arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.13256cs.CV
收藏

利用长时间信息的连续空时视频超分辨率

Continuous Space-Time Video Super-Resolution Utilizing Long-Range Temporal Information

Wuhan University(武汉大学);Huawei(华为)

Yuantong Zhang, Daiqin Yang, Zhenzhong Chen, Wenpeng Ding

摘要:

在本文中,我们考虑空时视频超分辨率(ST-VSR)的任务,即扩展一个给定的源视频到更高的帧速率和分辨率的同时。然而,大多数现有方案要么在训练阶段考虑固定的中间时间和尺度,要么只接受预设数量的输入帧(例如,两个相邻帧),其不能利用长距离时间信息。为了解决这些问题,我们提出了一个连续的ST-VSR(C-STVSR)的方法,可以将给定的视频转换到任何帧速率和空间分辨率。为了实现时间任意插值,我们提出了一个前向扭曲引导的帧合成模块和光流引导的上下文一致性损失,以更好地近似极端运动,并保持输入和预测帧之间的相似结构。此外,我们设计了一个内存友好的级联深度到空间模块,实现连续空间上采样。同时,通过对光流的精细重组,该方法具有内存友好性,使得从远距离相邻帧中传播信息成为可能,从而获得更好的重建质量。实验结果表明,该算法具有很好的灵活性,在各种数据集上,无论是客观评价还是主观视觉效果,都比现有方法有更好的性能。

英文摘要:

In this paper, we consider the task of space-time video super-resolution (ST-VSR), namely, expanding a given source video to a higher frame rate and resolution simultaneously. However, most existing schemes either consider a fixed intermediate time and scale in the training stage or only accept a preset number of input frames (e.g., two adjacent frames) that fails to exploit long-range temporal information. To address these problems, we propose a continuous ST-VSR (C-STVSR) method that can convert the given video to any frame rate and spatial resolution. To achieve time-arbitrary interpolation, we propose a forward warping guided frame synthesis module and an optical-flow-guided context consistency loss to better approximate extreme motion and preserve similar structures among input and prediction frames. In addition, we design a memory-friendly cascading depth-to-space module to realize continuous spatial upsampling. Meanwhile, with the sophisticated reorganization of optical flow, the proposed method is memory friendly, making it possible to propagate information from long-range neighboring frames and achieve better reconstruction quality. Extensive experiments show that the proposed algorithm has good flexibility and achieves better performance on various datasets compared with the state-of-the-art methods in both objective evaluations and subjective visual effects.

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。

↑