* add hashmap size and num_levels to instant_ngp_field, issue 1158
* Add Windows installation tips to quickstart
* Include notes for CUDA 11.7
* separate duplicate targets in installation.md
* change installation page to use tabs
* started adding equirectangular to process_data
* was multiplying frame by 255 twice
* added equi2planar configs for the 3 presets
* fixed presets
* setup process data
* changed variable name and comment
* fixed middle preset
* removed third preset
* added progress bar and fixed video for equirectangular input
* fixed whitespace stuff
* added pyequilib dependencey
* Updated for JPG support for equirectangular image input
Updated process_data_utils for JPG support for equirectangular image input, since even though .jpg images worked, .JPG images (output from 360 camera software) were not working.
* changed file type matching
* added equirect utils
* added license header
* added docstring on equirect utils
* added heuristic for image size
* added heuristic for videos
* fixed linty stuff
* shortened code
* raised error if no ims in directory
* Updated ProcessVideo for fixing directories for equirectangular input
Updated the ProcessVideo for equirectangular input to make the image directory have the correct perspective projections. The original equirectangular images are copied into a temp_images folder which also holds the perspective projections. This folder is deleted once the perspective projections are copied into the process data images folder.
---------
Co-authored-by: cvachha <cyrus.vachha@yahoo.com>
Co-authored-by: cvachha <cvachha549@gmail.com>
* Update Dockerfile, bump CUDA from 11.7.1 to 11.8.0, bump Colmap from 3.7 to 3.8, add user to sudoers list.
* Improve description.
* Fix wrong description and typos.
* Add better description.
* Fix build error of Dockerfile.
* Bump pytorch versions.
---------
Co-authored-by: Nicolas Zunhammer <n.zunhammer@tum.de>
* Allow black/white background color in Nerfacto
* Use white background in Nerfacto Blender Benchmark
* Fixed unused import
* Updated index for license headers script
* add monosdf normal loss and midas scale invariant depth loss
* add context to scale/shift calc and normal loss, consolidate MidasMSE loss
* consolidated, add info on gradient reg term
* add info on ssi
* more documentation and type annotation
* move compute scale/shift to class
* fix pylint errors
* fix tensortype error
* fix comments
* change single var name and update comment
* fix input tensortype
* fix black error
* fix mask shape
* Update pytorch (and functorch) to 1.13.1
Note that for existing installations, the following is recommended due to complications with older versions of functorch:
- `pip uninstall torch torchvision functorch`
- install the correct pytorch 1.13.1 version for your CUDA installation from https://pytorch.org/get-started/locally/ but add functorch to the command -- for example, Windows CUDA 11.7 would be `pip3 install torch torchvision functorch--extra-index-url https://download.pytorch.org/whl/cu117`
- reinstall nerfstudio e.g. `pip install -e .` from the source directory
* Update installation.md
* Allow 1.13.1, don't force
* pytorch 1.12.1 and 1.13.1
* Update README.md
* Update installation.md
* Allow skipping copy+downscale of images in ns-process-data, fix bug when using --skip-colmap on images.bin with non-standard image names
* Rename flags and improve error messages
---------
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
This fix allows loading Metashape XML files which
contain an additional uncalibrated sensor.
Metashape XML format keeps unmatched images but
assignes a dummy sensor to them. The sensor has
no calibration data.
Co-authored-by: gilureta <gilureta@amazon.com>
Matthew Tancik
Nicolas ZunhammerandNicolas Zunhammer
Ethan Weber
Dreek Fire
Sacha Lewin
Alexander Kristoffersen
Pablo Vela
Jonáš Kulhánek
NCJ
machenmusik
Mark Colley
LSongandLcDog
NCJ
Yiming Zhou
Francisca T. Gil Uretaandgilureta
ManuConcepBrito