AI 中文总结
该研究提出首个无显式距离约束的几何Transformer SLAMFormer-∞，通过内存条件实现灵活坐标系统，前端高效局部计算、后端全局联合优化，在大规模数据集的轨迹估计与场景重建中性能优异，可适配超17公里的长轨迹。
AI 中文摘要
我们提出了无限SLAM Transformer（SLAMFormer-∞），这是首个无需显式距离约束即可同时支持长程前端与后端处理的几何Transformer。SLAMFormer-∞未依赖首帧锚定的公式，而是采用内存条件定义输入帧的灵活坐标系与尺度，从而实现更具表达力的结构条件。基于该公式，前端保留高效的局部计算，后端则以全局一致的方式联合优化长程轨迹与场景几何。实验结果表明，SLAMFormer-∞在大规模数据集的轨迹估计与场景重建任务中均取得了更优或极具竞争力的性能，尤其能泛化到极长轨迹，成功在超过17公里的序列上运行。
英文摘要
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 $17\mathrm{km}$.
