With the rapid development of deep neural networks in computer vision, style transfer technology has also made significant progress. Cycle-GAN can perform object deformation, style transfer, and image enhancement without one-to-one mapping between source and target domains. In the painting style transfer task, the performance of Cycle-GAN is recognized. In Cycle-GAN, the choice of generator model is crucial, and common backbones are ResNet and U-Net. The ResNet generator retains part of the original features through the jump connection of the residual structure, preventing the image from losing important information, and has the potential to maintain the authenticity of the image. The U-Net generator extracts more features and details through a complex and in-depth network architecture, which has excellent potential for tasks requiring a lot of feature extraction. However, few studies have directly compared their performance differences in the context of Cycle-GAN style transfer tasks. This paper compares and analyzes the effects of U-Net and ResNet generators in Cycle-GAN style transfer from different perspectives. The author discusses their respective advantages and limitations in training processes and the quality of generated images. The author presents quantitative and qualitative analyses based on experimental results, providing references and insights for researchers and practitioners in different scenarios. The research findings indicate that in the artwork style transfer task of Cycle-GAN, the U-Net generator tends to generate excessive details and texture, leading to overly complex transformed images. In contrast, the ResNet generator demonstrates superior performance, generating desired images faster, higher quality, and more natural results.

中文翻译：

---

基于不同生成器的 Cycle-GAN 中艺术风格迁移的比较

随着深度神经网络在计算机视觉领域的快速发展，风格迁移技术也取得了重大进展。 Cycle-GAN 可以执行对象变形、风格迁移和图像增强，而无需源域和目标域之间的一对一映射。在绘画风格迁移任务中，Cycle-GAN的表现得到认可。在Cycle-GAN中，生成器模型的选择至关重要，常见的backbone是ResNet和U-Net。 ResNet生成器通过残差结构的跳跃连接保留了部分原始特征，防止图像丢失重要信息，并且具有保持图像真实性的潜力。 U-Net生成器通过复杂而深入的网络架构提取更多的特征和细节，对于需要大量特征提取的任务具有极好的潜力。然而，很少有研究直接比较它们在 Cycle-GAN 风格传输任务中的性能差异。本文从不同角度比较分析了 U-Net 和 ResNet 生成器在 Cycle-GAN 风格迁移中的效果。作者讨论了它们各自在训练过程和生成图像质量方面的优点和局限性。作者根据实验结果进行了定量和定性分析，为不同场景下的研究者和实践者提供参考和见解。研究结果表明，在 Cycle-GAN 的艺术风格迁移任务中，U-Net 生成器往往会生成过多的细节和纹理，导致变换后的图像过于复杂。相比之下，ResNet 生成器表现出卓越的性能，可以更快地生成所需的图像、更高的质量和更自然的结果。