korrawe / halo Goto Github PK

Hello,

Thank you for your great work.
I am trying to train halo_base by myself. Will you be able to share the config file in example experiments?

Best,

i wonder in the mano loss, why the mano output divide by 10? in my opinion, mano output is meter unit, and the GT joints is meter too.

Hi! Thanks for your great work! I want to know how to convert my 3d keypoints( from mano) to canonical pose? Or could you tell me which function in this repo is the implementation of B ^{-1} in the paper of equation 1 as the figure below?

I tried transform_to_canonical() in halo/converter.py but that didn't work.
I am not sure if I was wrong. Could you help me ?

Thanks for your awesome job again!

hi，HALO's Chamfer-L1 distance is 0.719mm(3D surface reconstruction quality) in the paper, but the eval_meshes.csv show the Chamfer-L1 distance is 0.00119,why?

Hello, Mr.Karunratanakul,

HALO is a nice work, especially the skeleton canonicalization part in paper.

It offers another feasible way to parameterize the pose.

In fact, I am reproducing HALO in FreiHAND dataset and I have some naive questions.

1): FreiHAND dataset doesn't has evaluation dataset, so I cannot observe the val loss in training.

My question is how can I know the training should be stopped from the real-time trainning loss?

2): Could you offer the Supplemently material you mentioned in paper?

I wish to know more details about the experiment.

3): I obtained YT3D dataset from official website.

However, they didn't provide joints and mano parameters.

And I notice that in line 32 of prepare_data_from_mano_param_keypoints.py , there is "default='../../data/youtuhand_raw'".

What is that?
How can I get this?

Sincerely looking forward to your reply.

Best wishes.

Hello,

Thank you for your great work.
I am trying to train halo_base by myself. When I run "prepare_data_from_mano_param_keypoints.py", I cannot find the file 'resource/skinning_weight_r.npy'. Could you share it?

Hello, Mr.Karunratanakul,
In your paper, you report the experiment result about IKNet in Table 2.
Did you reproduce this work on Youtube3D dataset?

Hi there!

First of all, congrats for this 3DV paper! It looks outstanding.

Did you use the MANO model implementation without any changes? I can't find the no_root_rot parameter in the original code.

Moreover, it would be great to know why did you use Hasson's MANO implementation and not the one from the repo related to the MANO paper? I am asking this because InterHands dataset used the latter, and it seems you adapted the code to use Hasson's implementation.

Appreciate your time and effort!