Portrait video processing method
A video processing and portrait technology, applied in the field of portrait video processing, can solve the problem of inability to take into account accurate facial details and gestures, etc., to achieve the effect of natural look, strong sense of reality, and accurate facial details
Active Publication Date: 2021-08-06
GUANGDONG UNIV OF TECH
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to overcome the defect that the above-mentioned existing portrait video generation technology cannot take into account accurate facial details and gesture actions, the present invention provides a portrait video processing method, which can generate a portrait video with realistic facial details, natural gesture actions, and synchronous picture and sound. Strong sense of reality, natural look and feel
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0070] This embodiment provides a portrait video processing method, such as figure 1 shown, including:
[0071] S1: Obtain the original video clip of the first person and the original video clip of the second person;
[0072] S2: Extracting facial parameters, body parameters and audio data of the first person's original video clip of each frame of image from the first person's original video clip; extracting facial control information and action control information from the second person's original video clip;
[0073] Before extracting the facial parameters, body parameters and audio data of the original video clip of the first person from the original video clip of the first person, the original video clip of the first person needs to be preprocessed, including:
[0074] Delete blurred images, use human body recognition technology to delete blurred and unrecognizable images;
[0075] Extract image frames, use FFmpeg video codec tool to extract image frames from video;
[...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a portrait video processing method, which comprises the following steps: acquiring a first figure original video clip, and extracting face parameters, posture parameters and audio data from the first figure original video clip; acquiring a original video clip of a second character and extracting face control information and action control information from the original video clip of the second character; performing face expression migration according to the face parameters of a first character, the audio data and the face control information of the second character to obtain a new fitting face image of the first character; performing posture motion migration according to the posture parameters of the first character and the motion control information of the second character to obtain a new fitted posture graph of the first character; replacing the faces in the fitting new posture graph with the fitting new face graph to generate new whole-body images of the first character; and synthesizing all the new whole-body images of the first character into a video, loading audio data, and obtaining a new video clip of the first character. The new character video clip generated by the invention has vivid facial details, natural postures and actions and a character video with synchronous sound and picture, and is strong in reality sense and natural in impression.
Description
technical field [0001] The present invention relates to the technical field of portrait video processing, and more specifically, to a portrait video processing method. Background technique [0002] With the continuous development of science and technology and the Internet economy, video images have gradually become an indispensable part of people's lives. With the popularity of short videos, more and more people realize that this kind of intuitive, convenient and low-threshold video images are accepted by the public. In recent years, many industries have launched the Internet + model, which is presented to people with the new model of online video, such as online education, online live broadcast sales, news anchors, etc. The economic benefits brought by the new model are huge. However, the shortcomings of the existing video imaging technology are gradually exposed. Taking online education as an example, the recording mode is the most common way in the field of online educat...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/161G06V40/174G06V40/171G06N3/045
Inventor 杨志景徐永宗温瑞冕李为杰李凯凌永权
Owner GUANGDONG UNIV OF TECH