GP-GAN: Towards Realistic High-Resolution Image Blending
Wu, Huikai1,2; Zheng, Shuai3; Zhang, Junge1,2; Huang, Kaiqi1,2
2019-10
会议名称ACM International Conference on Multimedia
页码2487–2495
会议日期21-25 October 2019
会议地点Nice, France
摘要

It is common but challenging to address high-resolution image blending in the automatic photo editing application. In this paper, we would like to focus on solving the problem of high-resolution image blending, where the composite images are provided. We propose a framework called Gaussian-Poisson Generative Adversarial Network (GP-GAN) to leverage the strengths of the classical gradient-based approach and Generative Adversarial Networks. To the best of our knowledge, it's the first work that explores the capability of GANs in high-resolution image blending task. Concretely, we propose Gaussian-Poisson Equation to formulate the high-resolution image blending problem, which is a joint optimization constrained by the gradient and color information. Inspired by the prior works, we obtain gradient information via applying gradient filters. To generate the color information, we propose a Blending GAN to learn the mapping between the composite images and the well-blended ones. Compared to the alternative methods, our approach can deliver high-resolution, realistic images with fewer bleedings and unpleasant artifacts. Experiments confirm that our approach achieves the state-of-the-art performance on Transient Attributes dataset. A user study on Amazon Mechanical Turk finds that the majority of workers are in favor of the proposed method. The source code is available in \urlhttps://github.com/wuhuikai/GP-GAN, and there's also an online demo in \urlhttp://wuhuikai.me/DeepJS.

七大方向——子方向分类图像视频处理与分析
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/38526
专题复杂系统认知与决策实验室_智能系统与工程
通讯作者Huang, Kaiqi
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.University of Oxford
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Wu, Huikai,Zheng, Shuai,Zhang, Junge,et al. GP-GAN: Towards Realistic High-Resolution Image Blending[C],2019:2487–2495.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
代表性论文1-武慧凯.pdf(8723KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wu, Huikai]的文章
[Zheng, Shuai]的文章
[Zhang, Junge]的文章
百度学术
百度学术中相似的文章
[Wu, Huikai]的文章
[Zheng, Shuai]的文章
[Zhang, Junge]的文章
必应学术
必应学术中相似的文章
[Wu, Huikai]的文章
[Zheng, Shuai]的文章
[Zhang, Junge]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 代表性论文1-武慧凯.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。