【摘要】We propose a novel end-to-end deep learning framework, the Joint Matting Network(JMNet), to automatically generate alpha mattes for human images.We utilize the intrinsic structures of the human body as seen in images by introducing a pose estimation module,which can provide both global structural guidance and a local attention focus for the matting task. Our network model includes a pose network, a trimap network, a matting network, and a shared encoder to extract features for the above three networks. We also append a trimap refinement module and utilize gradient loss to provide a sharper alpha matte. Extensive experiments have shown that our method outperforms state-of-theart human matting techniques; the shared encoder leads to better performance and lower memory costs.Our model can process real images downloaded from the Internet for use in composition applications.
【关键词】
《建筑知识》 2015-05-12
《中国医疗管理科学》 2015-05-12
《中国医疗管理科学》 2015-05-12
《中国医疗管理科学》 2015-05-12
《旅游世界》 2015-07-06
《重庆与世界》 2015-07-01
《重庆高教研究》 2015-06-26
《重庆高教研究》 2015-06-30
Copyright © 2013-2016 ZJHJ Corporation,All Rights Reserved
发表评论
登录后发表评论 (已发布 0条)点亮你的头像 秀出你的观点