Learning 3D object-centric representation through prediction

arXiv:2403.03730v1 Announce Type: cross
Abstract: As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D environments without supervision, models that learn the same set of abilities with similar constraints faced by human infants are lacking. Towards this end, we developed a novel network architecture that simultaneously learns to 1) segment objects from discrete images, 2) …

3d object abstract arxiv block building concepts constraints core cs.ai cs.cv cs.lg environments human humans knowledge learn object objects part prediction reasoning representation set supervision symbolic reasoning through type