search

3dlg-hcvc / paris

[ICCV 2023] Official implementation of the paper "PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects"
https://3dlg-hcvc.github.io/paris/
MIT License
59 stars 2 forks source link

Parameters setting #8

Closed Tokyo-dream closed 9 months ago

Tokyo-dream commented 9 months ago

This is the result trained through pretrain/parsed.yaml 0 This is the result trained by pretrained model 0 How can I set the parameters to make the mobile part more accurate?

Tokyo-dream commented 9 months ago

Thanks for this amazing work !

SevenLJY commented 9 months ago

Hi @Tokyo-dream. Thanks for your interest in our work!

As you’ve noted, the training for each object is essentially an optimization process, which can be easily affected by the randomness. I was also encountering the unstable training issue you mentioned in my practice. To get better results, it sometimes helps to tweak the learning rate a little bit or just train multiple times.

From my experience, there are varying degrees of training difficulty across these ten cases. Objects with relatively thin parts present a particular challenge as there are fewer opportunities for these regions to establish the correct correspondence. This can be considered a limitation inherent to our method. Increasing the number of views can, in many cases, help to enhance the likelihood of obtaining consistent positive results.