公开(公告)号：US11055828B2

公开(公告)日：2021-07-06

申请号：US16407915

申请日：2019-05-09

Applicant: Adobe Inc.

Inventor： Mai Long ,  Zhaowen Wang ,  Ning Xu ,  John Philip Collomosse ,  Haotian Zhang ,  Hailin Jin

IPC: G06T5/00 ,  G06N3/04 ,  G06K9/62

Abstract: Techniques of inpainting video content include training a neural network to perform an inpainting operation on a video using only content from that video. For example, upon receiving video content including a sequence of initial frames, a computer generates a sequence of inputs corresponding to at least some of the sequence of initial frames and each input including, for example, a uniform noise map. The computer then generates a convolutional neural network (CNN) using the sequence of input as the initial layer. The parameters of the CNN are adjusted according to a cost function, which has components including a flow generation loss component and a consistency loss component. The CNN then outputs, on a final layer, estimated image values in a sequence of final frames.