An authentic face restoration system is becoming increasingly demanding in many computer vision applications, e.g., image enhancement, video communication, and taking portrait. Most of the advanced face restoration models can recover high-quality faces from low-quality ones but usually fail to faithfully generate realistic and high-frequency details that are favored by users. To achieve authentic restoration, we propose $\textbf{IDM}$, an $\textbf{I}$teratively learned face restoration system based on denoising $\textbf{D}$iffusion $\textbf{M}$odels (DDMs). We define the criterion of an authentic face restoration system, and argue that denoising diffusion models are naturally endowed with this property from two aspects: intrinsic iterative refinement and extrinsic iterative enhancement. Intrinsic learning can preserve the content well and gradually refine the high-quality details, while extrinsic enhancement helps clean the data and improve the restoration task one step further. We demonstrate superior performance on blind face restoration tasks. Beyond restoration, we find the authentically cleaned data by the proposed restoration system is also helpful to image generation tasks in terms of training stabilization and sample quality. Without modifying the models, we achieve better quality than state-of-the-art on FFHQ and ImageNet generation using either GANs or diffusion models.
AuthFace: Towards Authentic Blind Face Restoration with Face-oriented Generative Diffusion Prior
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；vivo Mobile Communication Co., Ltd（vivo移动通信有限公司）；Nanyang Technological University（南洋理工大学）
Unified Image Restoration and Enhancement: Degradation Calibrated Cycle Reconstruction Diffusion Model
College of Computer Science and Engineering, Chongqing University of Technology（重庆理工大学计算机科学与工程学院）；School of Science, Engineering and Environment, University of Salford（索尔福德大学科学、工程与环境学院）；College of Computer Science, Chongqing University（重庆大学计算机学院）
A Generative Data Framework with Authentic Supervision for Underwater Image Restoration and Enhancement
Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）；Department of Automation, Shanghai Jiao Tong University（自动化系，上海交通大学）；School of Artificial Intelligence, Optics and ElectroNics (iOPEN), Northwestern Polytechnical University（人工智能、光学与电子学学院（iOPEN），西北工业大学）；Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences（西安光学精密机械研究所，中国科学院）
With more advanced deep network architectures and learning schemes such as GANs, the performance of video restoration algorithms has greatly improved recently. Meanwhile, the loss functions for optimizing deep neural networks remain relatively unchanged. To this end, we propose a new framework for building effective loss functions by learning a discriminative space specific to a video restoration task. Our framework is similar to GANs in that we iteratively train two networks - a generator and a loss network. The generator learns to restore videos in a supervised fashion, by following ground t…
Supervise-assisted Multi-modality Fusion Diffusion Model for PET Restoration
Beijing Institute of Technology（北京理工大学）；Research and Development Center of Agricultural Bank of China（中国农业银行研发中心）；Peking University（北京大学）；Beijing Normal University（北京师范大学）
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）
Mi-Ripple: Restoring Images Degraded by Iterative AI Editing
Miyang Technology (Shanghai) Co., Ltd.（米扬科技（上海）有限公司）；Key Laboratory of System Software (Chinese Academy of Sciences)（中国科学院系统软件重点实验室）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）；Tianjin University（天津大学）
Enhancing Diffusion Model Stability for Image Restoration via Gradient Management
College of Computer Science, Sichuan University（四川大学计算机学院）；National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University（合成视觉基础科学国家重点实验室（四川大学））；Engineering Research Center of Machine Learning（机器学习工程研究中心）
College of Medicine and Biological Information Engineering, Northeastern University（东北大学医学与生物信息工程学院）；Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education（教育部医学影像智能计算重点实验室）；Department of Electrical and Computer Engineering, Stevens Institute of Technology（史蒂文斯理工学院电气与计算机工程系）
The iterative weighted shrinkage-thresholding algorithm (IWSTA) has shown superiority to the classic unweighted iterative shrinkage-thresholding algorithm (ISTA) for solving linear inverse problems, which address the attributes differently. This paper proposes a new entropy regularized IWSTA (ERIWSTA) that adds an entropy regularizer to the cost function to measure the uncertainty of the weights to stimulate attributes to participate in problem solving. Then, the weights are solved with a Lagrange multiplier method to obtain a simple iterative update. The weights can be explained as the probab…
FADRA: Frequency-Aware Diffusion with Residual Adaptation for Video Face Restoration
United Arab Emirates University (UAEU)（阿联酋大学）；Ocean University of China (OUC)（中国海洋大学）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）
Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration
Samsung AI Center Cambridge（三星剑桥人工智能中心）；National Taiwan University（国立台湾大学）；Technical University of Iasi（雅西科技大学）；Chang Gung University（长庚大学）；University of Wurzburg（维尔茨堡大学）；Queen Mary University of London（伦敦玛丽女王大学）
The problem of restoration of digital images from their degraded measurements plays a central role in a multitude of practically important applications. A particularly challenging instance of this problem occurs in the case when the degradation phenomenon is modeled by an ill-conditioned operator. In such a case, the presence of noise makes it impossible to recover a valuable approximation of the image of interest without using some a priori information about its properties. Such a priori information is essential for image restoration, rendering it stable and robust to noise. Particularly, if …
Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家科学研究中心）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工大学）；LJK（实验室）；MaLGa Centre（MaLGa中心）；DIBRIS（DIBRIS研究所）；Università di Genova（热那亚大学）；MMS（MMS机构）；Italian Institute of Technology（意大利理工学院）
Microsoft Research（微软研究院）；Sony Electronics Inc（索尼电子公司）；Purdue University at West Lafayette（普渡大学西拉法叶分校）
The inherent noise in the observed (e.g., scanned) binary document image degrades the image quality and harms the compression ratio through breaking the pattern repentance and adding entropy to the document images. In this paper, we design a cost function in Bayesian framework with dictionary learning. Minimizing our cost function produces a restored image which has better quality than that of the observed noisy image, and a dictionary for representing and encoding the image. After the restoration, we use this dictionary (from the same cost function) to encode the restored image following the …
The problem of reconstruction of digital images from their degraded measurements is regarded as a problem of central importance in various fields of engineering and imaging sciences. In such cases, the degradation is typically caused by the resolution limitations of an imaging device in use and/or by the destructive influence of measurement noise. Specifically, when the noise obeys a Poisson probability law, standard approaches to the problem of image reconstruction are based on using fixed-point algorithms which follow the methodology first proposed by Richardson and Lucy. The practice of usi…
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 …
RIKEN Center for Advanced Intelligence Project (AIP)（理化学研究所先进智能项目中心）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Paradigm Inc.（第四范式有限公司）；Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究生院）；LISMARS, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）
Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) restoration, which includes the tasks of denoising, compressed HSI reconstruction and inpainting. Unfortunately, while its restoration performance benefits from more spectral bands, its runtime also substantially increases. In this paper, we claim that the HSI lies in a global spectral low-rank subspace, and the spectral subspaces of each full band patch group should lie in this global low-rank subspace. This motivates us to propose a unified paradigm combining the spatial and …
This article describes a fast iterative algorithm for image denoising and deconvolution with signal-dependent observation noise. We use an optimization strategy based on variable splitting that adapts traditional Gaussian noise-based restoration algorithms to account for the observed image being corrupted by mixed Poisson-Gaussian noise and quantization errors.
Deep neural networks (DNNs) have shown very promising results for various image restoration (IR) tasks. However, the design of network architectures remains a major challenging for achieving further improvements. While most existing DNN-based methods solve the IR problems by directly mapping low quality images to desirable high-quality images, the observation models characterizing the image degradation processes have been largely ignored. In this paper, we first propose a denoising-based IR algorithm, whose iterative steps can be computed efficiently. Then, the iterative process is unfolded in…
CMAMRNet: A Contextual Mask-Aware Network Enhancing Mural Restoration Through Comprehensive Mask Guidance
University of Macau（澳门大学）；Guangdong University of Technology（广东工业大学）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）；Shenzhen Polytechnic University（深圳职业技术大学）
Beijing Institute of Technology（北京理工大学）；National Institute of Informatics（国立信息学研究所）
A series of methods have been proposed to reconstruct an image from compressively sensed random measurement, but most of them have high time complexity and are inappropriate for patch-based compressed sensing capture, because of their serious blocky artifacts in the restoration results. In this paper, we present a non-iterative image reconstruction method from patch-based compressively sensed random measurement. Our method features two cascaded networks based on residual convolution neural network to learn the end-to-end full image restoration, which is capable of reconstructing image patches …
University of Electronic Science and Technology of China（中国电子科技大学）
Recovering a large matrix from limited measurements is a challenging task arising in many real applications, such as image inpainting, compressive sensing and medical imaging, and this kind of problems are mostly formulated as low-rank matrix approximation problems. Due to the rank operator being non-convex and discontinuous, most of the recent theoretical studies use the nuclear norm as a convex relaxation and the low-rank matrix recovery problem is solved through minimization of the nuclear norm regularized problem. However, a major limitation of nuclear norm minimization is that all the sin…
This paper presents a scalable approximate Bayesian method for image restoration using total variation (TV) priors. In contrast to most optimization methods based on maximum a posteriori estimation, we use the expectation propagation (EP) framework to approximate minimum mean squared error (MMSE) estimators and marginal (pixel-wise) variances, without resorting to Monte Carlo sampling. For the classical anisotropic TV-based prior, we also propose an iterative scheme to automatically adjust the regularization parameter via expectation-maximization (EM). Using Gaussian approximating densities wi…
Unified Restoration-Perception Learning: Maritime Infrared-Visible Image Fusion and Segmentation
Laboratory of Underwater Acoustic Communication and Marine Information Technology, Ministry of Education, Xiamen University（厦门大学水声通信与海洋信息技术教育部重点实验室）；PAMI Research Group, Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系PAMI研究组）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区网络空间安全学院）
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…
DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration
School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；Shenzhen Research Institute of Northwestern Polytechnical University（西北工业大学深圳研究院）；State Key Laboratory of Internet of Things for Smart City, University of Macau（澳门大学智慧城市物联网国家重点实验室）
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…
Shanghai Jiao Tong University（上海交通大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Shanghai AI Laboratory（上海人工智能实验室）
Blind face restoration usually synthesizes degraded low-quality data with a pre-defined degradation model for training, while more complex cases could happen in the real world. This gap between the assumed and actual degradation hurts the restoration performance where artifacts are often observed in the output. However, it is expensive and infeasible to include every type of degradation to cover real-world cases in the training data. To tackle this robustness issue, we propose Diffusion-based Robust Degradation Remover (DR2) to first transform the degraded image to a coarse but degradation-inv…
MeInTime: Bridging Age Gap in Identity-Preserving Face Restoration
Beijing University of Posts and Telecommunications（北京邮电大学）；Department of Computer Science and Technology, Institute for AI, Tsinghua University（清华大学计算机科学与技术系，人工智能研究院）；Minzu University of China（民族大学）；Xiaomi Corporation（小米公司）
Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration
Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；School of Computing and Information Sciences, Saint Francis University（圣芳济大学计算与信息科学学院）；School of Engineering, Huaqiao University（华侨大学工程学院）；School of Information Science and Engineering, Huaqiao University（华侨大学信息科学与工程学院）
