Original line drawing auxiliary drawing method and device based on a neural network

A neural network and neural network model technology, which is applied in the field of assisted drawing of original line draft based on neural network, can solve the problems of lack of art skills, high labor cost and time, shortening development cycle, etc., to reduce the heavy drawing work, Easy to create and modify effects

Active Publication Date: 2019-05-24
武汉金山世游艺创文化有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, because the current drawing of the original painting largely depends on the experience of the artist, and it often takes a lot of time to draw, so this makes the software developer or outsourcing design company spend a lot of labor costs and time to Complete the above tasks
At the same time, because in the early stage of video game or animation production, all parties need to conduct repeated consultations and revisions on the specific design, and the

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
  • Original line drawing auxiliary drawing method and device based on a neural network
  • Original line drawing auxiliary drawing method and device based on a neural network
  • Original line drawing auxiliary drawing method and device based on a neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The concept, specific structure and technical effects of the present application will be clearly and completely described below in conjunction with the embodiments and drawings, so as to fully understand the purpose, scheme and effect of the present application. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0063] It should be noted that, unless otherwise specified, when a feature is called "fixed" or "connected" to another feature, it can be directly fixed and connected to another feature, or indirectly fixed and connected to another feature. on a feature. In addition, descriptions such as up, down, left, and right used in the application are only relative to the mutual positional relationship of the components of the application in the drawings. As used in this application and the appended claims, the singular forms "a", "the", and "the" are intend...

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

An original line drawing auxiliary drawing method based on a neural network comprises the steps of acquiring a plurality of graffiti drafts and formal drafts before and after correction of the original line drawing , marking shape parameters of all subdivided areas of the formal drafts and forming original line drawing data samples; using Keras to initialize an original picture neural network model, wherein the original picture neural network model adopts a recurrent neural network; importing an original line drawing data sample as a training set, and carrying out supervised learning on the original drawing neural network model; and automatically correcting the input graffiti draft by using the trained original picture neural network model. The invention further discloses a corresponding auxiliary drawing device for the original line drawing draft based on the neural network. The method and the device have the beneficial effects that the graffiti draft is subjected to auxiliary correction by utilizing the neural network, so that the heavy work of drawing the formal draft of the original picture is reduced, and the original picture can be conveniently and quickly manufactured and modified.

Description

technical field [0001] The invention relates to the field of computer learning, in particular to a neural network-based method and device for assisting drawing of original line drawings. Background technique [0002] Whether it is the production of electronic products such as video games and animations, or the drawing of manga and inserts, etc., a lot of original painting work is required. For example, for video game development, software developers need to design game characters, game scenes, original paintings of game props or standing paintings of main characters in the game, avatars with various expressions, etc. according to project planning. These original painting designs, especially the original drawing line drafts, will become an important reference for the development of video games later, so the drawing of the above-mentioned original paintings often has high requirements for image quality and fineness, so that other artists can base on the original paintings, acc...

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): G06T11/20G06N3/04G06N3/08
CPCY02P90/30
Inventor 强项胡文彬周湘君蒋晓光
Owner 武汉金山世游艺创文化有限公司
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