Predicting 3D Human Dynamics from Video

by   Jason Y. Zhang, et al.

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 we predict the future. This effectively facilitates autoregressive predictions when the input differs from the output domain. Our approach can be trained on video sequences obtained in-the-wild without 3D ground truth labels. The project website with videos can be found at


page 6

page 8

page 11

page 15

page 16

page 17

page 18

page 19


Learning 3D Human Dynamics from Video

From an image of a person in action, we can easily guess the 3D motion o...

Video (language) modeling: a baseline for generative models of natural videos

We propose a strong baseline model for unsupervised feature learning usi...

EgoTransfer: Transferring Motion Across Egocentric and Exocentric Domains using Deep Neural Networks

Mirror neurons have been observed in the primary motor cortex of primate...

When will you do what? - Anticipating Temporal Occurrences of Activities

Analyzing human actions in videos has gained increased attention recentl...

Customizing First Person Image Through Desired Actions

This paper studies a problem of inverse visual path planning: creating a...

Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks

Human motion prediction, which plays a key role in computer vision, gene...

Learning Motion Predictors for Smart Wheelchair using Autoregressive Sparse Gaussian Process

Constructing a smart wheelchair on a commercially available powered whee...

Please sign up or login with your details

Forgot password? Click here to reset