InfoStyler：用于艺术风格迁移的解耦信息瓶颈
InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer
AI总结：
提出 InfoStyler，通过信息瓶颈与跨域重构策略实现内容与风格特征的清晰解耦，有效平衡艺术风格迁移中的内容保持与风格丰富度。
摘要：
艺术风格迁移旨在将艺术品的风格迁移到照片上，同时保持其原有的整体内容。许多先前的工作专注于设计各种迁移模块，将风格统计信息迁移到内容图像中。尽管有效，但由于从一开始就忽略了内容特征和风格特征的清晰解耦，它们难以在内容保持和风格迁移之间取得平衡。为了解决这个问题，我们提出了一种新颖的信息解耦方法，名为 InfoStyler，从预训练的编码网络中捕获内容和风格表示的最小充分信息。InfoStyler 将解耦表示学习形式化为一个信息压缩问题，通过消除内容图像中的风格统计信息并移除风格图像中的内容结构来实现。此外，为了进一步促进解耦学习，通过重构内容域和风格域，提出了一种跨域 Information Bottleneck (IB) 学习策略。大量实验表明，我们的 InfoStyler 能够合成高质量的风格化图像，同时平衡内容结构的保持和风格模式的丰富度。
英文摘要：
Artistic style transfer aims to transfer the style of an artwork to a photograph while maintaining its original overall content. Many prior works focus on designing various transfer modules to transfer the style statistics to the content image. Although effective, ignoring the clear disentanglement of the content features and the style features from the first beginning, they have difficulty in balancing between content preservation and style transferring. To tackle this problem, we propose a novel information disentanglement method, named InfoStyler, to capture the minimal sufficient information for both content and style representations from the pre-trained encoding network. InfoStyler formulates the disentanglement representation learning as an information compression problem by eliminating style statistics from the content image and removing the content structure from the style image. Besides, to further facilitate disentanglement learning, a cross-domain Information Bottleneck (IB) learning strategy is proposed by reconstructing the content and style domains. Extensive experiments demonstrate that our InfoStyler can synthesize high-quality stylized images while balancing content structure preservation and style pattern richness.
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。
