Restoration
-
EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions
2026-03-26 07:56:18Taegyoon Yoon, Yegyu Han, Seojin Ji, Jaewoo Park, Sojeong Kim, Taein Kwon, Hyung-Sin KimAbstract
Smart glass is emerging as an useful device since it provides plenty of insights under hands-busy, eyes-on-task situations. To understand the context of the wearer, 6D object pose estimation in egocentric view is becoming essential. However, existing 6D object pose estimation benchmarks fail to capture the challenges of real-world egocentric applications, which are often dominated by severe motion blur, dynamic illumination, and visual obstructions. This discrepancy creates a significant gap between controlled lab data and chaotic real-world application. To bridge this gap, we introduce EgoXtreme, a new large-scale 6D pose estimation dataset captured entirely from an egocentric perspective. EgoXtreme features three challenging scenarios - industrial maintenance, sports, and emergency rescue - designed to introduce severe perceptual ambiguities through extreme lighting, heavy motion blur, and smoke. Evaluations of state-of-the-art generalizable pose estimators on EgoXtreme indicate that their generalization fails to hold in extreme conditions, especially under low light. We further demonstrate that simply applying image restoration (e.g., deblurring) offers no positive improvement for extreme conditions. While performance gain has appeared in tracking-based approach, implying using temporal information in fast-motion scenarios is meaningful. We conclude that EgoXtreme is an essential resource for developing and evaluating the next generation of pose estimation models robust enough for real-world egocentric vision. The dataset and code are available at this https URL
Abstract (translated)
智能眼镜正逐渐成为一种实用设备，因其在双手忙碌、眼睛需专注任务的场景中能提供大量洞察。为理解佩戴者的环境上下文，基于第一人称视角的6D物体姿态估计变得至关重要。然而，现有6D物体姿态估计基准数据集未能捕捉真实世界第一人称应用中的挑战，这些场景通常受严重运动模糊、动态光照和视觉遮挡的影响。这种差异造成了受控实验室数据与混乱现实应用之间的显著差距。为弥合这一差距，我们推出了EgoXtreme——一个全新的大规模6D姿态估计数据集，完全从第一人称视角采集。EgoXtreme涵盖三个具有挑战性的场景——工业维护、运动和紧急救援，旨在通过极端光照、严重运动模糊和烟雾引入强烈的感知歧义。在EgoXtreme上对最先进的可泛化姿态估计器进行评估表明，它们的泛化能力在极端条件下（尤其是低光照环境）无法保持。我们进一步证明，单纯应用图像修复（如去模糊）对极端条件并无积极改进。而基于跟踪的方法出现了性能提升，暗示在高速运动场景中利用时序信息具有意义。我们认为，EgoXtreme是开发和评估下一代足够稳健以应对真实世界第一人称视觉的姿态估计模型的重要资源。数据集与代码可通过此链接获取。
URL
https://arxiv.org/abs/2603.25135
PDF
-
CARE: Training-Free Controllable Restoration for Medical Images via Dual-Latent Steering
2026-03-26 04:43:28Xu LiuAbstract
Medical image restoration is essential for improving the usability of noisy, incomplete, and artifact-corrupted clinical scans, yet existing methods often rely on task-specific retraining and offer limited control over the trade-off between faithful reconstruction and prior-driven enhancement. This lack of controllability is especially problematic in clinical settings, where overly aggressive restoration may introduce hallucinated details or alter diagnostically important structures. In this work, we propose CARE, a training-free controllable restoration framework for real-world medical images that explicitly balances structure preservation and prior-guided refinement during inference. CARE uses a dual-latent restoration strategy, in which one branch enforces data fidelity and anatomical consistency while the other leverages a generative prior to recover missing or degraded information. A risk-aware adaptive controller dynamically adjusts the contribution of each branch based on restoration uncertainty and local structural reliability, enabling conservative or enhancement-focused restoration modes without additional model training. We evaluate CARE on noisy and incomplete medical imaging scenarios and show that it achieves strong restoration quality while better preserving clinically relevant structures and reducing the risk of implausible reconstructions and show that it achieves strong restoration quality while better preserving clinically relevant structures and reducing the risk of implausible reconstructions. The proposed approach offers a practical step toward safer, more controllable, and more deployment-ready medical image restoration.
Abstract (translated)
医学图像恢复对于提升含噪声、不完整及存在伪影的临床扫描图像的可用性至关重要，然而现有方法往往依赖任务特定的重训练，且在忠实重建与先验驱动增强之间的权衡上控制有限。这种缺乏可控性的问题在临床环境中尤为突出，因为过于激进的恢复可能引入幻觉细节或改变诊断关键结构。在本研究中，我们提出了CARE——一种面向真实世界医学图像的无训练可控恢复框架，能在推理过程中显式平衡结构保持与先验引导的细化。CARE采用双潜变量恢复策略：其中一个分支 enforcing 数据保真度与解剖一致性，另一分支则利用生成先验恢复缺失或退化信息。其风险感知自适应控制器能根据恢复不确定性与局部结构可靠性动态调整各分支贡献，从而在无需额外模型训练的情况下实现保守型或增强导向型恢复模式。我们在含噪声和不完整的医学成像场景中评估了CARE，结果表明该方法在实现高质量恢复的同时，能更好保留临床相关结构并降低不合理重建风险。所提出的方法为更安全、更可控且更易部署的医学图像恢复提供了实用进展。
URL
https://arxiv.org/abs/2603.25026
PDF
-
PASDiff: Physics-Aware Semantic Guidance for Joint Real-world Low-Light Face Enhancement and Restoration
2026-03-26 03:02:39Yilin Ni, Wenjie Li, Zhengxue Wang, Juncheng Li, Guangwei Gao, Jian YangAbstract
Face images captured in real-world low light suffer multiple degradations-low illumination, blur, noise, and low visibility, etc. Existing cascaded solutions often suffer from severe error accumulation, while generic joint models lack explicit facial priors and struggle to resolve clear face structures. In this paper, we propose PASDiff, a Physics-Aware Semantic Diffusion with a training-free manner. To achieve a plausible illumination and color distribution, we leverage inverse intensity weighting and Retinex theory to introduce photometric constraints, thereby reliably recovering visibility and natural chromaticity. To faithfully reconstruct facial details, our Style-Agnostic Structural Injection (SASI) extracts structures from an off-the-shelf facial prior while filtering out its intrinsic photometric biases, seamlessly harmonizing identity features with physical constraints. Furthermore, we construct WildDark-Face, a real-world benchmark of 700 low-light facial images with complex degradations. Extensive experiments demonstrate that PASDiff significantly outperforms existing methods, achieving a superior balance among natural illumination, color recovery, and identity consistency.
