Fix remote viewing setup doc
SSH command should specific localport:remotehost:remoteport rather than localport:localhost:remoteport in -L switch. Changed description for clarity.
* starting the framework for dreamfusion
* Removed view direction from RGB to calculate albedo
* Started diffusion
* Added dreamfusion to CLI, removed direction embeddings
* Normals in dreamfusion
* Lambertian shading added
* Train normals in Dreamfusion
* Stable diffusion from Stable Dreamfusion
* Fix normal orientation loss
* Configurable light direction sampling
* adding density initalization at origin
* V1 datamanager
* Don't train normals for first 1k iters
* SDS loss added to dreamfusion
* Dreamfusion pipeline
* Background MLP and SphereCollider
* Normals prediction training fixed
* Sigmoid on background, prompt in config
* Shading hyperparameter adjustements
* Shading hyperparameter tuning
* Location based prompting, density initialization fades, LR change
* Cleaned imports, more config options
* Tuning, more config changes
* remove unused sampler, normalize predicted normals from network
* change position encoding to direction encoding for background color mlp
* Updating dreamfusion to use custom trainer, fixed bug, multi-gpu support (put diffusion on one specific device), merged with main
* Hard coding less, offloading to config
* Appeasing the linter
* First pass opacity / sparsity losses
* Small patches and configs
* Accidentally pushed logs
* Removing logs for real this time
* Transmittance loss bug fix
* 12 GB Dreamfusion!
* Lint
* Remove unecissary collider changes
* Start SD cleanup
* Cleanup SD code
* adding overhead location prompting
* Use lambertian renderer
* turn grad accum off by default, decrease background mlp size, add overhead text embedding
* Cleanup
* Fix normals vis
* change uniform sampler to prediction network, add option to jit unet for faster sds_loss
* Use shaders
* cleaning up jit code
* add warning if using non jit unet
* add proposal network optimizer to config
* speed up render and cleanup code
* Clean up datamanager
* Add distortion loss
* fix wanb
* adding interpolated location sampling
* Update configs
* interpolated location prompting option, lowering init density, transmittance loss interpolation flipped
* rename alphas mult to alphas loss mult
* Mess around with normals
* add option to use random bg color + bg mlp
* Remove Dreamfusion Trainer (#1423)
* Dreamfusion trainer no longer needed
* Added typing for grad scaler
* SDS return loss
* Fix CFG
* Cleanup
* Update configs
* Fix opacity loss, use unform sampling first round of prop
* add prompt edditing to viewer
* Choose your own diffusion
* remove dreamfusion pipeline file
* merging + remove dreamfusion pipeline file
* Update configs
* add stable diff utils
* cleanup
* cleanup
* Fix test
* positional prompting bugfix
* Warmups
* tune
* lint
* Remove dataparser
* merging + text embedding bugfix
* Set data path to launch viewer for DreamFusion (#1776)
* Set data path to launch viewer for DreamFusion
* Apply formatter
* Fallback to 'base_dir' if data manager has no path
* Make if statement non-inline
* Reformat
---------
Co-authored-by: Matthew Tancik <mattt4001@gmail.com>
* add deepfloyd option first try
* merging
* merging from main
* merging
* removing comments, cleaning code, making stable diff utils usable for deepfloyd, remove deepfloyd text encoder after use
* undo chagnes in data folder
* cleaning code, removing unneccesary changes from main, removed normals prediction network
* remove old scripts files, rename generative pipeline flag to no_input_data, revert to default histogram padding in proposal sampler
* changing pipeline flag
* move no input data flag from pipeline to datamanager
* undo config and merge in deepfloyd from main
* merging grad scaler pipeline addition
* merging + setting proposal net scheduler
* revert nerfacto config change
* typing + linting
* rename dreamfusion datamanager to random camras datamanager, check datamanager typing in pipeline and trainer
* fix test import
* fix test import
* changing datamanager check in trainer, add typing in random cameras datamanager
* add Tensor to randomcamerasdatamanager
* remove old comments
* resolve tyro warning
* update fields to use tcnn
* lint
* add packages for deepfloyd
* add versions
* docs first draft
* rename to generfacto, clean docs
* fix import error
* minor changes
* fix orientation loss bug, retune params
* cleanup
* typing
* trying docs fix
* fixing generative package imports
* fix pyright
* docs fix
* merge w main
* docs minor change
* tuning + bugfixes
* remove torch.backends
---------
Co-authored-by: Abhik Ahuja <ahujaabhik@berkeley.edu>
Co-authored-by: David McAllister <davidrmc2@gmail.com>
Co-authored-by: Jake Austin <jake-austin@berkeley.edu>
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
Co-authored-by: Matt Tancik <mattt4001@gmail.com>
Co-authored-by: SeungWoo Yoo <dreamy1534@gmail.com>
Co-authored-by: ayaanzhaque <ayaanzhaque@gmail.com>
Co-authored-by: Ayaan Haque <ayaanzhaque@berkeley.edu>
An even larger version of nerfacto with scaled hashgrid resolution, MLP sizes, batch sizes, appearance embeddings, proposal sampler resolution, and more.
Also includes some minor tweaks to nerfacto-big configs
* 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>
