Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Some questions about citygsv2 training #110

Closed
qqa111 opened this issue Feb 14, 2025 · 1 comment
Closed

Some questions about citygsv2 training #110

qqa111 opened this issue Feb 14, 2025 · 1 comment

Comments

@qqa111
Copy link

qqa111 commented Feb 14, 2025

1、When performing the Finetune model parallel and merge steps, the merged result is a checkpoint, How to generate a ply?
2、In Mesh extraction and evaluation step, python utils/gs2d_mesh_extraction.py
outputs/$NAME
--voxel_size $VOXEL_SIZE
--sdf_trunc $SDF_TRUNC
--depth_trunc $DEPTH_TRUNC \
What do the parameters voxelzize, sdf_trunc, and depth_trunc mean and how to set them?
3、Can we set sh_degree to 3 in citygsv2 \ lfls_sth2_trim. yaml during the Train coarse model step?

@DekuLiuTesla
Copy link
Owner

Hi, @qqa111, 1. you could try utils/ckpy2ply.py. 2. Please search for TSDF for more details. 3. Yes, of course. Just simply change it in the config file.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants