提出概率框架下的偏移噪声，解决扩散模型生成过亮数据的缺陷。
A Probabilistic Formulation of Offset Noise in Diffusion Models
- 在前向与反向过程中引入可调均值的高斯噪声，实现更灵活的扩散过程。
- 实验显示在高维数据上显著改善亮度异常问题，优于传统方法。
- 适合关注扩散模型稳定性和生成质量优化的研究者。
扩散模型已成为机器学习中建模数据分布的核心工具。尽管取得成功，这些模型在生成极端亮度数据时仍存在局限，这在大规模实际应用中已有所体现。偏移噪声被提出作为经验性解决方案，但其理论基础尚不充分。本文提出一种新的扩散模型，在严格的概率框架下自然融入额外噪声。该方法同时修改前向与反向扩散过程，使输入可被扩散为具有任意均值结构的高斯分布。我们基于证据下界推导出损失函数，发现其结构与偏移噪声相似，且系数随时间变化。在可控合成数据集上的实验表明，所提模型有效缓解了亮度相关限制，在高维设置下性能优于传统方法。
原文摘要 · Abstract (English)
Diffusion models have become fundamental tools for modeling data distributions in machine learning. Despite their success, these models face challenges when generating data with extreme brightness values, as evidenced by limitations observed in practical large-scale diffusion models. Offset noise has been proposed as an empirical solution to this issue, yet its theoretical basis remains insufficiently explored. In this paper, we propose a novel diffusion model that naturally incorporates additional noise within a rigorous probabilistic framework. Our approach modifies both the forward and reverse diffusion processes, enabling inputs to be diffused into Gaussian distributions with arbitrary mean structures. We derive a loss function based on the evidence lower bound and show that the resulting objective is structurally analogous to that of offset noise, with time-dependent coefficients. Experiments on controlled synthetic datasets demonstrate that the proposed model mitigates brightness-related limitations and achieves improved performance over conventional methods, particularly in high-dimensional settings.
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。