Generative diffusion models are becoming one of the most popular prior in image restoration (IR) tasks due to their remarkable ability to generate realistic natural images. Despite achieving satisfactory results, IR methods based on diffusion models present several limitations. First of all, most non-blind approaches require an analytical expression of the degradation model to guide the sampling process. Secondly, most existing blind approaches rely on families of pre-defined degradation models for training their deep networks. The above issues limit the flexibility of these approaches and so their ability to handle real-world degradation tasks. In this paper, we propose a novel INN-guided probabilistic diffusion algorithm for non-blind and blind image restoration, namely INDIGO and BlindINDIGO, which combines the merits of the perfect reconstruction property of invertible neural networks (INN) with the strong generative capabilities of pre-trained diffusion models. Specifically, we train the forward process of the INN to simulate an arbitrary degradation process and use the inverse to obtain an intermediate image that we use to guide the reverse diffusion sampling process through a gradient step. We also introduce an initialization strategy, to further improve the performance and inference speed of our algorithm. Experiments demonstrate that our algorithm obtains competitive results compared with recently leading methods both quantitatively and visually on synthetic and real-world low-quality images.
TTTIR: Unlocking Instance-Specific State Evolution via Test-Time Training for Image Restoration
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Tsinghua University（清华大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；Shenzhen University（深圳大学）；Peng Cheng Laboratory（鹏城实验室）
Hong Kong Baptist University（香港浸会大学）；Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究院）；vivo Mobile Communication Co. Ltd（维沃移动通信有限公司）；City University of Hong Kong（香港城市大学）；Nanyang Technological University（南洋理工大学）
High Dynamic Range (HDR) imaging via multi-exposure fusion is an important task for most modern imaging platforms. In spite of recent developments in both hardware and algorithm innovations, challenges remain over content association ambiguities caused by saturation, motion, and various artifacts introduced during multi-exposure fusion such as ghosting, noise, and blur. In this work, we propose an Attention-guided Progressive Neural Texture Fusion (APNT-Fusion) HDR restoration model which aims to address these issues within one framework. An efficient two-stream structure is proposed which sep…
Recently, much attention has been spent on neural architecture search (NAS), aiming to outperform those manually-designed neural architectures on high-level vision recognition tasks. Inspired by the success, here we attempt to leverage NAS techniques to automatically design efficient network architectures for low-level image restoration tasks. In particular, we propose a memory-efficient hierarchical NAS (termed HiNAS) and apply it to two such tasks: image denoising and image super-resolution. HiNAS adopts gradient based search strategies and builds a flexible hierarchical search space, includ…
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）
University of Notre Dame（圣母大学）；University of Ljubljana（卢布尔雅那大学）
Advances in image restoration and enhancement techniques have led to discussion about how such algorithmscan be applied as a pre-processing step to improve automatic visual recognition. In principle, techniques like deblurring and super-resolution should yield improvements by de-emphasizing noise and increasing signal in an input image. But the historically divergent goals of the computational photography and visual recognition communities have created a significant need for more work in this direction. To facilitate new research, we introduce a new benchmark dataset called UG^2, which contain…
A Regularization-Guided Equivariant Approach for Image Restoration
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China（西安交通大学数学与统计学学院）；Macau University of Science and Technology, Taipa, Macao（澳门科学技术大学）；Pengcheng Laboratory, Shenzhen, China（鹏城实验室）
Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration
School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China（中山大学智能系统工程学院深圳校区）；Department of Frontier Research, Peng Cheng Laboratory, Shenzhen, Guangdong 518055, China（鹏城实验室前沿研究部）；Guangdong Provincial Key Laboratory of Fire Science and Technology, Guangzhou 510006, China（广东省消防科学与技术重点实验室）
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）
Nanyang Technological University（南洋理工大学）；University of Science and Technology of China（中国科学技术大学）；Nankai University（南开大学）
Image and video restoration has achieved a remarkable leap with the advent of deep learning. The success of deep learning paradigm lies in three key components: data, model, and loss. Currently, many efforts have been devoted to the first two while seldom study focuses on loss function. With the question ``are the de facto optimization functions e.g., $L_1$, $L_2$, and perceptual losses optimal?'', we explore the potential of loss and raise our belief ``learned loss function empowers the learning capability of neural networks for image and video restoration''. Concretely, we stand on the shoul…
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；ByteDance, Inc（字节跳动公司）；University of Science and Technology of China（中国科学技术大学）
Jiangxi Normal University（江西师范大学）；University of Science and Technology of China（中国科学技术大学）；East China Normal University（华东师范大学）；Beijing Jiaotong University（北京交通大学）
Lightweight Data-Free Denoising for Detail-Preserving Biomedical Image Restoration
School of Computation, Information and Technology, Technical University of Munich（计算信息学院，慕尼黑技术大学）；Helmholtz AI, Helmholtz Munich - German Research Center for Environmental Health（海德堡人工智能，海德堡-德国环境健康研究所以及研究中心）；School of Biomedical Engineering and Imaging Sciences, King’s College London（生物医学工程与成像科学学院，伦敦国王学院）
Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization
Mohamed bin Zayed University of Artificial Intelligence（莫扎德·本·泽德人工智能大学）；University of Trento（特伦托大学）；ETH Zürich（苏黎世联邦理工学院）；HKUST (GZ)（香港科技大学（广州））；Peking University（北京大学）；University of California, Merced（加州大学默塞德分校）
