Some confusion in the paper

[HongqingThomas]

Some confusion in the paper

[Steve-Tod]

In short, in the packed scenario, more graspable regions are occluded compared with the piled scenario, where occluded regions are usually also not graspable. So the GAP between GIGA and GIGA-Aff is larger in the packed scenario.

Even in the piled scenario, GIGA is still better, although not as much as in the packed scenario. And we assume this is also due to the geometric understanding from multi-task training.

These two points do not contradict each other. Because when we discussed the piled scenario, we didn't say we do not have this property in the packed scenario. On the contrary, as you mentioned, we did say the geometrically-aware feature representation learned via geometry supervision facilitates the model to predict grasps on partially visible objects for packed scenario.

[HongqingThomas]

Thanks for your explaination, it's very useful!