Neural cellular automata grow a full-res image from purely local rules (cells2pixels.github.io)
Neural cellular automata are bio-inspired: identical cells run a learned local rule and self-organize into an image, with the regeneration tricks of living tissue. The catch was always resolution — compute scaled quadratically with the grid.
The EPFL/Google fix pairs a coarse NCA grid with a tiny implicit decoder that fills in arbitrary-resolution pixels. The demos are live and abusable: a few brush swipes, one commenter found, and the stabilized kitten dissolves completely.
Sign in to save