David Bojanić

Hi, not an expert but i believe there might be an error in quaternion multipication in transform_functions.py --> qmul(q, r) function. ``` w = terms[:, 0, 0] - terms[:, 1,...

Centering and scaling ruins the results?

2

Hi, first of all, thank you for the python implementation. I tried registering the bunnies you provided with the `test.py` function and the results were good. However, when centering and...

Hi, thank you for the open-source code. I am using the python wrapper for GO-ICP from @aalavandhaann and I noticed something. When I use his script with default parameters and...

Hi Song, thank you for your work. As the title says, could you share the fitted SMPL models onto the 194 male and 181 female subjects from the NOMO dataset?...

Training data + augmentation process for the 3D model LVD_voxels_SMPL

1

Hi thank you for your great work! I wanted to ask what data did you use to train the 3D version of the code LVD_voxels_SMPL with the IF-Net backbone?

Hi, in your paper you state that the DFaust dataset "contains 40, 000 real undressed human meshes for 65 action sequences." Could you please elaborate this? I cannot find the...

Hi, can you specify more clearly which data do you use for training? In the paper you say that you use the SURREAL and DFAUST dataset to train your network....

Hello, first of all, thank you for sharing your code with the community. I was wondering how do you address that people sometimes go outside of the frame of the...

Quesiton regarding test set

1

Hi, you say in your work the following: > We use the point cloud pairs whose overlap is τo ≥ 30%, resulting in about 16.6K pairs for training and about...

Backbone gpu memory increasing after each batch

8

Hello, first of all, thank you very much for sharing the implementation! I was wondering if you experienced issues with GPU memory increasing after every batch using the ViT backbone?...