Updated the documentation to explicate that zero value in depth images is treated as unknown depth. This behavior is defined in a484d255b4/nerfstudio/model_components/losses.py (L242)
Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
To prevent abusing of root privilege, please use custom user privilege to start.
If not, sometimes the Docker images may be started with the permissions of root or other users. If you modify the mounted files in the container , it will cause permission errors or other errors.
Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
* nerfbusters dataparser
* nerfbuster dataparser and visualization of eval views
* resolved some errors from pyright
* enable ns-process-data to take two videos as input and use one for eval and the other for train
* resolve some pyright issues
* instead of data being a tuple, I added eval_data as another argument
* implemented train eval split for all cases
* implemented train eval split for all cases
* reverting equi changes
* reverting reality capture changes
* raise valueerror
* revert comment
* added split override code back to dataparser
* reverted one change
* using image border now
* adding docs
---------
Co-authored-by: Ethan Weber <eweb0124@gmail.com>
* Remove system-level CUDA install from Linux install instructions
* Remove system-level CUDA from Windows install instructions
* Un-flip CUDA 11.7 / 11.8
* Render VR180 video
Adding the VR180 camera model to render VR180 video and images. I condensed the omnidirectional stereo and VR180 render post processing in the render script. I have updated the documentation for VR180 support.
* Condensing formatting of camera types
Condensing the if statement for camera type intrinsics.
Update to omnidirectional stereo rendering (VR 360) to fix slight positional alignment to accurately composite with Blender objects. Modified documentation for ODS and the Blender add-on to include details on Blender camera settings to composite with the Nerfstudio ODS camera model.
Fixed an error in the documentation where the incorrect path notation was used for Windows systems. The documentation had paths denoted with "./", which is incorrect for Windows. This has been corrected to ".\", the appropriate notation for Windows.
This change ensures that Windows users correctly follow the instructions in the documentation without encountering any path-related issues.
Fix remote viewing setup doc
SSH command should specific localport:remotehost:remoteport rather than localport:localhost:remoteport in -L switch. Changed description for clarity.
* installation.md: Use https instead of ssh for git clone.
Https git clone can be run by anyone directly, without account, whereas ssh git on Github requires having a Github account set up.
* Add .git
---------
Co-authored-by: Matthew Tancik <mattt4001@gmail.com>
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
* Render Omni-directional stereo (360 3D VR)
Adding the omni-directional stereo camera model to render 3D 360 video and images for VR. This includes the camera models for the left and right eyes and additions to the render script to stack the left and right renders for the final render.
I have also updated the documentation on the custom_dataset page to have information on ODS but let me know if there is a better place to put it.
* Updated ODS camera model and render paths
Updates based on suggested code changes including adding a helper function for ODS and improving path creation.
I also added a part where if a user tries to render a video with an output path that doesn't have an extension it will automatically add .mp4 to the end. Otherwise this usually results in an error when there is no file extension when rendering a video.
* Updated formatting for render and cam path scripts
Updated python formatting for render and camera_paths script
* Adding type checking for ODS function and reformatting camera type code
Added the type checking and doc string for the ODS camera rays function and reformatted the cam_type ray if statements.
* Fix bug related to distributed data parallel training
* fix format by black
* Add nerfacto-big multi-gpu commands
* cleaned up docs
* reverted default dataset to poster
---------
Co-authored-by: Ethan Weber <eweb0124@gmail.com>
* Bump minimum Python version to 3.8
* typing_extensions.Literal -> typing.Literal
* ns-dev-test
* typing_extensions.get_args => typing.get_args
* Format with older version of black
* Bump `black`
* Run black
* Document how to use equirectangular sensor with metashape
* equirectangular sensor is actually supported by nerfstudio!
* Update custom_dataset.md
* equirectangular: fix COLMAP workflow
* metashape_utils.py: black
---------
Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
* removed insta360 and also updated equirect images docs to include cropping
* removed unused import
---------
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
* changed percent-crop arg to crop-factor so it's more clear that it's a float
* added error if crop values are less than 0 or more than 1
* added value hint and changed error to console thing
* added imports
* fixed linter issues
* refixed linter issues
* add hashmap size and num_levels to instant_ngp_field, issue 1158
* Add Windows installation tips to quickstart
* Include notes for CUDA 11.7
* separate duplicate targets in installation.md
* change installation page to use tabs
* Update Dockerfile, bump CUDA from 11.7.1 to 11.8.0, bump Colmap from 3.7 to 3.8, add user to sudoers list.
* Improve description.
* Fix wrong description and typos.
* Add better description.
* Fix build error of Dockerfile.
* Bump pytorch versions.
---------
Co-authored-by: Nicolas Zunhammer <n.zunhammer@tum.de>
* Update pytorch (and functorch) to 1.13.1
Note that for existing installations, the following is recommended due to complications with older versions of functorch:
- `pip uninstall torch torchvision functorch`
- install the correct pytorch 1.13.1 version for your CUDA installation from https://pytorch.org/get-started/locally/ but add functorch to the command -- for example, Windows CUDA 11.7 would be `pip3 install torch torchvision functorch--extra-index-url https://download.pytorch.org/whl/cu117`
- reinstall nerfstudio e.g. `pip install -e .` from the source directory
* Update installation.md
* Allow 1.13.1, don't force
* pytorch 1.12.1 and 1.13.1
* Update README.md
* Update installation.md
Fix docker not supporting older CUDA architectures.
Co-authored-by: Nicolas Zunhammer <n.zunhammer@tum.de>
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
* Blender addon script and documentation
First version of blender addon python script located in scripts/blender and new documentation for the addon. The Blender addon is for importing or exporting a camera path for visual effects and compositing.
* Updated formatting of Blender script
Updated the formatting based on the script tests for the blender addon script.
* Updated Blender addon to fix FOV and alignment
Updated how FOV is calculated for both blender cam to json and json to blender cam. The FOV is calculated based on the aspect ratio, angle of view, and sensor fit and size.
* Updated Blender addon documentation with examples
Updated the Blender add-on documentation with a few example gif composite animations
* Updated Blender addon to match frame rate and fixed formatting
Updated the Blender add-on script and docs to match the Blender frame rate. Also the formatting should be fixed. There are also now error message popups instead of console prints for invalid input in the add-on.
* Updated the blender addon for formatting
Updated pylint formatting and comments
* Add the following fixes to documentation:
* Fix trailing backslash in “Use docker image” section
* Replace escaped backslash with double-escaped backslash (see Sphinx issue: https://github.com/sphinx-doc/sphinx/issues/6730)
* Close backtick in `contributing.md`
* Add “run” to instructions for “Render Video”
* Remove unnecessary “,” in “Render Video”
* Correct “before preceding” to “before proceeding”
* Correct “viewpoinrts” to “viewpoints”
* Add missing “.” in “Process data”
* Specify “bash” for code blocks (for consistency with other blocks in the page)
* Fix code block in `viewer_quickstart.rst` (”Copy to clipboard” widget now works)
* Fix some code formatting issues in `export_geometry.md`
* Correct "harmoincs" to "harmonics" in docs.
