How can I transform the poses (nerfstudio format) to opencv convention from OpenGL convention?

Question

How can I transform the poses (nerfstudio format) to opencv convention from OpenGL convention?

Opened this issue 3 months ago · 1 comments

I try to flip the y and z axes direction of the camera-to-world matrix but it seems that it is not enough. when I train generalizable Gaussian Splatting on DL3DV. The RGB loss suddenly increased a lot and failed.

c2w[..., :, 1:3] *= -1

Answer 1 · 2024-09-29T12:58:32.000Z

It seems to be code dependent. Have you figured out what happened in your code?