Projection Matrices for LUT formation

[aseemk98]

Hi, thanks so much for the paper and the implementation. I'm particularly interested in how you are populating your lookup table for fast-ray transform. The LUT stores a mapping between voxel coordinates -> image feature coordinates. And this is pre-configured before training/inference.
I'm having difficulty in understanding how you calculated the transformation matrix that allows the transform from voxel coordinates to image feature coordinates.
I see a transformation matrix called "sensor2ego" in nuscenes, is the inverse of this transformation used? Any insight would be greatly appreciated, thanks.

[aseemk98]

https://github.com/Sense-GVT/Fast-BEV/blob/9de045abcd8ca7d1229181d19e0224e0516d5425/script/view_tranform_cuda/input/projection_data.bin

I see this file but can you elaborate on the creation of this file?

[venkataramanas1]

hey @aseemk98 : were you able to make the project up and running ? if so cna you provide me steps

[trand2k]

Hi, i have some trouble went try to create LUT for my own camera setup too, can u give me some advise ?