基于陀螺仪的深度视频去模糊
Gyro-based Deep Video Deblurring
利用陀螺仪测量的旋转运动与估计的平移运动联合构建模糊核，并输入视频去模糊网络，为视频去模糊提供了新的传感器融合思路和可复用的模糊核构建方案。
原文依据 We propose a novel blur kernel construction scheme that jointly accounts for rotational and translational motion.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现代相机（如智能手机相机和数码单反相机）配备了测量相机运动的陀螺仪传感器。虽然运动信息对去模糊很有价值，但基于陀螺仪的去模糊尚未得到广泛研究，尤其是视频领域。已有少数基于陀螺仪的视频去模糊方法被提出，但它们存在固有局限。首先，陀螺仪传感器仅捕获旋转运动，导致这些方法忽略平移运动。其次，它们依赖简化的模糊模型和基于反卷积的解决方案，限制了整体性能。为解决这些局限，我们提出GyroDVD，这是首个基于学习的陀螺仪视频去模糊框架。我们提出一种新颖的模糊核构建方案，同时考虑旋转和平移运动。然后，视频去模糊网络利用构建的模糊核与视频帧一起恢复清晰视频。为了训练和评估，我们引入了GyroVD数据集，这是一个专为基于陀螺仪的去模糊设计的大规模真实数据集。大量实验表明，我们的方法显著优于先前基于陀螺仪的图像和视频去模糊方法。
英文原文摘要 1208 字符
Modern cameras, such as smartphone cameras and DSLRs, are equipped with gyro sensors that measure motion of the camera. While the motion information is valuable for deblurring, gyro-based deblurring has not been widely studied, particularly for video. A few gyro-based video deblurring methods have been proposed, but they exhibit inherent limitations. First, gyro sensors capture only rotational motion, leading these methods to ignore translational motion. Second, their dependence on simplified blur models and deconvolution-based solutions restricts overall performance. To address these limitations, we introduce GyroDVD, the first learning-based framework for gyro-based video deblurring. We propose a novel blur kernel construction scheme that jointly accounts for rotational and translational motion. A video deblurring network then restores sharp videos by exploiting the constructed kernels together with the video frames. For training and evaluation, we introduce the GyroVD dataset, a large-scale and realistic dataset specifically designed for gyro-based deblurring. Extensive experiments demonstrate that our method significantly outperforms prior gyro-based image and video deblurring methods.