Frequency-Aware Physics-Inspired Degradation Model for Real-World Image Super-Resolution
John Hopcroft Center for Computer Science, Shanghai Jiao Tong University（上海交通大学约翰·霍普克罗夫特计算机科学中心）；Institute of Image Communication and Network Engineering,Shanghai Jiao Tong University（上海交通大学图像通信与网络工程研究所）；Department of Electrical and Computer Engineering, University of Alabama（阿拉巴马大学电气与计算机工程系）；State Key Lab of Advanced Optical Communication Systems and Networks, Shanghai Jiao Tong University（上海交通大学先进光通信系统与网络国家重点实验室）
Zhenxing Dong, Hong Cao, Wang Shen, Yu Gan, Yuye Ling, Guangtao Zhai, Yikai Su
Current learning-based single image super-resolution (SISR) algorithms underperform on real data due to the deviation in the assumed degrada-tion process from that in the real-world scenario. Conventional degradation processes consider applying blur, noise, and downsampling (typicallybicubic downsampling) on high-resolution (HR) images to synthesize low-resolution (LR) counterparts. However, few works on degradation modelling have taken the physical aspects of the optical imaging system intoconsideration. In this paper, we analyze the imaging system optically andexploit the characteristics of the real-world LR-HR pairs in the spatial frequency domain. We formulate a real-world physics-inspired degradationmodel by considering bothopticsandsensordegradation; The physical degradation of an imaging system is modelled as a low-pass filter, whose cut-off frequency is dictated by the object distance, the focal length of thelens, and the pixel size of the image sensor. In particular, we propose to use a convolutional neural network (CNN) to learn the cutoff frequency of real-world degradation process. The learned network is then applied to synthesize LR images from unpaired HR images. The synthetic HR-LR image pairs are later used to train an SISR network. We evaluatethe effectiveness and generalization capability of the proposed degradation model on real-world images captured by different imaging systems. Experimental results showcase that the SISR network trained by using our synthetic data performs favorably against the network using the traditional degradation model. Moreover, our results are comparable to that obtained by the same network trained by using real-world LR-HR pairs, which are challenging to obtain in real scenes.
Physics-Inspired Degradation Models for Hyperspectral Image Fusion
Beijing Institute of Technology（北京理工大学）；Hunan University（湖南大学）；University of Science and Technology of China（中国科学技术大学）；Beijing Normal University（北京师范大学）
Causal Disentanglement-Inspired Degradation Representation Learning for Full-Reference Image Quality Assessment
School of Computing and Artificial Intelligence, Southwest Jiaotong University（计算机与人工智能学院，西南交通大学）；School of Transportation and Logistics, Southwest Jiaotong University（交通运输与物流学院，西南交通大学）；School of Physics, Northeast Normal University（物理学院，东北师范大学）；School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics（计算机与人工智能学院，江西财经大学）；School of Information Management, Jiangxi University of Finance and Economics（信息管理学院，江西财经大学）
Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能技术重点实验室）；Harbin Institute of Technology（哈尔滨工业大学）
Typical methods for blind image super-resolution (SR) focus on dealing with unknown degradations by directly estimating them or learning the degradation representations in a latent space. A potential limitation of these methods is that they assume the unknown degradations can be simulated by the integration of various handcrafted degradations (e.g., bicubic downsampling), which is not necessarily true. The real-world degradations can be beyond the simulation scope by the handcrafted degradations, which are referred to as novel degradations. In this work, we propose to learn a latent representa…
The HongKong Polytechnic University（香港理工大学）；Shenzhen Institute of Advanced Technology, CAS（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai AI Laboratory（上海人工智能实验室）
Degradation models play an important role in Blind super-resolution (SR). The classical degradation model, which mainly involves blur degradation, is too simple to simulate real-world scenarios. The recently proposed practical degradation model includes a full spectrum of degradation types, but only considers complex cases that use all degradation types in the degradation process, while ignoring many important corner cases that are common in the real world. To address this problem, we propose a unified gated degradation model to generate a broad set of degradation cases using a random gate con…
The HongKong Polytechnic University（香港理工大学）；OPPO Research（OPPO研究院）
Efficient and effective real-world image super-resolution (Real-ISR) is a challenging task due to the unknown complex degradation of real-world images and the limited computation resources in practical applications. Recent research on Real-ISR has achieved significant progress by modeling the image degradation space; however, these methods largely rely on heavy backbone networks and they are inflexible to handle images of different degradation levels. In this paper, we propose an efficient and effective degradation-adaptive super-resolution (DASR) network, whose parameters are adaptively speci…
