OMoBlur：面向真实世界局部运动去模糊的物体运动模糊数据集与基准
OMoBlur: An Object Motion Blur Dataset and Benchmark for Real-World Local Motion Deblurring
针对静态场景中空间异质的局部物体运动模糊，提供了通过可编程传感器控制模拟曝光光子积分过程的采集方案，并给出无需像素级精确掩码的物体运动感知去模糊网络（运动-外观提取块 + 光流引导门控预测 + 自适应门控融合），可直接用于研究局部运动去模糊与真实模糊分布对齐问题。
原文依据 emulates realistic exposure integration via programmable sensor control, ensuring close alignment between synthetic and real blur distributions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论静态场景中的物体运动模糊在空间上是异质的，这与传统去模糊问题不同，却频繁出现在真实手持拍摄场景中。现有数据集要么依赖成本高昂且存在残余失配的分光采集，要么采用无法建模曝光期间连续光子积分过程的合成模糊。为克服这些局限，我们提出 OMoBlur，一个基于物理原理的数据集，通过可编程传感器控制模拟真实的曝光积分过程，确保合成模糊与真实模糊分布之间紧密对齐。OMoBlur 提供 20,000 组模糊-清晰-掩码三元组，覆盖多样的物体运动类型。借助该数据集，我们进一步提出 OMDNet，一种物体运动感知的去模糊网络，集成了运动-外观提取块、光流引导门控预测器和自适应门控融合机制。该设计使网络能够选择性地恢复模糊区域，同时保留静态背景，且无需像素级精确的掩码标注。大量实验表明，OMoBlur 物理上忠实的数据采集与大规模多样性显著增强了网络对真实世界运动模糊的泛化能力，使 OMoBlur 与 OMDNet 成为局部运动去模糊的稳健基准与实用解决方案。数据集与代码已公开于 https://yudingchuan.github.io/OMoBlur_homepage/。
英文原文摘要 1446 字符
Object motion blur in static scenes is spatially heterogeneous, differing from conventional deblurring problems yet frequently occurring in real handheld capture scenarios. Existing datasets either rely on costly beam-splitting capture with residual misalignment or employ synthetic blur that fails to model the continuous photon-integration process during exposure. To overcome these limitations, we introduce OMoBlur, a physically grounded dataset that emulates realistic exposure integration via programmable sensor control, ensuring close alignment between synthetic and real blur distributions. OMoBlur provides 20,000 blur-sharp-mask pairs covering diverse object motion types. Leveraging this dataset, we further propose OMDNet, an object-motion-aware deblurring network that integrates a Motion-Appearance Extract Block, a Flow-Guided Gate Predictor, and an Adaptive Gated Fusion mechanism. This design enables the network to selectively restore blurred regions while preserving static backgrounds, without requiring pixel-accurate mask annotations. Extensive experiments demonstrate that OMoBlur's physically faithful data collection and large-scale diversity significantly enhance the network's generalization to real-world motion blur, establishing OMoBlur and OMDNet as a robust benchmark and practical solution for local motion deblurring. The dataset and code is publicly released at https://yudingchuan.github.io/OMoBlur_homepage/.