通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2602.21917cs.CV
扫描簇，而非像素：一种以簇为中心的高效超高清图像修复范式
Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration
National University of Defense Technology（国防科技大学）；HKUST(GZ)（香港理工大学）；Qilu University of Technology（青岛科技大学）；Technical University of Munich（慕尼黑技术大学）；TeleAI, China Telecom（TeleAI，中国电信）；Beihang University（北航）
Ultra-High-Definition (UHD) image restoration is trapped in a scalability crisis: existing models, bound to pixel-wise operations, demand unsustainable computation. While state space models (SSMs) like Mamba promise linear complexity, their pixel-serial scanning remains a fundamental bottleneck for the millions of pixels in UHD content. We ask: must we process every pixel to understand the image? This paper introduces C$^2$SSM, a visual state space model that breaks this taboo by shifting from pixel-serial to cluster-serial scanning. Our core discovery is that the rich feature distribution of a UHD image can be distilled into a sparse set of semantic centroids via a neural-parameterized mixture model. C$^2$SSM leverages this to reformulate global modeling into a novel dual-path process: it scans and reasons over a handful of cluster centers, then diffuses the global context back to all pixels through a principled similarity distribution, all while a lightweight modulator preserves fine details. This cluster-centric paradigm achieves a decisive leap in efficiency, slashing computational costs while establishing new state-of-the-art results across five UHD restoration tasks. More than a solution, C$^2$SSM charts a new course for efficient large-scale vision: scan clusters, not pixels.
RCL-Mamba: A Dual-domain State Space Model for Measurement-oriented Image Restoration in Rotational Sparse-View Scanning Computed Laminography
Key Laboratory of Optoelectronic Technology and Systems, Ministry of Education, Chongqing University（重庆大学光电技术及系统教育部重点实验室）；Engineering Research Center of Industrial CT Nondestructive Testing, Ministry of Education, Chongqing University（重庆大学工业CT无损检测教育部工程研究中心）
Digital scans of analogue photographic film typically contain artefacts such as dust and scratches. Automated removal of these is an important part of preservation and dissemination of photographs of historical and cultural importance. While state-of-the-art deep learning models have shown impressive results in general image inpainting and denoising, film artefact removal is an understudied problem. It has particularly challenging requirements, due to the complex nature of analogue damage, the high resolution of film scans, and potential ambiguities in the restoration. There are no publicly av…
DSwinIR: Rethinking Window-based Attention for Image Restoration
School of Computer Science and Technology, Harbin Institute of Technology（计算机科学与技术学院，哈尔滨工业大学）；School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（计算机科学与技术学院，哈尔滨工业大学（深圳））
Traffic Image Restoration under Adverse Weather via Frequency-Aware Mamba
School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；College of Electronic Science, Air Force Aviation University（空军航空大学电子科学学院）；Intelligent Visual Information Perception Laboratory, Institute of Advanced Technology, Nanjing University of Posts and Telecommunications（南京邮电大学先进技术研究院智能视觉信息感知实验室）；School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）
Learning Adaptive Dynamical Features via Multi-$τ$ Liquid-Mamba for All-in-one Image Restoration
Department of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学与技术系）；Department of Architecture and Design, Harbin Institute of Technology（哈尔滨工业大学建筑与设计系）
Pathology Image Restoration via Mixture of Prompts
ShanghaiTech University（上海科技大学）；Shanghai Jiao Tong University（上海交通大学）；Shanghai Clinical Research and Trial Center（上海临床研究与试验中心）；Nanjing University of Information Science and Technology（南京信息工程大学）
London Centre for Nanotechnology, University College London, London, United Kingdom（伦敦纳米技术中心，伦敦大学学院，英国）；Department of Electronic and Electrical Engineering, University College London, London, United Kingdom（电子与电气工程系，伦敦大学学院，英国）；University of Trieste, Trieste, Italy（特里斯特大学，意大利）
Scanning tunnelling microscopy (STM) enables atomic-resolution imaging and atom manipulation, but its utility is often limited by tip degradation and slow serial data acquisition. Fabrication adds another layer of complexity since the tip is often subjected to large voltages, which may alter the shape of its apex, requiring it to be conditioned. Here, we propose a machine learning (ML) approach for image repair and super-resolution to alleviate both challenges. Using a dataset of only 36 pristine experimental images of Si(001):H, we demonstrate that a physics-informed synthetic data generation…
Multi-dimensional Visual Prompt Enhanced Image Restoration via Mamba-Transformer Aggregation
School of Digital Industry, Jiangxi Normal University（江西师范大学数字产业学院）；School of Computer and Information Engineering, Jiangxi Normal University（江西师范大学计算机与信息工程学院）
Nankai International Advanced Research Institute（南开大学国际高等研究院）；Peng Cheng Laboratory（鹏城实验室）；College of Computer Science, Nankai University（南开大学计算机学院）；University of Science and Technology Beijing（北京科技大学）；University of Macau（澳门大学）
Tsinghua University（清华大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Shanghai Jiao Tong University（上海交通大学）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen University（深圳大学）；Peng Cheng Laboratory（鹏城实验室）；ETH Zürich（苏黎世联邦理工学院）
EpiAgent: An Agent-Centric System for Ancient Inscription Restoration
