StyleGAN-based CLIP-guided Image Shape Manipulation

StyleGAN-based CLIP-guided Image Shape Manipulation
复制标题

DOI:
10.1145/3549555.3549556
复制
发表时间:
2022-09
期刊:
Proceedings of the 19th International Conference on Content-based Multimedia Indexing
影响因子:
--
通讯作者:
Yuchen Qian;Kohei Yamamoto;Keiji Yanai
Yuchen Qian;Kohei Yamamoto;Keiji Yanai
中科院分区:
其他
文献类型:
--
作者:
Yuchen Qian;Kohei Yamamoto;Keiji Yanai

文献摘要

相似文献

在本文中,我们提出了一个文本引导的图像处理方法,重点是编辑形状属性使用文本描述。我们联合收割机了图像生成模型StyleGAN 2和图像-文本匹配模型CLIP,通过修改预训练的StyleGAN 2生成器的参数,我们实现了图像形状属性操作的目标。定性和定量的评价进行证明所提出的方法的有效性。
In this paper, we propose a text-guided image manipulation method which focuses on editing shape attribute using text description. We combine an image generation model, StyleGAN2, and image-text matching model, CLIP, and we have achieved the goal of image shape attribute manipulation by modifying the parameters of the pretrained StyleGAN2 generator. Qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of the proposed method.