Face Super-resolution Reconstruction Research Articles

SwinDPSR: Dual-Path Face Super-Resolution Network Integrating Swin Transformer

Whether to use face priors in the face super-resolution (FSR) methods is a symmetry problem.Various face priors are used to describe the overall and local face features, making the generation of super-resolution face images expensive and laborious. FSR methods that do not require any prior information tend to focus too much on the local features of the face, ignoring the modeling of global information. To solve this problem, we propose a dual-path facial image super-resolution network (SwinDPSR) fused with Swin Transformer. The network does not require additional face priors, and it learns global face shape and local face components through two independent branches. In addition, the channel attention ECA module is used to aggregate the global and local face information in the above dual-path sub-networks, which can generate corresponding high-quality face images. The results of face super-resolution reconstruction experiments on public face datasets and a real-scene face dataset show that SwinDPSR is superior to previous advanced methods both in terms of visual effects and objective indicators. The reconstruction results are evaluated with four evaluation metrics: peak signal-to-noise ratio (PSNR), structural similarity (SSIM), learned perceptual image patch similarity (LPIPS), and mean perceptual score (MPS).

UFSRNet: U-shaped face super-resolution reconstruction network based on wavelet transform

UFSRNet: U-shaped face super-resolution reconstruction network based on wavelet transform

Research on the Integration Strategy of Technology and Teaching in the Construction of Accounting Smart Classroom in Colleges and Universities

Abstract In the “Internet+” era, the smart classroom has emerged as a significant focal point in the research on educational informatization. This advancement represents a synergistic melding of novel technologies and academic practices. Accordingly, this study proposes a smart classroom teaching model tailored for accounting courses in higher education institutions. Within this framework, we have developed a specialized model to evaluate teaching efficacy in such environments. This evaluation model incorporates an enhanced version of the basic YOLOv5s model, which has been modified in three key areas to facilitate the detection of students’ facial expressions during lectures. Furthermore, to accommodate low-resolution images, the model integrates an advanced DRN-F face super-resolution reconstruction algorithm, thereby augmenting the accuracy of face recognition. This paper introduces a composite model for assessing the effectiveness of smart classroom teaching by amalgamating the two refined models. Comparative analysis with traditional manual recognition methods reveals that our model aligns more closely with the actual attentive responses of students when their faces are unobscured. A practical study on the teaching application further substantiates the efficacy of the smart classroom approach. Employing an independent sample t-test, the findings demonstrate a statistically significant difference in the post-test scores between the experimental and control groups, with a Sig. Value of 0.001 (p<0.05). This indicates that the learning achievements of students under the smart classroom model are significantly enhanced compared to those in conventional teaching settings.

A STUDY ON FACE SUPER-RESOLUTION RECONSTRUCTION ALGORITHM BASED ON IMPROVED SRGAN

In this paper, we propose a novel approach to address the challenges of Super-Resolution Generative Adversarial Network (SRGAN) in face image super-resolution reconstruction. We introduce a new improved SRGAN algorithm, named Wasserstein SRGAN (W-SRGAN), which addresses the limitations of the original model by enhancing the loss function, generator, and discriminator. Our approach utilizes the embedded residual structure combined with feature fusion as the new generator, while removing the Sigmoid of the last layer of the discriminator of SRGAN by borrowing the idea of Wasserstein GAN (W-GAN). Additionally, we replace the Kullback–Leibler (KL) divergence of SRGAN with Wasserstein distance. The contributions of our research are twofold. Firstly, we propose a new face super-resolution reconstruction algorithm that outperforms existing methods in terms of visual quality. Secondly, we introduce a new loss function and generator–discriminator architecture that can be applied to other image super-resolution tasks, extending the applicability of GANs in this domain. Experimental results demonstrate that our proposed W-SRGAN outperforms Bicubic, Super-Resolution Convolutional Neural Network (SRCNN), and SRGAN in terms of visual quality on all Celeb A datasets. These results confirm the effectiveness of our proposed algorithm and provide a new solution for face super-resolution reconstruction.

A Novel Multi-Task Face Super-Resolution Framework Embedding Degraded Augmented GAN Networks

The training method that uses predefined degradation methods to provide training data for deep convolutional neural networks suffers from overfitting and image distortion when performing face super-resolution reconstruction. In this paper, we propose a multi-task facial super-resolution reconstruction framework embedded in a degraded augmented GAN network. Compared with the commonly used method of generating low-quality face images through pixel interpolation, this paper inversely embeds a generative adversarial network composed of residual coding blocks in the network. Through the feature learning ability of the network, the feature fitting of the face images collected in the natural scene is performed to generate training data that can more fully represent the real noise in the natural scene, thereby improving the noise reduction and image reconstruction capabilities of the network. In order to take full advantage of the task-specific features, the semantic features of the dataset are extracted through a pre-trained facial organ semantic detection framework and the data is used to add face semantic information in the super-resolution reconstruction network. The experimental results show that the model proposed in this study can achieve super-resolution reconstruction of ultra-low-resolution face images simply and efficiently, and achieve super-resolution face images with lower visual quality than other advanced methods with lower model complexity. It solves the problem of single style and distortion of face reconstruction images caused by the training method of the data set obtained by the usual predefined degradation.

The face image super-resolution algorithm based on combined representation learning

Face super-resolution reconstruction is the process of predicting high-resolution face images from one or more observed low-resolution face images, which is a typical pathological problem. As a domain-specific super-resolution task, we can use facial priori knowledge to improve the effect of super-resolution. We propose a method of face image super-resolution reconstruction based on combined representation learning method, using deep residual networks and deep neural networks as generators and discriminators, respectively. First, the model uses residual learning and symmetrical cross-layer connection to extract multilevel features. Local residual mapping improves the expressive capability of the network to enhance performance, solves gradient dissipation in network training, and reduces the number of convolution cores in the model through feature reuse. The feature expression of the face image at the high-dimensional visual level is obtained. The visual feature is sent to the decoder through the cross-layer connection structure. The deconvolution layer is used to restore the spatial dimension gradually and repair the details and texture features of the face. Finally, combine the attention block and the residual block reconstruction in the deep residual network to super-resolution face images that are highly similar to high-resolution images and difficult to be discriminated by the discriminator. On this basis, combined representation learning is conducted to obtain numerous realistic results of visual perception. The experimental results on the face datasets can show that the Peak Signal-to-Noise Ratio of the proposed method is improved.

Face Super-Resolution Reconstruction Based on Self-Attention Residual Network

Aiming at the problems of the face image super-resolution reconstruction method based on convolutional neural network, such as single feature extraction scale, low utilization rate of features and blurred face images texture, a model combining convolutional neural network with self-attention mechanism is proposed. Firstly, the shallow features of the image are extracted by the cascaded 3 × 3 convolutional kernels, and then self-attention mechanism is combined with the residual blocks in depth residual network to extract the deep detail features of faces. Finally, the extracted features are fused globally by skip connections, which provide more high-frequency details for face reconstruction. Experiments on Helen, CelebA face datasets and real-world images showed that the proposed method could make full use of facial feature information, and its peak signal to noise ratio (PSNR) and structural similarity (SSIM) were both higher than the comparison methods with better subjective visual effects.

The visual human face super-resolution reconstruction algorithm based on improved deep residual network

Deep learning is a hot method in face super-resolution reconstruction in recent years, but it needs to further improve the details of reconstructed images and speed up network training. This paper improves the deep residual network from two aspects of residual unit and network structure and proposes a face super-resolution reconstruction algorithm based on the improved model. We improve the network structure of the residual unit by connecting with a densely connected convolutional layer and removing the BN layer, thereby enhancing the information flow between the inner convolutional layers and eliminate the damage to the spatial information of the image by batch normalization processing. At the same time, we combine the output characteristics of each residual unit on the basis of the global residual structure, so the face feature information is more fully utilized and the model detail recovery ability is also improved. Experiments on FDDB and AFLW face datasets show that the proposed method has better performance in feature description and detail information reconstruction, and higher PSNR and SSIM than other methods.

