KV-Tracker：基于 Transformer 的实时位姿跟踪
KV-Tracker: Real-Time Pose Tracking with Transformers
把多视图几何网络（π³）全局自注意力层的 KV 对缓存下来当作唯一的场景表示，从而免去逐帧重跑网络，实现实时 6-DoF 跟踪与在线重建；这种模型无关的 KV 缓存思路可直接迁移到其他多视图/前馈重建网络做在线化加速。
原文依据 cache the global self-attention block's key-value (KV) pairs and use them as the sole scene representation for online tracking
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多视图三维几何网络提供了强大的先验，但对实时应用而言速度过慢。我们提出一种将其适配于在线使用的新方法，能够从单目 RGB 视频中实现实时的 6-DoF 位姿跟踪以及对物体和场景的在线重建。我们的方法快速选取并管理一组图像作为关键帧，借助 π³ 与完整的双向注意力对场景或物体进行建图。随后我们缓存全局自注意力块的键值（KV）对，并将其作为在线跟踪唯一的场景表示。这使得推理阶段最高可获得 15 倍加速，且无需担心漂移或灾难性遗忘。我们的缓存策略与模型无关，无需重新训练即可应用于其他现成的多视图网络。我们在场景级跟踪以及更具挑战性的、无需深度测量或物体先验的即时物体跟踪与重建任务上展示了 KV-Tracker。在 TUM RGB-D、7-Scenes、Arctic 和 OnePose 数据集上的实验表明，本系统性能强劲，同时保持最高约 30 FPS 的高帧率。
英文原文摘要 1120 字符
Multi-view 3D geometry networks offer a powerful prior but are prohibitively slow for real-time applications. We propose a novel way to adapt them for online use, enabling real-time 6-DoF pose tracking and online reconstruction of objects and scenes from monocular RGB videos. Our method rapidly selects and manages a set of images as keyframes to map a scene or object via \pi^3 [??] with full bidirectional attention. We then cache the global self-attention block's key-value (KV) pairs and use them as the sole scene representation for online tracking. This allows for up to 15xspeedup during inference without the fear of drift or catastrophic forgetting. Our caching strategy is model-agnostic and can be applied to other off-the-shelf multi-view networks without retraining. We demonstrate KV-Tracker on both scene-level tracking and the more challenging task of on-the-fly object tracking and reconstruction without depth measurements or object priors. Experiments on the TUM RGB-D, 7-Scenes, Arctic and OnePose datasets show the strong performance of our system while maintaining high frame-rates up to ~ 30 FPS.