About camera-bevpool.cu and camera-geometry.cu

[cn-hezhu]

when I use my own transformation matrix with four cameras, there is a problem: the value of interval.z was negative, causing output_offset to be negative.

#pragma unroll
for (int j = 0; j < tile_size; j++) {
unsigned int output_offset = interval.z + (feature_block + j) * out_h * out_w;
output_bevfeat[output_offset] = accumulate[j];
}
May be there are some bugs in camera-geometry.cu？
But I don‘t know how to fix it.

[hopef]

Could you add my WeChat(woshixiwanga) to co-debug this?
I know that some implementations in camera-geometry.cu may be hard to understand and need to be careful.
I'll update this part later.

[cn-hezhu]

Could you add my WeChat(woshixiwanga) to co-debug this? I know that some implementations in camera-geometry.cu may be hard to understand and need to be careful. I'll update this part later.

OK, thank you for your reply.