# 记住、重访、修正：用于长时程3D几何的支架记忆

> 原文链接：https://robotics.hellobike.com/papers/2026-10-14-2610-19674
> 频道：papers | 更新日期：2026-10-14 | 标签：arxiv, cs.RO
> 核心摘要：SMORE为冻结几何基础模型加入可修正外部记忆，并在五个数据集的多类3D几何任务上验证长序列推理改进。

# 记住、重访、修正：用于长时程3D几何的支架记忆

::: v-pre
> 原文链接：[Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry](https://arxiv.org/abs/2610.19674)（arXiv 2610.19674 · 发布日期：2026-10-14）

**Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry**

SMORE为冻结几何基础模型加入可修正外部记忆，并在五个数据集的多类3D几何任务上验证长序列推理改进。

## 核心要点

- 长序列几何重建中，窗口式模型会累积误差，流式模型难以回修早期估计。
- SMORE将观察者位置与观测内容关联，支持存储、检索、校验并修正过去观测。
- 在八个几何模型和五个数据集上，SMORE提升长序列位姿估计并降低多类误差。
- 结果包括多视图深度误差最高降58%、点云Chamfer距离最高降43%，SLAM轨迹误差低至2.9厘米。

**验证范围与局限**：验证范围为五个数据集上的相机位姿估计、多视图深度估计、3D点云重建、SLAM和新视角合成任务。

## 英文摘要 (Abstract)

Geometry foundation models estimate camera poses and 3D scene structure from video sequences, but maintaining consistent reconstructions over long horizons remains challenging. Feed-forward models process long sequences as independent, fixed-length frame windows and align their predictions, causing pose and reconstruction errors to accumulate across windows. Streaming models retain information from past frames to inform future predictions, but cannot revise earlier estimates when later observations reveal errors. To address this, we introduce Scaffold MemOry for Revision (SMORE), a framework equipping frozen geometry foundation models with a revisable external memory for long-horizon inference. Inspired by hippocampal associative memory in biological brains, which links spatial context with sensory experience, SMORE associates where an observer is with what it observes, enabling past observations to be stored, retrieved, verified against new evidence, and revised when inconsistencies are detected. We evaluate SMORE with eight competitive geometry models on five datasets spanning camera pose estimation, multi-view depth estimation, 3D point-cloud reconstruction, simultaneous localization and mapping (SLAM), and novel view synthesis. Across all evaluated models, SMORE consistently improves long-sequence pose estimation, reduces multi-view depth error by up to 58%, reduces Chamfer distance for 3D point-cloud reconstruction by up to 43%, and achieves average trajectory error as low as 2.9 cm in long-horizon SLAM. By retaining corrected poses and observations, SMORE further improves the fidelity and spatial consistency of large-scale 3D scene reconstruction. These results establish revisable external memory as a flexible interface for extending pretrained geometry models beyond fixed-context prediction toward iterative, error-correcting inference over long visual sequences.

作者：Soumick Sarker, Mengmi Zhang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.19674：Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry](https://arxiv.org/abs/2610.19674)