derkaczda

Thanks for the quick response! For the Open3D approach do you have code published for this project?

Thanks @OuyangJunyuan, I would like to have the code for your simple viz. You can send it via mail [email protected]. Thank you very much :)

I already wrote @OuyangJunyuan about that couple of weeks ago but did not get any reply, I don't want to post his code without his consent.

> In 2 to 5 iterations, we fine-tune the model from the previous iter for 256 epochs to save time. Also, it is ok to train for 3 iters since...

Interesting because it already takes up to 10 days to train the unet for me (RTX 6000) , did you do any further improvements?

Hello @ry4nzhu, any progress on this one? I have the same problem, also if I visualize the point clouds and compare them to the ground truth flow it is for...

Now that you mention it, I had a similar experience: Could reproduce it on a Quadro RTX 5000 but not on a RTX 3070

About 2.: Why multiply by 5, this seems like a random number to me. Similar to that why do this loop 5 times. https://github.com/liuzhengzhe/One-Thing-One-Click/blob/c6c2e05b57663c4fa490195d09c547b6fd197821/merge/model/pointgroup/pointgroup.py#L392-L395