Realistic image restoration with high texture areas such as removing face masks is challenging. The state-of-the-art deep learning-based methods fail to guarantee high-fidelity, cause training instability due to vanishing gradient problems (e.g., weights are updated slightly in initial layers) and spatial information loss. They also depend on intermediary stage such as segmentation meaning require external mask. This paper proposes a blind mask face inpainting method using residual attention UNet to remove the face mask and restore the face with fine details while minimizing the gap with the ground truth face structure. A residual block feeds info to the next layer and directly into the layers about two hops away to solve the gradient vanishing problem. Besides, the attention unit helps the model focus on the relevant mask region, reducing resources and making the model faster. Extensive experiments on the publicly available CelebA dataset show the feasibility and robustness of our proposed model. Code is available at \url{https://github.com/mdhosen/Mask-Face-Inpainting-Using-Residual-Attention-Unet}
翻译:以高质度区域(如去除面罩)恢复真实形象是困难的。 最先进的深层次学习方法无法保证高度不忠,导致培训不稳定,原因是渐渐消失的梯度问题(例如,重量在初始层中略有更新)和空间信息丢失。它们还取决于中间阶段,例如分层的含义需要外部遮罩。 本文建议使用蒙眼睛蒙面涂漆方法, 利用残余注意力UNet来清除面罩, 并用细细细节恢复面部, 并尽量缩小地面真实面部结构的缺口。 残余的块状信息将信息传送到下一层, 直接传送到两层, 以解决渐渐渐消失的问题。 此外, 关注单位帮助模型关注相关的蒙面区域, 减少资源,并使模型更快化。 有关可公开获取的切列巴数据集的广泛实验显示我们拟议模型的可行性和稳健性。 代码可在以下https://github.com/mdhosen/Mask-Face- Inpainting-Using-Restial-Restial-Resion-Resion-Restion-Atnet-Unet}查阅。