HyperGAN-CLIP：面向域自适应、图像合成与操纵的统一框架
HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation
AI总结：
本文提出HyperGAN-CLIP框架，通过超网络将CLIP空间集成到预训练StyleGAN中，实现域自适应、参考引导合成和文本引导操纵，无需文本特定训练数据即可完成风格迁移。
摘要：
生成对抗网络（GAN），尤其是StyleGAN及其变体，在生成高度逼真图像方面展现出卓越能力。尽管取得了成功，但在有限训练数据条件下，将这些模型适配到域自适应、参考引导合成和文本引导操纵等多种任务仍然具有挑战性。为此，在本研究中，我们提出了一种新颖框架，通过超网络将CLIP空间集成到预训练StyleGAN中，从而显著扩展其能力。这种集成允许StyleGAN动态适配由参考图像或文本描述定义的新域。此外，我们引入了一种CLIP引导的判别器，增强了生成图像与目标域之间的对齐，确保卓越的图像质量。我们的方法展现出前所未有的灵活性，无需特定文本训练数据即可实现文本引导图像操纵，并促进无缝风格迁移。全面的定性和定量评估证实了与现有方法相比，该框架具有鲁棒性和优越性能。
英文摘要：
Generative Adversarial Networks (GANs), particularly StyleGAN and its variants, have demonstrated remarkable capabilities in generating highly realistic images. Despite their success, adapting these models to diverse tasks such as domain adaptation, reference-guided synthesis, and text-guided manipulation with limited training data remains challenging. Towards this end, in this study, we present a novel framework that significantly extends the capabilities of a pre-trained StyleGAN by integrating CLIP space via hypernetworks. This integration allows dynamic adaptation of StyleGAN to new domains defined by reference images or textual descriptions. Additionally, we introduce a CLIP-guided discriminator that enhances the alignment between generated images and target domains, ensuring superior image quality. Our approach demonstrates unprecedented flexibility, enabling text-guided image manipulation without the need for text-specific training data and facilitating seamless style transfer. Comprehensive qualitative and quantitative evaluations confirm the robustness and superior performance of our framework compared to existing methods.
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。
