Closed ostapagon closed 2 months ago
Hi @ostapagon!
Thank you for your pull request and welcome to our community.
In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.
In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.
Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed
. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.
If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!
Thanks! This is a way to do what you need, but I'm afraid I don't think it fits as a component in PyTorch3D as it currently is. You have a new lighting class which is actually coupled to the particular mesh. So while the whole shading system in PyTorch3D can be overridden to do all kinds of things, as you demonstrate, I think it would add confusion to have a class like this.
@bottler thank you for the feedback. Could you consider adding notebook to the example folder? So users could try training lighting for the scene in a form of environment map, I checked issues and saw that people ask about it a lot(#1049, #695, #349). In the notebook I`ve provided a class with environment map and also converter from SH to env map texture.
I can provide more details in the description and write more sequential theory flow of what is happening there.
I`ve provided feature request here with a motivation to add this class. "render_with_envmap.ipynb" noteboot is just an example for usage of this class and posibility to convert spherical harmonics to environment map.