Depth Estimation is the process of determining the distance between the camera and each pixel in an image.
This can be achieved through analyzing either single or multiple views of a scene.
In the case of traditional methods, depth is derived by employing multi-view geometry techniques to establish the connection between different images. However, more recent approaches have emerged that enable direct depth estimation. This can be accomplished by minimizing the regression loss or by training a model to generate a new perspective from a sequence of images.

These advancements have opened up new possibilities in accurately estimating depth information from visual data.