* render nearest camera to render view
* added lpips
* added the rotation distance and the depth check for the cameras
* render nearest training img
* formatting
* add flag for occlusions
* remove commented import
* remove comments
* fix pyright test
* remove None
* add assert
* fix pyright tests
* format
* made it a flag render-nearest-camera
* added default cams and dataset for tests
* maintain resolution of training images
* Make resetting the near_plane in NearFarCollider optional.
It is not always desired to reset the near plane to 0.0 during inference.
Added an optional flag.
* no need to change precision
* Update scene_colliders.py
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
* Viewer changes for render panel for fps and resolution
Small changes for the new viewer including changing the FPS slider to a text entry and fixing the incorrect resolution text box description.
* Check if render_time is nonzero in render state machine
Added a check if render_time is non zero in the render_state_machine file in the new viewer due to a divide by zero error occasionally causing the viewer to stop running. I noticed this usually happened when using nerfacto-huge.
* Move only per-chunk data to the GPU to support large images
* make type checking happy
* Use isinstance check
torch.is_tensor() doesn't have a TypeGuard annotation
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
* fix jittering in markdown in viewer beta
* Revert "fix jittering in markdown in viewer beta"
This reverts commit 70ade42e46.
* static rendering never triggered
* Initial multiclient, jittery screen bc fighting between clients
* Fix multiclient jitter with separate render threads for each client
* Handle client disconnect
* Fix viewer.init_scene and viewer_elements.get_camera for multiclient
---------
Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
Co-authored-by: Brent Yi <yibrenth@gmail.com>
* Add camera_type dropdown in new viewer
Added a gui dropdown menu for selecting the camera type. Currently, the render view doesn't update to preview the equirectangular or fisheye render.
* Updating the image url of nerfstudio logo images for the viewer
Changing the image urls to restore the nerfstudio logo in the viewer
---------
Co-authored-by: Brent Yi <yibrenth@gmail.com>
* Update URLs for readme and image references
Update the image URLs and documentation links due to change in docs url structure. Files edited include readme, documentation, and legacy viewer files.
* Updating url in custom dataset
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>
* (minor) Align upsampling in TensorCPEncoding with TensorVMEncoding
* Fix black
---------
Co-authored-by: Matthew Tancik <mattt4001@gmail.com>
Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
* Fourier Feature encodings and polyhedron encodings
Rework RFFEncoding to be a subclass of the more general Fourier Feature
Encodings and introduce Polyhedron encodings as introduced in
mipnerf360.
* b_matrix -> basis
* Add typing
* fighting pyright
* use scale argument
* continue the fight
* ignore
* ignore em all
* add docstring and rename generate_basis to generate_polyhedron_basis
* Try to please pyright with assert
* Immediately allocate tensor on correct device
* private functions and docstrings update
* doc fix continued
---------
Co-authored-by: Jonáš Kulhánek <jonas.kulhanek@live.com>
