tink/nerfstudio
4
0 Fork 0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-13 19:33:46 +08:00
Code Activity
1,504 Commits 85 Branches 40 Tags
415a037880618035f91e197389aa4e817afafdfb
Commit Graph
1504 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Matthew Tancik 415a037880 Update method docs (#1925) 
* Update method docs

* Cleanup
 2023-05-15 13:47:40 -07:00
Matthew Tancik 531f9d0c4c Split up render commands (#1923) 
* Split up render commands

* bump viewer
 2023-05-15 11:34:40 -07:00
ksnzh 445e17a3c6 fix pytorch 2.0 optimizer no inf check error (#1919) 
* fix pytorch 2.0 optimizer no inf check error

* Update optimizers.py
 2023-05-15 16:49:55 +02:00
Ethan Weber 13e0fce122 Update copyright (#1917) 
* updated copyright

* including txt file

* updated black

* removing license

* fixing license
 2023-05-12 16:16:13 -07:00
Fernando Rivas-ManzanequejperezhMatthew Tancik
 		bc2651963c Improved interpolate render (#1911) 
* [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>
 2023-05-12 15:19:13 -07:00
wuziruiandMatthew Tancik bc110d7bd9 extract dataparser configs to a stand-alone file, support custom dataparsers (#1909) 
* extract dataparser configs to a stand-alone file, support custom dataparsers

* add license

* fix pylint issues

* fix type error issue

* update naming; add documentations;

* print f string

* fix pylint issue

---------

Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
 2023-05-12 15:11:46 -07:00
Ayaan HaqueandRuilong Li fe4586839a Add INGP Docs (#1774) 
* initial draft

* updates

* added details on sampling

* updates

* final notes

---------

Co-authored-by: Ruilong Li(李瑞龙) <ruilongli94@gmail.com>
 2023-05-12 14:51:00 -07:00
Matthew Tancik 4242a3c982 Make rich console global (#1916) 2023-05-12 14:20:40 -07:00
Jonáš Kulhánek 02f449b661 Implement gradient scaling (#1901) 
* Implement gradient scaling

* Make grad scaling more general

* Fix pylint errors

* Fix lint error + change gradient scaling

* Fix issues with grad scaling

* Fix linting errors
 2023-05-12 07:23:41 +02:00
Matthew Tancik 93d0a854be Fix split options (#1904) 2023-05-11 17:12:32 -07:00
Milan van Wouden 278f193721 #1732 fix sdf dataparser no mono paths (#1910) 
* fix sdfstudio data parse without mono depth/normal paths

* fix sdfstudio data parse without mono depth/normal paths
 2023-05-11 16:52:28 -07:00
Aman Salykov 79b06ee2bf fix metashape_to_json() if there is no 'components' tag in .xml (#1906) 
fix metashape_to_json() if no 'components' in .xml
 2023-05-10 14:50:48 -07:00
Matthew Tancik b1ddb9e695 Add split screen (#1898) 
* Add split screen

* bug fixes
 2023-05-10 10:55:17 -07:00
Yuantao Chen e9bba85b08 FIx random indices bug (#1900) 
* Fix mask bug

* Fix Fix_indices bug
 2023-05-10 01:38:34 -07:00
Matthew Tancik 72a14b0b22 Move scripts folder into nerfstudio (#1897) 
move scripts folder into nerfstudio
 2023-05-09 16:44:21 -07:00
Matthew Tancik 82c0c5545b Fix misc warnings (#1894) 2023-05-09 14:11:28 -07:00
Matthew Tancik 28532c583f Render with colormaps (#1893) 
* render with colormaps

* black
 2023-05-09 12:26:44 -07:00
Jonáš Kulhánek 935e308c93 Fix viewer when opened before train setup finishes (#1888) 
* Fix viewer when opened before train setup finishes

* is_initialized fix docs
 2023-05-09 19:52:05 +02:00
Matthew Tancik df514b121c Update docs for ns-viewer (#1892) 2023-05-09 10:07:11 -07:00
Yan XiaoandYan Xiao 38cbb0f358 implementing l1 and tv reg in the original tensorf paper (#1855) 
* implementing l1 and tv reg in the original tensorf paper

* added documentation for tv loss

* added test for tv loss

* fix formating

* fix formatting

---------

Co-authored-by: Yan Xiao <yax010@ucsd.edu>
 2023-05-09 09:32:51 -07:00
Yuantao Chen f92275603a Fix mask bug (#1891) 2023-05-09 09:32:05 -07:00
sasaki takeru 91aec92653 CropParamsMessage (#1886) 2023-05-09 09:28:21 -07:00
Matthew TancikandJonas Kulhanek 069fa0f498 Skip scheduler step is opt is not performed (#1854) 
Skip scheduler step is opt is not perfomed

