We address the problem of generating realistic 3D motions of humans interacting with objects in a scene. Our key idea is to create a neural interaction field attached to a specific object, which outputs the distance to the valid interaction manifold given a human pose as input. This interaction field guides the sampling of an object-conditioned human motion diffusion model, so as to encourage plausible contacts and affordance semantics. To support interactions with scarcely available data, we propose an automated synthetic data pipeline. For this, we seed a pre-trained motion model, which has priors for the basics of human movement, with interaction-specific anchor poses extracted from limited motion capture data. Using our guided diffusion model trained on generated synthetic data, we synthesize realistic motions for sitting and lifting with several objects, outperforming alternative approaches in terms of motion quality and successful action completion. We call our framework NIFTY: Neural Interaction Fields for Trajectory sYnthesis.
@article{arxiv.2307.07511,
title = {NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis},
author = {Nilesh Kulkarni and Davis Rempe and Kyle Genova and Abhijit Kundu and Justin Johnson and David Fouhey and Leonidas Guibas},
journal= {arXiv preprint arXiv:2307.07511},
year = {2023}
}
Comments
Project Page with additional results available https://nileshkulkarni.github.io/nifty