预训练扩散模型已革新了现实世界图像超分辨率（Real-ISR），但因迭代采样导致计算瓶颈。最近的单步蒸馏加速了推理，但面临感知-失真权衡的严峻挑战，由于固有的时间步初始化、分布轨迹不匹配和脆弱的随机调制。为此，我们提出了Adaptive Inversion和Degradation-aware Sampling for Real-ISR（IDaS-SR），一个连接确定性恢复和随机生成流形的单步框架。其核心是Manifold Inversion Noise Estimator（MINE），通过预测严重性感知的时间步和倒置噪声，精确地将低质量潜在映射到扩散轨迹上。此外，为缓解脆弱的随机调制，我们提出了CHARIOT，一种连续生成引导机制。通过重新调度轨迹和插值噪声，它使显式导航感知-失真边界而不影响结构先验。大量实验表明，IDaS-SR优于现有最先进方法，能够无缝从严格的结构恢复器过渡到复杂的纹理 hallucinator，在单步推理中实现。
英文摘要：
Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR), but their iterative sampling is computationally prohibitive, driving efforts to distill it into a single step. General one-step methods fine-tune the generative prior into a deterministic mapping, restoring efficiency but discarding its stochastic nature. Conversely, recent attempts re-engage generation by shifting the timestep or injecting random noise, adjusting either the position or the state while the other stays fixed. Because only one side is controlled, the two align at isolated preset timesteps but drift apart once steered, leaving generation unstable. To address this, we present one-step diffusion via Inversion and Degradation-aware Sampling for Real-ISR (IDaS-SR), a one-step framework that bridges deterministic restoration and stochastic generation. At its core, Manifold Anchoring grounds the low-quality latent on the pretrained trajectory through two operations jointly estimated by the Manifold Inversion Noise Estimator (MINE): positioning declares where the latent lies and how it deviates from the clean state, while inversion aligns the latent to the declared position. Upon the anchor, CHARIOT reintroduces controlled stochasticity by jointly rescheduling the trajectory and interpolating the noise, enabling a single scalar to smoothly navigate the fidelity-realism trade-off. Extensive experiments demonstrate that IDaS-SR effectively unleashes the generative prior, achieving state-of-the-art performance under explicit control in a single inference step.
Bridging Degradation Discrimination and Generation for Universal Image Restoration
Institute of Medical Technology, Peking University（北京大学医学技术学院）；Biomedical Engineering Department, College of Future Technology, Peking University（北京大学未来技术学院生物医学工程系）；National Biomedical Imaging Center, Peking University（北京大学国家生物医学成像中心）；China Mobile Research Institute（中国移动研究院）
V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration
The Hong Kong University of Science and Technology（香港科学与技术大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；The Chinese University of Hong Kong（香港中文大学）
IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China（脑启发智能感知与认知联合实验室，信息科学与技术学院，中国科学技术大学）
Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Tasks
School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区智能系统工程学院）；Guangdong Provincial Key Laboratory of Fire Science and Technology（广东省火灾科学与技术重点实验室）
Bridging the Gap Between Image Restoration and Navigational Safety in Hazy Conditions: A New Visibility Estimation Metric for Maritime Surveillance
Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya 572000, China（武汉理工大学三亚科学教育创新园，三亚572000，中国）；School of Navigation, Wuhan University of Technology, Wuhan 430063, China（武汉理工大学航海学院，武汉430063，中国）；State Key Laboratory of Maritime Technology and Safety, Wuhan University of Technology, Wuhan 430063, China（武汉理工大学海洋技术与安全国家重点实验室，武汉430063，中国）；Department of Mechanics and Maritime Sciences, Chalmers University of Technology, Göteborg 41296, Sweden（楚科奇大学机械与航海科学系，哥德堡41296，瑞典）
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）
Image Restoration Learning via Noisy Supervision in the Fourier Domain
Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电子与电气工程系）；Key Laboratory of Image Processing and Intelligent Control, Ministry of Education（教育部图像处理与智能控制重点实验室；华中科技大学人工智能与自动化学院）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology
ETH Zurich（苏黎世联邦理工学院）；Meta Inc.（Meta公司）；KU Leuven（鲁汶大学）
视频恢复（例如，视频超分辨率）旨在从低质量帧恢复高质量帧。与单个图像复原不同，视频复原通常需要利用来自多个相邻但通常未对准的视频帧的时间信息。现有的深度方法通常通过利用滑动窗口策略或递归架构来解决这个问题，这要么受到逐帧恢复的限制，要么缺乏长期建模能力。在本文中，我们提出了一个视频恢复Transformer（VRT）与并行帧预测和长期的时间依赖建模能力。更具体地说，VRT由多个尺度组成，每个尺度由两种类型的模块组成：时间相互自我注意（TMSA）和并行扭曲。TMSA将视频分割成小片段，在小片段上应用相互注意进行联合运动估计、特征对齐和特征融合，而自注意用于特征提取。为了启用跨剪辑交互，视频序列每隔一层移动一次。此外，并行变形被用来进一步融合信息从相邻帧的并行特征变形。在视频超分辨率、视频去模糊、视频去噪、视频帧内插和时空视频超分辨率等5个任务上的实验结果表明，VRT在14个基准数据集上的性能明显优于现有方法（$\textbf{up to 2.16dB}$）.
Microscopy Image Restoration using Deep Learning on W2S
EPFL（洛桑联邦理工学院）
我们利用深度学习技术来联合去噪和超分辨率荧光显微镜采集的生物医学图像。我们开发了一种基于最近W2S论文中描述的网络和方法的深度学习算法，以解决联合去噪和超分辨率问题。具体来说，我们解决SIM图像从宽视场图像的恢复。我们的TensorFlow模型是在W2S细胞图像数据集上训练的，可以在这个存储库中在线访问：https://github.com/mchatton/w2s-tensorflow。在测试图像上，该模型显示出视觉上令人信服的去噪效果，并将分辨率提高了两倍。对于512 $\times$ 512图像，推断在Titan X GPU上花费不到1秒，在普通CPU上花费大约15秒。我们进一步提出了在训练中使用的损失的不同变化的结果。
Bridging the Gap Between Computational Photography and Visual Recognition
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））
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）
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）
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
Nanyang Technological University（南洋理工大学）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
