5,337
edits
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume: Difference between revisions
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume (view source)
Revision as of 00:33, 16 June 2020
, 16 June 2020→Learnable Cost Volume
| Line 70: | Line 70: | ||
===Learnable Cost Volume=== | ===Learnable Cost Volume=== | ||
A disparity space image (DSI) is a | A disparity space image (DSI) is a 2D tensor which stores the matching values between two scanlines. | ||
In 3D (with 2D images rather than 1D scanlines), it is called a 3D cost volume. | In 3D (with 2D images rather than 1D scanlines), it is called a 3D cost volume. | ||
Each slice \(i\) is computed by taking images \(I_1\) and \(I_2\), sliding image \(I_2\) down by \(i\) pixels, and subtracting them to yield | Each slice \(i\) is computed by taking images \(I_1\) and \(I_2\), sliding image \(I_2\) down by \(i\) pixels, and subtracting them to yield | ||