Skip navigation
Given a monocular video as input, #HOLD reconstructs 3D hand and object surfaces for every frame…
0:00 / 0:10

Given a monocular video as input, #HOLD reconstructs 3D hand and object surfaces for every frame…

Michael Black

@Michael_J_Black107K followers

Visit on X

21,613 views #HOLD

Given a monocular video as input, #HOLD reconstructs 3D hand and object surfaces for every frame without assuming a known object template. Our key insight is that interacting hands and objects provide complementary cues about each other's shape and pose. 1/4

Comments

Comments from the original post on X (Twitter)

No comments yet