search

donydchen / mvsplat

🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
https://donydchen.github.io/mvsplat
MIT License
848 stars 40 forks source link

training with acid #73

Open ChengLiDuoJi opened 3 weeks ago

ChengLiDuoJi commented 3 weeks ago

屏幕截图 2024-10-27 215743 I use acid too. I found that after 60k steps, it often skip bad samples. Should I stop training? But I found your config file wrote that mvsplat should train 300k steps.

ChengLiDuoJi commented 3 weeks ago

屏幕截图 2024-10-27 215743

donydchen commented 3 weeks ago

Hi @ChengLiDuoJi, the skipping operation is as expected, and there is nothing to be worried about. This is because the training mainly intends to use raw data with image resolution 360x640, those raw images with other resolutions will be automatically skipped. Related technical details are in https://github.com/donydchen/mvsplat/blob/31ac68880f93c40ea9e7b2f9d6ff6caf187e5871/src/dataset/dataset_re10k.py#L156-L164

In short, ignore this warning message and continue training to 300K steps.