用神经网络分离前景背景，实现更自然的风格迁移。
Style Transfer: From Stitching to Neural Networks
- 用分割网络分离前景与背景，仅对背景做风格迁移。
- 相比传统拼贴法，保留了前景细节，且效率更高。
- 适合需要精细保留主体的图像处理场景。
本文对比了图像处理中的两种风格迁移方法：传统方法通过拼接现有图像的小块来合成新图像，擅长生成艺术化抽象效果但易出现拼接痕迹；现代基于机器学习的方法利用分割网络分离前景对象，仅对背景应用风格迁移。该方法在保持前景完整性的同时提升背景美感，兼具更好的视觉质量与计算效率。研究表明，机器学习方法更适合需保留前景细节的真实应用场景。
原文摘要 · Abstract (English)
This article compares two style transfer methods in image processing: the traditional method, which synthesizes new images by stitching together small patches from existing images, and a modern machine learning-based approach that uses a segmentation network to isolate foreground objects and apply style transfer solely to the background. The traditional method excels in creating artistic abstractions but can struggle with seamlessness, whereas the machine learning method preserves the integrity of foreground elements while enhancing the background, offering improved aesthetic quality and computational efficiency. Our study indicates that machine learning-based methods are more suited for real-world applications where detail preservation in foreground elements is essential.
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。