NIFTY: Neural Object Interaction Fields for Guided Human Motion
  Synthesis

Nilesh Kulkarni; Davis Rempe; Kyle Genova; Abhijit Kundu; Justin Johnson; David Fouhey; Leonidas Guibas

返回文献探索

Paper · arXiv 2307.07511

NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis

Nilesh Kulkarni, Davis Rempe, Kyle Genova, Abhijit Kundu, Justin Johnson, David Fouhey, Leonidas Guibas

6 upvotesJuly 14, 2023arXiv 预印本

AI 摘要

A framework uses neural interaction fields and diffusion models to generate realistic 3D human motions interacting with objects using limited data.

neural interaction fieldinteraction manifoldhuman poseobject-conditioned human motion diffusion modelplausible contactsaffordance semanticssynthetic data pipelinepre-trained motion modelinteraction-specific anchor posesguided diffusion modelmotion qualitysuccessful action completion

Abstract

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.