arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.00501cs.CVcs.AIcs.LG
收藏

使用最短路径扩散进行图像生成

Image generation with shortest path diffusion

MediaTek Research(联发科技研究院);Imperial College London(帝国理工学院);University of Edinburgh(爱丁堡大学)

Ayan Das, Stathi Fotiadis, Anil Batra, Farhang Nabiei, FengTing Liao, Sattar Vakili, Da-shan Shiu, Alberto Bernacchia

AI总结:

针对扩散模型中图像退化过程缺乏最优性依据的问题,本文提出在概率分布空间中用 Fisher 度量计算最短路径,并据此构建 SPD,实现无需调优的更优图像生成性能。

摘要:

得益于扩散模型(Diffusion Models)的引入,图像生成领域取得了显著进展;这类模型学习逐步逆转给定的图像退化过程。最近,一些研究在扩散模型中引入了替代的图像退化方式,并将重点放在模糊上。然而,这些研究纯粹是经验性的,目前仍不清楚退化图像的最优过程是什么。在本工作中,我们假设最优过程会使图像朝给定最终状态退化时所经过路径的长度最小化。我们提出用 Fisher 度量来衡量概率分布空间中的路径长度。我们根据该度量计算最短路径,并表明它对应的是图像锐化(而非模糊)与噪声去模糊的组合。尽管以往工作中的退化过程是任意选择的,我们的最短路径扩散(Shortest Path Diffusion,SPD)唯一地确定了退化的整个时空结构。我们表明,SPD 在无需任何超参数调优的情况下改进了强基线,并且优于以往所有基于图像模糊的扩散模型。此外,对最短路径的任何微小偏离都会导致性能下降,这表明 SPD 提供了退化图像的最优过程。我们的工作为近期研究中的观察结果提供了新的阐释,并为改进图像及其他类型数据上的扩散模型提供了一种新方法。

英文摘要:

The field of image generation has made significant progress thanks to the introduction of Diffusion Models, which learn to progressively reverse a given image corruption. Recently, a few studies introduced alternative ways of corrupting images in Diffusion Models, with an emphasis on blurring. However, these studies are purely empirical and it remains unclear what is the optimal procedure for corrupting an image. In this work, we hypothesize that the optimal procedure minimizes the length of the path taken when corrupting an image towards a given final state. We propose the Fisher metric for the path length, measured in the space of probability distributions. We compute the shortest path according to this metric, and we show that it corresponds to a combination of image sharpening, rather than blurring, and noise deblurring. While the corruption was chosen arbitrarily in previous work, our Shortest Path Diffusion (SPD) determines uniquely the entire spatiotemporal structure of the corruption. We show that SPD improves on strong baselines without any hyperparameter tuning, and outperforms all previous Diffusion Models based on image blurring. Furthermore, any small deviation from the shortest path leads to worse performance, suggesting that SPD provides the optimal procedure to corrupt images. Our work sheds new light on observations made in recent works and provides a new approach to improve diffusion models on images and other types of data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