Lune

CVPR2020

GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes

Enric Corona, Albert Pumarola, Guillem Alenyà, Francesc Moreno-Noguer, Grégory Rogez

DOI出版方

摘要

Figure 1: GanHand predicts hand shape and pose for grasping multiple objects given a single RGB image. The figure shows sample results on the YCB-Affordance dataset we propose, the largest dataset of human grasp affordances in real scenes.