Unsupervised Dynamics Prediction with Object-Centric Kinematics

arXiv:2404.18423v1 Announce Type: new
Abstract: Human perception involves discerning complex multi-object scenes into time-static object appearance (\ie, size, shape, color) and time-varying object motion (\ie, location, velocity, acceleration). This innate ability to unconsciously understand the environment is the motivation behind the success of dynamics modeling. Object-centric representations have emerged as a promising tool for dynamics prediction, yet they primarily focus on the objects' appearance, often overlooking other crucial attributes. In this paper, we propose Object-Centric Kinematics (OCK), a framework for …

abstract arxiv color cs.ai cs.cv dynamics environment human location modeling motivation object perception prediction success the environment tool type unsupervised