how to deal the differernt shape between vibe predicted and gt?

[rabbitchenrui]

Thanks for your good job! It behaves well on many dataseets. But when I want to train my motion-aware SmoothNet, I meet the question that vibe geet different frames to gt? I noticed that your ASSIT++ data predicted and gt has the same dimension and frames, so how to deal the differernt shape between vibe predicted and gt? Were you delete the redundant frames ？ or other methods? Thanks for your good job again.

[ailingzengzzz]

Hi @rabbitchenrui,

Could you please tell me why you get the different prediction and GT frames? Aligning the corresponding prediction with GT should be proper. In this case, you can simply delete the redundant frames.