Language-Embedded Gaussian Splats (LEGS):使用移动机器人增量构建房间级表示
Language-Embedded Gaussian Splats (LEGS): Incrementally Building Room-Scale Representations with a Mobile Robot
AI总结:
提出LEGS地图系统,通过移动机器人在线训练增量构建统一外观与语义的3D场景表示,实现开放词汇物体查询定位,训练速度比LERF快3.5倍以上,查询准确率达66%。
摘要:
构建语义3D地图对于在办公室、仓库、商店和家中搜索感兴趣物体非常有价值。我们提出了一种地图构建系统,能够增量构建Language-Embedded Gaussian Splat (LEGS):一种在统一表示中编码外观和语义的详细3D场景表示。LEGS在机器人遍历环境时进行在线训练,以实现开放词汇物体查询的定位。我们在4个房间级场景上评估LEGS,查询场景中的物体以评估LEGS如何捕获语义含义。我们将LEGS与LERF进行比较,发现两个系统的物体查询成功率相当,但LEGS的训练速度比LERF快3.5倍以上。结果表明,多相机设置和增量束调整可以提高受限机器人轨迹下的视觉重建质量,并表明LEGS能够以高达66%的准确率定位开放词汇和长尾物体查询。
英文摘要:
Building semantic 3D maps is valuable for searching for objects of interest in offices, warehouses, stores, and homes. We present a mapping system that incrementally builds a Language-Embedded Gaussian Splat (LEGS): a detailed 3D scene representation that encodes both appearance and semantics in a unified representation. LEGS is trained online as a robot traverses its environment to enable localization of open-vocabulary object queries. We evaluate LEGS on 4 room-scale scenes where we query for objects in the scene to assess how LEGS can capture semantic meaning. We compare LEGS to LERF and find that while both systems have comparable object query success rates, LEGS trains over 3.5x faster than LERF. Results suggest that a multi-camera setup and incremental bundle adjustment can boost visual reconstruction quality in constrained robot trajectories, and suggest LEGS can localize open-vocabulary and long-tail object queries with up to 66% accuracy.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。