期刊
IET IMAGE PROCESSING
卷 -, 期 -, 页码 -出版社
WILEY
DOI: 10.1049/ipr2.12786
关键词
convolutional neural nets; data analysis; image restoration
This paper proposes a novel idea to tackle the problems of image person removal by data synthesis. Two dataset production methods are proposed to automatically generate images, masks, and ground truths. A learning framework similar to local image degradation is used to guide the feature extraction process and gather more texture information for final prediction. Experimental results demonstrate the effectiveness of the method and the trained network has good generalization ability.
As a special case of common object removal, image person removal is playing an increasingly important role in social media and criminal investigation domains. Due to the integrity of person area and the complexity of human posture, person removal has its own dilemmas. In this paper, a novel idea is proposed to tackle these problems from the perspective of data synthesis. Concerning the lack of a dedicated dataset for image person removal, two dataset production methods are proposed to automatically generate images, masks and ground truths, respectively. Then, a learning framework similar to local image degradation is proposed so that the masks can be used to guide the feature extraction process and more texture information can be gathered for final prediction. A coarse-to-fine training strategy is further applied to refine the details. The data synthesis and learning framework combine well with each other. Experimental results verify the effectiveness of the method quantitatively and qualitatively, and the trained network proves to have good generalization ability either on real or synthetic images.
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