CNIPA.AI
返回搜索
档案

VIDEO COMPRESSION USING OPTICAL FLOW

发明专利审中
10浏览
14权利要求 · 3 独立
§ Ⅰ

卷宗概要

发明人

George Dan Toderici; Eirikur Thor Agustsson; Fabian Julius Mentzer; David Charles Minnen; Johannes Balle; Nicholas Johnston

IPC 分类

H4N 19/91G6T 3/18G6T 5/70H4N 19/124H4N 19/137

CPC 分类

H4N19/91G6T3/18G6T5/70H4N19/124H4N19/137G6T2207/20084

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing video data. In one aspect, a method comprises: receiving a video sequence of frames; generating, using a flow prediction network, an optical flow between two sequential frames, wherein the two sequential frames comprise a first frame and a second frame that is subsequent the first frame; generating from the optical flow, using a first autoencoder neural network: a predicted optical flow between the first frame and the second frame; and warping a reconstruction of the first frame according to the predicted optical flow and subsequently applying a blurring operation to obtain an initial predicted reconstruction of the second frame.

原文(中文)

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing video data. In one aspect, a method comprises: receiving a video sequence of frames; generating, using a flow prediction network, an optical flow between two sequential frames, wherein the two sequential frames comprise a first frame and a second frame that is subsequent the first frame; generating from the optical flow, using a first autoencoder neural network: a predicted optical flow between the first frame and the second frame; and warping a reconstruction of the first frame according to the predicted optical flow and subsequently applying a blurring operation to obtain an initial predicted reconstruction of the second frame.