StippleDiffusion is a late-stage denoising ControlNet on an optimal-transport point-set diffusion baseline that produces capacity-constrained stipples from arbitrary density maps, generalizes to unseen point budgets, and matches optimization baselines on Icons-50 while remaining end-to-end trainable
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
citing papers explorer
-
StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion
StippleDiffusion is a late-stage denoising ControlNet on an optimal-transport point-set diffusion baseline that produces capacity-constrained stipples from arbitrary density maps, generalizes to unseen point budgets, and matches optimization baselines on Icons-50 while remaining end-to-end trainable
-
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.