Jun Gao

I managed to submit my result to the server, but I have been kept in the status: "Evaluation is in progress" for two days, is it typical to be so...

Thanks a lot!

The test_list.txt has the same format as pixel2mesh: https://github.com/nywang16/Pixel2Mesh/blob/master/Data/test_list.txt

Hi @Kuang-Hiu It seems VS didn't have the corresponding C++ compiler from this error information (note that the code also require `nvcc` to compile the custom cuda kernel, not sure...

Hi @Kuang-Hiu I checked the github issue from [StyleGAN3](https://github.com/NVlabs/stylegan3) Maybe this [issue](https://github.com/NVlabs/stylegan3/issues/98) is helpful for you?

Hi @Sheldonmao, We haven't included that part in the code yet, this is in our future plan of release, please stay tuned!

Hi, @Siziff Thanks for checking our paper so carefully! Re 1: the rendered images from the synthetic dataset (e.g. shapenet) are used to feed into the discriminator to classify whether...

Hi @dmoham1476, Since we're doing unconditional 3D shape generation, we don't need the input image during the inference, the `val.txt` and `text.txt` are only used for evaluating the performance of...

Hi @SteveJunGao, We didn't do that in our paper, you can check this issue for more details about it #48

Hi @zhu-yuefeng , Re detailed mesh: What's your `tet_res` when you run the inference? You can increase it to `100` or even higher to make a more detailed mesh (You...