首页> 外国专利> Methods and systems for generating human 3D reconstructions

Methods and systems for generating human 3D reconstructions

机译:用于生成人3D重建的方法和系统

摘要

PROBLEM TO BE SOLVED: To provide a method and a system for generating a human 3D reconstruction. A method of generating a human three-dimensional (3D) reconstruction is provided. The method comprises obtaining at least one color image and a corresponding depth image of a scene containing a human object that is at least partially obstructed by one or more items. Areas within at least one color image corresponding to a human object are identified. The point cloud of the scene is generated based on at least one color image and the corresponding depth image. One or more parameters of the parametric model are then adjusted based on the area of the point cloud identified to correspond to the human object. The tuned parametric model is then used to generate a 3D reconstruction of the human object. The parametric model provides an estimate of the points in the point cloud that correspond to the obstructed part of the human object. A corresponding system is also provided. [Selection diagram] Fig. 2
机译:要解决的问题:提供一种用于生成人3D重建的方法和系统。提供了一种生成人三维(3D)重建的方法。该方法包括获得至少一个彩色图像和包含至少由一个或多个物品至少部分地阻挡的人体的场景的相应深度图像。鉴定了对应于人体对象的至少一个彩色图像内的区域。基于至少一个彩色图像和相应的深度图像生成场景的点云。然后基于所识别的点云的区域来调整参数模型的一个或多个参数,该参数模型调整为对应于人体对象。然后使用调谐的参数模型来生成人体对象的3D重建。参数模型提供了对应于人体对象的阻塞部分的点云中的点的估计。还提供了相应的系统。 [选择图]图2

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号