Can We Change the Stroke Size for Easier Diffusion?
cs.CV, cs.AI
Submitted: 2026-03-25
Updated: 2026-09-05
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
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 roughness of the supervised target, predictions and perturbations across timesteps, in an attempt to ease the low signal-to-noise challenge via prediction target simplification.
Sources
- Elucidating the Design Space of Diffusion-Based Generative Models
- Denoising Task Difficulty-based Curriculum for Training Diffusion Models
- A Note on the Inception Score
- Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
- Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
- Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis
- Classifier-Free Diffusion Guidance
- Image Super-Resolution via Iterative Refinement
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models