Automatic portrait slimming method based on 3D modeling

A 3D, slimming technology, applied in 3D modeling, image enhancement, image analysis, etc., can solve the problems that it is difficult to meet the user's detailed requirements for the figure's shape, cannot guarantee the size of the original image, and cannot perform slimming operations, etc., to overcome the image size Effects of making changes, overcoming fine-grained adjustments, and simplifying steps

Active Publication Date: 2020-12-11
HARBIN INST OF TECH AT WEIHAI
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the current mainstream automatic slimming technology cannot complete fine-grained slimming operations according to the characteristics of different parts of the human body and

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
  • Automatic portrait slimming method based on 3D modeling
  • Automatic portrait slimming method based on 3D modeling
  • Automatic portrait slimming method based on 3D modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Such as figure 1 As shown, a 3D modeling-based automatic portrait slimming method includes the following steps:

[0023] S1. Use the self-trained human body detection algorithm to obtain all human body positions, corresponding genders, and fat and thin ratings in the picture;

[0024] S2. Use the Openpose algorithm that can identify 25 key parts to obtain key point coordinates and confidence values ​​for each object in the human body position frame, and then organize the results of Openpose according to the format of the COCO data set;

[0025] S3. Send the key point data organized according to the format of the COCO dataset into the Pose2Seg background removal algorithm to complete the background removal of the human body area;

[0026] S4. Send the human body area and bone key point data with the background removed to the smplify-x modeling algorithm to obtain a 3D model of the human body;

[0027] S5. For the output results of the modeling, use PCA principal compon...

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 automatic portrait slimming method based on 3D modeling. The automatic portrait slimming method comprises the following steps: acquiring position coordinates, genders and weight grades of all human bodies in a picture by using a self-training human body detection algorithm; for each to-be-processed human body area, obtaining skeleton key points of a figure main body, andremoving a background; matching the human body area with the background removed with the key point coordinates, sending into a 3D modeling algorithm to obtain a 3D model of the human body; obtaininghuman body shape parameters output by the 3D model through PCA principal component analysis, and achieving slimming operation on the 3D model; projecting the 3D model completing slimming onto a 2D image; and obtaining a triangular mesh by using a Delaunay triangle subdivision algorithm to obtain a final slimming result. According to the invention, the step of manually liquefying and slimming by using software is greatly simplified, and the difficulty that a mainstream automatic slimming function cannot be used for carrying out fine-grained adjustment on each part of the body is overcome.

Description

technical field [0001] The invention relates to the technical fields of computer vision and computer graphics, in particular to an automatic portrait slimming method based on 3D modeling. Background technique [0002] In the digital age, people are gradually relying on software to modify the portraits in pictures in an attempt to create a perfect image that they are satisfied with. In this process, liquefying and slimming is a very time-consuming and difficult operation, which requires not only software The frequent operation of the user requires the user to have a perfect understanding of the curves of various parts of the human body. People's pursuit of beauty makes this task more and more difficult. At the same time, the current mainstream automatic slimming technology cannot complete fine-grained slimming operations according to the characteristics of different parts of the human body and cannot guarantee that the size of the original image will not be affected by the po...

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): G06T17/20G06T3/00G06T5/00G06K9/62
CPCG06T17/20G06T3/0031G06T5/005G06T2207/30196G06F18/2135
Inventor 张盛平李宗霖
Owner HARBIN INST OF TECH AT WEIHAI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap