check_colmap_installed() in nerfstudio.utils.install_checks.py previously didn't use the colmap_cmd attribute of ColmapConverterToNerfstudioDataset. This change addresses that so an alternative colmap_cmd can actually be used
generalize get average image metrics
Co-authored-by: Le Hoanh <leh19@csl-leh19.cs.aalto.fi>
Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
* Fix exported poses when Splatfacto pose optimization is enabled
Currently works correctly only with --eval-mode=all
* Make Splatfacto pose adjustments consistent with Nerfacto
Also allow exporting Nerfacto-optimized poses. Fixes#3073.
Second revision where the rotation and translation parts
are handled separately.
Fix: when --use-sfm-depth is enabled and the model is given by --colmap-model-path. It searches the wrong reconstruction directory
Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
* pixi installation optiont
* chore: Update .gitignore to include /third_party and include pixi lock file
* feat: Update download and training commands for dozer data
The commit updates the download and training commands for the dozer data in the `pixi.toml` file. It renames the `download-sample-data` command to `download-dozer-data` and modifies the `train-example-splat` and `train-example-nerf` commands to include the dozer data as a dependency.
This makes it easy to run an example training for both nerfacto and splatfacto
* update to include range between 3.8 -3.10
* Add Pixi installation instructions to the installation.md file
---------
Co-authored-by: maturk <30566358+maturk@users.noreply.github.com>
* Update user creation process (non sudo)
Minor simplifications
* Keep default shell (sh) during build
* Add sudo privilages
Custom rules for sudo group
Comented lines for easy image modification
---------
Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
If the user sets near_plane as 0.0, the "or" will take the second term (float(torch.min(depth))) instead of using the 0.0 value. We fix this by checking explicitely for a "None" variable
* bionerf markdown file
* method description in markdown file
* inserting bionerf in index file
* bionerf description
* fixing image paths
* including results on readme
* deleting last line from bionerfs page
* fixing typos in bionerf.md
* bionerf markdown file
* method description in markdown file
* inserting bionerf in index file
* bionerf description
* fixing image paths
* including results on readme
* deleting last line from bionerfs page
* Added the possibility to import a metashape ply file
* FIxed double import and import order
* Ruff Format
* Ruff Format
* Ruff Format
* Ruff SUCKS
* make ply as an option and use applied_transform
* fix ruff
* fix bugs when ply doesn't exist
* fix bugs when ply doesn't exist
* no backtrace for ValueError
* hot fix
* Add return type
---------
Co-authored-by: simonbethke <simon.bethke@gmail.com>
Co-authored-by: Jianbo Ye <jianboye@amazon.com>
Co-authored-by: Brent Yi <yibrenth@gmail.com>
* metashape_utils: work with camera groups
* metashape_utils: console message when skipping a camera due to a missing image
---------
Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
* Use AbsGrad to get better results with less gaussians
* some adjustment such that splatfacto-big don't go OOM
* use new gsplat version
---------
Co-authored-by: Jianbo Ye <jianboye@amazon.com>
Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
* GaussianSplats export: allow uint8 in ply
* Ruff formatting
* Add test and narrower typing
* Formatting
* Revert narrow typing, not supported by old python
* Fix typing for old pythons
* changed run_hloc args to fill image_ids (added image_list and changed camera_mode to PER_IMAGE)
* added parameter same_camera on ns-process-data for multifocal cases in hloc. Also updated colmap_to_json to detect if there is one or several cameras per frame while keeping the camera type specifications
* ruff-formatted changes in colmap_utils.py
* use_single_camera_mode update args, including colmap_utils and hloc_utils
* changed multicamera warning's print to CONSOLE.print
* fix path typo console print
* rewritten use-single-camera-mode comment in ns-process-data
* (fix) inverted bool for colmap_utils
* change im_id to im_data.camera_id
---------
Co-authored-by: Jianbo Ye <jianboye@amazon.com>
* changes for trainer to support webui
* Update trainer to support webui
* format
* add a seperated shutdown() function to stop training
* typo fix
* get rid of _stop_viewer_server()
* Update trainer.py
* organize import
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
