论文标题
有效的纹理感知的多器具用于图像插图
Efficient texture-aware multi-GAN for image inpainting
论文作者
论文摘要
最近基于GAN的（生成对抗网络）填充方法显示出显着的改进，并使用多阶段网络或上下文注意模块（CAM）生成了合理的图像。但是，这些技术增加了模型的复杂性，从而限制了其在低资源环境中的应用。此外，由于GAN稳定性问题，它们无法生成具有逼真的纹理细节的高分辨率图像。在这些观察结果的推动下，我们提出了一个多通建筑，以提高性能和渲染效率。我们的培训模式以端到端的方式优化了四个渐进效率发电机和歧视器的参数。由于尺寸较小的空间，填充低分辨率图像的挑战较小。同时，它指导较高的分辨率发生器学习图像的全球结构一致性。为了限制介质任务并确保细粒度的纹理，我们采用了基于LBP的损失功能，以最大程度地减少生成的真相纹理和地面真相纹理之间的差异。我们在Place2和CelebHQ数据集上进行实验。定性和定量结果表明，所提出的方法不仅针对最新算法有利，而且可以加快推理时间。
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.
