction across large-scale datasets. Notably, SLAMFormer-$\infty$ generalizes to extremely long trajectories, successfully operating on sequences exceeding $17\mathrm{km}$.
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。