Tsinghua University（清华大学）；ETH Zürich（苏黎世联邦理工学院）；ByteDance Inc（字节跳动公司）；University of Texas at Dallas（德克萨斯大学达拉斯分校）；University of Würzburg（维尔茨堡大学）
Blind image super-resolution (Blind-SR) aims to recover a high-resolution (HR) image from its corresponding low-resolution (LR) input image with unknown degradations. Most of the existing works design an explicit degradation estimator for each degradation to guide SR. However, it is infeasible to provide concrete labels of multiple degradation combinations (e.g., blur, noise, jpeg compression) to supervise the degradation estimator training. In addition, these special designs for certain degradation, such as blur, impedes the models from being generalized to handle different degradations. To t…
Blind super-resolution (SR) aims to recover high-quality visual textures from a low-resolution (LR) image, which is usually degraded by down-sampling blur kernels and additive noises. This task is extremely difficult due to the challenges of complicated image degradations in the real-world. Existing SR approaches either assume a predefined blur kernel or a fixed noise, which limits these approaches in challenging cases. In this paper, we propose a Degradation-guided Meta-restoration network for blind Super-Resolution (DMSR) that facilitates image restoration for real cases. DMSR consists of a …
Computer Vision Lab, ETH Zurich（苏黎世联邦理工学院计算机视觉实验室）；KU Leuven（比利时鲁汶大学）；Computer Vision Lab, ETH Zurich, Switzerland（苏黎世联邦理工学院计算机视觉实验室，瑞士）
It is widely acknowledged that single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images. Although several degradation models take additional factors into consideration, such as blur, they are still not effective enough to cover the diverse degradations of real images. To address this issue, this paper proposes to design a more complex but practical degradation model that consists of randomly shuffled blur, downsampling and noise degradations. Specifically, the blur is approximated by two convolutions with isotropic …
Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e.g., bicubic downsampling. However, these methods only learn the inverse process of the predetermined operation, so they fail to super resolve the real-world LR images; the true formulation deviates from the predetermined operation. To address this problem, we propose a novel supervised method to simulate an unknown degradation process with the inclusion of the prior hardware knowledge of the imaging …
Content-decoupled Contrastive Learning-based Implicit Degradation Modeling for Blind Image Super-Resolution
School of Control and Computer Engineering, North China Electric Power University（华北电力大学控制与计算机工程学院）；School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）
Single Image Super-Resolution (SISR) aims to generate a high-resolution (HR) image of a given low-resolution (LR) image. The most of existing convolutional neural network (CNN) based SISR methods usually take an assumption that a LR image is only bicubicly down-sampled version of an HR image. However, the true degradation (i.e. the LR image is a bicubicly downsampled, blurred and noisy version of an HR image) of a LR image goes beyond the widely used bicubic assumption, which makes the SISR problem highly ill-posed nature of inverse problems. To address this issue, we propose a deep SISR netwo…
Learning the Degradation Distribution for Blind Image Super-Resolution
University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；National Laboratory of Pattern Recognition (NLPR)（模式识别国家重点实验室）；Center for Research on Intelligent Perception and Computing (CRIPAC)（智能感知与计算研究中心）
Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；The University of Sydney（悉尼大学）；Shanghai AI Laboratory（上海人工智能实验室）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；ETH Zürich（苏黎世联邦理工学院）
Adaptive Blind Super-Resolution Network for Spatial-Specific and Spatial-Agnostic Degradations
VCIP, College of Computer Science, Nankai University, Tianjin, 300350, China（VCIP，计算机科学学院，南开大学，天津，300350，中国）；School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen 518107, P.R. China（网络安全科学与技术学院，深圳校区，中山大学，深圳 518107，中华人民共和国中国）；College of Artificial Intelligence, Nankai University, Tianjin, 300350, China（人工智能学院，南开大学，天津，300350，中国）；Laboratory of Science and Technology on Integrated Logistics Support, National University of Defense Technology, Changsha 410073, China（集成物流支持科学技术实验室，国防科技大学，长沙 410073，中国）
Deep Convolutional Neural Networks (CNNs) have achieved remarkable results on Single Image Super-Resolution (SISR). Despite considering only a single degradation, recent studies also include multiple degrading effects to better reflect real-world cases. However, most of the works assume a fixed combination of degrading effects, or even train an individual network for different combinations. Instead, a more practical approach is to train a single network for wide-ranging and variational degradations. To fulfill this requirement, this paper proposes a unified network to accommodate the variation…
Key Laboratory of Design Intelligence and Digital Creativity of Zhejiang Province, Zhejiang University（浙江大学浙江省设计智能与数字创意重点实验室）
