Lucas Nunes

Hi! So, first regarding the loss getting stuck, I would say that it is normal. Also when training with semanticKITTI I was also noticing the same, but even with it...

To check whether it is overfitting I suggest to give as input one of the training point clouds. Also, you can try changing the conditioning weights in the completion pipeline,...

You could be that your dataset is too small. How many samples do you have? For me to have a better view of it, could you share the results using...

Can you share the config file used for training and the command you used to generate those results? I want to check the hyperparameters used for training and during inference....

Alright! Can you try generating again with more denoising steps, with `-T 200` for example?

I would suggest training for longer and removing the scheduler from models.py Since you have less data you for sure need to train for longer, but with the scheduler, the...

1. You can replace this [line](https://github.com/PRBonn/LiDiff/blob/4dc21ce098b06266b8fceae0cebf2bbcee61ca28/lidiff/models/models.py#L346) with just "return optimizer" 2. To train the diffusion model the amount of iterations counts a lot (since at each training iteration a random...

If the loss goes to nan the learning is too high, you can decrease it by half and try training again. Regarding the points placed in origin I haven’t seen...

You can send me an email and we can arrange the meeting through the email: [email protected]

I would try to replicate the same setup that we have on SemanticKITTI but using your data. So, using the default parameters and trying to have the condition point cloud...