Towards Controllable and Photorealistic Region-wise Image Manipulation

doi:10.1145/3474085.3475206

	Towards Controllable and Photorealistic Region-wise Image Manipulation
	You, Ansheng 1; Zhou, Chenglin2 ; Zhang, Qixuan2 ; Xu, Lan2
	2021-10-17
会议录名称	MM 2021 - PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA
页码	535-543
DOI	10.1145/3474085.3475206
摘要	Adaptive and flexible image editing is a desirable function of modern generative models. In this work, we present a generative model with auto-encoder architecture for per-region style manipulation. We apply a code consistency loss to enforce an explicit disentanglement between content and style latent representations, making the content and style of generated samples consistent with their corresponding content and style references. The model is also constrained by a content alignment loss to ensure the foreground editing will not interfere background contents. As a result, given interested region masks provided by users, our model supports foreground region-wise style transfer. Specially, our model receives no extra annotations such as semantic labels except for self-supervision. Extensive experiments show the effectiveness of the proposed method and exhibit the flexibility of the proposed model for various applications, including region-wise style editing, latent space interpolation, cross-domain style transfer. © 2021 ACM.
会议录编者/会议主办者	ACM SIGMM
关键词	Codes (symbols) Auto encoders Code consistency Content alignment Controllable and photorealistic Encoder architecture Generative model Image editing Image manipulation Interested regions Photo realistic
会议名称	29th ACM International Conference on Multimedia, MM 2021
会议地点	Virtual, Online, China
会议日期	October 20, 2021 - October 24, 2021
URL	查看原文
收录类别	EI
语种	英语
出版者	Association for Computing Machinery, Inc
EI入藏号	20214711200255
EI主题词	Semantics
EI分类号	723.2 Data Processing and Image Processing
原始文献类型	Conference article (CA)
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/133549
专题	信息科学与技术学院_本科生信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_许岚组
通讯作者	Zhou, Chenglin
作者单位	1.Peking University, Beijing, China; 2.ShanghaiTech University, Shanghai, China
通讯作者单位	上海科技大学
推荐引用方式 GB/T 7714	You, Ansheng,Zhou, Chenglin,Zhang, Qixuan,et al. Towards Controllable and Photorealistic Region-wise Image Manipulation[C]//ACM SIGMM:Association for Computing Machinery, Inc,2021:535-543.