[Paper Notes] [CVPR 2020] GanHand

最新推荐文章于 2024-08-14 23:17:29 发布

Anita_CZ

最新推荐文章于 2024-08-14 23:17:29 发布

阅读量309

点赞数

分类专栏：论文阅读笔记文章标签：计算机视觉人工智能

本文链接：https://blog.csdn.net/weixin_42441466/article/details/121423759

版权

GanHand论文介绍了如何从单个RGB图像预测多物体场景中的人类抓取可能性，生成展示与目标物体多个接触点的手部配置，同时避免与其他场景元素相交。该方法估计物体的3D形状/姿态，预测33类抓取类型，并通过MANO模型参数优化细化手部配置。

摘要由CSDN通过智能技术生成

Paper information

GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes
Paper
Code
Video

Given a single RGB image of a scene with an arbitrary number of objects, we aim to predict human grasp affordances,

i.e. predict multiple plausible solutions of how a human would grasp each one of the observed objects
This implies producing valid hand configurations showing several contact points with the target object but no intersection with other elements of the scene.

estimates the 3D shape/pose of the objects
predicts the best grasp type according to a taxonomy with 33 classes
refines the hand configuration given by the grasping class, through an optimization of the 51 parameters of the MANO model
YCB affordance dataset

¹ 33-class grasp taxonomy
² differentiable hand model
Affordance: opportunities of interaction in the scene

Notation	Meaning	Notes
$I$	image
$M$	model
$C$	grasp type	a coarse hand representation, within the 33-grasp taxonomy
$P$	hand pose
$V$	hand shape	set of vertices of hand mesh
$H$	={P, V}	51-DoF parameters of MANO model
$H_C$		representative hand configuration of class $C$
$T_{object}$

关注