Unlock instant, AI-driven research and patent intelligence for your innovation.

Image processing method and device and electronic equipment

An image and target image technology, applied in image data processing, animation production, instruments, etc., can solve problems such as inability to obtain bone driving coefficients

Pending Publication Date: 2021-03-26
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present application provides an image processing method, device and electronic equipment, which solves the problem in the prior art that the bone driving coefficient matching the facial image cannot be obtained

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing method and device and electronic equipment
  • Image processing method and device and electronic equipment
  • Image processing method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] image 3 It is a schematic flowchart of the image processing method provided according to the first embodiment of the present application. The image processing method may be executed by software and / or hardware devices, for example, the hardware device may be a network device. For example, see image 3 As shown, the image processing method may include:

[0045] S301. Acquire an image to be processed and N BlendShape models.

[0046] For example, when obtaining the image to be processed, the pre-stored image to be processed can be obtained directly from the network device, or the image to be processed can be received from the terminal. For example, when the user wants to use his own face image to generate an animated avatar, You can use the terminal to take your own facial image, and send the captured facial image to the network device, so that the network device can obtain the facial image, which is the image to be processed received by the network device from the ter...

Embodiment 2

[0061] Figure 5 It is a schematic flowchart of determining the target bone driving coefficient according to the second embodiment of the present application. The method for determining the target bone driving coefficient can be executed by software and / or hardware devices. For example, the hardware device can be a network device. For example, see Figure 5 As shown, the determination method of the target bone driving coefficient may include:

[0062] S501. For each node in the base skin skeletal model, according to the preset bone driving coefficient corresponding to the node under each BlendShape model and the global rigid pose matrix of the parent node of the node under each BlendShape model, determine the current global position of the node under each BlendShape model Rigid pose matrix.

[0063]For example, when obtaining the global rigid pose matrix of the parent node of the node under each BlendShape model, for each node in the tree base skin skeleton model, the pose c...

Embodiment 3

[0106] Figure 9 is a schematic structural diagram of the image processing device 90 provided according to the third embodiment of the present application, for example, please refer to Figure 9 As shown, the image processing device 90 may include:

[0107] The acquiring module 901 is configured to acquire the image to be processed and N BlendShape models.

[0108] The processing module 902 is configured to respectively determine the weight coefficient corresponding to each BlendShape model according to the image to be processed and the N BlendShape models.

[0109] The determination module 903 is used to determine the target bone drive coefficient corresponding to each node in the base skin skeleton model according to the weight coefficients corresponding to N BlendShape models, N preset bone drive coefficients and the base skin skeleton model, so as to Drive coefficient to obtain the target image corresponding to the image to be processed; where the bones of the BlendShape...

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

No PUM Login to View More

Abstract

The invention discloses an image processing method and device and electronic equipment, and relates to the technical field of artificial intelligence such as computer vision, deep learning and augmented reality. According to the specific implementation scheme, when a target skeleton driving coefficient used for generating a target image is determined, N preset skeleton driving coefficients are optimized through weight coefficients corresponding to N BlendShape models according to a to-be-processed image and the N BlendShape models, therefore, the optimized target skeleton driving coefficient corresponding to each node in the basal skin skeleton model describes the characteristics of the face image, and the problem that the skeleton driving coefficient matched with the face image cannot beobtained in the prior art is solved. Moreover, when the skeleton driving model generated based on the optimized target skeleton driving coefficient is rendered, the generated animation head portrait is closer to a real face image.

Description

technical field [0001] The present application relates to the technical fields of artificial intelligence such as computer vision, deep learning, and augmented reality, and in particular relates to an image processing method, device, and electronic equipment. Background technique [0002] When obtaining the animated avatar corresponding to the user's face image, the staff needs to customize N bone drive coefficients according to the face image first, then generate a bone drive model based on the base skin bone model and the customized N bone drive coefficients, and then The bone-driven model is rendered to generate an animated avatar corresponding to the face image. [0003] However, when customizing N bone driving coefficients according to the face image, because the hierarchical structure of the bones is not easy to understand, and there are parent-child multi-level nodes, even if the technician repeatedly manually adjusts and customizes N bone driving coefficients, The N...

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
no application Login to View More
IPC IPC(8): G06T13/20
CPCG06T13/20
Inventor 彭昊天
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD