Deep Learning-based Face Super-resolution: A Survey

Jiang, Junjun; Wang, Chenyang; Liu, Xianming; Ma, Jiayi

doi:10.1145/3485132

Cited by 101 publications

(43 citation statements)

References 175 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Human face super-resolution (SR) aims to obtain visualpleasing high-resolution (HR) face images from the lowresolution ones [33]. Early face SR methods [4]- [6], [34]- [36] utilize hand-craft image priors and degradation models.…”

Section: Human Face Super-resolutionmentioning

confidence: 99%

Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution

Hou¹,

Hu²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-cycled Cycle-GAN architecture is widely employed to achieve promising performance on face SR, but prone to produce artifacts upon challenging cases in real-world scenarios, since joint participation in the same degradation branch will impact final performance due to huge domain gap between real-worldand synthetic LR ones obtained by generators. To better exploit the powerful generative capability of GAN for real-world face SR, in this paper, we establish two independent degradation branches in the forward and backward cycle-consistent reconstruction processes, respectively, while the two processes share the same restoration branch. Our Semi-Cycled Generative Adversarial Networks (SCGAN) is able to alleviate the adverse effects of the domain gap between the real-world LR face images and the synthetic LR ones, and to achieve accurate and robust face SR performance by the shared restoration branch regularized by both the forward and backward cycle-consistent learning processes. Experiments on two synthetic and two real-world datasets demonstrate that, our SCGAN outperforms the state-of-the-art methods on recovering the face structures/details and quantitative metrics for real-world face SR. The code will be publicly released at https://github.com/HaoHou-98/SCGAN.

show abstract

Section: Human Face Super-resolutionmentioning

confidence: 99%

Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution

Hou¹,

Hu²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For blind face restoration(BFR) in the real world, the restoration problem becomes more complex due to the particularity of the face image itself and the influence of many unknown degradation factors, such as compression artifacts, low resolution, blur, and noise. There are three main research trends [24] for this task: basic CNN-based methods, GANbased methods, and Prior-guided methods.…”

Section: A Face Restorationmentioning

confidence: 99%

Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior

Hu¹,

Liu²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Facial semantic guidance (facial landmarks, facial parsing maps, facial heatmaps, etc.) and facial generative adversarial networks (GAN) prior have been widely used in blind face restoration (BFR) in recent years. Although existing BFR methods have achieved good performance in ordinary cases, these solutions have limited resilience when applied to face images with serious degradation and pose-varied (look up, look down, laugh, etc.) in real-world scenarios. In this work, we propose a well-designed blind face restoration network with generative facial prior. The proposed network is mainly comprised of an asymmetric codec and StyleGAN2 prior network. In the asymmetric codec, we adopt a mixed multi-path residual block (MMRB) to gradually extract weak texture features of input images, which can improve the texture integrity and authenticity of our networks. Furthermore, the MMRB block can also be plugand-play in any other network. Besides, a novel self-supervised training strategy is specially designed for face restoration tasks to fit the distribution closer to the target and maintain training stability. Extensive experiments over synthetic and real-world datasets demonstrate that our model achieves superior performance to the prior art for face restoration and face superresolution tasks and can tackle seriously degraded face images in diverse poses and expressions.

show abstract

“…However, most of them did not consider the identity information of the face images or did not fully consider two similar tasks, face hallucination and face recognition, together. The identity information contains identity-aware details which is essential for boosting down-stream face recognition accuracy after reconstruction (Jiang et al, 2021).…”

Section: Identity-aware Face Hallucinationmentioning

confidence: 99%

C-Face: Using Compare Face on Face Hallucination for Low-Resolution Face Recognition

Hong¹,

Wang²,

Shen³

et al. 2022

jair

View full text Add to dashboard Cite

Face hallucination is a task of generating high-resolution (HR) face images from low-resolution (LR) inputs, which is a subfield of the general image super-resolution. However, most of the previous methods only consider the visual effect, ignoring how to maintain the identity of the face. In this work, we propose a novel face hallucination model, called C-Face network, which can generate HR images with high visual quality while preserving the identity information. A face recognition network is used to extract the identity features in the training process. In order to make the reconstructed face images keep the identity information to a great extent, a novel metric, i.e., C-Face loss, is proposed. We also propose a new training algorithm to deal with the convergence problem. Moreover, since our work mainly focuses on the recognition accuracy of the output, we integrate face recognition into the face hallucination process which ensures that the model can be used in real scenarios. Extensive experiments on two large scale face datasets demonstrate that our C-Face network has the best performance compared with other state-of-the-art methods.

show abstract

Deep Learning-based Face Super-resolution: A Survey

Cited by 101 publications

References 175 publications

Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution

Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution

Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior

C-Face: Using Compare Face on Face Hallucination for Low-Resolution Face Recognition

Contact Info

Product

Resources

About