公开(公告)号：US10812825B2

公开(公告)日：2020-10-20

申请号：US16349532

申请日：2017-09-29

Applicant: Google LLC

Inventor： Ziwei Liu ,  Yiming Liu ,  Aseem Agarwala

IPC: H04N7/12 ,  H04N19/587 ,  H04N19/89 ,  G06N3/08 ,  H04N7/01 ,  G06T3/40

Abstract: The present disclosure provides systems and methods that leverage machine-learned models (e.g., neural networks) to provide video frame synthesis. In particular, the systems and methods of the present disclosure can include or otherwise leverage a machine-learned video frame synthesis model to allow for video frames to be synthesized from videos. In one particular example, the video frame synthesis model can include a convolutional neural network having a voxel flow layer and provides one or more synthesized video frames as part of slow-motion video.

公开(公告)号：US20190289321A1

公开(公告)日：2019-09-19

申请号：US16349532

申请日：2017-09-29

Applicant: Google LLC

Inventor： Ziwei Liu ,  Yiming Liu ,  Aseem Agarwala

IPC: H04N19/587 ,  H04N19/89 ,  G06N3/08 ,  H04N7/01

Abstract: The present disclosure provides systems and methods that leverage machine-learned models (e.g., neural networks) to provide video frame synthesis. In particular, the systems and methods of the present disclosure can include or otherwise leverage a machine-learned video frame synthesis model to allow for video frames to be synthesized from videos. In one particular example, the video frame synthesis model can include a convolutional neural network having a voxel flow layer and provides one or more synthesized video frames as part of slow-motion video.