Wang Peiyong, Xiao Bohan, He Qisheng, Glide-Hurst Carri, Dong Ming
Wayne State University, Detroit, USA.
University of Wisconsin - Madison, Madison, USA.
Proc ACM Int Conf Multimed. 2024 Oct-Nov;2024:10765-10773. doi: 10.1145/3664647.3680999. Epub 2024 Oct 28.
Image-to-image translation is defined as the process of learning a mapping between images from a source domain and images from a target domain. The probabilistic structure that maps a fixed initial state to a pinned terminal state through a standard Wiener process is a Brownian bridge. In this paper, we propose a score-based Stochastic Differential Equation (SDE) approach via the Brownian bridges, termed the Amenable Brownian Bridges (A-Bridges), to image-to-image translation tasks as an unconditional diffusion model. Our framework embraces a large family of Brownian bridge models, while the discretization of the linear A-Bridge exploits its advantage that provides the explicit solution in a closed form and thus facilitates the model training. Our model enables the accelerated sampling and has achieved record-breaking performance in sample quality and diversity on benchmark datasets following the guidance of its SDE structure.
图像到图像的翻译被定义为学习源域图像和目标域图像之间映射的过程。通过标准维纳过程将固定初始状态映射到固定终端状态的概率结构是布朗桥。在本文中，我们提出了一种基于分数的随机微分方程（SDE）方法，通过布朗桥，称为可处理布朗桥（A-Bridges），作为无条件扩散模型用于图像到图像的翻译任务。我们的框架包含了一大类布朗桥模型，而线性A-桥的离散化利用了其优势，即以封闭形式提供显式解，从而便于模型训练。我们的模型实现了加速采样，并在其SDE结构的指导下，在基准数据集上的样本质量和多样性方面取得了破纪录的性能。
