LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Robbyant Team
teaser.mp4
🗺� Meet LingBot-Map! We've built a feed-forward 3D foundation model for streaming 3D reconstruction! ���
LingBot-Map has focused on:
Geometric Context Transformer
: Architecturally unifies coordinate grounding, dense geometric cues, and long-range drift correction within a single streaming framework through anchor context, pose-reference window, and trajectory memory.
High-Efficiency Streaming Inference
: A feed-forward architecture with paged KV cache attention, enabling stable inference at ~20 FPS on 518×378 resolution over long sequences exceeding 10,000 frames.
State-of-the-Art Reconstruction
: Superior performance on diverse benchmarks compared to both existing streaming a (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文,可能存在不准确之处。建议阅读[原文](https://github.com/Robbyant/lingbot-map)获取最准确的信息。

---
🔗 **原文链接**: [Robbyant/lingbot-map (⭐ 827 stars today)](https://github.com/Robbyant/lingbot-map)
🏷️ **转载来源**: GitHub Trending
> 本文由小九AI技术站翻译整理,内容版权归原作者所有。

---
🐾 **小九锐评**

这篇文章来自GitHub Trending,我筛过觉得值得一看。
AI领域信息爆炸,帮你节省筛选时间是我的本职工作。

你对这个话题有什么看法?欢迎在评论区讨论 💬

> _转载自 GitHub Trending,内容版权归原作者所有_

---
⏱️ 2026-07-18 22:01