arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.15435cs.CVcs.GRcs.LG
收藏

功能扩散

Functional Diffusion

KAUST(阿卜杜拉国王科技大学)

Biao Zhang, Peter Wonka

摘要:

本文提出了一类新的生成扩散模型,称为功能扩散。与以前的工作相比,功能扩散的作品的样本表示的功能与连续域。泛函扩散可以看作是经典扩散模型到无限维域的扩展。功能扩散是非常通用的,因为图像,视频,音频,3D形状,变形,\etc,可以通过相同的框架进行最小的更改。此外,函数扩散特别适用于不规则数据或定义在非标准域中的数据。在我们的工作中,我们得到了必要的基础功能扩散,并提出了第一个实现的基础上的Transformer架构。我们生成的结果,复杂的签署距离函数和变形功能定义在3D表面上。

英文摘要:

We propose a new class of generative diffusion models, called functional diffusion. In contrast to previous work, functional diffusion works on samples that are represented by functions with a continuous domain. Functional diffusion can be seen as an extension of classical diffusion models to an infinite-dimensional domain. Functional diffusion is very versatile as images, videos, audio, 3D shapes, deformations, \etc, can be handled by the same framework with minimal changes. In addition, functional diffusion is especially suited for irregular data or data defined in non-standard domains. In our work, we derive the necessary foundations for functional diffusion and propose a first implementation based on the transformer architecture. We show generative results on complicated signed distance functions and deformation functions defined on 3D surfaces.

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。

↑