IPNet
IPNet copied to clipboard
bharat-b7
Repo for "Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction, ECCV'20(Oral)""
Dear Authors, Thank you for your amazing work! I have been following your work on IPNET with great interest and admiration. Your approach has shown remarkable results in your paper....
Hi guys, does anyone encounter this problem? ``` python smpl_registration/fit_SMPL_IPNet.py out_dir/body.ply out_dir/full.ply out_dir/parts.npy out_dir/cent.npy out_dir/ Traceback (most recent call last): File "smpl_registration/fit_SMPL_IPNet.py", line 16, in from kaolin.metrics.mesh import point_to_surface, laplacian_loss...
Thank you for providing the wonderful paper and code. I followed your ReadMe and ran "Run demo IP-Net". As a result, I got a mesh that looks like the mesh...
I download the model by https://datasets.d2.mpi-inf.mpg.de/IPNet2020/IPNet_p5000_01_exp_id01.zip, but it damaged
Hi, Thank you very much for sharing your work. I am trying to prepare the training data. However, I come across two questions. (1) In step 1. we are supposed...
Thank you for the excellent work. By the way, would you also share your pre-trained models for the IPNetMano (Parts, especially hands modeling) and IPNetSingleSurface (for the case, where there...
As in the training cmd, the project use 0.15 and 0.015 to multiply on a normal distribution for points shift augmentation; my question is that what size is your voxel...
 I use fit_SMPLD.py to fit scan.obj, but the result is not good. Could you please point out where I was wrong?
If I have a texture island map and want it to register to the SMPL model along with my scan obj file for the same. How can we do that?
@bharat-b7 Hi, Bharat~ I really interesting about your paper and code, but I have a question about the part probabilities: For each query point p, you calculate a probability _parts_softmax_...
