Predicting Human Dynamics

Jason Y. Zhang Panna Felsen Angjoo Kanazawa Jitendra Malik University of California, Berkeley In ICCV 2019 [Paper] [Video] Given a video of a person in action, we can easily guess the 3D future motion of the person. In this work, we present perhaps the first approach for predicting a future 3D mesh model sequence of a person from past video input. We do this for periodic motions such as walking and also actions like bowling and squatting seen in sports or workout videos. While there has been a surge of future prediction problems in computer vision, most approaches predict 3D future from 3D past or 2D future from 2D past inputs. In this work, we focus on the problem of predicting 3D future motion from past image sequences, which has a plethora of practical applications in autonomous systems that must operate safely around people from visual inputs. Inspired by the success of autoregressive models in language modeling tasks, we learn an intermediate latent space on which w...

5 mentions: @akanazawa@HCI_Research@roadrunning01@jasonyzhang2@d__strukt
Date: 2019/08/15 02:17

Referring Tweets

@akanazawa New work where we predict the future human 3D mesh motion from a short video! With @jasonyzhang2, Panna Felsen, Jitendra Malik. #ICCV2019
@HCI_Research Predicting 3D Human Dynamics from Video
@roadrunning01 Predicting 3D Human Dynamics from Video pdf: abs: project page:

Bookmark Comments

id:Nyoho Human pose estimation & sonogo prediction