Abstract
Given an arbitrary content and style image, arbitrary style transfer aims to render a new stylized image which preserves the content image's structure and possesses the style image's style. Existing arbitrary style transfer methods are based on either small models or pre-trained large-scale models. The small model-based methods fail to generate high-quality stylized images, bringing artifacts and disharmonious patterns. The pre-trained large-scale model-based methods can generate high-quality stylized images but struggle to preserve the content structure and cost long inference time. To this end, we propose a new framework, called SPAST, to generate high-quality stylized images with less inference time. Specifically, we design a novel Local-global Window Size Stylization Module (LGWSSM)tofuse style features into content features. Besides, we introduce a novel style prior loss, which can dig out the style priors from a pre-trained large-scale model into the SPAST and motivate the SPAST to generate high-quality stylized images with short inference this http URL conduct abundant experiments to verify that our proposed method can generate high-quality stylized images and less inference time compared with the SOTA arbitrary style transfer methods.
Abstract (translated)
给定任意的内容图像和风格图像，任意风格迁移的目标是生成一个新的风格化图像，该图保持内容图像的结构，并具备风格图像的特点。现有的任意风格迁移方法要么基于小模型，要么基于预训练的大规模模型。基于小模型的方法无法生成高质量的风格化图像，会产生伪影和不和谐的图案；而基于预训练大规模模型的方法虽然能够生成高质量的风格化图像，但难以保持内容结构，并且需要较长的时间进行推理。为此，我们提出了一种新的框架——SPAST（Style Prior Assisted Stylization Transfer），以更短的推理时间生成高质量的风格化图像。 具体来说，我们设计了一个新颖的局部-全局窗口大小风格化模块（LGWSSM）来融合风格特征和内容特征。此外，我们还引入了一种新的风格先验损失，可以从预训练的大规模模型中提取出风格先验，并激励SPAST在短时间内生成高质量的风格化图像。 我们进行了大量的实验以验证所提出的方法相较于现有的最先进的任意风格迁移方法能够生成更高质量的风格化图像和减少推理时间。
URL
https://arxiv.org/abs/2505.08695
