Rana Hanocka
> Also you added the assert there, it must be some reason. May i know what problem you have experienced before? So if the smallest connected component (a pyramid object)...
> 1. Would like to ask if this could work with a data set that has no defined category (example vases could be mixed in with mugs in the same...
> Yes i can combine your set of "aliens" and "chairs" but would it still work if i do not explicitly categorize them as "aliens" and "chairs" when training/testing?.So for...
> I see, i kind of understand what you are trying to say. > So it would be close to impossible to label the alien model parts with 1-3 and...
I think you can try to work with the data I have first, to see if it will work first on a single shape class (i.e., just aliens). And then...
Hi @liangqianqian123 , It is called a "mesh union" in the code. Specifically, see [union_groups line](https://github.com/ranahanocka/MeshCNN/blob/29c30a4d6dee123cacbb662e3f5666420c0e94c5/models/layers/mesh_pool.py#L107) in `__pool_side`. This is defined in the [Mesh_union](https://github.com/ranahanocka/MeshCNN/blob/master/models/layers/mesh_union.py) class.
> Is it in the class MeshUnion "rebuild_features_average"? yep!
As we discussed previously, I will add my MATLAB scripts (eventually...) to this repo which does that. But of course, I will accept a PR which does that within the...
Awesome! Thanks for letting me know. Yeah, I trained that network on 2250 edges, so deviating from that too much probably won't work well. It is possible to retrain the...
@obisker I am curious -- where is this mesh from? It looks like it may have been scanned or something, which is pretty cool.