Sampling points process in Pointrend

[MacavityT]

The process of sampling points described in the paper is as follows:
In each iteration, PointRend upsamples its previously predicted segmentation using bilinear interpolation and then selects the N most uncertain points (e.g., those with probabilities closest to 0.5 for a binary mask) on this denser grid.

But I find that implementation in detectron2 add some extra factors in ''detectron2/projects/PointRend/point_rend/point_features.py, line 141&142"

point_coords[:, :, 0] = w_step / 2.0 + (point_indices % W).to(torch.float) * w_step
point_coords[:, :, 1] = h_step / 2.0 + (point_indices // W).to(torch.float) * h_step

Why should point_coords add offset "w_setp/2.0" and "h_step / 2.0"?