用多尺度几何特征实现逼真风格迁移，无需训练且速度快。
GIST: Towards Photorealistic Style Transfer via Multiscale Geometric Representations
- 基于图像几何结构的多尺度表示替代传统编码器
- 通过最优传输匹配纹理与结构，提升细节保真度
- 无需训练和后处理，适合实时应用
当前最先进的风格迁移方法常依赖为判别任务优化的预训练编码器，难以适应图像生成，易产生伪影并损失真实感。受多尺度几何表示捕捉细粒度细节与全局结构能力的启发，我们提出 GIST：一种基于几何的风格迁移方法，利用内容与风格图像的几何特性。GIST 将标准神经风格迁移的自编码框架替换为多尺度图像扩展机制，在无需后处理或模型训练的情况下保留场景细节。通过求解最优传输问题，匹配如小波、轮廓波等多分辨率、多方向表示，实现高效纹理迁移。实验表明，GIST 在性能上达到或超越近期逼真风格迁移方法，同时显著降低处理时间。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。