Jianhang Yan

Something wrong in computing 3D IoU

4

https://github.com/hughw19/NOCS_CVPR2019/blob/14dbce775c3c7c45bb7b19269bd53d68efb8f73f/utils.py#L192 Hi, when I debugged method `asymmetric_3d_iou()`, I found that ` bbox_3d_1` shape is (3, 8). Therefore, `bbox_1_max` shape is (8,), so are `bbox_1_min`, `bbox_2_max`, and`bbox_2_min`. But I think their...

Pearson Correlation Loss in paper or code

4

Hi, I found that the Pearson Correlation Loss of paper and code is inconsistent. in paper:  in code: https://github.com/VITA-Group/FSGS/blob/8c2e181821b6e21afe030aa52d155c7eac18eb47/train.py#L105-L108