Generate 3D coordinates by importing the corresponding 2D positions after the alignment process

[JesseJiang010]

I need to obtain the 3D coordinates of a specific point on an object that Reality Capture can hardly detect as a feature point. Is it possible to manually input the pixel coordinates of this point on the image, and have the software automatically generate its 3D position?

[OndrejTrhan (otrhan)]

Camera Parameters in the output XMP file

You can do it in RealityCapture, but for such places it could be not so precise. Like, place at least two control points on the images and then you can check the value in pixels and 3D pose of the aligned model. [image] [image] To reverse the process, I meant to compute it backwards. Like, you know the 2D coordinates, so (px - (image width / 2)) / scale = m[0] and so on. For this we don’t have any documentation, but it is possible to find some way over the internet (I mean the general pro…

[JesseJiang010]

Thanks! I’m working on reversing the process to calculate a specific 3D position using two cameras. Just to confirm, in Reality Capture, does the image origin in pixels start from the top-left corner? And for normalized coordinates (where x and y are in the range [-0.5, 0.5]), is the origin at the center of the image, with x positive to the right and y positive upwards?

[OndrejTrhan (otrhan)]

Yes, the systems should be oriented like that.

[JesseJiang010]

Thank you so much for the response!