get output disparity referred to the right about hd3 HOT 2 CLOSED

Hi, I can think of two solutions for your purpose:

1. Feed the original two images into the network and you'll get the disparity map w.r.t the left image. Then you can unproject the image coordinates of left image to 3D space, transform them according to the relative camera motion, and project them into the right image. You'll get the disparity/depth map of the right frame, but the density might not be 100%;

2. Swap the left and right images, and flip them horizontally at the same time. Feed the processed image pair to the network, and flip the prediction at last. In that case, you'll get a dense disparity map of the right image.

from hd3.

will try that. thanks for the quick reply!

from hd3.