Computer Graphics Forum (Proceedings of Eurographics), 2019

Learning a Generative Model for Multi-Step
Human-Object Interactions from Videos

He Wang1       Sören Pirk1       Ersin Yumer2       Vladimir G. Kim3       Ozan Sener4       Srinath Sridhar1       Leonidas J. Guibas1

1Stanford University       2 Uber ATG       3Adobe Research       4Intel Labs





Abstract

Creating dynamic virtual environments consisting of humans interacting with objects is a fundamental problem in computer graphics. While it is well-accepted that agent interactions play an essential role in synthesizing such scenes, most extant techniques exclusively focus on static scenes, leaving the dynamic component out. In this paper, we present a generative model to synthesize plausible multi-step dynamic human-object interactions. Generating multi-step interactions is challenging since the space of such interactions is exponential in the number of objects, activities, and time steps. We propose to handle this combinatorial complexity by learning a lower dimensional space of plausible human-object interactions. We use action plots to represent interactions as a sequence of discrete actions along with the participating objects and their states. To build action plots, we present an automatic method that uses state-of-the-art computer vision techniques on RGB videos in order to detect individual objects and their states, extract the involved hands, and recognize the actions performed. The action plots are built from observing videos of everyday activities and are used to train a generative model based on a Recurrent Neural Network (RNN). The network learns the causal dependencies and constraints between individual actions and can be used to generate novel and diverse multi-step human-object interactions. Our representation and generative model allows new capabilities in a variety of applications such as interaction prediction, animation synthesis, and motion planning for a real robotic agent.


Video



Paper

PDF
 

Bibtex

to appear