Abstract (translated)
在真实低光环境下采集的人脸图像常面临多重退化问题——光照不足、模糊、噪声及低可见度等。现有级联方案常因严重的误差累积而受限，而通用联合模型则缺乏显式的人脸先验知识，难以重建清晰的面部结构。本文提出一种无需训练的物理感知语义扩散模型PASDiff。为获得合理的光照与色彩分布，我们借助逆强度加权与Retinex理论引入光度约束，从而可靠恢复图像可见度与自然色度。为忠实重建面部细节，我们设计的风格无关结构注入模块（SASI）可从现成的人脸先验中提取结构特征，同时过滤其内在光度偏差，使身份特征与物理约束自然融合。此外，我们构建了包含700张复杂退化低光人脸图像的真实世界基准数据集WildDark-Face。大量实验表明，PASDiff显著优于现有方法，在自然光照、色彩恢复与身份一致性之间取得了优异平衡。
URL
https://arxiv.org/abs/2603.24969
PDF
-
InstanceRSR: Real-World Super-Resolution via Instance-Aware Representation Alignment
2026-03-25 12:27:58Zixin Guo, Kai Zhao, Luyan ZhangAbstract
Existing real-world super-resolution (RSR) methods based on generative priors have achieved remarkable progress in producing high-quality and globally consistent reconstructions. However, they often struggle to recover fine-grained details of diverse object instances in complex real-world scenes. This limitation primarily arises because commonly adopted denoising losses (e.g., MSE) inherently favor global consistency while neglecting instance-level perception and restoration. To address this issue, we propose InstanceRSR, a novel RSR framework that jointly models semantic information and introduces instance-level feature alignment. Specifically, we employ low-resolution (LR) images as global consistency guidance while jointly modeling image data and semantic segmentation maps to enforce semantic relevance during sampling. Moreover, we design an instance representation learning module to align the diffusion latent space with the instance latent space, enabling instance-aware feature alignment, and further incorporate a scale alignment mechanism to enhance fine-grained perception and detail recovery. Benefiting from these designs, our approach not only generates photorealistic details but also preserves semantic consistency at the instance level. Extensive experiments on multiple real-world benchmarks demonstrate that InstanceRSR significantly outperforms existing methods in both quantitative metrics and visual quality, achieving new state-of-the-art (SOTA) performance.
Abstract (translated)
现有基于生成先验的真实世界超分辨率（RSR）方法在生成高质量、全局一致的图像重建方面取得了显著进展。然而，它们在复杂真实场景中恢复多样目标实例的细粒度细节方面往往存在不足。这一局限性主要源于常用的去噪损失函数（如MSE）本质上倾向于全局一致性，而忽略了实例级的感知与修复。针对该问题，我们提出了InstanceRSR，一种新型RSR框架，通过联合建模语义信息并引入实例级特征对齐来解决问题。具体而言，我们采用低分辨率（LR）图像作为全局一致性指导，同时联合建模图像数据与语义分割图，以在采样过程中强化语义相关性。此外，我们设计了实例表征学习模块，将扩散隐空间与实例隐空间进行对齐，实现实例感知的特征对齐，并进一步引入尺度对齐机制以增强细粒度感知与细节恢复能力。得益于上述设计，我们的方法不仅能生成照片般真实的细节，还能在实例层面保持语义一致性。在多个真实场景基准数据集上的大量实验表明，InstanceRSR在定量指标与视觉质量上均显著优于现有方法，达到了新的最先进（SOTA）性能。
URL
https://arxiv.org/abs/2603.24240
PDF
-
High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking
2026-03-25 05:02:48Peipeng Yu, Jinfeng Xie, Chengfu Ou, Xiaoyu Zhou, Jianwei Fei, Yunshu Dai, Zhihua Xia, Chip Hong ChangAbstract
The proliferation of AIGC-driven face manipulation and deepfakes poses severe threats to media provenance, integrity, and copyright protection. Prior versatile watermarking systems typically rely on embedding explicit localization payloads, which introduces a fidelity--functionality trade-off: larger localization signals degrade visual quality and often reduce decoding robustness under strong generative edits. Moreover, existing methods rarely support content recovery, limiting their forensic value when original evidence must be reconstructed. To address these challenges, we present VeriFi, a versatile watermarking framework that unifies copyright protection, pixel-level manipulation localization, and high-fidelity face content recovery. VeriFi makes three key contributions: (1) it embeds a compact semantic latent watermark that serves as an content-preserving prior, enabling faithful restoration even after severe manipulations; (2) it achieves fine-grained localization without embedding localization-specific artifacts by correlating image features with decoded provenance signals; and (3) it introduces an AIGC attack simulator that combines latent-space mixing with seamless blending to improve robustness to realistic deepfake pipelines. Extensive experiments on CelebA-HQ and FFHQ show that VeriFi consistently outperforms strong baselines in watermark robustness, localization accuracy, and recovery quality, providing a practical and verifiable defense for deepfake forensics.
