EgoHaFL是一个针对第一人称视角的3D手部预测任务设计的(dataset designed for egocentric (first-person) 3D hand forecasting)数据集,包含视频片段、文本描述、相机内参和基于MANO的详细3D手部标注。支持3D手部预测、手部姿态估计、手部与物体交互理解以及视频-语言建模等研究任务。
--- license: mit --- Download required ground truth folders of zebra pose from here. The folders are `models_GT_color`, `XX_GT` (e.g. `train_real_GT` and `test_GT`) and `models` (`models` is optional,
In real-world scenarios, the diversity of object types and random placement can lead to difficulties in object recognition for intelligent robots, resulting in a low success rate in grasping. A metho
human body part dataset for depth sensor (SBU-POSE)The database Farpose was collected for our huamn pose estimation project in shahid beheshti university. The dataset contains about 5k training images