首页> 外国专利> Understanding and generating scenes using neural networks

Understanding and generating scenes using neural networks

机译:使用神经网络了解和生成场景

摘要

PROBLEM TO BE SOLVED: To provide a method, a system and an apparatus including a computer program encoded on a computer storage medium for rendering an image. In one aspect, the method is a step of receiving a plurality of observations that characterize a particular scene, each observation comprising an image of the particular scene and data identifying the location of the camera that captured the image. , Including steps. In another aspect, the method is the step of receiving multiple observations that characterize a particular video, where each observation contains video frames from a particular video and data that identifies the time stamps of the video frames in a particular video. Including, including steps. In yet another embodiment, the method comprises receiving multiple observations that characterize a particular image, each observation comprising cropping a particular image and data that characterizes the crop of a particular image. .. The method uses an observation neural network to process each of the multiple observations and determine the numerical representation as an output. [Selection diagram] Fig. 1
机译:要解决的问题:提供一种方法,系统和包括在计算机存储介质上编码的计算机程序的方法,用于呈现图像。在一个方面,该方法是接收特征特定场景的多个观察的步骤,每个观察包括特定场景的图像和识别捕获图像的相机的位置的数据。 ,包括步骤。在另一方面,该方法是接收特定视频特征的多个观察的步骤,其中每个观察包含来自特定视频的视频帧和数据识别特定视频中的视频帧的时间戳。包括包括步骤。在又一个实施例中,该方法包括接收特定图像的特征的多个观察,每个观察包括裁剪特定图像和表征特定图像的裁剪的数据。 ..该方法使用观察神经网络来处理多个观察中的每一个,并确定作为输出的数值表示。 [选择图]图1

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