Abstract (translated)
AIGC驱动的人脸操作与深度伪造技术的泛滥，对媒体来源追溯、内容完整性和版权保护构成了严重威胁。此前通用的水印系统通常依赖嵌入显式的定位载荷，这引入了保真度-功能性权衡：更大的定位信号会降低视觉质量，并常在强生成性编辑下削弱解码鲁棒性。此外，现有方法极少支持内容恢复，限制了当原始证据必须重建时的取证价值。为应对这些挑战，我们提出了VeriFi，一个统一版权保护、像素级操作定位与高保真人脸内容恢复的通用水印框架。VeriFi的三项核心贡献包括：(1) 嵌入紧凑的语义隐式水印作为内容保持先验，即使在严重操作后也能忠实恢复；(2) 通过关联图像特征与解码的来源信号，在不嵌入定位特定伪影的情况下实现细粒度定位；(3) 引入结合隐空间混合与无缝融合的AIGC攻击模拟器，以提升对现实深度伪造流程的鲁棒性。在CelebA-HQ与FFHQ上的大量实验表明，VeriFi在水印鲁棒性、定位精度与恢复质量上持续优于强基线方法，为深度伪造取证提供了实用且可验证的防御方案。
URL
https://arxiv.org/abs/2603.23940
PDF
-
DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models
2026-03-24 17:59:13Jaewon Min, Jaeeun Lee, Yeji Choi, Paul Hyunbin Cho, Jin Hyeon Kim, Tae-Young Lee, Jongsik Ahn, Hwayeong Lee, Seonghyun Park, Seungryong KimAbstract
Optical flow models trained on high-quality data often degrade severely when confronted with real-world corruptions such as blur, noise, and compression artifacts. To overcome this limitation, we formulate Degradation-Aware Optical Flow, a new task targeting accurate dense correspondence estimation from real-world corrupted videos. Our key insight is that the intermediate representations of image restoration diffusion models are inherently corruption-aware but lack temporal awareness. To address this limitation, we lift the model to attend across adjacent frames via full spatio-temporal attention, and empirically demonstrate that the resulting features exhibit zero-shot correspondence capabilities. Based on this finding, we present DA-Flow, a hybrid architecture that fuses these diffusion features with convolutional features within an iterative refinement framework. DA-Flow substantially outperforms existing optical flow methods under severe degradation across multiple benchmarks.
Abstract (translated)
在高质量数据上训练的光流模型，在面对模糊、噪声和压缩伪影等真实世界退化时，性能往往会严重下降。为克服这一限制，我们提出了“退化感知光流”（Degradation-Aware Optical Flow）这一新任务，旨在从真实世界退化的视频中实现准确的稠密对应估计。我们的核心见解是：图像修复扩散模型的中间表示天然具备退化感知能力，但缺乏时序感知能力。为解决此问题，我们通过全时空注意力机制使模型能够跨相邻帧进行关注，并实证表明由此产生的特征具有零样本对应能力。基于这一发现，我们提出了DA-Flow——一种混合架构，它在迭代精炼框架内融合了这些扩散特征与卷积特征。在多个基准测试的严重退化场景下，DA-Flow的表现均显著优于现有光流方法。
URL
https://arxiv.org/abs/2603.23499
PDF
-
VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought
2026-03-24 09:40:50Xuanyu Zhang, Weiqi Li, Qunliang Xing, Jingfen Xie, Bin Chen, Junlin Li, Li Zhang, Jian Zhang, Shijie ZhaoAbstract
Video restoration in real-world scenarios is challenged by heterogeneous degradations, where static architectures and fixed inference pipelines often fail to generalize. Recent agent-based approaches offer dynamic decision making, yet existing video restoration agents remain limited by insufficient quality perception and inefficient search strategies. We propose VQ-Jarvis, a retrieval-augmented, all-in-one intelligent video restoration agent with sharper vision and faster thought. VQ-Jarvis is designed to accurately perceive degradations and subtle differences among paired restoration results, while efficiently discovering optimal restoration trajectories. To enable sharp vision, we construct VSR-Compare, the first large-scale video paired enhancement dataset with 20K comparison pairs covering 7 degradation types, 11 enhancement operators, and diverse content domains. Based on this dataset, we train a multiple operator judge model and a degradation perception model to guide agent decisions. To achieve fast thought, we introduce a hierarchical operator scheduling strategy that adapts to video difficulty: for easy cases, optimal restoration trajectories are retrieved in a one-step manner from a retrieval-augmented generation (RAG) library; for harder cases, a step-by-step greedy search is performed to balance efficiency and accuracy. Extensive experiments demonstrate that VQ-Jarvis consistently outperforms existing methods on complex degraded videos.
Abstract (translated)
在真实场景中，视频修复面临异质退化的挑战，静态架构与固定推理流程往往难以泛化应对。近期基于智能体的方法虽能实现动态决策，但现有视频修复智能体仍受限于质量感知不足与搜索策略低效。我们提出VQ-Jarvis——一个检索增强型全能智能视频修复系统，具备更敏锐的视觉感知与更迅捷的决策能力。该系统可精准识别退化类型及配对修复结果间的细微差异，同时高效探索最优修复路径。为实现敏锐视觉，我们构建了VSR-Compare——首个大规模视频配对增强数据集，包含2万组对比样本，涵盖7类退化类型、11种增强算子及多样化的内容领域。基于该数据集，我们训练了多算子评判模型与退化感知模型以指导智能体决策。为达成快速推理，我们引入分层算子调度策略，可根据视频难度自适应调整：对简单案例，通过检索增强生成（RAG）库实现单步检索最优修复路径；对复杂案例则采用逐步贪心搜索，在效率与精度间取得平衡。大量实验表明，VQ-Jarvis在复杂退化视频场景下持续优于现有方法。
URL
https://arxiv.org/abs/2603.22998
PDF
-
A Feature Shuffling and Restoration Strategy for Universal Unsupervised Anomaly Detection
2026-03-24 07:04:20Wei Luo, Haiming Yao, Zhenfeng Qiang, Xiaotian Zhang, Weihang ZhangAbstract
Unsupervised anomaly detection is vital in industrial fields, with reconstruction-based methods favored for their simplicity and effectiveness. However, reconstruction methods often encounter an identical shortcut issue, where both normal and anomalous regions can be well reconstructed and fail to identify outliers. The severity of this problem increases with the complexity of the normal data distribution. Consequently, existing methods may exhibit excellent detection performance in a specific scenario, but their performance sharply declines when transferred to another scenario. This paper focuses on establishing a universal model applicable to anomaly detection tasks across different settings, termed as universal anomaly detection. In this work, we introduce a novel, straightforward yet efficient framework for universal anomaly detection: \uline{F}eature \uline{S}huffling and \uline{R}estoration (FSR), which can alleviate the identical shortcut issue across different settings. First and foremost, FSR employs multi-scale features with rich semantic information as reconstruction targets, rather than raw image pixels. Subsequently, these multi-scale features are partitioned into non-overlapping feature blocks, which are randomly shuffled and then restored to their original state using a restoration network. This simple paradigm encourages the model to focus more on global contextual information. Additionally, we introduce a novel concept, the shuffling rate, to regulate the complexity of the FSR task, thereby alleviating the identical shortcut across different settings. Furthermore, we provide theoretical explanations for the effectiveness of FSR framework from two perspectives: network structure and mutual information. Extensive experimental results validate the superiority and efficiency of the FSR framework across different this http URL is available at this https URL.