In real-world single image super-resolution (SISR) task, the low-resolution image suffers more complicated degradations, not only downsampled by unknown kernels. However, existing SISR methods are generally studied with the synthetic low-resolution generation such as bicubic interpolation (BI), which greatly limits their performance. Recently, some researchers investigate real-world SISR from the perspective of the camera and smartphone. However, except the acquisition equipment, the display device also involves more complicated degradations. In this paper, we focus on the camera-screen degrad…
Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Peng Cheng Laboratory（鹏城实验室）；Tencent PCG（腾讯平台与内容事业群）；Shanghai AI Laboratory（上海人工智能实验室）
Interactive image restoration aims to restore images by adjusting several controlling coefficients, which determine the restoration strength. Existing methods are restricted in learning the controllable functions under the supervision of known degradation types and levels. They usually suffer from a severe performance drop when the real degradation is different from their assumptions. Such a limitation is due to the complexity of real-world degradations, which can not provide explicit supervision to the interactive modulation during training. However, how to realize the interactive modulation …
To overcome inherent hardware limitations of hyperspectral imaging systems with respect to their spatial resolution, fusion-based hyperspectral image (HSI) super-resolution is attracting increasing attention. This technique aims to fuse a low-resolution (LR) HSI and a conventional high-resolution (HR) RGB image in order to obtain an HR HSI. Recently, deep learning architectures have been used to address the HSI super-resolution problem and have achieved remarkable performance. However, they ignore the degradation model even though this model has a clear physical interpretation and may contribu…
LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，中国科学院自动化研究所）；North China Electric Power University（华北电力大学）；Beijing Jiaotong University（北京交通大学）；YunQue AGI, Hangzhou, China（云阙AGI，杭州，中国）
Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition
Xi’an University of Architecture and Technology（西安建筑科技大学）；Northwestern Polytechnical University（西北工业大学）；University of Macau（澳门大学）；Xi’an Institute of Optics and Precision Mechanics of CAS（中国科学院西安光学精密机械研究所）
Institute of Cyber-System and Control, Zhejiang University（浙江大学智能系统与控制研究所）；Ningbo Research Institute, Zhejiang University（浙江大学宁波研究院）；State Key Laboratory of Industrial Control Technology, Zhejiang University（浙江大学工业控制技术国家重点实验室）
In spite of the success on benchmark datasets, most advanced face super-resolution models perform poorly in real scenarios since the remarkable domain gap between the real images and the synthesized training pairs. To tackle this problem, we propose a novel domain-adaptive degradation network for face super-resolution in the wild. This degradation network predicts a flow field along with an intermediate low resolution image. Then, the degraded counterpart is generated by warping the intermediate image. With the preference of capturing motion blur, such a model performs better at preserving ide…
Expanding Synthetic Real-World Degradations for Blind Video Super Resolution
K|Lens GmbH（K|Lens有限公司）；Saarland Informatics Campus（萨尔兰信息学园区）；IIT Jammu（印度理工学院查谟分校）；MPI Informatics（马克斯·普朗克信息学研究所）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））
Remote sensing images (RSIs) in real scenes may be disturbed by multiple factors such as optical blur, undersampling, and additional noise, resulting in complex and diverse degradation models. At present, the mainstream SR algorithms only consider a single and fixed degradation (such as bicubic interpolation) and cannot flexibly handle complex degradations in real scenes. Therefore, designing a super-resolution (SR) model that can cope with various degradations is gradually attracting the attention of researchers. Some studies first estimate the degradation kernels and then perform degradation…
Optimal Transport Based Unsupervised Restoration Learning Exploiting Degradation Sparsity
School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, China（信息科学与电子工程学院，上海交通大学）；School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China（通信工程学院，杭州电子科技大学）
In this paper, we present a medical AttentIon Denoising Super Resolution Generative Adversarial Network (AID-SRGAN) for diographic image super-resolution. First, we present a medical practical degradation model that considers various degradation factors beyond downsampling. To the best of our knowledge, this is the first composite degradation model proposed for radiographic images. Furthermore, we propose AID-SRGAN, which can simultaneously denoise and generate high-resolution (HR) radiographs. In this model, we introduce an attention mechanism into the denoising module to make it more robust …
National University of Defense Technology（国防科技大学）；The University of Tokyo（东京大学）；RIKEN AIP（日本理化学研究所先进智能研究中心）
Most existing CNN-based super-resolution (SR) methods are developed based on an assumption that the degradation is fixed and known (e.g., bicubic downsampling). However, these methods suffer a severe performance drop when the real degradation is different from their assumption. To handle various unknown degradations in real-world applications, previous methods rely on degradation estimation to reconstruct the SR image. Nevertheless, degradation estimation methods are usually time-consuming and may lead to SR failure due to large estimation errors. In this paper, we propose an unsupervised degr…
