The State Key Lab for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；Australian National University（澳大利亚国立大学）；Imperial College London（伦敦帝国理工学院）；Tencent（腾讯）
Face Restoration (FR) aims to restore High-Quality (HQ) faces from Low-Quality (LQ) input images, which is a domain-specific image restoration problem in the low-level computer vision area. The early face restoration methods mainly use statistical priors and degradation models, which are difficult to meet the requirements of real-world applications in practice. In recent years, face restoration has witnessed great progress after stepping into the deep learning era. However, there are few works to systematically study the deep learning based face restoration methods. Thus, in this paper, we provide a comprehensive survey of recent advances in deep learning techniques for face restoration. Specifically, we first summarize different problem formulations and analyze the characteristics of face images. Second, we discuss the challenges of face restoration. With regard to these challenges, we present a comprehensive review of recent FR methods, including prior-based methods and deep-learning methods. Then, we explore developed techniques in the task of FR covering network architectures, loss functions, and benchmark datasets. We also conduct a systematic benchmark evaluation on representative methods. Finally, we discuss the future directions including network designs, metrics, benchmark datasets, applications, etc. We also provide an open source repository for all the discussed methods, which is available at https://github.com/TaoWangzj/Awesome-Face-Restoration.
Image degradation due to atmospheric turbulence is common while capturing images at long ranges. To mitigate the degradation due to turbulence which includes deformation and blur, we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image. The disentanglement is achieved by decomposing the distortion due to turbulence into blur and deformation components using deblur generator and deformation correction generator respectively. Two paths of restoration are implemented to regularize the disentanglemen…
University of Science and Technology of China（中国科学技术大学）
Face restoration from low resolution and noise is important for applications of face analysis recognition. However, most existing face restoration models omit the multiple scale issues in face restoration problem, which is still not well-solved in research area. In this paper, we propose a Sequential Gating Ensemble Network (SGEN) for multi-scale noise robust face restoration issue. To endow the network with multi-scale representation ability, we first employ the principle of ensemble learning for SGEN network architecture designing. The SGEN aggregates multi-level base-encoders and base-decod…
Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos
The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；ARC Lab, Tencent PCG（腾讯平台与内容事业群ARC实验室）；The Guangdong University of Technology（广东工业大学）；Texas A&M University（德克萨斯农工大学）
Survey on Deep Face Restoration: From Non-blind to Blind and Beyond
Beijing University of Posts and Telecommunications（北京邮电大学）；ETH Zürich（苏黎世联邦理工学院）；Shanghai University（上海大学）；Nanyang Technological University（南洋理工大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）；National Tsing Hua University（国立清华大学）
Civil Aviation Flight University of China（中国民用航空飞行学院）；University of Electronic Science and Technology of China（电子科技大学）；Institute of North Electronic Equipment（北方电子设备研究所）；Pensees Ptd Ltd（澎思科技有限公司）；Baidu Research（百度研究院）；Tencent AI Lab（腾讯人工智能实验室）；National University of Singapore（新加坡国立大学）
In real-world scenarios, many factors may harm face recognition performance, e.g., large pose, bad illumination,low resolution, blur and noise. To address these challenges, previous efforts usually first restore the low-quality faces to high-quality ones and then perform face recognition. However, most of these methods are stage-wise, which is sub-optimal and deviates from the reality. In this paper, we address all these challenges jointly for unconstrained face recognition. We propose an Multi-Degradation Face Restoration (MDFR) model to restore frontalized high-quality faces from the given l…
With the recent increase in intelligent CCTVs for visual surveillance, a new image degradation that integrates resolution conversion and synthetic rain models is required. For example, in heavy rain, face images captured by CCTV from a distance have significant deterioration in both visibility and resolution. Unlike traditional image degradation models (IDM), such as rain removal and superresolution, this study addresses a new IDM referred to as a scale-aware heavy rain model and proposes a method for restoring high-resolution face images (HR-FIs) from low-resolution heavy rain face images (LR…
Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey
School of Mathematical Sciences, Dalian University of Technology（大连理工大学数学科学学院）；Centre for Advances in Reliability and Safety, Hong Kong, China（香港可靠性与安全中心）；Hong Kong Polytechnic University（香港理工大学）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）
Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey
University of Science and Technology of China（科学技术大学）；National University of Singapore（国立新加坡大学）；Eastern Institute for Advanced Study（东部高级研究机构）；Microsoft Research Asia（微软亚洲研究院）
Shandong University of Traditional Chinese Medicine（山东中医药大学）；Nankai University（南开大学）；ShanghaiTech University（上海科技大学）；Taishan University（泰山学院）；United Imaging Co.（联影公司）
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-world and 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 fo…
Towards Real-world Video Face Restoration: A New Benchmark
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
Tianjin University（天津大学）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
The face super-resolution (FSR) task is to reconstruct high-resolution face images from low-resolution inputs. Recent works have achieved success on this task by utilizing facial priors such as facial landmarks. Most existing methods pay more attention to global shape and structure information, but less to local texture information, which makes them cannot recover local details well. In this paper, we propose a novel recurrent convolutional network based framework for face super-resolution, which progressively introduces both global shape and local texture information. We take full advantage o…
Inception Institute of Artificial Intelligence（英ception人工智能研究所）；Beijing Institute of Technology（北京理工大学）；Nvidia（英伟达）；University of California at Merced（加州大学默塞德分校）
In this paper, we propose an effective and efficient face deblurring algorithm by exploiting semantic cues via deep convolutional neural networks. As the human faces are highly structured and share unified facial components (e.g., eyes and mouths), such semantic information provides a strong prior for restoration. We incorporate face semantic labels as input priors and propose an adaptive structural loss to regularize facial local structures within an end-to-end deep convolutional neural network. Specifically, we first use a coarse deblurring network to reduce the motion blur on the input face…
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；School of Marine Science and Technology, Tianjin University（天津大学海洋科学与技术学院）；Tencent AI Lab（腾讯人工智能实验室）
Previous research on face restoration often focused on repairing a specific type of low-quality facial images such as low-resolution (LR) or occluded facial images. However, in the real world, both the above-mentioned forms of image degradation often coexist. Therefore, it is important to design a model that can repair LR occluded images simultaneously. This paper proposes a multi-scale feature graph generative adversarial network (MFG-GAN) to implement the face restoration of images in which both degradation modes coexist, and also to repair images with a single type of degradation. Based on …
A Comparative Study of Image Restoration Networks for General Backbone Network Design
University of Macau（澳门大学）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Chinese Academy of Sciences（中国科学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Shenzhen University of Advanced Technology（深圳先进技术大学）
Atmospheric turbulence deteriorates the quality of images captured by long-range imaging systems by introducing blur and geometric distortions to the captured scene. This leads to a drastic drop in performance when computer vision algorithms like object/face recognition and detection are performed on these images. In recent years, various deep learning-based atmospheric turbulence mitigation methods have been proposed in the literature. These methods are often trained using synthetically generated images and tested on real-world images. Hence, the performance of these restoration methods depen…
DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
State-of-the-art algorithms for imaging inverse problems (namely deblurring and reconstruction) are typically iterative, involving a denoising operation as one of its steps. Using a state-of-the-art denoising method in this context is not trivial, and is the focus of current work. Recently, we have proposed to use a class-adapted denoiser (patch-based using Gaussian mixture models) in a so-called plug-and-play scheme, wherein a state-of-the-art denoiser is plugged into an iterative algorithm, leading to results that outperform the best general-purpose algorithms, when applied to an image of a …
DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model
School of Information Engineering, Chang’an University（信息工程学院，长安大学）；School of Electronics and Information, Northwestern Polytechnical University（电子与信息学院，西北工业大学）
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；The Hong Kong Polytechnic University（香港理工大学）
