阅读说明：本技术 从捕获的视频数据输出扭曲图像 (Outputting a warped image from captured video data ) 是由 安德烈·赫切巴琴科 弗朗西斯·云峰·葛 尹波 陈石 法比安·朗格特 约翰内斯·彼得·科普夫 于 2021-05-24 设计创作，主要内容包括：本申请涉及从捕获的视频数据输出扭曲图像。在一个实施例中,一种方法包括从捕获的图像序列生成输出的扭曲图像序列。使用该捕获的图像序列,计算系统可以为捕获的图像序列中的每个图像确定对象特征的一个或更多个三维位置和对应的摄像机位置。利用每个图像的摄像机位置,计算系统可以确定表示虚拟摄像机的视角的视图路径。计算系统可以识别位于视图路径上的虚拟摄像机的一个或更多个虚拟摄像机位置,并且随后从捕获图像序列扭曲一个或更多个图像,以表示虚拟摄像机在每个相应虚拟摄像机位置处的视角。这导致扭曲图像序列,该扭曲图像序列可以被输出以供在客户端设备上查看和交互。(The present application relates to outputting a warped image from captured video data. In one embodiment, a method includes generating an output warped image sequence from a captured image sequence. Using the captured sequence of images, the computing system may determine, for each image in the captured sequence of images, one or more three-dimensional locations of the object feature and a corresponding camera position. With the camera position for each image, the computing system may determine a view path representing the perspective of the virtual camera. The computing system may identify one or more virtual camera positions of the virtual camera that lie on the view path, and then warp one or more images from the sequence of captured images to represent the perspective of the virtual camera at each respective virtual camera position. This results in a sequence of warped images that can be output for viewing and interaction on the client device.)