Face super-resolution reconstruction and recognition using non-local similarity dictionary learning based algorithm

One of the challenges of face recognition in surveillance is the low resolution of face region. Therefore many superresolution (SR) face reconstruction methods are proposed to produce a high-resolution face image from one or a set of low-resolution face images. However, existing dictionary learning based algorithms are sensitive to noise and very time-consuming. In this paper, we define and prove the multi-scale linear combination consistency. In order to improve the performance of SR, we propose a novel SR face reconstruction method based on nonlocal similarity and multi-scale linear combination consistency (NLS-MLC). We further proposed a new recognition approach for very low resolution face images based on resolution scale invariant feature (RSIF). A series of experiments are conducted on two public face image databases to test feasibility of our proposed methods. Experimental results show that the proposed SR method is more robust and computationally effective in face hallucination, and the recognition accuracy of RSIF is higher than some state-of-art algorithms.

A novel face super resolution approach for noisy images using contour feature and standard deviation prior

Face Super Resolution (FSR) is to infer high resolution (HR) face images from given low resolution (LR) face images with the help of HR/LR training examples. The most representative FSR is NE methods, which are based on the consistency assumption that the HR/LR patch pairs form similar local geometric structures. But NE methods have difficulty in dealing with noisy facial images. The reason lies in the wrong neighborhood relationship caused by low quality scenarios that even two distinct patches have similar relation in local geometry. Therefore, the consistency assumption is not well held anymore. This paper presents a novel FSR approach suitable for noisy facial images. Our work are twofold. Firstly, different from the existing methods which directly enhance the noisy input image in intensity feature space, the proposed method introduces a contour feature which is robust to noise. By applying the contour feature as constraint, the noise effects can be effectively suppressed. Secondly, different from the existing methods which directly constrain the noisy input image with low quality contour feature, a standard deviation prior is proposed to enhance the low quality contour feature. Through enhancing the contour feature into high quality, the FSR reconstruction can be better constrained. Both simulation and the real-world scenario experiments demonstrate that the proposed approach outperforms most classic methods both quantitatively and qualitatively.

A Novel Face Hallucination with an Error Regression Model and MPCA in RGB Color Space

This paper proposes a novel face super-resolution reconstruction (hallucination) technique, color face images reconstruction of RGB space with an error regression model in multi-linear principal component analysis (MPCA). From hallucination framework, many color face images are explained in RGB space. Then, they can be naturally described as tensors or multi-linear arrays. In this way, the error regression analysis is used to find the error estimation which can be obtained from the existi ng LR in tensor space. The framework consists of learning and hallucinating process. In learning process is from the mistakes in reconstruct face images of the training dataset by MPCA, then finding the relationship between input and error by regression analysis. In hallucinating process uses normal method by back-projection of MPCA, after that the result is corrected with the error estimation. In this contribution we show that our hallucination technique can be suitable for color face images both in RGB space. By using the MPCA subspace with error regression model, we can generate photorealistic color face images. Our approach is demonstrated by extensive experiments with high-quality hallucinated color faces. In addition, our experiments on face images from FERET database validate our algorithm

Morphable model space based face super-resolution reconstruction and recognition

Super-resolution image reconstruction is the process of producing a high-resolution image from a set of low-resolution images of the same scene. For the applications of performing face evaluation and/or recognition from low-resolution video surveillance, in the past, super-resolution image reconstruction was mainly used as a separate preprocessing step to obtain a high-resolution image in the pixel domain that is later passed to a face feature extraction and recognition algorithm. Such three-stage approach suffers a high degree of computational complexity. A low-dimensional morphable model space based face super-resolution reconstruction and recognition algorithm is proposed in this paper. The approach tries to construct the high-resolution information both required by reconstruction and recognition directly in the low dimensional feature space. We show that comparing with generic pixel domain algorithms, the proposed approach is more robust and more computationally efficient.

Feature Space Based Face Super-resolution Reconstruction

摘要: 超分辨率图像重构是利用关于同一场景的多帧低分辨率图像重构出一幅具有更高分辨率图像的过程.传统的超分辨率图像重构算法是基于像素空间,通过利用高、低分辨率像素空间之间的映射关系来求解,具有计算复杂性高等缺点. 针对低分辨率人脸放大问题,提出了一个基于特征空间的人脸超分辨率图像重构算法.与传统算法相比,该算法不仅降低了计算复杂性,还具有更好的鲁棒性. 关键词: 超分辨率 / 特征空间 / 图像序列 / 图像重构