D2Styler：利用离散扩散方法推进任意风格迁移
D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods
AI总结：
本文提出 D²Styler 框架，结合 VQ-GAN 离散表示与离散扩散方法，并以 AdaIN 特征作为反向扩散引导，有效缓解任意风格迁移中的模式坍塌和风格化失衡问题，在多个指标上优于十二种现有方法。
摘要：
在图像处理中，最具挑战性的任务之一是使用各种艺术手法来呈现图像的语义含义。现有的任意风格迁移（AST）技术由于风格图像与内容图像之间的差异，经常出现模式坍塌、过度风格化或风格化不足的问题。我们提出了一种名为 D²Styler（Discrete Diffusion Styler，离散扩散风格化器）的新框架，该框架利用了 VQ-GAN 的离散表示能力以及离散扩散的优势，包括训练稳定和避免模式坍塌。我们的方法使用自适应实例归一化（AdaIN）特征作为反向扩散过程的上下文引导。这使得风格图像的特征能够无偏地迁移到内容图像中。所提出的方法显著提升了风格迁移图像的视觉质量，使内容与风格能够以视觉上吸引人的方式相结合。我们从 WikiArt 数据集中选取风格图像，从 COCO 数据集中选取内容图像。实验结果表明，D²Styler 生成了高质量的风格迁移图像，并在几乎所有指标上优于十二种现有方法。定性结果和消融研究进一步证明了我们技术的有效性。代码可在 https://github.com/Onkarsus13/D2Styler 获取。
英文摘要：
In image processing, one of the most challenging tasks is to render an image's semantic meaning using a variety of artistic approaches. Existing techniques for arbitrary style transfer (AST) frequently experience mode-collapse, over-stylization, or under-stylization due to a disparity between the style and content images. We propose a novel framework called D$^2$Styler (Discrete Diffusion Styler) that leverages the discrete representational capability of VQ-GANs and the advantages of discrete diffusion, including stable training and avoidance of mode collapse. Our method uses Adaptive Instance Normalization (AdaIN) features as a context guide for the reverse diffusion process. This makes it easy to move features from the style image to the content image without bias. The proposed method substantially enhances the visual quality of style-transferred images, allowing the combination of content and style in a visually appealing manner. We take style images from the WikiArt dataset and content images from the COCO dataset. Experimental results demonstrate that D$^2$Styler produces high-quality style-transferred images and outperforms twelve existing methods on nearly all the metrics. The qualitative results and ablation studies provide further insights into the efficacy of our technique. The code is available at https://github.com/Onkarsus13/D2Styler.
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。
