Jun Gao

Hi @EJShim, Yes, I also observed the normals could be flipped during training. This is because the isosurfacing (DMTet part) in GET3D only focuses on the extracted surface, and the...

Hi @EadmondDai, I haven't seen the Segmentation fault error in this code, do you have more information about the bug and the systems you're running (e.g. Ubuntu or Windows, GPUs?)

Hi @mazhelearn, Unfortunately, they're different matrices. The transformation matrix defined [here](https://github.com/nv-tlabs/GET3D/blob/6fda9cd15ab78e88db3ba00766df489a3ce88b41/render_shapenet_data/render_shapenet.py#L275) was only used to make it compatible with NGP. To use [the code](https://github.com/nv-tlabs/GET3D/blob/6fda9cd15ab78e88db3ba00766df489a3ce88b41/uni_rep/render/neural_render.py#L38) you mentioned, you need to use...

Hi @pallgeuer, thanks for the great questions! I think the divergence might be because the GAN is unstable to train. There're several opinions you can try to increase stability: -...

Hi, @Dandelionym, Thanks for your interest in our work! the 16GB memory is the default training size and it can be applied to either one category or multi-categories (the model...

Thanks for the information! I'm wondering, in the experiment section of the paper (Sec. 4 & 5), are you using this coordinate system? or do you have other additional alignment...