Abstract (translated)
无监督异常检测在工业领域中至关重要，其中基于重建的方法因其简洁性和有效性而备受青睐。然而，重建方法常面临一个相同的捷径问题：正常与异常区域均能被良好重建，导致无法识别异常点。此问题的严重程度随正常数据分布复杂度的增加而加剧。因此，现有方法在特定场景中可能表现优异，但迁移至其他场景时性能会急剧下降。本文聚焦于构建适用于不同场景异常检测任务的通用模型，即通用异常检测。本研究提出一种新颖、简洁且高效的通用异常检测框架：\uline{特}征\uline{打}乱与\uline{恢}复（FSR），该框架可缓解不同场景下的相同捷径问题。首先，FSR采用富含语义信息的多尺度特征作为重建目标，而非原始图像像素。随后，将这些多尺度特征划分为非重叠的特征块，随机打乱后通过恢复网络还原至原始状态。这一简单范式促使模型更关注全局上下文信息。此外，我们引入了“打乱率”这一新概念，以调节FSR任务的复杂度，从而缓解不同场景间的相同捷径问题。进一步地，我们从网络结构和互信息两个角度对FSR框架的有效性提供了理论解释。大量实验结果验证了FSR框架在不同场景下的优越性与高效性。this http URL is available at this https URL.
URL
https://arxiv.org/abs/2603.22861
PDF
-
PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal
2026-03-24 06:32:12Zining Fang, Cheng Xue, Chunhui Liu, Bin Xu, Ming Chen, Xiaowei HuAbstract
Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.
Abstract (translated)
手术烟雾会严重降低术中视频质量，遮蔽解剖结构并限制手术感知。现有的基于学习的去烟雾方法依赖于稀缺的配对监督和确定性恢复流程，难以在真实手术条件下进行探索或基于强化的精细调整。我们提出了PhySe-RPO，一个通过物理与语义引导的相对策略优化进行优化的扩散式恢复框架。其核心思想是将确定性恢复转化为随机策略，从而通过组相对优化支持轨迹级探索和无评判器更新。物理引导奖励施加光照与颜色一致性约束，而从基于CLIP的手术概念中学习的视觉概念语义奖励则促进无烟雾且解剖连贯的恢复。结合无参考感知约束，PhySe-RPO在合成与真实机器人手术数据集上生成了物理一致、语义忠实且临床可解释的结果，为在有限配对监督下实现稳健的扩散式恢复提供了原则性路径。
URL
https://arxiv.org/abs/2603.22844
PDF
-
URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection
2026-03-24 06:27:17Wei Luo, Peng Xing, Yunkang Cao, Haiming Yao, Weiming Shen, Zechao LiAbstract
Unsupervised anomaly detection plays a pivotal role in industrial defect inspection and medical image analysis, with most methods relying on the reconstruction framework. However, these methods may suffer from over-generalization, enabling them to reconstruct anomalies well, which leads to poor detection performance. To address this issue, instead of focusing solely on normality reconstruction, we propose an innovative Uncertainty-Integrated Anomaly Perception and Restoration Attention Network (URA-Net), which explicitly restores abnormal patterns to their corresponding normality. First, unlike traditional image reconstruction methods, we utilize a pre-trained convolutional neural network to extract multi-level semantic features as the reconstruction target. To assist the URA-Net learning to restore anomalies, we introduce a novel feature-level artificial anomaly synthesis module to generate anomalous samples for training. Subsequently, a novel uncertainty-integrated anomaly perception module based on Bayesian neural networks is introduced to learn the distributions of anomalous and normal features. This facilitates the estimation of anomalous regions and ambiguous boundaries, laying the foundation for subsequent anomaly restoration. Then, we propose a novel restoration attention mechanism that leverages global normal semantic information to restore detected anomalous regions, thereby obtaining defect-free restored features. Finally, we employ residual maps between input features and restored features for anomaly detection and localization. The comprehensive experimental results on two industrial datasets, MVTec AD and BTAD, along with a medical image dataset, OCT-2017, unequivocally demonstrate the effectiveness and superiority of the proposed method.
Abstract (translated)
无监督异常检测在工业缺陷检测与医学图像分析中发挥着关键作用，多数方法依赖于重建框架。然而，这些方法可能因过度泛化而能够良好重建异常样本，导致检测性能下降。针对这一问题，我们不再仅关注正常重建，而是提出了一种创新的不确定性集成异常感知与修复注意力网络（URA-Net），该网络能将异常模式显式修复为对应的正常状态。首先，不同于传统图像重建方法，我们利用预训练卷积神经网络提取多级语义特征作为重建目标。为辅助URA-Net学习异常修复，我们引入了新颖的特征级人工异常合成模块，用于生成训练用的异常样本。随后，我们提出了基于贝叶斯神经网络的新型不确定性集成异常感知模块，用于学习异常与正常特征的分布。这有助于估计异常区域与模糊边界，为后续异常修复奠定基础。接着，我们设计了新型修复注意力机制，利用全局正常语义信息修复检测到的异常区域，从而获得无缺陷的修复特征。最后，我们通过输入特征与修复特征之间的残差图实现异常检测与定位。在工业数据集MVTec AD、BTAD及医学图像数据集OCT-2017上的 comprehensive 实验结果充分证明了所提方法的有效性与优越性。
URL
https://arxiv.org/abs/2603.22840
PDF
-
It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal
2026-03-24 04:32:16Lishen Qu, Shihao Zhou, Jie Liang, Hui Zeng, Lei Zhang, Jufeng YangAbstract
Flicker artifacts, arising from unstable illumination and row-wise exposure inconsistencies, pose a significant challenge in short-exposure photography, severely degrading image quality. Unlike typical artifacts, e.g., noise and low-light, flicker is a structured degradation with specific spatial-temporal patterns, which are not accounted for in current generic restoration frameworks, leading to suboptimal flicker suppression and ghosting artifacts. In this work, we reveal that flicker artifacts exhibit two intrinsic characteristics, periodicity and directionality, and propose Flickerformer, a transformer-based architecture that effectively removes flicker without introducing ghosting. Specifically, Flickerformer comprises three key components: a phase-based fusion module (PFM), an autocorrelation feed-forward network (AFFN), and a wavelet-based directional attention module (WDAM). Based on the periodicity, PFM performs inter-frame phase correlation to adaptively aggregate burst features, while AFFN exploits intra-frame structural regularities through autocorrelation, jointly enhancing the network's ability to perceive spatially recurring patterns. Moreover, motivated by the directionality of flicker artifacts, WDAM leverages high-frequency variations in the wavelet domain to guide the restoration of low-frequency dark regions, yielding precise localization of flicker artifacts. Extensive experiments demonstrate that Flickerformer outperforms state-of-the-art approaches in both quantitative metrics and visual quality. The source code is available at this https URL.
