鲁棒的文本驱动图像编辑方法：在StyleGAN和CLIP的潜在空间中自适应探索方向
Robust Text-driven Image Editing Method that Adaptively Explores Directions in Latent Spaces of StyleGAN and CLIP
AI总结：
提出一种基于SVM的方法，在StyleGAN和CLIP空间中自适应构建编辑方向，实现仅依赖图像和文本指令的鲁棒文本驱动图像编辑，性能与StyleCLIP基线相当且不增加计算时间。
摘要：
自动图像编辑因其众多应用而具有巨大需求，而使用自然语言指令对于实现用户想象中的灵活直观编辑至关重要。文本驱动图像编辑的先驱工作StyleCLIP在CLIP空间中寻找编辑方向，然后通过将该方向映射到StyleGAN空间来编辑图像。同时，除了原始图像和文本指令外，很难为图像编辑调整合适的输入。在本研究中，我们提出了一种使用SVM在StyleGAN和CLIP空间中自适应构建编辑方向的方法。我们的模型将编辑方向表示为CLIP空间中的法向量，该法向量是通过训练SVM对正负图像进行分类获得的。这些图像是根据图像与文本指令之间的CLIP相似度，从最初用于预训练StyleGAN的大规模图像语料库中检索出来的。我们确认我们的模型表现与StyleCLIP基线一样好，同时它允许简单的输入而不增加计算时间。
英文摘要：
Automatic image editing has great demands because of its numerous applications, and the use of natural language instructions is essential to achieving flexible and intuitive editing as the user imagines. A pioneering work in text-driven image editing, StyleCLIP, finds an edit direction in the CLIP space and then edits the image by mapping the direction to the StyleGAN space. At the same time, it is difficult to tune appropriate inputs other than the original image and text instructions for image editing. In this study, we propose a method to construct the edit direction adaptively in the StyleGAN and CLIP spaces with SVM. Our model represents the edit direction as a normal vector in the CLIP space obtained by training a SVM to classify positive and negative images. The images are retrieved from a large-scale image corpus, originally used for pre-training StyleGAN, according to the CLIP similarity between the images and the text instruction. We confirmed that our model performed as well as the StyleCLIP baseline, whereas it allows simple inputs without increasing the computational time.
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。
