Nilesh Kulkarni

Hi @mickeyding, Thanks for your interest in our work, I checked the links and the CMU box links seems accessible. Let me know if you are still facing issues. Thanks,...

Hi, Please find the models here. https://umich.box.com/s/lik2xukm5qtn68lmqim60altus7k5o1g Also, if you can access the `mean_shape.mat` file under `cachedir/shapenet/` it also has the corresponding verts and faces which you can dump as...

Hi Anand, Step 2 can be done using this [code](https://github.com/shubhtuls/volumetricPrimitives/blob/3d994709925166d55aca32f1b6f448978836a05d/preprocess/shapenet/precomputeShapeData.m#L63). Alternately you can also run [binvox](https://www.patrickmin.com/binvox/) on the mesh obj file, and then using that voxel volume as input to...

Hello, Thanks for your interest in our work 1. The mapping from a 2D image to UV is a predicted value output by the learned CNN. 2. The mat file...

@carpedm20 Hi, Did you find any possibles pointers on this issue of high test perplexity? I was trying to debug it and any help would be appreciated.

I think this is an issue with PyTorch version. The code is implemented for 0.4 Thanks!

I think you should refer to this if you are still interested in viz. It is available once you login https://samp.is.tue.mpg.de/media/upload/show_pkl.txt