Image generation method and device based on AIGC

The invention discloses an AIGC-based image generation method and device, and the method comprises the steps: completing the training of a generative adversarial network model in a photographing preview stage, enabling the generative adversarial network model to generate a corresponding restoration...

Full description

Saved in:
Bibliographic Details
Main Authors YUAN BAO, LIU HUIJING
Format Patent
LanguageChinese
English
Published 11.06.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
PHYSICS
PICTORIAL COMMUNICATION, e.g. TELEVISION
Online AccessGet full text

Cover

More Information
Summary:The invention discloses an AIGC-based image generation method and device, and the method comprises the steps: completing the training of a generative adversarial network model in a photographing preview stage, enabling the generative adversarial network model to generate a corresponding restoration region according to the features of a defect region when a target camera obtains that the defect region exists in an original image, and enabling the restoration region to be more accurate. And thus, the repaired target image is obtained. Therefore, the quality and success rate of mobile phone snapshot are greatly improved. According to the invention, more intelligent and convenient photographing experience is provided for the user, and it is ensured that each beautiful moment can be perfectly captured. 本申请公开了一种基于AIGC的图像生成方法和装置，在拍照预览阶段完成对生成对抗网络模型的训练，使得生成对抗网络模型能够在目标摄像头采集得到原始图像中存在缺陷区域时，根据缺陷区域的特征生成对应的修复区域，从而得到修复后的目标图像。从而大幅提升手机抓拍的质量与成功率。本申请为用户提供了更加智能、便捷的拍照体验，确保每一个美好瞬间都能被完美捕捉。
Bibliography:Application Number: CN202410592132