Depth map generation

摘要

Aspects of the disclosure relate generally to generating depth data from a video. As an example, one or more computing devices may receive an initialization request for a still image capture mode. After receiving the request to initialize the still image capture mode, the one or more computing devices may automatically begin to capture a video including a plurality of image frames. The one or more computing devices track features between a first image frame of the video and each of the other image frames of the video. Points corresponding to the tracked features may be generated by the one or more computing devices using a set of assumptions. The assumptions may include a first assumption that there is no rotation and a second assumption that there is no translation. The one or more computing devices then generate a depth map based at least in part on the points.

主权项

1. A computer-implemented method comprising:
receiving, by one or more computing devices, an initialization request for a still image capture mode; after receiving the request to initialize the still image capture mode, automatically beginning, by the one or more computing devices, to capture a video including a plurality of image frames; tracking, by the one or more computing devices, features between a first image frame of the video and each of the other image frames of the video; generating, by the one or more computing devices, a set of 3D points corresponding to the tracked features using a set of assumptions, the set of assumptions including a first assumption that there is no rotation between the plurality of image frames of the video and a second assumption that there is no translation between the plurality of image frames of the video; and generating a depth map of a scene, by the one or more computing devices, based at least in part on the set of 3D points.