研究人员开发了REACH-Net，一个新颖的3D手部姿态估计系统，能够从房间角落的固定摄像头准确追踪手部形状和姿态。该系统通过利用手部-身体协调和时间进展，设计用于处理极低分辨率和遮挡的视图。为了训练和评估REACH-Net，创建了一个名为REACH的大型新数据集，包含50名参与者进行日常活动的数据，手部数据通过隐藏的胸部摄像头捕获。 AI
影响 在具有挑战性的现实环境中，能够实现更鲁棒的3D手部追踪，用于人类行为分析等应用。
排序理由 该集群包含一篇研究论文，详细介绍了一个用于特定计算机视觉任务的新模型和数据集。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2605.22231v1 Announce Type: new Abstract: We introduce a novel 3D hand pose estimator that can accurately recover the shape and pose of people's hands in a room from afar, typically from fixed cameras at room corners, in extremely low-resolution and frequently occluded view…
We introduce a novel 3D hand pose estimator that can accurately recover the shape and pose of people's hands in a room from afar, typically from fixed cameras at room corners, in extremely low-resolution and frequently occluded views. Our key idea is to fully leverage hand-body c…