* 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.
* `isort` -> `ruff`
* `pylint` -> `ruff`
* Remove line
* More minor cleanup
* Better documentation for rules we are enabling
* Fix gitignore, run black
* vscode settings
---------
Co-authored-by: Matt Tancik <mattt4001@gmail.com>
* [WIP] Speed is adjusted depending on camera distance
* [WIP] Speed is adjusted depending on camera distance
* Speed is adjusted depending on camera distance
* Constant time between poses and ordered poses
* Removed old speed adjust
* remove prints
* renamed variables
* added launch.json back
* added back blank lines
* Trying to solve blank line git issue in launch.json
* Added docstring and type annotations
---------
Co-authored-by: jperezh <jperezh@arquimea.com>
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
* 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
* profiling
* set pose_optimizer to None if it's mode is "off"
* radial_and_tangential_undistort in nerfacc
* fix camera distortions
* update to nerfacc 0.5.1. Upgrade instant-ngp model.
* revert nerfacc to 0.5.1
* format
* allows to fall back to the pytorch undistortion
* format
* fix linting
* fix test
* fix test
* fix nerfplayer-ngp
* enable_collider=False for NGP
* nerfplayer verified.
* zero cone_angle for ngp bounded
* fix format
* fix pylint
* add initial method configs and data manager
* add neus scheduler
* add initial surface model and neus
* add Neus ray sampler
* add sdf field
* move scale/shift calc to math utils
* add debug and fix sdf_dataset typo
* update vscode neus debug
* fix dataset and get initial working version
* add magic number from original repo
* black fixes
* clean up get weights/transmittance from alphas
* clean up typos in sdf datamanager
* type annotations on neus scheduler and remove unused params
* clean up and annotate sdf field along w/ other fixes
* more clean up
* remove unnessary directions norm
* resolve comments
* update neus scheduler to follow refactor
* fix linter errors
* fix some typos
* remove get_weights_from_alpha
* more comment fixes
* more linter error fixes
* clean up and add comments
* more little fixes for types/comments
* more comments
* rename NeuS Scheduler to DelayedScheduler
* rename DelayedScheduler to CosineDecayScheduler
* MinimalDataParser add options, allow Nerfstudio data format to specify test indices
* Switch from indices to filenames and add tests
* Fix #1581
* Fix changed interface
* feat(plugins/registry): Improve Type Hints
* feat(exporter/texture_utils): Improve Type Hints
* feat(exporter/tsdf_utils): Improve Type Hints
* feat(cameras/camera_utils): Improve Type Hints
* feat(cameras/cameras): Improve Type Hints
* feat(cameras/rays): Improve Type Hints
* fix: add default value for device
* fix: ArrayLike type hint
* Extending ns-render to support loop rendering using interpolated cameras.
* Adding docstring for render.py. Applying formating.
* Expanding docstrings for class. Renaming trajectory type.
* Removing mentions of loop from render.py.
* fixed an exception bug in case of num_samples is 0
fixed an exception bug when num samples is 0 ,
"IndexError tensors used as indices must be long, byte or bool tensors"
change type to long ( was float32)
* implemented crop box in gui. For now works on instant-ngp-bounded
* fixed import bugs
* update aabb every time and not only on training
* prevent crash when chosing accomulation and crop box
* Checkbox
* max_box is bounded by scevne box in the gui
* implemented altenative intesection to nerfacc
* convert str to bool correctly
* fixed isort bug
* fixed isort bug2
* update viewer version
* remove json bug
* Update UI
* Force black background
* Fix formatting
Co-authored-by: dror <you@example.com>
Co-authored-by: Matt Tancik <tancik@berkeley.edu>
Co-authored-by: Matthew Tancik <mattt4001@gmail.com>
* Render cameras with render times for dynamic nerfs
* Add --dynamic flag to cmd. Clamp render times.
* Fix for issues with clamping renderTime
* Only add render_time to camera path if dynamic nerf
* change DEFAULT_TIME to DEFAULT_RENDER_TIME
Co-authored-by: Liam Schoneveld <liam.schoneveld@woven-planet.global>
Making TrainerConfig an InstantiateConfig so it can be swapped in and out with different methods. Also made the TrainerConfig a subclass of ExperimentConfig (which was changed from a printableconfig to an instantiateconfig), since we were already instantiating the Trainer class with the ExperimentConfig
Removed the "config" field from the TrainerCallbackAttributes struct to eliminate circular dependencies when types are checked.
