Wehrwein Scott, Bala Kavita, Snavely Noah
IEEE Trans Vis Comput Graph. 2021 Apr;27(4):2495-2501. doi: 10.1109/TVCG.2020.2993195. Epub 2021 Feb 25.
When observing the visual world, temporal phenomena are ubiquitous: people walk, cars drive, rivers flow, clouds drift, and shadows elongate. Some of these, like water splashing and cloud motion, occur over time intervals that are either too short or too long for humans to easily observe. High-speed and timelapse videos provide a popular and compelling way to visualize these phenomena, but many real-world scenes exhibit motions occurring at a variety of rates. Once a framerate is chosen, phenomena at other rates are at best invisible, and at worst create distracting artifacts. In this article, we propose to automatically normalize the pixel-space speed of different motions in an input video to produce a seamless output with spatiotemporally varying framerate. To achieve this, we propose to analyze scenes at different timescales to isolate and analyze motions that occur at vastly different rates. Our method optionally allows a user to specify additional constraints according to artistic preferences. The motion normalized output provides a novel way to compactly visualize the changes occurring in a scene over a broad range of timescales.
在观察视觉世界时，时间现象无处不在：人在行走、汽车在行驶、河流在流淌、云朵在漂移、影子在拉长。其中一些现象，如水花飞溅和云的运动，其发生的时间间隔要么太短，要么太长，人类难以轻松观察到。高速视频和延时视频提供了一种流行且引人注目的方式来可视化这些现象，但许多现实世界场景呈现出以各种速率发生的运动。一旦选择了帧率，其他速率的现象充其量是不可见的，最坏的情况是会产生干扰性伪像。在本文中，我们建议自动归一化输入视频中不同运动的像素空间速度，以产生具有时空变化帧率的无缝输出。为实现这一点，我们建议在不同时间尺度上分析场景，以分离和分析以截然不同速率发生的运动。我们的方法允许用户根据艺术偏好选择性地指定额外的约束条件。运动归一化输出提供了一种新颖的方式，可紧凑地可视化在广泛时间尺度上场景中发生的变化。
