论文标题
模糊的插值变压器，用于现实世界的模糊
Blur Interpolation Transformer for Real-World Motion from Blur
论文作者
论文摘要
本文研究了从Blur恢复运动的挑战性问题，该运动（也称为关节脱毛和插值或暂时超级分辨率。挑战是双重的：1）即使在合成数据集上，当前的方法仍在视觉质量方面留出很大的改进空间，而2）对现实世界数据的概括不佳。为此，我们提出了一个模糊的插值变压器（位），以有效揭示在模糊中编码的基本时间相关。基于多尺度的残留SWIN变压器块，我们介绍了双端时间监督和时间对称的结合策略，以生成有效的特征，以实现时变运动渲染。此外，我们设计了一个混合摄像头系统，以收集第一到一对模糊视频对的第一个真实数据集。实验结果表明，BIT比公共数据集AdoBE240上的最新方法具有显着增益。此外，所提出的现实世界数据集有效地有助于模型概括为真实的模糊场景。代码和数据可在https://github.com/zzh-tech/bit上找到。
This paper studies the challenging problem of recovering motion from blur, also known as joint deblurring and interpolation or blur temporal super-resolution. The challenges are twofold: 1) the current methods still leave considerable room for improvement in terms of visual quality even on the synthetic dataset, and 2) poor generalization to real-world data. To this end, we propose a blur interpolation transformer (BiT) to effectively unravel the underlying temporal correlation encoded in blur. Based on multi-scale residual Swin transformer blocks, we introduce dual-end temporal supervision and temporally symmetric ensembling strategies to generate effective features for time-varying motion rendering. In addition, we design a hybrid camera system to collect the first real-world dataset of one-to-many blur-sharp video pairs. Experimental results show that BiT has a significant gain over the state-of-the-art methods on the public dataset Adobe240. Besides, the proposed real-world dataset effectively helps the model generalize well to real blurry scenarios. Code and data are available at https://github.com/zzh-tech/BiT.
