You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, I am generating point cloud data with my own images using gray_code_decoder_disp.py. But the point cloud is scalloped as seen in the photo. In other words, it consists of many small squares parallel to the plane of the camera.
Sorry I totally missed this issue. I guess this problem is due to the stereo system's depth resolution. According to the stereo formula $z=bf/d$, when the focal length $f$ is fixed, given a unit of disparity $d$, the depth resolution is related to the baseline $b$. I.e., if you want the surface to be more smooth, you may need to narrow down the baseline.
Hello, I am generating point cloud data with my own images using gray_code_decoder_disp.py. But the point cloud is scalloped as seen in the photo. In other words, it consists of many small squares parallel to the plane of the camera.
Point Cloud Photos:
Full cloud: https://ibb.co/bWGD1DX
Zoom to small squares : https://ibb.co/f1TMFQc
Zoom squares side view: https://ibb.co/tL9xdqw
Even though the surface of the piece I scanned is completely smooth and flat, the point cloud is formed in this way.
The text was updated successfully, but these errors were encountered: