Chen-Hsuan Lin
Chen-Hsuan Lin
Hi @a1445605672, could you post your training command and the full error log?
Could you post the full error log? It's not possible to identify issues without it.
Hi @chongxian, could you verify if COLMAP found the correct camera poses?
You can use [this notebook](https://github.com/NVlabs/neuralangelo/blob/main/projects/neuralangelo/scripts/visualize_colmap.ipynb) to help visualize the cameras and verify if the trajectory looks consistent with the images.
Hi @GuangyuWang99, which commit are you at in the code? If you're not at the latest `main`, does the issue persist if you pull and rerun the mesh extraction?
@DerKleineLi thanks for this! It's indeed a bug on our side. We will fix it in the coming days.
I have been able to reproduce the issue. This has been marked as a bug and we will look into this.
Update: we have updated the data structure of the COLMAP artifacts in the latest `main` branch to avoid confusion. We are now storing the raw images in `images_raw` and the...