* Fix arguments that are not passed from config to NerfactoField
* Add comments
* Reset base_res and features_per_level config of nerfacto-big and nerfacto-huge to default to match the original behavior
---------
Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
* Merge video image extraction and downscaling
* Linting
* Fix extracting all frames, only apply vfr when thumnailing
* integrate downscale chains into image processing
* fast polycam upscale/downscale depth
* black
* black
* Update process_data_utils.py
Remove code change from other branch.
* use same suffix for downscale, don't force png
* black
---------
Co-authored-by: Sebastiaan Meijer <seb@stiaan.io>
* Try non-strict model loading on RuntimeError. ...
This allows tcnn models that contained a torch hash_table to load.
In particular, it allows us to load tcnn models prior to PR #2175.
cf. https://github.com/nerfstudio-project/nerfstudio/pull/2175
* Only allow non-strict loading when called with defaults.
* Reflow to avoid code duplication; blacken.
---------
Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
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.
* add `build-arg` cuda version to dockerfile
* [Feature] add 'vis' option to 'ns-viewer' script
* fix pylint
* [Fix] fix data format
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
* fixes div by 1 error
* removes pytorch hash_table if tcnn is used
* formatting
* test fixes
---------
Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
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.
* allow ns-process-data to use CR2 raw images
* Update process_data_utils.py
* black wants an extra newline
---------
Co-authored-by: Matias Turkulainen <30566358+maturk@users.noreply.github.com>
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>
