Shubh Maheshwari

Training Loss explodes when training on NTU-Dataset 120

8

Hey @DegardinBruno Great work. Thanks for sharing your code! While training on the NTU-120 the generator loss is exploding. We only changed the batchsize from 32 to 380 ``` [Epoch...

Rotation term during post-processing

1

Hi @wenbin-lin, Thanks for releasing the motion completion module in OcclusionFusion. I had a doubt regarding the implementation of graph-based ARAP deformation. The paper mentions the use of ARAP term...

Inconsistency in pred_vismask computed from Corrnet

3

Hi, I am trying to reproduce results for Morig, but facing issues with deforming the mesh using the point cloud motion. The deformation (specifically `pred_vtx_traj` ) I am getting by...

Kindly have a look at https://github.com/Algomorph/NeuralTracking/blob/9b78710cf51fd97211c95517b4ed65b2c1cd8be5/rendering/pytorch3d_renderer.py#L37 should be ```` fx = fx_screen / half_image_width ```` Similarly in line 39