godzarathustra / symmetrynet Goto Github PK

I read your paper with great interest. It is very detailed, visual, and mathematically thorough.
But one point you breeze past is the method how you generate the ground truth symmetry data. Could you explain which algorithm or project you used, so this work can be applied to other datasets like linemod.

There is no image data in symmetrynet/data/scannet/rgbd/holdout_scene/<scene_folder>.

FileNotFoundError: [Errno 2] No such file or directory: '/home/zz/dataset/symmetrynet/data/scannet/rgbd/holdout_scene/scene0011_00/000000-color.jpg'

I cannot access the files on Dropbox (error message is "link temporarily disabled") and the Baidu Linux client is not working. Could you provide an alternative way to access the files?
Thanks in advance for your help.

Thanks for your excellent work. I was confused by the following code snippets,. What are the rules for setting target_mode?

Good morning, I am reproducing the results with a custom dataset, whenever y try to join side by side the original pointcloud and the computed reflected pointlcouds, both appear really far away from each other, which is easy to solve by substracing the center, but the thing is that the reflected pointcloud appears rotated, any idea on what could be happening?
Thank you in advance!

Hello! We have replicated your method and interpreted the code. In order to obtain a parametric representation of the symmetry planes, I tested it on the pretrained model and dataset you provided using the evaluation/eval_ref_shapenet.py script. I saved the variables 'points', 'out_cent', 'out_sym', 'target_cent', and 'target_sym' from lines 182 and 183, and performed error calculations and visualizations. However, we found these results to be very strange and the accuracy was quite low. We are looking forward to your guidance on this matter. Thank you very much!

I am very interested in your work. Recently, I have tried to reproduce your work, but I do not have a complete data set. I hope I can get a complete data set.My email is [email protected]
Thank you very much!

Heya, could you upload the weights on Dropbox or any other website which doesn't force spyware on your computer please?