Deep learning can promote the mammography-based computer-aided diagnosis (CAD) for breast cancers, but it generally suffers from the small sample size problem. Self-supervised learning (SSL) has shown its effectiveness in medical image analysis with limited training samples. However, the network model sometimes cannot be well pre-trained in the conventional SSL framework due to the limitation of the pretext task and fine-tuning mechanism. In this work, a Task-driven Self-supervised Bi-channel Networks (TSBN) framework is proposed to improve the performance of classification model the mammograp…
We present a CNN-based predictive lossless compression scheme for raw color mosaic images of digital cameras. This specialized application problem was previously understudied but it is now becoming increasingly important, because modern CNN methods for image restoration tasks (e.g., superresolution, low lighting enhancement, deblurring), must operate on original raw mosaic images to obtain the best possible results. The key innovation of this paper is a high-order nonlinear CNN predictor of spatial-spectral mosaic patterns. The deep learning prediction can model highly complex sample dependenc…
University of Southern California（南加州大学）；Baidu Research (USA)（百度研究院（美国））
Normalizing flow models have been used successfully for generative image super-resolution (SR) by approximating complex distribution of natural images to simple tractable distribution in latent space through Invertible Neural Networks (INN). These models can generate multiple realistic SR images from one low-resolution (LR) input using randomly sampled points in the latent space, simulating the ill-posed nature of image upscaling where multiple high-resolution (HR) images correspond to the same LR. Lately, the invertible process in INN has also been used successfully by bidirectional image res…
TAT: Task-Adaptive Transformer for All-in-One Medical Image Restoration
School of Biological Science and Medical Engineering（生物科学与医学工程学院）；State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）；Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education（教育部生物力学与机力学重点实验室）；Beijing Advanced Innovation Center for Biomedical Engineering（北京生物医学工程先进创新中心）；Beihang University（北京航空航天大学）；Sinovision Technologies (Beijing) Co., Ltd.（北京视界科技有限公司）；ByteDance Inc.（字节跳动公司）
Normalizing flow models using invertible neural networks (INN) have been widely investigated for successful generative image super-resolution (SR) by learning the transformation between the normal distribution of latent variable $z$ and the conditional distribution of high-resolution (HR) images gave a low-resolution (LR) input. Recently, image rescaling models like IRN utilize the bidirectional nature of INN to push the performance limit of image upscaling by optimizing the downscaling and upscaling steps jointly. While the random sampling of latent variable $z$ is useful in generating divers…
Neural Architecture Search (NAS) for automatically finding the optimal network architecture has shown some success with competitive performances in various computer vision tasks. However, NAS in general requires a tremendous amount of computations. Thus reducing computational cost has emerged as an important issue. Most of the attempts so far has been based on manual approaches, and often the architectures developed from such efforts dwell in the balance of the network optimality and the search cost. Additionally, recent NAS methods for image restoration generally do not consider dynamic opera…
Position: Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；The University of Hong Kong（香港大学）；INSAIT, Sofia University ``St. Kliment Ohridski''（INSAIT，索菲亚大学『圣克莱孟·奥赫里迪斯』）；Shenzhen Loop Area Institute（深圳河套学院）；The Chinese University of Hong Kong（香港中文大学）；University of the Chinese Academy of Sciences（中国科学院大学）；Fudan University（复旦大学）；Shenzhen University of Advanced Technology（深圳先进技术大学）；Shanghai AI Laboratory（上海人工智能实验室）
University of Notre Dame（圣母大学）；Honeywell ACST（霍尼韦尔先进概念与科学技术（ACST））；Northwestern University（西北大学）；Zendar Co.（Zendar公司）；Texas A&M University（德克萨斯农工大学）；Peking University（北京大学）；National University of Singapore（新加坡国立大学）；National Tsing Hua University（国立清华大学）；Johns Hopkins University（约翰霍普金斯大学）；Noblis（诺布利斯（Noblis））
What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step to improve image interpretability for manual analysis or automatic visual recognition to classify scene content? While there have been important advances in the area of computational photography to restore or enhance the visual quality of an image, the capabilities of such techniques have not always translated in a useful way to visual recognition tasks. Consequently, there is a pressi…
The Third Challenge on Image Denoising at NTIRE 2026: Methods and Results
ETH Zurich（苏黎世联邦理工学院）；University of Würzburg（维尔茨堡大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Tianjin University（天津大学）；Nanjing University of Science and Technology（南京理工大学）；University of Beira Interior（贝拉内大学）；Siddaganga Institute of Technology（西达甘加理工学院）；National Institute of Technology Karnataka（卡纳塔克邦国立理工学院）；Sardar Vallabhbhai National Institute of Technology（萨达尔·瓦拉巴伊·帕特尔国立理工学院）；University of Luxembourg（卢森堡大学）；University of Twente（特温特大学）；University of Kragujevac（克拉古耶瓦茨大学）；Prince Sultan University（苏丹王子大学）；University of Tunis El Manar（突尼斯埃尔马纳尔大学）；University of Electronic Science and Technology of China（电子科技大学）；Wuhan University（武汉大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Peng Cheng Laboratory（鹏城实验室）
Haze-Aware Attention Network for Single-Image Dehazing
School of Ocean Information Engineering, Jimei University（集美大学海洋信息工程学院）；College of Artificial Intelligence, Southwest University（西南大学人工智能学院）；School of Computer Science, Jimei University（集美大学计算机科学学院）
FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Tsinghua University（清华大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）
Closed-Form Nonlocal Shrinkage for Multiplicative Image Denoising and SAR Despeckling
School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）；Kunshan Innovation Institute of Xidian University（西安电子科技大学昆山创新研究院）；University of Montenegro（黑山大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）；Macquarie University（麦考瑞大学）
