TECHNIQUES FOR PROCESSING VIDEOS USING TEMPORALLY-CONSISTENT TRANSFORMER MODEL

Techniques are disclosed for enhancing videos using a machine learning model that is a temporally-consistent transformer model. The machine learning model processes blocks of frames of a video in which the temporally first input video frame of each block of frames is a temporally second to last outp...

Full description

Saved in:
Bibliographic Details
Main Authors AYDIN, Tunc Ozan, SCHROERS, Christopher Richard, SONG, Mingyang, ZHANG, Yang
Format Patent
LanguageEnglish
Published 07.09.2023
Subjects
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Techniques are disclosed for enhancing videos using a machine learning model that is a temporally-consistent transformer model. The machine learning model processes blocks of frames of a video in which the temporally first input video frame of each block of frames is a temporally second to last output video frame of a previous block of frames. After the machine learning model is trained, blocks of video frames, or features extracted from the video frames, can be warped using an optical flow technique and transformed using a wavelet transform technique. The transformed video frames are concatenated along a channel dimension and input into the machine learning model that generates corresponding processed video frames.
Bibliography:Application Number: US202217876373