Abstract (translated)
闪烁伪影源于光照不稳定与逐行曝光不一致，在短曝光摄影中构成重大挑战，会严重降低图像质量。与噪声、低光照等典型伪影不同，闪烁是一种具有特定时空模式的结构化退化，而当前通用复原框架未将其纳入考量，导致闪烁抑制效果不佳并产生重影伪影。本研究揭示闪烁伪影具有周期性与方向性两大内在特性，并提出基于Transformer的Flickerformer架构，可在消除闪烁的同时避免引入重影。具体而言，Flickerformer包含三个关键组件：基于相位的融合模块（PFM）、自相关前馈网络（AFFN）以及基于小波的方向注意力模块（WDAM）。基于周期性，PFM通过帧间相位相关自适应聚合burst特征；AFFN则利用自相关挖掘帧内结构规律，共同增强网络对空间重复模式的感知能力。此外，受闪烁方向性启发，WDAM借助小波域高频变化引导低频暗区复原，实现闪烁伪影的精确定位。大量实验表明，Flickerformer在定量指标与视觉质量上均优于现有先进方法。源代码已公开于此链接。
URL
https://arxiv.org/abs/2603.22794
PDF
-
From Pixels to Semantics: A Multi-Stage AI Framework for Structural Damage Detection in Satellite Imagery
2026-03-24 03:50:41Bijay Shakya, Catherine Hoier, Khandaker Mamun AhmedAbstract
Rapid and accurate structural damage assessment following natural disasters is critical for effective emergency response and recovery. However, remote sensing imagery often suffers from low spatial resolution, contextual ambiguity, and limited semantic interpretability, reducing the reliability of traditional detection pipelines. In this work, we propose a novel hybrid framework that integrates AI-based super-resolution, deep learning object detection, and Vision-Language Models (VLMs) for comprehensive post-disaster building damage assessment. First, we enhance pre- and post-disaster satellite imagery using a Video Restoration Transformer (VRT) to upscale images from 1024x1024 to 4096x4096 resolution, improving structural detail visibility. Next, a YOLOv11-based detector localizes buildings in pre-disaster imagery, and cropped building regions are analyzed using VLMs to semantically assess structural damage across four severity levels. To ensure robust evaluation in the absence of ground-truth captions, we employ CLIPScore for reference-free semantic alignment and introduce a multi-model VLM-as-a-Jury strategy to reduce individual model bias in safety-critical decision making. Experiments on subsets of the xBD dataset, including the Moore Tornado and Hurricane Matthew events, demonstrate that the proposed framework enhances the semantic interpretation of damaged buildings. In addition, our framework provides helpful recommendations to first responders for recovery based on damage analysis.
Abstract (translated)
自然灾害后快速准确的结构损伤评估对于有效的应急响应和恢复至关重要。然而，遥感影像常受限于空间分辨率低、上下文模糊以及语义可解释性不足，这降低了传统检测管线的可靠性。本研究提出一种新颖的混合框架，该框架整合了基于AI的超分辨率技术、深度学习目标检测以及视觉语言模型（VLMs），用于综合灾后建筑损伤评估。首先，我们采用视频恢复Transformer（VRT）对灾前灾后卫星影像进行增强，将图像从1024×1024分辨率提升至4096×4096，从而改善结构细节的可视性。随后，基于YOLOv11的检测器在灾前影像中定位建筑物，并对裁剪后的建筑区域使用VLMs进行语义分析，按四个严重程度等级评估结构损伤。为确保在缺乏真实标注描述的情况下进行稳健评估，我们采用CLIPScore进行无参考语义对齐，并引入多模型VLM-as-a-Jury策略以减少安全关键决策中的个体模型偏差。在xBD数据集子集（包括摩尔龙卷风和飓风马修事件）上的实验表明，所提框架增强了受损建筑的语义解释能力。此外，我们的框架还能基于损伤分析为救援人员提供恢复建议。
URL
https://arxiv.org/abs/2603.22768
PDF
-
TimeWeaver: Age-Consistent Reference-Based Face Restoration with Identity Preservation
2026-03-24 01:48:27Teer Song, Yue Zhang, Yu Tian, Ziyang Wang, Xianlin Zhang, Guixuan Zhang, Xuan Liu, Xueming Li, Yasen ZhangAbstract
Recent progress in face restoration has shifted from visual fidelity to identity fidelity, driving a transition from reference-free to reference-based paradigms that condition restoration on reference images of the same person. However, these methods assume the reference and degraded input are age-aligned. When only cross-age references are available, as in historical restoration or missing-person retrieval, they fail to maintain age fidelity. To address this limitation, we propose TimeWeaver, the first reference-based face restoration framework supporting cross-age references. Given arbitrary reference images and a target-age prompt, TimeWeaver produces restorations with both identity fidelity and age consistency. Specifically, we decouple identity and age conditioning across training and inference. During training, the model learns an age-robust identity representation by fusing a global identity embedding with age-suppressed facial tokens via a transformer-based ID-Fusion module. During inference, two training-free techniques, Age-Aware Gradient Guidance and Token-Targeted Attention Boost, steer sampling toward desired age semantics, enabling precise adherence to the target-age prompt. Extensive experiments show that TimeWeaver surpasses existing methods in visual quality, identity preservation, and age consistency.
