通过调整笔触大小，让扩散模型在高噪声下更容易生成图像。
Can We Change the Stroke Size for Easier Diffusion?
- 引入笔触大小控制，简化生成目标和预测过程
- 在低信噪比条件下显著提升生成质量
- 适合研究扩散模型优化与图像生成的开发者
扩散模型在低信噪比场景下面临挑战，需在高噪声干扰下进行像素级预测。这种情形类似于整幅油画始终使用最细笔触，可能效率低下。为此，本文研究了笔触大小控制作为可控干预手段，通过调节不同时间步的监督目标、预测结果和扰动的粗糙度，实现生成目标的简化，从而缓解低信噪比带来的困难。
原文摘要 · Abstract (English)
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 \emph{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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。