* colormaps: remove useless "pca" choice, add "gray"
- The "pca" choice didn't work when applied to a single-channel image (it crashed the viewer), and it's applied by default to any image of more than 3 channels, where the colormap choice is ignore anyway.
- Add the trivial "gray" colormap, useful to eg extract accumulation.
* colormaps.py: re-add "pca"
* control_panel: don't show the "pca" option either
---------
Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
Also remove the image skipping logic, which seems to be a remnant of some old code (all images should exist)
Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
dirty fix for the eval_utils script that fails because generics don't work with yaml configs
Co-authored-by: Jakub Mysliwiec <jmysliwiec@cyclomedia.com>
* Update point cloud exporter to accept the same arguments as the poisson mesh export wrt normals + hoist validate pipeline up so both exporters can use it
* Update viewer to support both normal methods for point cloud and poisson export
* Lint fixes
* Undo eslint comments
* Add types and documentation for args in validate pipeline function
---------
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
* 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>
Changed the ValueError message when using a camera.xml that contains multiple sensors. Per-frame intrinsics can be defined, the previous message said that they were not supported.
* Fix model loading collate_fn non-static
* Fix serialization
* Add tests to reproduce the error
* Comment the change to let the tests fail
* Finish changes
* 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.
* started a package to easily swap out tcnn for pytorch
* trains with pytorch and not tcnn
* cleaned up imports
* making it easy to install on mac
* removed/reverted files
* merged main
* reverted changes
* updating config
* starting to add nerfacto to tests
* fixxing default value
* fixed default implementation
* defaults to torch if tcnn and not installed
* update log
* add comment
* resolved pr comments
* fix
* update default
---------
Co-authored-by: Ethan Weber <ethanweber@eecs-128-32-175-250.dhcp.berkeley.edu>
* add deepfloyd model
* black
* lint
* linting
* cast sds gradient to tensor
* change generator type to optional
* lint
* Type fixes
* add typing to sds
---------
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
Co-authored-by: Matt Tancik <mattt4001@gmail.com>
* process additional images
* added on_train_end to base pipeline
* added on_train_end to base pipeline
* remove on_train_end from Base Model and Base Datamanager
* Add new callback type OnTrainEndCallback
* return empty list as default
* add on_train_end to trainingcallbacklocation enum
* make step var into union of int and None
* after train end callback
* Delete unnecessary file
* Delete unnecessary file
* Delete unnecessary file
---------
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
* Increase max_res of first proposal network
* start on ViewerCamera
* crop controls exposed
* lint
* fix viewer crash when invisible element has its value set
* fov, look_at, and camera type
* stuff
* set update interval correctly in cameracontrols, smooth transitions work now
* demo with depth zooming
* depth min
* WIP adding click message
* put the clock back in viewerwindow
* use setlookat when pos and target are defined at the same time
* remove demo from nerfacto
* Add click commands as rays (origin, direction)
* short doc
* Fix double event for doubleclick
* add ViewerClick, cleanup docs
* add docs
* cleanup
* remove scripts
* remove nerfacto changes
* js compile things
* update viewer version
* fix mutable state thing
* docs improvements
* add kwarg value for enableTransition
* fix
* lint
* path in sync-defs
* Misc doc edits requested in pr
* Add click description
* WIP remove redefinition of banner_height, refer to SCSS vars
* add docstring
* radix
* radix
* speed
---------
Co-authored-by: Chung Min Kim <chungmin99@gmail.com>
* knocking out a couple
* Fix more errors
* Add pyright
* Remove some unnecessary cv2 type ignores, warning on missing imports
(for missing tinycudann)
* Minor annotation fixes
* Update docs
* Drop `None` from temporal distortion output
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