Abstract (translated)
近期人脸修复领域的进展已从视觉保真度转向身份保真度，推动了从无参考图像到参考图像驱动范式的转变，即依据同一人的参考图像进行修复。然而，这些方法假设参考图像与退化输入在年龄上对齐。当仅存在跨年龄参考图像时（如历史影像修复或寻人检索场景），现有方法无法保持年龄保真度。为应对此局限，我们提出TimeWeaver——首个支持跨年龄参考图像的参考型人脸修复框架。给定任意参考图像与目标年龄提示词，TimeWeaver可生成兼具身份保真度与年龄一致性的修复结果。具体而言，我们在训练与推理阶段解耦身份与年龄条件：训练时，模型通过基于Transformer的ID融合模块，将全局身份嵌入与年龄抑制的面部令牌相融合，学习抗年龄干扰的身份表征；推理时，采用两种无需训练的技术——年龄感知梯度引导与令牌定向注意力增强，引导采样过程朝向目标年龄语义，实现精确遵循目标年龄提示词。大量实验表明，TimeWeaver在视觉质量、身份保持与年龄一致性上均超越现有方法。
URL
https://arxiv.org/abs/2603.22701
PDF
-
Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models
2026-03-23 14:33:43Purui Bai, Junxian Duan, Pin Wang, Jinhua Hao, Ming Sun, Chao Zhou, Huaibo HuangAbstract
Although diffusion-based real-world image restoration (Real-IR) has achieved remarkable progress, efficiently leveraging ultra-large-scale pre-trained text-to-image (T2I) models and fully exploiting their potential remain significant challenges. To address this issue, we propose ResFlow-Tuner, an image restoration framework based on the state-of-the-art flow matching model, FLUX.1-dev, which integrates unified multi-modal fusion (UMMF) with test-time scaling (TTS) to achieve unprecedented restoration performance. Our approach fully leverages the advantages of the Multi-Modal Diffusion Transformer (MM-DiT) architecture by encoding multi-modal conditions into a unified sequence that guides the synthesis of high-quality images. Furthermore, we introduce a training-free test-time scaling paradigm tailored for image restoration. During inference, this technique dynamically steers the denoising direction through feedback from a reward model (RM), thereby achieving significant performance gains with controllable computational overhead. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple standard benchmarks. This work not only validates the powerful capabilities of the flow matching model in low-level vision tasks but, more importantly, proposes a novel and efficient inference-time scaling paradigm suitable for large pre-trained models.
Abstract (translated)
尽管基于扩散的真实世界图像恢复（Real-IR）已取得显著进展，但高效利用超大规模预训练文本到图像（T2I）模型并充分发挥其潜力仍是重大挑战。针对此问题，我们提出了基于最先进流匹配模型FLUX.1-dev的图像恢复框架ResFlow-Tuner，该框架融合了统一多模态融合（UMMF）与测试时缩放（TTS）技术，实现了前所未有的恢复性能。我们的方法通过将多模态条件编码为统一序列来指导高质量图像合成，充分利用了多模态扩散Transformer（MM-DiT）架构的优势。此外，我们引入了专为图像恢复设计的无训练测试时缩放范式：推理过程中，该技术通过奖励模型（RM）的反馈动态引导去噪方向，从而在可控的计算开销下实现显著的性能提升。大量实验表明，我们的方法在多个标准基准上达到了最先进性能。本研究不仅验证了流匹配模型在低层视觉任务中的强大能力，更重要的是提出了一种适用于大型预训练模型的新型高效推理时缩放范式。
URL
https://arxiv.org/abs/2603.22027
PDF
-
Dynamic Exposure Burst Image Restoration
2026-03-23 10:25:49Woohyeok Kim, Jaesung Rim, Daeyeon Kim, Sunghyun ChoAbstract
Burst image restoration aims to reconstruct a high-quality image from burst images, which are typically captured using manually designed exposure settings. Although these exposure settings significantly influence the final restoration performance, the problem of finding optimal exposure settings has been overlooked. In this paper, we present Dynamic Exposure Burst Image Restoration (DEBIR), a novel burst image restoration pipeline that enhances restoration quality by dynamically predicting exposure times tailored to the shooting environment. In our pipeline, Burst Auto-Exposure Network (BAENet) estimates the optimal exposure time for each burst image based on a preview image, as well as motion magnitude and gain. Subsequently, a burst image restoration network reconstructs a high-quality image from burst images captured using these optimal exposure times. For training, we introduce a differentiable burst simulator and a three-stage training strategy. Our experiments demonstrate that our pipeline achieves state-of-the-art restoration quality. Furthermore, we validate the effectiveness of our approach on a real-world camera system, demonstrating its practicality.
Abstract (translated)
连拍图像恢复旨在从通常采用手动设计曝光参数拍摄的连拍图像中重建高质量图像。尽管这些曝光参数会显著影响最终恢复效果，但寻找最优曝光参数的问题却一直未被重视。本文提出动态曝光连拍图像恢复（DEBIR）这一新颖的连拍图像恢复流程，通过动态预测适应拍摄环境的最佳曝光时间来提升恢复质量。在该流程中，连拍自动曝光网络（BAENet）基于预览图像以及运动幅度和增益，为每张连拍图像估算最优曝光时间。随后，连拍图像恢复网络利用这些最优曝光时间拍摄的连拍图像重建高质量图像。为进行训练，我们引入了可微分连拍模拟器和三阶段训练策略。实验表明，我们的流程达到了最先进的恢复质量。此外，我们还在真实相机系统上验证了方法的有效性，证明了其实用性。
URL
https://arxiv.org/abs/2603.21784
PDF
-
TAFG-MAN: Timestep-Adaptive Frequency-Gated Latent Diffusion for Efficient and High-Quality Low-Dose CT Image Denoising
2026-03-21 15:59:36Tangtangfang Fang, Yang Jiao, Xiangjian He, Jingxi Hu, Jiaqi YangAbstract
Low-dose computed tomography (LDCT) reduces radiation exposure but also introduces substantial noise and structural degradation, making it difficult to suppress noise without erasing subtle anatomical details. In this paper, we present TAFG-MAN, a latent diffusion framework for efficient and high-quality LDCT image denoising. The framework combines a perceptually optimized autoencoder, conditional latent diffusion restoration in a compact latent space, and a lightweight Timestep-Adaptive Frequency-Gated (TAFG) conditioning design. TAFG decomposes condition features into low- and high-frequency components, predicts timestep-adaptive gates from the current denoising feature and timestep embedding, and progressively releases high-frequency guidance in later denoising stages before cross-attention. In this way, the model relies more on stable structural guidance at early reverse steps and introduces fine details more cautiously as denoising proceeds, improving the balance between noise suppression and detail preservation. Experiments show that TAFG-MAN achieves a favorable quality-efficiency trade-off against representative baselines. Compared with its base variant without TAFG, it further improves detail preservation and perceptual quality while maintaining essentially the same inference cost, and ablation results confirm the effectiveness of the proposed conditioning mechanism.
