PulseAugur
实时 10:04:10
English(EN) AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation

新数据集助力AI手部检测和姿态估计

研究人员开发了新的数据集来改进手部检测和姿态估计,解决了现有真实世界数据的局限性。其中一个数据集是从Egohands数据集合成的,使用事件相机和RGB相机来克服运动模糊和低帧率问题。另一个数据集AnyHand提供了大规模的合成RGB-D图像集合,包含详细的3D手部姿态估计标注,涵盖了遮挡和手部与物体交互等情况。 AI

影响 这些数据集旨在提高AI模型在手部相关任务中的准确性和鲁棒性,可能为更复杂的人机交互和增强现实应用提供支持。

排序理由 该集群包含两篇介绍计算机视觉任务新数据集的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新数据集助力AI手部检测和姿态估计

报道来源 [3]

  1. arXiv cs.CV TIER_1 English(EN) · Bharghav Kota (Zurich University of Applied Sciences, W\"adenswil, Switzerland), Yulia Sandamirskaya (Zurich University of Applied Sciences, W\"adenswil, Switzerland) ·

    用于第一人称视角手部检测的多模态RGB和事件数据集

    arXiv:2606.10790v1 Announce Type: new Abstract: Existing hand detection algorithms work on images and the detection rate is restricted by the frame rate of the camera. In hand detection applications for moving robotic systems, conventional cameras cause motion blur, especially in…

  2. arXiv cs.CV TIER_1 English(EN) · Yulia Sandamirskaya ·

    用于第一人称视角手部检测的多模态RGB和事件数据集

    Existing hand detection algorithms work on images and the detection rate is restricted by the frame rate of the camera. In hand detection applications for moving robotic systems, conventional cameras cause motion blur, especially in darker lighting conditions. We can leverage the…

  3. arXiv cs.CV TIER_1 English(EN) · Chen Si, Yulin Liu, Bo Ai, Jianwen Xie, Rolandos Alexandros Potamias, Chuanxia Zheng, Hao Su ·

    AnyHand:用于 RGB(-D) 手部姿态估计的大规模合成数据集

    arXiv:2603.25726v3 Announce Type: replace Abstract: We present AnyHand, a large-scale synthetic dataset designed to advance the state of the art in 3D hand pose estimation. While recent works with foundation approaches have shown that scaling training data markedly improves hand …