Supercharge Your Innovation With Domain-Expert AI Agents!

Image generation method and terminal device

An image generation and image technology, applied in the field of image processing, can solve problems such as difficulty in obtaining images, and achieve the effect of improving experience

Pending Publication Date: 2019-08-16
BEIJING SAMSUNG TELECOM R&D CENT +1
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the prior art, when a user draws an image, the user usually needs to have rich drawing experience. For a user with insufficient drawing experience, it is difficult to obtain an image that can accurately reflect their own ideas.

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
  • Image generation method and terminal device
  • Image generation method and terminal device
  • Image generation method and terminal device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0123] Embodiment 2 mainly includes: context-based intelligent optimization and recommendation, and specifically includes the following at least two aspects:

[0124] 1. Context information refers to the knowledge base established in the system, including user profile information, artistic positioning (personal artistic positioning and the artistic positioning of the user's social group) and common sense; among them,

[0125] 1) The user's personal profile information is used as a context constraint for the system to generate or modify images, and is updated in real time according to user input, including: nationality, race, gender, age and other information;

[0126] 2) Establish an image decomposition model from each artistic level, perform artistic evaluation on the images that users are satisfied with, and obtain the user's personal artistic positioning information to generate images that are more in line with personal preferences;

[0127] 3) Perform artistic positioning ...

Embodiment 3

[0131] The third embodiment mainly includes: generating a multi-layer image, which includes at least the following three aspects; wherein,

[0132] 1. Multiple layers can be generated according to user needs;

[0133] 2. Generate some additional information, such as depth information, to assist in placing elements of different layers;

[0134] 3. Each layer can be adjusted independently or jointly to produce the final image.

[0135] In the embodiment of the present invention, image generation is text input through voice recognition, user handwriting or keyboard text input, or copy and paste, and the text-to-image generation process is started by the user clicking a button, voice command, and the like. The input text is converted into semantics that can be understood by the image generation model (GAN model) by the natural language understanding module. Therefore, the description information input by the user needs to include a description of the content and characteristics ...

Embodiment 1

[0137] Embodiment 1 of the present invention introduces the application scenario in detail, the method flow of image generation is as follows image 3 Shown:

[0138] Step 301. Obtain description information corresponding to the image to be generated.

[0139] Specifically, the description information includes at least one of the following: text description information, voice description information, and image description information.

[0140] The user can input voice, text or image as description information, wherein the user can input voice through the voice assistant application, input text by handwriting or keyboard, or input text or image by copying and pasting. After the system receives the description information input by the user, it can determine the text corresponding to the description information. If the description information input by the user contains voice and / or images, the system can convert the input voice into text through voice recognition, and convert th...

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 provides an image generation method. The image generation method comprises the steps: obtaining description information corresponding to a to-be-generated image, and generating an imagecorresponding to the description information according to the description information. The image generation method and the terminal equipment provided by the invention are suitable for generating thecorresponding image according to the acquired image description information.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular, the present invention relates to an image generation method and a terminal device. Background technique [0002] The form and expression of images are more vivid and intuitive, and people often express their thoughts through images. For example, various charts in business meeting reports, design sketches in product design, navigation maps drawn during route navigation, etc. [0003] In the prior art, when a user draws an image, the user usually needs to have relatively rich drawing experience, and it is difficult for a user with insufficient drawing experience to obtain an image that can accurately reflect his or her own ideas. [0004] Therefore, how to obtain an image that can accurately express the user's thoughts is a problem that needs to be solved urgently in the prior art. Contents of the invention [0005] In order to overcome the above-mentioned techni...

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): G06T11/00
CPCG06T11/001
Inventor 王华张卫华罗振波王长威王晋夫宋先松
Owner BEIJING SAMSUNG TELECOM R&D CENT
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com