# ABot-Recon：重新审视局部上下文以实现长时流式 3D 重建

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-27 08:00
- AIHOT 分数：36
- AIHOT 链接：https://aihot.virxact.com/items/cmtgoiqdy04qjrochkqziip6m
- 原文链接：https://arxiv.org/abs/2608.27529

## AI 摘要

ABot-Recon 提出一种仅缓存前 11 帧 KV 特征的流式 3D 重建模型，通过保持学习时序状态严格局部化，使预测目标不随序列长度变化。该方法以当前相机坐标系下的点图和相邻帧相对位姿为预测对象，并借助轻量时序精化器与组合感知位姿损失抑制漂移。

## 正文

Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation. Early streaming models achieve causal, bounded-cost inference using finite context buffers or compact recurrent states, yet their estimates often deteriorate as sequences grow. Recent methods improve long-horizon stability by coupling short-range context with persistent or multi-level long-range memory. We pursue a different route: we keep the learned temporal state strictly local and formulate predictions whose targets remain independent of sequence length. We present ABot-Recon, a simple streaming model that caches KV features from only the preceding 11 frames. It predicts a point map in the current camera coordinate system together with an adjacent-frame relative pose. These predictions remain equivariant under changes of reference frame, and global poses and geometry are recovered through sequential composition. To reduce accumulated drift, a lightweight temporal refiner improves relative rotations using recent visual and motion context, while a composition-aware pose loss supervises multi-step pose composition. Extensive evaluations on challenging long-sequence benchmarks demonstrate the superior long-horizon performance of our local-context approach. On Oxford Spires, ABot-Recon achieves an ATE of 4.35 m and an RPE-R of 0.12^circ, reducing both errors by approximately 40% relative to the best prior results.