English

Can We Change the Stroke Size for Easier Diffusion?

Computer Vision and Pattern Recognition 2026-04-29 v2 Artificial Intelligence

Abstract

Diffusion models can be challenged in the low signal-to-noise regime, where they have to make pixel-level predictions despite the presence of high noise. The geometric intuition is akin to using the finest stroke for oil painting throughout, which may be ineffective. We therefore study stroke-size control as a controlled intervention that changes the effective roughness of the supervised target, predictions and perturbations across timesteps, in an attempt to ease the low signal-to-noise challenge.

Keywords

Cite

@article{arxiv.2603.26783,
  title  = {Can We Change the Stroke Size for Easier Diffusion?},
  author = {Yunwei Bai and Ying Kiat Tan and Yao Shu and Tsuhan Chen},
  journal= {arXiv preprint arXiv:2603.26783},
  year   = {2026}
}
R2 v1 2026-07-01T11:41:30.197Z