期刊
2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
卷 -, 期 -, 页码 2433-2437出版社
IEEE
DOI: 10.1109/ICIP42928.2021.9506601
关键词
Text-guided image manipulation; generative adversarial network; semantic segmentation
类别
资金
- JSPS KAKENHI [JP17H01744]
This paper presents a novel approach to improve text-guided image manipulation performance by introducing foreground-aware and background-aware biases, addressing the issue of modifying undesired parts in images caused by differences in representation ability between text descriptions and images. By integrating an image segmentation network into the generative adversarial network for image manipulation, the effectiveness of the proposed method is demonstrated through comparative experiments with three state-of-the-art methods.
We propose a novel approach that improves text-guided image manipulation performance in this paper. Text-guided image manipulation aims at modifying some parts of an input image in accordance with the user's text description by semantically associating the regions of the image with the text description. We tackle the conventional methods' problem of modifying undesired parts caused by differences in representation ability between text descriptions and images. Humans tend to pay attention primarily to objects corresponding to the foreground of images, and text descriptions by humans mostly represent the foreground. Therefore, it is necessary to introduce not only a foreground-aware bias based on text descriptions but also a background-aware bias that the text descriptions do not represent. We introduce an image segmentation network into the generative adversarial network for image manipulation to solve the above problem. Comparative experiments with three state-of-the-art methods show the effectiveness of our method quantitatively and qualitatively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据