autonomousvision / differentiable_volumetric_rendering

This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"
http://www.cvlibs.net/publications/Niemeyer2020CVPR.pdf
MIT License
794 stars 90 forks source link

How to prepare data for the model? #60

Closed Ethycs closed 3 years ago

Ethycs commented 3 years ago

Hi,

It's not clear to me how to replicate your data format for the training data that comes with the model. Would you mind providing guidance?

Thanks

m-niemeyer commented 3 years ago

Hi @Ethycs , if you use our download script as indicated here in the readme the data is automatically extracted such that you can start training model.

Good luck with your research!

Ethycs commented 3 years ago

@m-niemeyer, allow me to restate: Can you please provide guidance on preparing other data (such as other models from Shapenet) to be compatible with the Choy and Kato renderings and describe your methodology.

Ethycs commented 3 years ago

@m-niemeyer