In supervised image restoration tasks, one key issue is how to obtain the aligned high-quality (HQ) and low-quality (LQ) training image pairs. Unfortunately, such HQ-LQ training pairs are hard to capture in practice, and hard to synthesize due to the complex unknown degradation in the wild. While several sophisticated degradation models have been manually designed to synthesize LQ images from their HQ counterparts, the distribution gap between the synthesized and real-world LQ images remains large. We propose a new approach to synthesizing realistic image restoration training pairs using the e…
Universal Image Restoration via Internalized Chain-of-Thought Reasoning
Hong Kong JC Lab of Smart City and Department of Computer Science, City University of Hong Kong（香港城市大学智慧城市香港联合实验室及计算机科学系）；School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院）；Computer Science and Information Engineering, National Taiwan University（国立台湾大学计算机科学与信息工程学系）
The triangulation of images has become an active research area in recent years for its compressive representation and ease of image processing and visualization. However, little work has been done on how to faithfully recover image intensities from a triangulated mesh of an image, a process also known as image restoration or decoding from meshes. The existing methods such as linear interpolation, least-square interpolation, or interpolation based on radial basis functions (RBFs) work to some extent, but often yield blurred features (edges, corners, etc.). The main reason for this problem is du…
Image demoireing is a multi-faceted image restoration task involving both texture and color restoration. In this paper, we propose a novel multiscale bandpass convolutional neural network (MBCNN) to address this problem. As an end-to-end solution, MBCNN respectively solves the two sub-problems. For texture restoration, we propose a learnable bandpass filter (LBF) to learn the frequency prior for moire texture removal. For color restoration, we propose a two-step tone mapping strategy, which first applies a global tone mapping to correct for a global color shift, and then performs local fine tu…
Harnessing Diffusion-Yielded Score Priors for Image Restoration
Shenzhen Institute of Advanced Technology, CAS（深圳先进技术研究院，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；Hong Kong Metropolitan University（香港 Metropolitan 大学）；INSAIT, Sofia University（INSAIT，索菲亚大学）；Shenzhen Institutes of Advanced Technology, CAS（深圳先进技术研究院，中国科学院）；Shenzhen University of Advanced Technology（深圳大学先进技术学院）
TIDE: Two-Stage Inverse Degradation Estimation with Guided Prior Disentanglement for Underwater Image Restoration
Mohamed bin Zayed University of AI（莫扎德·本·泽亚德人工智能大学）；University of Amsterdam（阿姆斯特丹大学）；University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；Nagasaki University（长崎大学）
Blind face restoration usually encounters with diverse scale face inputs, especially in the real world. However, most of the current works support specific scale faces, which limits its application ability in real-world scenarios. In this work, we propose a novel scale-aware blind face restoration framework, named FaceFormer, which formulates facial feature restoration as scale-aware transformation. The proposed Facial Feature Up-sampling (FFUP) module dynamically generates upsampling filters based on the original scale-factor priors, which facilitate our network to adapt to arbitrary face sca…
School of Engineering, Universidad Autonoma de Madrid（马德里自治大学工程学院）
In this paper we develop FaceQgen, a No-Reference Quality Assessment approach for face images based on a Generative Adversarial Network that generates a scalar quality measure related with the face recognition accuracy. FaceQgen does not require labelled quality measures for training. It is trained from scratch using the SCface database. FaceQgen applies image restoration to a face image of unknown quality, transforming it into a canonical high quality image, i.e., frontal pose, homogeneous background, etc. The quality estimation is built as the similarity between the original and the restored…
Face restoration is an inherently ill-posed problem, where additional prior constraints are typically considered crucial for mitigating such pathology. However, real-world image prior are often hard to simulate with precise mathematical models, which inevitably limits the performance and generalization ability of existing prior-regularized restoration methods. In this paper, we study the problem of face restoration under a more practical ``dual blind'' setting, i.e., without prior assumptions or hand-crafted regularization terms on the degradation profile or image contents. To this end, a nove…
Super-resolution (SR) has become a widely researched topic in recent years. SR methods can improve overall image and video quality and create new possibilities for further content analysis. But the SR mainstream focuses primarily on increasing the naturalness of the resulting image despite potentially losing context accuracy. Such methods may produce an incorrect digit, character, face, or other structural object even though they otherwise yield good visual quality. Incorrect detail restoration can cause errors when detecting and identifying objects both manually and automatically. To analyze …
