mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-11 18:44:21 +08:00
38f3df3d10
The Newton undistortion loop selects a zero step when its Jacobian determinant is too small, but computes a division by the original determinant in the unused branch of `torch.where`. Forward output is finite while coordinate and calibration gradients become NaN at a singular Jacobian. |
||
|---|---|---|
| .. | ||
| cameras | ||
| data | ||
| dataparsers | ||
| field_components | ||
| model_components | ||
| pipelines | ||
| plugins | ||
| process_data | ||
| scripts | ||
| utils | ||
| test_nerfacto_integration.py | ||
| test_splatfacto_integration.py | ||
| test_train.py | ||