Recently, deep convolution neural networks (CNNs) steered face super-resolution methods have achieved great progress in restoring degraded facial details by jointly training with facial priors. However, these methods have some obvious limitations. On the one hand, multi-task joint learning requires additional marking on the dataset, and the introduced prior network will significantly increase the computational cost of the model. On the other hand, the limited receptive field of CNN will reduce the fidelity and naturalness of the reconstructed facial images, resulting in suboptimal reconstructed images. In this work, we propose an efficient CNN-Transformer Cooperation Network (CTCNet) for face super-resolution tasks, which uses the multi-scale connected encoder-decoder architecture as the backbone. Specifically, we first devise a novel Local-Global Feature Cooperation Module (LGCM), which is composed of a Facial Structure Attention Unit (FSAU) and a Transformer block, to promote the consistency of local facial detail and global facial structure restoration simultaneously. Then, we design an efficient Feature Refinement Module (FRM) to enhance the encoded features. Finally, to further improve the restoration of fine facial details, we present a Multi-scale Feature Fusion Unit (MFFU) to adaptively fuse the features from different stages in the encoder procedure. Extensive evaluations on various datasets have assessed that the proposed CTCNet can outperform other state-of-the-art methods significantly. Source code will be available at https://github.com/IVIPLab/CTCNet.
翻译:最近,通过与人脸先验共同训练,在恢复退化面部细节方面,深度卷积神经网络(CNN)为导向的面部超分辨率方法取得了巨大的进展。然而,这些方法存在明显的局限性。一方面,多任务联合学习需要对数据集进行额外标记,引入的先验网络将显着增加模型的计算成本。另一方面,CNN的有限感受野会降低重建面部图像的保真度和自然度,从而导致次优重建图像。在这项工作中,我们提出了一种用于人脸超分辨率任务的高效的CNN-Transformer协作网络(CTCNet),其使用多尺度连接的编码器-解码器架构作为骨干。具体来说,我们首先设计了一种新颖的局部-全局特征协作模块(LGCM),它由一种面部结构注意单元(FSAU)和一个Transformer块组成,可同时促进局部面部细节和全局面部结构恢复的一致性。然后,我们设计了一个高效的特征细化模块(FRM),以增强编码后的特征。最后,为了进一步改善细微面部细节的恢复,我们提出了一个多尺度特征融合单元(MFFU),以自适应地融合来自编码器过程中不同阶段的特征。对各种数据集的广泛评估表明,所提出的CTCNet可以显着优于其他最先进的方法。源代码将在https://github.com/IVIPLab/CTCNet公开。