Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Surface reconstruction method of 3D model of single frame image based on deep learning

A 3D model and deep learning technology, applied in the field of computer vision, can solve problems such as the difficulty of reconstructing 3D models on complex surfaces, and achieve the effect of improving network operation speed, reducing operation difficulty, and smooth surface

Active Publication Date: 2021-05-28
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional setting of control point weights and coordinates requires a large number of initialization calculations and manual fine-tuning, which makes the reconstruction of complex surface 3D models more difficult.

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
  • Surface reconstruction method of 3D model of single frame image based on deep learning
  • Surface reconstruction method of 3D model of single frame image based on deep learning
  • Surface reconstruction method of 3D model of single frame image based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. The present invention obtains the control point coordinates and weight parameter values ​​required for the change of the NURBS surface through the deep learning neural network. On the one hand, the deep learning neural network can use its powerful feature extraction ability and analysis and calculation ability to automatically return to the needs of the NURBS surface change. On the other hand, the NURBS method does not need to perform regression calculations on every point of the 3D model. It only needs to obtain the weights and coordinates of the control points to achieve 3D reconstruction, reducing network parameters and reducing computational complexity. Spend.

[0044] Such as figure 1 As shown, the surface reconstruction method of a single-frame image 3D model based on deep learning includes the following steps:

[0045] Step 1: ...

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 present invention provides a single-frame image three-dimensional model surface reconstruction method based on deep learning. The neural network extracts the features of the image to obtain the high-level semantics of the two-dimensional image; the obtained high-level semantics is converted into the control point coordinates and weight parameters required for the change of the NURBS surface in the three-dimensional reconstruction stage through the fully connected neural network module; The point coordinates and weight parameters update the initialized NURBS model, and gradually carry out 3D reconstruction; train the deep learning model, input the training samples into the deep learning model for automatic training, obtain the optimal model parameters, and complete the 3D reconstruction. The invention can simply and efficiently perform three-dimensional reconstruction on a single frame image, and the reconstructed three-dimensional model has the characteristics of rich details, smooth surface and good overall.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method for surface reconstruction of a three-dimensional model of a single frame image based on deep learning. Background technique [0002] 3D reconstruction refers to the process of establishing a mathematical model of a 3D object in a real scene in a computer, and it is a popular research direction in the field of computer vision. Compared with two-dimensional images, three-dimensional models can provide the overall information of the object and more comprehensively display the characteristics of the object, so it has a wide range of applications in computer animation, human-computer interaction, modern medicine and other fields. [0003] With the rapid development of deep learning, new breakthroughs have been made in the field of 3D reconstruction of single frame images. Researchers use convolutional neural networks to extract features from single-frame images, and reconstru...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T17/00G06T15/00G06T19/20G06N3/04G06N3/08
CPCG06T17/00G06T15/005G06T19/20G06N3/084G06T2200/04G06N3/045
Inventor 杨路杨经纶李佑华
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com