School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其跨学科应用关键实验室（东南大学），教育部，中国）；Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China（计算机网络与信息集成关键实验室（东南大学），教育部，中国）；Nanjing University Museum, Nanjing University, China（南京大学博物馆，南京大学，中国）；The China Centre for Linguistic and Strategic Studies, Nanjing University, China（中国语言战略研究中心，南京大学，中国）
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 …
Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising
Hefei University of Technology（合肥工业大学）；Hangzhou Dianzi University（杭州电子科技大学）；Jinan University（暨南大学）；South China Agricultural University（华南农业大学）；The University of Tokyo（东京大学）
We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denoising synthetic Monte Carlo images, and reconstruction of undersampled MRI scans -- all corrupted by different proces…
An Efficient and Mixed Heterogeneous Model for Image Restoration
MAC Lab, Xiamen University, China（厦门大学）；National University of Singapore, Singapore（新加坡国立大学）；Smart City Research Institute, China Electronics Technology Group Corporation, China（中国电子科技集团有限公司智慧城市研究院）
Since convolutional neural networks perform well in learning generalizable image priors from large-scale data, these models have been widely used in image denoising tasks. However, the computational complexity increases dramatically as well on complex model. In this paper, We propose a novel lightweight Complementary Attention Module, which includes a density module and a sparse module, which can cooperatively mine dense and sparse features for feature complementary learning to build an efficient lightweight architecture. Moreover, to reduce the loss of details caused by denoising, this paper …
HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration
Hawkes Institute, UCL（UCL哈维斯研究所）；Dept. of Medical Physics and Biomedical Engineering, UCL（UCL医学物理与生物医学工程系）；Dept. of Computer Science, UCL（UCL计算机科学系）；Centre for AI, DS&AI, AstraZeneca, UK（阿斯利康AI中心）
Institute of Computer Science, University of Tartu（塔尔图大学计算机科学研究所）；Wellcome Sanger Institute（惠康桑格研究所）；PerkinElmer Cellular Technologies（珀金埃尔默细胞技术公司）
Biomedical images are noisy. The imaging equipment itself has physical limitations, and the consequent experimental trade-offs between signal-to-noise ratio, acquisition speed, and imaging depth exacerbate the problem. Denoising is, therefore, an essential part of any image processing pipeline, and convolutional neural networks are currently the method of choice for this task. One popular approach, Noise2Noise, does not require clean ground truth, and instead, uses a second noisy copy as a training target. Self-supervised methods, like Noise2Self and Noise2Void, relax data requirements by lear…
Physical photographs now can be conveniently scanned by smartphones and stored forever as a digital version, yet the scanned photos are not restored well. One solution is to train a supervised deep neural network on many digital photos and the corresponding scanned photos. However, it requires a high labor cost, leading to limited training data. Previous works create training pairs by simulating degradation using image processing techniques. Their synthetic images are formed with perfectly scanned photos in latent space. Even so, the real-world degradation in smartphone photo scanning remains …
University of California, Berkeley（加州大学伯克利分校）；Glidewell Dental Labs（格莱德威尔牙科实验室）
Computer vision has advanced significantly that many discriminative approaches such as object recognition are now widely used in real applications. We present another exciting development that utilizes generative models for the mass customization of medical products such as dental crowns. In the dental industry, it takes a technician years of training to design synthetic crowns that restore the function and integrity of missing teeth. Each crown must be customized to individual patients, and it requires human expertise in a time-consuming and labor-intensive process, even with computer-assiste…
JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration
Xiamen University（厦门大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Bytedance’s Pico（字节跳动Pico）；Tencent（腾讯）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；The Chinese University of Hong Kong（香港中文大学）
MedROI: Codec-Agnostic Region of Interest-Centric Compression for Medical Images
Division of Computer Engineering, Hankuk University of Foreign Studies（韩国外国语大学计算机工程系）；Department of Computer Science and Engineering, Hankuk University of Foreign Studies（韩国外国语大学计算机科学与工程系）
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）
GARD: Gamma-based Anatomical Restoration and Denoising for Retinal OCT
Christian Doppler Laboratory for Artificial Intelligence in Retina, Center for Medical Data Science, Medical University of Vienna, 1090 Vienna, Austria（人工视网膜人工智能实验室，医学数据科学中心，维也纳医科大学）；Institute of Artificial Intelligence, Center for Medical Data Science, Medical University of Vienna, 1090 Vienna, Austria（人工智能研究所，医学数据科学中心，维也纳医科大学）
Instituto de Matemática e Estatística, Universidade de São Paulo（圣保罗大学数学与统计研究所）；Universidade Federal de São Carlos（圣卡洛斯联邦大学）；Mayo Clinic College of Medicine（梅奥诊所医学院）；Universidade Federal de Alagoas（阿拉戈斯联邦大学）
Vibro-acoustography (VA) is a medical imaging method based on the difference-frequency generation produced by the mixture of two focused ultrasound beams. VA has been applied to different problems in medical imaging such as imaging bones, microcalcifications in the breast, mass lesions, and calcified arteries. The obtained images may have a resolution of 0.7--0.8 mm. Current VA systems based on confocal or linear array transducers generate C-scan images at the beam focal plane. Images on the axial plane are also possible, however the system resolution along depth worsens when compared to the l…
