Rana Hanocka

Hi @dhirajsuvarna , As a rule of thumb, it seems to be possible to collapse most datasets to 50% of the original edge count. There is no mathematical formula, I...

Hi @LiZimo , We did not include it (tried to keep the code as simple as possible), but you can easily add it to the code. Here is the function...

Hi, great question - thanks :) So ModelNet40 / ShapeNet is not manifold. Meshes that are not manifold do not have at most 2 incident faces - which breaks our...

> It might be worth using something like `pymesh` or `trimesh` to load and save meshes (nice built-in functionality to detect/fix non-manifold meshes). I tried these non-manifold fixes, and they...

Hi @sunhuaiqiang , The intermediate mesh pooling results are a nice way to visualize which parts didn't contribute to classification (they are exported during the test pass , if the...

Hi @fxy2012 , The links work fine for me. Are you in China? Since I am hosting the data in Dropbox, maybe the website is blocked by the firewall. In...

Hi @fxy2012 , The newest version of the code uses pytorch 1.2, you can install the environment as in the readme. Alternatively, you can check out an older version of...

Hi @liangqianqian123 , When encountering "bad" (valence 3) vertices (aka "invalids"), we clean them if possible. The issue is that these "valence 3" vertices cause many edges to be unable...

Hi @chengzg , You can remove small connected components using meshlab (via scripting).

Hi @chengzg , It is certainly possible, but it is more complicated. I believe meshlab is an easier approach. Here is a script which will do it ``` ``` You...