相关数据集
fhswf/COCO-WB133-Quaternion-Mapping-Dataset
WholeBody3D-to-AvatarPose数据集是一个合成数据集，旨在学习从3D全身姿势估计输出到以四元数表示的虚拟角色关节旋转的映射。其主要目标是训练能够将COCO WholeBody（133个关键点）3D关节坐标转换为物理上合理的虚拟角色姿势的模型，适用于实时动画、手语虚拟角色和具身代理。数据集包含无噪声的3D关节位置和精确的地面真实关节旋转，通过Blender合成生成。数据格式包括J
Hugging Face2026-01-20 更新180
Rendered Handpose Dataset Dataset
Rendered Handpose Dataset contains 41258 training and 2728 testing samples. Each sample provides: RGB image (320x320 pixels) Depth map (320x320 pixels) Segmentation masks (320x320 pixels) for the cl
paperswithcode.com130
eyelids_pupils_v1.zip
DLC model weights for eyelid and pupil estimation
DataCite Commons2022-03-28 更新70
Robotic Grasping Based on 6D Pose Estimation from Single View
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
DataCite Commons2025-04-27 更新160
Basic concept of the position estimation algorithm.
A. The strategy of the position estimation. To estimate the positions of body parts (shown as cross marks), the skeleton model of a rat (shown in red) is physically fitted into the 3D hull of a rat (s
NIAID Data Ecosystem90
