基于条件GANs的高分辨率图像合成模型  

A High-Resolution Image Synthesis Model Based on Conditional GANs

作　　者：张居正 

机构地区：[1]江西理工大学信息工程学院,江西 赣州

出　　处：《计算机科学与应用》2025年第2期220-229,共10页Computer Science and Application

摘　　要：本研究提出了一种创新的方法,旨在通过条件生成对抗网络(Conditional Generative Adversarial Networks, cGANs)从语义标签图合成高分辨率、照片级逼真的图像。尽管条件性GANs在多个领域展现出广泛的应用潜力,但其生成的图像通常分辨率较低,且与真实图像的相似度存在显著差距。针对这一挑战,本研究引入了一种新颖的对抗性损失函数,并设计了一种多尺度生成器和判别器架构,以提升图像合成的质量和分辨率。具体而言,我们的方法能够产生2048 × 1024像素的高分辨率图像,这些图像在视觉吸引力上取得了显著的提升。通过与现有技术的比较,我们的方法在深度图像合成和编辑的质量及分辨率方面均展现出明显的优越性。本研究的创新之处在于提出了一种新的对抗性学习目标和多尺度架构,有效解决了cGANs在生成高分辨率图像时的不稳定性问题,并显著提高了图像细节和纹理的真实性,为高分辨率图像合成领域提供了新的技术路径。This study presents an innovative approach aimed at synthesizing high-resolution, photo-realistic images from semantically labeled graphs via Conditional Generative Adversarial Networks (cGANs). Although conditional GANs show a wide range of potential applications in several domains, the images they generate are usually of low resolution and have significant gaps in similarity to real images. To address this challenge, this study introduces a novel adversarial loss function and designs a multi-scale generator and discriminator architecture to enhance the quality and resolution of image synthesis. Specifically, our method is able to produce high-resolution images of 2048 × 1024 pixels, which achieve remarkable results in terms of visual appeal. By comparing with existing techniques, our method demonstrates significant superiority in both quality and resolution of deep image synthesis and editing. The innovation of this study lies in the proposal of a ne

关 键 词：条件生成对抗网络 多尺度生成器和判别器架构 对抗性损失 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]