CNIPA.AI
검색으로 돌아가기
기록

VIDEO COMPRESSION USING OPTICAL FLOW

발명심사 중
12조회수
14청구항 · 3 독립항
§ Ⅰ

개요

발명자

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

IPC 분류

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

CPC 분류

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.

원문 (중국어)

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.