基于VGGT的3D语义建图系统，支持长视频流下实时导航与辅助定位。
SceneVGGT: VGGT-based online 3D semantic SLAM for indoor scene understanding and navigation
- 采用滑动窗口架构结合VGGT追踪头，实现高效3D语义映射
- 在ScanNet++上达到竞争性点云性能，内存稳定低于17GB
- 适合需要实时语义理解的智能导盲、机器人导航等场景
我们提出SceneVGGT，一种时空3D场景理解框架，融合SLAM与语义地图以支持自主和辅助导航。基于VGGT，该方法通过滑动窗口管道实现对长视频流的扩展。利用相机位姿变换对齐局部子图，实现在保持几何一致性的同时降低内存与计算开销。通过VGGT跟踪头将2D实例掩码提升至3D物体，维持随时间一致的身份信息，用于变化检测。作为概念验证，物体位置投影至估计的地板平面以支持辅助导航。整个流水线的GPU内存使用始终低于17 GB，与输入序列长度无关，并在ScanNet++基准上取得竞争性点云性能。整体而言，SceneVGGT确保鲁棒的语义识别，且速度足够支持带语音反馈的交互式辅助导航。
原文摘要 · Abstract (English)
We present SceneVGGT, a spatio-temporal 3D scene understanding framework that combines SLAM with semantic mapping for autonomous and assistive navigation. Built on VGGT, our method scales to long video streams via a sliding-window pipeline. We align local submaps using camera-pose transformations, enabling memory- and speed-efficient mapping while preserving geometric consistency. Semantics are lifted from 2D instance masks to 3D objects using the VGGT tracking head, maintaining temporally coherent identities for change detection. As a proof of concept, object locations are projected onto an estimated floor plane for assistive navigation. The pipeline's GPU memory usage remains under 17 GB, irrespectively of the length of the input sequence and achieves competitive point-cloud performance on the ScanNet++ benchmark. Overall, SceneVGGT ensures robust semantic identification and is fast enough to support interactive assistive navigation with audio feedback.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。