Construction method of creative three-dimensional voxel model modeling system based on deep learning

A 3D model, deep learning technology, applied in 3D modeling, image data processing, instruments, etc., can solve the problems of long design cycle, high labor cost, difficult to meet the needs of 3D models, and meet the needs of custom modification , The effect of simplifying the modeling process and shortening the modeling cycle

Active Publication Date: 2020-01-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012]The disadvantage of this method is that the design cycle is long, the labor cost is high, and it is difficult to meet the demand for 3D models in the future

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
  • Construction method of creative three-dimensional voxel model modeling system based on deep learning
  • Construction method of creative three-dimensional voxel model modeling system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention aims to propose a method for constructing a modeling system of a creative three-dimensional voxel model based on deep learning, and build a modeling system that can automatically generate a creative three-dimensional voxel model and has an interactive editing function. Based on this system, creative 3D models can be quickly generated and good interactive functions can be provided.

[0032] In terms of specific implementation, the construction method of the modeling system of the creative three-dimensional voxel model based on deep learning in the present invention includes the following steps:

[0033] 1. Make the voxel data set of the 3D model and the semantic component data set of the 3D model;

[0034] In this step, based on the known data set ShapeNetCore, the data set includes 3D models of 55 common object categories, and the voxel data set of the 3D model is produced by manual classification and alignment; then the ShapeNetCore data set is pr...

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 relates to the field of modeling of three-dimensional voxel models, discloses a construction method of a creative three-dimensional voxel model modeling system based on deep learning. The method constructs a modeling system capable of automatically generating a creative three-dimensional voxel model and having an interactive editing function. The method comprises: A, manufacturing avoxel data set of a three-dimensional model and a semantic component data set forming the three-dimensional model; B, building a generation model of a three-dimensional model and a generation model ofa three-dimensional model composition part, and respectively training by adopting a voxel data set and a semantic part data set; C, constructing a semantic structure model based on an encoder in thegeneration model of the trained three-dimensional model and an encoder in the generation model of the trained three-dimensional model component, and performing training; and D, integrating the trainedsemantic structure model into a system to serve as a modeling algorithm, and meanwhile, providing an interactive interface and a controllable editing interface for the generated three-dimensional model component for a user.

Description

technical field [0001] The invention relates to the field of modeling of three-dimensional voxel models, in particular to a construction method of a deep learning-based creative three-dimensional voxel model modeling system. Background technique [0002] With the change of people's entertainment methods, the demand for special effects in film and television, animation creation, game production and many other digital media fields has expanded rapidly. In these digital media fields, the modeling of 3D objects is an important part of the work, such as the modeling of environmental scenes, object modeling and character modeling. In addition, with the gradual maturity of 3D printing technology, the demand for 3D models is gradually increasing. [0003] The methods of 3D modeling in traditional technology usually have the following types: [0004] 1. Fully automatic real-time positioning and map construction method: [0005] This method uses a laser sensor or radar to model a t...

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 Applications(China)
IPC IPC(8): G06T17/00
CPCG06T17/00
Inventor 谢宁李康申恒涛
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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