The code implementation of roi's camera intrinsic matrix might be ​​inconsistent with the paper

[tiandunx]

At line 66 in mv2d_head.py, intrinsic[:, :2, 2] = intrinsic[:, :2, 2] - bbox[:, :2] - 0.5 / scale, but in paper,

So why do we need to divide by 0.5/scale in the formula instead of multiplying by scale？