Depth Estimation

Depth Estimation
Goal: Generate an image of depths from one or two images.

Background

Depth vs. Disparity

For stereo methods, people usually estimate pixel disparity rather than depth.
That is, determining how far a pixel moves along the epipolar line between two images.

Usually, this involves first rectifying an images using RANSAC or similar. Then a cost volume can be built. Then argmin is applied to the cost volume to find the best disparity estimate.

Disparity is related to depth by the following formula: \[disparity = baseline * focal / depth\]

• \(focal\) is the focal length in pixels. This is a correction factor for the resolution of the disparity.

  This can be calculated as (height/2) * cot(fov_h/2)

• \(baseline\) is the distance between the camera positions. This should be in the same units as your depth.

Stereo Depth

Typically people use cost-volume to estimate depth from a stereo camera setup.

• StereoNet (ECCV 2018) (My Summary) is a method by Google's Augmented Perception team.

• Casual 3D photography (SIGGRAPH ASIA 2017) includes a method for refining cost volumes and a system for synthesizing views from a few dozen photos]

Depth from Motion

Depth is generated in real-time based on motion of the camera

• Depth from Videos in the Wild (ICCV 2019)
• Depth from Motion for Smartphone AR (ACM TOG 2018)

Depth from Focus

• Single Image Depth from Defocus Cues (CVPR 2019)