简体繁体 English

光流估计和视差估计有什么区别？

[英]What is the difference between Optical flow estimation and Disparity estimation?

原文 2021-03-25 12:07:37 7 1 image-processing/ deep-learning/ computer-vision/ opticalflow/ disparity-mapping

I am trying to understand some computer vision topics.我正在尝试了解一些计算机视觉主题。 One main difference I observed between these two is that In optical flow, the 2nd image is often at time (t+1) whereas in disparity estimation, its often the same time-step unless one is having a static view and using single non-stereo camera.我在这两者之间观察到的一个主要区别是，在光流中，第二张图像通常在时间 (t+1)，而在视差估计中，它通常是相同的时间步长，除非一个具有 static 视图并使用单个非立体相机。 Is there any other difference and their respective implications?还有其他区别及其各自的含义吗？

1 个解决方案

As you pointed out, Optical flow represents the displacement of pixels between an image at time t and at time t+1 whereas disparity estimation is the displacement of a pixel between one camera and another.正如您所指出的，光流表示图像在时间 t 和时间 t+1 之间的像素位移，而视差估计是一个相机和另一个相机之间的像素位移。 Strictly speaking these two tasks could be considered identical.严格来说，这两个任务可以认为是相同的。

However, in practice, disparity is computed using a "right" and a "left" camera which are horizontally aligned.然而，在实践中，视差是使用水平对齐的“右”和“左”相机计算的。 Therefore, the disparity is only horizontal (and in a single direction due to the laws of optics) and can be represented by a heatmap.因此，视差仅是水平的（并且由于光学定律在单个方向上）并且可以用热图表示。

On the contrary, Optical flow is a 2D vector field in which vectors can take any value.相反，光流是一个二维向量场，其中向量可以取任何值。

In machine learning, this distinction mainly changes the dimension of the output (1D for disparity and 2D for Optical flow) to predict as well as its scale (positive for disparity vs all real numbers for Optical flow).在机器学习中，这种区别主要改变 output 的维度（视差为 1D，光流为 2D）以预测及其规模（视差为正数，光流为所有实数）。

I hope my answer was clear:)我希望我的回答很清楚:)