search

Sentient07 / IFMatch

Implementation of the paper Implicit Field Supervision for Robust Non-rigid Shape Matching
MIT License
22 stars 4 forks source link

Evaluation setting--template info. #3

Closed chunjins closed 2 years ago

chunjins commented 2 years ago

Hi there,

Your work is excellent. I like it very much.

Now I am trying to run the evaluation code with the pre-trained model and the test-set shapes (FAUST-Remesh dataset) you provided. But it seems that I need the template shape, I think it should be the one you use for training, right? Could you provide it?

I randomly set the template shape as 'tr_reg_080', but it does not work, since the corresponding surface point file does not have 'trig_id' and 'bary_coord'.

File "/IFMatch/code/dataset.py", line 220, in _get_template_info templ_trig_id = np.squeeze(templ_surf_mat['trig_id']) KeyError: 'trig_id'

Sentient07 commented 2 years ago

Hello,

Thanks for your interest. I've added the templates to our data directory (https://nuage.lix.polytechnique.fr/index.php/s/RjtprA8gSjgnEkt?path=%2F). We use the normal template at training and the high-res (called dense) for evaluation. Feel free to reopen if you still have questions.

chunjins commented 2 years ago

Thanks for providing the template file.

Now I meet another problem. According to the paper, there is only one human template for all different datasets, right? Then, how do you get the ground truth correspondences between the template and all training shapes?

I think it is related to the parameters of 'trig_id' and 'bary_coord'? But how can I get them?