GenMatter: Perceiving Physical Objects with Generative Matter Models

arXiv:2604.22160v1 Announce Type: cross Abstract: Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable chunks of matter, whether observing sparse moving dots, textured surfaces, or naturalistic scenes. In contrast, existing computer vision systems lack a unified approach that works across these diverse settings. Inspired by princip