logo

For the Inventor, By the Inventor

The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Patent No.:

US 12445625 B1

PDFFull Text
Date of Patent:
Oct. 14, 2025

Filed:

May. 17, 2023

Coding video frame key points to enable reconstruction of video frame

Applicant:

Tencent Technology (Shenzhen) Company Limited, Guangdong, CN;

Inventor:

Yuxuan Liang, Shenzhen, CN;

Assignee:

TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Nagaokakyo, JP;

Attorney:

ARENTFOX SCHIFF LLP

Primary Examiner:

Leron Beck

Int. Cl.
CPC ...
H04N 11/02 (2006.01); G06T 7/246 (2017.01); G06T 7/73 (2017.01); G06V 10/74 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); H04N 19/132 (2014.01); H04N 19/137 (2014.01); H04N 19/17 (2014.01); H04N 19/182 (2014.01); H04N 19/46 (2014.01); H04N 19/60 (2014.01);
U.S. Cl.
CPC ...
H04N 19/137 (2014.11); G06T 7/248 (2017.01); G06T 7/73 (2017.01); G06V 10/761 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 20/41 (2022.01); G06V 20/46 (2022.01); H04N 19/132 (2014.11); H04N 19/17 (2014.11); H04N 19/182 (2014.11); H04N 19/46 (2014.11); H04N 19/60 (2014.11); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01);
Abstract

An image processing method includes receiving coded image data of a video clip transmitted by an encoder, and decoding the coded image data to obtain a first video frame, key points in the first video frame, and key points in a second video frame not included in the coded image data received from the encoder. The key points represent positions of an object in the first and second video frames. The method further includes generating transforming information of motion of the object according to the key points in the first video frame and the key points in the second video frame, and reconstructing the second video frame according to the first video frame and the transforming information.

Find Patent Forward Citations

Loading…