junyanz / VON

[NeurIPS 2018] Visual Object Networks: Image Generation with Disentangled 3D Representation.
http://von.csail.mit.edu
Other
530 stars 90 forks source link

Where's the viewpoint code? #7

Closed deepmo24 closed 5 years ago

deepmo24 commented 5 years ago

Hello, I can't find the usage of viewpoint code in your source code, I am not sure whether I ignore something, can you tell me about it? thank you.

junyanz commented 5 years ago

We get our viewpoint from the data loader. See this line. We use it to render a 2.5D sketch (depth, mask) from a 3D model. See this line.

deepmo24 commented 5 years ago

Thank you very much. I read section 3.2 "Generating 2.5D Sketches" of the paper again, and now I understand it.

junyanz commented 5 years ago

This is great!