Co-authored-by: Jonas Kulhanek <jonas.kulhanek@live.com>
 2023-05-09 07:30:53 -07:00
Matthew Tancik f299098f46 Fix viewer quit-on-train-completion (#1885) 2023-05-08 11:48:28 -07:00
Brent Yi 63c6303736 Bump minimum Python version to 3.8 (#1876) 
* 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
 2023-05-06 13:29:48 -07:00
Ethan Weber 7537551f38 Avoids running test_train.py on external methods (#1882) 
removes testing on external methods
 2023-05-06 12:19:26 -07:00
Ethan Weber d847949fe9 fixing wandb envs (#1880) 
* adding back support for wandb envs

* remove .init
 2023-05-06 10:15:48 -07:00
Jonáš Kulhánek 1147fe4d5c Make VanillaDataManager generic (#1868) 
* Make VanillaDataManager generic

* Remove removed classes from docs

* Simplify generic datamanager

* Simplify code

* Add serialization tests
 2023-05-06 09:54:52 -07:00
Ethan Weber 081bf82bf5 Wandb/experiment improvements (#1879) 
exposing experiment settings
 2023-05-05 18:28:52 -07:00
Matthew Tancik ad706f59c4 v0.2.2 (#1875) v0.2.2 2023-05-04 14:43:45 -07:00
Jonáš Kulhánek 971c9eb307 Enable method config registration from env variable (#1869) 2023-05-04 20:53:52 +02:00
Matthew Tancik 9ace02b3ae Remove nerfacc aabb (#1874) 
* Remove nerfacc aabb

* remove custom nerfacc logic

* lint
 2023-05-04 10:46:51 -07:00
Milan van Wouden 8030367e6b Fix images to nerfstudio filename (#1853) 
fix images to nerfstudio filename
 2023-05-04 10:06:52 -07:00
Matthew Tancik 28e6f9c8fc Quit when not using viewer (#1873) 2023-05-04 10:06:25 -07:00
Daniel Crispell cf74119adc SceneContraction maps to range [-2, 2], not [-1, 1]. (#1872) 2023-05-04 10:04:30 -07:00
Sophus 68f2edcb05 Fix torchfield #1749 #1539 (#1859) 
* fix bugs in TorchNerfactoField

* remove unused package
 2023-05-04 09:25:30 -07:00
Jonáš Kulhánek 61bad4dab3 Fix flag name in tetra-nerf (#1870) 
Fix flag name for tetra-nerf
 2023-05-04 09:22:32 -07:00
Jonáš Kulhánek 686e995dd6 Tetra-NeRF docs - fix versions and table formatting. (#1864) 
* Add Tetra-NeRF to the docs

* Fix versions in tetranerf docs
 2023-05-03 14:50:30 -07:00
Jonáš Kulhánek f4064aa593 Add Tetra-NeRF to the docs (#1862) 
* Add Tetra-NeRF to the docs

* Add memory requirements + different model configurations
 2023-05-03 22:18:07 +02:00
Matthew Tancik 610fe8bbd4 Update logging docs (#1863) 2023-05-03 10:00:46 -07:00
Matias Turkulainen ea35897668 Remove unecessary assert in pixel sampler on image dimensions (#1861) 
remove uneccessary assert on image dimension
 2023-05-03 09:28:11 -07:00
Milan van Wouden cc80a331aa Fix typos in SDF Field (#1860) 2023-05-03 08:00:51 -07:00
Milan van Wouden 28c84d116b Fix typos in Ray Samplers docs (#1851) 2023-05-02 09:29:47 -07:00
Frédéric DevernayandFrédéric Devernay 9a0ecb6fd7 Support equirectangular sensor with metashape (#1841) 
* Document how to use equirectangular sensor with metashape

* equirectangular sensor is actually supported by nerfstudio!

* Update custom_dataset.md

* equirectangular: fix COLMAP workflow

* metashape_utils.py: black

---------

Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
 2023-05-01 14:44:00 -07:00
Matthew Tancik a2beb63a0d Fix viewer meshing options (#1846) 2023-05-01 10:04:58 -07:00
sasaki takeru 2da4eee9fb fix crop_center (#1844) 
crop_center
 2023-05-01 09:59:27 -07:00
Ruilong Li(李瑞龙) 7887b14ca0 Reduce the GPU memory required in viewer for NGP methods (#1837) 
Fix the issue #1835:

- change the default `viewer.num_rays_per_chunk` from `1 << 15` to `1 << 12`.
- remove the `render_step_size=0.001` for `instant-ngp-bounded` so that it is automatically calculated based on the scene aabb (target on roughly 1000 samples).
 2023-04-28 13:44:34 -07:00
Ruilong Li(李瑞龙) f015245ca4 Fix typo in readme (#1833) 2023-04-27 22:53:19 -07:00
Matthew Tancik b753a0063c Auto update viewer version (#1825) 2023-04-27 12:07:44 -07:00
akanazawa 3f43e0d4c3 Update README.md (#1828) 2023-04-26 18:02:21 -07:00