search

yihua7 / SC-GS

[CVPR 2024] Code for SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
https://yihua7.github.io/SC-GS-web/
MIT License
502 stars 28 forks source link

Unconvergence on aleks-teapot when training the SC-GS #40

Open guanjunwu opened 6 months ago

guanjunwu commented 6 months ago

Hi, thanks for your great work! I'm trying to use SC-GS to train the interp/aleks-teapot dataset. That's my command:

python train_gui.py --source_path data/hypernerf/interp/aleks-teapot --model_path outputs/hypernerf/interp/aleks-teapot --deform_type node --node_num 512 --hyper_dim 8 --eval --gt_alpha_mask_as_scene_mask --local_frame --resolution 2 --W 540 --H 960

image

It seems like training cannot convergence. I'm wondering whether the author are also faced with similar problem? As I concerned, it may caused by large motion and error camera poses?

yihua7 commented 6 months ago

Hi,

The problem is unusual, and I haven't encountered this phenomenon before. Even if the motion is significant, the static parts should remain unaffected and can be reconstructed accurately. Is this dataset synthetic or real? It could possibly be an issue with the camera, such as inaccurate parameters.