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 1808.03338cs.CVcs.GRcs.HC
收藏

DeepMag:使用梯度上升的源特定运动放大

DeepMag: Source Specific Motion Magnification Using Gradient Ascent

Massachusetts Institute of Technology(麻省理工学院);Microsoft Research(微软研究院)

Weixuan Chen, Daniel McDuff

摘要:

许多重要的物理现象都涉及到肉眼难以观察到的微妙信号,但将它们可视化可以提供非常丰富的信息。当前的运动放大技术可以揭示视频中的这些小的时间变化,但需要关于目标信号的精确先验知识,并且不能处理类似频率的干扰运动。DeepMag是一个基于梯度上升的端到端深度神经视频处理框架,即使在存在各种速度的大运动的情况下,也可以自动放大来自特定来源的细微颜色和运动信号。虽然该方法是可推广的,但DeepMag的优势通过基于视频的生理可视化任务突出显示。通过系统的定量和定性评价的方法对视频与不同层次的头部运动,我们比较了现有的最先进的方法的脉搏和呼吸的放大。我们的方法产生放大的视频,具有更少的伪影和模糊,同时以类似的程度放大生理变化。

英文摘要:

Many important physical phenomena involve subtle signals that are difficult to observe with the unaided eye, yet visualizing them can be very informative. Current motion magnification techniques can reveal these small temporal variations in video, but require precise prior knowledge about the target signal, and cannot deal with interference motions at a similar frequency. We present DeepMag an end-to-end deep neural video-processing framework based on gradient ascent that enables automated magnification of subtle color and motion signals from a specific source, even in the presence of large motions of various velocities. While the approach is generalizable, the advantages of DeepMag are highlighted via the task of video-based physiological visualization. Through systematic quantitative and qualitative evaluation of the approach on videos with different levels of head motion, we compare the magnification of pulse and respiration to existing state-of-the-art methods. Our method produces magnified videos with substantially fewer artifacts and blurring whilst magnifying the physiological changes by a similar degree.

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。

↑