Purposer: Putting Human Motion Generation in Context

arXiv:2404.12942v1 Announce Type: new
Abstract: We present a novel method to generate human motion to populate 3D indoor scenes. It can be controlled with various combinations of conditioning signals such as a path in a scene, target poses, past motions, and scenes represented as 3D point clouds. State-of-the-art methods are either models specialized to one single setting, require vast amounts of high-quality and diverse training data, or are unconditional models that do not integrate scene or other contextual information. As …

abstract art arxiv context cs.cv generate human novel path state type