Google Inc.

Zihong Fan

Bosun Adeoti

Gavan Kwan

A two-dimensional input image to be used in a creation of a three-dimensional video may be received and depth values for pixels in the image may be determined. A depth map may be generated based on the depth values for the pixels and pixel shift values for the pixels may be calculated based on the depth map and a view disparity value. A modified image corresponding to a particular frame of the three-dimensional video may be generated based on the input image and the pixel shift values. An additional modified image corresponding to a next frame of the three-dimensional video may be generated based on the modified image and the pixel shift values used to generate the modified image where the modified image in combination with the input image and the additional modified image are a sequence of frames in the three-dimensional video.

Conversion of 2D image to 3D video

A 3D video generator receives a two-dimensional image to be converted to a first three-dimensional video. The 3D video generator generates a depth map based on depth values for each of a plurality of pixels in the input image. Based on the depth map, the input image and a view disparity value, the 3D video generator creates a series of modified images that are associated with the input image. When combined, the series of modified images comprises a 3D video.

Systems and methods for automatically detecting scenes in a video based on parameters employed to encode the video are presented. In one or more aspects, a system is provided that includes a scene identification component configured to analyze a video comprising a plurality of sequential frames, including a plurality of intra-frames (I-frames) and a plurality of predictive frames (P-frames), and identify N groups of adjacent frames constituting N scenes of the video based in part on respective locations of the I-frames throughout the plurality of sequential frames, where N is an integer. The system further includes a video clip generation component configured to generate one or more video clips from one or more of the N scenes of the video, respectively, using portions of frames respectively associated with the one or more scenes of the N scenes of the video.

Growing community of inventors

Mountain View, CA, United States of America

Zihong Fan