chenxun

Are you training a camera-only model?

In fact, this operation is present in the original code of transfusion head in BEVFusion. However, the mit-bevfusion and the BEVFusion from NeurIPS 2022 differ in the final step of...

I'm confused about this too, but in the vtransform of the NeurIPS 2022 bevfusion, the output is [y,x], and in its (and BevDet's) transfusion head the position you mention is...

Have you tried a non-square bev LCFusion? Does the 2d backbone of the bev model accept input properly?

draw_heatmap_gaussian(heatmap[gt_labels_3d[idx]], center_int, radius) is the original version of transfusion head. The original version should correspond to BEV features in the format [Y, X], while center_int[[1,0]] corresponds to [X, Y]

So, the grid_size should also be reversed in the same way, but this was forgotten in the transfusion head of this version. Alternatively, consider using the original transfusion head but...

https://github.com/open-mmlab/mmdetection3d/blob/fe25f7a51d36e3702f961e198894580d83c4387b/mmdet3d/models/utils/gaussian.py#L46C5-L53C69 From this, it can be seen that the default heatmap shape in mmdet3d is [Y, X]

Yes, you can check the implementation of CenterHead in CenterPoint within mmdet3D, which also uses [Y, X] for BEV features. However, the BEV features obtained from the sparse encoder in...