Physical Property Understanding from Language-Embedded Feature Fields

arXiv:2404.04242v1 Announce Type: cross
Abstract: Can computers perceive the physical properties of objects solely through vision? Research in cognitive science and vision science has shown that humans excel at identifying materials and estimating their physical properties based purely on visual appearance. In this paper, we present a novel approach for dense prediction of the physical properties of objects using a collection of images. Inspired by how humans reason about physics through vision, we leverage large language models to propose candidate …

abstract arxiv cognitive cognitive science computers cs.ai cs.cl cs.cv cs.lg embedded excel feature fields humans language materials novel objects paper prediction property research science through type understanding vision visual