Hu Wenbo

Why the linear discriminator D works

9

Dear authors, Thanks a lot for the amazing work and sharing the code. Accroding the appendix A in the paper, "_discriminator D is a linear component (similarly to Kanazawa et...

Training time

4

Hi, Thanks for sharing the training code. Does the code work for multiple GPUs? If not, how long it takes to get the reported SOTA performance model? Thanks very much

Training scripts

1

Thanks for the valuable code and dataset. Is it possible to provide the training code for better reproducibility, as there are some training hyper-parameters. Thanks very much.

Questions regarding to the PSNR/SSIM results

9

Hi @cchen156 , This work is very exciting. But I have a question about the quantitative results reported in the paper Table3. I downloaded the source code and trained model,...

Hi, Thanks for your awesome work. I noticed the InterHand2.6M dataset used in the paper has 257K 2D hands in the training set, however, the latest released InterHand2.6M has 528K...

support for MipNeRF360

1

Thanks for your awesome project. Is there any plan to support the MipNeRF360 model/dataset?

Add an option to control backface culling

12

**Context** F3D is used to render different kind of geometries, most of them contain oriented faces with a concept of backfaces and frontfaces. F3D currently always show the backface but...

generate_ellipse_path

2

Hi, Thanks for your awesome framework. But I found the "generate_ellipse_path" function borrowed from the https://github.com/google-research/multinerf is not compatiable with the coordinate defined in "nerf_360_v2.py". Thus, with this function we...