* Add instructions for using Spectacular AI tools
Adds easy support for new device types: OAK-D, RealSense and
Azure Kinect, as well as an alternative pipeline for iOS.
* Grammar fixes in docs/quickstart/custom_dataset.md (Spectacular AI section)
Co-authored-by: Matias Turkulainen <30566358+maturk@users.noreply.github.com>
* Fix section label in the Spectacular AI section of custom_dataset.md
* Update custom_dataset.md: typo fix.
"montions" -> "motions"
---------
Co-authored-by: Matias Turkulainen <30566358+maturk@users.noreply.github.com>
fix pixel sampler setup for cameras with metadata other than fisheye crop radius
Co-authored-by: Matias Turkulainen <30566358+maturk@users.noreply.github.com>
* Add support for Project Aria datasets.
1) An export script for processing Project Aria datasets
2) Add support for Fisheye624 cameras
3) Add support for center-crop masking and sampling
Example commands for running nerfstudio on Project Aria data:
python scripts/datasets/process_project_aria.py --vrs_file=<path_to_vrs> --mps_data_dir=<path to MPS directory> --output_dir=<nerfstudio_data_dir>
ns-train nerfacto --data <nerfstudio_data_dir> nerfstudio-data --orientation-method none
* Clean up type errors
* Fix formatting
* Fix linter errors, import, and use absolute file paths
* Add aria subcommand to ns-process-data
* Appease ruff
* Add Aria to docs
* Fix docs, add back import try/except
* nit: path.as_posix() -> str(path)
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
* Fix large dataset (> 512 images) training in viewer_beta (#2586)
* fix index bug in update_camera_poses of viewer
* Set Ruff line lenth
---------
Co-authored-by: Gina Wu <42229107+ginazhouhuiwu@users.noreply.github.com>
* Update hloc and add new matcher types
* Update dockerfile comment to better reflect what the command is doing
---------
Co-authored-by: mfischer <michael.fischer@spleenlab.ai>
* Fixes bug in PairPixelSampler when working with masked dataset
* Formatting
* Black formatting now ok.
---------
Co-authored-by: AdamRashid96 <71362382+AdamRashid96@users.noreply.github.com>
Co-authored-by: Brent Yi <yibrenth@gmail.com>
The ParallelDataManager (see #2092) makes pytorch crash if the cameras instance's fx, fy, cx or cy tensors
are loaded from a common shared tensor.
This PR fixes the issue by cloning the respective tensors before passing them to the Cameras(...) constructor.
* render nearest camera to render view
* added lpips
* added the rotation distance and the depth check for the cameras
* render nearest training img
* formatting
* add flag for occlusions
* remove commented import
* remove comments
* fix pyright test
* remove None
* add assert
* fix pyright tests
* format
* made it a flag render-nearest-camera
* added default cams and dataset for tests
* maintain resolution of training images
* Make resetting the near_plane in NearFarCollider optional.
It is not always desired to reset the near plane to 0.0 during inference.
Added an optional flag.
* no need to change precision
* Update scene_colliders.py
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
* Viewer changes for render panel for fps and resolution
Small changes for the new viewer including changing the FPS slider to a text entry and fixing the incorrect resolution text box description.
* Check if render_time is nonzero in render state machine
Added a check if render_time is non zero in the render_state_machine file in the new viewer due to a divide by zero error occasionally causing the viewer to stop running. I noticed this usually happened when using nerfacto-huge.
* Move only per-chunk data to the GPU to support large images
* make type checking happy
* Use isinstance check
torch.is_tensor() doesn't have a TypeGuard annotation
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
* fix jittering in markdown in viewer beta
* Revert "fix jittering in markdown in viewer beta"
This reverts commit 70ade42e46.
* static rendering never triggered