Abstract (translated)
低剂量计算机断层扫描（LDCT）虽能减少辐射暴露，但也会引入大量噪声和结构退化，使得在抑制噪声的同时保留细微解剖结构变得困难。本文提出TAFG-MAN，一种用于高效高质量LDCT图像去噪的潜在扩散框架。该框架结合了感知优化自编码器、紧凑潜在空间中的条件潜在扩散复原，以及轻量级的时间步自适应频率门控（TAFG）条件设计。TAFG将条件特征分解为低频与高频分量，从当前去噪特征和时间步嵌入中预测时间步自适应门控，并在交叉注意力之前于后续去噪阶段逐步释放高频引导。如此，模型在早期反向步骤中更依赖稳定的结构引导，并在去噪过程中更谨慎地引入精细细节，从而改善噪声抑制与细节保留之间的平衡。实验表明，TAFG-MAN相较于代表性基线方法实现了质量与效率的有利权衡。与不含TAFG的基础变体相比，其在保持推理成本基本不变的同时进一步提升了细节保留和感知质量，消融实验结果也验证了所提条件机制的有效性。
URL
https://arxiv.org/abs/2603.20868
PDF
-
High-Quality and Efficient Turbulence Mitigation with Events
2026-03-21 08:10:20Xiaoran Zhang, Jian Ding, Yuxing Duan, Haoyue Liu, Gang Chen, Yi Chang, Luxin YanAbstract
Turbulence mitigation (TM) is highly ill-posed due to the stochastic nature of atmospheric turbulence. Most methods rely on multiple frames recorded by conventional cameras to capture stable patterns in natural scenarios. However, they inevitably suffer from a trade-off between accuracy and efficiency: more frames enhance restoration at the cost of higher system latency and larger data overhead. Event cameras, equipped with microsecond temporal resolution and efficient sensing of dynamic changes, offer an opportunity to break the bottleneck. In this work, we present EHETM, a high-quality and efficient TM method inspired by the superiority of events to model motions in continuous sequences. We discover two key phenomena: (1) turbulence-induced events exhibit distinct polarity alternation correlated with sharp image gradients, providing structural cues for restoring scenes; and (2) dynamic objects form spatiotemporally coherent ``event tubes'' in contrast to irregular patterns within turbulent events, providing motion priors for disentangling objects from turbulence. Based on these insights, we design two complementary modules that respectively leverage polarity-weighted gradients for scene refinement and event-tube constraints for motion decoupling, achieving high-quality restoration with few frames. Furthermore, we construct two real-world event-frame turbulence datasets covering atmospheric and thermal cases. Experiments show that EHETM outperforms SOTA methods, especially under scenes with dynamic objects, while reducing data overhead and system latency by approximately 77.3% and 89.5%, respectively. Our code is available at: this https URL.
Abstract (translated)
湍流缓解(TM) 因其随机性而具有高度不适定性。多数方法依赖传统相机拍摄的多帧图像来捕捉自然场景中的稳定模式，但不可避免地面临精度与效率的权衡：增加帧数虽能提升复原质量，却会带来更高的系统延迟与数据开销。事件相机具备微秒级时间分辨率并能高效感知动态变化，为突破这一瓶颈提供了可能。本研究提出 EHETM，一种受事件在连续序列中建模运动优势启发的高质量高效 TM 方法。我们发现两个关键现象：(1) 湍流引发的事件呈现与清晰图像梯度相关的明显极性交替，为场景复原提供结构线索；(2) 动态物体形成时空连贯的“事件管”，与湍流事件中的不规则模式形成对比，为分离物体与湍流提供运动先验。基于这些洞察，我们设计了两个互补模块：分别利用极性加权梯度进行场景细化，以及通过事件管约束实现运动解耦，从而以少量帧实现高质量复原。此外，我们构建了两个涵盖大气与热辐射场景的真实世界事件-帧湍流数据集。实验表明，EHETM 优于当前最优方法，尤其在动态物体场景中表现突出，同时将数据开销与系统延迟分别降低约 77.3% 和 89.5%。代码已公开：this https URL。
URL
https://arxiv.org/abs/2603.20708
PDF
-
MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolution
2026-03-21 07:18:01Ruiqing Wang, Kai Zhang, Yuanzhi Zhu, Hanshu Yan, Shilin Lu, Jian YangAbstract
Diffusion- and flow-based models have advanced Real-world Image Super-Resolution (Real-ISR), but their multi-step sampling makes inference slow and hard to deploy. One-step distillation alleviates the cost, yet often degrades restoration quality and removes the option to refine with more steps. We present Mean Flows for Super-Resolution (MFSR), a new distillation framework that produces photorealistic results in a single step while still allowing an optional few-step path for further improvement. Our approach uses MeanFlow as the learning target, enabling the student to approximate the average velocity between arbitrary states of the Probability Flow ODE (PF-ODE) and effectively capture the teacher's dynamics without explicit rollouts. To better leverage pretrained generative priors, we additionally improve original MeanFlow's Classifier-Free Guidance (CFG) formulation with teacher CFG distillation strategy, which enhances restoration capability and preserves fine details. Experiments on both synthetic and real-world benchmarks demonstrate that MFSR achieves efficient, flexible, and high-quality super-resolution, delivering results on par with or even better than multi-step teachers while requiring much lower computational cost.
