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

Method for generating sketch to bas relief model based on generative adversarial network

A bas-relief and network technology, applied in the field of generation of sketches to bas-relief models based on generative confrontation networks, can solve problems such as inability to obtain relief models and limit creators' imagination, achieve good visual effects, and release creative space.

Inactive Publication Date: 2020-02-07
HUNAN UNIV
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although digital relief can be quickly obtained by computer, it is necessary to input the pre-corresponding 3D model when making the relief model, which greatly limits the creator's imagination. When creating, it is necessary to select the corresponding 3D model. 3D model, the relief model 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
  • Method for generating sketch to bas relief model based on generative adversarial network
  • Method for generating sketch to bas relief model based on generative adversarial network
  • Method for generating sketch to bas relief model based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The invention provides a method for generating a sketch-to-bas-relief model based on a generative confrontation network, which adopts a generative confrontation network structure. By designing a convolutional neural network model based on the height field of the sketch to the bas-relief model based on the generative confrontation network, and then collecting a large number of sketches and corresponding bas-relief models to make a data set, and then input the collected data set into the designed neural network model Carry out training to optimize model parameters, and finally test the hand-drawn sketch input by the user into a corresponding bas-relief model in real time, which greatly facilitates the user's creation and no longer needs the corresponding 3D model as input. The resulting bas-relief model has good visual effects.

[0042] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described ...

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 a method for generating a sketch to bas-relief model based on a generative adversarial network. The method comprises the following steps: model design: designing a reasonable network model based on a generative adversarial network structure; acquiring a data set; acquiring the corresponding sketch and the corresponding bas-relief model for the three-dimensional model at different visual angles, extracting and storing the height field of the obtained bas-relief model as a picture, and establishing a sketch-relief data set; model training: inputting the established data set into a designed model for training, and optimizing the parameters of the generation network and the discrimination network; and user testing: performing feature extraction on the sketch input by the user to generate a height field of the bas-relief model corresponding to network output, and then restoring the generated height field into the bas-relief model. According to the method, the generative adversarial network structure is used, and the corresponding bas-relief model can be generated according to the hand-drawn sketch of the user, and the obtained bas-relief model has a good visual effect.

Description

technical field [0001] The invention relates to the field of picture generation, in particular to a method for generating a sketch-to-bas-relief model based on a generation confrontation network. Background technique [0002] Relief is an ancient and mature art form. The sculptor carves the image he wants to shape on a flat plate to make it out of the plane of the original material. Relief modeling has also been widely introduced into the field of computer graphics. According to the thickness, it mainly includes three types: high relief, concave relief and shallow relief (that is, shallow relief). Creating bas-reliefs by hand is a cumbersome and inefficient process as it relies entirely on the artist's three-dimensional imagination and skill. In the last ten years of development, great progress has been made by converting 3D models into digital reliefs. Although digital relief can be quickly obtained by computer, it is necessary to input the pre-corresponding 3D model whe...

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): G06T17/00G06N3/04G06N3/08
CPCG06T17/00G06N3/08G06N3/045
Inventor 刘泽宇周世哲
Owner HUNAN UNIV
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