4DGaussians icon indicating copy to clipboard operation
4DGaussians copied to clipboard

Published 20 hours ago • verified publisher icon hustvl

The performance of the model

Open zhaohaoyu376 opened this issue 11 months ago • 5 comments

I followed the example code to train hypernerf scenes such as virg/broom, but the training results are not as expected. Why is that?

13999_0 13499_0

zhaohaoyu376 avatar Mar 28 '24 02:03 zhaohaoyu376

QQ图片20240328153734 The model doesn't converge.

zhaohaoyu376 avatar Mar 28 '24 07:03 zhaohaoyu376

I have tried multiple environments, including py37+torch1.31+cu11.6 and py38+torch2.01+cu11.8. However, the final results are all not satisfactory.

zhaohaoyu376 avatar Mar 28 '24 11:03 zhaohaoyu376

I have tried multiple environments, including py37+torch1.31+cu11.6 and py38+torch2.01+cu11.8. However, the final results are all not satisfactory.

It looks very strange. Can you show me the point clouds generated by colmap? It may look like: image

which is previewed by visual studio code.

guanjunwu avatar Mar 28 '24 14:03 guanjunwu

I have tried multiple environments, including py37+torch1.31+cu11.6 and py38+torch2.01+cu11.8. However, the final results are all not satisfactory.

It looks very strange. Can you show me the point clouds generated by colmap? It may look like: image

which is previewed by visual studio code.

This is the point clouds generated by colmap. QQ图片20240329092121 This is the point clouds generated by the model. QQ图片20240329092218

zhaohaoyu376 avatar Mar 29 '24 01:03 zhaohaoyu376

It seems that the original 3D Gaussians do not fit well. In my test, after 3000 coarse iterations, the training PSNR will be up to 20. Have you tested in any other scenes?

guanjunwu avatar Mar 29 '24 07:03 guanjunwu