Minor scripts and docs changes to accommodate the update to the config struct, meaning the flags that were associated with the TrainerConfig were moved up to the top level of the config.
When using auto_orient_and_center_poses with method="none" the returned pose if 4x4 (contrary to up and pca) which triggers an assertion error later. This modification solves it.
* start of mesh PR
* point cloud export mvp
* start of mesh PR
* point cloud export mvp
* Save out mesh. Poor quality atm
* reorganized mesh algorithms and specified CLI
* CLI reorg
* tsdf algorithm in progress
* debugging
* tsdf functional but camera distortion params not in
* playing with distortion params
* TSDF works but texture looks bad
* added trimesh
* moved to exporter
* removed files
* saving progress
* save texture image
* seems to work w/o barycentric
* barycentric start
* gap between triangles
* blocking out diagonal
* new barcentric and scaling
* meshing working. need to remove extra rows
* fixed triangle packing
* gitignore changes
* removed package
* fix Literal import
* comments
* update .mtl file
* poisson mesh with model output normals & resolved some PR comments on git
* starting docs. breaking up big function. todo: add xatlas
* xatlas and nvdiffrast working
* triangle_id
* progress on expensive texture coordinates method
* pytorch meshing works
* removing nvdiffrast
* remove trimesh
* cleanup
* few changes
* pred normals by default and add minimum additions to viewer
* fix cli in viewer
* add xatlas as dependency
* make point cloud more dense
* reverted viewer changes
* turn off normals by default
* fix docs
* finished todos on github
* remove xatlas
* xatlas
* black
Co-authored-by: Matt Tancik <tancik@berkeley.edu>
This branch gives us the flexibility to use Cameras as a tensordataclass, giving arbitrary batch dimensions, slicing, etc all for free. It tests this with the phototourism dataset.
Tensordataclass changes:
Originally, the tensordataclass would look at tensors in an object and take everything in front of the last dimension to be the batch dimensions, but in the case of the camera_to_world matrices, everything except for the last TWO are the important dimensions, so we needed to have a way for the tensordataclass to acknowledge these specific fields where there are multiple data dimensions behind the batch dimensions. This is important for things like reshaping where we need to know which dimensions get reshaped and which dimensions get left alone.
Cameras changes:
Now subclass of tensordataclass, which required a change to the tensordataclass itself.
The possibility of extra batch dimensions is the hairy part that requires the majority of these changes. The extra batch dimensions aren't a hassle in every function except in ray generation. The ray generation is where this operates different relative to the old cameras. The reason for this is before, for each ray we wanted to generate, we could specify a single index into our batch of cameras, but if you have multiple camera dimensions, for each ray, you need to now specify one index per camera batch dimension, meaning our camera_indices we specify need to have one extra dimension at the end, a dimension of size Cameras.ndim (number of batch dimensions in the camera object).
I also added some neat logic in generate_rays where if you want your output raybundle to be batched, if you specify batched camera_indices, you will receive the same batch size for the output raybundle, meaning you can easily generate raybundles corresponding to things like image patches and whatnot.
Phototourism changes:
The difficulty here is that images in the phototourism dataset are of different sizes, which is difficult because we can no longer batch the image tensors. We also need to better utilize caching in the CacheDataloader since the vanilladatamanager defaults don't really use it as well as they could, and without properly utilizing it, the rays / sec are maybe 25% of the standard nerfstudio dataset speeds (which are 10% of the size of the phototourism datasets). To do this, we specify a collate function in the existing datamanager configs, and we make a subclass of the vanilladatamanagerconfig named VariableResDataManagerConfig which will have a custom collate function storing the images in a list, and using better defaults for caching in the dataloader, caching ~40 images at a time. The slowest part of using a list is pixel sampling, where we added a custom if case for if our pixel sampler receives a batch of images that are in a list, and the lack of ability to vectorize operations over a list means that caching in the dataloader is even more important.
* Add D-NeRF temporal distortion and D-NeRF model
This allows for temporal distortion to be enabled on a variety of models through config
parameters, without an explicit model. Temporal distortion and MIP-NeRF are not currently
jointly runnable but can be changed in the future.
* Simplifying changes
* Simplifying changes
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
* Add dnerf dataparser
* Switch time to be stored per camera
I realized it would be better downstream to store times on the ray bundle, and in order to store
them on the ray bundle it's much easier to store them on the camera. Rather than having to
revert this change, I just made it here.