基于任务导向三维高斯事件表征的事件相机运动去模糊
Event-Based Motion Deblurring Using Task-Oriented 3D Gaussian Event Representations
把事件流用可学习的3D高斯核聚合成对运动方向和速度敏感的局部运动特征，替代手工事件表征（如事件帧、体素网格），可直接迁移到其他事件相机+RGB的底层视觉任务（去模糊、插帧、HDR重建）中作为事件编码前端。
原文依据 we propose a learnable 3D Gaussian event representation module that adaptively selects key spatiotemporal coordinates for deblurring
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于事件的运动去模糊近年来受到越来越多的关注，因为事件相机的高时序分辨率提供了传统RGB传感器所不具备的运动线索，从而使去模糊更为有效。在真实场景中，运动模糊往往复杂且非线性，不同区域呈现出各异的运动速度与方向。然而，现有方法大多依赖手工设计的事件表征，忽略了这种时空运动异质性，导致去模糊性能欠佳。为解决这一局限，我们提出一个可学习的三维高斯事件表征模块，它根据模糊图像内容与事件密度分布自适应地为去模糊选取关键的时空坐标。随后，事件流通过三维高斯加权核进行聚合，以提取对运动方向和速度敏感的局部运动特征。此外，为充分利用事件表征中编码的运动信息，我们采用两阶段融合策略。第一阶段利用局部运动特征增强细节恢复；第二阶段由双向注意力融合模块利用一维高斯加权事件帧来校正全局空间错位，从而实现更准确的结构对齐。在合成数据集与真实数据集上的大量实验验证了本方法的有效性，并表明其持续优于最优方法。
英文原文摘要 1523 字符
Event-based motion deblurring has attracted increasing attention, as the high temporal resolution of event cameras provides motion cues unavailable to conventional RGB sensors, thereby enabling more effective deblurring. In real-world scenes, motion blur is often complex and nonlinear, with different regions exhibiting diverse motion speeds and directions. However, most existing approaches rely on handcrafted event representations that overlook such spatiotemporal motion heterogeneity, resulting in suboptimal deblurring performance. To address this limitation, we propose a learnable 3D Gaussian event representation module that adaptively selects key spatiotemporal coordinates for deblurring based on the blurred image content and the event density distribution. The event stream is then aggregated with 3D Gaussian weighting kernels to extract local motion features that are sensitive to motion direction and speed. Furthermore, to fully exploit the motion information encoded in the event representation, we adopt a two-stage fusion strategy. In the first stage, local motion features are used to enhance fine detail restoration. In the second stage, a bidirectional attention fusion module leverages one-dimensional Gaussian-weighted event frames to correct global spatial misalignment, leading to more accurate structural alignment. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of our method and show that it consistently outperforms state-of-the-art approaches.