用于全帧视频稳定的深度迭代帧内插
Deep Iterative Frame Interpolation for Full-frame Video Stabilization
摘要：
视频稳像技术是提高视频质量的一项基本而重要的技术。先前的工作已经广泛地探索了视频稳定，但是它们中的大多数涉及帧边界的裁剪并且引入适度水平的失真。我们提出了一种新的深度视频稳定方法，可以生成没有裁剪和低失真的视频帧。所提出的框架利用帧内插技术来生成帧之间的帧，从而减少帧间抖动。一旦以迭代方式应用，稳定效果变得更强。一个主要的优点是，我们的框架是端到端的可训练的无监督的方式。此外，我们的方法能够近实时（15 fps）运行。据我们所知，这是第一个提出无监督深度全帧视频稳定方法的工作。我们通过定量和定性的评价，显示我们的方法的优势相比，国家的最先进的方法。
英文摘要：
Video stabilization is a fundamental and important technique for higher quality videos. Prior works have extensively explored video stabilization, but most of them involve cropping of the frame boundaries and introduce moderate levels of distortion. We present a novel deep approach to video stabilization which can generate video frames without cropping and low distortion. The proposed framework utilizes frame interpolation techniques to generate in between frames, leading to reduced inter-frame jitter. Once applied in an iterative fashion, the stabilization effect becomes stronger. A major advantage is that our framework is end-to-end trainable in an unsupervised manner. In addition, our method is able to run in near real-time (15 fps). To the best of our knowledge, this is the first work to propose an unsupervised deep approach to full-frame video stabilization. We show the advantages of our method through quantitative and qualitative evaluations comparing to the state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