Abstract (translated)
扩散模型与流模型推动了真实世界图像超分辨率（Real-ISR）的发展，但其多步采样过程导致推理速度缓慢且难以部署。一步蒸馏虽能降低计算成本，却常损害修复质量并丧失多步精细调整的可能性。本文提出超分辨率平均流（MFSR）这一新型蒸馏框架，既能单步生成照片级真实结果，又保留可选的多步优化路径以实现进一步提升。该方法以平均流作为学习目标，使学生模型能够逼近概率流常微分方程（PF-ODE）任意状态间的平均速度，无需显式展开即可有效捕捉教师模型动态。为更好利用预训练生成先验，我们进一步改进原始平均流的无分类器引导（CFG）公式，通过教师CFG蒸馏策略增强修复能力并保留精细细节。在合成与真实世界基准测试中，MFSR均展现出高效、灵活且高质量的超分辨率性能，其效果与多步教师模型相当甚至更优，而计算成本显著降低。
URL
https://arxiv.org/abs/2603.20690
PDF
-
TRGS-SLAM: IMU-Aided Gaussian Splatting SLAM for Blurry, Rolling Shutter, and Noisy Thermal Images
2026-03-20 19:18:31Spencer Carmichael, Katherine A. SkinnerAbstract
Thermal cameras offer several advantages for simultaneous localization and mapping (SLAM) with mobile robots: they provide a passive, low-power solution to operating in darkness, are invariant to rapidly changing or high dynamic range illumination, and can see through fog, dust, and smoke. However, uncooled microbolometer thermal cameras, the only practical option in most robotics applications, suffer from significant motion blur, rolling shutter distortions, and fixed pattern noise. In this paper, we present TRGS-SLAM, a 3D Gaussian Splatting (3DGS) based thermal inertial SLAM system uniquely capable of handling these degradations. To overcome the challenges of thermal data, we introduce a model-aware 3DGS rendering method and several general innovations to 3DGS SLAM, including B-spline trajectory optimization with a two-stage IMU loss, view-diversity-based opacity resetting, and pose drift correction schemes. Our system demonstrates accurate tracking on real-world, fast motion, and high-noise thermal data that causes all other tested SLAM methods to fail. Moreover, through offline refinement of our SLAM results, we demonstrate thermal image restoration competitive with prior work that required ground truth poses.
Abstract (translated)
热成像相机为移动机器人同时定位与地图构建（SLAM）提供了多项优势：它们提供了一种在黑暗中运行的被动式低功耗解决方案，不受快速变化或高动态范围光照的影响，且能够穿透雾、灰尘和烟雾。然而，在大多数机器人应用中唯一实用的非制冷微测辐射热计热成像相机，却存在严重的运动模糊、卷帘快门畸变和固定模式噪声问题。本文提出TRGS-SLAM，一种基于3D高斯泼溅（3DGS）的热惯性SLAM系统，独特地能够处理这些退化问题。为克服热成像数据的挑战，我们引入了模型感知的3DGS渲染方法，并对3DGS SLAM进行了多项通用创新，包括采用两阶段IMU损失的B样条轨迹优化、基于视图多样性的透明度重置机制，以及位姿漂移校正方案。我们的系统在真实世界的高速运动和高噪声热成像数据上展现出精确的跟踪性能，这些数据导致所有其他测试的SLAM方法失效。此外，通过对SLAM结果进行离线优化，我们展示了与需要真实位姿的先前工作具有竞争力的热成像图像恢复效果。
URL
https://arxiv.org/abs/2603.20443
PDF
-
Improving Image-to-Image Translation via a Rectified Flow Reformulation
2026-03-20 17:59:03Satoshi Iizuka, Shun Okamoto, Kazuhiro FukuiAbstract
In this work, we propose Image-to-Image Rectified Flow Reformulation (I2I-RFR), a practical plug-in reformulation that recasts standard I2I regression networks as continuous-time transport models. While pixel-wise I2I regression is simple, stable, and easy to adapt across tasks, it often over-smooths ill-posed and multimodal targets, whereas generative alternatives often require additional components, task-specific tuning, and more complex training and inference pipelines. Our method augments the backbone input by channel-wise concatenation with a noise-corrupted version of the ground-truth target and optimizes a simple t-reweighted pixel loss. This objective admits a rectified-flow interpretation via an induced velocity field, enabling ODE-based progressive refinement at inference time while largely preserving the standard supervised training pipeline. In most cases, adopting I2I-RFR requires only expanding the input channels, and inference can be performed with a few explicit solver steps (e.g., 3 steps) without distillation. Extensive experiments across multiple image-to-image translation and video restoration tasks show that I2I-RFR generally improves performance across a wide range of tasks and backbones, with particularly clear gains in perceptual quality and detail preservation. Overall, I2I-RFR provides a lightweight way to incorporate continuous-time refinement into conventional I2I models without requiring a heavy generative pipeline.
Abstract (translated)
在本工作中，我们提出了图像到图像整流流重构（I2I-RFR），这是一种实用的即插式重构方法，可将标准I2I回归网络重新诠释为连续时间传输模型。虽然逐像素I2I回归具有简单、稳定且易于跨任务适配的优点，但它常会过度平滑病态且多模态的目标，而生成式替代方案通常需要额外组件、任务特定调优以及更复杂的训练和推理流程。我们的方法通过将噪声扰动后的真实目标图像与主干网络输入进行通道级拼接来增强输入，并优化一个简单的t重加权像素损失。该目标函数可通过诱导的速度场获得整流流解释，从而在推理时实现基于ODE的渐进式细化，同时基本保持标准的监督训练流程。在大多数情况下，采用I2I-RFR仅需扩展输入通道数，且推理可通过少数显式求解器步骤（例如3步）完成，无需知识蒸馏。在多个图像到图像转换和视频恢复任务上的大量实验表明，I2I-RFR通常能提升广泛任务和主干网络的性能，尤其在感知质量和细节保留方面有显著提升。总体而言，I2I-RFR提供了一种轻量级方式，可将连续时间细化融入传统I2I模型，而无需构建复杂的生成式流程。
URL
https://arxiv.org/abs/2603.20186
PDF
