流式三维重建需在在线处理不断扩展的场景时，保留每一帧的证据。空间记忆通过按重建后的三维位置组织历史信息，成为一种自然的选择。然而，Point3R 利用空间邻近性既将新观测与现有记忆条目关联，又决定是否进行融合，从而混淆了共位性与状态身份。由于指针是对图像块的摘要，邻近的指针可能编码不同的表面、视角或可见性条件；在后续帧消除歧义之前对它们进行平均可能会破坏互补证据。我们认为，位置应决定地址，而非决定观测是否必须合并。Slot3R 实现了这一原则，作为一种免训练的组相联改造方案，允许多个状态在共享地址下共存，同时保持预训练的 Point3R 主干网络冻结。有界稀疏读出机制进一步解耦了持久存储与每帧解码器访问。在采样 300-500 帧的情况下，Slot3R 在 7Scenes 数据集上将 Point3R 的点云精度误差（Acc）降低了 57.1%-63.1%，在 NeuralRGBD 数据集上降低了 64.0%-72.0%；在所有三个姿态基准测试中降低了 Sim(3) 对齐的绝对轨迹误差（ATE），并在视频深度估计任务中保持竞争力。在相同协议下，它能在约 19 FPS 的速度下完成从 600 到 1000 采样帧的所有评估设置，而 Point3R 和 InfiniteVGGT 在 800 帧及以上时会因内存不足而失败。

Streaming 3D reconstruction must preserve evidence from each frame while processing an expanding scene online. Spatial memory is a natural fit because it organizes history by reconstructed 3D location. Yet Point3R uses spatial proximity both to associate a new observation with an existing memory entry and to decide whether to fuse it, conflating co-location with state identity. Because pointers summarize image patches, nearby pointers may encode distinct surfaces, viewpoints, or visibility conditions; averaging them can destroy complementary evidence before later frames disambiguate it. We argue that location should determine address, not whether observations must merge. Slot3R realizes this principle as a training-free, set-associative retrofit that lets multiple states coexist at a shared address while keeping the pretrained Point3R backbone frozen. A bounded sparse readout further decouples persistent storage from per-frame decoder access. At 300-500 sampled frames, Slot3R reduces Point3R's point-cloud accuracy error (Acc) by 57.1%-63.1% on 7Scenes and 64.0%-72.0% on NeuralRGBD, lowers Sim(3)-aligned absolute trajectory error (ATE) on all three pose benchmarks, and remains competitive on video-depth estimation. It completes all evaluated settings from 600 to 1000 sampled frames at about 19 FPS under the same protocol, whereas Point3R and InfiniteVGGT run out of memory at 800 frames and beyond.