GenMatter is a generative hierarchical model that groups low-level motion and high-level features into particles and clusters representing independently moveable physical entities, validated across dot kinematograms, camouflaged objects, and RGB videos.
Object discovery from motion- guided tokens
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GenMatter: Perceiving Physical Objects with Generative Matter Models
GenMatter is a generative hierarchical model that groups low-level motion and high-level features into particles and clusters representing independently moveable physical entities, validated across dot kinematograms, camouflaged objects, and RGB videos.