East China Normal University（华东师范大学）；ETH Zürich（苏黎世联邦理工学院）；Huawei Technologies Ltd（华为技术有限公司）
Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution (LR) images of different degradation levels, which significantly restricts their practical deployments on resource-limited devices. In this paper, we propose a novel Dynamic Channel Splitting scheme for efficient Real-world Image Super-Resolution, termed DCS-RISR. Specifically, we first introduce the light degradation prediction network to regress the degradation vector to simulate …
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）
Unsupervised real world super resolution (USR) aims to restore high-resolution (HR) images given low-resolution (LR) inputs, and its difficulty stems from the absence of paired dataset. One of the most common approaches is synthesizing noisy LR images using GANs (i.e., degradation generators) and utilizing a synthetic dataset to train the model in a supervised manner. Although the goal of training the degradation generator is to approximate the distribution of LR images given a HR image, previous works have heavily relied on the unrealistic assumption that the conditional distribution is a del…
Harbin Institute of Technology（哈尔滨工业大学）；The Hong Kong Polytechnic University（香港理工大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from a high-resolution (HR) image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. Moreover, they lack scalability in learning a single model to non-blindly deal with multiple degradations. To address these issues, we propose a general framework with dimensionality stretching strategy th…
Beijing Normal University（北京师范大学）；Xidian University（西安电子科技大学）；Xinjiang Medical University（新疆医科大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）
Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally time-consuming and less effective, as the estimation of degradation proceeds from a blind initialization and lacks interpretable degradation priors. To address it, this paper proposes a transitional learning method for blind SR using an end-to-end network without any additional iterations in inference, and explores an effective representation for unknown degradation. To begin with, we analyze and demonstrate the tra…
PHISWID: Physics-Inspired Underwater Image Dataset Synthesized from RGB-D Images
Graduate School of Engineering, The University of Osaka（大阪大学工学研究科）；Graduate School of BASE, Tokyo University of Agriculture and Technology（东京大学农业技术大学院大学）
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）
Super-resolution and denoising are ill-posed yet fundamental image restoration tasks. In blind settings, the degradation kernel or the noise level are unknown. This makes restoration even more challenging, notably for learning-based methods, as they tend to overfit to the degradation seen during training. We present an analysis, in the frequency domain, of degradation-kernel overfitting in super-resolution and introduce a conditional learning perspective that extends to both super-resolution and denoising. Building on our formulation, we propose a stochastic frequency masking of images used in…
This paper proposes a biologically-inspired low-level spatiochromatic-model-based similarity method (BLeSS) to assist full-reference image-quality estimators that originally oversimplify color perception processes. More specifically, the spatiochromatic model is based on spatial frequency, spatial orientation, and surround contrast effects. The assistant similarity method is used to complement image-quality estimators based on phase congruency, gradient magnitude, and spectral residual. The effectiveness of BLeSS is validated using FSIM, FSIMc and SR-SIM methods on LIVE, Multiply Distorted LIV…
Youtu Lab, Tencent（腾讯优图实验室）；Shanghai Development Center of Computer Software Technology（上海计算机软件技术开发中心）
To achieve promising results on blind image super-resolution (SR), some attempts leveraged the low resolution (LR) images to predict the kernel and improve the SR performance. However, these Supervised Kernel Prediction (SKP) methods are impractical due to the unavailable real-world blur kernels. Although some Unsupervised Degradation Prediction (UDP) methods are proposed to bypass this problem, the \textit{inconsistency} between degradation embedding and SR feature is still challenging. By exploring the correlations between degradation embedding and SR feature, we observe that jointly learnin…
How to extract more and useful information for single image super resolution is an imperative and difficult problem. Learning-based method is a representative method for such task. However, the results are not so stable as there may exist big difference between the training data and the test data. The regularization-based method can effectively utilize the self-information of observation. However, the degradation model used in regularization-based method just considers the degradation in intensity space. It may not reconstruct images well as the degradation reflections in various feature space…
