Face Hallucination Using Split-Attention in Split-Attention Network

Face Hallucination Using Split-Attention in Split-Attention Network

Recently, attention mechanism has been applied into convolutional neural networks(CNNs) based super-resolution (SR) tasks for exploring internal feature map correlation. However, most of them ignore the correlation between multi-path features channels for coarse-to-fine attention focusing.In this paper, we propose a split-attention in split-attention network (SISN) to fuse internal channel features and external (cross) multi-path features for exploring face structure information. First, internal-feature split attention block maintains the fidelity of facial local details. Then external-internal split attention group provides cross-features interaction to finetune multi-path features for stabilizing facial structure information. External-feature fusion module is designed to fuse face structure and local detail features for preserving the consistency of images from coarse-to-fine. Experimental results demonstrate that the proposed approach consistently and significantly improves the subjective and objective performances for face hallucination over some state-of-the-art methods.

分割注意力网络中使用分割注意力的幻觉

近来，注意力机制已被应用于基于卷积神经网络（CNN）的超分辨率（SR）任务，以探索内部特征图的相关性。但是，它们中的大多数都忽略了多路径特征通道之间的相关性，以实现从粗到精的注意力集中。.. 在本文中，我们提出了一种分割注意力网络（SISN）中的分割注意力，以融合内部通道特征和外部（交叉）多径特征以探索人脸结构信息。首先，内部特征分散注意力区保持面部局部细节的保真度。然后，内外分心小组提供跨功能的交互，以微调多路径功能，以稳定面部结构信息。外部特征融合模块旨在融合人脸结构和局部细节特征，以保持从粗糙到精细的图像一致性。实验结果表明，与某些最新方法相比，该方法始终有效地显着改善了幻觉的主观和客观表现。 （阅读更多）