Recent GAN-based (Generative adversarial networks) inpainting methods show remarkable improvements and generate plausible images using multi-stage networks or Contextual Attention Modules (CAM). However, these techniques increase the model complexity limiting their application in low-resource environments. Furthermore, they fail in generating high-resolution images with realistic texture details due to the GAN stability problem. Motivated by these observations, we propose a multi-GAN architecture improving both the performance and rendering efficiency. Our training schema optimizes the parameters of four progressive efficient generators and discriminators in an end-to-end manner. Filling in low-resolution images is less challenging for GANs due to the small dimensional space. Meanwhile, it guides higher resolution generators to learn the global structure consistency of the image. To constrain the inpainting task and ensure fine-grained textures, we adopt an LBP-based loss function to minimize the difference between the generated and the ground truth textures. We conduct our experiments on Places2 and CelebHQ datasets. Qualitative and quantitative results show that the proposed method not only performs favorably against state-of-the-art algorithms but also speeds up the inference time.
翻译:以GAN为基础的GAN(Genementive 对抗性网络)近期的涂色方法显示显著的改进,并利用多阶段网络或背景关注模块(CAM)产生可信的图像。然而,这些技术增加了模型的复杂性,限制了其在低资源环境中的应用。此外,由于GAN稳定性问题,这些技术未能产生高分辨率图像,并具有现实的纹理细节。我们根据这些观察,提议了一个多GAN结构来改善性能和效率。我们的培训计划以端到端的方式优化四个进步高效的生成器和歧视器的参数。填补低分辨率图像对于GAN来说,由于空间小,对GAN来说难度较小。同时,这些技术引导更高的分辨率生成器来学习图像的全球结构一致性。为了限制任务和确保精细的纹理,我们采用了基于LBP的亏损功能,以最大限度地缩小生成的和地面事实文本之间的差异。我们在Paces2和CeebHQ数据集上进行实验。定性和定量结果显示,拟议的方法不仅可以对州进行有利的,而且能够对时间进行。