GIST：通过多尺度几何表示实现照片级真实感风格迁移
GIST: Towards Photorealistic Style Transfer via Multiscale Geometric Representations
AI总结：
本文提出 GIST，利用多尺度几何表示与最优传输匹配内容和风格图像的 Wavelets、Contourlets 特征，在无需训练或后处理的情况下实现照片级风格迁移并显著减少处理时间。
摘要：
最先进的风格迁移方法通常利用为判别任务优化的预训练编码器，这可能并不适合图像合成，从而导致明显伪影和照片真实感丧失。受多尺度几何图像表示能够捕捉细粒度细节和全局结构的能力启发，我们提出了 GIST：Geometric-based Image Style Transfer（基于几何的图像风格迁移），这是一种利用内容图像与风格图像几何特性的新型风格迁移技术。GIST 用多尺度图像展开取代了标准的神经风格迁移自编码框架，无需后处理或训练即可保留场景细节。我们的方法通过求解最优传输问题来匹配 Wavelets 和 Contourlets 等多分辨率、多方向表示，从而实现高效的纹理迁移。实验表明，GIST 与近期照片级真实感风格迁移方法相当或更优，同时在无需模型训练的情况下显著缩短了处理时间。
英文摘要：
State-of-the-art Style Transfer methods often leverage pre-trained encoders optimized for discriminative tasks, which may not be ideal for image synthesis. This can result in significant artifacts and loss of photorealism. Motivated by the ability of multiscale geometric image representations to capture fine-grained details and global structure, we propose GIST: Geometric-based Image Style Transfer, a novel Style Transfer technique that exploits the geometric properties of content and style images. GIST replaces the standard Neural Style Transfer autoencoding framework with a multiscale image expansion, preserving scene details without the need for post-processing or training. Our method matches multiresolution and multidirectional representations such as Wavelets and Contourlets by solving an optimal transport problem, leading to an efficient texture transferring. Experiments show that GIST is on-par or outperforms recent photorealistic Style Transfer approaches while significantly reducing the processing time with no model training.
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。
